diff --git a/.agents/notes/archived/architecture/2026-08-11-plugin-settings-tabs.i18n.yaml b/.agents/notes/archived/architecture/2026-08-11-plugin-settings-tabs.i18n.yaml new file mode 100644 index 0000000000..8b40d4a6bb --- /dev/null +++ b/.agents/notes/archived/architecture/2026-08-11-plugin-settings-tabs.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-08-11-plugin-settings-tabs.md: 1f1701e000b891b4fc00bc666f603ee00bae50a7 +2026-08-11-plugin-settings-tabs.zh.md: f76a4a9e2317eb6603b48e1a7e451abdc55e00ff diff --git a/.agents/notes/implemented/architecture/2026-08-11-plugin-settings-tabs.md b/.agents/notes/archived/architecture/2026-08-11-plugin-settings-tabs.md similarity index 99% rename from .agents/notes/implemented/architecture/2026-08-11-plugin-settings-tabs.md rename to .agents/notes/archived/architecture/2026-08-11-plugin-settings-tabs.md index 96e4c48926..1f1701e000 100644 --- a/.agents/notes/implemented/architecture/2026-08-11-plugin-settings-tabs.md +++ b/.agents/notes/archived/architecture/2026-08-11-plugin-settings-tabs.md @@ -1,6 +1,7 @@ # Agent Note: Feature-owned tabs in Plugins settings Status: implemented +Archived: 2026-08-22 English | [中文](2026-08-11-plugin-settings-tabs.zh.md) diff --git a/.agents/notes/implemented/architecture/2026-08-11-plugin-settings-tabs.zh.md b/.agents/notes/archived/architecture/2026-08-11-plugin-settings-tabs.zh.md similarity index 99% rename from .agents/notes/implemented/architecture/2026-08-11-plugin-settings-tabs.zh.md rename to .agents/notes/archived/architecture/2026-08-11-plugin-settings-tabs.zh.md index fa8f462640..f76a4a9e23 100644 --- a/.agents/notes/implemented/architecture/2026-08-11-plugin-settings-tabs.zh.md +++ b/.agents/notes/archived/architecture/2026-08-11-plugin-settings-tabs.zh.md @@ -1,6 +1,7 @@ # Agent Note: “插件”设置中的功能自有标签页 Status: implemented +Archived: 2026-08-22 [English](2026-08-11-plugin-settings-tabs.md) | 中文 diff --git a/.agents/notes/archived/bug-fix/2026-08-04-large-history-pagination-call-stack.i18n.yaml b/.agents/notes/archived/bug-fix/2026-08-04-large-history-pagination-call-stack.i18n.yaml new file mode 100644 index 0000000000..4567896a25 --- /dev/null +++ b/.agents/notes/archived/bug-fix/2026-08-04-large-history-pagination-call-stack.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-08-04-large-history-pagination-call-stack.md: 12e9bbf72c2eea2058bf83fe864e09b4a520d391 +2026-08-04-large-history-pagination-call-stack.zh.md: 288687b05ecdfc2858b4d67e1be199135ea20227 diff --git a/.agents/notes/implemented/bug-fix/2026-08-04-large-history-pagination-call-stack.md b/.agents/notes/archived/bug-fix/2026-08-04-large-history-pagination-call-stack.md similarity index 98% rename from .agents/notes/implemented/bug-fix/2026-08-04-large-history-pagination-call-stack.md rename to .agents/notes/archived/bug-fix/2026-08-04-large-history-pagination-call-stack.md index 28c2212112..12e9bbf72c 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-04-large-history-pagination-call-stack.md +++ b/.agents/notes/archived/bug-fix/2026-08-04-large-history-pagination-call-stack.md @@ -1,6 +1,7 @@ # Agent Note: Large history provenance is scanned without argument expansion Status: implemented +Archived: 2026-08-22 English | [中文](2026-08-04-large-history-pagination-call-stack.zh.md) diff --git a/.agents/notes/implemented/bug-fix/2026-08-04-large-history-pagination-call-stack.zh.md b/.agents/notes/archived/bug-fix/2026-08-04-large-history-pagination-call-stack.zh.md similarity index 98% rename from .agents/notes/implemented/bug-fix/2026-08-04-large-history-pagination-call-stack.zh.md rename to .agents/notes/archived/bug-fix/2026-08-04-large-history-pagination-call-stack.zh.md index 57dde9bdc0..288687b05e 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-04-large-history-pagination-call-stack.zh.md +++ b/.agents/notes/archived/bug-fix/2026-08-04-large-history-pagination-call-stack.zh.md @@ -1,6 +1,7 @@ # Agent Note: 大规模历史记录的溯源信息通过扫描处理，不做参数展开 Status: implemented +Archived: 2026-08-22 [English](2026-08-04-large-history-pagination-call-stack.md) | 中文 diff --git a/.agents/notes/archived/bug-fix/2026-08-06-plan-narrow-viewport-regression.i18n.yaml b/.agents/notes/archived/bug-fix/2026-08-06-plan-narrow-viewport-regression.i18n.yaml new file mode 100644 index 0000000000..a6305c1f5d --- /dev/null +++ b/.agents/notes/archived/bug-fix/2026-08-06-plan-narrow-viewport-regression.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-08-06-plan-narrow-viewport-regression.md: c42a110bf487ffab8f5975e65a8eb9bff4f1b0ae +2026-08-06-plan-narrow-viewport-regression.zh.md: 3df4f8aca57a1830d7f8062cefe76ac1afa9c2ce diff --git a/.agents/notes/implemented/bug-fix/2026-08-06-plan-narrow-viewport-regression.md b/.agents/notes/archived/bug-fix/2026-08-06-plan-narrow-viewport-regression.md similarity index 99% rename from .agents/notes/implemented/bug-fix/2026-08-06-plan-narrow-viewport-regression.md rename to .agents/notes/archived/bug-fix/2026-08-06-plan-narrow-viewport-regression.md index 945d014e0c..c42a110bf4 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-06-plan-narrow-viewport-regression.md +++ b/.agents/notes/archived/bug-fix/2026-08-06-plan-narrow-viewport-regression.md @@ -1,6 +1,7 @@ # Agent Note: narrow-viewport plan chip click-area regression test Status: implemented +Archived: 2026-08-22 English | [中文](2026-08-06-plan-narrow-viewport-regression.zh.md) diff --git a/.agents/notes/implemented/bug-fix/2026-08-06-plan-narrow-viewport-regression.zh.md b/.agents/notes/archived/bug-fix/2026-08-06-plan-narrow-viewport-regression.zh.md similarity index 99% rename from .agents/notes/implemented/bug-fix/2026-08-06-plan-narrow-viewport-regression.zh.md rename to .agents/notes/archived/bug-fix/2026-08-06-plan-narrow-viewport-regression.zh.md index 56b3056454..3df4f8aca5 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-06-plan-narrow-viewport-regression.zh.md +++ b/.agents/notes/archived/bug-fix/2026-08-06-plan-narrow-viewport-regression.zh.md @@ -1,6 +1,7 @@ # Agent Note: 窄视口下 Plan chip 点击区域回归测试 Status: implemented +Archived: 2026-08-22 [English](2026-08-06-plan-narrow-viewport-regression.md) | 中文 diff --git a/.agents/notes/archived/bug-fix/2026-08-11-preset-card-description-clamp.i18n.yaml b/.agents/notes/archived/bug-fix/2026-08-11-preset-card-description-clamp.i18n.yaml new file mode 100644 index 0000000000..644cd813ce --- /dev/null +++ b/.agents/notes/archived/bug-fix/2026-08-11-preset-card-description-clamp.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-08-11-preset-card-description-clamp.md: b9088b46184cde6f000fa39afbfe2d1145137b24 +2026-08-11-preset-card-description-clamp.zh.md: a7a3c4f26a55405715fe017ec3a7deb164432b0e diff --git a/.agents/notes/implemented/bug-fix/2026-08-11-preset-card-description-clamp.md b/.agents/notes/archived/bug-fix/2026-08-11-preset-card-description-clamp.md similarity index 99% rename from .agents/notes/implemented/bug-fix/2026-08-11-preset-card-description-clamp.md rename to .agents/notes/archived/bug-fix/2026-08-11-preset-card-description-clamp.md index 16ebf371d5..b9088b4618 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-11-preset-card-description-clamp.md +++ b/.agents/notes/archived/bug-fix/2026-08-11-preset-card-description-clamp.md @@ -1,6 +1,7 @@ # Agent Note: Preset cards clamp their description instead of sizing the roster Status: implemented +Archived: 2026-08-22 English | [中文](2026-08-11-preset-card-description-clamp.zh.md) diff --git a/.agents/notes/implemented/bug-fix/2026-08-11-preset-card-description-clamp.zh.md b/.agents/notes/archived/bug-fix/2026-08-11-preset-card-description-clamp.zh.md similarity index 99% rename from .agents/notes/implemented/bug-fix/2026-08-11-preset-card-description-clamp.zh.md rename to .agents/notes/archived/bug-fix/2026-08-11-preset-card-description-clamp.zh.md index 5b7a18f41e..a7a3c4f26a 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-11-preset-card-description-clamp.zh.md +++ b/.agents/notes/archived/bug-fix/2026-08-11-preset-card-description-clamp.zh.md @@ -1,6 +1,7 @@ # Agent Note: 预设卡片截断自身描述，而不是由描述决定整份名单的高度 Status: implemented +Archived: 2026-08-22 [English](2026-08-11-preset-card-description-clamp.md) | 中文 diff --git a/.agents/notes/archived/feature/2026-07-30-versioned-gui-welcome-onboarding.i18n.yaml b/.agents/notes/archived/feature/2026-07-30-versioned-gui-welcome-onboarding.i18n.yaml new file mode 100644 index 0000000000..87a43d82ca --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-30-versioned-gui-welcome-onboarding.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-30-versioned-gui-welcome-onboarding.md: 370793dd4e6d744ea61fc9319a94728dbbf3e1fe +2026-07-30-versioned-gui-welcome-onboarding.zh.md: 7b99377d00127174d5bfd8d080107c2cb67e6fff diff --git a/.agents/notes/implemented/feature/2026-07-30-versioned-gui-welcome-onboarding.md b/.agents/notes/archived/feature/2026-07-30-versioned-gui-welcome-onboarding.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-30-versioned-gui-welcome-onboarding.md rename to .agents/notes/archived/feature/2026-07-30-versioned-gui-welcome-onboarding.md index 9c8684c051..370793dd4e 100644 --- a/.agents/notes/implemented/feature/2026-07-30-versioned-gui-welcome-onboarding.md +++ b/.agents/notes/archived/feature/2026-07-30-versioned-gui-welcome-onboarding.md @@ -1,6 +1,7 @@ # Agent Note: Versioned GUI welcome onboarding Status: implemented +Archived: 2026-08-22 English | [中文](2026-07-30-versioned-gui-welcome-onboarding.zh.md) diff --git a/.agents/notes/implemented/feature/2026-07-30-versioned-gui-welcome-onboarding.zh.md b/.agents/notes/archived/feature/2026-07-30-versioned-gui-welcome-onboarding.zh.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-30-versioned-gui-welcome-onboarding.zh.md rename to .agents/notes/archived/feature/2026-07-30-versioned-gui-welcome-onboarding.zh.md index d4fe40a1af..7b99377d00 100644 --- a/.agents/notes/implemented/feature/2026-07-30-versioned-gui-welcome-onboarding.zh.md +++ b/.agents/notes/archived/feature/2026-07-30-versioned-gui-welcome-onboarding.zh.md @@ -1,6 +1,7 @@ # Agent Note: 版本化 GUI 欢迎引导 Status: implemented +Archived: 2026-08-22 [English](2026-07-30-versioned-gui-welcome-onboarding.md) | 中文 diff --git a/.agents/notes/archived/feature/2026-08-06-bundled-dsh-badge-skill.i18n.yaml b/.agents/notes/archived/feature/2026-08-06-bundled-dsh-badge-skill.i18n.yaml new file mode 100644 index 0000000000..4cb64e37c0 --- /dev/null +++ b/.agents/notes/archived/feature/2026-08-06-bundled-dsh-badge-skill.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-08-06-bundled-dsh-badge-skill.md: 2909736d53f8aff41ca69e705de44657bc1b4f1e +2026-08-06-bundled-dsh-badge-skill.zh.md: de85e9476d3945cd13335ef596243bc2a126ae55 diff --git a/.agents/notes/implemented/feature/2026-08-06-bundled-dsh-badge-skill.md b/.agents/notes/archived/feature/2026-08-06-bundled-dsh-badge-skill.md similarity index 98% rename from .agents/notes/implemented/feature/2026-08-06-bundled-dsh-badge-skill.md rename to .agents/notes/archived/feature/2026-08-06-bundled-dsh-badge-skill.md index 4c6fbdcb76..2909736d53 100644 --- a/.agents/notes/implemented/feature/2026-08-06-bundled-dsh-badge-skill.md +++ b/.agents/notes/archived/feature/2026-08-06-bundled-dsh-badge-skill.md @@ -1,6 +1,7 @@ # Agent Note: Bundled dsh badge skill Status: implemented +Archived: 2026-08-22 English | [中文](2026-08-06-bundled-dsh-badge-skill.zh.md) diff --git a/.agents/notes/implemented/feature/2026-08-06-bundled-dsh-badge-skill.zh.md b/.agents/notes/archived/feature/2026-08-06-bundled-dsh-badge-skill.zh.md similarity index 98% rename from .agents/notes/implemented/feature/2026-08-06-bundled-dsh-badge-skill.zh.md rename to .agents/notes/archived/feature/2026-08-06-bundled-dsh-badge-skill.zh.md index fe291d4986..de85e9476d 100644 --- a/.agents/notes/implemented/feature/2026-08-06-bundled-dsh-badge-skill.zh.md +++ b/.agents/notes/archived/feature/2026-08-06-bundled-dsh-badge-skill.zh.md @@ -1,6 +1,7 @@ # Agent Note: 内置 dsh 徽章 skill Status: implemented +Archived: 2026-08-22 [English](2026-08-06-bundled-dsh-badge-skill.md) | 中文 diff --git a/.agents/notes/archived/feature/2026-08-07-workspace-picker-composer-entry.i18n.yaml b/.agents/notes/archived/feature/2026-08-07-workspace-picker-composer-entry.i18n.yaml new file mode 100644 index 0000000000..7459c96dae --- /dev/null +++ b/.agents/notes/archived/feature/2026-08-07-workspace-picker-composer-entry.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-08-07-workspace-picker-composer-entry.md: 023cbe09dd75015a1555103642d1b66ce75aafc9 +2026-08-07-workspace-picker-composer-entry.zh.md: 6b84885b11fb5372a51d620b40ea7d24fe7e45a2 diff --git a/.agents/notes/implemented/feature/2026-08-07-workspace-picker-composer-entry.md b/.agents/notes/archived/feature/2026-08-07-workspace-picker-composer-entry.md similarity index 99% rename from .agents/notes/implemented/feature/2026-08-07-workspace-picker-composer-entry.md rename to .agents/notes/archived/feature/2026-08-07-workspace-picker-composer-entry.md index dc9c26c291..023cbe09dd 100644 --- a/.agents/notes/implemented/feature/2026-08-07-workspace-picker-composer-entry.md +++ b/.agents/notes/archived/feature/2026-08-07-workspace-picker-composer-entry.md @@ -1,6 +1,7 @@ # Agent Note: The no-Workspace composer opens the existing picker Status: implemented +Archived: 2026-08-22 English | [中文](2026-08-07-workspace-picker-composer-entry.zh.md) diff --git a/.agents/notes/implemented/feature/2026-08-07-workspace-picker-composer-entry.zh.md b/.agents/notes/archived/feature/2026-08-07-workspace-picker-composer-entry.zh.md similarity index 99% rename from .agents/notes/implemented/feature/2026-08-07-workspace-picker-composer-entry.zh.md rename to .agents/notes/archived/feature/2026-08-07-workspace-picker-composer-entry.zh.md index 9121750ae1..6b84885b11 100644 --- a/.agents/notes/implemented/feature/2026-08-07-workspace-picker-composer-entry.zh.md +++ b/.agents/notes/archived/feature/2026-08-07-workspace-picker-composer-entry.zh.md @@ -1,6 +1,7 @@ # Agent Note: 未选择 Workspace 时从编辑器打开现有选择器 Status: implemented +Archived: 2026-08-22 [English](2026-08-07-workspace-picker-composer-entry.md) | 中文 diff --git a/.agents/notes/archived/feature/2026-08-10-creator-guidance-introduce-cue.i18n.yaml b/.agents/notes/archived/feature/2026-08-10-creator-guidance-introduce-cue.i18n.yaml new file mode 100644 index 0000000000..27eba69e62 --- /dev/null +++ b/.agents/notes/archived/feature/2026-08-10-creator-guidance-introduce-cue.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-08-10-creator-guidance-introduce-cue.md: 2954bb9dca6bd5359ab3ed4b7e32bd8336709a10 +2026-08-10-creator-guidance-introduce-cue.zh.md: 4f818b3a444cbc7bbd4355ac8e7a883aaa4bfa51 diff --git a/.agents/notes/implemented/feature/2026-08-10-creator-guidance-introduce-cue.md b/.agents/notes/archived/feature/2026-08-10-creator-guidance-introduce-cue.md similarity index 99% rename from .agents/notes/implemented/feature/2026-08-10-creator-guidance-introduce-cue.md rename to .agents/notes/archived/feature/2026-08-10-creator-guidance-introduce-cue.md index 888fee7b3d..2954bb9dca 100644 --- a/.agents/notes/implemented/feature/2026-08-10-creator-guidance-introduce-cue.md +++ b/.agents/notes/archived/feature/2026-08-10-creator-guidance-introduce-cue.md @@ -1,6 +1,7 @@ # Agent Note: Creator guidance lands as an introduce cue on the preset chip Status: implemented +Archived: 2026-08-22 English | [中文](2026-08-10-creator-guidance-introduce-cue.zh.md) diff --git a/.agents/notes/implemented/feature/2026-08-10-creator-guidance-introduce-cue.zh.md b/.agents/notes/archived/feature/2026-08-10-creator-guidance-introduce-cue.zh.md similarity index 99% rename from .agents/notes/implemented/feature/2026-08-10-creator-guidance-introduce-cue.zh.md rename to .agents/notes/archived/feature/2026-08-10-creator-guidance-introduce-cue.zh.md index d80260abd1..4f818b3a44 100644 --- a/.agents/notes/implemented/feature/2026-08-10-creator-guidance-introduce-cue.zh.md +++ b/.agents/notes/archived/feature/2026-08-10-creator-guidance-introduce-cue.zh.md @@ -1,6 +1,7 @@ # Agent Note: 创造模式引导以介绍动效落在预设 chip 上 Status: implemented +Archived: 2026-08-22 [English](2026-08-10-creator-guidance-introduce-cue.md) | 中文 diff --git a/.agents/notes/archived/feature/2026-08-11-collapsible-ask-user-question-card.i18n.yaml b/.agents/notes/archived/feature/2026-08-11-collapsible-ask-user-question-card.i18n.yaml new file mode 100644 index 0000000000..6fc55e3a3e --- /dev/null +++ b/.agents/notes/archived/feature/2026-08-11-collapsible-ask-user-question-card.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-08-11-collapsible-ask-user-question-card.md: 08e87b0d1f05f47c5bc87ef9b32cab05ef229e5c +2026-08-11-collapsible-ask-user-question-card.zh.md: fd3b838ff174dcdb3d4994fe30b193d63f5c4d15 diff --git a/.agents/notes/implemented/feature/2026-08-11-collapsible-ask-user-question-card.md b/.agents/notes/archived/feature/2026-08-11-collapsible-ask-user-question-card.md similarity index 99% rename from .agents/notes/implemented/feature/2026-08-11-collapsible-ask-user-question-card.md rename to .agents/notes/archived/feature/2026-08-11-collapsible-ask-user-question-card.md index 5c7e62749e..08e87b0d1f 100644 --- a/.agents/notes/implemented/feature/2026-08-11-collapsible-ask-user-question-card.md +++ b/.agents/notes/archived/feature/2026-08-11-collapsible-ask-user-question-card.md @@ -1,6 +1,7 @@ # Agent Note: Collapsible Ask-User Question Card Status: implemented +Archived: 2026-08-22 English | [中文](2026-08-11-collapsible-ask-user-question-card.zh.md) diff --git a/.agents/notes/implemented/feature/2026-08-11-collapsible-ask-user-question-card.zh.md b/.agents/notes/archived/feature/2026-08-11-collapsible-ask-user-question-card.zh.md similarity index 99% rename from .agents/notes/implemented/feature/2026-08-11-collapsible-ask-user-question-card.zh.md rename to .agents/notes/archived/feature/2026-08-11-collapsible-ask-user-question-card.zh.md index 5f4b5851e4..fd3b838ff1 100644 --- a/.agents/notes/implemented/feature/2026-08-11-collapsible-ask-user-question-card.zh.md +++ b/.agents/notes/archived/feature/2026-08-11-collapsible-ask-user-question-card.zh.md @@ -1,6 +1,7 @@ # Agent Note: 可收起的提问卡片 Status: implemented +Archived: 2026-08-22 [English](2026-08-11-collapsible-ask-user-question-card.md) | 中文 diff --git a/.agents/notes/archived/feature/2026-08-11-web-export-command-and-dialog.i18n.yaml b/.agents/notes/archived/feature/2026-08-11-web-export-command-and-dialog.i18n.yaml new file mode 100644 index 0000000000..da756e7493 --- /dev/null +++ b/.agents/notes/archived/feature/2026-08-11-web-export-command-and-dialog.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-08-11-web-export-command-and-dialog.md: aba9048f26237ea01e861a5ee6e31b89429629c8 +2026-08-11-web-export-command-and-dialog.zh.md: be4a3a53b1ff75cfbe176e258fb6a73e5abfee22 diff --git a/.agents/notes/implemented/feature/2026-08-11-web-export-command-and-dialog.md b/.agents/notes/archived/feature/2026-08-11-web-export-command-and-dialog.md similarity index 99% rename from .agents/notes/implemented/feature/2026-08-11-web-export-command-and-dialog.md rename to .agents/notes/archived/feature/2026-08-11-web-export-command-and-dialog.md index d28925500a..aba9048f26 100644 --- a/.agents/notes/implemented/feature/2026-08-11-web-export-command-and-dialog.md +++ b/.agents/notes/archived/feature/2026-08-11-web-export-command-and-dialog.md @@ -1,6 +1,7 @@ # Agent Note: Web `/export` shares the streamed Session ZIP download Status: implemented +Archived: 2026-08-22 English | [中文](2026-08-11-web-export-command-and-dialog.zh.md) diff --git a/.agents/notes/implemented/feature/2026-08-11-web-export-command-and-dialog.zh.md b/.agents/notes/archived/feature/2026-08-11-web-export-command-and-dialog.zh.md similarity index 99% rename from .agents/notes/implemented/feature/2026-08-11-web-export-command-and-dialog.zh.md rename to .agents/notes/archived/feature/2026-08-11-web-export-command-and-dialog.zh.md index a9a9c4a5cc..be4a3a53b1 100644 --- a/.agents/notes/implemented/feature/2026-08-11-web-export-command-and-dialog.zh.md +++ b/.agents/notes/archived/feature/2026-08-11-web-export-command-and-dialog.zh.md @@ -1,6 +1,7 @@ # Agent Note: Web `/export` 共用流式 Session ZIP 下载 Status: implemented +Archived: 2026-08-22 [English](2026-08-11-web-export-command-and-dialog.md) | 中文 diff --git a/.agents/notes/archived/feature/2026-08-18-web-home-path-tilde.i18n.yaml b/.agents/notes/archived/feature/2026-08-18-web-home-path-tilde.i18n.yaml new file mode 100644 index 0000000000..d001e4a95c --- /dev/null +++ b/.agents/notes/archived/feature/2026-08-18-web-home-path-tilde.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-08-18-web-home-path-tilde.md: 108674740c804a42ec3b0491505186215a9d9fcd +2026-08-18-web-home-path-tilde.zh.md: 1f742158f62b9b7fbb8eae8be35c13adc95f3a09 diff --git a/.agents/notes/implemented/feature/2026-08-18-web-home-path-tilde.md b/.agents/notes/archived/feature/2026-08-18-web-home-path-tilde.md similarity index 99% rename from .agents/notes/implemented/feature/2026-08-18-web-home-path-tilde.md rename to .agents/notes/archived/feature/2026-08-18-web-home-path-tilde.md index b148833bab..108674740c 100644 --- a/.agents/notes/implemented/feature/2026-08-18-web-home-path-tilde.md +++ b/.agents/notes/archived/feature/2026-08-18-web-home-path-tilde.md @@ -1,6 +1,7 @@ # Agent Note: Web UI abbreviates POSIX home paths as `~` Status: implemented +Archived: 2026-08-22 English | [中文](2026-08-18-web-home-path-tilde.zh.md) diff --git a/.agents/notes/implemented/feature/2026-08-18-web-home-path-tilde.zh.md b/.agents/notes/archived/feature/2026-08-18-web-home-path-tilde.zh.md similarity index 99% rename from .agents/notes/implemented/feature/2026-08-18-web-home-path-tilde.zh.md rename to .agents/notes/archived/feature/2026-08-18-web-home-path-tilde.zh.md index 9d15cd6dca..1f742158f6 100644 --- a/.agents/notes/implemented/feature/2026-08-18-web-home-path-tilde.zh.md +++ b/.agents/notes/archived/feature/2026-08-18-web-home-path-tilde.zh.md @@ -1,6 +1,7 @@ # Agent Note: Web UI abbreviates POSIX home paths as `~` Status: implemented +Archived: 2026-08-22 [English](2026-08-18-web-home-path-tilde.md) | 中文 diff --git a/.agents/notes/archived/feature/2026-08-19-high-cache-hit-decimal-display.i18n.yaml b/.agents/notes/archived/feature/2026-08-19-high-cache-hit-decimal-display.i18n.yaml new file mode 100644 index 0000000000..fbbf621db9 --- /dev/null +++ b/.agents/notes/archived/feature/2026-08-19-high-cache-hit-decimal-display.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-08-19-high-cache-hit-decimal-display.md: 83c031bd1049ec26029d2e9ba0dc5cd623c3f867 +2026-08-19-high-cache-hit-decimal-display.zh.md: 62f27e39d37cf2445ac6796030092e892d82b581 diff --git a/.agents/notes/implemented/feature/2026-08-19-high-cache-hit-decimal-display.md b/.agents/notes/archived/feature/2026-08-19-high-cache-hit-decimal-display.md similarity index 99% rename from .agents/notes/implemented/feature/2026-08-19-high-cache-hit-decimal-display.md rename to .agents/notes/archived/feature/2026-08-19-high-cache-hit-decimal-display.md index 952d838fdf..83c031bd10 100644 --- a/.agents/notes/implemented/feature/2026-08-19-high-cache-hit-decimal-display.md +++ b/.agents/notes/archived/feature/2026-08-19-high-cache-hit-decimal-display.md @@ -1,6 +1,7 @@ # Agent Note: High cache-hit decimal display Status: implemented +Archived: 2026-08-22 English | [中文](2026-08-19-high-cache-hit-decimal-display.zh.md) diff --git a/.agents/notes/implemented/feature/2026-08-19-high-cache-hit-decimal-display.zh.md b/.agents/notes/archived/feature/2026-08-19-high-cache-hit-decimal-display.zh.md similarity index 99% rename from .agents/notes/implemented/feature/2026-08-19-high-cache-hit-decimal-display.zh.md rename to .agents/notes/archived/feature/2026-08-19-high-cache-hit-decimal-display.zh.md index ba33bd8a26..62f27e39d3 100644 --- a/.agents/notes/implemented/feature/2026-08-19-high-cache-hit-decimal-display.zh.md +++ b/.agents/notes/archived/feature/2026-08-19-high-cache-hit-decimal-display.zh.md @@ -1,6 +1,7 @@ # Agent Note: 高缓存命中率的小数显示 Status: implemented +Archived: 2026-08-22 [English](2026-08-19-high-cache-hit-decimal-display.md) | 中文 diff --git a/.agents/notes/archived/manifest.json b/.agents/notes/archived/manifest.json index 2c9391bc96..05fb2f3712 100644 --- a/.agents/notes/archived/manifest.json +++ b/.agents/notes/archived/manifest.json @@ -43,6 +43,9 @@ "architecture/2026-07-28-dsh-native-typescript-source-launch.i18n.yaml": "sha256:af071e07bce5d9bc8f3df65fed9dcd9b3779a98c5864badbd530363bda021b55", "architecture/2026-07-28-dsh-native-typescript-source-launch.md": "sha256:1b56e3454277ace713e2a01c4da538c756c45bf633fd24d7b16443d584afac5d", "architecture/2026-07-28-dsh-native-typescript-source-launch.zh.md": "sha256:8c0f97472c2c89d2c19ae5cfa68c6e67f32b50960b08b60b46496f78ea6ffad1", + "architecture/2026-08-11-plugin-settings-tabs.i18n.yaml": "sha256:0365da2b317fc5f94dd190064198565f4c624afc91d2e62161ab9170f79d11bc", + "architecture/2026-08-11-plugin-settings-tabs.md": "sha256:fdd92cfe55b6c4cd31b3f768dd46a2ecf129a04c9818249cbdd33857cf722bbf", + "architecture/2026-08-11-plugin-settings-tabs.zh.md": "sha256:8993df1a0178aba1ea35c460ee67c522900344a4b386287bba9dfac2bfb87efa", "bug-fix/2026-07-20-code-mode-result-card-completeness.i18n.yaml": "sha256:1035dae11d049d32ab09fd7d4f950eceae44bf46ba498b3cfaf3c75102b9fb64", "bug-fix/2026-07-20-code-mode-result-card-completeness.md": "sha256:6ca2c9d4df98be18813ef38b7462db880900b5bcd6944fbcd1b8f2258006b93e", "bug-fix/2026-07-20-code-mode-result-card-completeness.zh.md": "sha256:ed85fa7f935e5f525d566bc37a92014614983e649c75de9a9f244939097a7991", @@ -94,9 +97,18 @@ "bug-fix/2026-08-03-tui-long-session-render-costs.i18n.yaml": "sha256:f65f7bf8fc84c7a1f022ee393c8d969c06d9bde8bed3a0206de86fb35b246ac6", "bug-fix/2026-08-03-tui-long-session-render-costs.md": "sha256:6ecf2ef831f527f361ade18a882d79bc6eccf15cc676d05728e7753f41cde051", "bug-fix/2026-08-03-tui-long-session-render-costs.zh.md": "sha256:5f44e707b332e13fa06d625212173ea055c1c3c0aee60888435a0ff099ec6037", + "bug-fix/2026-08-04-large-history-pagination-call-stack.i18n.yaml": "sha256:9bb1ceec013521116ee73eb9ec28c5708ae9520d6e53dcd4a3621fd2283b215c", + "bug-fix/2026-08-04-large-history-pagination-call-stack.md": "sha256:38c5afd347b131abd6b73634d25210d593bcb1fd72c7ba501bad0b33fb639810", + "bug-fix/2026-08-04-large-history-pagination-call-stack.zh.md": "sha256:2a2790b3b3400c747e20b998edfa96788b4035ccfa5fd4100dbc9a0e694ed30e", + "bug-fix/2026-08-06-plan-narrow-viewport-regression.i18n.yaml": "sha256:fe0539da9ce4015c6deaf585350e586e99d86e0073a36e131b6f1f62cc13382b", + "bug-fix/2026-08-06-plan-narrow-viewport-regression.md": "sha256:ccecdf52213dd1f6ab9935db31906520b83a7d9166f612376877d612230d1331", + "bug-fix/2026-08-06-plan-narrow-viewport-regression.zh.md": "sha256:be10805f0cd5a4f0812c883ab7f3e1e9396b579be455696d5cd726434a26b3e1", "bug-fix/2026-08-10-web-favicon-dark-mode.i18n.yaml": "sha256:859c4399f9a017a68ba89552fdafa05e73c0599d94cee9551c84ea5b749a14f3", "bug-fix/2026-08-10-web-favicon-dark-mode.md": "sha256:4d17e247abd76ae3aed5fb4e075fd66a2838292f89f7021c82a79fe37ed905e6", "bug-fix/2026-08-10-web-favicon-dark-mode.zh.md": "sha256:7bbff8a3b7061c127afcc75cd2a8043b02a999b78c0180edd8f7e4807fcfe71d", + "bug-fix/2026-08-11-preset-card-description-clamp.i18n.yaml": "sha256:d50452503b59aa22c81617888f9391f31f12a779c4b18efb2b4b6de1bd9702a6", + "bug-fix/2026-08-11-preset-card-description-clamp.md": "sha256:7eb8db697f3ad3dea8c0a6045331c05730a010404a89e2b08348cb7b0fad26c8", + "bug-fix/2026-08-11-preset-card-description-clamp.zh.md": "sha256:6d2f7b55ce02275a45adfdd853805e7daf2d6534929b77beb86685a54fc34f85", "bug-fix/2026-08-12-collapsed-sidebar-shared-entry-motion.i18n.yaml": "sha256:3ce4f6e39e173fc304bf64deca9c95bcddc1dbb492e065ca8c267a7a40788588", "bug-fix/2026-08-12-collapsed-sidebar-shared-entry-motion.md": "sha256:7b169aa4543edfc965de5a8b7b9e60aa9d9d5218693cd0b57908e2d482280723", "bug-fix/2026-08-12-collapsed-sidebar-shared-entry-motion.zh.md": "sha256:88db36c698800bf55c3c7531d6f92665576d978c29c15ff7d74215fb93376cb1", @@ -241,6 +253,9 @@ "feature/2026-07-30-tui-details-command.i18n.yaml": "sha256:033cea6df0a16fc68cbdb435babdc6e75c1199a8e70e1a71d87c800c40f5a044", "feature/2026-07-30-tui-details-command.md": "sha256:a13478d4e55ec6d358209b51b541413ec75d0e20dfc22196ace28020f03f0c2d", "feature/2026-07-30-tui-details-command.zh.md": "sha256:de9c449b98468cef34ce4f9a9d2a854a5d8905eecd61f80e27a9a0e4495e9901", + "feature/2026-07-30-versioned-gui-welcome-onboarding.i18n.yaml": "sha256:3d453f1a8f1a642ed569d1900009b785e582614bcabf9fede566ecbd9842e3ef", + "feature/2026-07-30-versioned-gui-welcome-onboarding.md": "sha256:cfaa38cfec722ac3792a4770f7733372805a6c0571f4f08519f367976b0d2379", + "feature/2026-07-30-versioned-gui-welcome-onboarding.zh.md": "sha256:0ce0e4616580c583725aa3d28063dc009889d7f0a260a3cdda53ff48721c1ae4", "feature/2026-07-30-versioned-tui-first-run-welcome.i18n.yaml": "sha256:4c3fc380b0512ad7c00baacd0ac610e1a78ae45374311d9bd43bab6b5e29e630", "feature/2026-07-30-versioned-tui-first-run-welcome.md": "sha256:296f153e6c839f3743078e4f5aab3b2befc211c934835238668c57bdeae52231", "feature/2026-07-30-versioned-tui-first-run-welcome.zh.md": "sha256:82871a9cca1fec46bb08a5b39daad28a44bb2419dea367b4ae41af3cf07bfa65", @@ -259,9 +274,30 @@ "feature/2026-07-31-web-cards-toolrow.i18n.yaml": "sha256:f9a6ab72a77934cdcc02167c7313f08d7e9925362017b34bed7ad56c8c70fbaa", "feature/2026-07-31-web-cards-toolrow.md": "sha256:5058f7cec4497d1cb0a5c8e77b88fddacac6eead034f3edec88e8514919b8a3e", "feature/2026-07-31-web-cards-toolrow.zh.md": "sha256:ba84ef2e1be61211ab5ba6950b78ede3d3a979f252bc068d3e04e2c025f7bc03", + "feature/2026-08-06-bundled-dsh-badge-skill.i18n.yaml": "sha256:4b568d89976a71b7b3864e13b36925bf055479213739ffd4ac81614e00e93e36", + "feature/2026-08-06-bundled-dsh-badge-skill.md": "sha256:7b67f7c09b7e2b2ca756983a8951dad3a15786b8cd3adc6e819f316c67d31b2c", + "feature/2026-08-06-bundled-dsh-badge-skill.zh.md": "sha256:dcc0acb2dca596196ac034a8e86a644131c5b7fb09b184ec9d8493f93019d2b1", + "feature/2026-08-07-workspace-picker-composer-entry.i18n.yaml": "sha256:24a8bb2956371c7c840a662ac16dffbe04a6bb40a7296d01db86cb85da58d238", + "feature/2026-08-07-workspace-picker-composer-entry.md": "sha256:036212fbae6f5d7194e8c7fc9b1e7cd1c35251e9c227e895834a7d00bd5f69f8", + "feature/2026-08-07-workspace-picker-composer-entry.zh.md": "sha256:fb65c3330e8324f90d1270345e1ac941fc800e8caaf3b4bbee1bbb743f713262", "feature/2026-08-08-dsh-run-headless-command.i18n.yaml": "sha256:1c2b4c5b61b9263b6267275d6fc69faeaad3cc887f0728a7ed4172d817af812b", "feature/2026-08-08-dsh-run-headless-command.md": "sha256:7695fe7fd322377d5986f14e35f13337f4cd376405c758218a81230f6d182d1c", "feature/2026-08-08-dsh-run-headless-command.zh.md": "sha256:113c14a36c64d2facc8ae46f37c7aa76359d8cacb9c18fcba26a723f15d036fb", + "feature/2026-08-10-creator-guidance-introduce-cue.i18n.yaml": "sha256:74f519839f0cf82c7304bdeae41ae1cab8bb930bfb94f79ab44708acd3b72128", + "feature/2026-08-10-creator-guidance-introduce-cue.md": "sha256:3e25409dda498de150de18943ee332e1760963e377a40a365902b66f667fdc9f", + "feature/2026-08-10-creator-guidance-introduce-cue.zh.md": "sha256:203847010cab9e9d13c3969f17921d3a5aa0d69377eccfef555c7ff96572f162", + "feature/2026-08-11-collapsible-ask-user-question-card.i18n.yaml": "sha256:9c0873bbb1437bcd5025f5859e1dc447a6b936f19c2c2ad2250521a3aa773a12", + "feature/2026-08-11-collapsible-ask-user-question-card.md": "sha256:4f3b3f5d7020fefbbac8a3c36a97642721ef14a0476a7d8117bde8a128d25f42", + "feature/2026-08-11-collapsible-ask-user-question-card.zh.md": "sha256:e7186c92f77d337a875f981ae39b16331a1c5466a948415bcacfe108ad98fb63", + "feature/2026-08-11-web-export-command-and-dialog.i18n.yaml": "sha256:db7d523a2a1f82a86f532661bd2953ee8538d971d91f886e4bd4e0d88f7226b2", + "feature/2026-08-11-web-export-command-and-dialog.md": "sha256:ec44b47589ca7924018dc24f7fa73379a97b8f053d9e8ccce2aebb600230e47b", + "feature/2026-08-11-web-export-command-and-dialog.zh.md": "sha256:ad28e67d397c87300cfe1705ba3d206cc4d054e07f5647c095c718ac8cf4ec98", + "feature/2026-08-18-web-home-path-tilde.i18n.yaml": "sha256:f151e3e3514f59784fc646c2feb3075dc954c65110d48c2cc482ad486fc0b86f", + "feature/2026-08-18-web-home-path-tilde.md": "sha256:8c7ecf120ff8c81826160acab5fc906a2a0a14213bcd2958343cfea47328d68e", + "feature/2026-08-18-web-home-path-tilde.zh.md": "sha256:3486c5b42aed5bcadf12c62c5e1e6cf7c1b493fc1085ad7d154cdf2ec34076cc", + "feature/2026-08-19-high-cache-hit-decimal-display.i18n.yaml": "sha256:c2cb839ed676040ed62153c2aab65b677fa59739f69253af50246e79a2347620", + "feature/2026-08-19-high-cache-hit-decimal-display.md": "sha256:08cb68bfc379da47a05b816afac26126146d36d6248350d4380f7cb98607d573", + "feature/2026-08-19-high-cache-hit-decimal-display.zh.md": "sha256:9d7afe3e2fc3029fbccc643b432a01bcb3b5671750adb6945ac414ec843ca063", "process/2026-06-11-doc-sync-enforcement.i18n.yaml": "sha256:33b6d5874427bd7a2bd82e7e2f4f482b12448b2464aef15a9c57975edb48554d", "process/2026-06-11-doc-sync-enforcement.md": "sha256:aa2fe83d519fc30d48dff19e596e83c8922aacc9e063e14fe2cc35b769b9100e", "process/2026-06-11-doc-sync-enforcement.zh.md": "sha256:698017bd35f030fdea3eac51df9e43138c48140f504739d687b7251d13fced2b", @@ -322,6 +358,9 @@ "process/2026-08-08-review-driven-issue-lifecycle-triggers.i18n.yaml": "sha256:4c28c59d3fc323e7cd01eff31f1fe759834719c5bede1e82b39f868970bf856d", "process/2026-08-08-review-driven-issue-lifecycle-triggers.md": "sha256:1b0514de5d030170e91e12e4d6ba788a9247f840e82700faa385a1c0c76ab857", "process/2026-08-08-review-driven-issue-lifecycle-triggers.zh.md": "sha256:028d78d61f603d8bac64c4cce20b393a78f8e029d3bb4976e79a47ecaefa6032", + "process/2026-08-12-documentation-site-navigation-and-chrome.i18n.yaml": "sha256:dde0041399b253e3758045f0858488db8178ffc563ce889c8b396c87af6c3730", + "process/2026-08-12-documentation-site-navigation-and-chrome.md": "sha256:56cb836ed862378afd33eb5c1a9dc159958b35a0aed3bf4336fcf26ab0b84b8b", + "process/2026-08-12-documentation-site-navigation-and-chrome.zh.md": "sha256:f2dd4adde38a09fe312866a1e6dad0f465684d809287862f40f1a488acd4fe18", "simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.i18n.yaml": "sha256:ad3d1263cb0051b885173bf064de62065e2c646ccaae2d7250723da3b4eab90c", "simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.md": "sha256:8fb061d51c8c23b47d2367814bab3623c6d5b972f38d207a273caa9030b579bd", "simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.zh.md": "sha256:2ffeaca91f82844a5616d6dcce6b4af514bb8a7c46f78e47f668b204ac6edc04", @@ -406,6 +445,18 @@ "simplification/2026-08-03-explicit-config-dsh-entrypoint.i18n.yaml": "sha256:5466161f3fb8f2e8117fe8ff242675cc9fe9ef264d1e29b9bc586891c73c051a", "simplification/2026-08-03-explicit-config-dsh-entrypoint.md": "sha256:f23accae7d05c2e75cb73ec69b492307f1ce7526ecfa9f6b12a621e02fd1a0c3", "simplification/2026-08-03-explicit-config-dsh-entrypoint.zh.md": "sha256:a32d2c6ecf748a16a2c35b59cd2da2fda75769e3ab24be6a2e026d8655466db4", + "simplification/2026-08-11-cmdline-program-action.i18n.yaml": "sha256:e33b6dee66e23beabf03275e4e4f15134d23a82740ae7be6afd28c11c3163fca", + "simplification/2026-08-11-cmdline-program-action.md": "sha256:e6a274bd92a35c98ea24704161b408507876de3162c0f640b4bc70a86ab4d86f", + "simplification/2026-08-11-cmdline-program-action.zh.md": "sha256:bd213ad65ea6129c5360f28b2f52e6f3e224a58d07f56da190702939e7b402ee", + "simplification/2026-08-11-quickstart-documentation-home.i18n.yaml": "sha256:548c0ff16d40fed3b3318b0b9a26e11d53a60582ff457098a212fc64e7d67eac", + "simplification/2026-08-11-quickstart-documentation-home.md": "sha256:21946a828417aca4a214a874a35e88fe5a3e5989c330421f3849937b35bb9a9b", + "simplification/2026-08-11-quickstart-documentation-home.zh.md": "sha256:cb292a428d427cf36aff0a184347f0ab653331edb874daf3c5b58a0d1f8e6964", + "simplification/2026-08-13-remove-first-run-beta-notice.i18n.yaml": "sha256:51267b74e39544991bfe606e3f749a26914162e454cf357f26223a6ed8de5fad", + "simplification/2026-08-13-remove-first-run-beta-notice.md": "sha256:7ef5c712b8dff1152becee6a3f800acd5f7589d7b000f01544f57b175660bcc1", + "simplification/2026-08-13-remove-first-run-beta-notice.zh.md": "sha256:f899c79f838b97d1eea4a118de2cf00a97bae910d86d4aabdc447b4e02fb585f", + "simplification/2026-08-19-knip-config-cleanup.i18n.yaml": "sha256:ca8f5726aed57ce376c3fbd8b70113e235f3ba37dbf290683157fb4bf143ab13", + "simplification/2026-08-19-knip-config-cleanup.md": "sha256:18c61713b3358d3019dac096afc26ce8e5189002f626b25e858dfc5e6f626c8d", + "simplification/2026-08-19-knip-config-cleanup.zh.md": "sha256:b8ff16089c1a331603bb80278544c637cb16c1fa3bcfca3c5e1187152a1a0947", "testing/2026-06-20-remove-redundant-snapshot-log-expected-output.i18n.yaml": "sha256:4177012c0821a8c22499852ecdf096af56d7263cb91c5d9d1bcd552cc26a3e00", "testing/2026-06-20-remove-redundant-snapshot-log-expected-output.md": "sha256:45234e7cc04b6010c6141f8d5924c04547300098f96262d423c50108e7c7011a", "testing/2026-06-20-remove-redundant-snapshot-log-expected-output.zh.md": "sha256:15e5a4ad3dee0bb711480cabe45cd97ec37bbdba19c2c2b47d1e9c203b07a48b", diff --git a/.agents/notes/archived/process/2026-08-12-documentation-site-navigation-and-chrome.i18n.yaml b/.agents/notes/archived/process/2026-08-12-documentation-site-navigation-and-chrome.i18n.yaml new file mode 100644 index 0000000000..439c0c1d47 --- /dev/null +++ b/.agents/notes/archived/process/2026-08-12-documentation-site-navigation-and-chrome.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-08-12-documentation-site-navigation-and-chrome.md: f33f017d54bcbb3583f37be27dcd6c69952bc66a +2026-08-12-documentation-site-navigation-and-chrome.zh.md: 7f3ff5c829c561167d8e2475cd1c2adf050975be diff --git a/.agents/notes/implemented/process/2026-08-12-documentation-site-navigation-and-chrome.md b/.agents/notes/archived/process/2026-08-12-documentation-site-navigation-and-chrome.md similarity index 99% rename from .agents/notes/implemented/process/2026-08-12-documentation-site-navigation-and-chrome.md rename to .agents/notes/archived/process/2026-08-12-documentation-site-navigation-and-chrome.md index 03cd44b94f..f33f017d54 100644 --- a/.agents/notes/implemented/process/2026-08-12-documentation-site-navigation-and-chrome.md +++ b/.agents/notes/archived/process/2026-08-12-documentation-site-navigation-and-chrome.md @@ -1,6 +1,7 @@ # Agent Note: Documentation-site navigation and repository chrome Status: implemented +Archived: 2026-08-22 English | [中文](2026-08-12-documentation-site-navigation-and-chrome.zh.md) diff --git a/.agents/notes/implemented/process/2026-08-12-documentation-site-navigation-and-chrome.zh.md b/.agents/notes/archived/process/2026-08-12-documentation-site-navigation-and-chrome.zh.md similarity index 99% rename from .agents/notes/implemented/process/2026-08-12-documentation-site-navigation-and-chrome.zh.md rename to .agents/notes/archived/process/2026-08-12-documentation-site-navigation-and-chrome.zh.md index d0972f909e..7f3ff5c829 100644 --- a/.agents/notes/implemented/process/2026-08-12-documentation-site-navigation-and-chrome.zh.md +++ b/.agents/notes/archived/process/2026-08-12-documentation-site-navigation-and-chrome.zh.md @@ -1,6 +1,7 @@ # Agent Note: 文档站导航与仓库 chrome Status: implemented +Archived: 2026-08-22 [English](2026-08-12-documentation-site-navigation-and-chrome.md) | 中文 diff --git a/.agents/notes/archived/simplification/2026-08-11-cmdline-program-action.i18n.yaml b/.agents/notes/archived/simplification/2026-08-11-cmdline-program-action.i18n.yaml new file mode 100644 index 0000000000..69735dfe18 --- /dev/null +++ b/.agents/notes/archived/simplification/2026-08-11-cmdline-program-action.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-08-11-cmdline-program-action.md: 96cbe2342eef90e68dece3c78b12a2de1bbea7c0 +2026-08-11-cmdline-program-action.zh.md: f5a9fea1447c78c9f099d3b54acd5b90a21aa503 diff --git a/.agents/notes/implemented/simplification/2026-08-11-cmdline-program-action.md b/.agents/notes/archived/simplification/2026-08-11-cmdline-program-action.md similarity index 99% rename from .agents/notes/implemented/simplification/2026-08-11-cmdline-program-action.md rename to .agents/notes/archived/simplification/2026-08-11-cmdline-program-action.md index 40c4dae1d3..96cbe2342e 100644 --- a/.agents/notes/implemented/simplification/2026-08-11-cmdline-program-action.md +++ b/.agents/notes/archived/simplification/2026-08-11-cmdline-program-action.md @@ -1,6 +1,7 @@ # Agent Note: parseCmdline runs the program's own commander action Status: implemented +Archived: 2026-08-22 English | [中文](2026-08-11-cmdline-program-action.zh.md) diff --git a/.agents/notes/implemented/simplification/2026-08-11-cmdline-program-action.zh.md b/.agents/notes/archived/simplification/2026-08-11-cmdline-program-action.zh.md similarity index 99% rename from .agents/notes/implemented/simplification/2026-08-11-cmdline-program-action.zh.md rename to .agents/notes/archived/simplification/2026-08-11-cmdline-program-action.zh.md index 1eb9746162..f5a9fea144 100644 --- a/.agents/notes/implemented/simplification/2026-08-11-cmdline-program-action.zh.md +++ b/.agents/notes/archived/simplification/2026-08-11-cmdline-program-action.zh.md @@ -1,6 +1,7 @@ # Agent Note: parseCmdline 运行 program 自己的 commander action Status: implemented +Archived: 2026-08-22 [English](2026-08-11-cmdline-program-action.md) | 中文 diff --git a/.agents/notes/archived/simplification/2026-08-11-quickstart-documentation-home.i18n.yaml b/.agents/notes/archived/simplification/2026-08-11-quickstart-documentation-home.i18n.yaml new file mode 100644 index 0000000000..9ad4e8aacb --- /dev/null +++ b/.agents/notes/archived/simplification/2026-08-11-quickstart-documentation-home.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-08-11-quickstart-documentation-home.md: 653c702eba4c90e52ee0539959d926ae23a98e6c +2026-08-11-quickstart-documentation-home.zh.md: 3d21566f9e4a822d095a115a5e65bfbaa3f947df diff --git a/.agents/notes/implemented/simplification/2026-08-11-quickstart-documentation-home.md b/.agents/notes/archived/simplification/2026-08-11-quickstart-documentation-home.md similarity index 99% rename from .agents/notes/implemented/simplification/2026-08-11-quickstart-documentation-home.md rename to .agents/notes/archived/simplification/2026-08-11-quickstart-documentation-home.md index 3fd98843fc..653c702eba 100644 --- a/.agents/notes/implemented/simplification/2026-08-11-quickstart-documentation-home.md +++ b/.agents/notes/archived/simplification/2026-08-11-quickstart-documentation-home.md @@ -1,6 +1,7 @@ # Agent Note: Route documentation roots to quick start Status: implemented +Archived: 2026-08-22 English | [中文](2026-08-11-quickstart-documentation-home.zh.md) diff --git a/.agents/notes/implemented/simplification/2026-08-11-quickstart-documentation-home.zh.md b/.agents/notes/archived/simplification/2026-08-11-quickstart-documentation-home.zh.md similarity index 99% rename from .agents/notes/implemented/simplification/2026-08-11-quickstart-documentation-home.zh.md rename to .agents/notes/archived/simplification/2026-08-11-quickstart-documentation-home.zh.md index 63871b01c4..3d21566f9e 100644 --- a/.agents/notes/implemented/simplification/2026-08-11-quickstart-documentation-home.zh.md +++ b/.agents/notes/archived/simplification/2026-08-11-quickstart-documentation-home.zh.md @@ -1,6 +1,7 @@ # Agent Note: 将文档根路由指向快速开始 Status: implemented +Archived: 2026-08-22 [English](2026-08-11-quickstart-documentation-home.md) | 中文 diff --git a/.agents/notes/archived/simplification/2026-08-13-remove-first-run-beta-notice.i18n.yaml b/.agents/notes/archived/simplification/2026-08-13-remove-first-run-beta-notice.i18n.yaml new file mode 100644 index 0000000000..abe87647e3 --- /dev/null +++ b/.agents/notes/archived/simplification/2026-08-13-remove-first-run-beta-notice.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-08-13-remove-first-run-beta-notice.md: 535d0a20a5805c137551e6047f40fc5cf53153b8 +2026-08-13-remove-first-run-beta-notice.zh.md: 20626bbd9d0bd13c00d4ee66f5dbc267c2e92082 diff --git a/.agents/notes/implemented/simplification/2026-08-13-remove-first-run-beta-notice.md b/.agents/notes/archived/simplification/2026-08-13-remove-first-run-beta-notice.md similarity index 99% rename from .agents/notes/implemented/simplification/2026-08-13-remove-first-run-beta-notice.md rename to .agents/notes/archived/simplification/2026-08-13-remove-first-run-beta-notice.md index 21396eb9cc..535d0a20a5 100644 --- a/.agents/notes/implemented/simplification/2026-08-13-remove-first-run-beta-notice.md +++ b/.agents/notes/archived/simplification/2026-08-13-remove-first-run-beta-notice.md @@ -1,6 +1,7 @@ # Agent Note: Remove the first-run beta notice Status: implemented +Archived: 2026-08-22 English | [中文](2026-08-13-remove-first-run-beta-notice.zh.md) diff --git a/.agents/notes/implemented/simplification/2026-08-13-remove-first-run-beta-notice.zh.md b/.agents/notes/archived/simplification/2026-08-13-remove-first-run-beta-notice.zh.md similarity index 99% rename from .agents/notes/implemented/simplification/2026-08-13-remove-first-run-beta-notice.zh.md rename to .agents/notes/archived/simplification/2026-08-13-remove-first-run-beta-notice.zh.md index c7c31b163d..20626bbd9d 100644 --- a/.agents/notes/implemented/simplification/2026-08-13-remove-first-run-beta-notice.zh.md +++ b/.agents/notes/archived/simplification/2026-08-13-remove-first-run-beta-notice.zh.md @@ -1,6 +1,7 @@ # Agent Note: 移除首次启动内测声明 Status: implemented +Archived: 2026-08-22 [English](2026-08-13-remove-first-run-beta-notice.md) | 中文 diff --git a/.agents/notes/archived/simplification/2026-08-19-knip-config-cleanup.i18n.yaml b/.agents/notes/archived/simplification/2026-08-19-knip-config-cleanup.i18n.yaml new file mode 100644 index 0000000000..6612299cc4 --- /dev/null +++ b/.agents/notes/archived/simplification/2026-08-19-knip-config-cleanup.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-08-19-knip-config-cleanup.md: 56426aeb7ff53caf7828b3f252269559e596940d +2026-08-19-knip-config-cleanup.zh.md: a74fa831f2301d9b95d5e34b003585293501c874 diff --git a/.agents/notes/implemented/simplification/2026-08-19-knip-config-cleanup.md b/.agents/notes/archived/simplification/2026-08-19-knip-config-cleanup.md similarity index 99% rename from .agents/notes/implemented/simplification/2026-08-19-knip-config-cleanup.md rename to .agents/notes/archived/simplification/2026-08-19-knip-config-cleanup.md index 629e64be79..56426aeb7f 100644 --- a/.agents/notes/implemented/simplification/2026-08-19-knip-config-cleanup.md +++ b/.agents/notes/archived/simplification/2026-08-19-knip-config-cleanup.md @@ -1,6 +1,7 @@ # Agent Note: Deleted stale and duplicative knip.json workspace entries Status: implemented +Archived: 2026-08-22 English | [中文](2026-08-19-knip-config-cleanup.zh.md) diff --git a/.agents/notes/implemented/simplification/2026-08-19-knip-config-cleanup.zh.md b/.agents/notes/archived/simplification/2026-08-19-knip-config-cleanup.zh.md similarity index 99% rename from .agents/notes/implemented/simplification/2026-08-19-knip-config-cleanup.zh.md rename to .agents/notes/archived/simplification/2026-08-19-knip-config-cleanup.zh.md index e7a1ec9121..a74fa831f2 100644 --- a/.agents/notes/implemented/simplification/2026-08-19-knip-config-cleanup.zh.md +++ b/.agents/notes/archived/simplification/2026-08-19-knip-config-cleanup.zh.md @@ -1,6 +1,7 @@ # Agent Note: 删除 knip.json 中失效与重复的 workspace 条目 Status: implemented +Archived: 2026-08-22 [English](2026-08-19-knip-config-cleanup.md) | 中文 diff --git a/.agents/notes/implemented/architecture/2026-06-13-capability-seams.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-13-capability-seams.i18n.yaml index b7a0ea7192..1c4eadabc1 100644 --- a/.agents/notes/implemented/architecture/2026-06-13-capability-seams.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-13-capability-seams.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-13-capability-seams.md -2026-06-13-capability-seams.md: 2a166278ea454895177fa12b58f5493276f19cd1 -2026-06-13-capability-seams.zh.md: 28b45cbbc7f65a0b783db3d91a2e559132b5779f +2026-06-13-capability-seams.md: 46a2c39e927e859c7eb95956d8586f3bf04c7b1c +2026-06-13-capability-seams.zh.md: f44e3e68d2153149435b0fd0aaa5fd121cf3ecad diff --git a/.agents/notes/implemented/architecture/2026-06-13-capability-seams.md b/.agents/notes/implemented/architecture/2026-06-13-capability-seams.md index 2a166278ea..46a2c39e92 100644 --- a/.agents/notes/implemented/architecture/2026-06-13-capability-seams.md +++ b/.agents/notes/implemented/architecture/2026-06-13-capability-seams.md @@ -6,7 +6,7 @@ English | [中文](2026-06-13-capability-seams.zh.md) ## Problem -The harness has swappable capabilities — bash execution today, sandboxed/remote executors and alternative model providers tomorrow. A capability has three concerns that change at different rates and for different reasons: the *contract* (what the capability is), the *implementation* (how it runs), and the *consumer API* (what the model and other plugins program against). Bundling them in one package couples those rates of change — swapping a local executor for a sandboxed one would churn the tool schemas the model sees, even though the model-facing contract never changed. +The harness has swappable capabilities, including shell execution and model providers. A capability has three concerns that change at different rates and for different reasons: the *contract* (what the capability is), the *implementation* (how it runs), and the *consumer API* (what the model and other plugins program against). Bundling them in one package couples those rates of change — swapping a local executor for a sandboxed one would churn the tool schemas the model sees, even though the model-facing contract never changed. This is distinct from "who provides vs. needs a capability at runtime", which Cordis already answers with services + `inject` (a provider registers `ctx.shell`; a consumer declares `inject: ['bash']` and its fiber pends until the service exists). That mechanism is necessary but doesn't dictate package boundaries; this Agent Note does. diff --git a/.agents/notes/implemented/architecture/2026-06-13-capability-seams.zh.md b/.agents/notes/implemented/architecture/2026-06-13-capability-seams.zh.md index 28b45cbbc7..f44e3e68d2 100644 --- a/.agents/notes/implemented/architecture/2026-06-13-capability-seams.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-13-capability-seams.zh.md @@ -6,7 +6,7 @@ Status: implemented ## 问题 -harness 具有可替换的能力：当前是 bash 执行，未来会有沙箱化／远程执行器和替代模型提供方。一项能力涉及三个关注点，它们以不同速率、因不同原因变化：*约定*（这项能力是什么）、*实现*（它如何运行）、*消费方 API*（模型和其他插件面向什么编程）。将三者捆绑在一个包中会耦合这些变化速率——把本地执行器换成沙箱化执行器时，模型看到的工具 schema 也会被搅动，尽管面向模型的约定从未改变。 +harness 具有可替换的能力，包括 shell 执行和模型提供方。一项能力涉及三个关注点，它们以不同速率、因不同原因变化：*约定*（这项能力是什么）、*实现*（它如何运行）、*消费方 API*（模型和其他插件面向什么编程）。将三者捆绑在一个包中会耦合这些变化速率——把本地执行器换成沙箱化执行器时，模型看到的工具 schema 也会被搅动，尽管面向模型的约定从未改变。 这与「谁在运行时提供、谁需要一项能力」是不同的问题，后者 Cordis 已通过服务 + `inject` 解决（提供方注册 `ctx.shell`；消费方声明 `inject: ['bash']`，其 fiber 挂起直到服务存在）。该机制是必要的，但不决定包的边界；本 Agent Note 决定的是包的边界。 diff --git a/.agents/notes/implemented/architecture/2026-06-20-branded-ids.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-20-branded-ids.i18n.yaml index 8cad585a9b..971be89d2f 100644 --- a/.agents/notes/implemented/architecture/2026-06-20-branded-ids.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-20-branded-ids.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-20-branded-ids.md -2026-06-20-branded-ids.md: 68558071c47fb2b74e559b6b9936366911eb6548 -2026-06-20-branded-ids.zh.md: 5ea2547b8ab45534188a6a4a9e61f3458358beb3 +2026-06-20-branded-ids.md: b282993be1cfbb1ee67057ab8ba7bd2cbbfd1eac +2026-06-20-branded-ids.zh.md: 862c7eb72b08f4cf0be8ff9cd9bc757e5b36c32a diff --git a/.agents/notes/implemented/architecture/2026-06-20-branded-ids.md b/.agents/notes/implemented/architecture/2026-06-20-branded-ids.md index 68558071c4..b282993be1 100644 --- a/.agents/notes/implemented/architecture/2026-06-20-branded-ids.md +++ b/.agents/notes/implemented/architecture/2026-06-20-branded-ids.md @@ -56,7 +56,7 @@ Kept deliberately narrow per the "not every string needs a brand" policy. Each o - **`ToolName`** (the `ToolRuntime` key) — author-defined, human-readable, and rarely confused with another id; the weakest candidate, likely not worth a brand. - **`ErrorCode`** (`HarnessError.code`) — a closed vocabulary (`ABORTED`, `NO_ADAPTER`, …), not a per-instance id; better served by a string-literal union than a brand, if anything. - **Numeric ordinals** — turn number, step number, and the event `seq` are `number`, not `string`, so `Branded` does not apply; a parallel `number & { readonly [BRAND]: B }` variant could brand them, but they are positional ordinals rarely passed across boundaries, so the payoff is low. -- **Validated construction** — the brand factories are pure casts with no runtime check, and every boundary (ACP `sessionId`, provider-issued `call.id`, the empty-string fallback in `dsh-llm-deepseek`) trusts the raw string today. A `SessionId.parse()` / `isValid()` companion that throws on malformed input at boundaries is a genuine gap, but it is a *runtime-behavior* change with its own design (what is "malformed"? what happens on failure?) and belongs in its own decision, not bundled into this type-only change. +- **Validated construction** — the brand factories are pure casts with no runtime check, and every boundary (ACP `sessionId`, provider-issued `call.id`, the empty-string fallback in `dsh-llm-deepseek`) trusts the raw string. A `SessionId.parse()` / `isValid()` companion that throws on malformed input at boundaries is a genuine gap, but it is a *runtime-behavior* change with its own design (what is "malformed"? what happens on failure?) and belongs in its own decision, not bundled into this type-only change. ## Verification diff --git a/.agents/notes/implemented/architecture/2026-06-20-branded-ids.zh.md b/.agents/notes/implemented/architecture/2026-06-20-branded-ids.zh.md index 5ea2547b8a..862c7eb72b 100644 --- a/.agents/notes/implemented/architecture/2026-06-20-branded-ids.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-20-branded-ids.zh.md @@ -56,7 +56,7 @@ export function OwnerToken(id: string): OwnerToken { - **`ToolName`**（`ToolRuntime` 的键）：由作者定义、人类可读，且很少与其他 id 混淆；最弱的候选，可能不值得加 brand。 - **`ErrorCode`**（`HarnessError.code`）：一个封闭词汇（`ABORTED`、`NO_ADAPTER`……），不是逐实例的 id；如果要做，string 字面量联合类型比 brand 更合适。 - **数值序号**：轮次号、步骤号和事件 `seq` 是 `number` 而非 `string`，`Branded` 不适用；可以用并行的 `number & { readonly [BRAND]: B }` 变体来 brand 它们，但它们是位置序号、很少跨边界传递，收益较低。 -- **带校验的构造**：brand 工厂是纯 cast，无运行时检查，且每个边界（ACP `sessionId`、提供方签发的 `call.id`、`dsh-llm-deepseek` 中的空字符串回退）今天都信任裸 string。一个在边界处对格式错误的输入抛异常的 `SessionId.parse()` / `isValid()` 配套工具确实是缺口，但它是*运行时行为*变更，有自己的设计问题（什么算「格式错误」？失败时会怎样？），应在独立决策中处理，不应捆绑进这次纯类型变更。 +- **带校验的构造**：brand 工厂是纯 cast，无运行时检查，且每个边界（ACP `sessionId`、提供方签发的 `call.id`、`dsh-llm-deepseek` 中的空字符串回退）都信任裸 string。一个在边界处对格式错误的输入抛异常的 `SessionId.parse()` / `isValid()` 配套工具确实是缺口，但它是*运行时行为*变更，有自己的设计问题（什么算「格式错误」？失败时会怎样？），应在独立决策中处理，不应捆绑进这次纯类型变更。 ## 验证 diff --git a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.i18n.yaml index 1b5420b35a..2b6c63d334 100644 --- a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md -2026-06-21-mandatory-app-attribution-headers.md: 479d3a46dc41c5cc9ae9b77b81dbef3d6524370b -2026-06-21-mandatory-app-attribution-headers.zh.md: 1b11cb6ef1e96609c6777134a85de298ca979c58 +2026-06-21-mandatory-app-attribution-headers.md: 9e0c029dc03c722512680a563c24e470128ee322 +2026-06-21-mandatory-app-attribution-headers.zh.md: 1427daf8f6065ec2dee324075a8381a625d9e960 diff --git a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md index 479d3a46dc..9e0c029dc0 100644 --- a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md +++ b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md @@ -42,7 +42,7 @@ Wire mapping (`attributionHeaders`; header names lowercase in code - HTTP field |---|---| | All HTTP-based adapters | `User-Agent: {product}/{version} (+{url})` - the parenthesized `+url` comment stays within RFC 9110's conservative product/comment syntax. | | Direct DeepSeek endpoint | `User-Agent` for app attribution; `x-deepseek-harness-user-id` and conditional `x-deepseek-harness-session-id` are separate request identity under the DeepSeek-specific decision. Do not send OpenRouter-only headers unless DeepSeek documents an equivalent contract. | -| OpenRouter endpoints | `User-Agent` only for now. Do not send `HTTP-Referer`, `X-OpenRouter-Title`, `X-Title`, or `X-OpenRouter-Categories` under this decision. | +| OpenRouter endpoints | `User-Agent` only. This decision excludes `HTTP-Referer`, `X-OpenRouter-Title`, `X-Title`, and `X-OpenRouter-Categories`. | | Future providers | `User-Agent` only unless a later provider-specific Agent Note accepts additional headers. Do not reuse `HTTP-Referer` by analogy. | Endpoint detection is not part of this Agent Note because no endpoint-specific mapping is accepted here. If OpenRouter support lands later, detection must be explicit: either a dedicated OpenRouter provider package or an explicit `provider: 'openrouter'` / `attributionTarget: 'openrouter'` config, not arbitrary path fragments or model names. diff --git a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.zh.md b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.zh.md index 1b11cb6ef1..1427daf8f6 100644 --- a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.zh.md @@ -42,7 +42,7 @@ OpenRouter 应用归属刻意未实现。`HTTP-Referer`、`X-OpenRouter-Title` |---|---| | 所有基于 HTTP 的适配器 | `User-Agent: {product}/{version} (+{url})`——括号中的 `+url` 注释符合 RFC 9110 保守的 product/comment 语法。 | | 直连 DeepSeek 端点 | `User-Agent` 用于应用归属；`x-deepseek-harness-user-id` 与条件性的 `x-deepseek-harness-session-id` 由 DeepSeek 特有决策作为独立请求身份管理。除非 DeepSeek 文档化了等效约定，否则不发送 OpenRouter 特有头部。 | -| OpenRouter 端点 | 目前仅 `User-Agent`。本决策下不发送 `HTTP-Referer`、`X-OpenRouter-Title`、`X-Title` 或 `X-OpenRouter-Categories`。 | +| OpenRouter 端点 | 仅发送 `User-Agent`。本决策排除 `HTTP-Referer`、`X-OpenRouter-Title`、`X-Title` 与 `X-OpenRouter-Categories`。 | | 未来提供方 | 仅 `User-Agent`，除非后续提供方特有的 Agent Note 接受额外头部。不要类比复用 `HTTP-Referer`。 | 端点检测不在本 Agent Note 范围内，因为此处不接受任何端点特有的映射。如果后续支持 OpenRouter，检测必须是显式的：要么是专门的 OpenRouter 提供方包，要么是显式的 `provider: 'openrouter'` / `attributionTarget: 'openrouter'` 配置，而非任意路径片段或模型名称。 diff --git a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.i18n.yaml index b2478911dc..23c4ea4142 100644 --- a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md -2026-07-05-reconstructable-requests.md: 63146fa2d392a45543daa32ce2b00158782fddb2 -2026-07-05-reconstructable-requests.zh.md: 94c1d323be0107eb8b6072a05d1e8832ebd1fffc +2026-07-05-reconstructable-requests.md: 3f49ba71a6b98a84b05530c900e902b0cf9f6449 +2026-07-05-reconstructable-requests.zh.md: 7b8a9df65b60f975bc3ae60b2c1b0c3a8cc22e95 diff --git a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md index 63146fa2d3..3f49ba71a6 100644 --- a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md +++ b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md @@ -51,5 +51,6 @@ Like MiniCode, the conversation advances append-only and resets only when model- - What still costs full price at the provider is inherent and logged: compaction (its `compaction/*` events and replacement entry), a real prompt, tool, or config change (`request/header` with reason `change`), or a process boundary with drift (a differing `resume` snapshot). The provider's own reasoning-content exclusion is managed server-side. - `agent/pre-step` is the current-request message channel; direct inbox mutation is the eventual later-request channel. - Tool-result trimming needs no new mechanism: a logged single-entry surface replace (`start === end`) carrying a trimmed `tool/result` under the same `callId` — compaction-family, replay-correct, cache-bust batched by the same pressure logic. +- Unreadable referenced attachment objects still fail model requests; [automatic attachment quarantine](../../proposed/bug-fix/2026-08-20-attachment-read-quarantine.md) records the proposed recovery without weakening byte-exact reconstruction. - Session logs grow one `request/header` snapshot per loop instance plus snapshots on real changes. This is larger than a delta codec but small beside chunk-heavy logs and retains one replay representation. `SESSION_FORMAT_VERSION` stays `0`; legacy delta events are rejected rather than migrated. - Snapshot expected outputs changed once (every transcript gains its header events); the fs-writing fixtures are stored in the normalized authored form with cwd-relative tool arguments, because replay only round-trips cwd-independent argument paths. diff --git a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.zh.md b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.zh.md index 94c1d323be..7b8a9df65b 100644 --- a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.zh.md @@ -51,5 +51,6 @@ Status: implemented - 在提供方处仍需全价计算的内容是固有的且已记录的：压缩（其 `compaction/*` 事件和替换条目）、真正的提示词、工具或配置变更（reason 为 `change` 的 `request/header`），或带漂移的进程边界（不同的 `resume` 快照）。提供方自身的 reasoning-content 排除由服务端管理。 - `agent/pre-step` 是当前请求的消息通道；直接修改 inbox 则是最终进入后续请求的通道。 - 工具结果裁剪无需新机制：一个已记录的单条目 surface replace（`start === end`），携带同一 `callId` 下裁剪后的 `tool/result`——属压缩家族，回放正确，缓存失效由相同的压力逻辑批量处理。 +- 无法读取的被引用附件对象仍会让模型请求失败；[附件自动隔离](../../proposed/bug-fix/2026-08-20-attachment-read-quarantine.zh.md)记录了不削弱字节精确重建的拟议恢复方案。 - 会话日志每个循环实例增长一个 `request/header` 快照，并在真正变更时增加快照。它比 delta 编解码器更大，但相对分片密集型日志仍然很小，并只保留一种回放表示。`SESSION_FORMAT_VERSION` 保持 `0`；旧的 delta 事件被拒绝而非迁移。 - 快照预期输出变更一次（每个 transcript（文本记录）增加其 header 事件）；写入文件系统的 fixture（测试前置数据）以规范化的撰写形式存储，工具参数使用 cwd 相对路径，因为回放只对 cwd 无关的参数路径做往返。 diff --git a/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.i18n.yaml index 580e74f217..66dd29f3a4 100644 --- a/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md -2026-07-06-timeout-deadline-library.md: 38f048d16ecba0e5278ae34b0c88b7889dcfa47a -2026-07-06-timeout-deadline-library.zh.md: c8d189c2a7588ee57b0f7fe02137b78c9ad7ff9d +2026-07-06-timeout-deadline-library.md: 95adc41bffff6d7711685ebc52cb73b2b455df41 +2026-07-06-timeout-deadline-library.zh.md: 8b7b18a2d1e7757102afc81bea03245de2707d86 diff --git a/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md index 38f048d16e..95adc41bff 100644 --- a/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md +++ b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md @@ -8,7 +8,7 @@ English | [中文](2026-07-06-timeout-deadline-library.zh.md) Timeout handling was drifting apart across the tool-bearing capabilities, and the divergence was not superficial — it was the same logic re-implemented three ways, each with its own subtle correctness burden. -- **bash** (then in the bash-local implementation's `run.ts`) had a full, correct timeout inside the process plumbing: a config-clamped `timeoutMs`, two independent triggers — a `killTimer` for the timeout and an `onAbort` listener for upstream cancellation — each calling one `kill()` closure that escalates SIGTERM→grace→SIGKILL on the process group, and two orthogonal outcome booleans (`timedOut`, `aborted`) latched independently. After this consolidation, the plumbing — today [packages/subprocess/subprocess-local/src/spawn.ts](../../../../packages/subprocess/subprocess-local/src/spawn.ts) — only reacts to aborts; [packages/shell/bash-local/src/index.ts](../../../../packages/shell/bash-local/src/index.ts) owns the fused deadline and the `timedOut`/`aborted` classification. +- **bash** (then in the bash-local implementation's `run.ts`) had a full, correct timeout inside the process plumbing: a config-clamped `timeoutMs`, two independent triggers — a `killTimer` for the timeout and an `onAbort` listener for upstream cancellation — each calling one `kill()` closure that escalates SIGTERM→grace→SIGKILL on the process group, and two orthogonal outcome booleans (`timedOut`, `aborted`) latched independently. After this consolidation, the plumbing — [packages/subprocess/subprocess-local/src/spawn.ts](../../../../packages/subprocess/subprocess-local/src/spawn.ts) — only reacts to aborts; [packages/shell/bash-local/src/index.ts](../../../../packages/shell/bash-local/src/index.ts) owns the fused deadline and the `timedOut`/`aborted` classification. - **web_fetch** ([packages/web/web-fetch-http/src/provider.ts](../../../../packages/web/web-fetch-http/src/provider.ts)) had a correct but *hand-rolled* timeout: it constructed an `AbortController`, wired `setTimeout(() => controller.abort(new WebError(…, 'WEB_FETCH_TIMEOUT')))`, manually added and removed the upstream-signal listener, cleared the timer in a `finally`, and recovered the timeout reason from `signal.reason` in a `translateAbortOrNetwork` helper because the reader surfaces a bare `AbortError`. - **web_search** ([packages/web/tool-web/src/search.ts](../../../../packages/web/tool-web/src/search.ts)) had **no timeout at all**: `WebSearchRequest` ([packages/web/web/src/types.ts](../../../../packages/web/web/src/types.ts)) carries no `timeoutMs` field, and each provider's `search()` only forwards `exec.signal`. (web_search stays untimed here — see Consequences.) diff --git a/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.zh.md b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.zh.md index c8d189c2a7..8b7b18a2d1 100644 --- a/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.zh.md @@ -8,7 +8,7 @@ Status: implemented 超时处理在各个承载工具的能力之间逐渐分化，而且这种分化并非表面的：同一套逻辑被以三种方式重新实现，各自带有微妙的正确性负担。 -- **bash**（当时位于 bash-local 实现的 `run.ts`）在进程管道内部有一套完整、正确的超时实现：一个经配置钳位的 `timeoutMs`，两个独立触发器（用于超时的 `killTimer` 和用于上游取消的 `onAbort` 监听器），各自调用同一个 `kill()` 闭包对进程组执行 SIGTERM→宽限期→SIGKILL 升级，以及两个正交的结果布尔值（`timedOut`、`aborted`）独立锁存。经此次整合之后，这套管道——今天位于 [packages/subprocess/subprocess-local/src/spawn.ts](../../../../packages/subprocess/subprocess-local/src/spawn.ts)——只响应中止；[packages/shell/bash-local/src/index.ts](../../../../packages/shell/bash-local/src/index.ts) 拥有融合的 deadline 以及 `timedOut`/`aborted` 分类。 +- **bash**（当时位于 bash-local 实现的 `run.ts`）在进程管道内部有一套完整、正确的超时实现：一个经配置钳位的 `timeoutMs`，两个独立触发器（用于超时的 `killTimer` 和用于上游取消的 `onAbort` 监听器），各自调用同一个 `kill()` 闭包对进程组执行 SIGTERM→宽限期→SIGKILL 升级，以及两个正交的结果布尔值（`timedOut`、`aborted`）独立锁存。经此次整合之后，这套管道——位于 [packages/subprocess/subprocess-local/src/spawn.ts](../../../../packages/subprocess/subprocess-local/src/spawn.ts)——只响应中止；[packages/shell/bash-local/src/index.ts](../../../../packages/shell/bash-local/src/index.ts) 拥有融合的 deadline 以及 `timedOut`/`aborted` 分类。 - **web_fetch**（[packages/web/web-fetch-http/src/provider.ts](../../../../packages/web/web-fetch-http/src/provider.ts)）有一套正确但*手写*的超时：构造一个 `AbortController`，连接 `setTimeout(() => controller.abort(new WebError(…, 'WEB_FETCH_TIMEOUT')))`，手动添加和移除上游信号监听器，在 `finally` 中清除定时器，并在 `translateAbortOrNetwork` 辅助函数中从 `signal.reason` 恢复超时原因（因为 reader 只抛出裸 `AbortError`）。 - **web_search**（[packages/web/tool-web/src/search.ts](../../../../packages/web/tool-web/src/search.ts)）**完全没有超时**：`WebSearchRequest`（[packages/web/web/src/types.ts](../../../../packages/web/web/src/types.ts)）不携带 `timeoutMs` 字段，各提供方的 `search()` 只转发 `exec.signal`。（web_search 在本次设计中保持无超时——见「后果」。） diff --git a/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.i18n.yaml index 398eaab528..554114fff0 100644 --- a/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.md -2026-07-06-tool-result-retention-library.md: 8d938db8f5fa78398a39e97cc877308200f7d60f -2026-07-06-tool-result-retention-library.zh.md: 747b545ee8c900c13d80c7aef6caecc8ae8dc0ad +2026-07-06-tool-result-retention-library.md: 464e3d51a0051487b7c29f0c01a11acb91d160e5 +2026-07-06-tool-result-retention-library.zh.md: 49361eec4b649d2d68dc36929baa0f9ff580eb68 diff --git a/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.md b/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.md index 8d938db8f5..464e3d51a0 100644 --- a/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.md +++ b/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.md @@ -16,7 +16,7 @@ The shared abstraction the tools need is **retention**, not generic collection. The library has two independent retainers: -- `ItemRetainer` handles ordered logical units such as paths, grep matches, or search sources. It supports `head` retention only in v1, while keeping the retainer shape open to additional retention strategies later. +- `ItemRetainer` handles ordered logical units such as paths, grep matches, or search sources. It supports only `head` retention, while keeping the retainer shape open to additional strategies. - `TextRetainer` handles byte-oriented text streams such as bash stdout/stderr or web response bodies. It supports `head`, `tail`, and `headTail` retention while preserving UTF-8 boundaries at `finish()`. Both retainers return a small `PushDecision` after each `push()` so callers can tell whether that unit/chunk was fully retained and whether the accumulated result is now truncated. Omission counts are exact because callers keep feeding every observed item/chunk. @@ -95,7 +95,7 @@ type TextRetentionStrategy = ### Tool mapping -`read` is intentionally outside the v1 retention library. Its `read-render` helper owns a file-specific pagination contract: `offset` / `limit`, line numbers, `totalLines`, offset-out-of-range errors, per-line preview truncation, and a selected-output byte cap that can stop scanning mid-window. That is a line-window renderer, not a generic retention primitive. It may share future neutral notice helpers, but it should not pass its already-selected window through `ItemRetainer`. +`read` is intentionally outside the retention library. Its `read-render` helper owns a file-specific pagination contract: `offset` / `limit`, line numbers, `totalLines`, offset-out-of-range errors, per-line preview truncation, and a selected-output byte cap that can stop scanning mid-window. That is a line-window renderer, not a generic retention primitive. It may share future neutral notice helpers, but it should not pass its already-selected window through `ItemRetainer`. `FsGlobEntry` and `FlatGrepMatch` below are the intended discovery-tool item shapes, not existing retention-library exports. `FsGlobEntry` is one backend-derived path, and `FlatGrepMatch` is one ungrouped grep match before the backend groups retained matches by file. @@ -142,15 +142,15 @@ The formatter hook is deliberately small: a tool turns a `RetentionNotice` into **Boundaries the library holds.** `truncated` means the retainer omitted otherwise-available content because of a budget; it never means the upstream was incomplete. Tool-specific states — `incomplete`, permission failures, provider partial failures, binary skips, bash spill-path recovery, invalid UTF-8 — stay in tool-domain fields, outside the retainer. When a future change migrates a tool, that package's README and tests must prove the model-facing result text is unchanged except for deliberate notice wording. -**Tradeoffs accepted.** The v1 API deliberately supports only item `head` retention and text `head` / `tail` / `headTail`; windows, grouped budgets, sort-aware caps, and upstream-stop control wait until a second consumer proves the need. Text retention counts bytes for process/body safety, leaving character- and line-level preview budgets as separate tool-owned concerns. +**Tradeoffs accepted.** The API deliberately supports only item `head` retention and text `head` / `tail` / `headTail`; windows, grouped budgets, sort-aware caps, and upstream-stop control wait until a second consumer proves the need. Text retention counts bytes for process/body safety, leaving character- and line-level preview budgets as separate tool-owned concerns. ## Alternatives considered **Post-hoc `truncate(text)` only.** Rejected: it matches Codex's history/tool-output truncation use case but loses item counts, grouping boundaries, UTF-8-safe byte windows, and exact omission metadata. -**One generic `Collector` with pluggable callbacks.** Rejected for v1: it hides the two important resource modes. Logical item retention counts items; text retention counts bytes and preserves UTF-8 boundaries. Separate `ItemRetainer` and `TextRetainer` names make that difference explicit while keeping the API small. +**One generic `Collector` with pluggable callbacks.** Rejected: it hides the two important resource modes. Logical item retention counts items; text retention counts bytes and preserves UTF-8 boundaries. Separate `ItemRetainer` and `TextRetainer` names make that difference explicit while keeping the API small. -**Put `read` windowing behind `ItemRetainer`.** Rejected for v1: `read` is the only current window consumer, and its semantics are file pagination rather than generic retention. A single `Omitted` count cannot represent both sides of a line window, and `read` also carries `totalLines`, offset-range errors, per-line preview truncation, and a byte cap over selected output. Keeping `read-render` tool-owned avoids growing the shared library around one special case. +**Put `read` windowing behind `ItemRetainer`.** Rejected: `read` is the only shipped window consumer, and its semantics are file pagination rather than generic retention. A single `Omitted` count cannot represent both sides of a line window, and `read` also carries `totalLines`, offset-range errors, per-line preview truncation, and a byte cap over selected output. Keeping `read-render` tool-owned avoids growing the shared library around one special case. **Make truncation part of `ToolExecutionResult`.** Rejected: the tool registry would have to understand tool-specific recovery guidance, grouping, line numbering, exit status, and provider semantics. Retention is a library used by a tool's Native renderer; the model-facing projection remains tool-owned while the [canonical value](2026-07-20-canonical-tool-output-contract.md) may retain the complete acquired result. diff --git a/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.zh.md b/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.zh.md index 747b545ee8..49361eec4b 100644 --- a/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.zh.md @@ -16,7 +16,7 @@ Status: implemented 该库包含两个相互独立的 retainer： -- `ItemRetainer` 处理有序逻辑单元，例如路径、grep 匹配项或搜索来源。v1 只支持 `head` 保留，同时维持 retainer 形态，以便未来加入其他保留策略。 +- `ItemRetainer` 处理有序逻辑单元，例如路径、grep 匹配项或搜索来源。它只支持 `head` 保留，同时维持 retainer 形态，以便未来加入其他保留策略。 - `TextRetainer` 处理面向字节的文本流，例如 bash stdout／stderr 或 web 响应正文。它支持 `head`、`tail` 和 `headTail` 保留，并在 `finish()` 时维持 UTF-8 边界。 两个 retainer 都会返回一个小型 `PushDecision`；每次调用 `push()` 后，调用方都能得知该单元／分片是否完整保留，以及累积结果此时是否已被截断。因为调用方会继续输入每一个已观察到的条目／分片，所以省略计数是精确的。 @@ -95,7 +95,7 @@ type TextRetentionStrategy = ### 工具映射 -`read` 被有意排除在 v1 保留库之外。它的 `read-render` 辅助函数拥有文件专用的分页约定：`offset`／`limit`、行号、`totalLines`、offset 越界错误、逐行预览截断，以及能够在窗口中途停止扫描的所选输出字节上限。这是行窗口渲染器，不是通用保留原语。它未来可以共享中性的提示辅助函数，但不应把已经选定的窗口再传入 `ItemRetainer`。 +`read` 被有意排除在保留库之外。它的 `read-render` 辅助函数拥有文件专用的分页约定：`offset`／`limit`、行号、`totalLines`、offset 越界错误、逐行预览截断，以及能够在窗口中途停止扫描的所选输出字节上限。这是行窗口渲染器，不是通用保留原语。它未来可以共享中性的提示辅助函数，但不应把已经选定的窗口再传入 `ItemRetainer`。 下文的 `FsGlobEntry` 与 `FlatGrepMatch` 是预期由发现工具使用的条目形态，不是现有保留库的导出。`FsGlobEntry` 是一个由后端派生的路径；`FlatGrepMatch` 是后端将保留匹配项按文件分组之前的一条未分组 grep 匹配。 @@ -142,15 +142,15 @@ const formatGrepNotice = (notice: RetentionNotice): string => **该库维持的边界。** `truncated` 表示 retainer 因预算省略了原本可用的内容，绝不表示上游不完整。工具专用状态，包括 `incomplete`、权限失败、提供方局部失败、跳过二进制文件、bash spill 路径恢复和无效 UTF-8，均留在工具领域字段中、位于 retainer 之外。未来改动迁移某项工具时，该包的 README 与测试必须证明，除了有意改变的提示措辞外，模型可见的结果文本没有变化。 -**接受的取舍。** v1 接口刻意只支持条目的 `head` 保留，以及文本的 `head`／`tail`／`headTail` 保留；窗口、分组预算、感知排序的上限和上游停止控制，要等第二个消费方证明需求后再引入。文本保留按字节计数，以保障进程／正文安全；字符级和行级预览预算继续由具体工具负责。 +**接受的取舍。**接口刻意只支持条目的 `head` 保留，以及文本的 `head`／`tail`／`headTail` 保留；窗口、分组预算、感知排序的上限和上游停止控制，要等第二个消费方证明需求后再引入。文本保留按字节计数，以保障进程／正文安全；字符级和行级预览预算继续由具体工具负责。 ## 考虑过的替代方案 **只进行事后 `truncate(text)`。** 不予采纳：它适合 Codex 的历史／工具输出截断场景，却会丢失条目计数、分组边界、UTF-8 安全的字节窗口与精确省略元数据。 -**使用一个带可插拔回调的通用 `Collector`。** v1 不予采纳，因为它会掩盖两种重要的资源模式。逻辑条目保留按条目计数；文本保留按字节计数并维持 UTF-8 边界。独立的 `ItemRetainer` 与 `TextRetainer` 名称明确表达这种差异，同时保持 API 精简。 +**使用一个带可插拔回调的通用 `Collector`。**不予采纳，因为它会掩盖两种重要的资源模式。逻辑条目保留按条目计数；文本保留按字节计数并维持 UTF-8 边界。独立的 `ItemRetainer` 与 `TextRetainer` 名称明确表达这种差异，同时保持 API 精简。 -**把 `read` 窗口交给 `ItemRetainer`。** v1 不予采纳：`read` 是当前唯一的窗口消费方，其语义属于文件分页，而不是通用保留。一个 `Omitted` 计数无法表示行窗口两侧，而且 `read` 还携带 `totalLines`、offset 范围错误、逐行预览截断和针对所选输出的字节上限。让 `read-render` 由工具所有，可以避免共享库围绕一项特例膨胀。 +**把 `read` 窗口交给 `ItemRetainer`。**不予采纳：`read` 是唯一已交付的窗口消费方，其语义属于文件分页，而不是通用保留。一个 `Omitted` 计数无法表示行窗口两侧，而且 `read` 还携带 `totalLines`、offset 范围错误、逐行预览截断和针对所选输出的字节上限。让 `read-render` 由工具所有，可以避免共享库围绕一项特例膨胀。 **让截断成为 `ToolExecutionResult` 的一部分。** 不予采纳：工具注册表将不得不理解工具专用的恢复指引、分组、行号、退出状态和提供方语义。保留是由工具的 Native renderer（原生渲染器）使用的库；模型可见投影继续由工具所有，而[规范值](2026-07-20-canonical-tool-output-contract.zh.md)可以保留完整的已采集结果。 diff --git a/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.i18n.yaml index 7f42f584f8..9533ed9b09 100644 --- a/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.md -2026-07-08-tool-output-spill-files.md: 341cb1ce131f627eed0f76ca6eb6a26fbb9dc689 -2026-07-08-tool-output-spill-files.zh.md: bd7c5dc058a8c753cefff3dd81802802426529ec +2026-07-08-tool-output-spill-files.md: 343b1af889ec14d5cac265ca6a7d073f9c0e4a06 +2026-07-08-tool-output-spill-files.zh.md: d6a163500a9e247fde46fadd2ada38ce60ce7b18 diff --git a/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.md b/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.md index 341cb1ce13..343b1af889 100644 --- a/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.md +++ b/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.md @@ -147,8 +147,8 @@ Those cases can consume `ctx.spillStore` directly in later work. They are not pa ## Non-goals -- No new model-facing `artifact_read` or `artifact_search` tool in v1. -- No per-tool retention configuration in v1. +- This decision adds no model-facing `artifact_read` or `artifact_search` tool. +- This decision adds no per-tool retention configuration. - No model-facing timeout/truncation arguments. - No migration of `read` output into spill files. - No replacement for provider/resource caps such as `web-fetch-http.maxBodyChars`. @@ -174,9 +174,9 @@ Those cases can consume `ctx.spillStore` directly in later work. They are not pa The default policy only sees final formatted text. It cannot preserve provider-internal content that was already capped or runtime artifacts that were never part of the result. This is acceptable for the first cut because the showcase is final-result spill, not early spill; tool-owned early spill remains deferred work. -Returning real paths from the local backend keeps v1 simple and matches proven agent-tool behavior, while the seam itself only promises an opaque locator plus retrieval hint so remote backends can return non-file locators. +Returning real paths keeps the local backend simple and matches proven agent-tool behavior, while the seam itself only promises an opaque locator plus retrieval hint so remote backends can return non-file locators. -The local-backend value proposition depends on the existing `read`/`grep` tools being able to inspect the returned local path, even when the spill directory is outside the session cwd. That holds today because the filesystem policy records observations and write guards but does not confine reads to the workspace. A future workspace-confinement policy must either allow local spill paths explicitly or use a non-file spill backend whose retrieval hint points at a supported reader. +The local-backend value proposition depends on the existing `read`/`grep` tools being able to inspect the returned local path, even when the spill directory is outside the session cwd. That holds because the filesystem policy records observations and write guards but does not confine reads to the workspace. A future workspace-confinement policy must either allow local spill paths explicitly or use a non-file spill backend whose retrieval hint points at a supported reader. **Snapshot gap.** No ACP snapshot scenario covers the transcript-visible `web_fetch` spill notice yet. The ACP snapshot harness replays keyless and cannot hit the live web, and a `web_fetch` spill requires a real over-cap HTTP body; a deterministic scenario would need a seeded loopback fetch target the replay tree does not currently wire (the examples do not load `tool-web` at all). The behavior is covered instead by the `dsh-tool-web` integration test against a loopback server. Closing the gap is follow-up work: wire `tool-web` + a seeded fetch target into the ACP example, then record a `web-fetch-spill` scenario. @@ -184,7 +184,7 @@ The policy can become too large if it starts owning tool-specific semantics. It ## Alternatives considered -**Require each tool to opt in with a retention declaration.** Rejected for v1: the goal is a default behavior similar to Claude Code's generic tool-result persistence. A single `maxInlineBytes` deployment knob is enough to prove the shape. +**Require each tool to opt in with a retention declaration.** Rejected: the goal is a default behavior similar to Claude Code's generic tool-result persistence. A single `maxInlineBytes` deployment knob is enough to prove the shape. **Make `tool-results` a broad tool-result platform.** Rejected: a broad package name invites retention policy, result replacement, preview wording, search, and early spill into one seam. The shared storage part is smaller: save text and return a locator plus retrieval hint. diff --git a/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.zh.md b/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.zh.md index bd7c5dc058..d6a163500a 100644 --- a/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.zh.md @@ -147,8 +147,8 @@ ctx.tools.register(defineTool({ ## 非目标 -- v1 不增加面向模型的 `artifact_read` 或 `artifact_search` 工具。 -- v1 不增加逐工具的保留配置。 +- 本决策不增加面向模型的 `artifact_read` 或 `artifact_search` 工具。 +- 本决策不增加逐工具的保留配置。 - 不增加面向模型的超时／截断参数。 - 不把 `read` 输出迁移到 spill 文件。 - 不取代 `web-fetch-http.maxBodyChars` 等提供方／资源上限。 @@ -174,9 +174,9 @@ ctx.tools.register(defineTool({ 默认策略只能看见最终格式化文本。它无法保留已经由提供方限制的内部内容，也无法保留从未成为结果一部分的运行时产物。第一版聚焦最终结果 spill 而不是提前 spill，因此可以接受这一限制；由工具负责的提前 spill 仍属于后续工作。 -本地后端返回真实路径，使 v1 保持简单并符合已经验证的 agent（智能体）工具行为；seam 本身只承诺一个不透明定位符加检索提示，所以远程后端可以返回非文件定位符。 +本地后端返回真实路径，使其保持简单并符合已经验证的 agent（智能体）工具行为；seam 本身只承诺一个不透明定位符加检索提示，所以远程后端可以返回非文件定位符。 -本地后端的价值取决于现有 `read`／`grep` 工具能否检查返回的本地路径，即使 spill 目录位于会话 cwd 之外。目前这一条件成立，因为文件系统策略会记录观察结果并设置写保护，但不会把读取限制在工作区内。未来的工作区限制策略必须显式允许本地 spill 路径，或改用检索提示指向受支持读取器的非文件 spill 后端。 +本地后端的价值取决于现有 `read`／`grep` 工具能否检查返回的本地路径，即使 spill 目录位于会话 cwd 之外。这一条件成立，因为文件系统策略会记录观察结果并设置写保护，但不会把读取限制在工作区内。未来的工作区限制策略必须显式允许本地 spill 路径，或改用检索提示指向受支持读取器的非文件 spill 后端。 **快照缺口。** 目前没有 ACP 快照场景覆盖 transcript（文本记录）可见的 `web_fetch` spill 提示。ACP 快照 harness 在无密钥环境中回放，无法访问实时 web，而 `web_fetch` spill 需要一个真实的超上限 HTTP 正文；确定性场景需要一个预置的 loopback fetch 目标，但当前回放树尚未接线（示例根本没有加载 `tool-web`）。该行为改由 `dsh-tool-web` 针对 loopback server 的集成测试覆盖。弥补该缺口属于后续工作：把 `tool-web` 和预置 fetch 目标接入 ACP 示例，然后录制 `web-fetch-spill` 场景。 @@ -184,7 +184,7 @@ ctx.tools.register(defineTool({ ## 考虑过的替代方案 -**要求每个工具通过保留声明选择加入。** v1 不予采纳，因为目标是实现类似 Claude Code 通用工具结果持久化的默认行为。只需一个 `maxInlineBytes` 部署配置项即可验证该形态。 +**要求每个工具通过保留声明选择加入。**不予采纳，因为目标是实现类似 Claude Code 通用工具结果持久化的默认行为。只需一个 `maxInlineBytes` 部署配置项即可验证该形态。 **把 `tool-results` 建成宽泛的工具结果平台。** 不予采纳：宽泛的包名会诱使系统把保留策略、结果替换、预览措辞、搜索和提前 spill 合并进一个 seam。可共享的存储部分更小：保存文本，并返回定位符与检索提示。 diff --git a/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml index 5c977fb644..11c83a197b 100644 --- a/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md -2026-07-15-llm-model-catalog-and-acp-selection.md: 8a7b882c3c6b6e6153a2d3b26d5c56440cb09658 -2026-07-15-llm-model-catalog-and-acp-selection.zh.md: 77c27bf1f2148ecae7ab8857572bf58fbc3086a9 +2026-07-15-llm-model-catalog-and-acp-selection.md: 55d6f58ce05e72fc28d55320695f67216f3f8061 +2026-07-15-llm-model-catalog-and-acp-selection.zh.md: b1a43a0092bc2f71d058a69dca28aed4f18380e7 diff --git a/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md index 8a7b882c3c..55d6f58ce0 100644 --- a/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md +++ b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md @@ -28,7 +28,7 @@ Catalog membership is advisory. It drives selectors and diagnostics but never ch ### Per-session selection in the front end -A selection is owned by the front end that offers it (today the TUI `/model` selector), never by `LlmRuntime` or `AgentOptions`: those are deployment-wide or creation-wide objects, and mutating them would couple concurrent sessions. Each opaque choice carries the full provider/model pair, because the same model id may appear under multiple routes. +A selection is owned by the front end that offers it, never by `LlmRuntime` or `AgentOptions`: those are deployment-wide or creation-wide objects, and mutating them would couple concurrent sessions. Each opaque choice carries the full provider/model pair, because the same model id may appear under multiple routes. The ACP automation transport is not a catalog consumer. Its deployment config supplies one optional provider/model target for newly created agents, and it advertises no model selector or configuration-option interface. diff --git a/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md index 77c27bf1f2..b1a43a0092 100644 --- a/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md @@ -28,7 +28,7 @@ ACP 选择还必须保留提供方维度。同一个模型 ID 可能存在于多 ### 前端内的会话级选择 -选择由提供它的前端拥有（今天是 TUI 的 `/model` 选择器），而不由 `LlmRuntime` 或 `AgentOptions` 拥有：它们是部署级或创建级对象，改动它们会把并发会话耦合在一起。每个不透明选项都携带完整的提供方／模型对，因为同一模型 ID 可能出现在多个路由下。 +选择由提供它的前端拥有，而不由 `LlmRuntime` 或 `AgentOptions` 拥有：它们是部署级或创建级对象，改动它们会把并发会话耦合在一起。每个不透明选项都携带完整的提供方／模型对，因为同一模型 ID 可能出现在多个路由下。 ACP 自动化传输层不是目录消费方。它通过部署配置为新创建的 agent 提供一个可选的提供方／模型目标，不展示模型选择器或配置选项接口。 diff --git a/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.i18n.yaml index 1ed087f38c..38e07804b7 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md -2026-07-19-gui-layering-and-rpc-protocol.md: 620803668e88f5a462ab2a75e6e916a85d433ed6 -2026-07-19-gui-layering-and-rpc-protocol.zh.md: 137cbce3e5dbc0be2736472f6e26d58112422697 +2026-07-19-gui-layering-and-rpc-protocol.md: 372bf4926011835999ebae9b1e2d1f5beb8eb663 +2026-07-19-gui-layering-and-rpc-protocol.zh.md: ecce57c01c155c2a0b19b7729da13c39d1a520a6 diff --git a/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md b/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md index 620803668e..372bf49260 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md +++ b/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md @@ -209,7 +209,7 @@ The same domain tree as `ApiProxy`, but unary methods **take the business payloa ### The instance-level envelope observation aspect -All four quadrant full forms pass through `onEnvelope`; the base implementation is an **instance-owned microtask-batched buffer** (frame storms must not disturb consumers per frame; module-level state would leak across instances/tests, hence instance-owned). Observers subscribe via `subscribeEnvelopes(listener)` (receiving whole batches as `readonly RpcMessage[]`, returning an unsubscribe function); a listener throw is isolated (observation must never bite the carrier). With no subscribers the buffering costs nothing. No shipped consumer subscribes today — the aspect is the designated seat for wire diagnostics (the retired RPC debug panel was its first consumer, and a future one plugs in without touching the carrier). +All four quadrant full forms pass through `onEnvelope`; the base implementation is an **instance-owned microtask-batched buffer** (frame storms must not disturb consumers per frame; module-level state would leak across instances/tests, hence instance-owned). Observers subscribe via `subscribeEnvelopes(listener)` (receiving whole batches as `readonly RpcMessage[]`, returning an unsubscribe function); a listener throw is isolated (observation must never bite the carrier). With no subscribers the buffering costs nothing. No shipped consumer subscribes — the aspect is the designated seat for wire diagnostics (the retired RPC debug panel was its first consumer, and a future one plugs in without touching the carrier). ### The subclass table (transport carriage) diff --git a/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.zh.md b/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.zh.md index 137cbce3e5..ecce57c01c 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.zh.md @@ -207,7 +207,7 @@ export type ResponseValue = ### 实例级 envelope 观测切面 -四象限全形均过 `onEnvelope`；基类实现是**实例持有的微任务合批缓冲**（帧风暴不逐帧惊扰消费方；模块级状态会跨实例/测试泄漏，故实例持有）。观测者经 `subscribeEnvelopes(listener)` 订阅（收整批 `readonly RpcMessage[]`，返回退订函数）；listener 抛异常被隔离（观测不得反噬载体）。无订阅者时零缓冲成本。当前没有任何现役消费方订阅——该切面是 wire 诊断的预留位（已退役的 RPC 调试面板是它的首个消费方，将来的诊断消费方接入时不动载体）。 +四象限全形均过 `onEnvelope`；基类实现是**实例持有的微任务合批缓冲**（帧风暴不逐帧惊扰消费方；模块级状态会跨实例/测试泄漏，故实例持有）。观测者经 `subscribeEnvelopes(listener)` 订阅（收整批 `readonly RpcMessage[]`，返回退订函数）；listener 抛异常被隔离（观测不得反噬载体）。无订阅者时零缓冲成本。没有任何已交付消费方订阅——该切面是 wire 诊断的预留位（已退役的 RPC 调试面板是它的首个消费方，将来的诊断消费方接入时不动载体）。 ### 子类表（传输承载） diff --git a/.agents/notes/implemented/architecture/2026-07-23-toolview-dissolution.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-23-toolview-dissolution.i18n.yaml index 0221b115ce..c09133e0c0 100644 --- a/.agents/notes/implemented/architecture/2026-07-23-toolview-dissolution.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-23-toolview-dissolution.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-23-toolview-dissolution.md -2026-07-23-toolview-dissolution.md: 173af01ff6cd5dc74f2f0916fd49ad278636d1bb -2026-07-23-toolview-dissolution.zh.md: 23f6f5dd037531892fde93ea170f958b535d89db +2026-07-23-toolview-dissolution.md: 3e38d2faf45d851b3f8f9a10459588570190b3fb +2026-07-23-toolview-dissolution.zh.md: 79c1f7d7630389462bf77d34df614bfd32798d50 diff --git a/.agents/notes/implemented/architecture/2026-07-23-toolview-dissolution.md b/.agents/notes/implemented/architecture/2026-07-23-toolview-dissolution.md index 173af01ff6..3e38d2faf4 100644 --- a/.agents/notes/implemented/architecture/2026-07-23-toolview-dissolution.md +++ b/.agents/notes/implemented/architecture/2026-07-23-toolview-dissolution.md @@ -18,7 +18,7 @@ This decision originally placed `'conversation.chat.toolview'` under the chat en ## Accepted semantic changes -Four behavioral deltas were accepted deliberately, not overlooked. Cross-view appearance was initially per-view registration; the follow-up note records why root/subcall composition later justified one Tool-wide presentation owner. Same-key double registration is a loud throw where the registry let later-wins silently override — a discipline correction, not a loss. Session-dimension dispatch, when a row needs it, belongs inside the component (the standard kit already carries `useSessions`), not in registry predicates — there is no shipped session-variant exemplar today. Registry-level shape override by third parties (a scoped registration shadowing a global one) has no equivalent; a real future need routes through key-naming conventions or a small in-component resolver, never a revived parallel registry. +Four behavioral deltas were accepted deliberately, not overlooked. Cross-view appearance was initially per-view registration; the follow-up note records why root/subcall composition later justified one Tool-wide presentation owner. Same-key double registration is a loud throw where the registry let later-wins silently override — a discipline correction, not a loss. Session-dimension dispatch, when a row needs it, belongs inside the component (the standard kit already carries `useSessions`), not in registry predicates — there is no shipped session-variant exemplar. Registry-level shape override by third parties (a scoped registration shadowing a global one) has no equivalent; a real future need routes through key-naming conventions or a small in-component resolver, never a revived parallel registry. ## Alternatives considered diff --git a/.agents/notes/implemented/architecture/2026-07-23-toolview-dissolution.zh.md b/.agents/notes/implemented/architecture/2026-07-23-toolview-dissolution.zh.md index 23f6f5dd03..79c1f7d763 100644 --- a/.agents/notes/implemented/architecture/2026-07-23-toolview-dissolution.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-23-toolview-dissolution.zh.md @@ -18,7 +18,7 @@ Status: implemented ## 接受的语义变化 -四项行为增量是刻意接受而非疏漏。跨视图出场最初采用逐视图注册；后续 Note 记录了为何 root/subcall 编排后来证明由一个 Tool 级展示所有者统一负责是合理的。同 key 重复注册从注册表的 later-wins 静默覆盖变为 loud throw——纪律修正而非损失。会话维分发若行需要，归组件内部（标配 kit 已带 `useSessions`），不走注册表谓词——今天没有已落地的会话变体样例。第三方在 registry 级覆盖形态（scoped 注册压过 global）不复存在；真出现的未来需求走 key 命名空间约定或组件内小 resolver，永不复活平行注册表。 +四项行为增量是刻意接受而非疏漏。跨视图出场最初采用逐视图注册；后续 Note 记录了为何 root/subcall 编排后来证明由一个 Tool 级展示所有者统一负责是合理的。同 key 重复注册从注册表的 later-wins 静默覆盖变为 loud throw——纪律修正而非损失。会话维分发若行需要，归组件内部（标配 kit 已带 `useSessions`），不走注册表谓词——没有已交付的会话变体样例。第三方在 registry 级覆盖形态（scoped 注册压过 global）不复存在；真出现的未来需求走 key 命名空间约定或组件内小 resolver，永不复活平行注册表。 ## Alternatives considered diff --git a/.agents/notes/implemented/architecture/2026-07-25-web-client-session-scope-and-provide-channel.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-25-web-client-session-scope-and-provide-channel.i18n.yaml index 32caddfbc6..64e6bbc289 100644 --- a/.agents/notes/implemented/architecture/2026-07-25-web-client-session-scope-and-provide-channel.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-25-web-client-session-scope-and-provide-channel.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-25-web-client-session-scope-and-provide-channel.md -2026-07-25-web-client-session-scope-and-provide-channel.md: 81ae4bdfa4f9666efc9eccd05bc4fe95d24b3dba -2026-07-25-web-client-session-scope-and-provide-channel.zh.md: dd5c09696525b0391b1c74693753ff2f6d372eba +2026-07-25-web-client-session-scope-and-provide-channel.md: 6f159dc16e0e4063f9077c31829a10caca98eae0 +2026-07-25-web-client-session-scope-and-provide-channel.zh.md: 2cb082dce75f1845e52a52289a8e3eaa1a000931 diff --git a/.agents/notes/implemented/architecture/2026-07-25-web-client-session-scope-and-provide-channel.md b/.agents/notes/implemented/architecture/2026-07-25-web-client-session-scope-and-provide-channel.md index 81ae4bdfa4..6f159dc16e 100644 --- a/.agents/notes/implemented/architecture/2026-07-25-web-client-session-scope-and-provide-channel.md +++ b/.agents/notes/implemented/architecture/2026-07-25-web-client-session-scope-and-provide-channel.md @@ -132,5 +132,5 @@ Slot scope is the closed set `root | session-maybe | session`: - Plugins gain session context isomorphic to the host's: per-session state hangs on the actx and mounts/tears down in one piece with the scope fiber, making leaks structurally impossible; two-session isolation is structurally guaranteed by the scope filter. - The client object layer converges to a wire mirror: session identity, lifecycle, and capability adjudication all defer to the host entity — the input system (the next layer) always faces a session with a real Agent, and providers like slash/skill uniformly address by sessionId directly. - Blank-session governance takes zero dedicated mechanisms: state rides one derived bit, visibility rides the unified list projection (only the current blank shows, as `New Session`), reclamation rides lazy persistence's existing contract (evaporation on restart), and the ordinary ceiling rides same-Workspace reuse. -- The cost: the id→ctx handoff discipline and provide's Concurrent discipline are conventions rather than type-enforced, pinned by review and tests. The single state axis still withholds machine faces until a Session exists; the resident card routes activation to the Workspace picker during that interval ([decision](../feature/2026-08-07-workspace-picker-composer-entry.md)). +- The cost: the id→ctx handoff discipline and provide's Concurrent discipline are conventions rather than type-enforced, pinned by review and tests. The single state axis still withholds machine faces until a Session exists; the [resident conversation shell](../../../../packages/client/ui-conversation/README.md) routes activation to the Workspace picker during that interval. - Known gaps: approval/question recovery across prune (TODO); model selection returns in live-mutation shape (the host `selectModel` trio is ready-made, its client consumer not yet built). diff --git a/.agents/notes/implemented/architecture/2026-07-25-web-client-session-scope-and-provide-channel.zh.md b/.agents/notes/implemented/architecture/2026-07-25-web-client-session-scope-and-provide-channel.zh.md index dd5c096965..2cb082dce7 100644 --- a/.agents/notes/implemented/architecture/2026-07-25-web-client-session-scope-and-provide-channel.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-25-web-client-session-scope-and-provide-channel.zh.md @@ -132,5 +132,5 @@ slot scope 是闭集 `root | session-maybe | session`： - 插件获得与 host 同构的会话上下文：逐会话状态挂 actx、随 scope fiber 一次拆装，泄漏结构性不可能；双会话隔离由 scope filter 结构性保证。 - client 对象层收敛为 wire 镜像：会话身份、生命周期、能力判别全部以 host 实体为准——输入体系（下一层）面对的永远是「有真 Agent 的会话」，slash/skill 等提供方一律以 sessionId 直接寻址。 - 空会话治理零专用机制：状态靠一个派生位，可见性靠统一列表投影（仅 current blank 以 `New Session` 展示），回收靠 lazy persistence 的既有约定（重启蒸发），常规上限靠同 Workspace 复用。 -- 代价：id→ctx 换乘纪律、provide 的 Concurrent 纪律都是约定而非类型强制，靠 review 与测试钉住。单一状态轴仍会在 Session 存在前隐藏 machine face；这段时间内，常驻卡片会把激活操作转到 Workspace picker（[决策](../feature/2026-08-07-workspace-picker-composer-entry.zh.md)）。 +- 代价：id→ctx 换乘纪律、provide 的 Concurrent 纪律都是约定而非类型强制，靠 review 与测试钉住。单一状态轴仍会在 Session 存在前隐藏 machine face；这段时间内，[常驻会话壳](../../../../packages/client/ui-conversation/README.zh.md)会把激活操作转到 Workspace picker。 - 已知欠账：approval/question 跨 prune 恢复（TODO）；模型选择以 live-mutation 形状回归（host `selectModel` 三件套现成，其 client 消费方尚未构建）。 diff --git a/.agents/notes/implemented/architecture/2026-07-26-job-registry-seam.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-26-job-registry-seam.i18n.yaml index 55f1a4c04c..4c1d7988e9 100644 --- a/.agents/notes/implemented/architecture/2026-07-26-job-registry-seam.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-26-job-registry-seam.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-26-job-registry-seam.md -2026-07-26-job-registry-seam.md: b4a8a66ef63f1a4955e2497cad2d0d0b1ef138ec -2026-07-26-job-registry-seam.zh.md: 1e990542e946854d85dd7d1accf3e5bba8ca2ccb +2026-07-26-job-registry-seam.md: fc344c9a9b24c13871475993dc52d7fdb92ed3be +2026-07-26-job-registry-seam.zh.md: 692937cfbae599b4dcaacdc31220a15f17a912aa diff --git a/.agents/notes/implemented/architecture/2026-07-26-job-registry-seam.md b/.agents/notes/implemented/architecture/2026-07-26-job-registry-seam.md index b4a8a66ef6..fc344c9a9b 100644 --- a/.agents/notes/implemented/architecture/2026-07-26-job-registry-seam.md +++ b/.agents/notes/implemented/architecture/2026-07-26-job-registry-seam.md @@ -22,7 +22,7 @@ The seam keeps the in-process contract semantics unchanged: `JobStart.run()` sti ## Alternatives considered -**Keep the concrete service until a second backend exists (status quo).** This was the original runtime note's position: extracting a Service Definition before a second provider risks freezing the wrong boundary. It lost because the boundary is no longer speculative — the nine service methods and their semantics have been stable across every producer integration since introduction, they are exactly the API `dsh-tool-jobs` and the producers already program against, and the repository convention treats swappable capabilities as three packages by default. The residual risk (a durable backend needing contract changes) is unchanged by the split: those changes would land in the Service Definition package either way, and today they would also churn every Consumer's provider dependency. +**Keep the concrete service until a second backend exists (status quo).** This was the original runtime note's position: extracting a Service Definition before a second provider risks freezing the wrong boundary. It lost because the boundary is no longer speculative — the nine service methods and their semantics have been stable across every producer integration since introduction, they are exactly the API `dsh-tool-jobs` and the producers already program against, and the repository convention treats swappable capabilities as three packages by default. The residual risk (a durable backend needing contract changes) is unchanged by the split: those changes would land in the Service Definition package either way, and they would also churn every Consumer's provider dependency. **Service-Definition-only extraction inside one package (export an abstract class beside the concrete one).** Rejected because it separates nothing operationally: Consumers still depend on the package that carries the provider and its dependencies, and a replacement backend still cannot ship without the local one in its graph. The package boundary is the unit of independent evolution here. diff --git a/.agents/notes/implemented/architecture/2026-07-26-job-registry-seam.zh.md b/.agents/notes/implemented/architecture/2026-07-26-job-registry-seam.zh.md index 1e990542e9..692937cfba 100644 --- a/.agents/notes/implemented/architecture/2026-07-26-job-registry-seam.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-26-job-registry-seam.zh.md @@ -22,7 +22,7 @@ Status: implemented ## 曾考虑的替代方案 -**在第二个后端出现之前保持具体服务（维持现状）。**这正是运行时 Agent Note 当初的立场：在第二个 Service Provider 出现前抽取 Service Definition，可能固化错误的边界。该方案落选，因为这条边界已不再是臆测：九个服务方法及其语义自引入以来在每一次生产方集成中都保持稳定，它们正是 `dsh-tool-jobs` 与各生产方已经面向编程的那套接口，而且仓库约定默认将可替换能力拆成三个包。剩余风险（持久化后端可能需要变更约定）不因这次拆分而改变：无论拆分与否，这类变更都会落在 Service Definition 包里；而若维持现状，它们今天还会连带搅动每个 Consumer 的提供方依赖。 +**在第二个后端出现之前保持具体服务（维持现状）。**这正是运行时 Agent Note 当初的立场：在第二个 Service Provider 出现前抽取 Service Definition，可能固化错误的边界。该方案落选，因为这条边界已不再是臆测：九个服务方法及其语义自引入以来在每一次生产方集成中都保持稳定，它们正是 `dsh-tool-jobs` 与各生产方已经面向编程的那套接口，而且仓库约定默认将可替换能力拆成三个包。剩余风险（持久化后端可能需要变更约定）不因这次拆分而改变：无论拆分与否，这类变更都会落在 Service Definition 包里；而若维持现状，它们还会连带搅动每个 Consumer 的提供方依赖。 **在单个包内仅抽取 Service Definition（在具体类旁导出一个抽象类）。**否决，因为它在运作层面并未分离任何东西：Consumer 依然依赖携带 Service Provider 及其依赖项的那个包，而替换后端若不把本地 Service Provider 纳入自身依赖图，就仍然无法发布。在这里，包边界才是独立演进的单位。 diff --git a/.agents/notes/implemented/architecture/2026-07-28-api-browser-trust-boundary.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-28-api-browser-trust-boundary.i18n.yaml index bce9b41482..c206e01dba 100644 --- a/.agents/notes/implemented/architecture/2026-07-28-api-browser-trust-boundary.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-28-api-browser-trust-boundary.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-28-api-browser-trust-boundary.md -2026-07-28-api-browser-trust-boundary.md: f4d14201d052299bb6063553e962a5d7c74fdb4b -2026-07-28-api-browser-trust-boundary.zh.md: 8c8e414e5f76b2ef2090ddc99916defa196da352 +2026-07-28-api-browser-trust-boundary.md: 92b76c109aa9b55bc72bb76f8b208ea2d814d8ce +2026-07-28-api-browser-trust-boundary.zh.md: 653ff32f2e62bf0e2982517f82649ff2d06e40d4 diff --git a/.agents/notes/implemented/architecture/2026-07-28-api-browser-trust-boundary.md b/.agents/notes/implemented/architecture/2026-07-28-api-browser-trust-boundary.md index f4d14201d0..92b76c109a 100644 --- a/.agents/notes/implemented/architecture/2026-07-28-api-browser-trust-boundary.md +++ b/.agents/notes/implemented/architecture/2026-07-28-api-browser-trust-boundary.md @@ -21,7 +21,7 @@ Two boundaries stay deliberately out of scope: reachability is the webserver bin - **Per-RPC guards (status quo extended).** Rejected: the guard list trails the method list forever, the highest-value methods were already unguarded, and a loopback rule on browse RPCs would break the remote deployments they exist for. - **CORS headers + credential omission.** Rejected: we never want cross-origin reads at all, so answering preflights only widens the surface; refusing them is strictly stronger and simpler. -- **Auth tokens now.** Rejected for this change: token minting/storage/rotation is real product surface; the fence closes the browser-deputy holes today without pre-deciding the auth design. +- **Authentication tokens.** Rejected for this change: token minting/storage/rotation is real product surface; the fence closes the browser-deputy holes without pre-deciding the auth design. ## Consequences diff --git a/.agents/notes/implemented/architecture/2026-07-28-api-browser-trust-boundary.zh.md b/.agents/notes/implemented/architecture/2026-07-28-api-browser-trust-boundary.zh.md index 8c8e414e5f..653ff32f2e 100644 --- a/.agents/notes/implemented/architecture/2026-07-28-api-browser-trust-boundary.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-28-api-browser-trust-boundary.zh.md @@ -21,7 +21,7 @@ Web GUI 宿主以纯 HTTP 提供 `/api`（默认 `127.0.0.1:3080`，支持 `--ho - **按 RPC 设防（延续现状）。** 否决：守卫清单永远追着方法清单跑，价值最高的方法本来就没被守住，而 browse RPC 上的回环规则会破坏它们为之存在的远程部署。 - **CORS 头与省略凭据。** 否决：我们根本不想要任何跨源读取，应答预检只会扩大暴露面；拒绝预检严格更强也更简单。 -- **现在就上认证令牌。** 在本变更中否决：令牌的签发、存储、轮换是真实的产品面；栅栏今天就能封死浏览器混淆代理人漏洞，无需预先决定认证设计。 +- **认证令牌。** 在本变更中否决：令牌的签发、存储、轮换是真实的产品面；栅栏能够封死浏览器混淆代理人漏洞，无需预先决定认证设计。 ## 后果 diff --git a/.agents/notes/implemented/architecture/2026-07-28-directory-picker-capability-seam.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-28-directory-picker-capability-seam.i18n.yaml index 994bd33a39..a72957b18a 100644 --- a/.agents/notes/implemented/architecture/2026-07-28-directory-picker-capability-seam.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-28-directory-picker-capability-seam.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-28-directory-picker-capability-seam.md -2026-07-28-directory-picker-capability-seam.md: 2e663e9bc90841dd843bf8a8ff5676e4ca3b91b3 -2026-07-28-directory-picker-capability-seam.zh.md: 46d62aeaadd73d00de71be8ecd7c478b978f918d +2026-07-28-directory-picker-capability-seam.md: 423fec3ad517e645f1cdee3513bad312a56989a8 +2026-07-28-directory-picker-capability-seam.zh.md: f652157fc152dee44a50ab8b55cc6120d92a1a26 diff --git a/.agents/notes/implemented/architecture/2026-07-28-directory-picker-capability-seam.md b/.agents/notes/implemented/architecture/2026-07-28-directory-picker-capability-seam.md index 2e663e9bc9..423fec3ad5 100644 --- a/.agents/notes/implemented/architecture/2026-07-28-directory-picker-capability-seam.md +++ b/.agents/notes/implemented/architecture/2026-07-28-directory-picker-capability-seam.md @@ -19,7 +19,7 @@ Placement and policy rulings folded into this decision: - **Not the `ctx.fs` seam.** `packages/fs/` is the model/session-facing storage stack (policy events, sandbox-swappable backends). Riding it would couple GUI browsing to the model's confinement backend — swapping `fs-sandbox` for the model must never change GUI behavior — and OS facts (home anchoring, hidden conventions) are not storage primitives. The picker seam stays presentation-free and model-free; `packages/host/` is its consumer-domain home. - **Dependency survey (hand-roll vs adopt).** Node's stdlib *is* the maintained cross-platform OS layer (`readdir(withFileTypes)`, `homedir`, path semantics); surveyed alternatives fail the dependency bar — file-manager packages (`node-file-manager`, `files-and-folders`, Syncfusion's provider) are whole HTTP apps (fit), drive-letter helpers (`drivelist` native addon, `windows-drive-letters` ~7y stale) fail health/proportionality. The browse backend is a thin adapter over stdlib. - **Hidden entries: return-and-flag.** The host stamps `hidden` (POSIX dot convention) and returns everything; the client filters. Display policy stays client-side, and the show-hidden toggle shipped as exactly that client-only change: a fixed-label footer toggle whose state lives in the pressed presentation (`aria-pressed` + check glyph), a dot-led path-draft prefix reveals the hidden entries it names, and the current selection is exempt from both the hidden and the prefix filter (it anchors the two-pane view). Windows' `FILE_ATTRIBUTE_HIDDEN` is not exposed by dirents — documented limitation until a native probe pays for itself. -- **Path-editor cancel scope: the dialog card.** The browse client's path editor cancels on Escape and on focus leaving the card, both observed at a card-scope wrapper rather than the input — after Tab parks focus on a filtered row the input is off the event path, yet Escape must collapse the editor (not the dialog) and a later focus departure must still cancel. Non-cancel exemptions: window/tab focus loss, in-card focus moves, and pointer paths (rows and the toggle suppress focus steal on mousedown while editing). Separators for seeding and draft-tail filtering are inferred from `listing.home`; the wire-field alternative below records the deferred authoritative form. Combobox semantics between the editor and the list it filters (`aria-expanded`/`aria-controls`/active-descendant, result announcements) are likewise deferred — today they read to assistive tech as separate widgets. +- **Path-editor cancel scope: the dialog card.** The browse client's path editor cancels on Escape and on focus leaving the card, both observed at a card-scope wrapper rather than the input — after Tab parks focus on a filtered row the input is off the event path, yet Escape must collapse the editor (not the dialog) and a later focus departure must still cancel. Non-cancel exemptions: window/tab focus loss, in-card focus moves, and pointer paths (rows and the toggle suppress focus steal on mousedown while editing). Separators for seeding and draft-tail filtering are inferred from `listing.home`; the wire-field alternative below records the deferred authoritative form. Combobox semantics between the editor and the list it filters (`aria-expanded`/`aria-controls`/active-descendant, result announcements) are likewise deferred — assistive technology reads them as separate widgets. - **The path editor advertises itself, and the panes follow the draft.** The click-to-edit zone is not invisible: a pencil glyph sits at the bar's right edge and hover/focus lights the WHOLE bar in the editor's own box — the bar carries the outline and padding in both modes, so the hover previews exactly the field the click produces and nothing resizes when zone and input swap. While the editor is open the panes track the draft instead of whatever level happened to be listed when it opened — the final segment prefix-filters the level its directory part names, a tail nobody matches releases the filter (a name still being spelled must not empty the pane it is being spelled into), and any other directory part is scanned after a 250ms rest and lands through the same selection-anchored, two-pane landing every navigation uses, so typing a path moves the Miller view exactly as a crumb jump does — typing deeper descends, erasing segments walks back up — without leaving the editor. **The pane arity is the invariant**: the last pane always lists the level the path names, with its parent beside it and nothing but a display root listing alone. Skipping the scan whenever *any* pane happened to list the directory was the cheaper rule and the wrong one — erasing a segment then left the level being typed on the left with its own child pane still standing to its right, so the panes stopped reading as "where I am, and where I came from". Only the last pane's own tail costs no scan. One landing shape, two callers: a submitted path closes the editor and announces failures, the draft-following scan keeps both to itself. That scan is speculative — half-typed directories are unreadable most of the time — so a failure keeps the last readable panes and stays silent. Enter remains the authoritative commit: it owns the view from submission until landing (a debounce timer armed by the same keystrokes is held back rather than superseding the navigation, and a rejected submission stays held until the next edit) and it alone surfaces the failure. Two consequences are deliberate. The wait is keyed on the draft, not on the directory part it names, so a keystroke that superseded an in-flight scan re-arms one and an edit after a rejected submission releases the hold; the panes it reads are a ref rather than a dependency, or the landing would re-arm the wait and a host answering with a differently spelled path would scan forever. And a walk is not rewound: closing the editor — cancellation included — leaves the panes where the draft took them, named by the crumbs and followed by Open's fallback target, because the operator watched them move. A landing that unmounts the row a keyboard operator Tabbed onto re-parks focus on the editor, since the Modal has no focus trap. Two further rules keep one keystroke to one movement: the walk waits BOTH legs out rather than taking the submitted-navigation wait bound (nothing waits on a speculative scan, so landing single-pane and upgrading would be the very flash this exists to avoid, and it would strand the two-pane view whenever a tail keystroke aborted a slow parent leg), and the tail filters only the LAST pane — narrowing a pane the draft has walked away from would move the view once as it narrows and again as its landing replaces it. A level also keeps answering the directory text that produced it (`scanned`), because the Host resolves what it is given: `..` segments and, on Windows, forward slashes reach a level whose own path spells the request differently, and without the memo those drafts would rescan on every keystroke and never filter. - **Navigation lands selection-anchored, quiet, and bounded.** Away from the display root (the same collapse the crumb header renders, so crumbs and pane shape never disagree), the landing is two-pane: the target's actual parent-level entry re-selected (platform case folding on Windows), its children on the right, so a crumb jump reads as stepping back one pane rather than collapsing to a single column. Target and parent legs land as **one frame** when the parent leg settles within the 200ms wait bound — the stale view keeps rendering until then, so navigation swaps the panes without an intermediate single-pane flash — and past the bound the target commits alone at once (an Enter-submitted navigation is never held hostage by a stalled parent) with the late parent leg upgrading the landing in place. The parent leg runs under the landing's supersession scope and is aborted on the wire by any newer intent (Escape inside the landing window therefore withdraws the whole navigation); a failed parent leg, or a truncated parent window lacking the target, leaves the single-pane landing — the upgrade must never orphan the selection it exists to anchor. The loading indicator follows the same quiet rule: it floats over the content's bottom-right corner (never a layout-shifting row; the truncated/error rows own the bottom left and keep rendering through a scan) and only once a scan outlives a 300ms silence window, so a local listing swaps with nothing shown at all. Row picks are deliberately exempt from the one-frame rule: a pick's immediate pane split is its selected-state feedback (aria-current, crumbs following), while a navigation has nothing to acknowledge the click but the swap itself. All three timing constants — the 200ms parent-leg bound, the 300ms silence window, and the editor's 250ms draft rest — are calibrated for local enumeration; a remote deployment (one RPC per level, commonly 100–400ms) would sit inside the silence window with no pressed state on the crumbs, and would pay rest plus RPC before the panes follow a typed path — revisit all three together when a remote consumer lands. - **Symlinks: follow for enterability.** `stat` probes symlinks (broken/cyclic → skipped); crumbs keep the logical path the operator navigated, and `workspace.create` already canonicalizes via realpath at adoption. diff --git a/.agents/notes/implemented/architecture/2026-07-28-directory-picker-capability-seam.zh.md b/.agents/notes/implemented/architecture/2026-07-28-directory-picker-capability-seam.zh.md index 46d62aeaad..f652157fc1 100644 --- a/.agents/notes/implemented/architecture/2026-07-28-directory-picker-capability-seam.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-28-directory-picker-capability-seam.zh.md @@ -19,7 +19,7 @@ web GUI 的「打开本地文件夹」流程被焊死在一种交互上：`host. - **不用 `ctx.fs` seam。** `packages/fs/` 是面向模型／会话的存储栈（policy 事件、沙箱可换后端）。骑上去会把 GUI 浏览耦合进模型的限制后端——为模型换 `fs-sandbox` 绝不能改变 GUI 行为——而 OS 事实（home 锚定、隐藏约定）也不是存储原语。picker seam 保持无展示、无模型；`packages/host/` 是它消费方域的家。 - **依赖调研（手写 vs 引入）。** Node 标准库本身就是维护中的跨平台 OS 层（`readdir(withFileTypes)`、`homedir`、路径语义）；调研过的替代品都过不了依赖门槛——文件管理器包（`node-file-manager`、`files-and-folders`、Syncfusion 的提供方）是整套 HTTP 应用（契合度不过），盘符工具（原生扩展 `drivelist`、约七年未更的 `windows-drive-letters`）健康度／比例失当。browse 后端是标准库上的薄适配器。 - **隐藏条目：返回并打标。** 宿主标注 `hidden`（POSIX 点前缀约定）并返回全部条目；客户端过滤。展示策略留在客户端，「显示隐藏」开关正是作为这一纯客户端改动落地：标签固定的 footer 开关，其状态由按下态呈现承载（`aria-pressed` + 勾选符号）；以点开头的路径草稿前缀会显出它所指名的隐藏条目；当前选中项则不受隐藏与前缀两种过滤影响（它锚定着双栏视图）。Windows 的 `FILE_ATTRIBUTE_HIDDEN` 不被 dirent 暴露——记为限制，直到原生探测的收益抵得上其成本。 -- **路径编辑器的取消范围：对话框卡片。** browse 客户端的路径编辑器在按 Escape 与焦点离开卡片时取消，两者都在卡片范围的包装层而非输入框上监听——Tab 把焦点停到某个过滤命中的行之后，输入框已不在事件路径上，但 Escape 仍须收起编辑器（而非对话框），其后的焦点离开也仍须取消。不取消的豁免：窗口／标签页失焦、卡片内焦点移动，以及指针路径（编辑期间行与开关在 mousedown 时抑制焦点夺取）。预填与草稿末段过滤所用的分隔符从 `listing.home` 推断；下文的线上字段替代方案记录了被延期的权威形态。编辑器与其过滤的列表之间的 combobox 语义（`aria-expanded`／`aria-controls`／active-descendant、结果播报）同样被延期——目前二者在辅助技术看来是彼此独立的控件。 +- **路径编辑器的取消范围：对话框卡片。** browse 客户端的路径编辑器在按 Escape 与焦点离开卡片时取消，两者都在卡片范围的包装层而非输入框上监听——Tab 把焦点停到某个过滤命中的行之后，输入框已不在事件路径上，但 Escape 仍须收起编辑器（而非对话框），其后的焦点离开也仍须取消。不取消的豁免：窗口／标签页失焦、卡片内焦点移动，以及指针路径（编辑期间行与开关在 mousedown 时抑制焦点夺取）。预填与草稿末段过滤所用的分隔符从 `listing.home` 推断；下文的线上字段替代方案记录了被延期的权威形态。编辑器与其过滤的列表之间的 combobox 语义（`aria-expanded`／`aria-controls`／active-descendant、结果播报）同样被延期——辅助技术会把二者读成是彼此独立的控件。 - **路径编辑器自我点明，各栏跟随草稿。** 点击即编辑的区域不再是隐形的：栏右端坐着一枚铅笔图标，悬停／聚焦时**整条栏**以编辑器自身的那只框亮起——轮廓与内边距在两种模式下都由栏承载，于是悬停预览的正是点击后出现的那只输入框，区域与输入框互换时也没有任何尺寸变化。编辑器打开期间，各栏跟随草稿，而不是停在它打开那一刻恰好列出的层级——末段对其目录部分所指的层级做前缀过滤，无一匹配的末段解除过滤（还在拼写中的名字不该把正在拼写它的那一栏清空），而其余任何目录部分都会在停顿 250ms 后被扫描，并经由每次导航共用的那套以选中项为锚的双栏落地落定，于是键入路径移动 Miller 视图的方式与 crumb 跳转完全一致——继续键入即下潜、删掉末段即上退——全程不必离开编辑器。**分栏个数才是不变量**：最后一栏永远是路径所指的那一层，其上一层在它旁边，只有展示根会独占一栏。「只要任意一栏碰巧列出了该目录就跳过扫描」是更省事、也是错的规则——删掉一段之后，正在键入的那一层会留在左栏，而它自己的子栏仍立在右边，于是两栏不再读作「我在哪儿、我从哪儿来」。只有最后一栏自己的末段不需要扫描。一种落地形态、两个调用方：提交的路径关闭编辑器并呈现失败，草稿跟随扫描则两者都不做。该扫描是推测性的——键入到一半的目录多数时候读不出来——因此失败时保留最后一次可读的分栏并保持沉默。Enter 仍是权威提交：自提交至落地由它独占视图（同一批按键武装的防抖计时器会被扣住，而不是顶掉这次导航；提交被拒后仍扣住，直到下一次编辑），也只有它把失败呈现出来。有两点是刻意为之。等待以草稿为键，而非以它指名的目录部分为键，于是顶掉在飞扫描的那次按键会重新武装等待，被拒提交之后的编辑也能释放那道扣留；而它读取的分栏是 ref 而非依赖，否则落地会重新武装等待，遇到以不同拼写作答的宿主便会永远扫描下去。以及，走过的路不回退：关闭编辑器——包括取消——都把分栏留在草稿带到的地方，由面包屑指明、Open 的兜底目标随之而动，因为操作者亲眼看着它们移动。若落地卸载了键盘操作者 Tab 停留的那一行，焦点会被重新停回编辑器——Modal 并没有焦点陷阱。另有两条规则保证一次按键只让视图移动一次：这段行走会**等齐两程**，而不套用提交导航的等待上限（推测性扫描没有任何东西在等它，先落单栏再升级恰恰就是它要避免的那次闪动，而且一旦末段按键中止了缓慢的父层级这一程，双栏视图就会永久丢失）；末段也只过滤**最后一栏**——去收窄一个草稿已经走开的分栏，会让视图先因收窄动一次、再因它自己的落地动一次。此外，层级会持续应答产生它的那段目录文本（`scanned`），因为宿主会解析它收到的东西：`..` 段与 Windows 的正斜杠都会抵达一个自身路径拼写不同的层级；没有这份记忆，这类草稿会每敲一键就重扫一次，而且永远过滤不了。 - **导航以选中项为锚、安静且有界地落地。** 在展示根之外（与 crumb 头部渲染的是同一塌缩，因此 crumb 与分栏形态永不相左），落地即双栏：重新选中目标在父层级中的实际条目（Windows 上按平台惯例折叠大小写），右侧展示其子项，因此 crumb 跳转读作后退一栏，而不是塌缩成单列。父层级这一程在 200ms 等待上限内落定时，目标与父层级两程以**同一帧**落地——在此之前陈旧视图持续渲染，导航换栏时因此没有中间的单栏闪现——超出该上限则目标即刻单独提交（Enter 提交的导航绝不会被滞塞的父层级扣作人质），迟到的父层级这一程再就地升级这次落地。父层级这一程在落地的 supersession 范围下运行，任何较新的意图都会在线上将其中止（因此在落地窗口内按 Escape 即撤回整次导航）；父层级这一程失败，或被截断的父窗口缺少目标时，都保留单栏落地——升级的存在正是为了锚定选中项，绝不能反而让它悬空。加载指示器遵循同一安静规则：它浮于内容右下角（绝不是会挪动布局的一行；截断／错误行占据左下角，并在扫描期间持续渲染），且仅在扫描超出 300ms 静默窗口后才出现，因此本地列举切换时什么也不显示。行选取被刻意豁免于同一帧规则：选取后立即分栏本身就是其选中态反馈（aria-current、crumb 跟随），而导航除了换栏本身没有任何东西可确认这次点击。三个时序常量——200ms 父层级上限、300ms 静默窗口，以及编辑器的 250ms 草稿停顿——都按本地列举校准；远程部署（每层级一次 RPC，通常 100–400ms）会落在静默窗口之内、crumb 上却没有按下态，而且要先付停顿再付 RPC 分栏才跟上——待远程消费方落地时，三者一并重新审视。 - **符号链接：为可进入性而跟随。** 用 `stat` 探测符号链接（断链／循环→跳过）；面包屑保留操作者导航的逻辑路径，`workspace.create` 在接纳时本就做 realpath 规范化。 diff --git a/.agents/notes/implemented/architecture/2026-07-29-dsh-source-launch-tsx-esm.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-29-dsh-source-launch-tsx-esm.i18n.yaml index 4ec48834d9..a46174dd21 100644 --- a/.agents/notes/implemented/architecture/2026-07-29-dsh-source-launch-tsx-esm.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-29-dsh-source-launch-tsx-esm.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-29-dsh-source-launch-tsx-esm.md -2026-07-29-dsh-source-launch-tsx-esm.md: 425cf46ca802e8d3ac1d49a1955c5e7ea208bd20 -2026-07-29-dsh-source-launch-tsx-esm.zh.md: 87b323c82f28135396d1d16991e2365c691fcc6a +2026-07-29-dsh-source-launch-tsx-esm.md: 23cf4023e91d148b2e129faa7395fdccdd3e0a2b +2026-07-29-dsh-source-launch-tsx-esm.zh.md: e2dede0036dd1128718bdf41a11f5949555b69a5 diff --git a/.agents/notes/implemented/architecture/2026-07-29-dsh-source-launch-tsx-esm.md b/.agents/notes/implemented/architecture/2026-07-29-dsh-source-launch-tsx-esm.md index 425cf46ca8..23cf4023e9 100644 --- a/.agents/notes/implemented/architecture/2026-07-29-dsh-source-launch-tsx-esm.md +++ b/.agents/notes/implemented/architecture/2026-07-29-dsh-source-launch-tsx-esm.md @@ -26,7 +26,7 @@ The node-compat CI matrix (Node 22.19 and 26) gains `dsh-source-launch-smoke` (` **Make the source graph erasable-only so Node 26 strip mode accepts it.** Rejected: parameter properties and value namespaces pervade vendored Cordis/cosmokit/loader/schemastery; rewriting them is unbounded churn re-applied on every vendor sync. -**A repo-owned in-thread loader (`module.registerHooks()` + esbuild or `@swc/core` transform).** Rejected for now: prototypes measured ~0.45s (esbuild path untested end-to-end; SWC breaks on `vendor/hmr`'s decorator + namespace merge in both decorator modes), but it means owning transform correctness and a resolve hook that tsx already provides. Revisit only if the ~0.3s gap becomes a real cost; the profiling evidence lives in the PR discussion. +**A repo-owned in-thread loader (`module.registerHooks()` plus an esbuild or `@swc/core` transform).** Rejected: prototypes measured about 0.45s, while the esbuild path lacked end-to-end validation and SWC failed on `vendor/hmr`'s decorator plus namespace merge in both decorator modes. This option also makes the repository own transform correctness and a resolve hook that tsx already provides. Revisit only if the measured 0.3s gap becomes a material cost. **Run built `lib/` for Node 26 and keep native for 24.** Rejected: loses the zero-build development loop on the newest Node line and mixes source and artifact planes. diff --git a/.agents/notes/implemented/architecture/2026-07-29-dsh-source-launch-tsx-esm.zh.md b/.agents/notes/implemented/architecture/2026-07-29-dsh-source-launch-tsx-esm.zh.md index 87b323c82f..e2dede0036 100644 --- a/.agents/notes/implemented/architecture/2026-07-29-dsh-source-launch-tsx-esm.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-29-dsh-source-launch-tsx-esm.zh.md @@ -26,7 +26,7 @@ node-compat CI 矩阵（Node 22.19 与 26）新增 `dsh-source-launch-smoke`（` **把源码图改成 erasable-only 以适配 Node 26 strip 模式。** 拒绝：参数属性与值 namespace 遍布 vendor 的 Cordis/cosmokit/loader/schemastery；改写是无界 churn，且每次 vendor sync 都要重做。 -**仓库自有的同线程 loader（`module.registerHooks()` + esbuild 或 `@swc/core` 转换）。** 暂拒：原型实测约 0.45s（esbuild 路径未端到端验证；SWC 在 `vendor/hmr` 的装饰器 + namespace 合并上两种装饰器模式都会崩），但这意味着要自行负责转换正确性，以及实现 tsx 已经提供的解析钩子。仅当约 0.3s 的差距成为真实成本时再重新考虑；性能分析证据在 PR 讨论中。 +**仓库自有的同线程 loader（`module.registerHooks()` 加 esbuild 或 `@swc/core` 转换）。**不予采纳：原型实测约 0.45s，而 esbuild 路径缺少端到端验证，SWC 在两种装饰器模式下都会因 `vendor/hmr` 的装饰器与 namespace 合并失败。该方案还会让仓库负责转换正确性和 tsx 已经提供的解析钩子。仅当实测约 0.3s 的差距成为实质成本时再重新考虑。 **Node 26 运行构建产物 `lib/`，24 保留原生。** 拒绝：在最新 Node 版本线上失去零构建开发循环，且混淆源码面与产物面。 diff --git a/.agents/notes/implemented/architecture/2026-07-30-config-plane-boundaries.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-30-config-plane-boundaries.i18n.yaml index b9f14a45d8..ac8f90ed76 100644 --- a/.agents/notes/implemented/architecture/2026-07-30-config-plane-boundaries.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-30-config-plane-boundaries.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-30-config-plane-boundaries.md -2026-07-30-config-plane-boundaries.md: aab0d7a80c2732b33637ec721a9ab7c1b50fce3f -2026-07-30-config-plane-boundaries.zh.md: 7e01aad93947266362cec31fdeab18524ea14cd9 +2026-07-30-config-plane-boundaries.md: 7b234ec64669cc1e6f0d5a67437005747edcea98 +2026-07-30-config-plane-boundaries.zh.md: f543c511d9374a50955331911b2eb2d62dab0675 diff --git a/.agents/notes/implemented/architecture/2026-07-30-config-plane-boundaries.md b/.agents/notes/implemented/architecture/2026-07-30-config-plane-boundaries.md index aab0d7a80c..7b234ec646 100644 --- a/.agents/notes/implemented/architecture/2026-07-30-config-plane-boundaries.md +++ b/.agents/notes/implemented/architecture/2026-07-30-config-plane-boundaries.md @@ -22,7 +22,7 @@ Three smaller defects sat beside them. `llm/adapters-updated` documented contain **Reading configuration is as privileged as writing it.** `settings.describe` and `credentials.describe` join the loopback-only set, so the whole configuration plane stays same-origin until real authentication exists. The model catalog (`llm.providers`, `llm.models`) deliberately does not: it carries provider ids, display names, and model lists — no endpoints, no key state — and a LAN client's model picker needs it. The boundary is asserted over a real HTTP server rather than a hand-assembled request, because the `Host` header a browser actually sends is what decides it. -**The plane serves exactly the namespaces a registered model provider addresses.** `ctx.llm.listConfigurableProviders()` is the allow-list, so the product boundary is enforced rather than inferred from today's plugin set, and a future namespace becomes web-configurable only by joining that directory. An unregistered namespace and an unexposed one answer identically (`settings-not-exposed`), so probing cannot enumerate the registry. +**The plane serves exactly the namespaces a registered model provider addresses.** `ctx.llm.listConfigurableProviders()` is the allow-list, so the product boundary is enforced rather than inferred from the installed plugin set, and a future namespace becomes web-configurable only by joining that directory. An unregistered namespace and an unexposed one answer identically (`settings-not-exposed`), so probing cannot enumerate the registry. **A caller with a partial view names the field it means.** `SettingsProvider.mutate(ns, ops)` applies `set`/`unset` path ops to the section as it stands at the front of the write queue. The client builds ops by diffing its opening snapshot against its draft, so it mentions only fields it can see: a secret absent from both sides produces no op and survives by construction, not by care. `replace` remains the deliberate wholesale reset. diff --git a/.agents/notes/implemented/architecture/2026-07-30-config-plane-boundaries.zh.md b/.agents/notes/implemented/architecture/2026-07-30-config-plane-boundaries.zh.md index 7e01aad939..f543c511d9 100644 --- a/.agents/notes/implemented/architecture/2026-07-30-config-plane-boundaries.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-30-config-plane-boundaries.zh.md @@ -22,7 +22,7 @@ Status: implemented **读取配置与写入配置同样属于特权操作。**`settings.describe` 与 `credentials.describe` 加入仅限回环的集合，因此在真正的认证层出现之前，整个配置面都保持同源。模型目录（`llm.providers`、`llm.models`）刻意不在其中：它携带的是提供方 id、显示名与模型列表——没有端点、没有密钥状态——而 LAN 客户端的模型选择器正需要它。这条边界由一台真实 HTTP 服务器来断言，而不是手工拼装的请求，因为真正决定它的，是浏览器实际发出的那个 `Host` 头。 -**这个面恰好服务于已注册模型提供方所指向的那些 namespace。**`ctx.llm.listConfigurableProviders()` 就是允许列表，于是产品边界是被执行的，而不是从今天的插件集合里推断出来的；将来的 namespace 只有加入该目录才会变得可在 Web 上配置。未注册的 namespace 与未暴露的 namespace 得到完全相同的答复（`settings-not-exposed`），因此探测无法枚举注册表。 +**这个面恰好服务于已注册模型提供方所指向的那些 namespace。**`ctx.llm.listConfigurableProviders()` 就是允许列表，于是产品边界是被执行的，而不是从已安装的插件集合里推断出来的；将来的 namespace 只有加入该目录才会变得可在 Web 上配置。未注册的 namespace 与未暴露的 namespace 得到完全相同的答复（`settings-not-exposed`），因此探测无法枚举注册表。 **持有局部视图的调用方，点名它真正要改的字段。**`SettingsProvider.mutate(ns, ops)` 会把 `set`/`unset` 路径 op 施加在写入排到队首那一刻的分节上。客户端通过对比自己打开时的快照与草稿来构造 op，因此它只提及自己看得见的字段：两侧都没有的机密不会产生任何 op，它的留存是构造使然，而非小心使然。`replace` 仍是那个刻意的整体重置。 diff --git a/.agents/notes/implemented/architecture/2026-07-30-credential-boundaries-and-atomic-registration.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-30-credential-boundaries-and-atomic-registration.i18n.yaml index 82e5a70c63..b096299ad0 100644 --- a/.agents/notes/implemented/architecture/2026-07-30-credential-boundaries-and-atomic-registration.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-30-credential-boundaries-and-atomic-registration.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-30-credential-boundaries-and-atomic-registration.md -2026-07-30-credential-boundaries-and-atomic-registration.md: 95c16ef2bf3d82d7b8b53e3975ece3f0c63402f3 -2026-07-30-credential-boundaries-and-atomic-registration.zh.md: d09f24c3bd93934432f543e77bb8d92595b458ad +2026-07-30-credential-boundaries-and-atomic-registration.md: 32b49fbc957b251606627c471e3211909a35cf68 +2026-07-30-credential-boundaries-and-atomic-registration.zh.md: 7067ee1d1f610aa65ffed456326b422f3137d7e8 diff --git a/.agents/notes/implemented/architecture/2026-07-30-credential-boundaries-and-atomic-registration.md b/.agents/notes/implemented/architecture/2026-07-30-credential-boundaries-and-atomic-registration.md index 95c16ef2bf..32b49fbc95 100644 --- a/.agents/notes/implemented/architecture/2026-07-30-credential-boundaries-and-atomic-registration.md +++ b/.agents/notes/implemented/architecture/2026-07-30-credential-boundaries-and-atomic-registration.md @@ -14,7 +14,7 @@ Two request-path defects sat beside them. DeepSeek resolved connection and crede ## Decision -**The credential document belongs to the credential provider alone.** No surface loads it into `process.env`. It was `$DSH_HOME/.env` here; the [credentials document split](2026-08-04-credentials-yaml-and-user-environment-layer.md) later moved it to `$DSH_HOME/.credentials.yaml`, so today it is the old path that is loaded — as the user's ordinary environment layer, holding no provider-managed secret. The genuine launch environment and the invoking directory's `.env` (loaded by the bin) stay the read-only ambient layer, so a composition without the provider resolves keys exactly as before, while a stored key stays file-sourced and writable across restarts — proven by a real restart in the loader composition rather than by a unit assertion about `describe()`. +**The credential document belongs to the credential provider alone.** No surface loads it into `process.env`. It was `$DSH_HOME/.env` here; the [credentials document split](2026-08-04-credentials-yaml-and-user-environment-layer.md) later moved it to `$DSH_HOME/.credentials.yaml`, so `$DSH_HOME/.env` is the user's ordinary environment layer, holding no provider-managed secret. The genuine launch environment and the invoking directory's `.env` (loaded by the bin) stay the read-only ambient layer, so a composition without the provider resolves keys exactly as before, while a stored key stays file-sourced and writable across restarts — proven by a real restart in the loader composition rather than by a unit assertion about `describe()`. **The stored credential has no boundary against the model, and the READMEs say so.** `0600` under a `0700` directory stops other OS users; the model's bash and filesystem tools run as that same user, and the shipped default confines nothing. What the harness does hold to is narrower and stated as exactly that: no surface hoists the document into `process.env`, and the model is never handed a resolved path to it, so reaching the value takes a deliberate read of a path it was not given. An OS-keychain provider — a store the model's processes cannot read at all — is recorded as the real answer rather than implied by a partial one. diff --git a/.agents/notes/implemented/architecture/2026-07-30-credential-boundaries-and-atomic-registration.zh.md b/.agents/notes/implemented/architecture/2026-07-30-credential-boundaries-and-atomic-registration.zh.md index d09f24c3bd..7067ee1d1f 100644 --- a/.agents/notes/implemented/architecture/2026-07-30-credential-boundaries-and-atomic-registration.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-30-credential-boundaries-and-atomic-registration.zh.md @@ -18,7 +18,7 @@ Status: implemented ## 决策 -**凭据文档只归凭据提供方所有。**没有任何一个面会把它加载进 `process.env`。当时该文档是 `$DSH_HOME/.env`；[凭据文档拆分](2026-08-04-credentials-yaml-and-user-environment-layer.zh.md)后来把它移到 `$DSH_HOME/.credentials.yaml`，因此如今被加载的正是那条旧路径——作为用户的普通环境层，其中不含任何提供方管理的密钥。真正的启动环境，以及调用目录中由 bin 加载的 `.env`，仍然是那一层只读的环境来源，因此不挂载该提供方的组合，解析密钥的方式与从前完全一致，而存下的密钥跨重启仍然来源于文件、仍然可写——这一点由 loader 组合中的一次真实重启来证明，而不是靠对 `describe()` 的单元断言。 +**凭据文档只归凭据提供方所有。**没有任何一个面会把它加载进 `process.env`。当时该文档是 `$DSH_HOME/.env`；[凭据文档拆分](2026-08-04-credentials-yaml-and-user-environment-layer.zh.md)后来把它移到 `$DSH_HOME/.credentials.yaml`，因此 `$DSH_HOME/.env` 是用户的普通环境层，其中不含任何提供方管理的密钥。真正的启动环境，以及调用目录中由 bin 加载的 `.env`，仍然是那一层只读的环境来源，因此不挂载该提供方的组合，解析密钥的方式与从前完全一致，而存下的密钥跨重启仍然来源于文件、仍然可写——这一点由 loader 组合中的一次真实重启来证明，而不是靠对 `describe()` 的单元断言。 **存下的凭据对模型没有边界，而 README 就是这么写的。**`0700` 目录下的 `0600` 挡得住其他 OS 用户；模型的 bash 与文件系统工具正是以同一用户身份运行，而已交付的默认配置不提供任何约束。harness 真正守住的边界更窄，文档也严格按这一范围表述：没有任何一个面会把该文档提升进 `process.env`，模型也从不会拿到它的解析后路径，因此要拿到这个值，需要刻意去读一条并未交给它的路径。OS 钥匙串（keychain）提供方——一个模型的进程根本读不到的存储——被记录为真正的答案，而不是靠一个残缺的方案去暗示它。 diff --git a/.agents/notes/implemented/architecture/2026-07-30-web-config-plane.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-30-web-config-plane.i18n.yaml index dc41a56889..ca0cd569c9 100644 --- a/.agents/notes/implemented/architecture/2026-07-30-web-config-plane.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-30-web-config-plane.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-30-web-config-plane.md -2026-07-30-web-config-plane.md: ac989cb100190e9a41ebf04b5b2d80125d49e0cb -2026-07-30-web-config-plane.zh.md: 538a90ae107e69c61c039d94efe47b258f313d55 +2026-07-30-web-config-plane.md: c8397d03cd7b8eb4ea127cdc26124f5e721e822d +2026-07-30-web-config-plane.zh.md: b0724c3a8cb160cbac5fc88fe07d35e79accfc49 diff --git a/.agents/notes/implemented/architecture/2026-07-30-web-config-plane.md b/.agents/notes/implemented/architecture/2026-07-30-web-config-plane.md index ac989cb100..c8397d03cd 100644 --- a/.agents/notes/implemented/architecture/2026-07-30-web-config-plane.md +++ b/.agents/notes/implemented/architecture/2026-07-30-web-config-plane.md @@ -27,9 +27,9 @@ The request-level configuration seam made LLM adapter configuration restart-free ## Alternatives considered - **Serving JSON Schema over the wire** — schemastery's `toJSON()` envelope round-trips `role()`/meta and rehydrates into the validator the client already ships for drafts; converting to JSON Schema loses exactly the role annotations the credential control and secret redaction key on. -- **A generic schema-driven form renderer** — implemented first, then replaced: field truth without visual hierarchy produced an ugly, unusable card, and making it good meant building a hint vocabulary (primary/advanced grouping, per-field descriptions, array item cards) rivaling the hand-written editor in cost while still fitting no mockup exactly. Two schemas exist today (the deepseek `Config` and the shared pi-ai profile), so hand-writing is two thin namespace-keyed layouts; the drift risk is bounded by save-time schema validation and by unknown fields staying untouched in the document. +- **A generic schema-driven form renderer** — implemented first, then replaced: field truth without visual hierarchy produced an ugly, unusable card, and making it good meant building a hint vocabulary (primary/advanced grouping, per-field descriptions, array item cards) rivaling the hand-written editor in cost while still fitting no mockup exactly. The two relevant schemas are the DeepSeek `Config` and the shared pi-ai profile, so hand-writing is two thin namespace-keyed layouts; the drift risk is bounded by save-time schema validation and by unknown fields staying untouched in the document. - **Masking secrets per-field with sentinel backfill on `replace`** — the request-level seam decision (secrets are references) already deleted the stored-literal case for the product default; structural redaction plus a write-only credential path handles the residue without teaching every writer a sentinel protocol. -- **Storing the typed key as a literal `apiKey` setting** — the v1 "one API key input" requirement could have written the literal into the profile, but every UI removal path rebuilds the user section from the *redacted* layers, so any reset or row deletion would silently drop stored sibling keys; deriving a reference keeps the input single-field while keeping `settings.yaml` secret-free and every replace safe. +- **Storing the typed key as a literal `apiKey` setting** — the single API key input requirement could have written the literal into the profile, but every UI removal path rebuilds the user section from the *redacted* layers, so any reset or row deletion would silently drop stored sibling keys; deriving a reference keeps the input single-field while keeping `settings.yaml` secret-free and every replace safe. - **A `models` bridge plugin owning provider configuration** — same rejection as in the request-level seam note: per-plugin namespaces plus a four-field directory declaration give the UI everything it needs; the bridge's unified dict re-imports the adapter-mapping indirection. - **Page-side polling instead of pushed frames** — the mux already carries `host/commands-changed`; three more frames cost one shape each and make a second tab, an external `settings.yaml` edit, and a settings-born route converge at event speed. - **Hard-coding `$DSH_HOME/settings.yaml` or returning `documentPath` through `host.openPath` in the browser** — rejected because `settings-file.path` may select another YAML/JSON document, non-file providers have no Host path, and a general path request makes the browser the authority for a local filesystem target. Provider preparation is the authoritative source, and the Host-owned operation feeds the existing opener. diff --git a/.agents/notes/implemented/architecture/2026-07-30-web-config-plane.zh.md b/.agents/notes/implemented/architecture/2026-07-30-web-config-plane.zh.md index 538a90ae10..b0724c3a8c 100644 --- a/.agents/notes/implemented/architecture/2026-07-30-web-config-plane.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-30-web-config-plane.zh.md @@ -27,9 +27,9 @@ Status: implemented ## 曾考虑的替代方案 - **在 wire 上改发 JSON Schema**——schemastery 的 `toJSON()` 信封能往返保留 `role()`/meta，并还原成客户端为草稿校验本就自带的那个校验器；转换成 JSON Schema 丢掉的恰恰是凭据控件与 secret 脱敏所依赖的角色注解。 -- **通用的 schema 驱动表单渲染器**——先实现、后被替换：如实呈现字段却缺失视觉层级，产出的卡片丑陋且不可用；要把它做好，就意味着构建一套提示词汇（主要／进阶分组、逐字段描述、数组项卡片），成本堪比手写编辑器，却仍无法与任何设计稿完全吻合。今天存在两份 schema（deepseek 的 `Config` 与共享的 pi-ai profile），手写因此就是两套以 namespace 为键的薄布局；漂移风险由保存时的 schema 校验以及未知字段在文档中的原样保留共同约束。 +- **通用的 schema 驱动表单渲染器**——先实现、后被替换：如实呈现字段却缺失视觉层级，产出的卡片丑陋且不可用；要把它做好，就意味着构建一套提示词汇（主要／进阶分组、逐字段描述、数组项卡片），成本堪比手写编辑器，却仍无法与任何设计稿完全吻合。相关的两份 schema 是 DeepSeek 的 `Config` 与共享的 pi-ai profile，手写因此就是两套以 namespace 为键的薄布局；漂移风险由保存时的 schema 校验以及未知字段在文档中的原样保留共同约束。 - **逐字段脱敏机密并在 `replace` 时回填哨兵值**——请求级 seam 的决策（机密是引用）已经为产品默认形态删掉了「存储字面量」这种情况；结构化脱敏加上只写的凭据通道足以处理残余情形，无需让每个写入方都学会一套哨兵协议。 -- **把键入的密钥存成字面 `apiKey` 设置**——v1「单个 API 密钥输入框」的需求本可以把字面量直接写进 profile，但 UI 的每条删除路径都会从*脱敏后的*各层重建用户分节，任何重置或整行删除都会静默丢掉已存储的兄弟密钥；派生引用让输入保持单字段，同时让 `settings.yaml` 不含机密、每一次 replace 都安全。 +- **把键入的密钥存成字面 `apiKey` 设置**——单个 API 密钥输入框的需求本可以把字面量直接写进 profile，但 UI 的每条删除路径都会从*脱敏后的*各层重建用户分节，任何重置或整行删除都会静默丢掉已存储的兄弟密钥；派生引用让输入保持单字段，同时让 `settings.yaml` 不含机密、每一次 replace 都安全。 - **由 `models` 桥接插件持有提供方配置**——与请求级 seam note 相同的否决理由：按插件划分的 namespace 加上四字段的目录声明已经给了 UI 需要的一切；桥接层的统一字典会把适配器映射那层间接重新引进来。 - **页面侧轮询而非推送帧**——mux 已经承载 `host/commands-changed`；再加三个帧，每个只需增加一种形状，就能让第二个标签页、外部的 `settings.yaml` 编辑和由设置催生的路由都以事件速度收敛。 - **在浏览器中硬编码 `$DSH_HOME/settings.yaml`，或经 `host.openPath` 回传 `documentPath`**——否决，因为 `settings-file.path` 可能选择另一份 YAML/JSON 文档、非文件提供方没有 Host 路径，而且通用路径请求会让浏览器成为本地文件系统目标的权威。提供方的准备操作才是权威来源，由 Host 持有的操作会把结果交给现有打开器。 diff --git a/.agents/notes/implemented/architecture/2026-07-31-code-runtime-python-fd3-protocol.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-31-code-runtime-python-fd3-protocol.i18n.yaml index 57aab42257..312c609705 100644 --- a/.agents/notes/implemented/architecture/2026-07-31-code-runtime-python-fd3-protocol.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-31-code-runtime-python-fd3-protocol.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-31-code-runtime-python-fd3-protocol.md -2026-07-31-code-runtime-python-fd3-protocol.md: 5f9600a3f658df907d68ae695d42154009947fbd -2026-07-31-code-runtime-python-fd3-protocol.zh.md: ed6b7a70ab459b8b065805ee599528a766d2873a +2026-07-31-code-runtime-python-fd3-protocol.md: 5572fe58cb1dd8832ff9405670afc7f80a20362c +2026-07-31-code-runtime-python-fd3-protocol.zh.md: 6254e94a7b48b38edfbe23a6ea0b994d04ac21f4 diff --git a/.agents/notes/implemented/architecture/2026-07-31-code-runtime-python-fd3-protocol.md b/.agents/notes/implemented/architecture/2026-07-31-code-runtime-python-fd3-protocol.md index 5f9600a3f6..5572fe58cb 100644 --- a/.agents/notes/implemented/architecture/2026-07-31-code-runtime-python-fd3-protocol.md +++ b/.agents/notes/implemented/architecture/2026-07-31-code-runtime-python-fd3-protocol.md @@ -6,21 +6,21 @@ English | [中文](2026-07-31-code-runtime-python-fd3-protocol.zh.md) ## Problem -The CPython code-runtime backend (`@deepseek-ai/dsh-code-runtime-python`, arriving across a PR stack) runs each model program in a fresh `python3 -I` subprocess and bridges binding calls and completion values over the child's fd 3. That channel needs a wire protocol both sides agree on, and the host cannot trust it: model code has full access to fd 3 and can forge any frame, so every inbound frame is hostile input the host must validate and rebuild before reading. The protocol also has to carry lossless JSON without the depth limit `JSON.stringify`/`json.dumps` impose, because the seam's `CodeJsonValue` is depth-unbounded. +`@deepseek-ai/dsh-code-runtime-python` owns the wire protocol intended for a CPython code-runtime provider. Such a provider runs each model program in a fresh `python3 -I` subprocess and bridges binding calls and completion values over the child's fd 3. The host cannot trust that channel: model code has full access to fd 3 and can forge any frame, so every inbound frame is hostile input that the host must validate and rebuild before reading. The protocol also has to carry lossless JSON without the depth limit `JSON.stringify` and `json.dumps` impose, because the seam's `CodeJsonValue` is depth-unbounded. -This layer of the stack delivers only that protocol, so the large `PythonCodeRuntime` implementation and its real-subprocess integration suite land on a reviewed wire contract instead of arriving fused with it. The parent stack splits [#436](https://github.com/deepseek-harness/deepseek-harness/pull/436) — a 9000-line single PR — into reviewable layers; this is the protocol layer, based on the [seam extension](2026-07-31-code-runtime-portable-identifier-seam.md). +The package ships the protocol independently from a runtime implementation. It exports no `PythonCodeRuntime`, subprocess path, or Python-side JSON codec; those remain work for a future provider. The protocol builds on the [portable identifier seam](2026-07-31-code-runtime-portable-identifier-seam.md). ## Decision `src/protocol.ts` is the host side of the wire vocabulary and its hostile-frame codec: - **`validateChildFrame`** shape-validates and REBUILDS every inbound frame. The compile-time union means nothing on fd 3 — a forged frame can carry `null`, poisoned fields, or omit required ones — so each accepted frame is reconstructed field by field: forged extras never ride along, a non-finite call id can never be echoed into a reply, and junk returns `undefined` to be dropped rather than throwing in the host's message handler. -- **`encodeJsonPlain` / `checkDoneValue` / `hasUnsafeIntegerToken` / `hasNonLosslessNumber`** are the lossless-JSON codec and meters. They traverse iteratively (an explicit stack, not recursion) so a deep value below the byte budget crosses intact; `checkDoneValue` folds byte-metering and number-losslessness into one walk that rejects an over-budget payload before the INCREMENTAL work it would otherwise add — the enqueued children; strings and keys are metered by a non-allocating escaped-size scan (`jsonStringBytesUpTo`), so the escaped copy is never materialized. It does not re-bound the frame's own width: `done.value` is already `JSON.parse`'d when the check runs, so the payload's size is paid upstream and capped there by the host's fixed fd-3 receive buffer (a later stack layer), not here. Beyond-safe-range integral doubles serialize through `BigInt` digits so the exact integer crosses, not `String()`'s rounded form. +- **`encodeJsonPlain` / `checkDoneValue` / `hasUnsafeIntegerToken` / `hasNonLosslessNumber`** are the lossless-JSON codec and meters. They traverse iteratively (an explicit stack, not recursion) so a deep value below the byte budget crosses intact; `checkDoneValue` folds byte-metering and number-losslessness into one walk that rejects an over-budget payload before the incremental work it would otherwise add — the enqueued children; strings and keys are metered by a non-allocating escaped-size scan (`jsonStringBytesUpTo`), so the escaped copy is never materialized. It does not re-bound the frame's own width: `done.value` is already `JSON.parse`'d when the check runs, so a consuming runtime must cap fd-3 bytes before parsing. Beyond-safe-range integral doubles serialize through `BigInt` digits so the exact integer crosses, not `String()`'s rounded form. - **`logTruncationMarker`** produces the in-band marker text a log ledger emits when it exhausts its byte budget. `py/protocol.py` mirrors the message shapes as `TypedDict`s and re-declares the two surfaces both sides EXECUTE against — `PROTOCOL_FD = 3` and `log_truncation_marker` — with byte-identical text. -The package skeleton (`package.json`, `tsconfig.json`, `tsdown.config.ts`, `src/index.ts`, `src/invariant.ts`, README triplet) ships here rather than in a later stack layer: `check-workspace-constraints` reads every `packages//` package.json unconditionally, and the coverage and invariant-topology gates require the package to exist and build the moment its directory does. The later backend-core PR extends `src/index.ts` with `PythonCodeRuntime` and grows `package.json`'s dependencies; because it bases on this branch, those are edits, not conflicts. +The package remains independently buildable with protocol-only exports. `check-workspace-constraints` reads every `packages///package.json` unconditionally, while the coverage and invariant-topology checks exercise the package as soon as its directory exists. ## Wire contract @@ -28,16 +28,16 @@ Frames are JSON-lines on fd 3, one object per line, leaving stdout/stderr free f ## Mirror alignment -Round-12 review of #436 found `py/protocol.py` stale against `src/protocol.ts` in three declarations — `LogMessage` lacked `truncated`, `DoneMessage.error` lacked `kind`, and `Namespace` lacked the optional `errorClass`. This PR aligns all three when lifting the file, so the stale mirror is not carried forward. To keep it aligned, `tests/protocol-mirror.e2e.ts` spawns a real `python3` and asserts, against `src/protocol.ts`: `PROTOCOL_FD` and `log_truncation_marker` (the two surfaces both sides execute), and each `TypedDict`'s required/optional wire field set — so a renamed or dropped field, or one side making a field optional the other requires (exactly the round-12 drift), fails the test. Field *types* are not compared across the language boundary; that residue stays with review. +`py/protocol.py` and `src/protocol.ts` agree that `LogMessage` carries `truncated`, `DoneMessage.error` carries `kind`, and `Namespace` may carry `errorClass`. `tests/protocol-mirror.e2e.ts` spawns a real `python3` and asserts `PROTOCOL_FD`, `log_truncation_marker`, and each `TypedDict`'s required and optional wire field sets against `src/protocol.ts`. A renamed or dropped field, or a required/optional mismatch, fails the test. Field *types* are not compared across the language boundary; review and a future provider's real-subprocess suite own that gap. ## Alternatives considered -**Move the Python JSON codec (`_encode_json_plain` / `_decode_json_plain`) into `py/protocol.py` for cross-side symmetry with `protocol.ts`.** Rejected. The repository's "prefer symmetry for parallel values" rule points at genuinely parallel values; these are not. The host-side codec in `protocol.ts` validates HOSTILE input and is self-contained. The Python codec produces output on the TRUSTED side and is coupled to bootstrap-internal helpers (`_Emit`, `_dump_scalar`/`_dump_string`/`_dump_float`, `LogBuffer`'s cost accounting, `_check_done_value`, `_lossless_json_violation`); lifting only the two entry points would drag that web into `protocol.py` or create a `bootstrap.py` ↔ `protocol.py` import cycle. The real cross-side parallel is "host validates inbound (`protocol.ts`) ↔ child trusts host and emits (`bootstrap.py`)", and that symmetry is preserved: `protocol.py` stays the pure wire-vocabulary mirror it is on the TS side. The Python codec stays in `bootstrap.py`, delivered by the backend-core PR. +**Require a future Python JSON codec (`_encode_json_plain` / `_decode_json_plain`) to live in `py/protocol.py` for cross-side symmetry with `protocol.ts`.** Rejected. The repository's "prefer symmetry for parallel values" rule points at genuinely parallel values; these are not. The host-side codec in `protocol.ts` validates hostile input and is self-contained. A child-side codec would produce trusted output and belong with bootstrap-owned emission and cost accounting; forcing only its entry points into `protocol.py` would couple the vocabulary mirror to runtime internals or create an import cycle. `protocol.py` remains a pure wire-vocabulary mirror. No Python codec ships in this package. -**Defer the package skeleton to the backend-core PR that "owns" package.json.** Rejected: the workspace-constraint, coverage, and invariant-topology gates fail the instant the `code-runtime-python` directory exists without a buildable package. A stacked split cannot create source files in a package that does not yet compile. +**Keep the protocol files outside a buildable package until a runtime ships.** Rejected: the workspace-constraint, coverage, and invariant-topology checks require every directory under `packages//` to be a buildable package, and the protocol has independent tests and a public wire vocabulary. ## Consequences -Bought: the fd-3 protocol and its hostile-input codec land as a self-contained, fully unit-covered layer, and the py/ts mirror drift the round-12 review found is fixed with an executing guard against its recurrence. The backend-core PR builds on a reviewed wire contract. +Bought: the fd-3 protocol and its hostile-input codec form a self-contained, fully unit-covered layer, with an executing guard against TypeScript/Python field-set drift. A future runtime can consume a reviewed wire contract. -Cost: `src/index.ts` and `package.json` are introduced minimally here and edited (not created) by the backend-core PR. The mirror e2e compares field NAMES and required/optional-ness across the two sides but not field TYPES — comparing type declarations across TypeScript and Python has no mechanical equivalent, so that residue stays with review plus the backend's real-subprocess suite. +Cost: the package name denotes a Python runtime family while `src/index.ts` exports only the protocol vocabulary. The mirror e2e compares field names and required/optional status across the two sides but not field types; comparing type declarations across TypeScript and Python has no mechanical equivalent, so review and the future runtime's real-subprocess suite retain that responsibility. diff --git a/.agents/notes/implemented/architecture/2026-07-31-code-runtime-python-fd3-protocol.zh.md b/.agents/notes/implemented/architecture/2026-07-31-code-runtime-python-fd3-protocol.zh.md index ed6b7a70ab..6254e94a7b 100644 --- a/.agents/notes/implemented/architecture/2026-07-31-code-runtime-python-fd3-protocol.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-31-code-runtime-python-fd3-protocol.zh.md @@ -6,21 +6,21 @@ Status: implemented ## Problem -CPython code-runtime 后端（`@deepseek-ai/dsh-code-runtime-python`，分多个 PR 落地）在一个全新的 `python3 -I` 子进程里运行每个模型程序，并把 binding 调用和完成值通过子进程的 fd 3 桥接。这条通道需要两侧一致的 wire protocol，而 host 不能信任它：模型代码对 fd 3 有完全访问权、可以伪造任意帧，所以每个入站帧都是 host 必须先校验并重建才能读取的敌意输入。协议还必须承载无深度限制的 lossless JSON，因为 seam 的 `CodeJsonValue` 深度无界，而 `JSON.stringify`/`json.dumps` 都有递归深度限制。 +`@deepseek-ai/dsh-code-runtime-python` 负责供 CPython code-runtime 提供方使用的 wire protocol。这样的提供方会在全新的 `python3 -I` 子进程中运行每个模型程序，并通过子进程 fd 3 桥接 binding 调用与完成值。Host 不能信任这条通道：模型代码可以完全访问 fd 3 并伪造任意帧，因此 host 必须把每个入站帧视为敌意输入，先校验并重建后才能读取。协议还必须承载无深度限制的 lossless JSON，因为 seam 的 `CodeJsonValue` 深度无界，而 `JSON.stringify` 和 `json.dumps` 都有递归深度限制。 -本层只交付这个协议，使得庞大的 `PythonCodeRuntime` 实现及其真子进程集成测试能落在一个已 review 的 wire contract 之上，而不是与它揉在一起到达。父 stack 把 [#436](https://github.com/deepseek-harness/deepseek-harness/pull/436)——一个 9000 行的单一 PR——拆成可 review 的层；本 PR 是协议层，base 是 [seam 扩展](2026-07-31-code-runtime-portable-identifier-seam.zh.md)。 +该包独立交付协议，不包含 runtime 实现。它不导出 `PythonCodeRuntime`、子进程路径或 Python 侧 JSON codec；这些属于未来提供方。协议建立在[可移植标识符 seam](2026-07-31-code-runtime-portable-identifier-seam.zh.md)之上。 ## Decision `src/protocol.ts` 是 wire vocabulary 的 host 侧及其敌意帧编解码： - **`validateChildFrame`** 对每个入站帧做形状校验并重建。编译期 union 在 fd 3 上毫无意义——伪造帧可携带 `null`、被污染的字段，或省略必需字段——所以每个被接受的帧都逐字段重建：伪造的额外字段绝不随行，非有限的 call id 绝不会被回显进 reply，垃圾返回 `undefined` 被丢弃，而不是在 host 的 message handler 里抛错。 -- **`encodeJsonPlain` / `checkDoneValue` / `hasUnsafeIntegerToken` / `hasNonLosslessNumber`** 是 lossless-JSON 编解码器与计量器。它们迭代遍历（显式栈，非递归），使低于字节预算的深层值能完整穿越；`checkDoneValue` 把字节计量和数字无损性折进一次遍历，在它本会新增的 INCREMENTAL 工作之前就拒绝超预算 payload——即入栈子节点；字符串与 key 由非分配的转义尺寸扫描（`jsonStringBytesUpTo`）计量，从不物化转义副本。它不会重新约束帧自身的宽度：`done.value` 在检查运行时已被 `JSON.parse`，故 payload 的尺寸是上游代价，由 host 固定的 fd-3 接收缓冲（后续 stack 层）在那里封顶，而非本函数。超出安全范围的整数型 double 通过 `BigInt` 数字序列化，穿越的是精确整数而非 `String()` 的舍入形式。 +- **`encodeJsonPlain` / `checkDoneValue` / `hasUnsafeIntegerToken` / `hasNonLosslessNumber`** 是 lossless-JSON 编解码器与计量器。它们迭代遍历（显式栈，非递归），使低于字节预算的深层值能完整穿越；`checkDoneValue` 把字节计量和数字无损性折进一次遍历，在新增入栈子节点之前就拒绝超预算 payload；字符串与 key 由非分配的转义尺寸扫描（`jsonStringBytesUpTo`）计量，从不物化转义副本。它不会重新约束帧自身的宽度：`done.value` 在检查运行时已经过 `JSON.parse`，因此消费 runtime 必须在解析前限制 fd-3 字节数。超出安全范围的整数型 double 通过 `BigInt` 数字序列化，穿越的是精确整数而非 `String()` 的舍入形式。 - **`logTruncationMarker`** 产出日志 ledger 耗尽字节预算时发出的带内标记文本。 `py/protocol.py` 用 `TypedDict` 镜像消息形状，并重新声明两侧都会 EXECUTE 的两个面——`PROTOCOL_FD = 3` 与 `log_truncation_marker`——文本逐字节一致。 -包骨架（`package.json`、`tsconfig.json`、`tsdown.config.ts`、`src/index.ts`、`src/invariant.ts`、README 三件套）在此交付，而非放到后续 stack 层：`check-workspace-constraints` 无条件读取每个 `packages//` 的 package.json，coverage 与 invariant-topology gate 也要求包在其目录出现的那一刻即存在且可构建。后续的 backend-core PR 会用 `PythonCodeRuntime` 扩展 `src/index.ts` 并增补 `package.json` 的依赖；因为它 base 在本分支上，那些是编辑，不是冲突。 +该包只导出协议，同时保持独立可构建。`check-workspace-constraints` 会无条件读取每个 `packages///package.json`，coverage 与 invariant-topology 检查则会在包目录存在时立即覆盖该包。 ## Wire contract @@ -28,16 +28,16 @@ CPython code-runtime 后端（`@deepseek-ai/dsh-code-runtime-python`，分多个 ## Mirror alignment -#436 的 round-12 review 发现 `py/protocol.py` 相对 `src/protocol.ts` 有三处声明陈旧——`LogMessage` 缺 `truncated`、`DoneMessage.error` 缺 `kind`、`Namespace` 缺可选的 `errorClass`。本 PR 在搬运该文件时对齐了这三处，不把陈旧镜像带过来。为持续保持对齐，`tests/protocol-mirror.e2e.ts` 启动一个真实 `python3`，对照 `src/protocol.ts` 断言：`PROTOCOL_FD` 与 `log_truncation_marker`（两侧都会执行的面），以及每个 `TypedDict` 的必填/可选 wire 字段集——于是字段被重命名或删除、或一侧把另一侧要求的字段改成可选（正是 round-12 那类漂移），测试即失败。字段的*类型*不跨语言边界比较，那部分残留留给 review。 +`py/protocol.py` 与 `src/protocol.ts` 一致规定：`LogMessage` 携带 `truncated`，`DoneMessage.error` 携带 `kind`，`Namespace` 可以携带 `errorClass`。`tests/protocol-mirror.e2e.ts` 启动真实 `python3`，对照 `src/protocol.ts` 断言 `PROTOCOL_FD`、`log_truncation_marker` 以及每个 `TypedDict` 的必填和可选 wire 字段集。字段改名、删除或必填／可选性不一致都会使测试失败。字段*类型*不跨语言边界比较；这项缺口由评审和未来提供方的真实子进程套件负责。 ## Alternatives considered -**把 Python JSON codec（`_encode_json_plain` / `_decode_json_plain`）挪进 `py/protocol.py` 以与 `protocol.ts` 跨侧对称。** 拒绝。仓库的 “prefer symmetry for parallel values” 规则指向真正平行的值；这两者不是。`protocol.ts` 里的 host 侧 codec 校验的是敌意输入，自包含。Python codec 在受信任侧产出输出，且耦合于 bootstrap 内部 helper（`_Emit`、`_dump_scalar`/`_dump_string`/`_dump_float`、`LogBuffer` 的成本核算、`_check_done_value`、`_lossless_json_violation`）；只把两个入口挪过去会把这一整片拖进 `protocol.py`，或制造 `bootstrap.py` ↔ `protocol.py` 的 import 环。真正的跨侧平行是 “host 校验入站（`protocol.ts`） ↔ child 信任 host 并发出（`bootstrap.py`）”，这个对称性被保留：`protocol.py` 保持它在 TS 侧一样的纯 wire-vocabulary 镜像定位。Python codec 留在 `bootstrap.py`，由 backend-core PR 交付。 +**要求未来的 Python JSON codec（`_encode_json_plain` / `_decode_json_plain`）放进 `py/protocol.py`，以便与 `protocol.ts` 跨侧对称。**拒绝。仓库的 “prefer symmetry for parallel values” 规则指向真正平行的值；这两者不是。`protocol.ts` 中的 host 侧 codec 校验敌意输入且自包含。Child 侧 codec 会产出受信任输出，应与 bootstrap 拥有的发出逻辑和成本核算放在一起；只把入口强塞进 `protocol.py` 会让 vocabulary 镜像耦合 runtime 内部实现，或制造 import 环。`protocol.py` 保持纯 wire-vocabulary 镜像。本包尚未交付 Python codec。 -**把包骨架推迟到“拥有” package.json 的 backend-core PR。** 拒绝：workspace-constraint、coverage、invariant-topology gate 会在 `code-runtime-python` 目录一存在而包不可构建时立即失败。stacked 拆分无法在一个尚不能编译的包里创建源文件。 +**在 runtime 交付前把协议文件放在不可构建的包外。**拒绝：workspace-constraint、coverage 与 invariant-topology 检查要求 `packages//` 下的每个目录都是可构建包，而协议本身拥有独立测试与公开 wire vocabulary。 ## Consequences -收获：fd-3 协议及其敌意输入 codec 作为自包含、unit 全覆盖的一层落地，round-12 review 发现的 py/ts 镜像漂移被修复，并有一个执行中的 guard 防其复发。backend-core PR 建立在已 review 的 wire contract 之上。 +收获：fd-3 协议及其敌意输入 codec 构成自包含、unit 全覆盖的一层，并由执行中的 guard 防止 TypeScript／Python 字段集漂移。未来 runtime 可以直接消费经过评审的 wire contract。 -代价：`src/index.ts` 与 `package.json` 在此以最小形态引入，并由 backend-core PR 编辑（而非创建）。mirror e2e 比较两侧的字段名与必填/可选性，但不比较字段类型——跨 TypeScript 与 Python 比较类型声明无机械等价物，那部分残留留给 review 加后端真子进程套件。 +代价：包名表示 Python runtime 家族，而 `src/index.ts` 只导出协议 vocabulary。mirror e2e 会比较两侧字段名与必填／可选状态，但不比较字段类型；跨 TypeScript 与 Python 比较类型声明没有机械等价物，因此评审与未来 runtime 的真实子进程套件继续负责这项检查。 diff --git a/.agents/notes/implemented/architecture/2026-08-02-typert-remote-method-calls.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-02-typert-remote-method-calls.i18n.yaml index 918857d1f5..53bfd94dd7 100644 --- a/.agents/notes/implemented/architecture/2026-08-02-typert-remote-method-calls.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-02-typert-remote-method-calls.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-02-typert-remote-method-calls.md -2026-08-02-typert-remote-method-calls.md: 645eaf94dc734c674d526d26a33731faded7071c -2026-08-02-typert-remote-method-calls.zh.md: 4fbc4cc64d8c266f02c27f339d7324251e091c9f +2026-08-02-typert-remote-method-calls.md: b95e3f0dec56287cbec2586921477284d0489a40 +2026-08-02-typert-remote-method-calls.zh.md: 50f04fd44a06ae3914998f0337fef09c75fe707c diff --git a/.agents/notes/implemented/architecture/2026-08-02-typert-remote-method-calls.md b/.agents/notes/implemented/architecture/2026-08-02-typert-remote-method-calls.md index 645eaf94dc..b95e3f0dec 100644 --- a/.agents/notes/implemented/architecture/2026-08-02-typert-remote-method-calls.md +++ b/.agents/notes/implemented/architecture/2026-08-02-typert-remote-method-calls.md @@ -154,10 +154,10 @@ Descriptors exist only in the local registry on each side. The wire carries only ## Typert runtime registry ```text -ctx.typert.local 当前进程自己的 Host 或 Client reflection -ctx.typert.remotes 消费端显式 mount 的对端 Remote contribution -ctx.typert.lookups wire ID 到 Host 对象的 provider 与组合策略 -ctx.typert.contexts Host Context resolver 与 Client Context binder +ctx.typert.local Host or Client reflection for this process +ctx.typert.remotes peer Remote contributions explicitly mounted by a consumer +ctx.typert.lookups providers and composition policy from wire IDs to Host objects +ctx.typert.contexts Host Context resolvers and Client Context binders ``` Every registration returns a disposer owned by the caller's Cordis fiber. Client contribution mounting registers the descriptor set and concrete methods as one owned operation. The Host Gateway caches only the set of SRC-owned endpoint names and discards it whenever the Cordis Service set changes; it retains no descriptor, Service, or provider. Invocation resolves all live objects from current state, so removing a strict definition, Service, or provider makes the corresponding call unavailable without leaving a stale live object. diff --git a/.agents/notes/implemented/architecture/2026-08-02-typert-remote-method-calls.zh.md b/.agents/notes/implemented/architecture/2026-08-02-typert-remote-method-calls.zh.md index 4fbc4cc64d..50f04fd44a 100644 --- a/.agents/notes/implemented/architecture/2026-08-02-typert-remote-method-calls.zh.md +++ b/.agents/notes/implemented/architecture/2026-08-02-typert-remote-method-calls.zh.md @@ -154,10 +154,10 @@ descriptor 只存在于两端本地 registry。wire 上只有 `/api` channel、e ## Typert 运行时 registry ```text -ctx.typert.local 当前进程自己的 Host 或 Client reflection -ctx.typert.remotes 消费端显式 mount 的对端 Remote contribution -ctx.typert.lookups wire ID 到 Host 对象的 provider 与组合策略 -ctx.typert.contexts Host Context resolver 与 Client Context binder +ctx.typert.local Host or Client reflection for this process +ctx.typert.remotes peer Remote contributions explicitly mounted by a consumer +ctx.typert.lookups providers and composition policy from wire IDs to Host objects +ctx.typert.contexts Host Context resolvers and Client Context binders ``` 每次注册都返回由调用方 Cordis fiber 持有的 disposer。挂载 Client contribution 时，descriptor 集与具体方法会作为一项有明确所有者的操作统一注册。Host Gateway 只缓存 SRC 所认领的 endpoint 名称集合，并在 Cordis Service 集合发生变化时整体丢弃该集合；它不保留 descriptor、Service 或提供方。调用时会从当前状态解析所有活对象，因此移除 strict definition、Service 或提供方会使相应调用不可用，且不会留下陈旧的活对象。 diff --git a/.agents/notes/implemented/architecture/2026-08-03-per-session-agent-presets.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-03-per-session-agent-presets.i18n.yaml index 6d956d86ec..81d921b96c 100644 --- a/.agents/notes/implemented/architecture/2026-08-03-per-session-agent-presets.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-03-per-session-agent-presets.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-03-per-session-agent-presets.md -2026-08-03-per-session-agent-presets.md: 5a82f0220058c10892b819a83499c817aa9be6ad -2026-08-03-per-session-agent-presets.zh.md: 0adcfec8b2c39a1f97d74edfa784f45062b52a99 +2026-08-03-per-session-agent-presets.md: 9999d0125de87c43a8aa3b6b6b7c9bc90a81da77 +2026-08-03-per-session-agent-presets.zh.md: 514f2d40c95b608cb8512fd27a56ddba222d3173 diff --git a/.agents/notes/implemented/architecture/2026-08-03-per-session-agent-presets.md b/.agents/notes/implemented/architecture/2026-08-03-per-session-agent-presets.md index 5a82f02200..9999d0125d 100644 --- a/.agents/notes/implemented/architecture/2026-08-03-per-session-agent-presets.md +++ b/.agents/notes/implemented/architecture/2026-08-03-per-session-agent-presets.md @@ -31,7 +31,7 @@ Which preset an unnamed session gets is a user setting (`agent-presets.default`) ## Consequences -**The effective default is read per resolution, never snapshotted.** A cached value would need a `watch` subscription and a reload path to stay honest, and the resolved scope already re-reads a hot-reloaded document. Reading through is also what makes the boundary correct rather than merely cheap: the new value applies to the next session created, and every running session keeps the composition it was built from. That invariant is the same one the session log enforces from the other side — the header records the id a session was CREATED with and an `agent-preset/selected` event records any later blank-session switch, so a reader resolves the pair (`resolveSessionPreset`) and never the header alone: a resume rebuilds the composition its history was produced under rather than today's default, a cold transcript's presenters resolve in that composition's layer, and the gateway rejects an attempt to adopt a live session under a preset other than the one it currently runs. A snapshot would make the two disagree at exactly the moment the setting changes. +**The effective default is read per resolution, never snapshotted.** A cached value would need a `watch` subscription and a reload path to stay honest, and the resolved scope already re-reads a hot-reloaded document. Reading through is also what makes the boundary correct rather than merely cheap: the new value applies to the next session created, and every running session keeps the composition it was built from. That invariant is the same one the session log enforces from the other side — the header records the id a session was CREATED with and an `agent-preset/selected` event records any later blank-session switch, so a reader resolves the pair (`resolveSessionPreset`) and never the header alone: a resume rebuilds the composition its history was produced under rather than the deployment default at resume time, a cold transcript's presenters resolve in that composition's layer, and the gateway rejects an attempt to adopt a live session under a preset other than the one it currently runs. A snapshot would make the two disagree at exactly the moment the setting changes. **A directly-plugged subtree is invisible to the boot audit.** It never links itself to an `Entry`, so it is absent from `ctx.loader.entries()` and `assertEntriesActivated` cannot see it. The mount audits its own rows instead, reading the tree through an `Include` subclass that publishes it. diff --git a/.agents/notes/implemented/architecture/2026-08-03-per-session-agent-presets.zh.md b/.agents/notes/implemented/architecture/2026-08-03-per-session-agent-presets.zh.md index 0adcfec8b2..514f2d40c9 100644 --- a/.agents/notes/implemented/architecture/2026-08-03-per-session-agent-presets.zh.md +++ b/.agents/notes/implemented/architecture/2026-08-03-per-session-agent-presets.zh.md @@ -31,7 +31,7 @@ Status: implemented ## 后果 -**有效默认值在每次解析时读取，绝不保存快照。** 缓存下来就需要一个 `watch` 订阅和一条重载路径才能保持诚实，而解析后的 scope 本来就会重读热重载过的文档。读穿也不只是省事，它让边界本身是对的：新值作用于**下一个新建的会话**，每个运行中的会话保持它被构建时的那份组装。这条不变量正是 session 日志从另一侧执行的同一条——header 记录会话**创建时**的 id，此后空白期的任何切换由 `agent-preset/selected` 事件记录，因此读取方解析的是两者之和（`resolveSessionPreset`）、绝不单看 header：恢复重建的是其历史所产出的那份组装而不是当下的默认值，冷读记录的 presenter 在那份组装的层里解析，网关也会拒绝把一个活着的会话收编到它当前运行的 preset 以外的 preset 之下。快照会让两者恰好在设置改变的那一刻各说各话。 +**有效默认值在每次解析时读取，绝不保存快照。** 缓存下来就需要一个 `watch` 订阅和一条重载路径才能保持诚实，而解析后的 scope 本来就会重读热重载过的文档。读穿也不只是省事，它让边界本身是对的：新值作用于**下一个新建的会话**，每个运行中的会话保持它被构建时的那份组装。这条不变量正是 session 日志从另一侧执行的同一条——header 记录会话**创建时**的 id，此后空白期的任何切换由 `agent-preset/selected` 事件记录，因此读取方解析的是两者之和（`resolveSessionPreset`）、绝不单看 header：恢复重建的是其历史所产出的那份组装而不是恢复时的部署默认值，冷读记录的 presenter 在那份组装的层里解析，网关也会拒绝把一个活着的会话收编到它当前运行的 preset 以外的 preset 之下。快照会让两者恰好在设置改变的那一刻各说各话。 **直接挂载的子树对启动审计不可见。** 它不会把自己关联到 `Entry`，因此不在 `ctx.loader.entries()` 中，`assertEntriesActivated` 也看不到它。改由挂载过程自行校验各行，通过一个会公开自身 tree 的 `Include` 子类读取。 diff --git a/.agents/notes/implemented/architecture/2026-08-04-configuration-source-ownership.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-04-configuration-source-ownership.i18n.yaml index aaed5ddc6b..7f9dcea635 100644 --- a/.agents/notes/implemented/architecture/2026-08-04-configuration-source-ownership.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-04-configuration-source-ownership.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-04-configuration-source-ownership.md -2026-08-04-configuration-source-ownership.md: 2cd09ae2daca2b15657caa18ff210fa178c2999b -2026-08-04-configuration-source-ownership.zh.md: fc47c3e47dc8d5d9ae763ddb5fe932a80e72c3d1 +2026-08-04-configuration-source-ownership.md: 1fe5908ab77632732996bd1d5c1eed9c8ab048e6 +2026-08-04-configuration-source-ownership.zh.md: 197cb936cdff303e23425d008c7a2cb738500ae0 diff --git a/.agents/notes/implemented/architecture/2026-08-04-configuration-source-ownership.md b/.agents/notes/implemented/architecture/2026-08-04-configuration-source-ownership.md index 2cd09ae2da..1fe5908ab7 100644 --- a/.agents/notes/implemented/architecture/2026-08-04-configuration-source-ownership.md +++ b/.agents/notes/implemented/architecture/2026-08-04-configuration-source-ownership.md @@ -40,7 +40,7 @@ inherited process environment (read-only, wins) The launching environment wins because `DEEPSEEK_API_KEY=… dsh`, a CI secret, and a container `-e` are the one override an operator must be able to apply per run without editing machine state, and because it cannot be edited from inside it must be *visibly* read-only. Configuration is meant to carry only the *reference* — which name to resolve — and that name follows the non-secret ordering above. -**The project the harness is launched in is trusted, by default and without a prompt.** A checkout may carry its own endpoint, its own ordinary variables, and its own key; the key ranks below the managed store, so a key stored through the Models page is never displaced by one a checkout happens to contain. `LaunchEnvironmentSnapshot.getFrom(name, sources)` still searches only the layers a caller names, and omitting one is a refusal rather than a demotion — the mechanism exists for the decisions where a layer must be unreachable, not because the project is one of them today. +**The project the harness is launched in is trusted, by default and without a prompt.** A checkout may carry its own endpoint, its own ordinary variables, and its own key; the key ranks below the managed store, so a key stored through the Models page is never displaced by one a checkout happens to contain. `LaunchEnvironmentSnapshot.getFrom(name, sources)` still searches only the layers a caller names, and omitting one is a refusal rather than a demotion — the mechanism exists for decisions where a layer must be unreachable; this decision includes the project layer. **Trust does not extend to changing the harness itself.** `loadLayeredEnv` rejects, at load and before anything is materialized, any `.env` that sets a variable governing how a process launches (`PATH`, `SHELL`, `NODE_OPTIONS`, `LD_PRELOAD`), which ambient program handles an operation (`EDITOR`, `PAGER`, `BROWSER`), what code a runtime executes before the program it was asked to run (`BASH_ENV`, `PERL5OPT`, `PYTHONSTARTUP`, `RUBYOPT`, `JAVA_TOOL_OPTIONS`, the Git hook commands), where model-visible instructions load from (the whole `DSH_*` namespace, `HOME`, `XDG_*`), or how the network is reached and trusted (proxy and CA variables). Matching is case-insensitive, so `https_proxy` is not a bypass. diff --git a/.agents/notes/implemented/architecture/2026-08-04-configuration-source-ownership.zh.md b/.agents/notes/implemented/architecture/2026-08-04-configuration-source-ownership.zh.md index fc47c3e47d..197cb936cd 100644 --- a/.agents/notes/implemented/architecture/2026-08-04-configuration-source-ownership.zh.md +++ b/.agents/notes/implemented/architecture/2026-08-04-configuration-source-ownership.zh.md @@ -41,7 +41,7 @@ inherited process environment (read-only, wins) 继承环境优先，因为 `DEEPSEEK_API_KEY=… dsh`、CI 机密与容器 `-e` 是运维必须能按次施加、且无需改动机器状态的那一种覆盖；而它无法从进程内部修改，就必须*可见地*只读。配置本应只携带*引用*——解析哪个名字——该名字本身遵循上面的非机密顺序。 -**harness 被启动于其中的项目默认可信，且不做询问。** 一个 checkout 可以携带自己的 endpoint、自己的普通变量和自己的密钥；密钥排在受管存储之下，因此通过 Models 页存下的密钥绝不会被 checkout 中恰好带有的那一个顶掉。`LaunchEnvironmentSnapshot.getFrom(name, sources)` 仍然只搜索调用方点名的层，省略某层仍是拒绝而不是降级——该机制是为「某一层必须不可达」的那些决策准备的，而项目层今天不在其列。 +**harness 被启动于其中的项目默认可信，且不做询问。** 一个 checkout 可以携带自己的 endpoint、自己的普通变量和自己的密钥；密钥排在受管存储之下，因此通过 Models 页存下的密钥绝不会被 checkout 中恰好带有的那一个顶掉。`LaunchEnvironmentSnapshot.getFrom(name, sources)` 仍然只搜索调用方点名的层，省略某层仍是拒绝而不是降级——该机制供要求某一层不可达的决策使用；本决策包含项目层。 **信任不延伸到改变 harness 本身。** `loadLayeredEnv` 会在加载时、且在物化任何内容之前，拒绝任何设置了下列变量的 `.env`：决定进程如何启动的（`PATH`、`SHELL`、`NODE_OPTIONS`、`LD_PRELOAD`）、决定由哪个环境程序处理一项操作的（`EDITOR`、`PAGER`、`BROWSER`）、决定运行时在执行被要求运行的程序之前先执行哪些代码的（`BASH_ENV`、`PERL5OPT`、`PYTHONSTARTUP`、`RUBYOPT`、`JAVA_TOOL_OPTIONS`、Git 的钩子命令）、决定模型可见指令从哪里加载的（整个 `DSH_*` 命名空间、`HOME`、`XDG_*`），以及决定网络如何访问以及如何建立信任的（proxy 与 CA 变量）。匹配不区分大小写，因此 `https_proxy` 不是绕过手段。 diff --git a/.agents/notes/implemented/architecture/2026-08-06-web-shell-dist-chunk-layout.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-06-web-shell-dist-chunk-layout.i18n.yaml index 3b80f87a89..81249420ff 100644 --- a/.agents/notes/implemented/architecture/2026-08-06-web-shell-dist-chunk-layout.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-06-web-shell-dist-chunk-layout.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-06-web-shell-dist-chunk-layout.md -2026-08-06-web-shell-dist-chunk-layout.md: 1c7b4273dc243685317b149e2fd7fddf2a6c18d1 -2026-08-06-web-shell-dist-chunk-layout.zh.md: d1435215d3c077efc3afaac7b3a7a1c2e2ffdae7 +2026-08-06-web-shell-dist-chunk-layout.md: 5407188dab4aaebb1032b49af33731d1cbdbc6e5 +2026-08-06-web-shell-dist-chunk-layout.zh.md: 15dcc7775f05916884ed704d4c1eace9df8eaaa5 diff --git a/.agents/notes/implemented/architecture/2026-08-06-web-shell-dist-chunk-layout.md b/.agents/notes/implemented/architecture/2026-08-06-web-shell-dist-chunk-layout.md index 1c7b4273dc..5407188dab 100644 --- a/.agents/notes/implemented/architecture/2026-08-06-web-shell-dist-chunk-layout.md +++ b/.agents/notes/implemented/architecture/2026-08-06-web-shell-dist-chunk-layout.md @@ -24,7 +24,7 @@ The apps/web shell previously built into a single ~1.2 MB (minified) index chunk - The `assets/` root keeps only the index and vendor js (with their adjacent sourcemaps) and css. - Grammar chunks go under `assets/langs/`. The criterion is whether a chunk's `moduleIds` include an `@shikijs/langs` member, not the facade: the shared chunks of embedded grammars (php/ruby/mdx embed html+javascript, which rollup splits out for sharing) **have no facade**, so a facade criterion would miss them; index and vendor are excluded by name, because vendor legitimately carries the three boot grammars. -- Fonts go under `assets/fonts/` (`FONT_EXTENSIONS`: woff2/woff/ttf; today all of them are KaTeX faces referenced by vendor.css — katex.min.css is imported by an index-side component, but CSS modules go through manualChunks like any module and follow `katex` into vendor.css; the browser fetches only woff2, on demand and only when a formula renders). +- Fonts go under `assets/fonts/` (`FONT_EXTENSIONS`: woff2/woff/ttf; all shipped files are KaTeX faces referenced by vendor.css — katex.min.css is imported by an index-side component, but CSS modules go through manualChunks like any module and follow `katex` into vendor.css; the browser fetches only woff2, on demand and only when a formula renders). - Sourcemaps need no arrangement: rollup writes each `.map` next to its js and references it by bare relative filename, so when a chunk moves directories its map follows automatically. All cross-directory references (index's dynamic imports into `langs/`, same-directory relative references among grammar chunks, vendor.css's relative references into `fonts/`) are emitted by the bundler, so the runtime needs zero accompanying changes; the host-side webserver serves the nested paths verbatim under its static prefix. diff --git a/.agents/notes/implemented/architecture/2026-08-06-web-shell-dist-chunk-layout.zh.md b/.agents/notes/implemented/architecture/2026-08-06-web-shell-dist-chunk-layout.zh.md index d1435215d3..15dcc7775f 100644 --- a/.agents/notes/implemented/architecture/2026-08-06-web-shell-dist-chunk-layout.zh.md +++ b/.agents/notes/implemented/architecture/2026-08-06-web-shell-dist-chunk-layout.zh.md @@ -24,7 +24,7 @@ apps/web 的壳此前打成单一约 1.2 MB（minified）的 index 分片，其 - `assets/` 根只留 index 与 vendor 的 js（含随行 sourcemap）与 css。 - 语法 chunk 归 `assets/langs/`。判据是 chunk 的 `moduleIds` 含 `@shikijs/langs` 成员，而非 facade：内嵌语法共享 chunk（php/ruby/mdx 内嵌 html+javascript，被 rollup 拆出共享）**没有 facade**，facade 判据会漏；index/vendor 按名排除，因 vendor 合法携带 boot 三语法。 -- 字体归 `assets/fonts/`（`FONT_EXTENSIONS`：woff2/woff/ttf；今日全部为 vendor.css 引用的 KaTeX 字体面——katex.min.css 虽由 index 侧组件 import，css 模块同样经 manualChunks 归属、随 `katex` 落入 vendor.css；浏览器按需只拉 woff2，且仅在公式渲染时）。 +- 字体归 `assets/fonts/`（`FONT_EXTENSIONS`：woff2/woff/ttf；所有已交付文件都是 vendor.css 引用的 KaTeX 字体面——katex.min.css 虽由 index 侧组件 import，css 模块同样经 manualChunks 归属、随 `katex` 落入 vendor.css；浏览器按需只拉 woff2，且仅在公式渲染时）。 - sourcemap 无需安排：rollup 把 `.map` 写在各自 js 旁并以裸相对文件名引用，分片挪目录时 map 自动跟随。 跨目录引用（index 的动态 import 指向 `langs/`、语法 chunk 间同目录相对引用、vendor.css 相对引用 `fonts/`）均由构建器生成，运行时零配套改动；host 侧 webserver 按静态前缀原样服务嵌套路径。 diff --git a/.agents/notes/implemented/architecture/2026-08-09-cordis-event-walk-backstop.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-09-cordis-event-walk-backstop.i18n.yaml index a5189293df..cc9768eeac 100644 --- a/.agents/notes/implemented/architecture/2026-08-09-cordis-event-walk-backstop.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-09-cordis-event-walk-backstop.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-09-cordis-event-walk-backstop.md -2026-08-09-cordis-event-walk-backstop.md: c031b7c444a4d9bdfb0792523ba50e297f53b56a -2026-08-09-cordis-event-walk-backstop.zh.md: 316a79d774491b723c85ed65402d724e169ca66f +2026-08-09-cordis-event-walk-backstop.md: 5a85c5df2705c69f7a045e04a32345149135c427 +2026-08-09-cordis-event-walk-backstop.zh.md: 17660d90bd60c770b63eec95c42b0aeacf269d43 diff --git a/.agents/notes/implemented/architecture/2026-08-09-cordis-event-walk-backstop.md b/.agents/notes/implemented/architecture/2026-08-09-cordis-event-walk-backstop.md index c031b7c444..5a85c5df27 100644 --- a/.agents/notes/implemented/architecture/2026-08-09-cordis-event-walk-backstop.md +++ b/.agents/notes/implemented/architecture/2026-08-09-cordis-event-walk-backstop.md @@ -24,7 +24,7 @@ The audit that motivated this found the host face already complete: 48 rendered ## Verification -`scripts/gen-cordis-catalog-partition.spec.ts` proves each acceptance path: the green partition, an invisible unexempted event (named with its declaring file), a stale rendered-event exemption, a stale never-declared exemption, the service mirror of each, unmapped rendered surface in both page maps, rendered surface the scan cannot see (the third direction), and the scan reaching nested Events-only merges, every block of a multi-block file, double-quoted heads, and `.tsx` sources. Deleting one live exemption from the real tree makes `gen-cordis-catalog` fail loud with the event's name and declaring file; restoring it returns the generator to a byte-identical no-op regeneration (85 artifacts, 0 written), which also proves the new exemptions exactly cover today's surface. `verify-cordis-catalog` in doc-sync executes the partition on every run. +`scripts/gen-cordis-catalog-partition.spec.ts` proves each acceptance path: the green partition, an invisible unexempted event (named with its declaring file), a stale rendered-event exemption, a stale never-declared exemption, the service mirror of each, unmapped rendered surface in both page maps, rendered surface the scan cannot see (the third direction), and the scan reaching nested Events-only merges, every block of a multi-block file, double-quoted heads, and `.tsx` sources. Deleting one live exemption from the real tree makes `gen-cordis-catalog` fail loud with the event's name and declaring file; restoring it returns the generator to a byte-identical no-op regeneration (85 artifacts, 0 written), which also proves the new exemptions exactly cover the scanned surface. `verify-cordis-catalog` in doc-sync executes the partition on every run. ## Alternatives considered diff --git a/.agents/notes/implemented/architecture/2026-08-09-cordis-event-walk-backstop.zh.md b/.agents/notes/implemented/architecture/2026-08-09-cordis-event-walk-backstop.zh.md index 316a79d774..17660d90bd 100644 --- a/.agents/notes/implemented/architecture/2026-08-09-cordis-event-walk-backstop.zh.md +++ b/.agents/notes/implemented/architecture/2026-08-09-cordis-event-walk-backstop.zh.md @@ -24,7 +24,7 @@ Status: implemented ## 验证 -`scripts/gen-cordis-catalog-partition.spec.ts` 证明每条验收路径：绿色分区、不可见且未豁免的事件（报出声明文件）、已渲染事件的陈旧豁免、从未声明的陈旧豁免、服务侧的对称路径、两个页面映射中未映射的已渲染表面、扫描看不到的已渲染表面（第三方向），以及扫描触达嵌套的仅含 Events 的 merge、多块文件的每个块、双引号头部与 `.tsx` 源文件。在真实源码树上删除一条现役豁免会让 `gen-cordis-catalog` 以事件名与声明文件显式报错；恢复后生成器回到字节相同的 no-op 再生成（85 个产物，写入 0 个），这同时证明新豁免恰好覆盖当下表面。doc-sync 中的 `verify-cordis-catalog` 每次运行都会执行该分区检查。 +`scripts/gen-cordis-catalog-partition.spec.ts` 证明每条验收路径：绿色分区、不可见且未豁免的事件（报出声明文件）、已渲染事件的陈旧豁免、从未声明的陈旧豁免、服务侧的对称路径、两个页面映射中未映射的已渲染表面、扫描看不到的已渲染表面（第三方向），以及扫描触达嵌套的仅含 Events 的 merge、多块文件的每个块、双引号头部与 `.tsx` 源文件。在真实源码树上删除一条现役豁免会让 `gen-cordis-catalog` 以事件名与声明文件显式报错；恢复后生成器回到字节相同的 no-op 再生成（85 个产物，写入 0 个），这同时证明新豁免恰好覆盖扫描到的表面。doc-sync 中的 `verify-cordis-catalog` 每次运行都会执行该分区检查。 ## 考虑过的替代方案 diff --git a/.agents/notes/implemented/architecture/2026-08-10-host-plane-ownership-after-presets.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-10-host-plane-ownership-after-presets.i18n.yaml index cb8b03e051..79ed44e6a0 100644 --- a/.agents/notes/implemented/architecture/2026-08-10-host-plane-ownership-after-presets.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-10-host-plane-ownership-after-presets.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-10-host-plane-ownership-after-presets.md -2026-08-10-host-plane-ownership-after-presets.md: f6a2604cdd8be59296fada148f47dea7503356a7 -2026-08-10-host-plane-ownership-after-presets.zh.md: 6e9b078c9cc46b1167b9fa92c9d8222ecc492530 +2026-08-10-host-plane-ownership-after-presets.md: 78410368cdc66b14fe478a4de9f0ae7a1cbefac5 +2026-08-10-host-plane-ownership-after-presets.zh.md: 862b793fab23b209f6f43b2e8045ad7330c30ba0 diff --git a/.agents/notes/implemented/architecture/2026-08-10-host-plane-ownership-after-presets.md b/.agents/notes/implemented/architecture/2026-08-10-host-plane-ownership-after-presets.md index f6a2604cdd..78410368cd 100644 --- a/.agents/notes/implemented/architecture/2026-08-10-host-plane-ownership-after-presets.md +++ b/.agents/notes/implemented/architecture/2026-08-10-host-plane-ownership-after-presets.md @@ -32,7 +32,7 @@ Three limits stay open and are recorded where they bite rather than fixed here: **Keep the meter in the preset and scope-layer the projection registry.** The precise fix, and much larger: `snapshot`, `checkpoint`, and the eager drive would each need a session→scope resolution that a cold read does not have without the api-proxy's `presenterScopeFor`. Rejected as disproportionate to one Service with no per-preset state at all; the general rule is documented on the registry instead. -**Veto publication for an unjoined agent.** Loud beats silent, and the registry supports it — a synchronous `agent/created` listener that throws rolls the creation back. Rejected because composing an agent outside the roster is legal: `recompose` documents the bare agent it then binds, and the ACP bridge, the SDK server, and the headless bundle all create one today. A veto would convert a capability gap into an outage. +**Veto publication for an unjoined agent.** Loud beats silent, and the registry supports it — a synchronous `agent/created` listener that throws rolls the creation back. Rejected because composing an agent outside the roster is legal: `recompose` documents the bare agent it then binds, and the ACP bridge, the SDK server, and the headless bundle all create one. A veto would convert a capability gap into an outage. **Check the join at `agent/created` in the companion too.** Rejected: publication cannot distinguish a missed join from an agent that will be bound later, so the check would reject a documented path. Prompt assembly can distinguish them. diff --git a/.agents/notes/implemented/architecture/2026-08-10-host-plane-ownership-after-presets.zh.md b/.agents/notes/implemented/architecture/2026-08-10-host-plane-ownership-after-presets.zh.md index 6e9b078c9c..862b793fab 100644 --- a/.agents/notes/implemented/architecture/2026-08-10-host-plane-ownership-after-presets.zh.md +++ b/.agents/notes/implemented/architecture/2026-08-10-host-plane-ownership-after-presets.zh.md @@ -32,7 +32,7 @@ Status: implemented **把 meter 留在 preset，改为给投影注册表分层。** 这是更精确的修法，代价也大得多：`snapshot`、`checkpoint` 与主动驱动都需要一次「会话 → 作用域」的解析，而冷读在没有 api-proxy 的 `presenterScopeFor` 时并不具备。相对于一个完全没有 per-preset 状态的 Service，这不成比例，因此改为把通则写在注册表上。 -**对未加入的 agent 否决发布。** 大声胜过静默，注册表也支持这么做——同步的 `agent/created` 监听器抛出会把创建整体回滚。否决的理由是：在名单之外组装 agent 是合法的——`recompose` 写明了它随后绑定的那个裸 agent，而 ACP 桥、SDK server 与 headless bundle 今天都会创建一个。否决会把能力缺口变成一次故障。 +**对未加入的 agent 否决发布。** 大声胜过静默，注册表也支持这么做——同步的 `agent/created` 监听器抛出会把创建整体回滚。否决的理由是：在名单之外组装 agent 是合法的——`recompose` 写明了它随后绑定的那个裸 agent，而 ACP 桥、SDK server 与 headless bundle 都会创建一个。否决会把能力缺口变成一次故障。 **让配套也在 `agent/created` 处检查加入情况。** 否决：发布时分不清漏掉的加入与之后才会被绑定的 agent，因此该检查会拒绝一条已写明的路径。提示词组装分得清。 diff --git a/.agents/notes/implemented/architecture/2026-08-10-remote-event-delivery.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-10-remote-event-delivery.i18n.yaml index f068885f5a..e1b8afe3d3 100644 --- a/.agents/notes/implemented/architecture/2026-08-10-remote-event-delivery.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-10-remote-event-delivery.