diff --git a/.agents/notes/archived/manifest.json b/.agents/notes/archived/manifest.json index f8786470c7..2c9391bc96 100644 --- a/.agents/notes/archived/manifest.json +++ b/.agents/notes/archived/manifest.json @@ -334,6 +334,9 @@ "simplification/2026-07-02-remove-stream-chunk-mirror.i18n.yaml": "sha256:eef600eafd70a576b2ac16a74f5dd5010ee601376008a90be10f1da56d746cee", "simplification/2026-07-02-remove-stream-chunk-mirror.md": "sha256:0c22a896260c6eb8991cc8babd8172f7b6889fc41bb891d748f34650b3eee5ec", "simplification/2026-07-02-remove-stream-chunk-mirror.zh.md": "sha256:ae7a3c2450b16fdf2f8da9e1f83cd987bf387671ecc8ebb76d2e7541695e7ee1", + "simplification/2026-07-04-drop-image-content-block.i18n.yaml": "sha256:6af8bc85be1fc23b445b17ff96df69488afa82c7194fcb47beb7a6b7b5a1de6a", + "simplification/2026-07-04-drop-image-content-block.md": "sha256:31e619d09405044a4db4951084f8d12417868b8f255ca26a44af0a5a13d43e6b", + "simplification/2026-07-04-drop-image-content-block.zh.md": "sha256:8fa6558bbb014a38853796102099ffbd5d8151371d68d40b2bf262ad07f4c976", "simplification/2026-07-04-drop-inert-request-knobs.i18n.yaml": "sha256:e4c992a27ae0e37e5ef663c2cddf55eefe20387fd6103bebf655834d8e75e9db", "simplification/2026-07-04-drop-inert-request-knobs.md": "sha256:8735c2b868a85b13235e0491a0fa7b9570dd090eef5170324fc5e93782687b67", "simplification/2026-07-04-drop-inert-request-knobs.zh.md": "sha256:78b243f5d580f2a6fbbdb7d26574295d6ed74feb8d9bba34bbcdf4aa87624b5c", diff --git a/.agents/notes/implemented/simplification/2026-07-04-drop-image-content-block.i18n.yaml b/.agents/notes/archived/simplification/2026-07-04-drop-image-content-block.i18n.yaml similarity index 69% rename from .agents/notes/implemented/simplification/2026-07-04-drop-image-content-block.i18n.yaml rename to .agents/notes/archived/simplification/2026-07-04-drop-image-content-block.i18n.yaml index f51aaf86b4..f718de7c8a 100644 --- a/.agents/notes/implemented/simplification/2026-07-04-drop-image-content-block.i18n.yaml +++ b/.agents/notes/archived/simplification/2026-07-04-drop-image-content-block.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/2026-07-04-drop-image-content-block.md -2026-07-04-drop-image-content-block.md: 5d0357270973ac20234d8ce72c403f27ce2ad0e0 -2026-07-04-drop-image-content-block.zh.md: a13133059cdf4f6e6e8fe44e313a9795a57c10c9 +2026-07-04-drop-image-content-block.md: 362afbbe7c5c1a3b46b1e8abda3b0fec77d1a0e6 +2026-07-04-drop-image-content-block.zh.md: 07fbbd1f165887bf3305ccfa7ba137656ce0a99c diff --git a/.agents/notes/implemented/simplification/2026-07-04-drop-image-content-block.md b/.agents/notes/archived/simplification/2026-07-04-drop-image-content-block.md similarity index 99% rename from .agents/notes/implemented/simplification/2026-07-04-drop-image-content-block.md rename to .agents/notes/archived/simplification/2026-07-04-drop-image-content-block.md index 5d03572709..362afbbe7c 100644 --- a/.agents/notes/implemented/simplification/2026-07-04-drop-image-content-block.md +++ b/.agents/notes/archived/simplification/2026-07-04-drop-image-content-block.md @@ -1,6 +1,7 @@ # Agent Note: Drop the `image` content block until a path can honor it Status: implemented +Archived: 2026-08-19 English | [中文](2026-07-04-drop-image-content-block.zh.md) diff --git a/.agents/notes/implemented/simplification/2026-07-04-drop-image-content-block.zh.md b/.agents/notes/archived/simplification/2026-07-04-drop-image-content-block.zh.md similarity index 99% rename from .agents/notes/implemented/simplification/2026-07-04-drop-image-content-block.zh.md rename to .agents/notes/archived/simplification/2026-07-04-drop-image-content-block.zh.md index a13133059c..07fbbd1f16 100644 --- a/.agents/notes/implemented/simplification/2026-07-04-drop-image-content-block.zh.md +++ b/.agents/notes/archived/simplification/2026-07-04-drop-image-content-block.zh.md @@ -1,6 +1,7 @@ # Agent Note: 移除 `image` 内容块，直到有路径能真正处理它 Status: implemented +Archived: 2026-08-19 [English](2026-07-04-drop-image-content-block.md) | 中文 diff --git a/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.i18n.yaml index a8dd8129ce..dac9ce6b5c 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-11-content-block-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/architecture/2026-06-11-content-block-vocabulary.md -2026-06-11-content-block-vocabulary.md: 5228724bb9101307db9929aaf7831b477c2a6022 -2026-06-11-content-block-vocabulary.zh.md: 63c50ea6dfae79557cb33b9952eb581c90efdcd4 +2026-06-11-content-block-vocabulary.md: a31df6a7d16ea7cba649702fdb474dab34533c1b +2026-06-11-content-block-vocabulary.zh.md: da387b179816cda64791e71ca7affa1fbdfd195b diff --git a/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.md b/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.md index 5228724bb9..a31df6a7d1 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.md +++ b/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.md @@ -22,7 +22,7 @@ In-session context injection (`context/message`) and mid-turn steering originall ## Consequences - Reasoning has a core home without provider-specific shapes. -- Multimodal blocks return only with coordinated adapter, UI, and compaction support; see [the drop-image Agent Note](../simplification/2026-07-04-drop-image-content-block.md). +- Multimodal blocks return only with coordinated adapter, UI, and compaction support; see [the drop-image Agent Note](../../archived/simplification/2026-07-04-drop-image-content-block.md). - Cache hints and assistant prefill remain absent until a shipping adapter can honor them; see the [producer-less variants](../../archived/simplification/2026-07-04-prune-producerless-vocabulary-variants.md) and [inert request knobs](../../archived/simplification/2026-07-04-drop-inert-request-knobs.md) Agent Notes. - Every adapter pays a translation cost; the first real adapters have since validated the streaming protocol, and new adapters should continue proving their provider-specific mapping in adapter-local tests. - IDs that cross package boundaries are branded (`CallId`, the shared agent/session `SessionId`) — nominal typing at zero runtime cost. diff --git a/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.zh.md b/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.zh.md index 63c50ea6df..da387b1798 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.zh.md @@ -22,7 +22,7 @@ harness 需要一套统一的内部消息语言，供 agent loop（智能体循 ## 后果 - 推理（reasoning）在核心层有了归属，无需依赖提供方特有的结构。 -- 多模态块只有在适配器、UI 和上下文压缩（context compaction）三方协同支持后才会回归；见 [drop-image Agent Note](../simplification/2026-07-04-drop-image-content-block.zh.md)。 +- 多模态块只有在适配器、UI 和上下文压缩（context compaction）三方协同支持后才会回归；见 [drop-image Agent Note](../../archived/simplification/2026-07-04-drop-image-content-block.md)。 - 缓存提示与 assistant prefill 在有实际适配器能兑现之前保持缺席；见[无生产者的词汇变体](../../archived/simplification/2026-07-04-prune-producerless-vocabulary-variants.md)与[无端到端可用路径的请求旋钮](../../archived/simplification/2026-07-04-drop-inert-request-knobs.md) Agent Note。 - 每个适配器都需承担翻译成本；首批真实适配器已验证了流式输出协议，新适配器应继续在适配器本地测试中验证其提供方特有的映射。 - 跨包边界的 ID 使用品牌类型（`CallId`、agent 与会话共享的 `SessionId`）——零运行时开销的名义类型。 diff --git a/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.i18n.yaml index fbc5a3371b..8097b8cbb0 100644 --- a/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.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/2026-06-18-shared-persistence-write-coordinator.md -2026-06-18-shared-persistence-write-coordinator.md: 93b6cd1bd058499e71948d3909de8e4c076b445e -2026-06-18-shared-persistence-write-coordinator.zh.md: 3a2f73b76b14e81b021a97660c79fac479fc70a4 +2026-06-18-shared-persistence-write-coordinator.md: 286bbb7d5cd3720109db0d0abc0bb72ddbfcbdcd +2026-06-18-shared-persistence-write-coordinator.zh.md: 70db616b0a71826c648072228fff936ad423ad8f diff --git a/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md b/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md index 93b6cd1bd0..286bbb7d5c 100644 --- a/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md +++ b/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md @@ -16,6 +16,10 @@ Composition, not inheritance. The coordinator is a concrete class the backend ho The coordinator holds one lifecycle entry for each exact live `Session`: initialization plus a package-private write controller that owns pending events, a fixed batching deadline, the active write, failure retention, and the shared flush barrier. Each `session/event` enters that bounded write path, and `session/flush` bypasses the wait to observe quiescence. The [flush-controller simplification](../simplification/2026-07-23-collapse-persistence-flush-state.md) owns controller consolidation; the [bounded batching decision](2026-08-08-bounded-session-persistence-write-batching.md) owns scheduling cadence. +Creation borrows the exact `Session.events` snapshot as its persistence seed. `Session` has already detached, validated, and deeply frozen every event, and the snapshot array remains stable when later appends replace the cached view. The coordinator and its backend hooks only read this typed in-process value, so cloning the complete log again would duplicate the ownership work described by the [agent-scope runtime decision](2026-07-12-agent-scope-runtime-design.md#session-append-materialize-validate-commit-notify). Public persistence `append()` still snapshots caller-owned input at its API boundary. + +Prepared-session suffixes and events admitted to the write-behind queue retain their existing copies. Those paths establish asynchronous queue ownership one suffix or event at a time and have no measured whole-log clone cost; removing their copies remains a separate ownership audit rather than part of creation-seed borrowing. + The coordinator retires a session from `session/disposed`: it waits for the controller's initialization and current flush, serializes a final drain, and removes the controller and owned per-id state only after success. A failure leaves the controller discoverable for backend teardown to retry. Settled per-id chain tails remove themselves only when they are still current, so a completion cannot erase a newer operation for the same id. Backend teardown unregisters write-path listeners, flushes every remaining controller, awaits per-id operations, and then closes the backend. ### The hook interface (`PersistenceBackend`) diff --git a/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.zh.md b/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.zh.md index 3a2f73b76b..70db616b0a 100644 --- a/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.zh.md @@ -16,6 +16,10 @@ Status: implemented 协调器为每个存活的 `Session` 实例持有一个生命周期条目：初始化，加上一个包私有写入控制器，后者负责待处理事件、固定批处理截止时间、活跃写入、失败保留和共享 flush 屏障。每个 `session/event` 都进入这条有界写入路径，`session/flush` 则绕过等待以观察完全停稳。控制器归并由 [flush 控制器简化](../simplification/2026-07-23-collapse-persistence-flush-state.zh.md)定义；调度节奏由[有界批处理决策](2026-08-08-bounded-session-persistence-write-batching.zh.md)定义。 +创建流程将 `Session.events` 的原始快照借作持久化种子。`Session` 已经分离、验证并深度冻结每个事件，后续追加会替换缓存视图，因此该快照数组保持稳定。协调器及其后端钩子只读取这个有类型的进程内值；再次克隆完整日志会重复 [agent scope 运行时决策](2026-07-12-agent-scope-runtime-design.zh.md#session-append-materialize-validate-commit-notify)规定的所有权工作。持久化服务的公开 `append()` 仍在 API 边界为调用方拥有的输入创建快照。 + +已准备 Session 的后缀，以及进入 write-behind 队列的事件，仍保留现有复制。这些路径会逐个后缀或事件建立异步队列所有权，且没有已测得的完整日志克隆成本；移除这些复制属于单独的所有权审计，不属于创建种子的借用决策。 + 协调器通过 `session/disposed` 退役会话：它等待控制器完成初始化和当前 flush，串行执行最后一次排空，且仅在成功后才移除控制器与其拥有的每 id 状态。失败时保持控制器可被找到，以供后端 teardown（拆除）重试。每个 id 的已结算链尾仅在其仍是当前链尾时才移除自身，因此旧操作完成后不会抹除同一 id 的新操作。后端 teardown 会注销写入路径监听器、flush 每个剩余的控制器、等待所有按 id 串行化的操作，最后关闭后端。 ### 钩子接口（`PersistenceBackend`） diff --git a/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.i18n.yaml index 5167819d72..373b1293ce 100644 --- a/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.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/2026-07-07-tool-call-timeout-policy.md -2026-07-07-tool-call-timeout-policy.md: ce414e541f8e374dd48e46d68cb00121e0004247 -2026-07-07-tool-call-timeout-policy.zh.md: 6b1975981b0311cf0ea02ee9667720c414bb7b43 +2026-07-07-tool-call-timeout-policy.md: 92618cc8c761b38d7e516c9d00eb3de1c37831a8 +2026-07-07-tool-call-timeout-policy.zh.md: 0303fadd134c6eb8c41449823b62f1458f4523ba diff --git a/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.md b/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.md index ce414e541f..92618cc8c7 100644 --- a/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.md +++ b/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.md @@ -77,7 +77,7 @@ No new session event is needed for reconstructability: `TOOL_TIMEOUT` is the fin ### Existing tool adaptation -`web_fetch` and `web_search` are migrated. `dsh-tool-web` keeps ownership of their model-facing schemas, and those schemas expose no timeout knob: `web_fetch` dropped its `timeout_ms` parameter to match the reference-agent shape, and `web_search` stays query-only. The tool bodies do not import `@deepseek-ai/dsh-timeout`; they forward `exec.signal` to `ctx.web`. +`web_fetch` and `web_search` are migrated. `dsh-tool-web` keeps ownership of their model-facing schemas, and those schemas expose no timeout knob: `web_fetch` has no `timeout_ms` parameter, while `web_search` accepts a required `queries` array without a timeout argument. The tool bodies do not import `@deepseek-ai/dsh-timeout`; they forward `exec.signal` to `ctx.web`. `dsh-web-fetch-http` keeps one configured provider-level `timeoutMs` as a large resource backstop for direct `ctx.web.fetch()` callers and misconfigured deployments; it owns no model-facing timeout. When a `TOOL_TIMEOUT` signal reaches the fetch provider first, provider-scoped classification treats it as upstream `WEB_ABORTED`, and the outer `tools/execute` wrapper replaces the final tool result with `TOOL_TIMEOUT`. A shipped web-tool deployment configures the provider backstop above the `timeout-policy` budget so the tool-call policy normally wins for model calls. diff --git a/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.zh.md b/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.zh.md index 6b1975981b..0303fadd13 100644 --- a/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.zh.md @@ -77,7 +77,7 @@ function toolTimeoutResult(timeoutMs: number): ToolExecutionResult { ### 现有工具适配 -`web_fetch` 和 `web_search` 已迁移。`dsh-tool-web` 保留对其面向模型 schema 的所有权，这些 schema 不暴露超时旋钮：`web_fetch` 移除了 `timeout_ms` 参数以匹配参考 agent（智能体）的形状，`web_search` 保持仅查询。工具体不导入 `@deepseek-ai/dsh-timeout`；它们将 `exec.signal` 转发给 `ctx.web`。 +`web_fetch` 和 `web_search` 已迁移。`dsh-tool-web` 保留对其面向模型 schema 的所有权，这些 schema 不暴露超时旋钮：`web_fetch` 没有 `timeout_ms` 参数，`web_search` 接受必填的 `queries` 数组，但不接受超时参数。工具体不导入 `@deepseek-ai/dsh-timeout`；它们将 `exec.signal` 转发给 `ctx.web`。 `dsh-web-fetch-http` 保留一个在提供方层面配置的 `timeoutMs`，作为较大的资源兜底值，服务于直接调用 `ctx.web.fetch()` 的调用方和配置错误的部署；它不拥有面向模型的超时。当 `TOOL_TIMEOUT` 信号先到达 fetch 提供方时，提供方作用域的分类将其视为上游 `WEB_ABORTED`，而外层 `tools/execute` 包装器将最终工具结果替换为 `TOOL_TIMEOUT`。一个已发布的 web 工具部署将提供方兜底配置为高于 `timeout-policy` 预算，使工具调用策略在模型调用中通常胜出。 diff --git a/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.i18n.yaml index a58ce97eff..b8bcc4246e 100644 --- a/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.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/2026-07-10-single-file-executable-sdk-runtime-distribution.md -2026-07-10-single-file-executable-sdk-runtime-distribution.md: fa2f86893b730aa1ba020bd568d268ec8d9d6239 -2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md: 4778a2b83ad12fc4155399440e387dde86e3bfc4 +2026-07-10-single-file-executable-sdk-runtime-distribution.md: 40433d99e5d1aa569c3fdf094a280d3de62ad588 +2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md: cff72ae10eb82c65c499123cc559cc6ad7e440ab diff --git a/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md index fa2f86893b..40433d99e5 100644 --- a/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md +++ b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md @@ -36,19 +36,21 @@ Config discovery has two channels and fails loudly when both are missing: the `D Inside the exe's VFS sits a **real package tree in build-artifact form** (each package's `lib/` plus a real `node_modules`). The packaged JSON-RPC entry supplies its installed harness base to app-boot's root Include: relative plugin specifiers resolve from the external configuration directory, while bare package names resolve from the VFS, so a configuration inside another Node project cannot shadow the packaged plugin set. The ordinary development bin leaves bare packages configuration-owned. Bare specifiers in the packaged entry resolve upward along `node_modules` from the entry's position inside the VFS and land inside the VFS naturally. The closed set needs no allowlist code — the set is whatever the VFS has installed, and importing a name outside the set fails. -The deploy root is [`python/sdk-runtime/package.json`](../../../../python/sdk-runtime/package.json) (`dsh-jsonrpc-agent-pkg`, a pnpm workspace member and a zero-code pure dependency manifest) — the unified source of truth for "which plugins the exe ships" and "what the Python runtime distributes". Adding a plugin to the exe = adding one dependency line to the manifest and repackaging. [`scripts/verify-runtime-closure.ts`](../../../../scripts/verify-runtime-closure.ts) traverses every workspace package covered by that manifest and requires every non-optional workspace peer at the runtime root, reporting the complete referencing-package → missing-peer chain; `pnpm run hygiene`, CI static, and the single-exe build run it before packaging. Deploy also packs by each package's `files`, so the shared chunks tsdown splits out must be covered by `files`. +The deploy root is [`python/sdk-runtime/package.json`](../../../../python/sdk-runtime/package.json) (`dsh-jsonrpc-agent-pkg`, a pnpm workspace member and a zero-code pure dependency manifest) — the unified source of truth for "which plugins the exe ships" and "what the Python runtime distributes". Adding a plugin to the exe = adding one dependency line to the manifest and repackaging. [`scripts/verify-runtime-closure.ts`](../../../../scripts/verify-runtime-closure.ts) reads every shipped `apps/cli/config/agent-presets/*/agent.cordis.yml`, evaluates `disabled` conditions that compare `process.platform` for every target in `python/sdk-runtime/platforms.json`, and requires each active workspace plugin at the runtime root through an explicit `workspace:` dependency. It also traverses every workspace package covered by that manifest and requires every non-optional workspace peer, reporting the complete preset or referencing-package → missing-dependency chain; unknown platform conditions remain active so a plugin cannot be omitted by an unsupported expression. `pnpm run hygiene`, CI static, and the single-exe build run it before packaging. Deploy also packs by each package's `files`, so the shared chunks tsdown splits out must be covered by `files`. + +The deploy root includes `@deepseek-ai/dsh-mcp-client` as an explicitly supported custom-configuration plugin even though no shipped preset mounts it. An external config can therefore connect to user-supplied stdio and Streamable HTTP MCP servers and register their tools; the distribution does not carry those servers or extend the bridge to MCP Resources and Prompts. The executable and installed-wheel smokes start a temporary stdio server, discover its tool, and complete one model-requested call. ### Build pipeline and artifacts -[`scripts/build-exe-for-python-sdk.ts`](../../../../scripts/build-exe-for-python-sdk.ts): runtime closure verification → `pnpm run build` → (after clearing) `pnpm --filter dsh-jsonrpc-agent-pkg deploy --legacy --prod --config.node-linker=hoisted --config.auto-install-peers=false --config.link-workspace-packages=true` **directly into** `python/sdk-runtime/src/deepseek_harness_runtime/runtime/node/` → restore any direct workspace package that legacy deploy hoisted back under the source manifest's `node_modules`, omitting its package-local dependency tree and rejecting any remaining manifest gap → replace every staged dependency symlink with its target bytes, remove package-manager `.bin` links, and fail if any symlink remains → inject the pkg configuration (`bin` points at `node_modules/@deepseek-ai/dsh-sdk-jsonrpc-demo/lib/packaged-bin.js` inside the closure, `assets` is a full glob — dynamic import is invisible to pkg's static analysis, so everything must be packed in explicitly) → stage the target `node-pty` addon → one `pkg --sea` per target → the executables `dsh-jsonrpc-agent-pkg--` land in `dist-exe/` and are copied back into the runtime directory. Linux installs build `pty.node` from source; CI rebuilds that addon inside the matching manylinux 2.28 container before packaging, and the builder copies it from the root install into the staged closure because legacy deploy omits that side-effect directory. macOS uses its target prebuild and emits the required `-spawn-helper` beside the executable. CI treats these products as intermediate test inputs and retains their platform wheels. All four deploy flags are grounded in measurement: `--legacy` is the mandatory path with inject-workspace-packages off; hoisted gives pkg a stable single-instance layout that the explicit materialization pass makes symlink-free; disabling automatic peer installation prevents undeclared peers from expanding the closure; link-workspace-packages selects direct workspace dependencies. [`pnpm-workspace.yaml`](../../../../pnpm-workspace.yaml) overrides the transitive `@deepseek-ai/cosmokit` and `@deepseek-ai/schemastery` semver requests to the pinned vendor sources so legacy deploy never resolves those unpublished names from a registry. +[`scripts/build-exe-for-python-sdk.ts`](../../../../scripts/build-exe-for-python-sdk.ts): runtime closure verification → `pnpm run build` → (after clearing) `pnpm --filter dsh-jsonrpc-agent-pkg deploy --legacy --prod --config.node-linker=hoisted --config.auto-install-peers=false --config.link-workspace-packages=true` **directly into** `python/sdk-runtime/src/deepseek_harness_runtime/runtime/node/` → restore any direct workspace package that legacy deploy hoisted back under the source manifest's `node_modules`, omitting its package-local dependency tree and rejecting any remaining manifest gap → replace every staged dependency symlink with its target bytes, remove package-manager `.bin` links, and fail if any symlink remains → inject the pkg configuration (`bin` points at `node_modules/@deepseek-ai/dsh-sdk-jsonrpc-demo/lib/packaged-bin.js` inside the closure, `assets` is a full glob — dynamic import is invisible to pkg's static analysis, so everything must be packed in explicitly) → stage the target `node-pty` addon → one `pkg --sea` per target → the executables `dsh-jsonrpc-agent-pkg--` land in `dist-exe/` and are copied back into the runtime directory. Linux installs build `pty.node` from source; CI rebuilds that addon inside the matching manylinux 2.28 container before packaging, and the builder copies it from the root install into the staged closure because legacy deploy omits that side-effect directory. Every target copies its native `@vscode/ripgrep` binary beside the executable as the required `-rg` sidecar; pkg runtimes select that sidecar through `process.pkg`, while ordinary Node execution uses `@vscode/ripgrep` directly. macOS uses its target prebuild and also emits the required `-spawn-helper`. CI treats these products as intermediate test inputs and retains their platform wheels. All four deploy flags are grounded in measurement: `--legacy` is the mandatory path with inject-workspace-packages off; hoisted gives pkg a stable single-instance layout that the explicit materialization pass makes symlink-free; disabling automatic peer installation prevents undeclared peers from expanding the closure; link-workspace-packages selects direct workspace dependencies. [`pnpm-workspace.yaml`](../../../../pnpm-workspace.yaml) overrides the transitive `@deepseek-ai/cosmokit` and `@deepseek-ai/schemastery` semver requests to the pinned vendor sources so legacy deploy never resolves those unpublished names from a registry. CI: [`.github/workflows/build-exe-for-python-sdk.yml`](../../../../.github/workflows/build-exe-for-python-sdk.yml), called for linux-x64 by the [required Python runtime pull-request validation](../testing/2026-08-12-required-python-runtime-pull-request-ci.md), triggered explicitly by `workflow_dispatch` or the `build-exe` label for selected targets, and called for all targets by the [public publication workflow](../process/2026-08-11-python-publication-workflow.md). Native builds run on linux-x64 / linux-arm64 (`ubuntu-24.04-arm`) / macos-arm64, with `~/.pkg-cache` cached, and pkg handles macOS ad-hoc signing. Each leg drives a mock SSE model through the SDK with the default config and a custom `cordis.yml`, drives the exe directly over NDJSON JSON-RPC, verifies the JSONL and final response, and installs release-shaped wheels into a clean venv without `runtime_bin`; Linux additionally inspects both the executable and native addon's GLIBC requirements and runs in a manylinux 2.28 container, while macOS verifies that the executable's deployment target fits the wheel tag. A full three-target run retains four artifacts, each containing one release file: the platform-independent SDK wheel and three native runtime wheels; a subset dispatch retains the SDK wheel and selected runtime wheels. Bare executables and source bundles remain intermediate test inputs. [`.gitlab-ci.yml`](../../../../.gitlab-ci.yml) accepts `python-v` tag pipelines whose version matches the root `package.json`, builds one SDK wheel and three native runtime wheels, then a single serialized job checks and publishes all four to the project PyPI registry. Windows is a non-goal. ### Python SDK distribution: two carriers, exe for production, node for development -The Python SDK lives at [`python/`](../../../../python/README.md): `python/sdk` (the client) + `python/sdk-runtime` (the runtime carrier package). The runtime package's data directory holds the checked-in default `runtime/cordis.yml`, the build-injected platform exe and optional helper, and the build-injected `runtime/node/` closure tree. `resolve_bundled_launch_args()` automatic resolution **finds the exe only**; the node carrier is enabled only by an explicit `DSH_RUNTIME_MODE=node` (running `runtime/node/node_modules/@deepseek-ai/dsh-sdk-jsonrpc-demo/lib/packaged-bin.js`, requiring a system node ≥22.19), positioned as the development-verification channel for members of this repo, and does not enter wheel distributions. +The Python SDK lives at [`python/`](../../../../python/README.md): `python/sdk` (the client) + `python/sdk-runtime` (the runtime carrier package). The runtime package's data directory holds the checked-in default `runtime/cordis.yml`, the build-injected platform exe with its required `-rg` sidecar and optional macOS helper, and the build-injected `runtime/node/` closure tree. `resolve_bundled_launch_args()` automatic resolution **finds the exe only**; the node carrier is enabled only by an explicit `DSH_RUNTIME_MODE=node` (running `runtime/node/node_modules/@deepseek-ai/dsh-sdk-jsonrpc-demo/lib/packaged-bin.js`, requiring a system node ≥22.19), positioned as the development-verification channel for members of this repo, and does not enter wheel distributions. -[`scripts/build-python-release.py`](../../../../scripts/build-python-release.py) reads the authoritative `X.Y.Z` or prerelease version from the repository root `package.json`, converts prereleases to their PEP 440 spelling, and stages both packages at that wheel version, with `deepseek-harness-sdk` depending exactly on the matching `deepseek-harness-runtime-bin`. An optional `python-v` release tag is a consistency assertion and is rejected when it differs from the repository version; the source `pyproject.toml` development sentinel never determines a release version. Staging also carries the repository license into both wheels and the third-party notices into the bundled runtime wheel. The SDK is a `py3-none-any` wheel; each wheel-only runtime package contains one exe, and the macOS wheel also contains its architecture-matched helper. Runtime wheels use one of `py3-none-manylinux_2_28_x86_64`, `py3-none-manylinux_2_28_aarch64`, or the conservative `py3-none-macosx_14_0_arm64` tag for the Node 24 executable's macOS 13.5 deployment target; the Hatch hook rejects sdists, universal tags, mixed-platform payloads, missing or extra helpers, and unsupported platforms. +[`scripts/build-python-release.py`](../../../../scripts/build-python-release.py) reads the authoritative `X.Y.Z` or prerelease version from the repository root `package.json`, converts prereleases to their PEP 440 spelling, and stages both packages at that wheel version, with `deepseek-harness-sdk` depending exactly on the matching `deepseek-harness-runtime-bin`. An optional `python-v` release tag is a consistency assertion and is rejected when it differs from the repository version; the source `pyproject.toml` development sentinel never determines a release version. Staging also carries the repository license into both wheels and the third-party notices into the bundled runtime wheel. The SDK is a `py3-none-any` wheel; each wheel-only runtime package contains one exe and its architecture-matched `-rg` sidecar, and the macOS wheel also contains its architecture-matched spawn helper. Runtime wheels use one of `py3-none-manylinux_2_28_x86_64`, `py3-none-manylinux_2_28_aarch64`, or the conservative `py3-none-macosx_14_0_arm64` tag for the Node 24 executable's macOS 13.5 deployment target; the Hatch hook rejects sdists, universal tags, mixed-platform payloads, missing or extra sidecars, and unsupported platforms. The exe's "must be explicitly configured" hard semantic is unchanged; the zero-config experience is restored by the wrapper: when the caller gave no `cordis`, named no explicit runtime, and the environment has no `DSH_CORDIS_CONFIG`, the client explicitly injects the checked-in default `cordis.yml` (agent-core + preloaded llm-deepseek + JSONL persistence + bash-local + the `dsh-sdk-jsonrpc-server` serving entry, with `!!js` environment-variable fallbacks) via `DSH_CORDIS_CONFIG`. @@ -62,7 +64,7 @@ The exe's "must be explicitly configured" hard semantic is unchanged; the zero-c ## Testing -The verification surface has three tiers. Mechanism tier: the measured conclusions for the `--sea` chain are embedded in the Decision sections (ESM dynamic import inside the VFS, single cordis instance, fail-loud config chain, `node:sqlite`, macOS ad-hoc signing runs). SDK tier: the complete keyless pytest suite covers the client protocol against a fake runtime peer, subprocess cleanup, absolute cwd propagation, dual-carrier launch, and carrier resolution; root CI runs it on Python 3.10. End-to-end tier: every platform build completes a turn against a mock endpoint through the default SDK path, a custom config, the checked-in standalone minimal composition, and the direct binary protocol, with final text and JSONL checked. The minimal run asserts its exact system prompt and two-tool catalog, retains Bash state across calls, and invokes the editor. The custom config additionally drives `run_code` and a zero-agent `workflow` through their real worker files inside the packaged VFS. The same build leg runs a committed executable-specific snapshot through the Python SDK: a keyless scripted model mounts a Cordis plugin that registers a tool, invokes that tool from `run_code`, runs a direct spawn subagent and a workflow that starts a second spawn child, then unmounts the plugin. The fixture explicitly disables its unused bundled Bash and local skill discovery so its tool set does not depend on repository-external state, and the comparison normalizes opaque message, agent, workflow-run, and session IDs across the SDK result and notification stream plus the parent and two child JSONL logs. This harness stays separate from ACP's `pnpm run test:snapshot` because the protocols and build artifacts differ. The platform wheel is then installed in a clean venv and run without `runtime_bin`. +The verification surface has three tiers. Mechanism tier: the measured conclusions for the `--sea` chain are embedded in the Decision sections (ESM dynamic import inside the VFS, single cordis instance, fail-loud config chain, `node:sqlite`, macOS ad-hoc signing runs). SDK tier: the complete keyless pytest suite covers the client protocol against a fake runtime peer, subprocess cleanup, absolute cwd propagation, dual-carrier launch, and carrier resolution; root CI runs it on Python 3.10. End-to-end tier: every platform build completes a turn against a mock endpoint through the default SDK path, a custom config, the checked-in standalone minimal composition, and the direct binary protocol, with final text and JSONL checked. The minimal run asserts its exact system prompt and two-tool catalog, retains Bash state across calls, and invokes the editor. The custom config additionally drives `run_code` and a zero-agent `workflow` through their real worker files inside the packaged VFS. The filesystem-search scenario requires the model to call both `glob` and `grep` through the target-native `-rg` sidecar. The MCP scenario starts a temporary external stdio server, deliberately delays its initial `tools/list` response, then immediately starts the first SDK prompt; the prompt must see and call the discovered tool, proving that `initialize` is a real Loader-settlement readiness boundary rather than a timing sleep. The same build leg runs a committed executable-specific snapshot through the Python SDK: a keyless scripted model mounts a Cordis plugin that registers a tool, invokes that tool from `run_code`, runs a direct spawn subagent and a workflow that starts a second spawn child, then unmounts the plugin. The fixture explicitly disables its unused bundled Bash and local skill discovery so its tool set does not depend on repository-external state, and the comparison normalizes opaque message, agent, workflow-run, and session IDs across the SDK result and notification stream plus the parent and two child JSONL logs. This harness stays separate from ACP's `pnpm run test:snapshot` because the protocols and build artifacts differ. The platform wheel is then installed in a clean venv and run without `runtime_bin`. Manual-driving caveat: the bin treats stdin EOF as "the client is gone" and disposes immediately, so a short-lived pipe aborts an in-flight turn — pipe-driven runs must keep stdin open until the turn ends. diff --git a/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md index 4778a2b83a..cff72ae10e 100644 --- a/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md @@ -36,19 +36,21 @@ exe 使用 [@yao-pkg/pkg](https://github.com/yao-pkg/pkg)（vercel/pkg 归档后 exe 的 VFS 内是**构建产物形态的真实包树**（各包的 `lib/` + 真实 `node_modules`）。打包专用 JSON-RPC 入口会向 app-boot 的根 Include 提供自身已安装 harness 的基准位置：相对插件说明符从外部配置目录解析，裸包名则从 VFS 解析，因此位于另一个 Node 项目内的配置无法遮蔽已打包的插件集合。普通开发 bin 仍由配置项目提供裸包。打包入口中的裸包名从该入口在 VFS 内的位置沿 `node_modules` 向上解析，自然落在 VFS 内。封闭集不需要白名单代码——VFS 中安装了什么，集合中就有什么；`import()` 集合外的名称会失败。 -部署根目录是 [`python/sdk-runtime/package.json`](../../../../python/sdk-runtime/package.json)（`dsh-jsonrpc-agent-pkg`，pnpm 工作区成员、零代码纯依赖 manifest），也是「exe 安装哪些插件」与「Python 运行时分发什么」的统一真源。向 exe 添加插件，就是在 manifest 中增加一行依赖后重新打包。[`scripts/verify-runtime-closure.ts`](../../../../scripts/verify-runtime-closure.ts) 遍历该 manifest 覆盖的全部工作区包，要求每个非可选的工作区对等依赖（peer dependency）都显式列在运行时根目录，并报告“引用包 → 缺失对等依赖”的完整链路；`pnpm run hygiene`、CI 静态检查与 single-exe 构建都会在打包前运行该门禁。部署还会依据各包的 `files` 字段打包，因此 tsdown 拆出的共享分片必须被 `files` 覆盖。 +部署根目录是 [`python/sdk-runtime/package.json`](../../../../python/sdk-runtime/package.json)（`dsh-jsonrpc-agent-pkg`，pnpm 工作区成员、零代码纯依赖 manifest），也是「exe 安装哪些插件」与「Python 运行时分发什么」的统一真源。向 exe 添加插件，就是在 manifest 中增加一行依赖后重新打包。[`scripts/verify-runtime-closure.ts`](../../../../scripts/verify-runtime-closure.ts) 读取每个已发布的 `apps/cli/config/agent-presets/*/agent.cordis.yml`，针对 `python/sdk-runtime/platforms.json` 中的每个目标解析比较 `process.platform` 的 `disabled` 条件，并要求该目标启用的每个工作区插件都通过显式的 `workspace:` 依赖列在运行时根目录。它还遍历该 manifest 覆盖的全部工作区包，要求每个非可选的工作区对等依赖（peer dependency）都显式列出，并报告“preset 或引用包 → 缺失依赖”的完整链路；无法识别的平台条件会保持启用，避免因不支持的表达式遗漏插件。`pnpm run hygiene`、CI 静态检查与 single-exe 构建都会在打包前运行该门禁。部署还会依据各包的 `files` 字段打包，因此 tsdown 拆出的共享分片必须被 `files` 覆盖。 + +部署根目录显式包含 `@deepseek-ai/dsh-mcp-client`，将其作为自定义配置可用的插件，即使随附 preset 均未挂载该插件。外部配置因此可以连接由用户提供的 stdio 与 Streamable HTTP MCP server 并注册其工具；分发物不包含这些 server，也不将桥接范围扩展到 MCP Resources 和 Prompts。可执行程序与已安装 wheel 包的冒烟测试会启动临时 stdio server，发现其工具，并完成一次由模型请求的调用。 ### 构建流水线与产物 -[`scripts/build-exe-for-python-sdk.ts`](../../../../scripts/build-exe-for-python-sdk.ts)：运行时闭包校验 → `pnpm run build` →（清空后）`pnpm --filter dsh-jsonrpc-agent-pkg deploy --legacy --prod --config.node-linker=hoisted --config.auto-install-peers=false --config.link-workspace-packages=true` **直接写入** `python/sdk-runtime/src/deepseek_harness_runtime/runtime/node/` → 恢复被 legacy deploy 提升回源 manifest 的 `node_modules` 下的任何直接工作区包，同时省略其包内依赖树，并拒绝剩余的 manifest 缺口 → 将暂存依赖中的每个符号链接替换为目标文件内容，删除包管理器的 `.bin` 链接，并在仍有任何符号链接时失败 → 注入 pkg 配置（`bin` 指向闭包内的 `node_modules/@deepseek-ai/dsh-sdk-jsonrpc-demo/lib/packaged-bin.js`；`assets` 使用全量 glob，因为动态 `import()` 对 pkg 静态分析不可见，必须显式打入全部内容）→ 暂存目标平台的 `node-pty` addon → 每个构建目标调用一次 `pkg --sea` → 可执行文件 `dsh-jsonrpc-agent-pkg--` 写入 `dist-exe/`，并拷回运行时目录。Linux 安装会从源码构建 `pty.node`；CI 会在打包前进入匹配架构的 manylinux 2.28 容器重新构建该 addon，而 `--legacy` 部署会省略这一副作用目录，因此构建器会把它从根安装目录复制到暂存闭包。macOS 使用对应目标的预构建产物，并在可执行文件旁生成所需的 `-spawn-helper`。CI 将这些产物作为测试中间输入，只保留对应平台的 wheel 包。四个部署标志都有实测依据：未启用 `inject-workspace-packages` 时必须使用 `--legacy`；`hoisted` 为 pkg 提供稳定的单实例布局，再由显式物化步骤消除符号链接；关闭对等依赖自动安装可防止未声明的对等依赖扩大闭包；`link-workspace-packages` 选择直接工作区依赖。[`pnpm-workspace.yaml`](../../../../pnpm-workspace.yaml) 将传递的 `@deepseek-ai/cosmokit` 与 `@deepseek-ai/schemastery` semver 请求覆盖到固定的 vendor 源码，使 legacy deploy 不会从注册表解析这些未发布名称。 +[`scripts/build-exe-for-python-sdk.ts`](../../../../scripts/build-exe-for-python-sdk.ts)：运行时闭包校验 → `pnpm run build` →（清空后）`pnpm --filter dsh-jsonrpc-agent-pkg deploy --legacy --prod --config.node-linker=hoisted --config.auto-install-peers=false --config.link-workspace-packages=true` **直接写入** `python/sdk-runtime/src/deepseek_harness_runtime/runtime/node/` → 恢复被 legacy deploy 提升回源 manifest 的 `node_modules` 下的任何直接工作区包，同时省略其包内依赖树，并拒绝剩余的 manifest 缺口 → 将暂存依赖中的每个符号链接替换为目标文件内容，删除包管理器的 `.bin` 链接，并在仍有任何符号链接时失败 → 注入 pkg 配置（`bin` 指向闭包内的 `node_modules/@deepseek-ai/dsh-sdk-jsonrpc-demo/lib/packaged-bin.js`；`assets` 使用全量 glob，因为动态 `import()` 对 pkg 静态分析不可见，必须显式打入全部内容）→ 暂存目标平台的 `node-pty` addon → 每个构建目标调用一次 `pkg --sea` → 可执行文件 `dsh-jsonrpc-agent-pkg--` 写入 `dist-exe/`，并拷回运行时目录。Linux 安装会从源码构建 `pty.node`；CI 会在打包前进入匹配架构的 manylinux 2.28 容器重新构建该 addon，而 `--legacy` 部署会省略这一副作用目录，因此构建器会把它从根安装目录复制到暂存闭包。每个目标都会把对应的原生 `@vscode/ripgrep` 二进制复制到可执行文件旁，作为必需的 `-rg` 伴随文件；pkg 运行时通过 `process.pkg` 选择该伴随文件，普通 Node 执行则直接使用 `@vscode/ripgrep`。macOS 使用对应目标的预构建产物，并额外生成所需的 `-spawn-helper`。CI 将这些产物作为测试中间输入，只保留对应平台的 wheel 包。四个部署标志都有实测依据：未启用 `inject-workspace-packages` 时必须使用 `--legacy`；`hoisted` 为 pkg 提供稳定的单实例布局，再由显式物化步骤消除符号链接；关闭对等依赖自动安装可防止未声明的对等依赖扩大闭包；`link-workspace-packages` 选择直接工作区依赖。[`pnpm-workspace.yaml`](../../../../pnpm-workspace.yaml) 将传递的 `@deepseek-ai/cosmokit` 与 `@deepseek-ai/schemastery` semver 请求覆盖到固定的 vendor 源码，使 legacy deploy 不会从注册表解析这些未发布名称。 CI 使用 [`.github/workflows/build-exe-for-python-sdk.yml`](../../../../.github/workflows/build-exe-for-python-sdk.yml)：[必需的 Python 运行时拉取请求验证](../testing/2026-08-12-required-python-runtime-pull-request-ci.zh.md)调用它构建 linux-x64，手动派发 `workflow_dispatch` 或 PR（Pull Request）的 `build-exe` 标签可以显式选择构建目标，[公开发布工作流](../process/2026-08-11-python-publication-workflow.zh.md)则调用它构建全部目标。linux-x64、linux-arm64（`ubuntu-24.04-arm`）和 macos-arm64 三个平台分别进行原生构建，并缓存 `~/.pkg-cache`；macOS 的 ad-hoc 签名由 pkg 处理。每个平台都使用 mock SSE（Server-Sent Events）模型，分别通过默认配置和自定义 `cordis.yml` 驱动 SDK，再通过 NDJSON JSON-RPC 直接驱动 exe，校验 JSONL 与最终响应；最后把发布形态的 wheel 包安装到干净的 venv 中，并在不传 `runtime_bin` 的情况下运行。Linux 还会检查可执行文件和原生 addon 各自的 GLIBC 依赖，并在 manylinux 2.28 容器中运行；macOS 则验证可执行文件的部署目标符合 wheel 包标签。完整构建三个目标时保留 4 个产物，每个产物只含一个发布文件：平台无关的 SDK wheel 包与 3 个原生运行时 wheel 包；手动选择部分目标时保留 SDK wheel 与所选运行时 wheel。裸 exe 与源码包只作为测试中间输入。[`.gitlab-ci.yml`](../../../../.gitlab-ci.yml) 只接受版本与根目录 `package.json` 匹配的 `python-v` 标签流水线，构建一个 SDK wheel 包和 3 个原生运行时 wheel 包，再由单个串行任务校验并将这 4 个文件发布到项目的 PyPI 注册表。Windows 不在目标范围内。 ### Python SDK 分发：双载体，exe 用于生产，`node` 用于开发 -Python SDK 位于 [`python/`](../../../../python/README.zh.md)：`python/sdk` 是客户端，`python/sdk-runtime` 是运行时载体包。运行时包的数据目录包含检入的默认 `runtime/cordis.yml`、构建注入的平台 exe 与可选 helper，以及构建注入的 `runtime/node/` 闭包树。`resolve_bundled_launch_args()` 的自动解析**只查找 exe**；`node` 载体仅在显式设置 `DSH_RUNTIME_MODE=node` 时启用（运行 `runtime/node/node_modules/@deepseek-ai/dsh-sdk-jsonrpc-demo/lib/packaged-bin.js`，需要系统 Node ≥22.19），定位为本仓库成员的开发验证通道，不随 wheel 包分发。 +Python SDK 位于 [`python/`](../../../../python/README.zh.md)：`python/sdk` 是客户端，`python/sdk-runtime` 是运行时载体包。运行时包的数据目录包含检入的默认 `runtime/cordis.yml`、构建注入的平台 exe 及其必需的 `-rg` 伴随文件和可选的 macOS helper，以及构建注入的 `runtime/node/` 闭包树。`resolve_bundled_launch_args()` 的自动解析**只查找 exe**；`node` 载体仅在显式设置 `DSH_RUNTIME_MODE=node` 时启用（运行 `runtime/node/node_modules/@deepseek-ai/dsh-sdk-jsonrpc-demo/lib/packaged-bin.js`，需要系统 Node ≥22.19），定位为本仓库成员的开发验证通道，不随 wheel 包分发。 -[`scripts/build-python-release.py`](../../../../scripts/build-python-release.py) 从仓库根目录的 `package.json` 读取权威的 `X.Y.Z` 或预发布版本，把预发布版本转换为 PEP 440 写法，并以该 wheel 包版本暂存两个包，让 `deepseek-harness-sdk` 精确依赖匹配版本的 `deepseek-harness-runtime-bin`。可选的 `python-v` 发布标签只是一项一致性断言，与仓库版本不同时会被拒绝；源码 `pyproject.toml` 中的开发占位版本从不决定发布版本。暂存过程还会把仓库许可证放入两个 wheel 包，并把第三方声明放入内置运行时 wheel 包。SDK 是 `py3-none-any` wheel 包；每个只提供 wheel 包的运行时包都包含一个 exe，macOS wheel 包还包含与其架构匹配的 helper。运行时 wheel 包使用 `py3-none-manylinux_2_28_x86_64`、`py3-none-manylinux_2_28_aarch64`，或针对 Node 24 可执行文件 macOS 13.5 部署目标而保守选择的 `py3-none-macosx_14_0_arm64` 标签；Hatch 钩子拒绝 sdist、通用标签、混合平台载荷、helper 缺失或多余，以及不支持的平台。 +[`scripts/build-python-release.py`](../../../../scripts/build-python-release.py) 从仓库根目录的 `package.json` 读取权威的 `X.Y.Z` 或预发布版本，把预发布版本转换为 PEP 440 写法，并以该 wheel 包版本暂存两个包，让 `deepseek-harness-sdk` 精确依赖匹配版本的 `deepseek-harness-runtime-bin`。可选的 `python-v` 发布标签只是一项一致性断言，与仓库版本不同时会被拒绝；源码 `pyproject.toml` 中的开发占位版本从不决定发布版本。暂存过程还会把仓库许可证放入两个 wheel 包，并把第三方声明放入内置运行时 wheel 包。SDK 是 `py3-none-any` wheel 包；每个只提供 wheel 包的运行时包都包含一个 exe 及其架构匹配的 `-rg` 伴随文件，macOS wheel 包还包含与其架构匹配的 spawn helper。运行时 wheel 包使用 `py3-none-manylinux_2_28_x86_64`、`py3-none-manylinux_2_28_aarch64`，或针对 Node 24 可执行文件 macOS 13.5 部署目标而保守选择的 `py3-none-macosx_14_0_arm64` 标签；Hatch 钩子拒绝 sdist、通用标签、混合平台载荷、伴随文件缺失或多余，以及不支持的平台。 exe「必须显式配置」的硬语义不变；零配置体验由包装层恢复：调用方没有提供 `cordis`、没有显式指定运行时，且环境中没有 `DSH_CORDIS_CONFIG` 时，客户端将检入的默认 `cordis.yml`（`agent-core` + 预载的 `llm-deepseek` + JSONL 持久化 + `bash-local` + `dsh-sdk-jsonrpc-server` 对外服务条目，并通过 `!!js` 使用环境变量兜底）显式注入 `DSH_CORDIS_CONFIG`。 @@ -62,7 +64,7 @@ exe 内支持 `dsh-workflow-worker-thread` 与 `dsh-code-runtime-worker-thread` ## 测试 -验证面分三层。机制层：`--sea` 链路的实测结论内嵌在「决策」各节（VFS 内 ESM 动态 `import()`、单一 Cordis 实例、明确报错的配置链路、`node:sqlite`、macOS ad-hoc 签名可运行）。SDK 层：完整的无密钥 pytest 套件以 mock 运行时对端覆盖客户端协议、子进程清理、绝对 `cwd` 传递、双载体启动与载体解析；根 CI 在 Python 3.10 上运行全部用例。端到端层：每个平台构建都通过默认 SDK 路径、自定义配置、仓库内置的独立 minimal 组合和直接二进制协议，对 mock 端点完成一个轮次，并校验最终文本与 JSONL。minimal 运行会断言其精确系统提示词与双工具目录，跨调用保留 Bash 状态，并调用编辑器。自定义配置还会通过打包进 VFS 的真实工作线程文件执行 `run_code` 和不启动 agent 的 `workflow`。同一构建任务还会经 Python SDK 运行一组检入的 exe 专用快照：无密钥脚本化模型挂载一个会注册工具的 Cordis 插件，从 `run_code` 调用该工具，运行一个直接 spawn 的 subagent 和一个会通过 spawn 启动第二个 subagent 的工作流，随后卸载该插件。该 fixture（测试前置数据）会显式禁用组合包中未使用的 Bash 和本地 skill（技能）发现，使其工具集不依赖仓库外部状态；比较时会规范化 SDK 结果与通知流，以及父会话和两个子会话 JSONL 日志中不透明的消息、agent、工作流运行与会话 ID。该 harness 与 ACP 的 `pnpm run test:snapshot` 保持独立，因为二者的协议和构建产物不同。随后把平台 wheel 包安装进干净的 venv，并在不传 `runtime_bin` 的情况下运行。 +验证面分三层。机制层：`--sea` 链路的实测结论内嵌在「决策」各节（VFS 内 ESM 动态 `import()`、单一 Cordis 实例、明确报错的配置链路、`node:sqlite`、macOS ad-hoc 签名可运行）。SDK 层：完整的无密钥 pytest 套件以 mock 运行时对端覆盖客户端协议、子进程清理、绝对 `cwd` 传递、双载体启动与载体解析；根 CI 在 Python 3.10 上运行全部用例。端到端层：每个平台构建都通过默认 SDK 路径、自定义配置、仓库内置的独立 minimal 组合和直接二进制协议，对 mock 端点完成一个轮次，并校验最终文本与 JSONL。minimal 运行会断言其精确系统提示词与双工具目录，跨调用保留 Bash 状态，并调用编辑器。自定义配置还会通过打包进 VFS 的真实工作线程文件执行 `run_code` 和不启动 agent 的 `workflow`。文件系统搜索场景要求模型通过目标平台的 `-rg` 伴随文件调用 `glob` 与 `grep`。MCP 场景会启动临时外部 stdio server，刻意延迟首次 `tools/list` 响应，随后立即启动第一个 SDK 提示词；该提示词必须看到并调用已发现的工具，从而证明 `initialize` 是真正以 Loader 插件树完全稳定为准的就绪边界，而不是依赖定时 sleep。同一构建任务还会经 Python SDK 运行一组检入的 exe 专用快照：无密钥脚本化模型挂载一个会注册工具的 Cordis 插件，从 `run_code` 调用该工具，运行一个直接 spawn 的 subagent 和一个会通过 spawn 启动第二个 subagent 的工作流，随后卸载该插件。该 fixture（测试前置数据）会显式禁用组合包中未使用的 Bash 和本地 skill（技能）发现，使其工具集不依赖仓库外部状态；比较时会规范化 SDK 结果与通知流，以及父会话和两个子会话 JSONL 日志中不透明的消息、agent、工作流运行与会话 ID。该 harness 与 ACP 的 `pnpm run test:snapshot` 保持独立，因为二者的协议和构建产物不同。随后把平台 wheel 包安装进干净的 venv，并在不传 `runtime_bin` 的情况下运行。 手工驱动注意：`bin` 将 stdin EOF 视为「客户端已离开」并立即 dispose，生命周期较短的管道会中止进行中的轮次——管道驱动必须保持 stdin 打开，直到轮次结束。 diff --git a/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.i18n.yaml index 28bdb324ac..7d8d2db1cf 100644 --- a/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.i18n.yaml @@ -3,4 +3,4 @@ # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md 2026-07-12-agent-scope-runtime-design.md: 9d70b8048b1d2bb50290d34158d9deb329d5e15e -2026-07-12-agent-scope-runtime-design.zh.md: 6ed883741b31d80bfe4392278dc2a0dda167f711 +2026-07-12-agent-scope-runtime-design.zh.md: 278bcede47fee9f67d3d2d2d7135e5357c120161 diff --git a/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.zh.md b/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.zh.md index 6ed883741b..278bcede47 100644 --- a/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.zh.md @@ -160,6 +160,8 @@ sequenceDiagram 此顺序让最终的 agent 和会话事件能使用匹配的作用域监听器，并使持久化观察者在最终刷新完成前保持附加。作用域 dispose 放在最后，因为注册撤销是外部可见的生命期边界。 + + ## 会话追加：物化、验证、提交、通知 会话事件跨越持久化边界，因此追加操作拥有其数据。算法的其余部分使用一条已附加的注册表条目和一个提交点。 diff --git a/.agents/notes/implemented/architecture/2026-07-24-web-config-tree-boot-and-transport-layering.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-24-web-config-tree-boot-and-transport-layering.i18n.yaml index 4f5d19800d..84409bdd5d 100644 --- a/.agents/notes/implemented/architecture/2026-07-24-web-config-tree-boot-and-transport-layering.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-24-web-config-tree-boot-and-transport-layering.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/2026-07-24-web-config-tree-boot-and-transport-layering.md -2026-07-24-web-config-tree-boot-and-transport-layering.md: f397ca6a25cffa0ba709d0a8e84717a1c228b951 -2026-07-24-web-config-tree-boot-and-transport-layering.zh.md: 87b0f4323850650b9b0e737ffbf6276fdbae42ed +2026-07-24-web-config-tree-boot-and-transport-layering.md: eb30ba84ef293a169931ef6519a9d6d2ea98af7f +2026-07-24-web-config-tree-boot-and-transport-layering.zh.md: a3e310a4a5ab8bc6a40ad8d0336cb94e29c1744f diff --git a/.agents/notes/implemented/architecture/2026-07-24-web-config-tree-boot-and-transport-layering.md b/.agents/notes/implemented/architecture/2026-07-24-web-config-tree-boot-and-transport-layering.md index f397ca6a25..eb30ba84ef 100644 --- a/.agents/notes/implemented/architecture/2026-07-24-web-config-tree-boot-and-transport-layering.md +++ b/.agents/notes/implemented/architecture/2026-07-24-web-config-tree-boot-and-transport-layering.md @@ -18,7 +18,7 @@ English | [中文](2026-07-24-web-config-tree-boot-and-transport-layering.zh.md) **Config sources have one declaration place each.