From 36db13dfb3e2f08e67cb0df01a8548cc79b01352 Mon Sep 17 00:00:00 2001 From: pku-xht Date: Fri, 21 Aug 2026 07:20:43 +0800 Subject: [PATCH] fix(subprocess): require verified range settlement --- ...6-07-06-timeout-deadline-library.i18n.yaml | 4 +-- .../2026-07-06-timeout-deadline-library.md | 4 +-- .../2026-07-06-timeout-deadline-library.zh.md | 4 +-- .../2026-07-15-lsp-capability-seam.i18n.yaml | 4 +-- .../2026-07-15-lsp-capability-seam.md | 2 +- .../2026-07-15-lsp-capability-seam.zh.md | 2 +- .../2026-07-26-subprocess-seam.i18n.yaml | 4 +-- .../2026-07-26-subprocess-seam.md | 4 +-- .../2026-07-26-subprocess-seam.zh.md | 4 +-- ...07-27-dispose-ladder-to-consumer.i18n.yaml | 4 +-- .../2026-07-27-dispose-ladder-to-consumer.md | 4 +-- ...026-07-27-dispose-ladder-to-consumer.zh.md | 4 +-- ...26-08-01-packaged-ripgrep-search.i18n.yaml | 4 +-- .../2026-08-01-packaged-ripgrep-search.md | 4 +-- .../2026-08-01-packaged-ripgrep-search.zh.md | 4 +-- ...ubagent-providers-in-shared-host.i18n.yaml | 4 +-- ...oduct-subagent-providers-in-shared-host.md | 4 +-- ...ct-subagent-providers-in-shared-host.zh.md | 4 +-- ...chronous-subprocess-exit-cleanup.i18n.yaml | 4 +-- ...-11-synchronous-subprocess-exit-cleanup.md | 8 +++--- ...-synchronous-subprocess-exit-cleanup.zh.md | 8 +++--- ...ipt-sdk-and-sdk-subagent-backend.i18n.yaml | 4 +-- ...typescript-sdk-and-sdk-subagent-backend.md | 2 +- ...escript-sdk-and-sdk-subagent-backend.zh.md | 2 +- ...code-and-codex-subagent-backends.i18n.yaml | 4 +-- ...claude-code-and-codex-subagent-backends.md | 22 +++++++-------- ...ude-code-and-codex-subagent-backends.zh.md | 22 +++++++-------- ...bagent-one-shot-background-tasks.i18n.yaml | 4 +-- ...duct-subagent-one-shot-background-tasks.md | 6 ++--- ...t-subagent-one-shot-background-tasks.zh.md | 6 ++--- ...agent-noninteractive-permissions.i18n.yaml | 4 +-- ...uct-subagent-noninteractive-permissions.md | 4 +-- ...-subagent-noninteractive-permissions.zh.md | 4 +-- ...8-product-subagent-failure-facts.i18n.yaml | 4 +-- ...26-08-18-product-subagent-failure-facts.md | 6 ++--- ...08-18-product-subagent-failure-facts.zh.md | 6 ++--- ...product-subagent-named-instances.i18n.yaml | 4 +-- ...-08-18-product-subagent-named-instances.md | 2 +- ...-18-product-subagent-named-instances.zh.md | 2 +- ...8-native-windows-pull-request-ci.i18n.yaml | 4 +-- ...26-08-08-native-windows-pull-request-ci.md | 2 +- ...08-08-native-windows-pull-request-ci.zh.md | 2 +- AGENTS.md | 2 +- docs/capability-seams.i18n.yaml | 4 +-- docs/capability-seams.md | 2 +- docs/capability-seams.zh.md | 2 +- docs/config-catalog.i18n.yaml | 4 +-- docs/config-catalog.md | 18 ++++++------- docs/config-catalog.zh.md | 18 ++++++------- docs/subsystems/subprocess.i18n.yaml | 4 +-- docs/subsystems/subprocess.md | 8 +++--- docs/subsystems/subprocess.zh.md | 8 +++--- packages/README.i18n.yaml | 4 +-- packages/README.md | 2 +- packages/README.zh.md | 2 +- .../extensions/tool-cordis/src/api-catalog.ts | 2 +- packages/fs/tool-fs-search/README.i18n.yaml | 4 +-- packages/fs/tool-fs-search/README.md | 6 ++--- packages/fs/tool-fs-search/README.zh.md | 6 ++--- packages/fs/tool-fs-search/src/glob.ts | 2 +- packages/fs/tool-fs-search/src/grep.ts | 2 +- packages/fs/tool-fs-search/src/index.ts | 4 +-- packages/fs/tool-fs-search/src/search-core.ts | 6 ++--- .../fs/tool-fs-search/tests/tools.spec.ts | 6 ++--- packages/lsp/lsp-stdio/README.i18n.yaml | 4 +-- packages/lsp/lsp-stdio/README.md | 4 +-- packages/lsp/lsp-stdio/README.zh.md | 4 +-- packages/lsp/lsp-stdio/src/connection.ts | 18 ++++++------- packages/lsp/lsp-stdio/src/index.ts | 4 +-- packages/lsp/lsp-stdio/src/instance.ts | 13 +++++---- packages/lsp/lsp-stdio/tests/instance.spec.ts | 2 +- packages/shell/bash-local/README.i18n.yaml | 4 +-- packages/shell/bash-local/README.md | 8 +++--- packages/shell/bash-local/README.zh.md | 8 +++--- packages/shell/bash-local/src/index.ts | 10 +++---- packages/shell/pwsh-local/README.i18n.yaml | 4 +-- packages/shell/pwsh-local/README.md | 6 ++--- packages/shell/pwsh-local/README.zh.md | 6 ++--- packages/shell/pwsh-local/src/index.ts | 6 ++--- .../shell/pwsh-local/tests/executor.spec.ts | 4 +-- .../subagent/subagent-acp/README.i18n.yaml | 4 +-- packages/subagent/subagent-acp/README.md | 6 ++--- packages/subagent/subagent-acp/README.zh.md | 6 ++--- packages/subagent/subagent-acp/src/index.ts | 4 +-- packages/subagent/subagent-acp/src/run.ts | 24 ++++++++--------- .../subagent-claude-code/README.i18n.yaml | 4 +-- .../subagent/subagent-claude-code/README.md | 6 ++--- .../subagent-claude-code/README.zh.md | 6 ++--- .../subagent-claude-code/src/index.ts | 2 +- .../subagent-claude-code/src/invariant.ts | 2 +- .../subagent-claude-code/src/process.ts | 10 +++---- .../subagent/subagent-claude-code/src/run.ts | 12 ++++----- .../subagent/subagent-codex/README.i18n.yaml | 4 +-- packages/subagent/subagent-codex/README.md | 6 ++--- packages/subagent/subagent-codex/README.zh.md | 6 ++--- packages/subagent/subagent-codex/src/index.ts | 2 +- .../subagent/subagent-codex/src/invariant.ts | 2 +- packages/subagent/subagent-codex/src/run.ts | 12 ++++----- .../tests/subagent-codex.spec.ts | 2 +- .../subagent/subagent/src/out-of-process.ts | 2 +- packages/subprocess/README.i18n.yaml | 4 +-- packages/subprocess/README.md | 4 +-- packages/subprocess/README.zh.md | 4 +-- .../subprocess/subprocess-local/src/index.ts | 7 +++-- .../subprocess/subprocess-local/src/spawn.ts | 10 +++---- .../subprocess-local/src/windows-job.ts | 24 +++++++++++++---- .../tests/fixtures/fake-job-runner.ts | 5 ++-- .../tests/native-windows.spec.ts | 2 ++ .../tests/windows-job.spec.ts | 27 +++++++++++++++++++ .../subprocess/subprocess/README.i18n.yaml | 4 +-- packages/subprocess/subprocess/README.md | 2 +- packages/subprocess/subprocess/README.zh.md | 2 +- packages/subprocess/subprocess/src/index.ts | 6 ++--- packages/subprocess/subprocess/src/types.ts | 6 ++--- scripts/gen-doc-graphs.ts | 2 +- 115 files changed, 348 insertions(+), 308 deletions(-) diff --git a/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.i18n.yaml index 580e74f217..0e523f1d20 100644 --- a/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md -2026-07-06-timeout-deadline-library.md: 38f048d16ecba0e5278ae34b0c88b7889dcfa47a -2026-07-06-timeout-deadline-library.zh.md: c8d189c2a7588ee57b0f7fe02137b78c9ad7ff9d +2026-07-06-timeout-deadline-library.md: 0c29c1d82c7ebced3d6b5ce6c6ae0ecafff8af43 +2026-07-06-timeout-deadline-library.zh.md: 4c56061f7430ec6d220b2110939ad29c0160bf21 diff --git a/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md index 38f048d16e..0c29c1d82c 100644 --- a/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md +++ b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md @@ -97,7 +97,7 @@ The signal only *notifies*; termination is always the listener's job, and the li ## Consequences -- `runBash`'s outcome no longer independently latches `timedOut` and `aborted`; a timeout and a user abort racing before process close now report a single first-abort cause instead of both being true. The uniform SIGTERM→grace→SIGKILL kill is unchanged, and the Service Definition type `ShellRunResult` keeps both booleans (now mutually exclusive), so `dsh-tool-bash`'s result rendering is untouched. +- `runBash`'s outcome no longer independently latches `timedOut` and `aborted`; a timeout and a user abort racing before process close now report a single first-abort cause instead of both being true. The subprocess provider still owns termination of its managed range, and the Service Definition type `ShellRunResult` keeps both booleans (now mutually exclusive), so `dsh-tool-bash`'s result rendering is untouched. - `SpawnSpec.timeoutMs` and `SpawnOutcome.timedOut`/`aborted` were removed rather than kept as always-zero/always-false vestiges: with `runBash` owning no timer and the executor owning classification, they were read nowhere. An always-0 field read by nothing is dead weight under the per-file coverage gate. - web_fetch shed its bespoke controller/timer/listener/reason-recovery; the classifier now keys off the deadline signal (`timeoutOf` + `aborted`) rather than the thrown error's shape, which is robust across both the request-phase reject-with-reason and the read-phase bare-`AbortError`. - `AbortSignal.any` and `using`/`Symbol.dispose` enter the repo for the first time here (Node ≥ 24 baseline, already met). @@ -113,4 +113,4 @@ Out of scope, named to mark the boundary: `web_search` can gain an optional mode **A `withTimeout(promise, ms)` wrapper instead of a signal factory.** Rejected because racing a promise against a timer resolves the *tool-call* promise on deadline without stopping the underlying work — the child process or fetch socket leaks on. Handing out a signal and requiring the capability to listen is what forces a real termination path to exist. This mirrors the "dispose must reach quiescence, not just request it" defensive rule. -**Keep separate bash timeout and cancellation triggers.** Rejected because one deadline signal removes the bespoke timer and standardizes classification. Racing causes report whichever abort arrived first, while the existing SIGTERM-to-SIGKILL termination path remains unchanged. +**Keep separate bash timeout and cancellation triggers.** Rejected because one deadline signal removes the bespoke timer and standardizes classification. Racing causes report whichever abort arrived first, while the existing provider-owned managed-range termination path remains unchanged. diff --git a/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.zh.md b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.zh.md index c8d189c2a7..4c56061f74 100644 --- a/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.zh.md @@ -97,7 +97,7 @@ export function timeoutOf(x: AbortSignal | { reason?: unknown }, code?: string): ## 后果 -- `runBash` 的结果不再独立锁存 `timedOut` 和 `aborted`；超时与用户中止在进程关闭前竞争时，现在报告单一的首个 abort 原因，而非两者同时为 true。统一的 SIGTERM→宽限期→SIGKILL 终止路径不变，Service Definition 类型 `ShellRunResult` 保留两个布尔值（现在互斥），因此 `dsh-tool-bash` 的结果渲染不受影响。 +- `runBash` 的结果不再独立锁存 `timedOut` 和 `aborted`；超时与用户中止在进程关闭前竞争时，现在报告单一的首个 abort 原因，而非两者同时为 true。subprocess provider 继续拥有其 managed range 的终止过程，Service Definition 类型 `ShellRunResult` 保留两个布尔值（现在互斥），因此 `dsh-tool-bash` 的结果渲染不受影响。 - `SpawnSpec.timeoutMs` 和 `SpawnOutcome.timedOut`/`aborted` 被移除，而非作为始终为零/始终为 false 的残余保留：由于 `runBash` 不再拥有定时器且执行器负责分类，这些字段无处被读取。一个始终为 0 且无处读取的字段在逐文件覆盖率门禁下属于死代码。 - web_fetch 去除了其定制的 controller/timer/listener/reason-recovery；分类器现在基于 deadline 信号（`timeoutOf` + `aborted`）而非抛出错误的形状来判断，这在请求阶段的 reject-with-reason 和读取阶段的裸 `AbortError` 两种情况下都是健壮的。 - `AbortSignal.any` 和 `using`/`Symbol.dispose` 在此首次进入本仓库（Node ≥ 24 基线，已满足）。 @@ -113,4 +113,4 @@ export function timeoutOf(x: AbortSignal | { reason?: unknown }, code?: string): **用 `withTimeout(promise, ms)` 包装器代替信号工厂。** 否决，因为让 promise 与定时器竞争只是在截止时间到达时 resolve *工具调用*的 promise，而不会停止底层工作——子进程或 fetch socket 会泄漏。分发信号并要求能力监听，才能强制一条真实的终止路径存在。这与「dispose 必须达到完全停稳，而非仅仅请求它」的防御性规则一致。 -**保留 bash 独立的超时和取消触发器。** 否决，因为一个 deadline 信号移除了定制定时器并标准化了分类。发生竞争时，报告先到达的那个 abort 作为原因，而既有的 SIGTERM→SIGKILL 终止路径保持不变。 +**保留 bash 独立的超时和取消触发器。** 否决，因为一个 deadline 信号移除了定制定时器并标准化了分类。发生竞争时，报告先到达的那个 abort 作为原因，而既有的 provider-owned managed-range 终止路径保持不变。 diff --git a/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.i18n.yaml index 277e0b097d..8827fccdd1 100644 --- a/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.md -2026-07-15-lsp-capability-seam.md: 90f9daf4b890bd53621916e492d4d82baaa3e8cc -2026-07-15-lsp-capability-seam.zh.md: bdb5e812e94a4aec4402fe83ca9c818bfa00f9f9 +2026-07-15-lsp-capability-seam.md: b89b9afaa90aac8abf1f78c797f3219b6ef40248 +2026-07-15-lsp-capability-seam.zh.md: 40785612c3bfc219b0946ac09d6d0c36873b0c28 diff --git a/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.md b/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.md index 90f9daf4b8..b89b9afaa9 100644 --- a/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.md +++ b/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.md @@ -108,7 +108,7 @@ The transport-neutral presenter uses `{ card: 'generic', kind: 'search', title, The seam and provider add no startup or request deadline. Non-tool callers therefore receive no hidden timeout and must supply an `AbortSignal`, using `deadline()` when they need a budget. -Provider disposal occurs outside tool execution, so `dsh-lsp-stdio` keeps `shutdownTimeoutMs` (default `5_000`) for `shutdown`/`exit` and `killGraceMs` (default `2_000`) for both request-cancel grace and SIGTERM-to-SIGKILL escalation; the same bounds govern failed-instance cleanup. Timer values above Node's `2_147_483_647` ms scheduling range fail at load. The provider uses `deadline()` and `timeoutOf()` but owns request cancellation, process signals, and awaiting close because timeout notification does not terminate work. +Provider disposal occurs outside tool execution, so `dsh-lsp-stdio` keeps `shutdownTimeoutMs` (default `5_000`) for `shutdown`/`exit` and `killGraceMs` (default `2_000`) for request-cancel grace plus subprocess termination and output draining; the same bounds govern failed-instance cleanup. Timer values above Node's `2_147_483_647` ms scheduling range fail at load. The LSP provider uses `deadline()` and `timeoutOf()` and owns request cancellation, while the subprocess provider owns range termination and observation; timeout notification alone does not terminate work. ## Workspace, filesystem, and document synchronization diff --git a/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.zh.md b/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.zh.md index bdb5e812e9..40785612c3 100644 --- a/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.zh.md @@ -108,7 +108,7 @@ interface LspToolInput { seam 和提供方不增加启动或请求截止时间。非工具调用方不会获得隐藏超时，必须自行提供 `AbortSignal`，并在需要预算时使用 `deadline()`。 -提供方 dispose 发生在工具执行之外，因此 `dsh-lsp-stdio` 保留 `shutdownTimeoutMs`（默认 `5_000`）限制 `shutdown`/`exit`，以及 `killGraceMs`（默认 `2_000`），同时用于限制请求取消宽限期和从 SIGTERM 升级到 SIGKILL 的宽限期；失败实例的清理也使用相同边界。定时器值超过 Node `2_147_483_647` ms 的调度范围时，插件加载失败。提供方使用 `deadline()` 和 `timeoutOf()`，但仍负责请求取消、进程信号和等待关闭，因为超时通知不会终止工作。 +提供方 dispose 发生在工具执行之外，因此 `dsh-lsp-stdio` 保留 `shutdownTimeoutMs`（默认 `5_000`）限制 `shutdown`/`exit`，以及 `killGraceMs`（默认 `2_000`），同时用于限制请求取消宽限期，并提供给 subprocess 终止与输出排空；失败实例的清理也使用相同边界。定时器值超过 Node `2_147_483_647` ms 的调度范围时，插件加载失败。LSP provider 使用 `deadline()` 和 `timeoutOf()` 并拥有请求取消，subprocess provider 则拥有范围终止与观察；超时通知本身不会终止工作。 ## 工作区、文件系统与文档同步 diff --git a/.agents/notes/implemented/architecture/2026-07-26-subprocess-seam.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-26-subprocess-seam.i18n.yaml index 166541f1f2..a2d9f7d146 100644 --- a/.agents/notes/implemented/architecture/2026-07-26-subprocess-seam.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-26-subprocess-seam.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-26-subprocess-seam.md -2026-07-26-subprocess-seam.md: 92d36bf6d522ab939ef6c0de1063e0accea2946f -2026-07-26-subprocess-seam.zh.md: d271ad95ce84bb34256d3bf2ee6d793e21623d2b +2026-07-26-subprocess-seam.md: 973d3b2f9c88033ac61016c42ed3fe3320f4e0f6 +2026-07-26-subprocess-seam.zh.md: e535369b50f8f3e3b74c96de4e0f4341c185f1a6 diff --git a/.agents/notes/implemented/architecture/2026-07-26-subprocess-seam.md b/.agents/notes/implemented/architecture/2026-07-26-subprocess-seam.md index 92d36bf6d5..973d3b2f9c 100644 --- a/.agents/notes/implemented/architecture/2026-07-26-subprocess-seam.md +++ b/.agents/notes/implemented/architecture/2026-07-26-subprocess-seam.md @@ -39,6 +39,6 @@ Observed stream and lifecycle needs then moved the eligible process consumers on ## Consequences -Bought: "run and manage a process" is a swappable capability used by Bash, LSP, PTY, and ACP consumers; a containerized or remote process backend slots in without changing their domain semantics; tree signalling, escalation, bounded collection, terminal mechanics, and credential scrubbing each have one implementation; and background processes survive executor reloads, matching the job registry's lifetime model. Process and terminal plumbing is tested through `dsh-subprocess-local`; consumer suites pin only their owned behavior against the real service. +Bought: "run and manage a process" is a swappable capability used by Bash, LSP, PTY, and ACP consumers; a containerized or remote process backend slots in without changing their domain semantics; managed-range signalling, termination scheduling, bounded collection, terminal mechanics, and credential scrubbing each have one owner; and background processes survive executor reloads, matching the job registry's lifetime model. Process and terminal plumbing is tested through `dsh-subprocess-local`; consumer suites pin only their owned behavior against the real service. -Cost: one more package pair and one more composition row wherever a consumer loads; a missing subprocess provider leaves the consumer pending by standard service-injection behavior. Every backend implements executable lookup, three stdio modes, tree lifecycle, and one terminal primitive. The moved-vocabulary re-exports keep `dsh-shell` imports working but mean two packages name the same types; the subprocess seam is the owner. The spawn-failure note became single-delivery through Bash's consuming read cursor instead of repeatable stderr-buffer content. +Cost: one more package pair and one more composition row wherever a consumer loads; a missing subprocess provider leaves the consumer pending by standard service-injection behavior. Every backend implements executable lookup, three stdio modes, managed-range lifecycle, and one terminal primitive. The moved-vocabulary re-exports keep `dsh-shell` imports working but mean two packages name the same types; the subprocess seam is the owner. The spawn-failure note became single-delivery through Bash's consuming read cursor instead of repeatable stderr-buffer content. diff --git a/.agents/notes/implemented/architecture/2026-07-26-subprocess-seam.zh.md b/.agents/notes/implemented/architecture/2026-07-26-subprocess-seam.zh.md index d271ad95ce..e535369b50 100644 --- a/.agents/notes/implemented/architecture/2026-07-26-subprocess-seam.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-26-subprocess-seam.zh.md @@ -39,6 +39,6 @@ Status: implemented ## 后果 -换来的是：「运行并管理一个进程」成为 Bash、LSP、PTY 与 ACP 消费方共用的可替换能力；容器化或远程进程后端可以直接接入，而无需改变各领域语义；进程树信号、升级终止、有界收集、终端机制与凭据清除各自只剩一份实现；后台进程也能在执行器重载后存活，与任务注册表的存续期模型一致。进程与终端管道通过 `dsh-subprocess-local` 测试；消费方测试套件只需针对真实服务固定各自拥有的行为。 +换来的是：「运行并管理一个进程」成为 Bash、LSP、PTY 与 ACP 消费方共用的可替换能力；容器化或远程进程后端可以直接接入，而无需改变各领域语义；managed-range 信号、终止调度、有界收集、终端机制与凭据清除各自只有一个 owner；后台进程也能在执行器重载后存活，与任务注册表的存续期模型一致。进程与终端管道通过 `dsh-subprocess-local` 测试；消费方测试套件只需针对真实服务固定各自拥有的行为。 -代价是：多出一对包，而且凡加载消费方之处都多一行组合配置；缺少 subprocess 提供方时，消费方会按标准服务注入行为保持挂起。每个后端都要实现可执行文件查找、三种 stdio 模式、进程树生命周期和一个终端原语。迁移词汇的重导出让 `dsh-shell` 的导入继续可用，但也意味着两个包命名同一批类型；进程 seam 是所有者。spawn 失败提示经由 Bash 的消费式读取游标变为单次交付，不再是可重复读取的 stderr 缓冲内容。 +代价是：多出一对包，而且凡加载消费方之处都多一行组合配置；缺少 subprocess 提供方时，消费方会按标准服务注入行为保持挂起。每个后端都要实现可执行文件查找、三种 stdio 模式、managed-range 生命周期和一个终端原语。迁移词汇的重导出让 `dsh-shell` 的导入继续可用，但也意味着两个包命名同一批类型；进程 seam 是所有者。spawn 失败提示经由 Bash 的消费式读取游标变为单次交付，不再是可重复读取的 stderr 缓冲内容。 diff --git a/.agents/notes/implemented/architecture/2026-07-27-dispose-ladder-to-consumer.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-27-dispose-ladder-to-consumer.i18n.yaml index a81c4706e7..a96f2137a3 100644 --- a/.agents/notes/implemented/architecture/2026-07-27-dispose-ladder-to-consumer.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-27-dispose-ladder-to-consumer.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/2026-07-27-dispose-ladder-to-consumer.md -2026-07-27-dispose-ladder-to-consumer.md: 58d835864d2f6544152fdf09cf6e93380793a2ae -2026-07-27-dispose-ladder-to-consumer.zh.md: dc7413e85fa6e52de14f51fd175c7b37b43029a4 +2026-07-27-dispose-ladder-to-consumer.md: bcd6aa98f45fabda702e41738bbec929f145f739 +2026-07-27-dispose-ladder-to-consumer.zh.md: 4e0dc565e3c19f3780a04d00991490f7a56d5c0f diff --git a/.agents/notes/implemented/architecture/2026-07-27-dispose-ladder-to-consumer.md b/.agents/notes/implemented/architecture/2026-07-27-dispose-ladder-to-consumer.md index 58d835864d..bcd6aa98f4 100644 --- a/.agents/notes/implemented/architecture/2026-07-27-dispose-ladder-to-consumer.md +++ b/.agents/notes/implemented/architecture/2026-07-27-dispose-ladder-to-consumer.md @@ -10,7 +10,7 @@ English | [中文](2026-07-27-dispose-ladder-to-consumer.zh.md) ## Decision -The ladder moves to its one consumer. `dsh-subagent-acp` owns `disposeAcpChild(child, eofGraceMs)`, built entirely on the seam's public verbs: close `stdin`, bound a `waitForExit` on `eofGraceMs`, then call `terminate()`, whose SIGTERM→spec-grace→SIGKILL escalation already owns the signal timer, and await an unbounded `waitForExit()` for the subprocess owner's whole-tree exit proof. The seam keeps `kill`/`terminate`/`waitForExit` — mechanisms, not policy — and `waitForExit(signal?)