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-10-remote-event-delivery.md -2026-08-10-remote-event-delivery.md: ee3d9884b53f5fa5d0b0072660888c5f4d283b1b -2026-08-10-remote-event-delivery.zh.md: 01777bd8818d72cfc9650b9d35bc5ae5ee82d880 +2026-08-10-remote-event-delivery.md: c0bc459eb5f96dccd135417c0d5d4d2f743aad5e +2026-08-10-remote-event-delivery.zh.md: 08e3570708c20223697a186ee79e16f5ac3bda8b diff --git a/.agents/notes/implemented/architecture/2026-08-10-remote-event-delivery.md b/.agents/notes/implemented/architecture/2026-08-10-remote-event-delivery.md index ee3d9884b5..c0bc459eb5 100644 --- a/.agents/notes/implemented/architecture/2026-08-10-remote-event-delivery.md +++ b/.agents/notes/implemented/architecture/2026-08-10-remote-event-delivery.md @@ -26,7 +26,7 @@ When an `Events` entry's signature reaches a Host-only symbol (a Service, `Agent All five events ride this path, and their dedicated `HostFrame` variants or Client aliases are gone. Model consumers subscribe directly to both owner inputs, `llm/adapters-updated` and `settings/document-updated`; preset-derived consumers subscribe to `agent-preset/selected`. Frames that actually project or deduplicate data stay dedicated: `host/workspace-changed`/`-removed`/`host/archived-sessions-changed` (view derivation plus per-connection dedup state), and `host/session-added`/`-removed`/`host/session-status`/`host/agent-error` (live-object projection or frame-time derived fields). -`skills/change`, `tools/change`, and `system-prompt/change` have the same shape but **no consumer today**; under "require a current owner and need" they stay out of the allowlist and are recorded here only as the extension seat. +`skills/change`, `tools/change`, and `system-prompt/change` have the same shape but **no shipped consumer**; under "require a current owner and need" they stay out of the allowlist and are recorded here only as the extension seat. ### Consumer contract (dsh-typert-protocol) diff --git a/.agents/notes/implemented/architecture/2026-08-10-remote-event-delivery.zh.md b/.agents/notes/implemented/architecture/2026-08-10-remote-event-delivery.zh.md index 01777bd881..08e3570708 100644 --- a/.agents/notes/implemented/architecture/2026-08-10-remote-event-delivery.zh.md +++ b/.agents/notes/implemented/architecture/2026-08-10-remote-event-delivery.zh.md @@ -26,7 +26,7 @@ Host 拥有 `agent-preset/selected`、`commands/change`、`credentials/reference 五条事件全部走这条路径，专用帧与 Client 别名都已删除。模型消费方直接订阅 `llm/adapters-updated` 和 `settings/document-updated`；preset 消费方订阅 `agent-preset/selected`。真正需要投影或去重的数据仍保留专用帧。 -`skills/change`、`tools/change`、`system-prompt/change` 是同形状的纯失效事件但目前**没有任何消费者**，按「每个抽象都要有当前 owner 与需求」不进名单，只作为扩展位记录在此。 +`skills/change`、`tools/change`、`system-prompt/change` 是同形状的纯失效事件但**没有任何已交付消费者**，按「每个抽象都要有当前 owner 与需求」不进名单，只作为扩展位记录在此。 ### 消费端契约（dsh-typert-protocol） diff --git a/.agents/notes/implemented/architecture/2026-08-11-loader-entry-disabled-interpolation.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-11-loader-entry-disabled-interpolation.i18n.yaml index 9b266cdcde..c7efb03563 100644 --- a/.agents/notes/implemented/architecture/2026-08-11-loader-entry-disabled-interpolation.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-11-loader-entry-disabled-interpolation.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-11-loader-entry-disabled-interpolation.md -2026-08-11-loader-entry-disabled-interpolation.md: fd760ea0f15f19e5f287aaddc36fb8eeb5f519ba -2026-08-11-loader-entry-disabled-interpolation.zh.md: 41929a58b2e34974596ddb7f5b6748f14bd82e2d +2026-08-11-loader-entry-disabled-interpolation.md: 2d8fb73d95bab53367209afb2a9479a1b94cb949 +2026-08-11-loader-entry-disabled-interpolation.zh.md: 292b191f8293d31b53a7d5afa1f7d8017b31eeb4 diff --git a/.agents/notes/implemented/architecture/2026-08-11-loader-entry-disabled-interpolation.md b/.agents/notes/implemented/architecture/2026-08-11-loader-entry-disabled-interpolation.md index fd760ea0f1..2d8fb73d95 100644 --- a/.agents/notes/implemented/architecture/2026-08-11-loader-entry-disabled-interpolation.md +++ b/.agents/notes/implemented/architecture/2026-08-11-loader-entry-disabled-interpolation.md @@ -16,7 +16,7 @@ The mechanism completes the platform-layer fold: the base bundle's `cordis.patch ## Alternatives considered -**A declarative `platform` field on the row.** Static and gate-checkable, but a second composition mechanism beside `!!js`, and platform is only today's condition. +**A declarative `platform` field on the row.** Static and gate-checkable, but a second composition mechanism beside `!!js`, while platform is only one deployment condition. **Preset-level platform overlays.** Rejected: the condition belongs on the row it governs — the same principle folds the launcher's separate Windows platform layer into the base rows. diff --git a/.agents/notes/implemented/architecture/2026-08-11-loader-entry-disabled-interpolation.zh.md b/.agents/notes/implemented/architecture/2026-08-11-loader-entry-disabled-interpolation.zh.md index 41929a58b2..292b191f82 100644 --- a/.agents/notes/implemented/architecture/2026-08-11-loader-entry-disabled-interpolation.zh.md +++ b/.agents/notes/implemented/architecture/2026-08-11-loader-entry-disabled-interpolation.zh.md @@ -16,7 +16,7 @@ Loader 插值条目 `disabled` 字段（`vendor/loader/src/config/entry.ts`） ## 备选方案 -**行上的声明式 `platform` 字段。** 静态且可被门禁检查，但它是 `!!js` 之外的第二种组合机制，且平台只是今天的条件。 +**行上的声明式 `platform` 字段。**静态且可被门禁检查，但它是 `!!js` 之外的第二种组合机制，而平台只是众多部署条件之一。 **预设级平台 overlay。** 被否：条件应当属于它所治理的行——同一原则把启动器独立的 Windows 平台层折入 base 行。 diff --git a/.agents/notes/implemented/architecture/2026-08-11-repository-naming-contract-and-rename-ledger.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-11-repository-naming-contract-and-rename-ledger.i18n.yaml index 0c1ca6484d..d9003f4ec4 100644 --- a/.agents/notes/implemented/architecture/2026-08-11-repository-naming-contract-and-rename-ledger.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-11-repository-naming-contract-and-rename-ledger.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-11-repository-naming-contract-and-rename-ledger.md -2026-08-11-repository-naming-contract-and-rename-ledger.md: 895a202256504690b0451e6c09f3fc4ea8e7f4db -2026-08-11-repository-naming-contract-and-rename-ledger.zh.md: 1bf7bc9a44467dbaf099f2e99f3a8ee9634ae682 +2026-08-11-repository-naming-contract-and-rename-ledger.md: bf69f40884d8fee69cede839cd9ceb7c0d926c38 +2026-08-11-repository-naming-contract-and-rename-ledger.zh.md: 373bafaaa5590ccac7d33ba9ac27ce29f6dbefe5 diff --git a/.agents/notes/implemented/architecture/2026-08-11-repository-naming-contract-and-rename-ledger.md b/.agents/notes/implemented/architecture/2026-08-11-repository-naming-contract-and-rename-ledger.md index 895a202256..bf69f40884 100644 --- a/.agents/notes/implemented/architecture/2026-08-11-repository-naming-contract-and-rename-ledger.md +++ b/.agents/notes/implemented/architecture/2026-08-11-repository-naming-contract-and-rename-ledger.md @@ -309,7 +309,7 @@ Keep atomic-write, brand, native-command, timeout utility, directory-picker, `ds | `ConversationService` | `ConversationController` | The object controls the active conversation state and user actions. | | `InputService` | `SessionInputResolver` | The interface resolves the input facade for one session scope. It is neither a global input registry nor an execution service. Keep `InputHub` as the concrete hub and `ctx.conversation.input` as the published face. | -Use `Ui`, not `UI`, inside PascalCase identifiers. Keep the remaining client package names unless this ledger names them. Keep the deprecated client connection and Host `ApiProxy` vocabulary for now; the API plane will replace them, and a rename would add churn to a surface scheduled for removal. +Use `Ui`, not `UI`, inside PascalCase identifiers. Keep the remaining client package names unless this ledger names them. Retain the deprecated client connection and Host `ApiProxy` vocabulary until the API plane removes those surfaces; renaming them earlier would add churn without establishing a lasting name. ## Explicit non-renames diff --git a/.agents/notes/implemented/architecture/2026-08-11-repository-naming-contract-and-rename-ledger.zh.md b/.agents/notes/implemented/architecture/2026-08-11-repository-naming-contract-and-rename-ledger.zh.md index 1bf7bc9a44..373bafaaa5 100644 --- a/.agents/notes/implemented/architecture/2026-08-11-repository-naming-contract-and-rename-ledger.zh.md +++ b/.agents/notes/implemented/architecture/2026-08-11-repository-naming-contract-and-rename-ledger.zh.md @@ -309,7 +309,7 @@ PascalCase 标识符中的首字母缩略词使用首字母大写格式：`Ui` | `ConversationService` | `ConversationController` | 该对象控制当前对话状态和用户操作。 | | `InputService` | `SessionInputResolver` | 该接口为一个会话作用域解析输入外观。它既不是全局输入注册表，也不是执行服务。保留 `InputHub` 作为具体中枢，并保留 `ctx.conversation.input` 作为对外接口。 | -PascalCase 标识符内部使用 `Ui`，不要使用 `UI`。除非清单明确要求重命名，否则保留其余客户端包名。暂时保留已弃用的客户端连接和 Host `ApiProxy` 词汇；API 平面将替换它们，而在计划移除的表面上重命名只会增加改动量。 +PascalCase 标识符内部使用 `Ui`，不要使用 `UI`。除非清单明确要求重命名，否则保留其余客户端包名。在 API 平面移除相关表层之前，保留已弃用的客户端连接与 Host `ApiProxy` 词汇；提前重命名只会增加改动量，不会建立持久名称。 ## 明确保留的名称 diff --git a/.agents/notes/implemented/architecture/2026-08-12-pi-ai-route-default-input-modalities.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-12-pi-ai-route-default-input-modalities.i18n.yaml index 4ab07f7f07..9338e0cf6c 100644 --- a/.agents/notes/implemented/architecture/2026-08-12-pi-ai-route-default-input-modalities.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-12-pi-ai-route-default-input-modalities.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-12-pi-ai-route-default-input-modalities.md -2026-08-12-pi-ai-route-default-input-modalities.md: efd20b2cd73979208bb777fa42536bc5b918e29e -2026-08-12-pi-ai-route-default-input-modalities.zh.md: 069a7916c8d4ffe738ff910a851e0a9cd1f66d0a +2026-08-12-pi-ai-route-default-input-modalities.md: eb03d5330a1283d439e16262325965cf2e7e8087 +2026-08-12-pi-ai-route-default-input-modalities.zh.md: dfbbd2ae6db7a78e82955db66fe506d3506209fd diff --git a/.agents/notes/implemented/architecture/2026-08-12-pi-ai-route-default-input-modalities.md b/.agents/notes/implemented/architecture/2026-08-12-pi-ai-route-default-input-modalities.md index efd20b2cd7..eb03d5330a 100644 --- a/.agents/notes/implemented/architecture/2026-08-12-pi-ai-route-default-input-modalities.md +++ b/.agents/notes/implemented/architecture/2026-08-12-pi-ai-route-default-input-modalities.md @@ -18,17 +18,17 @@ The assumption was justified in the source as the adapter's real capability rath **The route value is a fallback, not an override — the catalog outranks it.** This is the `default*` ordering rather than `compat`'s, and the two are not interchangeable: `compat` shadows the catalog because a route-level protocol repoint invalidates the catalog's reasoning-dispatch facts wholesale, while a modality is a per-model property the catalog states accurately for the models it ships. Making the route value win would mean `defaultInput: [text]` silently strips images from every catalog vision model on the route — a footgun with no matching benefit, since narrowing one such model is what that model's own `input` is for. -**Undeclared means `[text]`, and that is the absence of a declaration rather than a guess at the endpoint.** Nothing can interrogate a gateway for its modalities — no OpenAI-compatible listing endpoint reports them — so the only honest floor is the modality every supported protocol certainly carries. This is where the modality fallback parts company with the capacity ones: 262,144 tokens is merely plausible and wrong in both directions (a gateway serving 8k overflows, one serving 1M is wasted), while text is safe in one direction. The two wrong answers do not cost the same either. Under-claiming refuses the image before it is attached, naming the model, and the remedy is one documented line. Over-claiming admits an image the provider then rejects mid-turn, *after* prompt admission has committed the message durably, so the session keeps re-sending a request that cannot succeed and model selection refuses a switch to any text-only model. A cheap refusal at the earliest resolvable point beats an expensive one at the latest. +**Undeclared means `[text]`, and that is the absence of a declaration rather than a guess at the endpoint.** Nothing can interrogate a gateway for its modalities because no OpenAI-compatible listing endpoint reports them. The only safe floor is the modality every supported protocol certainly carries. Under-claiming refuses the image before it is attached, names the model, and has a documented configuration remedy. Over-claiming admits and persists an image before the provider can reject it. Later requests to that same incorrectly declared route will encounter the image again, although the user can select a text-only model because request assembly projects durable images to placeholders. **An entry's empty list means the same as an absent one; the route's is refused.** `[]` describes a model that accepts nothing and could serve no request, so it states no answer and resolution continues past it. That reading is not cosmetic: the config schema materializes `[]` for an absent array, so treating it as "accepts nothing" would silently strip images from every catalog vision model a `models` list happens to name. The route value has nothing below it to answer instead, so its empty list is refused where it is written. The route's `models` list already resolves absent-and-empty the same way for the same reason. **No configuration surface edits `input`.** It joins `compat`, `reasoningEfforts`, `thinkingBudgets`, and `headers` as a settings-document field, and the model-list editor stays a hand-written form over id, name, and the two capacities. This costs nothing durable because that card was already built to carry fields it does not edit: its row patch spreads the stored row before applying changes, and adoption keeps an existing row over a rediscovered candidate, so a hand-written `input` survives both. -The DeepSeek chat-completions adapter is untouched. Its `['text']` is a fact about its serializer, not a missing declaration, and it keeps refusing before the send. +The direct DeepSeek adapter owns a separate exact-model catalog. Its supported vision entry declares image input, while its text models and unlisted pass-through ids remain text-only. ## Alternatives considered -- **An optimistic `[text, image]` default** — makes the motivating case work with zero configuration, and the web form writes no modality at all, so a conservative default leaves the remedy in a file a web-only user has no reason to open. Rejected on the severity of being wrong: a refused attachment is a speed bump with a documented fix, while a provider rejection poisons the session, presents as an unexplained repeating failure, and is escapable only by switching models or starting over. Documenting the remedy on the model-configuration page closes the discoverability gap; nothing closes the poisoned session. +- **An optimistic `[text, image]` default** — makes the motivating case work with zero configuration, and the web form writes no modality at all, so a conservative default leaves the remedy in the settings document. Rejected because a false positive persists an image before the provider refuses it and causes repeated failure on that route. Text-only request projection provides recovery but does not make the declaration true. - **A route value that overrides the catalog** (`compat`'s ordering: entry → route → catalog) — lets a deployment that repoints a catalog route at its own gateway declare "no vision here" once. Rejected because the same sentence then silently disables every catalog vision model on a route where someone wrote it by analogy with the capacity fields, and the legitimate case is served by that model's own `input`. An override would also have to be named `input` at the route, since calling it `default*` beside two genuine fallbacks would misdescribe it. - **No route field at all, only the entry one** — closest to upstream, which has no route-level concept. Rejected on the bulk case the product's own flow produces: "fetch available models" adopts thirty ids with no modality, and an all-vision gateway would need `input` hand-written on each. - **A route-level `defaultInput` with no entry field** — cannot mix modalities on one route or correct a single catalog model, leaving "split the provider across two route keys" as the only workaround, at the cost of a second permanent provider id and a duplicate entry in every model selector. @@ -42,7 +42,7 @@ A vision model on a custom provider costs one line, `input: [text, image]`, writ The image-admission gate keeps its meaning everywhere, because every modality it reads is now either recorded by the installed catalog or written by a person. Nothing claims a capability on a deployment's behalf. -A model that declares images its endpoint does not serve is not caught locally — the claim is not verified — and the resulting failure is expensive. Prompt admission commits the user message durably (`agent/inbox/spliced`) before the request is built, so the rejected image stays in the session log: that model keeps re-sending it, and model selection refuses a switch to any text-only model. Recovery is to select a model that does serve images, fork before the image, or start a session. Making that failure non-destructive — rolling an unconsumed image message back out of the log when the send fails — is the change that would make an optimistic default reconsiderable, and is not attempted here. +A model that declares image input its endpoint does not serve is not caught locally because the claim is not verified. Prompt admission commits the user message durably before request construction, so the rejected image stays in the session log and later requests to that route can fail again. Recovery is to correct the declaration, select an image-capable route, or select a text-only route whose request projection replaces durable images with placeholders. ## Testing diff --git a/.agents/notes/implemented/architecture/2026-08-12-pi-ai-route-default-input-modalities.zh.md b/.agents/notes/implemented/architecture/2026-08-12-pi-ai-route-default-input-modalities.zh.md index 069a7916c8..dfbbd2ae6d 100644 --- a/.agents/notes/implemented/architecture/2026-08-12-pi-ai-route-default-input-modalities.zh.md +++ b/.agents/notes/implemented/architecture/2026-08-12-pi-ai-route-default-input-modalities.zh.md @@ -18,17 +18,17 @@ Harness 把缺失的模态当作否定能力，并有三个准入点在构造任 **路由值是回退值而非覆盖值——catalog 的优先级更高。** 这采用的是 `default*` 的顺序而非 `compat` 的，两者不可互换：`compat` 之所以盖住 catalog，是因为路由级的协议改指会整体作废 catalog 关于推理分派的事实；而模态是按模型的属性，对 catalog 自己出货的那些模型，它记录得准确无误。让路由值获胜就意味着 `defaultInput: [text]` 会悄悄剥掉该路由上每一个 catalog 视觉模型的图片能力——一个没有对应收益的坑，因为收窄其中某个模型正是该模型自己的 `input` 要做的事。 -**未声明即 `[text]`，而这是「尚未声明」，不是对端点的猜测。** 没有任何环节能去询问网关的模态——没有任何 OpenAI 兼容的列表端点会报告它们——因此唯一诚实的底线是每个受支持协议都确定携带的那个模态。这也正是模态回退值与容量回退值分道扬镳之处：262,144 只是个说得过去的数字，且两个方向都会错（网关只给 8k 会溢出，给 1M 则被浪费），而 text 在一个方向上是安全的。两种猜错的代价同样并不对等。少声明会在图片被附加之前就拒绝并点名该模型，补救办法是一行有文档可依的配置。多声明会接纳一张图片、再由提供方在轮次中途拒绝——而此时 prompt 准入**早已**把消息持久化提交，于是会话会不断重发一个不可能成功的请求，且模型选择拒绝切换到任何纯文本模型。在最早可解析点付出一次廉价的拒绝，胜过在最晚点付出一次昂贵的。 +**未声明即 `[text]`，而这是「尚未声明」，不是对端点的猜测。** 没有任何环节能询问网关的模态，因为 OpenAI 兼容列表端点不会报告它们。安全的底线是每个受支持协议都确定携带的模态。少声明会在图片附加之前拒绝、点名模型，并给出有文档的配置补救方法。多声明会先接纳并持久化图片，再由提供方拒绝。之后对同一错误声明路由的请求还会再次遇到图片，但用户可以选择纯文本模型，因为请求组装会把持久图片投影为占位符。 **条目的空列表与缺省同义；路由的空列表则被拒绝。** `[]` 描述的是一个什么都不接受、无法服务任何请求的模型，因此不作答，解析继续往下走。这个读法不是修辞：配置 schema 会为缺省数组物化出 `[]`，把它当作“什么都不接受”，会悄悄剥掉 `models` 列表恰好点到的每一个 catalog 视觉模型的图片能力。而路由值下面没有可以代为作答的层级，因此它的空列表在写入处即被拒绝。路由的 `models` 列表出于同样的理由，早已用同一种方式解析缺省与空。 **没有任何配置界面编辑 `input`。** 它和 `compat`、`reasoningEfforts`、`thinkingBudgets`、`headers` 一样是 settings 文档字段，而模型列表编辑器仍是一张只覆盖 id、名称和两个容量的手写表单。这不会带来持久代价，因为那张卡片本来就是按“承载自己并不编辑的字段”建造的：它的行 patch 会先展开已存储的行再应用改动，而采纳候选时已有行优先于重新发现的候选，因此手写的 `input` 在两条路径上都能存活。 -DeepSeek chat-completions 适配器保持不动。它的 `['text']` 是关于其序列化器的事实，而不是一处缺失的声明，它继续在发送前拒绝。 +DeepSeek 直接适配器拥有独立的精确模型目录。支持视觉的条目声明图片输入，纯文本模型和未列出的透传 ID 保持纯文本。 ## 备选方案 -- **乐观的 `[text, image]` 默认值** —— 让触发本次变更的场景零配置即可工作；而且网页表单不会写入任何模态，因此保守默认值会把补救办法留在一个纯 Web 用户没有理由打开的文件里。被否决的理由是猜错时的严重程度：被拒绝的附件是一个有文档可依的减速带，而提供方拒绝会毒化整个会话、表现为一次无从解释的反复失败，且只能靠换模型或重开会话脱身。把补救办法写进配置模型页即可补上可发现性的缺口；而毒化的会话没有任何东西能补。 +- **乐观的 `[text, image]` 默认值** —— 让触发场景无需配置即可工作，而网页表单不会写入模态，因此保守默认值会把补救方法留在 settings 文档里。否决原因是错误的肯定声明会在提供方拒绝之前持久化图片，并让该路由重复失败。纯文本请求投影提供了恢复方法，但不能让错误声明变成事实。 - **让路由值盖住 catalog**（`compat` 的顺序：条目 → 路由 → catalog）—— 可以让把 catalog 路由改指到自家网关的部署，一句话声明「这里没有视觉能力」。被否决是因为同一句话也会在有人照着容量字段类比写下它的路由上，悄悄禁用每一个 catalog 视觉模型；而那个正当场景由该模型自己的 `input` 承担。覆盖值还必须在路由级改名叫 `input`，因为在两个货真价实的回退值旁边把它叫作 `default*` 是名不副实。 - **完全不要路由字段，只要条目字段** —— 最贴近上游（上游没有路由级概念）。被否决的理由是产品自身流程会产生的批量场景：「获取可用模型」一次采纳三十个不带模态的 id，全是视觉模型的网关就得逐个手写 `input`。 - **只要路由级 `defaultInput`，不要条目字段** —— 无法在一条路由上混合模态，也无法修正单个 catalog 模型，唯一的变通办法只剩「把该提供方拆成两个路由键」，代价是多一个永久的 provider id 和每个模型选择器里的一项重复。 @@ -42,7 +42,7 @@ DeepSeek chat-completions 适配器保持不动。它的 `['text']` 是关于其 图片准入门禁在各处都保住了自己的意义，因为它读到的每一个模态，如今要么由已安装 catalog 记录，要么由人写下。没有任何环节会替部署宣称一项能力。 -声明了端点并不提供的图片能力的模型不会在本地被拦下——该断言不经验证——而由此产生的失败代价高昂。prompt 准入在构造请求之前就把用户消息持久化提交（`agent/inbox/spliced`），因此被拒绝的图片会留在会话日志里：该模型会不断重发它，而模型选择拒绝切换到任何纯文本模型。恢复途径是选择一个确实提供图片能力的模型、fork 到图片之前，或者开启新会话。让这次失败不具破坏性——发送失败时把尚未消费的图片消息从日志中回滚出去——才是能让乐观默认值重新可考虑的那项改动，本次未做尝试。 +声明了端点并不提供的图片能力时，本地无法发现该错误，因为声明不会被远端验证。prompt 准入会在请求构造前持久化用户消息，因此被拒绝的图片留在会话日志中，之后对该路由的请求可能再次失败。恢复方法是修正声明、选择支持图片的路由，或选择由请求投影把持久图片替换为占位符的纯文本路由。 ## 测试 diff --git a/.agents/notes/implemented/architecture/2026-08-12-plugin-owned-settings-surface.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-12-plugin-owned-settings-surface.i18n.yaml index c3d26e40a4..8ae275a581 100644 --- a/.agents/notes/implemented/architecture/2026-08-12-plugin-owned-settings-surface.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-12-plugin-owned-settings-surface.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-12-plugin-owned-settings-surface.md -2026-08-12-plugin-owned-settings-surface.md: 722e6cfbe890418e8305f89790e76976027d7775 -2026-08-12-plugin-owned-settings-surface.zh.md: ddb1d70aed5427e58720a9be558a83a5e034c335 +2026-08-12-plugin-owned-settings-surface.md: daed91b8ac4ce0acb81e19908ec08c9f3f7ac21e +2026-08-12-plugin-owned-settings-surface.zh.md: ba39b84faaf90be413ad8d7b8327c67b2fa27cea diff --git a/.agents/notes/implemented/architecture/2026-08-12-plugin-owned-settings-surface.md b/.agents/notes/implemented/architecture/2026-08-12-plugin-owned-settings-surface.md index 722e6cfbe8..daed91b8ac 100644 --- a/.agents/notes/implemented/architecture/2026-08-12-plugin-owned-settings-surface.md +++ b/.agents/notes/implemented/architecture/2026-08-12-plugin-owned-settings-surface.md @@ -52,7 +52,7 @@ So the exposure this change actually adds, in this repository, is one namespace: ## Consequences -A plugin distributed outside this repository is configurable from the settings page with no change here: it registers its namespace on the Host and its card under that key in the browser, and the section pairs the two. Cards now appear in card registration order rather than by hand-assigned `order`. That is stable for the cards this package registers, which install from one generator, and **not** stable across plugins: apply order between packages is unconstrained (`packages/client/AGENTS.md`), so several external cards can still reorder between boots. Ordering them needs an explicit key the section can sort on, which the keyed registration does not carry today. +A plugin distributed outside this repository is configurable from the settings page with no change here: it registers its namespace on the Host and its card under that key in the browser, and the section pairs the two. Cards now appear in card registration order rather than by hand-assigned `order`. That is stable for the cards this package registers, which install from one generator, and **not** stable across plugins: apply order between packages is unconstrained (`packages/client/AGENTS.md`), so several external cards can still reorder between boots. Ordering them needs an explicit key the section can sort on, which the keyed registration does not carry. Deferred, and larger than this change: the redactor returns a `role('secret')` reachable only through a union, intersection, or transform verbatim (its own `TODO(settings-wire-redaction)`), and `schema.toJSON()` carries a secret's default. That gap predates this change, but serving every registered namespace widens its blast radius from schemas audited in this repository to any third-party schema, so the wire should refuse a namespace it cannot prove it can redact. Also deferred: an assembled-composition test of the headline capability — an overlay-mounted fixture plugin whose Host half registers a namespace and whose `dsh.client` half registers a card, asserted end-to-end. The current coverage proves each half separately; the shipped cards' unchanged output cannot prove the new path. diff --git a/.agents/notes/implemented/architecture/2026-08-12-plugin-owned-settings-surface.zh.md b/.agents/notes/implemented/architecture/2026-08-12-plugin-owned-settings-surface.zh.md index ddb1d70aed..ba39b84faa 100644 --- a/.agents/notes/implemented/architecture/2026-08-12-plugin-owned-settings-surface.zh.md +++ b/.agents/notes/implemented/architecture/2026-08-12-plugin-owned-settings-surface.zh.md @@ -52,7 +52,7 @@ Status: implemented ## Consequences -在本仓库之外分发的插件无需改动这里即可从设置页配置：它在 Host 上注册自己的命名空间、在浏览器里把卡片注册在该键上，由分区把两者配对。卡片现在按卡片注册顺序出现，而不再依赖手工指定的 `order`。对本包注册的这几张卡它是稳定的——它们从同一个 generator 安装；对**跨插件**的卡片它并不稳定：包与包之间的 apply 顺序是无约束的（`packages/client/AGENTS.md`），因此多个外部卡片仍可能在不同次启动之间重排。要为它们定序，需要一个 section 可排序的显式键，而 keyed 注册今天并不携带。 +在本仓库之外分发的插件无需改动这里即可从设置页配置：它在 Host 上注册自己的命名空间、在浏览器里把卡片注册在该键上，由分区把两者配对。卡片现在按卡片注册顺序出现，而不再依赖手工指定的 `order`。对本包注册的这几张卡它是稳定的——它们从同一个 generator 安装；对**跨插件**的卡片它并不稳定：包与包之间的 apply 顺序是无约束的（`packages/client/AGENTS.md`），因此多个外部卡片仍可能在不同次启动之间重排。要为它们定序，需要一个 section 可排序的显式键，而 keyed 注册并不携带。 以下延后，且都大于本次改动：脱敏器对只能经由 union、intersection 或 transform 抵达的 `role('secret')` 原样返回（其自身的 `TODO(settings-wire-redaction)`），而 `schema.toJSON()` 会携带 secret 的默认值。该缺口早于本次改动，但服务每一个已注册命名空间，把它的影响面从本仓库内经审计的 schema 扩大到任意第三方 schema，因此协议应当拒绝服务它无法证明可安全脱敏的命名空间。同样延后的还有：对本次头号能力的组装态测试——用 overlay 挂载一个 fixture 插件（Host 半注册命名空间、`dsh.client` 半注册卡片）并在端到端断言。当前覆盖分别证明了两个半侧；已发卡片输出未变这一点，证明不了新路径。 diff --git a/.agents/notes/implemented/architecture/2026-08-13-credential-records-and-authorization-flows.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-13-credential-records-and-authorization-flows.i18n.yaml index fb9c5c6442..5dba989cb5 100644 --- a/.agents/notes/implemented/architecture/2026-08-13-credential-records-and-authorization-flows.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-13-credential-records-and-authorization-flows.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-13-credential-records-and-authorization-flows.md -2026-08-13-credential-records-and-authorization-flows.md: a52d85854c8c660b4965d07a13a2dbfefbac5723 -2026-08-13-credential-records-and-authorization-flows.zh.md: 7ba73f133f240e41bf2aecff32a45115b9bed531 +2026-08-13-credential-records-and-authorization-flows.md: 23d3dda6e90809817b74dce98f380334bbbc0f4d +2026-08-13-credential-records-and-authorization-flows.zh.md: c6ec580b4ed73f8d0a9d6f9922b2b6b220f2c428 diff --git a/.agents/notes/implemented/architecture/2026-08-13-credential-records-and-authorization-flows.md b/.agents/notes/implemented/architecture/2026-08-13-credential-records-and-authorization-flows.md index a52d85854c..23d3dda6e9 100644 --- a/.agents/notes/implemented/architecture/2026-08-13-credential-records-and-authorization-flows.md +++ b/.agents/notes/implemented/architecture/2026-08-13-credential-records-and-authorization-flows.md @@ -53,7 +53,7 @@ Withdrawal settles an attempt whether or not its flow reacts to the signal. A fl `.credentials.yaml` gains a version and two sections. A boot upgrades the recognized pre-release flat layout in place — an all-string flat mapping nests verbatim under `refs:` under the writer lock — because a key stored through the Models page by an earlier internal build must survive the layout change without a hand edit and without its model requests failing. Any flat shape the recognizer cannot prove it understands keeps the by-name refusal with the hand migration stated in the message; the parser itself still reads exactly one layout, and the migration step retires with the pre-release stance at the first tagged release. Every fixture in the repo that wrote the flat document was rewritten; the llm suites' fixtures were missed by the record change itself and fixed here. -`openai-codex` returns to the provider picker and to the Models page directory. Signing in is offered for every installed provider that ships a login, which today is all 38 — 31 collect a key through pi-ai's own prompt, six offer that beside a subscription login, and Codex offers only the subscription login. +`openai-codex` returns to the provider picker and to the Models page directory. All 38 installed providers offer sign-in: 31 collect a key through pi-ai's own prompt, six offer that beside a subscription login, and Codex offers only the subscription login. What this does not yet include is the surface: the wire contract that carries notices and prompts to the browser, and the Models-page control that starts a login. Until that lands, the flows are reachable only in-process, and a deployment still configures a key by typing it into the settings form. @@ -65,4 +65,4 @@ The seam's suite pins the lifecycle it owns: single-flight refusal and release, `llm-pi-ai` covers the three translations against a real `$DSH_HOME` document — an api-key credential field by field, an OAuth credential verbatim including its refresh half, a foreign plugin's record skipped by scope, and the write refusal without a credentials service — plus every `AuthEvent` and `AuthPrompt` member restated, with `Models.login()` mocked at the collection boundary since a real one opens a browser. Two real-composition tests boot the plugin with and without the authorization seam. -The `models-settings` and `onboarding-usable-provider` web e2e goldens regain exactly the `openai-codex` option line they lost when it was withheld — the whole assembled-application difference this change makes today, because the Models page has no login control yet to record. +The `models-settings` and `onboarding-usable-provider` web e2e goldens regain exactly the `openai-codex` option line they lost when it was withheld — the only assembled-application difference this decision records, because the Models page has no login control yet to record. diff --git a/.agents/notes/implemented/architecture/2026-08-13-credential-records-and-authorization-flows.zh.md b/.agents/notes/implemented/architecture/2026-08-13-credential-records-and-authorization-flows.zh.md index 7ba73f133f..c6ec580b4e 100644 --- a/.agents/notes/implemented/architecture/2026-08-13-credential-records-and-authorization-flows.zh.md +++ b/.agents/notes/implemented/architecture/2026-08-13-credential-records-and-authorization-flows.zh.md @@ -53,7 +53,7 @@ seam 的边缘与写入路径同一纪律。prompt 被拒是结果而非故障 `.credentials.yaml` 增加了版本与两个分区。启动时会把能精确识别的发布前扁平布局原地升级——全字符串的扁平 mapping 在写锁下逐字下沉到 `refs:` 之下——因为早期内测构建经模型页面存下的密钥必须在布局变更后继续可用，不能要求手工编辑，也不能让模型请求失败。识别器无法证明自己理解的扁平形态仍被指名拒绝，迁移办法写在报错信息里；解析器本身始终只读一种布局，迁移步骤将随发布前立场在首个正式版本时移除。仓库中所有写扁平文档的 fixture 都已改写；llm 各套件的 fixture 被记录改动本身漏掉了，在此补上。 -`openai-codex` 回到提供方选择器与 Models 页目录。凡是自带登录的已安装提供方都会得到登录入口，而今天这是全部 38 个——31 个经 pi-ai 自己的提示收取密钥，6 个在此之外还提供订阅登录，Codex 只提供订阅登录。 +`openai-codex` 回到提供方选择器与 Models 页目录。全部 38 个已安装提供方都提供登录入口：31 个经 pi-ai 自己的提示收取密钥，6 个在此之外还提供订阅登录，Codex 只提供订阅登录。 尚未包含的是界面：把 notice 与 prompt 送到浏览器的 wire 契约，以及 Models 页上发起登录的控件。在那之前，flow 只能在进程内触达，部署方仍然通过在设置表单里输入密钥来配置。 @@ -65,4 +65,4 @@ seam 自己的套件钉住它拥有的生命周期：单飞的拒绝与释放、 `llm-pi-ai` 针对一份真实的 `$DSH_HOME` 文档覆盖三处翻译——逐字段的 api-key 凭据、连 refresh 半边一起原样保存的 OAuth 凭据、按 scope 跳过的他插件记录，以及没有凭据服务时的写入拒绝——外加每一个 `AuthEvent` 与 `AuthPrompt` 成员的重述；`Models.login()` 在集合边界处被 mock，因为真实登录会打开浏览器。两个真实组合测试分别在挂载与不挂载授权 seam 的情况下启动插件。 -`models-settings` 与 `onboarding-usable-provider` 两条 web e2e golden 恰好收回了被扣留时失去的那一行 `openai-codex` 选项——这是本次改动今天在装配后的应用上造成的全部差异，因为 Models 页还没有可录制的登录控件。 +`models-settings` 与 `onboarding-usable-provider` 两条 web e2e golden 恰好收回了被扣留时失去的那一行 `openai-codex` 选项——这是本决策记录的唯一装配后应用差异，因为 Models 页还没有可录制的登录控件。 diff --git a/.agents/notes/implemented/bug-fix/2026-08-17-image-dimension-admission-limit.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-19-shared-win32-process-primitives.i18n.yaml similarity index 55% rename from .agents/notes/implemented/bug-fix/2026-08-17-image-dimension-admission-limit.i18n.yaml rename to .agents/notes/implemented/architecture/2026-08-19-shared-win32-process-primitives.i18n.yaml index ec3cea9dc2..780aa7e236 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-17-image-dimension-admission-limit.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-19-shared-win32-process-primitives.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-17-image-dimension-admission-limit.md -2026-08-17-image-dimension-admission-limit.md: 027259c0949d142ce8d8af27e7daa2abd54769ab -2026-08-17-image-dimension-admission-limit.zh.md: 38422615aa93b7f1639877d7d3751322c77de1eb +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-19-shared-win32-process-primitives.md +2026-08-19-shared-win32-process-primitives.md: 8765e5f7350dab56ad42169f6e16b55679ca8982 +2026-08-19-shared-win32-process-primitives.zh.md: b21ece8445e8863c08818c42d6c9bf7672813823 diff --git a/.agents/notes/implemented/architecture/2026-08-19-shared-win32-process-primitives.md b/.agents/notes/implemented/architecture/2026-08-19-shared-win32-process-primitives.md new file mode 100644 index 0000000000..8765e5f735 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-19-shared-win32-process-primitives.md @@ -0,0 +1,35 @@ +# Agent Note: Windows sandbox process primitives have one low-level owner + +Status: implemented + +English | [中文](2026-08-19-shared-win32-process-primitives.zh.md) + +## Problem + +The Windows ACL sandbox owns restricted-token, SID, DACL, grant, and workspace policy, but its process launch path also carried the generic Koffi ABI, command-line quoting, anonymous pipes, inherited stdio, Job setup, waits, and HANDLE cleanup. A second Windows process consumer would otherwise have to depend on sandbox policy or copy native resource logic, while fixes to allocation and failure cleanup would need to remain synchronized. + +## Decision + +`@deepseek-ai/dsh-win32-process` owns the reusable Win32 process ABI and native resource operations currently consumed by `sandbox-windows-acl`. The package lazily loads `kernel32.dll` and `advapi32.dll`, verifies the x64 `STARTUPINFOW` and `PROCESS_INFORMATION` layouts, quotes argv for `CreateProcessAsUserW`, and exposes checked restricted-token pipe and inherited-stdio Job operations. + +The Windows ACL sandbox remains the only owner of restricted-token creation, SID and DACL policy, grants, writable-path decisions, temporary-directory policy, and the public sandbox child result. It extends the shared binding context with policy-specific APIs, supplies the primary token, combines pipe drains and waits, and closes the caller-owned Job at its lifecycle boundary. + +Every native allocation and HANDLE has one owner within each shared operation. A process operation frees its Koffi out-parameters and closes every pipe, thread, process, or Job handle it acquired before a controlled failure. Successful pipe creation returns the process plus stdout/stderr read handles to the sandbox. Inherited-stdio creation starts the target suspended, assigns it to the kill-on-close Job, and resumes it only after assignment, so target code cannot run outside the Job. Assignment failure terminates the suspended target before releasing its handles; resume failure closes the assigned Job. The sandbox retains its existing pipe-drain, direct-wait, result, and returned-Job lifecycle. + +The package exports only operations used by the sandbox production path. Ordinary `CreateProcessW`, exact `applicationName`, parent-stdio release, and whole-Job settlement remain absent until an ordinary process consumer needs them. The package is a library, not a Cordis service or a public Windows SDK. + +## Verification + +The shared suite covers x64 ABI values, command-line quoting, binding extension, pipe EOF and drain allocation reuse, restricted-token process creation, suspended creation followed by Job assignment and resume, wait and exit-code reads, native allocation release, and the acquired-resource failure paths. Sandbox tests retain restricted-token, fail-closed, pipe/inherit, result, and disposal composition without duplicating the low-level matrix. The committed header probes and Windows package tests cover the migrated ABI and native paths; Wine supplies the emulated Windows package and composition signal. + +## Alternatives considered + +**Keep process primitives inside the sandbox package.** Rejected because a process consumer would inherit ACL/token policy or duplicate the native ABI and cleanup paths. + +**Copy the Koffi implementation into each consumer.** Rejected because struct layouts, error capture, and partial-failure cleanup would have multiple owners. + +**Publish ordinary-runner operations before a current consumer exists.** Rejected because unused `CreateProcessW`, application-name, parent-stdio, and Job-settlement APIs would freeze speculative obligations and enlarge the failure matrix. + +## Consequences + +The sandbox keeps its public behavior while generic Win32 resource ownership has one package and one test home. The package boundary adds one workspace dependency and a published library, and callers must explicitly own policy, scheduling, result composition, and returned HANDLE closure. Suspended creation guarantees that target code starts only after Job assignment, but it does not make the runner's create-to-assignment interval atomic against external termination. Future process consumers extend the low-level package only when their production path exists. diff --git a/.agents/notes/implemented/architecture/2026-08-19-shared-win32-process-primitives.zh.md b/.agents/notes/implemented/architecture/2026-08-19-shared-win32-process-primitives.zh.md new file mode 100644 index 0000000000..b21ece8445 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-19-shared-win32-process-primitives.zh.md @@ -0,0 +1,35 @@ +# Agent Note：Windows sandbox process primitives 只有一个低层 owner + +Status: implemented + +[English](2026-08-19-shared-win32-process-primitives.md) | 中文 + +## Problem + +Windows ACL sandbox 拥有 restricted token、SID、DACL、grant 与 workspace policy，但其进程启动路径还同时承载通用 Koffi ABI、命令行引用、匿名管道、继承 stdio、Job 设置、wait 与 HANDLE 清理。第二个 Windows process consumer 否则只能依赖 sandbox policy 或复制 native resource 逻辑，而 allocation 与失败清理修复也必须在多份实现间保持同步。 + +## Decision + +`@deepseek-ai/dsh-win32-process` 拥有 `sandbox-windows-acl` 当前消费的可复用 Win32 process ABI 与 native resource 操作。该包惰性加载 `kernel32.dll` 和 `advapi32.dll`，核验 x64 `STARTUPINFOW` 与 `PROCESS_INFORMATION` 布局，为 `CreateProcessAsUserW` 引用 argv，并提供带检查的 restricted-token pipe 与 inherited-stdio Job 操作。 + +Windows ACL sandbox 继续唯一拥有 restricted-token 创建、SID 与 DACL policy、grants、可写路径裁定、临时目录 policy 和公共 sandbox child result。它通过共享 binding context 扩展 policy-specific API，提供 primary token，组合 pipe drain 与 wait，并在自己的生命周期边界关闭调用方拥有的 Job。 + +每项 native allocation 与 HANDLE 在各个 shared operation 内只有一个 owner。process operation 会释放 Koffi out-parameter，并在受控失败前关闭它已经取得的每个 pipe、thread、process 或 Job handle。pipe 创建成功时，把 process 与 stdout/stderr read handles 返回给 sandbox。inherited-stdio 创建以 suspended 状态启动目标，把它分配给 kill-on-close Job，并只在分配后恢复，因此目标代码不会在 Job 外运行。分配失败会先终止 suspended target 再释放句柄；恢复失败会关闭已经分配的 Job。sandbox 保留既有 pipe-drain、direct-wait、result 与返回 Job 的生命周期。 + +该包只导出 sandbox 生产路径已使用的操作。ordinary `CreateProcessW`、精确 `applicationName`、parent-stdio release 与 whole-Job settlement 在 ordinary process consumer 出现前保持缺席。该包是 library，不是 Cordis service 或公共 Windows SDK。 + +## Verification + +shared suite 覆盖 x64 ABI 值、命令行引用、binding extension、pipe EOF 与 drain allocation 复用、restricted-token process 创建、suspended 创建后的 Job 分配与恢复、wait 与 exit-code 读取、native allocation 释放，以及已取得资源的失败路径。sandbox 测试保留 restricted-token、fail-closed、pipe/inherit、result 与 disposal 组合行为，不重复低层矩阵。已提交的 header probe 与 Windows package 测试覆盖迁移后的 ABI 和 native 路径；Wine 提供模拟 Windows package 与组合信号。 + +## Alternatives considered + +**把 process primitives 留在 sandbox package。** 拒绝，因为 process consumer 将被迫继承 ACL/token policy，或复制 native ABI 与清理路径。 + +**为每个 consumer 复制 Koffi 实现。** 拒绝，因为 struct layout、错误捕获与局部失败清理会出现多个 owner。 + +**在当前 consumer 出现前发布 ordinary-runner operations。** 拒绝，因为未使用的 `CreateProcessW`、application-name、parent-stdio 与 Job-settlement API 会冻结推测性义务，并扩大失败矩阵。 + +## Consequences + +sandbox 保持公共行为，而通用 Win32 resource ownership 只有一个 package 与一个测试归属。该 package boundary 增加一个 workspace dependency 和发布 library；调用方必须显式拥有 policy、调度、result 组合与返回 HANDLE 的关闭责任。suspended 创建保证目标代码只在 Job 分配后启动，但不会让 runner 的 create-to-assignment 区间对外部终止具备原子性。后续 process consumer 只在其生产路径存在时扩展低层 package。 diff --git a/.agents/notes/implemented/bug-fix/2026-08-06-plan-narrow-viewport-regression.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-20-preview-cloudflare-pages-deploy.i18n.yaml similarity index 55% rename from .agents/notes/implemented/bug-fix/2026-08-06-plan-narrow-viewport-regression.i18n.yaml rename to .agents/notes/implemented/architecture/2026-08-20-preview-cloudflare-pages-deploy.i18n.yaml index 3a62ad16dc..83f673d68e 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-06-plan-narrow-viewport-regression.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-20-preview-cloudflare-pages-deploy.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-06-plan-narrow-viewport-regression.md -2026-08-06-plan-narrow-viewport-regression.md: 945d014e0c51cbaf4080e72f50ee60763d851698 -2026-08-06-plan-narrow-viewport-regression.zh.md: 56b305645484060693dbd38397228676be73645c +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-20-preview-cloudflare-pages-deploy.md +2026-08-20-preview-cloudflare-pages-deploy.md: 38b2834d612153d235d3b0aaffead3bd2b33eec7 +2026-08-20-preview-cloudflare-pages-deploy.zh.md: 3ebb8eba95666729ee1021ffe2c958dad40aed1c diff --git a/.agents/notes/implemented/architecture/2026-08-20-preview-cloudflare-pages-deploy.md b/.agents/notes/implemented/architecture/2026-08-20-preview-cloudflare-pages-deploy.md new file mode 100644 index 0000000000..38b2834d61 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-20-preview-cloudflare-pages-deploy.md @@ -0,0 +1,27 @@ +# Agent Note: per-PR preview deployments on Cloudflare Pages + +Status: implemented + +English | [中文](2026-08-20-preview-cloudflare-pages-deploy.zh.md) + +## Problem + +The browser worker preview exists to observe a pull request's frontend and host code running, so it needs a static host per pull request that outsiders cannot reach. GitHub Pages publishes privately only on GitHub Enterprise Cloud, which this organization has not settled, and one Pages site per repository cannot isolate pull requests. The first deployment run also exposed a packaging defect: on a clean checkout `pnpm install` never creates the `dsh-pack-vfs-image` bin link, so `build:preview` fails with `command not found` anywhere but a working tree whose install ran after a build. + +## Decision + +**Deployment.** Every push to a pull request publishes `apps/web/dist` to the Cloudflare Pages project `dsh-build-preview` under the branch alias `pr-`, behind Cloudflare Access (`.github/workflows/build-preview-cloudflare.yml`). The upload carries build products only — the platform never holds repository sources, and sourcemaps are deleted before upload because they embed complete sources. `preview.html` replaces `index.html` as the deployment root: the served page cannot boot without a host injecting `window.__DSH_BOOT__`, so the root must be the page that boots. Per pull request the newest build wins; across pull requests each alias is its own URL, so nothing contends. The run passes only after a service-token request proves the protected URL serves the packed image: HTTP 200 (Access admitted the token; 302 means the Access policy lacks its Service Auth rule), no `content-encoding` (the platform must not claim transport compression over an already-compressed body, which would leave the worker's `DecompressionStream` inflating a plain tar), and the gzip magic `1f 8b`. A marker-guarded comment states the stable alias URL once per pull request. + +**Bin link.** pnpm creates a workspace bin link only when the link target exists at install time. A `bin` entry naming a build product (`lib/bin.js`) therefore never gets its link on a clean checkout — building later does not revisit linking. The packer commits a root `bin.js` as the stable link target; it forwards to `lib/bin.js` and, when the build product is missing, names `pnpm run build` and exits 1. Same pattern as `dsh-subprocess-local`'s committed spawn-helper entry. + +## Alternatives considered + +**GitHub Pages, privately published.** Enterprise-Cloud-only, and `deploy-pages` replaces the whole site, so pull requests would overwrite each other; per-branch subdirectories require the legacy branch-deploy path and its build-rate limits. + +**Actions artifact as the preview.** Download permission aligns exactly with repository read access and costs nothing, but an artifact is a zip download, not a browsable site. Kept as the fallback if the Cloudflare surface goes away. + +**Documenting "install again after building" instead of committing a link target.** Leaves every clean checkout broken in an order-dependent way the error message does not explain; CI is precisely such a checkout on every run. + +## Consequences + +A pull request's preview lives at `https://pr-.dsh-build-preview.pages.dev` and demands a Cloudflare Access sign-in; automation reaches it with a service token. The deployment platform holds no sources and no sourcemaps, which also means the preview cannot map its bundles back to source until sourcemap handling is designed deliberately. The image byte path — bytes stored compressed, served without transport re-encoding — is asserted on every deployment, so a platform behavior change fails the run instead of the worker boot. The packer bin works from any clean checkout after one full build, and the constraints table pins `bin.js` in the published file list. diff --git a/.agents/notes/implemented/architecture/2026-08-20-preview-cloudflare-pages-deploy.zh.md b/.agents/notes/implemented/architecture/2026-08-20-preview-cloudflare-pages-deploy.zh.md new file mode 100644 index 0000000000..3ebb8eba95 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-20-preview-cloudflare-pages-deploy.zh.md @@ -0,0 +1,27 @@ +# Agent Note：每 PR 预览部署上 Cloudflare Pages + +状态：已实现 + +[English](2026-08-20-preview-cloudflare-pages-deploy.md) | 中文 + +## 问题 + +浏览器 worker 预览的存在意义是观察某个 pull request 的前端与 host 代码运行态，因此需要一个外人无法访问的、按 pull request 隔离的静态托管。GitHub Pages 的私有发布只在 GitHub Enterprise Cloud 上可用，而本组织尚未定夺；且一个仓库一个 Pages 站点无法隔离多个 pull request。首次部署运行还暴露了一个打包缺陷：干净 checkout 上 `pnpm install` 永远不会创建 `dsh-pack-vfs-image` 的 bin 链接，`build:preview` 在任何「install 不是在 build 之后跑的」工作树上都以 `command not found` 失败。 + +## 决定 + +**部署。**pull request 的每次推送把 `apps/web/dist` 发布到 Cloudflare Pages 项目 `dsh-build-preview` 的分支别名 `pr-` 下，置于 Cloudflare Access 之后（`.github/workflows/build-preview-cloudflare.yml`）。上传只携带构建产物——平台永远拿不到仓库源码，sourcemap 因内嵌完整源码在上传前删除。`preview.html` 顶替 `index.html` 成为部署根：served 页面没有 host 注入 `window.__DSH_BOOT__` 就无法启动，所以根必须是能启动的那张页。同一 pull request 内最新构建胜出；不同 pull request 各占各的别名 URL，互不争抢。运行只有在 service token 请求证明受保护 URL 真的送达打包镜像后才算通过：HTTP 200（Access 放行了该 token；302 意味着 Access 策略缺 Service Auth 规则）、无 `content-encoding`（平台不得对已压缩的 body 声明传输压缩，否则 worker 的 `DecompressionStream` 会对着解开的裸 tar 充气）、gzip 魔数 `1f 8b`。带标记守卫的评论对每个 pull request 只报一次稳定别名 URL。 + +**bin 链接。**pnpm 只在链接目标于 install 时已存在的情况下创建 workspace bin 链接。`bin` 指向构建产物（`lib/bin.js`）因此在干净 checkout 上永远得不到链接——事后构建不会补建链接。packer 在包根提交 `bin.js` 作为稳定链接目标；它转发到 `lib/bin.js`，构建产物缺失时点名 `pnpm run build` 并以 1 退出。与 `dsh-subprocess-local` 提交 spawn-helper 入口是同一模式。 + +## 曾考虑的替代方案 + +**GitHub Pages 私有发布。**Enterprise Cloud 独占，且 `deploy-pages` 整站替换，多个 pull request 会互相覆盖；按分支子目录要走遗留的分支部署通道并吃其构建频率限制。 + +**用 Actions artifact 当预览。**下载权限与仓库 read 权限逐字对齐、零成本，但 artifact 是 zip 下载不是可浏览的站点。留作 Cloudflare 面失效时的兜底。 + +**用「build 之后再 install 一次」的文档说明代替提交链接目标。**让每个干净 checkout 都以一种错误信息解释不了的、依赖顺序的方式坏掉；CI 每次运行恰恰就是这样的 checkout。 + +## 后果 + +pull request 的预览位于 `https://pr-.dsh-build-preview.pages.dev`，访问要求 Cloudflare Access 登录；自动化用 service token 通行。部署平台不持有源码与 sourcemap，这也意味着在 sourcemap 处理被专门设计之前，预览无法把 bundle 映射回源码。镜像的字节通路——压缩存储、无传输再编码送达——在每次部署时被断言，平台行为变化会让运行失败而不是让 worker 启动失败。packer bin 在任何干净 checkout 上一次完整构建后即可用，constraints 表把 `bin.js` 钉进发布文件清单。 diff --git a/.agents/notes/implemented/feature/2026-08-18-web-home-path-tilde.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-20-webworker-node-face.i18n.yaml similarity index 59% rename from .agents/notes/implemented/feature/2026-08-18-web-home-path-tilde.i18n.yaml rename to .agents/notes/implemented/architecture/2026-08-20-webworker-node-face.i18n.yaml index 0c4a921c34..4b5a98a8d5 100644 --- a/.agents/notes/implemented/feature/2026-08-18-web-home-path-tilde.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-20-webworker-node-face.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-18-web-home-path-tilde.md -2026-08-18-web-home-path-tilde.md: b148833bab09eadce4c9c1a362dd99d04eba5977 -2026-08-18-web-home-path-tilde.zh.md: 9d15cd6dca1128927389d5731dff6bf831cffe76 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-20-webworker-node-face.md +2026-08-20-webworker-node-face.md: 08119cce96eff244f8e9ada3462ce5d35c1b538d +2026-08-20-webworker-node-face.zh.md: 573c0be055d066d2d6d0db11a2476ba528517727 diff --git a/.agents/notes/implemented/architecture/2026-08-20-webworker-node-face.md b/.agents/notes/implemented/architecture/2026-08-20-webworker-node-face.md new file mode 100644 index 0000000000..08119cce96 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-20-webworker-node-face.md @@ -0,0 +1,34 @@ +# Agent Note: the worker's Node face — builtins, VFS, and the shell process layer + +Status: implemented + +English | [中文](2026-08-20-webworker-node-face.zh.md) + +## Problem + +The worker runs the web profile's Cordis configuration byte for byte — no worker-specific rows — so a browser's missing platform must be replaced at the module layer, where a proxied module keeps its identity and changes its implementation. That covers three fronts: the Node builtins the tree imports, the filesystem those builtins answer from, and a process layer for the bash tool, which mounted, advertised itself to the model, and then failed on every call while `node:child_process` was a structural stub. + +## Decision + +**Builtins.** The proxy table replaces Node builtins and external npm packages, never workspace or vendored modules. `./implemented/.ts` carries real semantics over a worker data source; `./mock/.ts` mounts silently and reports the missing capability when a call reaches it. The loader's table holds one memoized thunk per specifier — evaluation happens at first `require`, not at assembly — and each shim's exported face typechecks against Node's own module type, with the narrow, documented exceptions where structural identity (a real class) cannot be satisfied. The worker installs the `process` global itself and fills it into the table at assembly. + +**VFS.** Memory is the truth. `statSync(path, { bigint: true })` returns Node's BigInt shape, and two fields carry real information because `dsh-fs-local`'s stale-write guard depends on them: `ino` is per-path identity from a monotonic counter (a recreated path reports a new identity), and `mtimeMs` is strictly increasing per entry (`max(now, previous + 1)`), because in-memory writes routinely land in one millisecond and an equal timestamp would let a stale overwrite pass. The hunt that produced this also fixed the silence around it: cordis's logger verbosity counts UP, so an exporter that declares no level drops every warning — `startWorkerHost` installs a console exporter with `levels: { default: 2 }` before any entry mounts. + +**Shell.** `node:child_process` is a real implementation over the VFS. The grammar is bought — `@yarnpkg/parsers`' `parseShell` — and the evaluator and command table are owned, because every candidate interpreter brings its own filesystem: pipelines are strings handed along, and each program is a function over the VFS. The table is the machine's whole `/bin`; an absent name reports `command not found` (127). Each `spawn` starts a child Web Worker from this same bundle, its first frame declaring the shell-process role, so the termination ladder is real: `SIGTERM` asks at the next command boundary, `SIGKILL` terminates the worker mid-loop — the preemption an in-thread interpreter can never have. The filesystem face is asynchronous end to end (child frames to the host VFS); `execSync`, `execFileSync`, and `fork` refuse, and `node-pty` stays a stub. + +## Alternatives considered + +**Replacing `dsh-subprocess-local` or the bash executor.** The first would let the proxy table replace a workspace package against its own classification and invert the layering; the second trips `dsh-permission-presets`' boot-time `sandboxMode` validation and drops tested timeout/output behavior. + +**`@yarnpkg/shell`, WASM shells, WebContainer.** The matching interpreter is built on real Node streams (~1.5 MB closure to own); WASM was removed from this deployment by decision and WASI has no `fork`; all of them arrive with their own filesystem, the one part that cannot be reused. + +**`SharedArrayBuffer` + `Atomics.wait` for a synchronous child filesystem.** Measured on the deployment target: without COOP/COEP headers `SharedArrayBuffer` is not defined, and GitHub Pages cannot set response headers. The asynchronous face is a superset; a SAB backend can slot under it later without touching a program. + +**Fabricating stats or widening error predicates instead of honoring `bigint`.** Constant `ino`/wall-clock `mtimeNs` silently disable the stale-write guard; swallowing `FS_IO_ERROR` in skill discovery would have made the same bug a permanently empty catalog with no failure anywhere. + +## Consequences + +- Sandbox modes other than `danger-full-access` fail loud: `SandboxEnforcement` has no "nothing was enforced" value and a browser has no kernel, so `ctx.sandbox.confine` fails closed and the command never starts. Real enforcement at the VFS frame gate is a designed follow-up, not this note. +- The Node-host ladder test (`tests/node/child-process.spec.ts`) is registered windows-unsupported: the ladder's win32 kill rung is taskkill-by-real-pid, undeliverable to a process-table pid, while the worker itself always reports `linux`. +- Output is incremental but not streamed: programs write into sinks forwarded as `data` events, and a pipeline stage completes before the next starts. +- The runtime's tests mirror `src/` (`tests/node/`, `tests/shell/`, `tests/storage/`, …), so each shim family owns its behavior cases beside the oracle-diff suites. diff --git a/.agents/notes/implemented/architecture/2026-08-20-webworker-node-face.zh.md b/.agents/notes/implemented/architecture/2026-08-20-webworker-node-face.zh.md new file mode 100644 index 0000000000..573c0be055 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-20-webworker-node-face.zh.md @@ -0,0 +1,34 @@ +# Agent Note：worker 的 Node 面——builtin、VFS 与 shell 进程层 + +状态：已实施 + +[English](2026-08-20-webworker-node-face.md) | 中文 + +## 问题 + +worker 逐字节运行 web profile 的 Cordis 配置——没有 worker 专属行——因此浏览器缺失的平台必须在模块层被替换：被代理的模块保持身份、更换实现。这覆盖三条战线：树所 import 的 Node builtin、这些 builtin 背后应答的文件系统，以及 bash 工具的进程层——在 `node:child_process` 还是结构桩的时期，工具照常挂载、向模型自我宣告，然后每次调用都失败。 + +## 决定 + +**Builtin。** 代理表只替换 Node builtin 与外部 npm 包，绝不替换 workspace 或 vendored 模块。`./implemented/.ts` 在 worker 数据源之上承载真语义；`./mock/.ts` 静默挂载、在调用真正抵达时报告缺失的能力。装载器的表按 specifier 各持一个 memoized thunk——求值发生在首次 `require` 而非装配期——且每个垫片的导出面对 Node 自身的模块类型作类型检查，仅在结构身份（真实类）确不可满足处留最窄的、有说明的例外。`process` 全局由 worker 自装，装配期填入表中。 + +**VFS。** 内存为真相。`statSync(path, { bigint: true })` 返回 Node 的 BigInt 形状，其中两个字段承载真实信息，因为 `dsh-fs-local` 的 stale-write guard 依赖它们：`ino` 是按路径的身份（单调计数器分配，路径重建即新身份），`mtimeMs` 按条目严格递增（`max(now, previous + 1)`）——内存写例行落在同一毫秒内，相等的时间戳会放过陈旧覆写。这场排查同时修掉了它周围的静默：cordis 日志器的详细度数值向上计数，未声明等级的 exporter 会丢掉所有 warning——`startWorkerHost` 在任何 entry 挂载前安装 `levels: { default: 2 }` 的 console exporter。 + +**Shell。** `node:child_process` 是 VFS 之上的真实现。语法是买来的——`@yarnpkg/parsers` 的 `parseShell`——求值器与命令表是自有的，因为每个候选解释器都自带文件系统：管道是逐段传递的字符串，每个程序是 VFS 上的一个函数。命令表就是这台机器的全部 `/bin`；不存在的名字报告 `command not found`（127）。每次 `spawn` 从同一个 bundle 起一个子 Web Worker，首帧声明 shell 进程角色，因此终止梯是真的：`SIGTERM` 在下一命令边界处请求停止，`SIGKILL` 在任意时刻终止 worker——这是线程内解释器永远没有的抢占。文件系统面端到端异步（子进程经帧到宿主 VFS）；`execSync`、`execFileSync`、`fork` 拒绝，`node-pty` 保持桩。 + +## 曾考虑的替代方案 + +**整包替换 `dsh-subprocess-local` 或替换 bash 执行器。** 前者让代理表首次替换 workspace 包、违背其自身分类并倒置分层；后者撞上 `dsh-permission-presets` 对 `sandboxMode` 的 boot 期硬校验，并丢掉执行器已被测试钉住的超时/输出行为。 + +**`@yarnpkg/shell`、WASM shell、WebContainer。** 配套解释器建立在真实 Node streams 之上（约 1.5 MB 闭包要自养）；WASM 已被本部署的决定排除，WASI 没有 `fork`；且它们全都自带文件系统——恰是无法复用的那部分。 + +**`SharedArrayBuffer` + `Atomics.wait` 给子进程同步文件系统。** 在部署目标实测：无 COOP/COEP 头时 `SharedArrayBuffer` 未定义，而 GitHub Pages 无法设置响应头。异步面是超集；SAB 后端将来可垫入其下而不动任何程序。 + +**伪造 stats 或放宽错误谓词，而非如实实现 `bigint`。** 常量 `ino`/纯挂钟 `mtimeNs` 会静默废掉 stale-write guard；让技能发现吞下 `FS_IO_ERROR` 则会把同一个 bug 变成处处无失败的永久空目录。 + +## 后果 + +- `danger-full-access` 之外的沙箱档 fail loud：`SandboxEnforcement` 没有「未执法」值、浏览器没有内核，`ctx.sandbox.confine` 落闭、命令零启动。在 VFS 帧闸口做真执法是设计中的后续，不属本条。 +- Node 宿主的阶梯测试（`tests/node/child-process.spec.ts`）登记为 windows 不支持：阶梯的 win32 kill 梯级是按真 pid 的 taskkill，对进程表 pid 不可投递，而 worker 自身恒报 `linux`。 +- 输出增量但不流式：程序写入的 sink 以 `data` 事件转发，一个管道阶段完成后下一阶段才开始。 +- 运行时的测试镜像 `src/`（`tests/node/`、`tests/shell/`、`tests/storage/`……），每个垫片族在 oracle-diff 套件旁拥有自己的行为用例。 diff --git a/.agents/notes/implemented/bug-fix/2026-08-04-large-history-pagination-call-stack.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-20-webworker-pack-lowering-and-preview.i18n.yaml similarity index 54% rename from .agents/notes/implemented/bug-fix/2026-08-04-large-history-pagination-call-stack.i18n.yaml rename to .agents/notes/implemented/architecture/2026-08-20-webworker-pack-lowering-and-preview.i18n.yaml index 96fb51ced0..b93c9676cb 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-04-large-history-pagination-call-stack.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-20-webworker-pack-lowering-and-preview.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-04-large-history-pagination-call-stack.md -2026-08-04-large-history-pagination-call-stack.md: 28c22121123a227c507c506683ae727d238d98bd -2026-08-04-large-history-pagination-call-stack.zh.md: 57dde9bdc0a4aa52e1af024eb606bf9258430fa7 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-20-webworker-pack-lowering-and-preview.md +2026-08-20-webworker-pack-lowering-and-preview.md: 37c7730c5da664560156a8e4bd9ba594c78369ee +2026-08-20-webworker-pack-lowering-and-preview.zh.md: 09d9356ee8744ba2406bd765a6ca6a060f93853a diff --git a/.agents/notes/implemented/architecture/2026-08-20-webworker-pack-lowering-and-preview.md b/.agents/notes/implemented/architecture/2026-08-20-webworker-pack-lowering-and-preview.md new file mode 100644 index 0000000000..37c7730c5d --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-20-webworker-pack-lowering-and-preview.md @@ -0,0 +1,35 @@ +# Agent Note: pack-time lowering and the single-build preview + +Status: implemented + +English | [中文](2026-08-20-webworker-pack-lowering-and-preview.zh.md) + +## Problem + +The browser worker can neither compile modules at load nor be served by the product webserver: every module body must arrive runnable, and the page must be a static artifact. Both surfaces drifted early. The loader carried a fallback compiler, so a collector gap surfaced as a slow boot instead of a broken image — and `acorn` rode into `lib/worker.js` through the package barrel, a parser a runtime that only wraps pre-lowered bodies never needs. The preview was a second HTML template beside the served one, a page the served index could silently drift away from. + +## Decision + +**Lowering happens at pack time only.** `@deepseek-ai/dsh-experimental-webworker-packer` composes the profile, materializes the closure, and lowers every JavaScript body; `LOWERING_VERSION` and `WRAPPER_PARAMS` are the pack↔worker contract and live in `src/image-layout.ts` beside the rest of the image layout. The loader wraps bodies exactly as the image holds them: a body still carrying module syntax is a refusal naming the image, and `startWorkerHost` requires the manifest's `lowered` to equal this build's contract before it mounts a single module. `lowerModuleSource` is the transform's only face and the packer its only caller; inside the worker graph, imports name the module that owns the value — never the package barrel, which is the edge that smuggled the parser in. + +**The preview is the served page plus one tag.** One Vite build emits `dist/index.html` and `dist/preview.html` sharing every chunk; the only difference is a prepended bootstrap entry whose module connects the worker host. Startup then converges on one protocol: whichever side applies the injection table settles the `__DSH_BOOT_READY__` deferred — the served renderer resolves it in a tail script after the rendered rows, the worker bootstrap installs it before its first await and settles it after the last row — and the client entry awaits it before reading any injected state, so the chain from the stock entry onward is the served chain verbatim. The build uses a relative base so the output mounts under any static directory; the served form anchors deep SPA-fallback paths by rendering `` at serve time, keeping the on-disk pages byte-shared. + +Both packages live in `packages/experimental/` as `@deepseek-ai/dsh-experimental-*`, private and outside official releases. The boundary that carries product promises stays in the product packages: the injection table, `__DSH_TRANSPORT__`, and the `/plugins` bundle bytes are owned by `dsh-host-webserver`, `dsh-client-modules`, and `dsh-client-connection`. + +## Alternatives considered + +**A load-time transform as a safety net.** It turned a broken image into a timing regression nobody attributed, and made "which path lowered this body" unanswerable from outside. + +**Contract constants inside the transform, trusting tree shaking.** The transform functions did shake out, but `acorn` declares no `sideEffects`, so the barrel edge alone carried the whole parser into the worker bundle. + +**A separate preview template.** The retired `preview.html` template duplicated the served document and drifted (language, title, entry wiring). Deriving the page from the built index at `closeBundle` removes the second document entirely. + +**Gating the stock entry on top-level await ordering instead of a deferred.** Sibling module scripts do not wait for one another's top-level awaits; the `??=`-installed deferred makes the handshake order-independent and lets a failed handshake reject into the boot page's failure rendering. + +## Consequences + +- `lib/worker.js` contains no parser (423.5 kB → 246.3 kB at the time of the cut, before the shell process layer landed). +- `diff dist/index.html dist/preview.html` is exactly one script tag; `packages/experimental/webworker-packer/tests/image-loadable.spec.ts` pins both halves of the loader contract, and `apps/web/tests/preview-boot.e2e.ts` pins preview usability (boot to an interactive page) in the web browser lane, replacing the retired `apps/web/scripts/preview/` probe scripts. +- The transform corpus imports every built bundle through Node before comparing its lowered exports. Its pinned exemptions name the actual non-importable bundle and fail when one becomes importable: after Win32 process primitives became the Koffi type owner, `win32-process` carries the duplicate-type exemption and `sandbox-windows-acl` does not. +- The served `` anchor exists because relative asset URLs would resolve under the request directory on SPA-fallback paths; remove it only together with the relative build base. +- The image ships as a deterministically gzip-compressed tar (`vfs-image.tar.gz`; MTIME 0, OS byte 0xff): static hosts do not compress binary content types (type allowlists, CDN size caps), so the compression rides the artifact, and the worker inflates the fetch body through the browser's native `DecompressionStream` while it downloads. diff --git a/.agents/notes/implemented/architecture/2026-08-20-webworker-pack-lowering-and-preview.zh.md b/.agents/notes/implemented/architecture/2026-08-20-webworker-pack-lowering-and-preview.zh.md new file mode 100644 index 0000000000..09d9356ee8 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-20-webworker-pack-lowering-and-preview.zh.md @@ -0,0 +1,35 @@ +# Agent Note：pack 期 lowering 与单构建 preview + +状态：已实施 + +[English](2026-08-20-webworker-pack-lowering-and-preview.md) | 中文 + +## 问题 + +浏览器 worker 既不能在装载期编译模块，也不能由产品 webserver 提供页面：每个模块体必须以可直接运行的形态到达，页面必须是静态产物。两个面早期都发生过漂移。装载器曾携带一个兜底编译器，于是收集器的缺口表现为「启动变慢」而不是「镜像坏了」——而且 `acorn` 经包 barrel 混进了 `lib/worker.js`，一个只包装预 lowered 模块体的运行时根本不需要解析器。preview 曾是服务页面旁的第二份 HTML 模板，一个 served index 可以悄悄漂离的页面。 + +## 决定 + +**Lowering 只发生在 pack 期。** `@deepseek-ai/dsh-experimental-webworker-packer` 组合 profile、物化闭包、lower 每个 JavaScript 模块体；`LOWERING_VERSION` 与 `WRAPPER_PARAMS` 是 pack↔worker 的契约，与镜像布局的其余部分一起放在 `src/image-layout.ts`。装载器完全按镜像持有的形态包装模块体：仍带模块语法的模块体是一次点名镜像的拒绝，且 `startWorkerHost` 在挂载任何模块之前要求 manifest 的 `lowered` 等于本构建的契约。`lowerModuleSource` 是转换器唯一的面、packer 是它唯一的调用方；worker 图内部的 import 一律指向拥有该值的模块——绝不指向包 barrel，那正是把解析器偷运进来的那条边。 + +**preview 就是服务页面加一个标签。** 一次 Vite 构建产出共享全部 chunk 的 `dist/index.html` 与 `dist/preview.html`；唯一差异是前插的一个引导入口，其模块负责连接 worker host。启动随之汇于一个协议：应用注入表的一方 settle `__DSH_BOOT_READY__` deferred——served 渲染器在渲染完的行之后用尾部脚本 resolve，worker 引导段在首个 await 之前安装、末行生效后 settle——client 入口在读取任何注入状态前 await 它，因此从标准入口起的链路逐字就是 served 链路。构建使用相对 base，产物可挂载于任意静态目录；served 形态在 serve 期渲染 `` 锚定深层 SPA fallback 路径，磁盘上的两个页面保持字节共享。 + +两个包以 `@deepseek-ai/dsh-experimental-*` 名义放在 `packages/experimental/`，私有且在官方发布之外。承载产品承诺的边界仍在产品包里：注入表、`__DSH_TRANSPORT__` 与 `/plugins` bundle 字节由 `dsh-host-webserver`、`dsh-client-modules`、`dsh-client-connection` 拥有。 + +## 曾考虑的替代方案 + +**保留装载期转换器作安全网。** 它把坏镜像变成无人归因的耗时回归，并且让「这个模块体是谁 lower 的」从外部不可回答。 + +**契约常量留在转换器里，信任 tree shaking。** 转换函数确实被摇掉了，但 `acorn` 未声明 `sideEffects`，仅 barrel 一条边就把整个解析器带进了 worker bundle。 + +**独立的 preview 模板。** 已退役的 `preview.html` 模板复制了服务文档并发生漂移（语言、标题、入口接线）。在 `closeBundle` 从 built index 派生页面则彻底消灭了第二份文档。 + +**用顶层 await 顺序而非 deferred 去闸标准入口。** 兄弟 module script 互不等待对方的顶层 await；`??=` 安装的 deferred 使握手与求值顺序无关，且失败的握手能 reject 进 boot 页的失败呈现。 + +## 后果 + +- `lib/worker.js` 不含解析器（当刀落时为 423.5 kB → 246.3 kB，早于 shell 进程层落地）。 +- `diff dist/index.html dist/preview.html` 恰为一个 script 标签；`packages/experimental/webworker-packer/tests/image-loadable.spec.ts` 钉住装载器契约的两半，`apps/web/tests/preview-boot.e2e.ts` 在 web 浏览器车道钉住 preview 可用性（boot 到可交互页面），替代已撤编的 `apps/web/scripts/preview/` 探针脚本。 +- 转换 corpus 会先通过 Node 导入每个已构建 bundle，再比较 lowered export。固定豁免会点名真正不可导入的 bundle，并在其恢复可导入时失败：`win32-process` 是 Koffi 类型 owner 并承担重复类型豁免；`sandbox-windows-acl` 可正常导入，不承担该豁免。 +- served 的 `` 锚存在的原因是：相对资产 URL 在 SPA fallback 深路径下会解析进请求目录；只有与相对构建 base 一起才可移除它。 +- 镜像以确定性 gzip 压缩的 tar 交付（`vfs-image.tar.gz`；MTIME 0、OS 字节 0xff）：静态托管不压缩二进制 content-type（类型白名单、CDN 尺寸帽），压缩必须随制品走；worker 用浏览器原生 `DecompressionStream` 在下载的同时解压 fetch body。 diff --git a/.agents/notes/implemented/bug-fix/2026-07-29-atomic-web-image-admission.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-29-atomic-web-image-admission.i18n.yaml index d5c2e38a49..a897753a57 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-29-atomic-web-image-admission.i18n.yaml +++ b/.agents/notes/implemented/bug-fix/2026-07-29-atomic-web-image-admission.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-07-29-atomic-web-image-admission.md -2026-07-29-atomic-web-image-admission.md: c09d376f101a41994df3a10c22c06da4e59f06f6 -2026-07-29-atomic-web-image-admission.zh.md: 8785f7489b0c433cba43a1747533b1d38aada3d3 +2026-07-29-atomic-web-image-admission.md: dd2faf1e14c6147c80bcba571d5310899c2e8e22 +2026-07-29-atomic-web-image-admission.zh.md: 8f15f8848dcb38fe6be178b86082a72b4ff0c8eb diff --git a/.agents/notes/implemented/bug-fix/2026-07-29-atomic-web-image-admission.md b/.agents/notes/implemented/bug-fix/2026-07-29-atomic-web-image-admission.md index c09d376f10..dd2faf1e14 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-29-atomic-web-image-admission.md +++ b/.agents/notes/implemented/bug-fix/2026-07-29-atomic-web-image-admission.md @@ -6,24 +6,24 @@ English | [中文](2026-07-29-atomic-web-image-admission.zh.md) ## Problem -Image prompt admission and `session.selectModel` each read session modality state across asynchronous model and attachment lookups. Without one ordering boundary, an image prompt could validate an image-capable target while a concurrent selection installed a text-only target, or selection could miss a prompt after inbox dequeue but before its durable message event. Scanning the immutable event log avoided the second race but permanently blocked a text-only selection even after compaction removed the image from current model history. +Image prompt admission and `session.selectModel` each cross asynchronous model and attachment lookups. Without one ordering point, an image prompt could validate an image-capable target while a concurrent selection installed a text-only target. Selection could also change the route after admission had begun but before the durable message event was published. ## Decision -Each live Web agent has one private promise chain shared by image-bearing prompt admission and model selection. A failed operation settles its caller normally and leaves the chain usable. Text-only prompts bypass the chain because they cannot change the modality constraint. +Each live Web agent has one private promise chain shared by image-bearing prompt admission and model selection. A failed operation settles its caller normally and leaves the chain usable. Text-only prompts bypass the chain because they cannot create this ordering conflict. -The pending-publication set records a queued occurrence at dequeue and a steering occurrence already at enqueue (steering items never enter the queued UI mirror), and retains each until its matching `user/message` or `steering/message` event publishes. If admission ends without publishing, the transition to idle retires the entries; inbox discard retires the listed work, and session disposal retires every remaining entry. Model selection checks that set, the queued UI mirror, and `Session.deriveMessages()`, which is the current model-visible history after compaction. +The chain gives the two operations a deterministic order. When selection runs first, later image admission observes the selected model and refuses an unsupported image before persistence. When image admission runs first, its attachment and event publication complete before selection changes the route. The shared LLM runtime can then project durable image blocks to deterministic text placeholders for a text-only request without rewriting the session log. Steering uses the same admission chain even though it does not enter the queued UI mirror. Provider adapters remain the final enforcement boundary. The host ordering only prevents its mutable route and pending image state from contradicting each other before request assembly. ## Alternatives considered -**Scan every immutable session event.** This catches published images but treats compacted-away content as permanently model-visible, preventing a valid later switch to a text-only route. +**Scan durable or derived history before selection.** This prevented a text-only route from being selected whenever history contained an image. Request-local projection now supports that route directly, so history is no longer a selection constraint. -**Retire the pending mirror at inbox dequeue.** Dequeue precedes the durable message append and leaves the exact interval in which model selection can miss both pending and published state. +**Track pending publication separately.** A queued occurrence could be retained from dequeue through its matching event. The promise chain already keeps selection behind the complete admission operation, so a second lifecycle mirror is unnecessary. **Serialize every prompt and session mutation.** Text-only prompts and unrelated session operations cannot introduce an image requirement. A broader lock would add latency and ownership without closing another modality race. ## Consequences -An image prompt and a concurrent model selection have deterministic order, and a text-only target cannot strand an image that has been admitted but not yet published. Selection may wait for an in-flight image admission, while unrelated prompts retain their existing concurrency. Compaction can make a text-only target valid once no pending or derived image remains. +An image prompt and a concurrent model selection have deterministic order. Selection may wait for in-flight image admission, while unrelated text prompts retain their existing concurrency. Text-only model selection remains available after images enter durable history because request assembly projects those images to placeholders. diff --git a/.agents/notes/implemented/bug-fix/2026-07-29-atomic-web-image-admission.zh.md b/.agents/notes/implemented/bug-fix/2026-07-29-atomic-web-image-admission.zh.md index 8785f7489b..8f15f8848d 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-29-atomic-web-image-admission.zh.md +++ b/.agents/notes/implemented/bug-fix/2026-07-29-atomic-web-image-admission.zh.md @@ -6,24 +6,24 @@ Status: implemented ## 问题 -包含图片的提示词准入与 `session.selectModel` 都会在跨越异步模型查询与附件查询的过程中读取会话模态状态。如果没有统一的顺序边界，包含图片的提示词可能在支持图片的目标上通过校验，并发的选择操作却设置了纯文本目标；选择操作也可能在提示词已从 inbox 出队、但其持久消息事件尚未发布时漏掉该提示词。扫描不可变事件日志可以避免第二种竞态，但即使压缩（compaction）已经从当前模型历史中移除图片，仍会永久阻止选择纯文本目标。 +包含图片的提示词准入与 `session.selectModel` 都会跨越异步模型查询和附件查询。没有统一的排序点时，包含图片的提示词可能在支持图片的目标上通过校验，并发选择却设置了纯文本目标。选择也可能在准入已经开始、持久消息事件尚未发布时改变路由。 ## 决策 -每个活跃 Web agent（智能体）都有一条私有 promise 链，由包含图片的提示词准入与模型选择共享。操作失败会照常传递给调用方，且不会使该链失效。纯文本提示词绕过该链，因为它们不会改变模态约束。 +每个活跃 Web agent（智能体）都有一条私有 promise 链，由包含图片的提示词准入与模型选择共享。操作失败会照常传递给调用方，且不会使该链失效。纯文本提示词绕过该链，因为它们不会产生这类排序冲突。 -待发布集合会在排队条目出队时记录它，而 steering 条目在入队时即被记录（steering 条目从不进入排队 UI 镜像），并各自保留到匹配的 `user/message` 或 `steering/message` 事件发布。若准入结束时未发布事件，转为空闲状态会移除这些条目；inbox 丢弃会移除列出的工作项，会话 dispose（资源释放）则会移除所有剩余条目。模型选择会检查该集合、排队 UI 镜像以及 `Session.deriveMessages()`；后者表示压缩后模型当前可见的历史。 +该链为两个操作提供确定顺序。模型选择先执行时，后续图片准入会看到已选模型，并在持久化之前拒绝不支持的图片。图片准入先执行时，附件和事件会在模型选择改变路由之前完成发布。之后，共享 LLM 运行时可以在纯文本请求中把持久图片块投影为确定的文本占位符，无需改写会话日志。steering 不进入排队 UI 镜像，但仍使用同一条准入链。 提供方适配器仍是最终的强制检查边界。宿主的顺序控制仅用于避免其可变路由与待发布图片状态在请求组装前彼此矛盾。 ## 曾考虑的替代方案 -**扫描每个不可变会话事件。** 这能捕获已发布的图片，但会把经压缩移除的内容视为永久对模型可见，从而阻止之后合法切换到纯文本路由。 +**选择前扫描持久历史或派生历史。** 这会在历史包含图片时阻止选择纯文本路由。请求期投影已经可以直接支持该路由，因此历史不再是选择约束。 -**在 inbox 出队时退役待处理镜像。** 出队早于持久消息追加，因此恰好会留下一个时间区间，让模型选择既看不到待处理状态，也看不到已发布状态。 +**单独跟踪待发布状态。** 排队条目可以从出队一直保留到匹配事件发布。promise 链已经让模型选择等待完整的准入操作，因此不需要第二套生命周期镜像。 **序列化每个提示词和会话变更。** 纯文本提示词和无关的会话操作无法引入图片要求。更宽的锁会增加延迟与所有权复杂度，却不会再消除任何模态竞态。 ## 后果 -包含图片的提示词准入与并发模型选择之间具有确定的先后顺序，纯文本目标无法使已获准入但尚未发布的图片搁浅。模型选择可能等待正在进行的图片准入完成，而无关提示词仍按现有方式并发处理。当没有图片等待发布，且派生历史经过压缩后也不再含图片时，纯文本目标可以变得有效。 +包含图片的提示词准入与并发模型选择之间具有确定顺序。模型选择可能等待正在进行的图片准入完成，无关的纯文本提示词仍按现有方式并发处理。图片进入持久历史后仍可选择纯文本模型，因为请求组装会把图片投影为占位符。 diff --git a/.agents/notes/implemented/bug-fix/2026-07-29-human-transcript-append-origin.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-29-human-transcript-append-origin.i18n.yaml index cc523de6ac..7593352560 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-29-human-transcript-append-origin.i18n.yaml +++ b/.agents/notes/implemented/bug-fix/2026-07-29-human-transcript-append-origin.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-07-29-human-transcript-append-origin.md -2026-07-29-human-transcript-append-origin.md: 5e9b5c254d54a7eb189f353f44cd6eb18c1bc2df -2026-07-29-human-transcript-append-origin.zh.md: 51cf6e2f122f8f452213ce1d5ed02bb1a7eeba70 +2026-07-29-human-transcript-append-origin.md: 72cafb5a1a149bcdb73d885d4e4fc4ac01e48cd2 +2026-07-29-human-transcript-append-origin.zh.md: 79fcc56b7b60082ebd2946d70419a659ff5687b7 diff --git a/.agents/notes/implemented/bug-fix/2026-07-29-human-transcript-append-origin.md b/.agents/notes/implemented/bug-fix/2026-07-29-human-transcript-append-origin.md index 5e9b5c254d..72cafb5a1a 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-29-human-transcript-append-origin.md +++ b/.agents/notes/implemented/bug-fix/2026-07-29-human-transcript-append-origin.md @@ -30,7 +30,7 @@ The terminal's [archived live compaction progress decision](../../archived/featu ## Alternatives considered -**Recognize a checkpoint by shape (a replacement `user/message`).** Rejected: it reads a coincidence of today's producers instead of a declared contract, and any future producer that replaces a range with a user message would silently inherit the compaction marker. The seam already publishes `COMPACT_CHECKPOINT_SOURCE` precisely so consumers can recognize a checkpoint independently of the backend. +**Recognize a checkpoint by shape (a replacement `user/message`).** Rejected: it reads a coincidence of the shipped producer set instead of a declared contract, and any future producer that replaces a range with a user message would silently inherit the compaction marker. The seam already publishes `COMPACT_CHECKPOINT_SOURCE` precisely so consumers can recognize a checkpoint independently of the backend. **Keep rendering the checkpoint as an injected-context card.** Rejected: the framed checkpoint is an instruction envelope written for the model, not human conversation content. Showing it while hiding the history it replaced inverts what the reader needs. diff --git a/.agents/notes/implemented/bug-fix/2026-07-29-human-transcript-append-origin.zh.md b/.agents/notes/implemented/bug-fix/2026-07-29-human-transcript-append-origin.zh.md index 51cf6e2f12..79fcc56b7b 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-29-human-transcript-append-origin.zh.md +++ b/.agents/notes/implemented/bug-fix/2026-07-29-human-transcript-append-origin.zh.md @@ -30,7 +30,7 @@ Status: implemented ## 曾考虑的替代方案 -**按形态识别检查点（一个替换型 `user/message`）。** 被否决：那读取的是当前生产者的巧合而非已声明的约定，而未来任何用用户消息替换一段范围的生产者都会静默地继承压缩标记。seam 已经发布 `COMPACT_CHECKPOINT_SOURCE`，正是为了让消费方与后端无关地识别检查点。 +**按形态识别检查点（一个替换型 `user/message`）。** 被否决：那读取的是已交付生产者集合的巧合而非已声明的约定，而未来任何用用户消息替换一段范围的生产者都会静默地继承压缩标记。seam 已经发布 `COMPACT_CHECKPOINT_SOURCE`，正是为了让消费方与后端无关地识别检查点。 **继续把检查点渲染为注入上下文卡片。** 被否决：带框的检查点是为模型撰写的指令信封，不是人类对话内容。展示它却隐藏它替换掉的历史，正好颠倒了读者的需要。 diff --git a/.agents/notes/implemented/bug-fix/2026-07-30-web-transcript-log-ordered-projection.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-30-web-transcript-log-ordered-projection.i18n.yaml index a33ceea5e1..6db4668e86 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-30-web-transcript-log-ordered-projection.i18n.yaml +++ b/.agents/notes/implemented/bug-fix/2026-07-30-web-transcript-log-ordered-projection.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-07-30-web-transcript-log-ordered-projection.md -2026-07-30-web-transcript-log-ordered-projection.md: 102bdab27eddab8f3f61390b0025c0d6ce0c3edc -2026-07-30-web-transcript-log-ordered-projection.zh.md: d7f6c980db1eeb58fa1315b50ecbd2a62e81e86c +2026-07-30-web-transcript-log-ordered-projection.md: e4c9fdd6fcdec0b14ed2724dd58365e1d98af8b4 +2026-07-30-web-transcript-log-ordered-projection.zh.md: 625bd993a0b20bbbed318edf71d79866fa80bff0 diff --git a/.agents/notes/implemented/bug-fix/2026-07-30-web-transcript-log-ordered-projection.md b/.agents/notes/implemented/bug-fix/2026-07-30-web-transcript-log-ordered-projection.md index 102bdab27e..e4c9fdd6fc 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-30-web-transcript-log-ordered-projection.md +++ b/.agents/notes/implemented/bug-fix/2026-07-30-web-transcript-log-ordered-projection.md @@ -51,9 +51,9 @@ The unmerged manual-compaction-queueing branch fixes the same interleaving bug b **Value-import the predicate** from the new leaf and add `dsh-compaction` to the client `INLINE_SAFE` allowlist. Rejected: the client needs the plugin id, not the predicate — a type is enough, and an erased import never reaches the purity gate, so nothing has to be admitted to it. The allowlist would only matter for a value import, and there it is a poor trade: `INLINE_SAFE` matches on specifier *prefix*, so admitting the package admits its cordis-importing root along with the leaf. -**A bare shape rule** — any replacement `user/message` is a compaction. Rejected: correct today only because compaction is the sole producer of replacement `user/message`s, with nothing to catch it if that changes. The pinning spec costs one file and removes exactly that risk. +**A bare shape rule** — any replacement `user/message` is a compaction. Rejected: correct only because compaction is the sole producer of replacement `user/message`s, with nothing to catch it if that changes. The pinning spec costs one file and removes exactly that risk. -**Tag the checkpoint host-side** through the projection or wire contract. Rejected: most aligned with the "collaborate through cordis services" rule, but the client folds raw `SessionEvent`s today, so it means a wire contract change out of proportion to one pure predicate. +**Tag the checkpoint host-side** through the projection or wire contract. Rejected: most aligned with the "collaborate through cordis services" rule, but the client folds raw `SessionEvent`s, so it means a wire contract change out of proportion to one pure predicate. **Move frozen-node ownership into the adapter** (`nodes(extraNodes)`), as the unmerged branch does. Rejected: the interrupted nodes come from the `turn/end` sweep `Session` already runs over the window, and with a seq-monotonic transcript the simple shape is correct — the adapter returns nodes, the session merges frozen ones by seq. Widening the adapter's signature would buy nothing and split the sweep from its product. diff --git a/.agents/notes/implemented/bug-fix/2026-07-30-web-transcript-log-ordered-projection.zh.md b/.agents/notes/implemented/bug-fix/2026-07-30-web-transcript-log-ordered-projection.zh.md index d7f6c980db..625bd993a0 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-30-web-transcript-log-ordered-projection.zh.md +++ b/.agents/notes/implemented/bug-fix/2026-07-30-web-transcript-log-ordered-projection.zh.md @@ -51,9 +51,9 @@ const COMPACT_PLUGIN: CompactionCheckpointSource['plugin'] = 'compact' **从新叶子值导入该谓词**，并把 `dsh-compaction` 加入客户端 `INLINE_SAFE` 白名单。已拒绝：客户端需要的是插件 id，不是谓词——一个类型就够了，而被擦除的导入根本不会抵达纯度门禁，因此无需向它放行任何东西。白名单只在值导入时才有意义，而在那里它是笔糟糕的交换：`INLINE_SAFE` 按模块说明符*前缀*匹配，因此放行该包会连它那个会导入 cordis 的根部一起放行。 -**一条纯形状规则**——任何 replacement `user/message` 都是压缩。已拒绝：它今天正确只因为压缩是 replacement `user/message` 的唯一生产者，一旦这点改变便无任何机制能捕获。那个 pin 测试只花一个文件，就精确消除了这一风险。 +**一条纯形状规则**——任何 replacement `user/message` 都是压缩。已拒绝：它正确只因为压缩是 replacement `user/message` 的唯一生产者，一旦这点改变便无任何机制能捕获。那个 pin 测试只花一个文件，就精确消除了这一风险。 -**在宿主侧给检查点打标**，经投影或线协议。已拒绝：这最贴合“经 cordis 服务协作”的规则，但客户端今天折叠的是原始 `SessionEvent`，因此这意味着一次线协议约定变更——为一个纯谓词付出的代价不成比例。 +**在宿主侧给检查点打标**，经投影或线协议。已拒绝：这最贴合“经 cordis 服务协作”的规则，但客户端折叠的是原始 `SessionEvent`，因此这意味着一次线协议约定变更——为一个纯谓词付出的代价不成比例。 **把冻结节点的归属移进适配器**（`nodes(extraNodes)`），像那个未合并分支所做的那样。已拒绝：被打断的节点来自 `Session` 已经在窗口上运行的 `turn/end` 清扫，而在按 seq 单调的记录之上，简单形态就是正确的——适配器返回节点，会话按 seq 归并冻结节点。加宽适配器签名什么也换不到，还会把清扫与它的产物拆开。 diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.i18n.yaml index 4436b5ead9..a96ce55a01 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.i18n.yaml +++ b/.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.md -2026-07-31-composer-text-layers-share-one-scrollport.md: d01231f706a7d3850ce1b3770ef351cb7e211384 -2026-07-31-composer-text-layers-share-one-scrollport.zh.md: 831e2434324ce0dea0e433bbede07e5536def962 +2026-07-31-composer-text-layers-share-one-scrollport.md: 4989ab3bcedcf0ea29b95b565b2e0756ab9d5b62 +2026-07-31-composer-text-layers-share-one-scrollport.zh.md: 95b6d3055775f733f6c700823ce307869d1c0961 diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.md b/.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.md index d01231f706..4989ab3bce 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.md +++ b/.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.md @@ -48,7 +48,7 @@ Revealing the caret is the one thing that now depends on the browser rather than **Scroll both layers from JavaScript, with the textarea `overflow: hidden` and a wheel handler assigning both offsets in one task.** No divergence during wheel gestures, since nothing scrolls without us. Rejected because it replaces native scrolling — momentum, trackpad rubber-banding, scrollbar dragging, keyboard scrolling — with a hand-written approximation, and the caret-reveal path (the browser setting the textarea's own offset) still lands asynchronously. -**Keep the cap on the mirror and just wrap today's structure in a scroller.** The layers would stay window-sized, not draft-sized: `inset: 0` on an absolutely positioned child resolves against the scrollport's padding box, not its scrollable overflow area, so both layers would scroll away from the content that is supposed to be underneath them. The stack has to be the full draft height for the arrangement to mean anything. +**Keep the cap on the mirror and just wrap the existing structure in a scroller.** The layers would stay window-sized, not draft-sized: `inset: 0` on an absolutely positioned child resolves against the scrollport's padding box, not its scrollable overflow area, so both layers would scroll away from the content that is supposed to be underneath them. The stack has to be the full draft height for the arrangement to mean anything. **Give the backdrop `overflow: auto` and let it scroll itself.** It would then have an offset of its own to keep in step, which is the same problem plus a second scrollbar painted over the input. The backdrop is a projection of the textarea, not an independently navigable surface. diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.zh.md b/.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.zh.md index 831e243432..95b6d30557 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.zh.md +++ b/.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.zh.md @@ -48,7 +48,7 @@ Safari 的原生文本控件存在一个引擎例外：跨过软换行阈值的 **两层都由 JavaScript 驱动滚动：textarea 设 `overflow: hidden`，滚轮处理器在同一个任务里给两个偏移赋值。** 滚轮手势期间不会分离，因为没有我们就没有东西会滚动。被否决，是因为它用手写近似替换了原生滚动——惯性、触控板回弹、拖拽滚动条、键盘滚动——而且光标回视路径（浏览器设置 textarea 自己的偏移）仍然是异步落地的。 -**把上限留在镜像层上，只在今天的结构外面套一个滚动容器。** 那样两层仍是「窗口大小」而非「草稿大小」：绝对定位子元素的 `inset: 0` 是相对滚动容器的 padding box 解析的，而不是相对其可滚动溢出区域，于是两层会从本该垫在它们下面的内容上滚开。栈必须与整份草稿等高，这套排布才有意义。 +**把上限留在镜像层上，只在既有结构外面套一个滚动容器。** 那样两层仍是「窗口大小」而非「草稿大小」：绝对定位子元素的 `inset: 0` 是相对滚动容器的 padding box 解析的，而不是相对其可滚动溢出区域，于是两层会从本该垫在它们下面的内容上滚开。栈必须与整份草稿等高，这套排布才有意义。 **给 backdrop 加 `overflow: auto`，让它自己滚动。** 那样它就有了一个自己的偏移需要保持同步，即同一个问题再加一条画在输入框上的滚动条。backdrop 是 textarea 的投影，不是一个可独立导航的界面。 diff --git a/.agents/notes/implemented/bug-fix/2026-08-02-goal-round-wrapup-message.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-08-02-goal-round-wrapup-message.i18n.yaml index 5bbf2c832c..14f569f1f7 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-02-goal-round-wrapup-message.i18n.yaml +++ b/.agents/notes/implemented/bug-fix/2026-08-02-goal-round-wrapup-message.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-02-goal-round-wrapup-message.md -2026-08-02-goal-round-wrapup-message.md: c6bc3d5912b0789efde55880c2be892e98e34a5b -2026-08-02-goal-round-wrapup-message.zh.md: a39f1e7d5705b95fe078b75198d885881842d07c +2026-08-02-goal-round-wrapup-message.md: 22a7d329d28ec989faa890c1b3687ec8b96d4a86 +2026-08-02-goal-round-wrapup-message.zh.md: fb62391655d7e1c2b09207765cf307edde6d5260 diff --git a/.agents/notes/implemented/bug-fix/2026-08-02-goal-round-wrapup-message.md b/.agents/notes/implemented/bug-fix/2026-08-02-goal-round-wrapup-message.md index c6bc3d5912..22a7d329d2 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-02-goal-round-wrapup-message.md +++ b/.agents/notes/implemented/bug-fix/2026-08-02-goal-round-wrapup-message.md @@ -22,7 +22,7 @@ Scripting the keyless proof required one snapshot-harness addition: `dsh-llm-rep ## Alternatives considered -- **Surface the completion text on the `update_goal` UI card** — rejected: `complete` carries no free text today, and adding a `summary` argument would route a user-facing report through tool arguments while still cutting off the model's natural post-result message. +- **Surface the completion text on the `update_goal` UI card** — rejected: `complete` carries no free text, and adding a `summary` argument would route a user-facing report through tool arguments while still cutting off the model's natural post-result message. - **Keep `concludeTurn()` and add a "one more text-only step" loop primitive** — rejected: new `agent-loop` machinery for behavior the ordinary stop already provides once nothing concludes the turn. - **Instruct inside the tool result content** — rejected: the goal tools' canonical output is compact JSON consumed programmatically; a prose instruction block inside it would mix the model-facing contract with the tool's replayable value. diff --git a/.agents/notes/implemented/bug-fix/2026-08-02-goal-round-wrapup-message.zh.md b/.agents/notes/implemented/bug-fix/2026-08-02-goal-round-wrapup-message.zh.md index a39f1e7d57..fb62391655 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-02-goal-round-wrapup-message.zh.md +++ b/.agents/notes/implemented/bug-fix/2026-08-02-goal-round-wrapup-message.zh.md @@ -22,7 +22,7 @@ Goal Round 的 `complete` 或 `blocked` 成功不再调用 `concludeTurn()`。 ## 曾考虑的替代方案 -- **在 `update_goal` 的 UI 卡片上展示完成文本** — 拒绝：`complete` 如今不携带任何自由文本；新增 `summary` 参数会让面向用户的汇报走工具参数通道，而且依然砍掉了模型在结果之后的自然发言。 +- **在 `update_goal` 的 UI 卡片上展示完成文本** — 拒绝：`complete` 不携带任何自由文本；新增 `summary` 参数会让面向用户的汇报走工具参数通道，而且依然砍掉了模型在结果之后的自然发言。 - **保留 `concludeTurn()` 并新增“再多一步纯文本”的 loop 原语** — 拒绝：为常规停止路径已经能提供的行为（只要没有结果终结轮次）增加新的 `agent-loop` 机制。 - **把指令写进工具结果内容** — 拒绝：goal 工具的规范输出是被程序化消费的紧凑 JSON；在其中混入散文指令会把模型侧约定和工具的可回放值搅在一起。 diff --git a/.agents/notes/implemented/bug-fix/2026-08-04-composer-tab-gutter-reservation.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-08-04-composer-tab-gutter-reservation.i18n.yaml index b936c379ef..b4da830df6 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-04-composer-tab-gutter-reservation.i18n.yaml +++ b/.agents/notes/implemented/bug-fix/2026-08-04-composer-tab-gutter-reservation.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-04-composer-tab-gutter-reservation.md -2026-08-04-composer-tab-gutter-reservation.md: 8bd9fb2d86982d82b44a82c55b7303fcd9a5bf4d -2026-08-04-composer-tab-gutter-reservation.zh.md: d3a9691f5f5fb095fc53b4cf6b627025220a8148 +2026-08-04-composer-tab-gutter-reservation.md: 37a07b2b98bc676ff9c11fe90bc8e346f6189690 +2026-08-04-composer-tab-gutter-reservation.zh.md: bd6a7899515505017549960c2a5769e9ab076ca5 diff --git a/.agents/notes/implemented/bug-fix/2026-08-04-composer-tab-gutter-reservation.md b/.agents/notes/implemented/bug-fix/2026-08-04-composer-tab-gutter-reservation.md index 8bd9fb2d86..37a07b2b98 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-04-composer-tab-gutter-reservation.md +++ b/.agents/notes/implemented/bug-fix/2026-08-04-composer-tab-gutter-reservation.md @@ -36,7 +36,7 @@ The reservation is worth what it costs only because the bar takes layout space h - Chat's content column is permanently 8px narrower — in the hero phase and while the transcript is short as well, where no bar is drawn. That is the trade: one card position at every content height, instead of the widest possible column. - The card holds one position across three transitions, by two mechanisms: the reservation keeps Chat's seat at one width across its own phases (short ↔ scrolling transcript, hero ↔ first scrolling turn), and the overlay seat's compensation matches it on the Chat ↔ Trajectory transition ([the seat-width compensation](2026-08-12-composer-overlay-seat-width-compensation.md)). -- The overlay state is now a scroll container. Nothing in it can overflow today; a future view that let its content exceed the column would scroll this box instead of clipping, and would need its own clip the way the Trajectory view already has one. +- The overlay state is now a scroll container. No shipped content can overflow it; a future view that let its content exceed the column would scroll this box instead of clipping, and would need its own clip the way the Trajectory view already has one. - The committed golden records the reserved band, so a change to the sheet's `::-webkit-scrollbar` width — the value that decides how wide the reservation is — arrives as a reviewable diff in this scenario as well as in the sidebar's. ## Testing diff --git a/.agents/notes/implemented/bug-fix/2026-08-04-composer-tab-gutter-reservation.zh.md b/.agents/notes/implemented/bug-fix/2026-08-04-composer-tab-gutter-reservation.zh.md index d3a9691f5f..bd6a789951 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-04-composer-tab-gutter-reservation.zh.md +++ b/.agents/notes/implemented/bug-fix/2026-08-04-composer-tab-gutter-reservation.zh.md @@ -36,7 +36,7 @@ composer 座位在组件树中只有一个节点、一个位置，但它究竟 - Chat 的内容列永久变窄 8px——hero 态与 transcript 尚短、根本不绘制滚动条时同样如此。这就是这笔交易：以最宽的列换取卡片在任何内容高度下都只有一个位置。 - 卡片在三种切换下保持同一位置，由两种机制达成：预留让 Chat 的座位在自身各相位间保持同一宽度（transcript 较短 ↔ 可滚动、hero ↔ 第一个可滚动轮次），Chat ↔ Trajectory 的切换则由覆盖座位的补偿来对齐（[座位宽度补偿](2026-08-12-composer-overlay-seat-width-compensation.zh.md)）。 -- overlay 状态现在是一个滚动容器。今天其中没有任何内容会溢出；将来若有视图允许自身内容超出会话列，这个盒子会滚动而不是裁剪，那个视图就需要像 Trajectory 视图那样自带裁剪。 +- overlay 状态现在是一个滚动容器。其中没有已交付内容会溢出；将来若有视图允许自身内容超出会话列，这个盒子会滚动而不是裁剪，那个视图就需要像 Trajectory 视图那样自带裁剪。 - 提交的 golden 记录了预留条带，因此样式表中 `::-webkit-scrollbar` 宽度的变化——决定这条预留有多宽的那个值——会在本场景中与在侧边栏场景中一样，以可评审的 diff 形式出现。 ## 测试 diff --git a/.agents/notes/implemented/bug-fix/2026-08-06-token-surface-unpriced-replace-compatibility.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-08-06-token-surface-unpriced-replace-compatibility.i18n.yaml index 2a9e6f4e43..7ef0a2a2f9 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-06-token-surface-unpriced-replace-compatibility.i18n.yaml +++ b/.agents/notes/implemented/bug-fix/2026-08-06-token-surface-unpriced-replace-compatibility.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-06-token-surface-unpriced-replace-compatibility.md -2026-08-06-token-surface-unpriced-replace-compatibility.md: cf672a426f20fa65aea9b7b6391a002d41631b4c -2026-08-06-token-surface-unpriced-replace-compatibility.zh.md: 2fc269ebac0e0179e6bea525bec7df915996bc7e +2026-08-06-token-surface-unpriced-replace-compatibility.md: a271d3697c4ca27fcc2bb30358eb54dfe2b05ad8 +2026-08-06-token-surface-unpriced-replace-compatibility.zh.md: 21145723deb690c72bc8341f99efab8eb13e857b diff --git a/.agents/notes/implemented/bug-fix/2026-08-06-token-surface-unpriced-replace-compatibility.md b/.agents/notes/implemented/bug-fix/2026-08-06-token-surface-unpriced-replace-compatibility.md index cf672a426f..a271d3697c 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-06-token-surface-unpriced-replace-compatibility.md +++ b/.agents/notes/implemented/bug-fix/2026-08-06-token-surface-unpriced-replace-compatibility.md @@ -26,7 +26,7 @@ Both projections share the one fold, so neither gains state fields nor bumps its ## Consequences -An unpriced replacement holds the total still instead of shrinking it, so the compacted-away span stays counted: `contextBreakdown.messageTokens` retains the overcount, and `contextPressure.projectedTokens` overestimates occupancy only until the next usage sample re-anchors it, because that figure tracks movement since the sample rather than the absolute level. The error direction is safe — overestimating occupancy at worst invites an earlier compaction. +An unpriced replacement holds the total still instead of shrinking it, so the compacted-away span stays counted: `contextBreakdown.messageTokens` retains the overcount, and `contextPressure.projectedTokens` overestimates occupancy only until the next usage sample re-anchors it, because that figure tracks movement since the sample rather than the absolute level. Overestimating occupancy can only trigger an earlier compaction. The loud failure survives where it still means something: a range-mismatched adjacent claim is a current producer bug and still throws. diff --git a/.agents/notes/implemented/bug-fix/2026-08-06-token-surface-unpriced-replace-compatibility.zh.md b/.agents/notes/implemented/bug-fix/2026-08-06-token-surface-unpriced-replace-compatibility.zh.md index 2fc269ebac..21145723de 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-06-token-surface-unpriced-replace-compatibility.zh.md +++ b/.agents/notes/implemented/bug-fix/2026-08-06-token-surface-unpriced-replace-compatibility.zh.md @@ -26,7 +26,7 @@ Status: implemented ## 影响 -未计价的替换让总量保持不动而不是缩小，因此被压缩（compaction）掉的区段仍被计入：`contextBreakdown.messageTokens` 保留这部分多计的量；`contextPressure.projectedTokens` 会高估占用率，但只持续到下一个用量样本重新锚定为止，因为该数字追踪的是自样本以来的增减，而非绝对水平。误差方向是安全的：高估占用率最坏不过是招致一次更早的压缩。 +未计价的替换让总量保持不动而不是缩小，因此被压缩（compaction）掉的区段仍被计入：`contextBreakdown.messageTokens` 保留这部分多计的量；`contextPressure.projectedTokens` 会高估占用率，但只持续到下一个用量样本重新锚定为止，因为该数字追踪的是自样本以来的增减，而非绝对水平。高估占用率只可能触发更早的压缩。 响亮失败保留在它仍有意义的地方：区间不匹配的相邻声明是现行生产方的缺陷，仍会抛出异常。 diff --git a/.agents/notes/implemented/bug-fix/2026-08-11-preset-card-description-clamp.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-08-11-preset-card-description-clamp.i18n.yaml deleted file mode 100644 index 21b6957cd2..0000000000 --- a/.agents/notes/implemented/bug-fix/2026-08-11-preset-card-description-clamp.i18n.yaml +++ /dev/null @@ -1,6 +0,0 @@ -# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each -# side as of the last confirmed-consistent state. Both languages carry equal authority; -# after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-11-preset-card-description-clamp.md -2026-08-11-preset-card-description-clamp.md: 16ebf371d5af7c9e54fcc37819696b380856d5cb -2026-08-11-preset-card-description-clamp.zh.md: 5b7a18f41e4b3e8acd681a001f6826b19ca7026d diff --git a/.agents/notes/implemented/bug-fix/2026-08-12-composer-overlay-seat-width-compensation.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-08-12-composer-overlay-seat-width-compensation.i18n.yaml index d5045408e2..06746a97a8 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-12-composer-overlay-seat-width-compensation.i18n.yaml +++ b/.agents/notes/implemented/bug-fix/2026-08-12-composer-overlay-seat-width-compensation.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-12-composer-overlay-seat-width-compensation.md -2026-08-12-composer-overlay-seat-width-compensation.md: 0ec4d1272ac1adab5b724dccf44f567e15cc3368 -2026-08-12-composer-overlay-seat-width-compensation.zh.md: e4a56e5bfa5db65cfb68fb9da48c055678434c44 +2026-08-12-composer-overlay-seat-width-compensation.md: 35f1e25c2814d4123a7b70e1ba3fd35c90034da5 +2026-08-12-composer-overlay-seat-width-compensation.zh.md: 7979f25f2ff864f2212a675a2a8811043cdb482a diff --git a/.agents/notes/implemented/bug-fix/2026-08-12-composer-overlay-seat-width-compensation.md b/.agents/notes/implemented/bug-fix/2026-08-12-composer-overlay-seat-width-compensation.md index 0ec4d1272a..35f1e25c28 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-12-composer-overlay-seat-width-compensation.md +++ b/.agents/notes/implemented/bug-fix/2026-08-12-composer-overlay-seat-width-compensation.md @@ -24,7 +24,7 @@ The compensation value is not a literal: ui-theme's scrollbar.css defines `--dsh **Accept the 4px card shift.** Dropping the reservation without compensating the seat would move the input card on every tab switch, which is exactly the symptom the earlier note fixed. Rejected: the card position is a deliberate cross-tab invariant. -**Inset the overlay seat by the bar's width.** The [gutter-reservation note](2026-08-04-composer-tab-gutter-reservation.md) rejected exactly this, and this note adopts it; what changed is the rejection's premise. The number was the engine's, not ours — the WebKit path draws the sheet's 8px bar while the Firefox path draws whatever `scrollbar-width: thin` resolves to — so a hardcoded inset would line the two states up in Chromium and drift elsewhere. The overlay branch reserved an engine-resolved gutter of its own back then, so an inset had to match that width exactly. Today the overlay branch reserves nothing, so the compensation is the overlay side's only mechanism, and the literal half of the rejection is answered by making the 8px a variable that mirrors the `::-webkit-scrollbar` rule in the same diff. The Firefox half remains: Chat reserves the engine-resolved width while the compensation stays fixed, and the residual drift where the two differ is recorded as an accepted cost in Consequences. +**Inset the overlay seat by the bar's width.** The [gutter-reservation note](2026-08-04-composer-tab-gutter-reservation.md) rejected exactly this, and this note adopts it; what changed is the rejection's premise. The number was the engine's, not ours — the WebKit path draws the sheet's 8px bar while the Firefox path draws whatever `scrollbar-width: thin` resolves to — so a hardcoded inset would line the two states up in Chromium and drift elsewhere. The rejected design assumed an engine-resolved gutter in the overlay branch, so an inset had to match that width exactly. The overlay branch reserves nothing, so the compensation is the overlay side's only mechanism, and the literal half of the rejection is answered by making the 8px a variable that mirrors the `::-webkit-scrollbar` rule in the same diff. The Firefox half remains: Chat reserves the engine-resolved width while the compensation stays fixed, and the residual drift where the two differ is recorded as an accepted cost in Consequences. ## Consequences diff --git a/.agents/notes/implemented/bug-fix/2026-08-12-composer-overlay-seat-width-compensation.zh.md b/.agents/notes/implemented/bug-fix/2026-08-12-composer-overlay-seat-width-compensation.zh.md index e4a56e5bfa..7979f25f2f 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-12-composer-overlay-seat-width-compensation.zh.md +++ b/.agents/notes/implemented/bug-fix/2026-08-12-composer-overlay-seat-width-compensation.zh.md @@ -24,7 +24,7 @@ trajectory 表格让这个代价显形：整行分隔线在面板右边缘前 8p **接受 4px 卡片位移。** 去掉预留却不补偿座位，会在每次切换标签页时移动输入卡——正是前一份 note 修复的症状。已拒绝：卡片位置是刻意保持的跨标签页不变量。 -**把 overlay 座位按滚动条宽度内缩。** [滚动条槽预留 note](2026-08-04-composer-tab-gutter-reservation.zh.md) 当初否决的正是这个方案，本 note 采纳了它；变的是否决的前提。这个数字属于引擎而不属于我们——WebKit 路径绘制样式表里的 8px 滚动条，Firefox 路径绘制 `scrollbar-width: thin` 解析出的宽度——因此硬编码的内缩会让两种状态在 Chromium 上对齐、在别处继续漂移。当初 overlay 分支自己预留的是引擎解析出的槽宽，内缩必须精确匹配那个宽度。如今 overlay 分支不预留任何槽位，补偿成为覆盖侧唯一的机制；否决的字面量那一半，通过把 8px 变成与 `::-webkit-scrollbar` 规则同处一个 diff 的变量来回应。Firefox 那一半仍然存在：Chat 预留引擎解析宽度，补偿保持固定 8px，两者不等之处的残余漂移作为接受的代价记录在后果中。 +**把 overlay 座位按滚动条宽度内缩。** [滚动条槽预留 note](2026-08-04-composer-tab-gutter-reservation.zh.md) 当初否决的正是这个方案，本 note 采纳了它；变的是否决的前提。这个数字属于引擎而不属于我们——WebKit 路径绘制样式表里的 8px 滚动条，Firefox 路径绘制 `scrollbar-width: thin` 解析出的宽度——因此硬编码的内缩会让两种状态在 Chromium 上对齐、在别处继续漂移。被否决的设计假定 overlay 分支预留引擎解析出的槽宽，内缩必须精确匹配那个宽度。overlay 分支不预留任何槽位，补偿成为覆盖侧唯一的机制；否决的字面量那一半，通过把 8px 变成与 `::-webkit-scrollbar` 规则同处一个 diff 的变量来回应。Firefox 那一半仍然存在：Chat 预留引擎解析宽度，补偿保持固定 8px，两者不等之处的残余漂移作为接受的代价记录在后果中。 ## 后果 diff --git a/.agents/notes/implemented/bug-fix/2026-08-13-feedback-note-editor-popover.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-08-13-feedback-note-editor-popover.i18n.yaml index d84f437915..c7289d869f 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-13-feedback-note-editor-popover.i18n.yaml +++ b/.agents/notes/implemented/bug-fix/2026-08-13-feedback-note-editor-popover.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-13-feedback-note-editor-popover.md -2026-08-13-feedback-note-editor-popover.md: 33b7cd84b97ceac7fef1d96f1dee279fbb215800 -2026-08-13-feedback-note-editor-popover.zh.md: b130ab1e9c66372cf2a52bc5e12f65027c64cf51 +2026-08-13-feedback-note-editor-popover.md: 42c08e39cfb054db689503e23306c5049a97b6cb +2026-08-13-feedback-note-editor-popover.zh.md: 553029f8a42dae42a38e909d716b41e2c6dd252e diff --git a/.agents/notes/implemented/bug-fix/2026-08-13-feedback-note-editor-popover.md b/.agents/notes/implemented/bug-fix/2026-08-13-feedback-note-editor-popover.md index 33b7cd84b9..42c08e39cf 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-13-feedback-note-editor-popover.md +++ b/.agents/notes/implemented/bug-fix/2026-08-13-feedback-note-editor-popover.md @@ -14,7 +14,7 @@ The same stylesheet also named four `--dsw-alias-*` tokens that the theme does n ## Decision -The note editor does not enter the row's flex layout at all. It is a popover: a fixed-position panel, portaled to `document.body`, whose coordinates come from the note trigger's rect. The row keeps its single line of icons and the note trigger, so nothing has to shrink, wrap, or reflow around the editor, and no `order` or wrapping is needed anywhere. Portaling out of the conversation column also escapes its `overflow` clip, so the panel cannot be cropped at the scroll edge and it moves with the message it annotates when the transcript scrolls. This reuses the same portal mechanism `ui-primitives/Menu` uses for anchored menus (`ui-subagent`'s catalog popover is built on it): the panel is `position: fixed`, placed from the anchor rect on open, clamped inside the viewport, and re-placed on scroll (capture phase) and resize. That anchoring is shared rather than copied: `ui-primitives/useAnchoredPosition` owns measure-offset-clamp-and-track, and the duplication gate is what forced the extraction — an inline copy of the clamp and its listener pair reported a 10-line clone against `Menu`. `Menu` keeps its own effect because its placement also resolves `side`/`align` variants and an optional caller-supplied anchor rect, which this surface does not need; the hook covers the plain below-the-anchor case both would otherwise spell out. +The note editor does not enter the row's flex layout at all. It is a popover: a fixed-position panel, portaled to `document.body`, whose coordinates come from the note trigger's rect. The row keeps its single line of icons and the note trigger, so nothing has to shrink, wrap, or reflow around the editor, and no `order` or wrapping is needed anywhere. Portaling out of the conversation column also escapes its `overflow` clip, so the panel cannot be cropped at the scroll edge and it moves with the message it annotates when the transcript scrolls. This reuses the same portal mechanism `ui-primitives/Menu` uses for anchored menus (`ui-subagent`'s catalog popover is built on it): the panel is `position: fixed`, placed from the anchor rect on open, clamped inside the viewport, and re-placed on scroll (capture phase) and resize. `ui-primitives/useAnchoredPosition` owns the shared measure-offset-clamp-and-track behavior. `Menu` keeps its own effect because its placement also resolves `side`/`align` variants and an optional caller-supplied anchor rect, which this surface does not need; the hook covers the plain below-the-anchor case both would otherwise spell out. **The action strip.** The like/dislike buttons and the note trigger stay in the row, unchanged. The trigger is a plain button (`aria-haspopup="dialog"`, `aria-expanded` while open) that shows "Add a note" before a note exists and the note text afterward. @@ -24,7 +24,7 @@ The note editor does not enter the row's flex layout at all. It is a popover: a ## Alternatives considered -**Inline expansion on the row, the editor claiming its own line via a full-width flex basis with the row allowed to wrap** — the approach first shipped on this branch and rejected here. It fixes the geometry (the row reports zero overflow from 1680px down to 600px) but at a visible cost: the branch action and the end clock wrap below the editor while it is open, the row occupies three lines, and the interaction competes for the same horizontal strip the row already fills. That cost is what [#2561](https://github.com/deepseek-harness/deepseek-harness/issues/2561) reported from real use — the row reads as misaligned once the editor expands — and it asked for the popover the chat surface already uses. A popover removes the editor from the row entirely, so the strip and the keyboard tab order are untouched whether the editor is open or not. +**Inline expansion on the row, with the editor claiming its own line through a full-width flex basis and wrapping.** Rejected: it fixes the geometry (the row reports zero overflow from 1680px down to 600px) but makes the branch action and end clock wrap below the editor, expands the row to three lines, and puts the interaction in the same horizontal strip the row already fills. [Issue #2561](https://github.com/deepseek-harness/deepseek-harness/issues/2561) reports the resulting misalignment and requests the popover pattern the chat surface already uses. A popover removes the editor from the row, leaving the strip and keyboard tab order unchanged whether the editor is open or not. **An absolutely-positioned popover not portaled out of the column** — rejected: the conversation column is an `overflow-y: auto` scroller, so a panel laid out inside it is clipped at the scroll edge and does not track the message as the column scrolls. Portaling to `document.body` with fixed placement from the trigger rect is what makes the floating panel viable, exactly as `Menu`'s portal mode and the subagent catalog popover already do. @@ -40,4 +40,4 @@ The `ui-message-feedback` package adds `@types/react-dom` so the `createPortal` Known limitations are accepted rather than fixed here. A rating click while the panel is open closes it, and the close path returns focus to the note trigger rather than leaving it on the rating button the human just pressed; the same happens when an outside click lands on another focusable control, which the browser focuses before the close returns focus to the trigger. A pointer user does not notice either; a keyboard user feels the focus move. The clamp assumes the panel fits: a panel taller than the viewport makes the upper bound `innerHeight - height - margin` smaller than `margin`, so `top` goes negative and the panel's head is cut off rather than its foot. The panel's three-row textarea carries `resize: vertical`, so a human can drag past that size; `.notePanel` therefore bounds its height at `calc(100vh - 24px)` and scrolls its own content, the counterpart of the existing `max-width` and the same 12px margin the clamp uses. If the rating disappears while the editor is open, the panel unmounts on the `rating !== undefined` guard but `noteOpen` stays true, so the document-level Escape and pointer-down listeners remain attached; should the item reappear through a later resync, the panel returns with the previous draft and without refocusing the textarea. The window is one click or Escape wide, and the save failure it could hide already falls back to the row, so it is left as it is. A failure that lands after the panel was closed and reopened is not written into the new session's panel: its draft was reseeded from the stored note, so an old attempt's error would mislabel it, and the uncommitted content is already gone — the failure is dropped rather than shown. And while the placement replays on scroll, window resize, and the panel's own size changes, jsdom has no layout, so the real geometry is proven by the browser scenario while the unit spec covers the wiring through a `ResizeObserver` stub. -A residual narrow-viewport clock overflow remains below 520px from the clock string alone, unrelated to the feedback surface. The repo has no gate for undefined design tokens, and a scan during this work found more in `ui-agent-preset`, `ui-conversation`, `ui-jobs`, `ui-settings-plugins`, and `ui-tool`; they are untouched here and want their own change. +A residual narrow-viewport clock overflow remains below 520px from the clock string alone, unrelated to the feedback surface. Undefined design-token references remain in `ui-agent-preset`, `ui-conversation`, `ui-jobs`, `ui-settings-plugins`, and `ui-tool`; the repository has no gate that rejects them. diff --git a/.agents/notes/implemented/bug-fix/2026-08-13-feedback-note-editor-popover.zh.md b/.agents/notes/implemented/bug-fix/2026-08-13-feedback-note-editor-popover.zh.md index b130ab1e9c..553029f8a4 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-13-feedback-note-editor-popover.zh.md +++ b/.agents/notes/implemented/bug-fix/2026-08-13-feedback-note-editor-popover.zh.md @@ -14,7 +14,7 @@ Status: implemented ## Decision -备注编辑器完全不进入行的 flex 布局。它是一个浮层：一张固定定位的面板，portal 到 `document.body`，其坐标来自备注触发按钮的矩形。行保持其单行图标与备注触发按钮，因此没有任何东西需要围绕编辑器收缩、换行或回流，任何地方都不需要 `order` 或换行。portal 出会话列也逃出了列的 `overflow` 裁剪，因此面板不会被滚动边缘裁掉，并且当对话记录滚动时会随它所批注的消息一起移动。这里复用 `ui-primitives/Menu` 为锚定菜单所用的同一套 portal 机制（`ui-subagent` 的 catalog popover 就构建在它之上）：面板 `position: fixed`，打开时从 anchor rect 定位，钳制在视口内，并在滚动（捕获阶段）与缩放时重新定位。这套锚定逻辑是共享而非复制的：`ui-primitives/useAnchoredPosition` 持有「测量—偏移—钳制—跟随」这一件事，而促成这次抽取的正是重复代码门禁——内联的钳制与那对监听器被报为与 `Menu` 的 10 行克隆。`Menu` 保留自己的 effect，因为它的定位还要解析 `side`/`align` 变体与可选的调用方 anchor rect，而本界面不需要这些；该 hook 覆盖的是两边本来都要各写一遍的「锚点正下方」这一简单情形。 +备注编辑器完全不进入行的 flex 布局。它是一个浮层：一张固定定位的面板，portal 到 `document.body`，其坐标来自备注触发按钮的矩形。行保持其单行图标与备注触发按钮，因此没有任何东西需要围绕编辑器收缩、换行或回流，任何地方都不需要 `order` 或换行。portal 出会话列也逃出了列的 `overflow` 裁剪，因此面板不会被滚动边缘裁掉，并且当对话记录滚动时会随它所批注的消息一起移动。这里复用 `ui-primitives/Menu` 为锚定菜单所用的同一套 portal 机制（`ui-subagent` 的 catalog popover 就构建在它之上）：面板 `position: fixed`，打开时从 anchor rect 定位，钳制在视口内，并在滚动（捕获阶段）与缩放时重新定位。`ui-primitives/useAnchoredPosition` 负责共享的「测量—偏移—钳制—跟随」行为。`Menu` 保留自己的 effect，因为它的定位还要解析 `side`/`align` 变体与可选的调用方 anchor rect，而本界面不需要这些；该 hook 覆盖的是两边本来都要各写一遍的「锚点正下方」这一简单情形。 **操作条。** 点赞/点踩按钮与备注触发按钮保持原样留在行内。触发按钮是普通 `button`（`aria-haspopup="dialog"`，打开时 `aria-expanded`），在没有备注时显示「补充说明」，已有备注时显示备注文本。 @@ -24,7 +24,7 @@ Status: implemented ## Alternatives considered -**行内展开：编辑器通过整行 flex basis 独占一行，并让行允许换行** — 这是本分支最初交付、在此否决的做法。它修好了几何（行在 1680px 到 600px 报告零溢出），但有可见代价：branch 与末尾时钟在编辑器打开时换行到编辑器下方，行占三行，交互与行本就占满的横向条带争空间。这一代价正是 [#2561](https://github.com/deepseek-harness/deepseek-harness/issues/2561) 在真实使用中反馈的问题——编辑器展开后这一行读起来是错位的——并提出改用 chat 界面已有的弹窗。浮层把编辑器完全移出行，因此无论编辑器是否打开，操作条与键盘 Tab 顺序都不受影响。 +**行内展开：编辑器通过整行 flex basis 独占一行，并让行允许换行。**否决：这种做法能修正几何（行在 1680px 到 600px 报告零溢出），但会让 branch 操作与末尾时钟在编辑器打开时换行到编辑器下方，使行占据三行，并让交互与行本就占满的横向条带争空间。[Issue #2561](https://github.com/deepseek-harness/deepseek-harness/issues/2561)记录了由此产生的错位，并要求采用 chat 界面已有的浮层模式。浮层把编辑器完全移出行，因此无论编辑器是否打开，操作条与键盘 Tab 顺序都不受影响。 **不 portal 出列的绝对定位浮层** — 否决：会话列是 `overflow-y: auto` 的滚动容器，因此在列内布局的面板会被滚动边缘裁掉，且不随列滚动而跟住消息。portal 到 `document.body` 并从触发按钮矩形做固定定位，才让浮动面板可行，正如 `Menu` 的 portal 模式与 subagent catalog popover 已然做到的那样。 @@ -40,4 +40,4 @@ Status: implemented 有若干已知限制在此接受而非修复。面板打开时点击评分会关闭它，而关闭路径把焦点归还给备注触发按钮，而不是留在用户刚按下的评分按钮上；外部点击落在另一个可聚焦控件上时同理——浏览器先把焦点给该控件，随后关闭路径又把它拉回触发按钮。指针用户对两者都无感，键盘用户会察觉焦点移动。钳制假定面板放得下：面板高于视口时，上界 `innerHeight - height - margin` 会小于 `margin`，于是 `top` 变为负值、被裁掉的是面板顶部而非底部。面板里的三行 textarea 带 `resize: vertical`，用户可以拖过这个尺寸，因此 `.notePanel` 把自身高度限制在 `calc(100vh - 24px)` 并自行滚动内容——这是既有 `max-width` 的对应项，用的是与钳制相同的 12px 边距。编辑器打开时若评分消失，面板会因 `rating !== undefined` 守卫卸载，但 `noteOpen` 仍为 true，因此 document 级的 Escape 与 pointer-down 监听继续挂着；若该 item 之后经 resync 重新出现，浮层会带着上一次的草稿回来且不重新聚焦 textarea。该窗口只有一次点击或一次 Escape 那么宽，而它可能遮住的保存失败已经有行内回退，因此保持现状。若失败在面板关闭并重开后才到达，不会写入新会话的面板：其草稿已按已存备注重新播种，旧尝试的错误会误标新草稿，而未提交的内容本就不存在——该失败被丢弃而不展示。以及，定位虽然会在滚动、窗口缩放与面板自身尺寸变化时重放，但 jsdom 没有布局，因此真实几何由浏览器场景证明，单测则通过 `ResizeObserver` stub 覆盖其接线。 -520px 以下仍残留仅来自时钟字符串的窄视口溢出，与本界面无关。仓库没有针对未定义设计 token 的门禁；本次工作中的一次扫描在 `ui-agent-preset`、`ui-conversation`、`ui-jobs`、`ui-settings-plugins` 与 `ui-tool` 中又发现更多，本次未触碰，需要单独的改动处理。 +520px 以下仍残留仅来自时钟字符串的窄视口溢出，与本界面无关。`ui-agent-preset`、`ui-conversation`、`ui-jobs`、`ui-settings-plugins` 与 `ui-tool` 仍引用未定义的 design token；仓库没有拒绝此类引用的门禁。 diff --git a/.agents/notes/implemented/bug-fix/2026-08-15-max-token-replay-state-alignment.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-08-15-max-token-replay-state-alignment.i18n.yaml index 3be0c200fd..887950ad94 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-15-max-token-replay-state-alignment.i18n.yaml +++ b/.agents/notes/implemented/bug-fix/2026-08-15-max-token-replay-state-alignment.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-15-max-token-replay-state-alignment.md -2026-08-15-max-token-replay-state-alignment.md: 256a64403a08377cf35ba645175698678eaa7f8b -2026-08-15-max-token-replay-state-alignment.zh.md: f7a7280ab7657124541d93e3c592eab9ec75d28e +2026-08-15-max-token-replay-state-alignment.md: 0d8c9f2e55d826769325ea489d797a8561ac0e8e +2026-08-15-max-token-replay-state-alignment.zh.md: 30f11b990abbe1ddfb36241b2f80c188de75ed22 diff --git a/.agents/notes/implemented/bug-fix/2026-08-15-max-token-replay-state-alignment.md b/.agents/notes/implemented/bug-fix/2026-08-15-max-token-replay-state-alignment.md index 256a64403a..0d8c9f2e55 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-15-max-token-replay-state-alignment.md +++ b/.agents/notes/implemented/bug-fix/2026-08-15-max-token-replay-state-alignment.md @@ -12,7 +12,7 @@ pi-ai recorded one opaque replay blob per response, projected from the provider' Two changes, one per side of the durable boundary. -**Write side — one keep/drop decision.** The finish chunk's `replayState` becomes a typed `ReplayEnvelope`: an opaque `response` half plus optional opaque per-block entries aligned with the emitted block sequence. `BlockAssembler` computes its keep/drop decision once and applies it to blocks and envelope entries together, so any transformation assembly performs — today's max-token tool-call drop or a future one — prunes the matching metadata by construction. Retained blocks keep their entries, so a truncated response keeps signatures for the reasoning and text it kept. An envelope whose entries do not match the emitted block count is discarded whole (a misemitting adapter must not publish misattributed metadata). pi-ai splits its former flat state into a version-2 response half and per-block signature entries. +**Write side — one keep/drop decision.** The finish chunk's `replayState` becomes a typed `ReplayEnvelope`: an opaque `response` half plus optional opaque per-block entries aligned with the emitted block sequence. `BlockAssembler` computes its keep/drop decision once and applies it to blocks and envelope entries together, so any transformation assembly performs — the max-token tool-call drop or a future one — prunes the matching metadata by construction. Retained blocks keep their entries, so a truncated response keeps signatures for the reasoning and text it kept. An envelope whose entries do not match the emitted block count is discarded whole (a misemitting adapter must not publish misattributed metadata). pi-ai splits its former flat state into a version-2 response half and per-block signature entries. **Read side — durable content is authoritative.** `toPiAssistant` treats replay state as fidelity metadata, not as a load-bearing input: any state the reading build cannot use — another adapter's kind, another version (including the flat version-1 form already on disk), malformed metadata, or a block shape that no longer matches the content — degrades that one message to the existing foreign provider-neutral conversion and reports the `INVALID_REPLAY_STATE` diagnostic through the plugin's `onReplayDegrade` hook (a logger warning). The request proceeds. This is what lets sessions poisoned before this change continue instead of erroring forever, and it bounds every future divergence source to a fidelity loss on one message. @@ -22,7 +22,7 @@ Assembler unit tests prove pruning, misalignment discard, and pass-through for u ## Alternatives considered -**Suppress the whole replay state when assembly drops a tool call.** Works for today's one transformation, but re-derives the drop condition beside `blocks()` (the two drift silently), discards valid signatures for the retained blocks, and leaves read-time divergence — legacy sessions on disk foremost — a hard error. +**Suppress the whole replay state when assembly drops a tool call.** Works for the one shipped transformation, but re-derives the drop condition beside `blocks()` (the two drift silently), discards valid signatures for the retained blocks, and leaves read-time divergence — legacy sessions on disk foremost — a hard error. **Keep the state and relax pi-ai's block-count validation to attach what fits.** Rejected: index-aligned signatures attached to a different block list would present false native history to the provider. Degrading attaches nothing. diff --git a/.agents/notes/implemented/bug-fix/2026-08-15-max-token-replay-state-alignment.zh.md b/.agents/notes/implemented/bug-fix/2026-08-15-max-token-replay-state-alignment.zh.md index f7a7280ab7..30f11b990a 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-15-max-token-replay-state-alignment.zh.md +++ b/.agents/notes/implemented/bug-fix/2026-08-15-max-token-replay-state-alignment.zh.md @@ -12,7 +12,7 @@ pi-ai 为每个响应记录一个从提供方原生消息投影而来的不透 两处改动，各覆盖持久化边界的一侧。 -**写侧——一次保留/丢弃决定。** finish 分片的 `replayState` 变为有类型的 `ReplayEnvelope`：一个不透明的 `response` 半区，加上与发射块序列对齐的可选不透明逐块条目。`BlockAssembler` 只计算一次保留/丢弃决定，并把它同时应用于块和逐块条目，因此组装执行的任何变换——今天的 max-token 工具调用丢弃或未来的其他变换——都按构造裁剪掉对应元数据。保留的块保留其条目，所以被截断的响应仍为其保留的推理（reasoning）与文本保有签名。条目数与发射块数不一致的数据整体丢弃（发射不当的适配器不得发布归属错误的元数据）。pi-ai 把原先的平铺状态拆为版本 2 的 response 半区和逐块签名条目。 +**写侧——一次保留/丢弃决定。** finish 分片的 `replayState` 变为有类型的 `ReplayEnvelope`：一个不透明的 `response` 半区，加上与发射块序列对齐的可选不透明逐块条目。`BlockAssembler` 只计算一次保留/丢弃决定，并把它同时应用于块和逐块条目，因此组装执行的任何变换——max-token 工具调用丢弃或未来的其他变换——都按构造裁剪掉对应元数据。保留的块保留其条目，所以被截断的响应仍为其保留的推理（reasoning）与文本保有签名。条目数与发射块数不一致的数据整体丢弃（发射不当的适配器不得发布归属错误的元数据）。pi-ai 把原先的平铺状态拆为版本 2 的 response 半区和逐块签名条目。 **读侧——持久化内容是权威记录。** `toPiAssistant` 把回放状态当作保真度元数据，而非承重输入：读取方无法使用的任何状态——其他适配器的 kind、其他版本（包括已落盘的平铺版本 1 形式）、格式错误的元数据、或与内容不再匹配的块结构——都把这一条消息降级为既有的外来提供方无关转换，并通过插件的 `onReplayDegrade` 钩子（logger 警告）上报 `INVALID_REPLAY_STATE` 诊断。请求继续执行。正是这一点让本次改动之前已被毒化的会话得以继续而不是永远报错，也把未来一切分叉源约束为单条消息的保真度损失。 @@ -22,7 +22,7 @@ pi-ai 为每个响应记录一个从提供方原生消息投影而来的不透 ## 已考虑的替代方案 -**组装丢弃工具调用时抑制整个回放状态。** 对今天唯一的变换有效，但在 `blocks()` 旁边重新推导丢弃条件（两处会无声漂移），丢掉保留块的有效签名，并让读取时的分叉——首当其冲是已落盘的旧会话——仍然是硬错误。 +**组装丢弃工具调用时抑制整个回放状态。** 对唯一已交付的变换有效，但在 `blocks()` 旁边重新推导丢弃条件（两处会无声漂移），丢掉保留块的有效签名，并让读取时的分叉——首当其冲是已落盘的旧会话——仍然是硬错误。 **保留状态并放宽 pi-ai 的块数校验、能贴多少贴多少。** 否决：索引对齐的签名贴到不同的块清单上，会向提供方呈现虚假的原生历史。降级则什么都不贴。 diff --git a/.agents/notes/implemented/bug-fix/2026-08-17-image-dimension-admission-limit.md b/.agents/notes/implemented/bug-fix/2026-08-17-image-dimension-admission-limit.md deleted file mode 100644 index 027259c094..0000000000 --- a/.agents/notes/implemented/bug-fix/2026-08-17-image-dimension-admission-limit.md +++ /dev/null @@ -1,30 +0,0 @@ -# Agent Note: Per-side image dimension admission limit - -Status: implemented - -English | [中文](2026-08-17-image-dimension-admission-limit.zh.md) - -## Problem - -`read_image` durably committed an image and appended its block to session history before any dimension check beyond byte count and total pixels. Deployed model routes reject a request with HTTP 400 when it carries many images and any of them has a side above 2000px. An admitted image rides every later request of its session, so one oversized read poisoned the durable history: the next model request failed, and so did every retry, permanently killing the session. The same gap applied to every other image producer (host uploads, MCP tool images) because admission had no per-side bound at all. - -## Decision - -`ImageAttachmentLimits` carries `maxImageDimension`, enforced during the admission full decode (`detectImage`) as `IMAGE_DIMENSION_TOO_LARGE`, so every producer that commits through the attachment service refuses an oversized image before anything reaches durable history. `LocalAttachmentStore` exposes it as the `maxImageDimension` config field with default `DEFAULT_MAX_IMAGE_DIMENSION = 2000`, the strictest per-side bound deployed routes enforce; deployments with laxer routes raise it from cordis.yml. `read_image` maps `IMAGE_DIMENSION_TOO_LARGE` and `IMAGE_TOO_MANY_PIXELS` to model-facing errors that name the resolved path and the limit and tell the model to downscale and retry — the turn continues as a recoverable tool error. The Web composer surfaces `IMAGE_DIMENSION_TOO_LARGE` with dedicated copy naming the limit. The `read-image-dimension` snapshot scenario replays the refusal keylessly through the assembled app: a 2001x1 workspace fixture, a recoverable tool error, and a completed turn. - -## Alternatives considered - -- **Downscale at admission instead of refusing.** Resampling changes the stored bytes away from what the caller supplied, adds a resampling-quality policy, and hides the limit from the model. Refusal keeps admission a pure gate; the model or user can downscale with full knowledge. Worth revisiting only if refusals prove frequent in practice. -- **Enforce at the provider adapter per route.** Too late: by the time a request is assembled the image is already durable history, so every route and every retry re-fails. Admission is the last point where a provider-rejected image can be kept out. -- **Repair already-poisoned sessions** (drop or replace the oversized block on later requests). Out of scope for this fix; admission prevents new poisonings, and history rewriting needs its own design against the model-visible ⟺ logged invariant. - -## Related - -- [Minimal read_image tool](../feature/2026-08-10-minimal-read-image-tool.md) — the tool whose admission gap this closes. -- [Web image intake and limits alignment](../feature/2026-08-12-web-image-intake-and-limits-alignment.md) — the composer-side surfacing of the same `ImageAttachmentLimits`. - -## Consequences - -- One oversized `read_image` can no longer break a session; the model sees an actionable error and the turn completes. -- Images with a side above 2000px are refused even in compositions whose routes would accept them on small requests; such deployments must raise `maxImageDimension` explicitly. -- Sessions that already carry an oversized image remain broken; this change does not repair existing history. diff --git a/.agents/notes/implemented/bug-fix/2026-08-17-image-dimension-admission-limit.zh.md b/.agents/notes/implemented/bug-fix/2026-08-17-image-dimension-admission-limit.zh.md deleted file mode 100644 index 38422615aa..0000000000 --- a/.agents/notes/implemented/bug-fix/2026-08-17-image-dimension-admission-limit.zh.md +++ /dev/null @@ -1,30 +0,0 @@ -# Agent Note: 图片单边尺寸准入上限 - -Status: implemented - -[English](2026-08-17-image-dimension-admission-limit.md) | 中文 - -## Problem - -`read_image` 在字节数与总像素之外没有任何尺寸检查，就把图片持久提交并追加进会话历史。已部署的模型路由在请求携带多张图片且其中任何一张单边超过 2000px 时会以 HTTP 400 拒绝整个请求。已接纳的图片会随该会话之后的每次请求发送，因此一次超限读取就毒化了持久历史：下一次模型请求失败，之后的每次重试同样失败，会话被永久杀死。其他图片来源（宿主上传、MCP 工具图片）存在同样的缺口，因为准入完全没有单边上限。 - -## Decision - -`ImageAttachmentLimits` 增加 `maxImageDimension`，在准入完整解码（`detectImage`）中以 `IMAGE_DIMENSION_TOO_LARGE` 强制执行，因此所有经附件服务提交的来源都会在任何内容进入持久历史之前拒绝超限图片。`LocalAttachmentStore` 将其暴露为 `maxImageDimension` 配置项，默认值 `DEFAULT_MAX_IMAGE_DIMENSION = 2000`，即已部署路由强制执行的最严格单边上限；路由更宽松的部署可在 cordis.yml 中调高。`read_image` 把 `IMAGE_DIMENSION_TOO_LARGE` 与 `IMAGE_TOO_MANY_PIXELS` 映射为面向模型的错误，指明解析后的路径与上限并提示缩图重试，本轮以可恢复的工具错误继续。Web 输入框对 `IMAGE_DIMENSION_TOO_LARGE` 给出指明上限的专用文案。`read-image-dimension` 快照场景通过组装后的应用无 key 回放这次拒绝：2001x1 的工作区 fixture、一条可恢复的工具错误、一个正常完成的轮次。 - -## Alternatives considered - -- **准入时缩图而非拒绝。** 重采样会让存储字节偏离调用方提供的内容，引入重采样质量策略，还会对模型隐藏上限。拒绝让准入保持为纯粹的门禁；模型或用户可以在知情的前提下自行缩图。只有当拒绝在实践中频繁出现时才值得重新考虑。 -- **在 provider 适配器按路由强制执行。** 为时已晚：组装请求时图片已是持久历史，每条路由、每次重试都会再次失败。准入是把必然被上游拒绝的图片挡在外面的最后一道关口。 -- **修复已被毒化的会话**（在之后的请求中丢弃或替换超限图片块）。不在本次修复范围内；准入阻止新的毒化，而重写历史需要针对「模型可见 ⟺ 已记录」不变量单独设计。 - -## Related - -- [最小 read_image 工具](../feature/2026-08-10-minimal-read-image-tool.zh.md)，本次修复补上的正是该工具的准入缺口。 -- [Web 图片摄入与限制对齐](../feature/2026-08-12-web-image-intake-and-limits-alignment.zh.md)，同一组 `ImageAttachmentLimits` 在输入框侧的呈现。 - -## Consequences - -- 一次超限的 `read_image` 不再能弄坏会话；模型看到可操作的错误，轮次正常完成。 -- 单边超过 2000px 的图片即使在其路由本可接受（小请求）的组合中也会被拒绝；这类部署必须显式调高 `maxImageDimension`。 -- 已经携带超限图片的会话仍然是坏的；本次改动不修复既有历史。 diff --git a/.agents/notes/implemented/bug-fix/2026-08-18-rail-search-outside-click-self-dismissal.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-08-18-rail-search-outside-click-self-dismissal.i18n.yaml index 15e78356f5..1aef254fee 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-18-rail-search-outside-click-self-dismissal.i18n.yaml +++ b/.agents/notes/implemented/bug-fix/2026-08-18-rail-search-outside-click-self-dismissal.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-18-rail-search-outside-click-self-dismissal.md -2026-08-18-rail-search-outside-click-self-dismissal.md: 9893b3a2456b9a592e1feb107d21404e043dee78 -2026-08-18-rail-search-outside-click-self-dismissal.zh.md: 91e343b8843dc02ca9c1be2b145e79beb84e17b7 +2026-08-18-rail-search-outside-click-self-dismissal.md: b9f3aa33658919aa9061c0ec988878fea194de47 +2026-08-18-rail-search-outside-click-self-dismissal.zh.md: 72f19157dbef23c1109f799eca9686931a58156f diff --git a/.agents/notes/implemented/bug-fix/2026-08-18-rail-search-outside-click-self-dismissal.md b/.agents/notes/implemented/bug-fix/2026-08-18-rail-search-outside-click-self-dismissal.md index 9893b3a245..b9f3aa3365 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-18-rail-search-outside-click-self-dismissal.md +++ b/.agents/notes/implemented/bug-fix/2026-08-18-rail-search-outside-click-self-dismissal.md @@ -20,7 +20,7 @@ The outside-click dismissal listener does not mount while the rail gesture is in **Defer listener attachment by a frame or timeout.** A raw delay encodes the symptom (the click arrives "too early") instead of the cause (a gesture is in flight). `searchOnExpand` is already the explicit in-flight state with the correct end point; a frame boundary is neither. -**Dismiss on `pointerdown` instead of `click`.** The initiating gesture's `pointerdown` precedes the listener mount, so it cannot self-dismiss. Rejected because it changes dismissal semantics for every interaction — a drag or a press-and-slide-away would dismiss where a completed click today does not — to fix a problem scoped to one gesture. +**Dismiss on `pointerdown` instead of `click`.** The initiating gesture's `pointerdown` precedes the listener mount, so it cannot self-dismiss. Rejected because it changes dismissal semantics for every interaction — a drag or a press-and-slide-away would dismiss where a completed click does not — to fix a problem scoped to one gesture. ## Consequences diff --git a/.agents/notes/implemented/bug-fix/2026-08-18-rail-search-outside-click-self-dismissal.zh.md b/.agents/notes/implemented/bug-fix/2026-08-18-rail-search-outside-click-self-dismissal.zh.md index 91e343b884..72f19157db 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-18-rail-search-outside-click-self-dismissal.zh.md +++ b/.agents/notes/implemented/bug-fix/2026-08-18-rail-search-outside-click-self-dismissal.zh.md @@ -20,7 +20,7 @@ Status: implemented **将监听器挂载延迟一帧或一个定时器。** 裸延迟编码的是症状（点击来得"太早"）而非成因（手势正在进行）。`searchOnExpand` 已经是带有正确终点的显式进行中状态；帧边界两者都不是。 -**改在 `pointerdown` 上收起而非 `click`。** 发起手势的 `pointerdown` 先于监听器挂载，因而不会自我收起。被否决是因为它改变了所有交互的收起语义——拖拽或按下后滑走会触发收起，而如今完成的点击才会——只为修复一个局限于单个手势的问题。 +**改在 `pointerdown` 上收起而非 `click`。** 发起手势的 `pointerdown` 先于监听器挂载，因而不会自我收起。被否决是因为它改变了所有交互的收起语义——拖拽或按下后滑走会触发收起，而完成的点击不会——只为修复一个局限于单个手势的问题。 ## 影响 diff --git a/.agents/notes/implemented/bug-fix/2026-08-18-request-image-payload-bound.md b/.agents/notes/implemented/bug-fix/2026-08-18-request-image-payload-bound.md deleted file mode 100644 index 0ec4594888..0000000000 --- a/.agents/notes/implemented/bug-fix/2026-08-18-request-image-payload-bound.md +++ /dev/null @@ -1,36 +0,0 @@ -# Agent Note: Request-level image payload bound - -Status: implemented - -English | [中文](2026-08-18-request-image-payload-bound.zh.md) - -## Problem - -Every image in session history is base64-inlined into every model request by the pi-ai adapter, so a long session's request body grows monotonically with each admitted image. Gateways cap request-body size; once the accumulated payload crossed such a cap the request was rejected with 413 (`Failed to buffer the request body: length limit exceeded`), and because nothing bounds or trims the assembled request, every retry resent the same oversized body. The session was permanently unusable, and the failure text matched no `classifyPiAiError` rule, so it surfaced as the generic `PI_AI_ERROR`. Admission bounds (per image, per message) cannot prevent this: each image is individually admissible, and the sum still grows without bound. Two screenshots were enough to trigger it in production. - -## Decision - -The pi-ai provider profile and direct DeepSeek adapter carry `maxRequestImageBytes` (default `DEFAULT_MAX_REQUEST_IMAGE_BYTES = 20MiB`, a positive integer, changeable from cordis.yml and settings). The provider-neutral `offloadRequestImages` conversion sums the base64 length of every image in history from `ImageAttachmentRef.bytes` without reading data and, while the sum exceeds the bound, replaces the oldest image occurrences with a fixed model-facing placeholder. The placeholder tells the model to read the file again when a path is available or ask the user to attach the image again. The most recent images are omitted last; an image larger than the bound is itself omitted. Occurrence-order replacement does not depend on object identity, so replaying the same JSON log produces the same request. Offloaded images are never read from the attachment store. Both adapters classify 413 as `INVALID_REQUEST`; pi-ai also recognizes specific request-body-cap wording. Four images admitted at the attachment store's 3.5MiB raw-image default occupy at most 18.67MiB after base64 expansion. The 20MiB default therefore retains four such images and leaves headroom under the direct API's 30MiB request limit, while deployments behind stricter gateways lower the value per route. - -## Offload is conversion, not history - -The placeholder is model-visible but not logged as a session event. It stays within the model-visible ⟺ logged invariant the same way the adapter's other serialization does (`(no output)` fallbacks, text-only folding): the offload locations are a pure function of the logged history and the route configuration, so the exact request remains reconstructable from the session log plus the composition. A logged elision event becomes necessary only when offload decisions gain non-deterministic inputs (for example live gateway feedback), which belongs to the deferred capability-metadata design. - -## Alternatives considered - -- **Fail the request with a clear error instead of offloading.** Keeps the model informed but leaves the session wedged: the user cannot remove images from durable history, so a hard failure at the bound is permanent. Offload keeps the session serviceable, which is the point of the fix. -- **Upload images once and reference them by URL / file id.** Removes the linear body growth entirely and is the right medium-term shape (providers and the internal gateway both document a Files path), but it introduces upload lifecycle management across providers and is far beyond a P0 hotfix. -- **Count the full request body, not only images.** Text and tools contribute little and their sizes are only known after full serialization per protocol; bounding the dominant term with explicit headroom is accurate enough for the failure being fixed and much simpler. Revisit inside the route-capability design. -- **Trim at admission instead.** Admission cannot see future accumulation; only the assembled request knows its total. Admission-side bounds (per-side dimension, bytes) remain as the first layer and are owned by [the dimension-limit note](2026-08-17-image-dimension-admission-limit.md). - -## Related - -- [Per-side image dimension admission limit](2026-08-17-image-dimension-admission-limit.md) — the admission-layer companion fix; together they close the two observed session-poisoning failures (400 dimension, 413 body size). -- [Direct DeepSeek vision input](../feature/2026-08-19-direct-deepseek-vision-input.md) — applies this provider-neutral conversion to the official multimodal route. - -## Consequences - -- An image-heavy long session keeps completing requests. The oldest images are omitted first; the most recent image is omitted only when it cannot fit within the bound. -- Crossing the bound rewrites an early message, so the provider prompt-cache prefix ends at the newly offloaded image until the offloaded prefix stabilizes. -- The bound counts base64 image payload only; deployments must keep it below their gateway's request-body cap with headroom, and the shipped default cannot know a private gateway's cap. -- Route capability metadata driving admission and assembly together (image count, per-image size, request size, provider token formulas) remains deferred design work tracked outside this fix. diff --git a/.agents/notes/implemented/bug-fix/2026-08-18-request-image-payload-bound.zh.md b/.agents/notes/implemented/bug-fix/2026-08-18-request-image-payload-bound.zh.md deleted file mode 100644 index 7cdf6bb768..0000000000 --- a/.agents/notes/implemented/bug-fix/2026-08-18-request-image-payload-bound.zh.md +++ /dev/null @@ -1,36 +0,0 @@ -# Agent Note: 请求级图片载荷上限 - -Status: implemented - -[English](2026-08-18-request-image-payload-bound.md) | 中文 - -## Problem - -pi-ai 适配器把会话历史中的每张图片 base64 内联进每一个模型请求，长会话的请求体随每张入库图片单调增长。网关对请求体大小设有上限；累积载荷一旦越线，请求被以 413 拒绝（`Failed to buffer the request body: length limit exceeded`），而组装层没有任何约束或裁剪，每次重试都会原样重发同一个超限请求体，会话永久不可用。该报错文本不匹配 `classifyPiAiError` 的任何规则，只能落进笼统的 `PI_AI_ERROR`。准入上限（单图、单消息）无法阻止这一点：每张图片单独看都合规，总和仍然无界增长。线上两张截图即可触发。 - -## Decision - -pi-ai provider profile 与直接 DeepSeek 适配器都提供 `maxRequestImageBytes`（默认 `DEFAULT_MAX_REQUEST_IMAGE_BYTES = 20MiB`，正整数，可从 cordis.yml 与 settings 修改）。提供方无关的 `offloadRequestImages` 转换由 `ImageAttachmentRef.bytes` 推算每张历史图片的 base64 长度（无需读取数据）求和，总和超过上限时从最老的图片出现位置开始替换为一段固定的模型可见占位文本。占位文本要求模型在有路径时重新读取文件，否则请用户重新附上图片。越新的图片越晚被省略；单张图片本身超过上限时也会被省略。按出现顺序替换不依赖对象身份，因此重放同一份 JSON 日志会产生相同请求。被 offload 的图片不会从附件存储读取。两个适配器都把 413 归类为 `INVALID_REQUEST`；pi-ai 还会识别明确的请求体上限措辞。四张按附件存储默认上限准入的 3.5MiB 原始图片，经 base64 膨胀后最多占 18.67MiB。20MiB 默认上限因此可保留四张这样的图片，并在直接 API 的 30MiB 请求上限下留出余量；网关更严格的部署则按路由调低该值。 - -## offload 是转换而非历史 - -占位文本模型可见，但不记录为会话事件。它与适配器的其他序列化（`(no output)` 回退、纯文本折叠）以同样的方式满足「模型可见 ⟺ 已记录」不变量：offload 位置是已记录历史与路由配置的纯函数，确切请求仍可由会话日志加组合配置重建。只有当 offload 决策引入非确定性输入（例如网关的实时反馈）时才需要记录省略事件，那属于暂缓的能力元数据设计。 - -## Alternatives considered - -- **在上限处直接报错而不 offload。** 模型知情，但会话仍然卡死：用户无法从持久历史中删除图片，越线即永久失败。offload 让会话保持可用，这正是本修复的目标。 -- **图片上传一次、按 URL / file id 引用。** 从结构上消除请求体线性增长，是正确的中期形态（各提供方与内部网关都有 Files 路径），但要跨提供方管理上传生命周期，远超 P0 热修复范围。 -- **统计完整请求体而非只统计图片。** 文本与工具占比很小，且其大小要到按协议完整序列化后才可知；对主导项设上限并留出显式余量，对所修故障足够精确且简单得多。留到路由能力设计中再议。 -- **改在准入侧裁剪。** 准入看不到未来的累积，只有组装后的请求知道自己的总量。准入侧上限（单边尺寸、字节）作为第一层保留，归[尺寸上限笔记](2026-08-17-image-dimension-admission-limit.zh.md)所有。 - -## Related - -- [图片单边尺寸准入上限](2026-08-17-image-dimension-admission-limit.zh.md)，准入层的配套修复；两者合起来封住已观测到的两类会话毒化故障（400 尺寸、413 请求体）。 -- [直接 DeepSeek 视觉输入](../feature/2026-08-19-direct-deepseek-vision-input.zh.md)把这项提供方无关转换应用于官方多模态路由。 - -## Consequences - -- 图片较多的长会话持续可用。最老的图片优先省略；仅当最新图片本身无法装进上限时才会省略它。 -- 越过上限会改写较早的一条消息，提供方 prompt cache 前缀在新被 offload 的图片处截止，直到被 offload 的前缀稳定。 -- 上限只统计 base64 图片载荷；部署必须让它低于自家网关的请求体上限并留出余量，发行默认值无法预知私有网关的上限。 -- 由路由能力元数据同时驱动准入与组装（图片数量、单图大小、请求大小、提供方 token 公式）的设计仍为暂缓工作，在本修复之外跟踪。 diff --git a/.agents/notes/implemented/bug-fix/2026-08-20-explicit-web-index-paths.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-08-20-explicit-web-index-paths.i18n.yaml index 0efe5d0ca3..1a3807ef26 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-20-explicit-web-index-paths.i18n.yaml +++ b/.agents/notes/implemented/bug-fix/2026-08-20-explicit-web-index-paths.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-20-explicit-web-index-paths.md -2026-08-20-explicit-web-index-paths.md: 6ff08c3c2a18ffd79ef7a048f563a91e41a504da -2026-08-20-explicit-web-index-paths.zh.md: 7b419b9f4c8b4b0de20660b3f70d12e67ab264ff +2026-08-20-explicit-web-index-paths.md: 815cdd81d458547513225f9136a1d23b0f228ccc +2026-08-20-explicit-web-index-paths.zh.md: 4cbbac8413d3c4c8a5dcd25b5979dc0b70d47df5 diff --git a/.agents/notes/implemented/bug-fix/2026-08-20-explicit-web-index-paths.md b/.agents/notes/implemented/bug-fix/2026-08-20-explicit-web-index-paths.md index 6ff08c3c2a..815cdd81d4 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-20-explicit-web-index-paths.md +++ b/.agents/notes/implemented/bug-fix/2026-08-20-explicit-web-index-paths.md @@ -20,7 +20,7 @@ GET and HEAD use the same status and content type for index entries, files, and **Use an `Accept: text/html` request header as the fallback rule.** The header expresses representation preference, not whether the pathname is a declared client route. Browser fetches, bots, and monitors may request HTML for an invalid path, so the same false-success behavior remains. -**Add a configurable pathname allowlist now.** No current client route consumes such configuration. A future History API router can add an explicit server rule or configuration field together with the route that requires it, without preserving a speculative public option today. +**Add a configurable pathname allowlist.** No current client route consumes such configuration. A future History API router can add an explicit server rule or configuration field together with the route that requires it, without preserving a speculative public option. ## Consequences diff --git a/.agents/notes/implemented/bug-fix/2026-08-20-explicit-web-index-paths.zh.md b/.agents/notes/implemented/bug-fix/2026-08-20-explicit-web-index-paths.zh.md index 7b419b9f4c..4cbbac8413 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-20-explicit-web-index-paths.zh.md +++ b/.agents/notes/implemented/bug-fix/2026-08-20-explicit-web-index-paths.zh.md @@ -20,7 +20,7 @@ GET 与 HEAD 对 index 入口、文件和未命中项使用相同的状态码与 **把 `Accept: text/html` 请求头作为回退规则。** 该请求头表达的是内容表示偏好，而不是 pathname 是否为已声明的客户端路由。浏览器 fetch、机器人和监控都可能为无效路径请求 HTML，因此仍会产生同样的假成功行为。 -**立即添加可配置的 pathname 允许列表。** 当前没有客户端路由消费这项配置。未来的 History API 路由可以在引入所需路由时，同时添加显式服务器规则或配置字段，无需现在保留推测性的公开选项。 +**添加可配置的 pathname 允许列表。** 当前没有客户端路由消费这项配置。未来的 History API 路由可以在引入所需路由时，同时添加显式服务器规则或配置字段，无需保留推测性的公开选项。 ## 后果 diff --git a/.agents/notes/implemented/architecture/2026-08-11-plugin-settings-tabs.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-08-21-deepseek-files-inline-fallback.i18n.yaml similarity index 56% rename from .agents/notes/implemented/architecture/2026-08-11-plugin-settings-tabs.i18n.yaml rename to .agents/notes/implemented/bug-fix/2026-08-21-deepseek-files-inline-fallback.i18n.yaml index 20ffb2b3e5..c4f148394e 100644 --- a/.agents/notes/implemented/architecture/2026-08-11-plugin-settings-tabs.i18n.yaml +++ b/.agents/notes/implemented/bug-fix/2026-08-21-deepseek-files-inline-fallback.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-11-plugin-settings-tabs.md -2026-08-11-plugin-settings-tabs.md: 96e4c48926c835bcc3e6b5bf2d59126a999fbb2b -2026-08-11-plugin-settings-tabs.zh.md: fa8f4626408316fd1afbfa1ab4b4cab14d69c538 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-21-deepseek-files-inline-fallback.md +2026-08-21-deepseek-files-inline-fallback.md: 7442089038e2cf47f37661c0f098054d03f67aef +2026-08-21-deepseek-files-inline-fallback.zh.md: 0534514f9bc52f7871f43c288466643cebc7d69c diff --git a/.agents/notes/implemented/bug-fix/2026-08-21-deepseek-files-inline-fallback.md b/.agents/notes/implemented/bug-fix/2026-08-21-deepseek-files-inline-fallback.md new file mode 100644 index 0000000000..7442089038 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-08-21-deepseek-files-inline-fallback.md @@ -0,0 +1,37 @@ +# Agent Note: Recover DeepSeek image requests from Files resolution failures + +Status: implemented + +English | [中文](2026-08-21-deepseek-files-inline-fallback.zh.md) + +## Problem + +The direct DeepSeek vision route uses provider file ids so repeated requests do not resend image bytes. An unavailable, unsupported, or stalled Files endpoint can prevent chat before the model request begins even though the same endpoint still accepts inline image data. A fallback that retains the 128MiB Files budget would exceed the inline request-body limit, while a fallback that independently transforms images could send different pixels from the failed file-id attempt. + +## Decision + +Files remains the preferred transport. Each request-image file resolution has the configurable `filesApiTimeoutMs` deadline, one minute by default. The stream idle deadline defaults to five minutes, so the Files deadline normally leaves time for inline fallback. A deployment may configure the stream idle deadline to expire first. Successful resolutions refresh the outer idle watchdog. Caller cancellation and the outer stream deadline remain terminal outcomes. + +A file resolution failure discards the transient file parts assembled for that chat attempt and rebuilds the complete image request with base64 data URLs. Every retained image uses the already prepared deterministic `RequestImageAttachment`; the fallback performs no additional decode, resize, or encode, and a chat request never mixes file ids with inline images. Upload mappings committed before a later image fails remain available to later requests. The next request tries Files again, so recovery requires no process-wide outage state. + +Inline fallback has a separate base64-expanded high watermark, `maxInlineRequestImageBytes`, of 20MiB by default. `inlineImageOffloadByteQuantum` defaults to 10MiB, so crossing the high watermark advances the deterministic oldest-image prefix to the next 10MiB removal boundary. The existing 600-image bound and count quantum still apply. File mode retains its 128MiB high watermark and 64MiB removal quantum. + +Provider chat errors keep their existing classifications. A stale file id is invalidated, re-uploaded, and retried once. If that replacement resolution fails, the permitted retry uses the inline representation. A generic chat failure does not switch transports because it does not establish that Files resolution failed. + +## Alternatives considered + +**Send inline images first.** Rejected because successful Files uploads allow deterministic request bytes to be reused across turns without repeating base64 in every request. + +**Mix resolved file ids with inline images after one upload fails.** Rejected because the request would still depend on the failing Files service and would have two independent image budgets. + +**Apply the 128MiB Files bound to inline fallback.** Rejected because base64 expands the payload and can exceed the chat request-body limit. The 20MiB budget leaves space for JSON, text history, and tools. + +**Remember an outage and bypass Files on later requests.** Rejected because a process-local circuit state introduces recovery timing and shared failure state. Retrying Files on the next request detects service recovery without another timer. + +## Verification + +Serializer tests cover file and data-URL representations over the same request versions, all supported media types, tool-result placement, and 20-to-10 base64 offload. Adapter tests cover immediate resolution failure, failure after a partial set of file ids, deadline-triggered fallback, stale-id replacement failure, all-inline request bodies, caller cancellation without fallback, and generic chat failure without a transport switch. Configuration tests cover both inline bounds and independent Files and stream idle deadlines. + +## Consequences + +A Files outage no longer prevents an image chat that fits the inline budget. Fallback repeats image bytes and may omit more history than file mode because its limit is lower. A request can leave successful uploads behind when a later image fails, but their indexed mappings are reusable and do not change the chat body sent by the fallback. Explicit file-management operations continue to expose their own failures. diff --git a/.agents/notes/implemented/bug-fix/2026-08-21-deepseek-files-inline-fallback.zh.md b/.agents/notes/implemented/bug-fix/2026-08-21-deepseek-files-inline-fallback.zh.md new file mode 100644 index 0000000000..0534514f9b --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-08-21-deepseek-files-inline-fallback.zh.md @@ -0,0 +1,37 @@ +# Agent Note: DeepSeek Files 解析失败时恢复图片请求 + +Status: implemented + +[English](2026-08-21-deepseek-files-inline-fallback.md) | 中文 + +## Problem + +DeepSeek 官方视觉路由使用提供方文件 ID，使重复请求不必再次发送图片字节。如果 Files 端点不可用、不受支持或一直不返回，chat 会在模型请求开始前失败，即使同一端点仍接受内联图片数据。沿用 128MiB Files 预算的回退会超过内联请求体上限，独立转换图片的回退则可能发送与失败 file ID 尝试不同的像素。 + +## Decision + +Files 仍是首选传输方式。每张请求图片的文件解析都有可配置的 `filesApiTimeoutMs` 时限，默认一分钟。stream idle 时限默认为五分钟，因此 Files 时限通常会为内联回退留出时间。部署也可以把 stream idle 时限设得更短，让它先终止请求。每次成功解析都会刷新外层 idle watchdog。调用方取消和外层流时限仍直接终止请求。 + +文件解析失败后，适配器会丢弃为该次 chat 尝试组装的临时文件块，并用 base64 data URL 重新组装完整图片请求。每张保留图片都复用已经准备好的确定性 `RequestImageAttachment`；回退不会再次解码、缩放或编码，同一个 chat 请求也不会混用 file ID 和内联图片。较早图片在后续图片失败前已经提交的上传映射会保留，供之后请求使用。下一次请求会重新尝试 Files，因此不需要保存进程级故障状态。 + +内联回退使用独立的 base64 膨胀后高水位，`maxInlineRequestImageBytes` 默认为 20MiB。`inlineImageOffloadByteQuantum` 默认为 10MiB，因此越过高水位时，确定性的最旧图片前缀会推进到下一个 10MiB 移除边界。现有 600 张图片上限和数量步长继续生效。文件模式继续使用 128MiB 高水位和 64MiB 移除步长。 + +提供方 chat 错误继续使用现有分类。失效 file ID 会被清除、重新上传并重试一次。如果替换解析失败，这次允许的重试会使用内联表示。普通 chat 错误不能证明 Files 解析失败，因此不会切换传输方式。 + +## Alternatives considered + +**优先发送内联图片。** 不采用，因为 Files 上传成功后可以跨轮次复用确定性的请求字节，不必在每次请求中重复 base64。 + +**某次上传失败后混用已解析 file ID 和内联图片。** 不采用，因为请求仍依赖发生故障的 Files 服务，而且需要同时处理两套图片预算。 + +**把 128MiB Files 上限用于内联回退。** 不采用，因为 base64 会扩大负载，并可能超过 chat 请求体上限。20MiB 预算会为 JSON、文本历史和工具留下空间。 + +**记住故障，并在后续请求中跳过 Files。** 不采用，因为进程级状态会引入恢复时间和共享故障状态。下一次请求重新尝试 Files，可以在无需新增计时器的情况下发现服务恢复。 + +## Verification + +序列化测试覆盖相同请求版本的文件和 data URL 表示、全部支持的媒体类型、工具结果位置，以及 20MiB 到 10MiB 的 base64 offload。适配器测试覆盖立即解析失败、部分 file ID 成功后的失败、时限触发的回退、失效 ID 替换失败、全内联请求体、调用方取消时不回退，以及普通 chat 错误不切换传输方式。配置测试覆盖两项内联预算，以及相互独立的 Files 和 stream idle 时限。 + +## Consequences + +符合内联预算的图片 chat 不会再因 Files 故障而失败。回退会重复发送图片字节，而且由于上限更低，可能比文件模式省略更多历史。后续图片失败时，请求可能留下较早图片的成功上传，但这些索引映射可以复用，也不会改变回退发送的 chat 请求体。显式文件管理操作继续暴露自身错误。 diff --git a/.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.i18n.yaml b/.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.i18n.yaml index ac212df09f..1242784a2c 100644 --- a/.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.md -2026-06-17-filesystem-tool-schemas.md: 0245fd1d8c8771ba73973a1c298cfbbf520ca47a -2026-06-17-filesystem-tool-schemas.zh.md: 62b1928d9ea9e309f6cce71a2153b0f61036da17 +2026-06-17-filesystem-tool-schemas.md: 7680b1200314b5cfe89f8243e2690c748d8c00fe +2026-06-17-filesystem-tool-schemas.zh.md: d75c3f83d7be6dde2c9b70a40411433c581ce830 diff --git a/.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.md b/.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.md index 0245fd1d8c..7680b12003 100644 --- a/.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.md +++ b/.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.md @@ -107,6 +107,6 @@ Schema tests pin the required/optional argument set per tool, empty-`old_string` **The first schema is intentionally smaller than Claude Code's.** Dropping PDF pages, multimodal read, rich grep/list flags, and expected hash fields keeps the implementation focused, but users may ask for those quickly. They arrive as separate Agent Notes or focused follow-ups rather than overloads of the initial schema. -**No explicit model-facing stale guard in v1.** The schema does not ask the model to provide an expected hash/version. That is intentional: stale checks come from backend-produced versions and the `dsh-fs-observation-policy` plugin's observed state, not from fragile model-copied tokens. Filesystem safety failures surface through structured `FsError` codes owned by `dsh-fs`, not through model-supplied version fields. +**No explicit model-facing stale guard.** The schema does not ask the model to provide an expected hash/version. That is intentional: stale checks come from backend-produced versions and the `dsh-fs-observation-policy` plugin's observed state, not from fragile model-copied tokens. Filesystem safety failures surface through structured `FsError` codes owned by `dsh-fs`, not through model-supplied version fields. **Naming becomes public API.** Once shipped, changing `file_path` to `filePath` or `old_string` to `oldString` would churn prompts, examples, and downstream clients. This Agent Note chooses snake_case up front and treats it as the stable model-facing contract. diff --git a/.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.zh.md b/.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.zh.md index 62b1928d9e..d75c3f83d7 100644 --- a/.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.zh.md +++ b/.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.zh.md @@ -107,6 +107,6 @@ schema 测试固定每个工具的必填/可选参数集、空 `old_string` 拒 **首版 schema 有意小于 Claude Code 的。** 去掉 PDF pages、多模态 read、丰富的 grep/list flag 和 expected hash 字段使实现保持聚焦，但用户可能很快就会提出这些需求。这些功能将通过独立 Agent Note 或聚焦的后续工作引入，而不是让初始 schema 承载过多内容。 -**v1 中没有显式的面向模型的陈旧版本防护。** schema 不要求模型提供 expected hash/version。这是有意为之：陈旧检查来自后端产生的版本和 `dsh-fs-observation-policy` 插件的观测状态，而非模型复制的脆弱令牌。文件系统安全失败通过 `dsh-fs` 拥有的结构化 `FsError` 代码暴露，而非模型提供的版本字段。 +**没有显式的面向模型的陈旧版本防护。**schema 不要求模型提供 expected hash/version。这是有意为之：陈旧检查来自后端产生的版本和 `dsh-fs-observation-policy` 插件的观测状态，而非模型复制的脆弱令牌。文件系统安全失败通过 `dsh-fs` 拥有的结构化 `FsError` 代码暴露，而非模型提供的版本字段。 **命名成为公开 API。** 一旦发布，将 `file_path` 改为 `filePath` 或 `old_string` 改为 `oldString` 会导致提示词、示例和下游客户端随之改动。本 Agent Note 预先选择 snake_case，并将其视为稳定的面向模型的约定。 diff --git a/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.i18n.yaml b/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.i18n.yaml index dd7b9c49e5..d121a5db15 100644 --- a/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md -2026-06-30-session-store-fork-api.md: 01ff631bc449cf481d89e860934f3f7b94486062 -2026-06-30-session-store-fork-api.zh.md: f0fd158a51f59400756b2724332e7fb115e5e033 +2026-06-30-session-store-fork-api.md: ff7617f4bb306926a7b0782751ae82f6ef0c6371 +2026-06-30-session-store-fork-api.zh.md: ecef7ba2985321677b29d3fc7692a8dcb7afb2b6 diff --git a/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md b/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md index 01ff631bc4..ff7617f4bb 100644 --- a/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md +++ b/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md @@ -46,4 +46,4 @@ The Host creates the child through the agent registry with the selected seed and The public API stays small and discoverable: live session branching is part of `ctx.sessions`, next to `create({ seed })`, rather than a standalone service or a two-step helper pair. Persistence continues to work through existing `session/created` and `session/flush` behavior: a forked child starts life with seeded events, so existing backends persist that seed once and preserve `parentSession` / `seedLength` in the header. -The v1 scope still excludes ACP `session/fork`, unloaded persisted-session forking, model-facing tools, and subagent refactors. If a future ACP method is added, it should advertise the capability only after it has protocol and snapshot coverage; this Agent Note adds no ACP wire behavior, so no ACP snapshot is required. Fork-child replay remains covered by the existing [seed-boundary testing Agent Note](../testing/2026-06-22-fork-child-replay-seed-boundary.md); focused store, Host, carrier, and client tests pin the boundary and reconciliation contracts, while the real Chromium scenario pins the assembled message action and lineage tree. +This decision excludes ACP `session/fork`, unloaded persisted-session forking, model-facing tools, and subagent refactors. If a future ACP method is added, it should advertise the capability only after it has protocol and snapshot coverage; this Agent Note adds no ACP wire behavior, so no ACP snapshot is required. Fork-child replay remains covered by the existing [seed-boundary testing Agent Note](../testing/2026-06-22-fork-child-replay-seed-boundary.md); focused store, Host, carrier, and client tests pin the boundary and reconciliation contracts, while the real Chromium scenario pins the assembled message action and lineage tree. diff --git a/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.zh.md b/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.zh.md index f0fd158a51..ecef7ba298 100644 --- a/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.zh.md +++ b/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.zh.md @@ -46,4 +46,4 @@ Host 通过 agent（智能体）注册表，以选定的种子和谱系创建子 公开 API 保持精简且易于发现：活跃会话分支是 `ctx.sessions` 的一部分，紧邻 `create({ seed })`，而非一个独立服务或一对两步辅助函数。持久化继续通过现有的 `session/created` 和 `session/flush` 行为运作：fork 出的子会话创建时便带有种子事件，因此现有后端只需持久化该种子一次，并在 header 中保存 `parentSession`／`seedLength`。 -v1 范围仍然排除 ACP（Agent Client Protocol） `session/fork`、对未加载的已持久化会话的 fork、面向模型的工具，以及 subagent 重构。如果未来添加 ACP 方法，应在具备协议与快照覆盖后才声明支持该能力；本 Agent Note 不添加任何 ACP 协议行为，因此不需要 ACP 快照。fork 子会话的回放仍由现有的[种子边界测试 Agent Note](../testing/2026-06-22-fork-child-replay-seed-boundary.zh.md) 覆盖；store、Host、载体与客户端的专项测试固定边界和对账约定，真实 Chromium 场景则固定组装后的消息操作与谱系树。 +本决策排除 ACP（Agent Client Protocol）`session/fork`、对未加载的已持久化会话执行 fork、面向模型的工具，以及 subagent 重构。如果未来添加 ACP 方法，应在具备协议与快照覆盖后才声明支持该能力；本 Agent Note 不添加任何 ACP 协议行为，因此不需要 ACP 快照。fork 子会话的回放仍由现有的[种子边界测试 Agent Note](../testing/2026-06-22-fork-child-replay-seed-boundary.zh.md)覆盖；store、Host、载体与客户端的专项测试固定边界和对账约定，真实 Chromium 场景则固定组装后的消息操作与谱系树。 diff --git a/.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.i18n.yaml b/.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.i18n.yaml index d9fe00803c..70f4e6e6dc 100644 --- a/.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-05-dynamic-workflows.md -2026-07-05-dynamic-workflows.md: eff37365534cd41e46c98e20a5e763a233330647 -2026-07-05-dynamic-workflows.zh.md: 927d194d3432824c6e3026826e07993ce27fce8b +2026-07-05-dynamic-workflows.md: c1bce5d902c77aa1958905f4c31047524ea4b2b3 +2026-07-05-dynamic-workflows.zh.md: 035468a2f4c6dbb0a584a68ba3944681618d9d3b diff --git a/.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.md b/.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.md index eff3736553..c1bce5d902 100644 --- a/.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.md +++ b/.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.md @@ -57,7 +57,7 @@ Worker-side logic runs through an in-process `MessageChannel` so V8 coverage mea ## Deferred (documented non-goals) - **Background collection** (start tool → run id → completion notice → collect), designed alongside shell/subagent background unification. -- **Journaling + resume** (`resumeFromRunId`, cached agent() prefixes) — implementing it reintroduces CC's determinism bans as a script-contract tightening (scripts may read the clock today). +- **Journaling + resume** (`resumeFromRunId`, cached agent() prefixes) — implementing it reintroduces CC's determinism bans as a script-contract tightening (scripts may read the clock). - **Saved/bundled workflows** (a `.deepseek/workflows/` registry, slash-command API) and **script persistence to a run directory** (the tool-call event already records the script durably). - **Nested `workflow()`**, **token `budget`**, and the `effort`/`isolation`/`agentType` agent options (each rejects loud with a message naming it deferred). - **An overall run wall-clock timeout** — cancellation always frees the caller (result settles within the grace), so a cap on total run time is a policy knob for the background redesign, not a correctness need here. diff --git a/.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.zh.md b/.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.zh.md index 927d194d34..035468a2f4 100644 --- a/.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.zh.md +++ b/.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.zh.md @@ -57,7 +57,7 @@ worker 侧逻辑通过进程内 `MessageChannel` 运行，使 V8 覆盖率能够 ## 延迟（明确的非目标） - **后台收集**（启动工具 → run id → 完成通知 → 收集），与 shell/subagent 后台统一一起设计。 -- **日志化 + 恢复**（`resumeFromRunId`、缓存的 agent() 前缀）：实现它会以脚本约定收紧的形式重新引入 CC 的确定性禁令（脚本目前可以读取时钟）。 +- **日志化 + 恢复**（`resumeFromRunId`、缓存的 agent() 前缀）：实现它会以脚本约定收紧的形式重新引入 CC 的确定性禁令（脚本可以读取时钟）。 - **保存／打包的工作流**（`.deepseek/workflows/` 注册表、斜杠命令 API）和**脚本持久化到运行目录**（工具调用事件已经持久记录了脚本）。 - **嵌套 `workflow()`**、**token `budget`**，以及 `effort`/`isolation`/`agentType` agent 选项（每个都会明确拒绝，并在消息中注明其已延迟实现）。 - **整体运行的挂钟超时**：取消总能释放调用方（result 在宽限期内 settle），因此总运行时间上限是后台重设计的策略旋钮，不是此处的正确性需求。 diff --git a/.agents/notes/implemented/feature/2026-07-05-skill-system.i18n.yaml b/.agents/notes/implemented/feature/2026-07-05-skill-system.i18n.yaml index 4b4a5e85c6..ce361aadbd 100644 --- a/.agents/notes/implemented/feature/2026-07-05-skill-system.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-05-skill-system.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-05-skill-system.md -2026-07-05-skill-system.md: 481cdecbb4acaf5a0c38106ab47c6c489aca507c -2026-07-05-skill-system.zh.md: a0d7dd953337b0e9e764738d6d4cd7ef825999f5 +2026-07-05-skill-system.md: 650ecc0a943d3fd5419481f13d14e5a3a46e94f2 +2026-07-05-skill-system.zh.md: d3330060efe5c9b15752206405efcd562fa2691b diff --git a/.agents/notes/implemented/feature/2026-07-05-skill-system.md b/.agents/notes/implemented/feature/2026-07-05-skill-system.md index 481cdecbb4..650ecc0a94 100644 --- a/.agents/notes/implemented/feature/2026-07-05-skill-system.md +++ b/.agents/notes/implemented/feature/2026-07-05-skill-system.md @@ -14,7 +14,7 @@ DeepSeek Harness uses the same primitive so project-specific review, plugin-auth `@deepseek-ai/dsh-skill` is the pure provider registry (`ctx.skills`), `@deepseek-ai/dsh-skill-filesystem` is the shipped local filesystem provider, and `@deepseek-ai/dsh-tool-skill` owns the durable session catalog and model-facing loader tool. `dsh-agent-spine-demo` loads the registry, local provider, and consumer by default so TUI, headless, and ACP apps get the same behavior while embedded or remote providers contribute skills without changing the registry or consumer. Its `skills` config forwards `registry`, `local`, and `tool` branches to those owners. -Dedicated packaged providers can contribute immutable skills without filesystem discovery. The shipped CLI declares `@deepseek-ai/dsh-skill-badge` disabled by default; enabling its composition row contributes the official badge instructions through the same registry and consumer ([decision](2026-08-06-bundled-dsh-badge-skill.md)). +Dedicated packaged providers can contribute immutable skills without filesystem discovery. The shipped CLI declares `@deepseek-ai/dsh-skill-badge` disabled by default; enabling its composition row contributes the official badge instructions through the same registry and consumer (see [the package contract](../../../../packages/skill/skill-badge/README.md)). Provider plugins register synchronously during `apply()`. Provider membership is direct effect-owned state: registration and disposal invalidate completed catalogs synchronously, and discovery reads the current provider map on demand rather than observing registry-change events. Provider catalogs return ranked candidates from awaited `list()` calls, where remote providers perform initialization, authentication, and discovery while honoring the lookup abort signal. The registry validates each candidate, resolves same-name skills first-wins by rank, provider registration order, and provider-local order, then sorts summaries by skill name for deterministic consumers. It caches only completed catalog snapshots and retries when a provider/runtime revision changes during discovery, so an unload cannot freeze a stale, unresolvable skill into a session catalog. Runtime `ctx.skills.register(...)` remains a convenience for embedded in-process skills and uses project-over-user priority; `runtime` is reserved as the registry-owned provider name. diff --git a/.agents/notes/implemented/feature/2026-07-05-skill-system.zh.md b/.agents/notes/implemented/feature/2026-07-05-skill-system.zh.md index a0d7dd9533..d3330060ef 100644 --- a/.agents/notes/implemented/feature/2026-07-05-skill-system.zh.md +++ b/.agents/notes/implemented/feature/2026-07-05-skill-system.zh.md @@ -14,7 +14,7 @@ DeepSeek Harness 使用同一原语，使项目特定的评审、插件编写和 `@deepseek-ai/dsh-skill` 是纯提供方注册表（`ctx.skills`），`@deepseek-ai/dsh-skill-filesystem` 是随附的本地文件系统提供方，`@deepseek-ai/dsh-tool-skill` 负责持久化会话目录与面向模型的 loader 工具。`dsh-agent-spine-demo` 默认加载注册表、本地提供方和消费方，使 TUI、headless 与 ACP（Agent Client Protocol）应用获得相同行为，同时嵌入式或远程提供方可在不修改注册表或消费方的前提下贡献 skill。其 `skills` 配置将 `registry`、`local` 和 `tool` 分支分别转发给对应的所有者。 -专用的随包提供方可以贡献不可变的 skill，无需文件系统发现。交付的 CLI（命令行界面）默认将 `@deepseek-ai/dsh-skill-badge` 声明为禁用；启用其组合配置行，就会通过同一个注册表和消费方贡献官方徽章指令（见[决策](2026-08-06-bundled-dsh-badge-skill.zh.md)）。 +专用的随包提供方可以贡献不可变的 skill，无需文件系统发现。交付的 CLI（命令行界面）默认将 `@deepseek-ai/dsh-skill-badge` 声明为禁用；启用其组合配置行，就会通过同一个注册表和消费方贡献官方徽章指令（见[包约定](../../../../packages/skill/skill-badge/README.zh.md)）。 提供方插件在 `apply()` 期间同步注册。提供方成员资格是由直接 effect 持有的状态：注册与 dispose（资源释放）同步地使已完成的目录失效，发现操作按需读取当前提供方映射而非监听注册表变更事件。提供方目录从等待的 `list()` 调用返回排序后的候选项，远程提供方在此过程中执行初始化、认证和发现，同时遵守查找的 abort 信号。注册表校验每个候选项，按排名、提供方注册顺序和提供方内部顺序以先到先得方式解决同名 skill 冲突，然后按 skill 名称排序摘要以保证消费方获得确定性结果。它仅缓存已完成的目录快照，并在发现过程中提供方／运行时修订版本发生变化时重试，因此卸载操作不会将一个陈旧且不可解析的 skill 冻结到会话目录中。运行时 `ctx.skills.register(...)` 仍作为嵌入式进程内 skill 的便捷方式保留，使用 project 优先于 user 的优先级；`runtime` 保留为注册表拥有的提供方名称。 diff --git a/.agents/notes/implemented/feature/2026-07-06-sandbox.i18n.yaml b/.agents/notes/implemented/feature/2026-07-06-sandbox.i18n.yaml index ee6ca0ce0d..cf36bebebf 100644 --- a/.agents/notes/implemented/feature/2026-07-06-sandbox.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-06-sandbox.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-06-sandbox.md -2026-07-06-sandbox.md: 7c451d8fb2d59c20ad8170e8c74a93fad911573a -2026-07-06-sandbox.zh.md: 6fa1659039f916732afd3b5f24831bd062f11498 +2026-07-06-sandbox.md: 660406167b757a0c7161184dd98e4ab6327f12f8 +2026-07-06-sandbox.zh.md: e4fcb37a4cb56b7aa90eebe365c3ec5ddc0a9ed1 diff --git a/.agents/notes/implemented/feature/2026-07-06-sandbox.md b/.agents/notes/implemented/feature/2026-07-06-sandbox.md index 7c451d8fb2..660406167b 100644 --- a/.agents/notes/implemented/feature/2026-07-06-sandbox.md +++ b/.agents/notes/implemented/feature/2026-07-06-sandbox.md @@ -14,7 +14,7 @@ Confinement alone leaves two gaps. A denial with no escalation path is terminal ## Decision -One seam, one per-platform chain of local backends, one consumer, and two levers on top: a per-call escalation path and per-session runtime modes. Everything below composes from the leaf `cordis.yml`; nothing touches `agent-loop`. Cross-family fs enforcement and per-session workspace roots landed as follow-ups on the same policy carrier; the remaining phases — the `subagent-acp` consumer, more environments, and a Windows chain — stay under § Deferred phases. +One seam, one per-platform chain of local backends, one consumer, and two levers on top: a per-call escalation path and per-session runtime modes. Everything below composes from the leaf `cordis.yml`; nothing touches `agent-loop`. Cross-family fs enforcement, per-session workspace roots, and the Windows chain are shipped follow-ups on the same policy carrier; the `subagent-acp` consumer and more environments remain under § Deferred phases. ### How a deployment uses it @@ -128,7 +128,6 @@ Each phase gets its full design when picked up, validated against the code at th - **Second consumer** — `subagent-acp` optionally confines child agents (per-call policy; unconfined default — a child agent must write its own persistence). - **More environments** — an environment-coherent capability group example (e.g. bash+fs against one container). -- **Windows chain** — `PLATFORM_CHAINS.win32` is reserved and empty (fail-closed); filling it means a confinement runner from the AppContainer/restricted-token family, shipped from the main repository under `native/` following the `@deepseek-ai/node-addon-landlock-run` template, plus its profile dialect, denial signatures, and runner-failure rules. Wrapping the third-party landstrip runner instead was [considered and rejected](../../rejected/feature/2026-07-26-evaluate-landstrip-for-windows-sandbox-rung.md) — not battle-tested enough for a security invariant. ## Alternatives considered @@ -186,7 +185,7 @@ Costs and accepted limits: - **A command came back with `[sandbox: file access denied under read-only mode]` — did it fail?** It RAN, and the kernel refused a file effect: the denial is a result fact orthogonal to exit code. The teaching forbids retrying around it; the one sanctioned move is the same command retried once with an escalation request. - **How is a BROKEN sandbox told apart from a failing command?** Any provider-argv spawn rejection proves the confined launch never started, but it identifies a broken runner only when the caller-owned workdir is usable and Node reports attributable `ENOENT` or `EACCES` for that argv[0]. A bare `syscall: 'spawn'` without an exact error path and all other rejections remain ordinary command-start errors. After a process starts, runner failure outranks denial only when one `runnerFailureRules` entry matches both its optional exit-code gate and a fatal stderr line after exact informational exclusions. Foreground failures throw structured `SANDBOX_UNAVAILABLE` with spawn or matched-line detail; an asynchronously rejected or settled background job stamps `sandbox.runnerFailed` and renders its own marker. A `SubprocessRuntime` that synchronously throws the same `ENOENT`/`EACCES` shape with the runner path makes background start throw the structured error; other synchronous errors propagate unchanged. A Landlock partial-enforcement notice plus an ordinary child failure remains a command result. -- **What happens on a platform with no backend — Windows today?** `confine()` throws the fail-closed `SANDBOX_UNAVAILABLE` and the command never spawns; `win32` is a reserved EMPTY chain, pinned by test to fail closed identically until a Windows runner fills it (§ Deferred phases). +- **What happens on a platform with no backend?** `confine()` throws the fail-closed `SANDBOX_UNAVAILABLE`, and the command never spawns. - **`bwrap` is installed on my host but unusable (disabled unprivileged userns, an LSM denying `mount`) — what happens?** The chain probe is functional — it builds and enforces a real profile rather than checking `--version` — so a present-but-unusable `bwrap` fails its probe, selection falls to the packaged Landlock launcher, and the verdict is cached for the provider's lifetime. - **Does the sandbox restrict network or process visibility?** `SandboxMode` claims FILE effects only, and no backend claims network. Process visibility is backend-specific: bwrap unshares PID and mounts matching procfs because host `/proc/` magic links otherwise bypass file confinement, while Landlock and Seatbelt leave process visibility unchanged ([decision](../bug-fix/2026-08-06-bwrap-private-pid-namespace.md)). Whether network restriction becomes its own knob is left open in § The seam. - **Which tools actually run confined?** OS subprocesses through `ctx.shell` — the bash tools, and hook commands transitively — plus the filesystem tools (`read`/`write`/`edit`) through the sandboxed `ctx.fs` provider (the [cross-family fs sandbox RFC](2026-07-14-cross-family-fs-sandbox.md)): bash confines via the OS runner, fs via an in-process path fence, both keying off the same `ctx.sandboxPolicy` mode. web/todo stay in-process and unfenced (web's only effect is network, outside the file-effect mode vocabulary). diff --git a/.agents/notes/implemented/feature/2026-07-06-sandbox.zh.md b/.agents/notes/implemented/feature/2026-07-06-sandbox.zh.md index 6fa1659039..e4fcb37a4c 100644 --- a/.agents/notes/implemented/feature/2026-07-06-sandbox.zh.md +++ b/.agents/notes/implemented/feature/2026-07-06-sandbox.zh.md @@ -14,7 +14,7 @@ harness 是一个 SDK，因此约束必须是开发者可组合的能力：是 ## 决策 -一个 seam、一条按平台的本地后端链、一个消费方，加上两个上层控制项：按调用的升级路径与按会话的运行时模式。以下所有内容均从叶子 `cordis.yml` 组合而来；不触及 `agent-loop`。跨工具族 fs 强制与按会话工作区根目录已经作为后续设计落到同一策略载体上；剩余阶段——`subagent-acp` 消费方、更多环境与 Windows 链——仍列在 § 延迟阶段。 +一个 seam、一条按平台的本地后端链、一个消费方，加上两个上层控制项：按调用的升级路径与按会话的运行时模式。以下所有内容均从叶子 `cordis.yml` 组合而来；不触及 `agent-loop`。跨工具族 fs 强制、按会话工作区根目录与 Windows 链已经作为后续设计落到同一策略载体上；`subagent-acp` 消费方与更多环境仍列在 § 延迟阶段。 ### 部署方式 @@ -128,7 +128,6 @@ fs/web/todo 在进程内执行，因此它们的沙箱语义是各自能力边 - **第二个消费方**——`subagent-acp` 可选地约束子 agent（按调用策略；默认无约束——子 agent 必须写入自己的持久化）。 - **更多环境**——环境一致的能力组示例（如 bash+fs 对一个容器）。 -- **Windows 链**——`PLATFORM_CHAINS.win32` 保留为空（失败关闭）；填充它意味着来自 AppContainer/restricted-token 家族的约束 runner，由主仓库在 `native/` 下按 `@deepseek-ai/node-addon-landlock-run` 模板交付，加上其 profile 方言、拒绝签名和 runner 失败规则。改为包装第三方 landstrip runner 的方案[经考虑后已驳回](../../rejected/feature/2026-07-26-evaluate-landstrip-for-windows-sandbox-rung.zh.md)——它所经受的实战检验还不足以承载安全不变式。 ## 曾考虑的替代方案 @@ -186,7 +185,7 @@ fs/web/todo 在进程内执行，因此它们的沙箱语义是各自能力边 - **一个命令返回了 `[sandbox: file access denied under read-only mode]`——它失败了吗？** 它运行了，内核拒绝了一个文件操作：拒绝是与退出码正交的结果事实。相关指令禁止通过绕过限制来重试；唯一被认可的动作是以升级请求重试同一命令一次。 - **如何区分损坏的沙箱与失败的命令？** 提供方 argv 的任何 spawn 拒绝都能证明受限启动从未开始，但只有在调用方拥有的 workdir 可用，且 Node 为该 argv[0] 报告可归因的 `ENOENT` 或 `EACCES` 时，才能据此判定 runner 损坏。没有精确错误路径的裸 `syscall: 'spawn'` 和其他所有拒绝仍是普通的命令启动错误。进程启动后，只有当 `runnerFailureRules` 中某一条目同时匹配其可选退出码门控，以及排除整行精确信息性行后的一行致命 stderr 诊断时，runner 失败才会优先于拒绝。前台失败会抛出结构化的 `SANDBOX_UNAVAILABLE`，并附带 spawn 错误或匹配行作为详细信息；遭异步拒绝或已结算的后台任务则盖章 `sandbox.runnerFailed` 并渲染自己的标记。如果 `SubprocessRuntime` 同步抛出同样带有 runner 路径的 `ENOENT`／`EACCES` 形态，后台启动会抛出该结构化错误；其他同步错误原样传播。Landlock 部分强制执行通知加上普通子进程失败时，仍返回命令结果。 -- **在没有后端的平台上会发生什么——今天的 Windows？** `confine()` 抛出失败关闭的 `SANDBOX_UNAVAILABLE`，命令永不 spawn；`win32` 是保留的空链，由测试固定为同样失败关闭，直到 Windows runner 填充它（§ 延迟阶段）。 +- **在没有后端的平台上会发生什么？** `confine()` 抛出失败关闭的 `SANDBOX_UNAVAILABLE`，命令永不 spawn。 - **`bwrap` 已安装在我的主机上但不可用（禁用了非特权 userns、LSM 拒绝 `mount`）——会发生什么？** 链探测是功能性的——它构建并强制一个真实 profile 而非检查 `--version`——因此存在但不可用的 `bwrap` 探测失败，选择落到已打包的 Landlock launcher，结论在提供方生命周期内缓存。 - **沙箱限制网络或进程可见性吗？** `SandboxMode` 只声称文件影响，并且没有后端声称限制网络。进程可见性因后端而异：bwrap 会取消共享 PID 命名空间，并挂载与其匹配的 procfs，因为宿主 `/proc/` 的魔法链接会绕过文件约束；Landlock 与 Seatbelt 则保持进程可见性不变（见[相关决策](../bug-fix/2026-08-06-bwrap-private-pid-namespace.zh.md)）。网络限制是否成为自己的旋钮留在 § seam 中开放。 - **哪些工具实际在约束下运行？** 通过 `ctx.shell` 的 OS 子进程——bash 工具及传递性的钩子命令——再加上通过沙箱化 `ctx.fs` 提供方运行的文件系统工具（`read`/`write`/`edit`，见[跨工具族 fs 沙箱 RFC](2026-07-14-cross-family-fs-sandbox.zh.md)）：bash 通过 OS runner 约束，fs 通过进程内路径围栏约束，二者都以同一个 `ctx.sandboxPolicy` 模式为键。web/todo 仍在进程内且不受限制（web 的唯一效果是网络，不在文件效果模式词汇内）。 diff --git a/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.i18n.yaml b/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.i18n.yaml index 4eb1d7d4df..5ec6161319 100644 --- a/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.md -2026-07-07-mcp-client-plugin.md: f9d997fd06dbf14f86ec344a2d5f16c7412119d0 -2026-07-07-mcp-client-plugin.zh.md: 8cd59e5efe415b75c9d797a569c4865b4a91d750 +2026-07-07-mcp-client-plugin.md: cde9cf1130d6b6b971ddf35c64e34ad6d9fb7dee +2026-07-07-mcp-client-plugin.zh.md: 0cf69a97bc714efcc4083fc2b37519dfc10cdf32 diff --git a/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.md b/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.md index f9d997fd06..cde9cf1130 100644 --- a/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.md +++ b/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.md @@ -83,7 +83,7 @@ The model sees `mcp__github__create_issue`, `mcp__github__search_code`, `mcp__we ### Lifecycle -Boot-time from `cordis.yml`. HMR (`@cordisjs/plugin-hmr`) provides hot-swap: editing the yml entry triggers dispose of the old instance (disconnects, unregisters tools) and creation of a new one (connects, discovers, registers). No runtime-dynamic API for now. Public names are pure functions of `(serverName, rawName)`, so an HMR swap that keeps `serverName` recreates identical model-facing names — session history and permission rules stay valid — and adding or removing an unrelated server never renames an existing tool. +Boot-time from `cordis.yml`. HMR (`@cordisjs/plugin-hmr`) provides hot-swap: editing the yml entry triggers dispose of the old instance (disconnects, unregisters tools) and creation of a new one (connects, discovers, registers). No runtime-dynamic API is provided. Public names are pure functions of `(serverName, rawName)`, so an HMR swap that keeps `serverName` recreates identical model-facing names — session history and permission rules stay valid — and adding or removing an unrelated server never renames an existing tool. ### Tool discovery and registration @@ -167,7 +167,7 @@ Rejected. There is no foreseeable alternative MCP client implementation — MCP ### Auto-reconnect with exponential backoff -Rejected for v1: it added a partial-availability state (tools registered but temporarily non-functional), and stdio crashes often indicate configuration problems retrying cannot fix; HMR was the recovery path. Operational feedback reversed the deferral — the [auto-reconnect Agent Note](2026-08-06-mcp-client-auto-reconnect.md) implements it with a bounded per-outage budget and an opt-out. +Rejected by the connect-once design: it added a partial-availability state (tools registered but temporarily non-functional), and stdio crashes often indicate configuration problems retrying cannot fix; HMR was the recovery path. Operational feedback reversed the deferral — the [auto-reconnect Agent Note](2026-08-06-mcp-client-auto-reconnect.md) implements it with a bounded per-outage budget and an opt-out. ### Bridge Resources and Prompts @@ -179,7 +179,7 @@ Rejected — this was the original proposal, built on the premise that "most MCP ### Server-only namespace (`github__create_issue`, no `mcp__` marker) -Rejected for v1. It prevents cross-server collisions but does not separate MCP registrations from native harness tools, and it forfeits MCP-wide policy shapes (`mcp__*`). The marker costs 5 characters; the `mcp____` spelling matches Claude Code and Codex, maximizing model familiarity. If the ToolRuntime later grows source-aware namespaces, dropping the literal marker can be revisited as a naming-policy change. +Rejected. It prevents cross-server collisions but does not separate MCP registrations from native harness tools, and it forfeits MCP-wide policy shapes (`mcp__*`). The marker costs 5 characters; the `mcp____` spelling matches Claude Code and Codex, maximizing model familiarity. If the ToolRuntime later grows source-aware namespaces, dropping the literal marker can be revisited as a naming-policy change. ### Deriving the namespace from the server-announced `serverInfo.name` @@ -212,7 +212,7 @@ Coverage is named per tier; each behavior lives at the cheapest tier that can ex ## Consequences - A `cordis.yml` entry per MCP server is the entire integration cost: `serverName: filesystem` + a stdio command (or a Streamable HTTP URL) puts `mcp__filesystem__read_file` in the model's tool list, callable, with the raw `read_file` on the wire. -- Public names are part of session history and permission/configuration APIs; the naming algorithm is a v1 contract pinned by tests, and changing it after release is a breaking change. +- Public names are part of session history and permission/configuration APIs; tests pin the naming algorithm, and changing it after release is a breaking change. - The `mcp____` qualifier costs tokens on every name. Accepted: descriptions and JSON schemas dominate tool-definition tokens, and the qualifier buys stable identity, collision isolation, and MCP-wide policy shapes (`mcp__*`, `mcp__github__*`). - **MCP SDK stability**: the `@modelcontextprotocol/sdk` is still evolving; breaking changes require updating the bridge. The version is pinned, and the SDK is widely adopted (Claude Desktop, Cursor, VS Code) so breaking changes are unlikely to be silent. - **Tool schema quality**: MCP servers may expose poorly-described tools (vague descriptions, incomplete JSON schemas). The harness passes them through as-is — garbage-in-garbage-out; that is the server author's responsibility, not the bridge's. diff --git a/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.zh.md b/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.zh.md index 8cd59e5efe..0cf69a97bc 100644 --- a/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.zh.md +++ b/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.zh.md @@ -83,7 +83,7 @@ type Config = StdioConfig | StreamableHttpConfig ### 生命周期 -启动时从 `cordis.yml` 加载。HMR（热模块替换）（`@cordisjs/plugin-hmr`）提供热替换：编辑 yml 条目触发旧实例的 dispose（资源释放）（断开连接、注销工具），并创建新实例（连接、发现、注册）。目前不提供运行时动态 API。公开名称是 `(serverName, rawName)` 的纯函数，因此保持 `serverName` 不变的 HMR 替换会重建完全相同的模型可见名称——会话历史和权限规则保持有效——而添加或移除不相关的服务器永远不会重命名已有工具。 +启动时从 `cordis.yml` 加载。HMR（热模块替换）（`@cordisjs/plugin-hmr`）提供热替换：编辑 yml 条目触发旧实例的 dispose（资源释放）（断开连接、注销工具），并创建新实例（连接、发现、注册）。不提供运行时动态 API。公开名称是 `(serverName, rawName)` 的纯函数，因此保持 `serverName` 不变的 HMR 替换会重建完全相同的模型可见名称——会话历史和权限规则保持有效——而添加或移除不相关的服务器永远不会重命名已有工具。 ### 工具发现与注册 @@ -167,7 +167,7 @@ MCP 仅保证工具名在[单个服务器内](https://modelcontextprotocol.io/sp ### 指数退避自动重连 -v1 否决：引入了部分可用状态（工具已注册但暂时不可用），且 stdio 崩溃往往表明配置问题，重试无法修复；HMR 曾是恢复路径。运营反馈扭转了该延期决定——[自动重连 Agent Note](2026-08-06-mcp-client-auto-reconnect.zh.md) 以有界的单次故障预算和 opt-out 实现了自动重连。 +单次连接设计否决了该方案：它会引入部分可用状态（工具已注册但暂时不可用），且 stdio 崩溃往往表明配置问题，重试无法修复；HMR 曾是恢复路径。运营反馈扭转了该延期决定——[自动重连 Agent Note](2026-08-06-mcp-client-auto-reconnect.zh.md)以有界的单次故障预算和 opt-out 实现了自动重连。 ### 桥接 Resources 和 Prompts @@ -179,7 +179,7 @@ v1 否决：引入了部分可用状态（工具已注册但暂时不可用） ### 仅服务器命名空间（`github__create_issue`，无 `mcp__` 前缀） -v1 否决。它能防止跨服务器冲突，但无法将 MCP 注册与原生 harness 工具分离，也丧失了 MCP 全局策略匹配模式（`mcp__*`）。前缀仅多花 5 个字符；`mcp____` 拼写与 Claude Code 和 Codex 一致，最大化模型的熟悉度。如果 ToolRuntime 未来引入源感知命名空间，届时可作为命名策略变更重新考虑去掉字面前缀。 +不予采纳。它能防止跨服务器冲突，但无法将 MCP 注册与原生 harness 工具分离，也丧失了 MCP 全局策略匹配模式（`mcp__*`）。前缀仅多花 5 个字符；`mcp____` 拼写与 Claude Code 和 Codex 一致，最大化模型的熟悉度。如果 ToolRuntime 未来引入源感知命名空间，届时可作为命名策略变更重新考虑去掉字面前缀。 ### 从服务器公告的 `serverInfo.name` 派生命名空间 @@ -212,7 +212,7 @@ v1 否决。它能防止跨服务器冲突，但无法将 MCP 注册与原生 ha ## 后果 - 每个 MCP 服务器只需 `cordis.yml` 中的一条配置即完成集成：`serverName: filesystem` 加一条 stdio 命令（或一个 Streamable HTTP URL），就能将 `mcp__filesystem__read_file` 放入模型的工具列表，可调用，协议上使用原始的 `read_file`。 -- 公开名称是会话历史和权限/配置 API 的一部分；命名算法是由测试固定的 v1 约定，发布后变更即为破坏性变更。 +- 公开名称是会话历史和权限／配置 API 的一部分；测试固定了命名算法，发布后变更即为破坏性变更。 - `mcp____` 限定符在每个名称上消耗 token。已接受：描述和 JSON Schema 在工具定义 token 中占主导，而限定符换来了稳定标识、冲突隔离和 MCP 全局策略匹配模式（`mcp__*`、`mcp__github__*`）。 - **MCP SDK 稳定性**：`@modelcontextprotocol/sdk` 仍在演进中；破坏性变更需要更新桥接。版本已固定，且该 SDK 被广泛采用（Claude Desktop、Cursor、VS Code），因此破坏性变更不太可能悄然发生。 - **工具 schema 质量**：MCP 服务器可能暴露描述不佳的工具（模糊的描述、不完整的 JSON Schema）。harness 原样透传——垃圾进垃圾出；这是服务器作者的责任，不是桥接的。 diff --git a/.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.i18n.yaml b/.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.i18n.yaml index 05e9444ed9..cf3399f4b4 100644 --- a/.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md -2026-07-08-self-referential-cordis-toolset.md: d408bb774fa62dd6ff0deef7003f5b0851b80e82 -2026-07-08-self-referential-cordis-toolset.zh.md: 3c07a0af8c3f3a26795d14fc540db6e0f63775e4 +2026-07-08-self-referential-cordis-toolset.md: feb613d74c6be65f13aa9005b9f0d90c57beb14b +2026-07-08-self-referential-cordis-toolset.zh.md: 8840e548cac6dba2d0b5a9e724b747e46d187097 diff --git a/.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md b/.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md index d408bb774f..feb613d74c 100644 --- a/.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md +++ b/.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md @@ -75,7 +75,7 @@ The correctness investment therefore goes where it pays for every capability at **A hand-maintained service/event reference in the tool.** The first cut of the inspect tool carried a hand-written table of service method signatures. It was replaced by the generated `api-catalog.ts` because a hand table drifts from the JSDoc the moment a signature changes and nothing gates the drift, whereas the generated artifact is freshness-checked against the same AST the docs use. -**A new `cordis/mount` session event.** A durable event recording each mount's source and name has clear precedent (`hook/invoked`, `compaction/start`). It was declined for v1: mount and unmount are already visible as `tool/call` / `tool/result` pairs and the tool-set change is already logged as a full changed request header, so a dedicated event would only duplicate the record. It remains addable if an audit use case needs the mount source and name outside the tool call. +**A new `cordis/mount` session event.** A durable event recording each mount's source and name has clear precedent (`hook/invoked`, `compaction/start`). Rejected: mount and unmount are already visible as `tool/call` / `tool/result` pairs and the tool-set change is already logged as a full changed request header, so a dedicated event would only duplicate the record. It remains addable if an audit use case needs the mount source and name outside the tool call. **A hardened / capability-restricted sandbox.** Trapping Node built-ins and handing mount code a whitelist façade rather than the raw context might suggest an intent to sandbox for safety. It is explicitly not that: the traps and the façade narrow the *API* mount code sees — steering it onto cordis services and away from leak-prone Node built-ins and framework internals — for correctness and to close the unguarded-context escape, but the capabilities the façade exposes (`ctx.shell`, `ctx.fs`, `ctx.web`) reach the real runtime, so it is not a security boundary. A real one (separate process, permission prompts) was out of scope for a dev/opt-in toolset and would fight the entire point — handing the model the live runtime. diff --git a/.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.zh.md b/.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.zh.md index 3c07a0af8c..8840e548ca 100644 --- a/.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.zh.md +++ b/.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.zh.md @@ -75,7 +75,7 @@ vm 隔离了意外的全局污染，上下文门面隐藏了框架内部细节 **在工具中手工维护服务／事件参考。** inspect 工具的第一版携带了一份手写的服务方法签名表。它被生成的 `api-catalog.ts` 取代，因为手写表在签名变化的瞬间就会与 JSDoc 脱节且没有门禁约束这种漂移，而生成产物的新鲜度由文档使用的同一套 AST 检查。 -**新增 `cordis/mount` 会话事件。