** Bundle yml values are engineering defaults, Settings sections are writable user preferences, CLI flags address their owning launcher rows, and env values enter through yml `!!js` expressions. Patches replace a row's config wholesale. The resolved frontend `distIndex` uses that patch channel as an assembly fact. The transport-independent provider/model default belongs to `ctx.agentDefaultModel`; the [direct headless entry point](2026-08-09-headless-direct-core-entry-point.md) and the Web gateway consume the same state. -**The transport splits five ways.** `dsh-host-apiproxy` is the gateway plugin (`api-gateway` row): it default-exports `ApiProxyService`, configures only `{nativeOpen?}`, consumes the base layer's entry-point-neutral `ctx.agentDefaultModel`, provides `ctx.apiProxy`, remains transport-agnostic, and registers no routes. `dsh-host-webserver` is a plain route-registration plugin: `WebServer` provides `ctx.webServer` (`register(route) → disposer` with duplicate-pattern throw, `tapIndex` transforms applied in registration order, `port`), listens on activation, answers per-request failures with 400 and logging, and knows no harness concepts. The connection node half owns the `/api` binding from `ctx.apiProxy` through `toFetchHandler`. The modules node half (`ClientModuleRegistry`, providing `ctx.clientModules`) owns incremental package scanning, the bundle route, the index tap, and `onRebuilt`/`onGraphChanged` notification. The hmr node half owns dev reload through `fs.watchFile` membership and the `/plugins/events` SSE route. +**The transport splits five ways.** `dsh-host-apiproxy` is the gateway plugin (`api-gateway` row): it default-exports `ApiProxyService`, configures only `{nativeOpen?}`, consumes the base layer's entry-point-neutral `ctx.agentDefaultModel`, provides `ctx.apiProxy`, remains transport-agnostic, and registers no routes. `dsh-host-webserver` is a plain route-registration plugin: `WebServer` provides `ctx.webServer` (`register(route) → disposer` with duplicate-pattern throw, `renderIndex` rendering — structured `webserver/index-inject` rows, then raw `tapIndex` transforms in registration order — and `port`), listens on activation, answers per-request failures with 400 and logging, and knows no harness concepts. The connection node half owns the `/api` binding from `ctx.apiProxy` through `toFetchHandler`. The modules node half (`ClientModuleRegistry`, providing `ctx.clientModules`) owns incremental package scanning, the bundle route, the boot injection rows, and `onRebuilt`/`onGraphChanged` notification. The hmr node half owns dev reload through `fs.watchFile` membership and the `/plugins/events` SSE route. **Package export discipline.** The modules package exposes exactly `.` (node half) and `./client` (the complete browser half: `ClientModuleSystem`, `parseBootManifest`, the adoption plugin face) — no bespoke subpaths; wire types re-export through the root for host-side consumers. The adoption handshake: the kernel writes the constructed instance to `window.__DSH_MODULES__` before cordis exists; the `./client` apply reads the slot (missing = loud throw) and provides `ctx.modules`. diff --git a/.agents/notes/implemented/architecture/2026-07-24-web-config-tree-boot-and-transport-layering.zh.md b/.agents/notes/implemented/architecture/2026-07-24-web-config-tree-boot-and-transport-layering.zh.md index 87b0f43238..a3e310a4a5 100644 --- a/.agents/notes/implemented/architecture/2026-07-24-web-config-tree-boot-and-transport-layering.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-24-web-config-tree-boot-and-transport-layering.zh.md @@ -18,7 +18,7 @@ Status: implemented **每个配置源有唯一声明位置。** 组合包 yml 值是工程默认，Settings 分节是可写的用户偏好，CLI（命令行界面）flags 面向其归属的启动器配置行，env 值则通过 yml `!!js` 表达式进入。patch 会整体替换一行的 config。解析后的前端 `distIndex` 通过同一条 patch 通道作为组装事实传递。与传输无关的提供方／模型默认值归 `ctx.agentDefaultModel` 所有；[直接 headless 入口](2026-08-09-headless-direct-core-entry-point.zh.md)与 Web 网关消费同一份状态。 -**传输五分。** `dsh-host-apiproxy` 是网关插件（`api-gateway` 行）：默认导出 `ApiProxyService`，只配置 `{nativeOpen?}`，消费 base 层不偏向特定入口的 `ctx.agentDefaultModel`，provide `ctx.apiProxy`，保持传输无关且不注册路由。`dsh-host-webserver` 是朴素的路由注册插件：`WebServer` provide `ctx.webServer`（`register(route) → disposer`、重复 pattern 即抛、`tapIndex` 按注册序应用、`port`），激活即 listen，单请求失败时答 400 并记日志，且不认识任何 harness 概念。connection node 半拥有从 `ctx.apiProxy` 经 `toFetchHandler` 绑定到 `/api` 的逻辑。modules node 半（`ClientModuleRegistry`，provide `ctx.clientModules`）拥有单包增量扫描、bundle 路由、index tap 与 `onRebuilt`/`onGraphChanged` 通知。HMR（热模块替换） node 半通过 `fs.watchFile` membership 与 `/plugins/events` SSE 路由拥有开发期重载。 +**传输五分。** `dsh-host-apiproxy` 是网关插件（`api-gateway` 行）：默认导出 `ApiProxyService`，只配置 `{nativeOpen?}`，消费 base 层不偏向特定入口的 `ctx.agentDefaultModel`，provide `ctx.apiProxy`，保持传输无关且不注册路由。`dsh-host-webserver` 是朴素的路由注册插件：`WebServer` provide `ctx.webServer`（`register(route) → disposer`、重复 pattern 即抛、`renderIndex` 渲染——先结构化 `webserver/index-inject` 行、后原始 `tapIndex` 按注册序应用——与 `port`），激活即 listen，单请求失败时答 400 并记日志，且不认识任何 harness 概念。connection node 半拥有从 `ctx.apiProxy` 经 `toFetchHandler` 绑定到 `/api` 的逻辑。modules node 半（`ClientModuleRegistry`，provide `ctx.clientModules`）拥有单包增量扫描、bundle 路由、启动注入行与 `onRebuilt`/`onGraphChanged` 通知。HMR（热模块替换） node 半通过 `fs.watchFile` membership 与 `/plugins/events` SSE 路由拥有开发期重载。 **包出口纪律。** modules 包只暴露 `.`（node 半）与 `./client`（完整浏览器半：`ClientModuleSystem`、`parseBootManifest`、收编插件面）——不设专用子路径；wire 类型经根出口 re-export 给 host 侧消费方。收编握手：内核在 cordis 之前把建好的实例写入 `window.__DSH_MODULES__`；`./client` 的 apply 读取该槽位（缺少时显式抛错）并 provide `ctx.modules`。 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 2c09126baa..82e5a70c63 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: 69ddfdcf3cd6c15218c672d43cc5aadfd48a0223 -2026-07-30-credential-boundaries-and-atomic-registration.zh.md: dcac06c9deefc19fdbf021e45e3ca1469cee3eca +2026-07-30-credential-boundaries-and-atomic-registration.md: 95c16ef2bf3d82d7b8b53e3975ece3f0c63402f3 +2026-07-30-credential-boundaries-and-atomic-registration.zh.md: d09f24c3bd93934432f543e77bb8d92595b458ad 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 69ddfdcf3c..95c16ef2bf 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 @@ -8,7 +8,7 @@ English | [中文](2026-07-30-credential-boundaries-and-atomic-registration.zh.m ## Problem -The credential path leaked across boundaries it had drawn. The shipped surfaces hoisted `$DSH_HOME/.env` into `process.env` before cordis booted, so on the next run `credentials-local` classified every key it had stored itself as a read-only ambient launch override: `describe()` reported `source: 'env'` with `writable: false`, `set`/`unset` rejected as shadowed, and a key stored from the web page or TUI became unrotatable and undeletable while the adapter kept using the value captured at launch. The store's own write path repeated the settings-file defects the settings write-path note fixes (two independent chains, whole-file render from a stale cache), plus editor bugs of its own: a physical line inside another key's quoted multi-line value read as an assignment, CRLF endings degraded to LF, a multi-line entry reported `writable: true` while `set` always threw, and `credentials/updated` was emitted bare after the commit, so one broken observer made a durable write look failed. On the read side, the file's `0600` mode stops other OS users but not the model, whose bash and filesystem tools run as the same user. +The credential path leaked across boundaries it had drawn. The shipped surfaces hoisted `$DSH_HOME/.env` into `process.env` before cordis booted, so on the next run `credentials-local` classified every key it had stored itself as a read-only ambient launch override: `describe()` reported `source: 'env'` with `writable: false`, `set`/`unset` rejected as shadowed, and a key stored from the web page or TUI became unrotatable and undeletable while the adapter kept using the value captured at launch. The store's own write path repeated the settings-file defects the settings write-path note fixes (two independent chains, whole-file render from a stale cache), plus editor bugs of its own: a physical line inside another key's quoted multi-line value read as an assignment, CRLF endings degraded to LF, a multi-line entry reported `writable: true` while `set` always threw, and `credentials/reference-updated` was emitted bare after the commit, so one broken observer made a durable write look failed. On the read side, the file's `0600` mode stops other OS users but not the model, whose bash and filesystem tools run as the same user. Two request-path defects sat beside them. DeepSeek resolved connection and credential facts independently, so a settings generation the resolver rejected could still pair its credential choice with the previous generation's endpoint. pi-ai handed the SDK `undefined` when a configured `apiKeyEnv` resolved to nothing, letting pi-ai's own environment discovery authenticate with an unrelated provider key — another tenant, silently billed. And its route swap disposed the old registration before creating the new one: a route another adapter owned dropped every existing route, after which the facts cache could equal the registry's, so restoring the working configuration never re-applied. @@ -22,7 +22,7 @@ Two request-path defects sat beside them. DeepSeek resolved connection and crede **Route replacement is a registry operation, not a caller sequence.** `registerAdapter` returns a handle carrying `replace(providers)`: the candidate set is validated in full first (conflicts, names, provider metadata), then swapped in one synchronous section. A refused replacement leaves the previous routes registered and serving, and the caller's facts cache only advances after the registry actually holds the new set, so reverting to a working configuration re-applies. pi-ai's registration facts are sorted by provider, so a settings document that merely reorders its keys is no longer a route change. -**Contained publication for committed credential writes.** `CredentialProvider.notifyUpdated` fans `credentials/updated` out one listener at a time; sync throws and async rejections are logged without changing the committed operation's outcome, and `INVARIANT`-coded failures rethrow after every listener ran — the same shape the settings seam uses for `settings/updated`. `installSettingsSection`'s cleanup now distinguishes its two triggers: a provider detaching still falls back to the composition entry and re-derives, while the consumer's own unload returns immediately instead of re-registering routes during teardown. +**Contained publication for committed credential writes.** `CredentialProvider.notifyUpdated` fans `credentials/reference-updated` out one listener at a time; sync throws and async rejections are logged without changing the committed operation's outcome, and `INVARIANT`-coded failures rethrow after every listener ran — the same shape the settings seam uses for `settings/updated`. `installSettingsSection`'s cleanup now distinguishes its two triggers: a provider detaching still falls back to the composition entry and re-derives, while the consumer's own unload returns immediately instead of re-registering routes during teardown. ## Alternatives considered 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 dcac06c9de..d09f24c3bd 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 @@ -10,7 +10,7 @@ Status: implemented 凭据路径越过它自己划下的边界发生了泄漏。已交付的各个面在 Cordis 启动之前就把 `$DSH_HOME/.env` 提升进了 `process.env`，于是下一次运行时，`credentials-local` 会把它自己存下的每个键都判成来自环境的只读启动覆盖：`describe()` 报告 `source: 'env'` 且 `writable: false`，`set`/`unset` 以被遮蔽为由拒绝，从 web 页面或 TUI 存入的密钥既无法轮换也无法删除，而适配器还在继续使用启动时捕获的那个值。 -存储自身的写路径重演了 settings 写路径 note 在 settings-file 修掉的那些缺陷（两条相互独立的链、从陈旧缓存渲染整份文件），还叠加了编辑器自己的缺陷：另一个键的带引号多行值内部的一条物理行会被读成赋值，CRLF 行尾会退化成 LF，多行条目报告 `writable: true` 而 `set` 总是抛错，`credentials/updated` 又在提交之后裸发，于是一个出错的观察者就能让一次已经落盘的写入看起来失败。 +存储自身的写路径重演了 settings 写路径 note 在 settings-file 修掉的那些缺陷（两条相互独立的链、从陈旧缓存渲染整份文件），还叠加了编辑器自己的缺陷：另一个键的带引号多行值内部的一条物理行会被读成赋值，CRLF 行尾会退化成 LF，多行条目报告 `writable: true` 而 `set` 总是抛错，`credentials/reference-updated` 又在提交之后裸发，于是一个出错的观察者就能让一次已经落盘的写入看起来失败。 在读取一侧，文件的 `0600` 权限挡得住其他 OS 用户，却挡不住模型：它的 bash 与文件系统工具就以同一个用户身份运行。 @@ -26,7 +26,7 @@ Status: implemented **路由替换是注册表的操作，不是调用方的一串步骤。**`registerAdapter` 返回一个携带 `replace(providers)` 的句柄：候选集合先被完整校验（冲突、名称、提供方元数据），再在一个同步区段内完成替换。被拒绝的替换会让先前的路由保持注册并继续服务，而调用方的事实缓存只有在注册表确实持有新集合之后才会推进，因此改回可用配置时会重新生效。pi-ai 的注册事实按提供方排序，因此仅仅调换键顺序的设置文档不再算作路由变更。 -**已提交的凭据写入采用收容式发布。**`CredentialProvider.notifyUpdated` 逐个监听器扇出 `credentials/updated`；同步抛错与异步 rejection 都只记日志，不改变已提交操作的结果，而带 `INVARIANT` 代码的失败会在每个监听器都运行完之后重抛——与 settings seam 处理 `settings/updated` 的形状相同。`installSettingsSection` 的清理现在会区分它的两个触发来源：提供方脱离时仍回退到组合的 entry 配置并重新推导，而消费方自身卸载时立即返回，不再在拆卸过程中重新注册路由。 +**已提交的凭据写入采用收容式发布。**`CredentialProvider.notifyUpdated` 逐个监听器扇出 `credentials/reference-updated`；同步抛错与异步 rejection 都只记日志，不改变已提交操作的结果，而带 `INVARIANT` 代码的失败会在每个监听器都运行完之后重抛——与 settings seam 处理 `settings/updated` 的形状相同。`installSettingsSection` 的清理现在会区分它的两个触发来源：提供方脱离时仍回退到组合的 entry 配置并重新推导，而消费方自身卸载时立即返回，不再在拆卸过程中重新注册路由。 ## 曾考虑的替代方案 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 d5a44ae173..aaed5ddc6b 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: c90979ff3ade89c11af7fb9a73d536aa2c1daa12 -2026-08-04-configuration-source-ownership.zh.md: dbda79a0c02911e5ee0b431770e2177f44e7c947 +2026-08-04-configuration-source-ownership.md: 2cd09ae2daca2b15657caa18ff210fa178c2999b +2026-08-04-configuration-source-ownership.zh.md: fc47c3e47dc8d5d9ae763ddb5fe932a80e72c3d1 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 c90979ff3a..2cd09ae2da 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 @@ -42,7 +42,7 @@ The launching environment wins because `DEEPSEEK_API_KEY=… dsh`, a CI secret, **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. -**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`), 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. +**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. The line is that these take effect with no user action, before any turn, outside the permission policy and the sandbox. `DSH_PERMISSION_MODE` would switch off the approvals that make trusting a project meaningful at all, and `BASH_ENV` runs a file of the project's choosing on every single `bash -c` the bash tool issues — the project's code running under the agent's policy is the deal; the project rewriting that policy is not. Enumerating these is a losing game one variable at a time, which is why the whole `DSH_*` namespace is denied rather than an audited subset, and why the list is organised by what a variable *does* rather than by which runtime owns it. There is no opt-out: an escape hatch would have to be readable from somewhere, and anything a discovered file could set is the hole itself. @@ -53,7 +53,7 @@ The line is that these take effect with no user action, before any turn, outside ## Consequences - The web credential form now takes effect against an older key in the user's `.env`; only a key exported in the launching shell still makes it read-only, and the diagnostic says so. -- A `.env` holding `DSH_*`, `PATH`, or a proxy variable fails the launch instead of being applied. Developers keeping switches in a repository `.env` move them to their shell — a deliberate, loud break. +- A `.env` holding `DSH_*`, `PATH`, `BROWSER`, or a proxy variable fails the launch instead of being applied. Developers keeping switches in a repository `.env` move them to their shell — a deliberate, loud break. - Composition is no longer overridable by a stale shell endpoint. It is still overridable by a user's stored `settings.yaml`, which is the settings seam's layering and not something this note changes; the product CLI offers no flag above it, so a deployment that must win against stored settings owns its own bin or loader tree. - Not solved: the layers are still materialized into `process.env`, so ordinary project variables continue to reach child processes under the subprocess scrub. Bootstrap variables cannot come from a file at all; the environment package records the remaining subprocess reach as a limitation. - Exa and Perplexity still capture their key at load time rather than through the credential seam. They no longer read raw `process.env` — they resolve through the trusted layers — but converting them to per-request credential resolution is separate work. 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 dbda79a0c0..fc47c3e47d 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 @@ -43,7 +43,7 @@ inherited process environment (read-only, wins) **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。 -**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。 +**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。 这条界线在于：它们无需任何用户动作、在任何轮次开始之前、且在权限策略与沙箱之外就生效。`DSH_PERMISSION_MODE` 会关掉让「信任项目」根本成立的那道审批，而 `BASH_ENV` 会在 bash 工具每次发出 `bash -c` 时执行项目指定的文件——项目的代码在 agent（智能体）的策略下运行是约定，项目改写那份策略不是。一个变量一个变量地枚举是必输的游戏，所以整个 `DSH_*` 命名空间被拒绝而不是只拒绝一份经审查的子集，也所以这份清单是按变量*做什么*而不是按哪个运行时拥有它来组织的。不设逃生门：逃生门本身总得从某处读取，而任何被发现的文件能设置的东西，就是那个漏洞本身。 @@ -54,7 +54,7 @@ inherited process environment (read-only, wins) ## Consequences - Web 凭据表单现在能压过用户 `.env` 里更旧的密钥；只有在启动 shell 里 export 的密钥才会让它变成只读，诊断信息也会这么说。 -- 含 `DSH_*`、`PATH` 或 proxy 变量的 `.env` 会导致启动失败而不是被应用。把开关放在仓库 `.env` 里的开发者需要改放到 shell——这是一次刻意且响亮的破坏。 +- 含 `DSH_*`、`PATH`、`BROWSER` 或 proxy 变量的 `.env` 会导致启动失败而不是被应用。把开关放在仓库 `.env` 里的开发者需要改放到 shell——这是一次刻意且响亮的破坏。 - composition 不再会被陈旧的 shell endpoint 覆盖。但它仍然会被用户已存的 `settings.yaml` 覆盖，这是 settings seam 的分层方式，本 Note 不改变它；产品 CLI 没有高于它的标志，因此需要压过已存 settings 的部署方要自带 bin 或 loader 配置树。 - 未解决的：各层仍然会被物化进 `process.env`，因此普通项目变量继续按子进程清洗规则抵达子进程。bootstrap 变量完全不能来自文件；环境包将其余变量仍可抵达子进程这一点记录为一项限制。 - Exa 与 Perplexity 仍在加载时捕获密钥，而不是经凭据 seam。它们不再读裸 `process.env`——改为经受信层解析——但把它们改造成按请求解析凭据是另一件事。 diff --git a/.agents/notes/implemented/architecture/2026-08-10-cancelled-stream-prefix-finalize.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-10-cancelled-stream-prefix-finalize.i18n.yaml new file mode 100644 index 0000000000..50cdedbe5b --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-10-cancelled-stream-prefix-finalize.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/implemented/architecture/2026-08-10-cancelled-stream-prefix-finalize.md +2026-08-10-cancelled-stream-prefix-finalize.md: 0cae25b786922fba8204d68ca9c0a669e43d76a0 +2026-08-10-cancelled-stream-prefix-finalize.zh.md: e961ea6a51f74dcc244e4ad8970eae4cbe4c9a6c diff --git a/.agents/notes/implemented/architecture/2026-08-10-cancelled-stream-prefix-finalize.md b/.agents/notes/implemented/architecture/2026-08-10-cancelled-stream-prefix-finalize.md new file mode 100644 index 0000000000..0cae25b786 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-10-cancelled-stream-prefix-finalize.md @@ -0,0 +1,39 @@ +# Agent Note: Cancelled streams finalize their delivered prefix + +Status: implemented + +English | [中文](2026-08-10-cancelled-stream-prefix-finalize.zh.md) + +## Problem + +A cancelled stream can leave `assistant/chunk` events that clients continue rendering while `deriveMessages()` excludes them because no `assistant/message` records the delivered prefix. A follow-up such as "expand on your second point" then lacks text the user read, and a fork at the cancelled turn inherits the same gap. + +The model history must contain assistant content that remains visible to the user after cancellation. + +## Decision + +`ReactLoopAgent.step()` catches cancellation while consuming a model stream, when its `BlockAssembler`, logged chunk seqs, and provider route identify the delivered prefix. It appends that prefix as the step's `assistant/message` with `interrupted: true`, `surfaceOp: 'append'`, and `sourceEventSeqs` containing exactly the logged chunks. The append precedes `step/end` and the aborted `turn/end`. + +`BlockAssembler.interruptedBlocks()` returns closed and open `text` and `reasoning` blocks with non-whitespace content in stream order. It omits tool calls because interruption precedes dispatch and no real result exists; it also omits empty blocks and open unknown block types. An empty result appends no assistant message. Provider `error` and `aborted` finishes leave the stream-consumption scope before `agent/request-error`, so provider failures and cancellation during recovery commit no content from the failed request. + +Chat and Trajectory Conversation Definitions read `interrupted` from the durable message. Chat renders the Stopped marker, while Trajectory keeps the provider request in the error lifecycle after `step/end` and retains the durable result seq and provenance. Cancellation during tool execution follows the tool scheduler contract because the assistant message has already committed: started calls produce real results, and undispatched calls receive `ABORTED_BEFORE_DISPATCH` results. + +## Alternatives considered + +**Always discard the prefix.** This avoids a new durable marker but makes every cancel-then-follow-up and fork omit assistant content that remains visible to the user. + +**Assemble the prefix from chunks during projection.** `deriveMessages()` and client Conversation Definitions would each need interruption assembly rules, and the log would have no authoritative assistant message for the prefix. This also expands model history beyond the three `SurfaceEventType` events. + +**Retain complete tool calls with synthetic aborted results.** These calls never dispatched, so synthetic results would claim an execution outcome that did not occur and add content the user did not receive as a tool result. + +**Append a model-visible interruption message such as `[interrupted by user]`.** This can tell the model that the prefix is incomplete, but it requires a separate source type, projection rule, UI treatment, and localized wording. The durable aborted `turn/end` preserves the fact needed for that later decision. + +## Consequences + +Post-cancel follow-ups and forks include the delivered prefix. The ACP bridge drains ordered assistant output before settling the prompt, so the final `agent_message_chunk` update precedes the cancelled stop reason. + +Terminal provider errors still discard their streamed prefix. That asymmetry remains because an error turn ends without the user's cancellation decision and requires its own retention policy. + +## Testing + +`packages/core/agent-loop/tests/cancel.spec.ts` covers content, cited seqs, event order, next-request parity, reasoning-only output, tool-call omission, recovery cancellation, and the empty-prefix case. `packages/llm/llm/tests/assembler.spec.ts` covers `interruptedBlocks()`. `packages/client/ui-conversation/tests/conversation-node-definitions.client.spec.ts` and `packages/client/ui-trajectory/tests/conversation-definitions.client.spec.ts` cover both client projections. The keyless `cancel` ACP snapshot and `goal-round-driver` goal snapshot cover assembled applications. diff --git a/.agents/notes/implemented/architecture/2026-08-10-cancelled-stream-prefix-finalize.zh.md b/.agents/notes/implemented/architecture/2026-08-10-cancelled-stream-prefix-finalize.zh.md new file mode 100644 index 0000000000..e961ea6a51 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-10-cancelled-stream-prefix-finalize.zh.md @@ -0,0 +1,39 @@ +# Agent Note: 被取消的流定稿其已送达前缀 + +Status: implemented + +[English](2026-08-10-cancelled-stream-prefix-finalize.md) | 中文 + +## Problem + +被取消的流可能留下客户端继续渲染的 `assistant/chunk` 事件，但如果没有 `assistant/message` 记录已送达前缀，`deriveMessages()` 就会排除这部分内容。后续的「第二点展开讲讲」之类追问会缺少用户已读到的文本，在该轮次上创建的分支也会继承这个缺口。 + +模型历史必须包含取消后仍对用户可见的 assistant 内容。 + +## Decision + +`ReactLoopAgent.step()` 在消费模型流期间捕捉取消，此时 `BlockAssembler`、已记录的分片 seq 和提供方路由可以确定已送达前缀。循环把该前缀追加为 step 的 `assistant/message`，并设置 `interrupted: true`、`surfaceOp: 'append'` 以及恰好包含已记录分片的 `sourceEventSeqs`。该追加先于 `step/end` 和记录 aborted 的 `turn/end`。 + +`BlockAssembler.interruptedBlocks()` 按流顺序返回内容非空白的已闭合和未闭合 `text` 与 `reasoning` 块。打断先于分派，没有真实工具结果，因此它会省略工具调用，也会省略空块和未闭合的未知块类型。返回结果为空时不追加 assistant 消息。提供方的 `error` 和 `aborted` finish 会在 `agent/request-error` 前离开流消费范围，因此提供方故障和恢复期间的取消都不会提交失败请求的内容。 + +Chat 和 Trajectory Conversation Definition 从持久消息读取 `interrupted`。Chat 渲染 Stopped 标记，Trajectory 则在 `step/end` 后把提供方请求保持在 error 生命周期，并保留持久结果 seq 和提供方信息。工具执行期间的取消遵循工具调度器约定，因为 assistant 消息已提交：已启动的调用生成真实结果，未分派的调用获得 `ABORTED_BEFORE_DISPATCH` 结果。 + +## Alternatives considered + +**始终丢弃前缀。** 这能避免新增持久标记，但每次取消后的追问和分支都会缺少仍对用户可见的 assistant 内容。 + +**在投影时从分片组装前缀。** `deriveMessages()` 和客户端 Conversation Definition 都需要实现打断组装规则，日志中也没有该前缀的权威 assistant 消息。这还会让模型历史超出三类 `SurfaceEventType` 事件。 + +**保留完整工具调用并合成 aborted 结果。** 这些调用从未分派，合成结果会声称一个并未发生的执行结果，还会增加用户未收到的工具结果内容。 + +**追加 `[interrupted by user]` 之类模型可见的打断消息。** 这可以告诉模型前缀并不完整，但需要独立的来源类型、投影规则、UI 处理和本地化文案。持久的 aborted `turn/end` 保留了该后续决策所需的事实。 + +## Consequences + +取消后的追问和分支会包含已送达前缀。ACP 桥会在结算 prompt 前排空按序传送的 assistant 输出，因此最后一条 `agent_message_chunk` 更新先于 cancelled stop reason。 + +终局提供方错误仍会丢弃已流出前缀。该不对称保留，因为 error 轮次的结束不来自用户的取消决定，需要独立的保留策略。 + +## Testing + +`packages/core/agent-loop/tests/cancel.spec.ts` 覆盖内容、引用的 seq、事件顺序、下一请求的一致性、仅 reasoning 的输出、工具调用省略、恢复期间的取消和空前缀情形。`packages/llm/llm/tests/assembler.spec.ts` 覆盖 `interruptedBlocks()`。`packages/client/ui-conversation/tests/conversation-node-definitions.client.spec.ts` 和 `packages/client/ui-trajectory/tests/conversation-definitions.client.spec.ts` 覆盖两种客户端投影。keyless 的 `cancel` ACP 快照和 `goal-round-driver` goal 快照覆盖完整应用。 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 1353cbcb08..f068885f5a 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: 9c2b5087772a5a343514d1766a14e90edb261813 -2026-08-10-remote-event-delivery.zh.md: 2e056bf4d72ea63333aecaf9a79274b93ccef3f6 +2026-08-10-remote-event-delivery.md: ee3d9884b53f5fa5d0b0072660888c5f4d283b1b +2026-08-10-remote-event-delivery.zh.md: 01777bd8818d72cfc9650b9d35bc5ae5ee82d880 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 9c2b508777..ee3d9884b5 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 @@ -8,7 +8,7 @@ English | [中文](2026-08-10-remote-event-delivery.zh.md) [Typert Gateway targeted method calls](../../implemented/architecture/2026-08-02-typert-remote-method-calls.md) cover only the request/response shape and deliberately leave Session event streams and stateful interactions to separate designs. Every **one-way Host-to-consumer push** therefore still rides the legacy API Proxy. -The Host owns a family of one-way events whose payloads are already JSON and whose emission never binds an AgentScope: `agent-preset/selected`, `commands/change`, `credentials/updated`, `llm/adapters-updated`, and `settings/document-updated`. Reaching one UI subscriber took four hops: the Host cordis event, a hand-written `HostFrame` variant plus its zod branch in apiproxy, a hand-written bridge in client/runtime that re-emitted it as a Client cordis event, and finally the consumer's `ctx.on(...)`. Adding one such event edited five places (frame union, zod union, host-stream listener, client bridge, a duplicated Client-side `Events` declaration), and not one of them stated a new fact: the name, the payload type, and the emission point were all declared by the owner package's cordis `Events` merge. +The Host owns a family of one-way events whose payloads are already JSON and whose emission never binds an AgentScope: `agent-preset/selected`, `commands/change`, `credentials/reference-updated`, `llm/adapters-updated`, and `settings/document-updated`. Reaching one UI subscriber took four hops: the Host cordis event, a hand-written `HostFrame` variant plus its zod branch in apiproxy, a hand-written bridge in client/runtime that re-emitted it as a Client cordis event, and finally the consumer's `ctx.on(...)`. Adding one such event edited five places (frame union, zod union, host-stream listener, client bridge, a duplicated Client-side `Events` declaration), and not one of them stated a new fact: the name, the payload type, and the emission point were all declared by the owner package's cordis `Events` merge. That duplicated declaration is also **lossy**: the Client side restates it as `settings/changed(ns: string)`, flattening a branded type into bare `string` — the opposite of the Remote method contract, where a consumer type points at the business package's one canonical symbol. @@ -75,7 +75,7 @@ Delivery shares no implementation with the cordis event system: one-way only, no export const API_REMOTE_FORWARDED_EVENTS = [ 'agent-preset/selected', 'commands/change', - 'credentials/updated', + 'credentials/reference-updated', 'llm/adapters-updated', 'settings/document-updated', ] as const 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 2e056bf4d7..01777bd881 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 @@ -8,7 +8,7 @@ Status: implemented [Typert Remote 方法调用](../../implemented/architecture/2026-08-02-typert-remote-method-calls.zh.md)只覆盖「一次请求一个结果」的定向调用，明确把 Session 事件流与有状态交互留在别处；Host 向消费端的**单向事件推送**因此仍然全部压在遗留的 API Proxy 上。 -Host 拥有 `agent-preset/selected`、`commands/change`、`credentials/updated`、`llm/adapters-updated`、`settings/document-updated` 这五条单向事件；它们既不依赖 AgentScope，载荷也本来就是 JSON。过去每条都要穿过 host cordis 事件、apiproxy 手写帧、client/runtime 手写桥和 Client 事件别名才能抵达 UI，而这些层没有陈述 owner 事件之外的新事实。 +Host 拥有 `agent-preset/selected`、`commands/change`、`credentials/reference-updated`、`llm/adapters-updated`、`settings/document-updated` 这五条单向事件；它们既不依赖 AgentScope，载荷也本来就是 JSON。过去每条都要穿过 host cordis 事件、apiproxy 手写帧、client/runtime 手写桥和 Client 事件别名才能抵达 UI，而这些层没有陈述 owner 事件之外的新事实。 那份重复声明还是**有损**的：client 侧写成 `settings/changed(ns: string)`，brand 类型在这一跳被拍平成裸 `string`，与 Remote 方法侧「消费端类型指向业务包唯一符号」的既有契约相反。 @@ -75,7 +75,7 @@ $dispatch(event: string, args: readonly unknown[]): void export const API_REMOTE_FORWARDED_EVENTS = [ 'agent-preset/selected', 'commands/change', - 'credentials/updated', + 'credentials/reference-updated', 'llm/adapters-updated', 'settings/document-updated', ] as const diff --git a/.agents/notes/implemented/architecture/2026-08-11-pwsh-persistent-pty.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-11-pwsh-persistent-pty.i18n.yaml new file mode 100644 index 0000000000..80a1959b5a --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-11-pwsh-persistent-pty.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/implemented/architecture/2026-08-11-pwsh-persistent-pty.md +2026-08-11-pwsh-persistent-pty.md: 8353b3ab3cdbf20add22a55acb03312c94283602 +2026-08-11-pwsh-persistent-pty.zh.md: 95048a02416dfcf5f0ef2837d99a561008f6496f diff --git a/.agents/notes/implemented/architecture/2026-08-11-pwsh-persistent-pty.md b/.agents/notes/implemented/architecture/2026-08-11-pwsh-persistent-pty.md new file mode 100644 index 0000000000..8353b3ab3c --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-11-pwsh-persistent-pty.md @@ -0,0 +1,65 @@ +# Agent Note: Persistent pwsh over the terminal seam on Windows + +Status: implemented + +English | [中文](2026-08-11-pwsh-persistent-pty.zh.md) + +## Problem + +The harness had no persistent shell on Windows. The persistent `bash` stack was POSIX-only by construction: `@deepseek-ai/dsh-subprocess-local` threw at terminal allocation (`createProcessInspector()` rejected win32), `@deepseek-ai/dsh-terminal-bash` was bash-shaped (`/bin/bash` defaults, `PS1`/`PROMPT_COMMAND` environment markers), `@deepseek-ai/dsh-tool-bash-persistent` wrapped commands in bash syntax, and every pty test skipped on win32. The one-shot `pwsh` tool (`@deepseek-ai/dsh-tool-pwsh` over `@deepseek-ai/dsh-pwsh-local`) already ran on Windows, but each call started a fresh `pwsh -Command` process: cwd, `$env:` variables, functions, and interactive children ended with the call, and its README recorded "No persistent shell or PTY" as deferred work. + +The gap excluded Windows workflows whose state lives in a terminal: stepping a debugger, exploring in a Python or Node REPL, or returning to a shell after interrupting its foreground command — the same class of work the persistent bash pty serves on POSIX. + +Two foundations already existed. the terminal service itself (`ctx.terminals` registry, owner scoping, send/read/signal/kill contract) is platform-neutral. The Loader's `disabled: !!js` interpolation (PR #2234) gates shell rows per platform and pins the invariant that exactly one shell stack mounts per host; a persistent pwsh stack composes through the same rows. + +## Decision + +A model-facing persistent `pwsh` tool ships on Windows with the same contract as `tool-bash-persistent`: one owner-scoped persistent shell per Agent, marker-detected command completion, exact native exit codes, bounded output, and timeout/cancel/`exit` semantics that reset the shell and tell the model. Three pieces deliver it: a Windows substrate in `subprocess-local`, a shell-dialect option in `terminal-bash`, and the new `tool-pwsh-persistent` package with the minimal-preset composition rows. + +### Windows substrate in `@deepseek-ai/dsh-subprocess-local` + +`createProcessInspector()` returns a `WindowsProcessInspector` on win32 instead of throwing. The koffi-backed inspector enumerates the process table through Toolhelp32, combines GetProcessTimes creation identities with zero-time process-handle waits (pid-reuse fencing plus terminated-object detection), reports the **shell pid as a pseudo foreground group** (Windows has no POSIX groups; the stable value lets the prompt-marker readiness fast path settle in one poll interval), reports no stdin-wait evidence (readiness degrades exactly like macOS), and signals through `taskkill /T` escalation (`/F` only for SIGKILL). koffi (`^3.1.0`, the version `sandbox-windows-acl` already pins) loads lazily on win32 only. + +`LocalTerminalHandle` branches for win32 because node-pty's `kill(signal)` throws ("Signals not supported on windows") and its bare kill delegates to a console-list agent that fails without a parent console. Teardown escalates through taskkill fenced on the shell's start identity, and — because an externally taskkilled shell may never fire node-pty's exit notification — the handle settles `done` from the inspector-verified absence (`settleExitIfGone`). `signalForeground` maps SIGINT to a `\x03` Ctrl-C input write (the console-wide delivery conhost turns into a CTRL_C event; verified to interrupt a running command), routes SIGTERM/SIGKILL to taskkill, and rejects SIGTSTP/SIGHUP as unavailable on Windows. The public `PtySignal` set and seam types are unchanged; the mapping lives in the backend. + +### Shell dialect in `@deepseek-ai/dsh-terminal-bash` + +One backend, two dialects: `shellDialect: 'bash' | 'pwsh'` (default `'bash'`, existing deployments byte-identical). The effective `shellPath`/`shellArgs` resolve per dialect (bash `/bin/bash --noprofile --norc -i`; pwsh through the shared `dsh-pwsh-local` resolver with `-NoLogo -NoProfile`, keeping the interactive host for child REPLs). The child environment drops the bash-only `PS1`/`PROMPT_COMMAND` markers and adds `NO_COLOR` for pwsh. pwsh cannot install its prompt from the environment, so the backend writes the prompt function through the session at startup and waits until the controlled prompt is actually visible, looping over follow-up sends because the pwsh banner-to-prompt gap can outlast the silence bound; a `session_exit` or `timeout` wait rejects the spawn. Both dialects emit the same BEL-terminated OSC `133;D;` marker, so the sanitizer, `PROMPT_MARKER_PREFIX`, `CONTROLLED_PROMPT`, and the exact-tail readiness logic are reused untouched — the marker stays a readiness signal with an unconsumed payload, exactly as in the bash path, and no model-notification channel was added (aligned with the current implementation; the deferred BEL event channel stays deferred). + +### `@deepseek-ai/dsh-tool-pwsh-persistent` + +A new package mirroring `tool-bash-persistent`: same `Config` (`backendType` default `shell`, `timeoutMs`, `maxOutputChars`, `description`), same owner-scoped shell registry and serialized per-owner queue, same timeout/abort/exit/reset paths. The tool name is `pwsh`; it never co-mounts with the one-shot `tool-pwsh` because the preset rows are mutually exclusive per platform. + +Commands run through a wrapper that resets `$LASTEXITCODE` (assignable, verified), invokes the body via `Invoke-Expression` in a backtick-escaped double-quoted string (`quoteForPwsh`: backtick, quote, `$`, CRLF, and ESC escapes, so no raw control characters ride the input line and the wrapper survives ConstrainedLanguage), and reports the exact native exit code, `1` for a terminating PowerShell error, or `0` for success. PSReadLine echoes the submitted wrapper back into the stream — there is no `stty -echo` equivalent — so the extraction strips the wrapper source from captured output; the echo can never fabricate completion because the status regex needs digits immediately after the END nonce and the echo continues with quote characters. The prompt function installs the tool's own prompt (`__DSH_PERSISTENT_PWSH_PROMPT__ `) over the backend bootstrap value, the same two-layer structure as bash. + +### Composition + +The minimal preset gates its persistent shell stack by platform with the #2234 `disabled: !!js` interpolation: the bash rows (`terminal-bash` + `tool-bash-persistent`) mount on POSIX, and the pwsh rows (`terminal-bash` with `shellDialect: pwsh` + `tool-pwsh-persistent`) mount on win32 — exactly one persistent shell per host. `windows-shell.spec` pins the per-platform roster; the real Loader composition exercises the whole stack over a real ConPTY pwsh. + +### Testing + +The Windows test surface follows master's exemption structure: terminal-bash and subprocess-local tests stay excluded on win32 (`windowsUnsupportedTests`) and their sources stay coverage-exempt there (`windowsUnsupportedCoveragePackages`), so the platform-gated fixtures and node-translated commands remain the win32 dev-lane evidence, while the koffi-backed inspector joins the windows-only coverage exclusions on Linux. `tool-pwsh-persistent` is not exempt: its suite runs and its sources are coverage-required on the windows-native lane, mirroring `tool-bash-persistent`'s stub-mode matrix plus an echo-stripping mode; the real-pwsh suites prove persistent cwd/env, secret scrubbing, multiline and here-string commands, large-output clipping, and exit/reset over real ConPTY sessions. The ACP keyless snapshot boots the persistent tool through a real Loader composition and pins its model-visible schema and result. + +## Alternatives considered + +- **A separate `pty-pwsh-local` backend package.** Rejected: the local session, sanitizer, readiness tiers, and sandbox fence are shared machinery; duplicating the 500-line session for argv/env/startup differences trades one config field for a package of copy-paste, unlike the bash group's thin parallel executors. +- **tasklist or wmic polling for the process tree.** Rejected: `inspectForeground` runs on every readiness poll (~50 ms), so a spawned probe per tick is untenable, and wmic is removed from current Windows releases. koffi + Toolhelp32 is in-process and cheap. +- **A native helper or `GenerateConsoleCtrlEvent` for SIGINT.** Rejected: writing `\x03` to ConPTY input interrupts running commands (verified) with zero new code. The semantic difference — at a prompt, `\x03` cancels the pending line instead of signalling a process — is documented rather than engineered around. +- **Base64 body encoding for the wrapper.** Rejected: decoding needs `[Convert]`/`[System.Text.Encoding]` calls whose ConstrainedLanguage status is unproven, while backtick-escaped double-quoted strings use only language-level constructs and were verified end-to-end. +- **Tolerating the echo without stripping the wrapper.** Rejected: in complete and prompt-settled paths the echo is naturally excluded, but timeout and lost-START fallbacks would leak the wrapper source (including marker nonces) into model-visible text. +- **Resurrecting a BEL model-notification channel.** Rejected: the current implementation consumes no marker payload and delivers no BEL events; the design aligns with the current implementation and keeps the deferred item deferred. +- **Windows PowerShell 5.1 as a first-class target.** Rejected: pwsh 7 (including the Store install) is the target; `resolvePwshPath` keeps 5.1 as the last-resort executable fallback without promising full persistent-shell behavior on it. + +## Consequences + +**Windows became a first-class persistent-shell host.** The persistent pwsh stack runs and is coverage-gated on the windows-native lane; the one-shot/persistent shell split mirrors POSIX, and the preset spec pins exactly one shell stack per host on both platforms. + +**Windows coverage keeps master's exemption structure.** subprocess-local and terminal-bash sources stay coverage-exempt and their suites test-excluded on win32 exactly as on master; the Windows code paths are exercised through the win32 dev lane and the real-pwsh tool suites, and the new surface's coverage obligation on the windows-native lane sits on `tool-pwsh-persistent`. + +**Windows readiness is weaker than Linux.** The pseudo-pgid marker fast path covers shell prompts, but a child without a prompt settles on the silence tier (~3 s), exactly like macOS; there is no exact stdin-wait tier. + +**Windows teardown and signalling differ from POSIX.** taskkill without `/F` does not terminate console processes (the TERM tier is a grace wait before `/F`), SIGINT is console-wide Ctrl-C, SIGTSTP/SIGHUP are unavailable, and externally taskkilled shells may not fire node-pty's exit notification — the handle settles from verified absence instead. + +**Input echo is an accepted platform fact.** PSReadLine echoes submitted input; the marker-anchored extraction and wrapper-source strip remove it in complete results, with bounded residual in partial-output fallbacks. + +**Risks carried.** Under the Windows ACL sandbox's read-only mode, ConstrainedLanguage may deny the bootstrap's `[Console]::` encoding pin and prompt marker; commands then settle through the printable prompt and silence tier, while non-ASCII output may follow the host code page. A model redefinition of the `prompt` function likewise degrades readiness to the silence tier. Raw ESC characters in model commands are unsupported (PSReadLine consumes them). koffi is now a dependency of the process substrate, carrying the same install/prebuild review the sandbox package already has. diff --git a/.agents/notes/implemented/architecture/2026-08-11-pwsh-persistent-pty.zh.md b/.agents/notes/implemented/architecture/2026-08-11-pwsh-persistent-pty.zh.md new file mode 100644 index 0000000000..95048a0241 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-11-pwsh-persistent-pty.zh.md @@ -0,0 +1,65 @@ +# Agent Note: Windows 上基于 terminal seam 的持久化 pwsh + +Status: implemented + +[English](2026-08-11-pwsh-persistent-pty.md) | 中文 + +## 问题 + +harness 在 Windows 上没有持久 shell。持久 `bash` 栈按构造就是 POSIX-only：`@deepseek-ai/dsh-subprocess-local` 在终端分配时直接抛错（`createProcessInspector()` 拒绝 win32），`@deepseek-ai/dsh-terminal-bash` 是 bash 形态（`/bin/bash` 默认值、`PS1`/`PROMPT_COMMAND` 环境标记），`@deepseek-ai/dsh-tool-bash-persistent` 用 bash 语法包装命令，pty 测试全部在 win32 上 skip。一次性 `pwsh` 工具（`@deepseek-ai/dsh-tool-pwsh` + `@deepseek-ai/dsh-pwsh-local`）已经能在 Windows 运行，但每次调用都是全新的 `pwsh -Command` 进程：cwd、`$env:` 变量、函数和交互式子进程都随调用结束，其 README 把 "No persistent shell or PTY" 记为 deferred work。 + +这个缺口排除了状态驻留在终端里的 Windows 工作流：单步调试、在 Python 或 Node REPL 中探索、中断前台命令后回到原 shell —— 正是持久 bash pty 在 POSIX 上服务的同一类工作。 + +两个基础已经存在。PTY 服务本身（`ctx.terminals` 注册表、owner 作用域、send/read/signal/kill 契约）是平台无关的。Loader 的 `disabled: !!js` 插值（PR #2234）按平台门控 shell 行，并钉死了"每宿主恰好挂载一个 shell 栈"的不变量；持久 pwsh 栈通过同一行机制组合。 + +## 决定 + +模型侧持久 `pwsh` 工具在 Windows 上交付，契约与 `tool-bash-persistent` 逐项对齐：每个 Agent 一个 owner 作用域的持久 shell、标记检测的命令完成、精确的原生退出码、有界输出，以及超时/取消/`exit` 时重置 shell 并告知模型的语义。三块交付：`subprocess-local` 的 Windows 基座、`terminal-bash` 的 shell 方言选项、新的 `tool-pwsh-persistent` 包加 minimal 预设组合行。 + +### `@deepseek-ai/dsh-subprocess-local` 的 Windows 基座 + +`createProcessInspector()` 在 win32 返回 `WindowsProcessInspector` 而不是抛错。基于 koffi 的检查器通过 Toolhelp32 枚举进程表，把 GetProcessTimes 创建身份与进程句柄零时等待结合起来（同时防止 PID 复用并识别已终止的进程对象），把 **shell pid 作为伪前台进程组**（Windows 没有 POSIX 进程组；这个稳定值让 prompt-marker 就绪快路径在一个轮询间隔内结算），不报告 stdin-wait 证据（就绪与 macOS 同档），信号走 `taskkill /T` 升级（仅 SIGKILL 加 `/F`）。koffi（`^3.1.0`，`sandbox-windows-acl` 已固定的版本）仅在 win32 惰性加载。 + +`LocalTerminalHandle` 为 win32 分支，因为 node-pty 的 `kill(signal)` 会抛错（"Signals not supported on windows"），其无参 kill 委托的 console-list agent 在没有父控制台时失败。拆卸经 taskkill 升级并以 shell 的启动身份作栅栏；由于被外部 taskkill 的 shell 可能永远不会触发 node-pty 的退出通知，句柄从 inspector 验证的消失状态结算 `done`（`settleExitIfGone`）。`signalForeground` 把 SIGINT 映射为 `\x03` Ctrl-C 输入写入（conhost 转为控制台级 CTRL_C 事件的投递方式；实测可中断运行中的命令），SIGTERM/SIGKILL 路由到 taskkill，SIGTSTP/SIGHUP 以 Windows 不可用为由拒绝。公共 `PtySignal` 集合与 seam 类型不变；映射全部留在 backend。 + +### `@deepseek-ai/dsh-terminal-bash` 的 shell 方言 + +一个 backend、两种方言：`shellDialect: 'bash' | 'pwsh'`（默认 `'bash'`，存量部署逐字节不变）。有效 `shellPath`/`shellArgs` 按方言解析（bash `/bin/bash --noprofile --norc -i`；pwsh 经共享的 `dsh-pwsh-local` 解析器取 `-NoLogo -NoProfile`，保留交互宿主供子 REPL）。子环境去掉 bash 专属 `PS1`/`PROMPT_COMMAND` 标记并为 pwsh 加 `NO_COLOR`。pwsh 无法从环境安装提示符，因此 backend 在启动时通过会话写入 prompt 函数，并等待受控提示符真正可见——因为 pwsh 从横幅到提示符的间隙可能超过静默上限，所以会在后续 send 上循环等待；`session_exit` 或 `timeout` 结算拒绝 spawn。两种方言发出相同的 BEL 终结 OSC `133;D;` 标记，因此 sanitizer、`PROMPT_MARKER_PREFIX`、`CONTROLLED_PROMPT` 与精确尾部就绪逻辑原样复用——标记仍只是就绪信号、载荷不被消费，与 bash 路径完全一致，且没有新增模型通知通道（与当前实现对齐；延后的 BEL 事件通道保持延后）。 + +### `@deepseek-ai/dsh-tool-pwsh-persistent` + +新包镜像 `tool-bash-persistent`：同样的 `Config`（`backendType` 默认 `shell`、`timeoutMs`、`maxOutputChars`、`description`）、同样的 owner 作用域 shell 注册表与每 owner 串行队列、同样的超时/中止/退出/重置路径。工具名是 `pwsh`；它与一次性 `tool-pwsh` 永不共挂，因为预设行按平台互斥。 + +命令经包装器执行：先重置 `$LASTEXITCODE`（可赋值，已实测），通过 `Invoke-Expression` 在反引号转义的双引号字符串中执行 body（`quoteForPwsh`：反引号、引号、`$`、CRLF 与 ESC 转义，输入行上不携带裸控制字符，包装器可在 ConstrainedLanguage 下存活），报告精确原生退出码、PowerShell 终止性错误的 `1` 或成功的 `0`。PSReadLine 会把提交的包装器回显进流——没有 `stty -echo` 的对应物——因此提取会从捕获输出中剥离包装器原文；回显无法伪造完成，因为状态正则要求 END nonce 后紧跟数字，而回显继续是引号字符。prompt 函数安装工具自有提示符（`__DSH_PERSISTENT_PWSH_PROMPT__ `）覆盖 backend 引导值，与 bash 的双层结构相同。 + +### 组合 + +minimal 预设用 #2234 的 `disabled: !!js` 插值按平台门控持久 shell 栈：bash 行（`terminal-bash` + `tool-bash-persistent`）在 POSIX 挂载，pwsh 行（`shellDialect: pwsh` 的 `terminal-bash` + `tool-pwsh-persistent`）在 win32 挂载——每宿主恰好一个持久 shell。`windows-shell.spec` 钉死按平台的花名册；真实 Loader 组合在真实 ConPTY pwsh 上跑通整条栈。 + +### 测试 + +Windows 测试面沿用 master 的豁免结构：terminal-bash 与 subprocess-local 的测试在 win32 上继续排除（`windowsUnsupportedTests`），其源码在 win32 上继续覆盖豁免（`windowsUnsupportedCoveragePackages`），平台门控 fixture 与 node 翻译命令因此仍是 win32 开发车道的证据；koffi-backed inspector 在 Linux 侧加入 windows-only 覆盖豁免。`tool-pwsh-persistent` 不在豁免之列：其套件在 windows-native 车道上运行、源码受覆盖约束，镜像 `tool-bash-persistent` 的 stub 模式矩阵并加回显剥离模式；真实 pwsh 套件在真实 ConPTY 会话上证明持久 cwd/env、密钥清洗、多行与 here-string 命令、大输出裁剪与退出/重置。ACP keyless snapshot 通过真实 Loader 组合启动持久工具，并固定模型可见的 schema 与结果。 + +## 备选方案 + +- **独立的 `pty-pwsh-local` backend 包。** 拒绝：本地 session、sanitizer、就绪档位和沙箱栅栏是共享机制；为一个 config 字段复制 500 行 session 换来的是一包复制粘贴，与 bash 组并置薄 executor 的情形不同。 +- **tasklist 或 wmic 轮询进程树。** 拒绝：`inspectForeground` 每次就绪轮询（约 50ms）都跑，每 tick 生成一次探测进程不可行；wmic 已从现行 Windows 移除。koffi + Toolhelp32 是进程内、廉价的。 +- **为 SIGINT 加原生 helper 或 `GenerateConsoleCtrlEvent`。** 拒绝：向 ConPTY 输入写 `\x03` 即可中断运行中的命令（已实测），零新增代码。语义差异——在提示符处 `\x03` 取消当前行而不是给进程发信号——文档化而不是绕开。 +- **包装器 body 用 base64 编码。** 拒绝：解码需要 `[Convert]`/`[System.Text.Encoding]` 调用，其在 ConstrainedLanguage 下的可用性未证实；反引号转义的双引号字符串只用语言级构造，且已端到端实测。 +- **容忍回显而不剥离包装器。** 拒绝：完整路径和提示符就绪路径下回显天然被排除，但超时和 START 丢失的回退会把包装器源码（含 marker nonce）泄漏进模型可见文本。 +- **复活 BEL 模型通知通道。** 拒绝：当前实现不消费任何 marker 载荷、不投递任何 BEL 事件；设计对齐当前实现，deferred 项保持 deferred。 +- **把 Windows PowerShell 5.1 当一等目标。** 拒绝：pwsh 7（含 Store 安装）是目标；`resolvePwshPath` 保留 5.1 作为最后的可执行回退，但不承诺持久 shell 在其上的完整行为。 + +## 后果 + +**Windows 成为一等公民的持久 shell 宿主。** 持久 pwsh 栈在 windows-native 车道上运行并受覆盖门禁约束；一次性/持久 shell 的划分与 POSIX 镜像，预设 spec 在两种平台上都钉死每宿主恰好一个 shell 栈。 + +**Windows 覆盖沿用 master 的豁免结构。