` is exactly the quiescence probe a consumer ladder needs to hold the cooperative tier on real tree exit without deriving another timer from the termination grace. The seam's handle loses one method and one exported interface. +The ladder moves to its one consumer. `dsh-subagent-acp` owns `disposeAcpChild(child, eofGraceMs)`, built entirely on the seam's public verbs: close `stdin`, bound a `waitForExit` on `eofGraceMs`, then call the provider-owned `terminate()` procedure and await an unbounded `waitForExit()` for the subprocess owner's managed-range exit proof. The seam keeps `kill`/`terminate`/`waitForExit` — mechanisms, not policy — and `waitForExit(signal?)` is exactly the quiescence probe a consumer ladder needs to hold the cooperative tier on real range exit without deriving another timer from the termination grace. The seam's handle loses one method and one exported interface. ## Alternatives considered @@ -20,4 +20,4 @@ The ladder moves to its one consumer. `dsh-subagent-acp` owns `disposeAcpChild(c ## Consequences -Bought: the Service Definition is one method and one type smaller; Service Providers owe four verbs and no teardown policy; the cooperative EOF window lives beside the ACP config field that tunes it, while the subprocess owner alone owns the termination window and final join. Cost: a future backend wanting EOF-first teardown writes ~20 lines against the verbs (or lifts the ACP helper); the ladder's tier tests live in the ACP suite, and the Service Definition suite pins the verbs the ladder composes (bounded `waitForExit` false before escalation and an unbounded whole-tree join after it) instead of the composed policy. +Bought: the Service Definition is one method and one type smaller; Service Providers owe four verbs and no teardown policy; the cooperative EOF window lives beside the ACP config field that tunes it, while the subprocess owner alone owns termination and the final join. Cost: a future backend wanting EOF-first teardown writes ~20 lines against the verbs (or lifts the ACP helper); the ladder's tier tests live in the ACP suite, and the Service Definition suite pins the verbs the ladder composes (bounded `waitForExit` false before termination and an unbounded managed-range join after it) instead of the composed policy. diff --git a/.agents/notes/implemented/architecture/2026-07-27-dispose-ladder-to-consumer.zh.md b/.agents/notes/implemented/architecture/2026-07-27-dispose-ladder-to-consumer.zh.md index dc7413e85f..4e0dc565e3 100644 --- a/.agents/notes/implemented/architecture/2026-07-27-dispose-ladder-to-consumer.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-27-dispose-ladder-to-consumer.zh.md @@ -10,7 +10,7 @@ Status: implemented ## 决策 -阶梯移入其唯一消费方。`dsh-subagent-acp` 拥有 `disposeAcpChild(child, eofGraceMs)`，完全构建在 seam 的公开动词之上：关闭 `stdin`，以 `eofGraceMs` 约束一次 `waitForExit`，随后调用 `terminate()`（其 SIGTERM→spec 宽限期→SIGKILL 升级已拥有信号定时器），再无界等待 `waitForExit()`，由子进程责任方证明整棵进程树已经退出。seam 保留 `kill`／`terminate`／`waitForExit`——机制而非策略——而 `waitForExit(signal?)` 恰是消费方阶梯在协作层确认进程树真正退出所需的完全停稳探针，无需从终止宽限期再派生一个定时器。seam 的句柄少了一个方法和一个导出接口。 +阶梯移入其唯一消费方。`dsh-subagent-acp` 拥有 `disposeAcpChild(child, eofGraceMs)`，完全构建在 seam 的公开动词之上：关闭 `stdin`，以 `eofGraceMs` 约束一次 `waitForExit`，随后调用 provider-owned `terminate()` 过程，再无界等待 `waitForExit()`，由子进程责任方证明 managed range 已经退出。seam 保留 `kill`／`terminate`／`waitForExit`——机制而非策略——而 `waitForExit(signal?)` 恰是消费方阶梯在协作层确认范围真正退出所需的完全停稳探针，无需从终止宽限期再派生一个定时器。seam 的句柄少了一个方法和一个导出接口。 ## 曾考虑的替代方案 @@ -20,4 +20,4 @@ Status: implemented ## 后果 -买到的：Service Definition 少了一个方法和一个类型；Service Provider 只欠四个动词，不欠拆卸策略；协作式 EOF 时间窗与调节它的 ACP 配置字段住在一起，而终止时间窗与最终的整树退出等待仅由子进程责任方拥有。代价：未来想要 EOF 打头拆卸的后端需针对这些动词写约 20 行（或直接搬 ACP 的辅助函数）；阶梯的层级测试位于 ACP 套件，Service Definition 套件转而钉住阶梯所组合的动词（升级前有界 `waitForExit` 返回假，升级后无界等待整棵进程树退出），而非组合后的策略。 +买到的：Service Definition 少了一个方法和一个类型；Service Provider 只欠四个动词，不欠拆卸策略；协作式 EOF 时间窗与调节它的 ACP 配置字段住在一起，而终止与最终的 managed-range 等待仅由子进程责任方拥有。代价：未来想要 EOF 打头拆卸的后端需针对这些动词写约 20 行（或直接搬 ACP 的辅助函数）；阶梯的层级测试位于 ACP 套件，Service Definition 套件转而钉住阶梯所组合的动词（终止前有界 `waitForExit` 返回假，终止后无界等待 managed range 退出），而非组合后的策略。 diff --git a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.i18n.yaml index 870bf8ec05..b0f05e0482 100644 --- a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.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/2026-08-01-packaged-ripgrep-search.md -2026-08-01-packaged-ripgrep-search.md: c401bc1e30df0c3443ad58b37f64523b1c10cb31 -2026-08-01-packaged-ripgrep-search.zh.md: 6a195e59f77aa73b9d0918461cef45360e617098 +2026-08-01-packaged-ripgrep-search.md: bc73a6ebc6edfcbc2f4e4a932806217562d3e73d +2026-08-01-packaged-ripgrep-search.zh.md: 43e907bdc7114daa25ac56338c1be2999ed9c65a diff --git a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.md b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.md index c401bc1e30..bc73a6ebc6 100644 --- a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.md +++ b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.md @@ -12,9 +12,9 @@ The `glob`/`grep` tools ran through the bash executor seam, which made a system ## Decision -`@deepseek-ai/dsh-tool-fs-search` now runs the PACKAGED ripgrep binary (`@vscode/ripgrep`, an npm dependency whose optional platform packages ship the binary) through the `ctx.subprocess` seam: `runRipgrep()` spawns `rgPath` with a plain argv vector prefixed by `--no-config`, collect-mode stdout/stderr, `graceMs`, and `exec.signal` forwarded. `rgPath` resolves lazily at the first call (memoized per process): `@vscode/ripgrep` resolves its platform package at module evaluation, so a static import would turn a missing or corrupt platform package (`--omit=optional`, partial install) into a Loader-composition failure — the load-time failure mode this change exists to remove. There is no shell layer, so the shell-quoting boundary is gone from execution; the `singleQuote` helper and its shell-spawning tests are deleted with it. The raw streams request the seam's diagnostic-tail collect shape (no spill files — the tool never reads a raw spill path; a lossy stdout read fails as `SEARCH_RAW_OUTPUT_OVERFLOW`). The terminate grace and the stderr tail budget are validated `Config` fields (`graceMs` default 3000, `stderrMaxBytes` default 64 KiB), no longer inherited from bash-local's config. Registration is unconditional — the load-time `command -v rg` probe and the conditional registration decision are deleted, and with them the "rg not found" warning. The package injects `tools`, `systemPrompt`, and `subprocess`. +`@deepseek-ai/dsh-tool-fs-search` now runs the PACKAGED ripgrep binary (`@vscode/ripgrep`, an npm dependency whose optional platform packages ship the binary) through the `ctx.subprocess` seam: `runRipgrep()` spawns `rgPath` with a plain argv vector prefixed by `--no-config`, collect-mode stdout/stderr, `graceMs`, and `exec.signal` forwarded. `rgPath` resolves lazily at the first call (memoized per process): `@vscode/ripgrep` resolves its platform package at module evaluation, so a static import would turn a missing or corrupt platform package (`--omit=optional`, partial install) into a Loader-composition failure — the load-time failure mode this change exists to remove. There is no shell layer, so the shell-quoting boundary is gone from execution; the `singleQuote` helper and its shell-spawning tests are deleted with it. The raw streams request the seam's diagnostic-tail collect shape (no spill files — the tool never reads a raw spill path; a lossy stdout read fails as `SEARCH_RAW_OUTPUT_OVERFLOW`). The termination/output-drain grace and the stderr tail budget are validated `Config` fields (`graceMs` default 3000, `stderrMaxBytes` default 64 KiB), no longer inherited from bash-local's config. Registration is unconditional — the load-time `command -v rg` probe and the conditional registration decision are deleted, and with them the "rg not found" warning. The package injects `tools`, `systemPrompt`, and `subprocess`. -Exit semantics stay tool-owned: exit 0 is success with results, exit 1 is a successful empty search, anything else classifies into the existing `SEARCH_*` vocabulary (invalid pattern, launch failure, signal kill, raw-output overflow). Timeout is the cooperative tool-call budget attached to the tool definitions: `@deepseek-ai/dsh-tool-call-timeout-policy` aborts `exec.signal`, the subprocess seam's terminate escalation provides the hard kill, and the tool reports `SEARCH_ABORTED`. The working directory is the session header cwd when present, else `process.cwd()` — there is no executor config to default through anymore, so the tool owns the fallback. +Exit semantics stay tool-owned: exit 0 is success with results, exit 1 is a successful empty search, anything else classifies into the existing `SEARCH_*` vocabulary (invalid pattern, launch failure, signal kill, raw-output overflow). Timeout is the cooperative tool-call budget attached to the tool definitions: `@deepseek-ai/dsh-tool-call-timeout-policy` aborts `exec.signal`, the subprocess provider starts managed-range termination, and the tool reports `SEARCH_ABORTED`. The working directory is the session header cwd when present, else `process.cwd()` — there is no executor config to default through anymore, so the tool owns the fallback. The `fs-glob-sampling` ACP snapshot scenario now executes the real packaged binary against a prepared workspace whose fixed mtimes pin the `--sort=modified` order, replacing the PATH-injected `rg` stand-in (POSIX-only, because the displayed paths carry `/` separators the session-log comparison cannot normalize). diff --git a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.zh.md b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.zh.md index 6a195e59f7..43e907bdc7 100644 --- a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.zh.md +++ b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.zh.md @@ -12,9 +12,9 @@ Status: implemented ## 决策 -`@deepseek-ai/dsh-tool-fs-search` 现在运行 PACKAGED（打包的）ripgrep 二进制（`@vscode/ripgrep`，一个 npm 依赖，其可选平台包随附二进制），经由 `ctx.subprocess` seam：`runRipgrep()` 以纯 argv 向量 spawn `rgPath`，向量前缀 `--no-config`，配以 collect 模式 stdout/stderr、`graceMs` 与转发的 `exec.signal`。`rgPath` 在首次调用时懒解析（进程内 memoize）：`@vscode/ripgrep` 在模块求值阶段解析其平台包，静态导入会把平台包缺失/损坏（`--omit=optional`、安装不全）变成 Loader 组合加载失败——这正是本次改动要消除的加载期失败模式。不再有 shell 层，执行路径上的 shell 引号边界随之消失；`singleQuote` 工具与其 shell spawn 测试一并删除。原始流使用 seam 的诊断尾部 collect 形态（无 spill 文件——工具从不读取原始 spill 路径；lossy stdout 读取以 `SEARCH_RAW_OUTPUT_OVERFLOW` 失败）。终止宽限与 stderr 尾部预算成为经校验的 `Config` 字段（`graceMs` 默认 3000，`stderrMaxBytes` 默认 64 KiB），不再继承自 bash-local 的配置。注册变为无条件——加载期 `command -v rg` 探针与条件注册决策被删除，连同那条 "rg not found" 警告。本包注入 `tools`、`systemPrompt` 与 `subprocess`。 +`@deepseek-ai/dsh-tool-fs-search` 现在运行 PACKAGED（打包的）ripgrep 二进制（`@vscode/ripgrep`，一个 npm 依赖，其可选平台包随附二进制），经由 `ctx.subprocess` seam：`runRipgrep()` 以纯 argv 向量 spawn `rgPath`，向量前缀 `--no-config`，配以 collect 模式 stdout/stderr、`graceMs` 与转发的 `exec.signal`。`rgPath` 在首次调用时懒解析（进程内 memoize）：`@vscode/ripgrep` 在模块求值阶段解析其平台包，静态导入会把平台包缺失/损坏（`--omit=optional`、安装不全）变成 Loader 组合加载失败——这正是本次改动要消除的加载期失败模式。不再有 shell 层，执行路径上的 shell 引号边界随之消失；`singleQuote` 工具与其 shell spawn 测试一并删除。原始流使用 seam 的诊断尾部 collect 形态（无 spill 文件——工具从不读取原始 spill 路径；lossy stdout 读取以 `SEARCH_RAW_OUTPUT_OVERFLOW` 失败）。终止／输出排空宽限与 stderr 尾部预算成为经校验的 `Config` 字段（`graceMs` 默认 3000，`stderrMaxBytes` 默认 64 KiB），不再继承自 bash-local 的配置。注册变为无条件——加载期 `command -v rg` 探针与条件注册决策被删除，连同那条 "rg not found" 警告。本包注入 `tools`、`systemPrompt` 与 `subprocess`。 -退出语义仍由工具拥有：退出码 0 为有结果的成功，1 为成功的空搜索，其余归入既有 `SEARCH_*` 词汇（无效模式、启动失败、信号杀死、原始输出溢出）。超时是挂在工具定义上的协作式工具调用预算：`@deepseek-ai/dsh-tool-call-timeout-policy` 中止 `exec.signal`，subprocess seam 的终止升级提供硬终止，工具报告 `SEARCH_ABORTED`。工作目录为会话 header cwd（存在时），否则为 `process.cwd()`——不再有执行器配置可供默认化，因此回退由工具自己拥有。 +退出语义仍由工具拥有：退出码 0 为有结果的成功，1 为成功的空搜索，其余归入既有 `SEARCH_*` 词汇（无效模式、启动失败、信号杀死、原始输出溢出）。超时是挂在工具定义上的协作式工具调用预算：`@deepseek-ai/dsh-tool-call-timeout-policy` 中止 `exec.signal`，subprocess provider 启动 managed-range 终止，工具报告 `SEARCH_ABORTED`。工作目录为会话 header cwd（存在时），否则为 `process.cwd()`——不再有执行器配置可供默认化，因此回退由工具自己拥有。 `fs-glob-sampling` ACP（Agent Client Protocol）快照场景改为执行真实的打包二进制，作用于一个用固定 mtime 钉住 `--sort=modified` 顺序的预制工作区，取代 PATH 注入的 `rg` 替身（仅 POSIX：展示路径携带 `/` 分隔符，会话日志比较无法归一化）。 diff --git a/.agents/notes/implemented/architecture/2026-08-10-product-subagent-providers-in-shared-host.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-10-product-subagent-providers-in-shared-host.i18n.yaml index 66fa66d233..2f4dd87029 100644 --- a/.agents/notes/implemented/architecture/2026-08-10-product-subagent-providers-in-shared-host.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-10-product-subagent-providers-in-shared-host.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-product-subagent-providers-in-shared-host.md -2026-08-10-product-subagent-providers-in-shared-host.md: 196e28c1263c4b6d71eaeb59b9ba8457b36f3ff4 -2026-08-10-product-subagent-providers-in-shared-host.zh.md: 1451890e1b250a2095e3366c59d6ce0873b55fe9 +2026-08-10-product-subagent-providers-in-shared-host.md: 7ea5a17fcdab23621b0017ede56e8bfb11507f35 +2026-08-10-product-subagent-providers-in-shared-host.zh.md: 4623dde43d0e47cc0bc9bf5c6714c8572d1a5f01 diff --git a/.agents/notes/implemented/architecture/2026-08-10-product-subagent-providers-in-shared-host.md b/.agents/notes/implemented/architecture/2026-08-10-product-subagent-providers-in-shared-host.md index 196e28c126..7ea5a17fcd 100644 --- a/.agents/notes/implemented/architecture/2026-08-10-product-subagent-providers-in-shared-host.md +++ b/.agents/notes/implemented/architecture/2026-08-10-product-subagent-providers-in-shared-host.md @@ -14,13 +14,13 @@ The placement decision must preserve two independent facts. Loading a provider m Product providers remain process-scoped host-plane registrations. The [production-install exclusion decision](../simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.md) supersedes only this note's former base-bundle installation choice: production `dsh-base` neither depends on nor mounts them. A Profile that opts in installs the selected provider Bundle; its patch mounts the default instance, and the Profile may mount additional named instances on the host plane. The [named-instance decision](../feature/2026-08-18-product-subagent-named-instances.md) owns each row's registry identity: both products accept multiple unique `providerName` values while preserving `codex` and `claude-code` as their defaults. Loading either plugin only registers a dormant backend; the corresponding Codex or Claude process starts on the first actual delegation call. Agent Presets independently contribute ordinary `dsh-tool-subagent` rows whose `provider` and `toolName` values expose exactly the configured instances needed by one agent without changing the Host registry. -Each provider package owns its directly installable Bundle patch and private product runtime. This note continues to own process-wide Host placement whenever either provider is installed. The provider-contract note continues to own each product protocol, result mapping, cancellation, process-tree lifecycle, and evidence tiers. The [Agent Preset architecture](2026-08-03-per-session-agent-presets.md) continues to own the Host/Agent split, preset authoring, and the rule that edits affect only newly composed sessions. +Each provider package owns its directly installable Bundle patch and private product runtime. This note continues to own process-wide Host placement whenever either provider is installed. The provider-contract note continues to own each product protocol, result mapping, cancellation, managed-range lifecycle, and evidence tiers. The [Agent Preset architecture](2026-08-03-per-session-agent-presets.md) continues to own the Host/Agent split, preset authoring, and the rule that edits affect only newly composed sessions. Each Bundle delegates executable selection to its package-owned product runtime: the Codex package runs its declared wrapper, while the Claude Code package lets its pinned Agent SDK select the private native executable. Neither provider consults or falls back to a host product command. Profile loading creates no product state, probes no version or authentication, and may supply each mounted Provider instance's deployment configuration, including the product-specific `permissionMode` values owned by the [non-interactive permissions decision](../feature/2026-08-15-product-subagent-noninteractive-permissions.md), without moving those choices into an Agent Preset or model-facing tool. Missing platform payloads and product failures remain local to the attempted delegation. ## Verification -The base bundle test proves production `dsh-base` contains neither product provider dependency nor provider row. The Web composition installs both optional Bundles and covers none, Codex-only, Claude-only, and both tool sets, including generation isolation after an authored preset changes. Package-owned Loader compositions prove each Bundle default and additional named instances register without starting a product process. Keyless ACP snapshots pin the Codex two-tool roster and the final four-tool combination, while provider tests separately prove private platform-payload selection without host fallback, configuration isolation, failure, cancellation, and process-tree quiescence. +The base bundle test proves production `dsh-base` contains neither product provider dependency nor provider row. The Web composition installs both optional Bundles and covers none, Codex-only, Claude-only, and both tool sets, including generation isolation after an authored preset changes. Package-owned Loader compositions prove each Bundle default and additional named instances register without starting a product process. Keyless ACP snapshots pin the Codex two-tool roster and the final four-tool combination, while provider tests separately prove private platform-payload selection without host fallback, configuration isolation, failure, cancellation, and managed-range quiescence. ## Alternatives considered diff --git a/.agents/notes/implemented/architecture/2026-08-10-product-subagent-providers-in-shared-host.zh.md b/.agents/notes/implemented/architecture/2026-08-10-product-subagent-providers-in-shared-host.zh.md index 1451890e1b..4623dde43d 100644 --- a/.agents/notes/implemented/architecture/2026-08-10-product-subagent-providers-in-shared-host.zh.md +++ b/.agents/notes/implemented/architecture/2026-08-10-product-subagent-providers-in-shared-host.zh.md @@ -14,13 +14,13 @@ Status: implemented 产品提供方仍是进程级的 host plane（宿主平面）注册。[生产安装排除决策](../simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.zh.md)只取代本说明原先由 base bundle 安装提供方的选择：生产 `dsh-base` 既不依赖也不挂载它们。选择产品集成的 Profile 会安装目标提供方 Bundle；其 patch 挂载默认实例，而 Profile 可以在 host plane 挂载更多命名实例。[命名实例决策](../feature/2026-08-18-product-subagent-named-instances.zh.md)负责每个配置项的注册身份：两个产品都接受多个唯一的 `providerName`，同时保留 `codex` 与 `claude-code` 作为默认值。加载任一插件只会注册一个休眠后端；对应的 Codex 或 Claude 进程直到第一次实际委派调用时才启动。Agent Preset 通过普通 `dsh-tool-subagent` 配置项的 `provider` 与 `toolName` 准确公开单个 agent 所需的已配置实例，而无需更改 Host 注册表。 -每个提供方包都拥有可直接安装的 Bundle patch 与私有产品运行时。本说明继续负责每个已安装提供方的进程级 Host 放置。提供方约定说明继续负责每个产品的协议、结果映射、取消、进程树生命周期与证据层级。[Agent Preset 架构](2026-08-03-per-session-agent-presets.zh.md)继续负责宿主与 agent 的划分、preset 创作，以及改动只影响新组装会话的规则。 +每个提供方包都拥有可直接安装的 Bundle patch 与私有产品运行时。本说明继续负责每个已安装提供方的进程级 Host 放置。提供方约定说明继续负责每个产品的协议、结果映射、取消、managed-range 生命周期与证据层级。[Agent Preset 架构](2026-08-03-per-session-agent-presets.zh.md)继续负责宿主与 agent 的划分、preset 创作，以及改动只影响新组装会话的规则。 每个 Bundle 都把可执行文件选择交给包自有的产品运行时：Codex 包运行自身声明的 wrapper，Claude Code 包则让锁定的 Agent SDK 选择私有原生可执行文件。两个提供方都不会查询或回退宿主产品命令。加载 Profile 不会创建产品状态、探测版本或测试身份验证；它可以提供每个已挂载 Provider 实例的部署配置，包括由[非交互权限决策](../feature/2026-08-15-product-subagent-noninteractive-permissions.zh.md)负责的产品专属 `permissionMode` 值，但不会把这些选择移入 Agent Preset 或面向模型的工具。平台载荷缺失和产品故障仍局限于发生问题的那次委派。 ## 验证 -base bundle 测试证明生产 `dsh-base` 既不包含产品提供方依赖，也不包含提供方配置项。Web 组装会安装两个可选 Bundle，并覆盖不暴露任何工具、仅暴露 Codex、仅暴露 Claude 和同时暴露两者这四种工具集合，也覆盖自行创作的 preset 发生改动后的代际隔离。由包负责的 Loader 组装证明每个 Bundle 默认实例与额外命名实例都会完成注册，而不会启动产品进程。无密钥 ACP（Agent Client Protocol）快照固定 Codex 双工具集合与最终四工具组合，提供方测试则另行证明私有平台载荷选择与无宿主回退、配置隔离、失败、取消和进程树完全停稳。 +base bundle 测试证明生产 `dsh-base` 既不包含产品提供方依赖，也不包含提供方配置项。Web 组装会安装两个可选 Bundle，并覆盖不暴露任何工具、仅暴露 Codex、仅暴露 Claude 和同时暴露两者这四种工具集合，也覆盖自行创作的 preset 发生改动后的代际隔离。由包负责的 Loader 组装证明每个 Bundle 默认实例与额外命名实例都会完成注册，而不会启动产品进程。无密钥 ACP（Agent Client Protocol）快照固定 Codex 双工具集合与最终四工具组合，提供方测试则另行证明私有平台载荷选择与无宿主回退、配置隔离、失败、取消和 managed-range 完全停稳。 ## 考虑过的替代方案 diff --git a/.agents/notes/implemented/bug-fix/2026-08-11-synchronous-subprocess-exit-cleanup.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-08-11-synchronous-subprocess-exit-cleanup.i18n.yaml index 216e14e98c..88f71563cf 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-11-synchronous-subprocess-exit-cleanup.i18n.yaml +++ b/.agents/notes/implemented/bug-fix/2026-08-11-synchronous-subprocess-exit-cleanup.