** 一个持久事件记录每次挂载的源码和名称，有明确先例（`hook/invoked`、`compaction/start`）。v1 中予以否决：挂载和卸载已经作为 `tool/call`／`tool/result` 对可见，工具集变化已经作为完整的变更 request header 被记录，因此专用事件只会重复记录。如果审计用例需要在工具调用之外取得挂载的源码和名称，日后仍可添加。 +**新增 `cordis/mount` 会话事件。**一个持久事件记录每次挂载的源码和名称，有明确先例（`hook/invoked`、`compaction/start`）。不予采纳：挂载和卸载已经作为 `tool/call`／`tool/result` 对可见，工具集变化已经作为完整的变更 request header 被记录，因此专用事件只会重复记录。如果审计用例需要在工具调用之外取得挂载的源码和名称，日后仍可添加。 **加固的／能力受限的沙箱。** 对 Node 内置模块设陷阱并向挂载代码提供白名单门面而非原始上下文，可能暗示意图是为安全而沙箱化。这里明确不是：陷阱和门面收窄的是挂载代码所见的 *API*——将其引导至 cordis 服务、远离易泄漏的 Node 内置模块和框架内部——目的是正确性和封堵未受保护的上下文逃逸，但门面暴露的能力（`ctx.shell`、`ctx.fs`、`ctx.web`）触及真实运行时，因此它不是安全边界。真正的安全边界（独立进程、权限提示）超出了一个开发／显式启用工具集的范围，且会与其核心目的——将活跃运行时交给模型——相冲突。 diff --git a/.agents/notes/implemented/feature/2026-07-14-cross-family-fs-sandbox.i18n.yaml b/.agents/notes/implemented/feature/2026-07-14-cross-family-fs-sandbox.i18n.yaml index 5f6c5f7ae4..8a7560709a 100644 --- a/.agents/notes/implemented/feature/2026-07-14-cross-family-fs-sandbox.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-14-cross-family-fs-sandbox.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-14-cross-family-fs-sandbox.md -2026-07-14-cross-family-fs-sandbox.md: bd6284d47c0a8a5a4a58ec50f060eb12e2d9c75b -2026-07-14-cross-family-fs-sandbox.zh.md: a32f23175a67ca87b50124933a369e4086379054 +2026-07-14-cross-family-fs-sandbox.md: fca19cd30a958cb035c69d104dae249e0b70ef82 +2026-07-14-cross-family-fs-sandbox.zh.md: 42b082ff72649d1bea80839c89474f479cfe3af0 diff --git a/.agents/notes/implemented/feature/2026-07-14-cross-family-fs-sandbox.md b/.agents/notes/implemented/feature/2026-07-14-cross-family-fs-sandbox.md index bd6284d47c..fca19cd30a 100644 --- a/.agents/notes/implemented/feature/2026-07-14-cross-family-fs-sandbox.md +++ b/.agents/notes/implemented/feature/2026-07-14-cross-family-fs-sandbox.md @@ -69,7 +69,7 @@ The sandbox Agent Note's original cross-family sketch put fs enforcement on the - **Keep the override event in `dsh-shell` as `shell/sandbox-mode`** — rejected: the event is policy state consumed by two families; leaving it bash-named forces `dsh-fs-sandbox` to depend on bash vocabulary. Pre-release, the rename is a same-change move with snapshot re-records, no shims. - **Escalation choreography imported from the approval/agent packages into `dsh-sandbox`** — rejected: it would invert the layering (a base vocabulary package depending on UI/agent packages). The structural approver keeps the logic single-sourced in `dsh-sandbox` while the dependencies stay in the tool layer that already holds them. - **A consolidated mutation-options object on the fs seam** (the shape first sketched for the per-call carrier) — rejected on friction: it splits `signal` across an options bag for mutations while reads keep it positional. A trailing optional `SandboxExecutionPolicy` matches bash's carry-and-ignore pattern and keeps `signal` symmetric across the seam. -- **Extra writable-root grants on `SandboxPolicy` now** — deferred unchanged: `writableRoots()` derives from the mode meaning today; ad-hoc grants are an escalation-scope question the sandbox RFC left open. +- **Extra writable-root grants on `SandboxPolicy`** — deferred unchanged: `writableRoots()` derives from the defined mode meaning; ad-hoc grants are an escalation-scope question the sandbox RFC left open. ## Consequences diff --git a/.agents/notes/implemented/feature/2026-07-14-cross-family-fs-sandbox.zh.md b/.agents/notes/implemented/feature/2026-07-14-cross-family-fs-sandbox.zh.md index a32f23175a..42b082ff72 100644 --- a/.agents/notes/implemented/feature/2026-07-14-cross-family-fs-sandbox.zh.md +++ b/.agents/notes/implemented/feature/2026-07-14-cross-family-fs-sandbox.zh.md @@ -69,7 +69,7 @@ Status: implemented - **把覆盖事件留在 `dsh-shell` 里作 `shell/sandbox-mode`**——否决：该事件是被两个家族消费的策略状态；保留 bash 命名会迫使 `dsh-fs-sandbox` 依赖 bash 词汇。预发布阶段，该改名是同一变更内的迁移，附带快照重录，无任何 shim。 - **把升级编排从 approval/agent 包导入 `dsh-sandbox`**——否决：那会倒置分层（一个基础词汇包依赖 UI/agent 包）。结构式 approver 让逻辑单一来源于 `dsh-sandbox`，而依赖留在本就持有它们的工具层。 - **fs seam 上一个合并的 mutation-options 对象**（per-call 载体最初草拟的形状）——因摩擦被否决：它会把 `signal` 拆进变更专用的选项包，而读取仍保持位置参数。一个末尾可选的 `SandboxExecutionPolicy` 匹配 bash 的携带并忽略模式，并使 `signal` 在整个 seam 上保持对称。 -- **现在就在 `SandboxPolicy` 上加额外的可写根授权**——照旧延后：`writableRoots()` 如今由模式含义推导；临时授权是沙箱 RFC 留下的升级作用域问题。 +- **在 `SandboxPolicy` 上增加额外的可写根授权**——照旧延后：`writableRoots()` 由既定模式含义推导；临时授权是沙箱 RFC 留下的升级作用域问题。 ## 后果 diff --git a/.agents/notes/implemented/feature/2026-07-22-web-multimodal-image-input-and-durable-attachments.i18n.yaml b/.agents/notes/implemented/feature/2026-07-22-web-multimodal-image-input-and-durable-attachments.i18n.yaml index 55710b6e95..0702b19390 100644 --- a/.agents/notes/implemented/feature/2026-07-22-web-multimodal-image-input-and-durable-attachments.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-22-web-multimodal-image-input-and-durable-attachments.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-22-web-multimodal-image-input-and-durable-attachments.md -2026-07-22-web-multimodal-image-input-and-durable-attachments.md: 3f77ab8d55f8eca821cd12a4591c6239c2ea10f5 -2026-07-22-web-multimodal-image-input-and-durable-attachments.zh.md: c95c5abe664635f3cde3a1fc2d569c9474c69665 +2026-07-22-web-multimodal-image-input-and-durable-attachments.md: 30ac1dcff9e6400a3bcf58f7b8e5237e20bd5c04 +2026-07-22-web-multimodal-image-input-and-durable-attachments.zh.md: 359bb9048632222518d87aadd348bca217c8f7c4 diff --git a/.agents/notes/implemented/feature/2026-07-22-web-multimodal-image-input-and-durable-attachments.md b/.agents/notes/implemented/feature/2026-07-22-web-multimodal-image-input-and-durable-attachments.md index 3f77ab8d55..30ac1dcff9 100644 --- a/.agents/notes/implemented/feature/2026-07-22-web-multimodal-image-input-and-durable-attachments.md +++ b/.agents/notes/implemented/feature/2026-07-22-web-multimodal-image-input-and-durable-attachments.md @@ -69,7 +69,7 @@ interface ComposerAttachment { This split uses the session provide channel's input hook and actions as the single subscription path for live composer state while keeping non-serializable browser objects out of persisted JSON. Only the plain-text draft mirror uses `localStorage`; attachment identifiers, browser `File` objects, and object URLs remain scoped to the live session input shell. Unsent images therefore do not survive reload or session-scope disposal. A Workspace switch moves a mixed text-and-image draft only when the destination shell accepts the complete image batch; refusal leaves both parts with the source. A native client may stage input in an OS temporary directory, but it must treat that path exactly like the browser object URL: delete it when no longer needed and copy the bytes into the durable store before message acceptance. -The local attachment backend resolves an explicit `dshHome`, then `$DSH_HOME`, then `~/.dsh`. It stores content-addressed objects below `$DSH_HOME/attachments/v1/objects//` with owner-only directory and file permissions. On each process's first save for one home, it creates that home and synchronizes every ancestor entry to the filesystem root; existence is not treated as durability because another process may still be between `mkdir` and parent `fsync`. A temporary file is then written, synchronized, atomically published, and made durable with directory syncs on the publication path (POSIX; Windows relies on filesystem metadata journaling) before the service returns a reference. The content digest is encoded in the opaque `sha256:` identifier. Admission and reads fully decode supported rasters before accepting their format and dimensions, and every read also verifies the digest, byte length, and logged metadata. +The local attachment backend resolves an explicit `dshHome`, then `$DSH_HOME`, then `~/.dsh`. It stores content-addressed objects below `$DSH_HOME/attachments/v1/objects//` with owner-only directory and file permissions. On each process's first save for one home, it creates that home and synchronizes every ancestor entry to the filesystem root; existence is not treated as durability because another process may still be between `mkdir` and parent `fsync`. A temporary file is then written, synchronized, atomically published, and made durable with directory syncs on the publication path (POSIX; Windows relies on filesystem metadata journaling) before the service returns a reference. The content digest is encoded in the opaque `sha256:` identifier. Admission prepares a provider-independent master by applying orientation, removing metadata, converting to 8-bit sRGB/sRGBA, and preserving aspect ratio under independent dimension and byte limits. Reads verify the digest, byte length, and logged metadata. Route-specific deterministic request versions are cached separately; the full policy is recorded in [Unified image masters, request versions, and provider files](2026-08-20-unified-image-request-pipeline.md). The store performs no automatic deletion in version one. Sent user images and model-generated images remain reachable for history, resume, and fork. Reference-aware garbage collection needs a separate design because an age-only rule can delete data still referenced by a durable session. Deployment byte and pixel limits are admission policy on writes; reads verify the digest and recorded metadata without reapplying current admission limits, so lowering policy does not invalidate older history. @@ -114,7 +114,7 @@ type PromptInputPart = } ``` -Base64 crosses a wire boundary once and is discarded after persistence. Each front door validates canonical base64 and declared MIME shape, then calls `AttachmentStore.saveImages()` with the whole decoded batch. The service owns image count, aggregate bytes, individual bytes, fully decoded raster/MIME agreement, intrinsic dimensions, and decoded-pixel count; it validates every batch member before saving any member, so one malformed image cannot strand the batch's valid members as unreferenced objects. Storage commits then run in submission order to bound full-raster decoder memory. If a later storage I/O operation fails, the caller appends no model-visible event and receives no partial references, but an earlier immutable content-addressed object may remain unreferenced; version one leaves cleanup to future reference-aware garbage collection instead of adding destructive rollback to the deduplicated store. Only after every image succeeds does the front door call the agent with normalized text and durable image blocks in wire order. A failure exposes no attachment path or raw bytes. +Base64 crosses a wire boundary once and is discarded after persistence. Each front door validates canonical base64 and declared MIME fields, then calls `AttachmentStore.saveImages()` with the whole decoded batch. The service owns image count, aggregate bytes, individual bytes, fully decoded raster/MIME agreement, intrinsic dimensions, decoded-pixel count, and master preparation. It prepares and verifies every batch member once before publishing any member, so one malformed image cannot create partial references and large images are not decoded and encoded again at commit. Storage commits then run in submission order. If a later storage I/O operation fails, the caller appends no model-visible event and receives no partial references, but an earlier immutable content-addressed object may remain unreferenced under the existing storage rule. Only after every image succeeds does the front door call the agent with normalized text and durable image blocks in wire order. A failure exposes no attachment path or raw bytes. `session.attachment` is a read-only, session-scoped endpoint. The host serves bytes only when a durable event in that session references the requested attachment identifier. The client deduplicates loads by session and attachment identifier while that session is rendered, revokes resolved URLs on rendered-session disposal, and rejects invalidated late loads before allocating an object URL so an unmounted session or disposed service cannot repopulate the cache. @@ -122,15 +122,15 @@ Base64 crosses a wire boundary once and is discarded after persistence. Each fro Model catalog entries gain optional merge-extensible input modality declarations. A missing declaration means unknown; a present list without `image` is an explicit negative capability. -The host is the authoritative preflight boundary. It resolves the session's latest routed provider/model, falling back through agent options to host defaults; if that model explicitly excludes image input, it rejects the prompt before writing any attachment or event, and the client restores the draft. Image-bearing prompt admission and model selection share one per-agent serial boundary, and a dequeued prompt remains pending until its durable message event publishes ([ordering decision](../bug-fix/2026-07-29-atomic-web-image-admission.md)); a steering carrier gates from its enqueue until its `steering/message` event publishes, closing the outbox hop that never enters the queued mirror. Selection rejects a text-only target while an image is pending publication or remains in the session's current derived history. Compaction can remove old images and make a later text-only selection valid; idle without publication releases a claimed queued carrier, while steering retained in the outbox stays gated until publication or discard. `session.updateQueue` edits accept text content only, so a queue edit cannot inject an image past this admission boundary. Unknown capability proceeds to the adapter guard so uncatalogued model identifiers remain usable. The browser rejects unsupported declared image media types before allocating preview URLs, but it does not snapshot deployment limits or model capability: a handshake snapshot cannot represent a session's current target after `session.selectModel`, and deployment policy may change independently. The host validates the complete batch against current byte, count, aggregate, media, dimension, pixel, and routed-model policy before writing any attachment or event; its rejection announces through the composer's transient toast. +The host is the authoritative preflight point. It resolves the session's latest routed provider and model, falling back through agent options to host defaults; if that model explicitly excludes image input, it rejects a new image prompt before writing an attachment or event, and the client restores the draft. Image-bearing prompt admission and model selection share one per-agent serial chain ([ordering decision](../bug-fix/2026-07-29-atomic-web-image-admission.md)), including steering that does not enter the queued UI mirror. This gives a prompt and concurrent selection a deterministic order. Selection itself may target a text-only model after images enter durable history; the shared LLM runtime replaces retained image blocks with deterministic text placeholders for that request. `session.updateQueue` edits accept text content only, so a queue edit cannot inject an image past admission. Unknown capability proceeds to the adapter guard so uncatalogued model identifiers remain usable. The browser rejects unsupported declared image media types before allocating preview URLs, but it does not snapshot deployment limits or model capability. The host validates the complete batch against current byte, count, aggregate, media, dimension, pixel, and routed-model policy before writing an attachment or event; its rejection appears through the composer's transient toast. -Pi-AI and the direct DeepSeek adapter resolve `ctx.attachments` at request time, recursively convert each durable image reference including references nested inside tool results, and emit native image content only for models that declare image input. The direct route advertises `deepseek-v4-flash-vision-exp` as image-capable and accepts configured image-capable catalog entries; its Flash, Pro, custom models without an image declaration, and unlisted pass-through ids remain text-only. Request-time service resolution keeps Cordis load order from freezing optional attachment availability. No adapter may flatten or skip a retained image; unsupported roles and models fail with typed `UNSUPPORTED_CONTENT`. +Pi-AI and the direct DeepSeek adapter resolve `ctx.attachments` at request time, recursively convert each retained image reference including references nested inside tool results, and emit native image content only for models that declare image input. Both adapters request the same deterministic route-specific version from the durable normalized attachment. Pi-AI carries it inline under a base64-aware request budget. The built-in DeepSeek route advertises `deepseek-v4-flash-vision-exp`, uploads every retained version through Files API, and sends `file_id` blocks with indexed reuse, expiry, bounded stale-id retry, quota cleanup, and explicit deletion. DeepSeek text models, custom models without an image declaration, and unlisted pass-through ids remain text-only. Request-time service resolution keeps Cordis load order from freezing optional attachment availability. No adapter may flatten or silently skip a retained image; unsupported roles and models fail with typed `UNSUPPORTED_CONTENT`. Core supports structured assistant image blocks, but no current production provider route is certified for image output. Any future output-capable adapter must retrieve provider bytes under bounded size and time policy, validate them through the same attachment service, persist them, and only then publish the atomic `ImageBlock`. A URL in assistant Markdown remains text and is never downloaded automatically. Provider-neutral token estimation does not guess visual pricing from image dimensions; provider-reported usage remains authoritative. ACP advertises image prompts only when its configured exact route and attachment deployment can accept them, persists inline input before publishing the user event, and re-reads committed assistant image references for native ACP image updates. MCP keeps canonical raw blocks for programmatic callers while projecting admitted images to durable core blocks; Code Mode carries any settled image-bearing sub-result through the outer result as logged source-attributed context. -Compaction replays the selected conversation prefix, including image references, into the configured summarization route. A visual-capable route resolves those references through its adapter; a text-only route fails explicitly instead of silently dropping the visual context. The synthesized checkpoint remains text-only, and `compaction-basic` rejects image summary output with `UNSUPPORTED_CONTENT`. +Compaction replays the selected conversation prefix, including image references, into the configured summarization route. A visual-capable route uses the same deterministic request versions as ordinary turns. A text-only route receives the same deterministic attachment placeholders as any other LLM request. The synthesized checkpoint remains text-only, and `compaction-basic` rejects image summary output with `UNSUPPORTED_CONTENT`. ### History rendering and original preview @@ -140,7 +140,7 @@ Composer thumbnails and each `MessageImage` own ephemeral original-preview state ### Limits and trust boundaries -Version one accepts PNG, JPEG, WebP, and GIF only. SVG and remote URLs are excluded. Default limits are 3.5 MiB per image, 20 images and 100 MiB aggregate image bytes per message, 40 million intrinsic pixels per image, and 2000 pixels on either side. These deployment-varying limits are validated backend configuration and enforced by the host before persistence. The client connection carrier has an independent configurable `maxRequestBodyBytes` cap (160 MiB by default) for every API request and fails load if it cannot hold the attachment service's aggregate image limit after base64 and envelope expansion; lowering image policy therefore never silently lowers the carrier limit for valid text or other RPCs. A body without a declared length is rejected the moment it crosses the cap rather than drained to its end. +Version one accepts PNG, JPEG, WebP, and GIF only. SVG and remote URLs are excluded. Source intake defaults are 32 MiB per image, 20 images and 100 MiB aggregate image bytes per message, 100 million decoded pixels per image, and 16384px on either side. The provider-independent master defaults to a 2048px long edge and 4 MiB safety cap. Provider request pixel and encoded-byte limits are separate route policies. These deployment-varying limits are validated backend configuration and enforced before persistence or request transmission. The client connection carrier has an independent configurable `maxRequestBodyBytes` cap, 160 MiB by default, and fails load if it cannot hold the aggregate source limit after base64 and envelope expansion. A body without a declared length is rejected when it crosses the cap rather than drained to its end. Malformed base64, unsupported or mismatched media, truncated image payloads, excess bytes, excess image count, excess pixels, excess per-side dimensions, missing objects, and integrity mismatches return stable structured failures. Original filenames are reduced to a display basename, control characters are removed, and no local path is logged or returned to the browser. @@ -148,11 +148,11 @@ Malformed base64, unsupported or mismatched media, truncated image payloads, exc | Surface | Responsibility | | --- | --- | -| `packages/attachment/attachment` | Opaque attachment identifier, image reference, limits, failures, and single/batch admission through `ctx.attachments`. | -| `packages/attachment/attachment-local` | Private content-addressed storage, complete raster decoding, integrity verification, and configuration. | -| `packages/llm/llm` | Role-neutral `ImageBlock` and input-modality metadata. | -| `packages/llm/llm-pi-ai` | Resolve durable supported image input into native provider content. | -| `packages/llm/llm-deepseek` | Resolve declared official vision input and reject images for text-only models. | +| `packages/attachment/attachment` | Opaque attachment and request-version identifiers, image references, policies, failures, batch admission, derived reads, and crops through `ctx.attachments`. | +| `packages/attachment/attachment-local` | Private content-addressed masters, deterministic request cache, complete raster decoding, integrity verification, and configuration. | +| `packages/llm/llm` | Role-neutral `ImageBlock`, input-modality metadata, exact adapter generations, and text-only request projection. | +| `packages/llm/llm-pi-ai` | Resolve durable images to deterministic inline request versions. | +| `packages/llm/llm-deepseek` | Resolve official vision input to deterministic request versions and Files API ids. | | `packages/compaction/compaction-basic` | Preserve images in summary input and reject non-text checkpoint output explicitly. | | `packages/host/apiproxy` and `packages/bundle/base` | Narrow upload wire, shared batch admission, limits and routed-model preflight, persist-before-event ordering, session-authorized reads, and default profile composition. | | `packages/client/connection` and `packages/client/runtime` | Bounded request buffering, wire types, fixture images, prompt uploads, attachment reads, and durable-reference folding. | @@ -165,7 +165,7 @@ The attachment packages form the interface/implementation side of one capability ### Implementation -The implemented slice includes the attachment seam and shared batch admission, role-neutral image block, Pi-AI and direct DeepSeek input conversion, durable Web/ACP/MCP ordering, Web upload/read protocol, conditional ACP image wire support, lossless MCP canonical results with durable image projection, generic Code Mode rich-result forwarding, current image-limit enforcement, bounded Web request bodies, in-memory draft images, paste/drop rail, user and assistant history rendering, single-click preview, compaction handling, and keyless assembled Web and ACP coverage. +The implemented capability includes shared prepare-once batch admission, provider-independent masters, deterministic request versions, DeepSeek Files reuse, stable crop handles, role-neutral image blocks, Pi-AI and DeepSeek input conversion, durable Web/ACP/MCP ordering, Web upload/read protocol, conditional ACP image support, lossless MCP results with durable image projection, Code Mode rich-result forwarding, bounded Web requests, draft and historical image UI, compaction handling, and keyless assembled coverage. No compatibility shim is required for the pre-release prompt wire; all call sites and fixtures change with the introducing slice. @@ -210,11 +210,11 @@ Rejected because tool renderers are pure, synchronous, and replayable. MCP prepa ## Testing - Storage tests cover content-addressed deduplication, private permissions, admission failures, corruption/missing-object failures, and reading history after deployment limits are lowered. -- Host and protocol tests cover persist-before-event ordering, absence of base64 in logs, session-scoped authorization, capability rejection, upload limits, bounded HTTP request bodies, image-admission/model-selection races (queued and steering placements), pending publication, idle release without publication, text-only queue edits, and selection against current derived history after compaction. +- Host and protocol tests cover persist-before-event ordering, absence of base64 in logs, session-scoped authorization, capability rejection, upload limits, bounded HTTP request bodies, image-admission/model-selection ordering, text-only queue edits, and text-only request projection. - Client unit tests cover paste and drop, mixed clipboard text, image-only send, draft restoration, ordering, draft/session-scope/application object-URL cleanup, and a deferred historical read that completes after disposal; the keyless assembled built-client lane (`apps/web/tests/image-display.snapshot.ts`, `DSH_EXAMPLE_MODE=lib pnpm run test:snapshot`) covers the historical user and assistant galleries over the authorized attachment route, the original-size lightbox, and the composer paste rail. -- Adapter and compaction tests cover native Pi-AI image conversion, late attachment-service composition, text-only rejection, recursively nested tool-result images, preserved summary input, and explicit image-output rejection. +- Adapter and compaction tests cover deterministic Pi-AI request versions, DeepSeek Files upload and reuse, stale-id recovery, text-only projection, recursively nested tool-result images, shared summary request versions, and explicit image-output rejection. - Attachment, MCP, ACP, and Code Mode tests cover all-member validation before writes, mixed text/image ordering, no inline base64 in durable events, exact route-capability gates, explicit unsupported-content diagnostics, post-execute replacement/block precedence, cancellation during admission, verified assistant-image delivery, and generic nested-image forwarding. A keyless assembled ACP snapshot sends a real inline PNG and pins only its durable reference in the session log. -- A credentialed real-API test sends a PNG through the Anthropic `claude-opus-4-8` route and requires the model to identify its QR code. +- Credentialed real-API tests cover the configured Anthropic route and the built-in `deepseek-official` Files path. The DeepSeek test does not use a custom provider entry. - The current production adapter set has no certified image-output route; output-provider certification remains outside version one. ## Consequences diff --git a/.agents/notes/implemented/feature/2026-07-22-web-multimodal-image-input-and-durable-attachments.zh.md b/.agents/notes/implemented/feature/2026-07-22-web-multimodal-image-input-and-durable-attachments.zh.md index c95c5abe66..359bb90486 100644 --- a/.agents/notes/implemented/feature/2026-07-22-web-multimodal-image-input-and-durable-attachments.zh.md +++ b/.agents/notes/implemented/feature/2026-07-22-web-multimodal-image-input-and-durable-attachments.zh.md @@ -69,7 +69,7 @@ interface ComposerAttachment { 这一拆分把会话 provide 通道的输入 hook 与 actions 用作实时输入区状态的唯一订阅路径，同时避免把不可序列化的浏览器对象写进持久 JSON。只有纯文本草稿镜像使用 `localStorage`；附件标识符、浏览器 `File` 对象和对象 URL 都限定在实时会话输入外壳的 scope 内。未发送图片因此无法跨重载或会话 scope 释放保留。切换 Workspace 时，只有目标外壳接受完整图片批次，图文混合草稿才会移动；拒绝时，文本和图片都留在来源外壳。原生客户端可以在操作系统临时目录中暂存输入，但必须像对待浏览器对象 URL 一样对待该路径：不再需要时删除，并在消息被接受前把字节复制进持久存储。 -本地附件后端依次解析显式 `dshHome`、`$DSH_HOME` 和 `~/.dsh`。它把内容寻址对象存储在 `$DSH_HOME/attachments/v1/objects//` 下，并为目录和文件设置仅所有者可访问的权限。每个进程首次为某个 home 保存对象时，都会创建该 home，并逐级同步每个祖先目录项直至文件系统根目录；不能把存在视为持久性，因为另一个进程可能仍处于 `mkdir` 与父目录 `fsync` 之间。随后，服务写入并同步临时文件，再以原子方式发布，并对发布路径执行目录同步使其持久（POSIX；Windows 依赖文件系统元数据日志），之后才返回引用。内容摘要编码在不透明的 `sha256:` 标识符中。写入准入与读取都会完整解码受支持的光栅图片，之后才接受其格式和尺寸；每次读取还会校验摘要、字节长度和已记录的元数据。 +本地附件后端依次解析显式 `dshHome`、`$DSH_HOME` 和 `~/.dsh`。它把内容寻址对象存储在 `$DSH_HOME/attachments/v1/objects//` 下，并为目录和文件设置仅所有者可访问的权限。每个进程首次为某个 home 保存对象时，都会创建该 home，并逐级同步每个祖先目录项直至文件系统根目录；不能把存在视为持久性，因为另一个进程可能仍处于 `mkdir` 与父目录 `fsync` 之间。随后，服务写入并同步临时文件，再以原子方式发布，并对发布路径执行目录同步使其持久（POSIX；Windows 依赖文件系统元数据日志），之后才返回引用。内容摘要编码在不透明的 `sha256:` 标识符中。准入会应用方向、删除元数据、转换为 8-bit sRGB/sRGBA，并在独立尺寸和字节上限内保持宽高比，生成与提供方无关的主版本。读取会校验摘要、字节长度和已记录元数据。路由专用的确定性请求版本单独缓存，完整策略见[统一图片主版本、请求版本和提供方文件](2026-08-20-unified-image-request-pipeline.zh.md)。 第一版不对存储执行自动删除。已发送的用户图片和模型生成图片会一直保留，以供历史记录、恢复和 fork 使用。按引用感知的垃圾回收需要单独设计，因为仅按时间清理可能删除仍被持久会话引用的数据。部署的字节和像素限制是写入时的准入策略；读取时会校验摘要和已记录的元数据，但不重新应用当前准入限制，因此收紧策略不会导致旧历史记录失效。 @@ -114,7 +114,7 @@ type PromptInputPart = } ``` -Base64 只跨越一次协议边界，并在持久化后丢弃。每个入口都会校验规范 base64 与声明的 MIME 形状，再用完整解码批次调用 `AttachmentStore.saveImages()`。服务负责图片数量、总字节数、单张图片字节数、声明 MIME 与完整解码后的光栅图片是否一致、固有尺寸和解码像素数；它会在保存任何成员之前校验每个批次成员，因此一张畸形图片不会把批次中的有效成员留成无引用对象。随后按提交顺序执行存储提交，以限制完整光栅解码器的内存占用。如果后续存储 I/O 操作失败，调用方不会追加模型可见事件，也不会收到部分引用，但先前的不可变内容寻址对象可能保持无引用状态；第一版将清理留给未来按引用感知的垃圾回收，而不向去重存储添加破坏性回滚。只有每张图片都成功后，入口才会用规范化文本和按协议顺序排列的持久图片块调用 agent。失败时不公开任何附件路径或原始字节。 +Base64 只跨越一次协议边界，并在持久化后丢弃。每个入口都会校验规范 base64 与声明的 MIME 字段，再用完整解码批次调用 `AttachmentStore.saveImages()`。服务负责图片数量、总字节数、单张图片字节数、声明 MIME 与完整解码后的光栅图片是否一致、固有尺寸、解码像素数和主版本准备。它会在发布任何成员之前只准备并验证每个批次成员一次，因此一张畸形图片不会产生部分引用，大图也不会在提交时重复解码和编码。随后按顺序提交存储。如果后续存储 I/O 操作失败，调用方不会追加模型可见事件，也不会收到部分引用，但先前的不可变内容寻址对象可能按现有存储规则保持无引用状态。只有每张图片都成功后，入口才会用规范化文本和按协议顺序排列的持久图片块调用 agent。失败时不公开任何附件路径或原始字节。 `session.attachment` 是只读且限定于会话作用域的端点。只有该会话中的持久事件引用了所请求的附件标识符，宿主才提供字节。会话处于渲染状态时，客户端会按会话和附件标识符对加载操作去重；已渲染会话释放时会撤销已解析的 URL，并在分配对象 URL 前拒绝已失效的延迟加载，以免已卸载的会话或已释放的服务重新写入缓存。 @@ -122,15 +122,15 @@ Base64 只跨越一次协议边界，并在持久化后丢弃。每个入口都 模型目录项增加可选且可合并扩展的输入模态声明。缺少声明表示未知；声明存在但不含 `image`，则明确表示不支持图片。 -宿主是权威的前置检查边界。它会解析会话最新路由到的提供方和模型，并在缺失时依次回退到 agent 选项和宿主默认值；如果该模型明确排除图片输入，宿主会在写入任何附件或事件前拒绝提示词，客户端则恢复草稿。包含图片的提示词准入与模型选择共用一个逐 agent 的串行边界，而且已经出队的提示词在其持久消息事件发布前仍保持待发布状态（[顺序决策](../bug-fix/2026-07-29-atomic-web-image-admission.zh.md)）；steering 载体则从入队起就参与门槛，直到其 `steering/message` 事件发布为止，堵住了从不进入排队镜像的 outbox 窗口。当图片正等待发布或仍存在于会话当前的派生历史中时，模型选择会拒绝纯文本目标。压缩（compaction）可以移除旧图片，使之后选择纯文本目标变得有效；未发布任何事件即转入空闲时，已认领的 queued 载体会被释放，而保留在 outbox 中的 steering 在发布或丢弃前始终受门槛约束。`session.updateQueue` 的编辑只接受文本内容，因此队列编辑无法绕过该准入边界注入图片。能力未知时继续进入适配器强制检查，使未收录的模型标识符仍然可用。浏览器会在分配预览 URL 前拒绝声明不支持的图片媒体类型，但不会为部署限制或模型能力保留快照：握手快照无法表达 `session.selectModel` 之后会话的当前目标，部署策略也可能独立变化。宿主会根据当前的单张字节数、图片数量、总字节数、媒体类型、尺寸、像素数和路由模型策略校验整个批次，再写入任何附件或事件；其拒绝通过 composer 的短时 toast 播报。 +宿主是权威的前置检查点。它会解析会话最新路由到的提供方和模型，并在缺失时依次回退到 agent 选项和宿主默认值；如果模型明确排除图片输入，宿主会在写入附件或事件前拒绝新的图片提示词，客户端则恢复草稿。包含图片的提示词准入与模型选择共用一条逐 agent 串行链（[顺序决策](../bug-fix/2026-07-29-atomic-web-image-admission.zh.md)），也包括不进入排队 UI 镜像的 steering。这会为提示词和并发选择提供确定顺序。图片进入持久历史后仍可选择纯文本模型；共享 LLM 运行时会在该请求中把保留的图片块替换为确定的文本占位符。`session.updateQueue` 只接受文本内容，因此队列编辑无法绕过准入注入图片。能力未知时继续进入适配器强制检查，使未收录的模型标识符仍然可用。浏览器会在分配预览 URL 前拒绝声明不支持的图片媒体类型，但不会为部署限制或模型能力保留快照。宿主会根据当前的单张字节数、图片数量、总字节数、媒体类型、尺寸、像素数和路由模型策略校验整个批次，再写入附件或事件；拒绝会通过 composer 的短时 toast 显示。 -Pi-AI 与直接 DeepSeek 适配器都会在请求时解析 `ctx.attachments`，递归转换每个持久图片引用，包括嵌套在工具结果中的引用，并且仅为声明支持图片输入的模型生成提供方原生图片内容。直接路由会将 `deepseek-v4-flash-vision-exp` 公布为支持图片，并接受已配置且支持图片的 catalog 配置项；其 Flash、Pro、未声明图片能力的自定义模型和未列出原样传递 id 仍仅支持文本。在请求时解析服务，可避免 Cordis 加载顺序将可选附件服务的可用性固化。任何适配器都不得将保留的图片展平或跳过；不支持的角色与模型会以类型化的 `UNSUPPORTED_CONTENT` 失败。 +Pi-AI 与直接 DeepSeek 适配器都会在请求时解析 `ctx.attachments`，递归转换每个保留的图片引用，包括嵌套在工具结果中的引用，并且仅为声明支持图片输入的模型生成提供方原生图片内容。两个适配器都从持久主版本请求同一个确定性路由版本。Pi-AI 在考虑 base64 扩张的请求预算内内联携带它。内置 DeepSeek 路由公布 `deepseek-v4-flash-vision-exp`，把每个保留的版本上传到 Files API，并通过索引复用、过期处理、有界陈旧 ID 重试、配额清理和显式删除发送 `file_id` 块。DeepSeek 纯文本模型、未声明图片能力的自定义模型和未列出的透传 ID 保持纯文本。在请求时解析服务，可避免 Cordis 加载顺序将可选附件服务的可用性固化。适配器不得展平或静默跳过保留图片；不支持的角色与模型会以类型化的 `UNSUPPORTED_CONTENT` 失败。 核心层支持结构化助手图片块，但当前没有任何生产提供方路径通过图片输出认证。未来任何支持输出的适配器都必须在有界的大小和时间策略下获取提供方字节，通过同一个附件服务校验并持久化字节，之后才能以原子方式发布 `ImageBlock`。助手 Markdown 中的 URL 仍是文本，绝不自动下载。 提供方无关的 token 估算不会根据图片尺寸猜测视觉定价；提供方返回的用量仍是权威值。只有配置的确切路由与附件部署可以接受图片时，ACP（Agent Client Protocol）才公布图片提示词能力；它会在发布用户事件前持久化内联输入，并重新读取已提交的助手图片引用来发送原生 ACP 图片更新。MCP 为程序化调用方保留规范原始块，同时把已准入图片投影为持久核心块；Code Mode 会把任何已经结算且含图片的子结果经外层结果转运为带来源归属且写入日志的上下文。 -压缩会把选定的会话前缀（包含图片引用）回放到已配置的摘要生成路径中。支持视觉的路径会通过适配器解析这些引用；仅文本路径会明确失败，而不是静默丢弃视觉上下文。合成的检查点仍仅包含文本，`compaction-basic` 会以 `UNSUPPORTED_CONTENT` 拒绝包含图片的摘要输出。 +压缩会把选定的会话前缀和其中的图片引用回放到已配置的摘要生成路径。支持视觉的路径使用与普通轮次相同的确定性请求版本。纯文本路径接收与其他 LLM 请求相同的确定性附件占位符。合成的检查点仍仅包含文本，`compaction-basic` 会以 `UNSUPPORTED_CONTENT` 拒绝包含图片的摘要输出。 ### 历史渲染与原图预览 @@ -140,7 +140,7 @@ Pi-AI 与直接 DeepSeek 适配器都会在请求时解析 `ctx.attachments`， ### 限制与信任边界 -第一版仅接受 PNG、JPEG、WebP 和 GIF。不接受 SVG 和远程 URL。默认限制为每张图片 3.5 MiB、每条消息 20 张图片和 100 MiB 图片总字节数、每张图片 4,000 万个固有像素，以及任一边 2,000 像素。这些随部署变化的限制属于经过校验的后端配置，并由宿主在持久化前强制执行。客户端连接载体为每个 API 请求设置独立且可配置的 `maxRequestBodyBytes` 上限（默认 160 MiB）；如果该上限无法容纳附件服务的图片总量限制经 base64 和请求封装膨胀后的大小，加载就会失败。因此，降低图片策略绝不会静默降低有效文本或其他 RPC 的载体上限。未声明长度的请求体在越过上限的瞬间即被拒绝，而不是先读完再拒。 +第一版仅接受 PNG、JPEG、WebP 和 GIF。不接受 SVG 和远程 URL。源文件输入默认限制为每张图片 32 MiB、每条消息 20 张图片和 100 MiB 图片总字节数、每张图片一亿解码像素，以及任一边 16384px。与提供方无关的主版本默认长边 2048px，独立安全上限 4 MiB。提供方请求的像素和编码字节上限是单独的路由策略。这些随部署变化的限制属于经过校验的后端配置，并在持久化或请求发送前强制执行。客户端连接载体为每个 API 请求设置独立且可配置的 `maxRequestBodyBytes` 上限，默认 160 MiB；如果该上限无法容纳源文件总量限制经 base64 和请求封装膨胀后的大小，加载就会失败。未声明长度的请求体在越过上限时即被拒绝，而不是先读完再拒。 格式错误的 base64、不支持或不匹配的媒体、截断的图片数据、超出字节限制、超出图片数量、超出像素限制、超出单边尺寸限制、对象缺失和完整性不匹配都会返回稳定的结构化错误。原始文件名只保留用于显示的末段，控制字符会被移除，并且任何本地路径都不会写入日志或返回浏览器。 @@ -148,11 +148,11 @@ Pi-AI 与直接 DeepSeek 适配器都会在请求时解析 `ctx.attachments`， | 接口 | 职责 | | --- | --- | -| `packages/attachment/attachment` | 不透明附件标识符、图片引用、限制、错误，以及通过 `ctx.attachments` 提供的单张／批量准入。 | -| `packages/attachment/attachment-local` | 私有内容寻址存储、完整光栅解码、完整性校验和配置。 | -| `packages/llm/llm` | 角色无关的 `ImageBlock` 和输入模态元数据。 | -| `packages/llm/llm-pi-ai` | 将持久且受支持的图片输入解析为提供方原生内容。 | -| `packages/llm/llm-deepseek` | 解析已声明的官方视觉输入，并拒绝纯文本模型的图片。 | +| `packages/attachment/attachment` | 不透明附件和请求版本标识符、图片引用、策略、错误，以及通过 `ctx.attachments` 提供的批量准入、派生读取和裁剪。 | +| `packages/attachment/attachment-local` | 私有内容寻址主版本、确定性请求缓存、完整光栅解码、完整性校验和配置。 | +| `packages/llm/llm` | 角色无关的 `ImageBlock`、输入模态元数据、精确适配器代次和纯文本请求投影。 | +| `packages/llm/llm-pi-ai` | 把持久图片解析为确定性内联请求版本。 | +| `packages/llm/llm-deepseek` | 把官方视觉输入解析为确定性请求版本和 Files API ID。 | | `packages/compaction/compaction-basic` | 在摘要输入中保留图片，并明确拒绝非文本检查点输出。 | | `packages/host/apiproxy` 和 `packages/bundle/base` | 范围狭窄的上传协议、共享批量准入、限制和路由模型前置检查、先持久化再追加事件的顺序、会话授权读取，以及默认 profile 组合。 | | `packages/client/connection` 和 `packages/client/runtime` | 有界请求缓冲、协议类型、fixture（测试前置数据）图片、提示词上传、附件读取和持久引用折叠。 | @@ -165,7 +165,7 @@ Pi-AI 与直接 DeepSeek 适配器都会在请求时解析 `ctx.attachments`， ### 实现 -已实现的范围包括附件服务边界与共享批量准入、角色无关的图片块、Pi-AI 与直接 DeepSeek 输入转换、Web／ACP／MCP 的持久化顺序、Web 上传与读取协议、条件式 ACP 图片协议支持、无损 MCP 规范结果与持久图片投影、通用 Code Mode 丰富结果转发、当前图片限制执行、大小受限的 Web 请求体、内存草稿图片、粘贴与拖放附件栏、用户与助手历史图片渲染、单击预览、压缩处理，以及组装后无需密钥的 Web 与 ACP 覆盖。 +已实现能力包括只准备一次的共享批量准入、与提供方无关的主版本、确定性请求版本、DeepSeek Files 复用、稳定裁剪句柄、角色无关图片块、Pi-AI 和 DeepSeek 输入转换、Web／ACP／MCP 持久化顺序、Web 上传与读取协议、条件式 ACP 图片支持、带持久图片投影的无损 MCP 结果、Code Mode 丰富结果转发、有界 Web 请求、草稿与历史图片 UI、压缩处理，以及组装后的无密钥覆盖。 预发布提示词协议不需要兼容包装层；引入相应切片时会同时修改所有调用点和 fixture。 @@ -210,11 +210,11 @@ UI 状态可能陈旧，也无法保护直接 SDK、ACP、回放或未收录模 ## 测试 - 存储测试覆盖内容寻址去重、私有权限、准入失败、对象损坏或缺失时的失败，以及收紧部署限制后读取历史数据。 -- 宿主与协议测试覆盖先持久化再追加事件的顺序、日志中不含 base64、会话作用域授权、能力拒绝、上传限制、大小受限的 HTTP 请求体、图片准入与模型选择的竞态（排队与 steering 两种放置）、待发布状态、未发布即空闲时的门槛释放、仅文本的队列编辑，以及压缩后依据当前派生历史进行的选择。 +- 宿主与协议测试覆盖先持久化再追加事件的顺序、日志中不含 base64、会话作用域授权、能力拒绝、上传限制、大小受限的 HTTP 请求体、图片准入与模型选择的排序、仅文本的队列编辑，以及纯文本请求投影。 - 客户端单元测试覆盖粘贴与拖放、混合剪贴板文本、仅图片发送、草稿恢复、顺序、草稿、会话作用域和应用层级的对象 URL 清理，以及一项在释放后才完成的延迟历史读取；keyless 的组装后构建产物通道（`apps/web/tests/image-display.snapshot.ts`，`DSH_EXAMPLE_MODE=lib pnpm run test:snapshot`）覆盖经授权附件路由渲染的历史用户与助手图片画廊、原图 lightbox，以及 composer 粘贴缩略图条。 -- 适配器与压缩测试覆盖 Pi-AI 原生图片转换、后置附件服务组合、仅文本拒绝、递归嵌套在工具结果中的图片、保留摘要输入，以及明确拒绝图片输出。 +- 适配器与压缩测试覆盖确定性 Pi-AI 请求版本、DeepSeek Files 上传与复用、陈旧 ID 恢复、纯文本投影、递归嵌套在工具结果中的图片、共享摘要请求版本，以及明确拒绝图片输出。 - 附件、MCP、ACP 与 Code Mode 测试覆盖写入前校验全部成员、图文混合顺序、持久事件不含内联 base64、确切路由能力门禁、明确的不支持内容诊断、post-execute 替换／阻止优先级、准入期间取消、经过校验的助手图片交付，以及通用嵌套图片转发。组装后的无密钥 ACP 快照发送真实内联 PNG，并在会话日志中只固定其持久引用。 -- 需要凭据的实际 API 测试会通过 Anthropic `claude-opus-4-8` 路径发送一张 PNG，并要求模型识别其中的二维码。 +- 需要凭据的实际 API 测试会覆盖配置的 Anthropic 路由和内置 `deepseek-official` Files 路径。DeepSeek 测试不使用自定义提供方条目。 - 当前生产适配器集合没有经过认证的图片输出路由；输出提供方认证仍不在第一版范围内。 ## 后果 diff --git a/.agents/notes/implemented/feature/2026-07-29-directory-picker-adaptive-default.i18n.yaml b/.agents/notes/implemented/feature/2026-07-29-directory-picker-adaptive-default.i18n.yaml index aec4a3554d..9fc614eed0 100644 --- a/.agents/notes/implemented/feature/2026-07-29-directory-picker-adaptive-default.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-29-directory-picker-adaptive-default.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-29-directory-picker-adaptive-default.md -2026-07-29-directory-picker-adaptive-default.md: 7ff6529bb8e445f63343b1019ac520f56b19d5e4 -2026-07-29-directory-picker-adaptive-default.zh.md: ba2bb4424416557b119accc7df14fab4c94ddebf +2026-07-29-directory-picker-adaptive-default.md: 92eb2b5ab4fb1312f03537d891b9f4afff6c7f22 +2026-07-29-directory-picker-adaptive-default.zh.md: a3d0c4b79950ef3452ac906b4a8917321cec6829 diff --git a/.agents/notes/implemented/feature/2026-07-29-directory-picker-adaptive-default.md b/.agents/notes/implemented/feature/2026-07-29-directory-picker-adaptive-default.md index 7ff6529bb8..92eb2b5ab4 100644 --- a/.agents/notes/implemented/feature/2026-07-29-directory-picker-adaptive-default.md +++ b/.agents/notes/implemented/feature/2026-07-29-directory-picker-adaptive-default.md @@ -19,7 +19,7 @@ Why entry-level mounting is the load-bearing mechanism: the client module table - **Boot-glue resolution in `AppCLIEntry`** (ship both rows with static `disabled`, patch `disabled` from a `--directory-picker=auto|native|browse` flag). Works — `PatchOptions` patches metadata, and the modules scan skips disabled rows — but leaves the decision app-private where every future composition re-implements it; the chooser plugin gives any `cordis.yml` the same one-row adaptivity. Reintroduce the flag only when a deployment needs to *force* a backend without editing its yml. - **One merged plugin branching per call** (client tries `pick`, falls back to the browse dialog on `directory-picker-unavailable`). Rejected: the client would need both flows in one bundle — the bundle-purity gate forbids cross-plugin value imports and jscpd forbids copying the dialog — and per-call probing pays a doomed RPC on every open of a browse host. - **Resurrecting the wire advertisement** so both client flows mount and branch on the host's kind. Rejected: reverses the seam note's deletion for no consumer the chooser doesn't already serve, and collides with the `single` directory-flow holes. -- **Per-connection adaptivity** (native for a loopback browser, browse for a remote one, same server). Deferred: needs a per-client capability, the advertisement above, and both flows mounted; no deployment serves both operator shapes at once today. +- **Per-connection adaptivity** (native for a loopback browser, browse for a remote one, same server). Deferred: needs a per-client capability, the advertisement above, and both flows mounted; no shipped deployment serves both operator shapes at once. ## Consequences diff --git a/.agents/notes/implemented/feature/2026-07-29-directory-picker-adaptive-default.zh.md b/.agents/notes/implemented/feature/2026-07-29-directory-picker-adaptive-default.zh.md index ba2bb44244..a3d0c4b799 100644 --- a/.agents/notes/implemented/feature/2026-07-29-directory-picker-adaptive-default.zh.md +++ b/.agents/notes/implemented/feature/2026-07-29-directory-picker-adaptive-default.zh.md @@ -19,7 +19,7 @@ Status: implemented - **在 `AppCLIEntry` 里做启动胶水判定**（随附两行并带静态 `disabled`，由 `--directory-picker=auto|native|browse` 标志修补 `disabled`）。可行——`PatchOptions` 能修补元数据，模块扫描也会跳过禁用行——但把决策留成应用私有，此后每个组合都要重新实现；选择器插件让任何 `cordis.yml` 都获得同样的一行自适应。只有当某个部署需要不改自己的 yml 就*强制*指定后端时，才重新引入该标志。 - **合并成一个按调用分支的插件**（client 先试 `pick`，收到 `directory-picker-unavailable` 再回退到浏览对话框）。否决：client 得把两套流程装进同一个 bundle——bundle 纯净门禁禁止跨插件的值导入，jscpd 禁止复制对话框——而且按调用探测让 browse 宿主每次打开都付出一次注定失败的 RPC。 - **复活 wire 广播**，让两套 client 流程都挂载并按宿主的 kind 分支。否决：推翻 seam Agent Note 的那次删除，却服务不了任何选择器尚未服务的消费方，还与 `single` 目录流洞相冲突。 -- **按连接自适应**（同一台服务器，回环浏览器用 native、远程浏览器用 browse）。延期：需要按客户端的能力对象、上述广播，以及同时挂载两套流程；今天没有部署同时服务两种操作者形态。 +- **按连接自适应**（同一台服务器，回环浏览器用 native、远程浏览器用 browse）。延期：需要按客户端的能力对象、上述广播，以及同时挂载两套流程；没有已交付部署同时服务两种操作者形态。 ## 后果 diff --git a/.agents/notes/implemented/feature/2026-07-30-versioned-gui-welcome-onboarding.i18n.yaml b/.agents/notes/implemented/feature/2026-07-30-versioned-gui-welcome-onboarding.i18n.yaml deleted file mode 100644 index 99bd30dd67..0000000000 --- a/.agents/notes/implemented/feature/2026-07-30-versioned-gui-welcome-onboarding.i18n.yaml +++ /dev/null @@ -1,6 +0,0 @@ -# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each -# side as of the last confirmed-consistent state. Both languages carry equal authority; -# after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-30-versioned-gui-welcome-onboarding.md -2026-07-30-versioned-gui-welcome-onboarding.md: 9c8684c0510c50c28e8ece53fd794844c771e496 -2026-07-30-versioned-gui-welcome-onboarding.zh.md: d4fe40a1af40008589722b83a5f0751e4f341dde diff --git a/.agents/notes/implemented/feature/2026-07-30-web-diff-card.i18n.yaml b/.agents/notes/implemented/feature/2026-07-30-web-diff-card.i18n.yaml index c78d61ea2a..ea039e9ba6 100644 --- a/.agents/notes/implemented/feature/2026-07-30-web-diff-card.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-30-web-diff-card.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-30-web-diff-card.md -2026-07-30-web-diff-card.md: 465a6fc9e2fbe61fd1a2e6f11590d01e2553d506 -2026-07-30-web-diff-card.zh.md: 44a719a8e3ab83700fb7e293867ed75256868d94 +2026-07-30-web-diff-card.md: 42a3cc527824d29fce98a04bd2e2037cff93109e +2026-07-30-web-diff-card.zh.md: 35d169b254f7242f1cf6b6301d0deb8728470cb8 diff --git a/.agents/notes/implemented/feature/2026-07-30-web-diff-card.md b/.agents/notes/implemented/feature/2026-07-30-web-diff-card.md index 465a6fc9e2..42a3cc5278 100644 --- a/.agents/notes/implemented/feature/2026-07-30-web-diff-card.md +++ b/.agents/notes/implemented/feature/2026-07-30-web-diff-card.md @@ -30,7 +30,7 @@ The chat row renders the diff resident under its path-link summary, capped at `C ## Alternatives considered -**A side-by-side (two-column) diff.** Rejected for now by the owner: it is denser but does not fit the narrow chat row, and the goal was parity with the TUI's single-column unified form. A two-column mode in the details panel is a later props change, not a redesign. +**A side-by-side (two-column) diff.** Rejected: it is denser but does not fit the narrow chat row, and the selected design matches the TUI's single-column unified form. A two-column details-panel mode remains separable from this card design. **Git-style line-number gutters.** The `FileDiff` contract carries only `{ path, oldText, newText }` — `structuredPatch`'s hunk start lines are dropped in `diff.ts`, so no line number reaches the client. Rendering a numbered gutter needs a backend contract change (carry `oldStart`/`newStart`) and a matching TUI upgrade to stay consistent; deferred so this change stays a pure Web consumer of the existing contract. @@ -40,7 +40,7 @@ The chat row renders the diff resident under its path-link summary, capped at `C `DiffBlock` reads only the diff view's fields, so it stays a pure function of what the render intent carries — replay-safe like the presenters that produce the view. A UI without the diff capability still gets the bridge's generic fallback; nothing about the tool's result shape changed. No new runtime dependency: unlike the terminal card's `anser`, a diff needs no parser. -The multi-file arm of `DiffBlock` (one card, several path headers) has no producer today: `write`/`edit` each mutate one file per call, so a real card shows one file with one or more hunks. The arm is built and tested for a future multi-file mutation tool, not for a current consumer. +The multi-file arm of `DiffBlock` (one card, several path headers) has no shipped producer: `write`/`edit` each mutate one file per call, so a real card shows one file with one or more hunks. The arm is built and tested for a future multi-file mutation tool, not for a current consumer. ## Testing diff --git a/.agents/notes/implemented/feature/2026-07-30-web-diff-card.zh.md b/.agents/notes/implemented/feature/2026-07-30-web-diff-card.zh.md index 44a719a8e3..35d169b254 100644 --- a/.agents/notes/implemented/feature/2026-07-30-web-diff-card.zh.md +++ b/.agents/notes/implemented/feature/2026-07-30-web-diff-card.zh.md @@ -30,7 +30,7 @@ chat 行把 diff 常驻渲染在路径链接摘要之下，上限 `CHAT_DIFF_MAX ## Alternatives considered -**并排（双栏）diff。** owner 目前拒绝：它更密但不适合狭窄的 chat 行，目标是与 TUI 单栏统一形式对齐。详情面板里的双栏模式是后续的 props 改动，不是重设计。 +**并排（双栏）diff。**不予采纳：它更密，但不适合狭窄的 chat 行，而所选设计与 TUI 的单栏统一形式一致。详情面板中的双栏模式可以与本卡片设计分开引入。 **git 式行号槽。** `FileDiff` 约定只携带 `{ path, oldText, newText }` —— `structuredPatch` 的 hunk 起始行在 `diff.ts` 里被丢弃，所以没有行号抵达客户端。渲染行号槽需要后端约定改动（携带 `oldStart`/`newStart`）并同步升级 TUI 以保持一致；推迟，使本变更保持为对既有约定的纯 Web 消费。 @@ -40,7 +40,7 @@ chat 行把 diff 常驻渲染在路径链接摘要之下，上限 `CHAT_DIFF_MAX `DiffBlock` 只读 diff view 的字段，因此它是渲染意图所携带内容的纯函数 —— 与产出该视图的 presenter 一样回放安全。没有 diff 能力的 UI 仍得到 bridge 的通用回退；工具的 result 形状没有任何改变。无新增运行时依赖：不同于 terminal 卡片的 `anser`，diff 不需要解析器。 -`DiffBlock` 的多文件支路（一张卡、多个路径头）今天没有生产者：`write`/`edit` 每次调用各改一个文件，所以真实卡片显示一个文件带一个或多个 hunk。该支路为将来的多文件改动工具而构建并测试，不是为当前消费者。 +`DiffBlock` 的多文件支路（一张卡、多个路径头）没有已交付生产者：`write`/`edit` 每次调用各改一个文件，所以真实卡片显示一个文件带一个或多个 hunk。该支路为将来的多文件改动工具而构建并测试，不是为当前消费者。 ## Testing diff --git a/.agents/notes/implemented/feature/2026-07-31-even-out-shipped-tool-rosters.i18n.yaml b/.agents/notes/implemented/feature/2026-07-31-even-out-shipped-tool-rosters.i18n.yaml index 6165c9d3d6..651c076892 100644 --- a/.agents/notes/implemented/feature/2026-07-31-even-out-shipped-tool-rosters.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-31-even-out-shipped-tool-rosters.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-31-even-out-shipped-tool-rosters.md -2026-07-31-even-out-shipped-tool-rosters.md: 429fbe9b80b965a1ce12f1b28ae0f3357ea07db8 -2026-07-31-even-out-shipped-tool-rosters.zh.md: 5893400d6d6d3ff30229ff57b9f1fcfae49acc84 +2026-07-31-even-out-shipped-tool-rosters.md: 97a9fdaedb97de77c195c319f14f972aac850726 +2026-07-31-even-out-shipped-tool-rosters.zh.md: 130573f0ddf0b94b4dcb017f58f1e0935e53e844 diff --git a/.agents/notes/implemented/feature/2026-07-31-even-out-shipped-tool-rosters.md b/.agents/notes/implemented/feature/2026-07-31-even-out-shipped-tool-rosters.md index 429fbe9b80..97a9fdaedb 100644 --- a/.agents/notes/implemented/feature/2026-07-31-even-out-shipped-tool-rosters.md +++ b/.agents/notes/implemented/feature/2026-07-31-even-out-shipped-tool-rosters.md @@ -34,7 +34,7 @@ Withholding it narrows the surface without removing the reach: `bash` is mounted `@deepseek-ai/dsh-mcp-client` becomes a runtime dependency of the CLI without a row in any shipped config. The plugin mounts exactly one server per instance and `command` is required, so a default would have to name a third-party server and spawn it as a child process on every launch — outside `ctx.shell`, and therefore outside the sandbox policy the Web surface composes. -The layer that would make MCP a default is the one this repository does not have yet: a bridge that reads a user's server list and mounts one client per entry, the same shape [`dsh-hooks-claude-code`](../../../../packages/hooks/hooks-claude-code/README.md) already has for a Claude Code `hooks.json`. Shipping the dependency means an installed `dsh` can mount servers from `$DSH_HOME/config.yaml` today; the CLI README carries the YAML. +The layer that would make MCP a default is the one this repository does not have yet: a bridge that reads a user's server list and mounts one client per entry, the same shape [`dsh-hooks-claude-code`](../../../../packages/hooks/hooks-claude-code/README.md) already has for a Claude Code `hooks.json`. Shipping the dependency means an installed `dsh` can mount servers from `$DSH_HOME/config.yaml`; the CLI README carries the YAML. ## Testing diff --git a/.agents/notes/implemented/feature/2026-07-31-even-out-shipped-tool-rosters.zh.md b/.agents/notes/implemented/feature/2026-07-31-even-out-shipped-tool-rosters.zh.md index 5893400d6d..130573f0dd 100644 --- a/.agents/notes/implemented/feature/2026-07-31-even-out-shipped-tool-rosters.zh.md +++ b/.agents/notes/implemented/feature/2026-07-31-even-out-shipped-tool-rosters.zh.md @@ -34,7 +34,7 @@ Status: implemented `@deepseek-ai/dsh-mcp-client` 成为本 CLI（命令行界面）的运行时依赖,但在任何交付配置里都没有对应的行。该插件每个实例只挂载一台服务器,且 `command` 是必填,因此一个默认值必须点名一台第三方服务器,并在每次启动时把它作为子进程 spawn——不经 `ctx.shell`,因而也在 Web surface 所组合的沙箱策略之外。 -真正能让 MCP 成为默认的那一层,恰恰是本仓库尚未拥有的:一个读取用户服务器清单、按条目逐台挂载客户端的桥接,形态与 [`dsh-hooks-claude-code`](../../../../packages/hooks/hooks-claude-code/README.zh.md) 读取 Claude Code 的 `hooks.json` 完全相同。交付这个依赖意味着已安装的 `dsh` 今天就能从 `$DSH_HOME/config.yaml` 挂载服务器;CLI README 里给了那段 YAML。 +真正能让 MCP 成为默认的那一层,恰恰是本仓库尚未拥有的:一个读取用户服务器清单、按条目逐台挂载客户端的桥接,形态与 [`dsh-hooks-claude-code`](../../../../packages/hooks/hooks-claude-code/README.zh.md) 读取 Claude Code 的 `hooks.json` 完全相同。交付这个依赖意味着已安装的 `dsh` 能从 `$DSH_HOME/config.yaml` 挂载服务器;CLI README 里给了那段 YAML。 ## 测试 diff --git a/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.i18n.yaml b/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.i18n.yaml index 85e6ab91f4..ee12783b03 100644 --- a/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.md -2026-08-02-pwsh-tool-bash-parity.md: 0ae12e54e574fb46035fb664f815b3edba706812 -2026-08-02-pwsh-tool-bash-parity.zh.md: f45812d735898be207115f863ab92ddbe760b358 +2026-08-02-pwsh-tool-bash-parity.md: 67107e90d5aa509f76468d5ddde9d36d4aabaa6c +2026-08-02-pwsh-tool-bash-parity.zh.md: 3857f4fffc7ba389e17c85903d2462032add8805 diff --git a/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.md b/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.md index 0ae12e54e5..67107e90d5 100644 --- a/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.md +++ b/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.md @@ -28,7 +28,7 @@ The first Windows-native foundation shipped `dsh-tool-pwsh` as a deliberately mi ## Consequences -- The bash and pwsh tools are now behaviorally interchangeable for foreground, background, and sandboxed shell work (the sandbox surface arrived with the Windows ACL sandbox decision), and the pwsh prompt/description sentences are each backed by the renderer — the reviewer's grep-against-code check passes. +- The bash and pwsh tools are behaviorally interchangeable for foreground, background, and sandboxed shell work (the sandbox surface is owned by the Windows ACL sandbox decision), and renderer coverage pins every pwsh prompt and description sentence. - Parity ran BOTH ways once: the pwsh tool's structured foreground abort (`HarnessError('tool call aborted', TOOL_ABORTED)` with name `AbortError`) was backported to the bash tool, replacing its uncoded `Error('command aborted')` — a model-visible/logged change pinned by exact-shape tests on both sides and by the cancel-tool-calls fixture. - `@deepseek-ai/dsh-shell-env` is a new shipped package; `dsh-tool-bash`'s `dshHome` config moved there, so compositions mounting the shell tools must also mount `shell-env` (the spine bundles do). - Windows-only semantics (CRLF normalization, forced-termination exit-1/signal-null, POSIX-only self-signal) remain pinned by tests as before. diff --git a/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.zh.md b/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.zh.md index f45812d735..3857f4fffc 100644 --- a/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.zh.md +++ b/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.zh.md @@ -28,7 +28,7 @@ Status: implemented ## 后果 -- bash 与 pwsh 工具在前台、后台与沙箱化 shell 工作上行为可互换（沙箱面随 Windows ACL 沙箱决策到来），pwsh 的提示词/描述句每句都有渲染器背书——reviewer 的「拿代码 grep 对证」检查通过。 +- bash 与 pwsh 工具在前台、后台与沙箱化 shell 工作上行为可互换（沙箱表层由 Windows ACL 沙箱决策负责），渲染器覆盖固定了每一句 pwsh 提示词与描述。 - 对齐也反向发生过一次：pwsh 工具的结构化前台中止（`HarnessError('tool call aborted', TOOL_ABORTED)`，name 为 `AbortError`）被回移到 bash 工具，取代其无码的 `Error('command aborted')`——这是模型可见/入日志的变更，由两侧的精确形状测试与 cancel-tool-calls fixture（测试前置数据）钉住。 - `@deepseek-ai/dsh-shell-env` 成为新的交付包；`dsh-tool-bash` 的 `dshHome` 配置迁往那里，因此挂载 shell 工具的组合也必须挂载 `shell-env`（主干组合包已如此）。 - Windows 专属语义（CRLF 归一化、强制终止 exit-1/signal-null、仅 POSIX 的自信号）一如既往由测试钉住。 diff --git a/.agents/notes/implemented/feature/2026-08-02-win32-in-process-folder-dialog.i18n.yaml b/.agents/notes/implemented/feature/2026-08-02-win32-in-process-folder-dialog.i18n.yaml index 638d2c8f69..94d100bf69 100644 --- a/.agents/notes/implemented/feature/2026-08-02-win32-in-process-folder-dialog.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-02-win32-in-process-folder-dialog.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-02-win32-in-process-folder-dialog.md -2026-08-02-win32-in-process-folder-dialog.md: ef9232051d0ff6e3e752f08a68e9f04ce3c32ad6 -2026-08-02-win32-in-process-folder-dialog.zh.md: d2bab277ca078b6943b720d7dcbfce4e8a548270 +2026-08-02-win32-in-process-folder-dialog.md: 52eab80499de9556cc0a395ac17f0f307e52131f +2026-08-02-win32-in-process-folder-dialog.zh.md: af45bc18d60a0165d6cc8d7a2b253289a91bdbac diff --git a/.agents/notes/implemented/feature/2026-08-02-win32-in-process-folder-dialog.md b/.agents/notes/implemented/feature/2026-08-02-win32-in-process-folder-dialog.md index ef9232051d..52eab80499 100644 --- a/.agents/notes/implemented/feature/2026-08-02-win32-in-process-folder-dialog.md +++ b/.agents/notes/implemented/feature/2026-08-02-win32-in-process-folder-dialog.md @@ -24,4 +24,4 @@ The Windows directory picker's primary tier was a spawned PowerShell script arou - Every Windows machine gets the modern dialog with the best DPI awareness it supports (per-monitor-v2 on 1703+), PowerShell installed or not. - Real dialog rendering and the selection path stay a manual Windows check (the auto-close smoke proves open/abort/unwind). - The COM vtable slots and GUIDs used are frozen Windows ABI (Vista); a koffi signature mistake risks a native access violation, contained to the dialog child process — the host Node process survives and the failure surfaces as-is (no fallback tier; see the [chain removal](../simplification/2026-08-04-drop-windows-powershell-picker-fallback.md)). The mocked-koffi ABI pins and the real win32 smoke exist to catch such mistakes before shipping. -- The packaged-binary arm — the packaged executable spawning itself as the dialog entry — is not exercised by any automated test: the source plane and the built `lib/worker.cjs` under plain node are covered, and the packaged spawn remains deferred to the Windows CI roadmap. +- The packaged-binary arm — the packaged executable spawning itself as the dialog entry — is not exercised by any automated test. The source plane and built `lib/worker.cjs` under plain Node are covered; packaged self-spawn remains a named coverage gap. diff --git a/.agents/notes/implemented/feature/2026-08-02-win32-in-process-folder-dialog.zh.md b/.agents/notes/implemented/feature/2026-08-02-win32-in-process-folder-dialog.zh.md index d2bab277ca..af45bc18d6 100644 --- a/.agents/notes/implemented/feature/2026-08-02-win32-in-process-folder-dialog.zh.md +++ b/.agents/notes/implemented/feature/2026-08-02-win32-in-process-folder-dialog.zh.md @@ -24,4 +24,4 @@ Windows 目录选择器的主层此前是围绕 WinForms `FolderBrowserDialog` s - 每台 Windows 机器都得到带其所支持的最佳 DPI 感知（1703+ 为 per-monitor-v2）的现代对话框，无论是否安装 PowerShell。 - 真实对话框的渲染与完成选择的流程仍需在 Windows 上手动检查（自动关闭冒烟测试证明打开／中止／收尾）。 - 所用 COM vtable 槽位与 GUID 是冻结的 Windows ABI（Vista 起）；koffi 签名错误可能引发原生访问冲突，但被限制在对话框子进程内——宿主 Node 进程存活，失败原样上报（无回退层；见[链删除](../simplification/2026-08-04-drop-windows-powershell-picker-fallback.zh.md)）。mocked-koffi 的 ABI 固定测试与真实 win32 冒烟测试正是为了在交付前捕获这类错误。 -- 打包二进制路径——打包后的可执行文件以对话框入口形式自我 spawn——不受任何自动化测试覆盖：源码侧与普通 node 下构建出的 `lib/worker.cjs` 已被覆盖，打包 spawn 推迟到 Windows CI 路线图。 +- 打包二进制路径——打包后的可执行文件以对话框入口形式自我 spawn——不受任何自动化测试覆盖。源码侧与普通 Node 下构建出的 `lib/worker.cjs` 已被覆盖；打包后的自我 spawn 仍是一项明确的覆盖缺口。 diff --git a/.agents/notes/implemented/feature/2026-08-04-pointer-revealed-sidebar-scrollbars.i18n.yaml b/.agents/notes/implemented/feature/2026-08-04-pointer-revealed-sidebar-scrollbars.i18n.yaml index 019f84df2b..50a3a9609c 100644 --- a/.agents/notes/implemented/feature/2026-08-04-pointer-revealed-sidebar-scrollbars.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-04-pointer-revealed-sidebar-scrollbars.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-04-pointer-revealed-sidebar-scrollbars.md -2026-08-04-pointer-revealed-sidebar-scrollbars.md: 5c6fff378932d3e63bc92ed27e9b0341effaf6b8 -2026-08-04-pointer-revealed-sidebar-scrollbars.zh.md: dd9528fec4bd24a53b17ecf888a9af03d457ce0e +2026-08-04-pointer-revealed-sidebar-scrollbars.md: 5a9a0b948ed97af37cab135928bb8624fb2a4da9 +2026-08-04-pointer-revealed-sidebar-scrollbars.zh.md: 35350e1811da8a5e94a7b2eaefc6111d02b18c45 diff --git a/.agents/notes/implemented/feature/2026-08-04-pointer-revealed-sidebar-scrollbars.md b/.agents/notes/implemented/feature/2026-08-04-pointer-revealed-sidebar-scrollbars.md index 5c6fff3789..5a9a0b948e 100644 --- a/.agents/notes/implemented/feature/2026-08-04-pointer-revealed-sidebar-scrollbars.md +++ b/.agents/notes/implemented/feature/2026-08-04-pointer-revealed-sidebar-scrollbars.md @@ -10,7 +10,7 @@ The sidebar's session list overflows after a handful of sessions, and from that ## Decision -`SidebarRoot` tracks the pointer over the whole column and carries a `quietBars` class whenever it is outside. The rule that class selects rebinds ui-theme's indirection pair — `--dsh-scrollbar-thumb` and `--dsh-scrollbar-thumb-hover` — to `transparent`, so every scroll region nested under the column draws no thumb. The session list is the only one today; a future one inherits the behavior rather than opting into it. +`SidebarRoot` tracks the pointer over the whole column and carries a `quietBars` class whenever it is outside. The rule that class selects rebinds ui-theme's indirection pair — `--dsh-scrollbar-thumb` and `--dsh-scrollbar-thumb-hover` — to `transparent`, so every scroll region nested under the column draws no thumb. The session list is the only occupant; a future one inherits the behavior rather than opting into it. The tail is `SCROLLBAR_LINGER_MS = 2000`: leaving arms a timer, entering cancels a pending one, and only the timer firing puts the class back. A pointer that crosses the column's edge and returns — travelling around a portalled menu, or overshooting on the way to a row — never sees the thumb blink. @@ -45,7 +45,7 @@ Hiding no longer counts as elevating: only an l2 rebind exempts a sheet from "ev - A list scrolled by keyboard or by a touch drag shows no thumb once the linger passes, since neither leaves a pointer over the column. The e2e pins this rather than only describing it. - Dragging the thumb itself out of the column does not hide it mid-drag: the scrollbar takes the pointer capture, so the page receives no `pointermove` while the button is held. Measured in Chromium — the bar stays drawn and keeps scrolling with the pointer 900px to its right, past the linger window. - The column starts quiet on a cold load and stays so until the pointer first moves over it. A pointer already parked there when the page loads fires nothing until it moves, which is the browser's rule rather than this shell's. -- An elevated surface nested in the column that rebinds the pair to l2 for its own elevation overrides the quiet state and keeps its bar drawn. Nothing in the sidebar does this today. +- An elevated surface nested in the column that rebinds the pair to l2 for its own elevation overrides the quiet state and keeps its bar drawn. No sidebar surface does this. - The shell's DOM now carries a state class, so ui-sidebar's shell snapshots pin `quietBars` and a regression in the default state is a snapshot diff rather than something someone has to notice in a screenshot. ## Testing diff --git a/.agents/notes/implemented/feature/2026-08-04-pointer-revealed-sidebar-scrollbars.zh.md b/.agents/notes/implemented/feature/2026-08-04-pointer-revealed-sidebar-scrollbars.zh.md index dd9528fec4..35350e1811 100644 --- a/.agents/notes/implemented/feature/2026-08-04-pointer-revealed-sidebar-scrollbars.zh.md +++ b/.agents/notes/implemented/feature/2026-08-04-pointer-revealed-sidebar-scrollbars.zh.md @@ -10,7 +10,7 @@ Status: implemented ## 决策 -`SidebarRoot` 跟踪整列上的指针，只要指针不在列内就给根元素挂上 `quietBars` 类。该类选中的规则把 ui-theme 的那组间接变量——`--dsh-scrollbar-thumb` 与 `--dsh-scrollbar-thumb-hover`——重新绑定为 `transparent`，于是嵌套在这一列下的每个滚动区域都不绘制滑块。今天这样的区域只有会话列表；将来新增的区域会直接继承这一行为，而不需要逐个接入。 +`SidebarRoot` 跟踪整列上的指针，只要指针不在列内就给根元素挂上 `quietBars` 类。该类选中的规则把 ui-theme 的那组间接变量——`--dsh-scrollbar-thumb` 与 `--dsh-scrollbar-thumb-hover`——重新绑定为 `transparent`，于是嵌套在这一列下的每个滚动区域都不绘制滑块。只有会话列表占用这样的区域；将来新增的区域会直接继承这一行为，而不需要逐个接入。 拖尾是 `SCROLLBAR_LINGER_MS = 2000`：离开会启动一个定时器，进入会取消尚未触发的定时器，只有定时器真正触发才会把类加回去。指针越过列边界又折返时——绕过一个 portal 菜单，或是奔向某一行时冲过了头——不会看到滑块闪动。 @@ -45,7 +45,7 @@ Status: implemented - 用键盘或触摸拖动滚动的列表，在拖尾结束后不显示滑块，因为这两种方式都不会把指针留在列上。e2e 会钉住这一点，而不只是把它写下来。 - 拖动滑块本身移出列不会在拖动中途把它隐藏：滚动条会接管指针捕获，按住按键期间页面收不到 `pointermove`。已在 Chromium 实测——指针拖到列右侧 900px 处、超过拖尾窗口后，滚动条依然绘制并继续滚动。 - 冷启动时该列处于静默状态，直到指针第一次移到它上面为止。页面加载时就停在那里的指针在移动之前不会触发任何事件，这是浏览器的规则，而非这个外壳的。 -- 嵌套在列内、为自身抬升层级把这组变量重新绑定到 l2 的抬升表面，会覆盖静默状态并继续绘制自己的滚动条。今天侧边栏内没有这样的表面。 +- 嵌套在列内、为自身抬升层级把这组变量重新绑定到 l2 的抬升表面，会覆盖静默状态并继续绘制自己的滚动条。侧边栏内没有这样的表面。 - 外壳的 DOM 现在带有一个状态类，因此 ui-sidebar 的外壳快照会钉住 `quietBars`，默认状态出现回归时表现为快照 diff，而不是需要有人从截图里看出来的东西。 ## 测试 diff --git a/.agents/notes/implemented/feature/2026-08-04-web-context-source-and-steer-marks.i18n.yaml b/.agents/notes/implemented/feature/2026-08-04-web-context-source-and-steer-marks.i18n.yaml index a56f2fed91..754b846347 100644 --- a/.agents/notes/implemented/feature/2026-08-04-web-context-source-and-steer-marks.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-04-web-context-source-and-steer-marks.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-04-web-context-source-and-steer-marks.md -2026-08-04-web-context-source-and-steer-marks.md: 06f6b7b4bd12e2dccb62a38a5b57b153a6263901 -2026-08-04-web-context-source-and-steer-marks.zh.md: d8109d832fdf6974a89427a6296b24054c6eac36 +2026-08-04-web-context-source-and-steer-marks.md: 0a9d6a4ebd1035773cd768af5ea8614bcad9e0c3 +2026-08-04-web-context-source-and-steer-marks.zh.md: 3e3f80cc54f57e870077b735c4dbb04b9b462656 diff --git a/.agents/notes/implemented/feature/2026-08-04-web-context-source-and-steer-marks.md b/.agents/notes/implemented/feature/2026-08-04-web-context-source-and-steer-marks.md index 06f6b7b4bd..0a9d6a4ebd 100644 --- a/.agents/notes/implemented/feature/2026-08-04-web-context-source-and-steer-marks.md +++ b/.agents/notes/implemented/feature/2026-08-04-web-context-source-and-steer-marks.md @@ -18,7 +18,7 @@ The Chat Message Definition attaches a `provenance` view containing the producer **The label is read out of the log, never from a client-side table of producer names.** `agent-instructions` is named by the distinct instruction paths it reconciled, `session-reference` by the titles of the sessions it read, a plugin source by its logged plugin id, and any other source by its own `kind` — the documented default arm for a merge-extensible union. A source carrying no readable kind degrades to an unnamed injection. A new or renamed producer is therefore identifiable without a client release, no label can go stale against the code, and a resumed, forked, or foreign log projects exactly like a live session. -`recall` covers `session-reference` because that is the one shipped source that lifts another session's material into this one. No Web leaf mounts `dsh-session-reference` today — it had only a terminal host — so the arm exists for log portability rather than for a bundled producer, and it is exercised by unit coverage rather than an assembled Web scenario. +`recall` covers `session-reference` because that is the one shipped source that lifts another session's material into this one. No Web leaf mounts `dsh-session-reference` — it had only a terminal host — so the arm exists for log portability rather than for a bundled producer, and it is exercised by unit coverage rather than an assembled Web scenario. `MessageItem` captions durable and pending steering bubbles with `插话`. The Chat Inbox and Message Definitions replay durable `agent/inbox/spliced` events and project a user-origin `user/message` as `SteeringMessageNode` when that same message identity was claimed from `next-step`; a queued-turn claim stays a `UserMessageNode`, and a non-user next-step message stays context. This reverses one clause of the [archived no-steer decision](../../archived/simplification/2026-07-31-web-ui-no-steer-entry-or-interjection-chrome.md), which removed the badge because the composer could not steer and the label named a gesture users could not perform. The composer gained a Steer gesture afterwards without amending that note; this decision supplies the product decision its reintroduction clause required, and corrects the stale facts left in it. The caption is the only steering chrome here: composer modes, the Queue dock's strict-steer action, and pending-steering lifecycle stay with their own owners. diff --git a/.agents/notes/implemented/feature/2026-08-04-web-context-source-and-steer-marks.zh.md b/.agents/notes/implemented/feature/2026-08-04-web-context-source-and-steer-marks.zh.md index d8109d832f..3e3f80cc54 100644 --- a/.agents/notes/implemented/feature/2026-08-04-web-context-source-and-steer-marks.zh.md +++ b/.agents/notes/implemented/feature/2026-08-04-web-context-source-and-steer-marks.zh.md @@ -18,7 +18,7 @@ Chat Message Definition 为每个 `ContextMessageNode` 附加一份包含生产 **名称从日志中读出，绝不来自客户端维护的生产者名称表。** `agent-instructions` 以它对账过的去重指令文件路径命名，`session-reference` 以它读取的会话标题命名，插件来源以其记录的插件 id 命名，其余来源则以自身的 `kind` 命名——这正是可合并扩展联合类型有文档记载的默认分支。没有可读 kind 的来源降级为无名注入。于是新增或重命名的生产者无需客户端发版即可辨识，任何名称都不会相对代码失准，恢复、fork 或来自外部的日志与实时会话的投影结果完全一致。 -`recall` 覆盖 `session-reference`，因为它是当前唯一会把另一个会话的材料搬进本会话的已发布来源。今天没有任何 Web 叶子挂载 `dsh-session-reference`——它此前只有终端宿主——因此该分支的存在是为了日志可移植性，而不是为了某个已打包的生产方，其覆盖来自单元测试而非组装后的 Web 场景。 +`recall` 覆盖 `session-reference`，因为它是当前唯一会把另一个会话的材料搬进本会话的已发布来源。没有任何 Web 叶子挂载 `dsh-session-reference`——它此前只有终端宿主——因此该分支的存在是为了日志可移植性，而不是为了某个已打包的生产方，其覆盖来自单元测试而非组装后的 Web 场景。 Chat Inbox 与 Message Definition 会重放持久 `agent/inbox/spliced` 事件；如果一条用户来源的消息以相同身份从 `next-step` 被领取，后续 `user/message` 就投影为 `SteeringMessageNode`。`MessageItem` 为这种持久消息与待处理 steering 气泡加上 `插话` 标注。从排队轮次领取的消息仍是 `UserMessageNode`，非用户来源的 next-step 消息仍是上下文。这推翻了[已归档的取消 steer 入口与插话装饰决策](../../archived/simplification/2026-07-31-web-ui-no-steer-entry-or-interjection-chrome.md)中的一条结论。当时移除徽章，是因为 composer 无法 steer，标签指向了用户做不到的动作。此后 composer 获得了 Steer 手势，却没有同步修订那份 note；本决策提供了它在「重新引入」条款中要求的产品决策，并订正了其中留下的过时事实。标注是这里唯一的 steering 装饰：composer 模式、Queue dock 的严格 steer 操作、待处理 steering 的生命周期仍归各自的所有者。 diff --git a/.agents/notes/implemented/feature/2026-08-04-web-latency-throughput-metrics.i18n.yaml b/.agents/notes/implemented/feature/2026-08-04-web-latency-throughput-metrics.i18n.yaml index 54df52a8e9..f1ed369ae8 100644 --- a/.agents/notes/implemented/feature/2026-08-04-web-latency-throughput-metrics.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-04-web-latency-throughput-metrics.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-04-web-latency-throughput-metrics.md -2026-08-04-web-latency-throughput-metrics.md: 4d7627a9a38127259f1ba07121cea7282f794f2e -2026-08-04-web-latency-throughput-metrics.zh.md: f0089cb45775f2dc9701a7256119f04e4709dd76 +2026-08-04-web-latency-throughput-metrics.md: 14ec765a7aadb8a54609c7d4e0e6af149c3c96ba +2026-08-04-web-latency-throughput-metrics.zh.md: 52e6c33c52895f5a075f78019c5f353ecc8cc4b4 diff --git a/.agents/notes/implemented/feature/2026-08-04-web-latency-throughput-metrics.md b/.agents/notes/implemented/feature/2026-08-04-web-latency-throughput-metrics.md index 4d7627a9a3..14ec765a7a 100644 --- a/.agents/notes/implemented/feature/2026-08-04-web-latency-throughput-metrics.md +++ b/.agents/notes/implemented/feature/2026-08-04-web-latency-throughput-metrics.md @@ -18,7 +18,7 @@ The stats line reuses the same step reading in its window fold: `deriveStats` ac ## Alternatives considered -**A durable session projection (token-meter shape).** A `ProjectionDefinition` folding step timings host-side would survive compaction and window paging and cover the whole log. Deferred, not rejected: projection state must stay O(1) (averages, not percentiles), it needs a host change plus a schema, and the chat stats line is already documented as window-scoped for its duration facts — the new group joins that scope. A later PR can add the durable projection without moving these readings. +**A durable session projection (token-meter shape).** A `ProjectionDefinition` folding step timings host-side would survive compaction and window paging and cover the whole log. Deferred, not rejected: projection state must stay O(1) (averages, not percentiles), it needs a host change plus a schema, and the chat stats line is documented as window-scoped for its duration facts. A durable projection can be added without moving these readings. **Per-step footer chrome.** Showing each assistant message its own TTFT would attach chrome to mid-turn narration nodes, which the footer design deliberately keeps chrome-free; the trajectory view already exposes per-step timing detail. diff --git a/.agents/notes/implemented/feature/2026-08-04-web-latency-throughput-metrics.zh.md b/.agents/notes/implemented/feature/2026-08-04-web-latency-throughput-metrics.zh.md index f0089cb457..52e6c33c52 100644 --- a/.agents/notes/implemented/feature/2026-08-04-web-latency-throughput-metrics.zh.md +++ b/.agents/notes/implemented/feature/2026-08-04-web-latency-throughput-metrics.zh.md @@ -18,7 +18,7 @@ assistant 页脚把读数追加到既有 hover 显示的时间附属元素中、 ## 考虑过的替代方案 -**持久的会话投影（token-meter 形态）。** 在 host 侧用 `ProjectionDefinition` 折算步骤计时可以跨越压缩（compaction）与窗口分页、覆盖整个日志。是暂缓而非否决：投影状态必须保持 O(1)（只能均值，不能分位数），它需要 host 改动加 schema，而聊天统计行的耗时事实本就被记录为窗口作用域——新分组沿用该作用域。后续 PR（Pull Request）可以在不挪动这些读数的情况下补上持久投影。 +**持久的会话投影（token-meter 形态）。** 在 host 侧用 `ProjectionDefinition` 折算步骤计时可以跨越压缩（compaction）与窗口分页、覆盖整个日志。是暂缓而非否决：投影状态必须保持 O(1)（只能均值，不能分位数），它需要 host 改动加 schema，而聊天统计行的耗时事实被记录为窗口作用域。持久投影可以在不挪动这些读数的情况下补上。 **逐步骤页脚附属元素。** 让每条 assistant 消息显示自己的 TTFT，会给轮次中段的叙述节点挂上附属元素，而页脚设计刻意让它们保持无 chrome；trajectory 视图已经暴露逐步骤计时细节。 diff --git a/.agents/notes/implemented/feature/2026-08-05-context-form-vocabulary.i18n.yaml b/.agents/notes/implemented/feature/2026-08-05-context-form-vocabulary.i18n.yaml index a9895e1743..f125c62af7 100644 --- a/.agents/notes/implemented/feature/2026-08-05-context-form-vocabulary.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-05-context-form-vocabulary.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-05-context-form-vocabulary.md -2026-08-05-context-form-vocabulary.md: 27c36f999b676026ca09f4f0e226c8ed95ef4918 -2026-08-05-context-form-vocabulary.zh.md: 1aa874e09336f99b06d7ebc385e0ac0c195bacbf +2026-08-05-context-form-vocabulary.md: 9f20614dcd2ed0164efb51f938de9f74657d3bc3 +2026-08-05-context-form-vocabulary.zh.md: ebdabeab5a074f21e8fac9625a78c99cc401a6d3 diff --git a/.agents/notes/implemented/feature/2026-08-05-context-form-vocabulary.md b/.agents/notes/implemented/feature/2026-08-05-context-form-vocabulary.md index 27c36f999b..9f20614dcd 100644 --- a/.agents/notes/implemented/feature/2026-08-05-context-form-vocabulary.md +++ b/.agents/notes/implemented/feature/2026-08-05-context-form-vocabulary.md @@ -51,7 +51,7 @@ The tool presentation contract pairs its vocabulary with `presentCall(args)`, a **Map source kinds to renderers in the client.** Cheapest to write and requires no format change, but it puts producer knowledge back in the client: every new kind then needs a client release to render as anything but opaque, and a foreign log cannot be classified at all. It also reintroduces exactly the coupling the [source and steer marks decision](2026-08-04-web-context-source-and-steer-marks.md) removed for labels. -**Reuse `kind` as the form.** One discriminant is simpler, and `agent-instructions` is already 1:1 with its form. This design loses information when several producers share one form: three producers emit runtime snapshots today, and combining them into one kind would make it impossible to tell which producer supplied each message. Separate `kind` and `form` fields record the producer while allowing several producers to share one presentation. +**Reuse `kind` as the form.** One discriminant is simpler, and `agent-instructions` is already 1:1 with its form. This design loses information when several producers share one form: three shipped producers emit runtime snapshots, and combining them into one kind would make it impossible to tell which producer supplied each message. Separate `kind` and `form` fields record the producer while allowing several producers to share one presentation. **Let the client parse the model-facing prose.** The entries and file sections are visibly structured in the text. Parsing them couples the presentation to prompt wording, so every reword silently breaks a card — the same reason catalog identity moved off the text. diff --git a/.agents/notes/implemented/feature/2026-08-05-context-form-vocabulary.zh.md b/.agents/notes/implemented/feature/2026-08-05-context-form-vocabulary.zh.md index 1aa874e093..ebdabeab5a 100644 --- a/.agents/notes/implemented/feature/2026-08-05-context-form-vocabulary.zh.md +++ b/.agents/notes/implemented/feature/2026-08-05-context-form-vocabulary.zh.md @@ -51,7 +51,7 @@ Status: implemented **在客户端把来源 kind 映射到渲染器。** 写起来最省，也不用改格式，但它把生产方知识放回了客户端：此后每新增一个 kind 都要客户端发版才能渲染成 opaque 以外的东西，而外部日志根本无法分类。它还会重新引入[来源与 steer 标识决策](2026-08-04-web-context-source-and-steer-marks.zh.md)刚为名称去掉的那种耦合。 -**复用 `kind` 充当形态。** 单一判别字段更简单，`agent-instructions` 本来也与它的形态一一对应。但多个生产方共享同一形态时，这种设计无法保留完整信息：今天有三个生产方发出运行时快照，把它们并成一个 kind 后，将无法分辨每条消息由哪个生产方提供。独立的 `kind` 和 `form` 字段会记录生产方，同时允许多个生产方共用一种呈现方式。 +**复用 `kind` 充当形态。** 单一判别字段更简单，`agent-instructions` 本来也与它的形态一一对应。但多个生产方共享同一形态时，这种设计无法保留完整信息：三个已交付生产方发出运行时快照，把它们并成一个 kind 后，将无法分辨每条消息由哪个生产方提供。独立的 `kind` 和 `form` 字段会记录生产方，同时允许多个生产方共用一种呈现方式。 **让客户端解析面向模型的散文。** 条目与文件分节在文本里确实有可见结构。解析它们会把呈现耦合到提示词措辞上，于是每改一次文案就会悄悄破坏一张卡片——这也正是目录身份从文本上迁走的原因。 diff --git a/.agents/notes/implemented/feature/2026-08-06-bundled-dsh-badge-skill.i18n.yaml b/.agents/notes/implemented/feature/2026-08-06-bundled-dsh-badge-skill.i18n.yaml deleted file mode 100644 index d7d1c8e67b..0000000000 --- a/.agents/notes/implemented/feature/2026-08-06-bundled-dsh-badge-skill.i18n.yaml +++ /dev/null @@ -1,6 +0,0 @@ -# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each -# side as of the last confirmed-consistent state. Both languages carry equal authority; -# after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-06-bundled-dsh-badge-skill.md -2026-08-06-bundled-dsh-badge-skill.md: 4c6fbdcb76298759c2f17b3b5349a5b48198595e -2026-08-06-bundled-dsh-badge-skill.zh.md: fe291d498660e744cf193e123aa1a4a4f4a27b3b diff --git a/.agents/notes/implemented/feature/2026-08-06-mcp-client-auto-reconnect.i18n.yaml b/.agents/notes/implemented/feature/2026-08-06-mcp-client-auto-reconnect.i18n.yaml index d421c6ba82..50b48a757c 100644 --- a/.agents/notes/implemented/feature/2026-08-06-mcp-client-auto-reconnect.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-06-mcp-client-auto-reconnect.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-06-mcp-client-auto-reconnect.md -2026-08-06-mcp-client-auto-reconnect.md: 99a8aec1abe3713822f8f17c17d8efaca5d61a4d -2026-08-06-mcp-client-auto-reconnect.zh.md: 87acb6901cf3bc03fc5d71e89538e5ec23b2b118 +2026-08-06-mcp-client-auto-reconnect.md: 0f9119c62087a32e516583b72f841387c05105c1 +2026-08-06-mcp-client-auto-reconnect.zh.md: 62be78821d7f6e489e613f698d77a438aa1e10c7 diff --git a/.agents/notes/implemented/feature/2026-08-06-mcp-client-auto-reconnect.md b/.agents/notes/implemented/feature/2026-08-06-mcp-client-auto-reconnect.md index 99a8aec1ab..0f9119c620 100644 --- a/.agents/notes/implemented/feature/2026-08-06-mcp-client-auto-reconnect.md +++ b/.agents/notes/implemented/feature/2026-08-06-mcp-client-auto-reconnect.md @@ -6,7 +6,7 @@ English | [中文](2026-08-06-mcp-client-auto-reconnect.zh.md) ## Problem -The [MCP client](2026-07-07-mcp-client-plugin.md) connected once at plugin load. When a stdio server crashed or was killed, its registered tools stayed visible but every call failed with `Not connected` until a human edited the config (HMR) or restarted the Host — v1 explicitly deferred reconnection. Long-running hosts (ACP automation, web) cannot be bounced because a child process died, and for stdio the harness composition is the only party that can respawn it. External feedback escalated this as a real operational gap (issue #1746). +The [MCP client](2026-07-07-mcp-client-plugin.md) connected once at plugin load. When a stdio server crashed or was killed, its registered tools stayed visible but every call failed with `Not connected` until a human edited the config (HMR) or restarted the Host — the connect-once decision explicitly deferred reconnection. Long-running hosts (ACP automation, web) cannot be bounced because a child process died, and for stdio the harness composition is the only party that can respawn it. External feedback escalated this as a real operational gap (issue #1746). ## Decision @@ -20,7 +20,7 @@ The [MCP client](2026-07-07-mcp-client-plugin.md) connected once at plugin load. **Config and resolution.** Both transports accept `reconnect { enabled, initialDelayMs, maxDelayMs, maxAttempts }` with schemastery defaults (on, 500ms, 30s, 10). `resolveReconnectPolicy()` is the explicit resolve step: it re-judges every bound and cross-field constraint because programmatic construction may bypass Schemastery, and misconfiguration fails the plugin instance at load. -**Observable states.** An initial or retry-attempt failure says `connection failed`; an established generation ending says `connection lost`. Retrying logs at warn with attempt count and delay, recovery at info, final failure and disabled recovery at error. During an outage the last good generation stays registered and calls against it fail — deterministic public names mean a recovered unchanged tool list reproduces identical definitions, keeping the model-visible schema prefix stable instead of flapping. With `reconnect.enabled: false` a lost connection keeps the v1 manual-recovery behavior. +**Observable states.** An initial or retry-attempt failure says `connection failed`; an established generation ending says `connection lost`. Retrying logs at warn with attempt count and delay, recovery at info, final failure and disabled recovery at error. During an outage the last good generation stays registered and calls against it fail — deterministic public names mean a recovered unchanged tool list reproduces identical definitions, keeping the model-visible schema prefix stable instead of flapping. With `reconnect.enabled: false` a lost connection keeps the connect-once manual-recovery behavior. **Disposal.** Dispose flips the fence, cancels any pending timer, closes the current client, then awaits the in-flight attempt and the sync queue before unregistering — quiescence, not just a request to stop. The reconnect timer is unref'd so a waiting backoff never holds a finishing process open. @@ -32,17 +32,17 @@ The [MCP client](2026-07-07-mcp-client-plugin.md) connected once at plugin load. **Unregister tools immediately on disconnect, re-register on recovery.** Rejected: a transient outage would flap the model-visible tool list (two schema-prefix invalidations per crash) for no information gain; failing calls already signal the outage, and the swap on recovery is atomic per generation. Tools are unregistered at final failure so a permanently dead server does not leak permanently broken tools. -**Route Streamable HTTP request failures into the supervisor.** Rejected for now: the HTTP transport already reconnects its SSE stream with its own backoff, per-request errors do not imply a dead server, and there is no child process the harness could respawn. Transport close stays the single trigger. +**Route Streamable HTTP request failures into the supervisor.** Rejected: the HTTP transport already reconnects its SSE stream with its own backoff, per-request errors do not imply a dead server, and there is no child process the harness could respawn. Transport close stays the single trigger. **Restart through Loader/HMR machinery instead of an in-plugin supervisor.** Rejected: the Loader owns config-driven recomposition, not runtime health. A plugin restarting itself through the Loader would conflate config generations with connection generations and lose the per-outage budget. ## Testing -Unit (`tests/reconnect.spec.ts`, mocked SDK): recovery swaps generations without duplication or leaks and serves post-recovery calls, diagnostics distinguish initial or retry failure from established connection loss, strict startup registration survives a pre-connect `list_changed` notification, failed initialization waits for the old generation's close signal and fails closed when that signal never arrives, disposal waits for the same signal with a bounded incomplete-shutdown path, the failure cap unregisters tools and stops, dispose cancels a pending backoff and quiesces an in-flight sync, a close after dispose schedules nothing, disabled mode keeps the v1 behavior, the stability window resets the budget while a crash loop exhausts it, double failure signals schedule one retry, stale generations and handlers are inert, and `resolveReconnectPolicy` rejects each invalid bound. E2E (`tests/mcp-client.e2e.ts`, keyless): the fixture server gained a `crash` tool that replies then exits; real-process tests prove a stdio crash recovers end to end and that unloading the plugin mid-outage stops reconnection promptly. Snapshot: deliberately none, per the original note's rationale — reconnection adds no new presentation shape, and a snapshot composition spawning a crashing server would make replays timing-dependent. +Unit (`tests/reconnect.spec.ts`, mocked SDK): recovery swaps generations without duplication or leaks and serves post-recovery calls, diagnostics distinguish initial or retry failure from established connection loss, strict startup registration survives a pre-connect `list_changed` notification, failed initialization waits for the old generation's close signal and fails closed when that signal never arrives, disposal waits for the same signal with a bounded incomplete-shutdown path, the failure cap unregisters tools and stops, dispose cancels a pending backoff and quiesces an in-flight sync, a close after dispose schedules nothing, disabled mode keeps manual recovery, the stability window resets the budget while a crash loop exhausts it, double failure signals schedule one retry, stale generations and handlers are inert, and `resolveReconnectPolicy` rejects each invalid bound. E2E (`tests/mcp-client.e2e.ts`, keyless): the fixture server gained a `crash` tool that replies then exits; real-process tests prove a stdio crash recovers end to end and that unloading the plugin mid-outage stops reconnection promptly. Snapshot: deliberately none, per the original note's rationale — reconnection adds no new presentation shape, and a snapshot composition spawning a crashing server would make replays timing-dependent. ## Consequences - A crashed stdio MCP server recovers without human intervention: bounded backoff, re-discovery, atomic generation swap. Default policy retries an outage for roughly 2.5 minutes before giving up. -- Connection state is genuinely more intricate than connect-once — the partial-availability window v1 avoided now exists (registered tools failing during an outage), concentrated in one module with the invariants named. +- Connection state is genuinely more intricate than connect-once. The design accepts a partial-availability window with registered tools failing during an outage, concentrated in one module with the invariants named. - `reconnect` is new config surface on both transports, and the stability window is deliberately derived from `maxDelayMs`; making it independently tunable is a compatible future change. - After final failure or with reconnect disabled, the plugin stays loaded with no (or failing) tools until reload — deliberate and logged, so a chronically broken server cannot restart forever. diff --git a/.agents/notes/implemented/feature/2026-08-06-mcp-client-auto-reconnect.zh.md b/.agents/notes/implemented/feature/2026-08-06-mcp-client-auto-reconnect.zh.md index 87acb6901c..62be78821d 100644 --- a/.agents/notes/implemented/feature/2026-08-06-mcp-client-auto-reconnect.zh.md +++ b/.agents/notes/implemented/feature/2026-08-06-mcp-client-auto-reconnect.zh.md @@ -6,7 +6,7 @@ Status: implemented ## 问题 -[MCP 客户端](2026-07-07-mcp-client-plugin.zh.md)在插件加载时仅连接一次。stdio 服务器崩溃或被终止后，其已注册的工具仍然可见，但每次调用均以 `Not connected` 失败，直到人工编辑配置触发 HMR（热模块替换）重载，或重启 Host——v1 明确推迟了重连机制。长时间运行的 Host（ACP 自动化、Web）不能因为子进程死亡就被重启；而对于 stdio 传输，harness 组合层是唯一能重新拉起子进程的一方。外部反馈将此升级为真实的运维缺口（issue #1746）。 +[MCP 客户端](2026-07-07-mcp-client-plugin.zh.md)在插件加载时仅连接一次。stdio 服务器崩溃或被终止后，其已注册的工具仍然可见，但每次调用均以 `Not connected` 失败，直到人工编辑配置触发 HMR（热模块替换）重载，或重启 Host——单次连接决策明确推迟了重连机制。长时间运行的 Host（ACP 自动化、Web）不能因为子进程死亡就被重启；而对于 stdio 传输，harness 组合层是唯一能重新拉起子进程的一方。外部反馈将此升级为真实的运维缺口（issue #1746）。 ## 决策 @@ -20,7 +20,7 @@ Status: implemented **配置与解析。** 两种传输均接受 `reconnect { enabled, initialDelayMs, maxDelayMs, maxAttempts }` 配置，Schemastery 默认值为（启用、500ms、30s、10）。`resolveReconnectPolicy()` 是显式的解析步骤：它重新校验每个边界值和跨字段约束，因为程序化构造可能绕过 Schemastery，配置错误在加载时即令插件实例失败。 -**可观测状态。** 初始尝试或重试尝试失败时记录 `connection failed`，已建立的代结束时记录 `connection lost`；重试的 warn 日志包含尝试次数和延迟，恢复以 info 级别记录，最终失败和禁用重连时的断连以 error 级别记录。故障期间，上一个正常代保持注册，对其工具的调用返回失败——确定性公开名称意味着恢复后未变化的工具列表会复现相同的定义，保持模型可见 schema 前缀稳定而非反复抖动。设置 `reconnect.enabled: false` 后，断连保持 v1 的手动恢复行为。 +**可观测状态。** 初始尝试或重试尝试失败时记录 `connection failed`，已建立的代结束时记录 `connection lost`；重试的 warn 日志包含尝试次数和延迟，恢复以 info 级别记录，最终失败和禁用重连时的断连以 error 级别记录。故障期间，上一个正常代保持注册，对其工具的调用返回失败——确定性公开名称意味着恢复后未变化的工具列表会复现相同的定义，保持模型可见 schema 前缀稳定而非反复抖动。设置 `reconnect.enabled: false` 后，断连保持单次连接的手动恢复行为。 **资源释放。** dispose 翻转栅栏、取消待执行的定时器、关闭当前 client，然后等待正在进行的尝试和同步队列完成后再注销工具——完全停稳，而非仅发出停止请求。重连定时器使用 unref，因此等待中的退避不会阻止进程正常退出。 @@ -32,17 +32,17 @@ Status: implemented **断连时立即注销工具，恢复时重新注册。** 否决：短暂故障会使模型可见工具列表抖动（每次崩溃触发两次 schema 前缀失效），而无任何信息增益；失败的调用已足以标示故障，恢复时的切换按代原子执行。工具仅在最终失败时注销，确保永久死亡的服务器不会泄漏永久失效的工具。 -**将 Streamable HTTP 请求失败路由到监督器。** 暂不采纳：HTTP 传输已使用自己的退避机制重连其 SSE 流，逐请求错误并不意味着服务器已死，且 harness 没有可重新拉起的子进程。transport 关闭仍是唯一触发条件。 +**将 Streamable HTTP 请求失败路由到监督器。**不予采纳：HTTP 传输已使用自己的退避机制重连 SSE 流，逐请求错误并不意味着服务器已死，且 harness 没有可重新拉起的子进程。transport 关闭仍是唯一触发条件。 **通过 Loader/HMR 机制重启，而非使用插件内监督器。** 否决：Loader 负责配置驱动的重组合，而非运行时健康管理。插件通过 Loader 重启自身会混淆配置代与连接代，并丢失逐故障预算。 ## 测试 -单元测试（`tests/reconnect.spec.ts`，mock SDK）：恢复在不产生重复或泄漏的前提下切换代并服务恢复后的调用、诊断区分初始或重试尝试失败与已建立连接丢失、严格启动注册在连接前收到 `list_changed` 通知后仍然生效、初始化失败会等待旧代的关闭信号，若该信号始终未到则停止重连、dispose 同样等待同一关闭信号，并在有界等待到期时报告关停未完成、失败上限注销工具并停止、dispose 取消待执行的退避并使进行中的同步完全停稳、dispose 后的关闭不调度任何操作、禁用模式保持 v1 行为、稳定窗口重置预算而崩溃循环耗尽预算、双重失败信号仅调度一次重试、过时的代和处理器为惰性、`resolveReconnectPolicy` 拒绝每个无效边界值。E2E（`tests/mcp-client.e2e.ts`，无需密钥）：fixture 服务器新增了一个 `crash` 工具（先回复再退出）；真实进程测试证明 stdio 崩溃端到端恢复，以及在故障期间卸载插件能立即停止重连。快照：刻意不做，原因与原 Agent Note 相同——重连不引入新的展示形态，而在快照组合中 spawn 崩溃服务器会使回放依赖时序。 +单元测试（`tests/reconnect.spec.ts`，mock SDK）：恢复在不产生重复或泄漏的前提下切换代并服务恢复后的调用、诊断区分初始或重试尝试失败与已建立连接丢失、严格启动注册在连接前收到 `list_changed` 通知后仍然生效、初始化失败会等待旧代的关闭信号，若该信号始终未到则停止重连、dispose 同样等待同一关闭信号，并在有界等待到期时报告关停未完成、失败上限注销工具并停止、dispose 取消待执行的退避并使进行中的同步完全停稳、dispose 后的关闭不调度任何操作、禁用模式保持手动恢复、稳定窗口重置预算而崩溃循环耗尽预算、双重失败信号仅调度一次重试、过时的代和处理器为惰性、`resolveReconnectPolicy` 拒绝每个无效边界值。E2E（`tests/mcp-client.e2e.ts`，无需密钥）：fixture 服务器新增了一个 `crash` 工具（先回复再退出）；真实进程测试证明 stdio 崩溃端到端恢复，以及在故障期间卸载插件能立即停止重连。快照：刻意不做，原因与原 Agent Note 相同——重连不引入新的展示形态，而在快照组合中 spawn 崩溃服务器会使回放依赖时序。 ## 后果 - 崩溃的 stdio MCP 服务器无需人工干预即可恢复：有界退避、重新发现、原子代切换。默认策略对一次故障大约重试 2.5 分钟后放弃。 -- 连接状态确实比一次性连接更复杂——v1 刻意回避的部分可用窗口现已存在（故障期间已注册工具返回失败），集中在一个模块中并命名了所有不变式。 +- 连接状态确实比一次性连接更复杂。该设计接受一段部分可用窗口：故障期间已注册工具会返回失败；相关不变式集中在一个模块中并被明确命名。 - `reconnect` 是两种传输上的新配置表面，稳定窗口刻意从 `maxDelayMs` 推导；将其设为独立可调参数是兼容的未来变更。 - 最终失败后或禁用重连时，插件保持加载状态但无（或失败的）工具，直到重新加载——行为是刻意的且有日志记录，确保长期故障的服务器不能永远重启。 diff --git a/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.i18n.yaml b/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.i18n.yaml index 55ce6ceeb9..e340548145 100644 --- a/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.md -2026-08-06-web-skill-tool-row.md: 04e8ffcd6e506142b569e60458af144233810bbd -2026-08-06-web-skill-tool-row.zh.md: c68ddea1d44e3b071deafc9450f6a2d09023cd80 +2026-08-06-web-skill-tool-row.md: a78afd5d375d2cecd806ade663b4a5b7511ae279 +2026-08-06-web-skill-tool-row.zh.md: 469f9510ea5f31ceb8fb177432b090d91c8a5df8 diff --git a/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.md b/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.md index 04e8ffcd6e..a78afd5d37 100644 --- a/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.md +++ b/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.md @@ -14,7 +14,7 @@ The Web transcript renders `skill` calls through the generic fallback row, so a The collapsed row uses a 14-pixel document-and-sparkle glyph and the Bash row's neutral hierarchy: tertiary glyph, secondary `Skill` title, caption separator, and tertiary skill name. Running, failed, and interrupted calls retain the transcript's shimmer, error dot and first-line summary, and warning dot semantics. A settled call expands through the whole summary row into a 260-pixel bounded `Instructions` card containing the exact durable result text; the existing trajectory `Inspect` handoff remains available below the card. -The row derives every visible value from a paired call/result slice in the current runtime window. It reads the skill name from the recorded `name` argument and the instructions from durable result content, and never joins the current skill catalog for descriptions or provider metadata. If pagination leaves the call outside the window, the result has no tool identity and remains on the generic fallback rather than extending the history wire contract. The existing ACP `skill-load` recording is seeded through the real Web persistence and composition path for a keyless interaction and accessibility snapshot. +The row derives every visible value from a paired call/result slice in the current runtime window. It reads the skill name from the recorded `name` argument and the instructions from durable result content, and never joins the current skill catalog for descriptions or provider metadata. If pagination leaves the call outside the window, the result has no tool identity and remains on the generic fallback rather than extending the history wire contract. The existing ACP `skill-load` recording is seeded through the real Web persistence and composition path for a keyless interaction and accessibility snapshot. The snapshot removes a calendar date only when it immediately precedes the normalized clock and `Ran for` footer; the clock remains, so hosts in different timezones produce the same snapshot at a same-day boundary. ## Alternatives considered diff --git a/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.zh.md b/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.zh.md index c68ddea1d4..469f9510ea 100644 --- a/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.zh.md +++ b/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.zh.md @@ -14,7 +14,7 @@ Web transcript（文本记录）通过通用后备行渲染 `skill` 调用，使 收起的行使用 14 像素的文档与闪光组合图标，并沿用 Bash 行的中性色层级：图标采用三级色，`Skill` 标题采用二级色，分隔符采用 caption 色，skill 名称采用三级色。运行、失败和中断调用分别沿用 transcript 的扫光、错误状态点加首行摘要，以及警告状态点语义。已结算调用可以通过整个摘要行展开一个高度上限为 260 像素的 `Instructions` 卡片，其中原样呈现持久化结果文本；用于跳转至 trajectory 的现有 `Inspect` 入口仍保留在卡片下方。 -该行的所有可见值均派生自当前 runtime 窗口中已配对的调用／结果片段。skill 名称来自已记录的 `name` 参数，指令来自持久化的结果内容；该行绝不关联当前 skill 目录来读取描述或提供方元数据。如果分页将调用留在窗口外，结果便没有工具身份，并继续使用通用后备路径，而不是扩展 history 协议约定。现有的 ACP（Agent Client Protocol）`skill-load` 记录经由真实的 Web 持久化与组合路径写入，用于无需密钥的交互和无障碍快照。 +该行的所有可见值均派生自当前 runtime 窗口中已配对的调用／结果片段。