** subprocess-local 与 terminal-bash 源码在 win32 上保持覆盖豁免、其套件保持测试排除，与 master 完全一致；Windows 代码路径经 win32 开发车道与真实 pwsh 工具套件验证，新表面的覆盖义务在 windows-native 车道上落在 `tool-pwsh-persistent`。 + +**Windows 就绪弱于 Linux。** 伪 pgid marker 快路径覆盖 shell 提示符，但没有提示符的子进程按静默档结算（约 3s），与 macOS 完全一致；没有精确的 stdin-wait 档。 + +**Windows 的拆卸与信号不同于 POSIX。** 不带 `/F` 的 taskkill 无法终止控制台进程（TERM 档是 `/F` 升级前的宽限等待）、SIGINT 是控制台级 Ctrl-C、SIGTSTP/SIGHUP 不可用，且被外部 taskkill 的 shell 可能不触发 node-pty 的退出通知——句柄改从验证的消失状态结算。 + +**输入回显是接受的平台事实。** PSReadLine 回显提交的输入；marker 锚定提取与包装器原文剥离在完整结果中移除它，部分输出回退中残留有界。 + +**携带的风险。** Windows ACL 沙箱只读模式下，ConstrainedLanguage 可能拒绝引导代码通过 `[Console]::` 固定编码并写入 prompt marker；此时命令通过可打印提示符和静默档结算，非 ASCII 输出可能沿用宿主代码页。模型重定义 `prompt` 函数同样会使就绪降级到静默档。模型命令中的裸 ESC 字符不受支持（PSReadLine 会吞掉）。koffi 成为进程基座的依赖，承担与沙箱包相同的安装/prebuild 评审。 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 new file mode 100644 index 0000000000..fb9c5c6442 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-13-credential-records-and-authorization-flows.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/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 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 new file mode 100644 index 0000000000..a52d85854c --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-13-credential-records-and-authorization-flows.md @@ -0,0 +1,68 @@ +# Agent Note: Credential records and authorization flows + +Status: implemented + +English | [中文](2026-08-13-credential-records-and-authorization-flows.zh.md) + +## Problem + +The harness credential plane could only express one kind of secret: a value behind an environment-variable name. `CredentialRef` is a POSIX identifier, resolution layers the process environment over a managed file and `.env` fallbacks, and every consumer reads it per operation. That covers an API key exactly and covers nothing else. + +Some credentials are not values a deployment can be told to store. They are obtained — by a conversation with a human who opens a page, approves an account, and pastes a code back — and what comes out is a token document with a refresh half that rotates behind the user's back. pi-ai models this directly (`Credential = ApiKeyCredential | OAuthCredential`, an app-owned `CredentialStore`, `Models.login()`), and the harness had nowhere to put any of it. `PiAiAdapter` built its collection with `createModels()` and no options, so the store was pi-ai's in-memory default: empty at every boot, discarded on every configuration change. `openai-codex`, whose only method is OAuth, therefore failed every request with `Provider is not configured` — [withheld from the directory](../bug-fix/2026-08-13-oauth-only-providers-withheld.md) as a release fix, which removed the broken offer without adding the capability. + +Two further gaps followed from the same missing plane. A provider's own ambient discovery ran against the raw process environment, so a key held by the credential seam was invisible to it and a local credential file was never even looked for. And a login had no surface to run from, because nothing in the harness could ask a human a question on a plugin's behalf. + +## Decision + +Three seams, each owning one question, and every pi-ai concept behind an adapter inside `llm-pi-ai`. + +**`dsh-credentials` grows a second key space.** A `CredentialRef` answers *what is behind this environment-variable name*; a `CredentialKey` answers *what credential does this plugin hold for this id*. The record union is `{ kind: 'api-key', key?, env? } | { kind: 'grant', payload }` — the api-key half structural because the seam can describe it, the grant half opaque because a library that owns a token format keeps owning it. The only constraint on a payload is that it survives a JSON round trip, enforced on the way in and on the way out. + +The key is `/` where the scope is the **owning plugin's registered name**, not the provider's. A user knows `openai-codex`; which adapter family answers for the bytes inside that record is exactly what a bare provider name loses. Two plugins serving the same provider name would read each other's payload, and a record left by an uninstalled plugin could not be told from a live one. The `/` also keeps the two grammars disjoint, so the key spaces cannot collide. This assumes one adapter registers a given provider route, which the LLM registry already enforces. + +Records do not layer. There is no environment an authorization grant could be read from, so presence of the record is the whole fact, and the empty-value rule that governs references does not apply: an `api-key` record carrying neither a key nor env states that its owner confirmed ambient authentication, which is configured. + +**`dsh-authorization` owns the conversation, never the protocol.** A plugin that knows how to obtain its own credential registers a flow under the `CredentialKey` that flow writes. The seam runs one attempt per key, routes a neutral vocabulary of notices and prompts, and settles. A second authorization protocol arrives as another flow rather than as another seam, and a surface that renders one flow renders all of them. + +Two choices carry the weight: + +- **The flow owns the write.** `run()` resolving means the record is already committed through `ctx.credentials`; the seam confirms a commit it observed during the attempt — presence alone would let a re-authorization pass a stale record off as fresh — and refuses a flow that resolved without one. This is what lets `Models.login()` — which persists through the store adapter as part of logging in — stay the single writer, instead of the credential being copied back out and written a second time. +- **The interaction travels with the request, not a registry.** Whoever starts an authorization is the one who can talk to the human about it, so prompts reach exactly the page that asked, a headless caller supplies an interaction that declines, and there is no ambient provider to be absent or ambiguous between two open tabs. + +**`llm-pi-ai` holds all three translations.** `credentialStoreFrom` maps pi-ai's `CredentialStore` onto records; `authContextFrom` answers pi-ai's ambient questions from the credential seam, then the launch environment, with file existence checked against the host process's filesystem; `registerPiAiFlows` restates pi-ai's `AuthEvent`/`AuthPrompt` in the neutral vocabulary and runs `Models.login()`. Every collection is built with the first two, which is what keeps a signed-in provider signed in across the collection rebuild a configuration change causes. With a posture that works, the directory stops withholding OAuth-only routes and `openai-codex` is offered again. + +The credential plane stays optional, as it already was for reference resolution. Reads answer "nothing stored" without a credentials service, because such a composition genuinely holds no credential; writes refuse by name, because a login whose grant evaporated would report success and then fail every request. Flow registration is scoped to the authorization seam through `ctx.inject`, so a headless or ACP composition mounts with no sign-in and nothing else changed. + +### Two mechanisms the seams needed underneath + +`withFileLock` takes a per-call wait limit. pi-ai runs an OAuth refresh *inside* `credentials.modify()`, so the record write path holds the lock across a network round trip; the 2s default was chosen for a render-and-rename and would fail every other writer of the document. The retry cadence stays fixed — that is a protocol constant — while the wait is sized by the longest holder a contender can meet: refs and records share one file and one lock, so every writer of the document (`DOCUMENT_LOCK_WAIT_MS`, reference writes and record deletes included) waits an OAuth refresh out, not only the mutation that runs one. + +The seam's edges get the same discipline as its write path. A prompt decline is an outcome, not a breakage — an interaction rejects with `AuthorizationDeclinedError` and the attempt settles `cancelled` — while a notice a surface cannot render is logged and lost rather than failing the flow, and `authorization/settled` fans out with contained listener failures on the credentials seam's terms. On the store side, an api-key record is admitted before it is rendered (what `parseRecord` refuses at the next boot is refused at the write), and `llm-pi-ai` asks `isCredentialKeySegment` before addressing a record, so an arbitrary hand-declared route key reads as "nothing stored" instead of throwing mid-resolution. + +Withdrawal settles an attempt whether or not its flow reacts to the signal. A flow is supposed to stop when its signal fires, but one that does not would hold its key for the life of the process, and a wedged key is indistinguishable from a busy one from outside. The orphaned run is left to finish on its own. + +## Alternatives considered + +- **Putting the pi-ai `CredentialStore` shape into the seam itself.** It is the shape that works and it is already designed. It also names `api_key`/`oauth` as the world's two credential kinds and keys by provider id, which is the ownership loss above; a second adapter family would have to pretend to be pi-ai to participate. The record union is deliberately one step more abstract in exactly two places — the key, and the opacity of a grant. +- **A dedicated login-interaction seam beside `user-questions`.** Authorization prompts look like questions, and reusing `ctx.userQuestions` was tempting. But that seam is built for a model's tool call to pause on an agent's behalf: it validates the calling agent, refuses a delegated caller, and has one ambient UI provider. An authorization prompt has no agent, must reach the configuration page that started it, and can be withdrawn per prompt by a browser callback winning a race. The vocabularies overlap; the lifecycles do not. +- **Reading `~/.codex/auth.json` into a store.** It makes Codex work without any of this, and pi-ai would own the refresh. It also binds the harness to another tool's private file format for one provider, and leaves every other login unbuilt. +- **Joining a second `begin()` to the attempt already running.** Friendlier than refusing, until two humans are answering the same flow's questions. Refusal with `inFlight` on the entry lets a surface disable the button rather than discover the state by error. +- **Keeping the OAuth-only withholding as a safety net.** It would now hide a provider that works. The predicate is deleted rather than left inert; `docs/subsystems/credentials.md` and the package READMEs carry what replaced it. + +## Consequences + +`.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. + +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. + +Two limits are recorded in the package READMEs rather than fixed. An attempt is not durable, so reloading the page mid-login abandons it. And signing out is `deleteRecord`, which forgets the record locally without telling the issuer; a provider needing a server-side revoke has nowhere to declare it. + +## Testing + +The seam's suite pins the lifecycle it owns: single-flight refusal and release, withdrawal before the flow starts and during it, a flow that ignores its signal, the commit confirmation, and the settlement event including the `failed` case a caller sees as a thrown error. The invariant companion pins that a settled key is a free key, because a wedged one is otherwise invisible. + +`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. 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 new file mode 100644 index 0000000000..7ba73f133f --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-13-credential-records-and-authorization-flows.zh.md @@ -0,0 +1,68 @@ +# Agent Note: 凭据记录与授权 flow + +Status: implemented + +[English](2026-08-13-credential-records-and-authorization-flows.md) | 中文 + +## Problem + +harness 的凭据平面只能表达一种机密：藏在某个环境变量名之后的值。`CredentialRef` 是一个 POSIX 标识符，解析时按进程环境、受管文件、`.env` 回退分层，每个消费方按操作读取。这恰好覆盖 API key，此外什么都不覆盖。 + +有些凭据不是"可以让部署方去存"的值。它们是被**取得**的——与人对话：对方打开页面、批准账号、把码粘回来——产出的是一份带 refresh 半边、会在用户背后轮换的 token 文档。pi-ai 直接建模了这一点（`Credential = ApiKeyCredential | OAuthCredential`、由应用拥有的 `CredentialStore`、`Models.login()`），而 harness 无处安放其中任何一项。`PiAiAdapter` 用不带参数的 `createModels()` 构造集合，于是那个 store 就是 pi-ai 的内存默认实现：每次启动为空，每次配置变更被丢弃。只以 OAuth 认证的 `openai-codex` 因此每个请求都以 `Provider is not configured` 失败——[被目录withheld](../bug-fix/2026-08-13-oauth-only-providers-withheld.zh.md) 作为发布前修复，它移除了错误的供给，但没有补上能力。 + +同一处缺失还带来另外两个缺口。提供方自带的凭据发现是对着裸进程环境跑的，因此凭据 seam 保管的密钥对它不可见，本地凭据文件更是从未被查找过。而登录没有任何界面可以发起，因为 harness 里没有任何东西能代替插件向人发问。 + +## Decision + +三个 seam，各自拥有一个问题；所有 pi-ai 概念都藏在 `llm-pi-ai` 内部的适配器背后。 + +**`dsh-credentials` 长出第二个键空间。** `CredentialRef` 回答*这个环境变量名背后是什么*；`CredentialKey` 回答*这个插件为这个 id 持有什么凭据*。记录联合体是 `{ kind: 'api-key', key?, env? } | { kind: 'grant', payload }`——api-key 那半是结构化的，因为 seam 能描述它；grant 那半是不透明的，因为拥有 token 格式的库应当继续拥有它。对 payload 的唯一约束是它能原样通过一次 JSON 往返，读写两个方向都会校验。 + +键的形式是 `/`，其中 scope 是**拥有该记录的插件的注册名**，不是提供方名。用户知道的是 `openai-codex`；究竟哪个 adapter 家族为记录里的字节负责，恰恰是裸提供方名会丢掉的信息。服务同一个提供方名的两个插件会互相读到对方的 payload，已卸载插件留下的记录也无法与仍在使用的区分开。`/` 同时让两种文法互斥，两个键空间因此不可能相撞。这以"同一个 provider 路由只由一个 adapter 注册"为前提，而 LLM 注册表本就强制了这一点。 + +记录不分层。授权 grant 没有任何"环境"可供读取，因此记录是否存在就是全部事实，管辖引用的空值规则在此不适用：一条既无 key 也无 env 的 `api-key` 记录，陈述的是其拥有者确认了环境认证可用，这属于已配置。 + +**`dsh-authorization` 拥有对话，从不拥有协议。** 知道如何取得自己那份凭据的插件，以该 flow 写入的 `CredentialKey` 注册。seam 对每个键同时只跑一次尝试，路由一套中立的 notice/prompt 词汇，然后结算。第二种授权协议以另一个 flow 的形式到来，而不是另一个 seam；能渲染一个 flow 的界面就能渲染全部 flow。 + +两个选择承担了主要分量： + +- **写入由 flow 拥有。** `run()` 返回即表示记录已通过 `ctx.credentials` 提交；seam 核实的是本次尝试期间观察到的提交——只看记录存在与否，会让重新授权把陈旧记录冒充成新鲜的——并拒绝返回时没提交记录的 flow。正是这一点让 `Models.login()`——它把持久化当作登录的一部分，经由 store 适配器完成——保持为唯一写入方，而不是把凭据复制出来再写第二遍。 +- **交互随请求传入，而非注册表。** 发起授权的一方才是能与人对话的一方，因此提示恰好抵达发问的那个页面，无头调用方传入一个直接拒绝的交互实现，也不存在"环境提供方缺席"或"该归两个已打开标签页中哪一个"的问题。 + +**三处翻译全都留在 `llm-pi-ai`。** `credentialStoreFrom` 把 pi-ai 的 `CredentialStore` 映射到记录；`authContextFrom` 先查凭据 seam 再查启动环境来回答 pi-ai 的环境提问，文件存在性则按宿主进程的文件系统判断；`registerPiAiFlows` 把 pi-ai 的 `AuthEvent`/`AuthPrompt` 重述为中立词汇并运行 `Models.login()`。每个集合都用前两者构造，正是这一点让已登录的提供方在配置变更导致集合重建之后仍然处于登录状态。有了行得通的姿态之后，目录不再扣留仅 OAuth 的路由，`openai-codex` 重新被提供。 + +凭据平面仍是可选的，正如它在引用解析上一贯如此。没有凭据服务时读取回答"未存储"，因为这样的组合确实不持有任何凭据；写入则指名拒绝，因为一次 grant 凭空蒸发的登录会先报告成功、再让每个请求失败。flow 注册通过 `ctx.inject` 限定在授权 seam 之下，因此 headless 或 ACP 组合挂载后没有登录能力，其余一切不变。 + +### seam 底下需要的两处机制 + +`withFileLock` 接受按调用声明的等待上限。pi-ai 在 `credentials.modify()` **内部**执行 OAuth 刷新，因此记录写入路径要跨越一次网络往返持锁；2 秒的默认值是按"渲染并 rename"的量级选的，会让该文档的每一个其他写入方失败。重试节奏保持固定——那是协议常量——而等待时长按争用方可能遇到的最长持锁方来定：refs 与 records 共享同一份文件、同一把锁，因此该文档的每一个写入方（`DOCUMENT_LOCK_WAIT_MS`，含引用写入与记录删除）都要等得起一次 OAuth 刷新，而不只是执行刷新的那个 mutation。 + +seam 的边缘与写入路径同一纪律。prompt 被拒是结果而非故障——交互实现以 `AuthorizationDeclinedError` 拒绝，尝试以 `cancelled` 结算；渲染不了 notice 的界面只丢那条 notice、绝不拖垮 flow；`authorization/settled` 按 credentials seam 的条款以遏制方式分发监听器故障。存储侧，api-key 记录在渲染前先行准入（`parseRecord` 下次启动会拒绝的，写入时就拒绝），`llm-pi-ai` 在寻址记录前先问 `isCredentialKeySegment`，任意手写路由键读作「没有存储任何东西」，而不是在解析途中抛错。 + +撤销会结算一次尝试，无论其 flow 是否响应信号。flow 本应在信号触发时停止，但不停止的那个会把键占到进程结束，而被卡住的键从外部看与忙碌中的键无法区分。被遗弃的执行体听任其自行结束。 + +## Alternatives considered + +- **把 pi-ai 的 `CredentialStore` 形状直接放进 seam。** 那是行得通且已经设计好的形状。它同时把 `api_key`/`oauth` 定为世上仅有的两种凭据类别，并以 provider id 为键，也就是上文那种所有权丢失；第二个 adapter 家族将不得不假装自己是 pi-ai 才能参与。记录联合体刻意只在两处更抽象一步——键，以及 grant 的不透明性。 +- **在 `user-questions` 旁再建一个专用登录交互 seam。** 授权提示看起来就像问题，复用 `ctx.userQuestions` 很有诱惑力。但那个 seam 是为"模型的工具调用代表 agent 暂停"而建的：它校验调用方 agent、拒绝被委派的调用方、只有一个环境 UI 提供方。授权提示没有 agent，必须抵达发起它的配置页面，还可能被浏览器回调赢得竞速后按单个提示撤下。词汇重叠，生命周期不重叠。 +- **把 `~/.codex/auth.json` 读进一个 store。** 这能让 Codex 在不做上述任何事的情况下工作，刷新也由 pi-ai 负责。它同时为了一个提供方把 harness 绑死在另一个工具的私有文件格式上，且其余所有登录仍然没有着落。 +- **让第二次 `begin()` 并入已在运行的尝试。** 比拒绝更友好，直到两个人在回答同一个 flow 的问题为止。以 entry 上的 `inFlight` 配合拒绝，界面得以禁用按钮，而不是靠报错才发现状态。 +- **把"仅 OAuth 则扣留"当安全网保留。** 它现在会藏起一个能用的提供方。该判定被删除而不是留成惰性代码；`docs/subsystems/credentials.md` 与包 README 承载了取代它的内容。 + +## Consequences + +`.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。 + +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。 + +有两项限制记在包 README 里而非就地修复。一次尝试不可持久，登录途中刷新页面会丢弃它。登出即 `deleteRecord`，它只在本地遗忘而不通知签发方；需要服务端吊销的提供方无处声明这一点。 + +## Testing + +seam 自己的套件钉住它拥有的生命周期：单飞的拒绝与释放、flow 启动前与进行中的撤销、一个忽略自身信号的 flow、提交核实，以及包含"调用方看到的是抛出错误"那种 `failed` 情形的结算事件。invariant companion 钉住"已结算的键就是空闲的键"，因为被卡住的键否则不可见。 + +`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。 diff --git a/.agents/notes/implemented/architecture/2026-08-18-client-build-environment.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-18-client-build-environment.i18n.yaml new file mode 100644 index 0000000000..b97fb2d1e8 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-18-client-build-environment.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/implemented/architecture/2026-08-18-client-build-environment.md +2026-08-18-client-build-environment.md: 45ed6c8bc68e0f08157fb56a91ae4f6165e6e431 +2026-08-18-client-build-environment.zh.md: bb9633721401f66b443a65253dcbc0241f45d328 diff --git a/.agents/notes/implemented/architecture/2026-08-18-client-build-environment.md b/.agents/notes/implemented/architecture/2026-08-18-client-build-environment.md new file mode 100644 index 0000000000..45ed6c8bc6 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-18-client-build-environment.md @@ -0,0 +1,37 @@ +# Agent Note: Build-time public environment variables for client business code + +Status: implemented + +English | [中文](2026-08-18-client-build-environment.zh.md) + +## Problem + +Browser business packages need deployment builds to select static behavior, but the Web client has two artifact paths that do not contain one another: Vite builds the static shell, while the shared tsdown preset builds dynamically loaded plugins. Replacing an environment expression in only one path would give the same business expression different results depending on its package type. + +Browsers have no Node `process`, and embedding the build process's complete environment object would expose values unrelated to the frontend. Runtime configuration also does not accurately represent a build variant because this choice must remain fixed after an artifact is published. + +## Decision + +`DSH_CLIENT_*` is the build-time namespace for values that may be exposed to browser business code. Business code may use a static property read such as `process.env.DSH_CLIENT_NAME` to select behavior. Values come only from the build process environment, not from Vite `.env*` files. Set values are inlined as strings, and unset values evaluate to `undefined`. + +The Vite config and the shared tsdown preset for dynamic client bundles use one define generator. The generator creates exact substitutions only for `DSH_CLIENT_*` and reduces all remaining `process.env` reads to an empty object. The browser receives no global `process`, dynamic-key lookup, or environment enumeration capability. + +The `DSH_CLIENT_*` prefix itself declares that a value is public. Credentials, paths, and other Host- or CI-only values must not use it. + +The root build wrapper supplies one exact public environment to both bundlers. It derives `DSH_CLIENT_COMMIT_HASH` as the seven-character prefix of the source Git HEAD for every complete build; an explicit value supports build environments without repository metadata. `pnpm run build` otherwise inherits the caller's `DSH_CLIENT_*` values, while `pnpm run build:official` selects the repository's official artifact profile without shell-specific environment syntax and sets `DSH_CLIENT_BUILD_PROFILE=official` for deployment-specific business registrations. A successful complete build writes the exact public environment and a digest covering the Vite output and every dynamic client bundle. Partial build commands do not replace that record. + +## Alternatives considered + +**Replace values only in Vite.** A dynamic plugin's `lib/client.js` is loaded as an independent script and never enters Vite's module graph, so the expression would remain in a browser that has no `process`. + +**Expose every `DSH_*` value.** Host, test, and CI variables already use that prefix and may contain credentials or local paths. The narrower `DSH_CLIENT_*` prefix makes exposure intent auditable. + +**Provide a complete `process.env` object in the browser.** This would permit build-environment enumeration and turn a Node compatibility shim into a runtime API. Exact static substitutions are sufficient for build choices. + +**Standardize on `import.meta.env`.** Dynamic plugins are emitted as independent CommonJS factories and cannot retain `import.meta`. Business code would still need two interfaces depending on the artifact path. + +## Consequences + +The Vite static shell and shared tsdown dynamic bundles receive the same string for a given `DSH_CLIENT_*` build-process variable. An unset static property read evaluates to `undefined`; non-`DSH_CLIENT_*` values cannot enter browser artifacts through this mechanism, and business code cannot enumerate the build process environment. Every complete build carries its short source revision as public display metadata. CI build gates select the official profile without exposing its public values to source tests or unrelated workflow steps. npm packing and built Web tests verify the recorded environment and current artifact digest, so a default build followed by an official pack request, a partial rebuild, or modified output fails before consumption. + +Every `DSH_CLIENT_*` value referenced by business code becomes public artifact content, so a misnamed value can disclose information. Build choices are fixed when the artifact is generated; a setting that must change after deployment requires a validated, transported, and documented runtime configuration mechanism. diff --git a/.agents/notes/implemented/architecture/2026-08-18-client-build-environment.zh.md b/.agents/notes/implemented/architecture/2026-08-18-client-build-environment.zh.md new file mode 100644 index 0000000000..bb96337214 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-18-client-build-environment.zh.md @@ -0,0 +1,37 @@ +# Agent Note: Client 业务代码使用构建期公开环境变量 + +Status: implemented + +[English](2026-08-18-client-build-environment.md) | 中文 + +## Problem + +浏览器业务包需要按部署构建选择静态行为，但 Web client 有两条互不包含的产物路径：Vite 构建静态壳，共享 tsdown preset 构建运行时加载的动态插件。只在一条路径替换环境变量会使相同业务表达式因所在包类型不同而产生不同结果。 + +浏览器没有 Node `process`，而把构建进程的完整环境对象放入产物会泄露与前端无关的值。运行时配置也不能准确表达构建变体，因为产物发布后不应再改变这类选择。 + +## Decision + +`DSH_CLIENT_*` 是可公开给浏览器业务代码的构建期命名空间。业务代码可用静态点访问 `process.env.DSH_CLIENT_NAME` 选择行为；值只取自构建进程环境，不读取 Vite `.env*` 文件。设置的值在构建时内联为字符串，未设置的值为 `undefined`。 + +Vite 配置与动态 client bundle 的共享 tsdown preset 使用同一 define 生成器。生成器只为 `DSH_CLIENT_*` 创建精确替换，并把其余 `process.env` 读取收敛到空对象；浏览器不获得全局 `process`、动态键读取或环境枚举能力。 + +`DSH_CLIENT_*` 的名称本身表示公开性。凭据、路径和其他仅供 Host 或 CI 使用的值不得使用该前缀。 + +根构建包装脚本向两个 bundler 提供同一份精确的公开环境。每次完整构建都会把源码 Git HEAD 的七位前缀派生为 `DSH_CLIENT_COMMIT_HASH`；没有仓库元数据的构建环境可显式提供该值。除此之外，`pnpm run build` 继承调用方的 `DSH_CLIENT_*` 值，`pnpm run build:official` 则不依赖特定 shell 的环境变量语法，直接选择仓库的官方产物 profile，并设置 `DSH_CLIENT_BUILD_PROFILE=official` 供部署专属业务注册使用。完整构建成功后会写入精确的公开环境，以及覆盖 Vite 输出和所有动态 client bundle 的摘要；局部构建命令不会替换该记录。 + +## Alternatives considered + +**只在 Vite 中替换。** 动态插件的 `lib/client.js` 作为独立脚本由浏览器加载，不进入 Vite 模块图，表达式会残留到无 `process` 的浏览器。 + +**公开全部 `DSH_*`。** 仓库中的 Host、测试和 CI 变量使用该前缀，其中可能包含凭据或本地路径；更窄的 `DSH_CLIENT_*` 让公开意图可审计。 + +**在浏览器提供完整 `process.env` 对象。** 这会允许枚举构建环境并把 Node 兼容垫片变成运行时 API；静态精确替换足以承载构建选择。 + +**统一改用 `import.meta.env`。** 动态插件输出为独立 CJS factory，不能保留 `import.meta`；业务代码仍会因产物路径不同而使用两套接口。 + +## Consequences + +Vite 静态壳和共享 tsdown 动态 bundle 对同一 `DSH_CLIENT_*` 构建进程变量产生相同字符串值。未设置的静态点访问得到 `undefined`，非 `DSH_CLIENT_*` 值不会通过该机制进入浏览器产物，业务代码也无法枚举构建进程环境。每次完整构建都携带可公开展示的短源码 revision。CI 构建门禁选择官方 profile，而不把其中的公开值暴露给源码测试或无关 workflow 步骤。npm 打包与 built Web 测试会校验记录中的环境及当前产物摘要，因此默认构建后请求官方打包、局部重建或修改输出都会在消费产物前失败。 + +任何被业务代码引用的 `DSH_CLIENT_*` 值都会成为公开产物内容，命名错误可能泄露信息。构建选择在产物生成时固定；需要部署后变化的设置必须使用拥有校验、传输和文档的运行时配置机制。 diff --git a/.agents/notes/implemented/architecture/2026-08-18-experimental-agent-teams-packages.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-18-experimental-agent-teams-packages.i18n.yaml index 1b56228555..9ac53a7db3 100644 --- a/.agents/notes/implemented/architecture/2026-08-18-experimental-agent-teams-packages.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-18-experimental-agent-teams-packages.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/2026-08-18-experimental-agent-teams-packages.md -2026-08-18-experimental-agent-teams-packages.md: cec73be48a5cde25fae570587d2ecd17a4a87d01 -2026-08-18-experimental-agent-teams-packages.zh.md: 71b702daa8694fddec6e2a0972704f19955cb509 +2026-08-18-experimental-agent-teams-packages.md: cfaf7b23d03a1adecf8acc18a110717a62aa9ed1 +2026-08-18-experimental-agent-teams-packages.zh.md: 1d06addff6c8f347726408d3bb02bc72374492cb diff --git a/.agents/notes/implemented/architecture/2026-08-18-experimental-agent-teams-packages.md b/.agents/notes/implemented/architecture/2026-08-18-experimental-agent-teams-packages.md index cec73be48a..cfaf7b23d0 100644 --- a/.agents/notes/implemented/architecture/2026-08-18-experimental-agent-teams-packages.md +++ b/.agents/notes/implemented/architecture/2026-08-18-experimental-agent-teams-packages.md @@ -12,9 +12,9 @@ An experimental directory without a current package previously imposed placement ## Decision -`packages/experimental/team` and `packages/experimental/tool-team` are private workspace packages. Their npm names remain `@deepseek-ai/dsh-team` and `@deepseek-ai/dsh-tool-team`, so promotion changes paths and release metadata without renaming imports. +`packages/experimental/agent-team` and `packages/experimental/tool-agent-team` are private workspace packages. The [experimental package naming decision](2026-08-19-experimental-package-name-prefix.md) owns their npm names and promotion rename; this note owns their placement, release exclusion, and dependency isolation. -The dsh release family and local baseline publisher exclude every manifest below `packages/experimental/`. Workspace constraints require each experimental package to set `private: true` and omit `publishConfig`. The same top-level check rejects `dependencies`, `optionalDependencies`, and `peerDependencies` from release packages, release apps, or the Python runtime to an experimental package. Experimental packages may depend on release packages and each other; tests may use them through `devDependencies`, and examples may load them explicitly. +The dsh pack and publish set and the local baseline publisher exclude every manifest below `packages/experimental/`. `release:dsh` still advances their manifest versions with the shared dsh version without creating release tags. Workspace constraints require each experimental package to set `private: true` and omit `publishConfig`. The same top-level check rejects `dependencies`, `optionalDependencies`, and `peerDependencies` from release packages, release apps, or the Python runtime to an experimental package. Experimental packages may depend on release packages and each other; tests may use them through `devDependencies`, and examples may load them explicitly. The generic caller-reserved continuable child identity and selective direct-child drain remain in the stable Subagent service. They own Subagent identity and Activation lifecycle without importing or naming Agent Teams; the experimental Team service consumes them in the permitted direction. @@ -28,10 +28,8 @@ Experimental status changes publication and compatibility expectations only. The **Move the Subagent prerequisites into the experimental directory.** Child identity allocation and Activation teardown belong to the Subagent owner and contain no Team-specific contract. Moving or duplicating them would invert the dependency or split one lifecycle across packages. -**Publish experimental packages under different npm names.** Experimental suffixes would make promotion rename every import and configuration row without strengthening release exclusion; private manifests and release-family filtering enforce the actual requirement. - ## Consequences Agent Teams can use the full repository graph and quality checks without entering official tarballs or becoming a supported runtime dependency. A release package cannot expose Team until the Team packages are promoted, so CLI and Web experiments use explicit example or experimental compositions instead of the shipped base bundles. -The product-role grouping is less direct while the packages incubate, and promotion creates path churn. Keeping npm names stable limits that churn to repository paths, metadata, documentation, and composition. +The product-role grouping is less direct while the packages incubate. Promotion creates path and npm-name churn as specified by the experimental package naming decision. diff --git a/.agents/notes/implemented/architecture/2026-08-18-experimental-agent-teams-packages.zh.md b/.agents/notes/implemented/architecture/2026-08-18-experimental-agent-teams-packages.zh.md index 71b702daa8..1d06addff6 100644 --- a/.agents/notes/implemented/architecture/2026-08-18-experimental-agent-teams-packages.zh.md +++ b/.agents/notes/implemented/architecture/2026-08-18-experimental-agent-teams-packages.zh.md @@ -12,9 +12,9 @@ Agent Teams 的服务与工具约定仍在变化，但它需要使用真实 Sess ## 决策 -`packages/experimental/team` 与 `packages/experimental/tool-team` 是私有 workspace 包。其 npm 名仍为 `@deepseek-ai/dsh-team` 与 `@deepseek-ai/dsh-tool-team`，因此 promotion 只需修改路径与发布元数据，无需重命名 import。 +`packages/experimental/agent-team` 与 `packages/experimental/tool-agent-team` 是私有 workspace 包。[实验性包命名决策](2026-08-19-experimental-package-name-prefix.zh.md)负责其 npm 名和 promotion 重命名；本记录负责其目录归属、发布排除与依赖隔离。 -dsh 发布系列与本地 baseline 发布器均排除 `packages/experimental/` 下的所有 manifest。workspace 约束要求每个实验性包设置 `private: true` 并省略 `publishConfig`。同一个顶层检查会拒绝发布包、发布 app 或 Python runtime 通过 `dependencies`、`optionalDependencies` 或 `peerDependencies` 依赖实验性包。实验性包可以依赖发布包和其他实验性包；测试可以通过 `devDependencies` 使用它们，示例可以显式加载它们。 +dsh pack 与 publish 集合以及本地 baseline 发布器均排除 `packages/experimental/` 下的所有 manifest。`release:dsh` 仍会让这些 manifest 跟随 dsh 共享版本递增，但不会创建发布 tag。workspace 约束要求每个实验性包设置 `private: true` 并省略 `publishConfig`。同一个顶层检查会拒绝发布包、发布 app 或 Python runtime 通过 `dependencies`、`optionalDependencies` 或 `peerDependencies` 依赖实验性包。实验性包可以依赖发布包和其他实验性包；测试可以通过 `devDependencies` 使用它们，示例可以显式加载它们。 通用的调用方预留 continuable child 身份和精确 direct-child drain 仍属于稳定 Subagent 服务。它们负责 Subagent 身份与 Activation 生命周期，不 import 或命名 Agent Teams；实验性 Team 服务沿允许的方向消费这些能力。 @@ -28,10 +28,8 @@ dsh 发布系列与本地 baseline 发布器均排除 `packages/experimental/` **把 Subagent 前置能力移入 experimental 目录。** child 身份分配与 Activation teardown 属于 Subagent owner，且不包含 Team 专用约定。移动或复制这些能力会反转依赖方向，或把同一个生命周期拆到多个包中。 -**使用不同的 npm 名发布实验性包。** experimental 后缀会让 promotion 重命名所有 import 与配置项，却不能加强发布排除；私有 manifest 与发布系列过滤已经强制执行实际要求。 - ## 后果 Agent Teams 可以使用完整仓库依赖图与质量检查，而不进入正式 tarball，也不会成为受支持的运行时依赖。在 Team 包 promotion 前，发布包不能暴露 Team，因此 CLI 和 Web 实验使用显式示例或实验性组合，而不是已发布的基础组合包。 -孵化期间的产品职责分组不够直接，promotion 也会产生路径改动。保持 npm 名稳定后，改动范围仅包括仓库路径、元数据、文档和组合。 +孵化期间的产品职责分组不够直接。promotion 会按照实验性包命名决策产生路径和 npm 名改动。 diff --git a/.agents/notes/implemented/architecture/2026-08-18-sqlite-physical-chunk-row-compression.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-18-sqlite-physical-chunk-row-compression.i18n.yaml new file mode 100644 index 0000000000..4557bc64ed --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-18-sqlite-physical-chunk-row-compression.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/implemented/architecture/2026-08-18-sqlite-physical-chunk-row-compression.md +2026-08-18-sqlite-physical-chunk-row-compression.md: e46adf26ab4ce0a495f3509977ab0835631c16a9 +2026-08-18-sqlite-physical-chunk-row-compression.zh.md: d93aa64a53effa9d456b3eba2e1681b9478c448d diff --git a/.agents/notes/implemented/architecture/2026-08-18-sqlite-physical-chunk-row-compression.md b/.agents/notes/implemented/architecture/2026-08-18-sqlite-physical-chunk-row-compression.md new file mode 100644 index 0000000000..e46adf26ab --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-18-sqlite-physical-chunk-row-compression.md @@ -0,0 +1,81 @@ +# Agent Note: SQLite physical chunk-row compression + +Status: implemented + +English | [中文](2026-08-18-sqlite-physical-chunk-row-compression.zh.md) + +## Problem + +The scalar [`session-persistence-sqlite`](../../../../packages/session/session-persistence-sqlite/README.md) layout stores one physical row per logical `SessionEvent`. Provider streams produce token-sized `assistant/chunk` events with repeated turn, step, block, type, and envelope fields, so transaction batching reduces commits without reducing row count or repeated JSON payload. The logical stream cannot be coalesced because chunk boundaries, sequence numbers, timestamps, replay, partial output, UI fidelity, and `sourceEventSeqs` remain observable. + +A physical row that represents several events affects append contiguity, crash repair, suffix seeks, schema ownership, revisions, and stale writers. Durable decoding must also be fixed by the schema version; a configurable codec set could make one schema version unreadable under a different Cordis composition. + +## Decision + +`@deepseek-ai/dsh-session-persistence-sqlite` uses the packed schema-17 implementation. It is the only SQLite persistence package and provider; the predecessor scalar layout and the temporary versioned sibling are not retained. SQLite remains an opt-in switch, while shipped default compositions continue to use JSONL. Both backends implement the same `SessionPersistence` service through `PersistenceCoordinator`, so physical packing changes neither live event delivery nor the logical session API. + +Schema 17 keeps ordinary ROWID tables and the composite `events(session_id, seq)` primary-key index. Scalar rows represent one logical event. Packed rows use the storage tags `text-chunks`, `reasoning-chunks`, and `tool-call-chunks`; the SQL `seq` and `time` columns hold the first logical member, and `data` holds the packed payload. Packed rows set `ignorable=0` as a physical discriminator and leave `source_event_seqs` and `surface_op` as `NULL`; scalar rows use `ignorable=1` only for logical ignorable events and `NULL` otherwise. A future ignorable logical event may therefore reuse a storage-tag name without being decoded as a packed row. The tags are storage vocabulary, not `SessionEventMap` members. + +SQLite owns chunk encoding and validation inside the schema-17 package. Exact-field whitelisting means unknown fields, surface metadata, incompatible chunk identity, sequence gaps, and unsafe timestamps remain scalar rather than losing information. One packed row represents at most 1,024 events and 1 MiB of uncompressed UTF-8 `data`; the encoder partitions longer runs, and the decoder rejects rows outside those format limits. + +The `data` column accepts `TEXT` or `BLOB`. Serialized values below 4 KiB remain text. At or above the threshold, the writer uses Zstandard level 3 and retains the frame only when it is smaller than the text; the reader decompresses the blob before strict UTF-8 decoding and JSON parsing. The fixed moderate level and threshold limit frame overhead and synchronous CPU work while capturing the repeated payloads that dominate retained bytes. + +`source_event_seqs` remains the complete ordered list of earlier events cited by a surface node, including every streamed chunk behind an assembled assistant message. Schema 17 stores the first sequence as an unsigned varint and every subsequent signed difference as a ZigZag varint. This preserves arbitrary order and every sequence while exploiting the overwhelmingly consecutive lists produced by streaming. An empty list is an empty non-null blob, distinct from absent provenance. + +### Transactional append packing + +Each append acquires `BEGIN IMMEDIATE`, rechecks schema ownership, selects the bounded physical span that may cover the last stored sequence, and derives the next logical sequence from that decoded tail. A mismatch rejects a stale writer before mutation. The codec packs only the new durable batch. Its inserts, lazy session materialization, and one revision increment commit or roll back together. + +Normal append never deletes or replaces an earlier event row. Fixed write-behind windows normally collect high-frequency deltas into useful runs, while sparse or explicitly flushed batches may remain scalar. This makes physical event writes proportional to newly durable batches and prevents a stable retained-row count from hiding repeated replacement of a growing JSON value. + +### Reads and repair + +Full reads decode each physical row as one all-or-nothing logical span and validate contiguous logical sequences. A reverse pass identifies the last valid `turn/end` without retaining a second decoded copy of the full physical scan; the forward pass decodes one row at a time into the required logical result. A malformed row or gap before that committed boundary is corruption; a malformed final physical row becomes the opaque repair marker at that row's base sequence. Recovery re-reads and validates that marker while holding the write lock, then deletes the whole physical row and any later rows before binding synthetic closers as scalar events. A stale repair cannot delete a newer writer's valid suffix. + +`readFrom(id, fromSeq)` examines packed predecessors only within the maximum schema-17 row span, then reads from the earliest candidate that may contain `fromSeq`. The decoder filters reconstructed members below `fromSeq`, so a suffix may begin inside a packed row without parsing an unrelated earlier scalar row. Reading from that candidate also exposes an overlapping scalar row to contiguity validation instead of letting it hide the packed member. Packed data exceeding the uncompressed format byte limit rejects before JSON parsing. + +### Schema ownership + +A pristine database initializes at schema 17. Older physical schemas, foreign application identities, non-pristine unversioned databases, and incompatible schema objects reject; the pre-release package supplies no migration. Every connection disables trusted schemas and memory-mapped I/O before inspecting durable schema, then reads both settings back. After selecting and verifying the journal mode, the provider pins `synchronous=FULL` and verifies it so SQLite build defaults cannot weaken committed-append durability. Package code loads every statement and fixed pragma from closed-name `.sql` resources and binds runtime values as parameters. + +### Physical-write regression + +The repository regression guard writes 1,000 streamed deltas in 40-event durable batches. After every committed batch it compares every retained physical field, requires cumulative inserts to equal the final row count, and rejects changed or removed rows. It also checks the exact 31-row bound, the largest persisted record against the schema byte limit, and an idle interval with no WAL extent change. These checks prove bounded row structure and catch coarse write amplification; they do not establish device traffic because WAL frames can be overwritten in place and checkpoints also write the main database. Incident-class validation separately samples process physical bytes around active and idle periods and stresses synchronized multi-process access. Lock tests hold `BEGIN IMMEDIATE` in another process and verify bounded waiting and successful continuation. + +## Alternatives considered + +**Coalesce logical chunk events.** Rejected because it changes sequence references, replay, partial output, and live delivery. Physical records provide the storage reduction while restoring the authoritative log exactly. + +**Run a periodic or post-commit compactor.** Rejected because it adds another writer lifecycle, races append and repair, changes revisions without a logical append, and adds disposal work. + +**Merge each new batch into the prior packed tail.** Rejected because a stable database and row count can hide repeated delete-and-insert churn. Paced-stream measurement found higher process and WAL writes than the predecessor scalar layout even when the retained database was smaller. Batch-local packing gives up timing-independent row convergence to bound physical writes. + +**Use `synchronous=NORMAL` with WAL.** Rejected because it permits a recent committed transaction to roll back after an operating-system crash or power loss. `append()` resolves only after its batch is durable, so the provider explicitly retains SQLite's `FULL` durability level across builds. + +**Remove ROWID from `events`.** Rejected because the composite text/integer primary key then becomes the table B-tree key and is repeated through internal pages. On the 105-session comparison corpus, selective Zstandard with ordinary ROWID used 107.02 MB; the otherwise equivalent `WITHOUT ROWID` database used 126.75 MB. + +**Set a larger SQLite page size.** Rejected because the retained-size change was negligible: 4 KiB pages used 107.08 MB and 32 KiB pages used 106.89 MB in the layout reconstruction. The larger page also increases WAL-frame and cache granularity. The provider therefore issues no `page_size` pragma. + +**Compress every payload.** Rejected because small independent Zstandard frames add headers and synchronous CPU work while losing the cross-record dictionary opportunity of a whole-file stream. On the 105-session comparison corpus, a threshold sweep produced 75.01 MB at 4 KiB, versus 93.87 MB at 16 KiB and 60.92 MB at 1 KiB. The writer fixes level 3 rather than inheriting a library default, matching the moderate level used by [Codex cold-rollout compression](https://github.com/openai/codex/blob/main/codex-rs/rollout/src/compression.rs) while retaining independent row access. + +The final frozen comparison used 105 sessions, 2,507,860 logical events, 512-event durable batches, three independent builds per backend, and three read passes per build. SQLite used 75.01 MB, wrote in 8.58 s, read complete sessions at 3.95/21.58 ms p50/p95, read 50-event tails at 0.253/0.378 ms, and forked every session in 13.10 s. Zstandard JSONL used 30.65 MB and measured 28.21 s, 4.49/23.36 ms, 10.58/80.90 ms, and 14.48 s. The predecessor scalar SQLite layout used 709.57 MB and measured 10.64 s, 9.02/69.16 ms, 0.189/0.293 ms, and 19.30 s. The packed layout is 89.4% smaller than the predecessor, writes 19.4% faster, improves complete-read p50/p95 by 56.2%/68.8%, and reduces 2,507,860 physical event rows to 65,810. Scalar tail-50 and list micro-latency are lower, but the packed provider remains materially faster than JSONL on those paths and wins the dominant size, write, full-read, and fork costs. The 4 KiB threshold is the accepted balance rather than a strict dominance claim. + +**Store packed payloads under the logical `assistant/chunk` type.** Rejected because payload heuristics make malformed rows ambiguous and couple physical decoding to future logical payload fields. Explicit tags fail loudly. + +**Store `SessionHeader` fields in an extensible metadata blob.** Rejected for schema 17 because `agentPreset` is a typed core resume invariant shared by JSONL and SQLite, not provider extension metadata. Persisting validated core fields directly keeps both backends aligned; an untyped catch-all would add another compatibility mechanism without a current producer. Revisit this only with a core-owned, namespaced `SessionHeader` extension protocol implemented by every backend. + +**Expose compression rules through configuration or a live registry.** Rejected because same-version databases must be readable independently of runtime topology. The codec is modular source code, but the durable rule set is fixed by schema version. + +**Migrate older schemas in place.** Rejected under the pre-release policy. Changing strict column types requires rebuilding the event table, which turns the first append into an unbounded historical rewrite and temporarily duplicates storage. A new database keeps activation explicit and failure predictable. + +**Store forked history as a parent reference.** Deferred because it changes independent-session persistence rather than physical row encoding. Codex uses referenced history and excludes referenced or pointer-bearing rollouts from cold compression, but this provider would first need explicit parent retention, deletion, repair, export, and cross-backend semantics. Copying remains the bounded local choice until the session service owns those rules. + +**Keep the packed implementation as a versioned sibling.** Rejected because the pre-release repository has no compatibility promise for the scalar format, while two SQLite package names duplicate configuration, documentation, tests, and ownership. Historical benchmark artifacts retain the comparison without exposing a rollback provider. + +## Consequences + +The canonical SQLite provider preserves every logical persistence, replay, revision, crash-recovery, and model-facing behavior. High-frequency batches use fewer rows and fewer measured process disk-written bytes than the predecessor in paced-stream validation; idle samples add no measured writes. Packing ratio depends on durable batch boundaries, but previously committed rows are immutable outside explicit crash repair. + +The cost is no migration from older pre-release SQLite schemas and timing-dependent physical row count. SQLite and Zstandard remain synchronous: each connection uses the configured `busyTimeoutMs` for a competing lock and blocks its JavaScript thread during that wait, while large row encoding and decoding also run on that thread. A cold open yields after an immediate `SQLITE_BUSY` journal-mode transition and starts no further attempt after an open-relative retry cutoff; an in-progress synchronous call may finish later. External SQL tooling must use the provider decoder rather than assuming every physical `events.type` is a logical event type or every payload column is text. + +The [JSONL packed-row decision](2026-07-26-packed-chunk-rows-by-default.md), [bounded persistence batching](2026-08-08-bounded-session-persistence-write-batching.md), and original [session-persistence decision](2026-06-14-session-persistence.md) remain active: they respectively own the JSONL format, write scheduling, and backend-neutral service semantics. diff --git a/.agents/notes/implemented/architecture/2026-08-18-sqlite-physical-chunk-row-compression.zh.md b/.agents/notes/implemented/architecture/2026-08-18-sqlite-physical-chunk-row-compression.zh.md new file mode 100644 index 0000000000..d93aa64a53 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-18-sqlite-physical-chunk-row-compression.zh.md @@ -0,0 +1,81 @@ +# Agent Note: SQLite 物理分片行压缩 + +Status: implemented + +[English](2026-08-18-sqlite-physical-chunk-row-compression.md) | 中文 + +## 问题 + +标量 [`session-persistence-sqlite`](../../../../packages/session/session-persistence-sqlite/README.zh.md) 后端为每个逻辑 `SessionEvent` 存储一个物理行。提供方流会生成 token 大小的 `assistant/chunk` 事件，并重复轮次、步骤、块、类型和 envelope 字段，因此事务批处理可以减少提交次数，却不能减少行数或重复 JSON payload。逻辑流不能合并，因为分片边界、序列号、时间戳、回放、部分输出、UI 保真度和 `sourceEventSeqs` 仍然可观察。 + +一个表示多个事件的物理行会影响追加连续性、崩溃修复、后缀定位、schema 所有权、revision 和陈旧写入方。持久解码规则还必须由包版本固定；可配置 codec 集可能导致同一 schema 版本在不同 Cordis 组合下无法读取。 + +## 决策 + +`@deepseek-ai/dsh-session-persistence-sqlite` 使用打包后的 schema 17 实现。它是唯一的 SQLite 持久化包和提供方；仓库不保留此前的标量布局与临时版本化同级包。SQLite 仍是可选开关，随产品交付的默认组合继续使用 JSONL。两个后端都通过 `PersistenceCoordinator` 实现同一 `SessionPersistence` 服务，因此物理打包既不改变实时事件投递，也不改变逻辑会话 API。 + +Schema 17 保留普通 ROWID 表以及复合主键索引 `events(session_id, seq)`。标量行表示一个逻辑事件。打包行使用存储标签 `text-chunks`、`reasoning-chunks` 与 `tool-call-chunks`；SQL 的 `seq` 和 `time` 列保存第一个逻辑成员，`data` 保存打包 payload。