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-11-synchronous-subprocess-exit-cleanup.md -2026-08-11-synchronous-subprocess-exit-cleanup.md: 517b7e82f00ea16ec6d9f8731be67963a46035da -2026-08-11-synchronous-subprocess-exit-cleanup.zh.md: f9555bba3d7fb2dc9971aef21f8a2c8c17d25398 +2026-08-11-synchronous-subprocess-exit-cleanup.md: 4f0603f6e2cb3c0cc4c0d4c0cde1b0da0ae82763 +2026-08-11-synchronous-subprocess-exit-cleanup.zh.md: acb20c8989d21b1fd5e97fa44247cd2875fb4570 diff --git a/.agents/notes/implemented/bug-fix/2026-08-11-synchronous-subprocess-exit-cleanup.md b/.agents/notes/implemented/bug-fix/2026-08-11-synchronous-subprocess-exit-cleanup.md index 517b7e82f0..4f0603f6e2 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-11-synchronous-subprocess-exit-cleanup.md +++ b/.agents/notes/implemented/bug-fix/2026-08-11-synchronous-subprocess-exit-cleanup.md @@ -6,7 +6,7 @@ English | [中文](2026-08-11-synchronous-subprocess-exit-cleanup.zh.md) ## Problem -The local subprocess provider owns ordinary detached process trees and terminal sessions, but it previously reached them only through asynchronous Cordis disposal. A fatal launcher may call `process.exit()` before that disposal finishes: the [fail-loud release](2026-07-31-fail-loud-releases-the-terminal.md) waits at most two seconds, while a local process can have a longer termination grace. Once Node enters its synchronous exit phase, pending promises and escalation timers do not continue, so a TERM-resistant child can outlive the host and keep CPU, memory, or ports. Some ACP, JSON-RPC, and SDK entry points also have no root release callback. +The local subprocess provider owns ordinary managed ranges and terminal sessions, but it previously reached them only through asynchronous Cordis disposal. A fatal launcher may call `process.exit()` before that disposal finishes: the [fail-loud release](2026-07-31-fail-loud-releases-the-terminal.md) waits at most two seconds, while a local process can have a longer termination grace. Once Node enters its synchronous exit phase, pending promises and staged-termination timers do not continue, so a TERM-resistant child can outlive the host and keep CPU, memory, or ports. Some ACP, JSON-RPC, and SDK entry points also have no root release callback. The public subprocess seam correctly promises awaited quiescence during normal disposal. The defect is a separate final host-exit path below that seam, not a reason to weaken the normal lifecycle or duplicate process ownership in every launcher. @@ -20,11 +20,11 @@ The listener uses local-only final operations that are absent from the public `S - A terminal handle synchronously signals every captured and currently observable descendant with SIGKILL, kills the PTY root, then rescans once for members that became observable during that boundary. - The service contains each target's failure and continues with the remaining handles. The callback creates no promise or timer, writes no diagnostic, and does not change the original exit code or error. -Normal disposal remains the [subprocess seam's](../architecture/2026-07-26-subprocess-seam.md) terminate-and-join path: ordinary trees receive TERM, the configured grace, then KILL, and every ordinary or terminal cleanup is awaited to quiescence. The synchronous path requests final termination but does not publish a completion result or claim the OS tree is already gone when the callback returns. Remote providers retain their own sandbox ownership and do not inherit a local Node listener. +Normal disposal remains the [subprocess seam's](../architecture/2026-07-26-subprocess-seam.md) terminate-and-join path: each ordinary handle runs its provider-owned termination procedure, and every ordinary or terminal cleanup is awaited to quiescence. The synchronous path requests final termination but does not publish a completion result or claim the OS range is already gone when the callback returns. Remote providers retain their own sandbox ownership and do not inherit a local Node listener. | Host path | Local provider action | Completion evidence | | --- | --- | --- | -| Normal Cordis disposal | Cooperative termination, bounded escalation, and awaited ordinary/terminal cleanup | Every owned handle reaches quiescence before disposal settles | +| Normal Cordis disposal | Provider-owned termination and awaited ordinary/terminal cleanup | Every owned handle reaches quiescence before disposal settles | | `process.exit()`, default uncaught exception, or default unhandled rejection | Synchronous final signals against the service's current live sets | External observation after the host exits | | Default termination for an unhandled `SIGTERM`, `SIGINT`, or `SIGHUP`; `SIGKILL`; fatal OOM; `process.abort()`; native crash; or power loss | No in-process action can run | External supervisor, container, or OS ownership is required unless the application installs a signal handler that performs disposal or calls `process.exit()` | @@ -32,7 +32,7 @@ Normal disposal remains the [subprocess seam's](../architecture/2026-07-26-subpr A parent test starts an isolated TypeScript host through the repository source launcher, waits until exact root and descendant process identities are observable, then allows the host to take each fatal path. Direct exit, default uncaught exception, and default unhandled rejection cover ordinary TERM-resistant trees; direct exit also covers a real terminal root and descendant. The parent asserts the original host exit category and waits for every recorded process to disappear, while failure cleanup targets only recorded identities or the recorded Windows tree. -Unit evidence pins synchronous native-owner and fallback delivery, terminal scans before and after the PTY root kill, repeated finalization, per-target failure containment, normal TERM-to-KILL disposal, live-set retention during pending disposal, and listener removal after disposal. +Unit evidence pins synchronous native-owner and fallback delivery, terminal scans before and after the PTY root kill, repeated finalization, per-target failure containment, staged POSIX and immediate Windows disposal, live-set retention during pending disposal, and listener removal after disposal. ## Alternatives considered diff --git a/.agents/notes/implemented/bug-fix/2026-08-11-synchronous-subprocess-exit-cleanup.zh.md b/.agents/notes/implemented/bug-fix/2026-08-11-synchronous-subprocess-exit-cleanup.zh.md index f9555bba3d..acb20c8989 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-11-synchronous-subprocess-exit-cleanup.zh.md +++ b/.agents/notes/implemented/bug-fix/2026-08-11-synchronous-subprocess-exit-cleanup.zh.md @@ -6,7 +6,7 @@ Status: implemented ## Problem -本地 subprocess provider拥有普通 detached进程树和 terminal session，但此前只能通过异步 Cordis dispose触及它们。致命 launcher可能在 dispose完成前调用 `process.exit()`：[fail-loud release](2026-07-31-fail-loud-releases-the-terminal.zh.md)最多等待两秒，而本地进程可以拥有更长的终止宽限期。Node进入同步退出阶段后，待处理的 Promise与升级 timer不会继续执行，因此忽略 TERM的子进程可能比宿主存活更久，继续占用 CPU、内存或端口。部分 ACP、JSON-RPC和 SDK入口也没有 root release回调。 +本地 subprocess provider拥有普通 managed range和 terminal session，但此前只能通过异步 Cordis dispose触及它们。致命 launcher可能在 dispose完成前调用 `process.exit()`：[fail-loud release](2026-07-31-fail-loud-releases-the-terminal.zh.md)最多等待两秒，而本地进程可以拥有更长的终止宽限期。Node进入同步退出阶段后，待处理的 Promise与分阶段终止 timer不会继续执行，因此忽略 TERM的子进程可能比宿主存活更久，继续占用 CPU、内存或端口。部分 ACP、JSON-RPC和 SDK入口也没有 root release回调。 公共 subprocess seam在正常 dispose期间承诺等待完全停稳，这项承诺是正确的。缺陷属于 seam之下另一条最终宿主退出路径，不应削弱正常生命周期，也不应让每个 launcher重复保存进程所有权。 @@ -20,11 +20,11 @@ Status: implemented - Terminal handle同步向全部已捕获及当前可观察的后代发送 SIGKILL，终止 PTY root，然后再扫描一次并终止在该边界期间变得可观察的成员。 - 服务分别包含每个目标的失败并继续处理其余 handle。回调不会创建 Promise或 timer，不写诊断，也不改变原始退出码或错误。 -正常 dispose继续使用[subprocess seam](../architecture/2026-07-26-subprocess-seam.zh.md)的先终止再等待退出路径：普通进程树先接收 TERM，经过配置的宽限期后再接收 KILL，并等待每个普通或 terminal清理达到完全停稳。同步路径只请求最终终止，不发布完成结果，也不声称回调返回时 OS进程树已经消失。远程 provider继续由其 sandbox独立拥有，不继承本地 Node listener。 +正常 dispose继续使用[subprocess seam](../architecture/2026-07-26-subprocess-seam.zh.md)的先终止再等待退出路径：每个普通 handle 执行其 provider-owned termination procedure，并等待每个普通或 terminal 清理达到完全停稳。同步路径只请求最终终止，不发布完成结果，也不声称回调返回时 OS range 已经消失。远程 provider继续由其 sandbox独立拥有，不继承本地 Node listener。 | 宿主路径 | 本地 provider动作 | 完成证据 | | --- | --- | --- | -| 正常 Cordis dispose | 协作式终止、有界升级，并等待普通／terminal清理 | dispose结算前，每个自有 handle均达到完全停稳 | +| 正常 Cordis dispose | provider-owned termination，并等待普通／terminal清理 | dispose结算前，每个自有 handle均达到完全停稳 | | `process.exit()`、默认未捕获异常或默认未处理 rejection | 对服务当前存活集合发送同步最终信号 | 宿主退出后的外部观察 | | 未安装 handler 时由 `SIGTERM`、`SIGINT` 或 `SIGHUP` 默认终止；`SIGKILL`；fatal OOM；`process.abort()`；native crash；或断电 | 进程内操作无法运行 | 必须由外部 supervisor、容器或 OS 所有权负责；应用安装执行 dispose 或调用 `process.exit()` 的信号 handler 时除外 | @@ -32,7 +32,7 @@ Status: implemented 父测试通过仓库 source launcher启动隔离的 TypeScript宿主，等待精确 root与后代进程身份可观察后，再允许宿主进入各条致命路径。直接退出、默认未捕获异常和默认未处理 rejection覆盖忽略 TERM的普通进程树；直接退出还覆盖真实 terminal root与后代。父测试断言原始宿主退出类别，并等待所有已记录进程消失；失败清理只针对已记录身份或已记录的 Windows进程树。 -单元证据固定同步 native-owner 与 fallback 投递、PTY root终止前后的 terminal扫描、重复最终清理、逐目标失败包含、正常 TERM到 KILL dispose、dispose等待期间保留存活集合，以及 dispose后移除 listener。 +单元证据固定同步 native-owner 与 fallback 投递、PTY root终止前后的 terminal扫描、重复最终清理、POSIX 分阶段与 Windows 立即终止、dispose等待期间保留存活集合，以及 dispose后移除 listener。 ## Alternatives considered diff --git a/.agents/notes/implemented/feature/2026-07-27-typescript-sdk-and-sdk-subagent-backend.i18n.yaml b/.agents/notes/implemented/feature/2026-07-27-typescript-sdk-and-sdk-subagent-backend.i18n.yaml index a9a33f4ebf..76d7c3faa7 100644 --- a/.agents/notes/implemented/feature/2026-07-27-typescript-sdk-and-sdk-subagent-backend.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-27-typescript-sdk-and-sdk-subagent-backend.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-27-typescript-sdk-and-sdk-subagent-backend.md -2026-07-27-typescript-sdk-and-sdk-subagent-backend.md: 84314eaf5827464767666b1b9c65e105ea4e869a -2026-07-27-typescript-sdk-and-sdk-subagent-backend.zh.md: a822aac655ea3577660f09b2f2a2986f2a780d7a +2026-07-27-typescript-sdk-and-sdk-subagent-backend.md: f26c92fbda4fafe9e5bdc469dae7ed0ab530b0b9 +2026-07-27-typescript-sdk-and-sdk-subagent-backend.zh.md: e72aff91daa7f9e96007a09c0ced25e56881bf2e diff --git a/.agents/notes/implemented/feature/2026-07-27-typescript-sdk-and-sdk-subagent-backend.md b/.agents/notes/implemented/feature/2026-07-27-typescript-sdk-and-sdk-subagent-backend.md index 84314eaf58..f26c92fbda 100644 --- a/.agents/notes/implemented/feature/2026-07-27-typescript-sdk-and-sdk-subagent-backend.md +++ b/.agents/notes/implemented/feature/2026-07-27-typescript-sdk-and-sdk-subagent-backend.md @@ -15,7 +15,7 @@ Three packages, layered exactly like the existing Python stack, plus one Service - **`@deepseek-ai/dsh-sdk-protocol`** (`packages/sdk/protocol/`) — the wire made shared and nominal. `JsonRpcLineTransport` moves here verbatim from `dsh-sdk-jsonrpc-server` (which now imports it), and `types.ts` names every payload the server speaks: `InitializeParams/Result`, `SessionPromptParams/Result`, the four notification payloads, and the `HarnessSdkRequestMap`/`HarnessSdkNotificationMap` indexes. The package root explicitly exports that complete interface and provides no source-module deep imports. The server's `notify()` call sites are typed against these named payloads, so server drift breaks compilation, not clients. One behavioral change: an error response now rejects with `JsonRpcResponseError` carrying the wire `code`/`data` (the Python client already preserved these; the old transport threw a bare `Error` with only the message). - **`@deepseek-ai/dsh-sdk-client`** (`packages/sdk/client/`) — the TypeScript twin of `python/sdk`: `HarnessClient` (spawn, frame, fan out notifications, typed error surfaces, close-to-quiescence via the shared dispose ladder) under `DeepSeekHarness`/`HarnessSession` (lazy start, memoized `initialize`, `run()` pairing one `session/prompt` with its `session.finished`). Its package-root consumer interface explicitly exports both client layers, caller-facing types, and the protocol-owned `JsonRpcResponseError`; source modules, normalization helpers, and the notification producer stay internal. `TurnResult.events` contains only the root session's typed events, while `notifications` retains session ids across the root and descendants discovered from `subagent.started`; session-tree scoping is client-side, mirroring `client.py`. Deliberate asymmetries with Python: the launch spec is explicit `command`/`args` (no bundled-runtime resolution — that is a distribution concern with no TS consumer yet); `env` replaces rather than merges (callers own credential policy; `scrubbedParentEnv` from the subprocess seam is one import away); `TurnResult` carries the structured `reason` (Python exposes only `status`); teardown walks a private stdin-EOF → SIGTERM → SIGKILL ladder to actual exit (the client runs outside any harness context, so it cannot ride `ctx.subprocess`). - **`@deepseek-ai/dsh-subagent-dsh-sdk`** (`packages/subagent/subagent-dsh-sdk/`) — the second out-of-process `SubagentProvider`, structured as `subagent-acp`'s sibling: same all-false capabilities and `inheritsParentContext: false`, same publish-after-handshake ownership transaction, same result-never-rejects flattening through an `onError` sink, same parent-namespace run id. The child answer is read from streamed `session.event`s — the last complete `assistant/message`, else accumulated `text-delta` chunks, so partial answers survive cancellation. Stop reasons map from the child's structured `TurnEndReason` (`completed`/`max-tokens`/`aborted` pass through; everything else, including a settled-without-turn child, is `error`). Its `provider`/`model` config feeds the child's `initialize`; `env` is where deployments pass the child's own key and `DSH_CORDIS_CONFIG`. -- **The subagent seam grows `out-of-process.ts`**: the provider-side vocabulary both out-of-process backends share — `NO_START_CAPABILITIES`, timing-bound validation, child cwd resolution (config override, else the delegating parent session's workspace), the never-reject `settleRunResult`, and the `subprocessRunHandle` publication. Process mechanics (spawn, env scrub, tree-scoped teardown) live in the `dsh-subprocess` seam; `subagent-acp` spawns through `ctx.subprocess`, while this backend spawns through the SDK client (the subprocess README's documented exception for SDK-managed transports) and applies the seam's `scrubbedParentEnv()` itself. +- **The subagent seam grows `out-of-process.ts`**: the provider-side vocabulary both out-of-process backends share — `NO_START_CAPABILITIES`, timing-bound validation, child cwd resolution (config override, else the delegating parent session's workspace), the never-reject `settleRunResult`, and the `subprocessRunHandle` publication. Process mechanics (spawn, env scrub, managed-range teardown) live in the `dsh-subprocess` seam; `subagent-acp` spawns through `ctx.subprocess`, while this backend spawns through the SDK client (the subprocess README's documented exception for SDK-managed transports) and applies the seam's `scrubbedParentEnv()` itself. `dsh-sdk-jsonrpc-server` keeps serving unchanged (the wire is byte-identical); `dsh-jsonrpc-agent-pkg` (the Python runtime closure) gains the `dsh-sdk-protocol` dependency line. diff --git a/.agents/notes/implemented/feature/2026-07-27-typescript-sdk-and-sdk-subagent-backend.zh.md b/.agents/notes/implemented/feature/2026-07-27-typescript-sdk-and-sdk-subagent-backend.zh.md index a822aac655..e72aff91da 100644 --- a/.agents/notes/implemented/feature/2026-07-27-typescript-sdk-and-sdk-subagent-backend.zh.md +++ b/.agents/notes/implemented/feature/2026-07-27-typescript-sdk-and-sdk-subagent-backend.zh.md @@ -15,7 +15,7 @@ stdio JSON-RPC 对外服务接口（`@deepseek-ai/dsh-sdk-jsonrpc-server`，见[ - **`@deepseek-ai/dsh-sdk-protocol`**（`packages/sdk/protocol/`）—— 把线协议做成共享且具名。`JsonRpcLineTransport` 从 `dsh-sdk-jsonrpc-server` 原样移入（后者现在导入它），`types.ts` 为服务器所说的每个载荷命名：`InitializeParams/Result`、`SessionPromptParams/Result`、四个通知载荷，以及 `HarnessSdkRequestMap`/`HarnessSdkNotificationMap` 索引。该包根显式导出这一完整接口，且不提供指向源模块的深层导入。服务器的 `notify()` 调用点以这些具名载荷标注类型，服务器漂移会先破坏编译而不是破坏客户端。一处行为变化：错误响应现在以携带线上 `code`/`data` 的 `JsonRpcResponseError` 拒绝（Python 客户端本就保留这些；旧传输只抛携带消息的裸 `Error`）。 - **`@deepseek-ai/dsh-sdk-client`**（`packages/sdk/client/`）—— `python/sdk` 的 TypeScript 孪生：`HarnessClient`（spawn、分帧、通知扇出、有类型的错误表面、经共享 dispose（资源释放）阶梯关闭至完全停稳）之上是 `DeepSeekHarness`/`HarnessSession`（惰性启动、记忆化 `initialize`、`run()` 把一个 `session/prompt` 与其 `session.finished` 配对）。其包根消费方接口显式导出两层客户端、面向调用方的类型，以及协议包所拥有的 `JsonRpcResponseError`；源模块、规范化辅助函数和通知投递端都保留为内部实现。`TurnResult.events` 只包含根会话的类型化事件，而 `notifications` 则保留根会话及从 `subagent.started` 发现的后代各自的会话 id；基于 `subagent.started` 血缘边的会话树范围限定在客户端完成，镜像 `client.py`。与 Python 的刻意不对称：启动规格是显式 `command`/`args`（无捆绑运行时解析——那是尚无 TS 消费方的发行问题）；`env` 整体替换而非合并（凭据策略归调用方；subprocess seam 的 `scrubbedParentEnv` 一个 import 即得）；`TurnResult` 携带结构化 `reason`（Python 只暴露 `status`）；拆除走私有的 stdin-EOF → SIGTERM → SIGKILL 阶梯直到真正退出（客户端运行在任何 harness 上下文之外，无法搭乘 `ctx.subprocess`）。 - **`@deepseek-ai/dsh-subagent-dsh-sdk`**（`packages/subagent/subagent-dsh-sdk/`）—— 第二个进程外 `SubagentProvider`，采用与 `subagent-acp` 对等的结构：同样的全 false 能力与 `inheritsParentContext: false`，同样的握手后发布所有权事务，同样通过 `onError` sink 将结果归一为绝不拒绝，同样的父命名空间 run id。子答案从流式 `session.event` 读取——最后一条完整 `assistant/message`，否则累积的 `text-delta` 块，部分答案在取消时得以保留。停止原因由子进程的结构化 `TurnEndReason` 映射（`completed`/`max-tokens`/`aborted` 直通；其余一切、包括未运行任何轮次便已结束的子进程，都是 `error`）。其 `provider`/`model` 配置喂给子进程的 `initialize`；`env` 是部署传入子进程自有密钥与 `DSH_CORDIS_CONFIG` 的地方。 -- **subagent seam 新增 `out-of-process.ts`**：两个进程外后端共享的 provider 侧词汇——`NO_START_CAPABILITIES`、时限校验、子进程 cwd 解析（配置覆盖、否则发起委托的父会话工作区）、绝不拒绝的 `settleRunResult`、以及 `subprocessRunHandle` 发布。进程机制（spawn、环境清理、进程树清理）属于 `dsh-subprocess` seam；`subagent-acp` 经 `ctx.subprocess` spawn 子进程，本后端则经 SDK 客户端 spawn 子进程（subprocess README 记载的 SDK 托管传输例外）并自行应用该 seam 的 `scrubbedParentEnv()`。 +- **subagent seam 新增 `out-of-process.ts`**：两个进程外后端共享的 provider 侧词汇——`NO_START_CAPABILITIES`、时限校验、子进程 cwd 解析（配置覆盖、否则发起委托的父会话工作区）、绝不拒绝的 `settleRunResult`、以及 `subprocessRunHandle` 发布。进程机制（spawn、环境清理、managed-range 拆卸）属于 `dsh-subprocess` seam；`subagent-acp` 经 `ctx.subprocess` spawn 子进程，本后端则经 SDK 客户端 spawn 子进程（subprocess README 记载的 SDK 托管传输例外）并自行应用该 seam 的 `scrubbedParentEnv()`。 `dsh-sdk-jsonrpc-server` 的服务不变（协议字节完全一致）；`dsh-jsonrpc-agent-pkg`（Python 运行时闭包）增加 `dsh-sdk-protocol` 一行依赖。 