skill 名称来自已记录的 `name` 参数，指令来自持久化的结果内容；该行绝不关联当前 skill 目录来读取描述或提供方元数据。如果分页将调用留在窗口外，结果便没有工具身份，并继续使用通用后备路径，而不是扩展 history 协议约定。现有的 ACP（Agent Client Protocol）`skill-load` 记录经由真实的 Web 持久化与组合路径写入，用于无需密钥的交互和无障碍快照。快照只会在日历日期紧邻规范化时钟与 `Ran for` 页脚时移除该日期；时钟仍保留，使不同时区的宿主在同日边界产出相同快照。 ## 考虑过的替代方案 diff --git a/.agents/notes/implemented/feature/2026-08-07-workspace-picker-composer-entry.i18n.yaml b/.agents/notes/implemented/feature/2026-08-07-workspace-picker-composer-entry.i18n.yaml deleted file mode 100644 index 29c39a1018..0000000000 --- a/.agents/notes/implemented/feature/2026-08-07-workspace-picker-composer-entry.i18n.yaml +++ /dev/null @@ -1,6 +0,0 @@ -# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each -# side as of the last confirmed-consistent state. Both languages carry equal authority; -# after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-07-workspace-picker-composer-entry.md -2026-08-07-workspace-picker-composer-entry.md: dc9c26c291de6e7614ace3c787030c0032a9740d -2026-08-07-workspace-picker-composer-entry.zh.md: 9121750ae1cbef2a94630d9ac43a765c03a397a7 diff --git a/.agents/notes/implemented/feature/2026-08-08-web-background-job-display.i18n.yaml b/.agents/notes/implemented/feature/2026-08-08-web-background-job-display.i18n.yaml index 0b96758e87..32c4650128 100644 --- a/.agents/notes/implemented/feature/2026-08-08-web-background-job-display.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-08-web-background-job-display.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-08-web-background-job-display.md -2026-08-08-web-background-job-display.md: 25352ec4f137f0f40c04c90c5c578dcd73eb4e71 -2026-08-08-web-background-job-display.zh.md: f540c65b51a9d23e2f7d286e74cb5cec7356acf7 +2026-08-08-web-background-job-display.md: 1af949a537103637e8bac84b5bfa0f915fcf82e0 +2026-08-08-web-background-job-display.zh.md: 0aa8d65b7697312f603dd9ddd37f182da0b7f39c diff --git a/.agents/notes/implemented/feature/2026-08-08-web-background-job-display.md b/.agents/notes/implemented/feature/2026-08-08-web-background-job-display.md index 25352ec4f1..1af949a537 100644 --- a/.agents/notes/implemented/feature/2026-08-08-web-background-job-display.md +++ b/.agents/notes/implemented/feature/2026-08-08-web-background-job-display.md @@ -95,7 +95,7 @@ A running one-shot background subagent therefore appears both there and in the s **No web path calls `ctx.jobs.read()`.** It consumes the single output cursor, so a browser read would silently take bytes the model's `job_output` will never see. This is an invariant worth a test rather than a convention, because the failure is invisible at the call site. -**No cancellation.** That phase owes a decision the seam does not currently answer: `kill()` marks terminal delivery reported, so a human interrupt written against today's contract would leave the model believing its task is still running. +**No cancellation.** That phase owes a decision the seam does not currently answer: `kill()` marks terminal delivery reported, so a human interrupt written against the `kill()` contract would leave the model believing its task is still running. **No output watermark on the frame.** The output phase's delta channel is where an anchor field earns its place; one added now would have no reader. @@ -129,7 +129,7 @@ Below it, [`jobs-local`](../../../../packages/jobs/jobs-local/tests/jobs.spec.ts **Settled rows accumulate.** The registry retains settled tasks until owner disposal, so a long session with many background commands grows a long list. Capping the settled tail is a presentation change, not a protocol one, if it becomes a real complaint. -**`stopping` is nearly unreachable today.** Only the model's `job_kill` produces it, so the state is rendered but rarely seen until human cancellation lands. It is in the union now because leaving a status out would have made that phase a wire change. +**`stopping` is rarely visible.** Only the model's `job_kill` produces it, so the state is rendered but rarely seen until human cancellation lands. It is in the union now because leaving a status out would have made that phase a wire change. **Two entry points for one running subagent.** Accepted deliberately, and bounded to one-shot background delegations. If it reads as noise in practice, the fix is presentational — the catalog row can cite the task rather than the task list hiding the kind. diff --git a/.agents/notes/implemented/feature/2026-08-08-web-background-job-display.zh.md b/.agents/notes/implemented/feature/2026-08-08-web-background-job-display.zh.md index f540c65b51..0aa8d65b76 100644 --- a/.agents/notes/implemented/feature/2026-08-08-web-background-job-display.zh.md +++ b/.agents/notes/implemented/feature/2026-08-08-web-background-job-display.zh.md @@ -95,7 +95,7 @@ abstract onJobsChanged(listener: JobsChangedListener): () => void **没有任何 Web 路径调用 `ctx.jobs.read()`。** 它消费唯一的输出游标，浏览器读一次就悄悄拿走了模型 `job_output` 永远看不到的字节。这该是一条有测试兜底的不变量而不是一条约定，因为它的故障在调用点完全不可见。 -**不做中断。** 那一期欠一个 seam 目前没有回答的决策：`kill()` 会把终态投递标为已上报，所以照今天的契约写出来的人类中断，会让模型一直以为它的任务还在跑。 +**不做中断。** 那一期欠一个 seam 目前没有回答的决策：`kill()` 会把终态投递标为已上报，所以照 `kill()` 契约写出来的人类中断，会让模型一直以为它的任务还在跑。 **帧上不带输出水位。** 输出那一期的增量通道才是锚点字段该出现的地方；现在加就是一个没有读者的字段。 @@ -129,7 +129,7 @@ abstract onJobsChanged(listener: JobsChangedListener): () => void **终态行会堆积。** 注册表把已结算任务留到 owner 销毁，所以一个跑了很多后台命令的长会话会积出长列表。如果真的成为抱怨，给终态尾巴加上限是呈现层改动而非协议改动。 -**`stopping` 今天几乎不可达。** 只有模型的 `job_kill` 会产生它，所以这个状态会被渲染但在人类中断落地之前很少见到。现在就纳入联合类型，是因为把它留在外面会让那一期变成一次线路变更。 +**`stopping` 很少可见。** 只有模型的 `job_kill` 会产生它，所以这个状态会被渲染但在人类中断落地之前很少见到。现在就纳入联合类型，是因为把它留在外面会让那一期变成一次线路变更。 **一个运行中的 subagent 有两个入口。** 这是刻意接受的，且被限制在一次性后台委派这一种情况。如果实际用起来读着像噪声，修法是呈现层的——可以让目录行引用那个任务，而不是让任务列表隐藏这个 kind。 diff --git a/.agents/notes/implemented/feature/2026-08-08-windows-acl-restricted-token-sandbox.i18n.yaml b/.agents/notes/implemented/feature/2026-08-08-windows-acl-restricted-token-sandbox.i18n.yaml index e7438665da..2d2fc47c20 100644 --- a/.agents/notes/implemented/feature/2026-08-08-windows-acl-restricted-token-sandbox.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-08-windows-acl-restricted-token-sandbox.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-08-windows-acl-restricted-token-sandbox.md -2026-08-08-windows-acl-restricted-token-sandbox.md: 860ed18c8be2e0dab00631307e2c30fdcae12692 -2026-08-08-windows-acl-restricted-token-sandbox.zh.md: 6abbbeab49fc4eb3a1cb23cdbcc7084d5486a73a +2026-08-08-windows-acl-restricted-token-sandbox.md: f01c2f18cde78a561ccdd289a117f25916550ea4 +2026-08-08-windows-acl-restricted-token-sandbox.zh.md: 99e8a27f72544d01adb97d86c8397c562b171458 diff --git a/.agents/notes/implemented/feature/2026-08-08-windows-acl-restricted-token-sandbox.md b/.agents/notes/implemented/feature/2026-08-08-windows-acl-restricted-token-sandbox.md index 860ed18c8b..f01c2f18cd 100644 --- a/.agents/notes/implemented/feature/2026-08-08-windows-acl-restricted-token-sandbox.md +++ b/.agents/notes/implemented/feature/2026-08-08-windows-acl-restricted-token-sandbox.md @@ -28,7 +28,7 @@ An AppContainer token carries no ambient read access: every readable path must b ### Why not landstrip? -The [landstrip evaluation](../../rejected/feature/2026-07-26-evaluate-landstrip-for-windows-sandbox-rung.md) was rejected before implementation (not battle-tested; the in-house launcher plan won), and its Windows backend is AppContainer-shaped, inheriting the same arbitrary-read problem. +The landstrip evaluation was rejected before implementation (not battle-tested; the in-house launcher plan won), and its Windows backend is AppContainer-shaped, inheriting the same arbitrary-read problem. ## Consequences diff --git a/.agents/notes/implemented/feature/2026-08-08-windows-acl-restricted-token-sandbox.zh.md b/.agents/notes/implemented/feature/2026-08-08-windows-acl-restricted-token-sandbox.zh.md index 6abbbeab49..99e8a27f72 100644 --- a/.agents/notes/implemented/feature/2026-08-08-windows-acl-restricted-token-sandbox.zh.md +++ b/.agents/notes/implemented/feature/2026-08-08-windows-acl-restricted-token-sandbox.zh.md @@ -28,7 +28,7 @@ AppContainer 令牌没有环境读访问：每个可读路径都必须预先通 ### 为什么不选 landstrip？ -[landstrip 评估](../../rejected/feature/2026-07-26-evaluate-landstrip-for-windows-sandbox-rung.zh.md)在实现前已被否决（未经实战检验；自建 launcher 方案胜出），且其 Windows 后端是 AppContainer 形态，继承同样的任意路径读问题。 +landstrip 评估在实现前已被否决（未经实战检验；自建 launcher 方案胜出），且其 Windows 后端是 AppContainer 形态，继承同样的任意路径读问题。 ## 后果 diff --git a/.agents/notes/implemented/feature/2026-08-09-parallel-subagent-delegations.i18n.yaml b/.agents/notes/implemented/feature/2026-08-09-parallel-subagent-delegations.i18n.yaml index f116b7ac6d..6b942107c6 100644 --- a/.agents/notes/implemented/feature/2026-08-09-parallel-subagent-delegations.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-09-parallel-subagent-delegations.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-09-parallel-subagent-delegations.md -2026-08-09-parallel-subagent-delegations.md: 8601b997fbe67f7a3694e5963792ea9144fdd5f5 -2026-08-09-parallel-subagent-delegations.zh.md: d981388c8f9102b936fda650673fd4756d893333 +2026-08-09-parallel-subagent-delegations.md: 7e6f933749b3a65286ab4c428fc3e7d682e108ad +2026-08-09-parallel-subagent-delegations.zh.md: 1072697355a8a8a5d1b585f6d984063d9aca5617 diff --git a/.agents/notes/implemented/feature/2026-08-09-parallel-subagent-delegations.md b/.agents/notes/implemented/feature/2026-08-09-parallel-subagent-delegations.md index 8601b997fb..7e6f933749 100644 --- a/.agents/notes/implemented/feature/2026-08-09-parallel-subagent-delegations.md +++ b/.agents/notes/implemented/feature/2026-08-09-parallel-subagent-delegations.md @@ -24,7 +24,7 @@ Capacity stays where the scheduler note put it: `maxParallelToolCalls` caps one Package tests pin the classifier for both call forms. A gate test drives the registry directly with two children that each block until both have started, proving the half the declaration depends on: the tool body and provider start path tolerate concurrent dispatch — hidden serialization in that stack would deadlock instead of passing silently. A continuable gate holds two provider preparations at the same await, cancels one caller before publication, and proves that the cancelled child leaves no Agent or durable Session while its sibling reaches inbox acceptance and persists independently. The scheduling half, classification actually producing overlap, is owned by the classifier pin and the snapshot below. -The authored `subagent-parallel` snapshot pins the assembled-app transcript: one assistant message carries two subagent calls, the parent log records `tool/call, tool/call, tool/result, tool/result` (serial execution would interleave call/result pairs), and both children complete as separate sessions. Its twin delegations are deliberately identical: `dsh-llm-replay` binds child scripts by first-call order and the harvester orders children by `createdAt`, and neither is deterministic across concurrent children (the `XXX(concurrent-subagents)` marker), so only interchangeable twins replay race-free today. +The authored `subagent-parallel` snapshot pins the assembled-app transcript: one assistant message carries two subagent calls, the parent log records `tool/call, tool/call, tool/result, tool/result` (serial execution would interleave call/result pairs), and both children complete as separate sessions. Its twin delegations are deliberately identical: `dsh-llm-replay` binds child scripts by first-call order and the harvester orders children by `createdAt`, and neither is deterministic across concurrent children (the `XXX(concurrent-subagents)` marker), so only interchangeable twins replay deterministically. ## Alternatives considered diff --git a/.agents/notes/implemented/feature/2026-08-09-parallel-subagent-delegations.zh.md b/.agents/notes/implemented/feature/2026-08-09-parallel-subagent-delegations.zh.md index d981388c8f..1072697355 100644 --- a/.agents/notes/implemented/feature/2026-08-09-parallel-subagent-delegations.zh.md +++ b/.agents/notes/implemented/feature/2026-08-09-parallel-subagent-delegations.zh.md @@ -24,7 +24,7 @@ Status: implemented 包测试固定了两种调用形态的分类器。一个门控测试直接驱动注册表，其两个子 agent 各自阻塞，直到两者都已启动，以此证明该声明所依赖的那一半：工具体和提供方启动路径能容忍并发分发——这条栈中任何隐藏的串行化都会造成死锁，而不是静默通过。一个可继续门控测试让两项提供方准备停在同一个 await 上，在发布前取消其中一个调用方，并证明已取消的子 agent 不会留下 agent 或持久会话，而其同级则到达 inbox 接受状态并独立持久化。另一半（分类真正产生重叠执行）由分类器 pin 测试和下述快照负责。 -人工编写的 `subagent-parallel` 快照固定了组装后应用的 transcript（文本记录）：一条 assistant 消息携带两个 subagent 调用，父级日志记录为 `tool/call, tool/call, tool/result, tool/result`（串行执行会让调用/结果成对交错出现），两个子 agent 各自作为独立会话完成。其中的孪生委派刻意做成完全相同：`dsh-llm-replay` 按首次调用顺序绑定子脚本，harvester 按 `createdAt` 对子 agent 排序，二者在并发子 agent 之间都不具确定性（即 `XXX(concurrent-subagents)` 标记），因此目前只有可互换的孪生委派才能无竞态地回放。 +人工编写的 `subagent-parallel` 快照固定了组装后应用的 transcript（文本记录）：一条 assistant 消息携带两个 subagent 调用，父级日志记录为 `tool/call, tool/call, tool/result, tool/result`（串行执行会让调用/结果成对交错出现），两个子 agent 各自作为独立会话完成。其中的孪生委派刻意做成完全相同：`dsh-llm-replay` 按首次调用顺序绑定子脚本，harvester 按 `createdAt` 对子 agent 排序，二者在并发子 agent 之间都不具确定性（即 `XXX(concurrent-subagents)` 标记），因此只有可互换的孪生委派才能确定性回放。 ## 备选方案 diff --git a/.agents/notes/implemented/feature/2026-08-10-creator-guidance-introduce-cue.i18n.yaml b/.agents/notes/implemented/feature/2026-08-10-creator-guidance-introduce-cue.i18n.yaml deleted file mode 100644 index 08233cc4f0..0000000000 --- a/.agents/notes/implemented/feature/2026-08-10-creator-guidance-introduce-cue.i18n.yaml +++ /dev/null @@ -1,6 +0,0 @@ -# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each -# side as of the last confirmed-consistent state. Both languages carry equal authority; -# after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-10-creator-guidance-introduce-cue.md -2026-08-10-creator-guidance-introduce-cue.md: 888fee7b3def585ed3098fedcb7bc6169ee26a22 -2026-08-10-creator-guidance-introduce-cue.zh.md: d80260abd1995df1f95e3f24fefcb265bda64c11 diff --git a/.agents/notes/implemented/feature/2026-08-10-minimal-read-image-tool.i18n.yaml b/.agents/notes/implemented/feature/2026-08-10-minimal-read-image-tool.i18n.yaml index dcd01fc6d3..b0c70c4df4 100644 --- a/.agents/notes/implemented/feature/2026-08-10-minimal-read-image-tool.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-10-minimal-read-image-tool.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-10-minimal-read-image-tool.md -2026-08-10-minimal-read-image-tool.md: a43e53d70e98bac7a50aa6bbabbb1e177237df01 -2026-08-10-minimal-read-image-tool.zh.md: a94e4b296425ad50876b0b45a689442c896a85a1 +2026-08-10-minimal-read-image-tool.md: 19306a35fe709a04d94090a62056575b4d51f7bc +2026-08-10-minimal-read-image-tool.zh.md: c7562c433e909d1f81361c0ced56318795e6469e diff --git a/.agents/notes/implemented/feature/2026-08-10-minimal-read-image-tool.md b/.agents/notes/implemented/feature/2026-08-10-minimal-read-image-tool.md index a43e53d70e..19306a35fe 100644 --- a/.agents/notes/implemented/feature/2026-08-10-minimal-read-image-tool.md +++ b/.agents/notes/implemented/feature/2026-08-10-minimal-read-image-tool.md @@ -6,28 +6,27 @@ English | [中文](2026-08-10-minimal-read-image-tool.zh.md) ## Problem -The multimodal attachment work gave user uploads a complete durable path — bytes committed to the content-addressed attachment store before the owning `user/message`, an `ImageBlock` carrying only the `sha256:` reference, and the pi-ai route re-reading verified bytes per request — but the model itself had no way to look at an image on disk. `read` rejects binary content by contract, so an agent asked about a screenshot or a rendered chart either failed or shelled out to lossy workarounds. A first standalone attempt (PR #598) solved this together with loop-level route scoping: an `agent/request-ready` extension point publishing exact-model modalities before assembly, per-route schema/guidance visibility, and a reversible `image-placeholder-v1` history projection so text routes could continue over placeholder text. That design worked but coupled a tool to new agent-loop machinery, three new session-log concepts, and per-step registration churn — far more surface than the capability needs. +The multimodal attachment work gave user uploads a complete durable path, but the model itself had no way to inspect an image on disk. `read` rejects binary content by contract, so an agent asked about a screenshot or rendered chart either failed or used a lossy workaround. A standalone attempt in PR #598 combined the tool with loop-level route scoping, per-route schema visibility, and new session-log concepts. Those features were not required to publish a logged image tool result. ## Decision -Ship the smallest tool that loads an image into the next request's context, entirely over existing seams; the withdrawn PR #598 design is the explicit counter-example this note records. +Both image-reading operations live in `dsh-tool-fs` and publish ordinary logged tool results over existing extension points. -- **`read_image` lives in `dsh-tool-fs`** beside `read`/`write`/`edit`. Extension selects the declared PNG/JPEG/WebP/GIF media type; the attachment store's magic-byte and pixel validation stays authoritative. Bytes travel `ctx.fs.stat` → bounded `ctx.fs.readBytes` → `ctx.attachments.saveImage` → `fs/observed`, and the tool result is the metadata envelope plus a real `ImageBlock` — `ToolResultBlock.content` already admits image blocks, the pi-ai adapter already renders them, and the Web host's model-switch guard already scans tool results, so nothing downstream changes. +- **`read_image` reads a filesystem path.** Extension selects the declared PNG/JPEG/WebP/GIF media type; the attachment store's magic-byte and pixel validation stays authoritative. Bytes travel `ctx.fs.stat` → bounded `ctx.fs.readBytes` → `ctx.attachments.saveImage` → `fs/observed`. The tool result contains metadata and an `ImageBlock`. - **`FileSystem.readBytes(target, signal, maxBytes)`** is a new required provider primitive: the byte bound lives at the seam so no backend can buffer an unbounded file, with the stat-size short-circuit and a one-byte-past-cap stream guard against post-stat growth (`FS_TOO_LARGE`). -- **Registration is composition-conditional, execution is route-gated.** The tool registers only under `ctx.inject(['attachments'], …)` — no store, no tool. At execution, before any I/O, the strict gate resolves the calling route (latest `request/header` config, falling back to agent options) through `ctx.llm.resolveModelInfo` and requires `image` in `inputModalities`; unknown capability refuses. A refusal is a plain `isError` result, so a text route's durable history never acquires an image block and the session cannot brick its own route. +- **Registration is composition-conditional, execution is route-gated.** The tools register only under `ctx.inject(['attachments'], …)`. Before I/O, the strict gate resolves the calling route through `ctx.llm.resolveModelInfo` and requires `image` in `inputModalities`; unknown capability refuses. A text-only route can still consume prior durable images because the shared LLM runtime projects them to placeholders at request assembly. - **Code Mode forwards the image out-of-band**: a nested dispatch returns the canonical value (execution-local, no image block) and defers a `user`-role context message carrying the envelope and image, so the picture still reaches the next request. -- **llm-replay models may declare `inputModalities`**, which is what lets the two keyless ACP snapshots pin both sides of the gate — the sha256-referenced success on an image-capable replay route and the verbatim refusal on a text-only one. +- **llm-replay models may declare `inputModalities`**, which lets keyless ACP snapshots cover the image-capable result and the text-only refusal. ## Alternatives considered -- **PR #598's route-scoped design** (request-ready seam, per-route schema/guidance visibility, reversible history projection) — withdrawn in favor of this note's shape. What it bought: text routes could keep running after images entered history, and the tool disappeared from prompts where it cannot succeed. What it cost: agent-loop changes, three new durable concepts (`agent/request-ready`, `messageProjection`, availability notices), and registration that churned per step. The capability itself — see an image on the next request — never needed any of it. If per-route projection becomes a real requirement, that PR's history is the reference implementation. +- **PR #598's route-scoped design** used a request-ready extension point, per-route schema visibility, reversible projection, and three durable concepts. Shared LLM request projection now handles text-only routes without putting tool registration or session formats into agent-loop. - **`agent.inject()` instead of the image-bearing tool result** — routes the image around the tool result as a separate injected user message. Rejected: the image *is* the tool's result; splitting them adds a second logged message with no gain, and the tool-result path already works end to end. - **Magic-byte sniffing instead of extension declaration** — sniffing duplicates detection the attachment store already owns (sharp-backed, authoritative). The extension is only a *declaration*; a mismatch fails closed with a rename remedy rather than being silently accepted, which also keeps the model's mental map (file name ↔ content) honest. - **Registering unconditionally and failing on a missing store** — rejected; a deployment without an attachment store cannot ever satisfy the tool, so its schema would be a standing lie. The route gate, by contrast, is per-call state and correctly lives at the execution boundary. ## Consequences -- A text-only route refuses instead of degrading: no placeholder projection means no delegated-viewing story here — that is deliberately the next PR (subagent image readback rebuilt on the current subagent seams). -- The route gate races a concurrent model switch; the Web host's image-aware switch guard covers its surface, and other front doors own their equivalent. Recorded as a tool-fs Known Limitation. -- Repeated image results accumulate request-token cost until compaction; content addressing deduplicates bytes only. +- The tools refuse execution on a text-only route, while existing images in session history are represented by request-local placeholders. +- Repeated image results accumulate request cost until request projection or compaction removes them; content addressing deduplicates durable bytes. - The tool-result card renders the durable reference, not pixels; inline preview is deferred to the UI packages. diff --git a/.agents/notes/implemented/feature/2026-08-10-minimal-read-image-tool.zh.md b/.agents/notes/implemented/feature/2026-08-10-minimal-read-image-tool.zh.md index a94e4b2964..c7562c433e 100644 --- a/.agents/notes/implemented/feature/2026-08-10-minimal-read-image-tool.zh.md +++ b/.agents/notes/implemented/feature/2026-08-10-minimal-read-image-tool.zh.md @@ -6,28 +6,27 @@ Status: implemented ## 问题 -多模态附件工作为用户上传建立了完整的持久路径：字节在所属 `user/message` 之前提交到内容寻址的附件存储，`ImageBlock` 只携带 `sha256:` 引用，pi-ai 路由在每次请求时重新读取并校验字节。但模型自己没有查看磁盘图像的手段。`read` 按约定拒绝二进制内容，因此被问到截图或渲染图表的 agent 要么失败，要么退到有损的变通做法。第一次独立尝试（PR #598）把这个问题与循环级路由作用域一起解决：新增在组装前发布确切模型模态的 `agent/request-ready` 扩展点、按路由控制 schema／指导可见性，以及可逆的 `image-placeholder-v1` 历史投影让文本路由能在占位符上继续。该设计可行，但让一个工具耦合了新的 agent-loop 机制、三个新的会话日志概念和每步的注册变动，远超这项能力本身的需要。 +多模态附件工作为用户上传建立了完整的持久路径，但模型无法查看磁盘图片。`read` 按约定拒绝二进制内容，因此被问到截图或渲染图表的 agent 要么失败，要么使用有损的变通方法。PR #598 的独立尝试把工具与循环级路由作用域、按路由控制 schema 可见性和新的会话日志概念放在一起。这些能力不是发布一条带图片且已记录的工具结果所必需的。 ## 决定 -只交付能把图像载入下一次请求上下文的最小工具，完全建立在既有 seam 之上；撤回的 PR #598 设计是本记录明确保留的反例。 +两个图片读取操作都放在 `dsh-tool-fs`，通过现有扩展点发布普通的持久工具结果。 -- **`read_image` 放在 `dsh-tool-fs`**，与 `read`/`write`/`edit` 并列。扩展名选择声明的 PNG/JPEG/WebP/GIF 媒体类型；附件存储的魔数与像素校验保持权威。字节沿 `ctx.fs.stat` → 有界 `ctx.fs.readBytes` → `ctx.attachments.saveImage` → `fs/observed` 流动，工具结果是元数据信封加真正的 `ImageBlock`——`ToolResultBlock.content` 本就允许图像块，pi-ai 适配器本就会渲染它们，Web 宿主的模型切换防护本就会扫描工具结果，下游无需任何改动。 +- **`read_image` 读取文件系统路径。** 扩展名选择声明的 PNG/JPEG/WebP/GIF 媒体类型，附件存储的魔数与像素校验保持权威。字节沿 `ctx.fs.stat` → 有界 `ctx.fs.readBytes` → `ctx.attachments.saveImage` → `fs/observed` 流动。工具结果包含元数据和一个 `ImageBlock`。 - **`FileSystem.readBytes(target, signal, maxBytes)`** 是新的必备提供方原语：字节上限放在 seam 上，任何后端都无法无界缓冲文件；stat 大小先短路，随后的流最多多读一个字节以防 stat 之后的增长（`FS_TOO_LARGE`）。 -- **注册随组合条件挂载，执行按路由门禁。** 工具只在 `ctx.inject(['attachments'], …)` 作用域内注册——没有存储就没有工具。执行时在任何 I/O 之前，严格门禁通过 `ctx.llm.resolveModelInfo` 解析调用路由（最新 `request/header` 配置，缺失时回退到 agent 选项），要求 `inputModalities` 包含 `image`；能力未知即拒绝。拒绝是普通的 `isError` 结果，因此文本路由的持久历史绝不会出现图像块，会话不会毁掉自己的路由。 +- **注册随组合条件挂载，执行按路由门禁。** 工具只在 `ctx.inject(['attachments'], …)` 作用域内注册。执行时在 I/O 之前通过 `ctx.llm.resolveModelInfo` 解析调用路由，并要求 `inputModalities` 包含 `image`；能力未知即拒绝。纯文本路由仍可使用此前的持久图片，因为共享 LLM 运行时会在请求组装时把图片投影为占位符。 - **Code Mode 以带外方式转发图像**：嵌套分派返回规范值（仅限本次执行，不含图像块），并延迟提交一条携带信封和图像的 `user` 角色上下文消息，图片仍会到达下一次请求。 -- **llm-replay 模型可以声明 `inputModalities`**，这正是两个 keyless ACP 快照能钉住门禁两侧的原因：图像路由上以 sha256 引用的成功结果，和纯文本路由上逐字的拒绝。 +- **llm-replay 模型可以声明 `inputModalities`**，因此 keyless ACP 快照可以覆盖支持图片的结果和纯文本拒绝。 ## 考虑过的替代方案 -- **PR #598 的路由作用域设计**（request-ready 扩展点、按路由的 schema／指导可见性、可逆历史投影）——被本记录的形态取代后撤回。它换来的是：图像进入历史后文本路由仍能运行，工具在注定失败的提示词里消失。它付出的是：改动 agent-loop、三个新的持久概念（`agent/request-ready`、`messageProjection`、可用性通知）和每步变动的注册。而这项能力本身——下一次请求看到图像——从不需要这些。如果按路由投影将来成为真实需求，该 PR 的历史就是参考实现。 +- **PR #598 的路由作用域设计**使用 request-ready 扩展点、按路由控制 schema 可见性、可逆投影和三个持久概念。共享 LLM 请求投影现在可以处理纯文本路由，无需把工具注册或会话格式放进 agent-loop。 - **用 `agent.inject()` 代替带图像的工具结果**——把图像绕过工具结果，作为单独注入的用户消息。拒绝：图像就是工具的结果；拆开只会多一条无收益的日志消息，而工具结果路径本就端到端可用。 - **用魔数嗅探代替扩展名声明**——嗅探重复了附件存储已拥有的检测（基于 sharp，权威）。扩展名只是声明；不匹配时按改名修复提示失败关闭，而不是被静默接受，这也让模型对文件名与内容的对应保持诚实。 - **无条件注册、缺存储时执行报错**——拒绝；没有附件存储的部署永远无法满足该工具，其 schema 会是常态谎言。相反，路由门禁是逐调用状态，正确的位置就是执行边界。 ## 后果 -- 纯文本路由得到拒绝而不是降级：没有占位符投影意味着这里没有委托查看的方案——那有意留给下一个 PR（基于当前 subagent seam 重建的 subagent image readback）。 -- 路由门禁与并发模型切换存在竞态；Web 宿主的图像感知切换防护覆盖其表面，其他前端拥有各自的等价防护。已记入 tool-fs 的已知限制。 -- 重复的图像结果在压缩之前持续累积请求 token 成本；内容寻址只去重字节。 +- 工具在纯文本路由上拒绝执行，而会话历史中已经存在的图片会由请求期占位符表示。 +- 重复的图片结果会累积请求成本，直到请求投影或压缩将其移除；内容寻址只去重持久字节。 - 工具结果卡片渲染持久引用而非像素；内嵌预览延后到 UI 包处理。 diff --git a/.agents/notes/implemented/feature/2026-08-10-web-plugin-configuration.i18n.yaml b/.agents/notes/implemented/feature/2026-08-10-web-plugin-configuration.i18n.yaml index 496cec7c35..29dfe4c8aa 100644 --- a/.agents/notes/implemented/feature/2026-08-10-web-plugin-configuration.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-10-web-plugin-configuration.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-10-web-plugin-configuration.md -2026-08-10-web-plugin-configuration.md: 218d5ed4536c489f89cb53c62c457a988e451b7e -2026-08-10-web-plugin-configuration.zh.md: a1da262f728c823feb94ac60ad785379bdf49230 +2026-08-10-web-plugin-configuration.md: 8b8d231fd2920612c7d9d8c146253c1cb6e1c8a0 +2026-08-10-web-plugin-configuration.zh.md: 70a3b68730a750f03187e5a17e31765b36b8c879 diff --git a/.agents/notes/implemented/feature/2026-08-10-web-plugin-configuration.md b/.agents/notes/implemented/feature/2026-08-10-web-plugin-configuration.md index 218d5ed453..8b8d231fd2 100644 --- a/.agents/notes/implemented/feature/2026-08-10-web-plugin-configuration.md +++ b/.agents/notes/implemented/feature/2026-08-10-web-plugin-configuration.md @@ -49,4 +49,4 @@ Two costs are real. Adding a fourth plugin still requires an entry in the apipro The bash and pwsh executors now expose `config` as a getter over a source thunk rather than a readonly field. Every read site was already per-call, so nothing else changed, but a subclass that captured `this.config` at construction would silently pin the composition entry. -`verify-cordis-config` gained one check, paid for by this branch: merging master's rename of the client manifest field (`dshClient` → `dsh.client`) left this package declaring the old name, and the whole section vanished from the browser with no error anywhere — the row composed, the empty node half activated, and the browser roster scan simply never matched it. Nothing could catch that, because the composition file cannot tell a surface plugin from a Host plugin: the difference lives in the manifest. The gate now requires a `packages/client` package's `./client` export and its `dsh.client` declaration to agree in both directions. The check is scoped to that group because a Host package's `./client` export is the typed wire face its browser consumers import, not a plugin the roster serves. +`verify-cordis-config` requires every `packages/client` package's `./client` export and `dsh.client` declaration to agree in both directions. Without that check, a stale manifest field can leave the composition row and empty node half active while the browser roster silently omits the package. The check is scoped to that group because a Host package's `./client` export is the typed wire face its browser consumers import, not a plugin the roster serves. diff --git a/.agents/notes/implemented/feature/2026-08-10-web-plugin-configuration.zh.md b/.agents/notes/implemented/feature/2026-08-10-web-plugin-configuration.zh.md index a1da262f72..70a3b68730 100644 --- a/.agents/notes/implemented/feature/2026-08-10-web-plugin-configuration.zh.md +++ b/.agents/notes/implemented/feature/2026-08-10-web-plugin-configuration.zh.md @@ -49,4 +49,4 @@ Status: implemented bash 与 pwsh 执行器现在把 `config` 暴露为 source thunk 之上的 getter，而不再是 readonly 字段。所有读取点本就是按次读取，因此别无变化；但若某个子类在构造期捕获 `this.config`，就会悄然把组装条目钉死。 -`verify-cordis-config` 新增一项检查，代价由本分支付过：合并 master 对客户端清单字段的重命名（`dshClient` → `dsh.client`）后，本包仍声明旧名，于是整个分区从浏览器上消失，且任何地方都不报错——行照常组装、空的 node 半侧照常激活，只是浏览器 roster 扫描永远匹配不到它。这一点无从被既有门禁发现，因为组装文件区分不了 surface 插件与 Host 插件：差别在清单里。现在门禁要求 `packages/client` 包的 `./client` 导出与 `dsh.client` 声明双向一致。之所以只限这一组：Host 包的 `./client` 导出是给浏览器消费方 import 的类型化 wire face，不是 roster 要服务的插件。 +`verify-cordis-config` 要求每个 `packages/client` 包的 `./client` 导出与 `dsh.client` 声明双向一致。缺少这项检查时，陈旧的清单字段可能让组合行与空的 node 半侧保持激活，而浏览器 roster 会悄然漏掉该包。检查只限这一组，因为 Host 包的 `./client` 导出是供浏览器消费方 import 的类型化 wire face，不是 roster 要服务的插件。 diff --git a/.agents/notes/implemented/feature/2026-08-10-web-session-log-export.i18n.yaml b/.agents/notes/implemented/feature/2026-08-10-web-session-log-export.i18n.yaml index d79eaafd04..3d120f1027 100644 --- a/.agents/notes/implemented/feature/2026-08-10-web-session-log-export.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-10-web-session-log-export.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-10-web-session-log-export.md -2026-08-10-web-session-log-export.md: 24703bd5c98a91bf8708ae243ef7a44df4afb8f1 -2026-08-10-web-session-log-export.zh.md: 9595ea25df927e49b34cde1ba83d6e1720db5095 +2026-08-10-web-session-log-export.md: e64de4ecd564bf585ec857546913828a87ad1279 +2026-08-10-web-session-log-export.zh.md: 2ef377b4bb3c98f1935e67a1619bbcc5ed1789ef diff --git a/.agents/notes/implemented/feature/2026-08-10-web-session-log-export.md b/.agents/notes/implemented/feature/2026-08-10-web-session-log-export.md index 24703bd5c9..e64de4ecd5 100644 --- a/.agents/notes/implemented/feature/2026-08-10-web-session-log-export.md +++ b/.agents/notes/implemented/feature/2026-08-10-web-session-log-export.md @@ -13,7 +13,7 @@ The Trajectory view had no way to hand a debugging artifact to a human: the raw - **The export is a host-only download, not an RPC**: `GET /api/session.export?sessionId=…&includeDescendants=true` streams one ZIP attachment. Every file is a session's **stored artifact text verbatim**: `readRaw` on the persistence service reads the backend's own durable bytes (the JSONL backend decodes its physical zstd frames, or returns plaintext) — never a reconstruction from parsed events, so packed-chunk rows, key order, and line breaks survive byte-for-byte — under its original base name (`session.jsonl` at the root, `subagents//session.jsonl` for descendants). Compression runs on the host with fflate's streaming `Zip`/`ZipDeflate` API at validated `sessionExportCompressionLevel` 0–9 (default 6), letting deployments trade CPU and latency against archive size; each entry is deflated in bounded chunks as it is produced, so the response is chunked as it is generated and the host never holds the whole archive in one buffer (at most one descendant's artifact text beyond the preloaded root). At the 64 KiB response byte high-water mark, production waits for consumer pull to restore capacity; fflate's synchronous callback can add at most one bounded input push beyond that queue bound. No manifest is written — every file is byte-identical to the durable artifact and self-describing through its own header line. - **Error vocabulary is HTTP-native**: missing services → 500, a backend without per-session raw artifacts → 501, missing root session → 404 (all decided before any byte streams), and a descendant without a stored artifact → the stream errors (fail-loud, never silent under-export). Request abort remains cancellation instead of being rewritten as 500; request and response-consumer cancellation converge on the producer signal, which reaches lineage, persistence, and attachment reads and terminates the active compressor. The carrier (`toFetchHandler`) already applies the `/api` trust fence; the GET branch sits beside the existing SSE GET routes, and `ApiProxy.downloads.sessionLog` (host-only, no wire envelope, absent from `IApiClient`) implements it. - **The UI just downloads**: browser consumers may issue a bodyless `HEAD` preflight for preparation errors, then hand the GET endpoint to the browser's native download manager, so JavaScript never buffers the ZIP. The `session.log` RPC that an earlier iteration shipped was removed — the download endpoint is its only consumer, and the repo rule is no public interface without a current owner. The client bundle carries no archive implementation. -- The current Header and `/export` consumers are defined by the [Web export command and dialog decision](2026-08-11-web-export-command-and-dialog.md). +- The current Header and `/export` consumers are defined by the [session-log export package contract](../../../../packages/session-query/session-log-export/README.md). ## Alternatives considered diff --git a/.agents/notes/implemented/feature/2026-08-10-web-session-log-export.zh.md b/.agents/notes/implemented/feature/2026-08-10-web-session-log-export.zh.md index 9595ea25df..2ef377b4bb 100644 --- a/.agents/notes/implemented/feature/2026-08-10-web-session-log-export.zh.md +++ b/.agents/notes/implemented/feature/2026-08-10-web-session-log-export.zh.md @@ -13,7 +13,7 @@ Trajectory 视图没有任何方式把调试工件交到人手里：原始会话 - **导出是宿主侧的下载面，不是 RPC**：`GET /api/session.export?sessionId=…&includeDescendants=true` 流式返回一个 ZIP 附件。每个文件都是会话**存储工件的逐字原文**：持久化服务新增的 `readRaw` 读取后端自己的持久化字节（jsonl 后端解码其物理 zstd 帧，或直接返回明文）——绝非从解析后事件重建，因此 chunk 打包、键序、换行全部逐字节保留——放在其原始基础文件名下（根为 `session.jsonl`，子代理为 `subagents//session.jsonl`）。压缩在宿主侧使用 fflate 流式 `Zip`/`ZipDeflate` API 和已验证的 `sessionExportCompressionLevel` 0–9（默认 6），使部署可以在 CPU／延迟与归档大小之间取舍；每个条目按有界分块边产出边压缩，响应随生成分块写出，宿主从不把整个归档放进单个缓冲区（除预载的根外，最多同时持有一条后代的工件文本）。到达 64 KiB 响应字节高水位后，生产会等待 Consumer pull 恢复容量；fflate 的同步回调最多只会在该队列界限外再增加一次有界输入 push。不写清单——每个文件都与持久化工件逐字节一致，并通过自身 header 行自描述。 - **错误词汇是 HTTP 原生的**：服务缺失 → 500，后端不提供每会话原始工件 → 501，根会话缺失 → 404（三者都在任何字节流出前判定），后代缺少存储工件 → 流失败（fail-loud，绝不静默少导出）。请求中止会保持取消语义而不会改写成 500；请求取消与响应 Consumer 取消汇合到生产者 signal，该 signal 会传到血缘、持久化与附件读取，并终止活跃压缩器。载体（`toFetchHandler`）已对 `/api` 应用信任围栏；GET 分支与既有 SSE GET 路由并列，由 `ApiProxy.downloads.sessionLog`（host-only、无 wire 信封、不在 `IApiClient` 上）实现。 - **UI 只负责下载**：浏览器 Consumer 可以先发出不读取 body 的 `HEAD` 预检以取得准备阶段错误，再把 GET 端点交给浏览器原生下载管理器，因此 JavaScript 不会缓冲 ZIP。早先迭代发布的 `session.log` RPC 已删除——下载端点是它唯一的消费者，仓库规则是不留无当前所有者的公共接口。客户端 bundle 不包含任何归档实现。 -- 当前 Header 与 `/export` Consumer 由 [Web 导出命令与弹窗决策](2026-08-11-web-export-command-and-dialog.zh.md)定义。 +- 当前 Header 与 `/export` Consumer 由 [Session 日志导出包约定](../../../../packages/session-query/session-log-export/README.zh.md)定义。 ## 考虑过的替代方案 diff --git a/.agents/notes/implemented/feature/2026-08-11-collapsible-ask-user-question-card.i18n.yaml b/.agents/notes/implemented/feature/2026-08-11-collapsible-ask-user-question-card.i18n.yaml deleted file mode 100644 index e403530fec..0000000000 --- a/.agents/notes/implemented/feature/2026-08-11-collapsible-ask-user-question-card.i18n.yaml +++ /dev/null @@ -1,6 +0,0 @@ -# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each -# side as of the last confirmed-consistent state. Both languages carry equal authority; -# after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-11-collapsible-ask-user-question-card.md -2026-08-11-collapsible-ask-user-question-card.md: 5c7e62749e63a6042285b79751c400ba09038b49 -2026-08-11-collapsible-ask-user-question-card.zh.md: 5f4b5851e4b595e634841bf87827db70fe928afb diff --git a/.agents/notes/implemented/feature/2026-08-11-message-feedback-web-surface.i18n.yaml b/.agents/notes/implemented/feature/2026-08-11-message-feedback-web-surface.i18n.yaml index 83ed0baf8f..b67c1256e5 100644 --- a/.agents/notes/implemented/feature/2026-08-11-message-feedback-web-surface.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-11-message-feedback-web-surface.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-11-message-feedback-web-surface.md -2026-08-11-message-feedback-web-surface.md: 762137a6ab179dcbf0b7019cd0ee0163829bd767 -2026-08-11-message-feedback-web-surface.zh.md: 4ed2f61879a2880402300a3150793370d090d2c0 +2026-08-11-message-feedback-web-surface.md: a1fbce695ffa8e513e85842b50f629afde88ac01 +2026-08-11-message-feedback-web-surface.zh.md: 3551cc3b4a1956451886721a4dce712cf038066d diff --git a/.agents/notes/implemented/feature/2026-08-11-message-feedback-web-surface.md b/.agents/notes/implemented/feature/2026-08-11-message-feedback-web-surface.md index 762137a6ab..a1fbce695f 100644 --- a/.agents/notes/implemented/feature/2026-08-11-message-feedback-web-surface.md +++ b/.agents/notes/implemented/feature/2026-08-11-message-feedback-web-surface.md @@ -46,7 +46,7 @@ Toggle semantics keep the two verbs honest: re-clicking the recorded rating call The Web GUI records per-message ratings and notes. #1326's user-visible half now exists; the issue was reopened because the backend merge had closed it while no entry point existed. -`AssistantMessageNode.messageId` is optional, so every existing reader compiles unchanged, but any future consumer must handle absence rather than assume a finalized message. The two parallel materializers remain a duplication hazard: a third view that builds this node must remember to copy the id, and nothing enforces it. Only the chat view renders controls today, even though trajectory and waterfall nodes now carry the same id. +`AssistantMessageNode.messageId` is optional, so every existing reader compiles unchanged, but any future consumer must handle absence rather than assume a finalized message. The two parallel materializers remain a duplication hazard: a third view that builds this node must remember to copy the id, and nothing enforces it. Only the chat view renders controls, even though trajectory and waterfall nodes now carry the same id. Feedback stays invisible to the model — the sidecar reaches neither the Session log, model context, nor telemetry — so the package's Model Experience is an audited `none` entry rather than a structured block. diff --git a/.agents/notes/implemented/feature/2026-08-11-message-feedback-web-surface.zh.md b/.agents/notes/implemented/feature/2026-08-11-message-feedback-web-surface.zh.md index 4ed2f61879..3551cc3b4a 100644 --- a/.agents/notes/implemented/feature/2026-08-11-message-feedback-web-surface.zh.md +++ b/.agents/notes/implemented/feature/2026-08-11-message-feedback-web-surface.zh.md @@ -46,7 +46,7 @@ list 读取被推迟到首次 hover 或 focus，而不是在 mount 时触发， Web GUI 可以记录逐条消息的评价与备注。#1326 中用户可见的那一半现在存在了；该 Issue 之所以被重开，是因为后端合并在没有任何入口存在的情况下关闭了它。 -`AssistantMessageNode.messageId` 是可选的，因此所有既有读取方无需改动即可编译，但任何将来的消费方都必须处理缺失，而不能假定消息已完成。两个并行的物化点仍是重复隐患：第三个构造该节点的视图必须记得复制该 id，而没有任何机制强制这一点。今天只有 chat 视图渲染控件，尽管 trajectory 与 waterfall 节点现在携带同一个 id。 +`AssistantMessageNode.messageId` 是可选的，因此所有既有读取方无需改动即可编译，但任何将来的消费方都必须处理缺失，而不能假定消息已完成。两个并行的物化点仍是重复隐患：第三个构造该节点的视图必须记得复制该 id，而没有任何机制强制这一点。只有 chat 视图渲染控件，尽管 trajectory 与 waterfall 节点现在携带同一个 id。 反馈对模型保持不可见——该 sidecar 既不进入 Session 日志、也不进入模型上下文与 telemetry——因此该包的 Model Experience 是一条经审计的 `none` 条目，而不是结构化区块。 diff --git a/.agents/notes/implemented/feature/2026-08-11-web-export-command-and-dialog.i18n.yaml b/.agents/notes/implemented/feature/2026-08-11-web-export-command-and-dialog.i18n.yaml deleted file mode 100644 index 08b086f3f4..0000000000 --- a/.agents/notes/implemented/feature/2026-08-11-web-export-command-and-dialog.i18n.yaml +++ /dev/null @@ -1,6 +0,0 @@ -# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each -# side as of the last confirmed-consistent state. Both languages carry equal authority; -# after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-11-web-export-command-and-dialog.md -2026-08-11-web-export-command-and-dialog.md: d28925500a45111d348b6151df9d4c62cc6de54b -2026-08-11-web-export-command-and-dialog.zh.md: a9a9c4a5cc019a3242561e0cc5f8445625c7cb86 diff --git a/.agents/notes/implemented/feature/2026-08-12-web-image-intake-and-limits-alignment.i18n.yaml b/.agents/notes/implemented/feature/2026-08-12-web-image-intake-and-limits-alignment.i18n.yaml index 0720d5d9ee..3c2be099df 100644 --- a/.agents/notes/implemented/feature/2026-08-12-web-image-intake-and-limits-alignment.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-12-web-image-intake-and-limits-alignment.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-12-web-image-intake-and-limits-alignment.md -2026-08-12-web-image-intake-and-limits-alignment.md: 00cf7ea99d63e848c4b5839da1d97d94c9fb8464 -2026-08-12-web-image-intake-and-limits-alignment.zh.md: 7bf7f3621d6d305baf8e7c1c060bbc5810f28b77 +2026-08-12-web-image-intake-and-limits-alignment.md: 0bb8cadc8db4b4c28cf311bc9420c32744e173fb +2026-08-12-web-image-intake-and-limits-alignment.zh.md: fafa7652756554a54a0a0952e843bf5f4b81b00d diff --git a/.agents/notes/implemented/feature/2026-08-12-web-image-intake-and-limits-alignment.md b/.agents/notes/implemented/feature/2026-08-12-web-image-intake-and-limits-alignment.md index 00cf7ea99d..0bb8cadc8d 100644 --- a/.agents/notes/implemented/feature/2026-08-12-web-image-intake-and-limits-alignment.md +++ b/.agents/notes/implemented/feature/2026-08-12-web-image-intake-and-limits-alignment.md @@ -16,7 +16,7 @@ The second alignment step for issue #2248, after the [attachment display note](2 **History thumbnails (DeepSeek Chat rules).** A message's lone image renders at 240px on its long edge with the displayed ratio clamped to [0.25, 4], cropped by `cover` with the anchor at the top of very tall images and the left of very wide ones, never upscaled; several images render as fixed 64px square tiles in one wrapping row (10px gap, user messages right-aligned). Consecutive assistant `image` blocks merge into one gallery so they tile instead of each opening a one-image row. -**Limits aligned and projected.** Defaults are 20 images / 3.5 MiB per image / 100 MiB aggregate (`attachment-local`), with the HTTP carrier cap raised to one shared `DEFAULT_MAX_REQUEST_BODY_BYTES = 160 MiB` (http-bridge, previously two independent 32 MiB literals) to satisfy the load-time capacity assertion (aggregate × 4/3 + headroom ≈ 134.3 MiB). Consumer products cluster at 10–20 attachments (ChatGPT 10, Gemini 10, Claude 20; DeepSeek Chat's 50 is the outlier), and a vision-model image costs roughly 1300–4800 tokens, so 50 images can fill a 200k context in one message. Including base64 padding, a 3.5 MiB encoded file occupies at most 4.67 MiB and leaves 0.33 MiB below a 5 MiB route check. Deployments using only routes with larger limits can override it. A 512 MiB aggregate cannot pass this transport because base64-in-JSON would need a single JSON string past V8's ~512 MiB string ceiling. The limits reach clients as the `imageLimits` session projection — a constant-per-boot unit (`apply` returns the same state reference, so baselines alone carry it and no change frames exist) registered by **apiproxy**, not the attachment Service Definition: `dsh-llm` depends on `dsh-attachment` (`ImageBlock` → `ImageAttachmentRef`), so the seam package referencing `dsh-session-projection` (whose graph reaches `dsh-llm` through `dsh-session`) closes a project-reference cycle, and the per-message count/aggregate rules the value describes are the proxy's own admission checks anyway. The `SessionProjectionMap` merge rides the proxy's sessions wire-contract file, which every client program already includes through the carrier's type re-exports. +**Limits aligned and projected.** Intake defaults are 20 images, 32 MiB per source, 100 MiB aggregate source bytes, 100 million decoded pixels, and 16384px per source side. The attachment backend prepares a separate durable master with a 2048px long edge and 4 MiB safety cap. Model requests have their own route-specific pixel and encoded-byte budgets, so source admission does not use provider request limits. The HTTP carrier uses one shared `DEFAULT_MAX_REQUEST_BODY_BYTES = 160 MiB` to satisfy the load-time capacity assertion for the 100 MiB aggregate after base64 and envelope expansion. A 512 MiB aggregate cannot pass this transport because base64-in-JSON would require a JSON string near V8's string-size limit. The intake limits reach clients as the `imageLimits` session projection, a constant-per-boot unit registered by **apiproxy** rather than the attachment Service Definition. `dsh-llm` depends on `dsh-attachment`, while `dsh-session-projection` reaches `dsh-llm` through `dsh-session`; registering the projection in the seam package would create a project-reference cycle. The per-message count and aggregate rules are also enforced by the proxy. The `SessionProjectionMap` merge remains in the proxy sessions wire file, which clients already consume through carrier type re-exports. **Intake pre-check and error copy.** Both intake gestures converge on one `intakeImages` wrapper in InputBar that checks count, per-image bytes, and aggregate bytes against the projection before `addImages`: a violating batch is refused whole (DeepSeek Chat semantics) with an immediate banner naming the limit — no submit-time rollback theater. The host checks stay as the backstop for callers that bypass the composer. Banner copy follows one principle the user set: reasons a user can act on (model without vision, count, size, resolution, format — now a positive list of supported formats instead of echoing the rejected MIME type) get product sentences naming the way out; reasons they cannot act on (corrupt base64, lost references, read failures) fold into one send-failed sentence that keeps the reason code, because the product currently faces developers and a reportable code beats a dead end. Non-attachment error codes keep the raw message + code presentation. diff --git a/.agents/notes/implemented/feature/2026-08-12-web-image-intake-and-limits-alignment.zh.md b/.agents/notes/implemented/feature/2026-08-12-web-image-intake-and-limits-alignment.zh.md index 7bf7f3621d..fafa765275 100644 --- a/.agents/notes/implemented/feature/2026-08-12-web-image-intake-and-limits-alignment.zh.md +++ b/.agents/notes/implemented/feature/2026-08-12-web-image-intake-and-limits-alignment.zh.md @@ -16,7 +16,7 @@ issue #2248 的第二步对齐，接在[附件展示 note](2026-08-11-web-attach **历史缩略图（DeepSeek Chat 规则）。** 一条消息仅有的一张图长边 240px、展示比例钳制在 [0.25, 4]，`cover` 裁切，特别高的图锚定顶部、特别宽的锚定左侧，从不放大；多张图渲染为固定 64px 方块，单个可换行的横排（10px 间距，用户消息右对齐）。assistant 连续的 `image` 块合并进同一个画廊，平铺而不是各占一行。 -**上限对齐并投影。** 默认值为每条消息 20 张、单图 3.5 MiB、总量 100 MiB（`attachment-local`），HTTP 载体上限提为唯一共享的 `DEFAULT_MAX_REQUEST_BODY_BYTES = 160 MiB`（http-bridge，原先是两个独立的 32 MiB 字面量），以满足加载时的容量断言（总量 × 4/3 加余量 ≈ 134.3 MiB）。消费级产品集中在 10 到 20 个附件（ChatGPT 10、Gemini 10、Claude 20；DeepSeek Chat 的 50 是例外），且视觉模型一张图约 1300 到 4800 token，因此 50 张图可在一条消息中填满 200k 上下文。3.5 MiB 编码文件包括 base64 填充在内最多占 4.67 MiB，在 5 MiB 路由检查下保留 0.33 MiB 余量。仅使用较大上限路由的部署可以覆盖该值。512 MiB 总量无法通过当前传输，因为 base64 进 JSON 需要一个超过 V8 约 512 MiB 字符串上限的单个 JSON 字符串。限额以 `imageLimits` 会话投影到达客户端。它是每次启动恒定的单元（`apply` 返回同一状态引用，因此只靠基线携带、不存在变更帧），由 **apiproxy** 而非 attachment Service Definition 注册：`dsh-llm` 依赖 `dsh-attachment`（`ImageBlock` → `ImageAttachmentRef`），seam 包引用 `dsh-session-projection`（其图谱经 `dsh-session` 到达 `dsh-llm`）会闭合 project-reference 环，而该值描述的每消息数量与总量规则本来就是 proxy 自己的准入检查。`SessionProjectionMap` 合并放在 proxy 的 sessions 协议文件里，每个客户端程序都经载体的类型再导出包含它。 +**上限对齐并投影。** 输入默认值是每条消息 20 张、每个源文件 32 MiB、源文件总量 100 MiB、每张图片一亿解码像素，以及源文件任一边 16384px。附件后端另行生成长边 2048px、独立安全上限 4 MiB 的持久主版本。模型请求使用各路由自己的像素和编码字节预算，因此源文件准入不采用提供方请求限制。HTTP 载体统一使用 `DEFAULT_MAX_REQUEST_BODY_BYTES = 160 MiB`，满足 100 MiB 总量经过 base64 和请求封装扩张后的加载时容量断言。512 MiB 总量无法通过当前传输，因为 base64 进入 JSON 后会需要一个接近 V8 字符串大小上限的 JSON 字符串。输入上限通过 `imageLimits` 会话投影到达客户端。它是每次启动恒定的单元，由 **apiproxy** 而非 attachment Service Definition 注册。`dsh-llm` 依赖 `dsh-attachment`，而 `dsh-session-projection` 经 `dsh-session` 到达 `dsh-llm`；在 seam 包注册投影会形成 project-reference 环。每条消息的数量和总量规则也由 proxy 强制执行。`SessionProjectionMap` 合并继续放在 proxy 的 sessions 协议文件中，客户端已经通过载体类型再导出使用它。 **加入预检与错误文案。** 两种加入手势汇合到 InputBar 的一个 `intakeImages` 包装：在 `addImages` 之前按投影检查数量、单图字节与总字节，违规的一批整体拒收（DeepSeek Chat 语义）并立刻弹出点名上限的横幅——不再有提交时的回滚戏码。宿主检查保留，兜底绕过 composer 的调用方。横幅文案遵循用户定下的一条原则：用户能解决的原因（模型不支持视觉、数量、大小、分辨率、格式——格式改为正面列出支持列表而不是回显被拒的 MIME 类型）用点明出路的产品句子；用户无法解决的原因（base64 损坏、引用丢失、读取失败）折叠为一条保留原因码的发送失败句子，因为产品当前面向开发者，可上报的码好过死胡同。非附件错误码保留原文加错误码的展示。 diff --git a/.agents/notes/implemented/feature/2026-08-13-shared-modal-product-onboarding.i18n.yaml b/.agents/notes/implemented/feature/2026-08-13-shared-modal-product-onboarding.i18n.yaml index 84b070138b..fda5e932c9 100644 --- a/.agents/notes/implemented/feature/2026-08-13-shared-modal-product-onboarding.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-13-shared-modal-product-onboarding.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-13-shared-modal-product-onboarding.md -2026-08-13-shared-modal-product-onboarding.md: 771b6675ea170c5001fca7c880f6c246e19fe7f1 -2026-08-13-shared-modal-product-onboarding.zh.md: a46bc273e0c2fd24cc45efd5e93d3aa24b3102bd +2026-08-13-shared-modal-product-onboarding.md: ec3d3e5f112b04736a15645c6e62e942367bb4fa +2026-08-13-shared-modal-product-onboarding.zh.md: 78b17d02dba52170722042126cc5616e9272c722 diff --git a/.agents/notes/implemented/feature/2026-08-13-shared-modal-product-onboarding.md b/.agents/notes/implemented/feature/2026-08-13-shared-modal-product-onboarding.md index 771b6675ea..ec3d3e5f11 100644 --- a/.agents/notes/implemented/feature/2026-08-13-shared-modal-product-onboarding.md +++ b/.agents/notes/implemented/feature/2026-08-13-shared-modal-product-onboarding.md @@ -30,4 +30,4 @@ First-run onboarding mixed two interaction models: a viewport takeover for produ ## Consequences -A fresh loopback profile sees the specified internal-testing notice, then an inline DeepSeek key dialog only when no provider is usable. Acknowledgement remains versioned in `settings.yaml`, secrets remain write-only in `.credentials.yaml`, and already-ready or unsupported deployments render no onboarding chrome while readiness loads. The Models package now owns product-onboarding presentation as well as provider configuration; its README and browser coverage make that broader responsibility explicit. This decision restores a concise testing-stage notice after the historical [full-viewport beta notice removal](../simplification/2026-08-13-remove-first-run-beta-notice.md) without restoring that notice's telemetry copy or takeover layout. +A fresh loopback profile sees the specified internal-testing notice, then an inline DeepSeek key dialog only when no provider is usable. Acknowledgement remains versioned in `settings.yaml`, secrets remain write-only in `.credentials.yaml`, and already-ready or unsupported deployments render no onboarding chrome while readiness loads. The Models package now owns product-onboarding presentation as well as provider configuration; its README and browser coverage make that broader responsibility explicit. This decision restores a concise testing-stage notice after the historical [full-viewport beta notice removal](../../archived/simplification/2026-08-13-remove-first-run-beta-notice.md) without restoring that notice's telemetry copy or takeover layout. diff --git a/.agents/notes/implemented/feature/2026-08-13-shared-modal-product-onboarding.zh.md b/.agents/notes/implemented/feature/2026-08-13-shared-modal-product-onboarding.zh.md index a46bc273e0..78b17d02db 100644 --- a/.agents/notes/implemented/feature/2026-08-13-shared-modal-product-onboarding.zh.md +++ b/.agents/notes/implemented/feature/2026-08-13-shared-modal-product-onboarding.zh.md @@ -30,4 +30,4 @@ Status: implemented ## 后果 -新的回环 profile 会先看到指定的内测声明；仅当没有任何可用提供方时，之后才会出现行内 DeepSeek 密钥弹窗。确认仍按版本写入 `settings.yaml`，secret 仍以只写方式存入 `.credentials.yaml`，已就绪或无法修复的部署在加载判定期间不会渲染任何引导框架。Models 包现在同时持有产品引导展示与提供方配置；README 和浏览器覆盖明确记录了这项扩展后的职责。本决策在历史上的[全屏内测声明移除](../simplification/2026-08-13-remove-first-run-beta-notice.zh.md)之后恢复简洁的测试阶段声明，但不会恢复那份声明中的遥测文案或接管式布局。 +新的回环 profile 会先看到指定的内测声明；仅当没有任何可用提供方时，之后才会出现行内 DeepSeek 密钥弹窗。确认仍按版本写入 `settings.yaml`，secret 仍以只写方式存入 `.credentials.yaml`，已就绪或无法修复的部署在加载判定期间不会渲染任何引导框架。Models 包现在同时持有产品引导展示与提供方配置；README 和浏览器覆盖明确记录了这项扩展后的职责。本决策在历史上的[全屏内测声明移除](../../archived/simplification/2026-08-13-remove-first-run-beta-notice.md)之后恢复简洁的测试阶段声明，但不会恢复那份声明中的遥测文案或接管式布局。 diff --git a/.agents/notes/implemented/feature/2026-08-19-direct-deepseek-vision-input.i18n.yaml b/.agents/notes/implemented/feature/2026-08-19-direct-deepseek-vision-input.i18n.yaml deleted file mode 100644 index 467a951f7c..0000000000 --- a/.agents/notes/implemented/feature/2026-08-19-direct-deepseek-vision-input.i18n.yaml +++ /dev/null @@ -1,6 +0,0 @@ -# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each -# side as of the last confirmed-consistent state. Both languages carry equal authority; -# after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-19-direct-deepseek-vision-input.md -2026-08-19-direct-deepseek-vision-input.md: 76d3244e67a73c1cdf4419a6537ada38e0a75bd5 -2026-08-19-direct-deepseek-vision-input.zh.md: a77231104156371fe698f8a8ad386cfa03251990 diff --git a/.agents/notes/implemented/feature/2026-08-19-direct-deepseek-vision-input.md b/.agents/notes/implemented/feature/2026-08-19-direct-deepseek-vision-input.md deleted file mode 100644 index 76d3244e67..0000000000 --- a/.agents/notes/implemented/feature/2026-08-19-direct-deepseek-vision-input.md +++ /dev/null @@ -1,34 +0,0 @@ -# Agent Note: Direct DeepSeek vision input - -Status: implemented - -English | [中文](2026-08-19-direct-deepseek-vision-input.zh.md) - -## Problem - -DeepSeek vision deployments use the chat-completions image protocol, but the direct `deepseek-official` adapter declares every catalog and pass-through model text-only and rejects every `ImageBlock`. The durable attachment path therefore works only through configurable pi-ai routes, and a deployment cannot pass user uploads or image-bearing tool results through the direct provider. - -## Decision - -The shipped catalog declares `deepseek-v4-flash-vision-exp` with `inputModalities: [text, image]`; configured catalogs use the same declaration to opt another exact model into image input, and validation rejects empty, unknown, or duplicate modalities. Flash, Pro, unlisted ids, and configured models that omit `inputModalities` remain explicitly text-only. - -The adapter resolves `ctx.attachments` per image request, reads each retained durable reference with the request signal, and serializes verified bytes as ordered OpenAI-compatible `image_url` data URLs. Text-only user messages retain string content. Tool results retain string-only `tool` messages; image-only results use `(see attached image)`, and consecutive retained tool-result images follow in one `user` message beginning `Attached image(s) from tool result:`. System and assistant history images fail with `UNSUPPORTED_CONTENT` before attachment or network I/O. - -The direct adapter and pi-ai conversion share the deterministic [request-level image payload bound](../bug-fix/2026-08-18-request-image-payload-bound.md). Both default to 20 MiB of accumulated base64 payload, replace oldest image occurrences with the same fixed placeholder, and never read omitted attachments. Direct HTTP 413 responses are `INVALID_REQUEST`; attachment failures retain their stable attachment code rather than becoming `TRANSPORT`. - -Canonical messages continue to store only `ImageAttachmentRef`. Data URLs exist only while preparing one provider request, so no session event, persistence format, API schema, or SDK projection changes. The route accepts PNG, JPEG, WebP, and GIF already admitted by the attachment service. External image URLs, the Files API, and image output remain unsupported. - -## Alternatives considered - -- **Use only the pi-ai DeepSeek provider.** Its generic multimodal path proves the content conversion, but it does not make the direct official route truthful or usable with the official model id. -- **Declare the whole provider image-capable.** This would let Flash, Pro, and unknown pass-through ids accept durable images that their exact wire model cannot promise to consume. Capability remains exact-model metadata. -- **Send images inside `tool` message content.** The documented compatible form keeps tool content a string. A following user message avoids relying on an undocumented multimodal tool-role form while preserving call-result order. -- **Add external URLs or Files uploads.** Both require new canonical input, authorization, lifetime, cleanup, and replay decisions. Transient base64 uses the existing durable attachment contract without expanding those concerns. - -## Verification - -Package tests pin model discovery and fallback capabilities, configuration validation and live settings updates, user and tool-result wire messages, all admitted MIME types, cancellation, attachment failures, 413 classification, exact image-bound behavior, and pi-ai equivalence. A keyless assembled ACP request records the native adapter's tool-result data URL and oldest-image placeholder. A real-API smoke test with an explicit image-capable catalog entry sends a deterministic image only when `DEEPSEEK_VISION_E2E=1` is set in addition to the provider key. - -## Consequences - -The official DeepSeek vision route and configured vision routes can consume durable user and tool-result images without changing session durability or response streaming. Repeated history still expands request bodies, but deterministic oldest-first offload bounds the dominant payload and leaves headroom below the official 30 MiB request-body limit. Image token pricing remains provider-owned because the official image token formula is not available. diff --git a/.agents/notes/implemented/feature/2026-08-19-direct-deepseek-vision-input.zh.md b/.agents/notes/implemented/feature/2026-08-19-direct-deepseek-vision-input.zh.md deleted file mode 100644 index a772311041..0000000000 --- a/.agents/notes/implemented/feature/2026-08-19-direct-deepseek-vision-input.zh.md +++ /dev/null @@ -1,34 +0,0 @@ -# Agent Note: 直接 DeepSeek 视觉输入 - -Status: implemented - -[English](2026-08-19-direct-deepseek-vision-input.md) | 中文 - -## Problem - -DeepSeek 视觉部署使用 chat-completions 图片协议，但直接 `deepseek-official` 适配器把所有 catalog 与原样传递模型都声明为仅文本，并拒绝每一个 `ImageBlock`。因此，持久附件路径只能经可配置 pi-ai 路由工作，部署方无法通过直接提供方传递用户上传或包含图片的工具结果。 - -## Decision - -随附目录为 `deepseek-v4-flash-vision-exp` 声明 `inputModalities: [text, image]`；已配置目录可以用同一声明让另一个确切模型支持图片输入，校验会拒绝空列表、未知模态或重复模态。Flash、Pro、未列出 id，以及省略 `inputModalities` 的已配置模型仍明确仅支持文本。 - -适配器会对每个图片请求解析 `ctx.attachments`，用请求 signal 读取每个保留的持久引用，并将校验后的字节按顺序序列化为 OpenAI 兼容的 `image_url` data URL。纯文本 user 消息保留字符串内容。工具结果保留仅字符串的 `tool` 消息；仅含图片的结果使用 `(see attached image)`，连续工具结果中保留的图片随后合并进一条以 `Attached image(s) from tool result:` 开头的 `user` 消息。System 与 assistant 历史图片会在附件或网络 I/O 前以 `UNSUPPORTED_CONTENT` 失败。 - -直接适配器与 pi-ai 转换共享确定性的[请求级图片载荷上限](../bug-fix/2026-08-18-request-image-payload-bound.zh.md)。两者都以 20 MiB 累计 base64 payload 为默认值，用相同固定占位文本替换最旧的图片出现位置，并且绝不读取被省略的附件。直接 HTTP 413 响应归类为 `INVALID_REQUEST`；附件失败会保留其稳定附件 code，不会变成 `TRANSPORT`。 - -规范消息继续只存储 `ImageAttachmentRef`。Data URL 只在准备单次提供方请求时存在，因此无需修改会话事件、持久化格式、API schema 或 SDK 投影。路由接受已经由附件服务准入的 PNG、JPEG、WebP 和 GIF。不支持外部图片 URL、Files API 和图片输出。 - -## Alternatives considered - -- **只使用 pi-ai DeepSeek 提供方。** 其通用多模态路径验证了内容转换，但无法让直接官方路由如实公布能力，也无法让它配合官方模型 id 使用。 -- **把整个提供方声明为支持图片。** 这样会让 Flash、Pro 和未知的原样传递 id 接受持久图片，但其确切协议模型无法承诺消费这些图片。能力仍属于确切模型元数据。 -- **在 `tool` 消息内容中发送图片。** 已记录的兼容形式要求工具内容保持字符串。随后发送 user 消息可避免依赖未记录的多模态 tool role 形式，同时保留调用结果顺序。 -- **增加外部 URL 或 Files 上传。** 两者都需要新的规范输入、授权、生命周期、清理和重放决策。瞬态 base64 可以复用现有持久附件约定，不扩展这些问题。 - -## Verification - -包测试固定模型发现与回退能力、配置校验与存活 settings 更新、user 和工具结果协议消息、所有已准入 MIME 类型、取消、附件失败、413 分类、确切图片上限行为和 pi-ai 等价性。无需密钥的组装 ACP 请求会记录原生适配器的工具结果 data URL 与最旧图片占位文本。真实 API 冒烟测试会配置明确支持图片的目录项，并且仅在提供方密钥之外还设置 `DEEPSEEK_VISION_E2E=1` 时发送确定性图片。 - -## Consequences - -官方 DeepSeek 视觉路由与已配置视觉路由可以消费持久 user 与工具结果图片，而无需改变会话持久性或响应流。重复历史仍会扩张请求正文，但确定性的最旧优先 offload 会限制主导 payload，并在官方 30 MiB 请求正文上限下保留余量。由于官方图片 token 公式尚不可用，图片 token 定价仍由提供方掌握。 diff --git a/.agents/notes/implemented/feature/2026-08-19-high-cache-hit-decimal-display.i18n.yaml b/.agents/notes/implemented/feature/2026-08-19-high-cache-hit-decimal-display.i18n.yaml deleted file mode 100644 index b8c987747c..0000000000 --- a/.agents/notes/implemented/feature/2026-08-19-high-cache-hit-decimal-display.i18n.yaml +++ /dev/null @@ -1,6 +0,0 @@ -# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each -# side as of the last confirmed-consistent state. Both languages carry equal authority; -# after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-19-high-cache-hit-decimal-display.md -2026-08-19-high-cache-hit-decimal-display.md: 952d838fdf330175915e13ef767fd80d145506b2 -2026-08-19-high-cache-hit-decimal-display.zh.md: ba33bd8a265211c8514fda4babda5ba94ed02884 diff --git a/.agents/notes/implemented/bug-fix/2026-08-18-request-image-payload-bound.i18n.yaml b/.agents/notes/implemented/feature/2026-08-20-unified-image-request-pipeline.i18n.yaml similarity index 56% rename from .agents/notes/implemented/bug-fix/2026-08-18-request-image-payload-bound.i18n.yaml rename to .agents/notes/implemented/feature/2026-08-20-unified-image-request-pipeline.i18n.yaml index 8e355b809e..6a379a3532 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-18-request-image-payload-bound.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-20-unified-image-request-pipeline.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-18-request-image-payload-bound.md -2026-08-18-request-image-payload-bound.md: 0ec4594888db6157fb8cfd3e7bdb231b842d53c1 -2026-08-18-request-image-payload-bound.zh.md: 7cdf6bb768251cb792b6d590fafa094646e77ada +# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-20-unified-image-request-pipeline.md +2026-08-20-unified-image-request-pipeline.md: ada15d540539977c631e359ffdc7baa4fa84c78e +2026-08-20-unified-image-request-pipeline.zh.md: 85c9a1f837d82cba2bc62b30402433f50c873cbe diff --git a/.agents/notes/implemented/feature/2026-08-20-unified-image-request-pipeline.md b/.agents/notes/implemented/feature/2026-08-20-unified-image-request-pipeline.md new file mode 100644 index 0000000000..ada15d5405 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-08-20-unified-image-request-pipeline.md @@ -0,0 +1,69 @@ +# Agent Note: Unified normalized attachments, request versions, and provider files + +Status: implemented + +English | [中文](2026-08-20-unified-image-request-pipeline.zh.md) + +## Problem + +Durable image history, provider resolution, inline request size, and remote file reuse have different limits. Treating an admitted image as the bytes sent on every later request forced one byte cap and one raster to serve all four concerns. Large but ordinary input was refused, clean 16-bit PNG could pass into history and fail at DeepSeek, repeated base64 expanded long requests, and a provider rejection repeated because the same durable image stayed in every future request. + +## Decision + +The image path has two explicit versions. The attachment backend owns a provider-independent durable normalized attachment. Each image-capable model route owns a deterministic request policy, and the attachment backend derives and caches the exact request version from that attachment. Session history contains only the normalized attachment reference; inline bytes and provider file ids remain transient request projections. + +### Provider-independent normalized attachment + +Admission accepts at most 20 images and 200MiB of encoded source bytes per message. Each source is fully decoded under configurable 20MiB, 64,000,000-pixel, and 8192px-per-side limits. Normalization applies EXIF orientation, removes metadata and color profiles, converts to 8-bit sRGB/sRGBA, and preserves aspect ratio while limiting the long edge to `normalizedImageMaxDimension`, 2048px by default. When scaling reduces the raster, `originalDimensions` records its orientation-applied width and height before normalization. + +The normalized attachment has an independent `normalizedImageMaxBytes` safety cap, 4MiB by default. Alpha is never flattened. A nearest-neighbour bounded sample classifies color complexity without averaging high-frequency pixels. Confirmed low-color input tries PNG, with palette encoding only when no alpha channel is present, followed by WebP qualities 85, 80, and 75. Other alpha input tries WebP at those qualities; other opaque input tries JPEG. Candidates execute in order and stop at the first result within the cap. Dimensions shrink only after every candidate at one size exceeds the cap. The source extension does not classify a PNG as low color. A clean, single-frame 8-bit sRGB/sRGBA PNG, JPEG, or WebP within both normalization limits passes through byte-identically and retains content-addressed deduplication. GIF, animation, metadata, orientation, 16-bit PNG, and incompatible color spaces force conversion. The source and a converted output are each fully decoded once; the output must match its format, dimensions, depth, color space, and alpha facts before its digest enters the reference. + +Batch admission prepares and verifies every normalized attachment once before publishing any member. Validation failure starts no writes. Publication uses those prepared bytes directly, so a large batch does not repeat full decoding and encoding during commit. A later storage failure returns no partial references; already published immutable objects may remain unreachable under the existing storage rule. + +### Deterministic request versions + +`AttachmentStore.readImageRequest` derives a request version under route-owned total-pixel and encoded-byte budgets. Scaling is `min(1, sqrt(maxPixels / (width * height)))`, with no enlargement, followed by inward integer rounding so the encoded raster never exceeds the total-pixel cap. DeepSeek V4 Flash Vision Exp uses 640,000 total pixels and 1MiB raw encoded bytes by default; low detail uses 512 by 512 total pixels. A 2048 by 1024 normalized attachment projects to 1130 by 565 under the hard cap. Request encoding uses the same color branches, with PNG (palette only without alpha) then WebP 85 and 80 for low-color input, WebP 85 then 80 for other alpha input, and JPEG 85 then 80 for other opaque input. Each fallback runs only after the previous result exceeds 1MiB, and dimensions shrink only after both quality attempts exceed it. The same derivation is used by normal agent turns, direct `ctx.llm.stream` calls, compaction, and other auxiliary streams. + +The `variantId` and cache path cover the normalized attachment id, transform version, route pixel and byte budgets, and fixed encoder parameters. A new cache entry is fully decoded before publication. Cache hits use a header probe to check format, 8-bit sRGB/sRGBA facts, dimensions, alpha, and byte limits without decoding the complete raster again; a mismatch regenerates the entry. DeepSeek Files and pi-ai inline base64 therefore use the same deterministic bytes for the same policy. Inline accounting uses the derived byte length after base64 expansion, not the normalized attachment byte count. Equal in-process `variantId` calls share one transform and cache write. Each caller can cancel its own wait; the shared transform is aborted only after every waiter has cancelled. Callers preserve order by applying `Promise.all` to singular `readImageRequest` calls. The local implementation runs normalization and request transforms through one FIFO limiter; `imageCompressionConcurrency` is configurable from 1 through 8 and defaults to 2. Batch publication remains sequential after every normalized attachment has been prepared. + +Request-size offload is a deterministic oldest-first projection. Before reading attachments, each route uses `min(attachmentBytes, requestVersionMaxBytes)` as a conservative upper bound and removes the oldest over-budget prefix. Only retained attachments are read and transformed, so an omitted missing or corrupt object cannot block the request. A second projection uses exact derived lengths without bringing omitted images back. DeepSeek defaults to 128MiB and 600 referenced images. Its removed prefix advances past successive 64MiB byte boundaries and in 20-image count quanta, so 129 one-megabyte images remove the oldest 65, retain 64MiB, and keep that prefix stable until total history passes 192MiB. Pi-ai retains a configurable base64 request bound. A text-only route receives deterministic attachment placeholders, including nested tool-result images, while append-only session history keeps the original references. + +### Stable handles + +Every retained request image is preceded by its complete attachment id and actual request dimensions. User messages, tool results, agent-loop requests, compaction, and direct `ctx.llm.stream` calls share this projection. + +### DeepSeek Files lifecycle + +The direct `deepseek-official` adapter normally uploads every retained request version through the OpenAI-compatible Files API and sends `file_id` content blocks. A [bounded inline fallback](../bug-fix/2026-08-21-deepseek-files-inline-fallback.md) sends the same deterministic request versions when file resolution fails. The default catalog advertises `deepseek-v4-flash-vision-exp` as image-capable. Uploaded ids are indexed by endpoint and API-key scope plus `variantId`. Uploads request seven days by default and record the returned `expires_at`; a mapping with no more than one hour remaining is replaced without a preceding retrieve call. The index never stores the API key. + +An upload is indexed only after the response returns a complete file object, matching byte count, and `expires_at`. A missing or inconsistent response leaves no local mapping, so a later request uploads again. Concurrent upload resolution for one scoped `variantId` shares one provider operation; one waiter cannot cancel another, and the upload stops when every waiter has cancelled. A malformed upload index is an empty cache and is replaced on the next successful upload; filesystem I/O failures remain errors. If chat reports expired, deleted, missing, or invalid ids and names one or more ids used by the request, only those mappings are removed. A stale-file response without a specific id removes every mapping used by that chat attempt. The affected request bytes are uploaded again and chat is retried once. A second stale rejection clears the mappings identified by its response and returns the error without a third chat attempt. One upload quota error first lists the configured number of oldest harness-owned `dsh-` files, then deletes that collected set and retries once; deleting after pagination keeps provider cursors valid. Public file operations expose list, retrieve, delete, one-variant release, and namespace-wide release. Every Files request carries the shared Harness `User-Agent`. The client enforces the documented 128MiB upload limit, 32MiB chat-image limit, 10,000-file and 25GiB quotas, and one-hour to 30-day expiry range. + +### Diagnostics + +A 16-bit RGB or RGBA PNG is normal admitted input and converts to 8-bit sRGB/sRGBA. If local conversion fails, `read_image` names the path, detected 16-bit PNG, required normalized form, and manual conversion remedy. If DeepSeek rejects a normalized request version, the primary error names the attachment or display name, durable message and image position, normalized media type, 8-bit sRGB/sRGBA depth, dimensions, and provider message. An ambiguous multi-image rejection lists every candidate. The raw provider body remains the error cause rather than the only visible message. + +Historical attachment objects that later disappear or fail integrity verification remain fail-loud. Durable quarantine and verified recovery require session events and are tracked by [Quarantine unreadable historical attachments](../../proposed/bug-fix/2026-08-20-attachment-read-quarantine.md). + +## Alternatives considered + +**Use one 1MiB normalized attachment for storage and requests.** This makes model resolution determine durable image detail and combines local storage, inline expansion, Files quota, and model pixels into one setting. Independent normalization and request policies keep those responsibilities explicit. + +**Reject images above provider dimensions or at the encoding quality floor.** A provider limit is route-specific and future requests may use another model. Proportional normalization and request projection accept ordinary large images while bounding each later representation. + +**Treat PNG as a screenshot and reject 16-bit PNG.** File format does not reveal pixel complexity, and 16-bit RGB/RGBA is a convertible sample depth rather than an unsupported image type. Pixel sampling and post-conversion probes give the required facts. + +**Keep DeepSeek data URLs as the primary transport.** Inline base64 repeats bytes on every request and caps usable image history by request-body size. Files API references reuse uploaded deterministic request bytes and provide explicit expiry and deletion; the bounded fallback uses data URLs only when file resolution fails. + +**Trust a locally indexed file id indefinitely.** Remote expiry, deletion, and lost upload responses make local and provider state diverge. Response-directed invalidation and one re-upload recover without an unbounded retry loop; an ambiguous stale-file response must invalidate every file used by that attempt because it provides no safe exact target. + +**Refuse text-only model selection after any image.** Durable history can outlive the model that first consumed it. Request-local placeholders keep the session usable without rewriting history. + +**Remove one image whenever a request crosses its limit.** That changes an early request message after nearly every new upload. Quantized removed prefixes keep cache invalidation occasional while honoring the configured high bound. + +## Verification + +Package tests generate 16-bit RGB and RGBA PNG fixtures, prove 8-bit conversion and clean 8-bit passthrough, retain alpha under byte pressure, distinguish high-frequency and ordinary photos from low-color graphics, stop lazy encoding after the first fitting candidate, cover square and wide 640,000-pixel projections, enforce 1MiB request bytes, singleflight equal variants and uploads without shared-cancellation leaks, bound transform concurrency, preserve cache and upload identity, skip attachment reads for conservatively offloaded history, prepare batches once, reject inconsistent Files responses, refresh near-expiry ids without retrieve, recover once from single-id, multiple-id, and ambiguous stale responses, fall back to bounded all-inline requests after file resolution failure, paginate before quota deletion, normalize provider diagnostics, project text-only history, and share normal/compaction request bytes. Keyless assembled snapshots cover the real tool schemas and image request path. A credentialed test uses the built-in `deepseek-official` route and its configured endpoint, never a custom provider entry. + +## Consequences + +Normalized attachments consume up to the independent local safety cap, while request caches and remote Files consume additional derived storage. Deterministic identities and singleflight make that work reusable across turns and sessions sharing the same DSH home. Two simultaneous transforms reduce batch latency while increasing peak RSS relative to serial execution; deployments with tighter memory can set the limit to one. Encoder or transform-version changes create new future identities without rewriting existing history. DeepSeek image requests prefer Files reuse; bounded stale-id recovery handles inconsistent remote state, while file-resolution failures use the smaller inline budget. Missing or corrupt durable attachments still require the separate quarantine design. diff --git a/.agents/notes/implemented/feature/2026-08-20-unified-image-request-pipeline.zh.md b/.agents/notes/implemented/feature/2026-08-20-unified-image-request-pipeline.zh.md new file mode 100644 index 0000000000..85c9a1f837 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-08-20-unified-image-request-pipeline.zh.md @@ -0,0 +1,69 @@ +# Agent Note: 统一规范化附件、请求版本与提供方文件 + +Status: implemented + +[English](2026-08-20-unified-image-request-pipeline.md) | 中文 + +## Problem + +持久图片历史、提供方分辨率、内联请求大小和远端文件复用有不同限制。过去把已接纳图片直接作为之后每次请求发送的字节，导致一个字节上限和一份光栅同时承担四种职责。普通大图会被拒绝；干净的 16-bit PNG 可以进入历史，之后才被 DeepSeek 拒绝；重复 base64 使长会话请求持续增长；提供方拒绝后，同一持久图片还会进入每次后续请求。 + +## Decision + +图片路径有两个显式版本。附件后端拥有提供方无关的持久规范化附件。每条支持图片的模型路由拥有确定性请求策略，附件后端从该附件派生并缓存确切请求版本。会话历史只包含规范化附件引用；内联字节和提供方文件 ID 都是瞬时请求投影。 + +### 提供方无关的规范化附件 + +每条消息最多准入 20 张图片，源图编码字节总量不超过 200MiB。每张源图会在可配置的 20MiB、64,000,000 像素和单边 8192px 限制内完整解码。规范化过程会应用 EXIF 方向，删除元数据和色彩配置文件，转换为 8-bit sRGB/sRGBA，并保持宽高比把长边限制到 `normalizedImageMaxDimension`，默认 2048px。缩放减小光栅时，`originalDimensions` 记录规范化之前、应用方向之后的输入宽高。 + +规范化附件有独立的 `normalizedImageMaxBytes` 安全上限，默认 4MiB。透明通道绝不铺平。系统通过 nearest-neighbour 对有界样本判断色彩复杂度，不会通过像素平均把高频图片误判为低色数。确认的低色数输入先尝试 PNG，只有不带 alpha 通道时才使用 palette，随后依次尝试质量 85、80、75 的 WebP；其他透明输入依次尝试这些质量的 WebP；其他非透明输入依次尝试这些质量的 JPEG。候选按顺序执行，首个不超过上限的结果会立即返回。同一尺寸的候选全部超限后才会缩小尺寸。源扩展名不会把 PNG 归类为低色数图片。处于两个规范化上限内的干净、单帧、8-bit sRGB/sRGBA PNG、JPEG 或 WebP 按字节原样直通，并保留内容寻址去重。GIF、动图、元数据、方向、16-bit PNG 和不兼容色彩空间都会触发转换。源图和转换输出各完整解码一次；输出的格式、尺寸、位深、色彩空间和透明通道事实通过校验后，其摘要才会进入引用。 + +批量准入在发布任何成员前，为每张图片各准备并验证一次规范化附件。校验失败不会开始写入。发布直接使用这些已准备字节，因此大批次不会在提交时重复完整解码和编码。之后发生的存储失败不会返回部分引用；按现有存储规则，已经发布的不可变对象可能保持不可达。 + +### 确定性请求版本 + +`AttachmentStore.readImageRequest` 按路由拥有的总像素和编码字节预算派生请求版本。缩放公式为 `min(1, sqrt(maxPixels / (width * height)))`，不会放大小图，随后向预算内取整，确保编码光栅不超过总像素上限。DeepSeek V4 Flash Vision Exp 默认使用总像素 640,000 和原始编码字节 1MiB；low detail 使用总像素 512×512。2048×1024 规范化附件在这个硬上限下会投影为 1130×565。请求编码使用相同的分类分支：低色数输入先尝试 PNG，只有不带 alpha 通道时才使用 palette，随后依次尝试质量 85、80 的 WebP；其他透明输入依次尝试质量 85、80 的 WebP；其他非透明输入依次尝试质量 85、80 的 JPEG。只有前一结果超过 1MiB 时才执行下一个候选；两个质量档都超限后才缩小尺寸。普通 agent 轮次、直接 `ctx.llm.stream` 调用、压缩和其他辅助流都使用同一派生过程。 + +`variantId` 和缓存路径覆盖规范化附件 ID、变换策略版本、路由像素和字节预算及固定编码参数。新缓存条目在发布前会完整解码。缓存命中只探测文件头，校验格式、8-bit sRGB/sRGBA、尺寸、透明通道和字节上限，不会再次完整解码光栅；不匹配时会重新生成。因此，同一策略下的 DeepSeek Files 和 pi-ai 内联 base64 使用相同的确定性字节。内联计量使用派生字节经过 base64 膨胀后的长度，不使用规范化附件字节数。同一进程内相同 `variantId` 的调用共享一次变换和缓存写入。每个调用方可以取消自己的等待；只有全部等待方都取消时，共享变换才会中止。调用方对单数 `readImageRequest` 使用 `Promise.all` 保持结果顺序。本地实现通过一个 FIFO 限流器运行规范化和请求变换，`imageCompressionConcurrency` 的可配置范围为 1 至 8，默认值为 2。全部规范化附件准备完成后，批次仍按顺序发布。 + +请求大小 offload 是确定性的从旧到新投影。读取附件前，每条路由先以 `min(附件字节数, 请求版本字节上限)` 作为保守上界，移除超出预算的最旧前缀。系统只读取并转换保留的附件，因此已省略的缺失或损坏对象不会阻塞请求。第二次投影使用确切派生长度，但不会重新加入已省略图片。DeepSeek 默认上限为 128MiB 和 600 张引用图片。被移除前缀会越过连续的 64MiB 字节边界，并按 20 张图片数量步长递增，因此 129 张 1MiB 图片会移除最旧的 65 张并保留 64MiB；持久历史超过 192MiB 前，该前缀保持不变。Pi-ai 保留可配置的 base64 请求上限。纯文本路由会收到确定性的附件占位文本，其中包括嵌套工具结果图片；追加式会话历史继续保留原始引用。 + +### 稳定句柄 + +每张保留请求图片前都有完整附件 ID 和实际请求尺寸。用户消息、工具结果、agent loop 请求、压缩和直接 `ctx.llm.stream` 调用共享这套投影。 + +### DeepSeek Files 生命周期 + +直接 `deepseek-official` 适配器通常通过 OpenAI 兼容 Files API 上传每张保留的请求版本，并发送 `file_id` 内容块。文件解析失败时，[有界内联回退](../bug-fix/2026-08-21-deepseek-files-inline-fallback.zh.md)会发送相同的确定性请求版本。默认 catalog 把 `deepseek-v4-flash-vision-exp` 公布为支持图片。上传 ID 按端点和 API key 作用域以及 `variantId` 写入索引。上传默认请求 7 天有效期，并记录返回的 `expires_at`；本地映射剩余时间不超过一小时时会直接替换，不会先查询远端文件。索引绝不存储 API key。 + +只有上传响应返回完整文件对象、匹配的字节数和 `expires_at` 时，上传结果才会写入索引。缺失或不一致的响应不会留下本地映射，后续请求会重新上传。同一作用域和 `variantId` 的并发解析共享一次提供方上传；单个等待方无法取消其他等待方，全部等待方取消时才会停止上传。格式损坏的上传索引按空缓存处理，并在下一次成功上传时替换；文件系统 I/O 失败仍是错误。如果 chat 报告 ID 已过期、删除、缺失或无效，并指出本次请求使用的一个或多个 ID，适配器只删除这些映射。如果响应只说明文件状态失效而没有指出具体 ID，适配器会删除该次 chat 使用的全部映射。受影响的请求字节会重新上传，chat 只重试一次。第二次仍报告文件失效时，适配器会按响应清理映射并返回错误，不会发起第三次 chat。一次上传配额错误会先列出配置数量的最旧 `dsh-` 文件，再删除收集到的文件并重试一次；分页完成后才删除，避免游标失效。公开文件操作提供列表、查询、删除、单个变体释放和整个作用域释放。每个 Files 请求都携带 Harness 的共享 `User-Agent`。客户端执行文档规定的 Files 单次上传 128MiB、chat 单图 32MiB、10,000 个文件、25GiB，以及一小时到 30 天有效期限制。 + +### 诊断 + +16-bit RGB 或 RGBA PNG 属于普通可接纳输入，会转换为 8-bit sRGB/sRGBA。本地转换失败时，`read_image` 会写明路径、检测到的 16-bit PNG、所需规范形式和手工转换方法。如果 DeepSeek 拒绝已规范化请求版本，主错误会写明附件 ID 或显示名称、持久消息和图片位置、规范化媒体类型、8-bit sRGB/sRGBA 位深、尺寸和提供方消息。多图片错误无法确定对象时会列出全部候选图片。原始提供方正文保留为错误 cause，不会成为唯一可见消息。 + +持久附件对象之后缺失或无法通过完整性校验时，系统仍会明确失败。持久隔离和经校验恢复需要新增会话事件，由[隔离不可读历史附件](../../proposed/bug-fix/2026-08-20-attachment-read-quarantine.zh.md)继续跟踪。 + +## Alternatives considered + +**使用一份 1MiB 规范化附件同时负责存储和请求。** 这种做法让模型分辨率决定持久图片细节，并把本地存储、内联膨胀、Files 配额和模型像素合并成一个设置。独立的规范化和请求策略会明确区分这些职责。 + +**拒绝超过提供方尺寸或达到编码质量下限的图片。** 提供方限制属于具体路由，未来请求可能改用另一个模型。按比例规范化和投影请求版本可以接纳普通大图，同时约束每种后续表示。 + +**把 PNG 当作截图，并拒绝 16-bit PNG。** 文件格式不能说明像素复杂度，16-bit RGB/RGBA 是可转换位深，不是不支持的图片类型。像素采样和转换后探测能提供所需事实。 + +**把 DeepSeek data URL 作为首选传输方式。** 内联 base64 会在每次请求中重复字节，并按请求正文大小限制可用图片历史。Files API 引用会复用上传后的确定性请求字节，并提供显式有效期和删除操作；有界回退只在文件解析失败时使用 data URL。 + +**永久信任本地索引中的文件 ID。** 远端过期、删除和上传响应丢失会使本地与提供方状态不一致。按响应失效和一次重新上传可以恢复，同时避免无界重试；响应没有给出可安全使用的精确目标时，必须使该次请求使用的全部文件失效。 + +**历史中出现图片后拒绝选择纯文本模型。** 持久历史可能比最初读取它的模型存活更久。按请求生成的占位文本可以保持会话可用，无需改写历史。 + +**请求每次越过上限就移除一张图片。** 这种做法会在几乎每次新增图片后改写较早的请求消息。按固定步长递增的移除前缀会降低缓存失效频率，同时遵守配置的上限。 + +## Verification + +包测试会生成 16-bit RGB 和 RGBA PNG fixture，验证 8-bit 转换与干净 8-bit 字节直通、字节压力下保留透明通道、区分高频和普通照片与低色数图形、首个候选合规后停止编码、正方形和宽屏 640,000 像素投影、请求字节不超过 1MiB、相同变体与上传 singleflight 且不会共享取消、变换并发上限、缓存与上传身份、跳过已保守 offload 的历史附件读取、批量只准备一次、Files 响应不一致、进入刷新余量时不查询远端并更新 ID、单个 ID、多个 ID 和模糊失效响应只恢复一次、文件解析失败后回退到有界全内联请求、删除配额文件前完成分页、规范化提供方诊断、纯文本投影，以及普通请求与压缩共享请求字节。无需密钥的组装快照覆盖真实工具 schema 和图片请求路径。使用凭据的测试只使用内置 `deepseek-official` 路由及其已配置端点，不使用自定义提供方条目。 + +## Consequences + +持久规范化附件最多占用独立的本地安全上限，请求缓存和远端 Files 还会占用额外派生存储。确定性身份和 singleflight 使这些成本可以被共享同一 DSH home 的轮次和会话复用。同时执行两个变换会降低批次延迟，但峰值 RSS 高于串行执行；内存更紧张的部署可以把上限设为 1。编码器或变换策略版本变化会为未来内容产生新身份，不会改写已有历史。DeepSeek 图片请求优先复用 Files；有界的陈旧 ID 恢复会处理远端状态不一致，文件解析失败则使用较小的内联预算。缺失或损坏的持久附件仍需要单独的隔离设计。 diff --git a/.agents/notes/implemented/process/2026-07-06-node-engine-floor.i18n.yaml b/.agents/notes/implemented/process/2026-07-06-node-engine-floor.i18n.yaml index 6c1c7fa37b..81d27de0ca 100644 --- a/.agents/notes/implemented/process/2026-07-06-node-engine-floor.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-06-node-engine-floor.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-06-node-engine-floor.md -2026-07-06-node-engine-floor.md: 4d24a861bfa1a27b5aa4e07da1ed21452c7be566 -2026-07-06-node-engine-floor.zh.md: 180bfafb913f6af4d795a9b879004ceb4e7d12a3 +2026-07-06-node-engine-floor.md: 44dc09f32b855f11a1cfd7851a96427b9f471848 +2026-07-06-node-engine-floor.zh.md: ebd7d20fe0608a7895cab87ba3c1ea405996a062 diff --git a/.agents/notes/implemented/process/2026-07-06-node-engine-floor.md b/.agents/notes/implemented/process/2026-07-06-node-engine-floor.md index 4d24a861bf..44dc09f32b 100644 --- a/.agents/notes/implemented/process/2026-07-06-node-engine-floor.md +++ b/.agents/notes/implemented/process/2026-07-06-node-engine-floor.md @@ -19,7 +19,7 @@ Two Node features gate the source runtime: Those source features clear on the 22.x line at **22.18**, but the installed Pi adapter dependency raises the advertised LTS floor. `@deepseek-ai/dsh-llm-pi-ai` depends on `@earendil-works/pi-ai@0.79.3`, whose package declares `engines.node >=22.19.0`, so the LTS floor is **22.19**. The 24.x branch remains `>=24.0.0`. The disjoint range excludes Node 23 entirely: Node 23.0–23.5 still has at least one flagged source feature, and the 23 line is non-LTS/EOL, so advertising `>=23.6` would add a dead release line and a CI leg no deployment should use. -`@types/node` remains pinned to the 22.x line (`^22.20.0`) to match the LTS support line: reaching for a Node 23+/24+/25+ API fails `tsc` on every machine and in the typecheck gate, rather than compiling clean and surviving to a runtime failure only a floor matrix leg could catch. The whole tree typechecks clean against the Node 22 type API today, so the pin costs nothing. +`@types/node` remains pinned to the 22.x line (`^22.20.0`) to match the LTS support line: reaching for a Node 23+/24+/25+ API fails `tsc` on every machine and in the typecheck gate, rather than compiling clean and surviving to a runtime failure only a floor matrix leg could catch. The whole tree typechecks clean against the Node 22 type API, so the pin costs nothing. ## Consequences diff --git a/.agents/notes/implemented/process/2026-07-06-node-engine-floor.zh.md b/.agents/notes/implemented/process/2026-07-06-node-engine-floor.zh.md index 180bfafb91..ebd7d20fe0 100644 --- a/.agents/notes/implemented/process/2026-07-06-node-engine-floor.zh.md +++ b/.agents/notes/implemented/process/2026-07-06-node-engine-floor.zh.md @@ -19,7 +19,7 @@ Status: implemented 这些源码特性在 22.x 线上于 **22.18** 全部就绪，但已安装的 Pi 适配器依赖将宣传的 LTS 下限进一步提高。`@deepseek-ai/dsh-llm-pi-ai` 依赖 `@earendil-works/pi-ai@0.79.3`，后者的包声明 `engines.node >=22.19.0`，因此 LTS 下限为 **22.19**。24.x 分支保持 `>=24.0.0`。该不相交范围完全排除了 Node 23：Node 23.0–23.5 至少还有一个源码特性需要标志，而 23 线是非 LTS/已 EOL 的，宣传 `>=23.6` 会增加一条已终止的发布线和一条 CI 分支，而没有任何部署应当使用它。 -`@types/node` 继续固定在 22.x 线（`^22.20.0`），以匹配 LTS 支持线：使用 Node 23+/24+/25+ 的 API 会在所有机器和类型检查门禁中导致 `tsc` 失败，而不是先编译通过，直到下限矩阵分支运行时才暴露错误。目前整个代码树针对 Node 22 类型 API 的类型检查全部通过，因此固定该版本不产生任何代价。 +`@types/node` 继续固定在 22.x 线（`^22.20.0`），以匹配 LTS 支持线：使用 Node 23+/24+/25+ 的 API 会在所有机器和类型检查门禁中导致 `tsc` 失败，而不是先编译通过，直到下限矩阵分支运行时才暴露错误。整个代码树针对 Node 22 类型 API 的类型检查全部通过，因此固定该版本不产生任何代价。 ## 后果 diff --git a/.agents/notes/implemented/process/2026-07-13-documentation-site-projection.i18n.yaml b/.agents/notes/implemented/process/2026-07-13-documentation-site-projection.i18n.yaml index 5dcb93edcf..83d446e0f6 100644 --- a/.agents/notes/implemented/process/2026-07-13-documentation-site-projection.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-13-documentation-site-projection.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-13-documentation-site-projection.md -2026-07-13-documentation-site-projection.md: b3505f92fd3967c936376915d30aa9e0998cbe1b -2026-07-13-documentation-site-projection.zh.md: ce1e7ee2a348751ca7d8a5b765be2aee7526edef +2026-07-13-documentation-site-projection.md: eaaf7cfc50b5aba348533ea4f5a4a1f50641f30f +2026-07-13-documentation-site-projection.zh.md: c954fcc41c874007330a66b93cea50fef01f8e3e diff --git a/.agents/notes/implemented/process/2026-07-13-documentation-site-projection.md b/.agents/notes/implemented/process/2026-07-13-documentation-site-projection.md index b3505f92fd..eaaf7cfc50 100644 --- a/.agents/notes/implemented/process/2026-07-13-documentation-site-projection.md +++ b/.agents/notes/implemented/process/2026-07-13-documentation-site-projection.md @@ -16,7 +16,7 @@ Canonical Markdown remains in the repository tier that owns it. Product-facing g `scripts/project-doc-site.ts` projects the manifest into the ignored `website/.generated/` directory before VitePress starts or builds. The generated tree follows public routes so VitePress navigation, locale detection, and local search share the same route vocabulary. Each page receives an `editSource` frontmatter field pointing to its canonical repository file; the edit-link callback reads only that page data, so public URLs remain independent of the source layout. -Locale home projections retain only the canonical YAML frontmatter. The repository-facing body keeps its H1 and bilingual source links, while the frontmatter implements the [locale-preserving quick-start redirect](../simplification/2026-08-11-quickstart-documentation-home.md) and the site navigation owns locale switching. +Locale home projections retain only the canonical YAML frontmatter. The repository-facing body keeps its H1 and bilingual source links, while the frontmatter implements the [locale-preserving quick-start redirect](../../../../docs/user/index.md) and the site navigation owns locale switching. The projector parses Markdown links without reserializing the document. A link to another published source becomes a site-relative route; a link to an unpublished repository file becomes a source link under the `deepseek-ai/deepseek-harness` repository home; a repository image is copied into the generated tree and referenced from there ([why](2026-08-06-doc-site-carries-its-images.md)). Missing relative targets fail projection. Unit tests pin these transformations, and `docs:check` runs the projector tests plus a production VitePress build as part of `doc-sync` and the parallel documentation gates. diff --git a/.agents/notes/implemented/process/2026-07-13-documentation-site-projection.zh.md b/.agents/notes/implemented/process/2026-07-13-documentation-site-projection.zh.md index ce1e7ee2a3..c954fcc41c 100644 --- a/.agents/notes/implemented/process/2026-07-13-documentation-site-projection.zh.md +++ b/.agents/notes/implemented/process/2026-07-13-documentation-site-projection.zh.md @@ -16,7 +16,7 @@ Status: implemented 在 VitePress 启动或构建之前，`scripts/project-doc-site.ts` 会把 manifest 投影到被忽略的 `website/.generated/` 目录。生成目录树遵循公开路由，使 VitePress 导航、locale 检测和本地搜索使用同一套路由命名。每个页面都会获得一个指向其权威仓库文件的 `editSource` frontmatter 字段；编辑链接回调只读取该页面的数据，因此公开 URL 与源文件布局彼此独立。 -各 locale 的首页投影只保留权威 YAML frontmatter。面向仓库的正文保留其 H1 和双语源文件链接；frontmatter 实现[保持 locale 不变的快速开始重定向](../simplification/2026-08-11-quickstart-documentation-home.zh.md)，网站导航负责切换 locale。 +各 locale 的首页投影只保留权威 YAML frontmatter。面向仓库的正文保留其 H1 和双语源文件链接；frontmatter 实现[保持 locale 不变的快速开始重定向](../../../../docs/user/index.zh.md)，网站导航负责切换 locale。 投影器解析 Markdown 链接，但不会重新序列化文档。指向另一个已发布源文件的链接会变成站内相对路由；指向未发布仓库文件的链接会变成 `deepseek-ai/deepseek-harness` 仓库主页下的源文件链接；仓库图片会被拷贝进生成树并从那里引用（[原因](2026-08-06-doc-site-carries-its-images.zh.md)）。相对目标不存在时，投影会失败。单元测试会锁定这些转换行为，`docs:check` 则运行投影器测试和 VitePress 生产构建，并将二者纳入 `doc-sync` 和并行文档门禁。 diff --git a/.agents/notes/implemented/process/2026-07-22-product-first-root-readme.i18n.yaml b/.agents/notes/implemented/process/2026-07-22-product-first-root-readme.i18n.yaml index ab409d231d..a76dd67754 100644 --- a/.agents/notes/implemented/process/2026-07-22-product-first-root-readme.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-22-product-first-root-readme.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-22-product-first-root-readme.md -2026-07-22-product-first-root-readme.md: 65d6166773b09446f0d00e749678accede58e5eb -2026-07-22-product-first-root-readme.zh.md: 4f289a96ffdf9538627988feba8fc3a77cd7d719 +2026-07-22-product-first-root-readme.md: 24c6dc04f24bd758d8955824a17b1d99801ecd16 +2026-07-22-product-first-root-readme.zh.md: f5c0d821e916423c92258649c22ceed222c06439 diff --git a/.agents/notes/implemented/process/2026-07-22-product-first-root-readme.md b/.agents/notes/implemented/process/2026-07-22-product-first-root-readme.md index 65d6166773..24c6dc04f2 100644 --- a/.agents/notes/implemented/process/2026-07-22-product-first-root-readme.md +++ b/.agents/notes/implemented/process/2026-07-22-product-first-root-readme.md @@ -16,7 +16,7 @@ A note before installation thanks internal testers, states that features and exp The user-surface section adds the ACP automation server and Python/JSON-RPC SDK beside the existing Web, TUI, and headless entries. The installed TUI remains the single `dsh` command; the Web instructions build the active checkout before running `dsh web`, and custom or reused checkout paths stay explicit. These launch paths must remain executable through a real PTY and a production build/HTTP smoke, respectively. The capability paragraph keeps its compact inventory style while adding the shipped PTY, LSP, web, goal, planning, task, sandbox, approval, settings, credentials, session-query, and telemetry families and stating that compositions select subsets. One adjacent bullet records the authoritative-session-log rule because persistence, replay, queries, telemetry, and interfaces depend on it. -Detailed package and service inventories remain at their owning documentation. The English and Chinese README sides share the same technical structure, while their community sections continue to point to the primary channel for each language audience. The documentation website keeps a separate [quick-start entry route](../simplification/2026-08-11-quickstart-documentation-home.md) instead of presenting another product landing page. +Detailed package and service inventories remain at their owning documentation. The English and Chinese README sides share the same technical structure, while their community sections continue to point to the primary channel for each language audience. The documentation website keeps a separate [quick-start entry route](../../../../docs/user/index.md) instead of presenting another product landing page. ## Alternatives considered diff --git a/.agents/notes/implemented/process/2026-07-22-product-first-root-readme.zh.md b/.agents/notes/implemented/process/2026-07-22-product-first-root-readme.zh.md index 4f289a96ff..f5c0d821e9 100644 --- a/.agents/notes/implemented/process/2026-07-22-product-first-root-readme.zh.md +++ b/.agents/notes/implemented/process/2026-07-22-product-first-root-readme.zh.md @@ -16,7 +16,7 @@ Status: implemented 用户入口章节在已有的 Web、TUI 和 Headless 入口旁补充 ACP（Agent Client Protocol）自动化服务器和 Python/JSON-RPC SDK。