打包行把 `ignorable=0` 用作物理判别值，并让 `source_event_seqs` 与 `surface_op` 保持 `NULL`；标量行仅在逻辑事件可忽略时使用 `ignorable=1`，否则使用 `NULL`。因此，未来的可忽略逻辑事件即使复用了某个存储标签名称，也不会被解码为打包行。这些标签属于存储词汇，而不是 `SessionEventMap` 成员。 + +SQLite 在 schema 17 包内拥有分片编码和验证。字段完全匹配的白名单意味着未知字段、surface 元数据、不兼容的分片身份、序列缺口和不安全时间戳仍保持标量表示，不会丢失信息。一个打包行最多表示 1,024 个事件和 1 MiB 未压缩 UTF-8 `data`；编码器会分割更长的连续段，解码器则拒绝超出这些格式上限的行。 + +`data` 列接受 `TEXT` 或 `BLOB`。序列化值小于 4 KiB 时保持为文本。达到或超过该阈值时，写入方使用 Zstandard level 3，并且只在 frame 小于原文本时保留该 frame；读取方会先解压，再进行严格 UTF-8 解码和 JSON 解析。固定的适中级别与阈值限制 frame 开销与同步 CPU 工作，同时覆盖占据大部分保留字节的重复 payload。 + +`source_event_seqs` 是 surface 节点引用的早期事件的完整有序列表，包括组装后的 assistant 消息背后的每个流式分片。Schema 17 把第一个序列存为无符号 varint，把后续每个有符号差值存为 ZigZag varint。这样既能保留任意顺序和每个序列，又能利用流式处理所产生的绝大多数连续列表。空列表表示为空的非 `NULL` blob，与不存在来源区分开来。 + +### 事务化追加打包 + +每次追加会获取 `BEGIN IMMEDIATE`、重新检查 schema 所有权、选择可能覆盖最后存储序列的有界物理范围，并根据解码后的尾部推导下一逻辑序列。若不匹配，系统会在变更前拒绝陈旧写入方。Codec 只打包新的持久批次；其插入、会话惰性物化和一次 revision 递增会一起提交或回滚。 + +普通追加绝不删除或替换既有事件行。固定写后缓冲窗口通常会把高频 delta 收集成有效连续段，而稀疏或显式 flush 的批次可能保持标量形式。这样，物理事件写入量与新增持久批次成正比，稳定的保留行数无法再掩盖对不断增长 JSON 值的反复替换。 + +### 读取与修复 + +完整读取把每个物理行解码为全有或全无的逻辑范围，并验证逻辑序列连续。反向扫描会定位最后一个有效 `turn/end`，但不会保留完整物理扫描的第二份解码副本；正向扫描则逐行解码并写入必需的逻辑结果。在该已提交边界之前出现的畸形行或缺口属于损坏；畸形最终物理行则以该行的起始序列作为不透明修复标记。恢复会在持有写锁时重新读取并验证该 marker，再删除整个物理行及其后所有行，然后把合成 closers 绑定为标量事件。陈旧修复无法删除较新写入方的有效后缀。 + +`readFrom(id, fromSeq)` 只检查 schema 17 最大行跨度内的打包前驱，再从可能包含 `fromSeq` 的最早候选项开始读取。解码器会过滤重建后序列小于 `fromSeq` 的成员，因此后缀可以从打包行内部开始，而无需解析无关的更早标量行。从该候选项开始读取，还会让连续性验证看到相互重叠的标量行，而不是让它隐藏打包成员。打包数据超出未压缩格式字节上限时，会在解析 JSON 前拒绝。 + +### Schema 所有权 + +全新数据库初始化为 schema 17。旧物理 schema、外部 application identity、非空未版本化数据库以及不兼容 schema 对象都会被拒绝；该预发布提供方不提供迁移。每个连接都会在检查持久 schema 前禁用可信 schema 和内存映射 I/O，然后读回这两项设置。选择并验证 journal mode 后，提供方会把 `synchronous` 固定为 `FULL` 并验证该设置，避免 SQLite 构建默认值削弱已提交追加的持久性。包代码通过封闭名称的 `.sql` 资源加载每条语句和固定 pragma，并把运行时值作为参数绑定。 + +### 物理写入回归 + +仓库回归守卫以 40 个事件为持久批次写入 1,000 个流式 delta。它会在每个批次提交后比较所有保留物理字段，要求累计插入数等于最终行数，并拒绝发生变化或被移除的行。它还会检查精确的 31 行上限、最大持久记录不超过 schema 字节上限，并观察空闲区间内 WAL 范围不再变化。这些检查证明行结构有界并捕获粗粒度写放大；它们不能证明设备写流量，因为 WAL 帧可在原位覆写，检查点还会写入主数据库。事故级验证另行采样活动期和空闲期前后的进程物理写入字节，并对同步多进程访问进行压力测试。锁测试在另一个进程中持有 `BEGIN IMMEDIATE`，验证有界等待及之后成功继续。 + +## 考虑过的替代方案 + +**合并逻辑分片事件。** 不予采用，因为它会改变序列引用、回放、部分输出和实时投递。物理记录可以在准确恢复权威日志的同时获得存储缩减。 + +**运行周期性或提交后压缩器。** 不予采用，因为它会增加另一个写入方生命周期，与追加和修复竞争，在没有逻辑追加的情况下改变 revision，并增加资源释放工作。 + +**把每个新批次合并进已有打包尾部。** 不予采用，因为稳定的数据库与行数可能掩盖反复删除和插入产生的写入流量。节奏化流测量表明，即使保留数据库更小，该方案写入的进程字节与 WAL 字节仍高于此前的标量布局。逐批打包放弃与时序无关的行收敛，以换取有界物理写入。 + +**在 WAL 模式下使用 `synchronous=NORMAL`。** 不予采用，因为操作系统崩溃或断电后，最近提交的事务可能回滚。`append()` 只会在批次持久化后返回，因此提供方会在不同 SQLite 构建中显式保留 `FULL` 持久性级别。 + +**从 `events` 移除 ROWID。** 不予采用，因为复合文本／整数主键随后会成为表 B-tree 的键，并在内部页中重复。在 105 个会话的对比语料上，使用普通 ROWID 的选择性 Zstandard 数据库为 107.02 MB；其余条件相同的 `WITHOUT ROWID` 数据库为 126.75 MB。 + +**设置更大的 SQLite page size。** 不予采用，因为保留体积变化可以忽略：在独立的 page-size 布局重建中，4 KiB page 使用 107.08 MB，32 KiB page 使用 106.89 MB。更大的 page 还会增大 WAL frame 和 cache 粒度。因此提供方不设置 `page_size` pragma。 + +**压缩每个 payload。** 不予采用，因为小型独立 Zstandard frame 会增加 header 和同步 CPU 工作，也无法利用整文件流的跨记录字典。在 105 个会话的对比语料上，阈值扫描结果为：4 KiB 生成 75.01 MB，16 KiB 为 93.87 MB，1 KiB 为 60.92 MB。写入方固定使用 level 3，而不是继承库默认值；这与 [Codex 冷 rollout 压缩](https://github.com/openai/codex/blob/main/codex-rs/rollout/src/compression.rs)所用的适中级别一致，同时保留独立行访问。 + +最终冻结对比包含 105 个会话、2,507,860 个逻辑事件，以 512 个事件为持久批次；每个后端独立构建三次，每次构建执行三轮读取。SQLite 使用 75.01 MB，写入耗时 8.58 秒，完整读取 p50/p95 为 3.95/21.58 毫秒，读取最后 50 个事件为 0.253/0.378 毫秒，对所有会话执行 fork 为 13.10 秒。Zstandard JSONL 使用 30.65 MB，对应指标为 28.21 秒、4.49/23.36 毫秒、10.58/80.90 毫秒和 14.48 秒。此前的标量 SQLite 布局使用 709.57 MB，对应指标为 10.64 秒、9.02/69.16 毫秒、0.189/0.293 毫秒和 19.30 秒。打包布局比此前布局小 89.4%，写入快 19.4%，完整读取 p50/p95 改善 56.2%/68.8%，并把 2,507,860 个物理事件行减少到 65,810 行。标量布局的最后 50 个事件读取与 list 微延迟更低，但打包提供方在这些路径上仍明显快于 JSONL，并改善主要的空间、写入、完整读取和 fork 成本。4 KiB 阈值是接受的平衡点，而不是严格支配所有指标的结论。 + +**把打包 payload 存在逻辑 `assistant/chunk` 类型下。** 不予采用，因为 payload 启发式判断会使畸形行产生歧义，并把物理解码耦合到未来逻辑 payload 字段。显式标签会明确失败。 + +**把 `SessionHeader` 字段存入可扩展元数据 blob。** Schema 17 不采用该方案，因为 `agentPreset` 是 JSONL 与 SQLite 共同使用的强类型核心恢复不变量，而不是提供方扩展元数据。直接持久化已校验的核心字段可使两个后端保持一致；在没有当前生产方的情况下加入无类型兜底字段，只会增加另一套兼容机制。只有核心层定义由所有后端实现、带命名空间的 `SessionHeader` 扩展协议后，才应重新考虑该方案。 + +**通过配置或实时注册表暴露压缩规则。** 不予采用，因为同一版本数据库必须能独立于运行时拓扑被读取。Codec 在源码层保持模块化，但持久规则集由 schema 版本固定。 + +**原地迁移旧 schema。** 预发布策略不采用此方案。改变 strict 列类型需要重建事件表，这会把第一次追加变成无界的历史改写，并暂时复制存储。使用新数据库可让启用行为明确、失败方式可预测。 + +**把 fork 历史存为父级引用。** 延期处理，因为它改变的是独立会话持久化语义，而不是物理行编码。Codex 使用引用历史，并避免对被引用或带指针的 rollout 做冷压缩；但该提供方首先需要明确父级保留、删除、修复、导出和跨后端语义。在会话服务拥有这些规则之前，复制仍是有界的本地选择。 + +**把打包实现保留为版本化同级包。** 不予采用，因为预发布仓库不承诺兼容此前的标量格式，而两个 SQLite 包名会重复配置、文档、测试和所有权。历史 benchmark 产物保留对比，无需暴露回滚提供方。 + +## 后果 + +标准 SQLite 提供方保留每一项逻辑持久化、回放、revision、崩溃恢复和模型可见行为。在节奏流验证中，高频批次使用的行数和测得的进程磁盘写入字节少于此前布局；空闲样本没有新增测得写入。打包率取决于持久批次边界，但除显式崩溃修复外，已经提交的行保持不可变。 + +代价是不迁移旧的预发布 SQLite schema，以及取决于时序的物理行数。SQLite 与 Zstandard 都是同步操作：每个连接以配置的 `busyTimeoutMs` 等待竞争锁，该等待期间会阻塞其 JavaScript 线程，大型行的编码与解码也在该线程上执行。冷打开会在 journal-mode 切换立即返回 `SQLITE_BUSY` 后让出执行，并在从打开时计算的重试截止点后不再发起新尝试；正在执行的同步调用可能更晚才完成。外部 SQL 工具必须使用提供方解码器，而不能假定每个物理 `events.type` 都是逻辑事件类型或每个 payload 列都是文本。 + +[JSONL 打包行决策](2026-07-26-packed-chunk-rows-by-default.zh.md)、[有界持久化批处理](2026-08-08-bounded-session-persistence-write-batching.zh.md)和原始[会话持久化决策](2026-06-14-session-persistence.zh.md)继续保持 active：它们分别负责 JSONL 格式、写入调度以及后端无关的服务语义。 diff --git a/.agents/notes/implemented/architecture/2026-08-19-experimental-package-name-prefix.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-19-experimental-package-name-prefix.i18n.yaml new file mode 100644 index 0000000000..e25d832371 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-19-experimental-package-name-prefix.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/implemented/architecture/2026-08-19-experimental-package-name-prefix.md +2026-08-19-experimental-package-name-prefix.md: 3420fa20a0dd9519af5684142fc8f3e70f2ed779 +2026-08-19-experimental-package-name-prefix.zh.md: b7e7d073157eab272baed4ffb75f987a685f53d7 diff --git a/.agents/notes/implemented/architecture/2026-08-19-experimental-package-name-prefix.md b/.agents/notes/implemented/architecture/2026-08-19-experimental-package-name-prefix.md new file mode 100644 index 0000000000..3420fa20a0 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-19-experimental-package-name-prefix.md @@ -0,0 +1,29 @@ +# Agent Note: Mark experimental packages in npm names + +Status: implemented + +English | [中文](2026-08-19-experimental-package-name-prefix.zh.md) + +## Problem + +Directory placement, private manifests, and release-family filtering keep experimental packages out of releases, but an npm specifier or Cordis configuration row does not expose that status. A stable-looking package name can be copied into another composition without the reader seeing that its complete public contract remains experimental. + +## Decision + +Every package directly below `packages/experimental/` uses the `@deepseek-ai/dsh-experimental-*` npm prefix. The workspace constraints gate discovers those manifests and rejects a missing prefix alongside the existing `private: true` and omitted-`publishConfig` requirements. + +Agent Teams uses `@deepseek-ai/dsh-experimental-agent-team` from `packages/experimental/agent-team` and `@deepseek-ai/dsh-experimental-tool-agent-team` from `packages/experimental/tool-agent-team`. Package imports, Cordis configuration rows, generated catalogs, and repository metadata use those names without compatibility aliases. + +Promotion moves a package to its product-role group, removes `experimental-` from its npm name, and updates every repository reference atomically. The pre-release compatibility policy permits that rename without an alias package. + +## Alternatives considered + +**Keep stable-looking npm names while using only directory and release metadata for experimental status.** This minimizes promotion churn, but import specifiers and configuration rows hide the package status and cannot carry the repository-only placement rule into review. + +**Use an experimental suffix.** A prefix groups every experimental package under one searchable npm namespace and makes the status visible before the product role; a suffix would scatter that marker after role-specific names. + +## Consequences + +Experimental imports and configuration rows identify their support status without consulting repository layout. The top-level constraints command and its focused unit test prevent a newly added experimental package from omitting the prefix. + +Promotion deliberately renames imports, configuration, generated references, and metadata. No compatibility package preserves the experimental name. diff --git a/.agents/notes/implemented/architecture/2026-08-19-experimental-package-name-prefix.zh.md b/.agents/notes/implemented/architecture/2026-08-19-experimental-package-name-prefix.zh.md new file mode 100644 index 0000000000..b7e7d07315 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-19-experimental-package-name-prefix.zh.md @@ -0,0 +1,29 @@ +# Agent Note: 在 npm 名中标记实验性包 + +Status: implemented + +[English](2026-08-19-experimental-package-name-prefix.md) | 中文 + +## 问题 + +目录归属、私有 manifest 与发布系列过滤可以阻止实验性包进入发布，但 npm specifier 或 Cordis 配置项无法体现该状态。外观稳定的包名可能被复制到其他组合中，而读者看不出其完整公开约定仍处于实验阶段。 + +## 决策 + +`packages/experimental/` 直属的每个包都使用 `@deepseek-ai/dsh-experimental-*` npm 前缀。workspace constraints 门禁会发现这些 manifest，并在现有 `private: true` 与省略 `publishConfig` 要求之外拒绝缺少该前缀的包。 + +Agent Teams 使用位于 `packages/experimental/agent-team` 的 `@deepseek-ai/dsh-experimental-agent-team`，以及位于 `packages/experimental/tool-agent-team` 的 `@deepseek-ai/dsh-experimental-tool-agent-team`。包 import、Cordis 配置项、生成目录和仓库元数据直接使用这些名称，不提供兼容别名。 + +promotion 会把包移至其产品职责组、从 npm 名中移除 `experimental-`，并原子更新全部仓库引用。预发布兼容策略允许该重命名不提供别名包。 + +## 曾考虑的替代方案 + +**保留外观稳定的 npm 名，仅通过目录和发布元数据表达实验状态。** 这种方式可以减少 promotion 改动，但 import specifier 与配置项会隐藏包状态，也无法在评审中携带仅存在于仓库内的目录规则。 + +**使用 experimental 后缀。** 前缀会把所有实验性包归入一个可搜索的 npm 命名空间，并在产品职责之前显示状态；后缀会把该标记分散在各个职责名称之后。 + +## 后果 + +实验性 import 与配置项无需查阅仓库布局即可表明其支持状态。顶层 constraints 命令及其聚焦单元测试会阻止新实验性包遗漏该前缀。 + +promotion 会明确重命名 import、配置、生成引用与元数据。不会有兼容包保留实验名称。 diff --git a/.agents/notes/implemented/architecture/2026-08-19-session-projection-state-and-client-views.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-19-session-projection-state-and-client-views.i18n.yaml new file mode 100644 index 0000000000..98c731e584 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-19-session-projection-state-and-client-views.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/implemented/architecture/2026-08-19-session-projection-state-and-client-views.md +2026-08-19-session-projection-state-and-client-views.md: 14da0525b2cc838ff496d5902dd66ae6ab456af4 +2026-08-19-session-projection-state-and-client-views.zh.md: 3b1ed72bf240ebf43924826d42226ff301ad8fca diff --git a/.agents/notes/implemented/architecture/2026-08-19-session-projection-state-and-client-views.md b/.agents/notes/implemented/architecture/2026-08-19-session-projection-state-and-client-views.md new file mode 100644 index 0000000000..14da0525b2 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-19-session-projection-state-and-client-views.md @@ -0,0 +1,28 @@ +# Agent Note: Separate session projection state from client views + +Status: implemented + +English | [中文](2026-08-19-session-projection-state-and-client-views.zh.md) + +## Problem + +The projection registry persisted each unit's internal fold state without a runtime schema, while `SessionProjectionMap` described the client value returned by `view`. This left restored state unvalidated and made the same type table appear to describe two values that may differ. Host consumers also needed the current folded state without serializing every registered client view or exposing internal-only state through the client protocol. + +## Decision + +`SessionProjectionStateMap` is the merge-extensible table for host fold states. Every `ProjectionDefinition` key belongs to this table and supplies a `stateSchema`; cached rows are validated before they seed a fold. `SessionProjectionMap` retains its existing meaning and name as the sole table of client-visible whole values, preserving existing client data structures such as `title: string | null`. + +A unit whose key also appears in `SessionProjectionMap` supplies `wire.viewSchema` and `wire.view`. Every unit's state is checkpointed — client-visible and host-only alike; the `persist` opt-in is gone, so no unit can silently skip the durable cache. Snapshot APIs return only `SessionProjectionMap`, so internal states cannot enter API payloads. Host code reads one current state through `stateOf(session, key)`; the returned reference is borrowed and must not be mutated. + +## Consequences + +Projection state and client values are independently typed and validated without introducing a second client DTO vocabulary. A unit may expose a compact or compatibility-preserving client value while retaining richer host state. Malformed cached state cannot seed `viewCheckpoint`; restore rejects malformed state and the cache's existing full-read fallback rebuilds it from the log. Host consumers can replace private log scans with the same incremental fold used by carriers. + +The original [session-projection proposal](../../proposed/architecture/2026-07-27-session-projection-and-command-log.md) now records this split. The earlier [subagent identity projection](2026-08-06-subagent-list-identity-projection.md) and [projected token usage](2026-07-29-projected-token-usage-and-request-context.md) decisions remain current; their domain folds move to the state table without changing their user-facing values. + +## Alternatives considered + +- **Rename the existing map to a state table and introduce a new client map** — rejected because it changes the established client type name and invites unnecessary client payload migrations. +- **Keep one table for both state and client values** — rejected because a richer fold state and a compatibility-preserving client value then cannot be represented accurately. +- **Opt-in persistence for host-only units** — rejected: a `persist` flag lets a unit silently skip the durable cache, and the savings (one small row per session) never justify the asymmetry or the stateVersion confusion it invites. Every unit's state is checkpointed uniformly. +- **Return copied state from `stateOf`** — rejected because cloning every host read adds work without protecting a boundary; the method documents a readonly borrowed-reference obligation for typed same-process callers. diff --git a/.agents/notes/implemented/architecture/2026-08-19-session-projection-state-and-client-views.zh.md b/.agents/notes/implemented/architecture/2026-08-19-session-projection-state-and-client-views.zh.md new file mode 100644 index 0000000000..3b1ed72bf2 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-19-session-projection-state-and-client-views.zh.md @@ -0,0 +1,28 @@ +# Agent Note：拆分会话投影状态与客户端视图 + +状态：已实现 + +[English](2026-08-19-session-projection-state-and-client-views.md) | 中文 + +## 问题 + +投影注册表会持久化各单元的内部折叠状态，却没有运行时 schema；与此同时，`SessionProjectionMap` 描述的是 `view` 返回的客户端值。这使恢复出的状态未经校验，也让同一张类型表看似同时描述两种可能不同的值。host 消费方还需要读取当前折叠状态，但不应为此序列化全部已注册客户端视图，也不应把内部状态暴露到客户端协议。 + +## 决策 + +`SessionProjectionStateMap` 是 host 折叠状态的 merge-extensible 类型表。每个 `ProjectionDefinition` key 都属于此表并提供 `stateSchema`；缓存行只有通过校验后才能为折叠提供初始状态。`SessionProjectionMap` 保留原有名称和语义，继续作为唯一的客户端可见全量值类型表，因此 `title: string | null` 等既有客户端数据结构保持不变。 + +如果一个单元的 key 也存在于 `SessionProjectionMap`，该单元就提供 `wire.viewSchema` 与 `wire.view`。每个单元的状态都会写入检查点——client-visible 与 host-only 一视同仁；`persist` 选择项已移除，任何单元都不能悄悄跳过持久化缓存。快照 API 只返回 `SessionProjectionMap`，因此内部状态不会进入 API 载荷。host 代码通过 `stateOf(session, key)` 读取一份当前状态；返回的是借用引用，不得修改。 + +## 结果 + +投影状态和客户端值分别获得类型与校验，同时不引入第二套客户端 DTO 词汇。单元可以保留更丰富的 host 状态，并暴露紧凑或兼容既有结构的客户端值。畸形缓存状态不能为 `viewCheckpoint` 提供数据；恢复会拒绝畸形状态，并由缓存既有的全量读取回退从日志重建。host 消费方可以用同一套增量折叠替换私有日志扫描。 + +原始 [session-projection 提案](../../proposed/architecture/2026-07-27-session-projection-and-command-log.zh.md)已记录这次拆分。既有的 [subagent 身份投影](2026-08-06-subagent-list-identity-projection.zh.md)与[投影化 token 用量](2026-07-29-projected-token-usage-and-request-context.zh.md)决策仍然有效；其中的领域折叠迁入状态表，不改变面向用户的值。 + +## 考虑过的替代方案 + +- **把既有类型表改名为状态表，再引入新的客户端类型表**——不予采用，因为这会改变已经确立的客户端类型名称，并导致不必要的客户端载荷迁移。 +- **继续用一张类型表同时描述状态与客户端值**——不予采用，因为这样无法准确表达更丰富的折叠状态和保持兼容的客户端值。 +- **host-only 单元按需选择持久化**——不予采用：`persist` 标志会让单元悄悄跳过持久化缓存，而省下的（每会话一行小记录）永远不值得这种不对称或它带来的 stateVersion 困惑。每个单元的状态统一写入检查点。 +- **让 `stateOf` 返回状态副本**——不予采用，因为每次 host 读取都克隆会增加工作，却没有保护任何边界；该方法为同进程类型化调用方明确规定只读借用引用义务。 diff --git a/.agents/notes/implemented/architecture/2026-08-19-web-index-injection-table.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-19-web-index-injection-table.i18n.yaml new file mode 100644 index 0000000000..90d1f96dff --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-19-web-index-injection-table.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/implemented/architecture/2026-08-19-web-index-injection-table.md +2026-08-19-web-index-injection-table.md: 9ed02aa94cd318d107a32802d8723652e6b10ea2 +2026-08-19-web-index-injection-table.zh.md: 8ad036766faa14071b20da12ef907ab012cae23f diff --git a/.agents/notes/implemented/architecture/2026-08-19-web-index-injection-table.md b/.agents/notes/implemented/architecture/2026-08-19-web-index-injection-table.md new file mode 100644 index 0000000000..9ed02aa94c --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-19-web-index-injection-table.md @@ -0,0 +1,30 @@ +# Agent Note: structured index injection table (webserver/index-inject) + +Status: implemented + +English | [中文](2026-08-19-web-index-injection-table.zh.md) + +## Problem + +The web shell's boot HTML needs three kinds of injection: client-modules' boot protocol (the `__ModuleLoader__` registration queue inline script, the parser-blocking preload `` +})()` const preload = PARSER_PRELOAD_IDS.map(id => graph.entries.find(entry => entry.id === id)) .filter((entry): entry is WebBootEntry => entry !== undefined) - .map(entry => ``) - .join('') - const script = `${queue}${preload}` - const head = html.indexOf('') - if (head !== -1) return `${html.slice(0, head + 6)}${script}${html.slice(head + 6)}` - // Headless fixture pages may lack ; prepending keeps the read-before-shell ordering. - return `${script}${html}` + .map((entry): IndexInjection => ({ kind: 'script-src', placement: 'head', src: entry.url })) + return [ + { kind: 'script', placement: 'head', text: queue }, + ...preload, + { kind: 'global', name: '__DSH_BOOT__', value: graph }, + ] } /** * The web plugin table service: incremental `dsh.client` scan + wire composition - * + bundle route + index tap. Construction runs the activation scan + * + bundle route + index injection rows. Construction runs the activation scan * synchronously — a malformed declaration or missing bundle among the * already-loaded entries aggregates into one loud throw (FAILED fiber; the * boot activation audit reports it). @@ -353,10 +340,9 @@ export class ClientModuleRegistry extends Service { () => ctx.webServer.register({ kind: 'prefix', path: '/plugins', handler: this.serveBundle }), 'client-modules: bundle route', ) - ctx.effect( - () => ctx.webServer.tapIndex(html => injectBootManifest(html, this.composed)), - 'client-modules: boot manifest injection', - ) + ctx.on('webserver/index-inject', (table) => { + table.push(...bootInjections(this.composed)) + }) } /** diff --git a/packages/client/modules/tests/node-half.client.spec.ts b/packages/client/modules/tests/node-half.client.spec.ts index 0dc6ea0e3c..8577d2a57d 100644 --- a/packages/client/modules/tests/node-half.client.spec.ts +++ b/packages/client/modules/tests/node-half.client.spec.ts @@ -8,9 +8,9 @@ import { pathToFileURL } from 'node:url' import { runInNewContext } from 'node:vm' import { Context } from '@deepseek-ai/cordis' import { afterEach, describe, expect, it } from 'vitest' -import type { WebServer, WebRoute } from '@deepseek-ai/dsh-host-webserver' +import { renderIndexInjections, type WebServer, type WebRoute } from '@deepseek-ai/dsh-host-webserver' import * as modulesClient from '../src/client/index.ts' -import { ClientModuleRegistry, injectBootManifest, orderByModuleGraph } from '../src/index.ts' +import { ClientModuleRegistry, bootInjections, orderByModuleGraph } from '../src/index.ts' import type { ClientModuleLoaderTarget, WebBootEntry, WebBootGraph } from '../src/client/index.ts' const MODULES_ID = '@deepseek-ai/dsh-client-modules' @@ -81,9 +81,12 @@ function construct(packageNames: string[]): ClientModuleRegistry { return constructWithRoute(packageNames).service } -/** Execute the exact first inline script emitted by the Host HTML transform. */ +/** Execute the exact first inline script emitted by the Host boot rows. */ function injectedFacade(graph: WebBootGraph): { html: string; target: ClientModuleLoaderTarget } { - const html = injectBootManifest('', graph) + const html = renderIndexInjections( + '', + bootInjections(graph), + ) const source = /') const runtimeAt = html.indexOf('') - const graphAt = html.indexOf('window.__DSH_BOOT__ = ') + const graphAt = html.indexOf('globalThis["__DSH_BOOT__"] = ') const entryAt = html.indexOf('') expect([facadeAt, modulesAt, runtimeAt, graphAt, entryAt]).toEqual([...new Set([ facadeAt, modulesAt, runtimeAt, graphAt, entryAt, diff --git a/packages/client/runtime/README.i18n.yaml b/packages/client/runtime/README.i18n.yaml index cfc56e5efa..9697603704 100644 --- a/packages/client/runtime/README.i18n.yaml +++ b/packages/client/runtime/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 packages/client/runtime/README.md -README.md: cad8a08f015a7115ebff76cfce4d3ab5eb7a175e -README.zh.md: 746e5a55958e15fe73c7e14bc043b5d002f07aa2 +README.md: eae49163c14f122a3603bcaa8a61aaac7a9a7270 +README.zh.md: f8966c3aa1a5749b4c222d0ce3ea3dee7205d061 diff --git a/packages/client/runtime/README.md b/packages/client/runtime/README.md index cad8a08f01..eae49163c1 100644 --- a/packages/client/runtime/README.md +++ b/packages/client/runtime/README.md @@ -26,6 +26,8 @@ Workspace and Session lists have independent monotone `pending` → `ready` base SlotRegistry gives the renderer separate bare observables for `useSessions` and `useWorkspaces`; ui-renderer creates the hooks. Workspace business state does not enter `SessionListState` or an entry store. +`abbreviateHomePath` is the display-only POSIX home abbreviation used by Web Workspace hover cards and Tool summaries; a Windows drive or UNC path stays verbatim, and a missing, empty, or filesystem-root home leaves the path unchanged. + `indexSubagentDescendants()` derives per-parent total and running descendant counts from the retained list mirror. It follows only uninterrupted `origin: 'subagent'` ancestry, so an ordinary fork starts a separate ownership subtree; cycles stop without throwing, and a missing parent remains a harmless key until its summary arrives. `SessionListState.jobsBySession` mirrors the Host's `session/jobs` frames last-wins, keyed by session and needing no Session instance. An emptied set is stored as an absent key, so absence and `[]` are one representation and consumers never test a sentinel. Two clears keep it from outliving its truth: `session/subscribed` drops the session's mirror, because a fresh generation sends a baseline only for a non-empty set and a retained list would survive as a phantom, and `host/session-removed` drops it again, because owner disposal removed the records on the mux stream while the removal frame rides the host stream, leaving the two with no relative order. @@ -54,7 +56,7 @@ The Chat builder keeps one mutable keyed store per Session. Content updates noti ## Trajectory request data -Trajectory Definitions assemble one chronological, purpose-discriminated provider-request stream. Assistant requests always carry their numeric `turn` and `step`; compaction requests carry `step: 0` and a `turn` owner that may be `null`. That null owner means a manual compaction ran standalone between turns, not that it belongs to either adjacent turn. A `session/end-seed` boundary closes an unmatched compaction request as an error at the boundary time with `Compaction was interrupted before completion.`; a later start projects as an independent request instead of overwriting the orphan. +Trajectory Definitions assemble one chronological, purpose-discriminated provider-request stream. Assistant requests always carry their numeric `turn` and `step`; compaction requests carry `step: 0` and a `turn` owner that may be `null`. That null owner means a manual compaction ran standalone between turns, not that it belongs to either adjacent turn. A cancellation-finalized `assistant/message` retains its durable result seq and provider provenance but does not complete the request; `step/end` classifies that request as an error. A `session/end-seed` boundary closes an unmatched compaction request as an error at the boundary time with `Compaction was interrupted before completion.`; a later start projects as an independent request instead of overwriting the orphan. ## Code Mode child-call tree diff --git a/packages/client/runtime/README.zh.md b/packages/client/runtime/README.zh.md index 746e5a5595..f8966c3aa1 100644 --- a/packages/client/runtime/README.zh.md +++ b/packages/client/runtime/README.zh.md @@ -28,6 +28,8 @@ Workspace 和 Session 列表各自具有单调的 `pending` → `ready` 基线 SlotRegistry 分别为 renderer 提供 `useSessions` 与 `useWorkspaces` 的裸 observable；ui-renderer 创建钩子。Workspace 业务状态不会进入 `SessionListState` 或条目 store。 +`abbreviateHomePath` 是 Web Workspace 悬停卡片与 Tool 摘要使用的仅展示 POSIX 家目录缩写；Windows 盘符或 UNC 路径保持原样，缺失、空或文件系统根的 home 不改写路径。 + `indexSubagentDescendants()` 从保留的列表镜像中派生每个 parent 的后代总数与运行中后代数。它只沿不间断的 `origin: 'subagent'` 祖先链追踪，因此普通 fork 会开启独立的归属子树；遇到环时，追踪会停止但不会抛出异常，缺失的 parent 则会保留为无害的键，直至其摘要到达。 `SessionListState.jobsBySession` 按 last-wins 镜像宿主的 `session/jobs` 帧，以会话为键，不需要 Session 实例。被清空的集合存为缺失的键，因此「缺失」与 `[]` 是同一种表示，消费方永远不必检测哨兵值。两处清理让它不至于比它所反映的真相活得更久：`session/subscribed` 丢弃该会话的镜像，因为新一代只为非空集合发送 baseline，被留下的列表会变成幽灵；`host/session-removed` 再丢一次，因为 owner 销毁是在 mux 流上移除记录的，而移除帧走 host 流，两者没有相对顺序。 @@ -56,7 +58,7 @@ Chat builder 为每个 Session 保留一个 mutable keyed store。内容更新 ## Trajectory 请求数据 -Trajectory Definition 组装出一条按时间顺序排列、以用途为判别字段的提供方请求流。助手请求始终携带数值型 `turn` 与 `step`；压缩请求携带 `step: 0`，其 `turn` 所有者可以是 `null`。这个 null 所有者表示手动压缩独立运行在两个轮次之间，并不表示它属于任一相邻轮次。`session/end-seed` 边界会在边界时刻将未匹配的压缩请求以错误状态结束，错误固定为 `Compaction was interrupted before completion.`；后续 start 会投影为独立请求，而不会覆盖这项遗留的未匹配请求。 +Trajectory Definition 组装出一条按时间顺序排列、以用途为判别字段的提供方请求流。助手请求始终携带数值型 `turn` 与 `step`；压缩请求携带 `step: 0`，其 `turn` 所有者可以是 `null`。这个 null 所有者表示手动压缩独立运行在两个轮次之间，并不表示它属于任一相邻轮次。由取消定稿的 `assistant/message` 会保留持久结果 seq 和提供方信息，但不会将请求标记为完成；`step/end` 会把该请求归类为错误。`session/end-seed` 边界会在边界时刻将未匹配的压缩请求以错误状态结束，错误固定为 `Compaction was interrupted before completion.`；后续 start 会投影为独立请求，而不会覆盖这项遗留的未匹配请求。 ## Code Mode 子调用树 diff --git a/packages/client/runtime/package.json b/packages/client/runtime/package.json index ca21359f2f..051f573010 100644 --- a/packages/client/runtime/package.json +++ b/packages/client/runtime/package.json @@ -1,7 +1,7 @@ { "name": "@deepseek-ai/dsh-client-runtime", "description": "Client core services: SlotRegistry, SessionRuntime (scope tree + object layer)", - "version": "0.1.0-rc.7", + "version": "0.1.0-rc.8", "publishConfig": { "access": "public" }, diff --git a/packages/client/runtime/src/client/contract/session.ts b/packages/client/runtime/src/client/contract/session.ts index c3ef72e253..e07267d487 100644 --- a/packages/client/runtime/src/client/contract/session.ts +++ b/packages/client/runtime/src/client/contract/session.ts @@ -38,7 +38,11 @@ export interface ISession { * @param mode - 'queue' appends a turn; 'steer' interrupts the running one. * @returns acceptance, or the business error (also mirrored into snapshot.promptError). */ - prompt(content: PromptContentPart[], mode: 'queue' | 'steer'): Promise> + prompt( + content: PromptContentPart[], + mode: 'queue' | 'steer', + signal?: AbortSignal, + ): Promise> /** * Resolve one durable image referenced by this session. * @param attachmentId - opaque id found in the folded session log. diff --git a/packages/client/runtime/src/client/contract/sessions-port.ts b/packages/client/runtime/src/client/contract/sessions-port.ts index 551c3a16ee..8b9bf49229 100644 --- a/packages/client/runtime/src/client/contract/sessions-port.ts +++ b/packages/client/runtime/src/client/contract/sessions-port.ts @@ -32,11 +32,15 @@ export interface SessionsPort { /** Observable list snapshot (read face only; writes stay inside the sessions domain). */ readonly list: ObservableSnapshot /** - * Create a session on the host. - * @param opts - target workspace. - * @returns the new session id. + * Create or explicitly adopt a session on the host. + * @param opts - target workspace and optional confirmed blank-reuse id. + * @returns the created or adopted session id. */ - create(opts: { workspaceId: WorkspaceId }): Promise + create(opts: { + workspaceId: WorkspaceId + sessionId?: SessionId + reuseWorkspaceBlank?: true + }): Promise /** * Select a session as current. * @param id - session id (must exist in the list store). diff --git a/packages/client/runtime/src/client/index.ts b/packages/client/runtime/src/client/index.ts index bc8eb73330..90a2b2f5f3 100644 --- a/packages/client/runtime/src/client/index.ts +++ b/packages/client/runtime/src/client/index.ts @@ -46,7 +46,7 @@ export type { SessionProvideChannelHost } from './sessions/provide.ts' export { createScope } from './agents/scope.ts' export type { AgentScopeHandle } from './agents/scope.ts' export { DirectoryBrowseError, WorkspaceCreateError, WorkspaceRuntime } from './workspaces/service.ts' -export { resolveWorkspacePath } from './workspaces/path.ts' +export { abbreviateHomePath, resolveWorkspacePath } from './workspaces/path.ts' // Contract only: the scope implementation and its Host transport belong to // dsh-client-ui-settings (see that package's settings-scope.ts). export type { @@ -85,7 +85,7 @@ export { } from './sessions/conversation.ts' export { emptyAssistantBlock } from './sessions/partial.ts' export { isTokenDelta } from './sessions/assistant-timing.ts' -export { contextForm, contextProvenance } from './sessions/context-provenance.ts' +export { contextForm, contextProvenance, sessionRecallLabels } from './sessions/context-provenance.ts' export { displayFailureMessage } from './sessions/failure-display.ts' export type { ConversationContext, ConversationContextOriginKind, diff --git a/packages/client/runtime/src/client/sessions/context-provenance.ts b/packages/client/runtime/src/client/sessions/context-provenance.ts index 5912ea388a..dbd3b2dd30 100644 --- a/packages/client/runtime/src/client/sessions/context-provenance.ts +++ b/packages/client/runtime/src/client/sessions/context-provenance.ts @@ -58,6 +58,19 @@ function joined(names: string[]): string | null { return names.length > 0 ? names.join(', ') : null } +/** + * The referenced-session labels of one durable `session-reference` recall + * source, in first-seen order; empty for every other source shape, including + * a foreign or older log whose reference entries carry no readable label. + * @param source - the logged `user/message` source, exactly as recorded. + * @returns distinct non-empty reference labels. + */ +export function sessionRecallLabels(source: unknown): string[] { + const record = asRecord(source) + if (record === null || readString(record, 'kind') !== 'session-reference') return [] + return collect(record, 'references', 'label') +} + /** * Project one durable message source onto its transcript role and producer name. * diff --git a/packages/client/runtime/src/client/sessions/conversation.ts b/packages/client/runtime/src/client/sessions/conversation.ts index 698d8ab88f..44b6f7f42d 100644 --- a/packages/client/runtime/src/client/sessions/conversation.ts +++ b/packages/client/runtime/src/client/sessions/conversation.ts @@ -92,14 +92,14 @@ export interface AssistantTiming { completedTime: number } -/** A finalized (or interruption-frozen) assistant message. */ +/** A finalized assistant message or an interruption-frozen streaming prefix. */ export interface AssistantMessageNode { kind: 'assistant' seq: number /** - * Stable identity of the finalized model output, carried from the - * `assistant/message` event. Absent on interruption-frozen partials: those - * were never finalized, so they address no durable message. + * Stable identity carried from the `assistant/message` event. Absent only on + * synthetic interruption fallbacks assembled from chunks without a durable + * assistant message. */ messageId?: MessageId /** Unix epoch ms from the source session event (or turn/end when frozen from a partial). */ @@ -112,8 +112,9 @@ export interface AssistantMessageNode { requestConfig?: AssistantRequestConfig /** Timing derived from the recorded step/chunk/message event sequence. */ timing?: AssistantTiming - /** Frozen partial of an aborted turn (no finalize ever arrives): rendered with a 已停止 marker. - * Synthetic seq (fractional, derived from the turn/end seq) keeps it ordered inside the flow. */ + /** Prefix of an aborted turn, rendered with a 已停止 marker. A durable + * finalized prefix uses its event seq; a chunk-only fallback uses a fractional + * seq derived from the closing boundary to keep it ordered inside the flow. */ interrupted?: true } diff --git a/packages/client/runtime/src/client/sessions/manager.ts b/packages/client/runtime/src/client/sessions/manager.ts index 13aa20d1c8..bb8ed7bd6c 100644 --- a/packages/client/runtime/src/client/sessions/manager.ts +++ b/packages/client/runtime/src/client/sessions/manager.ts @@ -534,10 +534,18 @@ export class SessionManager { * @returns the create result. */ async create( - opts: { workspaceId?: WorkspaceId; cwd?: string; sessionId?: SessionId } = {}, + opts: { + workspaceId?: WorkspaceId + cwd?: string + sessionId?: SessionId + reuseWorkspaceBlank?: true + } = {}, ): Promise> { try { - const shared = opts.sessionId === undefined ? {} : { sessionId: opts.sessionId } + const shared = { + ...(opts.sessionId === undefined ? {} : { sessionId: opts.sessionId }), + ...(opts.reuseWorkspaceBlank === undefined ? {} : { reuseWorkspaceBlank: opts.reuseWorkspaceBlank }), + } const payload = opts.workspaceId !== undefined ? { workspaceId: opts.workspaceId, ...shared } : { ...(opts.cwd === undefined ? {} : { cwd: opts.cwd }), ...shared } diff --git a/packages/client/runtime/src/client/sessions/service.ts b/packages/client/runtime/src/client/sessions/service.ts index c66da4e0d3..5e23b3a10a 100644 --- a/packages/client/runtime/src/client/sessions/service.ts +++ b/packages/client/runtime/src/client/sessions/service.ts @@ -482,7 +482,12 @@ export class SessionRuntime implements ISessions { * @returns the new session id. * @throws {SessionCreateError} with the requested id. */ - async create(opts: { workspaceId?: WorkspaceId; cwd?: string; sessionId?: SessionId } = {}): Promise { + async create(opts: { + workspaceId?: WorkspaceId + cwd?: string + sessionId?: SessionId + reuseWorkspaceBlank?: true + } = {}): Promise { const result = await this.manager.create(opts) if (!result.ok) throw new SessionCreateError(result.error, opts.sessionId) this.projectList() diff --git a/packages/client/runtime/src/client/sessions/session.ts b/packages/client/runtime/src/client/sessions/session.ts index 3e5ec5a811..02939cf28f 100644 --- a/packages/client/runtime/src/client/sessions/session.ts +++ b/packages/client/runtime/src/client/sessions/session.ts @@ -187,7 +187,11 @@ export class Session implements SessionFace { * @param mode - queue appends after the current turn; steer interrupts it. * @returns the prompt result (also mirrored into promptError on failure). */ - async prompt(content: PromptContentPart[], mode: 'queue' | 'steer'): Promise> { + async prompt( + content: PromptContentPart[], + mode: 'queue' | 'steer', + signal?: AbortSignal, + ): Promise> { this.promptError = null this.lastAgentError = null // Synchronous, before the first await: the blank → engaging edge must be @@ -204,7 +208,7 @@ export class Session implements SessionFace { mode, content, clientTimeZone: resolvedClientTimeZone(), - })).result + }, signal)).result } else if (this.address.mode === 'one-shot') { result = { ok: false, @@ -231,7 +235,7 @@ export class Session implements SessionFace { ? [{ type: 'text' as const, text: part.text }] : []), clientTimeZone: resolvedClientTimeZone(), - })).result + }, signal)).result result = routed.ok ? { ok: true, value: { accepted: true } } : routed } } @@ -356,7 +360,7 @@ export class Session implements SessionFace { * @returns the admission result, or the error branch on transport failure. */ async command(line: string): Promise> { - const result = await this.remote.commands.execute(this.sessionId, line) + const result = await this.remote.commands.execute(this.sessionId, line, []) if (!result.ok) return result return { ok: true, value: { matched: result.value !== undefined } } } diff --git a/packages/client/runtime/src/client/workspaces/path.ts b/packages/client/runtime/src/client/workspaces/path.ts index d1512177ad..8bb3aa6645 100644 --- a/packages/client/runtime/src/client/workspaces/path.ts +++ b/packages/client/runtime/src/client/workspaces/path.ts @@ -5,9 +5,32 @@ * @returns an absolute path when a workspace root is available, otherwise the original path. */ export function resolveWorkspacePath(cwd: string | undefined, path: string): string { - if (path.startsWith('/') || /^[A-Za-z]:[/\\]/.test(path) || path.startsWith('\\\\')) return path + if (path.startsWith('/') || isWindowsStylePath(path)) return path if (cwd === undefined || cwd === '') return path const base = cwd.replace(/[/\\]+$/, '') const rel = path.replace(/^[/\\]+/, '') return `${base}/${rel}` } + +/** Drive-letter or UNC path; Web display must not rewrite these as `~`. */ +function isWindowsStylePath(value: string): boolean { + return /^[A-Za-z]:[/\\]/.test(value) || value.startsWith('\\\\') +} + +/** + * Display-only POSIX home abbreviation. Windows drive and UNC paths stay + * verbatim, including when `home` itself is a Windows path. A missing, empty, + * or filesystem-root `home` leaves `path` unchanged so `/` cannot become `~`. + * @param path - absolute or already-short display path. + * @param home - host account home from `host.describe`; absent skips abbreviation. + * @returns `~` or `~/…` for the POSIX home and its descendants, otherwise `path`. + */ +export function abbreviateHomePath(path: string, home?: string): string { + if (home === undefined || home === '') return path + if (isWindowsStylePath(path) || isWindowsStylePath(home)) return path + const root = home.replace(/\/+$/, '') + if (root === '' || root === '/') return path + if (path.replace(/\/+$/, '') === root) return '~' + if (path.startsWith(`${root}/`)) return `~${path.slice(root.length)}` + return path +} diff --git a/packages/client/runtime/src/client/workspaces/service.ts b/packages/client/runtime/src/client/workspaces/service.ts index c23e3b3a6c..bfce0c6e28 100644 --- a/packages/client/runtime/src/client/workspaces/service.ts +++ b/packages/client/runtime/src/client/workspaces/service.ts @@ -53,7 +53,7 @@ export class WorkspaceRuntime implements IWorkspaces { readonly list: SnapshotStore /** Workspace baseline and frame owner. */ private readonly manager: WorkspaceManager - /** In-flight blank-session creates keyed by workspace (connectWorkspace coalescing). */ + /** In-flight blank-session connects keyed by workspace (reuse or create). */ private readonly connecting = new Map>() /** Guards the runtime-owned one-shot initial-selection subscription. */ private initialSelectionStarted = false @@ -76,9 +76,11 @@ export class WorkspaceRuntime implements IWorkspaces { /** * Resolve the session a New Session flow lands in once this Workspace is - * chosen: reuse the workspace's existing blank session when one is in the - * list mirror, else create a fresh one on the host (`session.create` births - * the full Session+Agent — the client holds no intermediate state). The + * chosen: explicitly adopt the workspace's existing blank session when one + * is in the list mirror, else create a fresh one on the host + * (`session.create` births or resumes the full Session+Agent — the client + * holds no intermediate state). The adoption tells optional default owners + * that this exact session passed the reuse checks. * caller owns navigation: take the returned id to `sessions.open`. * Resolution guarantee (both arms): the returned id is already in the list * store and `sessions.binding(id)` resolves synchronously — draft hand-off @@ -107,7 +109,13 @@ export class WorkspaceRuntime implements IWorkspaces { const summary = sessions.byId[id] if (summary !== undefined && summary.blank && summary.cwd === workspace.path && workspace.sessionIds.includes(summary.id) - && !archived.includes(summary.id)) return summary.id + && !archived.includes(summary.id)) { + return this.sessions.create({ + workspaceId, + sessionId: summary.id, + reuseWorkspaceBlank: true, + }) + } } const attempt = this.sessions.create({ workspaceId }) .finally(() => { this.connecting.delete(workspaceId) }) diff --git a/packages/client/runtime/src/env.d.ts b/packages/client/runtime/src/env.d.ts deleted file mode 100644 index 54d3d9d8f3..0000000000 --- a/packages/client/runtime/src/env.d.ts +++ /dev/null @@ -1,5 +0,0 @@ -/** - * Bundler-replaced NODE_ENV: vite/tsdown substitute the literal, so browsers - * never evaluate a bare `process`. tsconfig carries no node types on purpose. - */ -declare const process: { env: { NODE_ENV?: string } } diff --git a/packages/client/runtime/tests/client-apply.client.spec.ts b/packages/client/runtime/tests/client-apply.client.spec.ts index 1026c55569..199181fe2e 100644 --- a/packages/client/runtime/tests/client-apply.client.spec.ts +++ b/packages/client/runtime/tests/client-apply.client.spec.ts @@ -91,7 +91,7 @@ describe('runtime client apply', () => { expect(workspaces.list.getSnapshot().items[0]?.workspaceId).toBe('w-new') // Mux sink and onConnected route without throwing (manager semantics own the behavior). bench.sinks?.onMuxEnvelope?.({ rpcId: 'r2' as never, payload: { type: 'stream/error', message: 'x' } as never }) - bench.sinks?.onConnected?.({ version: '0', cwd: '/f', attachedSessions: 0, canOpenPath: true }) + bench.sinks?.onConnected?.({ version: '0', cwd: '/f', attachedSessions: 0, home: '/h', canOpenPath: true }) }) it('selects the recent Workspace once when the first baselines have no current session', async () => { @@ -104,7 +104,7 @@ describe('runtime client apply', () => { })) bench.api.onList = () => Promise.resolve(ok({ items: [] })) - bench.sinks?.onConnected?.({ version: '0', cwd: '/f', attachedSessions: 0, canOpenPath: true }) + bench.sinks?.onConnected?.({ version: '0', cwd: '/f', attachedSessions: 0, home: '/h', canOpenPath: true }) await flushMicrotasks() const sessions = bench.ctx.get('sessions') as SessionRuntime diff --git a/packages/client/runtime/tests/context-provenance.client.spec.ts b/packages/client/runtime/tests/context-provenance.client.spec.ts index e243660d60..b64902719c 100644 Binary files a/packages/client/runtime/tests/context-provenance.client.spec.ts and b/packages/client/runtime/tests/context-provenance.client.spec.ts differ diff --git a/packages/client/runtime/tests/fake-api.client.ts b/packages/client/runtime/tests/fake-api.client.ts index 33a0efbbfd..e5bdaa5f66 100644 --- a/packages/client/runtime/tests/fake-api.client.ts +++ b/packages/client/runtime/tests/fake-api.client.ts @@ -108,10 +108,11 @@ export class FakeApiClient implements IApiClient { version: string cwd: string attachedSessions: number + home: string canOpenPath: boolean }>> = () => Promise.resolve(ok({ - version: '0-fake', cwd: '/f', attachedSessions: 0, canOpenPath: true, + version: '0-fake', cwd: '/f', attachedSessions: 0, home: '/h', canOpenPath: true, })) onPickDirectory: (payload: unknown) => Promise> = () => Promise.resolve(ok({ path: null })) diff --git a/packages/client/runtime/tests/path.client.spec.ts b/packages/client/runtime/tests/path.client.spec.ts new file mode 100644 index 0000000000..455df0d112 --- /dev/null +++ b/packages/client/runtime/tests/path.client.spec.ts @@ -0,0 +1,41 @@ +import { describe, expect, it } from 'vitest' +import { abbreviateHomePath, resolveWorkspacePath } from '../src/client/workspaces/path.ts' + +describe('abbreviateHomePath', () => { + it('collapses a POSIX home and its descendants', () => { + expect(abbreviateHomePath('/Users/u', '/Users/u')).toBe('~') + expect(abbreviateHomePath('/Users/u/', '/Users/u')).toBe('~') + expect(abbreviateHomePath('/Users/u/Documents/project', '/Users/u')).toBe('~/Documents/project') + expect(abbreviateHomePath('/Users/u/Documents/project/', '/Users/u/')).toBe('~/Documents/project/') + }) + + it('keeps prefix-adjacent names and non-home paths', () => { + expect(abbreviateHomePath('/Users/u2/a.ts', '/Users/u')).toBe('/Users/u2/a.ts') + expect(abbreviateHomePath('/etc/hosts', '/Users/u')).toBe('/etc/hosts') + expect(abbreviateHomePath('src/a.ts', '/Users/u')).toBe('src/a.ts') + expect(abbreviateHomePath('~/already', '/Users/u')).toBe('~/already') + }) + + it('does not abbreviate when home is missing, empty, or the filesystem root', () => { + expect(abbreviateHomePath('/Users/u/a.ts')).toBe('/Users/u/a.ts') + expect(abbreviateHomePath('/Users/u/a.ts', '')).toBe('/Users/u/a.ts') + expect(abbreviateHomePath('/etc/hosts', '/')).toBe('/etc/hosts') + expect(abbreviateHomePath('/etc/hosts', '///')).toBe('/etc/hosts') + }) + + it('leaves Windows drive and UNC paths verbatim', () => { + expect(abbreviateHomePath('C:\\Users\\u\\project', 'C:\\Users\\u')).toBe('C:\\Users\\u\\project') + expect(abbreviateHomePath('C:/Users/u/project', '/Users/u')).toBe('C:/Users/u/project') + expect(abbreviateHomePath('/Users/u/project', 'C:\\Users\\u')).toBe('/Users/u/project') + expect(abbreviateHomePath('\\\\server\\share\\u', '\\\\server\\share\\u')).toBe('\\\\server\\share\\u') + }) +}) + +describe('resolveWorkspacePath', () => { + it('joins a relative path under cwd and passes absolute paths through', () => { + expect(resolveWorkspacePath('/w', 'src/a.ts')).toBe('/w/src/a.ts') + expect(resolveWorkspacePath('/w/', '/abs/a.ts')).toBe('/abs/a.ts') + expect(resolveWorkspacePath(undefined, 'src/a.ts')).toBe('src/a.ts') + expect(resolveWorkspacePath('/w', 'C:\\x\\a.ts')).toBe('C:\\x\\a.ts') + }) +}) diff --git a/packages/client/runtime/tests/wire-events.client.spec.ts b/packages/client/runtime/tests/wire-events.client.spec.ts index f6798bd914..fbc4204b0d 100644 --- a/packages/client/runtime/tests/wire-events.client.spec.ts +++ b/packages/client/runtime/tests/wire-events.client.spec.ts @@ -28,7 +28,7 @@ function forwardedEventContracts(ctx: Context): void { const bare: typeof namespace = 'plain-string' void bare; void namespace; void source }) - ctx.remote.$on('credentials/updated', () => {}) + ctx.remote.$on('credentials/reference-updated', () => {}) ctx.remote.$on('commands/change', () => {}) ctx.remote.$on('llm/adapters-updated', () => {}) ctx.remote.$on('agent-preset/selected', (sessionId, agentPreset) => { @@ -106,7 +106,7 @@ describe('wire event bridge', () => { }) bench.sinks?.onHostEnvelope?.({ rpcId: 'r4' as never, - payload: { type: 'host/remote-event', event: 'credentials/updated', args: ['OPENAI_API_KEY'] }, + payload: { type: 'host/remote-event', event: 'credentials/reference-updated', args: ['OPENAI_API_KEY'] }, }) // The carrier does not second-guess the name: selecting what a consumer can // receive is the allowlist's job, and dropping an unsubscribed name is the @@ -118,7 +118,7 @@ describe('wire event bridge', () => { expect(seen).toEqual([ ['settings/document-updated', 'llm-pi-ai', 7], - ['credentials/updated', 'OPENAI_API_KEY'], + ['credentials/reference-updated', 'OPENAI_API_KEY'], ['nobody/listening', 'ignored'], ]) }) @@ -127,7 +127,7 @@ describe('wire event bridge', () => { const bench = await mount() let resets = 0 bench.ctx.on('connection/reset', () => { resets++ }) - const description = { version: '0', cwd: '/f', attachedSessions: 0, canOpenPath: true } + const description = { version: '0', cwd: '/f', attachedSessions: 0, home: '/h', canOpenPath: true } bench.sinks?.onConnected?.