diff --git a/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.i18n.yaml b/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.i18n.yaml index 30ab9e2b09..e5b9b1d0f5 100644 --- a/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.md -2026-08-04-claude-code-and-codex-subagent-backends.md: 9b47fcf49d47d2c3561245fa1e16ff8c5da0a35c -2026-08-04-claude-code-and-codex-subagent-backends.zh.md: 8ba4d259872558ced89083bb53f9228f46c3d45c +2026-08-04-claude-code-and-codex-subagent-backends.md: 3c77321d3f5252a26f484fc78f586eb172e6d465 +2026-08-04-claude-code-and-codex-subagent-backends.zh.md: f9b675735fa3e15693b558d8dfd0eaea38f33e88 diff --git a/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.md b/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.md index 9b47fcf49d..3c77321d3f 100644 --- a/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.md +++ b/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.md @@ -8,19 +8,19 @@ English | [中文](2026-08-04-claude-code-and-codex-subagent-backends.zh.md) The named [`ctx.subagents`](2026-06-21-subagent-capability-seam.md) registry lets a parent agent delegate work without knowing how the child runs, but the harness needs first-party routes to the real Codex and Claude Code products. Each route must hand the product one self-contained task, let it work in the parent Session's workspace, return a final answer or an explicit failure or cancellation, and leave no managed product process behind. -The product integrations must not become second owners for task text, cwd, cancellation, result settlement, or process trees. Required evidence therefore separates three facts: a keyless real-product test proves the official integration, native authentication shape, deterministic answer, and teardown; a Loader composition test proves that the public package and documented tool configuration load without starting the product; and a credentialed e2e proves that the production provider and real product can obtain a unique answer from the real DeepSeek service. Direct model HTTP or a product double cannot replace either product-running tier, and a hand-mounted plugin cannot replace the Loader tier. +The product integrations must not become second owners for task text, cwd, cancellation, result settlement, or managed ranges. Required evidence therefore separates three facts: a keyless real-product test proves the official integration, native authentication shape, deterministic answer, and teardown; a Loader composition test proves that the public package and documented tool configuration load without starting the product; and a credentialed e2e proves that the production provider and real product can obtain a unique answer from the real DeepSeek service. Direct model HTTP or a product double cannot replace either product-running tier, and a hand-mounted plugin cannot replace the Loader tier. ## Decision The harness publishes two sibling one-shot provider packages whose default registry names are `codex` and `claude-code`. This note owns their product protocols, result mapping, and process lifecycle; the [named-instance decision](2026-08-18-product-subagent-named-instances.md) owns Profile-selected provider identity and static tool binding, the [production-install exclusion decision](../simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.md) owns their independent optional Bundles and host-plane placement, the [product one-shot background decision](2026-08-12-product-subagent-one-shot-background-tasks.md) owns the model-visible scheduling choice, the [non-interactive permissions decision](2026-08-15-product-subagent-noninteractive-permissions.md) owns each product Provider's Profile-selected mode and safe permission decisions, and the [structured failure-facts decision](2026-08-18-product-subagent-failure-facts.md) owns version-pinned product categories, lifecycle stages, and process outcomes exposed through the same diagnostic. Both packages accept multiple named instances. Loading either provider starts no product process, and each tool accepts only a standalone text task; product and instance selection remain deployment configuration. -Both providers report `inheritsParentContext: false`, advertise no optional start capabilities, and pass the parent Session cwd without copying the parent conversation. Their documented tools use `backgroundMode: 'one-shot'` and `maxDepth: 'provider-managed'`: the consumer keeps foreground collection as the default and may place the same run in the generic Job runtime, while recursion policy stays with the out-of-process product. Every call creates a fresh product process and a non-resumable product conversation. `ctx.subagents` owns named-request resolution and paired lifecycle events; `dsh-tool-subagent` owns model-visible scheduling and foreground-versus-Job adaptation; `ctx.jobs` and `dsh-tool-jobs` own Job ids, state, output, controls, notices, and parent-owner cancellation; each product provider owns native result mapping, while `dsh-subprocess` owns credential scrubbing, process-tree termination, and whole-tree exit observation. +Both providers report `inheritsParentContext: false`, advertise no optional start capabilities, and pass the parent Session cwd without copying the parent conversation. Their documented tools use `backgroundMode: 'one-shot'` and `maxDepth: 'provider-managed'`: the consumer keeps foreground collection as the default and may place the same run in the generic Job runtime, while recursion policy stays with the out-of-process product. Every call creates a fresh product process and a non-resumable product conversation. `ctx.subagents` owns named-request resolution and paired lifecycle events; `dsh-tool-subagent` owns model-visible scheduling and foreground-versus-Job adaptation; `ctx.jobs` and `dsh-tool-jobs` own Job ids, state, output, controls, notices, and parent-owner cancellation; each product provider owns native result mapping, while `dsh-subprocess` owns credential scrubbing, managed-range termination, and quiescence observation. ```text configured tool -> dsh-tool-subagent -> ctx.subagents -> product provider -> product process foreground <- final product outcome background -> ctx.jobs / dsh-tool-jobs -> Job id / state / notice / controls - both -> provider disposal -> dsh-subprocess -> whole-tree exit + both -> provider disposal -> dsh-subprocess -> managed-range exit ``` ### Ownership and lifecycle @@ -30,7 +30,7 @@ configured tool -> dsh-tool-subagent -> ctx.subagents -> product provider -> pro | Delegation lifecycle | `ctx.subagents` | Resolve the named provider request and pair lifecycle events around the published `SubagentRun` | Unsupported context or malformed input fails before a run is published; start and terminal events remain paired | | Scheduling and adaptation | `dsh-tool-subagent` | Interpret `run_in_background`, choose foreground collection or one-shot Job registration, and map the shared stop reason | Foreground returns the product outcome; background returns a Job id after registration | | Job state and control | `ctx.jobs` and `dsh-tool-jobs` | Own Job state, output, cancellation, owner cleanup, completion notices, and model-facing controls | The exact parent can collect, list, or stop background work and receives its completion notice | -| Native run and teardown | Product provider and `dsh-subprocess` | Produce one native result, close the product protocol, request best-effort native cancellation, and prove process-tree exit | Foreground return and Job settlement both wait for idempotent disposal and whole-tree exit | +| Native run and teardown | Product provider and `dsh-subprocess` | Produce one native result, close the product protocol, request best-effort native cancellation, and prove managed-range exit | Foreground return and Job settlement both wait for idempotent disposal and managed-range exit | ## Codex provider @@ -42,7 +42,7 @@ Before publication, the provider validates a non-empty text-only task, starts th For command and file approvals, the unattended wire selects a non-approval decision offered by the request, preferring `cancel`; the stable 0.147.0 request shape without an offered-decision list falls back to `decline`. It grants no requested permissions for the turn, answers user-input requests with no answers, and declines MCP elicitation. It records safe categories for those requests, declined command/file items, and `sandboxError`. Codex emits some early `never` rejections and sandbox violations only on structured stderr, so the Provider pipes and forwards stderr unchanged while matching two fixed signatures in a bounded per-run tail; raw stderr never enters the diagnostic. A request with no legal unattended response, or any unknown server request, fails the run instead of waiting for a user interface the provider does not supply. -An unpublished startup failure closes the wire, terminates the acquired process tree, waits for exit, detaches the stderr observer, and then rejects `start()` with its fixed operation stage. Published disposal best-effort interrupts a known turn, closes the wire, ends stdin, invokes the shared termination escalation, waits for whole-tree exit, and detaches the observer. Independent cleanup failure reports `teardown`; when startup and rollback both fail, the aggregate's top message retains both safe stage lines while the underlying causes remain internal. +An unpublished startup failure closes the wire, invokes termination for any acquired managed range, waits for it to empty, detaches the stderr observer, and then rejects `start()` with its fixed operation stage. Published disposal best-effort interrupts a known turn, closes the wire, ends stdin, invokes the subprocess provider's termination procedure, waits for managed-range exit, and detaches the observer. Independent cleanup failure reports `teardown`; when startup and rollback both fail, the aggregate's top message retains both safe stage lines while the underlying causes remain internal. Codex 0.147.0 speaks the Responses protocol, while DeepSeek's public OpenAI-compatible endpoint speaks Chat Completions. The credentialed Codex e2e therefore uses a loopback-only, test-private bridge for one no-tool nonce request: real Codex sends Responses to the bridge, the bridge forwards the received bearer credential and extracted task to the fixed official DeepSeek endpoint, and it wraps the real text in the minimal Responses SSE lifecycle. The bridge is neither a production proxy nor evidence that Codex connects to DeepSeek Chat Completions natively. @@ -54,7 +54,7 @@ The public configuration contains a non-empty `providerName`, an explicit `env` The provider publishes only after both the SDK `Query` and a live managed CLI handle exist. It consumes the complete SDK stream and completes only when a `result` message has `subtype: "success"`, `is_error: false`, and a nonblank `result`, and the iterator then ends normally. The [structured failure-facts decision](2026-08-18-product-subagent-failure-facts.md) owns every non-success category, stage, process outcome, and its ordering with a contributing permission decision. Local cancellation wins and becomes `aborted` without either diagnostic fact. -Startup rollback and published disposal close the SDK query, abort the per-run controller, invoke shared process-tree termination, and wait for whole-tree exit. `Query.close()` expresses graceful protocol intent but does not replace the subprocess owner's exit proof. An unpublished failure exposes only fixed `query-start` facts; a published process failure can expose its independent exit code and signal; an independent cleanup rejection exposes `teardown`. Original SDK, Host, and cleanup errors remain on internal cause chains and logs rather than entering the diagnostic. +Startup rollback and published disposal close the SDK query, abort the per-run controller, invoke the subprocess provider's termination procedure, and wait for managed-range exit. `Query.close()` expresses graceful protocol intent but does not replace the subprocess owner's quiescence proof. An unpublished failure exposes only fixed `query-start` facts; a published process failure can expose its independent exit code and signal; an independent cleanup rejection exposes `teardown`. Original SDK, Host, and cleanup errors remain on internal cause chains and logs rather than entering the diagnostic. The credentialed Claude Code e2e uses the official DeepSeek Claude Code contract directly: the runtime-only DeepSeek key becomes `ANTHROPIC_AUTH_TOKEN`, the fixed official base gains `/anthropic`, and the main and subagent model variables select the documented DeepSeek models. It starts the production provider and real SDK/CLI, requires one random nonce as the complete answer, persists no credential in settings, and waits for every managed handle to exit. @@ -62,13 +62,13 @@ The credentialed Claude Code e2e uses the official DeepSeek Claude Code contract Each product owns branch-complete package tests, a required keyless real-product spec, a Loader composition e2e, and a credentialed DeepSeek e2e. The keyless product tier uses the exact official distribution under test, a non-empty fake product key, an isolated temporary workspace and product home, and a loopback fixed-answer model. Missing product requests, wrong authentication, altered task text, a non-exact answer, a skipped real product, or a surviving managed handle fails the required test. The Codex Loader fixture exposes two named Codex instances and tools; the Claude Code Loader fixture exposes the default Codex tool plus two named Claude Code instances and tools. Both fixtures include generic Job controls and start neither product process. The credentialed tier starts the same production provider and real product with a runtime-only key, requires a unique nonce from the fixed official DeepSeek service, and proves quiescence again; it self-skips only when a local operator supplied no key, while trusted CI preflights the secret. -The Codex evidence pins `@openai/codex@0.147.0`, `codex-cli 0.147.0`, and all six optional platform aliases. Its real-product spec observes the package-local wrapper argv, exact Bearer key, original task, byte-exact final answer, native permission modes, explicit dangerous-bypass writing in suite-owned temporary storage, and wrapper/native whole-tree exit. An isolated wrapper fixture proves missing-payload failure without host fallback, two named instances retain separate environments and modes, and production never resolves a host `codex` from `PATH`. The [structured failure-facts decision](2026-08-18-product-subagent-failure-facts.md) owns schema, failure, process-outcome, and final presentation evidence. +The Codex evidence pins `@openai/codex@0.147.0`, `codex-cli 0.147.0`, and all six optional platform aliases. Its real-product spec observes the package-local wrapper argv, exact Bearer key, original task, byte-exact final answer, native permission modes, explicit dangerous-bypass writing in suite-owned temporary storage, and wrapper/native managed-range exit. An isolated wrapper fixture proves missing-payload failure without host fallback, two named instances retain separate environments and modes, and production never resolves a host `codex` from `PATH`. The [structured failure-facts decision](2026-08-18-product-subagent-failure-facts.md) owns schema, failure, process-outcome, and final presentation evidence. The Codex credentialed e2e registers the production provider, starts the same real app-server, and requests one random nonce through the test-private bridge described above. It fixes the external endpoint and model, stores no credential or request payload, requires exactly one completed upstream response, compares the trimmed product answer byte-for-byte with the nonce, and waits for every managed handle to exit. -The Claude Code evidence pins Agent SDK 0.3.220, Claude Code 2.1.220, and all eight SDK platform packages. Its real-product spec lets the SDK select the installed payload, asserts that the shared subprocess argv begins with that package's native CLI, and observes the exact `x-api-key`, original task, byte-exact final answer, native permission modes, suite-owned denied and bypassed writes, and whole-tree exit. Package tests prove that production never resolves host `PATH`, omits the executable override, and forwards the SDK-selected Windows `claude.exe` without a batch shim. This evidence proves the pinned official SDK/CLI integration rather than compatibility with independently installed Claude versions; the [structured failure-facts decision](2026-08-18-product-subagent-failure-facts.md) owns failure and process-outcome evidence. Loader coverage resolves both products through their optional Bundle patches while starting neither product. +The Claude Code evidence pins Agent SDK 0.3.220, Claude Code 2.1.220, and all eight SDK platform packages. Its real-product spec lets the SDK select the installed payload, asserts that the shared subprocess argv begins with that package's native CLI, and observes the exact `x-api-key`, original task, byte-exact final answer, native permission modes, suite-owned denied and bypassed writes, and managed-range exit. Package tests prove that production never resolves host `PATH`, omits the executable override, and forwards the SDK-selected Windows `claude.exe` without a batch shim. This evidence proves the pinned official SDK/CLI integration rather than compatibility with independently installed Claude versions; the [structured failure-facts decision](2026-08-18-product-subagent-failure-facts.md) owns failure and process-outcome evidence. Loader coverage resolves both products through their optional Bundle patches while starting neither product. -The Claude Code credentialed e2e maps the key and fixed official endpoint only in the provider's in-memory environment, uses the documented `deepseek-v4-pro[1m]` and `deepseek-v4-flash` model variables, and traverses the production provider, official SDK, and real CLI. It compares the trimmed result with a random nonce and proves whole-tree exit without calling the Messages API directly from the test. +The Claude Code credentialed e2e maps the key and fixed official endpoint only in the provider's in-memory environment, uses the documented `deepseek-v4-pro[1m]` and `deepseek-v4-flash` model variables, and traverses the production provider, official SDK, and real CLI. It compares the trimmed result with a random nonce and proves managed-range exit without calling the Messages API directly from the test. The project owner's distribution authorization is scoped to the official `@anthropic-ai/claude-agent-sdk` identity and the official Claude Code CLI/platform payloads each SDK version declares through `optionalDependencies`. [`THIRD_PARTY_NOTICES.md`](../../../../THIRD_PARTY_NOTICES.md) derives and discloses the current payload set without reclassifying its declared terms as permissive. Version, license-field, and payload-set changes still undergo ordinary dependency, lockfile, compatibility, terms, and notices review; unrelated non-permissive runtime packages continue to fail closed. @@ -76,7 +76,7 @@ The project owner's distribution authorization is scoped to the official `@anthr **Direct model HTTP, `codex exec`, or a hand-written Claude CLI protocol.** These paths bypass the products' official extensible integration surfaces and cannot prove native configuration, tools, approvals, result semantics, or teardown. Each provider uses its official product integration instead. -**A shared product-process helper package.** The existing subagent and subprocess seams already own every shared task, result, environment, and process-tree concern. A new helper would duplicate ownership without deleting either private product adapter, so each adapter calls the existing seams directly. +**A shared product-process helper package.** The existing subagent and subprocess seams already own every shared task, result, environment, and managed-range concern. A new helper would duplicate ownership without deleting either private product adapter, so each adapter calls the existing seams directly. **A model-visible product selector.** Product availability, instance configuration, and authentication are deployment facts. Profile-bound tools keep each schema and provider binding explicit and avoid adding dynamic selection state to the common service. @@ -88,7 +88,7 @@ The project owner's distribution authorization is scoped to the official `@anthr ## Consequences -Users delegate through Profile-configured one-shot tools backed by the official product integrations. Explicit Profile installation and host-plane provider placement are owned by the [production-install exclusion decision](../simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.md); named instance identity and tool binding are owned by the [named-instance decision](2026-08-18-product-subagent-named-instances.md); per-Preset tool exposure and foreground-default optional Job scheduling are owned by the [product one-shot background decision](2026-08-12-product-subagent-one-shot-background-tasks.md). This note's provider lifecycle keeps native settings and behavior while shared services retain the sole ownership of job settlement and process-tree quiescence. +Users delegate through Profile-configured one-shot tools backed by the official product integrations. Explicit Profile installation and host-plane provider placement are owned by the [production-install exclusion decision](../simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.md); named instance identity and tool binding are owned by the [named-instance decision](2026-08-18-product-subagent-named-instances.md); per-Preset tool exposure and foreground-default optional Job scheduling are owned by the [product one-shot background decision](2026-08-12-product-subagent-one-shot-background-tasks.md). This note's provider lifecycle keeps native settings and behavior while shared services retain the sole ownership of job settlement and managed-range quiescence. Every delegation pays for a fresh product process and independent model context. Successful product payload remains final assistant text; a failed product run may separately expose the shared safe diagnostic containing provider-owned permission facts or version-pinned structured failure facts. Background scheduling additionally exposes generic Job ids, status, completion notices, and collection or cancellation results. Both products use Bundle-pinned platform CLIs plus native account and workspace settings and the selected Provider permission mode. Credentialed e2e runs also spend external API quota and depend on the official DeepSeek endpoint; deterministic protocol, failure, cancellation, and approval coverage remains in the keyless tier. The providers do not resume sessions, stream progress, accept new human interaction, roll back tool or file side effects, or impose a wall-clock timeout. diff --git a/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.zh.md b/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.zh.md index 8ba4d25987..f9b675735f 100644 --- a/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.zh.md +++ b/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.zh.md @@ -8,19 +8,19 @@ Status: implemented 命名的 [`ctx.subagents`](2026-06-21-subagent-capability-seam.zh.md) 注册表让父 agent（智能体）无需了解子 agent 的运行方式即可委派工作，但 harness 需要通往真实 Codex 与 Claude Code 产品的第一方路径。每条路径都必须向产品交付一项自包含任务，让它在父会话的工作区中执行，返回最终回答或明确的失败或取消结果，并且不留下任何受管的产品进程。 -产品集成不得成为任务文本、cwd、取消、结果结算或进程树的第二责任方。因此，所需证据要区分三个事实：无密钥真实产品测试证明官方集成、原生身份验证形态、确定性答案与资源清理；Loader 组合测试证明公开包和文档所示的工具配置无需启动产品即可加载；带密钥 e2e 证明生产提供方与真实产品能够从真实 DeepSeek 服务取得唯一答案。直接发起模型 HTTP 请求或使用产品替身无法取代上述任一产品运行层级；手工挂载插件无法取代 Loader 层级。 +产品集成不得成为任务文本、cwd、取消、结果结算或 managed range 的第二责任方。因此，所需证据要区分三个事实：无密钥真实产品测试证明官方集成、原生身份验证形态、确定性答案与资源清理；Loader 组合测试证明公开包和文档所示的工具配置无需启动产品即可加载；带密钥 e2e 证明生产提供方与真实产品能够从真实 DeepSeek 服务取得唯一答案。直接发起模型 HTTP 请求或使用产品替身无法取代上述任一产品运行层级；手工挂载插件无法取代 Loader 层级。 ## 决策 harness 交付两个同级的一次性提供方包，其默认注册名称分别为 `codex` 与 `claude-code`。