安装后的 TUI 仍只需执行一条 `dsh` 命令；Web 说明要求先构建当前检出，再运行 `dsh web`，并明确处理自定义或复用的检出路径。这两条启动路径必须分别能在真实 PTY 与生产构建／HTTP 冒烟中原样执行。能力段落沿用简洁清单的写法，补充已经交付的 PTY、LSP、Web、目标、规划、任务、沙箱、审批、设置、凭据、会话查询和遥测等能力类别，并说明不同组合只选用其中一部分。相邻的一条列表项说明权威会话日志规则，因为持久化、回放、查询、遥测和各类接口都依赖它。 -包与服务的完整清单仍由各自的归属文档维护。中英文 README 采用相同的技术结构，但社区章节仍分别指向各自语言受众的主要交流渠道。文档网站保留独立的[快速开始入口路由](../simplification/2026-08-11-quickstart-documentation-home.zh.md)，不另行呈现产品首页。 +包与服务的完整清单仍由各自的归属文档维护。中英文 README 采用相同的技术结构，但社区章节仍分别指向各自语言受众的主要交流渠道。文档网站保留独立的[快速开始入口路由](../../../../docs/user/index.zh.md)，不另行呈现产品首页。 ## 考虑过的替代方案 diff --git a/.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.i18n.yaml b/.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.i18n.yaml index d0c312c97c..4fe05d0ede 100644 --- a/.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.md -2026-07-26-briefed-minimal-translation-updates.md: 1c032fa07167ec2407d0f46707f942ba0c830494 -2026-07-26-briefed-minimal-translation-updates.zh.md: 9cb0d965f37442c9e6d3587d23aa340368fc9fa0 +2026-07-26-briefed-minimal-translation-updates.md: 049e0a2771c65972bf42bae62cf1a18a11841b83 +2026-07-26-briefed-minimal-translation-updates.zh.md: 1574617bd10e020853ea11c345d5caebfc98cae4 diff --git a/.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.md b/.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.md index 1c032fa071..049e0a2771 100644 --- a/.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.md +++ b/.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.md @@ -34,7 +34,7 @@ A second head-to-head replay on the same ten examples compared this note's shipp - **Whole-document re-translation as the update path** (what a naive pipeline does) — rejected on benchmark evidence: preservation collapse, terminology drift, highest cost. The contract's minimal-update rule survives with data behind it. - **Batching several pairs per subagent** — rejected: no measured saving (briefings already deduplicate the fixed content), and one stalled or confused pair holds the others hostage. - **Per-paragraph translation-memory records in the sidecar** (segment hashes instead of whole-file hashes) — rejected: paragraph boundaries may legitimately differ across the pair, either side can be authored first, and the records would bloat and conflict in merges. Span mapping computed on demand from the existing whole-file hashes recovers the same alignment when it is trustworthy and says so when it is not. -- **An update mode in the automated prompt pipeline (prompt-v5)** — deferred, not designed here: nothing drives [scripts/translation-prompt.ts](../../../../scripts/translation-prompt.ts) today, and the agent path was the live cost center. The pipeline keeps its whole-document v4 contract until it has a consumer. +- **An update mode in the automated prompt pipeline (prompt-v5)** — deferred, not designed here: no shipped consumer drives [scripts/translation-prompt.ts](../../../../scripts/translation-prompt.ts), and the agent path was the live cost center. The pipeline keeps its whole-document v4 contract until it has a consumer. ## Consequences diff --git a/.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.zh.md b/.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.zh.md index 9cb0d965f3..1574617bd1 100644 --- a/.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.zh.md +++ b/.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.zh.md @@ -34,7 +34,7 @@ Status: implemented - **把整篇重译作为更新路径**（朴素流水线的做法）：依据基准测试证据否决，理由是保留度崩塌、术语漂移、成本最高。约定的最小更新规则得以延续，且从此有数据支撑。 - **每个 subagent 批量处理多对文档**：否决。没有实测出节省（简报本身已对固定内容做了去重），而且一对文档停滞或陷入混乱会把其余配对一并拖住。 - **在伴随记录中保存逐段的翻译记忆条目**（用分段 hash 取代整文件 hash）：否决。配对两侧的段落边界可以合理地不同，任一侧都可能先撰写，这类条目还会不断膨胀并在合并时产生冲突。基于现有整文件 hash 按需计算的区间映射，在对齐可信时能恢复同样的对齐关系，不可信时会明确说明。 -- **给自动提示词流水线加一个更新模式（prompt-v5）**：推迟，本文不做设计。今天没有任何调用方在驱动 [scripts/translation-prompt.ts](../../../../scripts/translation-prompt.ts)，实际的成本中心是 agent 路径。流水线在拥有消费方之前，维持其整篇文档的 v4 约定。 +- **给自动提示词流水线加一个更新模式（prompt-v5）**：推迟，本文不做设计。没有已交付消费方驱动 [scripts/translation-prompt.ts](../../../../scripts/translation-prompt.ts)，实际的成本中心是 agent 路径。流水线在拥有消费方之前，维持其整篇文档的 v4 约定。 ## 后果 diff --git a/.agents/notes/implemented/process/2026-07-26-pnpm-action-setup-for-symmetric-ci-caching.i18n.yaml b/.agents/notes/implemented/process/2026-07-26-pnpm-action-setup-for-symmetric-ci-caching.i18n.yaml index 9aa6dfc8d2..aec2498598 100644 --- a/.agents/notes/implemented/process/2026-07-26-pnpm-action-setup-for-symmetric-ci-caching.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-26-pnpm-action-setup-for-symmetric-ci-caching.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-26-pnpm-action-setup-for-symmetric-ci-caching.md -2026-07-26-pnpm-action-setup-for-symmetric-ci-caching.md: c998986501eacfca88c8f7125f7ff4bc7f9a7101 -2026-07-26-pnpm-action-setup-for-symmetric-ci-caching.zh.md: 6e1b61e64995d0fb68c7509a0cd374b2a98d16ae +2026-07-26-pnpm-action-setup-for-symmetric-ci-caching.md: d485098f7ee04596e77322089fa0f6f45020024a +2026-07-26-pnpm-action-setup-for-symmetric-ci-caching.zh.md: 47bd525377d6c358891b238373410049987f5ee1 diff --git a/.agents/notes/implemented/process/2026-07-26-pnpm-action-setup-for-symmetric-ci-caching.md b/.agents/notes/implemented/process/2026-07-26-pnpm-action-setup-for-symmetric-ci-caching.md index c998986501..d485098f7e 100644 --- a/.agents/notes/implemented/process/2026-07-26-pnpm-action-setup-for-symmetric-ci-caching.md +++ b/.agents/notes/implemented/process/2026-07-26-pnpm-action-setup-for-symmetric-ci-caching.md @@ -23,7 +23,7 @@ Outside `landlock-run.yml`, each workflow that installed pnpm hand-provisioned i - **Convert serial-linux's store cache.** Rejected during implementation: the original proposal counted serial-linux among the symmetric setups, but its cache step is the producer half of the enterprise jobs' restore-only pairing — moving it to `setup-node`'s key format is the enterprise conversion by another route. - **Stop at the cache-bearing workflows and leave the other `corepack enable` sites.** Rejected: provisioning and caching are separable concerns, and leaving corepack in the cache-less jobs kept the future break and two provisioning idioms for no benefit. - **Rely on the runner image's Yarn.** Rejected: the hosted image exposes Yarn 1.22 after Corepack is removed, while the generated-project e2e requires Yarn 2 or newer. A locked root dev dependency makes that coverage independent of runner image contents. -- **A composite action wrapping action-setup + setup-node.** Rejected for now: the remaining per-job variation (node-version matrices, per-platform conditional caching, the restore-only pairing) is deliberate policy, not boilerplate — a wrapper would grow mirroring inputs or flatten a real asymmetry, and the two-line pair is already near the floor. +- **A composite action wrapping action-setup plus setup-node.** Rejected: the remaining per-job variation (Node-version matrices, per-platform conditional caching, and the restore-only pairing) is deliberate policy, not boilerplate. A wrapper would grow matching inputs or flatten a real asymmetry, while the two-line pair is already near the floor. ## Consequences diff --git a/.agents/notes/implemented/process/2026-07-26-pnpm-action-setup-for-symmetric-ci-caching.zh.md b/.agents/notes/implemented/process/2026-07-26-pnpm-action-setup-for-symmetric-ci-caching.zh.md index 6e1b61e649..47bd525377 100644 --- a/.agents/notes/implemented/process/2026-07-26-pnpm-action-setup-for-symmetric-ci-caching.zh.md +++ b/.agents/notes/implemented/process/2026-07-26-pnpm-action-setup-for-symmetric-ci-caching.zh.md @@ -23,7 +23,7 @@ Status: implemented - **转换 serial-linux 的 store 缓存。** 实现期间否决：原提案曾把 serial-linux 计入对称设置，但其缓存步骤是企业作业只恢复不上传配对中的生产者一端——把它改成 `setup-node` 的键格式，等于换条路径做了企业作业的转换。 - **只转换带缓存的工作流，留下其余出现 `corepack enable` 的位置。** 否决：提供 pnpm 与缓存是可分离的关注点，在无缓存作业里留下 corepack 只会保留未来失效点和两套并存的提供方式，毫无收益。 - **依赖 runner 镜像自带的 Yarn。** 否决：Corepack 移除后，托管镜像提供的是 Yarn 1.22，而 generated-project e2e 要求 Yarn 2 或更高版本。锁定版本的根开发依赖让该项覆盖率不再受 runner 镜像内容影响。 -- **用一个组合 action 包装 action-setup + setup-node。** 暂不采纳：剩余的按作业差异（node 版本矩阵、按平台的条件缓存、只恢复不上传配对）是刻意采用的策略而非样板——包装层要么不得不增加与这些差异一一对应的输入，要么抹平一处真实的不对称，而两行的组合已接近下限。 +- **用一个组合 action 包装 action-setup 加 setup-node。**不予采纳：剩余的按作业差异（Node 版本矩阵、按平台的条件缓存、只恢复不上传配对）是刻意采用的策略而非样板。包装层要么需要增加与这些差异一一对应的输入，要么会抹平真实的不对称，而两行组合已经接近下限。 ## 后果 diff --git a/.agents/notes/implemented/process/2026-08-03-package-anchored-subsystem-pages.i18n.yaml b/.agents/notes/implemented/process/2026-08-03-package-anchored-subsystem-pages.i18n.yaml index 04138e9332..07dedddfee 100644 --- a/.agents/notes/implemented/process/2026-08-03-package-anchored-subsystem-pages.i18n.yaml +++ b/.agents/notes/implemented/process/2026-08-03-package-anchored-subsystem-pages.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-08-03-package-anchored-subsystem-pages.md -2026-08-03-package-anchored-subsystem-pages.md: 40f330d0feaca519bdc683e1992597b4be46cd8e -2026-08-03-package-anchored-subsystem-pages.zh.md: 25f96e7411728e5cb49cd663dc5cd087688b068c +2026-08-03-package-anchored-subsystem-pages.md: 71e4c2a28f3f556e0d3df2242b410899df763e48 +2026-08-03-package-anchored-subsystem-pages.zh.md: 0f29a26e456ad7883d00ad51ae60aadc4acb5358 diff --git a/.agents/notes/implemented/process/2026-08-03-package-anchored-subsystem-pages.md b/.agents/notes/implemented/process/2026-08-03-package-anchored-subsystem-pages.md index 40f330d0fe..71e4c2a28f 100644 --- a/.agents/notes/implemented/process/2026-08-03-package-anchored-subsystem-pages.md +++ b/.agents/notes/implemented/process/2026-08-03-package-anchored-subsystem-pages.md @@ -16,7 +16,7 @@ Every type a generated signature references must resolve somewhere in the folder Every `packages//README.md` pair is a thin entry point in one shape: a why-first intro paragraph, a package table (Package / Role / ctx key), and a closing pointer to the owning subsystems page. Load-bearing prose that outgrows that shape relocates to the owning subsystems page rather than being deleted. -The [subsystems README](../../../../docs/subsystems/README.md) indexes every page in the folder on both language sides; `scripts/project-doc-site.spec.ts` enforces one table row per page, so a page added by a later PR (or absorbed in a merge) cannot silently miss the index. +The [subsystems README](../../../../docs/subsystems/README.md) indexes every page in the folder on both language sides; `scripts/project-doc-site.spec.ts` enforces one table row per page, so an added or merged page cannot silently miss the index. ## Alternatives considered diff --git a/.agents/notes/implemented/process/2026-08-03-package-anchored-subsystem-pages.zh.md b/.agents/notes/implemented/process/2026-08-03-package-anchored-subsystem-pages.zh.md index 25f96e7411..0f29a26e45 100644 --- a/.agents/notes/implemented/process/2026-08-03-package-anchored-subsystem-pages.zh.md +++ b/.agents/notes/implemented/process/2026-08-03-package-anchored-subsystem-pages.zh.md @@ -16,7 +16,7 @@ Status: implemented 每个 `packages//README.md` 配对都是统一形状的精简入口：一段先说明「为什么」的介绍、一张包表格（包 / 角色 / ctx 键）、一个指向对应子系统页面的收尾链接。如果承载关键信息的正文超出这一结构所能容纳的范围，就将其迁移到对应的子系统页面，而非删除。 -[子系统 README](../../../../docs/subsystems/README.zh.md) 在中英文两侧索引目录中的每一页；`scripts/project-doc-site.spec.ts` 强制每个页面对应一个表格行，因此后续 PR 新增（或合并吸收）的页面无法悄悄缺席索引。 +[子系统 README](../../../../docs/subsystems/README.zh.md) 在中英文两侧索引目录中的每一页；`scripts/project-doc-site.spec.ts` 强制每个页面对应一个表格行，因此新增或合并吸收的页面无法悄悄缺席索引。 ## 考虑过的替代方案 diff --git a/.agents/notes/implemented/process/2026-08-09-committed-artifact-citations.i18n.yaml b/.agents/notes/implemented/process/2026-08-09-committed-artifact-citations.i18n.yaml index ba1eda2a11..fa29e34aca 100644 --- a/.agents/notes/implemented/process/2026-08-09-committed-artifact-citations.i18n.yaml +++ b/.agents/notes/implemented/process/2026-08-09-committed-artifact-citations.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-08-09-committed-artifact-citations.md -2026-08-09-committed-artifact-citations.md: 044f7683d51ebf2038f56d2b5a27755ecc9be6d5 -2026-08-09-committed-artifact-citations.zh.md: 620a99195f9a9c0337b1145d87ba1f8a042eb430 +2026-08-09-committed-artifact-citations.md: a84b25545b97b6df62b3d51da895b4c7f8887ccf +2026-08-09-committed-artifact-citations.zh.md: 8cff257fd22d449d965067343e6aed4413b8eae7 diff --git a/.agents/notes/implemented/process/2026-08-09-committed-artifact-citations.md b/.agents/notes/implemented/process/2026-08-09-committed-artifact-citations.md index 044f7683d5..a84b25545b 100644 --- a/.agents/notes/implemented/process/2026-08-09-committed-artifact-citations.md +++ b/.agents/notes/implemented/process/2026-08-09-committed-artifact-citations.md @@ -17,6 +17,8 @@ Durable prose — comments, JSDoc, docs, notes, test comments and titles — cit - Fixed regressions are pinned as present-tense counterfactuals ("without X, Y happens"; "a naive X would…"), never as repo history ("used to Y"). - Implemented notes state shipped reality: a "deferred to a later PR" claim whose target shipped names the shipped note instead. - Recorded fixtures, snapshots, and archived notes are exempt: recorded model output and sealed history keep their original voice. Inside a note's change-story sections, a historical stage name ("the first cut shipped X") is current-state-safe; indexical stamps ("this cut") stay banned everywhere. +- Recall probes use lexical boundaries and are calibrated against a known positive and a near-miss negative. Authoring-language probes target the opposite-language surface instead of treating the complete Chinese corpus as untranslated residue. +- Owner-first edits trace every generated consumer. Verbatim code fences are copied byte-for-byte across bilingual pairs; model- or user-visible wording changes only with its owning behavior evidence, otherwise the audit leaves it unchanged and reports the deferral. One repo-wide purge applied these rules across the prose surfaces, including the generator-owned templates (`scripts/gen-doc-graphs.ts`, `scripts/gen-tool-catalog.ts`, the typert generator's page notice) with regeneration, the type-equiv source JSDoc with page re-pastes, and the bilingual counterparts with pair re-records. The [dsh-trim-cot-leakage skill](../../../skills/dsh-trim-cot-leakage/SKILL.md) operationalizes these rules: the audit taxonomy, the committed recall batteries, and few-shot examples for deciding what to keep or delete. diff --git a/.agents/notes/implemented/process/2026-08-09-committed-artifact-citations.zh.md b/.agents/notes/implemented/process/2026-08-09-committed-artifact-citations.zh.md index 620a99195f..8cff257fd2 100644 --- a/.agents/notes/implemented/process/2026-08-09-committed-artifact-citations.zh.md +++ b/.agents/notes/implemented/process/2026-08-09-committed-artifact-citations.zh.md @@ -17,6 +17,8 @@ Status: implemented - 已修复的回归以现在时反事实句固定下来（「没有 X 就会发生 Y」、「朴素的 X 会……」），绝不写成仓库历史（「过去曾 Y」）。 - 已实现的 Agent Note 陈述已交付的现实：「推迟到后续 PR」的说法若其目标已经交付，就改为点名那篇已交付的 note。 - 已录制的 fixture（测试前置数据）、快照与已归档的 Agent Note 不受此约束：已录制的模型输出与封存的历史保持原有行文。在 note 的变更故事段落内，历史阶段名称（「首版交付了 X」）符合只描述当前状态的要求；「this cut」这类指示当前版本的标记在任何地方都仍被禁止。 +- 召回检索使用词法边界，并以一个已知正例和一个近似反例校准。写作语言残留检索仅在另一语言的行文表面运行，不把整个中文语料库当作未翻译残留。 +- 先改归属源时追踪每个生成消费方。围栏代码块在双语配对中逐字节复制；模型或用户可见的文字只有在归属场景的行为证据随同更新时才改，否则审计保持原文并报告推迟项。 一次全仓库清理把这些规则应用到了各个行文表面，包括生成器持有的模板（`scripts/gen-doc-graphs.ts`、`scripts/gen-tool-catalog.ts`、typert 生成器的页面提示语，改后重新生成）、type-equiv 源码中的 JSDoc（改后重新同步到文档页）以及双语对侧文件（改后重新记录配对）。[dsh-trim-cot-leakage 技能](../../../skills/dsh-trim-cot-leakage/SKILL.md)把这些规则落地为可执行工作流：审计分类法、已提交的成批召回检索，以及用于判断保留或删除内容的少样本示例。 diff --git a/.agents/notes/implemented/process/2026-08-09-concrete-prose-names-actors-and-recorded-facts.i18n.yaml b/.agents/notes/implemented/process/2026-08-09-concrete-prose-names-actors-and-recorded-facts.i18n.yaml index a85d782857..5892d118ec 100644 --- a/.agents/notes/implemented/process/2026-08-09-concrete-prose-names-actors-and-recorded-facts.i18n.yaml +++ b/.agents/notes/implemented/process/2026-08-09-concrete-prose-names-actors-and-recorded-facts.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-08-09-concrete-prose-names-actors-and-recorded-facts.md -2026-08-09-concrete-prose-names-actors-and-recorded-facts.md: b7df5403ea11ff8ba32be0f9bede5a32d5bcd6ee -2026-08-09-concrete-prose-names-actors-and-recorded-facts.zh.md: 8a45d452bfd98c1fe87a9a42bd4930273d034ca8 +2026-08-09-concrete-prose-names-actors-and-recorded-facts.md: 887a3666501a97e0930fe7eb4282603f537c17e8 +2026-08-09-concrete-prose-names-actors-and-recorded-facts.zh.md: 0202be5c22c75ff4feec225cdff12b772d64d1cf diff --git a/.agents/notes/implemented/process/2026-08-09-concrete-prose-names-actors-and-recorded-facts.md b/.agents/notes/implemented/process/2026-08-09-concrete-prose-names-actors-and-recorded-facts.md index b7df5403ea..887a366650 100644 --- a/.agents/notes/implemented/process/2026-08-09-concrete-prose-names-actors-and-recorded-facts.md +++ b/.agents/notes/implemented/process/2026-08-09-concrete-prose-names-actors-and-recorded-facts.md @@ -16,6 +16,8 @@ Maintained prose names the exact actor, action, source, event, field, file, or p The rule applies to Markdown, READMEs, active Agent Notes, JSDoc and comments, prompts, diagnostics, and user-visible strings. An audit judges each sentence separately; it does not replace a term across the repository with one preferred synonym. The edited sentence preserves actor, action, conditions, order, modality, exceptions, ownership, failure behavior, and consequences. +Comments retain only facts that nearby code cannot express. Documentation stays at its owning level and omits private control flow and rare implementation cases unless they change supported behavior, safe use, compatibility, data integrity, security, or another maintained contract. The [simplification workflow](../../../skills/dsh-find-simplifications/SKILL.md) applies this rule while surveying code and prose together. + Exact code identifiers, public APIs, durable fields, protocol members, type names, headings with external references, and filenames stay unchanged unless a coordinated contract rename is independently required. Surrounding prose explains their fields or behavior directly. Generated documents and catalogs update from their owning source. Before using `contract`, `boundary`, or `shape`, writers check whether the sentence means a more specific rule, operation, data structure, field set, validation point, timing point, API, type, or failure condition. `Contract` remains correct for preconditions, postconditions, invariants, compatibility promises, and other obligations that callers, callees, implementers, providers, producers, or consumers rely on. `Boundary` remains correct for a literal security, trust, wire, process, serialization, transaction, or lifecycle division. `Shape` remains correct when the structural form itself is the subject and no narrower term such as fields, schema, type, union variant, file layout, or export form states the fact. Code and API names containing these words remain unchanged unless a separate coordinated rename is required. diff --git a/.agents/notes/implemented/process/2026-08-09-concrete-prose-names-actors-and-recorded-facts.zh.md b/.agents/notes/implemented/process/2026-08-09-concrete-prose-names-actors-and-recorded-facts.zh.md index 8a45d452bf..0202be5c22 100644 --- a/.agents/notes/implemented/process/2026-08-09-concrete-prose-names-actors-and-recorded-facts.zh.md +++ b/.agents/notes/implemented/process/2026-08-09-concrete-prose-names-actors-and-recorded-facts.zh.md @@ -16,6 +16,8 @@ Status: implemented 该规则适用于 Markdown、README、活跃 Agent Note、JSDoc 与注释、提示词、诊断信息和用户可见字符串。审查会分别判断每个句子，不会在整个仓库中用一个偏好的近义词统一替换某个术语。编辑后的句子保留执行者、动作、条件、顺序、情态、例外、归属、失败行为和后果。 +注释只保留附近代码无法表达的事实。文档停留在内容归属的层级；除非私有控制流或罕见实现情形会改变受支持行为、安全使用、兼容性、数据完整性、安全保障或另一项持续维护的约定，否则文档不描述它们。[简化工作流](../../../skills/dsh-find-simplifications/SKILL.md)在同时巡查代码与行文时应用此规则。 + 除非另一项独立需求明确要求协调重命名约定，否则确切的代码标识符、公开 API、持久字段、协议成员、类型名、带有外部引用的标题和文件名均保持不变。它们周围的行文直接说明其字段或行为。生成的文档和目录在维护它们的源文件修改后更新。 使用 `contract`、`boundary` 或 `shape` 之前，写作者要确认句子是否实际指更具体的规则、操作、数据结构、字段集合、校验点、时间点、API、类型或失败条件。调用方、被调用方、实现方、提供方、生产方或消费方依赖的前置条件、后置条件、不变量、兼容性承诺及其他义务仍可准确称为 `contract`。真实的安全、信任、wire、进程、序列化、事务或生命周期分界仍可准确称为 `boundary`。当结构形式本身就是主题，且字段、schema、类型、联合变体、文件布局或导出形式等更窄的词无法说明事实时，仍可使用 `shape`。除非另一项独立需求要求协调重命名，否则包含这些词的代码和 API 名称保持不变。 diff --git a/.agents/notes/implemented/process/2026-08-09-md-fragment-anchor-gate.i18n.yaml b/.agents/notes/implemented/process/2026-08-09-md-fragment-anchor-gate.i18n.yaml index d431553f1f..4d85c63d60 100644 --- a/.agents/notes/implemented/process/2026-08-09-md-fragment-anchor-gate.i18n.yaml +++ b/.agents/notes/implemented/process/2026-08-09-md-fragment-anchor-gate.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-08-09-md-fragment-anchor-gate.md -2026-08-09-md-fragment-anchor-gate.md: e02a917bedd9649a2326e3fb1f53072ac05c88a8 -2026-08-09-md-fragment-anchor-gate.zh.md: 09cd2326fd11457d62cab77fe566b5d71ffc8e7e +2026-08-09-md-fragment-anchor-gate.md: a5c4029f5b11f464e09356915d5d2f9134bee616 +2026-08-09-md-fragment-anchor-gate.zh.md: 50c941b3e2d43e4991ee3a748b1b50b36611e34d diff --git a/.agents/notes/implemented/process/2026-08-09-md-fragment-anchor-gate.md b/.agents/notes/implemented/process/2026-08-09-md-fragment-anchor-gate.md index e02a917bed..a5c4029f5b 100644 --- a/.agents/notes/implemented/process/2026-08-09-md-fragment-anchor-gate.md +++ b/.agents/notes/implemented/process/2026-08-09-md-fragment-anchor-gate.md @@ -14,7 +14,7 @@ English | [中文](2026-08-09-md-fragment-anchor-gate.zh.md) The slug function differs from `gen-cordis-catalog`'s region-anchor slugger (which drops underscores): the generator's headings are always reachable through its explicit `` anchors, so the two need not share one rule. Chinese pair sides follow the existing repository convention (`docs/glossary.zh.md`, `docs/cordis-primer.zh.md`): keep the English fragment in the link and place an explicit `` before the Chinese heading, so both language sides expose identical anchors. -The 15 broken fragments are fixed in the same change: stale slugs retargeted to the current headings, the relocated no-timeout contract now linked at its owning group README, and four zh documents given explicit anchors. `docs/AGENTS.md` and the `dsh-doc-standards` skill no longer prescribe the manual anchor grep for Markdown links; it survives only for anchors cited from TypeScript strings whose output never reaches gate-scanned Markdown (today's three all render into scanned pages, so the gate covers them through the committed output). +The 15 broken fragments are fixed in the same change: stale slugs retargeted to the current headings, the relocated no-timeout contract now linked at its owning group README, and four zh documents given explicit anchors. `docs/AGENTS.md` and the `dsh-doc-standards` skill no longer prescribe the manual anchor grep for Markdown links; it survives only for anchors cited from TypeScript strings whose output never reaches gate-scanned Markdown (the three scanned references all render into scanned pages, so the gate covers them through the committed output). ## Verification diff --git a/.agents/notes/implemented/process/2026-08-09-md-fragment-anchor-gate.zh.md b/.agents/notes/implemented/process/2026-08-09-md-fragment-anchor-gate.zh.md index 09cd2326fd..50c941b3e2 100644 --- a/.agents/notes/implemented/process/2026-08-09-md-fragment-anchor-gate.zh.md +++ b/.agents/notes/implemented/process/2026-08-09-md-fragment-anchor-gate.zh.md @@ -14,7 +14,7 @@ Status: implemented slug 函数与 `gen-cordis-catalog` 的区块锚点 slugger 不同（后者丢弃下划线）：生成器的标题总能通过其显式 `` 锚点到达，两者无需共享一条规则。中文侧沿用既有语料惯例（`docs/glossary.zh.md`、`docs/cordis-primer.zh.md`）：链接保留英文 fragment，在中文标题前放置显式 ``，使两个语言侧暴露相同的锚点。 -15 条坏 fragment 在同一变更中修复：陈旧 slug 重定向到当前标题，搬迁的无超时约定改链其属主 group README，四份中文文档补上显式锚点。`docs/AGENTS.md` 与 `dsh-doc-standards` skill 不再要求为 Markdown 链接手工 grep 锚点；人工 grep 只对输出从不进入受检 Markdown 的 TypeScript 字符串锚点保留（当下三处全部渲染进受检页面，gate 经由提交的产物覆盖它们）。 +15 条坏 fragment 在同一变更中修复：陈旧 slug 重定向到当前标题，搬迁的无超时约定改链其属主 group README，四份中文文档补上显式锚点。`docs/AGENTS.md` 与 `dsh-doc-standards` skill 不再要求为 Markdown 链接手工 grep 锚点；人工 grep 只对输出从不进入受检 Markdown 的 TypeScript 字符串锚点保留（扫描到的三处全部渲染进受检页面，gate 经由提交的产物覆盖它们）。 ## 验证 diff --git a/.agents/notes/implemented/process/2026-08-12-documentation-site-navigation-and-chrome.i18n.yaml b/.agents/notes/implemented/process/2026-08-12-documentation-site-navigation-and-chrome.i18n.yaml deleted file mode 100644 index ef5f11a4f8..0000000000 --- a/.agents/notes/implemented/process/2026-08-12-documentation-site-navigation-and-chrome.i18n.yaml +++ /dev/null @@ -1,6 +0,0 @@ -# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each -# side as of the last confirmed-consistent state. Both languages carry equal authority; -# after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-08-12-documentation-site-navigation-and-chrome.md -2026-08-12-documentation-site-navigation-and-chrome.md: 03cd44b94f853725da33800e8c89886b1a657a0b -2026-08-12-documentation-site-navigation-and-chrome.zh.md: d0972f909e648278cb3cecb7788705b228f4b675 diff --git a/.agents/notes/implemented/process/2026-08-13-public-vendor-and-native-sequences.i18n.yaml b/.agents/notes/implemented/process/2026-08-13-public-vendor-and-native-sequences.i18n.yaml index a013e9705b..11d862cd85 100644 --- a/.agents/notes/implemented/process/2026-08-13-public-vendor-and-native-sequences.i18n.yaml +++ b/.agents/notes/implemented/process/2026-08-13-public-vendor-and-native-sequences.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-08-13-public-vendor-and-native-sequences.md -2026-08-13-public-vendor-and-native-sequences.md: ada7c3bcbe5feb288d67fe8e7ee7204dda6b4597 -2026-08-13-public-vendor-and-native-sequences.zh.md: ba9381dda94c09424d9218d3982bfdb128225e5d +2026-08-13-public-vendor-and-native-sequences.md: 2b2b8039f8233ff38dc17aa39368a6c6c7282bda +2026-08-13-public-vendor-and-native-sequences.zh.md: 8ee806f0d49d2038f30e396371a4f09977a7cc57 diff --git a/.agents/notes/implemented/process/2026-08-13-public-vendor-and-native-sequences.md b/.agents/notes/implemented/process/2026-08-13-public-vendor-and-native-sequences.md index ada7c3bcbe..2b2b8039f8 100644 --- a/.agents/notes/implemented/process/2026-08-13-public-vendor-and-native-sequences.md +++ b/.agents/notes/implemented/process/2026-08-13-public-vendor-and-native-sequences.md @@ -30,7 +30,7 @@ Access is a property of the package, not of a version: the twelve packages alrea ## Alternatives considered -**Flip the whole scope public at once.** Rejected for now: it would make the next dsh release public as a side effect of a manifest change rather than a deliberate release decision. Opening the two dependency sequences first is the order that keeps every published package installable at each step, and it is the precondition for opening dsh whenever that is decided. +**Flip the whole scope public at once.** Rejected: it would make a dsh release public as a side effect of a manifest change rather than a deliberate release decision. Opening the two dependency sequences first keeps every published package installable at each step and is a precondition for opening dsh. **Keep everything restricted and grant a read-only team instead.** `npm access grant read-only ` is per-package with no scope wildcard, so covering the set means one grant per package plus a standing reconciliation job for every package added afterwards. It also only reaches organization members, which does not serve an installable public artifact. diff --git a/.agents/notes/implemented/process/2026-08-13-public-vendor-and-native-sequences.zh.md b/.agents/notes/implemented/process/2026-08-13-public-vendor-and-native-sequences.zh.md index ba9381dda9..8ee806f0d4 100644 --- a/.agents/notes/implemented/process/2026-08-13-public-vendor-and-native-sequences.zh.md +++ b/.agents/notes/implemented/process/2026-08-13-public-vendor-and-native-sequences.zh.md @@ -30,7 +30,7 @@ access 是包的属性、不是版本的属性:已经以 restricted 发布的这 ## Alternatives considered -**一次性把整个 scope 改成 public。** 暂不采用:那会让下一次 dsh 发布因为一次 manifest 改动而顺带变成公开,而不是出自一个刻意的发布决定。先公开这两条依赖序列,是能让每一步的已发布包都保持可安装的顺序,也是将来决定公开 dsh 时的前置条件。 +**一次性把整个 scope 改成 public。**不予采纳：这会让一次 dsh 发布因 manifest 改动而顺带公开，而不是来自刻意的发布决定。先公开两条依赖序列，能让每一步的已发布包都保持可安装，也是公开 dsh 的前置条件。 **全部保持受限,改为授予一个只读 team。** `npm access grant read-only <包>` 是逐包的、没有 scope 通配,覆盖全集意味着每个包一次 grant,外加一个为后续新增包长期补齐的对账任务。它也只能覆盖组织成员,无法服务一个可安装的公开产物。 diff --git a/.agents/notes/implemented/process/2026-08-18-in-job-partitioned-coverage.i18n.yaml b/.agents/notes/implemented/process/2026-08-18-in-job-partitioned-coverage.i18n.yaml index d517367d9d..b48f880c61 100644 --- a/.agents/notes/implemented/process/2026-08-18-in-job-partitioned-coverage.i18n.yaml +++ b/.agents/notes/implemented/process/2026-08-18-in-job-partitioned-coverage.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-08-18-in-job-partitioned-coverage.md -2026-08-18-in-job-partitioned-coverage.md: f86c2dffb6d3d30fdccfa445c57043c5217e439b -2026-08-18-in-job-partitioned-coverage.zh.md: 62bb77511dd2c28b31e470288ff5c906dd346aeb +2026-08-18-in-job-partitioned-coverage.md: 532c145f5b66bd6574f9ee167c12c739fd4d7fa9 +2026-08-18-in-job-partitioned-coverage.zh.md: dc8a089a7c089338b775e49fdfe67f134f077704 diff --git a/.agents/notes/implemented/process/2026-08-18-in-job-partitioned-coverage.md b/.agents/notes/implemented/process/2026-08-18-in-job-partitioned-coverage.md index f86c2dffb6..532c145f5b 100644 --- a/.agents/notes/implemented/process/2026-08-18-in-job-partitioned-coverage.md +++ b/.agents/notes/implemented/process/2026-08-18-in-job-partitioned-coverage.md @@ -28,7 +28,7 @@ A normal failed test still emits a blob through `--coverage.reportOnFailure`, al ## Verification -`scripts/coverage-partitions.spec.ts` pins argument construction, package-script separator removal, one-worker partitions, the single merged threshold command, failed-test merging, failure diagnostics before complete-blob validation, waiting for sibling partitions after a spawn failure, and link-safe cleanup. `scripts/run-gates.spec.ts` pins opt-in selection, invalid-count rejection, the complete Windows inventory with its blocking split, and unbuffered streamed output. +`scripts/coverage-partitions.spec.ts` pins argument construction, package-script separator removal, one-worker partitions, the single merged threshold command, failed-test merging, failure diagnostics before complete-blob validation, waiting for sibling partitions after a spawn failure, and link-safe cleanup. `scripts/run-gates.spec.ts` pins opt-in selection, invalid-count rejection, the complete Windows inventory with its blocking split, and unbuffered streamed output. React fake-timer cases that can move between partitions advance timers inside `act()`; geometry-dependent portal tests stub their element rectangles so a different shard schedule cannot turn deferred updates or jsdom coordinates into coverage-only failures. Completed native Windows comparisons measured two partitions near 405 seconds and sixteen partitions at 112.66–122.01 seconds, but the sixteen-way schedule could put more than twenty active execution units beside build and exempt coverage on a 16-core runner. Eight partitions keep separate-process isolation while accepting a longer feedback path for a materially lower peak. Two Linux samples measured the conservative two-partition configuration at 276.68 and 282.27 seconds; that configuration was stable but halved the ordinary path's four instrumented workers. Four partitions restore that fan-out, for six total coverage execution units on the 16-core hosted runner and at most 36 across the failover VM's six runner instances. These values come from completed runs or fixed capacity bounds; an unfinished run crossing an arbitrary elapsed-time mark is not evidence for increasing concurrency. diff --git a/.agents/notes/implemented/process/2026-08-18-in-job-partitioned-coverage.zh.md b/.agents/notes/implemented/process/2026-08-18-in-job-partitioned-coverage.zh.md index 62bb77511d..dc8a089a7c 100644 --- a/.agents/notes/implemented/process/2026-08-18-in-job-partitioned-coverage.zh.md +++ b/.agents/notes/implemented/process/2026-08-18-in-job-partitioned-coverage.zh.md @@ -28,7 +28,7 @@ Status: implemented ## 验证 -`scripts/coverage-partitions.spec.ts` 固定了参数构造、包脚本分隔符移除、单 worker 分区、唯一一次合并阈值命令、失败测试合并、完整 blob 校验前的失败诊断、spawn 失败后等待兄弟分区，以及链接安全清理。`scripts/run-gates.spec.ts` 固定了显式启用、非法数量拒绝、完整 Windows 清单及其阻断性划分，以及不缓冲的流式输出。 +`scripts/coverage-partitions.spec.ts` 固定了参数构造、包脚本分隔符移除、单 worker 分区、唯一一次合并阈值命令、失败测试合并、完整 blob 校验前的失败诊断、spawn 失败后等待兄弟分区，以及链接安全清理。`scripts/run-gates.spec.ts` 固定了显式启用、非法数量拒绝、完整 Windows 清单及其阻断性划分，以及不缓冲的流式输出。可能在分区间移动的 React fake-timer 用例会在 `act()` 内推进计时器；依赖几何位置的 portal 测试会固定元素矩形，使不同分片调度不会把延迟更新或 jsdom 坐标变成只在覆盖率运行中出现的失败。 已完成的原生 Windows 对比中，双分区耗时约 405 秒，16 分区耗时 112.66–122.01 秒，但 16 路调度与构建、豁免覆盖率并行时，会在 16 核运行器上形成超过 20 个活动执行单元。8 个分区继续保留独立进程隔离，同时接受更长的反馈路径，以显著降低峰值。两个 Linux 样本中，保守的双分区配置耗时 276.68 秒和 282.27 秒；该配置运行稳定，却把普通路径原有的 4 个插桩 worker 减半。4 个分区恢复这份并发，使 16 核托管 runner 上的覆盖率执行单元总数为 6，故障切换虚拟机的 6 个 runner 实例最多合计 36 个执行单元。这些数值来自完整运行或固定容量上限；运行尚未结束时跨过任意耗时刻度，不构成增加并发的证据。 diff --git a/.agents/notes/implemented/simplification/2026-07-20-unwrap-injected-content-envelopes.i18n.yaml b/.agents/notes/implemented/simplification/2026-07-20-unwrap-injected-content-envelopes.i18n.yaml index 6131c6bb6a..dbf98656ed 100644 --- a/.agents/notes/implemented/simplification/2026-07-20-unwrap-injected-content-envelopes.i18n.yaml +++ b/.agents/notes/implemented/simplification/2026-07-20-unwrap-injected-content-envelopes.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/simplification/2026-07-20-unwrap-injected-content-envelopes.md -2026-07-20-unwrap-injected-content-envelopes.md: c1a7376c0c9ba737daf4e35af5808afb74aa3026 -2026-07-20-unwrap-injected-content-envelopes.zh.md: bbd2b2f2000f5086710d2040813b7beec7538fda +2026-07-20-unwrap-injected-content-envelopes.md: 7d14ada7cc1b88071ec4f07870afcfff6211a883 +2026-07-20-unwrap-injected-content-envelopes.zh.md: 813adfb818cac35da6e8c3b279b2e795fa99ad1a diff --git a/.agents/notes/implemented/simplification/2026-07-20-unwrap-injected-content-envelopes.md b/.agents/notes/implemented/simplification/2026-07-20-unwrap-injected-content-envelopes.md index c1a7376c0c..7d14ada7cc 100644 --- a/.agents/notes/implemented/simplification/2026-07-20-unwrap-injected-content-envelopes.md +++ b/.agents/notes/implemented/simplification/2026-07-20-unwrap-injected-content-envelopes.md @@ -19,7 +19,7 @@ Injected session content projects verbatim; the caller owns any framing. `derive The `ContextEnvelope` type and every `envelope` field are removed — `context/message` in `SessionEventMap`, `InjectOptions`, `HookContext`, and the `inject()`/`additionalContexts` plumbing in `dsh-agent-loop`. `agent-instructions` no longer requests `'raw'`; its self-framed content renders as before. The `renderTagged`/`renderContextEnvelope` helpers are deleted. `context/message.meta` still carries durable, model-hidden JSON state. -The `source` attribution the envelopes carried is not lost — it remains on the durable events; it simply no longer renders into the transcript. +The `source` attribution remains on the durable events and is omitted from the transcript. ## Alternatives considered diff --git a/.agents/notes/implemented/simplification/2026-07-20-unwrap-injected-content-envelopes.zh.md b/.agents/notes/implemented/simplification/2026-07-20-unwrap-injected-content-envelopes.zh.md index bbd2b2f200..813adfb818 100644 --- a/.agents/notes/implemented/simplification/2026-07-20-unwrap-injected-content-envelopes.zh.md +++ b/.agents/notes/implemented/simplification/2026-07-20-unwrap-injected-content-envelopes.zh.md @@ -19,7 +19,7 @@ Status: implemented `ContextEnvelope` 类型和所有 `envelope` 字段都被移除——包括 `SessionEventMap` 中的 `context/message`、`InjectOptions`、`HookContext`，以及 `dsh-agent-loop` 中 `inject()`/`additionalContexts` 的相关管线。`agent-instructions` 不再请求 `'raw'`；它自带框架的内容渲染方式不变。`renderTagged`/`renderContextEnvelope` 辅助函数被删除。`context/message.meta` 仍携带持久的、对模型隐藏的 JSON 状态。 -封套曾携带的 `source` 来源信息并未丢失——它仍保留在持久事件上；只是不再渲染进 transcript。 +`source` 来源信息保留在持久事件上，不渲染进 transcript。 ## 权衡的替代方案 diff --git a/.agents/notes/implemented/simplification/2026-07-22-plan-specific-collaboration-state.i18n.yaml b/.agents/notes/implemented/simplification/2026-07-22-plan-specific-collaboration-state.i18n.yaml index dfb001aad5..363165af8f 100644 --- a/.agents/notes/implemented/simplification/2026-07-22-plan-specific-collaboration-state.i18n.yaml +++ b/.agents/notes/implemented/simplification/2026-07-22-plan-specific-collaboration-state.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/simplification/2026-07-22-plan-specific-collaboration-state.md -2026-07-22-plan-specific-collaboration-state.md: a85e7ced9f2792dfd447cb22e9fea08ce67256df -2026-07-22-plan-specific-collaboration-state.zh.md: 2754b01a41b573f809f556afa1d7dd213b07e597 +2026-07-22-plan-specific-collaboration-state.md: c2b882bd6f686662a2369d1b76d6e1611caee9b9 +2026-07-22-plan-specific-collaboration-state.zh.md: 1fdb4b260853be7480f1575d6ded86d036b7d746 diff --git a/.agents/notes/implemented/simplification/2026-07-22-plan-specific-collaboration-state.md b/.agents/notes/implemented/simplification/2026-07-22-plan-specific-collaboration-state.md index a85e7ced9f..c2b882bd6f 100644 --- a/.agents/notes/implemented/simplification/2026-07-22-plan-specific-collaboration-state.md +++ b/.agents/notes/implemented/simplification/2026-07-22-plan-specific-collaboration-state.md @@ -43,7 +43,7 @@ The tool renders the submitted plan as a generic card titled by its first headin ## Alternatives considered -**Keep a private generic registry and expose only plan today.** Rejected because the unused name/config machinery would still be maintained and tested without a second production consumer. A future collaboration state can establish the right shared seam from two concrete cases. +**Keep a private generic registry and expose only plan.** Rejected because the unused name/config machinery would still be maintained and tested without a second production consumer. A future collaboration state can establish the right shared seam from two concrete cases. **Fold sandbox or approval policy into plan state.** Rejected because collaboration guidance, execution confinement, and permission decisions have different owners, lifecycle semantics, and consumers. A mode-owned sandbox cap also makes a user's explicit sandbox selection appear to succeed while silently doing nothing. diff --git a/.agents/notes/implemented/simplification/2026-07-22-plan-specific-collaboration-state.zh.md b/.agents/notes/implemented/simplification/2026-07-22-plan-specific-collaboration-state.zh.md index 2754b01a41..1fdb4b2608 100644 --- a/.agents/notes/implemented/simplification/2026-07-22-plan-specific-collaboration-state.zh.md +++ b/.agents/notes/implemented/simplification/2026-07-22-plan-specific-collaboration-state.zh.md @@ -43,7 +43,7 @@ Plan mode 拥有一个 plan 专用产品包：位于 `packages/plan/plan-mode/` ## 考虑过的替代方案 -**保留私有的通用注册表，目前只暴露 plan。** 不予采纳，因为没有第二个生产消费方时，仍需维护和测试未使用的名称与配置机制。未来若出现另一种协作状态，可以从两个具体案例出发建立合适的共享 seam。 +**保留私有的通用注册表，只暴露 plan。** 不予采纳，因为没有第二个生产消费方时，仍需维护和测试未使用的名称与配置机制。未来若出现另一种协作状态，可以从两个具体案例出发建立合适的共享 seam。 **将沙箱或审批策略折叠进 plan 状态。** 不予采纳，因为协作引导、执行约束和权限决策有不同的归属方、生命周期语义和消费方。由 mode 拥有的沙箱上限还会让用户显式选择沙箱看似成功，实际却被静默忽略。 diff --git a/.agents/notes/implemented/simplification/2026-08-11-cmdline-program-action.i18n.yaml b/.agents/notes/implemented/simplification/2026-08-11-cmdline-program-action.i18n.yaml deleted file mode 100644 index 842a44a9cc..0000000000 --- a/.agents/notes/implemented/simplification/2026-08-11-cmdline-program-action.i18n.yaml +++ /dev/null @@ -1,6 +0,0 @@ -# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each -# side as of the last confirmed-consistent state. Both languages carry equal authority; -# after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write .agents/notes/implemented/simplification/2026-08-11-cmdline-program-action.md -2026-08-11-cmdline-program-action.md: 40c4dae1d3461f25ac7f34dee7c166434e6cd24d -2026-08-11-cmdline-program-action.zh.md: 1eb9746162f3b4eb8c43ca71f5abc3213d0203da diff --git a/.agents/notes/implemented/simplification/2026-08-11-quickstart-documentation-home.i18n.yaml b/.agents/notes/implemented/simplification/2026-08-11-quickstart-documentation-home.i18n.yaml deleted file mode 100644 index 5ba8461a95..0000000000 --- a/.agents/notes/implemented/simplification/2026-08-11-quickstart-documentation-home.i18n.yaml +++ /dev/null @@ -1,6 +0,0 @@ -# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each -# side as of the last confirmed-consistent state. Both languages carry equal authority; -# after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write .agents/notes/implemented/simplification/2026-08-11-quickstart-documentation-home.md -2026-08-11-quickstart-documentation-home.md: 3fd98843fc0e3e09fc1f4a5623729511aba98def -2026-08-11-quickstart-documentation-home.zh.md: 63871b01c4b552834907ecd41ea089c71ed246d8 diff --git a/.agents/notes/implemented/simplification/2026-08-13-remove-first-run-beta-notice.i18n.yaml b/.agents/notes/implemented/simplification/2026-08-13-remove-first-run-beta-notice.i18n.yaml deleted file mode 100644 index b501e15ee1..0000000000 --- a/.agents/notes/implemented/simplification/2026-08-13-remove-first-run-beta-notice.i18n.yaml +++ /dev/null @@ -1,6 +0,0 @@ -# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each -# side as of the last confirmed-consistent state. Both languages carry equal authority; -# after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write .agents/notes/implemented/simplification/2026-08-13-remove-first-run-beta-notice.md -2026-08-13-remove-first-run-beta-notice.md: 21396eb9cc3e0e766238115967e354abe1032bd2 -2026-08-13-remove-first-run-beta-notice.zh.md: c7c31b163d4c364b7d1d6ce8d03ac3492a176549 diff --git a/.agents/notes/implemented/simplification/2026-08-19-knip-config-cleanup.i18n.yaml b/.agents/notes/implemented/simplification/2026-08-19-knip-config-cleanup.i18n.yaml deleted file mode 100644 index 9a76fb2d7b..0000000000 --- a/.agents/notes/implemented/simplification/2026-08-19-knip-config-cleanup.i18n.yaml +++ /dev/null @@ -1,6 +0,0 @@ -# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each -# side as of the last confirmed-consistent state. Both languages carry equal authority; -# after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write .agents/notes/implemented/simplification/2026-08-19-knip-config-cleanup.md -2026-08-19-knip-config-cleanup.md: 629e64be797bdc1c92fba5e11670118b1aa54374 -2026-08-19-knip-config-cleanup.zh.md: e7a1ec91210eac8e66d1ff1c20f41d7d0211199f diff --git a/.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.i18n.yaml b/.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.i18n.yaml index 881c830a38..676b7c29a9 100644 --- a/.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.i18n.yaml +++ b/.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.md -2026-06-19-real-api-e2e-ci.md: feb5d83f087f66dfec7e1540f6b32e33656409d4 -2026-06-19-real-api-e2e-ci.zh.md: e808c057cbe49fe97a426de3437bd65161ae7a77 +2026-06-19-real-api-e2e-ci.md: 4f51032d90b6773d01db7bbfdced6328bd882ad0 +2026-06-19-real-api-e2e-ci.zh.md: 390df23aebec3a6a54bc48eb52022fe02e872164 diff --git a/.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.md b/.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.md index feb5d83f08..4f51032d90 100644 --- a/.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.md +++ b/.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.md @@ -62,7 +62,7 @@ The DeepSeek native `web_search` probe is registered but skipped. The live Anthr The repository's first CI secret requires a recorded threat model because access differs between same-repository, fork, and Dependabot pull requests and changes when the repository becomes public. -### Who can reach the secret today (private repo) +### Who can reach the secret in a private repository - **No write access (fork PRs): cannot.** Two independent facts block it. First, the workflow uses `pull_request`, **not** `pull_request_target` — GitHub does not pass repo secrets to fork-PR runs of `pull_request`, so `secrets.DEEPSEEK_API_KEY_EXTERNAL` resolves to empty on a fork runner. Second, the `if:` gate skips fork PRs entirely. The withholding is the real boundary; the gate is defense-in-depth and UX. - **Write (push) access: can.** A same-repo branch PR receives secrets, so a write-access author could modify test code (or an install lifecycle script, or the workflow YAML on their branch) to exfiltrate the key. This is **inherent to GitHub Actions, not introduced here**: anyone with push access to any repo can already exfiltrate any of its Actions secrets by authoring a workflow. Write access ⇒ secret access, always. The mitigation lives in who is granted write and in branch protection, not in this file. @@ -79,7 +79,7 @@ The secret stays protected from the public **through this workflow**: `pull_requ What gets worse is the *surrounding* model, and these are the things to address before flipping visibility: -- **Logs become world-readable.** A careless secret echo that today leaks to org members would leak to the entire internet and be scraped within minutes. Secret-handling discipline (no value/length echoes — already done) matters far more. +- **Logs become world-readable.** A careless secret echo that leaks to organization members would leak to the entire internet and be scraped within minutes. Secret-handling discipline (no value/length echoes — already done) matters far more. - **The `pull_request_target` footgun becomes catastrophic.** If anyone ever "fixes" PR runs by switching the trigger to `pull_request_target`, the workflow would run untrusted fork code in the base-repo context **with** secrets — a full key-leak vector. This is benign-ish on a private repo and disastrous on a public one. A `SECURITY —` comment on the trigger in e2e.yml forbids the change and points here. - **Rotate on flip.** The key lived in a private repo's CI; treat going-public as "assume exposed" and rotate `DEEPSEEK_API_KEY_EXTERNAL` at that moment. - **Settle the secret behind controls.** Confirm Settings → Actions → *"Send secrets to workflows from fork pull requests"* stays **off** (the one setting that would actually break the fork boundary), and consider moving the key into a GitHub **Environment** with required reviewers so even merged code uses it only under controlled conditions and rotation has a single home. diff --git a/.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.zh.md b/.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.zh.md index e808c057cb..390df23aeb 100644 --- a/.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.zh.md +++ b/.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.zh.md @@ -62,7 +62,7 @@ DeepSeek 原生 `web_search` 探测已注册但会跳过。线上 Anthropic 兼 仓库的首个 CI secret 需要一份记录在案的威胁模型，因为同仓库 PR、fork PR 和 Dependabot PR 的访问权限各不相同，且仓库公开后会发生变化。 -### 当前谁能触及 secret（私有仓库） +### 私有仓库中谁能触及 secret - **无写权限（fork PR）：不能。** 两个独立事实阻止了它。第一，工作流使用 `pull_request` 而**非** `pull_request_target`——GitHub 不会将 repo secret 传递给 fork PR 的 `pull_request` 运行，因此 `secrets.DEEPSEEK_API_KEY_EXTERNAL` 在 fork runner 上解析为空。第二，`if:` 门禁完全跳过 fork PR。secret 扣留是真正的边界；门禁是纵深防御和用户体验。 - **有写（push）权限：能。** 同仓库分支 PR 会收到 secret，因此有写权限的作者可以修改测试代码（或安装生命周期脚本，或其分支上的工作流 YAML）来窃取密钥。这**是 GitHub Actions 的固有特性，并非本文引入的**：任何对任何仓库有 push 权限的人都可以通过编写工作流来窃取该仓库的任何 Actions secret。写权限⇒secret 访问权，始终如此。缓解措施在于谁被授予写权限以及分支保护，而非本文件。 @@ -79,7 +79,7 @@ DeepSeek 原生 `web_search` 探测已注册但会跳过。线上 Anthropic 兼 变差的是*周边*模型，以下是翻转可见性之前需要处理的事项： -- **日志变为全球可读。** 今天泄露给组织成员的粗心 secret 回显，公开后会泄露给整个互联网并在数分钟内被爬取。secret 处理纪律（不回显值/长度——已做到）的重要性大幅提升。 +- **日志变为全球可读。** 泄露给组织成员的粗心 secret 回显，公开后会泄露给整个互联网并在数分钟内被爬取。secret 处理纪律（不回显值/长度——已做到）的重要性大幅提升。 - **`pull_request_target` 陷阱变为灾难性的。** 如果有人为了「修复」PR 运行而将触发器切换为 `pull_request_target`，工作流将在 base-repo 上下文中运行不可信的 fork 代码并**携带** secret——完整的密钥泄露向量。在私有仓库中这勉强无害，在公开仓库中则是灾难。e2e.yml 中触发器上的 `SECURITY —` 注释禁止此更改并指向本文。 - **翻转时轮换密钥。** 密钥曾存在于私有仓库的 CI 中；将公开视为「假定已暴露」，在那一刻轮换 `DEEPSEEK_API_KEY_EXTERNAL`。 - **将 secret 置于控制之下。** 确认 Settings → Actions → *"Send secrets to workflows from fork pull requests"* 保持**关闭**（这是唯一真正会打破 fork 边界的设置），并考虑将密钥移入带有 required reviewers 的 GitHub **Environment**，使即使已合并的代码也只在受控条件下使用它，且轮换有单一归属。 diff --git a/.agents/notes/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.i18n.yaml b/.agents/notes/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.i18n.yaml index 20b2d178bd..d923a2b4fe 100644 --- a/.agents/notes/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.i18n.yaml +++ b/.agents/notes/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.md -2026-06-22-fork-child-replay-seed-boundary.md: 2768f32adff2badf2d4b18d14ce7eebcb87fda09 -2026-06-22-fork-child-replay-seed-boundary.zh.md: d7a4468e5304a17b9b52bbc9669f6637e5207b15 +2026-06-22-fork-child-replay-seed-boundary.md: 0964f31de7038484f19cab2431bcd8e9f6113a37 +2026-06-22-fork-child-replay-seed-boundary.zh.md: 5caa5a8a66bc5630705319b180863b353c0e8249 diff --git a/.agents/notes/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.md b/.agents/notes/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.md index 2768f32adf..0964f31de7 100644 --- a/.agents/notes/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.md +++ b/.agents/notes/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.md @@ -12,7 +12,7 @@ A subagent script is derived from a recorded session log by [`deriveReplayScript A **fork** child is different. The fork backend seeds the child session with a *balanced completed-turn prefix of the parent's log* ([`dsh-subagent-in-process-driver`](../../../../packages/subagent/subagent-in-process-driver)), and that seed becomes the child session's persisted `log` (`Session`'s constructor copies the seed into `this.log`). So a fork child's `.jsonl` begins with the **parent's** events — including the parent's `assistant/chunk` events — and only then carries the child's own turn. -Deriving the child script from the whole fork-child log therefore replays the **parent's** recorded responses as the **child's** model calls: the live fork child's first `stream()` would receive the parent's first recorded chunk sequence instead of its own. The recorded scenarios are all spawn today, so this never fired — but a fork snapshot would have mis-routed silently, exactly the class of bug the snapshot tier exists to catch. +Deriving the child script from the whole fork-child log therefore replays the **parent's** recorded responses as the **child's** model calls: the live fork child's first `stream()` would receive the parent's first recorded chunk sequence instead of its own. All recorded scenarios use spawn, so this never fired — but a fork snapshot would have mis-routed silently, exactly the class of bug the snapshot tier exists to catch. ## Decision diff --git a/.agents/notes/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.zh.md b/.agents/notes/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.zh.md index d7a4468e53..5caa5a8a66 100644 --- a/.agents/notes/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.zh.md +++ b/.agents/notes/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.zh.md @@ -12,7 +12,7 @@ subagent 脚本由 [`deriveReplayScript`](../../../../packages/test-support/llm- **fork** 子会话不同。fork 后端用*父日志的一段平衡的已完成轮次前缀*（[`dsh-subagent-in-process-driver`](../../../../packages/subagent/subagent-in-process-driver)）来播种子会话，而该 seed 会成为子会话持久化的 `log`（`Session` 构造函数将 seed 复制进 `this.log`）。因此 fork 子会话的 `.jsonl` 以**父会话**的事件开头——包括父会话的 `assistant/chunk` 事件——之后才是子会话自身的轮次。 -从 fork 子会话的完整日志推导脚本，会把**父会话**的已录制响应当作**子会话**的模型调用来回放：实际运行的 fork 子会话第一次调用 `stream()` 时，会收到父会话的第一段分片序列而非自身的。当时已录制的场景全部是 spawn，所以这从未触发——但 fork 快照会静默地错误路由，恰好属于快照层存在的意义所要捕获的那类 bug。 +从 fork 子会话的完整日志推导脚本，会把**父会话**的已录制响应当作**子会话**的模型调用来回放：实际运行的 fork 子会话第一次调用 `stream()` 时，会收到父会话的第一段分片序列而非自身的。所有已录制场景都使用 spawn，所以这从未触发——但 fork 快照会静默地错误路由，恰好属于快照层存在的意义所要捕获的那类 bug。 ## 决策 diff --git a/.agents/notes/implemented/testing/2026-06-22-subagent-snapshot-replay.i18n.yaml b/.agents/notes/implemented/testing/2026-06-22-subagent-snapshot-replay.i18n.yaml index 5041596972..11cbbb229f 100644 --- a/.agents/notes/implemented/testing/2026-06-22-subagent-snapshot-replay.i18n.yaml +++ b/.agents/notes/implemented/testing/2026-06-22-subagent-snapshot-replay.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/testing/2026-06-22-subagent-snapshot-replay.md -2026-06-22-subagent-snapshot-replay.md: bdd4e93ea185c5483c2ff81eba617baaf8cc40b2 -2026-06-22-subagent-snapshot-replay.zh.md: 48691fe4db94febba8d041cf750b69aa9849dd52 +2026-06-22-subagent-snapshot-replay.md: 05ba69ee1927912309b94851d2812f147e81b1e2 +2026-06-22-subagent-snapshot-replay.zh.md: 5501db493ab0c29b69e8bdc08cb3c6fb166b8cfb diff --git a/.agents/notes/implemented/testing/2026-06-22-subagent-snapshot-replay.md b/.agents/notes/implemented/testing/2026-06-22-subagent-snapshot-replay.md index bdd4e93ea1..05ba69ee19 100644 --- a/.agents/notes/implemented/testing/2026-06-22-subagent-snapshot-replay.md +++ b/.agents/notes/implemented/testing/2026-06-22-subagent-snapshot-replay.md @@ -35,7 +35,7 @@ Child fixtures sort by `createdAt`, which matches call order while siblings run ## Alternatives considered -The alternative considered and rejected was a **call-ordered merge of the parent and child logs** into one global script (sound only because in-process subagent execution is strictly nested — the parent blocks on the child). It is simpler for today's synchronous cut but bakes in the parent-blocks-on-child invariant that a future backgrounded/concurrent subagent would break; per-session keying does not. +The alternative considered and rejected was a **call-ordered merge of the parent and child logs** into one global script (sound only because in-process subagent execution is strictly nested — the parent blocks on the child). It is simpler for the synchronous execution model but bakes in the parent-blocks-on-child invariant that a future backgrounded/concurrent subagent would break; per-session keying does not. ### 3. The harness harvests every log, primary-first diff --git a/.agents/notes/implemented/testing/2026-06-22-subagent-snapshot-replay.zh.md b/.agents/notes/implemented/testing/2026-06-22-subagent-snapshot-replay.zh.md index 48691fe4db..5501db493a 100644 --- a/.agents/notes/implemented/testing/2026-06-22-subagent-snapshot-replay.zh.md +++ b/.agents/notes/implemented/testing/2026-06-22-subagent-snapshot-replay.zh.md @@ -35,7 +35,7 @@ Status: implemented ## 曾考虑的替代方案 -曾考虑但否决的方案是：**将父子日志按调用顺序合并**为一份全局脚本（仅在进程内 subagent 执行严格嵌套——父 agent 阻塞等待子 agent——时才正确）。对当前的同步实现而言更简单，但将「父阻塞于子」这一不变式固化了进去；未来若引入后台/并发 subagent 就会失效。逐会话键控则不会。 +曾考虑但否决的方案是：**将父子日志按调用顺序合并**为一份全局脚本（仅在进程内 subagent 执行严格嵌套——父 agent 阻塞等待子 agent——时才正确）。对同步执行模型而言更简单，但将「父阻塞于子」这一不变式固化了进去；未来若引入后台/并发 subagent 就会失效。逐会话键控则不会。 ### 3. harness 收集所有日志，主会话优先 diff --git a/.agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.i18n.yaml b/.agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.i18n.yaml index a61435494d..97013fe8df 100644 --- a/.agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.i18n.yaml +++ b/.agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.md -2026-07-24-domain-kv-storage-and-workspace.md: ff0db847f6f15130d38a3a001daf8b129311f3a3 -2026-07-24-domain-kv-storage-and-workspace.zh.md: 82f00ddc3b108ed32058586f71eacdbcf5c035c9 +2026-07-24-domain-kv-storage-and-workspace.md: 68e26e6fb55c36c08e1c4d45ed699b05459f1ea6 +2026-07-24-domain-kv-storage-and-workspace.zh.md: 0e837b1fdba3dc7e9764d7a690508a74980f5078 diff --git a/.agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.md b/.agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.md index ff0db847f6..68e26e6fb5 100644 --- a/.agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.md +++ b/.agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.md @@ -6,7 +6,7 @@ English | [中文](2026-07-24-domain-kv-storage-and-workspace.zh.md) ## Problem -The host's only persistence surface is the session event log (`packages/session/session-persistence`: append-only, one file per session). Anything that does not belong to a single session has nowhere to live, and two real needs exist today: +The host's only persistence surface is the session event log (`packages/session/session-persistence`: append-only, one file per session). Anything that does not belong to a single session has nowhere to live, and two shipped needs exist: - **The workspace entity.** The GUI needs workspace as a real object: path, title, and the list of owned sessions. Ownership belongs to the workspace — "which sessions belong to this workspace" is not any single session's fact, so writing it into the session log is semantically wrong. Before this design, workspace was only a sidebar visual grouping derived from cwd, with no entity. - **Dynamic session metadata** (the foreseeable second consumer). Cold session listings read only the first log line (an immutable creation-time snapshot); title, terminal status, and anything that evolves with the session is unavailable. The fix direction is a sidecar metadata table — exactly a KV table with high-frequency per-key updates. @@ -83,9 +83,9 @@ Config is `path` (required, `':memory:'` allowed) plus `journalMode` (enum, defa CREATE TABLE IF NOT EXISTS units (name TEXT PRIMARY KEY, version INTEGER NOT NULL) STRICT; CREATE TABLE IF NOT EXISTS unit_globals ( unit TEXT PRIMARY KEY REFERENCES units(name), value TEXT NOT NULL) STRICT; --- 每 unit 每表： +-- One table per unit/table pair: CREATE TABLE IF NOT EXISTS "u__" ( - key TEXT PRIMARY KEY, value TEXT NOT NULL) STRICT; -- value = 记录 JSON 文档 + key TEXT PRIMARY KEY, value TEXT NOT NULL) STRICT; -- value = record JSON document ``` - Unit versions live in `units` rows; a descriptor mismatch → `version-mismatch`. Row granularity is document-per-row, preserving precise per-key durable updates (the path left open for high-frequency point-update tables like the session sidecar); when query needs appear, JSON1 reads the value column directly. @@ -97,8 +97,8 @@ A single implementation, not abstracted; consumers depend on this layer only and ```ts ignore-check export const Config = z.object({ - backend: z.string().required(), // 默认后端名，必填 - routes: z.dict(z.string()).default({}), // per-domain 覆盖：{ workspace: 'sqlite' } + backend: z.string().required(), // required default backend name + routes: z.dict(z.string()).default({}), // per-domain override: { workspace: 'sqlite' } }) export function apply(ctx: Context, config: Config) { @@ -135,21 +135,21 @@ export function domainTable(schema: ZodType): DomainTabl 6. Construct the `Domain` and register `ctx.effect()`: the disposer drains the write chain → `unit.close()`. ```ts ignore-check -export interface Domain { +export interface Domain { readonly name: string - readonly global: { get(): G; set(value: G): Promise } // 仅当 spec.global 声明 + readonly global: { get(): G; set(value: G): Promise } // only when spec.global exists table(name: N): KvTable, ValueOf> } export interface KvTable { - get(key: K): V | undefined // 内存快照，同步 + get(key: K): V | undefined // synchronous in-memory snapshot entries(): IterableIterator<[K, V]> keys(): IterableIterator readonly size: number put(key: K, value: V): Promise - delete(key: K): Promise // false = 本就不存在 + delete(key: K): Promise // false when already absent /** Atomic read-modify-write on the domain's single write chain; fn is sync-pure. */ - update(key: K, fn: (current: V) => V): Promise // 缺 key → DomainError('missing-key') + update(key: K, fn: (current: V) => V): Promise // missing key -> DomainError('missing-key') } ``` diff --git a/.agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.zh.md b/.agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.zh.md index 82f00ddc3b..0e837b1fdb 100644 --- a/.agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.zh.md +++ b/.agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.zh.md @@ -6,7 +6,7 @@ Status: proposed ## 问题 -host 侧唯一的持久化面是 session 事件日志（`packages/session/session-persistence`：仅追加、一 session 一文件）。凡是"不属于某个 session"的信息就没有落盘处，眼下有两个真实需求： +host 侧唯一的持久化面是 session 事件日志（`packages/session/session-persistence`：仅追加、一 session 一文件）。凡是"不属于某个 session"的信息就没有落盘处，存在两个已交付需求： - **workspace 实体**。GUI 要把 workspace 做成真实对象：路径、标题、关联 session 清单。归属关系由 workspace 持有——"哪些 session 属于这个 workspace"不是任何单个 session 自己的事实，塞进 session log 语义不成立。在本设计之前，workspace 只是 sidebar 上按 cwd 分组的视觉概念，没有实体。 - **session 动态元信息**（可预见的第二个消费方）。冷会话列表只读日志首行 header（创建时的不可变快照），title、结束状态这类随会话推进变化的信息拿不到；补齐方向是 sidecar 元数据表——正是一张按 key 高频点更新的 KV 表。 @@ -83,9 +83,9 @@ Config 为 `path`（必填，`':memory:'` 允许）+ `journalMode`（枚举， CREATE TABLE IF NOT EXISTS units (name TEXT PRIMARY KEY, version INTEGER NOT NULL) STRICT; CREATE TABLE IF NOT EXISTS unit_globals ( unit TEXT PRIMARY KEY REFERENCES units(name), value TEXT NOT NULL) STRICT; --- 每 unit 每表： +-- One table per unit/table pair: CREATE TABLE IF NOT EXISTS "u__
" ( - key TEXT PRIMARY KEY, value TEXT NOT NULL) STRICT; -- value = 记录 JSON 文档 + key TEXT PRIMARY KEY, value TEXT NOT NULL) STRICT; -- value = record JSON document ``` - unit 版本存 `units` 行，descriptor 不符 → `version-mismatch`。行粒度 document-per-row，保住按 key 精确落盘更新（为 session sidecar 这类高频点更新大表留路）；查询需求出现时 JSON1 直查 value 列。 @@ -97,8 +97,8 @@ CREATE TABLE IF NOT EXISTS "u__
" ( ```ts ignore-check export const Config = z.object({ - backend: z.string().required(), // 默认后端名，必填 - routes: z.dict(z.string()).default({}), // per-domain 覆盖：{ workspace: 'sqlite' } + backend: z.string().required(), // required default backend name + routes: z.dict(z.string()).default({}), // per-domain override: { workspace: 'sqlite' } }) export function apply(ctx: Context, config: Config) { @@ -135,21 +135,21 @@ export function domainTable(schema: ZodType): DomainTabl 6. 构造 `Domain` 并注册 `ctx.effect()`：disposer 排空写链 → `unit.close()`。 ```ts ignore-check -export interface Domain { +export interface Domain { readonly name: string - readonly global: { get(): G; set(value: G): Promise } // 仅当 spec.global 声明 + readonly global: { get(): G; set(value: G): Promise } // only when spec.global exists table(name: N): KvTable, ValueOf> } export interface KvTable { - get(key: K): V | undefined // 内存快照，同步 + get(key: K): V | undefined // synchronous in-memory snapshot entries(): IterableIterator<[K, V]> keys(): IterableIterator readonly size: number put(key: K, value: V): Promise - delete(key: K): Promise // false = 本就不存在 + delete(key: K): Promise // false when already absent /** Atomic read-modify-write on the domain's single write chain; fn is sync-pure. */ - update(key: K, fn: (current: V) => V): Promise // 缺 key → DomainError('missing-key') + update(key: K, fn: (current: V) => V): Promise // missing key -> DomainError('missing-key') } ``` diff --git a/.agents/notes/proposed/architecture/2026-07-27-session-projection-and-command-log.i18n.yaml b/.agents/notes/proposed/architecture/2026-07-27-session-projection-and-command-log.i18n.yaml index 7432dc0cba..88dadb758f 100644 --- a/.agents/notes/proposed/architecture/2026-07-27-session-projection-and-command-log.i18n.yaml +++ b/.agents/notes/proposed/architecture/2026-07-27-session-projection-and-command-log.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/proposed/architecture/2026-07-27-session-projection-and-command-log.md -2026-07-27-session-projection-and-command-log.md: 838d5888429d449144ef59734743bcd9b1a8568e -2026-07-27-session-projection-and-command-log.zh.md: 12e973ffe8ec8caeac90c3743bec794216a5bac8 +2026-07-27-session-projection-and-command-log.md: 1e0dd435d972cfe35d1433417a3884845e384444 +2026-07-27-session-projection-and-command-log.zh.md: dcb077d87eae02c28714fd752606e0966bc70f94 diff --git a/.agents/notes/proposed/architecture/2026-07-27-session-projection-and-command-log.md b/.agents/notes/proposed/architecture/2026-07-27-session-projection-and-command-log.md index 838d588842..1e0dd435d9 100644 --- a/.agents/notes/proposed/architecture/2026-07-27-session-projection-and-command-log.md +++ b/.agents/notes/proposed/architecture/2026-07-27-session-projection-and-command-log.md @@ -128,7 +128,7 @@ Two log-only (non-surface, model-invisible) events, mirroring the `tool/call`/`t 'command/done': { commandId: string; kind: 'success' | 'error'; text?: string } ``` -The host command executor (`packages/interaction/commands`) appends `command/run` before invoking the handler and `command/done` at settlement — direct standalone appends on the receiving agent's session, in the same shape as every other plugin-owned log-only event after the [synthetic-turn removal](../../implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.md): no turn wraps them (turns describe model-loop executions only), persistence drains them at ordinary checkpoints, and the commands package's own invariant companion enforces the run/done pairing. The payload is structured — `name` and, by default, `args` are the parser's own split (`parseCommand`'s name and rawInput), so a consumer (a projection unit folding its own command records, a rich command card) never re-parses a line. A definition sets `recordInput: false` when its authoritative domain event owns the payload; `command/run` then omits `args` rather than duplicating it. `text` is the handler's verbatim outcome — factual data of the same nature as `tool/result.content`, not presentation (how it is laid out remains client-computed at render time, satisfying the "presentation never enters the log" red line). Domains that want the model to know the outcome keep doing what they do today (plan's narration, goal's inject) — that is a domain decision, unchanged. +The host command executor (`packages/interaction/commands`) appends `command/run` before invoking the handler and `command/done` at settlement — direct standalone appends on the receiving agent's session, in the same shape as every other plugin-owned log-only event after the [synthetic-turn removal](../../implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.md): no turn wraps them (turns describe model-loop executions only), persistence drains them at ordinary checkpoints, and the commands package's own invariant companion enforces the run/done pairing. The payload is structured — `name` and, by default, `args` are the parser's own split (`parseCommand`'s name and rawInput), so a consumer (a projection unit folding its own command records, a rich command card) never re-parses a line. A definition sets `recordInput: false` when its authoritative domain event owns the payload; `command/run` then omits `args` rather than duplicating it. `text` is the handler's verbatim outcome — factual data of the same nature as `tool/result.content`, not presentation (how it is laid out remains client-computed at render time, satisfying the "presentation never enters the log" red line). Domains that want the model to know the outcome keep their existing behavior (plan's narration, goal's inject) — that is a domain decision, unchanged. Because committed events broadcast on the mux stream, refresh persistence, multi-tab sync, and fork/resume recovery all come for free. The `command.execute` RPC degrades to admission — `{ matched, commandId? }`: whether the line resolved, and the minted pairing id when it did, so the issuing client can correlate its request with the flow node the lifecycle events produce. The one-shot notice channel (`runDetached` → `noticeFor`) is retired. @@ -156,7 +156,7 @@ Infrastructure first; the three in-flight PRs are left untouched and re-target a **Client-side folding (per-domain projection cells with a `fromEvent`)** — rejected: once plan's unit folds two event types, a client cell must duplicate the host's transition logic in the browser — the same fold written twice, evolving separately. Pushing finished values (the title-frame precedent, generalized) keeps one computation site and reduces the client to a generic seq-guarded value store; domains write zero client code. -**Bounded reverse scan over the log tail (absorber declarations)** — rejected for now: nothing supports it today, it only serves domains whose every event carries the full folded state, and the persisted projection cache covers the same cold-read need uniformly (cache row + forward tail replay — the same recipe as the client's baseline + catch-up, and as paged loading). Revisit only if a real cold-read path emerges that checkpointing cannot serve. +**Bounded reverse scan over the log tail (absorber declarations).** Rejected: no implementation supports it, it serves only domains whose every event carries the full folded state, and the persisted projection cache covers the same cold-read need uniformly (cache row plus forward tail replay — the same recipe as the client's baseline and catch-up, and as paged loading). Revisit only if a real cold-read path emerges that checkpointing cannot serve. **An `invalidate`-style cell (mark dirty, refetch on domain events)** — rejected: it exists only to serve delta events. The whole-value rule makes every domain last-wins; goal's refetch loop, its coalescing, and its stale-read fence all disappear. diff --git a/.agents/notes/proposed/architecture/2026-07-27-session-projection-and-command-log.zh.md b/.agents/notes/proposed/architecture/2026-07-27-session-projection-and-command-log.zh.md index 12e973ffe8..dcb077d87e 100644 --- a/.agents/notes/proposed/architecture/2026-07-27-session-projection-and-command-log.zh.md +++ b/.agents/notes/proposed/architecture/2026-07-27-session-projection-and-command-log.zh.md @@ -128,7 +128,7 @@ type UseProjection = { 'command/done': { commandId: string; kind: 'success' | 'error'; text?: string } ``` -host 侧命令执行器（`packages/interaction/commands`）在调用处理器前追加 `command/run`，在结算时追加 `command/done`——在接收 agent（智能体）的会话上直接独立追加，与[合成轮次移除](../../implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.zh.md)之后所有插件自有 log-only 事件同一形状：没有轮次包裹它们（轮次只描述模型循环执行），持久化在常规检查点排空它们，run/done 配对由 commands 包自己的 invariant 伴生插件把守。载荷是结构化的——`name` 以及默认携带的 `args` 来自解析器自己的切分（`parseCommand` 的 name 与 rawInput），因此消费方（折叠自己命令记录的投影单元、富命令卡片）永远无需重新解析行文本。当载荷由权威领域事件持有时，命令定义会设置 `recordInput: false`；此时 `command/run` 省略 `args`，而不是重复该载荷。`text` 是处理器的原样结果——与 `tool/result.content` 同一性质的事实数据，不是呈现（版式如何编排仍由客户端在渲染时计算，满足「呈现永不入日志」这条红线）。想让模型知道结果的领域继续做它们今天在做的事（plan 的旁白、goal 的注入）——那是领域自己的决定，保持不变。 +host 侧命令执行器（`packages/interaction/commands`）在调用处理器前追加 `command/run`，在结算时追加 `command/done`——在接收 agent（智能体）的会话上直接独立追加，与[合成轮次移除](../../implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.zh.md)之后所有插件自有 log-only 事件同一形状：没有轮次包裹它们（轮次只描述模型循环执行），持久化在常规检查点排空它们，run/done 配对由 commands 包自己的 invariant 伴生插件把守。载荷是结构化的——`name` 以及默认携带的 `args` 来自解析器自己的切分（`parseCommand` 的 name 与 rawInput），因此消费方（折叠自己命令记录的投影单元、富命令卡片）永远无需重新解析行文本。当载荷由权威领域事件持有时，命令定义会设置 `recordInput: false`；此时 `command/run` 省略 `args`，而不是重复该载荷。`text` 是处理器的原样结果——与 `tool/result.content` 同一性质的事实数据，不是呈现（版式如何编排仍由客户端在渲染时计算，满足「呈现永不入日志」这条红线）。想让模型知道结果的领域保持既有行为（plan 的旁白、goal 的注入）——那是领域自己的决定，保持不变。 由于已提交事件会在 mux 流上广播，刷新后仍在、多标签页同步、fork/恢复后可还原这三件事随之全部自动获得。`command.execute` RPC 退化为准入判定——`{ matched, commandId? }`：该行是否匹配命中，以及命中时新铸的配对 id，发起命令的客户端据此把自己的请求与生命周期事件产出的 flow 节点关联起来。一次性通知通道（`runDetached` → `noticeFor`）就此下线。 @@ -156,7 +156,7 @@ host 侧命令执行器（`packages/interaction/commands`）在调用处理器 **客户端侧折叠（带 `fromEvent` 的按领域投影 cell）**——否决：一旦 plan 的单元要折叠两种事件，客户端 cell 就必须在浏览器里复刻 host 的状态转移逻辑——同一个折叠写两遍、各自演化。推送成品值（标题帧先例的泛化）保住唯一计算地点，并把客户端简化为一个由 seq 把守的通用值仓；领域零客户端代码。 -**对日志尾部的有界反向扫描（absorber 声明）**——暂不采纳：今天没有任何东西支持它，它只服务于「每个事件都携带完整折叠状态」的领域，而持久投影缓存以统一方式覆盖同一冷读需求（缓存行 + 正向尾部回放——与客户端的基线 + 追赶、与分页加载是同一套配方）。只有当出现检查点机制服务不了的真实冷读路径时才重议。 +**对日志尾部的有界反向扫描（absorber 声明）。**不予采纳：现有实现均不支持它，它只服务于「每个事件都携带完整折叠状态」的领域，而持久投影缓存以统一方式覆盖同一冷读需求（缓存行加正向尾部回放——与客户端的基线和追赶、与分页加载是同一套配方）。只有当出现检查点机制服务不了的真实冷读路径时才重议。 **`invalidate` 式 cell（标脏，遇领域事件就重取）**——不予采纳：它的存在只为伺候增量事件。全量值规则让每个领域都是 last-wins；goal 的重取循环、合并逻辑、陈旧读栅栏随之全部消失。 diff --git a/.agents/notes/proposed/architecture/2026-07-28-storage-root-and-derived-medium-recovery.i18n.yaml b/.agents/notes/proposed/architecture/2026-07-28-storage-root-and-derived-medium-recovery.i18n.yaml index 029f34b053..4c6bf4c75a 100644 --- a/.agents/notes/proposed/architecture/2026-07-28-storage-root-and-derived-medium-recovery.i18n.yaml +++ b/.agents/notes/proposed/architecture/2026-07-28-storage-root-and-derived-medium-recovery.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/proposed/architecture/2026-07-28-storage-root-and-derived-medium-recovery.md -2026-07-28-storage-root-and-derived-medium-recovery.md: 0eb040007e928412d30cd19aa80554f5a02a9c2a -2026-07-28-storage-root-and-derived-medium-recovery.zh.md: f26f94dc684d8b7d0f0bc00209d48af12543942c +2026-07-28-storage-root-and-derived-medium-recovery.md: cfed831be7eb0fceb5ef7d9778803c602e809179 +2026-07-28-storage-root-and-derived-medium-recovery.zh.md: e535cf703e55b03ccd9a767e03aa73f621b17466 diff --git a/.agents/notes/proposed/architecture/2026-07-28-storage-root-and-derived-medium-recovery.md b/.agents/notes/proposed/architecture/2026-07-28-storage-root-and-derived-medium-recovery.md index 0eb040007e..cfed831be7 100644 --- a/.agents/notes/proposed/architecture/2026-07-28-storage-root-and-derived-medium-recovery.md +++ b/.agents/notes/proposed/architecture/2026-07-28-storage-root-and-derived-medium-recovery.md @@ -10,7 +10,7 @@ The persisted projection cache ([note](2026-07-27-session-projection-and-command **Where the files actually live (root mismatch closed; resolve-once residual still open).** The shared base defaults the session store to the global harness home (`$DSH_HOME/sessions`, default `~/.dsh/sessions`), while the shipped Web overlay used to give the json backend the relative root `./.storages`: `workspace.json` and `session_projcache.json` landed under `/.storages/` — two launches from different directories shared their sessions yet saw different workspace registries and different projection caches, and the cache exists precisely to serve the cross-session cold listing, which missed for every session last cached under another launch directory. That mismatch is now closed: the overlay anchors `storage-json.root` to `$DSH_HOME/storages` with the same `!!js` expression the session root uses (`apps/cli/config/web.cordis.yml`). The residual hazard: `JsonStorageBackend` still never resolves its root — each unit open joins the path against whatever `process.cwd()` is at that moment (packages/storage/storage-json/src/index.ts); the shipped overlay root is already absolute and unaffected, but any relative root (bare Loader boots, tests) still splits on a later cwd change — the exact hazard the JSONL session backend resolves-once to prevent ("later process.cwd() changes cannot split one backend across roots", packages/session/session-persistence-jsonl/src/index.ts). -**How recovery works today.** Inside a healthy medium the cache is fully self-healing by design: a `stateVersion`-mismatched row is discarded and refolded, a log shrunk below a row's watermark is detected by the anchored restore floor and answered with one full re-read, and every background write is fail-soft. But at the *medium* level there is no recovery at all: a truncated, hand-edited, or version-bumped `session_projcache.json` fails `openJsonUnit` with `malformed-medium`/`version-mismatch` (packages/storage/storage-json/src/format.ts), a schema-drifted record fails domain open with `invalid-record` (packages/storage/storage-domain/src/index.ts), the rejection propagates through `SessionProjectionCache[Service.init]`, and under the CLI's fail-loud boot the assembly refuses to start. A file whose entire content is rebuildable from session logs can brick boot. This contradicts the cache package's own stated stance ("a stale or unreadable cache costs a longer tail replay, never a wrong value") and the cache domain spec's JSDoc ("version bumps discard the whole medium"), which today describes an aspiration, not the implementation. The same fail-loud path is *correct* for `workspace.json` — workspace records are authoritative, not derivable — so the missing concept is a per-domain declaration of authority, not a global behavior change. +**Recovery behavior.** Inside a healthy medium the cache is fully self-healing by design: a `stateVersion`-mismatched row is discarded and refolded, a log shrunk below a row's watermark is detected by the anchored restore floor and answered with one full re-read, and every background write is fail-soft. But at the *medium* level there is no recovery at all: a truncated, hand-edited, or version-bumped `session_projcache.json` fails `openJsonUnit` with `malformed-medium`/`version-mismatch` (packages/storage/storage-json/src/format.ts), a schema-drifted record fails domain open with `invalid-record` (packages/storage/storage-domain/src/index.ts), the rejection propagates through `SessionProjectionCache[Service.init]`, and under the CLI's fail-loud boot the assembly refuses to start. A file whose entire content is rebuildable from session logs can brick boot. This contradicts the cache package's own stated stance ("a stale or unreadable cache costs a longer tail replay, never a wrong value") and the cache domain spec's JSDoc ("version bumps discard the whole medium"), which describes an aspiration, not the implementation. The same fail-loud path is *correct* for `workspace.json` — workspace records are authoritative, not derivable — so the missing concept is a per-domain declaration of authority, not a global behavior change. ## Proposal diff --git a/.agents/notes/proposed/architecture/2026-07-28-storage-root-and-derived-medium-recovery.zh.md b/.agents/notes/proposed/architecture/2026-07-28-storage-root-and-derived-medium-recovery.zh.md index f26f94dc68..e535cf703e 100644 --- a/.agents/notes/proposed/architecture/2026-07-28-storage-root-and-derived-medium-recovery.zh.md +++ b/.agents/notes/proposed/architecture/2026-07-28-storage-root-and-derived-medium-recovery.zh.md @@ -10,7 +10,7 @@ Status: proposed **文件到底存在哪（根错位已收口，resolve-once 残余仍开放）。** 共享 base 将会话存储默认为全局 harness home（`$DSH_HOME/sessions`，默认 `~/.dsh/sessions`），而出厂 Web overlay 曾给 json 后端相对根 `./.storages`：`workspace.json` 和 `session_projcache.json` 落在 `<启动目录>/.storages/` 下——从两个不同目录启动，会话相同，工作区注册表和投影缓存却各是一份，而缓存存在的意义恰恰是跨会话冷列表，凡上次在别的启动目录下缓存过的会话全部 miss。这一错位已消除：overlay 现以与会话根同一段 `!!js` 表达式把 `storage-json.root` 锚定到 `$DSH_HOME/storages`（`apps/cli/config/web.cordis.yml`）。残余隐患：`JsonStorageBackend` 仍从不 resolve 根——每次打开 unit 都把路径 join 到当时的 `process.cwd()` 上（packages/storage/storage-json/src/index.ts）；出厂 overlay 的根已是绝对路径不受影响，但任何相对根（裸 Loader 启动、测试）仍会被后续 cwd 变化劈开，JSONL 会话后端用「构造时 resolve 一次」防住的正是它（"later process.cwd() changes cannot split one backend across roots"，packages/session/session-persistence-jsonl/src/index.ts）。 -**现在是怎么恢复的。** 在健康介质内部，缓存按设计完全自愈：`stateVersion` 不匹配的行被丢弃重折，日志缩短到行水位以下由带锚的 restore floor 检出并以一次全量重读回答，每次后台写都是 fail-soft。但在*介质*层面完全没有恢复：被截断、被手改或版本被 bump 的 `session_projcache.json` 会让 `openJsonUnit` 以 `malformed-medium`/`version-mismatch` 失败（packages/storage/storage-json/src/format.ts），schema 漂移的记录让域 open 以 `invalid-record` 失败（packages/storage/storage-domain/src/index.ts），拒绝一路穿过 `SessionProjectionCache[Service.init]`，在 CLI 的 fail-loud 启动下整个组装拒绝启动。一个内容完全可从会话日志重建的文件能把启动搞死。这与缓存包自己声明的立场（"a stale or unreadable cache costs a longer tail replay, never a wrong value"）和缓存域 spec 的 JSDoc（"version bumps discard the whole medium"）相矛盾——后者今天描述的是愿望而非实现。同一条 fail-loud 路径对 `workspace.json` 却是*正确*的——工作区记录是权威数据，不可派生——所以缺的概念是按域声明权威性，而不是全局改行为。 +**恢复行为。** 在健康介质内部，缓存按设计完全自愈：`stateVersion` 不匹配的行被丢弃重折，日志缩短到行水位以下由带锚的 restore floor 检出并以一次全量重读回答，每次后台写都是 fail-soft。但在*介质*层面完全没有恢复：被截断、被手改或版本被 bump 的 `session_projcache.json` 会让 `openJsonUnit` 以 `malformed-medium`/`version-mismatch` 失败（packages/storage/storage-json/src/format.ts），schema 漂移的记录让域 open 以 `invalid-record` 失败（packages/storage/storage-domain/src/index.ts），拒绝一路穿过 `SessionProjectionCache[Service.init]`，在 CLI 的 fail-loud 启动下整个组装拒绝启动。一个内容完全可从会话日志重建的文件能把启动搞死。这与缓存包自己声明的立场（"a stale or unreadable cache costs a longer tail replay, never a wrong value"）和缓存域 spec 的 JSDoc（"version bumps discard the whole medium"）相矛盾——后者描述的是愿望而非实现。同一条 fail-loud 路径对 `workspace.json` 却是*正确*的——工作区记录是权威数据，不可派生——所以缺的概念是按域声明权威性，而不是全局改行为。 ## 提案 diff --git a/.agents/notes/proposed/architecture/2026-07-29-durable-last-activity-index.i18n.yaml b/.agents/notes/proposed/architecture/2026-07-29-durable-last-activity-index.i18n.yaml index ce5f92c4fa..7d447b4b3b 100644 --- a/.agents/notes/proposed/architecture/2026-07-29-durable-last-activity-index.i18n.yaml +++ b/.agents/notes/proposed/architecture/2026-07-29-durable-last-activity-index.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/proposed/architecture/2026-07-29-durable-last-activity-index.md -2026-07-29-durable-last-activity-index.md: 99e50dd40b789db5d896cb7f9e25fa8893b02ae2 -2026-07-29-durable-last-activity-index.zh.md: 3f0ef9a755e437e6647083f43ad55347bd0bdb96 +2026-07-29-durable-last-activity-index.md: d3f21f0b6ddf793ffbc20ddcb2b2f5435c0858d1 +2026-07-29-durable-last-activity-index.zh.md: a690bd87681c0a56cf81446ccf8eedaf105877e7 diff --git a/.agents/notes/proposed/architecture/2026-07-29-durable-last-activity-index.md b/.agents/notes/proposed/architecture/2026-07-29-durable-last-activity-index.md index 99e50dd40b..d3f21f0b6d 100644 --- a/.agents/notes/proposed/architecture/2026-07-29-durable-last-activity-index.md +++ b/.agents/notes/proposed/architecture/2026-07-29-durable-last-activity-index.md @@ -27,7 +27,7 @@ Three questions must be answered before implementation, and none of them is sett **How is the shared predicate owned?** A stored field encodes the rule at write time, where the writer sees one batch, while the attached summary folds a whole log. Both must use one exported event predicate or reducer so new message-source variants cannot make attached and cold ordering disagree. -**How do pre-field logs behave?** Existing artifacts have no value. Falling back to mtime keeps them at today's accuracy; falling back to `createdAt` is honest but reorders every existing session in the picker and the tree. +**How do pre-field logs behave?** Existing artifacts have no value. Falling back to mtime keeps them at the existing mtime-based accuracy; falling back to `createdAt` is honest but reorders every existing session in the picker and the tree. **Is a sidecar acceptable for JSONL?** It reintroduces a second file per session that can disagree with the log, which the single-artifact design avoided. diff --git a/.agents/notes/proposed/architecture/2026-07-29-durable-last-activity-index.zh.md b/.agents/notes/proposed/architecture/2026-07-29-durable-last-activity-index.zh.md index 3f0ef9a755..a690bd8768 100644 --- a/.agents/notes/proposed/architecture/2026-07-29-durable-last-activity-index.zh.md +++ b/.agents/notes/proposed/architecture/2026-07-29-durable-last-activity-index.zh.md @@ -27,7 +27,7 @@ Status: proposed **共享谓词由谁拥有？** 已存储字段在写入时编码规则，写入方只看到一个批次，而已附加摘要折叠整份日志。两者必须使用同一个导出的事件谓词或 reducer，避免新的消息来源变体让已附加排序与冷排序发生分歧。 -**该字段引入之前的日志表现如何？** 既有产物里没有这个值。回退到 mtime 能让它们保持今天的准确度；回退到 `createdAt` 是诚实的，但会把选择器和会话树里每一个既有会话都重新排一次序。 +**该字段引入之前的日志表现如何？** 既有产物里没有这个值。回退到 mtime 能让它们保持现有基于 mtime 的准确度；回退到 `createdAt` 是诚实的，但会把选择器和会话树里每一个既有会话都重新排一次序。 **对 JSONL 来说伴随文件可以接受吗？** 它重新引入了每会话第二个文件，而该文件可能与日志不一致，这正是单产物设计所避开的。 diff --git a/.agents/notes/proposed/architecture/2026-08-10-unary-apiproxy-remote-migration.i18n.yaml b/.agents/notes/proposed/architecture/2026-08-10-unary-apiproxy-remote-migration.i18n.yaml index e3567e4124..d327972db7 100644 --- a/.agents/notes/proposed/architecture/2026-08-10-unary-apiproxy-remote-migration.i18n.yaml +++ b/.agents/notes/proposed/architecture/2026-08-10-unary-apiproxy-remote-migration.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/proposed/architecture/2026-08-10-unary-apiproxy-remote-migration.md -2026-08-10-unary-apiproxy-remote-migration.md: 6ed58647429182eb34015db246c83701f48bd19b -2026-08-10-unary-apiproxy-remote-migration.zh.md: 84f3b9c637c9fa637dce938f8a3d88292ffe0c56 +2026-08-10-unary-apiproxy-remote-migration.md: c4a308e16bee994df69f16228e859dd88d90c346 +2026-08-10-unary-apiproxy-remote-migration.zh.md: db263e1a7843963cf38082a88405453ee4b66af7 diff --git a/.agents/notes/proposed/architecture/2026-08-10-unary-apiproxy-remote-migration.md b/.agents/notes/proposed/architecture/2026-08-10-unary-apiproxy-remote-migration.md index 6ed5864742..c4a308e16b 100644 --- a/.agents/notes/proposed/architecture/2026-08-10-unary-apiproxy-remote-migration.md +++ b/.agents/notes/proposed/architecture/2026-08-10-unary-apiproxy-remote-migration.md @@ -72,7 +72,7 @@ Methods whose signatures contain only branded ids do not invoke Typert object lo ## Client and error behavior -Generated Remote methods return business values and throw an Error whose `cause` contains the existing RPC failure. Client business services own adaptation to their current result/store interfaces. They must settle successful results immediately exactly as they do today so event frames remain idempotent replays rather than the only update path. +Generated Remote methods return business values and throw an Error whose `cause` contains the existing RPC failure. Client business services own adaptation to their current result/store interfaces. They must settle successful results immediately exactly as the existing services do so event frames remain idempotent replays rather than the only update path. Resolver-owned `session-not-found` and `agent-busy` errors remain stable because the shared resolver raises `TypertLookupFailure`. Ordinary business exceptions become the Gateway's existing `internal` RPC failure. A selected Client consumer may migrate only if it does not branch on a more specific legacy business error code; if implementation finds such a branch, that RPC leaves this set unless the business package gains a transport-independent typed failure. diff --git a/.agents/notes/proposed/architecture/2026-08-10-unary-apiproxy-remote-migration.zh.md b/.agents/notes/proposed/architecture/2026-08-10-unary-apiproxy-remote-migration.zh.md index 84f3b9c637..db263e1a78 100644 --- a/.agents/notes/proposed/architecture/2026-08-10-unary-apiproxy-remote-migration.zh.md +++ b/.agents/notes/proposed/architecture/2026-08-10-unary-apiproxy-remote-migration.zh.md @@ -72,7 +72,7 @@ Lookup 策略作用于整个 key，而非特定端点。提示词输入、队列 ## Client 与错误行为 -生成的 Remote 方法返回业务值，并抛出一个 Error，其 `cause` 包含现有的 RPC 失败。Client 业务服务负责适配到当前的结果／store 接口。它们必须像当前一样让成功结果立即生效，使事件帧仍是幂等回放，而非唯一的更新路径。 +生成的 Remote 方法返回业务值，并抛出一个 Error，其 `cause` 包含现有的 RPC 失败。Client 业务服务负责适配到当前的结果／store 接口。它们必须与现有服务一样让成功结果立即生效，使事件帧仍是幂等回放，而非唯一的更新路径。 Resolver 拥有的 `session-not-found` 和 `agent-busy` 错误保持稳定，因为共享 resolver 会抛出 `TypertLookupFailure`。普通业务异常会变成 Gateway 现有的 `internal` RPC 失败。只有在选定的 Client 消费方不根据更具体的旧版业务错误码进行分支时，才能迁移该调用；如果实现过程中发现这种分支，除非业务包新增与传输无关的类型化失败，否则该 RPC 将退出此集合。 diff --git a/.agents/notes/proposed/bug-fix/2026-08-20-attachment-read-quarantine.i18n.yaml b/.agents/notes/proposed/bug-fix/2026-08-20-attachment-read-quarantine.i18n.yaml new file mode 100644 index 0000000000..b53d43cdc7 --- /dev/null +++ b/.agents/notes/proposed/bug-fix/2026-08-20-attachment-read-quarantine.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/proposed/bug-fix/2026-08-20-attachment-read-quarantine.md +2026-08-20-attachment-read-quarantine.md: 28e0f26cee2ec1e257fd4d43b4edc4300e2c6f23 +2026-08-20-attachment-read-quarantine.zh.md: 7f4ceae4e1fe9e656ed762de9828e14145976dc3 diff --git a/.agents/notes/proposed/bug-fix/2026-08-20-attachment-read-quarantine.md b/.agents/notes/proposed/bug-fix/2026-08-20-attachment-read-quarantine.md new file mode 100644 index 0000000000..28e0f26cee --- /dev/null +++ b/.agents/notes/proposed/bug-fix/2026-08-20-attachment-read-quarantine.md @@ -0,0 +1,38 @@ +# Agent Note: Quarantine unreadable historical attachments + +Status: proposed + +English | [中文](2026-08-20-attachment-read-quarantine.zh.md) + +## Problem + +An admitted `ImageAttachmentRef` remains in durable history and therefore participates in every later request until compaction replaces it. `AttachmentStore.readImage()` fails with `ATTACHMENT_NOT_FOUND`, `ATTACHMENT_CORRUPT`, or `ATTACHMENT_READ_FAILED` when the referenced object disappears, fails integrity verification, or cannot be read. The unchanged history then makes every later model request fail on the same object, leaving the session unable to continue even though the remaining messages are usable. This is the unavailable-object case left fail-loud by [reconstructable requests](../../implemented/architecture/2026-07-05-reconstructable-requests.md). + +## Proposal + +A session-backed image-request projection records unreadable references before provider dispatch. `ATTACHMENT_NOT_FOUND` and `ATTACHMENT_CORRUPT` immediately append `attachment/quarantine`; `ATTACHMENT_READ_FAILED` receives one cancellation-aware read retry and appends the same event with a retryable reason if the retry fails. Cancellation and unclassified failures do not quarantine data. + +The quarantine event identifies the attachment and failure class. Projection replaces each quarantined image with deterministic text containing its display name when present, attachment-id prefix, and failure class. Later requests derive the same replacement from the log and skip `readImage()` for that reference, while the original image block remains in append-only history. A request that discovers and records a quarantine reprojects before calling the provider, so the failed read does not become a terminal model-request attempt. + +Explicit recovery calls `readImage()` and appends `attachment/recovered` only after digest and metadata verification succeeds. Projection then restores the original image reference. Missing or corrupt bytes are never overwritten automatically, and clearing quarantine without verification is invalid. + +The shared request-projection consumer owns this policy. Attachment storage continues to report exact read failures, and provider adapters do not invent independent placeholders or recovery state. + +## Alternatives considered + +- **Keep failing every request.** This preserves strict error reporting but makes an otherwise usable durable session permanently unavailable after one storage fault. +- **Delete or rewrite the historical image block.** That loses evidence, violates append-only history, and prevents a repaired content-addressed object from restoring the original request. +- **Catch the error independently in each adapter.** An unlogged placeholder would make replay depend on which adapter and storage state happened to be present, while duplicated policies would drift. +- **Replace missing or corrupt bytes automatically.** The reference names verified immutable content; substituting different bytes under that identity would defeat integrity checking. + +## Acceptance criteria + +- A missing or corrupt historical image produces one durable quarantine transition and a stable placeholder; later model requests do not read that object or fail because of it. +- A general read failure is retried once without ignoring cancellation, then follows the retryable quarantine path. +- Restart and fork reconstruct the same quarantined request from the session log. +- Recovery restores image projection only after the original reference passes complete read verification. +- Package tests cover error classification, idempotent quarantine, cancellation, retry, recovery, and nested tool-result images; a keyless runnable snapshot pins the model-visible placeholder and durable events. + +## Risks + +Quarantine and recovery each change the provider prefix once. The implementation must identify the exact failing reference before recording state and must coordinate concurrent requests so duplicate failures produce one effective transition. Auxiliary calls without a live session cannot record recovery state; their failure policy remains explicit implementation scope rather than an adapter fallback. diff --git a/.agents/notes/proposed/bug-fix/2026-08-20-attachment-read-quarantine.zh.md b/.agents/notes/proposed/bug-fix/2026-08-20-attachment-read-quarantine.zh.md new file mode 100644 index 0000000000..7f4ceae4e1 --- /dev/null +++ b/.agents/notes/proposed/bug-fix/2026-08-20-attachment-read-quarantine.zh.md @@ -0,0 +1,38 @@ +# Agent Note: 隔离无法读取的历史附件 + +Status: proposed + +[English](2026-08-20-attachment-read-quarantine.md) | 中文 + +## 问题 + +已接纳的 `ImageAttachmentRef` 会留在持久历史中，因此在被压缩替换前都会参与之后的每次请求。