(description) bench.sinks?.onConnected?.(description) // second generation after a reconnect expect(resets).toBe(2) diff --git a/packages/client/runtime/tests/workspaces-service.client.spec.ts b/packages/client/runtime/tests/workspaces-service.client.spec.ts index cfdfa98e9b..68736f0a58 100644 --- a/packages/client/runtime/tests/workspaces-service.client.spec.ts +++ b/packages/client/runtime/tests/workspaces-service.client.spec.ts @@ -242,20 +242,28 @@ describe('WorkspaceRuntime', () => { { sessionId: sid('s-stray'), updatedAt: 4, running: false, blank: true, cwd: '/w/gamma' }, ] as never[], })) + api.onCreate = payload => Promise.resolve(ok({ + sessionId: (payload as { sessionId?: SessionId }).sessionId ?? sid('s-unexpected'), + })) await Promise.all([workspaces.refresh(), sessions.refresh()]) await Promise.resolve() - // Hit: same workspace → the parked member blank comes back (the earlier - // cwd-matching non-member stray is skipped), no create RPC. + // Hit: same workspace → the parked member blank is explicitly adopted + // after the earlier cwd-matching non-member stray is skipped. await expect(workspaces.connectWorkspace(wid('alpha'))).resolves.toBe('s-blank') - expect(api.callsOf('session.create')).toEqual([]) + expect(api.callsOf('session.create')).toEqual([{ + workspaceId: 'alpha', sessionId: 's-blank', reuseWorkspaceBlank: true, + }]) // Resolution guarantee: the id is binding-resolvable synchronously. expect(sessions.binding(sid('s-blank'))).toBeDefined() // Miss: beta has only a non-blank session → host create with workspaceId. api.onCreate = () => Promise.resolve(ok({ sessionId: sid('s-fresh') })) await expect(workspaces.connectWorkspace(wid('beta'))).resolves.toBe('s-fresh') - expect(api.callsOf('session.create')).toEqual([{ workspaceId: 'beta' }]) + expect(api.callsOf('session.create')).toEqual([ + { workspaceId: 'alpha', sessionId: 's-blank', reuseWorkspaceBlank: true }, + { workspaceId: 'beta' }, + ]) // Same guarantee on the create arm (draft hand-off writes the machine pre-open). expect(sessions.binding(sid('s-fresh'))).toBeDefined() @@ -263,7 +271,11 @@ describe('WorkspaceRuntime', () => { // never reused, a fresh accounted session is created instead. api.onCreate = () => Promise.resolve(ok({ sessionId: sid('s-fresh-3') })) await expect(workspaces.connectWorkspace(wid('gamma'))).resolves.toBe('s-fresh-3') - expect(api.callsOf('session.create')).toEqual([{ workspaceId: 'beta' }, { workspaceId: 'gamma' }]) + expect(api.callsOf('session.create')).toEqual([ + { workspaceId: 'alpha', sessionId: 's-blank', reuseWorkspaceBlank: true }, + { workspaceId: 'beta' }, + { workspaceId: 'gamma' }, + ]) // Unknown workspace fails loud instead of silently creating in nowhere. await expect(workspaces.connectWorkspace(wid('ghost'))).rejects.toThrow(/unknown workspace ghost/) @@ -284,6 +296,9 @@ describe('WorkspaceRuntime', () => { api.onList = () => Promise.resolve(ok({ items: [{ sessionId: sid('s-blank'), updatedAt: 2, running: false, blank: true, cwd: '/w/alpha' }] as never[], })) + api.onCreate = payload => Promise.resolve(ok({ + sessionId: (payload as { sessionId?: SessionId }).sessionId ?? sid('s-unexpected'), + })) await Promise.all([workspaces.refresh(), sessions.refresh()]) await Promise.resolve() const session = sessions.binding(sid('s-blank'))!.session @@ -292,7 +307,9 @@ describe('WorkspaceRuntime', () => { await Promise.resolve() // Failure leaves blank intact, so the same session is still the reuse hit. await expect(workspaces.connectWorkspace(wid('alpha'))).resolves.toBe('s-blank') - expect(api.callsOf('session.create')).toEqual([]) + expect(api.callsOf('session.create')).toEqual([{ + workspaceId: 'alpha', sessionId: 's-blank', reuseWorkspaceBlank: true, + }]) }) it('returns created Workspaces and preserves Host business errors', async () => { diff --git a/packages/client/tsdown.client.ts b/packages/client/tsdown.client.ts index 72f0346680..44aab8cf1b 100644 --- a/packages/client/tsdown.client.ts +++ b/packages/client/tsdown.client.ts @@ -17,6 +17,7 @@ import type { UserConfig } from 'tsdown' import { transform } from 'lightningcss' import { optionalStringArray } from './modules/src/client/manifest.ts' import { PLATFORM_MODULES, PRELOADED_CLIENT_EXTERNALS } from './web/src/platform.ts' +import { clientBuildEnvironmentDefines } from '../../scripts/client-build-environment.ts' /** * Virtual-id wrapper keeping module CSS away from tsdown's own css pipeline @@ -57,7 +58,7 @@ function styleInjectionModule( * Everything else under @deepseek-ai/* is either a module-table entry * (external) or a leak the purity gate rejects. */ -export const INLINE_SAFE = /^@deepseek-ai\/dsh-(host-apiproxy|session|llm|tools|brand)(\/|$)/ +export const INLINE_SAFE = /^@deepseek-ai\/dsh-(host-apiproxy|file-reference|session|llm|tools|brand)(\/|$)/ /** * Vendored framework libraries: rescoped into @deepseek-ai, so the gate below @@ -470,6 +471,7 @@ function clientConfig(id: string, entry: string): UserConfig { // key: zustand probes `import.meta.env ? import.meta.env.MODE : ...`, and // the truthiness probe would otherwise survive as an empty import.meta. define: { + ...clientBuildEnvironmentDefines(process.env), 'process.env.NODE_ENV': JSON.stringify(process.env.NODE_ENV ?? 'production'), 'import.meta.env.MODE': JSON.stringify(process.env.NODE_ENV ?? 'production'), 'import.meta.env': JSON.stringify({ MODE: process.env.NODE_ENV ?? 'production' }), diff --git a/packages/client/ui-agent-preset/package.json b/packages/client/ui-agent-preset/package.json index 8b4afb0fb3..81763a3e3e 100644 --- a/packages/client/ui-agent-preset/package.json +++ b/packages/client/ui-agent-preset/package.json @@ -1,7 +1,7 @@ { "name": "@deepseek-ai/dsh-client-ui-agent-preset", "description": "Agent-preset surfaces: the default for later sessions, this session's seat, and the composition editor", - "version": "0.1.0-rc.7", + "version": "0.1.0-rc.8", "publishConfig": { "access": "public" }, diff --git a/packages/client/ui-attachment/package.json b/packages/client/ui-attachment/package.json index 8e22c28e57..039e1a0d5f 100644 --- a/packages/client/ui-attachment/package.json +++ b/packages/client/ui-attachment/package.json @@ -1,7 +1,7 @@ { "name": "@deepseek-ai/dsh-client-ui-attachment", "description": "Dynamic attachment presentation plugin for conversation input and message-image slots", - "version": "0.1.0-rc.7", + "version": "0.1.0-rc.8", "publishConfig": { "access": "public" }, diff --git a/packages/client/ui-brand-official/README.i18n.yaml b/packages/client/ui-brand-official/README.i18n.yaml new file mode 100644 index 0000000000..9d438ad955 --- /dev/null +++ b/packages/client/ui-brand-official/README.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 packages/client/ui-brand-official/README.md +README.md: 7197bc7f4731cd3e6471549900e4868ad6d4796d +README.zh.md: 14d3ee3f1aa2f12ddd20b851d4034e1417baf5c9 diff --git a/packages/client/ui-brand-official/README.md b/packages/client/ui-brand-official/README.md new file mode 100644 index 0000000000..7197bc7f47 --- /dev/null +++ b/packages/client/ui-brand-official/README.md @@ -0,0 +1,20 @@ +# @deepseek-ai/dsh-client-ui-brand-official + +English | [中文](README.zh.md) + +This package fills `sidebar.brand.mark`, `sidebar.brand.name`, and `conversation.hero.brand.mark` only when `DSH_CLIENT_BUILD_PROFILE` is `official`. Other builds load the plugin but register no occupants, leaving the shell fallbacks visible. + +The three occupants install as one declaration-aware registration set through nested `slots.inject()` calls. The package therefore works whether its row activates before or after the sidebar and conversation declarers, withdraws all occupants when either declaration collapses, and leaves no partial brand mix during HMR. It retains no runtime state. The node half is an empty Loader seat, and the browser title remains a build-environment concern outside this package. + +## Model Experience + +None, as the package contributes browser presentation only; nothing here reaches a model request. + +#### KV Cache effect + +None; this package neither assembles nor sends a provider request. + +## Known Limitations and Deferred Work + +- **The package supplies one occupant set** — alternative presentation belongs in another Cordis package occupying the same slots. +- **The browser title is independent** — `DSH_CLIENT_TITLE` selects title text at build time rather than through a UI slot. diff --git a/packages/client/ui-brand-official/README.zh.md b/packages/client/ui-brand-official/README.zh.md new file mode 100644 index 0000000000..14d3ee3f1a --- /dev/null +++ b/packages/client/ui-brand-official/README.zh.md @@ -0,0 +1,20 @@ +# @deepseek-ai/dsh-client-ui-brand-official + +[English](README.md) | 中文 + +仅当 `DSH_CLIENT_BUILD_PROFILE` 为 `official` 时，本包才填充 `sidebar.brand.mark`、`sidebar.brand.name` 和 `conversation.hero.brand.mark`。其他构建仍会加载插件，但不注册 occupant，因此显示 shell fallback。 + +三个占位者通过嵌套的 `slots.inject()` 作为一组声明感知注册安装。因此无论该包的条目先于还是后于侧边栏和会话声明方激活，它都能工作；任一声明折叠时会撤回全部占位者，HMR 期间不会留下混合品牌。它不保留运行时状态。node 半边是空的 Loader seat；浏览器标题仍属于本包之外的构建环境事项。 + +## 模型体验 + +无，因为本包只贡献浏览器呈现；这里没有任何内容进入模型请求。 + +#### KV Cache 影响 + +无；本包既不组装也不发送 provider 请求。 + +## 已知限制与暂缓事项 + +- **本包只提供一组 occupant** —— 其他呈现应由占用相同 slot 的另一个 Cordis 包提供。 +- **浏览器标题相互独立** —— `DSH_CLIENT_TITLE` 在构建期选择标题文字，而不经过 UI slot。 diff --git a/packages/client/ui-brand-official/package.json b/packages/client/ui-brand-official/package.json new file mode 100644 index 0000000000..d08317fbbc --- /dev/null +++ b/packages/client/ui-brand-official/package.json @@ -0,0 +1,72 @@ +{ + "name": "@deepseek-ai/dsh-client-ui-brand-official", + "description": "Official DeepSeek Harness brand occupants for the Web client's sidebar and conversation Hero slots", + "version": "0.1.0-rc.8", + "publishConfig": { + "access": "public" + }, + "repository": { + "type": "git", + "url": "git+https://github.com/deepseek-ai/deepseek-harness.git", + "directory": "packages/client/ui-brand-official" + }, + "type": "module", + "main": "lib/index.js", + "types": "lib/types/index.d.ts", + "exports": { + ".": { + "types": "./lib/types/index.d.ts", + "default": "./lib/index.js" + }, + "./invariant": { + "types": "./lib/types/invariant.d.ts", + "default": "./lib/invariant.js" + }, + "./client": { + "types": "./lib/types/client/index.d.ts", + "default": "./lib/client.js" + }, + "./src/*": "./src/*", + "./package.json": "./package.json" + }, + "dsh": { + "client": { + "inject": [ + "@deepseek-ai/dsh-client-runtime", + "@deepseek-ai/dsh-client-ui-conversation", + "@deepseek-ai/dsh-client-ui-sidebar" + ], + "platform": "web" + } + }, + "scripts": { + "bundle": "tsdown", + "watch": "tsdown --watch" + }, + "license": "MIT", + "peerDependencies": { + "@deepseek-ai/dsh-client-runtime": "workspace:^", + "@deepseek-ai/dsh-client-ui-conversation": "workspace:^", + "@deepseek-ai/dsh-client-ui-sidebar": "workspace:^", + "@deepseek-ai/dsh-invariants": "workspace:^", + "@deepseek-ai/cordis": "workspace:^" + }, + "devDependencies": { + "@deepseek-ai/dsh-client-runtime": "workspace:^", + "@deepseek-ai/dsh-client-ui-conversation": "workspace:^", + "@deepseek-ai/dsh-client-ui-primitives": "workspace:^", + "@deepseek-ai/dsh-client-ui-sidebar": "workspace:^", + "@deepseek-ai/dsh-invariants": "workspace:^", + "@deepseek-ai/cordis": "workspace:^", + "@testing-library/react": "^16.1.0", + "@types/react": "~18.3.1", + "react": "^18.2.0", + "react-dom": "^18.2.0" + }, + "files": [ + "lib/index.js", + "lib/invariant.js", + "lib/client.js", + "lib/types/**/*.d.ts" + ] +} diff --git a/packages/client/ui-brand-official/src/client/Brand.tsx b/packages/client/ui-brand-official/src/client/Brand.tsx new file mode 100644 index 0000000000..4e0a60fd26 --- /dev/null +++ b/packages/client/ui-brand-official/src/client/Brand.tsx @@ -0,0 +1,22 @@ +import { BrandWordmark, FishLogo } from '@deepseek-ai/dsh-client-ui-primitives' +import type { HeroBrandMarkOwnerProps } from '@deepseek-ai/dsh-client-ui-conversation/client' +import type { SidebarBrandMarkOwnerProps } from '@deepseek-ai/dsh-client-ui-sidebar/client' + +type OfficialBrandMarkProps = HeroBrandMarkOwnerProps & SidebarBrandMarkOwnerProps + +/** + * Render the official mark with the presentation requested by its host surface. + * @param props - Host-supplied mark presentation. + * @returns the official whale mark. + */ +export function OfficialBrandMark({ size, className }: OfficialBrandMarkProps) { + return +} + +/** + * Render the official name artwork without its independently slotted mark. + * @returns the official name wordmark. + */ +export function OfficialBrandName() { + return +} diff --git a/packages/client/ui-brand-official/src/client/index.ts b/packages/client/ui-brand-official/src/client/index.ts new file mode 100644 index 0000000000..b291bda3e7 --- /dev/null +++ b/packages/client/ui-brand-official/src/client/index.ts @@ -0,0 +1,23 @@ +/** Official DeepSeek Harness occupants for the generic browser-brand slots. */ +import type { ClientContext } from '@deepseek-ai/dsh-client-runtime/client' +import type {} from '@deepseek-ai/dsh-client-ui-conversation/client' +import type {} from '@deepseek-ai/dsh-client-ui-sidebar/client' +import { OfficialBrandMark, OfficialBrandName } from './Brand.tsx' + +/** Required service: the UI slot registry. */ +export const inject = ['slots'] + +/** + * Fill every shipped brand slot as one declaration-aware registration set. + * @param ctx - Client root context. + */ +export function apply(ctx: ClientContext): void { + if (process.env.DSH_CLIENT_BUILD_PROFILE !== 'official') return + ctx.slots.inject('sidebar.brand.mark', () => + ctx.slots.inject('sidebar.brand.name', () => + ctx.slots.inject('conversation.hero.brand.mark', function* () { + yield ctx.slots.register({ name: 'sidebar.brand.mark' }, OfficialBrandMark) + yield ctx.slots.register({ name: 'sidebar.brand.name' }, OfficialBrandName) + yield ctx.slots.register({ name: 'conversation.hero.brand.mark' }, OfficialBrandMark) + }))) +} diff --git a/packages/client/ui-brand-official/src/index.ts b/packages/client/ui-brand-official/src/index.ts new file mode 100644 index 0000000000..df38f3cfa5 --- /dev/null +++ b/packages/client/ui-brand-official/src/index.ts @@ -0,0 +1,7 @@ +/** + * Official browser-brand plugin, node half. The empty apply gives Loader a + * host-side row while the browser half ships through `exports["./client"]`. + */ + +/** Host plugin body — this package contributes browser presentation only. */ +export function apply(): void {} diff --git a/packages/client/ui-brand-official/src/invariant.ts b/packages/client/ui-brand-official/src/invariant.ts new file mode 100644 index 0000000000..574054c383 --- /dev/null +++ b/packages/client/ui-brand-official/src/invariant.ts @@ -0,0 +1,30 @@ +/** + * Package-owned invariant companion for `@deepseek-ai/dsh-client-ui-brand-official`. + * @module @deepseek-ai/dsh-client-ui-brand-official/invariant + */ + +/* jscpd:ignore-start */ +import type { Context } from '@deepseek-ai/cordis' +import type { InvariantInstaller } from '@deepseek-ai/dsh-invariants' + +const PACKAGE_NAME = '@deepseek-ai/dsh-client-ui-brand-official' + +/** Cordis companion plugin name. */ +export const name = 'client-ui-brand-official-invariant' +/** Service required before the companion can reserve package ownership. */ +export const inject = ['invariants'] + +/** + * No runtime invariant: the package retains no mutable state, and its three + * slot occupants install and leave through one transactional effect. + */ +const install: InvariantInstaller = () => {} + +/** + * Register this package's invariant companion. + * @param ctx - Cordis context carrying the invariant service. + * @returns the installed registration's disposer after setup succeeds. + */ +export const apply = (ctx: Context): Promise<() => void> => + Promise.resolve(ctx.invariants.register(PACKAGE_NAME, install)) +/* jscpd:ignore-end */ diff --git a/packages/client/ui-brand-official/tests/browser-plugin.client.spec.tsx b/packages/client/ui-brand-official/tests/browser-plugin.client.spec.tsx new file mode 100644 index 0000000000..ee5275b9b7 --- /dev/null +++ b/packages/client/ui-brand-official/tests/browser-plugin.client.spec.tsx @@ -0,0 +1,79 @@ +// @vitest-environment jsdom +import { Context } from '@deepseek-ai/cordis' +import { afterEach, describe, expect, it, vi } from 'vitest' +import { cleanup, render } from '@testing-library/react' +import { SlotRegistry } from '@deepseek-ai/dsh-client-runtime/client' +import { apply, inject } from '../src/client/index.ts' +import { OfficialBrandMark, OfficialBrandName } from '../src/client/Brand.tsx' + +afterEach(() => { + cleanup() + vi.unstubAllEnvs() +}) + +const HOLES = [ + 'sidebar.brand.mark', + 'sidebar.brand.name', + 'conversation.hero.brand.mark', +] as const + +async function bench(declare = true) { + const ctx = new Context() + await ctx.plugin(SlotRegistry).await() + const slots = ctx.get('slots') as SlotRegistry + const declareHoles = () => slots.register({ + name: 'root', + children: Object.fromEntries(HOLES.map(name => [name, { kind: 'single', scope: 'root' }])), + } as never, () => null) + const disposeHoles = declare ? declareHoles() : undefined + return { ctx, slots, declareHoles, disposeHoles } +} + +describe('official browser-brand plugin', () => { + it('declares only the slot service it uses', () => { + expect(inject).toEqual(['slots']) + }) + + it('leaves every slot empty outside the official build profile', async () => { + vi.stubEnv('DSH_CLIENT_BUILD_PROFILE', 'local') + const subject = await bench() + await subject.ctx.plugin({ inject: [...inject], apply }).await() + for (const hole of HOLES) expect(subject.slots.entries(hole)).toHaveLength(0) + }) + + it('fills declarations before or after apply and removes every occupant on teardown', async () => { + vi.stubEnv('DSH_CLIENT_BUILD_PROFILE', 'official') + const before = await bench() + const fiber = before.ctx.plugin({ inject: [...inject], apply }) + await fiber.await() + for (const hole of HOLES) expect(before.slots.entries(hole)).toHaveLength(1) + + before.disposeHoles?.() + for (const hole of HOLES) expect(before.slots.entries(hole)).toHaveLength(0) + before.declareHoles() + await Promise.resolve() + for (const hole of HOLES) expect(before.slots.entries(hole)).toHaveLength(1) + + await fiber.dispose() + for (const hole of HOLES) expect(before.slots.entries(hole)).toHaveLength(0) + + const after = await bench(false) + await after.ctx.plugin({ inject: [...inject], apply }).await() + for (const hole of HOLES) expect(after.slots.entries(hole)).toHaveLength(0) + after.declareHoles() + await Promise.resolve() + for (const hole of HOLES) expect(after.slots.entries(hole)).toHaveLength(1) + }) + + it('renders the official name independently from both requested mark sizes', () => { + const name = render() + expect(name.container.querySelector('svg')?.getAttribute('viewBox')).toBe('26 0 156 24') + name.unmount() + + const mark = render() + expect(mark.container.querySelector('svg')?.getAttribute('width')).toBe('34') + expect(mark.container.querySelector('svg')?.getAttribute('class')).toBe('hero-mark') + mark.rerender() + expect(mark.container.querySelector('svg')?.getAttribute('width')).toBe('24') + }) +}) diff --git a/packages/client/ui-brand-official/tests/invariant.client.spec.ts b/packages/client/ui-brand-official/tests/invariant.client.spec.ts new file mode 100644 index 0000000000..d8d3dd2d95 --- /dev/null +++ b/packages/client/ui-brand-official/tests/invariant.client.spec.ts @@ -0,0 +1,18 @@ +import { Context } from '@deepseek-ai/cordis' +import InvariantRegistry from '@deepseek-ai/dsh-invariants' +import { describe, expect, it } from 'vitest' +import * as BrandInvariant from '../src/invariant.ts' +import { apply as nodeApply } from '../src/index.ts' + +describe('official brand invariant companion', () => { + it('reserves package ownership with an empty installer', async () => { + const ctx = new Context() + await ctx.plugin(InvariantRegistry, { enabled: true }) + + await expect(ctx.plugin(BrandInvariant).await()).resolves.toBeDefined() + }) + + it('keeps the node half as an inert Loader seat', () => { + expect(() => { nodeApply() }).not.toThrow() + }) +}) diff --git a/packages/client/ui-brand-official/tsconfig.json b/packages/client/ui-brand-official/tsconfig.json new file mode 100644 index 0000000000..f98c0a8b2f --- /dev/null +++ b/packages/client/ui-brand-official/tsconfig.json @@ -0,0 +1,30 @@ +{ + "extends": "../../../tsconfig.base.client.json", + "compilerOptions": { + "rootDir": "src", + "outDir": "lib/types" + }, + "include": [ + "src" + ], + "references": [ + { + "path": "../../runtime-diagnostics/invariants" + }, + { + "path": "../runtime" + }, + { + "path": "../ui-conversation" + }, + { + "path": "../ui-primitives" + }, + { + "path": "../ui-sidebar" + }, + { + "path": "../ui-slots" + } + ] +} diff --git a/packages/client/ui-brand-official/tsdown.config.ts b/packages/client/ui-brand-official/tsdown.config.ts new file mode 100644 index 0000000000..abc830c1f6 --- /dev/null +++ b/packages/client/ui-brand-official/tsdown.config.ts @@ -0,0 +1,3 @@ +import { clientBundle } from '../tsdown.client.ts' + +export default clientBundle('@deepseek-ai/dsh-client-ui-brand-official', ['lib/types/index.js', 'lib/types/invariant.js']) diff --git a/packages/client/ui-commands/README.i18n.yaml b/packages/client/ui-commands/README.i18n.yaml index e504920d37..c00becc4e1 100644 --- a/packages/client/ui-commands/README.i18n.yaml +++ b/packages/client/ui-commands/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 packages/client/ui-commands/README.md -README.md: 2cbf3f4652558449d183484cb89b43ee24303ba1 -README.zh.md: 70d0b8b73984d66fa5079c18a0f4fac895394dd5 +README.md: 7f1a54c99e4f9cf52af09e10b4c008b5c0f3e8da +README.zh.md: c69790b6e690d1d0654b0ddd6e6cf657ccfec434 diff --git a/packages/client/ui-commands/README.md b/packages/client/ui-commands/README.md index 2cbf3f4652..7f1a54c99e 100644 --- a/packages/client/ui-commands/README.md +++ b/packages/client/ui-commands/README.md @@ -8,6 +8,8 @@ Client command API (`ctx.commandUi`): the session-keyed command-directory cache, `CommandDirectory` (`src/client/directory.ts`) is the one wire-derived cache, keyed by session. Ordinary sessions fetch through `command.list({sessionId})`, and the source's scope-birth `warm` hook prewarms the session's entry. Catalog-addressed continuable children resolve an empty command directory locally: `command.list` is Agent-bound, so prewarming it would activate a child merely to view persisted history. Entries are soft-invalidated by the forwarded `commands/change` owner event (old snapshots serve while the repull flies) and by forwarded `agent-preset/selected` for that one session (recomposing an agent registers nothing, so the registry-wide signal never fires for it), hard-invalidated by `connection/reset`, and epoch-guarded so a superseded pull can never overwrite a newer one. `matchSpace` answers synchronously from this cache only; `matchEnter` strong-waits it on the SubmitAttempt signal and rejects on warmup failure — a `/` line is never silently downgraded to a plain prompt. +`matchEnter` also enforces the submission envelope: when the composer submits with image attachments, only a host command declaring `input.images` proceeds (its claim carries `images: true` and its submit forwards the serialized payloads to `command.execute`); every other command route — contribution popup, decorated popup, non-declaring claim, bare detached execute — throws the localized `notice.imagesUnsupported` refusal, which the input machine publishes as one error notice and the composer renders as a transient Toast banner with the draft and images retained. An image-carrying submit whose host handler answers an error result maps to an error outcome so the composer keeps the images; imageless submits keep the plain success mapping because the durable flow node owns the outcome rendering. + After `command.execute` returns a matched command result, this browser emits local `command/executed(sessionId, name, result)`. Other clients receive the durable command nodes through the Host event stream but never this acknowledgment, so a browser-only side effect can select successful results from the client that submitted the command without treating Session replay as an action request. Listener failures are logged and contained one by one; they cannot change the already-admitted command result or prevent later listeners from running. Menu queries fuzzy-match ordered, case-insensitive subsequences of command names. Prefixes rank first; separator boundaries, adjacent characters, and shorter gaps rank the remaining matches, with directory and contribution order breaking ties. This affects discovery only: space and Enter still require an exact command name. Rationale: [Web slash-command fuzzy discovery](../../../.agents/notes/implemented/feature/2026-08-04-web-slash-command-fuzzy-discovery.md). diff --git a/packages/client/ui-commands/README.zh.md b/packages/client/ui-commands/README.zh.md index 70d0b8b739..c69790b6e6 100644 --- a/packages/client/ui-commands/README.zh.md +++ b/packages/client/ui-commands/README.zh.md @@ -8,6 +8,8 @@ `CommandDirectory`（`src/client/directory.ts`）是唯一的 wire 派生缓存，以会话为 key。普通会话通过 `command.list({sessionId})` 拉取，source 的 scope 出生 `warm` 钩子会预热该会话的缓存项。由目录寻址的可继续子代理会在客户端解析为空命令目录：`command.list` 绑定 Agent，若预热它，就会仅因查看持久化历史而激活子代理。缓存项由转发的 owner 事件 `commands/change` 软失效（重拉在途期间旧快照继续服务），也由转发的 `agent-preset/selected` 对该会话单独软失效（重组 agent 不产生任何注册，注册表级信号不会为它触发），由 `connection/reset` 硬失效，并以 epoch 把关，被取代的旧拉取永远无法覆盖更新的结果。`matchSpace` 只凭该缓存同步应答；`matchEnter` 在 SubmitAttempt 信号上强等缓存，预热失败即拒绝——`/` 开头的一行绝不会被静默降级为普通提示词。 +`matchEnter` 还强制执行提交信封：composer 携带图片附件提交时，只有声明了 `input.images` 的宿主命令继续（其 claim 携带 `images: true`，其 submit 把序列化载荷转交 `command.execute`）；其余每条命令路径——contribution 弹窗、decoration 弹窗、未声明的 claim、bare 分离执行——都会抛出本地化的 `notice.imagesUnsupported` 拒绝，输入状态机发布一条错误通知，composer 以瞬态 Toast 横幅呈现它，草稿与图片原样保留。带图提交若宿主处理器返回错误结果，则映射为错误 outcome，composer 保留图片；不带图的提交维持原有的一律成功映射，因为结果呈现由持久化 flow 节点负责。 + `command.execute` 返回已匹配的命令结果后，当前浏览器会发布本地 `command/executed(sessionId, name, result)`。其他客户端只会通过 Host 事件流收到持久命令节点，不会收到这条确认，因此浏览器专属副作用可以筛选由实际提交命令的客户端收到的成功结果，而不会把 Session 回放当成操作请求。监听器失败会逐项记录并隔离，不会改变已经准入的命令结果，也不会阻止后续监听器运行。 菜单查询会按顺序且不区分大小写地模糊匹配命令名的子序列。前缀排名最高；其余匹配项按分隔符边界优先、相邻字符优先、间隔越短越优先的规则排序，若仍同分，则以目录顺序和贡献项顺序打破平局。此行为只影响命令发现：space 和 Enter 仍要求命令名精确匹配。原理：[Web 斜杠命令模糊发现](../../../.agents/notes/implemented/feature/2026-08-04-web-slash-command-fuzzy-discovery.zh.md)。 diff --git a/packages/client/ui-commands/package.json b/packages/client/ui-commands/package.json index c030024ff9..5cced81487 100644 --- a/packages/client/ui-commands/package.json +++ b/packages/client/ui-commands/package.json @@ -1,7 +1,7 @@ { "name": "@deepseek-ai/dsh-client-ui-commands", "description": "Client command surface: global directory cache, '/' source, three command UI kinds, popupSelect registry", - "version": "0.1.0-rc.7", + "version": "0.1.0-rc.8", "publishConfig": { "access": "public" }, diff --git a/packages/client/ui-commands/src/client/locales.ts b/packages/client/ui-commands/src/client/locales.ts index 63c5862cf2..1d04fe7eb7 100644 --- a/packages/client/ui-commands/src/client/locales.ts +++ b/packages/client/ui-commands/src/client/locales.ts @@ -9,6 +9,7 @@ export const zh = { 'status.empty': '无选项', 'overlay.aria': '/{command} 选项', 'listbox.aria': '/{command} 匹配项', + 'notice.imagesUnsupported': '/{command} 不接受图片附件，请先移除图片', } satisfies Record /** The command namespace key union. */ @@ -23,4 +24,5 @@ export const en = { 'status.empty': 'No options', 'overlay.aria': '/{command} options', 'listbox.aria': '/{command} matches', + 'notice.imagesUnsupported': '/{command} does not accept image attachments; remove them first', } satisfies Record diff --git a/packages/client/ui-commands/src/client/service.ts b/packages/client/ui-commands/src/client/service.ts index f9253c80d5..5db2033e29 100644 --- a/packages/client/ui-commands/src/client/service.ts +++ b/packages/client/ui-commands/src/client/service.ts @@ -14,9 +14,10 @@ import type { Context } from '@deepseek-ai/cordis' import type {} from '@deepseek-ai/dsh-api-remotes/client' import type { CommandResult } from '@deepseek-ai/dsh-commands/types' import type { ClientContext, ISessions, SessionId } from '@deepseek-ai/dsh-client-runtime/client' +import type { TranslateNS } from '@deepseek-ai/dsh-client-locale/client' import type { CandidateRequest, ClientSessionContext, CommandClaim, PickOutcome, InputTriggerCandidate, InputTriggerPick, - SubmitOutcome, + SubmitEnvelope, SubmitImageAttachment, SubmitOutcome, } from '@deepseek-ai/dsh-client-ui-input-trigger/client' import type { CommandContribution, CommandDecoration, CommandUiContract } from './contract.ts' import type { CommandDescriptor } from './directory.ts' @@ -122,6 +123,8 @@ export class CommandUiRuntime extends Service implements CommandUiContract { private readonly directory: CommandDirectory private readonly live: LiveState = { contributions: new Map(), decorations: new Map(), popups: new Map() } + /** `command`-namespace translator (composer refusal notices). */ + private readonly t: TranslateNS<'command'> /** * @param ctx - owning root context (plugin fiber; the service registers @@ -129,6 +132,9 @@ export class CommandUiRuntime extends Service implements CommandUiContract { */ constructor(ctx: Context) { super(ctx, 'commandUi') + const locale = ctx.get('locale') + if (locale === undefined) throw new Error('ui-commands: locale service unavailable') + this.t = locale.bind('command') this.directory = new CommandDirectory(async (sessionId) => { if (this.sessions().subagentAddress(sessionId) !== undefined) return [] const result = await ctx.remote.commands.list(sessionId) @@ -143,7 +149,7 @@ export class CommandUiRuntime extends Service implements CommandUiContract { candidates: (session, req) => this.candidates(session, req), onPick: pick => this.dispatch(pick), matchSpace: (session, token) => this.matchSpace(session, token), - matchEnter: (session, line, signal) => this.matchEnter(session, line, signal), + matchEnter: (session, line, signal, envelope) => this.matchEnter(session, line, signal, envelope), warm: (session) => { this.directory.warm(session.sessionId) }, }), 'command: slash source') ctx.remote.$on('commands/change', () => { this.directory.invalidateAll() }) @@ -302,8 +308,19 @@ export class CommandUiRuntime extends Service implements CommandUiContract { * warmup failure rejects — never a silent downgrade). Contributions and * bare host commands act on the bare token only; leadingInput claims * args-tolerant. + * + * Envelope policy: an enter submission carrying images resolves only + * through a command declaring image acceptance. Every other command route — + * popup, non-accepting claim, bare detached execute — throws the refusal + * so the machine surfaces one composer notice and the draft and images + * stay in place; nothing executes and nothing is dropped. */ - private async matchEnter(session: ClientSessionContext, line: string, signal: AbortSignal): Promise { + private async matchEnter( + session: ClientSessionContext, + line: string, + signal: AbortSignal, + envelope: SubmitEnvelope, + ): Promise { const trimmed = line.trim() if (!trimmed.startsWith('/')) return undefined const ws = trimmed.search(/\s/) @@ -311,9 +328,13 @@ export class CommandUiRuntime extends Service implements CommandUiContract { const bare = ws === -1 const name = token.slice(1) if (name === '') return undefined + const refuseImages = (): never => { + throw new Error(this.t('notice.imagesUnsupported', { command: name })) + } const contribution = this.live.contributions.get(name) if (contribution !== undefined && contribution.available(session)) { if (!bare) return undefined + if (envelope.images > 0) refuseImages() this.openPopup(name, contribution.ui, session, { via: 'enter', token }) return 'handled' } @@ -325,12 +346,17 @@ export class CommandUiRuntime extends Service implements CommandUiContract { if (bare) { const decoration = this.live.decorations.get(name) if (decoration !== undefined && decoration.available(session)) { + if (envelope.images > 0) refuseImages() this.openPopup(name, decoration.ui, session, { via: 'enter', token }) return 'handled' } } - if (desc.input !== undefined) return { claim: this.leadingClaim(desc, session) } + if (desc.input !== undefined) { + if (envelope.images > 0 && desc.input.images !== true) refuseImages() + return { claim: this.leadingClaim(desc, session) } + } if (!bare) return undefined + if (envelope.images > 0) refuseImages() this.consumeVia(session.sessionId, { via: 'enter', token }) this.runDetached(desc, session, trimmed) return 'handled' @@ -354,7 +380,8 @@ export class CommandUiRuntime extends Service implements CommandUiContract { return { token, ...(desc.input !== undefined ? { hint: desc.input.hint } : {}), - submit: (args, _actx) => this.execute(session, token + args), + ...(desc.input?.images === true ? { images: true } : {}), + submit: (args, _actx, images) => this.execute(session, token + args, images), } } @@ -365,16 +392,24 @@ export class CommandUiRuntime extends Service implements CommandUiContract { * plain success regardless of its handler outcome, because the host * executor durably logged the lifecycle (`command/run`/`command/done`) and * the outcome renders as a persistent flow node — the composer never - * echoes it. Transport failures throw. + * echoes it. A handler error result reports an error outcome so the + * composer keeps the submission (draft and images) for correction. + * Transport failures throw. */ private async execute( session: ClientSessionContext, line: string, + images: readonly SubmitImageAttachment[] = [], ): Promise { - const result = await this.ctx.remote.commands.execute(session.sessionId, line) + const result = await this.ctx.remote.commands.execute(session.sessionId, line, images) if (!result.ok) throw new Error(`command.execute failed: ${result.error.code}: ${result.error.message}`) if (result.value === undefined) return { kind: 'error', text: `unknown or malformed command: ${line}` } this.notifyExecuted(session.sessionId, submittedCommandName(line), result.value.result) + // An image-carrying submission consumed its images only on handler + // success; an error outcome keeps draft and images in the composer. + if (images.length > 0 && result.value.result.kind === 'error') { + return { kind: 'error', text: result.value.result.text } + } return { kind: 'success' } } diff --git a/packages/client/ui-commands/tests/service.client.spec.ts b/packages/client/ui-commands/tests/service.client.spec.ts index 08fa1de833..1d3bc796f4 100644 --- a/packages/client/ui-commands/tests/service.client.spec.ts +++ b/packages/client/ui-commands/tests/service.client.spec.ts @@ -12,7 +12,7 @@ import { describe, expect, it, vi } from 'vitest' import type { CommandResult } from '@deepseek-ai/dsh-commands/types' import { createScope, scopeOf } from '@deepseek-ai/dsh-client-runtime/client' import type { SessionId } from '@deepseek-ai/dsh-client-runtime/client' -import type { ClientSessionContext, ConsumeTokenRequest, InputTriggerPick, InputTriggerSource } from '@deepseek-ai/dsh-client-ui-input-trigger/client' +import type { ClientSessionContext, ConsumeTokenRequest, InputTriggerPick, InputTriggerSource, SubmitImageAttachment } from '@deepseek-ai/dsh-client-ui-input-trigger/client' import type { CommandContribution, CommandDecoration, CommandUiSpec, SelectOption } from '../src/client/contract.ts' import type { CommandDescriptor } from '../src/client/directory.ts' import { CommandUiRuntime } from '../src/client/service.ts' @@ -32,7 +32,7 @@ const S2_CMDS: CommandDescriptor[] = [ { name: 'attach', description: 'scoped shadow', input: { hint: 'path' } }, ] -type ExecuteValue = { matched: boolean; commandId?: string } +type ExecuteValue = { matched: boolean; commandId?: string; result?: CommandResult } interface BenchOptions { /** Scripted catalog per list payload; default serves the fixed catalogs by session. */ @@ -67,7 +67,7 @@ async function bench(opts: BenchOptions = {}) { const ctx = new Context() const registered = new Map() const listCalls: Array<{ sessionId: SessionId }> = [] - const executeCalls: Array<{ sessionId: SessionId; line: string }> = [] + const executeCalls: Array<{ sessionId: SessionId; line: string; images: readonly SubmitImageAttachment[] }> = [] // The service reads the generated commands Remote, which delivers the // carrier's outcome, so a programmed failure answers the error branch. const commandsRemote = { @@ -80,13 +80,13 @@ async function bench(opts: BenchOptions = {}) { return value.commands }) }, - execute: async (sessionId: SessionId, line: string) => { - executeCalls.push({ sessionId, line }) + execute: async (sessionId: SessionId, line: string, images: readonly SubmitImageAttachment[] = []) => { + executeCalls.push({ sessionId, line, images }) return await carried(async () => { const fallback = (): Promise => Promise.resolve({ matched: true }) const value = await (opts.execute ?? fallback)({ sessionId, line }) return value.matched - ? { commandId: value.commandId ?? 'fake-command', result: { kind: 'success' as const } } + ? { commandId: value.commandId ?? 'fake-command', result: value.result ?? { kind: 'success' as const } } : undefined }) }, @@ -98,6 +98,11 @@ async function bench(opts: BenchOptions = {}) { return () => { registered.delete(key) } }, }) + // Deterministic key-echo translator: notice assertions read `key{json}`. + ctx.provide('locale', { + bind: (ns: string) => (key: string, params?: Record) => + `${ns}:${key}${params === undefined ? '' : JSON.stringify(params)}`, + }) // Real scope tags behind a fake sessions face. const scopes = new Map } }>() ctx.provide('sessions', { @@ -297,9 +302,9 @@ describe('decorations (bare-invocation UI on host commands)', () => { command.decorate(goalDecoration()) const scope = mint('s1') await warm(proj('s1')) - expect(await source.matchEnter!(proj('s1'), '/goal', new AbortController().signal)).toBe('handled') + expect(await source.matchEnter!(proj('s1'), '/goal', new AbortController().signal, { images: 0 })).toBe('handled') expect(command.popupFor(scope.ctx).state.getSnapshot()).toMatchObject({ open: true, command: 'goal' }) - const argued = await source.matchEnter!(proj('s1'), '/goal ship it', new AbortController().signal) + const argued = await source.matchEnter!(proj('s1'), '/goal ship it', new AbortController().signal, { images: 0 }) if (argued === undefined || argued === 'handled' || !('claim' in argued)) throw new Error('expected the host claim') expect(argued.claim.token).toBe('/goal ') }) @@ -318,7 +323,7 @@ describe('decorations (bare-invocation UI on host commands)', () => { command.decorate(goalDecoration({ name: 'phantom' })) const scope = mint('s1') await warm(proj('s1')) - expect(await source.matchEnter!(proj('s1'), '/phantom', new AbortController().signal)).toBeUndefined() + expect(await source.matchEnter!(proj('s1'), '/phantom', new AbortController().signal, { images: 0 })).toBeUndefined() expect(menuPick(source, 'phantom', proj('s1'))).toBeUndefined() expect(command.popupFor(scope.ctx).state.getSnapshot().open).toBe(false) }) @@ -327,8 +332,8 @@ describe('decorations (bare-invocation UI on host commands)', () => { const { command, source, warm, executeCalls } = await bench() command.decorate(goalDecoration({ name: 'plan', available: () => false })) await warm(proj('s1')) - expect(await source.matchEnter!(proj('s1'), '/plan', new AbortController().signal)).toBe('handled') - expect(executeCalls).toEqual([{ sessionId: sid('s1'), line: '/plan' }]) + expect(await source.matchEnter!(proj('s1'), '/plan', new AbortController().signal, { images: 0 })).toBe('handled') + expect(executeCalls).toEqual([{ sessionId: sid('s1'), line: '/plan', images: [] }]) }) it('duplicate decoration names fail loud', async () => { @@ -383,7 +388,7 @@ describe('dispatch (menu column)', () => { expect(menuPick(source, 'plan', proj('s1'), 5)).toBe('handled') expect(consumes).toEqual([{ guard: { kind: 'span', span: { start: 0, end: 5, draftRev: 3 } } }]) await vi.waitFor(() => { - expect(executeCalls).toEqual([{ sessionId: sid('s1'), line: '/plan' }]) + expect(executeCalls).toEqual([{ sessionId: sid('s1'), line: '/plan', images: [] }]) expect(executions).toEqual([{ sessionId: sid('s1'), name: 'plan', @@ -440,7 +445,7 @@ describe('matchEnter (enter column)', () => { const { source } = await bench({ commands: () => new Promise((resolve) => { release = resolve }), }) - const wait = source.matchEnter!(proj('s1'), '/goal args', signal()) + const wait = source.matchEnter!(proj('s1'), '/goal args', signal(), { images: 0 }) release({ commands: S1_CMDS }) const outcome = await wait if (outcome === undefined || outcome === 'handled' || !('claim' in outcome)) throw new Error('expected claim') @@ -451,14 +456,14 @@ describe('matchEnter (enter column)', () => { const { source } = await bench({ commands: () => Promise.reject(new Error('warmup boom')), }) - await expect(source.matchEnter!(proj('s1'), '/goal', signal())).rejects.toThrow('warmup boom') + await expect(source.matchEnter!(proj('s1'), '/goal', signal(), { images: 0 })).rejects.toThrow('warmup boom') }) it('leadingInput claims args-tolerant (bare and with trailing text)', async () => { const { source, warm } = await bench() await warm(proj('s1')) for (const line of ['/goal', '/goal refactor the loop']) { - const outcome = await source.matchEnter!(proj('s1'), line, signal()) + const outcome = await source.matchEnter!(proj('s1'), line, signal(), { images: 0 }) if (outcome === undefined || outcome === 'handled' || !('claim' in outcome)) throw new Error('expected claim') expect(outcome.claim.token).toBe('/goal ') } @@ -473,16 +478,16 @@ describe('matchEnter (enter column)', () => { return true }) await warm(proj('s1')) - await expect(source.matchEnter!(proj('s1'), '/plan', signal())).resolves.toBe('handled') + await expect(source.matchEnter!(proj('s1'), '/plan', signal(), { images: 0 })).resolves.toBe('handled') expect(consumes).toEqual([{ guard: { kind: 'bare-token', token: '/plan' } }]) await Promise.resolve() - expect(executeCalls).toEqual([{ sessionId: sid('s1'), line: '/plan' }]) + expect(executeCalls).toEqual([{ sessionId: sid('s1'), line: '/plan', images: [] }]) }) it('bare kind with trailing text → undefined and no RPC (default sink owns the line)', async () => { const { source, warm, executeCalls } = await bench() await warm(proj('s1')) - await expect(source.matchEnter!(proj('s1'), '/plan now', signal())).resolves.toBeUndefined() + await expect(source.matchEnter!(proj('s1'), '/plan now', signal(), { images: 0 })).resolves.toBeUndefined() expect(executeCalls).toEqual([]) }) @@ -490,18 +495,86 @@ describe('matchEnter (enter column)', () => { const { command, source, mint, listCalls } = await bench() command.register(themeContribution()) const scope = mint('s1') - await expect(source.matchEnter!(proj('s1'), '/theme', signal())).resolves.toBe('handled') + await expect(source.matchEnter!(proj('s1'), '/theme', signal(), { images: 0 })).resolves.toBe('handled') expect(command.popupFor(scope.ctx).state.getSnapshot().open).toBe(true) expect(listCalls).toEqual([]) // contribution short-circuits ahead of ensureReady - await expect(source.matchEnter!(proj('s1'), '/theme dark', signal())).resolves.toBeUndefined() + await expect(source.matchEnter!(proj('s1'), '/theme dark', signal(), { images: 0 })).resolves.toBeUndefined() }) it('unknown name, bare "/", and non-slash lines → undefined', async () => { const { source, warm } = await bench() await warm(proj('s1')) - await expect(source.matchEnter!(proj('s1'), '/nope', signal())).resolves.toBeUndefined() - await expect(source.matchEnter!(proj('s1'), '/', signal())).resolves.toBeUndefined() - await expect(source.matchEnter!(proj('s1'), 'plain text', signal())).resolves.toBeUndefined() + await expect(source.matchEnter!(proj('s1'), '/nope', signal(), { images: 0 })).resolves.toBeUndefined() + await expect(source.matchEnter!(proj('s1'), '/', signal(), { images: 0 })).resolves.toBeUndefined() + await expect(source.matchEnter!(proj('s1'), 'plain text', signal(), { images: 0 })).resolves.toBeUndefined() + }) +}) + +describe('matchEnter envelope policy (images)', () => { + const signal = () => new AbortController().signal + const IMG_CMDS: CommandDescriptor[] = [ + ...S1_CMDS, + { name: 'vision', description: 'image-accepting leadingInput', input: { hint: 'describe', images: true } }, + ] + const png: SubmitImageAttachment = { mediaType: 'image/png', data: 'AA==' } + + it('a leadingInput command not declaring acceptance refuses; a declaring one claims with images minted', async () => { + const { source, warm } = await bench({ commands: () => Promise.resolve({ commands: IMG_CMDS }) }) + await warm(proj('s1')) + await expect(source.matchEnter!(proj('s1'), '/goal ship', signal(), { images: 1 })) + .rejects.toThrow('command:notice.imagesUnsupported{"command":"goal"}') + const outcome = await source.matchEnter!(proj('s1'), '/vision what is this', signal(), { images: 1 }) + if (outcome === undefined || outcome === 'handled' || !('claim' in outcome)) throw new Error('expected claim') + expect(outcome.claim.token).toBe('/vision ') + expect(outcome.claim.images).toBe(true) + }) + + it('bare popup routes refuse images: contribution and decorated host both stay closed', async () => { + const { command, source, mint, warm } = await bench() + command.register(themeContribution()) + command.decorate({ name: 'plan', available: () => true, ui: themeUi() }) + const scope = mint('s1') + await warm(proj('s1')) + await expect(source.matchEnter!(proj('s1'), '/theme', signal(), { images: 1 })) + .rejects.toThrow('command:notice.imagesUnsupported{"command":"theme"}') + await expect(source.matchEnter!(proj('s1'), '/plan', signal(), { images: 2 })) + .rejects.toThrow('command:notice.imagesUnsupported{"command":"plan"}') + expect(command.popupFor(scope.ctx).state.getSnapshot().open).toBe(false) + }) + + it('bare host detached execute refuses images before any RPC', async () => { + const { source, warm, executeCalls } = await bench() + await warm(proj('s1')) + await expect(source.matchEnter!(proj('s1'), '/plan', signal(), { images: 1 })) + .rejects.toThrow('command:notice.imagesUnsupported{"command":"plan"}') + expect(executeCalls).toEqual([]) + }) + + it('claim.submit forwards the images to execute; consumption follows the handler outcome', async () => { + let result: CommandResult = { kind: 'error', text: 'handler refused' } + const { source, warm, executeCalls } = await bench({ + commands: () => Promise.resolve({ commands: IMG_CMDS }), + execute: () => Promise.resolve({ matched: true, result }), + }) + await warm(proj('s1')) + const outcome = await source.matchEnter!(proj('s1'), '/vision x', signal(), { images: 1 }) + if (outcome === undefined || outcome === 'handled' || !