本说明负责它们的产品协议、结果映射和进程生命周期；[命名实例决策](2026-08-18-product-subagent-named-instances.zh.md)负责 Profile 选择的提供方身份与静态工具绑定，[生产安装排除决策](../simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.zh.md)负责各自独立的可选 Bundle 与 host plane（宿主平面）放置，[产品一次性后台任务决策](2026-08-12-product-subagent-one-shot-background-tasks.zh.md)负责模型可见的调度选择，[非交互权限决策](2026-08-15-product-subagent-noninteractive-permissions.zh.md)负责各产品提供方的 Profile 模式选择与安全权限决定，[结构化失败事实决策](2026-08-18-product-subagent-failure-facts.zh.md)则负责通过同一诊断公开锁定产品版本的类别、生命周期阶段与进程结果。两个包都接受多个命名实例。加载任一提供方都不会启动产品进程，而且每个工具只接受独立文本任务；产品与实例选择仍属于部署配置。 -这两个提供方都报告 `inheritsParentContext: false`，不声明任何可选的启动能力，并传递父会话 cwd，但不会复制父级对话。文档所示的工具使用 `backgroundMode: 'one-shot'` 与 `maxDepth: 'provider-managed'`：消费方默认在前台收集结果，也可把同一次运行放入通用 Job 运行时，而递归策略仍由进程外产品负责。每次调用都会创建一个全新的产品进程和一次不可续接的产品对话。`ctx.subagents` 负责具名请求解析与成对生命周期事件；`dsh-tool-subagent` 负责模型可见的调度以及前台与 Job 适配；`ctx.jobs` 和 `dsh-tool-jobs` 负责 Job id、状态、输出、控制、通知与父级 owner 取消；各产品提供方负责原生结果映射，`dsh-subprocess` 则负责凭证清洗、进程树终止以及整棵进程树的退出观测。 +这两个提供方都报告 `inheritsParentContext: false`，不声明任何可选的启动能力，并传递父会话 cwd，但不会复制父级对话。文档所示的工具使用 `backgroundMode: 'one-shot'` 与 `maxDepth: 'provider-managed'`：消费方默认在前台收集结果，也可把同一次运行放入通用 Job 运行时，而递归策略仍由进程外产品负责。每次调用都会创建一个全新的产品进程和一次不可续接的产品对话。`ctx.subagents` 负责具名请求解析与成对生命周期事件；`dsh-tool-subagent` 负责模型可见的调度以及前台与 Job 适配；`ctx.jobs` 和 `dsh-tool-jobs` 负责 Job id、状态、输出、控制、通知与父级 owner 取消；各产品提供方负责原生结果映射，`dsh-subprocess` 则负责凭证清洗、managed-range 终止与完全停稳观测。 ```text configured tool -> dsh-tool-subagent -> ctx.subagents -> product provider -> product process foreground <- final product outcome background -> ctx.jobs / dsh-tool-jobs -> Job id / state / notice / controls - both -> provider disposal -> dsh-subprocess -> whole-tree exit + both -> provider disposal -> dsh-subprocess -> managed-range exit ``` ### 归属与生命周期 @@ -30,7 +30,7 @@ configured tool -> dsh-tool-subagent -> ctx.subagents -> product provider -> pro | 委派生命周期 | `ctx.subagents` | 解析具名提供方请求，并为已发布的 `SubagentRun` 配对生命周期事件 | 不受支持的上下文或格式错误的输入会在发布运行前报错；启动与终态事件保持成对 | | 调度与适配 | `dsh-tool-subagent` | 解释 `run_in_background`，选择前台收集或 one-shot Job 登记，并映射共享停止原因 | 前台返回产品结果；后台在登记完成后返回 Job id | | Job 状态与控制 | `ctx.jobs` 与 `dsh-tool-jobs` | 负责 Job 状态、输出、取消、owner 清理、完成通知与面向模型的控制工具 | 准确父级可以收集、列出或停止后台工作，并收到完成通知 | -| 原生运行与清理 | 产品提供方与 `dsh-subprocess` | 产生一个原生结果、关闭产品协议、请求尽力而为的原生取消，并证明进程树退出 | 前台返回与 Job 结算都会等待幂等资源释放和整棵进程树退出 | +| 原生运行与清理 | 产品提供方与 `dsh-subprocess` | 产生一个原生结果、关闭产品协议、请求尽力而为的原生取消，并证明 managed range 退出 | 前台返回与 Job 结算都会等待幂等资源释放和 managed range 退出 | ## Codex 提供方 @@ -42,7 +42,7 @@ configured tool -> dsh-tool-subagent -> ctx.subagents -> product provider -> pro 对于命令与文件审批，无人值守的协议连接会从请求给出的决策选项中选择一项不予批准的决策，并优先选择 `cancel`；稳定的 0.147.0 请求形态没有决策选项列表，因此回退到 `decline`。它不授予该轮次请求的任何权限，不向用户输入请求提供任何答案，并拒绝 MCP elicitation。它会记录这些请求、被拒绝的命令／文件 item 与 `sandboxError` 的安全类别。Codex 的部分早期 `never` 拒绝和 sandbox violation 只写入结构化 stderr，因此提供方会 pipe 并原样转发 stderr，同时在每次运行的有界尾部中匹配两个固定签名；原始 stderr 绝不会进入诊断。若请求在无人值守模式下没有合法响应，或是未知服务器请求，此次运行就会失败，而不会等待本提供方没有提供的用户界面。 -若启动在发布前失败，提供方会关闭协议连接、终止已获取的进程树、等待其退出、移除 stderr observer，然后用固定操作阶段拒绝 `start()`。对已发布的运行执行资源释放时，提供方会尽力中断已知轮次、关闭协议连接、结束标准输入、调用共享的逐级终止机制，等待整棵进程树退出，并移除 observer。独立清理失败会报告 `teardown`；启动与回滚同时失败时，聚合的顶层消息会保留两条安全阶段说明，而底层 cause 仍只在内部可见。 +若启动在发布前失败，提供方会关闭协议连接、请求终止所有已取得的 managed range、等待范围为空、移除 stderr observer，然后用固定操作阶段拒绝 `start()`。对已发布的运行执行资源释放时，提供方会尽力中断已知轮次、关闭协议连接、结束标准输入、调用 subprocess provider 的终止过程，等待 managed range 退出，并移除 observer。独立清理失败会报告 `teardown`；启动与回滚同时失败时，聚合的顶层消息会保留两条安全阶段说明，而底层 cause 仍只在内部可见。 Codex 0.147.0 使用 Responses 协议，而 DeepSeek 的公开 OpenAI 兼容端点使用 Chat Completions。因此，带密钥 Codex e2e 会采用一个仅限回环、仅供测试内部使用的桥接层来处理一次不使用工具的随机数请求：真实 Codex 将 Responses 发送到桥接层，桥接层把收到的 Bearer 凭据与提取出的任务转发到固定的 DeepSeek 官方端点，再将真实文本包装进最小化的 Responses SSE（Server-Sent Events）生命周期。该桥接层既不是生产代理，也不能作为 Codex 原生连接 DeepSeek Chat Completions 的证据。 @@ -54,7 +54,7 @@ Codex 0.147.0 使用 Responses 协议，而 DeepSeek 的公开 OpenAI 兼容端 只有在 SDK `Query` 与受管的活动 CLI 句柄都已存在后，提供方才会发布运行。它会消费完整的 SDK 流；只有 `result` 消息具有 `subtype: "success"`、`is_error: false` 和非空白 `result`，且迭代器随后正常结束时，运行才会完成。[结构化失败事实决策](2026-08-18-product-subagent-failure-facts.zh.md)负责所有非成功类别、阶段、进程结果，以及它们与参与失败的权限决定之间的顺序。本地取消会胜出并成为 `aborted`，且不附带这两类诊断事实。 -启动回滚和已发布运行的资源释放都会关闭 SDK query、中止该次运行的控制器、调用共享的进程树终止机制，并等待整棵进程树退出。`Query.close()` 表达优雅的协议关闭意图，但不能取代子进程责任方的退出证明。未发布失败只公开固定的 `query-start` 事实；已发布进程失败可以分别公开退出码与信号；独立清理拒绝则公开 `teardown`。原始 SDK、Host 与清理错误只保留在内部 cause 链和日志中，不进入诊断。 +启动回滚和已发布运行的资源释放都会关闭 SDK query、中止该次运行的控制器、调用 subprocess provider 的终止过程，并等待 managed range 退出。`Query.close()` 表达优雅的协议关闭意图，但不能取代子进程责任方的完全停稳证明。未发布失败只公开固定的 `query-start` 事实；已发布进程失败可以分别公开退出码与信号；独立清理拒绝则公开 `teardown`。原始 SDK、Host 与清理错误只保留在内部 cause 链和日志中，不进入诊断。 带密钥 Claude Code e2e 直接使用官方 DeepSeek Claude Code 约定：仅在运行时提供的 DeepSeek 密钥会映射为 `ANTHROPIC_AUTH_TOKEN`，固定的官方基础 URL 会追加 `/anthropic`，主模型与 subagent 模型变量会选择文档所示的 DeepSeek 模型。该测试会启动生产提供方与真实 SDK 和 CLI，要求一个随机数作为完整答案，不会把任何凭据持久化到设置中，并等待所有受管句柄退出。 @@ -62,13 +62,13 @@ Codex 0.147.0 使用 Responses 协议，而 DeepSeek 的公开 OpenAI 兼容端 每个产品都负责覆盖所有分支的包测试、一项必跑的无密钥真实产品测试、一项 Loader 组合 e2e 和一项带密钥 DeepSeek e2e。无密钥产品层级使用被测的确切官方发行版、非空的伪产品密钥、隔离的临时工作区与产品主目录，以及能返回固定答案的回环模型。产品请求缺失、身份验证错误、任务文本被改动、答案不完全一致、真实产品被跳过或受管句柄仍存活，都会使这项必跑测试失败。Codex Loader fixture 会公开两个命名 Codex 实例与工具；Claude Code Loader fixture 会公开默认 Codex 工具以及两个命名 Claude Code 实例与工具。两个 fixture 都包含通用 Job 控制工具，而且不会启动任何产品进程。带密钥层级会使用仅在运行时提供的密钥启动同一生产提供方与真实产品，要求从固定的 DeepSeek 官方服务取得唯一随机数，并再次证明完全停稳；仅当本地操作者未提供密钥时才会自行跳过，而受信任的 CI 会预检该 secret。 -Codex 证据会锁定 `@openai/codex@0.147.0`、`codex-cli 0.147.0` 与六个平台 alias。其真实产品测试会观测包内 wrapper argv、确切的 Bearer 密钥、原始任务、逐字节完全一致的最终回答、原生权限模式、测试拥有临时存储中的显式危险绕过写入，以及 wrapper／原生整棵进程树退出。独立 wrapper fixture 会证明载荷缺失时不回退宿主命令，两个命名实例会保留彼此独立的环境与模式，生产环境也不会从 `PATH` 解析宿主 `codex`。[结构化失败事实决策](2026-08-18-product-subagent-failure-facts.zh.md)负责 schema、失败、进程结果与最终呈现证据。 +Codex 证据会锁定 `@openai/codex@0.147.0`、`codex-cli 0.147.0` 与六个平台 alias。其真实产品测试会观测包内 wrapper argv、确切的 Bearer 密钥、原始任务、逐字节完全一致的最终回答、原生权限模式、测试拥有临时存储中的显式危险绕过写入，以及 wrapper／原生 managed range 退出。独立 wrapper fixture 会证明载荷缺失时不回退宿主命令，两个命名实例会保留彼此独立的环境与模式，生产环境也不会从 `PATH` 解析宿主 `codex`。[结构化失败事实决策](2026-08-18-product-subagent-failure-facts.zh.md)负责 schema、失败、进程结果与最终呈现证据。 带密钥 Codex e2e 会注册生产提供方，启动同样的真实 app-server，并通过上述测试专用桥接层请求一个随机数。该测试固定外部端点与模型，不存储任何凭据或请求载荷，要求上游恰好完成一次响应，将去除首尾空白后的产品答案与该随机数逐字节比较，并等待所有受管句柄退出。 -Claude Code 证据会锁定 Agent SDK 0.3.220、Claude Code 2.1.220 与八个 SDK 平台包。真实产品测试会让 SDK 选择已安装载荷，断言共享子进程 argv 以该包的原生 CLI 开头，并观测确切的 `x-api-key`、原始任务、逐字节完全一致的最终回答、原生权限模式、测试拥有范围内的拒绝写入与 bypass 写入，以及整棵进程树退出。包测试还会证明生产运行从不解析宿主 `PATH`、省略可执行文件覆盖，并直接转发 SDK 所选的 Windows `claude.exe` 而不经过 batch shim。这项证据证明锁定的官方 SDK/CLI 集成，而不证明与独立安装的 Claude 版本兼容；[结构化失败事实决策](2026-08-18-product-subagent-failure-facts.zh.md)负责失败与进程结果证据。Loader 覆盖会通过各自的可选 Bundle patch 解析两个产品，且不会启动任一产品。 +Claude Code 证据会锁定 Agent SDK 0.3.220、Claude Code 2.1.220 与八个 SDK 平台包。真实产品测试会让 SDK 选择已安装载荷，断言共享子进程 argv 以该包的原生 CLI 开头，并观测确切的 `x-api-key`、原始任务、逐字节完全一致的最终回答、原生权限模式、测试拥有范围内的拒绝写入与 bypass 写入，以及 managed range 退出。包测试还会证明生产运行从不解析宿主 `PATH`、省略可执行文件覆盖，并直接转发 SDK 所选的 Windows `claude.exe` 而不经过 batch shim。这项证据证明锁定的官方 SDK/CLI 集成，而不证明与独立安装的 Claude 版本兼容；[结构化失败事实决策](2026-08-18-product-subagent-failure-facts.zh.md)负责失败与进程结果证据。Loader 覆盖会通过各自的可选 Bundle patch 解析两个产品，且不会启动任一产品。 -带密钥 Claude Code e2e 仅在提供方的内存环境中映射密钥与固定的官方端点，把模型变量设为文档所示的 `deepseek-v4-pro[1m]` 与 `deepseek-v4-flash`，并实际经过生产提供方、官方 SDK 与真实 CLI。它将去除首尾空白后的结果与一个随机数比较，并证明整棵进程树退出，且测试不会直接调用 Messages API。 +带密钥 Claude Code e2e 仅在提供方的内存环境中映射密钥与固定的官方端点，把模型变量设为文档所示的 `deepseek-v4-pro[1m]` 与 `deepseek-v4-flash`，并实际经过生产提供方、官方 SDK 与真实 CLI。它将去除首尾空白后的结果与一个随机数比较，并证明 managed range 退出，且测试不会直接调用 Messages API。 项目所有者的分发授权范围限定为官方 `@anthropic-ai/claude-agent-sdk` 身份，以及每个 SDK 版本通过 `optionalDependencies` 声明的官方 Claude Code CLI 与平台载荷。[`THIRD_PARTY_NOTICES.md`](../../../../THIRD_PARTY_NOTICES.md) 会推导并披露当前载荷集合，但不会将其声明条款重新归类为宽松条款。版本、许可证字段和载荷集合发生变化时，仍须经过常规的依赖、锁文件、兼容性、条款和声明评审；无关的非宽松运行时包继续以默认拒绝方式失败。 @@ -76,7 +76,7 @@ Claude Code 证据会锁定 Agent SDK 0.3.220、Claude Code 2.1.220 与八个 SD **直接模型 HTTP、`codex exec` 或手写的 Claude CLI 协议。** 这些路径会绕过产品的官方可扩展集成接口，无法证明原生配置、工具、审批、结果语义或资源清理。每个提供方都改用相应的官方产品集成。 -**共享产品进程辅助包。** 现有 subagent 与子进程 seam 已负责围绕任务、结果、环境和进程树的全部共享职责。新辅助包无法删除任一私有产品适配器，只会造成责任重复，因此每个适配器都会直接调用现有 seam。 +**共享产品进程辅助包。** 现有 subagent 与子进程 seam 已负责围绕任务、结果、环境和 managed range 的全部共享职责。新辅助包无法删除任一私有产品适配器，只会造成责任重复，因此每个适配器都会直接调用现有 seam。 **面向模型的产品选择器。** 产品可用性、实例配置和身份验证属于部署事实。由 Profile 绑定的工具使各自的 schema 与提供方绑定保持明确，也避免在通用服务中添加动态选择状态。 @@ -88,7 +88,7 @@ Claude Code 证据会锁定 Agent SDK 0.3.220、Claude Code 2.1.220 与八个 SD ## 后果 -用户通过由 Profile 配置、并由官方产品集成支持的一次性工具进行委派。显式 Profile 安装与 host plane 提供方放置由[生产安装排除决策](../simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.zh.md)负责；命名实例身份与工具绑定由[命名实例决策](2026-08-18-product-subagent-named-instances.zh.md)负责；按 Preset 暴露工具以及默认前台且可选通用 Job 的调度方式由[产品一次性后台任务决策](2026-08-12-product-subagent-one-shot-background-tasks.zh.md)负责。本说明规定的提供方生命周期会保留原生设置与行为，而共享服务继续独占作业结算与进程树完全停稳的责任。 +用户通过由 Profile 配置、并由官方产品集成支持的一次性工具进行委派。显式 Profile 安装与 host plane 提供方放置由[生产安装排除决策](../simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.zh.md)负责；命名实例身份与工具绑定由[命名实例决策](2026-08-18-product-subagent-named-instances.zh.md)负责；按 Preset 暴露工具以及默认前台且可选通用 Job 的调度方式由[产品一次性后台任务决策](2026-08-12-product-subagent-one-shot-background-tasks.zh.md)负责。本说明规定的提供方生命周期会保留原生设置与行为，而共享服务继续独占作业结算与 managed-range 完全停稳的责任。 每次委派都要承担新建产品进程和独立模型上下文的开销。成功的产品载荷仍只有最终 assistant 文本；失败的产品运行可以另行公开共享安全诊断，其中包含由提供方拥有的权限事实，或锁定版本产品提供的结构化失败事实。后台调度还会额外公开通用 Job id、状态、完成通知以及收集或取消结果。两个产品都使用 Bundle 锁定的平台 CLI，并保留原生账户与工作区设置以及所选提供方权限模式。带密钥 e2e 运行还会消耗外部 API 配额，并依赖 DeepSeek 官方端点；对协议、失败、取消与审批的确定性覆盖仍由无密钥层级承担。提供方不会恢复会话、以流式方式传送进度、接受新的人工交互、回滚工具或文件副作用，也不会施加按实际经过时间触发的超时。 diff --git a/.agents/notes/implemented/feature/2026-08-12-product-subagent-one-shot-background-tasks.i18n.yaml b/.agents/notes/implemented/feature/2026-08-12-product-subagent-one-shot-background-tasks.i18n.yaml index 48455ab7b7..434fd6f19a 100644 --- a/.agents/notes/implemented/feature/2026-08-12-product-subagent-one-shot-background-tasks.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-12-product-subagent-one-shot-background-tasks.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-12-product-subagent-one-shot-background-tasks.md -2026-08-12-product-subagent-one-shot-background-tasks.md: 5e9522f6fac6eadb874ba2d1d4f45100f962b9e2 -2026-08-12-product-subagent-one-shot-background-tasks.zh.md: fdf7fa58e49f6aa9b6fe7a21eb21e6208e56a86f +2026-08-12-product-subagent-one-shot-background-tasks.md: 8fc35ad82d75114dccd39a1176996665d0c28376 +2026-08-12-product-subagent-one-shot-background-tasks.zh.md: 3c6bb848688f891b29a94683573f3479e50da6e2 diff --git a/.agents/notes/implemented/feature/2026-08-12-product-subagent-one-shot-background-tasks.md b/.agents/notes/implemented/feature/2026-08-12-product-subagent-one-shot-background-tasks.md index 5e9522f6fa..8fc35ad82d 100644 --- a/.agents/notes/implemented/feature/2026-08-12-product-subagent-one-shot-background-tasks.md +++ b/.agents/notes/implemented/feature/2026-08-12-product-subagent-one-shot-background-tasks.md @@ -16,7 +16,7 @@ Production `dsh` does not install the optional product providers. A Profile that The [named-instance decision](2026-08-18-product-subagent-named-instances.md) allows multiple rows for either product. Each additional host provider row has its own `providerName`, and each exposed preset tool row binds that exact name through `provider` while keeping a unique `toolName`; the foreground/background scheduling choice does not constrain the number of instances. -The [generic one-shot background adapter](2026-07-08-background-subagent-tasks.md) owns background registration and settlement. It starts the same [`SubagentRun`](2026-06-21-subagent-capability-seam.md), uses a Job-owned cancellation signal across provider startup and execution, waits for `run.result` and `run.dispose()`, maps the terminal result and optional safe diagnostic into the Job, and lets `job_output`, `job_list`, `job_kill`, and the existing completion notice expose that state. The [product provider decision](2026-08-04-claude-code-and-codex-subagent-backends.md) continues to own native protocols, answer selection, local cancellation, and process-tree quiescence; the [non-interactive permissions decision](2026-08-15-product-subagent-noninteractive-permissions.md) owns each product Provider's Profile configuration and diagnostic production. +The [generic one-shot background adapter](2026-07-08-background-subagent-tasks.md) owns background registration and settlement. It starts the same [`SubagentRun`](2026-06-21-subagent-capability-seam.md), uses a Job-owned cancellation signal across provider startup and execution, waits for `run.result` and `run.dispose()`, maps the terminal result and optional safe diagnostic into the Job, and lets `job_output`, `job_list`, `job_kill`, and the existing completion notice expose that state. The [product provider decision](2026-08-04-claude-code-and-codex-subagent-backends.md) continues to own native protocols, answer selection, local cancellation, and managed-range quiescence; the [non-interactive permissions decision](2026-08-15-product-subagent-noninteractive-permissions.md) owns each product Provider's Profile configuration and diagnostic production. This scheduling decision adds no provider configuration, service interface, event, wire field, persistence format, or product identifier. A Provider may define its own Profile configuration independently; foreground and background still differ only in which existing consumer waits for the same one-shot run. @@ -39,7 +39,7 @@ product tool call | Product selection and exposure | Agent Preset | Bind one fixed tool name to one fixed provider | Enabling one row exposes only that product tool | | Foreground or background choice | `dsh-tool-subagent` | Resolve `run_in_background` under `one-shot` policy | Omission is foreground; explicit `true` returns a Job id | | Job id, state, output, cancellation, and notice | `ctx.jobs` and `dsh-tool-jobs` | Register and present the existing one-shot run | Generic job tools collect or stop the run for the exact parent | -| Native result, optional diagnostic, and process quiescence | Product provider and `dsh-subprocess` | Produce one final result and release one process tree | Job settlement and foreground return consume the same result and both wait for disposal | +| Native result, optional diagnostic, and process quiescence | Product provider and `dsh-subprocess` | Produce one final result and release one managed range | Job settlement and foreground return consume the same result and both wait for disposal | ## Published composition @@ -69,4 +69,4 @@ The Web composition test explicitly mounts both optional providers from the repo Agents can continue useful work while Codex or Claude Code handles an independent one-shot task, then collect the final answer or cancel it through the same Job controls used by other background producers. Foreground and one-shot background consumers present the same safe Provider diagnostic when a failed result supplies one. -Every product delegation still starts a fresh native process or query, produces final assistant text as its only assistant payload, and ends with provider disposal and whole-tree exit. A failed result may separately carry a safe diagnostic. A background call additionally exposes the generic Job id, status, completion notice, and collection or cancellation results. Background Jobs are process-local and parent-owned: they do not survive parent disposal, do not expose intermediate product activity, and do not make a product conversation resumable. Production installs do not pay for either product integration unless a Profile explicitly installs it; any composition that exposes the background argument must also keep the generic Job provider and controls available. +Every product delegation still starts a fresh native process or query, produces final assistant text as its only assistant payload, and ends with provider disposal and managed-range exit. A failed result may separately carry a safe diagnostic. A background call additionally exposes the generic Job id, status, completion notice, and collection or cancellation results. Background Jobs are process-local and parent-owned: they do not survive parent disposal, do not expose intermediate product activity, and do not make a product conversation resumable. Production installs do not pay for either product integration unless a Profile explicitly installs it; any composition that exposes the background argument must also keep the generic Job provider and controls available. diff --git a/.agents/notes/implemented/feature/2026-08-12-product-subagent-one-shot-background-tasks.zh.md b/.agents/notes/implemented/feature/2026-08-12-product-subagent-one-shot-background-tasks.zh.md index fdf7fa58e4..3c6bb84868 100644 --- a/.agents/notes/implemented/feature/2026-08-12-product-subagent-one-shot-background-tasks.zh.md +++ b/.agents/notes/implemented/feature/2026-08-12-product-subagent-one-shot-background-tasks.zh.md @@ -16,7 +16,7 @@ Codex 与 Claude Code 提供方已经能够运行一项自包含任务并返回 [命名实例决策](2026-08-18-product-subagent-named-instances.zh.md)允许两个产品分别拥有多个配置项。每个新增宿主提供方配置项都有独立的 `providerName`，每个公开的 preset 工具配置项都通过 `provider` 绑定该名称并保持唯一的 `toolName`；前台或后台调度选择不会限制实例数量。 -[通用 one-shot 后台适配器](2026-07-08-background-subagent-tasks.zh.md)负责后台登记与结算。它会启动同一个 [`SubagentRun`](2026-06-21-subagent-capability-seam.zh.md)，让 Job 自有的取消信号覆盖提供方启动与执行，等待 `run.result` 和 `run.dispose()`，把终态结果与可选安全诊断映射进 Job，并由 `job_output`、`job_list`、`job_kill` 与现有完成通知公开该状态。[产品提供方决策](2026-08-04-claude-code-and-codex-subagent-backends.zh.md)继续负责原生协议、答案选择、本地取消与进程树完全停稳；[非交互权限决策](2026-08-15-product-subagent-noninteractive-permissions.zh.md)负责各产品提供方的 Profile 配置与诊断生产。 +[通用 one-shot 后台适配器](2026-07-08-background-subagent-tasks.zh.md)负责后台登记与结算。它会启动同一个 [`SubagentRun`](2026-06-21-subagent-capability-seam.zh.md)，让 Job 自有的取消信号覆盖提供方启动与执行，等待 `run.result` 和 `run.dispose()`，把终态结果与可选安全诊断映射进 Job，并由 `job_output`、`job_list`、`job_kill` 与现有完成通知公开该状态。[产品提供方决策](2026-08-04-claude-code-and-codex-subagent-backends.zh.md)继续负责原生协议、答案选择、本地取消与 managed-range 完全停稳；[非交互权限决策](2026-08-15-product-subagent-noninteractive-permissions.zh.md)负责各产品提供方的 Profile 配置与诊断生产。 本调度决策不新增提供方配置、服务接口、事件、协议字段、持久化格式或产品标识符。提供方可以独立定义自己的 Profile 配置；前台与后台的区别仍然只在于由哪个现有消费方等待同一个 one-shot 运行。 @@ -39,7 +39,7 @@ product tool call | 产品选择与公开 | Agent Preset | 把一个固定工具名绑定到一个固定提供方 | 启用一行只会公开对应产品工具 | | 前台或后台选择 | `dsh-tool-subagent` | 按 `one-shot` 策略解析 `run_in_background` | 省略参数时在前台运行；显式传入 `true` 时返回 Job id | | Job id、状态、输出、取消与通知 | `ctx.jobs` 与 `dsh-tool-jobs` | 登记并展示现有 one-shot 运行 | 通用作业工具为准确父级收集或停止运行 | -| 原生结果、可选诊断与进程完全停稳 | 产品提供方与 `dsh-subprocess` | 产生一个最终结果并释放一棵进程树 | Job 结算与前台返回消费同一结果，且都会等待资源释放 | +| 原生结果、可选诊断与进程完全停稳 | 产品提供方与 `dsh-subprocess` | 产生一个最终结果并释放一个 managed range | Job 结算与前台返回消费同一结果，且都会等待资源释放 | ## 发布组装 @@ -69,4 +69,4 @@ Web 组装测试会从仓库 examples 依赖锚点显式挂载两个可选提供 agent 可以在 Codex 或 Claude Code 处理独立 one-shot 任务时继续推进其他工作，随后通过其他后台 producer 共用的 Job 控制工具收集最终回答或取消运行。若失败结果提供了安全的提供方诊断，前台与一次性后台消费方会呈现同一内容。 -每次产品委托仍会启动一个全新的原生进程或 query，把最终 assistant 文本作为唯一 assistant 载荷，并以提供方资源释放和整棵进程树退出结束。失败结果可以另行携带安全诊断。后台调用还会额外公开通用 Job id、状态、完成通知以及收集或取消结果。后台 Job 仅存在于当前进程且由父级拥有：它不会在父级资源释放后继续存活，不会公开产品中间活动，也不会让产品对话变得可恢复。只有 Profile 显式安装产品集成时，生产安装才承担对应成本；公开后台参数的任何组装还必须让通用 Job 提供方与控制工具保持可用。 +每次产品委托仍会启动一个全新的原生进程或 query，把最终 assistant 文本作为唯一 assistant 载荷，并以提供方资源释放和 managed-range 退出结束。失败结果可以另行携带安全诊断。后台调用还会额外公开通用 Job id、状态、完成通知以及收集或取消结果。后台 Job 仅存在于当前进程且由父级拥有：它不会在父级资源释放后继续存活，不会公开产品中间活动，也不会让产品对话变得可恢复。只有 Profile 显式安装产品集成时，生产安装才承担对应成本；公开后台参数的任何组装还必须让通用 Job 提供方与控制工具保持可用。 