引用对象丢失、完整性校验失败或无法读取时，`AttachmentStore.readImage()` 会返回 `ATTACHMENT_NOT_FOUND`、`ATTACHMENT_CORRUPT` 或 `ATTACHMENT_READ_FAILED`。未变化的历史随后会让之后每次模型请求在同一对象上失败，使会话无法继续，即使其余消息仍可使用。这是[可重建请求](../../implemented/architecture/2026-07-05-reconstructable-requests.zh.md)保留为明确失败的对象不可用情况。 + +## 提案 + +由会话支撑的图片请求投影在分派给提供方之前记录无法读取的引用。`ATTACHMENT_NOT_FOUND` 和 `ATTACHMENT_CORRUPT` 立即追加 `attachment/quarantine`；`ATTACHMENT_READ_FAILED` 先执行一次服从取消信号的读取重试，重试仍失败时追加同一事件并标记为可重试原因。取消和未分类失败不会隔离数据。 + +隔离事件标识附件和失败类别。投影把每张已隔离图片替换为确定性文本，包含可用时的显示名称、附件 ID 前缀和失败类别。之后的请求从日志派生相同替换结果，并跳过该引用的 `readImage()`，原始图片块仍留在仅追加历史中。请求发现并记录隔离后，会在调用提供方前重新投影，因此读取失败不会成为终止性的模型请求尝试。 + +显式恢复会调用 `readImage()`，且仅在内容摘要和元数据校验成功后追加 `attachment/recovered`。投影随后恢复原始图片引用。系统绝不会自动覆盖丢失或损坏的字节，也不允许未经验证就清除隔离。 + +共享请求投影消费方拥有这项策略。附件存储继续报告准确的读取失败，提供方适配器不会各自生成占位或恢复状态。 + +## 考虑过的替代方案 + +- **让每次请求继续失败。** 这保留了严格错误报告，但一次存储故障会让其他部分仍可使用的持久会话永久不可用。 +- **删除或重写历史图片块。** 这会丢失证据、违反仅追加历史，并使修复后的内容寻址对象无法恢复原始请求。 +- **由每个适配器分别捕获错误。** 未记录的占位会让回放取决于当时存在的适配器和存储状态，重复策略也会发生偏差。 +- **自动替换丢失或损坏的字节。** 引用标识经过验证的不可变内容；在该身份下替换成其他字节会破坏完整性校验。 + +## 接受标准 + +- 缺失或损坏的历史图片产生一次持久隔离转换和稳定占位；之后的模型请求不再读取该对象，也不会因它失败。 +- 一般读取失败会在服从取消信号的前提下重试一次，随后进入可重试隔离路径。 +- 重启和 fork 后会从会话日志重建相同的隔离请求。 +- 仅在原始引用通过完整读取校验后，恢复操作才恢复图片投影。 +- 包测试覆盖错误分类、幂等隔离、取消、重试、恢复和嵌套工具结果图片；一个无需密钥的可运行快照钉住模型可见占位和持久事件。 + +## 风险 + +隔离和恢复各会改变一次提供方前缀。实现必须在记录状态前识别准确的失败引用，并协调并发请求，使重复失败只产生一次有效转换。没有活跃会话的辅助调用无法记录恢复状态；它们的失败策略属于明确的实现范围，不能退回到适配器自行处理。 diff --git a/.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.i18n.yaml b/.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.i18n.yaml index cf38638484..fff61a1e56 100644 --- a/.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.i18n.yaml +++ b/.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.md -2026-06-30-pre-tool-input-rewrite.md: 63027079a996f2f7b9d2ef87afcd4e64a2691fb1 -2026-06-30-pre-tool-input-rewrite.zh.md: 7697f285506a2df029be3811429dfe621f65951d +2026-06-30-pre-tool-input-rewrite.md: a42b05ac7d2b4d5808807a5810b9e0c4354333a5 +2026-06-30-pre-tool-input-rewrite.zh.md: 8ef07ea7b6ca446b796c3977d5c87a1e7c49917a diff --git a/.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.md b/.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.md index 63027079a9..a42b05ac7d 100644 --- a/.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.md +++ b/.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.md @@ -16,7 +16,7 @@ In the loop, a tool call's arguments are committed to the log and read by live c 2. **`tool/call`** is the durable AUDIT record, appended before `ctx.tools.execute()`. 3. **Human-facing presentation reads `tool/call.arguments`**: UI renderers pass them to `presentResult`; `dsh-tool-bash` derives the card title, the rawInput, the cwd, and the terminal-vs-background treatment from them. -An execution-only rewrite would make the UI show one command while another ran and render the result against the wrong arguments. The registry prevents that failure mode today: it structured-clones and deep-freezes `arguments`, makes the execution identity properties non-writable, and exposes no test shim or listener path that can replace them. The rewrite design must preserve that protected-identity boundary rather than weaken it. +An execution-only rewrite would make the UI show one command while another ran and render the result against the wrong arguments. The registry prevents that failure mode: it structured-clones and deep-freezes `arguments`, makes the execution identity properties non-writable, and exposes no test shim or listener path that can replace them. The rewrite design must preserve that protected-identity boundary rather than weaken it. ## Proposal diff --git a/.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.zh.md b/.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.zh.md index 7697f28550..8ef07ea7b6 100644 --- a/.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.zh.md +++ b/.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.zh.md @@ -16,7 +16,7 @@ Status: proposed 2. **`tool/call`** 是持久化的审计记录，在 `ctx.tools.execute()` 之前追加。 3. **面向人类的展示读取 `tool/call.arguments`**：UI 渲染器将这些参数传给 `presentResult`；`dsh-tool-bash` 从中派生卡片标题、rawInput、cwd 以及终端/后台处理方式。 -如果只做执行层面的重写，UI 会显示一条命令而实际运行的是另一条，并且结果会对着错误的参数渲染。注册表目前通过以下方式防止这种失败模式：对 `arguments` 做 structured-clone 并深度冻结，将执行身份属性设为不可写，且不暴露任何可替换它们的测试 shim 或监听路径。重写设计必须维护这一受保护的身份边界，而非削弱它。 +如果只做执行层面的重写，UI 会显示一条命令而实际运行的是另一条，并且结果会对着错误的参数渲染。注册表通过以下方式防止这种失败模式：对 `arguments` 做 structured-clone 并深度冻结，将执行身份属性设为不可写，且不暴露任何可替换它们的测试 shim 或监听路径。重写设计必须维护这一受保护的身份边界，而非削弱它。 ## 提案 diff --git a/.agents/notes/proposed/feature/2026-07-06-recallable-compaction.i18n.yaml b/.agents/notes/proposed/feature/2026-07-06-recallable-compaction.i18n.yaml index da00fd4570..7ce81010a9 100644 --- a/.agents/notes/proposed/feature/2026-07-06-recallable-compaction.i18n.yaml +++ b/.agents/notes/proposed/feature/2026-07-06-recallable-compaction.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/proposed/feature/2026-07-06-recallable-compaction.md -2026-07-06-recallable-compaction.md: 377ced0b0ec001287c0c7a3f1900249b30872b95 -2026-07-06-recallable-compaction.zh.md: a78760d6dcaf40f9a8439d61b5ebcdf8a7a97a77 +2026-07-06-recallable-compaction.md: 7309297af84a43a29e03feae815ac8c937a9da6a +2026-07-06-recallable-compaction.zh.md: 890493ae7d6a7b9066dd071b2cc8f642e9c84c86 diff --git a/.agents/notes/proposed/feature/2026-07-06-recallable-compaction.md b/.agents/notes/proposed/feature/2026-07-06-recallable-compaction.md index 377ced0b0e..7309297af8 100644 --- a/.agents/notes/proposed/feature/2026-07-06-recallable-compaction.md +++ b/.agents/notes/proposed/feature/2026-07-06-recallable-compaction.md @@ -28,7 +28,7 @@ A committed stub is never rewritten and never re-enters a later compaction regio ### The state checkpoint -One mutable working-memory document (at most one; zero before the first pass), positioned after all stubs and before the retained tail. Each pass rewrites it from the previous state plus this pass's staled content — O(previous + new), under the merge-don't-restate rule already in the summarization prompt — covering decisions, current state, constraints, and next steps. It carries its own footer and a size cap at the scale of today's summary. +One mutable working-memory document (at most one; zero before the first pass), positioned after all stubs and before the retained tail. Each pass rewrites it from the previous state plus this pass's staled content — O(previous + new), under the merge-don't-restate rule already in the summarization prompt — covering decisions, current state, constraints, and next steps. It carries its own footer and a size cap at the scale of the existing summary. An inflation guard bounds the whole pass: if the post-compaction size is not strictly below the pre-compaction size, nothing commits and the turn proceeds; the attempt defers until more stale history accumulates. The guard compares one metric on both sides — provider-reported usage from the request path, falling back to the character estimator on both sides. @@ -50,7 +50,7 @@ Both read `exec.agent.session.events` (the tool-todo access pattern; non-agent c ### Cache and cost -The request prefix after a pass is `[system][stubs…][state][tail]`. Frozen stubs are byte-stable across passes, so the miss begins at the token replacing the previous state checkpoint and stays O(new chunks + state + tail) — against position zero today. Recall output lands at the tail, leaving the prefix untouched. Per-pass summarize input is roughly twice today's plus an m·S background term, bounded by a `chunkTokens` floor (a small multiple of the state cap) and a validated `stubTokens`/`chunkTokens` ratio ceiling; a shared-prefix input layout (preamble, then the byte-identical pass-start state, slice content in the tail) lets sibling calls earn cached-rate rereads. +The request prefix after a pass is `[system][stubs…][state][tail]`. Frozen stubs are byte-stable across passes, so the miss begins at the token replacing the previous state checkpoint and stays O(new chunks + state + tail) — instead of the baseline's position-zero miss. Recall output lands at the tail, leaving the prefix untouched. Per-pass summarize input is roughly twice the baseline input plus an m·S background term, bounded by a `chunkTokens` floor (a small multiple of the state cap) and a validated `stubTokens`/`chunkTokens` ratio ceiling; a shared-prefix input layout (preamble, then the byte-identical pass-start state, slice content in the tail) lets sibling calls earn cached-rate rereads. ### Packaging @@ -78,7 +78,7 @@ Deferred until observation calls for them: ## Alternatives considered -- **Staged delivery** (ship recall tools alone over today's backend; gate the checkpoint split on observed recall usage) — rejected: untrained models under-use any new tool, so the gate would measure training absence rather than design value, while the training side needs the complete mechanism to build environments against; the pre-release window is when persisted-format changes are cheapest; and the cache economics are first-party knowledge, not a hypothesis awaiting telemetry. The implementation still lands as stacked PRs with the recall tools first — construction order, not a decision gate. +- **Staged delivery** (ship recall tools alone over the existing backend; gate the checkpoint split on observed recall usage) — rejected: untrained models under-use any new tool, so the gate would measure training absence rather than design value, while the training side needs the complete mechanism to build environments against; the pre-release window is when persisted-format changes are cheapest; and the cache economics are first-party knowledge, not a hypothesis awaiting telemetry. The mechanism still introduces the recall tools before the checkpoint split; that is construction order, not a decision gate. - **All-frozen full-size summaries, no state checkpoint** — rejected: unbounded permanent-prefix growth, self-accelerating toward thrashing, with nothing left to re-prioritize. - **Pure stubs, no state checkpoint** — rejected: presumes the model knows what it is missing; fails on unknown unknowns. - **LLM aging/consolidation of frozen chunks** — rejected as a routine mechanism: summary-of-summary loss and frozen-prefix churn; the code-only rollup is its surviving form, deferred. @@ -102,9 +102,9 @@ Deferred until observation calls for them: ## Risks -- **Recall is a learned behavior**: untrained models will under-use it, and the bench report exists to track the gap while training closes it. Until then the state checkpoint keeps the floor at today's summary quality. +- **Recall is a learned behavior**: untrained models will under-use it, and the bench report exists to track the gap while training closes it. Until then the state checkpoint keeps the floor at the existing summary quality. - **Unknown unknowns remain**: a detail absent from summaries and keywords draws no recall. Recall converts "unreachable even when suspected" into "reachable when suspected". - **The stub directory occupies attention**: dozens of stable index cards per request may dilute focus; the bench measurement in the acceptance criteria tracks it against `compaction-basic`. -- **Cost**: per-pass summarize input is roughly twice today's; short sessions sit near today's cost and quality, and the design pays off with session length. +- **Cost**: per-pass summarize input is roughly twice the baseline input; short sessions sit near the baseline cost and quality, and the design pays off with session length. - **State drift and division-of-labor leakage** are observable through the handoff probe and stub review; their counters are specified follow-ups. - **Two backends** are a maintenance burden; the seam contract and the shared recall consumer bound it, and the bench comparison decides the default over time. diff --git a/.agents/notes/proposed/feature/2026-07-06-recallable-compaction.zh.md b/.agents/notes/proposed/feature/2026-07-06-recallable-compaction.zh.md index a78760d6dc..890493ae7d 100644 --- a/.agents/notes/proposed/feature/2026-07-06-recallable-compaction.zh.md +++ b/.agents/notes/proposed/feature/2026-07-06-recallable-compaction.zh.md @@ -28,7 +28,7 @@ Status: proposed ### 状态检查点 -系统维护一份可变的工作记忆文档（最多一份；第一次压缩前为零份），位于所有存根之后、保留尾部之前。每一轮根据先前状态与本轮变为陈旧的内容重写它，成本为 O(previous + new)；过程遵守摘要提示词中已有的「合并而不重复陈述」规则，并覆盖决策、当前状态、约束和后续步骤。它带有自己的页脚，其大小上限与当前摘要处于同一量级。 +系统维护一份可变的工作记忆文档（最多一份；第一次压缩前为零份），位于所有存根之后、保留尾部之前。每一轮根据先前状态与本轮变为陈旧的内容重写它，成本为 O(previous + new)；过程遵守摘要提示词中已有的「合并而不重复陈述」规则，并覆盖决策、当前状态、约束和后续步骤。它带有自己的页脚，其大小上限与现有摘要处于同一量级。 膨胀保护会约束整轮操作：如果压缩后大小没有严格小于压缩前大小，就不提交任何内容，并继续当前轮次；本次尝试延后至积累更多陈旧历史后再进行。保护逻辑在两侧比较同一项度量：优先使用请求路径上提供方报告的用量；如果不可用，则两侧都回退为字符估算器。 @@ -50,7 +50,7 @@ Status: proposed ### 缓存与成本 -一轮后的请求前缀为 `[system][stubs…][state][tail]`。冻结存根在各轮之间逐字节稳定，因此缓存缺失从替换先前状态检查点的 token 才开始，规模保持 O(new chunks + state + tail)，而当前实现会从位置零开始缺失。回溯输出落在尾部，不会改变前缀。每轮摘要输入大约是当前实现的两倍，另加一个 m·S 背景项；该成本受到 `chunkTokens` 下限（状态上限的小倍数）以及经过校验的 `stubTokens`／`chunkTokens` 比例上限约束。共享前缀输入布局依次为前导内容、逐字节相同的本轮开始状态、位于尾部的切片内容，使同级调用可以按缓存费率重复读取。 +一轮后的请求前缀为 `[system][stubs…][state][tail]`。冻结存根在各轮之间逐字节稳定，因此缓存缺失从替换先前状态检查点的 token 才开始，规模保持 O(new chunks + state + tail)，而基线实现会从位置零开始缺失。回溯输出落在尾部，不会改变前缀。每轮摘要输入大约是基线输入的两倍，另加一个 m·S 背景项；该成本受到 `chunkTokens` 下限（状态上限的小倍数）以及经过校验的 `stubTokens`／`chunkTokens` 比例上限约束。共享前缀输入布局依次为前导内容、逐字节相同的本轮开始状态、位于尾部的切片内容，使同级调用可以按缓存费率重复读取。 ### 打包方式 @@ -78,7 +78,7 @@ Status: proposed ## 考虑过的替代方案 -- **分阶段交付**（先在当前后端之上单独交付回溯工具；观察到回溯使用后，再决定是否拆分检查点）：不予采纳。未经训练的模型会低频使用任何新工具，因此该条件测量的是训练缺失，而不是设计价值；训练侧需要完整机制来构建环境；预发布阶段修改持久化格式的成本最低；缓存经济性则属于第一方已经掌握的知识，不是等待遥测验证的假设。实现仍以堆叠 PR（Pull Request）方式落地，并先交付回溯工具，但这只是构建顺序，不是决策门槛。 +- **分阶段交付**（先在现有后端之上单独交付回溯工具；观察到回溯使用后，再决定是否拆分检查点）：不予采纳。未经训练的模型会低频使用任何新工具，因此该条件测量的是训练缺失，而不是设计价值；训练侧需要完整机制来构建环境；预发布阶段修改持久化格式的成本最低；缓存经济性则属于第一方已经掌握的知识，不是等待遥测验证的假设。该机制仍先引入回溯工具，再拆分检查点；这只是构建顺序，不是决策门槛。 - **只保留冻结的全尺寸摘要，不设状态检查点**：不予采纳，因为永久前缀会无界增长、自我加速并最终发生颠簸，而且没有任何内容可以重新确定优先级。 - **只保留纯存根，不设状态检查点**：不予采纳，因为这假定模型知道自己缺少什么，在面对未知的未知时会失败。 - **由 LLM 老化／整合冻结分片**：不作为常规机制，因为摘要的摘要会丢失信息，并使冻结前缀频繁变化；其保留下来的形式是由代码汇总，且延后实现。 @@ -102,9 +102,9 @@ Status: proposed ## 风险 -- **回溯属于学习到的行为**：未经训练的模型会低频使用它，bench 报告会持续追踪这项差距，直至训练弥合问题。在此之前，状态检查点会让质量下限保持在当前摘要水平。 +- **回溯属于学习到的行为**：未经训练的模型会低频使用它，bench 报告会持续追踪这项差距，直至训练弥合问题。在此之前，状态检查点会让质量下限保持在现有摘要的质量水平。 - **未知的未知仍然存在**：如果某项细节既未出现在摘要中，也未出现在关键词中，就不会触发回溯。回溯把「即使已经怀疑也无法触达」变成「怀疑时可以触达」。 - **存根目录会占用注意力**：每次请求中包含数十张稳定的索引卡，可能稀释模型关注点；验收标准中的 bench 度量会将其与 `compaction-basic` 对比。 -- **成本**：每轮摘要输入大约是当前实现的两倍；短会话的成本和质量接近当前水平，而设计收益随会话长度增长。 +- **成本**：每轮摘要输入大约是基线输入的两倍；短会话的成本和质量接近基线水平，而设计收益随会话长度增长。 - **状态漂移与职责分工泄漏**可以通过交接探针和存根评审观察；对应措施已列为后续事项。 - **两个后端**会扩大维护范围；seam 约定和共享回溯消费方会限制这一范围，bench 对比则用于逐步决定默认实现。 diff --git a/.agents/notes/proposed/feature/2026-08-04-task-surface.i18n.yaml b/.agents/notes/proposed/feature/2026-08-04-task-surface.i18n.yaml index e8f45bb052..5c561d9188 100644 --- a/.agents/notes/proposed/feature/2026-08-04-task-surface.i18n.yaml +++ b/.agents/notes/proposed/feature/2026-08-04-task-surface.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/proposed/feature/2026-08-04-task-surface.md -2026-08-04-task-surface.md: 13edd1c89514363e43753f366b7b38b6810bd969 -2026-08-04-task-surface.zh.md: ac3fdc48073c7d63d1f0f33bdf7861064d4449c6 +2026-08-04-task-surface.md: dbf73976b606a4a45202c1b29b79f5cfbd77ac1c +2026-08-04-task-surface.zh.md: ecf8764b7b1da7a4a874dd78c6f69df80fb36f36 diff --git a/.agents/notes/proposed/feature/2026-08-04-task-surface.md b/.agents/notes/proposed/feature/2026-08-04-task-surface.md index 13edd1c895..dbf73976b6 100644 --- a/.agents/notes/proposed/feature/2026-08-04-task-surface.md +++ b/.agents/notes/proposed/feature/2026-08-04-task-surface.md @@ -6,7 +6,7 @@ English | [中文](2026-08-04-task-surface.zh.md) ## Problem -Some tasks are awkward to finish through alternating prose messages. Comparing several options, reordering a plan, reviewing a table, or filling a small set of related fields all work better as one structured interaction. Today an agent can describe such an interaction, but it cannot ask the Web client to render one without adding a permanent product component or generating executable Client Plugin code. +Some tasks are awkward to finish through alternating prose messages. Comparing several options, reordering a plan, reviewing a table, or filling a small set of related fields all work better as one structured interaction. An agent can describe such an interaction, but it cannot ask the Web client to render one without adding a permanent product component or generating executable Client Plugin code. Those two workarounds put ownership in the wrong place. Product-specific components require a new trigger and release for every task shape. Generated code has far more authority and lifecycle cost than a one-turn form needs. It also makes the presentation, rather than the user's conclusion, the durable artifact. @@ -274,7 +274,7 @@ The implementation depends on the existing message log, canonical tool output, t ## Risks -The first component set may be either too small for useful tasks or broad enough to become a weak application framework. Usage evidence should decide additions; v1 has no expression language or network behavior. +The first component set may be either too small for useful tasks or broad enough to become a weak application framework. Usage evidence should decide additions; the initial set has no expression language or network behavior. The Task Surface Markdown policy gives up inline images, media, and automatic link previews. Ordinary links remain useful, but only an explicit user activation may navigate or start a request. diff --git a/.agents/notes/proposed/feature/2026-08-04-task-surface.zh.md b/.agents/notes/proposed/feature/2026-08-04-task-surface.zh.md index ac3fdc4807..ecf8764b7b 100644 --- a/.agents/notes/proposed/feature/2026-08-04-task-surface.zh.md +++ b/.agents/notes/proposed/feature/2026-08-04-task-surface.zh.md @@ -6,7 +6,7 @@ Status: proposed ## 问题 -有些任务很难通过交替发送文本消息来完成。比较多个选项、调整计划顺序、审阅表格，或填写一小组关联字段，都更适合在一次结构化交互中处理。目前，agent（智能体）可以描述这类交互，但若不增加永久的产品组件或生成可执行的客户端插件代码，就无法要求 Web 客户端渲染这类交互。 +有些任务很难通过交替发送文本消息来完成。比较多个选项、调整计划顺序、审阅表格，或填写一小组关联字段，都更适合在一次结构化交互中处理。agent（智能体）可以描述这类交互，但若不增加永久的产品组件或生成可执行的客户端插件代码，就无法要求 Web 客户端渲染这类交互。 这两种变通方案的职责归属都不合理。产品专用组件要求每种任务形态都新增触发方式并发布新版本。对于只需一个轮次的表单，生成代码所拥有的权限和生命周期成本都远超实际需要。这样做还会把展示界面而非用户结论变成持久产物。 @@ -274,7 +274,7 @@ Web 插件将未提交值保存在一个有界、按会话持久化的 slot stor ## 风险 -第一批组件可能小到无法满足实际任务，也可能大到足以演变成一个粗糙的应用框架。是否新增组件应由使用证据决定；v1 不提供表达式语言或网络行为。 +第一批组件可能小到无法满足实际任务，也可能大到足以演变成一个粗糙的应用框架。是否新增组件应由使用证据决定；初始组件集不提供表达式语言或网络行为。 Task Surface 的 Markdown 策略舍弃行内图片、媒体和自动链接预览。普通链接仍有用，但只有用户显式操作后，才可以导航或发起请求。 diff --git a/.agents/notes/proposed/simplification/2026-07-04-prune-dead-core-spine-api.i18n.yaml b/.agents/notes/proposed/simplification/2026-07-04-prune-dead-core-spine-api.i18n.yaml index d13e5e6f1d..b84fc76dbd 100644 --- a/.agents/notes/proposed/simplification/2026-07-04-prune-dead-core-spine-api.i18n.yaml +++ b/.agents/notes/proposed/simplification/2026-07-04-prune-dead-core-spine-api.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/proposed/simplification/2026-07-04-prune-dead-core-spine-api.md -2026-07-04-prune-dead-core-spine-api.md: 64c9bb00a7f26463aea6767018da8814a13133ec -2026-07-04-prune-dead-core-spine-api.zh.md: 0666fa8b6b6228b97ade7ba91eb214db82f6bf94 +2026-07-04-prune-dead-core-spine-api.md: ae6ea2d763c1f84b32d1a24bae32f412c77c9976 +2026-07-04-prune-dead-core-spine-api.zh.md: 8e76827de10e119ed1e0d9fbf8a44e8eaf21575c diff --git a/.agents/notes/proposed/simplification/2026-07-04-prune-dead-core-spine-api.md b/.agents/notes/proposed/simplification/2026-07-04-prune-dead-core-spine-api.md index 64c9bb00a7..ae6ea2d763 100644 --- a/.agents/notes/proposed/simplification/2026-07-04-prune-dead-core-spine-api.md +++ b/.agents/notes/proposed/simplification/2026-07-04-prune-dead-core-spine-api.md @@ -47,7 +47,7 @@ Remove or demote every row as one bounded coordinated public-surface cleanup. Up ## Alternatives considered -**Keep test conveniences and self-contained results public.** Public helpers can make white-box tests convenient, self-contained result fields can look ergonomic, and future embedders might want the concrete loop or enumeration methods. Those benefits are hypothetical; today they make every implementation and document explain states that no shipped caller can observe. A real consumer can introduce the smallest contract it needs, with its ownership and failure semantics known. +**Keep test conveniences and self-contained results public.** Public helpers can make white-box tests convenient, self-contained result fields can look ergonomic, and future embedders might want the concrete loop or enumeration methods. Those benefits are hypothetical; retaining them makes every implementation and document explain states that no shipped caller can observe. A real consumer can introduce the smallest contract it needs, with its ownership and failure semantics known. **Keep every catalogued member for model-written mounts.** The self-referential toolset is a real generic consumer route, not generated-doc noise. Its value comes from an accurate, composable service API, however, not from preserving duplicate fields or incoherent argument pairs indefinitely; each catalogued contraction above removes a fact available elsewhere on the same execution, agent, or result and updates the API reference in the same change. diff --git a/.agents/notes/proposed/simplification/2026-07-04-prune-dead-core-spine-api.zh.md b/.agents/notes/proposed/simplification/2026-07-04-prune-dead-core-spine-api.zh.md index 0666fa8b6b..8e76827de1 100644 --- a/.agents/notes/proposed/simplification/2026-07-04-prune-dead-core-spine-api.zh.md +++ b/.agents/notes/proposed/simplification/2026-07-04-prune-dead-core-spine-api.zh.md @@ -47,7 +47,7 @@ Status: proposed ## 曾考虑的替代方案 -**保留测试便利函数和自包含的结果字段为公开。** 公开辅助函数可以让白盒测试更方便，自包含的结果字段看起来更易用，未来的嵌入者可能需要具体循环类或枚举方法。这些好处是假设性的；当前它们让每处实现和文档都要解释没有已交付调用者能观察到的状态。真正的消费方可以引入它所需的最小约定，其所有权和失败语义明确。 +**保留测试便利函数和自包含的结果字段为公开。** 公开辅助函数可以让白盒测试更方便，自包含的结果字段看起来更易用，未来的嵌入者可能需要具体循环类或枚举方法。这些好处是假设性的；保留它们会让每处实现和文档都要解释没有已交付调用者能观察到的状态。真正的消费方可以引入它所需的最小约定，其所有权和失败语义明确。 **保留所有 catalog 成员以供模型编写的 mount 使用。** 自引用工具集是一条真实的通用消费路径，而非生成文档的噪音。然而，它的价值来自准确、可组合的服务接口，而非无限期保留重复字段或不一致的参数对；上述每一项 catalog 收缩都移除了在同一次执行、同一个 agent（智能体）或同一结果中其他位置已可获得的事实，并在同一变更中更新 API 参考。 diff --git a/.agents/notes/proposed/simplification/2026-07-19-make-jsonrpc-directional.i18n.yaml b/.agents/notes/proposed/simplification/2026-07-19-make-jsonrpc-directional.i18n.yaml index de8021afc9..6f4de4d9ae 100644 --- a/.agents/notes/proposed/simplification/2026-07-19-make-jsonrpc-directional.i18n.yaml +++ b/.agents/notes/proposed/simplification/2026-07-19-make-jsonrpc-directional.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/proposed/simplification/2026-07-19-make-jsonrpc-directional.md -2026-07-19-make-jsonrpc-directional.md: be0d8003e066b8695fb413d5a546e43694bf2225 -2026-07-19-make-jsonrpc-directional.zh.md: d070983b14898078b481a930eb70e7f6db53714a +2026-07-19-make-jsonrpc-directional.md: 6afb75eaf39ef8ce32b8885fde0e42cd388a46ec +2026-07-19-make-jsonrpc-directional.zh.md: a6c6abb7bdb5b3c03746c93604660ab86a4ce9d6 diff --git a/.agents/notes/proposed/simplification/2026-07-19-make-jsonrpc-directional.md b/.agents/notes/proposed/simplification/2026-07-19-make-jsonrpc-directional.md index be0d8003e0..6afb75eaf3 100644 --- a/.agents/notes/proposed/simplification/2026-07-19-make-jsonrpc-directional.md +++ b/.agents/notes/proposed/simplification/2026-07-19-make-jsonrpc-directional.md @@ -28,7 +28,7 @@ Return the settled outcome directly from `session/prompt` as `{ status, reason } ## Alternatives considered -**Keep a generic symmetric JSON-RPC peer for future methods.** Server-initiated requests may eventually support interactive permissions, but no typed method or production consumer exists. The pre-release protocol can add the smallest required direction when that feature is designed instead of carrying an unexercised peer today. +**Keep a generic symmetric JSON-RPC peer for future methods.** Server-initiated requests may eventually support interactive permissions, but no typed method or production consumer exists. The pre-release protocol can add the smallest required direction when that feature is designed instead of carrying an unexercised peer in the shipped protocol. **Keep `session.finished` for streaming clients.** Turn settlement is not incremental data: the request response already marks the same boundary and follows all earlier notifications on the ordered stream. A second terminal notification creates two representations that clients must reconcile. diff --git a/.agents/notes/proposed/simplification/2026-07-19-make-jsonrpc-directional.zh.md b/.agents/notes/proposed/simplification/2026-07-19-make-jsonrpc-directional.zh.md index d070983b14..a6c6abb7bd 100644 --- a/.agents/notes/proposed/simplification/2026-07-19-make-jsonrpc-directional.zh.md +++ b/.agents/notes/proposed/simplification/2026-07-19-make-jsonrpc-directional.zh.md @@ -28,7 +28,7 @@ JSON-RPC 桥接层把两个端点都建模为对称的对等端，但实际协 ## 备选方案 -**为未来方法保留通用的对称 JSON-RPC 对等端。** 服务端发起的请求将来可能用于交互式权限，但当前没有类型化方法或生产消费方。该功能完成设计后，预发布协议可以增加所需的最小方向，无需提前保留未使用的对等端能力。 +**为未来方法保留通用的对称 JSON-RPC 对等端。** 服务端发起的请求将来可能用于交互式权限，但没有类型化方法或生产消费方。该功能完成设计后，预发布协议可以增加所需的最小方向，无需提前保留未使用的对等端能力。 **为流式客户端保留 `session.finished`。** 轮次结束不是增量数据：请求响应已经标识同一个边界，并且在有序流中位于先前所有通知之后。第二条终止通知会产生两种结果表示，迫使客户端进行协调。 diff --git a/.agents/notes/rejected/feature/2026-07-26-evaluate-landstrip-for-windows-sandbox-rung.i18n.yaml b/.agents/notes/rejected/feature/2026-07-26-evaluate-landstrip-for-windows-sandbox-rung.i18n.yaml deleted file mode 100644 index dca75b57c9..0000000000 --- a/.agents/notes/rejected/feature/2026-07-26-evaluate-landstrip-for-windows-sandbox-rung.i18n.yaml +++ /dev/null @@ -1,6 +0,0 @@ -# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each -# side as of the last confirmed-consistent state. Both languages carry equal authority; -# after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write .agents/notes/rejected/feature/2026-07-26-evaluate-landstrip-for-windows-sandbox-rung.md -2026-07-26-evaluate-landstrip-for-windows-sandbox-rung.md: e995ec4e20f41cc4377131c0f6e8672e0588ccea -2026-07-26-evaluate-landstrip-for-windows-sandbox-rung.zh.md: aac6b9772e2ae9ec8d72eaa569f3a84020df94d7 diff --git a/.agents/notes/rejected/feature/2026-07-26-evaluate-landstrip-for-windows-sandbox-rung.md b/.agents/notes/rejected/feature/2026-07-26-evaluate-landstrip-for-windows-sandbox-rung.md deleted file mode 100644 index e995ec4e20..0000000000 --- a/.agents/notes/rejected/feature/2026-07-26-evaluate-landstrip-for-windows-sandbox-rung.md +++ /dev/null @@ -1,34 +0,0 @@ -# Agent Note: Evaluate landstrip before building a Windows sandbox launcher - -Status: rejected — landstrip is not battle-tested (a days-old single-maintainer project, ~48 GitHub stars at rejection); a security-invariant dependency must have proven adoption, so the win32 rung keeps the in-house-launcher plan - -English | [中文](2026-07-26-evaluate-landstrip-for-windows-sandbox-rung.zh.md) - -## Problem - -The [sandbox decision](../../implemented/feature/2026-07-06-sandbox.md) leaves `PLATFORM_CHAINS.win32` empty and plans to fill it with "a confinement runner from the AppContainer/restricted-token family, shipped from its own repository on the `node-addon-landlock-run` template" — an estimated ~1,500-line new repo (the landlock-run subtree is ~1,460 lines of C/TS/scripts/tests plus docs and CI) authored and maintained in-house. - -Since that note was written, a maintained third-party runner has appeared: `@landstrip/landstrip` (npm, actively developed, Rust core with prebuilt per-platform `optionalDependencies`) covers Landlock + seccomp on Linux, Seatbelt on macOS, and AppContainer/restricted-user on Windows, with JSON/YAML policy input and a trap-fd denial-reporting channel. It is exec-wrapped like bwrap, so it fits the chain's `confine(argv)` shape without touching the Linux/macOS rungs. - -## Proposal - -When the Windows sandbox phase is picked up, evaluate wrapping landstrip's Windows backend as the `win32` chain runner before authoring an in-house AppContainer launcher repository. The evaluation must answer: - -- **Probe synthesis.** landstrip has no `--probe`; the chain's functional-probe contract would have to be synthesized from a trap run. -- **Dialect mapping.** Denial and runner-failure stderr dialects, and fail-closed exit-code classification, need explicit mapping into the chain's vocabulary. -- **License.** The binaries are LGPL-2.1-or-later; distribution review is required before it enters the shipped closure. -- **Source and build record.** Each in-house launcher binary is byte-pinned to a native CI build of a ~300-line reviewable C file; landstrip is a single-maintainer Rust binary set. For the *existing Linux rung* that trade is already settled — do not swap it ([sandbox note](../../implemented/feature/2026-07-06-sandbox.md) and the launcher's own migration away from a Rust dependency). For a rung we have not built, weighing third-party maintenance against a second in-house native repo is a genuinely open question. - -## Alternatives considered - -- **Build the in-house AppContainer launcher as planned.** Still the default if the evaluation fails on license, source/build auditability, or probe fit; the cost is owning a second native security launcher repo indefinitely. -- **Swap the Linux Landlock rung to landstrip too.** Rejected outright: sandbox correctness is a security invariant, the current launcher has reviewable C source and binaries byte-pinned to native CI builds, and it already migrated away from a Rust dependency for exactly this reason. - -## Acceptance criteria - -- Before any Windows-rung implementation starts, an evaluation records the probe, dialect, license, source repository, release process, and binary build answers, and the go/no-go is added to the sandbox note's deferred-phases plan. - -## Risks - -- Single-maintainer supply chain in a security-critical position — the reason this is an evaluation gate, not an adoption decision. -- The package is young; its API and packaging may churn before the Windows phase starts, so re-verify against the live registry then. diff --git a/.agents/notes/rejected/feature/2026-07-26-evaluate-landstrip-for-windows-sandbox-rung.zh.md b/.agents/notes/rejected/feature/2026-07-26-evaluate-landstrip-for-windows-sandbox-rung.zh.md deleted file mode 100644 index aac6b9772e..0000000000 --- a/.agents/notes/rejected/feature/2026-07-26-evaluate-landstrip-for-windows-sandbox-rung.zh.md +++ /dev/null @@ -1,34 +0,0 @@ -# Agent Note: 在构建 Windows 沙箱启动器之前先评估 landstrip - -Status: rejected — landstrip 未经实战检验（驳回时问世仅数天，只有一名维护者，GitHub 星标约 48 个）；关系到安全不变量的依赖必须经过广泛采用的验证，因此 win32 层级维持自研启动器的原计划 - -[English](2026-07-26-evaluate-landstrip-for-windows-sandbox-rung.md) | 中文 - -## 问题 - -[沙箱决策](../../implemented/feature/2026-07-06-sandbox.zh.md)将 `PLATFORM_CHAINS.win32` 留空，并计划用「AppContainer/受限令牌（restricted-token）家族的一个约束运行器，按 `node-addon-landlock-run` 模板从其独立仓库发布」来填充——一个估计约 1,500 行、需要自研编写并维护的新仓库（landlock-run 子树约为 1,460 行 C／TS／脚本／测试，外加文档与 CI）。 - -自那份决策记录写成以来，出现了一个持续维护的第三方运行器：`@landstrip/landstrip`（npm 包，活跃开发中，Rust 内核，附带按平台预构建的 `optionalDependencies`）覆盖 Linux 上的 Landlock + seccomp、macOS 上的 Seatbelt，以及 Windows 上的 AppContainer/受限用户，支持 JSON／YAML 策略输入和基于 trap-fd 的拒绝上报通道。它与 bwrap 一样采用 exec 包装方式，因此无需触碰 Linux/macOS 层级即可契合链的 `confine(argv)` 形态。 - -## 提案 - -当 Windows 沙箱阶段启动时，在动手编写自研 AppContainer 启动器仓库之前，先评估将 landstrip 的 Windows 后端包装为 `win32` 链运行器。评估必须回答： - -- **探测合成。** landstrip 没有 `--probe`；链所要求的功能探测约定必须从一次 trap 运行中合成出来。 -- **方言映射。** 拒绝与运行器失败两类 stderr 方言，以及失败关闭的退出码分类，都需要显式映射到链的词汇中。 -- **许可证。** 其二进制文件采用 LGPL-2.1-or-later 许可；在进入随产品发布的依赖闭包之前需要先做分发审查。 -- **源码与构建记录。** 每个自研启动器二进制都逐字节锁定到一个约 300 行、可完整评审的 C 文件的原生 CI 构建；而 landstrip 是单一维护者手中的一组 Rust 二进制文件。对*既有的 Linux 层级*而言，这笔权衡早有定论——不要替换它（见[沙箱 Agent Note](../../implemented/feature/2026-07-06-sandbox.zh.md)以及该启动器自身移除 Rust 依赖的迁移记录）。而对一个我们尚未构建的层级，在第三方维护与第二个自研原生仓库之间如何取舍，是一个真正悬而未决的问题。 - -## 曾考虑的替代方案 - -- **按原计划构建自研 AppContainer 启动器。** 若评估在许可证、源码／构建可审计性或探测契合度上不通过，这仍是默认选项；代价是要长期维护第二个原生安全启动器仓库。 -- **把 Linux Landlock 层级也换成 landstrip。** 直接否决：沙箱正确性是安全不变量，当前启动器有可审阅的 C 源码，其二进制逐字节锁定到原生 CI 构建，而且它正是出于这一原因才迁移摆脱了 Rust 依赖。 - -## 验收标准 - -- 在任何 Windows 层级实现开始之前，先有一份评估记录下探测、方言、许可证、源代码仓库、发布流程和二进制构建问题的答案，并把「采用／不采用」（go/no-go）结论加入沙箱 Agent Note 的延后阶段计划。 - -## 风险 - -- 处于安全关键位置的单一维护者供应链——这正是本提案定为一道评估门禁、而非采用决定的原因。 -- 该包尚且年轻；在 Windows 阶段启动之前其 API 与打包方式可能反复变动，届时需对照在线注册表重新核验。 diff --git a/.agents/notes/rejected/simplification/2026-07-26-dependency-swaps-rejected-by-nih-audit.i18n.yaml b/.agents/notes/rejected/simplification/2026-07-26-dependency-swaps-rejected-by-nih-audit.i18n.yaml index 3fc0ba2154..d51608534c 100644 --- a/.agents/notes/rejected/simplification/2026-07-26-dependency-swaps-rejected-by-nih-audit.i18n.yaml +++ b/.agents/notes/rejected/simplification/2026-07-26-dependency-swaps-rejected-by-nih-audit.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/rejected/simplification/2026-07-26-dependency-swaps-rejected-by-nih-audit.md -2026-07-26-dependency-swaps-rejected-by-nih-audit.md: c834142bccaeca2f7407c984767f5aa0af88bc22 -2026-07-26-dependency-swaps-rejected-by-nih-audit.zh.md: 043f87809cba0ad5bdae18eaef345d55ad3c41ec +2026-07-26-dependency-swaps-rejected-by-nih-audit.md: 14873d3296461357fe6582386f394bc1a5bd9483 +2026-07-26-dependency-swaps-rejected-by-nih-audit.zh.md: 4bdac0712972eb3cb85c8e721b39146995401385 diff --git a/.agents/notes/rejected/simplification/2026-07-26-dependency-swaps-rejected-by-nih-audit.md b/.agents/notes/rejected/simplification/2026-07-26-dependency-swaps-rejected-by-nih-audit.md index c834142bcc..14873d3296 100644 --- a/.agents/notes/rejected/simplification/2026-07-26-dependency-swaps-rejected-by-nih-audit.md +++ b/.agents/notes/rejected/simplification/2026-07-26-dependency-swaps-rejected-by-nih-audit.md @@ -67,7 +67,7 @@ Adopt the following dependency swaps. Rejected — per-item evidence below; a fu - **`syncpack`/`manypkg` for `check-workspace-constraints.ts`**: they cover ~20 lines of range alignment; the load-bearing 200+ lines (computed `files` lists, cordis peer=dev pairing, hierarchy shape) are repo policy no generic engine expresses. - **`remark-validate-links` for `verify-md-links.ts`**: the gate rides the repo's shared mdast toolchain; adopting remark-cli adds a second markdown stack to delete one small file. - **`prebuildify`/`node-gyp-build` for the landlock launcher packaging**: inapplicable — those load `.node` addons via dlopen; the launcher ships a standalone exec'd static binary, and per-platform `optionalDependencies` *is* the ecosystem convention for binaries. -- **Replacing the Landlock launcher itself with `@landstrip/landstrip`**: fails the security-invariant test — the launcher is a ~300-line reviewable C file whose binaries are byte-pinned to native CI builds and that already migrated away from a Rust dependency; a single-maintainer LGPL Rust binary set is a larger audit surface whose releases are harder to match to reviewed source. (The unbuilt Windows rung was weighed separately and also [rejected](../feature/2026-07-26-evaluate-landstrip-for-windows-sandbox-rung.md) — landstrip is not battle-tested.) +- **Replacing the Landlock launcher itself with `@landstrip/landstrip`**: fails the security-invariant test — the launcher is a ~300-line reviewable C file whose binaries are byte-pinned to native CI builds and that already migrated away from a Rust dependency; a single-maintainer LGPL Rust binary set is a larger audit surface whose releases are harder to match to reviewed source. The [Windows ACL decision](../../implemented/feature/2026-08-08-windows-acl-restricted-token-sandbox.md) records the same rejection for the shipped Windows rung. - **`hatch-nodejs-version` for Python release versioning**: roughly LOC-neutral (a custom metadata hook replaces the regex), inverts the recorded decision that the dev sentinel never determines a release version, and puts a single-maintainer build plugin in the release supply chain. - **YAML consolidation (`js-yaml` vs `yaml`)**: the repo carries both parsers, with the `!!js` tag defined four times on js-yaml (vendored include, app-boot, apps/cli, `scripts/verify-cordis-config.ts`) and twice on `yaml` (sdk-telemetry's `ScalarTag`, sdk-helper's comment-preserving Document editing). The direction is forced — js-yaml cannot replace `yaml` (sdk-helper needs the Document API) — but migrating the js-yaml sites cannot retire the library either (the vendored include pins it) and would put two parsers in charge of one dialect that must agree exactly, against the [personal-config note](../../implemented/feature/2026-07-20-dsh-cli-personal-config.md)'s deliberate load-only-copy parity. Deletable: ~20–25 lines of duplicate tag definitions and two `@types/js-yaml` entries. The consolidation moment is a future include sync, not now. diff --git a/.agents/notes/rejected/simplification/2026-07-26-dependency-swaps-rejected-by-nih-audit.zh.md b/.agents/notes/rejected/simplification/2026-07-26-dependency-swaps-rejected-by-nih-audit.zh.md index 043f87809c..4bdac07129 100644 --- a/.agents/notes/rejected/simplification/2026-07-26-dependency-swaps-rejected-by-nih-audit.zh.md +++ b/.agents/notes/rejected/simplification/2026-07-26-dependency-swaps-rejected-by-nih-audit.zh.md @@ -67,7 +67,7 @@ Status: rejected — 下列每一项替换在证据上都未达到净简化门 - **以 `syncpack`/`manypkg` 替换 `check-workspace-constraints.ts`**：它们只覆盖约 20 行的版本范围对齐；承重的 200+ 行（计算生成的 `files` 列表、cordis peer=dev 配对、层级形状）是仓库政策，没有通用引擎能表达。 - **以 `remark-validate-links` 替换 `verify-md-links.ts`**：该门禁搭载仓库共享的 mdast 工具链；采用 remark-cli 等于为删掉一个小文件而增加第二套 markdown 技术栈。 - **以 `prebuildify`/`node-gyp-build` 承担 landlock 启动器打包**：不适用——那些工具通过 dlopen 加载 `.node` addon；这个启动器交付的是独立 exec 的静态二进制，而按平台划分的 `optionalDependencies` 恰恰*就是*二进制分发的生态惯例。 -- **以 `@landstrip/landstrip` 替换 Landlock 启动器本身**：未通过安全不变式检验——启动器是一个约 300 行、可完整评审的 C 文件，其二进制逐字节锁定到原生 CI 构建，且早已从一个 Rust 依赖迁移出来；单一维护者的 LGPL Rust 二进制集合有更大的审计面，其发布更难与已审阅源码对应。（尚未构建的 Windows 层级经单独权衡后同样被[驳回](../feature/2026-07-26-evaluate-landstrip-for-windows-sandbox-rung.zh.md)——landstrip 未经实战检验。） +- **以 `@landstrip/landstrip` 替换 Landlock 启动器本身**：未通过安全不变式检验——启动器是一个约 300 行、可完整评审的 C 文件，其二进制逐字节锁定到原生 CI 构建，且早已从一个 Rust 依赖迁移出来；单一维护者的 LGPL Rust 二进制集合有更大的审计面，其发布更难与已审阅源码对应。[Windows ACL 决策](../../implemented/feature/2026-08-08-windows-acl-restricted-token-sandbox.zh.md)为已交付的 Windows 层级记录了同一否决。 - **以 `hatch-nodejs-version` 承担 Python 发布版本号**：代码行数大致持平（一个自定义 metadata 钩子换掉那个正则），却反转了「dev 哨兵值绝不决定发布版本」这条记录在案的决策，还把一个单一维护者的构建插件放进发布供应链。 - **YAML 归一（`js-yaml` 与 `yaml`）**：仓库同时携带两个解析器，`!!js` 标签在 js-yaml 上定义了四次（vendor 收录的 include、app-boot、apps/cli、`scripts/verify-cordis-config.ts`），在 `yaml` 上定义了两次（sdk-telemetry 的 `ScalarTag`、sdk-helper 的可保留注释的 Document 编辑）。方向是被迫的——js-yaml 无法取代 `yaml`（sdk-helper 需要 Document API）——但迁移 js-yaml 各调用点也退休不了这个库（vendor 收录的 include 锁定了它），还会让两个解析器共管一种必须完全一致的方言，违背[个人配置决策](../../implemented/feature/2026-07-20-dsh-cli-personal-config.zh.md)刻意的「仅加载副本」对等性。可删除的：约 20–25 行重复标签定义和两条 `@types/js-yaml` 条目。归一的时机是未来某次 include 同步，不是现在。 diff --git a/.agents/skills/dsh-doc-standards/SKILL.md b/.agents/skills/dsh-doc-standards/SKILL.md index 1ea836b8ee..c69b032d42 100644 --- a/.agents/skills/dsh-doc-standards/SKILL.md +++ b/.agents/skills/dsh-doc-standards/SKILL.md @@ -27,7 +27,7 @@ Apply the standard's authoring order to every human-facing document in scope. Do Then check constraints that make placement expensive or wrong: -- Paired docs (`pnpm run verify-translation-pairing --list`) cost a zh counterpart update and a `--write` re-record on every edit — prefer an unpaired home for content that will churn. +- Paired docs (`pnpm run verify-translation-pairing --list`) cost a zh counterpart update and a `--write` re-record on every edit — prefer an unpaired home for content that will churn. Verbatim code blocks are byte-exact across the pair: copy a corrected fence into both files instead of translating its comments independently. - Generated catalogs are never hand-edited; if the fact belongs there, change the generator's source. - Before renaming or moving any doc, grep for inbound references: `verify-md-links` catches Markdown link targets AND `#fragment` anchors onto Markdown files (heading slugs and explicit ``), and `verify-doc-refs` catches `docs/*.md` citations in TypeScript comments; anchors cited from TypeScript strings still need a manual grep when their output never reaches gate-scanned Markdown. - A move is atomic: remove from the old home, add to the new home, and fix every inbound link in the same change. diff --git a/.agents/skills/dsh-find-simplifications/SKILL.md b/.agents/skills/dsh-find-simplifications/SKILL.md index 2a10999c27..ef7f387c4e 100644 --- a/.agents/skills/dsh-find-simplifications/SKILL.md +++ b/.agents/skills/dsh-find-simplifications/SKILL.md @@ -1,6 +1,6 @@ --- name: dsh-find-simplifications -description: 'Use when working in the deepseek-harness repo to find non-obvious simplification candidates, write proposed Agent Notes or inline TODO/FIXME/XXX notes, audit or coalesce superseded Agent Notes, or fold worthwhile simplification ideas from another PR; especially for dead, duplicated, speculative, over-built, added-then-removed, or hand-rolled-where-a-dependency-exists surfaces.' +description: 'Use when working in the deepseek-harness repo to find non-obvious simplification candidates, remove redundant comments or implementation-heavy documentation, write proposed Agent Notes or inline TODO/FIXME/XXX notes, audit or coalesce superseded Agent Notes, or fold worthwhile simplification ideas from another PR; especially for dead, duplicated, speculative, over-built, added-then-removed, or hand-rolled-where-a-dependency-exists surfaces.' --- # Finding DeepSeek Harness Simplifications @@ -44,6 +44,13 @@ If subagents are unavailable, simulate the same breadth yourself. Do not let the Start with the largest production-code deltas. A broad simplification audit that stops after obvious unused symbols can miss the files where duplicated lifecycle or defensive machinery carries most of the cost. +## Simplify Prose With The Code + +Treat comments and documentation as maintained surface area. Apply [dsh-prose-standard](../dsh-prose-standard/SKILL.md) when a survey includes prose. + +- Delete comments that restate code or explain behavior owned elsewhere; keep required local contracts. +- Keep docs at their owning level; omit implementation details and rare cases unless they change a maintained contract. + ## Audit Trust And Lifecycle Boundaries For every defensive copy, freeze, validator, and callback capture, name where the value came from and who owns it next. Same-process typed service/plugin calls ordinarily borrow readonly values; parsers, config loaders, queues, model/tool JSON, durable files, workers, processes, and wire decoders own or validate their data. Tests built around hostile getters, fake typed objects, callback replacement, or mutation after a same-process handoff are evidence of a potentially speculative contract, not automatic justification for keeping it. diff --git a/.agents/skills/dsh-prose-standard/SKILL.md b/.agents/skills/dsh-prose-standard/SKILL.md index 069ba91fdd..9f9652415f 100644 --- a/.agents/skills/dsh-prose-standard/SKILL.md +++ b/.agents/skills/dsh-prose-standard/SKILL.md @@ -23,7 +23,7 @@ Always exclude `vendor/` from discovery, review, and edits, even when the reques Also exclude `.agents/notes/archived/` from prose review and edits. Archived Agent Notes are frozen snapshots; inspect an exact target only to understand a historical inbound citation, never to modernize its prose or outbound links. -Treat generated catalogs, snapshots, and fixtures as derivative. Edit the owning source or scenario first, then regenerate the artifact. When a generator extracts a summary from owner prose, make the extracted sentence complete for that surface. Bilingual pairs have no permanent owner: either language may be the authored side for an update. Follow the [lightweight routine path](../../../docs/AGENTS.md#writing-rules), update the counterpart minimally, and re-record the pair. +Treat generated catalogs, snapshots, and fixtures as derivative. Trace every consumer before editing: source JSDoc may also feed a generated model-visible catalog. Edit the owning source or scenario first, then regenerate every derivative. When a generator extracts a summary from owner prose, make the extracted sentence complete for that surface. Bilingual pairs have no permanent owner: either language may be the authored side for an update. Follow the [lightweight routine path](../../../docs/AGENTS.md#writing-rules), update the counterpart minimally, and re-record the pair. ## Preserve the complete proposition @@ -55,7 +55,7 @@ This is not a one-way shortening pass. Add or restore prose when code, types, an - **Postmortems:** retain the incident sequence, evidence, causal chain, impact, and prevention. Remove repeated persuasion or implementation detail that does not establish causality. - **Skills and agent instructions:** state behavioral guardrails and explicit scope limitations such as “guidance, not a script/checklist.” Keep the workflow concise and link its source of truth. - **Examples and configuration comments:** explain access limits, non-obvious wiring or load order, security stance, replay behavior, exceptions, and likely misuse. Do not narrate entries that the configuration already shows. -- **Prompts and visible strings:** treat wording as behavior. Inspect generated output and run behavior validation or state why no snapshot applies. +- **Prompts and visible strings:** treat wording as behavior. Update the owning runnable snapshot for model-visible text and the repository-required behavior evidence for GUI text. If the authorized scope has no owning scenario, leave the wording unchanged and report the deferral; do not silently fold it into a prose-only edit. - **Diagnostics:** name the failing subject or path, violated rule, and correction when it is non-obvious. Remove internal execution narration. Preserve searchable mechanism names and meaningful modal, temporal, or negative emphasis. Normalize decorative emphasis only. diff --git a/.agents/skills/dsh-prose-standard/references/examples.md b/.agents/skills/dsh-prose-standard/references/examples.md index c6bff65cbd..85d2b33db1 100644 --- a/.agents/skills/dsh-prose-standard/references/examples.md +++ b/.agents/skills/dsh-prose-standard/references/examples.md @@ -146,6 +146,8 @@ Keep the consequence of order, a surprising scope rule, or a security boundary. Wording that reaches a model is behavior, but duplication still drifts. Exactness belongs at the owner. +A prose-only audit may identify suspect wording but must not silently change it when no owning runnable snapshot exists. Leave it unchanged and report the deferral, or expand the authorized change to include the owner scenario and required GUI evidence. + ## Generated summaries must stand alone **Over-trimmed:** “Approval request and policy service.” The owner explains policy order and audit logging later, but the catalog exports only its first sentence. diff --git a/.agents/skills/dsh-trim-cot-leakage/SKILL.md b/.agents/skills/dsh-trim-cot-leakage/SKILL.md index 7fad4d50c2..8e7ea1714d 100644 --- a/.agents/skills/dsh-trim-cot-leakage/SKILL.md +++ b/.agents/skills/dsh-trim-cot-leakage/SKILL.md @@ -38,8 +38,8 @@ Unaided citation passes fail in both directions by deleting durable references a ## Workflow -1. Scope and exclusions per [dsh-prose-standard](../dsh-prose-standard/SKILL.md): require an explicit scope; never touch `vendor/`, `.agents/notes/archived/`, or recorded fixtures and snapshots — recorded model output and sealed history keep their original voice. -2. Audit read-only first: run the [recall batteries](references/recall-batteries.md) (with `--hidden` so `.agents/` is searched), then judge every hit semantically. The batteries are probes, not the definition — each review round of the original purge found cases the batteries missed, so also read the densest prose in scope (module JSDoc, READMEs, Agent Notes) without a pattern in hand. -3. Fix owner-first per surface: generated catalogs → fix the source JSDoc or generator template, then regenerate; type-equivalence fences → fix the source JSDoc, then re-paste both bilingual pages (`verify-type-equiv` pins them); bilingual pairs → update the counterpart and re-record per [dsh-translate-docs](../dsh-translate-docs/SKILL.md); model-visible strings → wording is behavior, so flag for a snapshot-backed change instead of silently rewording. +1. Scope and exclusions per [dsh-prose-standard](../dsh-prose-standard/SKILL.md): require an explicit scope; never touch `vendor/` or `.agents/notes/archived/`. Recorded fixtures and snapshots are derivatives, not prose targets: change the owning source or scenario and regenerate them only when an authorized behavior change requires new evidence. +2. Audit read-only first: run the [recall batteries](references/recall-batteries.md) (with `--hidden` so `.agents/` is searched), calibrating each probe against a known positive and a near-miss negative before trusting its output, then judge every hit semantically. The batteries are probes, not the definition — each review round of the original purge found cases the batteries missed, so also read the densest prose in scope (module JSDoc, READMEs, Agent Notes) without a pattern in hand. +3. Fix owner-first per surface: generated catalogs → trace every consumer, fix the source JSDoc or generator template, then regenerate all derivatives; type-equivalence fences → fix the source JSDoc, then re-paste both bilingual pages (`verify-type-equiv` pins them); bilingual prose → update the counterpart minimally and re-record it through the [lightweight routine](../../../docs/AGENTS.md#writing-rules); bilingual fences → copy the corrected verbatim block byte-for-byte into both sides per [dsh-doc-standards](../dsh-doc-standards/SKILL.md), then re-record the pair; model- or user-visible strings → route through [dsh-prose-standard](../dsh-prose-standard/SKILL.md) and change only with owning behavior evidence, otherwise leave unchanged and report the deferral. 4. Before deleting anything, enumerate the passage's propositions (prose-standard) and check the [overcorrection traps](references/examples.md#overcorrection-traps): trims that flip an obligation into an endorsement, promote a hypothetical to a shipped feature, delete a true fact, or drop provenance. 5. Verify: re-run the batteries expecting only sanctioned keeps, this skill's own directory, and the owning note's quoted evidence; confirm every remaining citation resolves at HEAD; run the gates for touched surfaces (`doc-sync` for docs, `verify-type-equiv`, `verify-translation-pairing`). diff --git a/.agents/skills/dsh-trim-cot-leakage/references/examples.md b/.agents/skills/dsh-trim-cot-leakage/references/examples.md index 9afc22c209..0d850fde15 100644 --- a/.agents/skills/dsh-trim-cot-leakage/references/examples.md +++ b/.agents/skills/dsh-trim-cot-leakage/references/examples.md @@ -176,6 +176,22 @@ Replace the hedge with the actual bound and the failure behavior when it is exce Working-language fragments and session separators are transcription residue. The Figma frame name stays: external provenance that resolves outside the repo by design. +### Authoring-language slip inside a paired fence + +**Leaked in both files:** `// 更新这里 before returning` inside a verbatim code block. + +**Fixed in both files:** `// Update this before returning.` + +Correct the block once and copy that byte-exact fence into both language files. Translating the code comment differently in the Chinese counterpart breaks the pairing contract even when both comments are individually fluent. + +## Behavior-visible candidates + +**Suspect:** An exported JSDoc sentence says "available for now," and a generator copies that sentence into a model-visible catalog. + +**Wrong:** Rewrite only the source sentence during a prose-only purge, or hand-edit only the generated catalog. + +**Right:** Trace the source's generated fan-out, update the owner, regenerate every derivative, and update the owning runnable snapshot. For a GUI string, include the repository-required behavior evidence. If the authorized scope has no owning scenario, leave the wording unchanged and report the deferral. + ## Keeps ### Issue references are durable on every surface @@ -208,6 +224,12 @@ The measurement pins the constant against uninformed retuning, and "measured" is "Old" and "new" here name two live runtime objects during handover, not repository states. The change-narration ban is about repo history, not lifecycle vocabulary. +### Runtime natural time is not a version stamp + +**Keep:** "What is today's date?" + +The prompt asks about the runtime clock; "today" does not contrast repository states. Because the text reaches a model, any rewrite still requires its owning behavior evidence. + ## Overcorrection traps Every trap below shipped in the original purge and was caught in review. Enumerate a passage's propositions before trimming it. diff --git a/.agents/skills/dsh-trim-cot-leakage/references/recall-batteries.md b/.agents/skills/dsh-trim-cot-leakage/references/recall-batteries.md index 9b1c79054c..4802413c4d 100644 --- a/.agents/skills/dsh-trim-cot-leakage/references/recall-batteries.md +++ b/.agents/skills/dsh-trim-cot-leakage/references/recall-batteries.md @@ -7,25 +7,34 @@ Probes for [the taxonomy](../SKILL.md#taxonomy), tuned during the 2026-08 purge. - Add `--hidden --glob '!.git/**'` so `.agents/` is searched; ripgrep skips dot-directories by default and the purge's biggest miss risk was Agent Notes. - Exclusions go last so a later include cannot re-admit them: `--glob '!vendor/**' --glob '!node_modules/**' --glob '!.agents/notes/archived/**' --glob '!.agents/skills/dsh-trim-cot-leakage/**'` (the skill's own files quote leaked wording as calibration), plus recorded fixture and snapshot directories in scope. The [owning note](../../../notes/implemented/process/2026-08-09-committed-artifact-citations.md) also self-hits through its quoted evidence; judge it as evidence, not usage. - Natural-language lines carry `-i` so sentence-initial capitals hit ("This PR adds…", "Probably fine…"); the first line, which matches code patterns, stays case-sensitive — `-i` would turn `\bT\d\b` and `\bP-I\b` into noise. -- A zero-hit pattern proves nothing until you have seen it match: test it against a known-positive string before trusting the negative. +- Bound complete phrases. `\bthis PR\b` must match "this PR adds" without matching "this project", "this process", or "this provider". +- A zero-hit pattern proves nothing until it matches a known positive, and a noisy pattern proves nothing until it rejects a near-miss negative. Calibrate both before trusting a corpus result. +- Target authoring-language probes at the opposite-language surface: search Chinese residue in otherwise-English Markdown and code comments/JSDoc, and search Chinese change narration within `*.zh.md`. A generic ASCII search for English residue in Chinese prose is too noisy around code and identifiers; compare the prose additions against their counterpart instead. ## English battery ```sh rg -n --hidden '\(decision \d|\(audit [A-Z]\d|design §|plan §|design ledger|\(B ruling|\bP-I\b|\bW\d\b|\bT\d\b' ... -rg -n --hidden -i 'this PR|this branch|this stack|later PR|previous commit|this commit' ... -rg -n --hidden -i 'used to |no longer|previously|the old |was renamed|was moved' ... +rg -n --hidden -i '\bthis PR\b|\bthis branch\b|\bthis stack\b|\blater PRs?\b|\bprevious commits?\b|\bthis commit\b' ... +rg -n --hidden -i '\bused to\b|\bno longer\b|\bpreviously\b|\bthe old\b|\bwas renamed\b|\bwas moved\b' ... rg -n --hidden -i '\bv1\b|this cut|\bcut \d|\btoday\b|\bfor now\b|roadmap' ... rg -n --hidden -i 'rejected in review|review round|reviewer|as of v\d' ... rg -n --hidden -i 'probably |should be enough|should suffice|it simply|is safe —|is safe --' ... rg -n --hidden '§\d' ... ``` -## Chinese battery +## Chinese batteries ```sh -rg -n --hidden '设计稿|评审|上一?轮|旧版|老的|不再|以前|本版|遗留|私有' ... -rg -n --hidden '(^|[^a-zA-Z])端([^a-zA-Z]|$)' --glob '*.md' ... +# Change or review narration in Chinese counterparts. +rg -n --hidden '评审|上一?轮|旧版|老的|不再|以前|本版|遗留' --glob '*.zh.md' ... + +# Chinese authoring-language slips in English Markdown. +rg -n --hidden '设计稿|评审|上一?轮|旧版|老的|不再|以前|本版|遗留|私有|(^|[^a-zA-Z])端([^a-zA-Z]|$)' --glob '*.md' --glob '!*.zh.md' ... + +# Chinese authoring-language slips in English code comments and JSDoc. +rg -n --hidden '(^[[:space:]]*(//|/\*|\*)|//|/\*)[^\r\n]*(设计稿|评审|上一?轮|旧版|老的|不再|以前|本版|遗留|私有|端)' --glob '*.{ts,tsx,js,jsx,mjs,cjs,css}' ... +rg -n --hidden '#[^\r\n]*(设计稿|评审|上一?轮|旧版|老的|不再|以前|本版|遗留|私有|端)' --glob '*.py' ... ``` ## Known false-positive families @@ -38,6 +47,6 @@ Judged and kept during the purge; expect them again: - **`v1` as protocol or path segment** — `/v1/chat` endpoints and wire-format names are identifiers, not version stamps. - **`§N` with a committed owner** — external standards (RFC 9110 §10.1.5) and committed docs that own their §-numbering stay citable by section. - **Contrastive "actually" and noun "wait"** — ordinary English, not hedging; no committed line probes them, so they surface only when you extend the battery with broader hedging patterns. -- **"Today" in generated timestamps and CLI output samples** — recorded output keeps its voice. +- **Runtime "today" and recorded timestamps** — prompts or tests that ask for the current date use natural time, not a repository version stamp; recorded CLI output keeps its voice. Wording that reaches a model or user still follows the behavior-evidence rule before any edit. - **本版本 in zh prose** — a legitimate rendering of "this release" in versioned-artifact contexts; the banned indexical is 本版 as a bare stamp mirroring "this cut". - **Alternatives-considered sections** — "rejected" inside an Agent Note's genre slot is the sanctioned home, not review choreography. diff --git a/.github/workflows/build-preview-cloudflare.yml b/.github/workflows/build-preview-cloudflare.yml new file mode 100644 index 0000000000..5f67b97893 --- /dev/null +++ b/.github/workflows/build-preview-cloudflare.yml @@ -0,0 +1,170 @@ +name: Build PR preview + +# Every push to a pull request publishes that pull request's preview to +# Cloudflare Pages under its own branch alias, behind Cloudflare Access. The +# upload carries build products only: the workflow never grants the deployment +# platform access to this repository's sources. + +on: + pull_request: + types: [opened, synchronize, reopened] + +# Within one pull request the newest build wins. Across pull requests there is +# nothing to serialize: each uploads to its own branch alias, so two deployments +# never contend for the same URL. +concurrency: + group: build-preview-cloudflare-${{ github.event.pull_request.number }} + cancel-in-progress: true + +permissions: + contents: read + pull-requests: write + +env: + PRIMARY_NODE_VERSION: '24' + # Cloudflare Pages project receiving the upload. Its preview deployments are + # the surface the Access application protects; the project's production branch + # is deliberately a name no deployment uses, so no unprotected URL exists. + CF_PROJECT: dsh-build-preview + # CI runs must never report to the production telemetry endpoint baked into + # apps/cli/cordis.yml (AppCLIEntry disables the row when set). + DSH_TELEMETRY_DISABLED: '1' + +jobs: + preview: + runs-on: dsh-ubuntu-24-04-16core + name: cloudflare pages preview + steps: + - uses: actions/checkout@v6 + with: + persist-credentials: false + + - uses: pnpm/action-setup@v4 + with: + dest: ${{ runner.temp }}/setup-pnpm + + - uses: actions/setup-node@v6 + with: + node-version: ${{ env.PRIMARY_NODE_VERSION }} + + - name: Configure pnpm store path + id: pnpm-store + run: | + store_root="$HOME/.local/share/pnpm/store" + echo "PNPM_CONFIG_STORE_DIR=$store_root" >> "$GITHUB_ENV" + store_path=$(PNPM_CONFIG_STORE_DIR="$store_root" pnpm store path --silent) + echo "path=$store_path" >> "$GITHUB_OUTPUT" + + # Read-only: the preview lane consumes the default-branch cache without + # putting cache upload on its own path. + - uses: actions/cache/restore@v4 + with: + path: ${{ steps.pnpm-store.outputs.path }} + key: ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-${{ hashFiles('pnpm-lock.yaml') }} + restore-keys: | + ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm- + + - name: Install (immutable) + run: pnpm install --frozen-lockfile + + # apps/web consumes workspace packages as built lib products, and + # build:preview packs the image through the packer's installed bin + # (lib/bin.js), so neither half exists before the full build runs. + - name: Build workspace + run: pnpm run build + + - name: Build the preview page and pack the VFS image + env: + DSH_CLIENT_TITLE: DSH preview pr-${{ github.event.pull_request.number }} + run: pnpm --filter @deepseek-ai/dsh-web-frontend run build:preview + + # Sourcemaps carry complete sources and stay off the deployment platform. + # index.html is the served page, which cannot boot without a host + # injecting window.__DSH_BOOT__; replacing it with the worker page makes + # the deployment root the usable entry instead of a page that never boots. + - name: Shape the upload + run: | + find apps/web/dist -name '*.map' -delete + cp apps/web/dist/preview.html apps/web/dist/index.html + + - name: Upload to Cloudflare Pages + env: + CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }} + CLOUDFLARE_ACCOUNT_ID: ${{ secrets.CLOUDFLARE_ACCOUNT_ID }} + run: | + npx --yes wrangler@4 pages deploy apps/web/dist \ + --project-name "$CF_PROJECT" \ + --branch "pr-${{ github.event.pull_request.number }}" \ + --commit-dirty=true + + # The image is what a worker boot fails on first and least visibly, so the + # run only passes once the protected URL serves it as gzip bytes. Three + # facts are asserted, each with its own failure meaning: + # 200 Access admitted the request; a 302 means the + # Access policy is missing its Service Auth rule + # for this token + # no content-encoding the platform did not claim transport + # compression, which would make the browser + # decode the body and leave the worker's + # DecompressionStream inflating a plain tar + # gzip magic 1f 8b the bytes really are the gzip member the + # packer wrote + # Accept-Encoding is sent because a browser sends it; the assertion is + # about what the platform does with a body that is already compressed. + - name: Verify the protected deployment serves the image + env: + CF_ACCESS_CLIENT_ID: ${{ secrets.CF_ACCESS_CLIENT_ID }} + CF_ACCESS_CLIENT_SECRET: ${{ secrets.CF_ACCESS_CLIENT_SECRET }} + run: | + url="https://pr-${{ github.event.pull_request.number }}.${CF_PROJECT}.pages.dev" + image="$url/preview/vfs-image.tar.gz" + code=000 + for attempt in 1 2 3 4 5; do + code=$(curl -sS -o image.bin -D headers.txt -w '%{http_code}' \ + -H 'Accept-Encoding: gzip' \ + -H "CF-Access-Client-Id: $CF_ACCESS_CLIENT_ID" \ + -H "CF-Access-Client-Secret: $CF_ACCESS_CLIENT_SECRET" \ + "$image" || echo 000) + echo "attempt $attempt: HTTP $code" + if [ "$code" = "200" ]; then break; fi + sleep 10 + done + if [ "$code" != "200" ]; then + echo "the protected image URL answered $code, not 200" + head -20 headers.txt + exit 1 + fi + if grep -qi '^content-encoding:' headers.txt; then + echo "the platform declared transport compression on an already-compressed image:" + grep -i '^content-encoding:' headers.txt + exit 1 + fi + magic=$(head -c 2 image.bin | od -An -tx1 | tr -d ' \n') + if [ "$magic" != "1f8b" ]; then + echo "image does not start with the gzip magic number: $magic" + exit 1 + fi + echo "image served as $(wc -c < image.bin) gzip bytes" + + # The alias URL follows from the pull request number, so it is stable + # across redeploys and worth stating once. The marker makes the comment + # idempotent: a pull request opened before this workflow existed never + # sees an `opened` event, and every later push must not restate the URL. + - name: Comment the preview URL + env: + GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} + PR: ${{ github.event.pull_request.number }} + run: | + marker='' + existing=$(gh pr view "$PR" --json comments \ + --jq "[.comments[] | select(.body | contains(\"$marker\")) | .url] | first // empty") + if [ -n "$existing" ]; then + echo "preview URL already commented: $existing" + exit 0 + fi + # The marker sits on its own line: markdown renders no link on a + # line that opens with a raw HTML comment. + printf '%s\n\n%s\n' \ + "$marker" \ + "[Preview for #$PR](https://pr-$PR.${CF_PROJECT}.pages.dev) (requires Cloudflare Access sign-in)" \ + | gh pr comment "$PR" --body-file - diff --git a/.oxlintrc.json b/.oxlintrc.json index 70f53fd4cd..1f11a9e989 100644 --- a/.oxlintrc.json +++ b/.oxlintrc.json @@ -57,6 +57,14 @@ } ], "no-useless-constructor": "error", + "no-restricted-properties": [ + "error", + { + "object": "crypto", + "property": "randomUUID", + "message": "browsers withhold crypto.randomUUID outside secure contexts (plain-HTTP LAN pages); mint through @deepseek-ai/dsh-util-crypto instead" + } + ], "typescript/await-thenable": "error", "typescript/ban-ts-comment": [ "error", @@ -316,6 +324,21 @@ "rules": { "@stylistic/quotes": "off" } + }, + { + "files": [ + "packages/experimental/webworker-runtime/src/node/**/*.ts", + "packages/experimental/webworker-runtime/src/storage/memory.ts", + "packages/experimental/webworker-runtime/src/module-system/module-loader.ts", + "packages/experimental/webworker-runtime/src/transport/synthetic-http.ts" + ], + "rules": { + "typescript/require-await": "off", // Async faces Node and Cordis define (fs promises, the module seam) reject rather than throw; the VFS beneath them never awaits. + "typescript/no-extraneous-class": "off" // Node constructs these (`new Script()`, `new Worker()`), so a stub that refuses must still be a class. + }, + "plugins": [ + "typescript" + ] } ] } diff --git a/AGENTS.md b/AGENTS.md index 28208b2c87..0a026bdb83 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -17,7 +17,7 @@ packages/ @deepseek-ai/dsh- workspaces at packages/// llm/ LLM capability: Service Definition/Consumer + DeepSeek providers e2b/ E2B POC: sandbox + FS/subprocess adapters shell/ bash capability: Service Definition + local/pwsh providers + shell Consumers - subprocess/ subprocess capability + local process-tree provider + subprocess/ subprocess capability + local process-tree provider + shared Win32 library terminal/ persistent sessions fs/ filesystem capability + policy lsp/ language-server capability @@ -117,7 +117,7 @@ Real-API tests and demos read `DEEPSEEK_API_KEY`, optional `DEEPSEEK_BASE_URL`, - **Source plane vs artifact plane, never mixed.** Static gates and tests resolve workspace imports through tsconfig `paths` to `src` and pass on a clean tree; gates consuming built `lib/` declare that dependency ([layout](docs/development.md#typescript-project-layout)). - **Keep compiler faces explicit.** Each package uses one aggregate except `api/remotes`; repo-wide programs seed a face config, never the root solution ([layout](docs/development.md#typescript-project-layout)). - **An empty `catch` names what it swallows** and why nothing else can reach it; keep the `try` to one statement. -- Do not comment on facts obvious from code. +- **Keep comments local.** Do not restate code, explain distant behavior unless locally required, or expand unrelated comments ([rationale](.agents/notes/implemented/process/2026-08-09-concrete-prose-names-actors-and-recorded-facts.md)). - **Prefer symmetry for parallel values**; unexplained asymmetry usually signals a missed extraction. - **Tests describe behavior, not correctness.** Change obsolete behavior with its tests; explain why in the PR. - **Non-trivial changes MUST include an Agent Note in the same PR;** only mechanical/local edits are exempt ([scope](.agents/notes/README.md#when-to-write-one)). Archived notes are frozen: never edit or treat them as current authority ([archive policy](.agents/notes/README.md#archiving-and-deletion)). diff --git a/README.i18n.yaml b/README.i18n.yaml index 1550aac8ca..4ce9085d88 100644 --- a/README.i18n.yaml +++ b/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write README.md -README.md: 9ccd27b8934449bd0d2311317dc38aee5a5c0cdc -README.zh.md: 103acdefa6bcc161e71224c8aea94a262ff96a67 +README.md: a007b230b0f766537a04c99db920271c96600d1d +README.zh.md: 63899fd3abb2333fcce8b0975c8be7f309845b33 diff --git a/README.md b/README.md index 9ccd27b893..a007b230b0 100644 --- a/README.md +++ b/README.md @@ -6,6 +6,8 @@ DeepSeek Harness (`dsh`) is an open-source agent harness developed by [DeepSeek It uses an architecture where **everything is a plugin**, and is powered by [Cordis](https://github.com/cordiverse/cordis), whose design is described in [_A Programming Paradigm for Spatiotemporal Composability_](https://github.com/cordiverse/paper). +Documentation: [https://deepseek-harness.github.io/deepseek-harness/](https://deepseek-harness.github.io/deepseek-harness/) + ## Developer preview DeepSeek Harness is currently in _developer preview_ and is iterating rapidly. **THERE WILL BE COMPATIBILITY-BREAKING CHANGES.** diff --git a/README.zh.md b/README.zh.md index 103acdefa6..63899fd3ab 100644 --- a/README.zh.md +++ b/README.zh.md @@ -6,6 +6,8 @@ DeepSeek Harness（`dsh`）是由 [DeepSeek AI](https://deepseek.com) 开发的 它采用**一切皆插件**的架构，并由 [Cordis](https://github.com/cordiverse/cordis) 驱动，其设计参见论文 [_A Programming Paradigm for Spatiotemporal Composability_](https://github.com/cordiverse/paper)。 +文档：[https://deepseek-harness.github.io/deepseek-harness/](https://deepseek-harness.github.io/deepseek-harness/) + ## 开发者预览 DeepSeek Harness 目前处于 _开发者预览_ 阶段，正在快速迭代。**未来将出现破坏兼容性的变更。** diff --git a/THIRD_PARTY_NOTICES.md b/THIRD_PARTY_NOTICES.md index 295eb1868f..bb9ad51cf1 100644 --- a/THIRD_PARTY_NOTICES.md +++ b/THIRD_PARTY_NOTICES.md @@ -39,6 +39,7 @@ External packages that a workspace package resolves at runtime. The tier covers | [`@joplin/turndown-plugin-gfm`](https://github.com/laurent22/joplin-turndown-plugin-gfm) | MIT | | [`@jridgewell/gen-mapping`](https://github.com/jridgewell/sourcemaps) | MIT | | [`@modelcontextprotocol/sdk`](https://github.com/modelcontextprotocol/typescript-sdk) | MIT | +| [`@noble/hashes`](https://github.com/paulmillr/noble-hashes) | MIT | | [`@openai/codex`](https://github.com/openai/codex) | Apache-2.0 | | [`@opentelemetry/api`](https://github.com/open-telemetry/opentelemetry-js) | Apache-2.0 | | [`@opentelemetry/api-logs`](https://github.com/open-telemetry/opentelemetry-js) | Apache-2.0 | @@ -51,7 +52,10 @@ External packages that a workspace package resolves at runtime. The tier covers | [`@tanstack/react-virtual`](https://github.com/TanStack/virtual) | MIT | | [`@types/mdast`](https://github.com/DefinitelyTyped/DefinitelyTyped) | MIT | | [`@vscode/ripgrep`](https://github.com/microsoft/vscode-ripgrep) | MIT | +| [`@yarnpkg/parsers`](https://github.com/yarnpkg/berry) | BSD-2-Clause | +| [`acorn`](https://github.com/acornjs/acorn) | MIT | | [`anser`](https://github.com/IonicaBizau/anser) | MIT | +| [`buffer`](https://github.com/feross/buffer) | MIT | | [`chokidar`](https://github.com/paulmillr/chokidar) | MIT | | [`clsx`](https://github.com/lukeed/clsx) | MIT | | [`commander`](https://github.com/tj/commander.js) | MIT | @@ -136,6 +140,7 @@ External packages **directly declared** only by repository tooling, test infrast | [`@types/react-dom`](https://github.com/DefinitelyTyped/DefinitelyTyped) | MIT | | [`@types/spdx-expression-parse`](https://github.com/DefinitelyTyped/DefinitelyTyped) | MIT | | [`@types/turndown`](https://github.com/DefinitelyTyped/DefinitelyTyped) | MIT | +| [`@types/use-sync-external-store`](https://github.com/DefinitelyTyped/DefinitelyTyped) | MIT | | [`@types/ws`](https://github.com/DefinitelyTyped/DefinitelyTyped) | MIT | | [`@vitejs/plugin-react`](https://github.com/vitejs/vite-plugin-react) | MIT | | [`@vitest/coverage-v8`](https://github.com/vitest-dev/vitest) | MIT | @@ -148,6 +153,7 @@ External packages **directly declared** only by repository tooling, test infrast | [`eslint-plugin-sonarjs`](https://github.com/SonarSource/SonarJS) | LGPL-3.0-only | | [`execa`](https://github.com/sindresorhus/execa) | MIT | | [`fast-check`](https://github.com/dubzzz/fast-check) | MIT | +| [`http-server`](https://github.com/http-party/http-server) | MIT | | [`istanbul-lib-report`](https://github.com/istanbuljs/istanbuljs) | BSD-3-Clause | | [`jscpd`](https://github.com/kucherenko/jscpd) | MIT | | [`jsdom`](https://github.com/jsdom/jsdom) | MIT | diff --git a/apps/cli/package.json b/apps/cli/package.json index fa75d3e0a8..b3cef32dea 100644 --- a/apps/cli/package.json +++ b/apps/cli/package.json @@ -1,7 +1,7 @@ { "name": "@deepseek-ai/dsh", "description": "dsh CLI: profile boot, plugin management, and the browser UI alias", - "version": "0.1.1-rc.1", + "version": "0.1.1-rc.2", "publishConfig": { "access": "public" }, @@ -18,6 +18,11 @@ "lib/*.js", "config" ], + "dsh": { + "configTrees": [ + { "mount": "config/agent-presets", "path": "config/agent-presets", "scanRoster": true } + ] + }, "license": "MIT", "dependencies": { "@deepseek-ai/cordis-plugin-hmr": "workspace:^", diff --git a/apps/cli/src/bin.ts b/apps/cli/src/bin.ts index 9aa44f8b22..321849f2d9 100644 --- a/apps/cli/src/bin.ts +++ b/apps/cli/src/bin.ts @@ -1,8 +1,6 @@ #!/usr/bin/env node /** - * dsh — command-line entry. Dynamic imports per mode keep unrelated modes out - * of each dispatch path; the adapter prints and exits for - * `--help`/`--version`/a parse error, so only a valid mode reaches the switch. + * Command-line entry for dsh. * @module @deepseek-ai/dsh/bin */ @@ -16,7 +14,6 @@ import { parseDshArgs } from './args.ts' // Both the source tree (apps/cli/src) and the bundled bin (apps/cli/lib) sit // one directory under apps/cli, so the checked-in manifest resolves with the // same relative hop from either artifact. -/** This app's version, read from its checked-in package.json. */ function readVersion(): string { const manifest = JSON.parse( readFileSync(fileURLToPath(new URL('../package.json', import.meta.url)), 'utf8'), diff --git a/apps/web/package.json b/apps/web/package.json index 3474056428..5bdfe8ebd7 100644 --- a/apps/web/package.json +++ b/apps/web/package.json @@ -1,7 +1,7 @@ { "name": "@deepseek-ai/dsh-web-frontend", "description": "Web application entry: vite build over the @deepseek-ai/dsh-client-web shell library; dist/ served by apps/cli's dsh web", - "version": "0.1.1-rc.1", + "version": "0.1.1-rc.2", "publishConfig": { "access": "public" }, @@ -17,12 +17,16 @@ }, "files": [ "dist", - "!dist/**/*.map" + "!dist/**/*.map", + "!dist/preview.html", + "!dist/preview" ], "scripts": { "build": "vite build", "dev": "vite", - "watch": "vite build --watch --no-emptyOutDir" + "watch": "vite build --watch --no-emptyOutDir", + "build:preview": "pnpm --filter @deepseek-ai/dsh-experimental-webworker-runtime exec tsdown && pnpm --filter @deepseek-ai/dsh-experimental-webworker-packer exec tsdown && vite build && dsh-pack-vfs-image --out dist/preview/vfs-image.tar.gz", + "serve:preview": "http-server dist -a 0.0.0.0 -p 4173 -c-1" }, "license": "MIT", "devDependencies": { @@ -33,16 +37,19 @@ "@deepseek-ai/dsh-client-web": "workspace:^", "@deepseek-ai/dsh-cmdline": "workspace:^", "@deepseek-ai/dsh-pwsh-local": "workspace:^", + "@deepseek-ai/dsh-experimental-webworker-packer": "workspace:^", + "@deepseek-ai/dsh-experimental-webworker-runtime": "workspace:^", "@types/node": "^22.0.0", "@types/react": "~18.3.1", "@types/react-dom": "~18.3.0", "@vitejs/plugin-react": "^4.0.0", + "http-server": "^14.1.1", + "fflate": "^0.8.2", "playwright": "^1.49.0", "react": "^18.2.0", "react-dom": "^18.2.0", "typescript": "^6.0.3", "vite": "^6.0.0", - "vitest": "^4.1.8", - "fflate": "^0.8.2" + "vitest": "^4.1.8" } } diff --git a/apps/web/src/main.ts b/apps/web/src/main.ts index 7359ce5ade..2ff361f3db 100644 --- a/apps/web/src/main.ts +++ b/apps/web/src/main.ts @@ -1,8 +1,4 @@ -/** - * Web application entry: thin bootstrap over the shell library. Everything — - * module-table seeding, the boot page, and the UI-renderer handoff — lives - * in @deepseek-ai/dsh-client-web; this file only finds the mount point. - */ +/** Browser entry for the Web client. */ import { AppWebEntry } from '@deepseek-ai/dsh-client-web' const el = document.getElementById('root') diff --git a/apps/web/src/node-module-stub.ts b/apps/web/src/node-module-stub.ts index 0a9b04ea5f..15e2c1c8da 100644 --- a/apps/web/src/node-module-stub.ts +++ b/apps/web/src/node-module-stub.ts @@ -3,10 +3,10 @@ * configured loader path and fails loud if that assumption changes. */ -/** Throwing stand-in for node:module's createRequire (never reached in the browser boot). */ +/** Fail if browser boot reaches Node's module loader. */ export const createRequire = (): never => { throw new Error('node:module is not available in the browser') } -/** Erased type peer for the vendored loader's type-only LoadHookContext import. */ +/** Type-only peer for the vendored loader. */ export type LoadHookContext = never diff --git a/apps/web/src/preview.ts b/apps/web/src/preview.ts new file mode 100644 index 0000000000..586cbcab5d --- /dev/null +++ b/apps/web/src/preview.ts @@ -0,0 +1,12 @@ +/** + * Worker-preview bootstrap: the one module preview.html adds ahead of the + * stock entry tag. Connecting the worker host installs the boot globals and + * settles `__DSH_BOOT_READY__`, where the stock entry's pre-boot await holds, + * so everything after this module is the served startup chain verbatim. A + * failed handshake rejects the deferred into the boot page's failure + * rendering; this module owns no page painting. + */ +import DshWorker from '@deepseek-ai/dsh-experimental-webworker-runtime/worker?worker' +import { connectWorkerHost, IMAGE_FILE_NAME } from '@deepseek-ai/dsh-experimental-webworker-runtime/client' + +await connectWorkerHost(new DshWorker({ name: 'dsh-host' }), { image: `preview/${IMAGE_FILE_NAME}` }) diff --git a/apps/web/src/vite-env.d.ts b/apps/web/src/vite-env.d.ts new file mode 100644 index 0000000000..11f02fe2a0 --- /dev/null +++ b/apps/web/src/vite-env.d.ts @@ -0,0 +1 @@ +/// diff --git a/apps/web/tests/approval-composer.e2e.ts b/apps/web/tests/approval-composer.e2e.ts index e57367ee46..9739c13b07 100644 --- a/apps/web/tests/approval-composer.e2e.ts +++ b/apps/web/tests/approval-composer.e2e.ts @@ -1,16 +1,5 @@ -// Web e2e scenario: the composer-takeover approval panel under a long -// command. The shipped composition confines bash through the sandbox policy -// and routes its escalation through the approval seam, so a read-only session -// asked to write a file produces a REAL pending approval — the panel renders -// in the browser, the test measures its geometry, answers through it, and the -// escalated command then runs. Replay is deterministic: the denial, the -// escalation retry and its command text arrive from replayed chunks, and the -// answer click is the test's own gesture (the same sanctioned reaction to -// model content as the question composer: the turn cannot complete without it). -// -// Geometry is the point of the scenario. The command is unbounded model text, -// and an uncapped card grows with it until the refuse/allow buttons leave the -// viewport — an approval the user could see and not answer. +// Browser geometry for a pending approval whose model-supplied command would +// push the actions outside the viewport without a capped text region. import { readFile } from 'node:fs/promises' import { fileURLToPath } from 'node:url' import { join } from 'node:path' @@ -29,17 +18,12 @@ import { connectFreshWorkspace, newEnglishPage, saveFailureShot } from './suppor const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/approval-composer', import.meta.url)) const FIXTURE = join(SNAPSHOT_DIR, 'session.jsonl') -// The scenario's one golden: the waiting panel. Everything the answered state -// proves is asserted directly — see the world-state block at the end. +// The golden covers the stable waiting panel; direct assertions cover its answer. const UI_EXPECTED = join(SNAPSHOT_DIR, 'ui.expected.md') const MODE = webSnapshotMode() -// Irreducible payload: the command has to be long enough to pass the card's -// height cap, which is the only command length that reproduces an action row pushed off -// screen. Unrelated tokens, not a repeated word — a repeated word is what the -// model compressed into `printf 'alpha %.0s' {1..400}` while recording, and a -// short command proves nothing here. The formula keeps the source small; the -// model receives the expanded literal it has to put in the command. +// Unrelated tokens keep the recorded model from compressing the payload into a +// short shell loop that would not overflow the card. const TOKENS = Array.from({ length: 220 }, (_, index) => `tok${((index + 1) * 7919 % 99991).toString(36)}`).join(' ') const PROMPT = `Write a file named notes.txt in the workspace containing exactly this text on one line: ${TOKENS}. Use one bash command with the literal text inline. Then reply with the single word DONE and stop.` @@ -77,19 +61,12 @@ describe('web e2e: approval takeover keeps its actions reachable', () => { const input = page.locator('textarea').first() await input.waitFor({ timeout: 10_000 }) - // The composer's own text cap, measured on the live draft scrollport before - // the takeover replaces it — the box that carries the cap, while the - // textarea inside it is as tall as the whole draft. The panel's scroll - // region must stop at the same height (the designer's requirement: one cap - // for the composer seat), and measuring it here keeps the assertion free of - // the px value itself. + // Derive the expected cap from the live composer instead of duplicating its pixel value. await input.fill(CAP_PROBE) const composerCap = await input.evaluate(el => el.closest('[data-input-scroll]')?.clientHeight ?? 0) expect(composerCap).toBeGreaterThan(0) await input.fill('') - // Read-only: the mode whose denial the model escalates from. Switched - // through the shipped access-mode chip, not a test-only override. await page.locator('[aria-label^="Access mode"]').click() await page.getByRole('menuitem', { name: 'Read Only' }).click() await expect.poll( @@ -101,22 +78,15 @@ describe('web e2e: approval takeover keeps its actions reachable', () => { await input.fill(PROMPT) await input.press('Enter') - // The panel takes over the input area while the tool blocks. Its presence - // is a STABLE waiting state (it stays until answered), so waitFor is - // race-free. const panel = page.locator('[data-approval-key]') await panel.waitFor({ timeout: MODE === 'record' ? 180_000 : 60_000 }) const scroll = panel.locator('[data-approval-scroll]') await expect.poll(() => scroll.getByText(/tok/).count(), { timeout: 15_000 }).toBeGreaterThan(0) if (MODE !== 'record') { - // This golden owns the stable waiting surface; the answered golden below - // owns the resulting transcript. const snapshot = await captureStableAria(page, '[data-approval-key]', scaffold.workspaceCwd) await compareOrRefreshGolden(UI_EXPECTED, snapshot, MODE) - // The uncapped-card hazard the header names, measured at the lane - // baseline and at a short viewport, on the live panel. const original = page.viewportSize() ?? { width: 1680, height: 1000 } for (const height of [1000, 700]) { await page.setViewportSize({ width: 900, height }) @@ -140,11 +110,8 @@ describe('web e2e: approval takeover keeps its actions reachable', () => { }) expect(geometry.buttons).toBe(2) expect(geometry.scrolls).toBe(true) - // One cap for the seat: the panel's text region stops where the - // composer draft does (sub-pixel tolerance for the shared padding). + // The panel and composer share one cap; allow sub-pixel layout variance. expect(Math.abs(geometry.capped - composerCap)).toBeLessThan(1) - // Both buttons stay inside the card AND inside the viewport — the - // answerable state the cap exists to guarantee. expect(geometry.actionsTop).toBeGreaterThan(0) expect(geometry.actionsBottom).toBeLessThanOrEqual(geometry.viewport) expect(geometry.actionsBottom).toBeLessThanOrEqual(geometry.cardBottom) @@ -159,12 +126,8 @@ describe('web e2e: approval takeover keeps its actions reachable', () => { await recordFixture(scaffold, sessionId, FIXTURE) return } - // World state: the granted escalation is what let the command run, and the - // panel leaves with the regular composer restored. Asserted on the world - // and the DOM rather than through a transcript golden — the denied first - // attempt renders the OS's own refusal ("Operation not permitted" on - // macOS, "Read-only file system" on Linux), so the answered transcript is - // not a platform-neutral golden surface. + // The denied attempt contains platform-specific OS text, so direct state + // and DOM assertions cover the answered outcome. expect(JSON.stringify(sessionEvents.filter(e => e.type === 'approval/decided').at(-1))) .toContain('allowed-once') const written = await readFile(join(scaffold.workspaceCwd, 'workspace', 'notes.txt'), 'utf8') diff --git a/apps/web/tests/background-job-list.e2e.ts b/apps/web/tests/background-job-list.e2e.ts index 9253edaaef..27a6c3c13a 100644 --- a/apps/web/tests/background-job-list.e2e.ts +++ b/apps/web/tests/background-job-list.e2e.ts @@ -1,8 +1,5 @@ -// Web e2e scenario: the session-header background-job list over the real -// host. No model call is involved — a genuine `run_in_background` bash call -// registers with `ctx.jobs`, and the assertion chain is the whole delivery -// path: registry change feed → api-proxy `session/jobs` frame → the client's -// `jobsBySession` mirror → the header action. +// Session-header background jobs driven by a real `ctx.jobs` entry. No model +// call is involved. import { readFile } from 'node:fs/promises' import { fileURLToPath } from 'node:url' import { join } from 'node:path' @@ -30,7 +27,7 @@ const SEED_ID = 'background-job-list-web-e2e' const COMMAND = 'sleep 45' /** - * Wait for the Host to publish the live Agent that opening a session resumes. + * Wait for opening a session to publish its live Agent. * @param scaffold - the booted web scaffold. * @param sessionId - the opened session's identity. * @returns the registered Agent instance. @@ -82,9 +79,7 @@ describe.skipIf(MODE === 'record')('web e2e: background job list', () => { it('shows a running background job in the session header without a refresh', async () => { onTestFailed(() => saveFailureShot(page, 'web-e2e-background-job-running')) - // Point assertion, not a poll: `expect.poll` retries until a predicate - // holds, so polling for zero passes at t=0 and proves nothing. The - // "renders nothing without a task" branch is owned by the component suite. + // Polling for zero would pass at t=0 before delivery and prove nothing. const trigger = page.getByRole('button', { name: '1 background job running' }) expect(await trigger.count()).toBe(0) @@ -116,8 +111,6 @@ describe.skipIf(MODE === 'record')('web e2e: background job list', () => { onTestFailed(() => saveFailureShot(page, 'web-e2e-background-job-settled')) expect(scaffold.ctx.jobs.kill(jobId, agent, 'web e2e cancellation')).toBe('requested') - // The trigger drops its live count once the task leaves running/stopping, - // which is also the proof that settlement reached the browser unprompted. const idle = page.getByRole('button', { name: '1 background job' }) await idle.waitFor({ timeout: 20_000 }) diff --git a/apps/web/tests/code-mode-round.e2e.ts b/apps/web/tests/code-mode-round.e2e.ts index 051700dc35..342f9328e0 100644 --- a/apps/web/tests/code-mode-round.e2e.ts +++ b/apps/web/tests/code-mode-round.e2e.ts @@ -1,11 +1,4 @@ -// Web e2e scenario: a Code Mode round trip. The scaffold boots the SAME -// shipped tree with the tools row patched to mode: code (the run_code-only -// wire), a real chromium sends a prompt engineered to elicit one run_code -// program with several sub-calls, and the UI must render the code-variant -// parent row with its always-visible nested sub-rows — each sub-row the same -// component a native call renders through — plus details-panel resolution for -// a clicked sub-row. Drive steps wait only on generic completion -// (whenTurnSettled); assertion steps run in replay/refresh only. +// Code Mode browser round trip with nested sub-calls and details selection. // Record: DSH_SNAPSHOT=record rewrites session.jsonl, then a keyless // DSH_SNAPSHOT=refresh regenerates ui.expected.md. import { readFile } from 'node:fs/promises' @@ -24,9 +17,7 @@ const FIXTURE = fileURLToPath(new URL('./snapshots/code-mode-round/session.jsonl const UI_EXPECTED = fileURLToPath(new URL('./snapshots/code-mode-round/ui.expected.md', import.meta.url)) const MODE = webSnapshotMode() -// The scenario's one drive prompt: elicits one program with a bash sub-call -// and a failing read the program tolerates — the sub-row set the assertions -// need. Never asserted against model prose. +// Elicits the successful and failed sub-rows this scenario asserts. const PROMPT = 'Using ONE run_code program: run bash `echo CODE_ROUND_OK`, then read the file missing.txt ' + 'catching its error in the program. Return an object with both outcomes. Then reply DONE and stop.' @@ -48,7 +39,6 @@ describe('web e2e: Code Mode round renders nested sub-calls', () => { tripwire = watchConsole(page) await page.goto(scaffold.baseUrl, { waitUntil: 'load' }) await page.waitForSelector('[class*="frame"]', { timeout: 30_000 }) - // Fresh world: connect a Workspace so the composer scenarios start live. await connectFreshWorkspace(page, scaffold.workspaceCwd) }, 120_000) @@ -60,7 +50,6 @@ describe('web e2e: Code Mode round renders nested sub-calls', () => { it('drives the recorded prompt to a settled turn (all modes)', async () => { onTestFailed(() => saveFailureShot(page, 'web-e2e-code-mode-drive')) if (MODE !== 'record') { - // Drift guard: the committed fixture must carry exactly the drive prompt. expect(fixtureUserPrompts(await readFile(FIXTURE, 'utf8'))).toEqual([PROMPT]) } const input = page.locator('textarea').first() @@ -75,11 +64,9 @@ describe('web e2e: Code Mode round renders nested sub-calls', () => { }, 200_000) it.skipIf(MODE === 'record')('the durable log carries run_code with full-content sub-dispatches', () => { - // Wire discipline: code mode collapsed the call surface to run_code. const calls = sessionEvents.filter(event => event.type === 'tool/call') expect(calls.length).toBeGreaterThanOrEqual(1) expect(new Set(calls.map(call => (call.data as { name: string }).name))).toEqual(new Set(['run_code'])) - // Sub-dispatches logged with the complete tool/result vocabulary. const dispatches = sessionEvents.filter(event => (event.type as string) === 'tool/code-dispatch') expect(dispatches.length).toBeGreaterThanOrEqual(2) for (const dispatch of dispatches) { @@ -107,14 +94,9 @@ describe('web e2e: Code Mode round renders nested sub-calls', () => { // description as its summary (the presentCall contract). const codeRow = page.locator('[data-variant="code"]').first() await codeRow.waitFor({ timeout: 10_000 }) - // Nested rows are visible WITHOUT any expand interaction, inside the - // sub-call nest, each rendered by the same components as native rows: - // the bash sub-call landed in the bash sample registration. const nest = page.locator('[data-subcalls]').first() await nest.waitFor({ timeout: 10_000 }) expect(await nest.locator('[data-sample="bash"]').count()).toBeGreaterThanOrEqual(1) - // The failing read sub-call wears the same error state a native failed - // row wears (the recorded program tolerates a read of missing.txt). expect(await nest.locator('[data-state="error"]').count()).toBeGreaterThanOrEqual(1) }, 60_000) @@ -124,7 +106,6 @@ describe('web e2e: Code Mode round renders nested sub-calls', () => { const frame = page.locator('[style*="grid-template-columns"]').first() expect(await frame.getAttribute('data-details-collapsed')).toBe('true') await nest.locator('[data-sample="bash"]').first().click() - // Tool rows do not drive layout geometry; the Session's default panel stays closed. await expect.poll(() => frame.getAttribute('data-details-collapsed'), { timeout: 5_000 }).toBe('true') }) diff --git a/apps/web/tests/composer-draft-scroll.e2e.ts b/apps/web/tests/composer-draft-scroll.e2e.ts index ae48dcddca..b8fa9a6121 100644 --- a/apps/web/tests/composer-draft-scroll.e2e.ts +++ b/apps/web/tests/composer-draft-scroll.e2e.ts @@ -1,35 +1,6 @@ -// Web e2e scenario: a composer draft longer than the 14-line cap scrolls its -// GLYPHS AND ITS CARET AS ONE. -// -// The composer paints its text in two stacked layers (see -// packages/client/ui-conversation/src/client/skeleton/InputBar.module.css): the -// `