('claim' in outcome)) throw new Error('expected claim') + // Handler error: the error outcome keeps draft and images in the composer. + await expect(outcome.claim.submit('x', new Context(), [png])) + .resolves.toEqual({ kind: 'error', text: 'handler refused' }) + expect(executeCalls).toEqual([{ sessionId: sid('s1'), line: '/vision x', images: [png] }]) + result = { kind: 'success', text: 'described' } + await expect(outcome.claim.submit('x', new Context(), [png])).resolves.toEqual({ kind: 'success' }) + }) + + it('an imageless submission keeps the always-success admission mapping over a handler error', async () => { + const { source, warm } = await bench({ + execute: () => Promise.resolve({ matched: true, result: { kind: 'error', text: 'late failure' } }), + }) + await warm(proj('s1')) + const outcome = source.matchSpace!(proj('s1'), '/goal') + if (outcome === undefined || outcome === 'handled' || !('claim' in outcome)) throw new Error('expected claim') + await expect(outcome.claim.submit('x', new Context(), [])).resolves.toEqual({ kind: 'success' }) }) }) @@ -513,8 +586,8 @@ describe('execute payload', () => { await warm(proj('s1')) const outcome = source.matchSpace!(proj('s1'), '/goal') if (outcome === undefined || outcome === 'handled' || !('claim' in outcome)) throw new Error('expected claim') - const settled = await outcome.claim.submit('ship it', new Context()) - expect(executeCalls).toEqual([{ sessionId: sid('s1'), line: '/goal ship it' }]) + const settled = await outcome.claim.submit('ship it', new Context(), []) + expect(executeCalls).toEqual([{ sessionId: sid('s1'), line: '/goal ship it', images: [] }]) // Pure admission: no outcome text ever rides the submit result — the // durable command lifecycle events render the outcome in the flow. expect(settled).toEqual({ kind: 'success' }) @@ -539,7 +612,7 @@ describe('execute payload', () => { b.ctx.on('command/executed', rejectingListener) b.ctx.on('command/executed', after) - await expect(outcome.claim.submit('ship it', new Context())).resolves.toEqual({ kind: 'success' }) + await expect(outcome.claim.submit('ship it', new Context(), [])).resolves.toEqual({ kind: 'success' }) expect(after).toHaveBeenCalledOnce() await Promise.resolve() await Promise.resolve() @@ -557,10 +630,10 @@ describe('execute payload', () => { return outcome.claim } const first = await claimOf({ execute: () => Promise.resolve({ matched: false }) }) - const bad = await first.submit('x', new Context()) + const bad = await first.submit('x', new Context(), []) expect(bad.kind).toBe('error') const second = await claimOf({ execute: () => Promise.resolve({ matched: true }) }) - await expect(second.submit('', new Context())).resolves.toEqual({ kind: 'success' }) + await expect(second.submit('', new Context(), [])).resolves.toEqual({ kind: 'success' }) }) }) @@ -584,7 +657,7 @@ describe('detached admission notices', () => { // Admission miss (matched:false): immediate composer feedback stays. mode = 'miss' - await source.matchEnter!(proj('s1'), '/plan', new AbortController().signal) + await source.matchEnter!(proj('s1'), '/plan', new AbortController().signal, { images: 0 }) await flush() expect(notices).toEqual([{ scope: sid('s1'), level: 'error', text: 'unknown or malformed command: /plan' }]) @@ -663,7 +736,7 @@ describe('popupFor', () => { consumes.push(r) return true }) - await source.matchEnter!(proj('s1'), '/theme', new AbortController().signal) + await source.matchEnter!(proj('s1'), '/theme', new AbortController().signal, { images: 0 }) const popup = command.popupFor(scope.ctx) await Promise.resolve() await popup.select(0) @@ -674,7 +747,7 @@ describe('popupFor', () => { const { command, source, mint } = await bench() command.register(themeContribution()) const scope = mint('s1') - await source.matchEnter!(proj('s1'), '/theme', new AbortController().signal) + await source.matchEnter!(proj('s1'), '/theme', new AbortController().signal, { images: 0 }) const popup = command.popupFor(scope.ctx) expect(popup.state.getSnapshot().open).toBe(true) diff --git a/packages/client/ui-conversation/README.i18n.yaml b/packages/client/ui-conversation/README.i18n.yaml index 96e11177c4..b087acd7ce 100644 --- a/packages/client/ui-conversation/README.i18n.yaml +++ b/packages/client/ui-conversation/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 packages/client/ui-conversation/README.md -README.md: d1a265b5789d9f1d9b5e630e0548ae5f619eebbf -README.zh.md: b1c0a502ce8e5985851afff16717e4b0c4c36986 +README.md: a90d1d9dd8156fc1063dc7358374f8b1715deb1a +README.zh.md: a2d514af398f8a023f21b3308477bb6236bf6786 diff --git a/packages/client/ui-conversation/README.md b/packages/client/ui-conversation/README.md index d1a265b578..a90d1d9dd8 100644 --- a/packages/client/ui-conversation/README.md +++ b/packages/client/ui-conversation/README.md @@ -6,7 +6,7 @@ Conversation domain: skeleton (header/tabs/composer/empty state), chat view (gro Compaction renders as one collapsed row at the checkpoint's flow position without replacing the transcript above it. Automatic compaction uses the context-compacted title. Every completed marker with a loaded `compaction/summary` event shows the replaced-item and estimated-token counts and discloses the summary on click. Manual `/compact` starts as a running `compact` row; on successful settlement its explicit summary-event reference folds that command into the checkpoint row under the same React key. A completed checkpoint keeps the context-compaction icon at rest and replaces it with the collapsed or expanded disclosure only on hover or keyboard focus. Input rejection, no compactable history, cancellation, and failure retain the generic command row and its handler-authored text. Pairing never depends on adjacency because durable context may be injected while compaction is running. The framed checkpoint payload is model-facing and never renders; when the cited `compaction/summary` event is outside the loaded window, the checkpoint remains visible but non-expandable. -The resident conversation shell survives no-session and session transitions. Without a current session it locks message actions and presents the whole dashed composer card as a trigger for the root-scoped `conversation.hero.workspace` Workspace picker; the textarea remains read-only and keyboard-accessible. Selecting a Workspace connects or reuses its Host-owned blank session and opens that session without replacing the shell. The root always owns the same scrollport and Hero/composer subtree; separate strict-session header and body outlets fill their regions when the first Session arrives, so the Workspace picker, scroll body, composer seat, and textarea retain their React and DOM identity. Blank sessions render the same composer body as active sessions, while the InputHub carries drafts across Workspace switches and mirrors them into the session store. In the active phase the session header shows only the current session title and view tabs as ordinary column chrome; fork lineage remains session data and is not projected into the header. Beneath it the scrollport (`data-conversation-scroll`) holds the flowing views and the sticky composer stack (stats dock + input docks + bar). That scrollport reserves its scrollbar gutter unconditionally, and a view opting into a composer overlay leaves it a scroll container, so the input card keeps one horizontal position whether or not the transcript scrolls and whichever view tab is shown ([decision](../../../.agents/notes/implemented/bug-fix/2026-08-04-composer-tab-gutter-reservation.md)). Wheel over the textarea chains: the capped draft scrolls locally until its edge, then forwards to that host. Safari alone receives a pre-paint recovery when a native edit shortens the draft and leaves stale soft-wrap overflow; draft growth, programmatic updates, and other browsers never read layout for that recovery ([decision](../../../.agents/notes/implemented/bug-fix/2026-08-13-safari-textarea-soft-wrap-reflow.md)). +The resident conversation shell survives no-session and session transitions. Without a current session it locks message actions and presents the whole dashed composer card as a trigger for the root-scoped `conversation.hero.workspace` Workspace picker; the textarea remains read-only and keyboard-accessible. The Hero's leading mark is the independent root-scoped `conversation.hero.brand.mark` slot, with the fish mark as its fallback. Selecting a Workspace connects or reuses its Host-owned blank session and opens that session without replacing the shell. The root always owns the same scrollport and Hero/composer subtree; separate strict-session header and body outlets fill their regions when the first Session arrives, so the Workspace picker, scroll body, composer seat, and textarea retain their React and DOM identity. Blank sessions render the same composer body as active sessions, while the InputHub carries drafts across Workspace switches and mirrors them into the session store. In the active phase the session header shows only the current session title and view tabs as ordinary column chrome; fork lineage remains session data and is not projected into the header. Beneath it the scrollport (`data-conversation-scroll`) holds the flowing views and the sticky composer stack (stats dock + input docks + bar). That scrollport reserves its scrollbar gutter unconditionally, and a view opting into a composer overlay leaves it a scroll container, so the input card keeps one horizontal position whether or not the transcript scrolls and whichever view tab is shown ([decision](../../../.agents/notes/implemented/bug-fix/2026-08-04-composer-tab-gutter-reservation.md)). Wheel over the textarea chains: the capped draft scrolls locally until its edge, then forwards to that host. Safari alone receives a pre-paint recovery when a native edit shortens the draft and leaves stale soft-wrap overflow; draft growth, programmatic updates, and other browsers never read layout for that recovery ([decision](../../../.agents/notes/implemented/bug-fix/2026-08-13-safari-textarea-soft-wrap-reflow.md)). Another plugin can make one session's composer inert through `ctx.conversation.blocks`: it sets a block carrying its own localized reason, and the bar renders the same disabled textarea with that reason as the placeholder — the no-workspace posture, reused. The push direction is the constraint, not a preference: the plugins that know a session cannot send (ui-model-selection, when no adapter serves its route) already depend on this package, so this package cannot read them. The model seat is the one control a block leaves live — every block this contract has is cleared by choosing a model, so locking it too would leave the composer asking for the only thing it prevents. A block is an affordance only; the Host refuses a prompt it cannot route regardless of what any client disables. The no-workspace state wins when both hold, because picking a workspace is the earlier prerequisite. @@ -14,15 +14,15 @@ The view ring is a slot: the strict session-body registration declares the sessi Chat business rows are independent registry contributions rather than a closed built-in union. A client plugin declaration-merges its typed `ChatNodeDataMap` key, registers a `ConversationNodeDefinition` on `ctx.conversationEvents`, and registers the matching keyed renderer on `conversation.chat.node`; it does not modify Session folds or a central renderer switch. The [Conversation Node cookbook](../../../docs/cookbook/adding-a-conversation-node.md) covers stable event ids, append/prepend replay, Location data, and renderer constraints. -Approvals take over the composer through the chain this package declares: `ApprovalPanel` registers as a selector-routed `'conversation.composer'` entry (the ui-user-questions pattern) and occupies the composer in place of the InputBar while an approval wait is pending (amber strip, justification headline, paired command line from the running call's args, one-shot refuse/allow). The `PendingApproval` domain face in `contract/slots.ts` owns the wire encoding — the `ApprovalResponsePayload` value with the audit correlation — over the runtime's `PendingWait` carrier; the broadcast `approval/resolved` frame settles the wait and restores the composer. The runtime manager projects every approval or question wait through `SessionSummary.pendingInteraction`, including sessions never instantiated; `ui-workspace` owns its sidebar presentation. Pending waits leave the message flow entirely: questions (ui-user-questions) and approvals (ApprovalPanel) both answer through the composer takeover, so no display-only placeholder card remains. The composer's bottom-row Access seat mounts `PermissionSelect`, fed by the host-computed `permissions` projection through the standard-kit `useProjection` (key absence hides the chip); the chip opens a Menu-primitive dropdown whose kebab-case preset names render as title-case labels. Safe preset picks submit `/permission ` immediately through the bar's injected `command` callback, while `danger-full-access` is presented as `Full access` and first opens an in-page Modal risk confirmation. The enabling action stays disabled until the user checks the acknowledgement; cancel, Escape, close, and mask click submit nothing. +Approvals take over the composer through the chain this package declares: `ApprovalPanel` registers as a selector-routed `'conversation.composer'` entry (the ui-user-questions pattern) and occupies the composer in place of the InputBar while an approval wait is pending (amber strip, justification headline, paired command line from the running call's args, one-shot refuse/allow). The `PendingApproval` domain face in `contract/slots.ts` owns the wire encoding — the `ApprovalResponsePayload` value with the audit correlation — over the runtime's `PendingWait` carrier; the broadcast `approval/resolved` frame settles the wait and restores the composer. The runtime manager projects every approval or question wait through `SessionSummary.pendingInteraction`, including sessions never instantiated; `ui-workspace` owns its sidebar presentation. Pending waits leave the message flow entirely: questions (ui-user-questions) and approvals (ApprovalPanel) both answer through the composer takeover, so no display-only placeholder card remains. The composer's bottom-row Access seat mounts `PermissionSelect`, fed by the host-computed `permissions` projection through the standard-kit `useProjection` (key absence hides the chip); the chip opens a Menu-primitive dropdown whose built-in preset ids render as localized product labels only when the host keeps their canonical names, while explicit host labels remain unchanged and unknown kebab-case names render in title case. Safe preset picks submit `/permission ` immediately through the bar's injected `command` callback, while `danger-full-access` first opens an in-page Modal risk confirmation. The enabling action stays disabled until the user checks the acknowledgement; cancel, Escape, close, and mask click submit nothing. The session header renders the session-scoped `'conversation.session.header.actions'` list beside the title and the independent `'conversation.session.header.utilities'` list at the right edge. Session context and lineage controls remain in `actions`; optional Session utilities cannot reorder or move them. The composer chain currency includes the current conversation `session`; ui-subagent selects one-shot or parent-unavailable addressed sessions for reason-specific read-only copy, while the ordinary InputBar keeps every addressed child Send-only because the continuation service exposes no public per-Activation cancellation operation and `session.cancel` would bypass its ownership. -Logged non-user messages render as a default-collapsed disclosure whose header names the role the runtime projected for the message — `上下文注入` for an injection, `跨会话召回` for a recalled session — followed by the producer name that projection read out of the durable source, so a reader distinguishes a skill catalog from a workspace instruction file or a recalled session without expanding. A source that names no producer shows the role alone. The shared `DisclosureRow` primitive gives this context surface the same compact geometry as other flow rows while retaining context semantics: the expanded body follows its content height up to a 141px scrolling cap and synthesizes no tool state or summary ([historical disclosure decision](../../../.agents/notes/archived/feature/2026-07-30-web-context-injection-disclosure.md), [producer-label decision](../../../.agents/notes/implemented/feature/2026-08-04-web-context-source-and-steer-marks.md)). That body follows the form the producer declared on its durable source: `instructions` names the reconciled files above their text, `catalog` lists the entries the source recorded instead of the model-facing prose, and every other value — absent, unknown to this version, or carrying no usable fields — renders the opaque body, which shows the model-facing text with its real line breaks and the remaining source fields. The opaque body is the documented default, not a leftover: a resumed, forked, or foreign log must render whether or not its producer is mounted here. A durable or pending steering bubble shares the user bubble's presentation unadorned; its mid-turn position in the flow is the only steering signal the transcript shows. +Logged non-user messages render as a default-collapsed disclosure whose header names the role the runtime projected for the message — `上下文注入` for an injection, `跨会话召回` for a recalled session — followed by the producer name that projection read out of the durable source, so a reader distinguishes a skill catalog from a workspace instruction file or a recalled session without expanding. A direct message that cites another session precedes its recall row in durable order. The Chat snapshot associates exact labels only from that immediately following sourced recall, preserving multi-word titles without carrying one recall's labels onto a later direct message. Recall uses a chat-bubble glyph while other context keeps the document glyph; a source that names no producer shows the role alone. Composer and user-bubble references use the same inline language: a chat-bubble, file, or folder glyph plus business-color text, without a nested capsule. Like claimed slash commands, composer references keep their complete display text in the transparent textarea and use the aligned backdrop for color and the leading domain glyph; native text metrics own width, wrapping, selection, and caret placement. The occurrence range remains structured for serialization and boundary deletion, while an edit inside it converts the remaining characters to ordinary text. The session draft mirror stores each occurrence's clipboard projection, so a remount without the occurrence table restores canonical parseable reference text instead of a display-only label. The shared `DisclosureRow` primitive gives this context surface the same compact geometry as other flow rows while retaining context semantics: the expanded body follows its content height up to a 141px scrolling cap and synthesizes no tool state or summary ([historical disclosure decision](../../../.agents/notes/archived/feature/2026-07-30-web-context-injection-disclosure.md), [producer-label decision](../../../.agents/notes/implemented/feature/2026-08-04-web-context-source-and-steer-marks.md)). That body follows the form the producer declared on its durable source: `instructions` names the reconciled files above their text, `catalog` lists the entries the source recorded instead of the model-facing prose, and every other value — absent, unknown to this version, or carrying no usable fields — renders the opaque body, which shows the model-facing text with its real line breaks and the remaining source fields. The opaque body is the documented default, not a leftover: a resumed, forked, or foreign log must render whether or not its producer is mounted here. A durable or pending steering bubble shares the user bubble's presentation unadorned; its mid-turn position in the flow is the only steering signal the transcript shows. A Think row stays collapsed by default and exposes live reasoning throughput without expanding the chain of thought: while its reasoning block is the streaming tail, the summary switches from the settled first line to the latest non-blank line and its one-line scrollport follows each delta to the inline end. Expanding the row removes the moving summary and leaves the full reasoning in ordinary page flow, so page reading never fights an internal follower; settlement restores the stable first-line summary at the left edge ([decision](../../../.agents/notes/implemented/feature/2026-08-02-web-thinking-tail-scroll.md)). -The chat view keeps Tool placement but delegates Tool presentation. Each ordered `tool-call` Conversation Node dispatches through the matching key of `conversation.chat.node`, while the details shell passes the selected call through `conversation.details.tool`. The assembled Web bundle registers [`ui-tool`](../ui-tool/README.md) for that Chat Node key; it renders the Runtime-projected recursive root/child tree and owns per-name dispatch, generic rendering, and render-intent cards. The details seat alone retains a raw-result fallback when that renderer is absent. +The chat view keeps Tool placement but delegates Tool presentation. Each ordered `tool-call` Conversation Node dispatches through the matching key of `conversation.chat.node`, while the details shell passes the selected call through `conversation.details.tool`. The assembled Web bundle registers [`ui-tool`](../ui-tool/README.md) for that Chat Node key; it renders the Runtime-projected recursive root/child tree and owns per-name dispatch, generic rendering, and render-intent cards. The details seat alone retains a raw-result fallback when that renderer is absent. A path click through the injected `openFile` asks the Host to open that path (relative paths resolve against the session cwd). A Host or OS refusal opens an in-page dialog with the thrown reason and a Retry of the same path; Cancel, Escape, the close control, and a mask click dismiss it ([decision](../../../.agents/notes/implemented/bug-fix/2026-08-18-tool-row-file-open-failure.md)). The chat flow projects consecutive model-retry nodes across retry turns into one stable, muted status row updated to the latest attempt; every retry event remains in the runtime snapshot and session log. Its frontend countdown anchors the scheduled delay to client receipt, avoiding host/browser clock skew, rounds remaining time up to seconds, and has a one-second floor. The latest unresolved retry uses a left-to-right text shimmer. Subsequent turn facts distinguish an attempt that started from one cancelled during backoff, while the Host running bit only controls the live animation; the row then shows a static completed or cancelled label. Normal policy rows show the finite retry maximum; always policy rows show `∞`. Activating the row reveals the latest exact retry delay and failure message. The client runtime removes each failed step's streaming tail before its retry node arrives, while the status remains visible after a later attempt succeeds. An unretried terminal failure renders as a persistent inline status at its turn boundary, showing the display-safe durable message and optional error code without offering an action the Host cannot fulfill; AUTH copy never echoes provider-supplied credential fragments. @@ -36,11 +36,11 @@ Keyboard message submission resolves delivery from the addressed session's runni Per-session UI state for selection and the active view lives in the declared chat store (`stores.ts` `createChatStore`); the InputHub owns the composer state machine and mirrors its draft into that store for persistence. Apply passes one store handle to the strict session subtree, chat view, and details registrations, so each session shares one instance and the framework owns its lifecycle. Components are pure: the framework standard kit supplies `useSession`/`sessionId`, global `useSessions`/`useWorkspaces`, and the input machine's `useInput`/`inputActions`; store faces and inject factories supply the remaining state and callbacks. -Image intake accepts paste and whole-page drop: the bar binds document-level drag listeners (the composer-bar slot is `kind: 'single'`, so at most one bar binds them) and shows the `DropOverlay` atom while a file drag is over the window — text drags pass through untouched, and a locked or busy composer shows the blocked overlay and refuses the drop. Both gestures feed one intake pre-check against the host's `imageLimits` projection (count, per-image bytes, aggregate bytes): an addition that would break a limit is refused as a whole batch with an immediate banner naming the limit, and never enters the rail. Host-side rejections that arrive anyway surface as product copy mapped from the `attachment-error` reason (`image-labels.ts` `attachmentErrorText`); reasons the user cannot act on fold into one send-failed line carrying the reason code, and non-attachment error codes keep their developer-facing message plus code. +Image intake accepts paste and whole-page drop: the bar binds document-level drag listeners (the composer-bar slot is `kind: 'single'`, so at most one bar binds them) and shows the `DropOverlay` atom while a file drag is over the window — text drags pass through untouched, and a locked or busy composer shows the blocked overlay and refuses the drop. Both gestures feed one intake pre-check against the host's `imageLimits` projection (count, per-image bytes, aggregate bytes): an addition that would break a limit is refused as a whole batch with an immediate banner naming the limit, and never enters the rail. Host-side rejections that arrive anyway surface as product copy mapped from the `attachment-error` reason (`image-labels.ts` `attachmentErrorText`); reasons the user cannot act on fold into one send-failed line carrying the reason code, and non-attachment error codes keep their developer-facing message plus code. Attached images are part of the submission envelope on every send path: a slash-command submit either consumes them (a claim declaring `images` has them serialized through the hub's `commandImages` plumbing, passed to `claim.submit`, and cleared plus released only on a success outcome) or refuses the whole submission with the `command.imagesUnsupported` notice while draft and images stay in place — a command can never consume the text and strand the images. The composer bar declares session-scoped single seats for `'conversation.input.plan'` (right of the local access-mode control) and `'conversation.input.model'` (immediately before the pending indicator and send/stop controls), plus list slots for overlay, dock, left, and right input extensions. Feature packages own each control and its state; ui-conversation supplies placement, the `locked` owner prop, and the standard slot shares. The leading plus button is a Command launcher, not an attachment surface: it asks the session's `InputTriggerController` to open only the `/` trigger's `command` source over the current textarea selection, while ui-input-trigger's existing `MenuView` remains the sole floating menu and pick path. No file row, file input, upload protocol, or second menu component is introduced. While the `plan` projection's effective target is plan mode, InputBar swaps its textarea placeholder to the plan-task wording, localized through the `conversation` locale namespace this package registers (the `placeholder.plan` / `hint.plan` keys) and shared verbatim with the claimed `/plan` command hint (a host-folded value read through the standard-kit `useProjection`; owner-supplied placeholders win). A pending composer takeover remains mounted when another conversation view is active so the blocked agent can still receive its answer; without a pending interaction, the active-session composer belongs to Chat. The composer-bar slot itself is `session-maybe`: with no current session the same bar keeps message actions inert (machine faces absent, `disabled` owner prop), while the whole dashed card opens the existing Workspace picker by pointer and the read-only textarea opens it through Enter or Space. Disabled controls release pointer events to the card, and the card contains `pointerdown` so the open picker's outside-close cannot race a reopen. The bar never swaps in a parallel tree, so the textarea DOM survives Workspace selection; strict-session control seats stay empty until a session exists. -The chat stats line takes its token accounting from the generic token-meter `tokenUsage` projection read through the standard-kit `useProjection`: billed input is uncached input plus cache reads and writes; cache hit divides cache reads by that total. The turn and step counts, the LLM and tool wall times, and the latency/throughput group all ride the whole-log `sessionStats` projection (host-folded from step boundaries, first-token chunks, tool pairs, and assembled messages), so paging and compaction cannot change any strip figure; an assembly without that unit falls back to the window fold over visible nodes, whose fields mirror the projection's. The strip averages each recorded step's TTFT and divides sampled output tokens by their summed decode spans into a latency/throughput group localized through the `conversation` locale namespace (`TTFT avg … · … tok/s` in English); a step missing a timing boundary or a usage sample drops out of those figures instead of skewing them, and durable count, token, and context groups remain visible when compaction leaves no assistant node in the loaded window. The turn-count, step-count, duration, cache, and token labels use the same namespace. Each settled turn additionally appends hover-revealed `TTFT {s}s · {tps} tok/s` labels to its assistant footer after the `Ran for` duration — the turn's first-step TTFT and its turn-aggregate decode throughput — gated on the turn's timing being in the loaded window (a contiguous log suffix, so an in-window turn carries every one of its steps) and omitting whichever figure is unrecorded. A deployment without token-meter drops the token groups; when the line overflows, it elides with an ellipsis and a delayed hover tooltip carries the full text only while actually clipped. Context occupancy renders as the composer's trailing ContextMeter: a 14px occupancy ring after the model seat, fed by `contextPressure` and rendered only once both a numerator and a route capacity are known, that click-opens a panel pairing the `percent used` header and `~used / capacity` figures with a color-segmented bar and `~`-prefixed heuristic composition rows (system prompt, tools, messages) from the `contextBreakdown` projection. The ring and header read `projectedTokens` — the provider sample carried forward over the surface's movement since — so a compaction registers immediately instead of after a further turn; the composition rows stay wholly heuristic and therefore still do not sum to the header ([rationale](../../llm/token-meter/README.md)). Occupancy is deliberately an approximation: numerator and capacity are independent last-wins projection fields, not one atomic request observation. +The chat stats line takes its token accounting from the generic token-meter `tokenUsage` projection read through the standard-kit `useProjection`: billed input is uncached input plus cache reads and writes; cache hit divides cache reads by that total. Every non-empty ratio starts with integer rounding. A non-full ratio adds decimal places only while the current precision would round to 100%, stopping at the minimum precision that remains below 100%; only a full cache hit displays 100%, and the precision has no fixed limit. The turn and step counts, the LLM and tool wall times, and the latency/throughput group all ride the whole-log `sessionStats` projection (host-folded from step boundaries, first-token chunks, tool pairs, and assembled messages), so paging and compaction cannot change any strip figure; an assembly without that unit falls back to the window fold over visible nodes, whose fields mirror the projection's. The strip averages each recorded step's TTFT and divides sampled output tokens by their summed decode spans into a latency/throughput group localized through the `conversation` locale namespace (`TTFT avg … · … tok/s` in English); a step missing a timing boundary or a usage sample drops out of those figures instead of skewing them, and durable count, token, and context groups remain visible when compaction leaves no assistant node in the loaded window. The turn-count, step-count, duration, cache, and token labels use the same namespace. Each settled turn additionally appends hover-revealed `TTFT {s}s · {tps} tok/s` labels to its assistant footer after the `Ran for` duration — the turn's first-step TTFT and its turn-aggregate decode throughput — gated on the turn's timing being in the loaded window (a contiguous log suffix, so an in-window turn carries every one of its steps) and omitting whichever figure is unrecorded. A deployment without token-meter drops the token groups; when the line overflows, it elides with an ellipsis and a delayed hover tooltip carries the full text only while actually clipped. Context occupancy renders as the composer's trailing ContextMeter: a 14px occupancy ring after the model seat, fed by `contextPressure` and rendered only once both a numerator and a route capacity are known, that click-opens a panel pairing the `percent used` header and `~used / capacity` figures with a color-segmented bar and `~`-prefixed heuristic composition rows (system prompt, tools, messages) from the `contextBreakdown` projection. The ring and header read `projectedTokens` — the provider sample carried forward over the surface's movement since — so a compaction registers immediately instead of after a further turn; the composition rows stay wholly heuristic and therefore still do not sum to the header ([rationale](../../llm/token-meter/README.md)). Occupancy is deliberately an approximation: numerator and capacity are independent last-wins projection fields, not one atomic request observation. `src/client/` is organized by domain. `contract/` is the shared face for slot declarations, composed props, and cross-domain types; `skeleton/`, `chat/`, `input/`, `queue/`, and `settings/` keep their implementations internal, while `apply.ts` is their assembly point. The `/client` exports contain only loader entries, service classes, and contract types; components and store factories reach the page through slot registrations. diff --git a/packages/client/ui-conversation/README.zh.md b/packages/client/ui-conversation/README.zh.md index b1c0a502ce..a2d514af39 100644 --- a/packages/client/ui-conversation/README.zh.md +++ b/packages/client/ui-conversation/README.zh.md @@ -6,7 +6,7 @@ 压缩（compaction）在检查点自身的消息流位置渲染为一行折叠标记，不替换其上方的 transcript（文本记录）。自动压缩使用「上下文已压缩」标题。每个已加载对应 `compaction/summary` 事件的完成标记都会显示被替换条目数量和估算 token 数量，并可点击展开摘要。手动 `/compact` 开始时显示为运行中的 `compact` 行；成功结算后，其显式摘要事件引用会在保持同一 React key 的前提下把该命令折叠进检查点行。完成的检查点静止时保留上下文压缩（context compaction）图标，仅在悬停或键盘聚焦时将其替换为收起／展开指示图标。输入被拒绝、没有可压缩历史、取消和失败时仍使用通用命令行及处理器撰写的文本。配对绝不依赖相邻关系，因为压缩运行期间可能注入持久上下文。面向模型的带框检查点载荷绝不渲染；被引用的 `compaction/summary` 事件位于已加载窗口之外时，检查点仍然可见但不可展开。 -常驻会话壳会跨无会话与会话状态切换而保留。没有当前会话时，它会锁定消息操作，并让整张虚线编辑器卡片成为根作用域 `conversation.hero.workspace` Workspace picker 的入口；textarea 保持只读且支持键盘操作。选择 Workspace 会连接或复用由 Host 拥有的空白会话，并在不替换会话壳的情况下打开该会话。根组件始终拥有同一个滚动容器与 Hero／编辑器子树；首个会话到达时，彼此独立的严格会话页头和主体 outlet 只填入各自区域，因此 Workspace picker、滚动主体、编辑器 seat 与 textarea 都保留原有 React 和 DOM identity。空白会话与活跃会话渲染相同的输入区主体；InputHub 则在 Workspace 切换间携带草稿，并将草稿镜像到会话 store。活跃阶段，会话标题栏作为普通列 chrome，仅显示当前会话标题和视图标签；fork 谱系仍保留为会话数据，不投影到标题栏。其下滚动容器（`data-conversation-scroll`）承载流动排版的各视图与 sticky 编辑器栈（统计 dock＋输入区 dock＋输入栏）。该滚动容器无条件预留自己的滚动条槽，选用编辑器 overlay 的视图也仍把它保留为滚动容器，因此无论对话记录是否滚动、无论展示哪个视图标签，输入卡片都保持同一个横向位置（[决策](../../../.agents/notes/implemented/bug-fix/2026-08-04-composer-tab-gutter-reservation.zh.md)）。textarea 上的滚轮会链式处理：限高草稿先在本地滚动，到达边缘后再转交给该宿主。只有 Safari 会在原生编辑缩短草稿并留下陈旧软换行溢出时执行绘制前恢复；草稿增长、程序化更新与其他浏览器都不会为这项恢复读取布局（[决策](../../../.agents/notes/implemented/bug-fix/2026-08-13-safari-textarea-soft-wrap-reflow.zh.md)）。 +常驻会话壳会跨无会话与会话状态切换而保留。没有当前会话时，它会锁定消息操作，并让整张虚线编辑器卡片成为根作用域 `conversation.hero.workspace` Workspace picker 的入口；textarea 保持只读且支持键盘操作。Hero 前方的标记是独立的根作用域 `conversation.hero.brand.mark` slot，未被占用时回退到鱼形标记。选择 Workspace 会连接或复用由 Host 拥有的空白会话，并在不替换会话壳的情况下打开该会话。根组件始终拥有同一个滚动容器与 Hero／编辑器子树；首个会话到达时，彼此独立的严格会话页头和主体 outlet 只填入各自区域，因此 Workspace picker、滚动主体、编辑器 seat 与 textarea 都保留原有 React 和 DOM identity。空白会话与活跃会话渲染相同的输入区主体；InputHub 则在 Workspace 切换间携带草稿，并将草稿镜像到会话 store。活跃阶段，会话标题栏作为普通列 chrome，仅显示当前会话标题和视图标签；fork 谱系仍保留为会话数据，不投影到标题栏。其下滚动容器（`data-conversation-scroll`）承载流动排版的各视图与 sticky 编辑器栈（统计 dock＋输入区 dock＋输入栏）。该滚动容器无条件预留自己的滚动条槽，选用编辑器 overlay 的视图也仍把它保留为滚动容器，因此无论对话记录是否滚动、无论展示哪个视图标签，输入卡片都保持同一个横向位置（[决策](../../../.agents/notes/implemented/bug-fix/2026-08-04-composer-tab-gutter-reservation.zh.md)）。textarea 上的滚轮会链式处理：限高草稿先在本地滚动，到达边缘后再转交给该宿主。只有 Safari 会在原生编辑缩短草稿并留下陈旧软换行溢出时执行绘制前恢复；草稿增长、程序化更新与其他浏览器都不会为这项恢复读取布局（[决策](../../../.agents/notes/implemented/bug-fix/2026-08-13-safari-textarea-soft-wrap-reflow.zh.md)）。 别的插件可以经 `ctx.conversation.blocks` 让某个会话的编辑器变为惰性：它设置一个携带自己本地化理由的 block，输入栏就渲染同一个禁用的 textarea，并把该理由作为 placeholder——复用无 Workspace 时的那套姿态。推送方向是约束而非偏好：知道某会话发不出消息的插件（ui-model-selection，在没有适配器服务其路由时）本就依赖本包，因此本包读不到它们。模型 seat 是 block 唯一保留可用的控件——这份约定里的每个 block 都靠选模型来解除，把它一起锁上会让编辑器索要它自己拦下的那件事。block 只是提示性设计；无论客户端禁用了什么，宿主都会拒绝一个它无法路由的提示词。两者同时成立时以无 Workspace 姿态为准，因为选 Workspace 是更靠前的前提。 @@ -16,15 +16,15 @@ Chat 业务行是彼此独立的注册表贡献，不是封闭的内建联合。 会话页头会在标题旁渲染会话作用域的 `'conversation.session.header.actions'` 列表，并在最右侧渲染独立的 `'conversation.session.header.utilities'` 列表。会话上下文和谱系控件保留在 `actions` 中；可选的会话工具不会改变它们的顺序或位置。编辑器链的 currency 包含当前对话 `session`；ui-subagent 会选取 one-shot 或 parent 不可用的已寻址会话，并按原因显示只读文案，而普通 InputBar 会让所有已寻址 child 仅保留 Send，因为继续执行服务不公开逐 Activation 取消操作，`session.cancel` 也会绕过其所有权。 -已记录的非用户消息渲染为默认折叠的展开项，标题栏先给出运行时为该消息投影出的角色——注入为 `上下文注入`，召回为 `跨会话召回`——其后是该投影从持久来源读出的生产者名称，因此读者无需展开即可区分 skill（技能）目录、工作区指令文件与被召回的会话。来源未提供生产者名称时只显示角色。共享的 `DisclosureRow` 原子组件让该上下文界面与消息流中的其他紧凑行保持相同几何，同时保留上下文语义：展开内容区的高度会随内容自适应，最大为 141px，超出后滚动，且不会合成工具状态或摘要（[历史展开项决策](../../../.agents/notes/archived/feature/2026-07-30-web-context-injection-disclosure.md)、[生产者标签决策](../../../.agents/notes/implemented/feature/2026-08-04-web-context-source-and-steer-marks.zh.md)）。该内容区按生产方在持久来源上声明的形态渲染：`instructions` 在正文之上列出它对账过的文件，`catalog` 列出来源记录的条目而非面向模型的正文，其余取值——未声明、本版本不认识、或字段不可用——一律渲染 opaque 内容区，即按真实换行展示面向模型的文本，并把剩余来源字段列出。opaque 不是兜底剩余物而是有文档的默认：恢复的、fork 的、外部写入的日志，无论其生产方是否挂载在此处，都必须渲染得出来。持久或待处理的 steering（中途引导）气泡沿用用户气泡的呈现，不加任何装饰；transcript 中唯一的 steering 信号是它出现在轮次中途的位置。 +已记录的非用户消息渲染为默认折叠的展开项，标题栏先给出运行时为该消息投影出的角色——注入为 `上下文注入`，召回为 `跨会话召回`——其后是该投影从持久来源读出的生产者名称，因此读者无需展开即可区分 skill（技能）目录、工作区指令文件与被召回的会话。引用其他会话的直接消息在持久顺序中位于其召回行之前。Chat 快照只从紧随其后的带来源召回中关联准确标签，因此既能保留多词标题，也不会把一条召回的标签带到后续直接消息上。召回使用聊天气泡图标，其他上下文保留文档图标；来源未提供生产者名称时只显示角色。输入框与用户气泡中的引用使用同一种行内语言：聊天气泡、文件或文件夹图标加业务色文字，不嵌套胶囊容器。与已认领的 slash command 相同，输入框引用会把完整展示文本保留在透明 textarea 中，再用对齐的 backdrop 提供颜色和开头的领域图标；宽度、换行、选择区与光标位置均由原生文本度量决定。occurrence 范围仍为序列化与边界整段删除保留结构身份，在范围内部编辑则会把剩余字符转为普通文本。会话草稿镜像会存储每个 occurrence 的剪贴板投影，因此在 occurrence 表缺失的情况下重新挂载时，会恢复可解析的规范引用文本，而不是仅供显示的标签。共享的 `DisclosureRow` 原子组件让该上下文界面与消息流中的其他紧凑行保持相同几何，同时保留上下文语义：展开内容区的高度会随内容自适应，最大为 141px，超出后滚动，且不会合成工具状态或摘要（[历史展开项决策](../../../.agents/notes/archived/feature/2026-07-30-web-context-injection-disclosure.md)、[生产者标签决策](../../../.agents/notes/implemented/feature/2026-08-04-web-context-source-and-steer-marks.zh.md)）。该内容区按生产方在持久来源上声明的形态渲染：`instructions` 在正文之上列出它对账过的文件，`catalog` 列出来源记录的条目而非面向模型的正文，其余取值——未声明、本版本不认识、或字段不可用——一律渲染 opaque 内容区，即按真实换行展示面向模型的文本，并把剩余来源字段列出。opaque 不是兜底剩余物而是有文档的默认：恢复的、fork 的、外部写入的日志，无论其生产方是否挂载在此处，都必须渲染得出来。持久或待处理的 steering（中途引导）气泡沿用用户气泡的呈现，不加任何装饰；transcript 中唯一的 steering 信号是它出现在轮次中途的位置。 Think 行默认保持折叠，并在不展开思维链的情况下暴露实时推理（reasoning）吞吐：当推理块是流式输出尾部时，摘要从结算后的首行切换到最新的非空行，其单行滚动区会随每个 delta 追到行内末端。展开该行会移除移动摘要，让完整推理进入普通页面流，因此页面阅读不会与内部跟随器争夺滚动；结算后恢复左对齐的稳定首行摘要（[决策](../../../.agents/notes/implemented/feature/2026-08-02-web-thinking-tail-scroll.zh.md)）。 -聊天视图保留工具的消息流位置，但委托其展示。每个已排序的 `tool-call` Conversation Node 都通过 `conversation.chat.node` 的同名 key 分发；详情壳层则通过 `conversation.details.tool` 传递当前选中的调用。组装后的 Web bundle 为该 Chat Node key 注册 [`ui-tool`](../ui-tool/README.zh.md)，由后者渲染运行时已投影的递归 root/child 树，并负责按名称分发、通用展示和 render-intent 卡片；只有详情席位会在该 renderer 缺席时保留 raw-result fallback。 +聊天视图保留工具的消息流位置，但委托其展示。每个已排序的 `tool-call` Conversation Node 都通过 `conversation.chat.node` 的同名 key 分发；详情壳层则通过 `conversation.details.tool` 传递当前选中的调用。组装后的 Web bundle 为该 Chat Node key 注册 [`ui-tool`](../ui-tool/README.zh.md)，由后者渲染运行时已投影的递归 root/child 树，并负责按名称分发、通用展示和 render-intent 卡片；只有详情席位会在该 renderer 缺席时保留 raw-result fallback。经注入的 `openFile` 点击路径会请 Host 打开该路径（相对路径按会话 cwd 解析）。Host 或操作系统拒绝时，页面内对话框展示抛出的原因，并提供对同一路径的重试；取消、Escape、关闭控件和点击遮罩会关掉对话框（[决策](../../../.agents/notes/implemented/bug-fix/2026-08-18-tool-row-file-open-failure.zh.md)）。 聊天流会将跨重试轮次连续出现的模型重试节点投影为一个稳定的弱化状态行，并用最新一次尝试更新该行；每个重试事件仍保留在运行时快照与会话日志中。前端倒计时以客户端收到事件的时刻为计划延迟的起点，避免 Host 与浏览器的时钟偏差；剩余时间向上取整到秒，且下限为 1 秒。最近一次尚未完成的重试会显示从左到右的文字渐变动画。后续轮次事实用于区分已开始的尝试与在退避期间取消的尝试，Host 的 running 位只控制实时动画；随后该行会显示静态的已完成或已取消标签。normal 策略行显示有限重试上限；always 策略行显示 `∞`。激活该行会显示最近一次重试的精确延迟和失败消息。客户端运行时会在相应重试节点到达前移除每个失败步骤的流式输出尾部；后续某次尝试成功后，该状态仍保持可见。未进入重试的终态失败会在其轮次边界渲染为持久的内联状态，展示适合显示的持久消息与可选错误码，但不会提供 Host 无法兑现的操作；AUTH 文案绝不会回显提供方给出的凭据片段。 -审批通过本包声明的链条接管编辑器：`ApprovalPanel` 注册为按选择器路由的 `'conversation.composer'` 配置项（ui-user-questions 模式），在审批等待未决期间取代 InputBar 占据编辑器（琥珀色条、理由标题、来自运行中调用参数的配对命令行、一次性的拒绝／允许）。`contract/slots.ts` 中的 `PendingApproval` 领域面在运行时 `PendingWait` 载体之上拥有 wire 编码——带审计关联的 `ApprovalResponsePayload` 值；广播的 `approval/resolved` 帧使等待落定并恢复编辑器。运行时 manager 会将所有审批或问题等待通过 `SessionSummary.pendingInteraction` 投影出来，未实例化的会话也不例外；`ui-workspace` 负责其侧边栏呈现。未决等待完全离开消息流：问题（ui-user-questions）与审批（ApprovalPanel）都经编辑器接管作答，不再保留只读占位卡。编辑器底行的 Access 席位挂载 `PermissionSelect`，由 host 计算的 `permissions` 投影经标准工具包 `useProjection` 供数（key 缺席即隐藏 chip）；chip 打开 Menu 原语下拉，其中 kebab-case 预设名渲染为 Title Case 标签；普通安全预设会立即经输入栏注入的 `command` 回调提交 `/permission `，而 `danger-full-access` 在界面中显示为 `Full access`，选择后先打开页面内的 Modal 风险确认。用户勾选确认项前启用按钮始终不可用；取消、Escape、关闭按钮与点击遮罩都不会提交命令。 +审批通过本包声明的链条接管编辑器：`ApprovalPanel` 注册为按选择器路由的 `'conversation.composer'` 配置项（ui-user-questions 模式），在审批等待未决期间取代 InputBar 占据编辑器（琥珀色条、理由标题、来自运行中调用参数的配对命令行、一次性的拒绝／允许）。`contract/slots.ts` 中的 `PendingApproval` 领域面在运行时 `PendingWait` 载体之上拥有 wire 编码——带审计关联的 `ApprovalResponsePayload` 值；广播的 `approval/resolved` 帧使等待落定并恢复编辑器。运行时 manager 会将所有审批或问题等待通过 `SessionSummary.pendingInteraction` 投影出来，未实例化的会话也不例外；`ui-workspace` 负责其侧边栏呈现。未决等待完全离开消息流：问题（ui-user-questions）与审批（ApprovalPanel）都经编辑器接管作答，不再保留只读占位卡。编辑器底行的 Access 席位挂载 `PermissionSelect`，由 host 计算的 `permissions` 投影经标准工具包 `useProjection` 供数（key 缺席即隐藏 chip）；chip 打开 Menu 原语下拉，其中内置预设 id 仅在 host 保留规范名称时渲染为本地化产品标签，显式 host 标签保持原样，未知 kebab-case 预设名仍渲染为 Title Case 标签；普通安全预设会立即经输入栏注入的 `command` 回调提交 `/permission `，而 `danger-full-access` 选择后先打开页面内的 Modal 风险确认。用户勾选确认项前启用按钮始终不可用；取消、Escape、关闭按钮与点击遮罩都不会提交命令。 `TodoDock` 以 `order: 0` 占用 `'conversation.input.dock'` 列表 slot（位于 Goal 与 Queue 之前），作为计划条读取 host 计算的 `todos` 投影（当前计划：其后没有更晚 `turn/start` 的最近一次 `todo/write`）并渲染 `TodoPanel`。面板接收纯列表，列表为空时自我隐藏；列表非空时默认折叠，表头显示标题及以 `·` 连接的各状态计数（如 `1 已完成 · 2 进行中 · 1 待处理`，省略零计数）。dock adapter 拥有 selection，因此面板保持为 props 的纯函数。输入区 composer 链隐藏的一切也会隐藏整个 dock。`todo_write` 工具行属于 [`ui-tool`](../ui-tool/README.zh.md)。 @@ -36,11 +36,11 @@ Host 带 placement 的 `session/queue` 快照也会携带待处理 steering。Qu 逐会话 UI 状态中的选择与活跃视图位于已声明的聊天 store（`stores.ts` `createChatStore`）中；InputHub 拥有输入区状态机，并将草稿镜像到该 store 以便持久化。apply 将同一个 store handle 传给严格限定于会话的子树、聊天视图和详情注册，因此每个会话内共享一个实例，框架拥有其生命周期。组件保持纯粹：框架标准工具包提供 `useSession`／`sessionId`、全局 `useSessions`／`useWorkspaces`，以及输入状态机的 `useInput`／`inputActions`；store 表层与 inject factory 提供其余状态和回调。 -图片经粘贴与整页拖放进入：输入栏绑定 document 级拖拽监听（composer-bar slot 为 `kind: 'single'`，同一时刻至多一个 bar 绑定），文件拖拽悬停窗口时显示 `DropOverlay` 原子组件——纯文本拖拽不受影响，锁定或忙碌的 composer 显示禁用遮罩并拒绝 drop。两种手势共用一条对宿主 `imageLimits` 投影的加入预检（数量、单图字节、总字节）：会突破上限的加入整批拒收，立刻弹出点名上限的横幅，完全不进入附件栏。仍然到达的宿主侧拒绝按 `attachment-error` 原因映射为产品文案（`image-labels.ts` 的 `attachmentErrorText`）；用户无法解决的原因折叠为一条带原因码的发送失败文案，非附件错误码保留开发者可读的原文加错误码。 +图片经粘贴与整页拖放进入：输入栏绑定 document 级拖拽监听（composer-bar slot 为 `kind: 'single'`，同一时刻至多一个 bar 绑定），文件拖拽悬停窗口时显示 `DropOverlay` 原子组件——纯文本拖拽不受影响，锁定或忙碌的 composer 显示禁用遮罩并拒绝 drop。两种手势共用一条对宿主 `imageLimits` 投影的加入预检（数量、单图字节、总字节）：会突破上限的加入整批拒收，立刻弹出点名上限的横幅，完全不进入附件栏。仍然到达的宿主侧拒绝按 `attachment-error` 原因映射为产品文案（`image-labels.ts` 的 `attachmentErrorText`）；用户无法解决的原因折叠为一条带原因码的发送失败文案，非附件错误码保留开发者可读的原文加错误码。已附加的图片在每条发送路径上都是提交信封的一部分：斜杠命令提交要么消费它们（声明 `images` 的 claim 经 hub 的 `commandImages` 管道序列化图片、传给 `claim.submit`，仅在成功 outcome 后清除并释放），要么以 `command.imagesUnsupported` 通知拒绝整个提交，草稿与图片原样保留——命令不可能消费了文字却把图片留在原地。 输入栏为 `'conversation.input.plan'`（位于本地 access 模式控件右侧）和 `'conversation.input.model'`（渲染在 pending 指示器与发送／停止控件之前）声明会话作用域的单实例 seat，并为 overlay、dock、left 和 right 输入扩展声明列表 slot。各功能包拥有相应控件及其状态；ui-conversation 提供放置位置、`locked` owner prop 和标准 slot share。前置加号按钮是 Command launcher，而非附件入口：它要求当前会话的 `InputTriggerController` 基于 textarea 当前 selection，只打开 `/` trigger 的 `command` source，同时 ui-input-trigger 既有的 `MenuView` 仍是唯一的浮层菜单与 pick 路径。不引入 File 行、file input、上传协议或第二套菜单组件。当 `plan` 投影的有效目标为 plan mode 时，InputBar 将文本框 placeholder 切换为 plan 任务措辞，经本包注册的 `conversation` locale 命名空间（`placeholder.plan` / `hint.plan` 键）本地化，并与已认领 `/plan` 命令的提示逐字共用同一份文案（经标准套件 `useProjection` 读取的 host 折叠值；owner 提供的 placeholder 优先）。另一个会话视图活跃时，待处理的 composer 接管仍保持挂载，使被阻塞的 agent（智能体）仍能收到回答；没有待处理交互时，活跃会话的 composer 归 Chat 所有。composer bar slot 本身为 `session-maybe`：没有当前会话时，同一个 bar 会让消息操作保持不可交互（machine face 均缺席、`disabled` owner prop），整张虚线卡片可经指针打开现有 Workspace picker，只读 textarea 也可通过 Enter 或 Space 打开。禁用控件会把指针事件交给卡片，卡片也会拦下 `pointerdown`，避免已打开 picker 的外点关闭与重新打开发生竞态。它不会换入一棵平行树，因此选择 Workspace 时 textarea DOM 不会被销毁；严格会话作用域的控件 seat 在会话存在之前保持为空。 -聊天统计行的 token 账目来自经标准套件 `useProjection` 读取的通用 token-meter 投影 `tokenUsage`：计费输入为未缓存输入、缓存读取与缓存写入之和；缓存命中率以缓存读取除以该总量。轮次与步骤计数、LLM（大语言模型）与工具墙钟时间、以及延迟／吞吐分组都来自全日志的 `sessionStats` 投影（Host 端从步边界、首 token chunk、工具配对与已组装消息折算），因此分页与压缩都无法改变统计条的任何数字；未组合该单元的装配回退为对可见节点做窗口折算，其字段与投影一一对应。统计条把每个有完整记录的步骤的 TTFT（首 token 延迟）取平均，并用采样到的输出 token 数除以其解码时长之和，得到经 `conversation` locale 命名空间本地化的延迟／吞吐分组（中文为 `首 token 平均 … · … tok/s`）；缺少某个 timing 边界或 usage 采样的步骤会直接退出这些数字，而不是让它们失真；压缩（compaction）使已加载窗口不再包含 assistant 节点时，持久计数、token 与上下文分组仍保持可见。轮次计数、步骤计数、耗时、缓存与 token 各项的标签也使用同一命名空间。每个已结算轮次还会在其 assistant footer 的 `用时` 之后追加 hover 才显示的 `首 token {s}秒 · {tps} tok/s` 标签——即该轮次首个步骤的 TTFT 与轮次聚合的解码吞吐——仅当该轮次的 timing 位于已加载窗口内才显示（窗口是日志的连续后缀，因此窗口内的轮次必然带着它的全部步骤），未记录的数字会各自省略。未组合 token-meter 的部署会整组省略 token 分组；统计行过长时以省略号截断，仅在内容真的被裁切时由延迟 hover tooltip 承载完整文本。上下文占用率渲染为 composer 尾部的 ContextMeter：模型座位之后的一枚 14px 占用圆环，由 `contextPressure` 供数，仅当分子与路由容量都已知时才渲染；点击弹出的面板把「已用百分比」标题与 `~已用 / 容量` 数字，与来自 `contextBreakdown` 投影、带 `~` 前缀的启发式组成明细行（系统提示词、工具、对话消息）及分色分段进度条并列。圆环与标题读取 `projectedTokens`——把提供方样本沿此后表层的增减推进到当下——因此压缩会立刻反映出来，而不必再等一整轮；组成明细行仍是纯启发式，因此加起来依然不等于标题数字（[原理](../../llm/token-meter/README.zh.md)）。占用率是刻意为之的近似值：分子与容量是两个相互独立的「后写覆盖」投影字段，并非同一次请求的原子观测。 +聊天统计行的 token 账目来自经标准套件 `useProjection` 读取的通用 token-meter 投影 `tokenUsage`：计费输入为未缓存输入、缓存读取与缓存写入之和；缓存命中率以缓存读取除以该总量。所有非空比率都先按整数舍入。非满命中只有在当前精度会舍入成 100% 时才增加小数位，并在首次得到低于 100% 的结果时停止；只有完整缓存命中才显示 100%，且精度没有固定上限。轮次与步骤计数、LLM（大语言模型）与工具墙钟时间、以及延迟／吞吐分组都来自全日志的 `sessionStats` 投影（Host 端从步边界、首 token chunk、工具配对与已组装消息折算），因此分页与压缩都无法改变统计条的任何数字；未组合该单元的装配回退为对可见节点做窗口折算，其字段与投影一一对应。统计条把每个有完整记录的步骤的 TTFT（首 token 延迟）取平均，并用采样到的输出 token 数除以其解码时长之和，得到经 `conversation` locale 命名空间本地化的延迟／吞吐分组（中文为 `首 token 平均 … · … tok/s`）；缺少某个 timing 边界或 usage 采样的步骤会直接退出这些数字，而不是让它们失真；压缩（compaction）使已加载窗口不再包含 assistant 节点时，持久计数、token 与上下文分组仍保持可见。轮次计数、步骤计数、耗时、缓存与 token 各项的标签也使用同一命名空间。