diff --git a/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.i18n.yaml b/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.i18n.yaml index 89bfdef747..44f4718609 100644 --- a/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.md -2026-08-15-product-subagent-noninteractive-permissions.md: 8788fba3492e08090dd038fc3e7377f6bd1e29cd -2026-08-15-product-subagent-noninteractive-permissions.zh.md: cbf3c3cd14fcecd2c24e335a8b71cc3b5370e247 +2026-08-15-product-subagent-noninteractive-permissions.md: aa69d1a296f55df01db2632b105511d24ad6b067 +2026-08-15-product-subagent-noninteractive-permissions.zh.md: 8525969f189dcb74dec55d19fc869c47f3a1e992 diff --git a/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.md b/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.md index 8788fba349..aa69d1a296 100644 --- a/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.md +++ b/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.md @@ -59,11 +59,11 @@ The foreground consumer presents the stop-reason headline, then the optional dia | Interaction decisions and safe diagnostic | One product run | Concurrent runs keep independent mode, protocol, and diagnostic state. | | Diagnostic type and byte limit | `dsh-subagent` | Consumers receive a bounded optional field separate from assistant output. | | Foreground and Job presentation | `dsh-tool-subagent` and the generic Job runtime | Scheduling choice does not change the underlying failure fact. | -| Process cancellation and quiescence | Product Provider and `dsh-subprocess` | Result settlement still precedes idempotent whole-tree disposal. | +| Process cancellation and quiescence | Product Provider and `dsh-subprocess` | Result settlement still precedes idempotent managed-range disposal. | ## Verification -Package tests pin every allowed and rejected Config value, the exact SDK and app-server field mappings, dangerous confirmations, unattended terminal responses, diagnostic sanitization and UTF-8 bound, successful-result omission, concurrent-run isolation, foreground ordering, Job detail, stderr observer disposal, and process cleanup. The real Claude Agent SDK/CLI fixture proves its safe default, restricted denial, explicit bypass, and whole-tree quiescence. The real Codex app-server fixture proves that thread-level `never` overrides ambient `on-request`, automatic review starts, dangerous bypass writes only inside suite-owned temporary storage, fixed stderr signatures produce safe diagnostics, and the wrapper/native tree exits. Loader composition proves non-default modes can be published without starting either product, and the keyless ACP snapshot records each product's failure diagnostic through foreground and Job presentation while the model-facing product tool schemas contain no permission parameter. +Package tests pin every allowed and rejected Config value, the exact SDK and app-server field mappings, dangerous confirmations, unattended terminal responses, diagnostic sanitization and UTF-8 bound, successful-result omission, concurrent-run isolation, foreground ordering, Job detail, stderr observer disposal, and process cleanup. The real Claude Agent SDK/CLI fixture proves its safe default, restricted denial, explicit bypass, and managed-range quiescence. The real Codex app-server fixture proves that thread-level `never` overrides ambient `on-request`, automatic review starts, dangerous bypass writes only inside suite-owned temporary storage, fixed stderr signatures produce safe diagnostics, and the wrapper/native managed range exits. Loader composition proves non-default modes can be published without starting either product, and the keyless ACP snapshot records each product's failure diagnostic through foreground and Job presentation while the model-facing product tool schemas contain no permission parameter. ## Alternatives considered diff --git a/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.zh.md b/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.zh.md index cbf3c3cd14..8525969f18 100644 --- a/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.zh.md +++ b/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.zh.md @@ -59,11 +59,11 @@ Codex 默认使用 `never`，并接受 Codex 0.147.0 公开的三种原生非交 | 交互决定与安全诊断 | 单次产品运行 | 并发运行分别拥有独立的模式、协议与诊断状态。 | | 诊断类型与字节上限 | `dsh-subagent` | 消费方收到与 assistant 输出分离的有界可选字段。 | | 前台与 Job 呈现 | `dsh-tool-subagent` 和通用 Job 运行时 | 调度选择不会改变底层失败事实。 | -| 进程取消与完全停稳 | 产品提供方和 `dsh-subprocess` | 结果结算后仍执行幂等的完整进程树资源释放。 | +| 进程取消与完全停稳 | 产品提供方和 `dsh-subprocess` | 结果结算后仍执行幂等的 managed-range 资源释放。 | ## Verification -包测试固定所有允许与拒绝的 Config 值、准确的 SDK 与 app-server 字段映射、危险确认、无人值守终态、诊断脱敏与 UTF-8 上限、成功结果不携带诊断、并发运行隔离、前台顺序、Job detail、stderr observer 释放和进程清理。真实 Claude Agent SDK/CLI fixture 证明其安全默认、受限拒绝、显式 bypass 与整棵进程树完全停稳。真实 Codex app-server fixture 证明线程级 `never` 覆盖环境中的 `on-request`、自动评审可以启动、危险绕过只在测试拥有的临时存储中写入、固定 stderr 签名产生安全诊断，而且 wrapper／native 进程树会退出。Loader 组装证明非默认模式可以在不启动任一产品的情况下发布；无密钥 ACP snapshot 则记录每个产品的失败诊断如何经过前台与 Job 呈现，同时面向模型的产品工具 schema 不包含权限参数。 +包测试固定所有允许与拒绝的 Config 值、准确的 SDK 与 app-server 字段映射、危险确认、无人值守终态、诊断脱敏与 UTF-8 上限、成功结果不携带诊断、并发运行隔离、前台顺序、Job detail、stderr observer 释放和进程清理。真实 Claude Agent SDK/CLI fixture 证明其安全默认、受限拒绝、显式 bypass 与 managed-range 完全停稳。真实 Codex app-server fixture 证明线程级 `never` 覆盖环境中的 `on-request`、自动评审可以启动、危险绕过只在测试拥有的临时存储中写入、固定 stderr 签名产生安全诊断，而且 wrapper／native managed range 会退出。Loader 组装证明非默认模式可以在不启动任一产品的情况下发布；无密钥 ACP snapshot 则记录每个产品的失败诊断如何经过前台与 Job 呈现，同时面向模型的产品工具 schema 不包含权限参数。 ## Alternatives considered diff --git a/.agents/notes/implemented/feature/2026-08-18-product-subagent-failure-facts.i18n.yaml b/.agents/notes/implemented/feature/2026-08-18-product-subagent-failure-facts.i18n.yaml index dca365d854..2bace94aa2 100644 --- a/.agents/notes/implemented/feature/2026-08-18-product-subagent-failure-facts.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-18-product-subagent-failure-facts.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-18-product-subagent-failure-facts.md -2026-08-18-product-subagent-failure-facts.md: 50d8e918f288a6b8a9b90474499b2ed20731643f -2026-08-18-product-subagent-failure-facts.zh.md: abdbf8c0ebddb1fb30cef3c7e80fcf7040e45d2d +2026-08-18-product-subagent-failure-facts.md: 79947c57a267b23e9f73dd595ebf89e209fed066 +2026-08-18-product-subagent-failure-facts.zh.md: 01a88322081b048ee1bf044ffb40ad16e88a1693 diff --git a/.agents/notes/implemented/feature/2026-08-18-product-subagent-failure-facts.md b/.agents/notes/implemented/feature/2026-08-18-product-subagent-failure-facts.md index 50d8e918f2..79947c57a2 100644 --- a/.agents/notes/implemented/feature/2026-08-18-product-subagent-failure-facts.md +++ b/.agents/notes/implemented/feature/2026-08-18-product-subagent-failure-facts.md @@ -35,7 +35,7 @@ Agent SDK 0.3.220 defines four error subtypes: `error_during_execution`, `error_ | `query-start` | SDK query construction, native platform-payload startup, and unpublished rollback | `start()` rejects with fixed safe facts and any process outcome observed before rollback | | `query-run` | Published SDK message iteration and strict terminal-result validation | The run resolves as `error` with the exact known subtype or a fixed result category | | `process` | Managed CLI exits before the SDK supplies a terminal result | The run resolves as `error` with `process-exit` and the available exit code and signal | -| `teardown` | Query close and managed process-tree release | `dispose()` rejects independently with fixed safe facts after cleanup still reaches its final exit wait | +| `teardown` | Query close and managed-range release | `dispose()` rejects independently with fixed safe facts after cleanup still reaches its final exit wait | ### Codex facts @@ -48,7 +48,7 @@ Codex app-server 0.147.0 defines eleven string categories and five object varian | `turn-start` | Published `turn/start` request, provisional ids, and early frames | The run resolves as `error` with a safe unknown fallback when no structured category exists | | `turn` | Terminal notification, final-answer selection, and error-info mapping | The complete category and optional HTTP status reach the non-completed result | | `process` | Managed app-server exits before another terminal path settles | The run resolves as `error` with `process-exit` and any available code and signal | -| `teardown` | Wire close and process-tree release | `dispose()` rejects independently; startup rollback aggregation exposes both startup and teardown lines | +| `teardown` | Wire close and managed-range release | `dispose()` rejects independently; startup rollback aggregation exposes both startup and teardown lines | `contextWindowExceeded` remains `max-tokens`; every other known or unknown Codex category remains `error`, and `cyberPolicy` does not become `refusal`. @@ -64,7 +64,7 @@ Codex app-server 0.147.0 defines eleven string categories and five object varian ## Verification -Claude Code package tests pin all four SDK subtypes, invalid success, missing result, unknown values and exceptions, all four stages, independent exit code and signal fields, permission-fact ordering, sanitization, successful-result and cancellation omission, concurrent-run isolation, and cleanup completion. Codex package tests pin all sixteen error-info variants, HTTP status presence and absence, all six stages, unknown fallback, stop-reason preservation, permission ordering, sanitization, cancellation, concurrency, and cleanup aggregation. The real SDK/CLI fixture produces an actual Claude `error_max_turns`; the real app-server fixture produces an actual Codex `internalServerError`; both fixtures cover process/protocol failure and whole-tree quiescence. The keyless ACP snapshot records each product's exact diagnostic in foreground error output, a background completion notice, and `job_output`. +Claude Code package tests pin all four SDK subtypes, invalid success, missing result, unknown values and exceptions, all four stages, independent exit code and signal fields, permission-fact ordering, sanitization, successful-result and cancellation omission, concurrent-run isolation, and cleanup completion. Codex package tests pin all sixteen error-info variants, HTTP status presence and absence, all six stages, unknown fallback, stop-reason preservation, permission ordering, sanitization, cancellation, concurrency, and cleanup aggregation. The real SDK/CLI fixture produces an actual Claude `error_max_turns`; the real app-server fixture produces an actual Codex `internalServerError`; both fixtures cover process/protocol failure and managed-range quiescence. The keyless ACP snapshot records each product's exact diagnostic in foreground error output, a background completion notice, and `job_output`. ## Alternatives considered diff --git a/.agents/notes/implemented/feature/2026-08-18-product-subagent-failure-facts.zh.md b/.agents/notes/implemented/feature/2026-08-18-product-subagent-failure-facts.zh.md index abdbf8c0eb..01a8832208 100644 --- a/.agents/notes/implemented/feature/2026-08-18-product-subagent-failure-facts.zh.md +++ b/.agents/notes/implemented/feature/2026-08-18-product-subagent-failure-facts.zh.md @@ -35,7 +35,7 @@ Agent SDK 0.3.220 定义四种错误子类型：`error_during_execution`、`erro | `query-start` | SDK query 构造、原生平台载荷启动与未发布回滚 | `start()` 以固定安全事实和回滚前已观测到的进程结果拒绝 | | `query-run` | 已发布 SDK 消息迭代与严格终态结果校验 | 运行以 `error` 兑现，并携带准确已知子类型或固定结果类别 | | `process` | SDK 提供终态结果之前受管 CLI 已退出 | 运行以 `error` 兑现，并携带 `process-exit` 以及可用的退出码和信号 | -| `teardown` | Query 关闭与受管进程树释放 | `dispose()` 独立拒绝并携带固定安全事实，同时清理仍会完成最终退出等待 | +| `teardown` | Query 关闭与 managed-range 释放 | `dispose()` 独立拒绝并携带固定安全事实，同时清理仍会完成最终退出等待 | ### Codex 事实 @@ -48,7 +48,7 @@ Codex app-server 0.147.0 定义十一种字符串类别与五种对象 variant | `turn-start` | 已发布 `turn/start` 请求、暂定 id 与早到 frame | 没有结构化类别时，运行以 `error` 和安全 unknown 回退兑现 | | `turn` | 终态通知、最终答案选择与 error-info 映射 | 完整类别与可选 HTTP status 进入非完成结果 | | `process` | 受管 app-server 在另一终态路径结算前退出 | 运行以 `error` 兑现，并携带 `process-exit` 以及可用的退出码与信号 | -| `teardown` | Wire 关闭与进程树释放 | `dispose()` 独立拒绝；启动回滚聚合会同时公开启动与 teardown 两行 | +| `teardown` | Wire 关闭与 managed-range 释放 | `dispose()` 独立拒绝；启动回滚聚合会同时公开启动与 teardown 两行 | `contextWindowExceeded` 仍是 `max-tokens`；其他所有已知或未知 Codex 类别仍是 `error`，`cyberPolicy` 不会变成 `refusal`。 @@ -64,7 +64,7 @@ Codex app-server 0.147.0 定义十一种字符串类别与五种对象 variant ## Verification -Claude Code 包测试固定四种 SDK 子类型、无效成功、缺失结果、未知值与异常、四个阶段、相互独立的退出码与信号字段、权限事实顺序、脱敏、成功结果与取消时省略诊断、并发运行隔离和清理完成。Codex 包测试固定全部十六种 error-info variant、HTTP status 存在与缺失、六个阶段、unknown 回退、终止原因保持不变、权限顺序、脱敏、取消、并发与清理聚合。真实 SDK/CLI fixture 会产生真实的 Claude `error_max_turns`，真实 app-server fixture 会产生真实的 Codex `internalServerError`；两个 fixture 都覆盖进程／协议失败与整棵进程树完全停稳。无密钥 ACP snapshot 会在前台错误输出、后台完成通知和 `job_output` 中记录两个产品各自的准确诊断。 +Claude Code 包测试固定四种 SDK 子类型、无效成功、缺失结果、未知值与异常、四个阶段、相互独立的退出码与信号字段、权限事实顺序、脱敏、成功结果与取消时省略诊断、并发运行隔离和清理完成。Codex 包测试固定全部十六种 error-info variant、HTTP status 存在与缺失、六个阶段、unknown 回退、终止原因保持不变、权限顺序、脱敏、取消、并发与清理聚合。真实 SDK/CLI fixture 会产生真实的 Claude `error_max_turns`，真实 app-server fixture 会产生真实的 Codex `internalServerError`；两个 fixture 都覆盖进程／协议失败与 managed-range 完全停稳。无密钥 ACP snapshot 会在前台错误输出、后台完成通知和 `job_output` 中记录两个产品各自的准确诊断。 ## Alternatives considered diff --git a/.agents/notes/implemented/feature/2026-08-18-product-subagent-named-instances.i18n.yaml b/.agents/notes/implemented/feature/2026-08-18-product-subagent-named-instances.i18n.yaml index 614f036a6a..2387488610 100644 --- a/.agents/notes/implemented/feature/2026-08-18-product-subagent-named-instances.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-18-product-subagent-named-instances.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-18-product-subagent-named-instances.md -2026-08-18-product-subagent-named-instances.md: 759d3941ff8404138954c409f0fd4949e357200e -2026-08-18-product-subagent-named-instances.zh.md: 6faf0e70f639cbc6528e27b800b8e5f99f0d6c86 +2026-08-18-product-subagent-named-instances.md: 997c555699e8de8c47be9a68bea729a596dbda10 +2026-08-18-product-subagent-named-instances.zh.md: 96b2bc34c082bbc372e7af43f86b1ee76289e83e diff --git a/.agents/notes/implemented/feature/2026-08-18-product-subagent-named-instances.md b/.agents/notes/implemented/feature/2026-08-18-product-subagent-named-instances.md index 759d3941ff..997c555699 100644 --- a/.agents/notes/implemented/feature/2026-08-18-product-subagent-named-instances.md +++ b/.agents/notes/implemented/feature/2026-08-18-product-subagent-named-instances.md @@ -29,7 +29,7 @@ Removing one provider row blocks new starts and removes only tools bound to that ## Verification -Both product packages pin their default and custom names, empty-name rejection, duplicate rollback, actual-name diagnostics, two concurrent instances with different permission modes, environments, and cleanup grace, cancellation isolation, and removal of one instance while its published run remains valid. The official product loopback tests run two named instances in one Host against separate model fixtures and prove independent unload and process-tree quiescence. Public Loader compositions mount two rows and two distinct tools for each product without starting either product, while keyless ACP snapshots pin the four-tool combined roster and the absence of a dynamic provider parameter. +Both product packages pin their default and custom names, empty-name rejection, duplicate rollback, actual-name diagnostics, two concurrent instances with different permission modes, environments, and cleanup grace, cancellation isolation, and removal of one instance while its published run remains valid. The official product loopback tests run two named instances in one Host against separate model fixtures and prove independent unload and managed-range quiescence. Public Loader compositions mount two rows and two distinct tools for each product without starting either product, while keyless ACP snapshots pin the four-tool combined roster and the absence of a dynamic provider parameter. ## Alternatives considered diff --git a/.agents/notes/implemented/feature/2026-08-18-product-subagent-named-instances.zh.md b/.agents/notes/implemented/feature/2026-08-18-product-subagent-named-instances.zh.md index 6faf0e70f6..96b2bc34c0 100644 --- a/.agents/notes/implemented/feature/2026-08-18-product-subagent-named-instances.zh.md +++ b/.agents/notes/implemented/feature/2026-08-18-product-subagent-named-instances.zh.md @@ -29,7 +29,7 @@ Profile 可以用多个配置项挂载同一个 Cordis 插件包，但 Codex 与 ## 验证 -两个产品包测试都会固定默认与自定义名称、空名称拒绝、重复注册回滚、实际名称诊断、使用不同权限模式、环境与清理宽限期的两个并发实例、取消隔离，以及移除一个实例后其已发布运行仍然有效。官方产品回环测试会在同一个 Host 中针对独立模型 fixture（测试前置数据）运行两个命名实例，并证明独立卸载与进程树完全停稳。公共 Loader 组合会为每个产品挂载两个配置项与两个不同工具，而且不启动任一产品；无密钥 ACP 快照固定最终四工具组合，并证明没有动态提供方参数。 +两个产品包测试都会固定默认与自定义名称、空名称拒绝、重复注册回滚、实际名称诊断、使用不同权限模式、环境与清理宽限期的两个并发实例、取消隔离，以及移除一个实例后其已发布运行仍然有效。官方产品回环测试会在同一个 Host 中针对独立模型 fixture（测试前置数据）运行两个命名实例，并证明独立卸载与 managed-range 完全停稳。公共 Loader 组合会为每个产品挂载两个配置项与两个不同工具，而且不启动任一产品；无密钥 ACP 快照固定最终四工具组合，并证明没有动态提供方参数。 ## 考虑过的替代方案 diff --git a/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.i18n.yaml b/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.i18n.yaml index 5fb38dbf24..5338856f63 100644 --- a/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.i18n.yaml +++ b/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.md -2026-08-08-native-windows-pull-request-ci.md: d4883cf1363a33a444f1172829149c0c41f21c10 -2026-08-08-native-windows-pull-request-ci.zh.md: 0ba9629e873d82aba33a2cbad9e46e264ffe4312 +2026-08-08-native-windows-pull-request-ci.md: 8c3e7b0788a8816143b15aad148eb927e66297d0 +2026-08-08-native-windows-pull-request-ci.zh.md: 57fa551291adde0c98eb198b344aef85186f7b7e diff --git a/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.md b/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.md index d4883cf136..8c3e7b0788 100644 --- a/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.md +++ b/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.md @@ -32,7 +32,7 @@ Windows durable JSONL paths keep drive roots in native spelling and apply the ex Post-boot profile watcher setup proceeds only while the root fiber and Loader are both live. A concurrent setup error is contained only when the same invocation's recorded signal already owns shutdown; unrelated HMR failures remain loud. The [process-shutdown controller](../bug-fix/2026-08-03-cli-signal-shutdown-escalation.md) lets a successful one-shot completion drain Node's remaining handles after root disposal, while teardown failure, deadline, and signal escalation retain forced exit. The vendored Include serializes debounced writes, retries only transient access or busy failures with bounded backoff, and observes every timer rejection. A terminal persistence failure remains on the queue and is rethrown to the teardown owner, while successful teardown drains the latest write. -Shiki disables lazy TextMate-regex compilation and warms each boot grammar before user content enters the unchanged per-line tokenization budget, so scheduler contention cannot publish a partial highlighted stream. The Codex real-product fixture is pinned to stable 0.147.0 schemas and selects an actually advertised command tool and argument shape, preserving the provider-owned protocol while proving unattended rejection and whole-tree exit on each host. +Shiki disables lazy TextMate-regex compilation and warms each boot grammar before user content enters the unchanged per-line tokenization budget, so scheduler contention cannot publish a partial highlighted stream. The Codex real-product fixture is pinned to stable 0.147.0 schemas and selects an actually advertised command tool and argument shape, preserving the provider-owned protocol while proving unattended rejection and managed-range exit on each host. ## Alternatives considered diff --git a/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.zh.md b/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.zh.md index 0ba9629e87..57fa551291 100644 --- a/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.zh.md +++ b/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.zh.md @@ -32,7 +32,7 @@ Windows 的持久 JSONL 路径会保留驱动器根目录的原生写法，并 启动后，只有根 fiber 与 Loader 均处于活跃状态时，系统才会继续设置 profile watcher。只有当同一次调用所记录的信号已取得关闭流程所有权时，系统才会隔离并发设置错误；无关 HMR 故障仍会响亮失败。[进程关闭控制器](../bug-fix/2026-08-03-cli-signal-shutdown-escalation.zh.md)会在根级 dispose 成功后让单次任务的正常完成流程排空 Node 剩余句柄，同时让拆卸失败、截止时间到期和信号升级继续强制退出。vendored Include 会串行化防抖写入，只对瞬时访问或忙碌故障执行有界退避重试，并确保每个由计时器触发的拒绝都得到观察。持久化最终失败后，该故障会保留在队列中，并重新抛给拆卸责任方；成功拆卸则会排空最新写入。 -Shiki 会禁用 TextMate 正则的延迟编译，并在用户内容进入保持不变的逐行 tokenization（词元化）预算前预热每种启动语法，从而避免调度器争用发布不完整的高亮流。Codex 真实产品 fixture 固定使用稳定版 0.147.0 schema，并选择实际提供的命令工具与对应参数形态；这样既保留由提供方负责的协议，也能在每种宿主上证明无人值守拒绝和整棵进程树退出。 +Shiki 会禁用 TextMate 正则的延迟编译，并在用户内容进入保持不变的逐行 tokenization（词元化）预算前预热每种启动语法，从而避免调度器争用发布不完整的高亮流。Codex 真实产品 fixture 固定使用稳定版 0.147.0 schema，并选择实际提供的命令工具与对应参数形态；这样既保留由提供方负责的协议，也能在每种宿主上证明无人值守拒绝和 managed-range 退出。 ## 曾考虑的替代方案 diff --git a/AGENTS.md b/AGENTS.md index a66d6cdc54..2024b12749 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -17,7 +17,7 @@ packages/ @deepseek-ai/dsh- workspaces at packages/// llm/ LLM capability: Service Definition/Consumer + DeepSeek providers e2b/ E2B POC: sandbox + FS/subprocess adapters shell/ bash capability: Service Definition + local/pwsh providers + shell Consumers - subprocess/ subprocess capability + local process-tree provider + shared Win32 library + subprocess/ subprocess capability + local managed-range provider + shared Win32 library terminal/ persistent sessions fs/ filesystem capability + policy lsp/ language-server capability diff --git a/docs/capability-seams.i18n.yaml b/docs/capability-seams.i18n.yaml index dbafe8c766..55343b9635 100644 --- a/docs/capability-seams.i18n.yaml +++ b/docs/capability-seams.