每个已结算轮次还会在其 assistant footer 的 `用时` 之后追加 hover 才显示的 `首 token {s}秒 · {tps} tok/s` 标签——即该轮次首个步骤的 TTFT 与轮次聚合的解码吞吐——仅当该轮次的 timing 位于已加载窗口内才显示（窗口是日志的连续后缀，因此窗口内的轮次必然带着它的全部步骤），未记录的数字会各自省略。未组合 token-meter 的部署会整组省略 token 分组；统计行过长时以省略号截断，仅在内容真的被裁切时由延迟 hover tooltip 承载完整文本。上下文占用率渲染为 composer 尾部的 ContextMeter：模型座位之后的一枚 14px 占用圆环，由 `contextPressure` 供数，仅当分子与路由容量都已知时才渲染；点击弹出的面板把「已用百分比」标题与 `~已用 / 容量` 数字，与来自 `contextBreakdown` 投影、带 `~` 前缀的启发式组成明细行（系统提示词、工具、对话消息）及分色分段进度条并列。圆环与标题读取 `projectedTokens`——把提供方样本沿此后表层的增减推进到当下——因此压缩会立刻反映出来，而不必再等一整轮；组成明细行仍是纯启发式，因此加起来依然不等于标题数字（[原理](../../llm/token-meter/README.zh.md)）。占用率是刻意为之的近似值：分子与容量是两个相互独立的「后写覆盖」投影字段，并非同一次请求的原子观测。 `src/client/` 按领域组织。`contract/` 是 slot 声明、组合 props 与跨领域类型的共享表层；`skeleton/`、`chat/`、`input/`、`queue/` 和 `settings/` 保持内部实现，`apply.ts` 是它们的组装点。`/client` 导出表层只包含 loader entry、service class 和 contract 类型；组件与 store factory 经 slot 注册抵达页面。 diff --git a/packages/client/ui-conversation/package.json b/packages/client/ui-conversation/package.json index 8fd8c44d4c..a8596f1209 100644 --- a/packages/client/ui-conversation/package.json +++ b/packages/client/ui-conversation/package.json @@ -1,7 +1,7 @@ { "name": "@deepseek-ai/dsh-client-ui-conversation", "description": "Conversation domain: skeleton, ordered chat flow, composer with the Host-backed busy-Enter preference, and details host", - "version": "0.1.0-rc.7", + "version": "0.1.0-rc.8", "publishConfig": { "access": "public" }, diff --git a/packages/client/ui-conversation/src/client/apply.ts b/packages/client/ui-conversation/src/client/apply.ts index 463c481eef..294009a09b 100644 --- a/packages/client/ui-conversation/src/client/apply.ts +++ b/packages/client/ui-conversation/src/client/apply.ts @@ -206,6 +206,7 @@ export function apply(ctx: Context): void { 'conversation.composer.dock': { kind: 'list', scope: 'session' }, 'conversation.input.left': { kind: 'list', scope: 'session' }, 'conversation.input.right': { kind: 'list', scope: 'session' }, + 'conversation.hero.brand.mark': { kind: 'single', scope: 'root' }, 'conversation.hero.workspace': { kind: 'single', scope: 'root' }, 'conversation.hero.agentPreset': { kind: 'single', scope: 'root' }, }, @@ -337,6 +338,7 @@ export function apply(ctx: Context): void { inputTriggers.toggleSource('command', { trigger: '/', query: '', + quoted: false, position: snapshot.draft.slice(0, selection.start).trim() === '' ? 'leading' : 'inline', span: { ...selection, draftRev: snapshot.draftRev }, }) @@ -396,10 +398,7 @@ export function apply(ctx: Context): void { fileMentions: owner => ctx.get('chatFileMentions')?.forClosing(owner), openFile: (path) => { const cwd = sessions.list.getSnapshot().byId[sessionId]?.cwd - void workspaces.openPath(resolveWorkspacePath(cwd, path)).catch(() => { - // Host/OS open failures stay silent in the chat row; the native - // app surfaces its own error dialog when the path is unusable. - }) + return workspaces.openPath(resolveWorkspacePath(cwd, path)) }, loadOlder: () => { void scoped.loadOlder() }, loadImage: attachment => conversation.resolveImage(sessionId, attachment), diff --git a/packages/client/ui-conversation/src/client/chat/AssistantMarkdown.module.css b/packages/client/ui-conversation/src/client/chat/AssistantMarkdown.module.css index 8fdba2baa0..c9e8d19d77 100644 --- a/packages/client/ui-conversation/src/client/chat/AssistantMarkdown.module.css +++ b/packages/client/ui-conversation/src/client/chat/AssistantMarkdown.module.css @@ -17,6 +17,28 @@ gap: 16px; } +/* Wide markdown tables (the renderer's ≥4-column md-table-wide hook) span + the whole transcript width instead of clipping at the 748px message + column, while the table content keeps starting at its normal x (the lead + padding compensates the negative margin) — deepsuite chat TableWrapper + parity, with 100cqw (the ChatView scroll container) standing in for its + JS-measured --dsl-virtual-list-width. `--dsh-table-spare` clamps to zero + when the transcript is narrower than the message column, so narrow + viewports keep the plain in-column scroll with no sideways shift. + Percentages resolve against the wrapper's containing block, so a table + indented inside a list still reaches the same transcript edges. */ +.body :global(.md-table-wide) { + --dsh-table-spare: max(0px, calc((100cqw - var(--dsh-chat-content-width)) / 2)); + --dsh-table-lead: calc(var(--dsh-table-spare) + min(var(--dsh-chat-content-width), 100cqw) - 100%); + box-sizing: border-box; + width: calc(100% + var(--dsh-table-lead) + var(--dsh-table-spare)); + /* The base .tableScroll caps at the column (max-width: 100%); the breakout + is exactly the case that must exceed it. */ + max-width: none; + margin-left: calc(-1 * var(--dsh-table-lead)); + padding-left: var(--dsh-table-lead); +} + /* Interrupted-turn terminal marker: quiet inline tag, no animation. */ .stopped { align-self: flex-start; diff --git a/packages/client/ui-conversation/src/client/chat/ChatView.module.css b/packages/client/ui-conversation/src/client/chat/ChatView.module.css index d16608c856..73fa688f95 100644 --- a/packages/client/ui-conversation/src/client/chat/ChatView.module.css +++ b/packages/client/ui-conversation/src/client/chat/ChatView.module.css @@ -18,6 +18,11 @@ /* Sides = composer clearance + 16px: on narrow viewports the transcript stays exactly 32px narrower than the input card (the shared width rule). */ padding: 16px calc(var(--dsh-composer-side-clearance) + 16px); + /* Inline-size query container: wide markdown tables size their breakout + against this box's content width (100cqw in AssistantMarkdown's + md-table-wide rule) — the CSS stand-in for deepsuite chat's JS-measured + --dsl-virtual-list-width. */ + container-type: inline-size; } :global([data-conversation-scroll]) .root { @@ -190,3 +195,8 @@ .toBottom:hover { background: var(--dsw-alias-button-floating-hover); } + +/* Host open-path refusal: same dialog family as the workspace folder error. */ +.modalAction { + min-width: 72px; +} diff --git a/packages/client/ui-conversation/src/client/chat/ChatView.tsx b/packages/client/ui-conversation/src/client/chat/ChatView.tsx index 4d9df510e1..80f9bc2d73 100644 --- a/packages/client/ui-conversation/src/client/chat/ChatView.tsx +++ b/packages/client/ui-conversation/src/client/chat/ChatView.tsx @@ -1,7 +1,8 @@ // ChatView: the default conversation view — one stable keyed parent list over // final business Nodes, plus paging, pending steering and bottom-follow. // Each row dispatches through 'conversation.chat.node'; ui-tool owns the -// tool-call renderer and its recursive root/subcall composition. +// tool-call renderer and its recursive root/subcall composition. A Host +// open-path refusal from the injected opener is an in-page dialog here. // // Scroll: when nested under `[data-conversation-scroll]` (active conversation // column), that host is the scrollport and this view is flow content; when @@ -14,7 +15,7 @@ import { useCallback, useEffect, useLayoutEffect, useMemo, useRef, useState } from 'react' import type { ConversationTimelineSnapshot } from '@deepseek-ai/dsh-client-runtime/client' -import { IconChevronDownOutline14 } from '@deepseek-ai/dsh-client-ui-primitives' +import { Button, IconChevronDownOutline14, Modal } from '@deepseek-ai/dsh-client-ui-primitives' import type { ChatViewSlotProps, RenderMessageImages } from '../contract/slots.ts' import { PendingSteeringBubble } from './MessageItem.tsx' import { ChatNodeSeat } from './ChatNodeSeat.tsx' @@ -95,6 +96,17 @@ function scrollPosition(list: HTMLElement, scrollport: HTMLElement): ChatScrollP } } +/** Host/OS refusal text for the file-open dialog; empty throws keep a locale fallback. */ +function openFailureMessage(error: unknown, fallback: string): string { + const message = error instanceof Error ? error.message : String(error) + return message === '' ? fallback : message +} + +/** ProducedFiles opens the session workspace as `.`. */ +function isFolderOpenPath(path: string): boolean { + return path === '.' +} + function runningTurnStartTime(timeline: ConversationTimelineSnapshot): number | null { let latest: number | null = null for (const turn of timeline.turns.values()) { @@ -159,6 +171,40 @@ export function ChatView({ const hasMore = useSession(s => s.hasMore) const loadingOlder = useSession(s => s.loadingOlder) const selectedCallId = useStore(s => s.selection?.callId) + const [fileOpenError, setFileOpenError] = useState<{ path: string; message: string } | null>(null) + const [fileOpenBusy, setFileOpenBusy] = useState(false) + // Close/retry must ignore a settlement that started before the latest + // gesture; otherwise a cancelled in-flight refusal reopens the dialog. + const fileOpenRequest = useRef(0) + + const requestOpenFile = useCallback((path: string) => { + const id = ++fileOpenRequest.current + setFileOpenBusy(true) + void openFile(path).then( + () => { + if (id !== fileOpenRequest.current) return + setFileOpenError(null) + setFileOpenBusy(false) + }, + (error: unknown) => { + if (id !== fileOpenRequest.current) return + setFileOpenError({ + path, + message: openFailureMessage( + error, + t(isFolderOpenPath(path) ? 'fileOpen.folderUnknown' : 'fileOpen.unknown'), + ), + }) + setFileOpenBusy(false) + }, + ) + }, [openFile, t]) + + const closeFileOpenError = useCallback(() => { + fileOpenRequest.current += 1 + setFileOpenError(null) + setFileOpenBusy(false) + }, []) const pendingSteering = useMemo( () => inbox.filter(item => item.placement === 'steering'), @@ -390,7 +436,7 @@ export function ChatView({ useSession={useSession} selectedCallId={selectedCallId} cwd={cwd} - openFile={openFile} + openFile={requestOpenFile} inspectCall={inspectCall} forkAt={forkAt} renderMessageImages={renderMessageImages} @@ -431,6 +477,44 @@ export function ChatView({ )} + {fileOpenError !== null && ( + { requestOpenFile(fileOpenError.path) }} + t={t} + /> + )} ) } + +/** In-page Host open-path refusal: the wire reason plus a retry of the same path. */ +function FileOpenErrorDialog({ + path, message, busy, onClose, onRetry, t, +}: { + path: string + message: string + busy: boolean + onClose: () => void + onRetry: () => void + t: ChatViewSlotProps['t'] +}) { + return ( + + + + + )} + /> + ) +} diff --git a/packages/client/ui-conversation/src/client/chat/ContextInjectionRow.tsx b/packages/client/ui-conversation/src/client/chat/ContextInjectionRow.tsx index 889b15b085..3e9e0f10b1 100644 --- a/packages/client/ui-conversation/src/client/chat/ContextInjectionRow.tsx +++ b/packages/client/ui-conversation/src/client/chat/ContextInjectionRow.tsx @@ -2,6 +2,7 @@ import { useState } from 'react' import type { ContextMessageNode } from '@deepseek-ai/dsh-client-runtime/client' import type { ChatViewSlotProps } from '../contract/slots.ts' import { DisclosureRow, IconBrowseOutline16 } from '@deepseek-ai/dsh-client-ui-primitives' +import { ReferenceIcon } from '../reference/ReferenceIcon.tsx' import { contextBody } from './ContextBody.tsx' import css from './ContextInjectionRow.module.css' @@ -37,7 +38,9 @@ export function ContextInjectionRow({ content, source, provenance, form, t }: Co return ( } + icon={provenance.role === 'recall' + ? + : } chevronClassName={css.chevron} title={t(provenance.role === 'recall' ? 'message.contextRecall' : 'message.contextInjection')} collapsedContent={provenance.label === null ? undefined : ( diff --git a/packages/client/ui-conversation/src/client/chat/MessageItem.module.css b/packages/client/ui-conversation/src/client/chat/MessageItem.module.css index 36824d228d..54e5f6f98d 100644 --- a/packages/client/ui-conversation/src/client/chat/MessageItem.module.css +++ b/packages/client/ui-conversation/src/client/chat/MessageItem.module.css @@ -28,6 +28,11 @@ color: var(--dsw-alias-label-primary); } +.referenceSummary { + color: var(--dsw-alias-label-tertiary); + font-size: 12px; + line-height: 18px; +} .contextRow { padding: 2px 0; } @@ -268,17 +273,19 @@ } } -/* Reference chip projection inside a user bubble (`name` model - spans render as chips; free geometry — no textarea pairing here). */ +/* Inline references use domain glyphs and business-color text without another + container inside the user bubble. */ .refChip { - display: inline-block; + display: inline-flex; + align-items: center; + gap: 4px; margin: 0 2px; - padding: 0 8px; - border-radius: 6px; - background: rgba(97, 135, 216, 0.22); - color: var(--dsw-alias-label-primary); - font-size: 0.85em; - line-height: 1.6; + color: var(--dsw-alias-state-business-primary); + font-weight: 500; white-space: nowrap; vertical-align: baseline; } + +.refIcon { + flex: none; +} diff --git a/packages/client/ui-conversation/src/client/chat/MessageItem.tsx b/packages/client/ui-conversation/src/client/chat/MessageItem.tsx index ecb0d11caa..8a882a70c5 100644 --- a/packages/client/ui-conversation/src/client/chat/MessageItem.tsx +++ b/packages/client/ui-conversation/src/client/chat/MessageItem.tsx @@ -10,6 +10,7 @@ import type { } from '@deepseek-ai/dsh-client-runtime/client' import { JsonBlock, MessageText, StateDot } from '@deepseek-ai/dsh-client-ui-primitives' import type { ChatNodeOwnerProps, ChatNodeViewProps, ChatViewSlotProps } from '../contract/slots.ts' +import { ReferenceIcon } from '../reference/ReferenceIcon.tsx' import { CompactionItem } from './CompactionItem.tsx' import { ContextInjectionRow } from './ContextInjectionRow.tsx' import { MessageIconActions } from './MessageIconActions.tsx' @@ -152,21 +153,59 @@ function TurnMaxTokensItem({ t }: { * scan as the composer, minus the lexicon: sent tokens were validated at * compose time, so shape alone decorates). */ -function projectUserText(text: string): ReactNode { - const re = /(^|\s)([/@][\w-]+)(?=\s|$)/g - const parts: ReactNode[] = [] - let cursor = 0 +function projectUserText(text: string, sessionLabels: readonly string[]): ReactNode { + const ranges: { start: number; end: number; label: string; kind: 'session' | 'plain' }[] = [] + for (const rawLabel of [...new Set(sessionLabels)].sort((a, b) => b.length - a.length)) { + const label = `@${rawLabel}` + let start = text.indexOf(label) + while (start >= 0) { + ranges.push({ start, end: start + label.length, label, kind: 'session' }) + start = text.indexOf(label, start + label.length) + } + } + const re = /(^|\s)(\/[\w-]+|@"[^"\n]+"|@[^\s]+)/gu let m: RegExpExecArray | null while ((m = re.exec(text)) !== null) { const tokenStart = m.index + (m[1]?.length ?? 0) - const label = m[2] ?? '' + const rawLabel = m[2] ?? '' + const label = rawLabel.startsWith('@"') + ? rawLabel + : rawLabel.replace(/[.,;:!?，。；：！？]+$/gu, '') + if (label.length <= 1) continue + ranges.push({ start: tokenStart, end: tokenStart + label.length, label, kind: 'plain' }) + } + ranges.sort((a, b) => a.start - b.start + || (a.kind === b.kind ? b.end - a.end : a.kind === 'session' ? -1 : 1)) + const parts: ReactNode[] = [] + let cursor = 0 + for (const range of ranges) { + if (range.start < cursor) continue + const { start: tokenStart, end, label, kind } = range if (tokenStart > cursor) parts.push() + const referenceKind = kind === 'session' + ? 'session' + : label.startsWith('@') + ? label.endsWith('/') ? 'folder' : 'file' + : undefined + const displayLabel = referenceKind === undefined + ? label + : referenceKind === 'session' + ? label.slice(1) + : label.slice(1).replace(/^"|"$/gu, '').split(/[\\/]/u).filter(Boolean).at(-1) ?? label.slice(1) parts.push( - - {label} + + {referenceKind !== undefined && ( + + )} + {displayLabel} , ) - cursor = tokenStart + label.length + cursor = end } if (parts.length === 0) return if (cursor < text.length) parts.push() @@ -175,7 +214,7 @@ function projectUserText(text: string): ReactNode { /** Right-aligned bubble shared by user and steering rows. */ function UserStyleBubble({ - content, renderMessageImages, actions, pending = false, t, + content, renderMessageImages, actions, pending = false, referenceLabels = [], t, }: { content: readonly unknown[] renderMessageImages: ChatNodeOwnerProps['renderMessageImages'] @@ -183,6 +222,8 @@ function UserStyleBubble({ actions?: (text: string) => ReactNode /** Whether this is the Host-authoritative pre-admission steering projection. */ pending?: boolean + /** Exact session mention labels associated by the adjacent recall node. */ + referenceLabels?: readonly string[] t: ChatViewSlotProps['t'] }): ReactNode { const { text, images, rest } = contentParts(content) @@ -193,9 +234,14 @@ function UserStyleBubble({
{renderMessageImages({ images, align: 'end' })} {showBubble &&
- {projectUserText(text)} + {projectUserText(text, referenceLabels)} {rest.map((block, i) => )}
} + {referenceLabels.length > 0 && ( +
+ {t('message.referenceSummary', { labels: referenceLabels.join(t('message.referenceSeparator')) })} +
+ )}
{actions?.(text)} @@ -240,6 +286,7 @@ export const UserMessageNodeView = memo(function UserMessageNodeView({ ( = threshold) { + lower = candidate + } else { + upper = candidate - 1 + } + } + return lower +} + /** - * Cache-hit share of prompt-side input over the whole durable log. + * Display-ready cache-hit share of prompt-side input over the whole durable log. * @param usage - the session's token-usage projection value. - * @returns rounded integer percent, or null when no input was billed. + * @returns integer text when integer rounding stays below 100, otherwise the + * minimum decimal precision that still rounds below 100; a full hit returns + * 100, and no billed input returns null. */ -export function cacheHitPercent(usage: TokenUsageProjection): number | null { +export function cacheHitPercent(usage: TokenUsageProjection): string | null { const denominator = billedInputTokens(usage) - return denominator === 0 - ? null - : Math.round(usage.cacheReadTokens / denominator * 100) + if (denominator === 0) return null + const missedInputTokens = usage.uncachedInputTokens + usage.cacheWriteTokens + if (missedInputTokens === 0) return '100' + + const integerPercent = roundedIntegerPercent(usage.cacheReadTokens, denominator) + if (integerPercent < 100) return String(integerPercent) + + // At the first distinguishing precision, the rounded result is 100 minus + // one to five units in the final decimal place. Scale only while the next + // multiplication remains at or below the denominator, then derive that + // final digit through exact small-factor comparisons. + let decimalPlaces = 1 + let scaledDoubleGap = missedInputTokens * 200 + const denominatorTens = Math.floor(denominator / 10) + while (scaledDoubleGap <= denominatorTens) { + scaledDoubleGap *= 10 + decimalPlaces += 1 + } + const denominatorOnes = denominator % 10 + let roundedLoss = 5 + for (let loss = 1; loss < 5; loss += 1) { + const factor = loss * 2 + 1 + const threshold = factor * denominatorTens + Math.floor(factor * denominatorOnes / 10) + if (scaledDoubleGap <= threshold) { + roundedLoss = loss + break + } + } + return `99.${'9'.repeat(decimalPlaces - 1)}${10 - roundedLoss}` } /** diff --git a/packages/client/ui-conversation/src/client/contract/slots.ts b/packages/client/ui-conversation/src/client/contract/slots.ts index 153fa85519..4ea0c79402 100644 --- a/packages/client/ui-conversation/src/client/contract/slots.ts +++ b/packages/client/ui-conversation/src/client/contract/slots.ts @@ -166,6 +166,11 @@ declare module '@deepseek-ai/dsh-client-ui-slots' { * reads the global workspace list. */ 'conversation.hero.workspace': { kind: 'single'; scope: 'root'; owner: EmptyWorkspaceOwnerProps } + /** + * Brand mark leading the blank-session headline. Declared by this + * package's `conversation` entry; the shell supplies a fish fallback. + */ + 'conversation.hero.brand.mark': { kind: 'single'; scope: 'root'; owner: HeroBrandMarkOwnerProps } /** * The agent-preset chip beside the workspace picker on the new-session * screen. Root scope: no session exists yet, so the choice is staged for @@ -598,6 +603,14 @@ export interface ComposerChainProps { session: ConversationSnapshot | undefined } +/** Presentation props supplied to the blank-session brand-mark occupant. */ +export interface HeroBrandMarkOwnerProps { + /** Requested square edge in pixels. */ + size: number + /** Host CSS class for preserving the default hero mark color and hover motion. */ + className?: string | undefined +} + /** * Full conversation-slot component props: runtime & child-render (view ring * + composer chain/bar + input-region + hero picker slots) & store & injected @@ -610,6 +623,7 @@ export type ConversationSlotProps = | 'conversation.input.overlay' | 'conversation.input.dock' | 'conversation.composer.dock' | 'conversation.input.left' | 'conversation.input.right' + | 'conversation.hero.brand.mark' | 'conversation.hero.workspace' | 'conversation.hero.agentPreset' > @@ -714,9 +728,11 @@ export interface ChatViewInjected { openDetails: (target: SelectionTarget) => void /** * Open a tool-arg filesystem path with the host OS default application - * (relative paths resolve against the session cwd). + * (relative paths resolve against the session cwd). Always returns a + * promise: fulfills when the Host opens the path, rejects when it cannot + * hand the path off (the chat view shows that reason and a retry). */ - openFile: (path: string) => void + openFile: (path: string) => Promise loadOlder: () => void /** Resolve a session-authorized historical image for inline display. */ loadImage: (attachment: ImageAttachmentRef) => Promise diff --git a/packages/client/ui-conversation/src/client/conversation-nodes/assistant.ts b/packages/client/ui-conversation/src/client/conversation-nodes/assistant.ts index 880bbafa44..df8f87ee53 100644 --- a/packages/client/ui-conversation/src/client/conversation-nodes/assistant.ts +++ b/packages/client/ui-conversation/src/client/conversation-nodes/assistant.ts @@ -163,6 +163,7 @@ function finalNode( firstTokenTime: state.firstTokenTime ?? null, completedTime: event.time, }, + ...event.data.interrupted === true ? { interrupted: true } : {}, } } const location = context.start?.location ?? context.matches.at(-1)?.location diff --git a/packages/client/ui-conversation/src/client/conversation-nodes/chat-snapshot-builder.ts b/packages/client/ui-conversation/src/client/conversation-nodes/chat-snapshot-builder.ts index be4e27111a..651fc780a3 100644 --- a/packages/client/ui-conversation/src/client/conversation-nodes/chat-snapshot-builder.ts +++ b/packages/client/ui-conversation/src/client/conversation-nodes/chat-snapshot-builder.ts @@ -5,6 +5,7 @@ import type { ConversationViewBuilder, ConversationViewDefinition, LegacyConversationSlice, PartialAssistant, RunningToolCall, } from '@deepseek-ai/dsh-client-runtime/client' +import { sessionRecallLabels } from '@deepseek-ai/dsh-client-runtime/client' import type { ChatNode } from '../contract/chat-nodes.ts' import { isRunningTool } from '../contract/chat-nodes.ts' @@ -138,6 +139,99 @@ function orderedVisible(nodes: readonly ChatConversationViewNode[]): ChatConvers .sort((left, right) => left.anchorSeq - right.anchorSeq || left.key.localeCompare(right.key)) } +function referenceMessageSeq(node: ChatConversationViewNode): number | undefined { + const candidate = node as ChatNode + return candidate.kind === 'user' || candidate.kind === 'steering' + ? candidate.data.seq + : undefined +} + +function followingRecall(node: ChatConversationViewNode): { + readonly messageSeq: number + readonly labels: readonly string[] +} | undefined { + const candidate = node as ChatNode + if (candidate.kind !== 'context') return undefined + return { + messageSeq: candidate.data.seq - 1, + labels: sessionRecallLabels(candidate.data.source), + } +} + +function withReferenceLabels( + node: ChatConversationViewNode, + labels: readonly string[], +): ChatConversationViewNode { + const candidate = node as ChatNode + if (candidate.kind !== 'user' && candidate.kind !== 'steering') return node + const current = candidate.data.referenceLabels ?? EMPTY_KEYS + const hasLabels = Object.hasOwn(candidate.data, 'referenceLabels') + if (sameReferences(current, labels) && hasLabels === (labels.length > 0)) return node + const data: Record = { ...candidate.data } + if (labels.length === 0) delete data.referenceLabels + else data.referenceLabels = labels + return { ...candidate, data } +} + +/** Associates a direct message with the sourced recall event that immediately follows it. */ +class ReferenceLabelProjector { + private readonly messagesBySeq = new Map() + private readonly labelsByMessageSeq = new Map() + + replace(nodes: readonly ChatConversationViewNode[]): readonly ChatConversationViewNode[] { + this.messagesBySeq.clear() + this.labelsByMessageSeq.clear() + for (const node of nodes) { + const messageSeq = referenceMessageSeq(node) + if (messageSeq !== undefined) this.messagesBySeq.set(messageSeq, node.key) + const recall = followingRecall(node) + if (recall !== undefined && recall.labels.length > 0) { + this.labelsByMessageSeq.set(recall.messageSeq, recall.labels) + } + } + return nodes.map((node) => { + const messageSeq = referenceMessageSeq(node) + return messageSeq === undefined + ? node + : withReferenceLabels(node, this.labelsByMessageSeq.get(messageSeq) ?? EMPTY_KEYS) + }) + } + + apply( + upserts: readonly ChatConversationViewNode[], + store: ChatNodeStore, + ): readonly ChatConversationViewNode[] { + const byKey = new Map(upserts.map(node => [node.key, node])) + const affected = new Set() + for (const node of upserts) { + const messageSeq = referenceMessageSeq(node) + if (messageSeq !== undefined) { + this.messagesBySeq.set(messageSeq, node.key) + affected.add(messageSeq) + } + const recall = followingRecall(node) + if (recall === undefined) continue + const current = this.labelsByMessageSeq.get(recall.messageSeq) + if (recall.labels.length === 0) this.labelsByMessageSeq.delete(recall.messageSeq) + else { + this.labelsByMessageSeq.set( + recall.messageSeq, + current !== undefined && sameReferences(current, recall.labels) ? current : recall.labels, + ) + } + affected.add(recall.messageSeq) + } + for (const messageSeq of affected) { + const key = this.messagesBySeq.get(messageSeq) + if (key === undefined) continue + const node = byKey.get(key) ?? store.get(key) + if (node === undefined) continue + byKey.set(key, withReferenceLabels(node, this.labelsByMessageSeq.get(messageSeq) ?? EMPTY_KEYS)) + } + return [...byKey.values()] + } +} + interface LegacyContribution { readonly anchorSeq: number readonly nodes: readonly ConversationNode[] @@ -384,6 +478,7 @@ export class ChatSnapshotBuilder implements ConversationViewBuilder node.key) + const nodes = this.referenceLabels.replace(input.nodes) + this.store.replace(nodes) + this.order = orderedVisible(nodes).map(node => node.key) this.locations.rebuild(this.order, this.store) - return this.snapshot(input.timeline, this.legacy.replace(input.nodes, input.timeline)) + return this.snapshot(input.timeline, this.legacy.replace(nodes, input.timeline)) } apply(input: { readonly upserts: readonly ChatConversationViewNode[] readonly timeline: ConversationTimelineSnapshot }): ChatSnapshot { + const upserts = this.referenceLabels.apply(input.upserts, this.store) let structural = false const contentOnly: ChatConversationViewNode[] = [] - for (const node of input.upserts) { + for (const node of upserts) { const previous = this.store.get(node.key) const nodeStructural = previous === undefined || previous.anchorSeq !== node.anchorSeq @@ -416,14 +513,14 @@ export class ChatSnapshotBuilder implements ConversationViewBuilder node.key) this.order = sameReferences(this.order, next) ? this.order : next this.locations.rebuild(this.order, this.store) } this.locations.touch(contentOnly) - return this.snapshot(input.timeline, this.legacy.apply(input.upserts, input.timeline)) + return this.snapshot(input.timeline, this.legacy.apply(upserts, input.timeline)) } private snapshot( diff --git a/packages/client/ui-conversation/src/client/conversation-nodes/message.ts b/packages/client/ui-conversation/src/client/conversation-nodes/message.ts index 085127f9c5..c60bbf79f1 100644 --- a/packages/client/ui-conversation/src/client/conversation-nodes/message.ts +++ b/packages/client/ui-conversation/src/client/conversation-nodes/message.ts @@ -8,14 +8,24 @@ import { import type { InboxState } from './inbox.ts' import { chatNode } from './common.ts' -type MessageNode = UserMessageNode | SteeringMessageNode | ContextMessageNode +interface ReferencedUserMessageNode extends UserMessageNode { + /** Labels cited by the immediately following session-reference context. */ + readonly referenceLabels?: readonly string[] +} + +interface ReferencedSteeringMessageNode extends SteeringMessageNode { + /** Labels cited by the immediately following session-reference context. */ + readonly referenceLabels?: readonly string[] +} + +type MessageNode = ReferencedUserMessageNode | ReferencedSteeringMessageNode | ContextMessageNode declare module '@deepseek-ai/dsh-client-ui-conversation/client' { interface ChatNodeDataMap { /** Ordinary turn-opening user message. */ - user: UserMessageNode + user: ReferencedUserMessageNode /** User message admitted into an active turn. */ - steering: SteeringMessageNode + steering: ReferencedSteeringMessageNode /** Non-user context injected into model history. */ context: ContextMessageNode } diff --git a/packages/client/ui-conversation/src/client/index.ts b/packages/client/ui-conversation/src/client/index.ts index 4a8b27acbb..814734411b 100644 --- a/packages/client/ui-conversation/src/client/index.ts +++ b/packages/client/ui-conversation/src/client/index.ts @@ -32,7 +32,7 @@ export type { ChatStore, ChatViewInjected, ChatViewSlotProps, CommandRowOwnerProps, CommandRowProps, ComposerBarInjected, ComposerAttachment, ComposerAttachmentsOwnerProps, ComposerAttachmentsProps, ComposerChainProps, ConversationInjected, ConversationSessionHeaderInjected, ConversationSessionInjected, ConversationSlotProps, ConvViewOwnerProps, - ConvViewProps, DetailsInjected, DetailsSlotProps, DetailsToolOwnerProps, EmptyWorkspaceOwnerProps, + ConvViewProps, DetailsInjected, DetailsSlotProps, DetailsToolOwnerProps, EmptyWorkspaceOwnerProps, HeroBrandMarkOwnerProps, MessageImagesOwnerProps, MessageImagesProps, RenderMessageImages, TurnTailOwnerProps, UseChatNodeTurnData, } from './contract/slots.ts' // Export discipline: packages/client/AGENTS.md. diff --git a/packages/client/ui-conversation/src/client/input/contract.ts b/packages/client/ui-conversation/src/client/input/contract.ts index bad1e55d75..b9ace8b863 100644 --- a/packages/client/ui-conversation/src/client/input/contract.ts +++ b/packages/client/ui-conversation/src/client/input/contract.ts @@ -35,7 +35,7 @@ export interface SessionInput extends InputTarget { setDraft(text: string): void /** Append ordered browser-owned image ids; busy admission phases refuse. */ addImages(ids: readonly DraftAttachmentId[]): boolean - /** Remove one browser-owned image id. */ + /** Remove one browser-owned image id; busy admission phases refuse. */ removeImage(id: DraftAttachmentId): void /** Drop ids whose browser-owned objects no longer exist. */ pruneImages(ids: readonly DraftAttachmentId[]): void @@ -75,7 +75,7 @@ export interface InputActions { setDraft(text: string): void /** Append ordered browser-owned image ids; busy admission phases refuse. */ addImages(ids: readonly DraftAttachmentId[]): boolean - /** Remove one browser-owned image id. */ + /** Remove one browser-owned image id; busy admission phases refuse. */ removeImage(id: DraftAttachmentId): void /** Drop ids whose browser-owned objects no longer exist. */ pruneImages(ids: readonly DraftAttachmentId[]): void @@ -149,9 +149,9 @@ export interface EditRange extends EditSelection { } /** - * One reference chip occurrence, backing exactly one U+FFFC placeholder in - * the draft. Identity is occurrenceId — same-named - * references stay independently addressable. label/clipboardText are the + * One reference occurrence backed by its complete inline display text in the + * draft. Identity is occurrenceId — same-named + * references stay independently addressable. label/appearance/clipboardText are the * owner's insert-time projections, cached so the chip survives owner loss * (invalid flips instead of dropping the occurrence). */ @@ -162,10 +162,14 @@ export interface Occurrence { readonly source: string /** Owner-scoped reference id. */ readonly ref: string - /** Placeholder offset in the draft; the occurrence occupies exactly [offset, offset+1). */ + /** Display-text offset in the draft. */ readonly offset: number - /** Chip display label (insert-time cache). */ + /** Display-text length; the occurrence occupies exactly [offset, offset+length). */ + readonly length: number + /** Inline display label (insert-time cache). */ readonly label: string + /** Optional domain glyph (insert-time cache). */ + readonly appearance?: ReferenceInsert['appearance'] /** Clipboard / persistence projection, e.g. `/name` (insert-time cache, never the model form). */ readonly clipboardText: string /** Owner-resolution failure flag: chip renders invalid; serialization must fail. */ @@ -214,8 +218,8 @@ export interface InputState { readonly draftRev: number readonly phase: 'plain' | 'adjudicating' | 'claimed' | 'submitting' /** Present exactly while claimed/submitting (claim snapshot during flight; submit closure withheld). */ - readonly claim?: { readonly token: string; readonly hint?: string } - /** Chip occurrence table, sorted by offset (one U+FFFC per entry). */ + readonly claim?: { readonly token: string; readonly hint?: string; readonly images?: boolean } + /** Reference occurrence table, sorted by offset. */ readonly occurrences: readonly Occurrence[] /** Live paste-match attempt (absent when no paste is matchable). */ readonly paste?: PasteAttemptState @@ -232,7 +236,7 @@ export interface InputState { export interface SubmitAttempt { readonly seq: number readonly signal: AbortSignal - /** Draft at enter time; rollback restores it only while the live draft still equals it. */ + /** Draft at enter time; settlement clears it only after acceptance. */ readonly draftSnapshot: string /** Default-message delivery intent retained while slash adjudication is pending. */ readonly mode: InputSubmitMode @@ -248,7 +252,7 @@ export type InputEvent = /** Full next draft from the textarea; editRange narrows the occurrence math (absent → diff scan). */ | { readonly type: 'draft-changed'; readonly draft: string; readonly editRange?: EditRange } | { readonly type: 'begin-command'; readonly claim: CommandClaim; readonly span: TokenSpan } - /** Place one U+FFFC at the span and mint the occurrence (scoped insert-reference event payload). */ + /** Place one inline reference at the span and mint the occurrence (scoped insert-reference event payload). */ | { readonly type: 'insert-ref'; readonly reference: ReferenceInsert; readonly span: TokenSpan } /** Delete a settled command token; success is observable as a draftRev advance. */ | { readonly type: 'consume-token'; readonly guard: ConsumeTokenGuard } @@ -271,10 +275,7 @@ export type InputEvent = | { readonly type: 'adjudicated'; readonly attempt: SubmitAttempt; readonly outcome: PickOutcome } | { readonly type: 'adjudication-failed'; readonly attempt: SubmitAttempt; readonly message: string } | { readonly type: 'submit-settled'; readonly attempt: SubmitAttempt; readonly ok: boolean; readonly outcome?: SubmitOutcome; readonly message?: string } - /** - * An ordinary (default-sink) send was accepted: clear the draft as a COMMIT — - * undo must not resurrect sent content (mirrors submit-settled's success arm). - */ + /** Commit an image-only send whose empty draft did not need an attempt. */ | { readonly type: 'send-committed' } | { readonly type: 'release' } @@ -286,5 +287,5 @@ export type InputEvent = export type InputEffect = | { readonly type: 'adjudicate'; readonly attempt: SubmitAttempt; readonly draft: string } | { readonly type: 'begin-submit'; readonly attempt: SubmitAttempt; readonly claim: CommandClaim; readonly args: string } - | { readonly type: 'default-sink'; readonly draft: string; readonly mode: InputSubmitMode } + | { readonly type: 'default-sink'; readonly attempt: SubmitAttempt; readonly draft: string; readonly mode: InputSubmitMode } | { readonly type: 'notice'; readonly level: 'info' | 'error'; readonly text: string } diff --git a/packages/client/ui-conversation/src/client/input/decorations.ts b/packages/client/ui-conversation/src/client/input/decorations.ts index bd3dd09040..1ae5e9404b 100644 --- a/packages/client/ui-conversation/src/client/input/decorations.ts +++ b/packages/client/ui-conversation/src/client/input/decorations.ts @@ -1,6 +1,6 @@ /** - * Draft decoration pure core (chips render from the occurrence - * table at placeholder offsets; the claim token renders as a mirror-layer + * Draft decoration pure core (references render from occurrence ranges; the + * claim token renders as a mirror-layer * highlight, the claim hint as ghost text). Zero React — the skeleton renders * the instructions; tests drive this directly. */ @@ -12,13 +12,19 @@ export interface TokenRange { readonly end: number } -/** One chip render instruction: the placeholder at `offset` draws as `label`. */ +/** One structured inline-reference render instruction. */ export interface ChipRender { /** Stable render key (same-labeled chips stay independent). */ readonly occurrenceId: number - /** Placeholder offset in the draft (the chip occupies [offset, offset+1)). */ + /** Display-text offset in the draft. */ readonly offset: number + /** Display-text length in the draft. */ + readonly length: number + /** Exact inline text whose native glyph metrics determine layout. */ + readonly text: string readonly label: string + /** Optional domain glyph beside the label. */ + readonly appearance?: 'session' | 'file' | 'folder' /** Owner-resolution failure styling bit. */ readonly invalid: boolean } @@ -34,6 +40,8 @@ export interface TextRefRange { readonly start: number readonly end: number readonly trigger: '/' | '@' + /** Optional icon domain for syntax-recognizable plain references. */ + readonly appearance?: 'folder' } /** Decoration product: claim token range + chip instructions + text-ref ranges + the ghost hint. */ @@ -42,7 +50,7 @@ export interface DraftDecorations { readonly token: TokenRange | null /** Chip render instructions in draft order (occurrence table is offset-sorted). */ readonly chips: readonly ChipRender[] - /** Scan-derived plain-text reference ranges (empty without a lexicon). */ + /** Scan-derived lexicon tokens and syntax-recognizable folder ranges. */ readonly textRefs: readonly TextRefRange[] /** Ghost hint shown while the claim's args are blank; null otherwise. */ readonly hint: string | null @@ -50,6 +58,7 @@ export interface DraftDecorations { /** Token matcher: a trigger char at line start or after whitespace, then a word-ish name (never crosses \n). */ const TEXT_REF_RE = /(^|\s)([/@])([\w-]+)/g +const FOLDER_REF_RE = /(^|\s)(@(?:"[^"\n]*\/|[^\s"]+\/))/g /** * Scan the draft for plain-text reference tokens against the hot lexicons. @@ -63,19 +72,31 @@ const TEXT_REF_RE = /(^|\s)([/@])([\w-]+)/g export function scanTextRefs( draft: string, lexicon: ReadonlyMap<'/' | '@', readonly string[]>, ): TextRefRange[] { - if (lexicon.size === 0 || draft === '') return [] + if (draft === '') return [] const out: TextRefRange[] = [] - TEXT_REF_RE.lastIndex = 0 - let m: RegExpExecArray | null - while ((m = TEXT_REF_RE.exec(draft)) !== null) { - const trigger = m[2] as '/' | '@' - const name = m[3] ?? '' - if (lexicon.get(trigger)?.includes(name)) { - const start = m.index + (m[1]?.length ?? 0) - out.push({ start, end: start + 1 + name.length, trigger }) + if (lexicon.size > 0) { + TEXT_REF_RE.lastIndex = 0 + let m: RegExpExecArray | null + while ((m = TEXT_REF_RE.exec(draft)) !== null) { + const trigger = m[2] as '/' | '@' + const name = m[3] ?? '' + if (lexicon.get(trigger)?.includes(name)) { + const start = m.index + (m[1]?.length ?? 0) + out.push({ start, end: start + 1 + name.length, trigger }) + } } } - return out + FOLDER_REF_RE.lastIndex = 0 + let folder: RegExpExecArray | null + while ((folder = FOLDER_REF_RE.exec(draft)) !== null) { + const token = folder[2] ?? '' + const start = folder.index + (folder[1]?.length ?? 0) + const end = start + token.length + if (!out.some(range => range.start < end && range.end > start)) { + out.push({ start, end, trigger: '@', appearance: 'folder' }) + } + } + return out.sort((left, right) => left.start - right.start) } /** The empty lexicon (default: zero text-ref decorations, old call sites unchanged). */ @@ -97,7 +118,10 @@ export function deriveDecorations( const chips = occurrences.map(o => ({ occurrenceId: o.occurrenceId, offset: o.offset, + length: o.length, + text: draft.slice(o.offset, o.offset + o.length), label: o.label, + ...o.appearance === undefined ? {} : { appearance: o.appearance }, invalid: o.invalid === true, })) const hint = claimActive && claim.hint !== undefined && draft.slice(claim.token.length).trim() === '' diff --git a/packages/client/ui-conversation/src/client/input/facade.ts b/packages/client/ui-conversation/src/client/input/facade.ts index 35aa9197a2..cc42d0c1ad 100644 --- a/packages/client/ui-conversation/src/client/input/facade.ts +++ b/packages/client/ui-conversation/src/client/input/facade.ts @@ -10,14 +10,14 @@ import type { ClientContext, ObservableSnapshot, SnapshotStore } from '@deepseek import { createSnapshotStore } from '@deepseek-ai/dsh-client-runtime/client' import type { ArbitrateKey, ArbitrateOutcome, CommandClaim, ConsumeTokenRequest, PickOutcome, - ReferenceInsert, InputTriggerController, TokenSpan, + ReferenceInsert, InputTriggerController, SubmitImageAttachment, SubmitOutcome, TokenSpan, } from '@deepseek-ai/dsh-client-ui-input-trigger/client' import type { DraftAttachmentId, EditRange, EditSelection, InputActions, InputEffect, InputNotice, InputState, PasteComponent, QueuedMessage, SessionInput, SubmitAttempt, } from './contract.ts' import type { InputSubmitMode } from '../contract/composer-submission.ts' -import { InputMachine } from './machine.ts' +import { InputMachine, projectClipboard } from './machine.ts' /** Popup face the shell needs (dismissal only; typed structurally to avoid a value import). */ export interface PopupDismissFace { @@ -45,7 +45,21 @@ export interface SessionInputDeps { */ steerQueue?: (() => void) | undefined /** The plain-message sink (send choreography / materialize fork — the hub owns it). */ - defaultSink(text: string, imageIds: readonly DraftAttachmentId[], mode: InputSubmitMode): void + defaultSink( + text: string, + imageIds: readonly DraftAttachmentId[], + mode: InputSubmitMode, + signal: AbortSignal, + ): Promise + /** Command-plane image plumbing (the hub owns the conversation face and the copy). */ + commandImages: { + /** Resolve ordered draft ids to wire payloads without sending them; rejects when an id no longer resolves. */ + serialize(ids: readonly DraftAttachmentId[]): Promise + /** Free consumed draft images after a successful command submit. */ + release(ids: readonly DraftAttachmentId[]): void + /** Localized composer notice for a claimed command that does not accept images. */ + unsupportedNotice(token: string): string + } } /** Guard tier from the machine phase. */ @@ -69,7 +83,7 @@ const EMPTY_LEXICON: ReadonlyMap<'/' | '@', readonly string[]> = new Map() export class SessionInputShell implements SessionInput { /** Published machine state + queue overlay (the InputZone currency source). */ readonly state: SnapshotStore - /** Latest surfaced notice (null after clear); the wiring renders it beside the error strip. */ + /** Latest surfaced notice (null after clear); the bar renders errors as banners and information inline. */ readonly notices: SnapshotStore = createSnapshotStore(null) /** The public provide-channel action face (one stable identity per session). */ readonly actions: InputActions = { @@ -84,10 +98,12 @@ export class SessionInputShell implements SessionInput { // production (the machine's no-clock default is a constant for pure tests). private readonly core = new InputMachine({ now: () => Date.now() }) private noticeSeq = 0 - private lastDraft = '' + private lastMirroredDraft = '' private imageIds: readonly DraftAttachmentId[] = [] + /** One image-only send at a time: Enter during the Host round-trip is a no-op. */ + private imageSendInFlight = false private disposed = false - /** Draft persistence mirror (chat store write; receives the clipboard projection, never raw placeholders). */ + /** Draft persistence mirror (chat store write; receives the clipboard projection, never display-only ranges). */ private mirrorFn: ((text: string) => void) | undefined constructor(private readonly deps: SessionInputDeps) { @@ -116,8 +132,13 @@ export class SessionInputShell implements SessionInput { return true } - /** Remove one image id from this draft. */ + /** + * Remove one image id from this draft. Busy admission phases refuse, like + * {@link addImages}: a removal landing while a command submit serializes + * would otherwise vanish from the rail yet still ride the in-flight send. + */ removeImage(id: DraftAttachmentId): void { + if (this.snapshot.phase === 'adjudicating' || this.snapshot.phase === 'submitting') return const next = this.imageIds.filter(candidate => candidate !== id) if (next.length === this.imageIds.length) return this.imageIds = next @@ -136,16 +157,6 @@ export class SessionInputShell implements SessionInput { this.publish() } - /** - * Restore a failed attempt before any images added after its admission. - * @param ids - failed attempt image ids. - */ - restoreImages(ids: readonly DraftAttachmentId[]): void { - const current = new Set(this.imageIds) - this.imageIds = [...ids.filter(id => !current.has(id)), ...this.imageIds] - this.publish() - } - /** * Clear the draft as a successful-send commit: no undo unit is recorded and * the undo history is cut, so Ctrl/Cmd-Z cannot resurrect sent content @@ -197,7 +208,28 @@ export class SessionInputShell implements SessionInput { */ submit(mode: InputSubmitMode = 'queue'): void { if (this.snapshot.draft.trim() === '' && this.imageIds.length > 0) { - if (this.snapshot.phase === 'plain') this.deps.defaultSink('', [...this.imageIds], mode) + if (this.snapshot.phase === 'plain' && !this.imageSendInFlight) { + const imageIds = [...this.imageIds] + this.imageSendInFlight = true + void this.deps.defaultSink('', imageIds, mode, new AbortController().signal).then((outcome) => { + this.imageSendInFlight = false + if (this.disposed) return + if (outcome.kind === 'success') this.commitSend(imageIds) + else if (outcome.text !== undefined) this.notify('error', outcome.text) + }, (error: unknown) => { + this.imageSendInFlight = false + if (!this.disposed) this.notify('error', error instanceof Error ? error.message : String(error)) + }) + } + return + } + // Claimed pre-gate: a claim that does not declare image acceptance never + // submits while images are attached — one notice, everything retained. + // Enter-time adjudication applies the same policy for unclaimed lines + // inside the command source itself. + const before = this.snapshot + if (before.phase === 'claimed' && this.imageIds.length > 0 && before.claim?.images !== true) { + this.notify('error', this.deps.commandImages.unsupportedNotice(before.claim?.token ?? before.draft)) return } this.run(this.core.dispatch({ type: 'enter', mode })) @@ -327,13 +359,21 @@ export class SessionInputShell implements SessionInput { * a scan-derived decoration, never state. * @param text - the plain reference text to splice in (e.g. `/name `). * @param span - pick-time span snapshot (draftRev CAS). + * @param keepCompleting - re-track at the caret after the splice so an open + * token (a directory pick's trailing slash) reopens the menu. * @returns whether the text was applied. */ - insertText(text: string, span: TokenSpan): boolean { + insertText(text: string, span: TokenSpan, keepCompleting = false): boolean { const snapshot = this.core.state if (span.draftRev !