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write docs/capability-seams.md -capability-seams.md: 9e99ebbdc0e3af22f9939c690ead479d4d20b00c -capability-seams.zh.md: 611902310e3472e05eaa92985011eb852bbeee6d +capability-seams.md: 263e870061467b89961f7e7026e567962acbfdf4 +capability-seams.zh.md: d5def25b4dc5b6a3c6bba7b419c0512cf51552ea diff --git a/docs/capability-seams.md b/docs/capability-seams.md index 9e99ebbdc0..263e870061 100644 --- a/docs/capability-seams.md +++ b/docs/capability-seams.md @@ -460,7 +460,7 @@ flowchart LR | `ctx.agentLoop` | `bundle` | [`agent-loop`](../packages/core/agent-loop) | - | [`agent-spine-demo`](../packages/examples/agent-spine-demo) | - | The one concrete loop plugin; extension packages depend on dsh-agent events and services, not on this package. | | `ctx.goals` | `core` | [`goal`](../packages/goal/goal) | - | - | - | Folds revisioned objective state from the session log and keeps live continuation activation process-local. | | `ctx.e2b` | `core` | [`e2b`](../packages/e2b/e2b) | - | [`fs-e2b`](../packages/e2b/fs-e2b), [`subprocess-e2b`](../packages/e2b/subprocess-e2b) | - | Owns one shared E2B SDK handle, remote working directory, and final sandbox disposition so both fundamental E2B providers inhabit the same Linux runtime. | -| `ctx.subprocess` | `seam` | [`subprocess`](../packages/subprocess/subprocess) | [`subprocess-local`](../packages/subprocess/subprocess-local), [`subprocess-e2b`](../packages/e2b/subprocess-e2b) | [`bash-local`](../packages/shell/bash-local), [`bash-sandbox`](../packages/shell/bash-sandbox), [`terminal-bash`](../packages/terminal/terminal-bash), [`lsp-stdio`](../packages/lsp/lsp-stdio), [`subagent-acp`](../packages/subagent/subagent-acp), [`subagent-codex`](../packages/subagent/subagent-codex), [`subagent-claude-code`](../packages/subagent/subagent-claude-code) | - | The bash executors, the PTY shell backend, the LSP host, and the out-of-process ACP, Codex, and Claude Code subagent backends spawn through ctx.subprocess; the service owns process coordinates, tree/session lifetime, stdio dispositions, terminal mechanics, and kill escalation. | +| `ctx.subprocess` | `seam` | [`subprocess`](../packages/subprocess/subprocess) | [`subprocess-local`](../packages/subprocess/subprocess-local), [`subprocess-e2b`](../packages/e2b/subprocess-e2b) | [`bash-local`](../packages/shell/bash-local), [`bash-sandbox`](../packages/shell/bash-sandbox), [`terminal-bash`](../packages/terminal/terminal-bash), [`lsp-stdio`](../packages/lsp/lsp-stdio), [`subagent-acp`](../packages/subagent/subagent-acp), [`subagent-codex`](../packages/subagent/subagent-codex), [`subagent-claude-code`](../packages/subagent/subagent-claude-code) | - | The bash executors, the PTY shell backend, the LSP host, and the out-of-process ACP, Codex, and Claude Code subagent backends spawn through ctx.subprocess; the service owns process coordinates, managed-range/session lifetime, stdio dispositions, terminal mechanics, and provider-defined termination. | | `ctx.shell` | `seam` | [`shell`](../packages/shell/shell) | [`bash-local`](../packages/shell/bash-local), [`bash-sandbox`](../packages/shell/bash-sandbox), [`pwsh-local`](../packages/shell/pwsh-local) | [`tool-bash`](../packages/shell/tool-bash), [`tool-pwsh`](../packages/shell/tool-pwsh), [`hooks-claude-code`](../packages/hooks/hooks-claude-code), [`hooks-codex`](../packages/hooks/hooks-codex) | - | The model-facing shell tools and hook bridges consume this seam; sandboxed, remote, or PowerShell executors replace bash-local without touching them. | | `ctx.shellEnv` | `core` | [`shell-env`](../packages/shell/shell-env) | - | [`tool-bash`](../packages/shell/tool-bash), [`tool-pwsh`](../packages/shell/tool-pwsh) | - | Plugins declare effect-scoped DSH_* facts; each shell tool collects one trusted snapshot per execution and its executor rebuilds the namespace. | | `ctx.terminals` | `seam` | [`terminal`](../packages/terminal/terminal) | [`terminal-bash`](../packages/terminal/terminal-bash) | [`tool-terminal`](../packages/terminal/tool-terminal) | - | The registry owns exact-Agent session identity and cleanup; backends own terminal mechanics, while tool-terminal exposes the owner-scoped model tools. | diff --git a/docs/capability-seams.zh.md b/docs/capability-seams.zh.md index 611902310e..d5def25b4d 100644 --- a/docs/capability-seams.zh.md +++ b/docs/capability-seams.zh.md @@ -462,7 +462,7 @@ flowchart LR | `ctx.agentLoop` | `bundle` | [`agent-loop`](../packages/core/agent-loop) | - | [`agent-spine-demo`](../packages/examples/agent-spine-demo) | - | 唯一的具体循环插件；扩展包依赖 dsh-agent 的事件和服务，而不依赖此包。 | | `ctx.goals` | `core` | [`goal`](../packages/goal/goal) | - | - | - | 从会话日志折叠带修订版本的目标状态，并将实时延续激活保留在进程本地。 | | `ctx.e2b` | `core` | [`e2b`](../packages/e2b/e2b) | - | [`fs-e2b`](../packages/e2b/fs-e2b), [`subprocess-e2b`](../packages/e2b/subprocess-e2b) | - | 拥有一个共享的 E2B SDK 句柄、远程工作目录和最终沙箱处置，使两个基础 E2B 提供方处于同一个 Linux 运行时中。 | -| `ctx.subprocess` | `seam` | [`subprocess`](../packages/subprocess/subprocess) | [`subprocess-local`](../packages/subprocess/subprocess-local), [`subprocess-e2b`](../packages/e2b/subprocess-e2b) | [`bash-local`](../packages/shell/bash-local), [`bash-sandbox`](../packages/shell/bash-sandbox), [`terminal-bash`](../packages/terminal/terminal-bash), [`lsp-stdio`](../packages/lsp/lsp-stdio), [`subagent-acp`](../packages/subagent/subagent-acp), [`subagent-codex`](../packages/subagent/subagent-codex), [`subagent-claude-code`](../packages/subagent/subagent-claude-code) | - | Bash 执行器、PTY shell 后端、LSP Host，以及进程外 ACP、Codex 和 Claude Code subagent 后端都通过 ctx.subprocess 执行 spawn；该服务负责进程坐标、进程树／会话生命周期、stdio 处置、终端机制和 kill 升级。 | +| `ctx.subprocess` | `seam` | [`subprocess`](../packages/subprocess/subprocess) | [`subprocess-local`](../packages/subprocess/subprocess-local), [`subprocess-e2b`](../packages/e2b/subprocess-e2b) | [`bash-local`](../packages/shell/bash-local), [`bash-sandbox`](../packages/shell/bash-sandbox), [`terminal-bash`](../packages/terminal/terminal-bash), [`lsp-stdio`](../packages/lsp/lsp-stdio), [`subagent-acp`](../packages/subagent/subagent-acp), [`subagent-codex`](../packages/subagent/subagent-codex), [`subagent-claude-code`](../packages/subagent/subagent-claude-code) | - | Bash 执行器、PTY shell 后端、LSP Host，以及进程外 ACP、Codex 和 Claude Code subagent 后端都通过 ctx.subprocess 执行 spawn；该服务负责进程坐标、managed-range／session 生命周期、stdio 处置、终端机制和 provider-defined termination。 | | `ctx.shell` | `seam` | [`shell`](../packages/shell/shell) | [`bash-local`](../packages/shell/bash-local), [`bash-sandbox`](../packages/shell/bash-sandbox), [`pwsh-local`](../packages/shell/pwsh-local) | [`tool-bash`](../packages/shell/tool-bash), [`tool-pwsh`](../packages/shell/tool-pwsh), [`hooks-claude-code`](../packages/hooks/hooks-claude-code), [`hooks-codex`](../packages/hooks/hooks-codex) | - | 面向模型的 shell 工具和钩子桥接消费此 seam；沙箱、远程或 PowerShell 执行器可以替换 bash-local，而无需改动这些消费方。 | | `ctx.shellEnv` | `core` | [`shell-env`](../packages/shell/shell-env) | - | [`tool-bash`](../packages/shell/tool-bash), [`tool-pwsh`](../packages/shell/tool-pwsh) | - | 插件声明限定于 effect 作用域的 DSH_* 事实；每个 shell 工具在每次执行时收集一份可信快照，其执行器据此重建命名空间。 | | `ctx.terminals` | `seam` | [`terminal`](../packages/terminal/terminal) | [`terminal-bash`](../packages/terminal/terminal-bash) | [`tool-terminal`](../packages/terminal/tool-terminal) | - | 注册表负责精确到 Agent 的会话身份和清理；后端负责终端机制，tool-terminal 则提供限定于所有者作用域的模型接口。 | diff --git a/docs/config-catalog.i18n.yaml b/docs/config-catalog.i18n.yaml index 432da9e27f..a124170716 100644 --- a/docs/config-catalog.i18n.yaml +++ b/docs/config-catalog.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 docs/config-catalog.md -config-catalog.md: 3595bc650153be25a4156f103af4980c9452f4f0 -config-catalog.zh.md: 66f35350640d5fcea7c9cb90d65bf0878ac68806 +config-catalog.md: 879484a1f5b6641cd22eef0a95ff46228b8e6d14 +config-catalog.zh.md: 65c9e1f9041d30e0e0ace6ef2da8fe999a60cc7f diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 3595bc6501..879484a1f5 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -361,7 +361,7 @@ export interface Config { maxOutputBytes?: number /** Per-stream spill-file cap; larger streams retain only their in-memory tail. */ maxSpillBytes?: number - /** Grace period for kill escalation and inherited pipes; at most `MAX_TIMER_DELAY_MS`. */ + /** Grace for subprocess termination and inherited-pipe draining; at most `MAX_TIMER_DELAY_MS`. */ graceMs?: number } ``` @@ -1323,9 +1323,9 @@ export interface LspLocalServerConfig { maxStderrBytes?: number /** Largest source file this host will open (bytes). Default 4000000. */ maxDocumentBytes?: number - /** Graceful `shutdown`/`exit` budget before escalation (ms). Default 5000. */ + /** Graceful `shutdown`/`exit` budget before provider termination (ms). Default 5000. */ shutdownTimeoutMs?: number - /** Request-cancel and SIGTERM→SIGKILL grace (ms). Default 2000. */ + /** Grace supplied to subprocess termination and output draining (ms). Default 2000. */ killGraceMs?: number } ``` @@ -1520,7 +1520,7 @@ export interface Config { maxOutputBytes?: number /** Per-stream spill-file cap; larger streams retain only their in-memory tail. */ maxSpillBytes?: number - /** Grace period for kill escalation and inherited pipes; at most `MAX_TIMER_DELAY_MS`. */ + /** Grace for subprocess termination and inherited-pipe draining; at most `MAX_TIMER_DELAY_MS`. */ graceMs?: number /** * Explicit pwsh executable. When omitted, well-known Windows install @@ -2171,11 +2171,11 @@ export interface Config { /** * Grace period (ms) for the child's EOF-driven quiesce on dispose — its * window to flush persistence and tear down its own nested subprocesses - * before the parent escalates to a signal. Must not exceed + * before the parent invokes provider termination. Must not exceed * `MAX_TIMER_DELAY_MS`. */ disposeEofGraceMs?: number - /** Termination-escalation grace (ms); must not exceed `MAX_TIMER_DELAY_MS`. */ + /** Grace for subprocess termination and output draining (ms); must not exceed `MAX_TIMER_DELAY_MS`. */ disposeGraceMs?: number } @@ -2208,7 +2208,7 @@ export interface Config { * `bypassPermissions` explicitly skips permission checks. */ permissionMode?: ClaudeCodePermissionMode - /** Grace in milliseconds for Claude Code process-tree termination. */ + /** Grace in milliseconds for Claude Code termination and output draining. */ disposeGraceMs?: number } @@ -2236,7 +2236,7 @@ export interface Config { env?: Record /** Native non-interactive permission mode fixed for this Provider instance. */ permissionMode?: CodexPermissionMode - /** Grace in milliseconds for app-server process-tree termination. */ + /** Grace in milliseconds for app-server termination and output draining. */ disposeGraceMs?: number } @@ -2553,7 +2553,7 @@ export interface Config { searchMetaMaxBytes?: number /** Max complete raw `rg` stdout bytes a search will parse; larger raw output fails with `SEARCH_RAW_OUTPUT_OVERFLOW`. */ rawOutputMaxBytes?: number - /** Terminate-escalation grace (ms), handed to the subprocess seam and bounded by `MAX_TIMER_DELAY_MS`. */ + /** Grace for subprocess termination and output draining (ms), bounded by `MAX_TIMER_DELAY_MS`. */ graceMs?: number /** Max bytes retained for one search's stderr tail; the excerpt is embedded in `SEARCH_*` error messages, never shown on success. */ stderrMaxBytes?: number diff --git a/docs/config-catalog.zh.md b/docs/config-catalog.zh.md index 66f3535064..65c9e1f904 100644 --- a/docs/config-catalog.zh.md +++ b/docs/config-catalog.zh.md @@ -363,7 +363,7 @@ export interface Config { maxOutputBytes?: number /** Per-stream spill-file cap; larger streams retain only their in-memory tail. */ maxSpillBytes?: number - /** Grace period for kill escalation and inherited pipes; at most `MAX_TIMER_DELAY_MS`. */ + /** Grace for subprocess termination and inherited-pipe draining; at most `MAX_TIMER_DELAY_MS`. */ graceMs?: number } ``` @@ -1325,9 +1325,9 @@ export interface LspLocalServerConfig { maxStderrBytes?: number /** Largest source file this host will open (bytes). Default 4000000. */ maxDocumentBytes?: number - /** Graceful `shutdown`/`exit` budget before escalation (ms). Default 5000. */ + /** Graceful `shutdown`/`exit` budget before provider termination (ms). Default 5000. */ shutdownTimeoutMs?: number - /** Request-cancel and SIGTERM→SIGKILL grace (ms). Default 2000. */ + /** Grace supplied to subprocess termination and output draining (ms). Default 2000. */ killGraceMs?: number } ``` @@ -1523,7 +1523,7 @@ export interface Config { maxOutputBytes?: number /** Per-stream spill-file cap; larger streams retain only their in-memory tail. */ maxSpillBytes?: number - /** Grace period for kill escalation and inherited pipes; at most `MAX_TIMER_DELAY_MS`. */ + /** Grace for subprocess termination and inherited-pipe draining; at most `MAX_TIMER_DELAY_MS`. */ graceMs?: number /** * Explicit pwsh executable. When omitted, well-known Windows install @@ -2174,11 +2174,11 @@ export interface Config { /** * Grace period (ms) for the child's EOF-driven quiesce on dispose — its * window to flush persistence and tear down its own nested subprocesses - * before the parent escalates to a signal. Must not exceed + * before the parent invokes provider termination. Must not exceed * `MAX_TIMER_DELAY_MS`. */ disposeEofGraceMs?: number - /** Termination-escalation grace (ms); must not exceed `MAX_TIMER_DELAY_MS`. */ + /** Grace for subprocess termination and output draining (ms); must not exceed `MAX_TIMER_DELAY_MS`. */ disposeGraceMs?: number } @@ -2211,7 +2211,7 @@ export interface Config { * `bypassPermissions` explicitly skips permission checks. */ permissionMode?: ClaudeCodePermissionMode - /** Grace in milliseconds for Claude Code process-tree termination. */ + /** Grace in milliseconds for Claude Code termination and output draining. */ disposeGraceMs?: number } @@ -2239,7 +2239,7 @@ export interface Config { env?: Record /** Native non-interactive permission mode fixed for this Provider instance. */ permissionMode?: CodexPermissionMode - /** Grace in milliseconds for app-server process-tree termination. */ + /** Grace in milliseconds for app-server termination and output draining. */ disposeGraceMs?: number } @@ -2556,7 +2556,7 @@ export interface Config { searchMetaMaxBytes?: number /** Max complete raw `rg` stdout bytes a search will parse; larger raw output fails with `SEARCH_RAW_OUTPUT_OVERFLOW`. */ rawOutputMaxBytes?: number - /** Terminate-escalation grace (ms), handed to the subprocess seam and bounded by `MAX_TIMER_DELAY_MS`. */ + /** Grace for subprocess termination and output draining (ms), bounded by `MAX_TIMER_DELAY_MS`. */ graceMs?: number /** Max bytes retained for one search's stderr tail; the excerpt is embedded in `SEARCH_*` error messages, never shown on success. */ stderrMaxBytes?: number diff --git a/docs/subsystems/subprocess.i18n.yaml b/docs/subsystems/subprocess.i18n.yaml index 8b51742982..8966af73e1 100644 --- a/docs/subsystems/subprocess.i18n.yaml +++ b/docs/subsystems/subprocess.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 docs/subsystems/subprocess.md -subprocess.md: 701d70629587c202c50047fb88158f39179920d1 -subprocess.zh.md: 643998ae0210e0fa2cdf8d5140809df07beaa27b +subprocess.md: 1cc704a30eeb7587c784886d31b7ca65e085ad93 +subprocess.zh.md: b861d99742956f5cf469851f8f78bd235706ebc8 diff --git a/docs/subsystems/subprocess.md b/docs/subsystems/subprocess.md index 701d706295..1cc704a30e 100644 --- a/docs/subsystems/subprocess.md +++ b/docs/subsystems/subprocess.md @@ -114,9 +114,9 @@ interface SubprocessSpawnSpec { */ graceMs: number /** - * Abort signal — starts the terminate escalation on the managed range when - * it fires. The caller owns deadlines and cause classification; this seam - * only reacts to the abort. + * Abort signal — starts the provider's termination procedure on the managed + * range when it fires. The caller owns deadlines and cause classification; + * this seam only reacts to the abort. */ signal?: AbortSignal | undefined /** @@ -284,7 +284,7 @@ Implementations must honor these semantics: - Executable paths belong to one execution world shared with the mounted filesystem provider. - spawn returns a live handle synchronously. Its pid is provider-owned and may remain unavailable during asynchronous startup. `done` resolves with the spawned command's exit facts and may reject for spawn or provider failures. - Collect-mode readers are offset-based and non-consuming, so independent readers never consume one another's output; lossy reads report truncation and the spill file holding the complete stream when one exists. Piped streams are handed to the caller raw and never buffered here. -- SubprocessHandle.terminate (and the spec's abort signal) starts the provider's documented procedure against its managed range. SubprocessHandle.waitForExit observes that same range so a consumer-owned teardown ladder can hold each tier on real quiescence; each provider documents its identity, signalling, and observability limits. +- SubprocessHandle.terminate (and the spec's abort signal) starts the provider's documented procedure against its managed range. SubprocessHandle.waitForExit observes that same range so consumer teardown can await real quiescence; each provider documents its identity, signalling, and observability limits. - Disposal of the service terminates all still-running managed processes and awaits their exit. - spawnTerminal owns terminal allocation, text transport, foreground groups, signalling, and whole-session quiescence behind one awaited termination method; readiness and persistent-shell policy stay in the PTY consumer. Its output stream ends after queued terminal output when the top-level process exits. diff --git a/docs/subsystems/subprocess.zh.md b/docs/subsystems/subprocess.zh.md index 643998ae02..b861d99742 100644 --- a/docs/subsystems/subprocess.zh.md +++ b/docs/subsystems/subprocess.zh.md @@ -114,9 +114,9 @@ interface SubprocessSpawnSpec { */ graceMs: number /** - * Abort signal — starts the terminate escalation on the managed range when - * it fires. The caller owns deadlines and cause classification; this seam - * only reacts to the abort. + * Abort signal — starts the provider's termination procedure on the managed + * range when it fires. The caller owns deadlines and cause classification; + * this seam only reacts to the abort. */ signal?: AbortSignal | undefined /** @@ -284,7 +284,7 @@ Implementations must honor these semantics: - Executable paths belong to one execution world shared with the mounted filesystem provider. - spawn returns a live handle synchronously. Its pid is provider-owned and may remain unavailable during asynchronous startup. `done` resolves with the spawned command's exit facts and may reject for spawn or provider failures. - Collect-mode readers are offset-based and non-consuming, so independent readers never consume one another's output; lossy reads report truncation and the spill file holding the complete stream when one exists. Piped streams are handed to the caller raw and never buffered here. -- SubprocessHandle.terminate (and the spec's abort signal) starts the provider's documented procedure against its managed range. SubprocessHandle.waitForExit observes that same range so a consumer-owned teardown ladder can hold each tier on real quiescence; each provider documents its identity, signalling, and observability limits. +- SubprocessHandle.terminate (and the spec's abort signal) starts the provider's documented procedure against its managed range. SubprocessHandle.waitForExit observes that same range so consumer teardown can await real quiescence; each provider documents its identity, signalling, and observability limits. - Disposal of the service terminates all still-running managed processes and awaits their exit. - spawnTerminal owns terminal allocation, text transport, foreground groups, signalling, and whole-session quiescence behind one awaited termination method; readiness and persistent-shell policy stay in the PTY consumer. Its output stream ends after queued terminal output when the top-level process exits. diff --git a/packages/README.i18n.yaml b/packages/README.i18n.yaml index 8129d42c0a..8697b9cfbb 100644 --- a/packages/README.i18n.yaml +++ b/packages/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/README.md -README.md: ad88e895cec423b71dbc3c0e961ddb8901e0f66d -README.zh.md: 81557ab3b9f3d7a00af6a5ad45a9e04cc7ea063b +README.md: 287e59a54dcd088894bcfe3946727169749220bd +README.zh.md: 6407754a10d1ca441df4c6138125efa4e6356fdc diff --git a/packages/README.md b/packages/README.md index ad88e895ce..287e59a54d 100644 --- a/packages/README.md +++ b/packages/README.md @@ -19,7 +19,7 @@ Groups hold `packages///`; names stay `@deepseek-ai/dsh-`. **Gr | [`identity/`](identity/README.md) | Shared anonymous identity | Product — stable API | | [`llm/`](llm/README.md) | LLM capability family: the abstract service + provider adapters | Product — stable API | | [`e2b/`](e2b/README.md) | E2B providers | POC | -| [`subprocess/`](subprocess/README.md) | Subprocess capability family: Service Definition, local process-tree provider, and shared Win32 process library | Product — stable API | +| [`subprocess/`](subprocess/README.md) | Subprocess capability family: Service Definition, local managed-range provider, and shared Win32 process library | Product — stable API | | [`shell/`](shell/README.md) | Bash capability family: executor seam, local impl, model-facing tool | Product — stable API | | [`terminal/`](terminal/README.md) | Persistent PTY capability family: owner-scoped sessions, local implementation, and model-facing tools | Product — stable API | | [`code-runtime/`](code-runtime/README.md) | Code-execution capability family: Service Definition + worker-thread provider + Code Mode Consumer | Product — stable API | diff --git a/packages/README.zh.md b/packages/README.zh.md index 81557ab3b9..6407754a10 100644 --- a/packages/README.zh.md +++ b/packages/README.zh.md @@ -19,7 +19,7 @@ npm scope 为 `@deepseek-ai/dsh-*`；Cordis `Service` 子类和函数插件通 | [`identity/`](identity/README.zh.md) | 共享匿名身份 | 产品：稳定 API | | [`llm/`](llm/README.zh.md) | LLM（大语言模型）能力系列：抽象服务 + 提供方适配器 | 产品：稳定 API | | [`e2b/`](e2b/README.zh.md) | E2B 提供方 | POC | -| [`subprocess/`](subprocess/README.zh.md) | 子进程能力系列：Service Definition、本地进程树提供方与共享 Win32 进程库 | 产品：稳定 API | +| [`subprocess/`](subprocess/README.zh.md) | 子进程能力系列：Service Definition、本地 managed-range 提供方与共享 Win32 进程库 | 产品：稳定 API | | [`shell/`](shell/README.zh.md) | Bash 能力系列：执行器 seam、本地实现、面向模型的工具 | 产品：稳定 API | | [`terminal/`](terminal/README.zh.md) | 持久 PTY 能力系列：限定所有者范围的会话、本地实现和面向模型的工具 | 产品：稳定 API | | [`code-runtime/`](code-runtime/README.zh.md) | 代码执行能力系列：Service Definition + worker 线程提供方 + Code Mode Consumer | 产品：稳定 API | diff --git a/packages/extensions/tool-cordis/src/api-catalog.ts b/packages/extensions/tool-cordis/src/api-catalog.ts index 488c2d756c..432015ade2 100644 --- a/packages/extensions/tool-cordis/src/api-catalog.ts +++ b/packages/extensions/tool-cordis/src/api-catalog.ts @@ -1866,7 +1866,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ { key: 'subprocess', summary: 'Abstract subprocess service.', - description: 'Abstract subprocess service. Subclass, implement spawn, and load the subclass as a plugin — it registers as `ctx.subprocess` (one implementation per context; loading a second throws, which is cordis\' standard duplicate-service behavior).