== snapshot.draftRev) return false const draft = snapshot.draft this.setDraft(draft.slice(0, span.start) + text + draft.slice(span.end)) + if (keepCompleting) { + // Machine-driven draft replacement never passes through onChange, so + // re-track at the caret inside the still-open token (see space()). + const next = this.snapshot + this.deps.inputTriggers?.()?.track(next.draft, span.start + text.length, { tier: guardOf(next.phase) }, next.draftRev) + } return true } @@ -398,7 +438,7 @@ export class SessionInputShell implements SessionInput { return } case 'default-sink': { - this.sinkSerialized(fx.draft, fx.mode) + this.sinkSerialized(fx.attempt, fx.draft, fx.mode) return } default: @@ -408,42 +448,78 @@ export class SessionInputShell implements SessionInput { /** * Prompt serialization before the sink: expand each - * placeholder to its owner's model form via the session controller's + * inline reference range to its owner's model form via the session controller's * codec routing. Owner missing / serialize failure / disposal blocks the * send — notice + draft and chips retained, never a silent downgrade to * the clipboard text. Chip-free drafts skip the async detour. */ - private sinkSerialized(draft: string, mode: InputSubmitMode): void { + private sinkSerialized(attempt: SubmitAttempt, draft: string, mode: InputSubmitMode): void { const imageIds = [...this.imageIds] const occurrences = this.core.state.occurrences if (occurrences.length === 0) { - this.deps.defaultSink(draft.trim(), imageIds, mode) + this.settleSubmit(attempt, this.deps.defaultSink(draft.trim(), imageIds, mode, attempt.signal), imageIds) return } const inputTriggers = this.deps.inputTriggers?.() const controller = new AbortController() void Promise.all(occurrences.map(async (o) => { if (inputTriggers === undefined) throw new Error(`no serializer for reference source "${o.source}"`) - return { offset: o.offset, text: await inputTriggers.serializeReference(o.source, o.ref, controller.signal) } + return { + offset: o.offset, + length: o.length, + text: await inputTriggers.serializeReference(o.source, o.ref, controller.signal), + } })).then( (parts) => { if (this.disposed) return - // Splice model forms over their placeholders (offsets are draft-time; + // Splice model forms over their display ranges (offsets are draft-time; // parts arrive offset-sorted since the table is). let out = '' let cursor = 0 for (const part of parts) { out += draft.slice(cursor, part.offset) + part.text - cursor = part.offset + 1 + cursor = part.offset + part.length } out += draft.slice(cursor) - this.deps.defaultSink(out.trim(), imageIds, mode) + this.settleSubmit(attempt, this.deps.defaultSink(out.trim(), imageIds, mode, attempt.signal), imageIds) }, (error: unknown) => { controller.abort() - if (this.disposed) return + if (this.dead(attempt)) return const message = error instanceof Error ? error.message : String(error) - this.notify('error', message) + this.run(this.core.dispatch({ type: 'submit-settled', attempt, ok: false, message })) + }, + ) + } + + /** Settle one admission attempt; successful sends consume only their captured images. */ + private settleSubmit( + attempt: SubmitAttempt, + pending: Promise, + imageIds: readonly DraftAttachmentId[] = [], + ): void { + pending.then( + (outcome) => { + if (this.dead(attempt)) return + if (outcome.kind === 'success' && imageIds.length > 0) { + const submitted = new Set(imageIds) + this.imageIds = this.imageIds.filter(id => !submitted.has(id)) + } + this.run(this.core.dispatch({ + type: 'submit-settled', + attempt, + ok: outcome.kind === 'success', + outcome, + })) + }, + (error: unknown) => { + if (this.dead(attempt)) return + this.run(this.core.dispatch({ + type: 'submit-settled', + attempt, + ok: false, + message: error instanceof Error ? error.message : String(error), + })) }, ) } @@ -456,7 +532,7 @@ export class SessionInputShell implements SessionInput { this.run(this.core.dispatch({ type: 'adjudicated', attempt, outcome: undefined })) return } - inputTriggers.adjudicate(draft.trim(), attempt.signal).then( + inputTriggers.adjudicate(draft.trim(), attempt.signal, { images: this.imageIds.length }).then( (outcome: PickOutcome) => { if (this.dead(attempt)) return this.run(this.core.dispatch({ type: 'adjudicated', attempt, outcome })) @@ -469,15 +545,34 @@ export class SessionInputShell implements SessionInput { ) } - /** The submit transaction: claim.submit against the session scope; ok maps from the outcome kind. */ + /** + * The submit transaction: claim.submit against the session scope; ok maps + * from the outcome kind. An accepting claim receives the serialized draft + * images, which are cleared and released only on a success outcome; a + * failure (serialize, transport, or handler error) keeps draft and images + * for correction. + */ private beginSubmit(attempt: SubmitAttempt, claim: CommandClaim, args: string): void { + const imageIds = claim.images === true ? [...this.imageIds] : [] Promise.resolve() - .then(() => claim.submit(args, this.deps.actx)) + .then(async () => { + const images = imageIds.length > 0 ? await this.deps.commandImages.serialize(imageIds) : [] + // Serialization may outlive the attempt (large files, session + // teardown); a dead attempt must not reach the Host executor. + if (this.dead(attempt)) return undefined + return claim.submit(args, this.deps.actx, images) + }) .then( (outcome) => { - if (this.dead(attempt)) return + if (outcome === undefined || this.dead(attempt)) return + if (outcome.kind === 'success' && imageIds.length > 0) { + const submitted = new Set(imageIds) + this.imageIds = this.imageIds.filter(id => !submitted.has(id)) + this.deps.commandImages.release(imageIds) + } this.run(this.core.dispatch({ type: 'submit-settled', attempt, ok: outcome.kind === 'success', outcome, + ...(outcome.kind === 'error' && outcome.text === undefined ? { message: 'command failed' } : {}), })) }, (error: unknown) => { @@ -501,9 +596,10 @@ export class SessionInputShell implements SessionInput { private publish(): void { const next = this.compose() this.state.set(next) - if (next.draft !== this.lastDraft) { - this.lastDraft = next.draft - this.mirrorFn?.(next.draft) + const mirroredDraft = projectClipboard(next) + if (mirroredDraft !== this.lastMirroredDraft) { + this.lastMirroredDraft = mirroredDraft + this.mirrorFn?.(mirroredDraft) } } } diff --git a/packages/client/ui-conversation/src/client/input/hub.ts b/packages/client/ui-conversation/src/client/input/hub.ts index 54e09200ce..7e3b95a314 100644 --- a/packages/client/ui-conversation/src/client/input/hub.ts +++ b/packages/client/ui-conversation/src/client/input/hub.ts @@ -9,7 +9,7 @@ * real host entity, so the sink is one unconditional prompt path. */ import type { ClientContext, ISessions, SessionBinding, SessionFace, SessionId } from '@deepseek-ai/dsh-client-runtime/client' -import type { InputTriggerController } from '@deepseek-ai/dsh-client-ui-input-trigger/client' +import type { InputTriggerController, SubmitImageAttachment, SubmitOutcome } from '@deepseek-ai/dsh-client-ui-input-trigger/client' import type { TranslateNS } from '@deepseek-ai/dsh-client-locale/client' import { queueReadFaceOf } from '../queue/store.ts' import type { ComposerKeyboard, DraftAttachmentId, SessionInputResolver, SessionInput } from './contract.ts' @@ -29,7 +29,9 @@ interface ConversationAttachmentFace { text: string, imageIds: readonly DraftAttachmentId[], mode: InputSubmitMode, - ): Promise + signal?: AbortSignal, + ): Promise + serializeDraftImages(imageIds: readonly DraftAttachmentId[]): Promise releaseDraftImage(id: DraftAttachmentId): void } @@ -75,8 +77,22 @@ export class InputHub implements SessionInputResolver { inputTriggers: () => this.controller(actx), popup: () => this.popup(actx), queue: queueReadFaceOf(session), - defaultSink: (text, imageIds, mode) => { this.sink(session, text, imageIds, mode) }, + defaultSink: (text, imageIds, mode, signal) => this.sink(session, text, imageIds, mode, signal), steerQueue: () => { void this.steerQueue(session, shell) }, + commandImages: { + serialize: ids => this.conversation().serializeDraftImages(ids), + // Asymmetric with serialize on purpose: release settles AFTER the + // submit RPC, where session teardown may already have unloaded the + // conversation service (the same tolerance as the scope disposer + // above); leaked preview URLs then die with the document. + release: (ids) => { + const conversation = this.rootCtx.get('conversation') as ConversationAttachmentFace | undefined + for (const imageId of ids) conversation?.releaseDraftImage(imageId) + }, + unsupportedNotice: token => this.t('command.imagesUnsupported', { + command: token.trim().replace(/^\//u, ''), + }), + }, }) this.shells.set(id, shell) // The one teardown axis: listeners, shell, and map entries all ride the @@ -90,7 +106,7 @@ export class InputHub implements SessionInputResolver { actx.on('slash/input-consume-token', req => shell.consumeToken(req.guard) ? true : undefined), actx.on('slash/input-insert-text', req => - shell.insertText(req.text, req.span) ? true : undefined), + shell.insertText(req.text, req.span, req.continue === true) ? true : undefined), ] return () => { for (const off of offs) off() @@ -144,27 +160,17 @@ export class InputHub implements SessionInputResolver { * Default sink: optimistic clear + prompt. The session is always a real * host entity (materialized when its workspace was picked), so there is * exactly one path; a failed first prompt is an ordinary prompt failure - * (error strip via promptError, draft restored only while untouched). + * (banner via promptError, draft restored only while untouched). */ private sink( session: SessionFace, text: string, imageIds: readonly DraftAttachmentId[], mode: InputSubmitMode, - ): void { - if (text === '' && imageIds.length === 0) return - const shell = this.shells.get(session.sessionId) - // Commit, not an editable clear: undo must not resurrect sent content. - shell?.commitSend(imageIds) - void this.conversation().sendSession(session, text, imageIds, mode).catch(() => { - if (this.shells.get(session.sessionId) === shell) { - shell?.restoreImages(imageIds) - if (shell?.snapshot.draft === '') shell.setDraft(text) - return - } - const conversation = this.rootCtx.get('conversation') as ConversationAttachmentFace | undefined - for (const id of imageIds) conversation?.releaseDraftImage(id) - }) + signal: AbortSignal, + ): Promise { + if (text === '' && imageIds.length === 0) return Promise.resolve({ kind: 'success' }) + return this.conversation().sendSession(session, text, imageIds, mode, signal) } /** diff --git a/packages/client/ui-conversation/src/client/input/machine.ts b/packages/client/ui-conversation/src/client/input/machine.ts index 25fdf2fc9a..a1a49004a4 100644 --- a/packages/client/ui-conversation/src/client/input/machine.ts +++ b/packages/client/ui-conversation/src/client/input/machine.ts @@ -4,8 +4,8 @@ * clock. Package-private — the SessionInput shell is the only caller and the * sole executor of the returned effects. * - * Draft truth: the draft string holds one U+FFFC placeholder per chip; the - * occurrence table carries identity and the owner's cached projections. Every + * Draft truth: the draft string holds each reference's complete inline display + * text; the occurrence table carries identity, range, and the owner's cached projections. Every * draft mutation is one transaction — draft edit, occurrence reconciliation, * and undo-log push are atomic inside dispatch() — and bumps draftRev, which * is what lets span CAS reduce to a revision-equality check: equal rev ⟹ @@ -20,9 +20,21 @@ import type { InputState, Occurrence, PasteAttemptState, PasteComponent, SubmitAttempt, } from './contract.ts' -/** The object-replacement character backing every chip occurrence in the draft. */ +/** Legacy fixed-width object replacement character rejected from pasted text. */ export const PLACEHOLDER = '' +const REFERENCE_PLACEHOLDER_RE = /[\uE100-\uE11D\uFFFC]/gu + +/** + * Build the inline draft text whose leading marker is decorated as the + * reference icon in the backdrop. + * @param reference - reference insertion with its cached display projection. + * @returns display text with one marker glyph followed by the complete label. + */ +export function referenceDraftText(reference: Pick): string { + return `@${reference.label}` +} + /** The machine never writes the queue; the wiring layer overlays the queue store's projection. */ const EMPTY_QUEUE: InputState['queue'] = [] @@ -67,10 +79,9 @@ function diffEdit(prev: string, next: string): EditRange { } /** - * Expand the draft's placeholders into their occurrences' clipboard text - * (the persistence mirror and clipboard both write this - * projection — U+FFFC never leaves the machine). Table order is offset - * order, so one linear walk pairs placeholders with entries. + * Expand the draft's reference ranges into their occurrences' clipboard text + * for persistence and clipboard projection. Table order is offset order, so + * one linear walk pairs ranges with entries. * @param state - published input state. * @returns the plain-text projection of the draft. */ @@ -81,7 +92,7 @@ export function projectClipboard(state: Pick= range.end) kept.push(delta === 0 ? o : { ...o, offset: o.offset + delta }) } this.occurrences = kept @@ -217,14 +236,16 @@ export class InputMachine { } /** Mint one occurrence at a draft offset. */ - private mint(reference: ReferenceInsert, offset: number): Occurrence { + private mint(reference: ReferenceInsert, offset: number, length: number): Occurrence { this.occurrenceSeq += 1 return { occurrenceId: this.occurrenceSeq, source: reference.source, ref: reference.ref, offset, + length, label: reference.label, + ...reference.appearance === undefined ? {} : { appearance: reference.appearance }, clipboardText: reference.clipboardText, } } @@ -285,19 +306,20 @@ export class InputMachine { } /** - * Shared chip-insertion transaction: replace [span) with one placeholder + * Shared reference-insertion transaction: replace [span) with one inline * occurrence (insert-ref and paste-upgrade both land here). A separating - * space follows the chip unless one is already next. - * @returns the inserted length (placeholder plus optional gap). + * space follows the reference unless one is already next. + * @returns the inserted length (display text plus optional gap). */ private replaceSpanWithChip(reference: ReferenceInsert, span: TokenSpan): number { this.pushTxn() this.typingRun = undefined const tail = this.draft.slice(span.end) const gap = tail.length === 0 || tail[0] !== ' ' ? ' ' : '' - const inserted = PLACEHOLDER + gap + const displayText = referenceDraftText(reference) + const inserted = displayText + gap this.reconcile({ start: span.start, end: span.end, insertedLength: inserted.length }) - this.withMinted([this.mint(reference, span.start)]) + this.withMinted([this.mint(reference, span.start, displayText.length)]) this.adopt(this.draft.slice(0, span.start) + inserted + tail) this.watchClaim() return inserted.length @@ -384,7 +406,7 @@ export class InputMachine { // ---- paste plane ---- /** - * Paste as one transaction: the text (U+FFFC-sanitized) replaces the + * Paste as one transaction: the text (reference-placeholder-sanitized) replaces the * selection; hot-snapshot sync matches componentize inside the SAME * transaction (one undo returns to pre-paste); a match attempt opens for * the async remainder while the phase still accepts reference mutations. @@ -395,19 +417,20 @@ export class InputMachine { ): InputEffect[] { const { start, end } = selection if (start < 0 || start > end || end > this.draft.length) return [] - const text = rawText.split(PLACEHOLDER).join('') + const text = rawText.replace(REFERENCE_PLACEHOLDER_RE, '') this.pushTxn(selection) this.typingRun = undefined // Componentize: replace each matched token range (paste-text coordinates, - // disjoint by contract) with a placeholder while assembling the insert. + // disjoint by contract) with inline display text while assembling the insert. const sorted = [...components].sort((a, b) => a.start - b.start) const minted: Occurrence[] = [] let inserted = '' let cursor = 0 for (const c of sorted) { inserted += text.slice(cursor, c.start) - minted.push(this.mint(c.reference, start + inserted.length)) - inserted += PLACEHOLDER + const displayText = referenceDraftText(c.reference) + minted.push(this.mint(c.reference, start + inserted.length, displayText.length)) + inserted += displayText cursor = c.end } inserted += text.slice(cursor) @@ -473,7 +496,9 @@ export class InputMachine { this.phase = 'adjudicating' return [{ type: 'adjudicate', attempt, draft: this.draft }] } - return [{ type: 'default-sink', draft: this.draft, mode }] + const attempt = this.beginAttempt(mode) + this.phase = 'submitting' + return [{ type: 'default-sink', attempt, draft: this.draft, mode }] } private onAdjudicated(attempt: SubmitAttempt, outcome: Extract['outcome']): InputEffect[] { @@ -491,11 +516,18 @@ export class InputMachine { } // 'handled' (source dealt internally), {insert} (no enter-time span // semantics), or a miss: all land plain; only the miss flows to the sink. + if (outcome === undefined) { + this.phase = 'submitting' + return [{ + type: 'default-sink', + attempt, + draft: attempt.draftSnapshot, + mode: attempt.mode, + }] + } this.inflight = undefined this.phase = 'plain' - return outcome === undefined - ? [{ type: 'default-sink', draft: attempt.draftSnapshot, mode: attempt.mode }] - : [] + return [] } private onAdjudicationFailed(attempt: SubmitAttempt, message: string): InputEffect[] { @@ -514,7 +546,13 @@ export class InputMachine { this.phase = 'plain' this.claim = undefined this.occurrences = [] - this.adopt('') + // Text appended after the sent snapshot during the Host round-trip + // survives the commit; edits interleaved with committed content cannot + // be separated from it, so only a pure suffix is retained. + const snapshot = flight.attempt.draftSnapshot + this.adopt(this.draft !== snapshot && this.draft.startsWith(snapshot) + ? this.draft.slice(snapshot.length) + : '') // Committed content is gone for good: undo must not resurrect a sent draft. this.log = [] this.redoStack = [] @@ -524,24 +562,24 @@ export class InputMachine { ? [{ type: 'notice', level: ev.outcome.kind === 'error' ? 'error' : 'info', text: ev.outcome.text }] : [] } - const text = ev.message ?? ev.outcome?.text ?? 'command failed' - // Drift guard: keep the enter-time draft (same claim) only while the - // live draft still equals it; user input typed during flight wins. + const text = ev.message ?? ev.outcome?.text + // Keep the same command claim only while the live draft still equals the + // enter-time draft; user input typed during flight wins. // Claimed re-entry additionally requires the watch to hold — an // enter-path snapshot may carry leading whitespace the token never had. if (this.draft === flight.attempt.draftSnapshot && this.claim !== undefined && this.draft.startsWith(this.claim.token)) { this.phase = 'claimed' - return [{ type: 'notice', level: 'error', text }] + return text === undefined ? [] : [{ type: 'notice', level: 'error', text }] } this.phase = 'plain' this.claim = undefined - return [{ type: 'notice', level: 'error', text }] + return text === undefined ? [] : [{ type: 'notice', level: 'error', text }] } - /** Ordinary send accepted: clear as a commit (no undo unit; sent content - * must not be resurrectable — same discipline as submit-settled success). */ + /** Cut undo state after an accepted image-only send. */ private onSendCommitted(): InputEffect[] { + if (this.phase !== 'plain') return [] this.claim = undefined this.occurrences = [] this.adopt('') diff --git a/packages/client/ui-conversation/src/client/locales.ts b/packages/client/ui-conversation/src/client/locales.ts index 368475c583..db4d218d21 100644 --- a/packages/client/ui-conversation/src/client/locales.ts +++ b/packages/client/ui-conversation/src/client/locales.ts @@ -66,11 +66,14 @@ export const zh = { 'settings.enter.description': '仅在智能体运行时生效；Cmd/Ctrl+Enter 使用另一行为', 'settings.enter.queue': '排队发送', 'settings.enter.steer': '插话发送', - 'access.confirm.title': '确认启用 Full access？', - 'access.confirm.description': '启用 Full access 后，agent 将减少确认步骤，并且可以直接执行更多操作，包括敏感操作、文件修改或外部命令。仅建议在你信任当前任务时使用。', + 'access.preset.readOnly': '仅可查看', + 'access.preset.workspaceWrite': '可写入工作区', + 'access.preset.fullAccess': '完全权限', + 'access.confirm.title': '确认启用完全权限？', + 'access.confirm.description': '启用完全权限后，智能体将减少确认步骤，并且可以直接执行更多操作，包括敏感操作、文件修改或外部命令。仅建议在你信任当前任务时使用。', 'access.confirm.acknowledge': '我已了解风险，并愿意继续', 'access.confirm.cancel': '取消', - 'access.confirm.enable': '启用 Full access', + 'access.confirm.enable': '启用完全权限', 'hero.headline': '探索未至之境', 'hero.preview': '预览版', 'hero.chooseWorkspace': '选择工作区', @@ -92,9 +95,15 @@ export const zh = { 'chat.loadError': '历史加载失败：{message}（{code}）', 'chat.loadOlder': '加载更早', 'chat.toBottom': '回到底部', + 'fileOpen.title': '无法打开文件', + 'fileOpen.unknown': '无法打开此文件', + 'fileOpen.folderTitle': '无法打开文件夹', + 'fileOpen.folderUnknown': '无法打开此文件夹', 'message.extraBlock': '附加内容块', 'message.contextInjection': '上下文注入', 'message.contextRecall': '跨会话召回', + 'message.referenceSummary': '引用会话 · {labels}', + 'message.referenceSeparator': '、', 'message.context.instructions.loaded': '已载入', 'message.context.instructions.added': '已新增', 'message.context.instructions.updated': '已更新', @@ -134,6 +143,7 @@ export const zh = { 'command.failed': '命令失败', 'command.done': '已完成', 'command.title': '命令', + 'command.imagesUnsupported': '/{command} 不接受图片附件，请先移除图片', 'approval.waiting': '等待审批', 'approval.detail.aria': '审批详情', 'approval.escalation': '工具 {toolName} 请求越权执行', @@ -236,6 +246,9 @@ export const en = { 'settings.enter.description': 'Busy only; Cmd/Ctrl+Enter uses the other behavior', 'settings.enter.queue': 'Queue', 'settings.enter.steer': 'Steer', + 'access.preset.readOnly': 'Read Only', + 'access.preset.workspaceWrite': 'Workspace Write', + 'access.preset.fullAccess': 'Full access', 'access.confirm.title': 'Enable Full access?', 'access.confirm.description': 'Full access reduces confirmation steps and lets the agent perform more actions directly, including sensitive operations, file changes, or external commands. Only use it when you trust the current task.', 'access.confirm.acknowledge': 'I understand the risks and want to continue', @@ -262,9 +275,15 @@ export const en = { 'chat.loadError': 'Failed to load history: {message} ({code})', 'chat.loadOlder': 'Load earlier', 'chat.toBottom': 'Back to bottom', + 'fileOpen.title': 'Couldn’t open file', + 'fileOpen.unknown': 'Couldn’t open this file', + 'fileOpen.folderTitle': 'Couldn’t open folder', + 'fileOpen.folderUnknown': 'Couldn’t open this folder', 'message.extraBlock': 'Extra content block', 'message.contextInjection': 'Context injection', 'message.contextRecall': 'Session recall', + 'message.referenceSummary': 'Referenced session · {labels}', + 'message.referenceSeparator': ', ', 'message.context.instructions.loaded': 'loaded', 'message.context.instructions.added': 'added', 'message.context.instructions.updated': 'updated', @@ -304,6 +323,7 @@ export const en = { 'command.failed': 'Command failed', 'command.done': 'Completed', 'command.title': 'Command', + 'command.imagesUnsupported': '/{command} does not accept image attachments; remove them first', 'approval.waiting': 'Waiting for approval', 'approval.detail.aria': 'Approval details', 'approval.escalation': 'Tool {toolName} requests privileged execution', diff --git a/packages/client/ui-conversation/src/client/reference/ReferenceIcon.tsx b/packages/client/ui-conversation/src/client/reference/ReferenceIcon.tsx new file mode 100644 index 0000000000..fcc89fe30e --- /dev/null +++ b/packages/client/ui-conversation/src/client/reference/ReferenceIcon.tsx @@ -0,0 +1,35 @@ +import type { ReactNode } from 'react' +import { + IconBrowseOutline16, IconFolderClose16, +} from '@deepseek-ai/dsh-client-ui-primitives' + +/** Reference domains with distinct composer and transcript glyphs. */ +export type ReferenceIconKind = 'session' | 'file' | 'folder' + +/** Props shared by inline reference glyphs. */ +export interface ReferenceIconProps { + kind: ReferenceIconKind + size?: number + className?: string | undefined +} + +/** + * Render the icon that identifies one inline reference domain. + * @param props - Reference kind, optional size, and optional CSS class. + * @returns The corresponding current-color SVG glyph. + */ +export function ReferenceIcon({ kind, size = 16, className }: ReferenceIconProps): ReactNode { + switch (kind) { + case 'session': + return ( + + + + ) + case 'file': return + case 'folder': return + } +} diff --git a/packages/client/ui-conversation/src/client/service.ts b/packages/client/ui-conversation/src/client/service.ts index 198eee5f0f..a37816472c 100644 --- a/packages/client/ui-conversation/src/client/service.ts +++ b/packages/client/ui-conversation/src/client/service.ts @@ -13,6 +13,7 @@ import type { Context } from '@deepseek-ai/cordis' // error, so scope resolution goes through the sessions service (scopeOf // method) instead of the standalone helper. import type { ISessions, SessionFace, SessionId } from '@deepseek-ai/dsh-client-runtime/client' +import type { SubmitImageAttachment, SubmitOutcome } from '@deepseek-ai/dsh-client-ui-input-trigger/client' import type { ImageAttachmentRef, ImageMediaType } from '@deepseek-ai/dsh-attachment' import type { ComposerAttachment } from './contract/slots.ts' import type { QueueAction, QueueItemId } from './contract/queue.ts' @@ -138,22 +139,26 @@ export class ConversationController extends Service implements IConversation { * @param text - serialized prompt text. * @param imageIds - ordered draft-local attachment ids. * @param mode - queue or steer delivery selected by composer policy. + * @param signal - optional cancellation for the complete Host admission. + * @returns the Host admission outcome; local attachment preparation failures reject. */ async sendSession( session: SessionFace, text: string, imageIds: readonly DraftAttachmentId[], mode: InputSubmitMode, - ): Promise { + signal?: AbortSignal, + ): Promise { const attachments = this.draftImages(imageIds) if (attachments.length !== imageIds.length) { throw new Error('conversation.sendSession: one or more draft images are no longer available') } const uploaded = await this.serializeImages(attachments.map(attachment => attachment.file)) const content = [...uploaded, ...(text === '' ? [] : [{ type: 'text' as const, text }])] - const result = await session.prompt(content, mode) - if (!result.ok) throw new Error(`conversation.send failed: ${result.error.code}: ${result.error.message}`) + const result = await session.prompt(content, mode, signal) + if (!result.ok) return { kind: 'error' } this.releaseDraftImages(attachments) + return { kind: 'success' } } /** @@ -185,6 +190,21 @@ export class ConversationController extends Service implements IConversation { return attachments } + /** + * Serialize ordered draft images to command-submit wire payloads without + * sending or releasing them (the composer releases only after the command + * settles successfully). + * @param imageIds - ordered draft-local attachment ids. + * @returns base64 payloads in id order. + */ + async serializeDraftImages(imageIds: readonly DraftAttachmentId[]): Promise { + const attachments = this.draftImages(imageIds) + if (attachments.length !== imageIds.length) { + throw new Error('conversation.serializeDraftImages: one or more draft images are no longer available') + } + return Promise.all(attachments.map(attachment => this.encodeImage(attachment.file))) + } + /** * Release one browser-owned draft image and preview URL. * @param id - draft attachment id. @@ -314,12 +334,16 @@ export class ConversationController extends Service implements IConversation { /** Convert browser files to canonical base64 prompt parts. */ private serializeImages(images: readonly File[]): Promise[0]> { - return Promise.all(images.map(async file => ({ - type: 'image' as const, + return Promise.all(images.map(async file => ({ type: 'image' as const, ...await this.encodeImage(file) }))) + } + + /** Canonical base64 wire form of one browser image file. */ + private async encodeImage(file: File): Promise { + return { mediaType: imageMediaType(file.type), data: bytesToBase64(new Uint8Array(await file.arrayBuffer())), ...(file.name === '' ? {} : { name: file.name }), - }))) + } } } diff --git a/packages/client/ui-conversation/src/client/skeleton/ConversationRoot.tsx b/packages/client/ui-conversation/src/client/skeleton/ConversationRoot.tsx index ef1221cd99..07655d7dba 100644 --- a/packages/client/ui-conversation/src/client/skeleton/ConversationRoot.tsx +++ b/packages/client/ui-conversation/src/client/skeleton/ConversationRoot.tsx @@ -159,7 +159,7 @@ export function ConversationRoot({ const composerBar = (
{hero && } - {hero && } + {hero && } {hero && heroWorkspaceRow} {zone !== undefined && renderSlot('conversation.input.dock', zone)} {inputBar} diff --git a/packages/client/ui-conversation/src/client/skeleton/EmptyHero.tsx b/packages/client/ui-conversation/src/client/skeleton/EmptyHero.tsx index 4865ceecfa..9db09e3141 100644 --- a/packages/client/ui-conversation/src/client/skeleton/EmptyHero.tsx +++ b/packages/client/ui-conversation/src/client/skeleton/EmptyHero.tsx @@ -102,6 +102,8 @@ export function HeroGlow({ className }: { className?: string | undefined }) { export interface HeroShellProps { /** The owner's locale seat, passed down as a plain prop. */ t: HeroTranslate + /** Authorized renderer for the hero brand-mark slot. */ + renderSlot: ConversationSlotProps['renderSlot'] /** Overlay content after the stack (modals). */ children?: ReactNode } @@ -112,14 +114,16 @@ export interface HeroShellProps { * @param props - see {@link HeroShellProps}. * @returns the centered hero element tree. */ -export function HeroShell({ t, children }: HeroShellProps) { +export function HeroShell({ t, renderSlot, children }: HeroShellProps) { return (
{/* figma 34:10412: fish 34×25 leading the headline, gap 10. */} - + {renderSlot('conversation.hero.brand.mark', { size: 34, className: css.fish }, { + fallback: , + })} {t('hero.headline')} {t('hero.preview')} diff --git a/packages/client/ui-conversation/src/client/skeleton/InputBar.module.css b/packages/client/ui-conversation/src/client/skeleton/InputBar.module.css index 6635322a5a..e5b85df3e9 100644 --- a/packages/client/ui-conversation/src/client/skeleton/InputBar.module.css +++ b/packages/client/ui-conversation/src/client/skeleton/InputBar.module.css @@ -1,12 +1,3 @@ -/* One-glyph font: maps ONLY U+FFFC to a blank 4em-advance glyph (every other - codepoint falls through to the next family). Loaded first in the composer - font stack, it gives the placeholder a real cell width INSIDE the textarea, - so the backdrop chip (same char, same stack) matches it by construction — - the two layers cannot drift and the chip gets a usable label cell. */ -@font-face { - font-family: 'DshChipCell'; - src: url('data:font/ttf;base64,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') format('truetype'); -} /* Floating capsule input (figma Input_Bottom 75:8208): card floats above the viewport bottom inside the centered message column; textarea on top, action @@ -24,7 +15,7 @@ /* Side pads ride the shared clearance (figma Input_Bottom drew L32/R32/B8; the sides narrow with the shared width axis); the bottom gradient mask is owned by the chat scroller. No top pad: the composer stack's gap owns - the space above; error/status strips still carry their own margin. */ + the space above; the status strip still carries its own margin. */ padding: 0 var(--dsh-composer-side-clearance) 8px; } @@ -47,11 +38,6 @@ line-height: 18px; } -.noticeError { - background: var(--dsw-alias-interactive-bg-hover-danger); - color: var(--dsw-alias-state-error-primary); -} - .card { box-sizing: border-box; position: relative; /* overlay anchor positioning context */ @@ -150,9 +136,9 @@ position: relative; } -/* Decoration backdrop: same metrics as the textarea, transparent glyphs; only - the highlight backgrounds and the ghost hint show through the transparent - textarea background above it. */ +/* Decoration backdrop: same metrics as the transparent-text textarea. It owns + every visible glyph plus the range colors and ghost hint; the textarea above + retains the native selection and caret. */ .backdrop { position: absolute; inset: 0; @@ -161,6 +147,11 @@ pointer-events: none; } +.backdropDisabled, +.backdropDisabled :is(.hlToken, .hint, .textRef, .chip, .chipInvalid) { + color: var(--dsw-alias-label-tertiary); +} + .hlToken { background-color: transparent; color: var(--dsw-alias-state-warn-label); @@ -205,6 +196,7 @@ outline: none; background: transparent; color: transparent; + -webkit-text-fill-color: transparent; /* Business blue, not brand-primary: that token resolves to ink in this sheet. */ caret-color: var(--dsw-alias-state-business-primary); } @@ -219,10 +211,7 @@ /* figma .InputText 34:10434: pl 16 / pr 12 / pt 4. Backdrop MUST share these metrics or the highlight ranges drift off the glyphs. */ padding: 4px 12px 0 16px; - /* DshChipCell first: ONLY U+FFFC resolves there (4em blank cell — the chip - slot); everything else falls through to the app stack. All three layers - share the stack, so placeholder advances agree by construction. */ - font-family: 'DshChipCell', var(--dsw-font-family); + font-family: var(--dsw-font-family); font-size: inherit; /* Three consumers, not two: the mirror sizes the stack, the layers must break lines identically, and the caret reveal parses this value to step one line @@ -247,12 +236,15 @@ /* figma 34:10434: #ADB2B8 light / #81858C dark — the caption pair exactly. */ .input::placeholder { color: var(--dsw-alias-label-caption); + -webkit-text-fill-color: var(--dsw-alias-label-caption); user-select: none; } -/* Running lock: grayed but the draft stays visible; the turn ending re-enables. */ +/* The backdrop owns disabled draft color; the textarea remains caret-only so + its marker glyphs cannot cover the reference icons beneath it. */ .input:disabled { - color: var(--dsw-alias-label-tertiary); + color: transparent; + -webkit-text-fill-color: transparent; cursor: not-allowed; } @@ -275,6 +267,7 @@ (figma Input_Bottom chrome). */ .row { display: flex; + flex-wrap: wrap; align-items: center; justify-content: space-between; gap: 12px; @@ -311,6 +304,12 @@ .trailing { flex: none; + /* Wrap keeps the left mode chips and the right controls apart when the card + runs out of row width: the trailing group (model + send) moves to its own + line instead of the left group shrinking until its chip overlaps the + model trigger (external:107). The auto margin re-anchors it right on the + wrapped line; on a single line space-between already pins it right. */ + margin-left: auto; gap: 12px; } @@ -425,43 +424,50 @@ display: none; } -/* Reference chip: rendered in the backdrop at the placeholder offset. Hard - alignment constraint: the chip's advance must equal the textarea's U+FFFC - advance EXACTLY or every glyph after it drifts (caret/selection follow the - textarea character stream). The ::before renders the same U+FFFC through - the same font stack (DshChipCell 4em cell), so both layers agree by - construction — no measured widths. The label overlays the cell, clipped - with an ellipsis; the full name rides the title tooltip. */ -.chip { +.textRefTrigger { position: relative; - border-radius: 6px; - background: rgba(97, 135, 216, 0.22); } -.chip::before { - content: '\FFFC'; +.textRefTriggerGlyph { color: transparent; } -.chipLabel { - /* Compensated-scale centering: overflow clipping happens BEFORE transform, - so the box is laid out at 1/0.72 of the cell and scaled back down — the - clip edge then lands on the visual cell edge, not mid-glyph. */ +.textRefIcon { position: absolute; - left: 50%; top: 50%; - width: calc(100% / 0.72 - 10px); - display: flex; - align-items: center; - justify-content: center; - overflow: hidden; - color: var(--dsw-alias-label-primary); - white-space: nowrap; - transform: translate(-50%, -50%) scale(0.72); + left: 50%; + transform: translate(-50%, -50%); +} + +/* Structured references use the same inline-backdrop technique as /skill: + their complete display text remains in the textarea, so wrapping and caret + geometry come from the browser's native glyph metrics. The leading marker + reserves the icon's advance while the backdrop paints the domain glyph. */ +.chip { + position: relative; + color: var(--dsw-alias-state-business-primary); + background: transparent; + -webkit-box-decoration-break: clone; + box-decoration-break: clone; +} + +.chipTrigger { + position: relative; +} + +.chipTriggerGlyph { + color: transparent; +} + +.chipIcon { + position: absolute; + top: 50%; + left: 50%; + transform: translate(-50%, -50%); } .chipInvalid { - background: rgba(216, 97, 97, 0.2); text-decoration: line-through; opacity: 0.7; + color: var(--dsw-alias-state-error-primary); } diff --git a/packages/client/ui-conversation/src/client/skeleton/InputBar.tsx b/packages/client/ui-conversation/src/client/skeleton/InputBar.tsx index 501001215d..2d96e3bf33 100644 --- a/packages/client/ui-conversation/src/client/skeleton/InputBar.tsx +++ b/packages/client/ui-conversation/src/client/skeleton/InputBar.tsx @@ -25,6 +25,7 @@ import type { ComposerBarProps } from '../contract/slots.ts' import { deriveDecorations } from '../input/decorations.ts' import type { DraftDecorations } from '../input/decorations.ts' import { attachmentErrorText, imageSizeText } from '../image-labels.ts' +import { ReferenceIcon } from '../reference/ReferenceIcon.tsx' import { ContextMeter } from './ContextMeter.tsx' import { PermissionSelect } from './PermissionSelect.tsx' import { isSafariBrowser, repairSafariTextareaLayout } from './safari.ts' @@ -65,9 +66,9 @@ export function InputBar({ [draftImages, input?.imageIds], ) const empty = draft.trim() === '' && attachments.length === 0 - // Transient error banner (image-intake rejections and prompt failures): the - // seq keys the Toast so an identical repeated message restarts the - // hold-then-fade cycle instead of silently reusing the faded one. + // Transient error banner (machine notices, image-intake rejections, and + // prompt failures): the seq keys the Toast so an identical repeated message + // restarts the hold-then-fade cycle instead of reusing the faded one. const [toast, setToast] = useState<{ seq: number; text: string } | null>(null) const toastSeq = useRef(0) const showToast = useCallback((text: string) => { @@ -91,6 +92,9 @@ export function InputBar({ ? attachmentErrorText(t, promptError.error.details.reason, imageLimits) : `${promptError.error.message} (${promptError.error.code})`) }, [promptError, showToast, t, imageLimits]) + useEffect(() => { + if (notice?.level === 'error') showToast(notice.text) + }, [notice, showToast]) const inputRef = useRef(null) const cardRef = useRef(null) const scrollRef = useRef(null) @@ -265,6 +269,14 @@ export function InputBar({ return () => { el.removeEventListener('wheel', onWheel) } }, []) + // selectionStart/End are number|null in lib.dom; the type-aware lint program narrows them. + /* oxlint-disable typescript/no-unnecessary-condition */ + const selectionOf = (el: HTMLTextAreaElement) => ({ + start: el.selectionStart ?? 0, + end: el.selectionEnd ?? el.selectionStart ?? 0, + }) + /* oxlint-enable typescript/no-unnecessary-condition */ + const onKeyDown = (e: KeyboardEvent): void => { if (workspaceTrigger) { if (e.key === 'Enter' || e.key === ' ') { @@ -275,13 +287,31 @@ export function InputBar({ } // Absent machine without a Workspace recovery action stays disabled; the // guard narrows the faces for the paths below. - if (keyboard === undefined || inputActions === undefined) return + if (input === undefined || keyboard === undefined || inputActions === undefined) return // Shift+Enter is the native newline UNCONDITIONALLY — decided before the // IME guard so a composition-closing Shift+Enter still breaks the line. if (e.key === 'Enter' && e.shiftKey) return // keyCode 229 is the legacy IME-composition signal engines emit without isComposing. // oxlint-disable-next-line typescript/no-deprecated const composing = composingRef.current || e.nativeEvent.isComposing || e.nativeEvent.keyCode === 229 + if (!composing && !machineBusy && !locked + && (e.key === 'Backspace' || e.key === 'Delete')) { + const selection = selectionOf(e.currentTarget) + if (selection.start === selection.end) { + const occurrence = input.occurrences.find(o => e.key === 'Backspace' + ? o.offset + o.length === selection.start + : o.offset === selection.start) + if (occurrence !== undefined) { + e.preventDefault() + const start = occurrence.offset + const end = occurrence.offset + occurrence.length + keyboard.setDraft(draft.slice(0, start) + draft.slice(end), { start, end, insertedLength: 0 }) + restoreCaret(e.currentTarget, start) + keyboard.track(keyboard.snapshot.draft, start) + return + } + } + } if (e.key === 'ArrowUp' || e.key === 'ArrowDown') { if (keyboard.arbitrate(e.key === 'ArrowUp' ? 'up' : 'down', composing) === 'consumed') e.preventDefault() return @@ -348,45 +378,32 @@ export function InputBar({ keyboard.track(next, e.target.selectionStart ?? next.length) } - // ---- chip atomicity (DOM layer; the machine sees only transactions) ---- - // Placeholders occupy exactly one char, so caret positions are always - // BETWEEN them — what needs normalizing is deletion (whole chip per - // Backspace/Delete via native single-char semantics, which U+FFFC already - // gives us) and selection endpoints: Shift-extension snapping is native - // too (one char = one step). Mouse selection of a chip is handled in the - // backdrop click handler below. Undo/redo must NOT reach the browser: the - // machine owns the transaction log. - // selectionStart/End are number|null in lib.dom; the type-aware lint program narrows them. - /* oxlint-disable typescript/no-unnecessary-condition */ - const selectionOf = (el: HTMLTextAreaElement) => ({ - start: el.selectionStart ?? 0, - end: el.selectionEnd ?? el.selectionStart ?? 0, - }) - /* oxlint-enable typescript/no-unnecessary-condition */ - const onCopyOrCut = (e: React.ClipboardEvent, cut: boolean): void => { if (input === undefined || keyboard === undefined) return // absent machine: no draft can be copied or cut const el = e.currentTarget const { start, end } = selectionOf(el) if (start === end) return - const slice = draft.slice(start, end) - const touched = input.occurrences.filter(o => o.offset >= start && o.offset < end) + const touched = input.occurrences.filter(o => o.offset < end && o.offset + o.length > start) if (touched.length === 0 && !cut) return // plain copy of plain text: native path is fine e.preventDefault() - // Expand placeholders to their owner clipboard projections. + const copyStart = touched.reduce((value, o) => Math.min(value, o.offset), start) + const copyEnd = touched.reduce((value, o) => Math.max(value, o.offset + o.length), end) + // Expand structured ranges to their owner clipboard projections. let text = '' - let cursor = start + let cursor = copyStart for (const o of touched) { text += draft.slice(cursor, o.offset) + o.clipboardText - cursor = o.offset + 1 + cursor = o.offset + o.length } - text += draft.slice(cursor, end) + text += draft.slice(cursor, copyEnd) e.clipboardData.setData('text/plain', text) if (cut && !machineBusy && !locked) { - keyboard.setDraft(draft.slice(0, start) + draft.slice(end), { start, end, insertedLength: 0 }) - restoreCaret(el, start) + keyboard.setDraft( + draft.slice(0, copyStart) + draft.slice(copyEnd), + { start: copyStart, end: copyEnd, insertedLength: 0 }, + ) + restoreCaret(el, copyStart) } - void slice } const onPaste = (e: React.ClipboardEvent): void => { @@ -493,16 +510,15 @@ export function InputBar({ ? null : - // Mirror-layer decorations: a visible backdrop with transparent text. The - // claim token highlights through behind the textarea glyphs; each U+FFFC - // placeholder renders as a chip (the textarea's own glyph is invisible, the - // backdrop chip supplies the visual); the claim hint is ghost text. + // Mirror-layer decorations: a visible backdrop with transparent textarea + // text. Claim tokens and references retain the draft's own glyph metrics, + // so their decoration cannot drift from wrapping, selection, or the caret. const deco = input === undefined ? INERT_DECORATIONS : deriveDecorations(input, lexicon) const backdrop: ReactNode[] = [] { - // Segment boundaries: the token range end, every chip offset, and every - // text-ref range — merged in draft order (the sources never - // overlap: chips sit on placeholders, text-refs on plain tokens, the + // Segment boundaries: the token range end, every structured-reference + // offset, and every text-ref range — merged in draft order (the sources never + // overlap: structured references own their ranges, text-refs own plain tokens, the // claim token only leads). let cursor = 0 const pushPlain = (upTo: number): void => { @@ -519,10 +535,10 @@ export function InputBar({ } type Boundary = | { at: number; kind: 'chip'; chip: (typeof deco.chips)[number] } - | { at: number; kind: 'text-ref'; ref: (typeof deco.textRefs)[number] } + | { at: number; kind: 'text-ref'; ref: (typeof deco.textRefs)[number]; ordinal: number } const boundaries: Boundary[] = [ ...deco.chips.map(chip => ({ at: chip.offset, kind: 'chip' as const, chip })), - ...deco.textRefs.map(ref => ({ at: ref.start, kind: 'text-ref' as const, ref })), + ...deco.textRefs.map((ref, ordinal) => ({ at: ref.start, kind: 'text-ref' as const, ref, ordinal })), ].sort((a, b) => a.at - b.at) for (const b of boundaries) { if (b.at < cursor) continue // claim-token overlap: the leading mark wins @@ -530,27 +546,49 @@ export function InputBar({ if (b.kind === 'chip') { const chip = b.chip backdrop.push( - // The cell's ::before renders U+FFFC itself so its advance equals the - // textarea's placeholder exactly (same char, same font); the label is - // a clipped overlay that never affects layout. - {chip.label} + {chip.appearance === undefined + ? chip.text[0] + : ( + + {chip.text[0]} + + + )} + {chip.text.slice(1)} , ) - cursor = chip.offset + 1 // the placeholder char the chip stands for + cursor = chip.offset + chip.length } else { // Plain-range highlight: the glyphs stay the // textarea's (advance untouched); the mark paints the chip look. + // The key is the draft-order ordinal: a fresh scan derives these + // ranges every render, so none of them carries identity past its + // position, and a draft-offset key would unmount the mark and its + // icon for every character typed ahead of it. Structured references + // key by occurrenceId, the identity their occurrence table owns. + const text = draft.slice(b.ref.start, b.ref.end) backdrop.push( - - {draft.slice(b.ref.start, b.ref.end)} + + {b.ref.appearance === 'folder' + ? ( + <> + + {text[0]} + + + {text.slice(1)} + + ) + : text} , ) cursor = b.ref.end @@ -580,8 +618,8 @@ export function InputBar({ onDone={dismissToast} /> )} - {notice !== null && ( -
+ {notice?.level === 'info' && ( +
{notice.text}
)} @@ -618,7 +656,14 @@ export function InputBar({ which a compositor-driven gesture outruns and leaves the words trailing the caret. */}
-
{backdrop}
+
+ {backdrop} +