\n\nImplementations must honor these semantics:\n\n- Executable paths belong to one execution world shared with the mounted filesystem provider.\n- spawn returns a live handle synchronously. Its pid is provider-owned and may remain unavailable during asynchronous startup. `done` resolves with the spawned command\'s exit facts and may reject for spawn or provider failures.\n- Collect-mode readers are offset-based and non-consuming, so independent readers never consume one another\'s output; lossy reads report truncation and the spill file holding the complete stream when one exists. Piped streams are handed to the caller raw and never buffered here.\n- SubprocessHandle.terminate (and the spec\'s abort signal) starts the provider\'s documented procedure against its managed range. SubprocessHandle.waitForExit observes that same range so a consumer-owned teardown ladder can hold each tier on real quiescence; each provider documents its identity, signalling, and observability limits.\n- Disposal of the service terminates all still-running managed processes and awaits their exit.\n- spawnTerminal owns terminal allocation, text transport, foreground groups, signalling, and whole-session quiescence behind one awaited termination method; readiness and persistent-shell policy stay in the PTY consumer. Its output stream ends after queued terminal output when the top-level process exits.', + description: 'Abstract subprocess service. Subclass, implement spawn, and load the subclass as a plugin — it registers as `ctx.subprocess` (one implementation per context; loading a second throws, which is cordis\' standard duplicate-service behavior).\n\nImplementations must honor these semantics:\n\n- Executable paths belong to one execution world shared with the mounted filesystem provider.\n- spawn returns a live handle synchronously. Its pid is provider-owned and may remain unavailable during asynchronous startup. `done` resolves with the spawned command\'s exit facts and may reject for spawn or provider failures.\n- Collect-mode readers are offset-based and non-consuming, so independent readers never consume one another\'s output; lossy reads report truncation and the spill file holding the complete stream when one exists. Piped streams are handed to the caller raw and never buffered here.\n- SubprocessHandle.terminate (and the spec\'s abort signal) starts the provider\'s documented procedure against its managed range. SubprocessHandle.waitForExit observes that same range so consumer teardown can await real quiescence; each provider documents its identity, signalling, and observability limits.\n- Disposal of the service terminates all still-running managed processes and awaits their exit.\n- spawnTerminal owns terminal allocation, text transport, foreground groups, signalling, and whole-session quiescence behind one awaited termination method; readiness and persistent-shell policy stay in the PTY consumer. Its output stream ends after queued terminal output when the top-level process exits.', methods: [ { signature: 'abstract resolveExecutable( command: string, env?: Readonly>, signal?: AbortSignal, ): Promise', diff --git a/packages/fs/tool-fs-search/README.i18n.yaml b/packages/fs/tool-fs-search/README.i18n.yaml index b1a2080662..9976f2a8b6 100644 --- a/packages/fs/tool-fs-search/README.i18n.yaml +++ b/packages/fs/tool-fs-search/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/fs/tool-fs-search/README.md -README.md: 84a3adc31f9c1580b90c038b0902e88b050f0340 -README.zh.md: d13581d7e584f97e0779eb232a47d2d119404647 +README.md: ae232afa161f7b8f0d4b28f4da5c0992643a5f4f +README.zh.md: 4b9372bbce129259a6e01694f2964a5528c6c19e diff --git a/packages/fs/tool-fs-search/README.md b/packages/fs/tool-fs-search/README.md index 84a3adc31f..ae232afa16 100644 --- a/packages/fs/tool-fs-search/README.md +++ b/packages/fs/tool-fs-search/README.md @@ -12,7 +12,7 @@ await ctx.plugin(ToolFsSearch, { sampleOverCapGlobResults: false }) await ctx.plugin(LocalSpillStore) // @deepseek-ai/dsh-spill-local ``` -Why spawn-backed: local workspace discovery is naturally a process-backed `rg` workflow, and putting search on `ctx.fs` would force every filesystem backend to grow a search API. The subprocess seam owns spawn execution, process-tree termination, environment scrubbing, and bounded output capture; this package owns schemas, argument validation, argv construction, parsing, retention, formatted-result spill, and timeout declaration. The tools never expose a background job — the call returns only after `rg` exits, is terminated by the cooperative timeout, is aborted, or fails. +Why spawn-backed: local workspace discovery is naturally a process-backed `rg` workflow, and putting search on `ctx.fs` would force every filesystem backend to grow a search API. The subprocess seam owns spawn execution, managed-range termination, environment scrubbing, and bounded output capture; this package owns schemas, argument validation, argv construction, parsing, retention, formatted-result spill, and timeout declaration. The tools never expose a background job — the call returns only after `rg` exits, is terminated by the cooperative timeout, is aborted, or fails. ## Deployment requirement: no host rg, co-located workdir/filesystem @@ -29,8 +29,8 @@ Node deployments receive the `@vscode/ripgrep` platform package on supported mac | `grepMaxMatches` | `250` | Max flat matches one `grep` call retains inline (matches Claude Code's `GrepTool` `head_limit`); later matches go to the formatted spill artifact. | | `grepMaxLineBytes` | `2000` | Byte cap per matched-line preview; the cut preserves UTF-8 boundaries and is marked `(line truncated)`. | | `rawOutputMaxBytes` | `20000000` | Max complete raw `rg` stdout a search will parse (matches Claude Code's ripgrep raw buffer); larger raw output fails with `SEARCH_RAW_OUTPUT_OVERFLOW`. | -| `timeoutMs` | `30000` | Cooperative tool-call budget attached to both tool definitions, enforced by `@deepseek-ai/dsh-tool-call-timeout-policy` through `exec.signal`; the subprocess seam's terminate escalation is the hard kill. | -| `graceMs` | `3000` | Positive terminate-escalation grace the subprocess seam grants past `timeoutMs` before the search fails as `SEARCH_ABORTED`; it cannot exceed [`MAX_TIMER_DELAY_MS`](../../util/timeout/README.md). | +| `timeoutMs` | `30000` | Cooperative tool-call budget attached to both tool definitions, enforced by `@deepseek-ai/dsh-tool-call-timeout-policy` through `exec.signal`; abort starts the subprocess provider's termination procedure. | +| `graceMs` | `3000` | Positive grace supplied to subprocess termination and output draining; it cannot exceed [`MAX_TIMER_DELAY_MS`](../../util/timeout/README.md). | | `stderrMaxBytes` | `65536` | Diagnostic-tail budget for `rg` stderr, captured through the subprocess seam's collect disposition; a lossy read keeps only the tail (marked `[stderr truncated]`). | ## Tools diff --git a/packages/fs/tool-fs-search/README.zh.md b/packages/fs/tool-fs-search/README.zh.md index d13581d7e5..4b9372bbce 100644 --- a/packages/fs/tool-fs-search/README.zh.md +++ b/packages/fs/tool-fs-search/README.zh.md @@ -12,7 +12,7 @@ await ctx.plugin(ToolFsSearch, { sampleOverCapGlobResults: false }) await ctx.plugin(LocalSpillStore) // @deepseek-ai/dsh-spill-local ``` -采用 spawn 支持的原因：本地工作区发现天然是由进程支持的 `rg` 工作流；如果把搜索放到 `ctx.fs` 上，就会迫使每个文件系统后端扩展搜索 API。subprocess seam 负责 spawn 执行、进程树终止、环境清理和有界输出捕获；本包负责 schema、参数校验、argv 构造、解析、保留、格式化结果 spill 和超时声明。工具绝不暴露后台任务——只有在 `rg` 退出、被协作式超时终止、被中止或失败后，调用才会返回。 +采用 spawn 支持的原因：本地工作区发现天然是由进程支持的 `rg` 工作流；如果把搜索放到 `ctx.fs` 上，就会迫使每个文件系统后端扩展搜索 API。subprocess seam 负责 spawn 执行、managed-range 终止、环境清理和有界输出捕获；本包负责 schema、参数校验、argv 构造、解析、保留、格式化结果 spill 和超时声明。工具绝不暴露后台任务——只有在 `rg` 退出、被协作式超时终止、被中止或失败后，调用才会返回。 ## 部署要求：无需宿主 rg，但工作目录与文件系统需共置 @@ -29,8 +29,8 @@ Node 部署在受支持的 macOS、Linux 与 Windows x64/arm64 目标上获得 ` | `grepMaxMatches` | `250` | 一次 `grep` 调用内联保留的最大平铺匹配数（与 Claude Code 的 `GrepTool` `head_limit` 相同）；后续匹配写入格式化 spill 产物。 | | `grepMaxLineBytes` | `2000` | 每条匹配行预览的字节上限；截断会保留 UTF-8 边界，并标记为 `(line truncated)`。 | | `rawOutputMaxBytes` | `20000000` | 搜索将解析的完整原始 `rg` stdout 上限（与 Claude Code 的 ripgrep 原始 buffer 相同）；更大的原始输出以 `SEARCH_RAW_OUTPUT_OVERFLOW` 失败。 | -| `timeoutMs` | `30000` | 附加到两个工具定义上的协作式工具调用预算，由 `@deepseek-ai/dsh-tool-call-timeout-policy` 通过 `exec.signal` 强制执行；subprocess seam 的终止升级提供硬终止。 | -| `graceMs` | `3000` | subprocess seam 在 `timeoutMs` 之外授予的终止升级宽限期须为正值；超过后搜索以 `SEARCH_ABORTED` 失败；该宽限期不得大于 [`MAX_TIMER_DELAY_MS`](../../util/timeout/README.zh.md)。 | +| `timeoutMs` | `30000` | 附加到两个工具定义上的协作式工具调用预算，由 `@deepseek-ai/dsh-tool-call-timeout-policy` 通过 `exec.signal` 强制执行；中止会启动 subprocess provider 的终止过程。 | +| `graceMs` | `3000` | 提供给 subprocess 终止与输出排空的宽限期须为正值，且不得大于 [`MAX_TIMER_DELAY_MS`](../../util/timeout/README.zh.md)。 | | `stderrMaxBytes` | `65536` | `rg` stderr 的诊断尾部预算，经 subprocess seam 的 collect 形态捕获；lossy 读取只保留尾部（标记 `[stderr truncated]`）。 | ## 工具 diff --git a/packages/fs/tool-fs-search/src/glob.ts b/packages/fs/tool-fs-search/src/glob.ts index 871dc16ae8..60ff5b4d80 100644 --- a/packages/fs/tool-fs-search/src/glob.ts +++ b/packages/fs/tool-fs-search/src/glob.ts @@ -47,7 +47,7 @@ export interface GlobToolCaps { maxMetaBytes: number /** Cap on the complete raw `rg` stdout the tool will parse. */ rawOutputMaxBytes: number - /** Terminate-escalation grace period (ms) for the search process. */ + /** Grace for subprocess termination and output draining (ms). */ graceMs: number /** Cap on the retained stderr diagnostic tail. */ stderrMaxBytes: number diff --git a/packages/fs/tool-fs-search/src/grep.ts b/packages/fs/tool-fs-search/src/grep.ts index 38f54aa2a5..439dde2310 100644 --- a/packages/fs/tool-fs-search/src/grep.ts +++ b/packages/fs/tool-fs-search/src/grep.ts @@ -45,7 +45,7 @@ export interface GrepToolCaps { maxMetaBytes: number /** Cap on the complete raw `rg` stdout the tool will parse. */ rawOutputMaxBytes: number - /** Terminate-escalation grace period (ms) for the search process. */ + /** Grace for subprocess termination and output draining (ms). */ graceMs: number /** Cap on the retained stderr diagnostic tail. */ stderrMaxBytes: number diff --git a/packages/fs/tool-fs-search/src/index.ts b/packages/fs/tool-fs-search/src/index.ts index 1765d1b781..fabd12df43 100644 --- a/packages/fs/tool-fs-search/src/index.ts +++ b/packages/fs/tool-fs-search/src/index.ts @@ -13,7 +13,7 @@ * ({@link module:@deepseek-ai/dsh-tool-fs-search/glob} / * {@link module:@deepseek-ai/dsh-tool-fs-search/grep}), result parsing, * retention, formatted-result spill, and timeout declaration; the subprocess - * seam owns spawn execution, process-tree termination, environment scrubbing, + * seam owns spawn execution, managed-range termination, environment scrubbing, * and raw output capture. The package injects `tools`, `systemPrompt`, and * `subprocess` — deliberately NOT `fs`, and `ctx.spillStore` is read * opportunistically with `ctx.get()` because formatted-result spill is optional. @@ -83,7 +83,7 @@ export interface Config { searchMetaMaxBytes?: number /** Max complete raw `rg` stdout bytes a search will parse; larger raw output fails with `SEARCH_RAW_OUTPUT_OVERFLOW`. */ rawOutputMaxBytes?: number - /** Terminate-escalation grace (ms), handed to the subprocess seam and bounded by `MAX_TIMER_DELAY_MS`. */ + /** Grace for subprocess termination and output draining (ms), bounded by `MAX_TIMER_DELAY_MS`. */ graceMs?: number /** Max bytes retained for one search's stderr tail; the excerpt is embedded in `SEARCH_*` error messages, never shown on success. */ stderrMaxBytes?: number diff --git a/packages/fs/tool-fs-search/src/search-core.ts b/packages/fs/tool-fs-search/src/search-core.ts index 5ac5521033..0852cbb36d 100644 --- a/packages/fs/tool-fs-search/src/search-core.ts +++ b/packages/fs/tool-fs-search/src/search-core.ts @@ -182,8 +182,8 @@ export function resolveRgPath(): Promise { * complete raw stdout. The working directory is the calling agent's session * cwd (`exec.agent.session.header.cwd`) when available, else * `process.cwd()`. `exec.signal` is forwarded so the cooperative tool timeout - * (`@deepseek-ai/dsh-tool-call-timeout-policy`) and caller cancellation terminate the - * process tree. + * (`@deepseek-ai/dsh-tool-call-timeout-policy`) and caller cancellation start the + * provider's managed-range termination procedure. * * The spawn is unconfined (a plain `ctx.subprocess` call), so `--no-config` * is prepended: a host `RIPGREP_CONFIG_PATH` (or `rg.conf` next to the @@ -208,7 +208,7 @@ export function resolveRgPath(): Promise { * @param toolName - `glob` or `grep`, used in error messages. * @param argv - the ripgrep arguments (every model value an unquoted argv element; no shell layer exists). * @param rawOutputMaxBytes - cap on the complete raw stdout the tool will parse. - * @param graceMs - the seam's terminate-escalation grace period. + * @param graceMs - grace supplied to subprocess termination and output draining. * @param stderrMaxBytes - cap on the retained stderr diagnostic tail. * @returns the complete stdout, the zero-result flag, and the resolved workdir. */ diff --git a/packages/fs/tool-fs-search/tests/tools.spec.ts b/packages/fs/tool-fs-search/tests/tools.spec.ts index abb7e75773..3a237e648d 100644 --- a/packages/fs/tool-fs-search/tests/tools.spec.ts +++ b/packages/fs/tool-fs-search/tests/tools.spec.ts @@ -93,7 +93,7 @@ class FakeReader implements SubprocessOutputReader { * A scriptable subprocess handle: `done` resolves with the scripted outcome * (or rejects with the scripted error), `terminate()` records the call, and * the spec's abort signal marks the handle terminated — mirroring the seam's - * abort→terminate escalation. + * abort-triggered provider termination. */ class FakeHandle implements SubprocessHandle { readonly pid = 4242 @@ -434,8 +434,8 @@ describe('workdir derivation and signal forwarding', () => { it('reports an abort fired during the run as SEARCH_ABORTED', async () => { // The cooperative tool timeout or caller cancellation aborts exec.signal; - // the subprocess seam then kills the process tree. The tool classifies - // the first cause it owns: the abort. + // the subprocess provider then starts managed-range termination. The tool + // classifies the first cause it owns: the abort. const { ctx, subprocess } = await setup() const controller = new AbortController() subprocess.handler = () => { diff --git a/packages/lsp/lsp-stdio/README.i18n.yaml b/packages/lsp/lsp-stdio/README.i18n.yaml index 6ca3618083..e08a01a19f 100644 --- a/packages/lsp/lsp-stdio/README.i18n.yaml +++ b/packages/lsp/lsp-stdio/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/lsp/lsp-stdio/README.md -README.md: beadc34ec738ae3f6511cae764240c0e9d8c61d7 -README.zh.md: 2d6516a25147fb7593e8d45d843315098cdff7d3 +README.md: 5b5e805f2e48d17aeed3cd5f4dce47928b0c9dc5 +README.zh.md: 6dd690a536cd96af889c8c13f2b62282a1cc9328 diff --git a/packages/lsp/lsp-stdio/README.md b/packages/lsp/lsp-stdio/README.md index beadc34ec7..5b5e805f2e 100644 --- a/packages/lsp/lsp-stdio/README.md +++ b/packages/lsp/lsp-stdio/README.md @@ -12,7 +12,7 @@ Namespace plugin (`name` / `inject` / `Config` / `apply`, no default export). - Lazily single-flights one server process per `(server id, canonical workspace target)`. A live server error is not replayed; if the selected pooled transport fails before or during a read-only query, the provider awaits its disposal and retries that query once on a fresh process. - Uses a compatibility-first **transient-open** sequence per query: resolve and byte-bound the source while streaming it through `ctx.fs`, `textDocument/didOpen` (version 1, full text), the requested request, then `textDocument/didClose` in `finally`. A failed or canceled `didOpen` write terminates the instance before the pool can reuse it. Documents close after each call, so the first version needs no `didChange`, content cache, or document LRU. - Serializes each source-read/open/query/close lifecycle through one abortable per-workspace queue so queued calls read current source only when their turn starts; distinct workspaces run in parallel. Provider disposal aborts filesystem and protocol work, awaits workspace lookups that have not entered a queue, then drains every queue and server. -- After protocol shutdown fails, terminates the server's descendant tree through the subprocess seam (POSIX process-group signaling; Windows `taskkill /T /F`). Tree-kill delivery is contained like every group signal — it races server exit — and quiescence is confirmed by the handle's tree-liveness wait rather than by the kill's own outcome. +- After protocol shutdown fails, invokes the subprocess provider's termination procedure and awaits the same managed range through `waitForExit()`. The provider owns signal delivery and observation failures; the LSP host owns only protocol-first teardown and the final quiescence wait. - Resolves the server executable, cwd, process, and protocol streams through `ctx.subprocess`; `initialize.processId` is `null` because another machine or PID namespace must not monitor the harness process. - Uses `ctx.fs` canonical containment, file URIs, and streamed text validation, but emits no `fs/observed`: only the LSP result is model-visible, so a query does not satisfy read-before-write policy. @@ -32,7 +32,7 @@ The `servers` record key is the stable provider id reserved on `ctx.lsp`; each v | `maxStderrBytes` | `1000000` | Largest stderr tail retained for diagnostics. | | `maxDocumentBytes` | `4000000` | Largest source file this host will open. | | `shutdownTimeoutMs` | `5000` | Graceful `shutdown`/`exit` budget before escalation. | -| `killGraceMs` | `2000` | Grace for request cancellation and for SIGTERM→SIGKILL escalation. | +| `killGraceMs` | `2000` | Grace supplied to subprocess termination and output draining. | `servers` must contain at least one entry, and every id must be non-empty. Timer budgets must be positive integers no greater than Node's `2_147_483_647` ms timer limit. All executables resolve at load after credential scrubbing; a bad later entry prevents every provider from registering. Processes launch lazily on the first matching query. diff --git a/packages/lsp/lsp-stdio/README.zh.md b/packages/lsp/lsp-stdio/README.zh.md index 2d6516a251..6dd690a536 100644 --- a/packages/lsp/lsp-stdio/README.zh.md +++ b/packages/lsp/lsp-stdio/README.zh.md @@ -12,7 +12,7 @@ Namespace 插件（`name`／`inject`／`Config`／`apply`，无默认导出） - 每个 `(server id, canonical workspace target)` 惰性 single-flight 一个服务器进程。服务器仍存活时返回的错误不会触发重试；如果选中的池化传输在只读查询之前或期间发生故障，提供方会等待其 dispose（资源释放）完成，并在新进程上重试该查询一次。 - 每次查询都使用兼容性优先的**临时打开**序列：通过 `ctx.fs` 流式读取源文件，同时解析并限制其字节数；随后执行 `textDocument/didOpen`（版本 1、完整文本）、所请求操作，再执行位于 `finally` 中的 `textDocument/didClose`。写入 `didOpen` 失败或取消时，会在池复用该实例前将其终止。文档在每次调用后关闭，因此第一版不需要 `didChange`、内容 cache 或文档 LRU。 - 通过一条逐 Workspace、可中止的队列，串行执行每个源读取／打开／查询／关闭生命周期，因此排队调用只会在轮到自身时读取当前源；不同 Workspace 并行运行。提供方 dispose 会中止文件系统与协议工作，等待尚未进入队列的 Workspace 查找完成，随后排空每条队列与每个服务器。 -- 协议 shutdown 失败后，经由子进程 seam 终止服务器后代树（POSIX 进程组信号；Windows `taskkill /T /F`）。树终止的投递结果与所有进程组信号一样被就地吸收，不向外抛出（投递与服务器退出存在竞态）；服务器是否完全停稳，由句柄的进程树存活等待确认，而非由这次终止自身的结果确认。 +- 协议 shutdown 失败后，调用 subprocess provider 的终止过程，并通过 `waitForExit()` 等待同一个 managed range。信号投递与观察失败归 provider 所有；LSP Host 只拥有协议优先的拆卸过程与最终完全停稳等待。 - 通过 `ctx.subprocess` 解析服务器可执行文件、cwd、进程和协议流；`initialize.processId` 为 `null`，因为另一台机器或 PID namespace 不得监视 harness 进程。 - 使用 `ctx.fs` 提供的规范化包含关系、文件 URI 与流式文本验证，但不发出 `fs/observed`：只有 LSP 结果对模型可见，因此查询不满足先读后写策略。 @@ -32,7 +32,7 @@ Namespace 插件（`name`／`inject`／`Config`／`apply`，无默认导出） | `maxStderrBytes` | `1000000` | 为诊断保留的 stderr 尾部最大大小。 | | `maxDocumentBytes` | `4000000` | 该主机可打开的源文件大小上限。 | | `shutdownTimeoutMs` | `5000` | 升级前用于优雅 `shutdown`／`exit` 的预算。 | -| `killGraceMs` | `2000` | 请求取消及 SIGTERM→SIGKILL 升级的宽限期。 | +| `killGraceMs` | `2000` | 提供给 subprocess 终止与输出排空的宽限期。 | `servers` 必须至少包含一个配置项，每个 id 都必须非空。定时器预算必须是正整数，且不超过 Node 的 `2_147_483_647` ms 定时器上限。所有可执行文件都会在清理 credential 后于加载时解析；后面的坏配置项会阻止所有提供方注册。进程在第一次匹配查询时惰性启动。 diff --git a/packages/lsp/lsp-stdio/src/connection.ts b/packages/lsp/lsp-stdio/src/connection.ts index 5cfcf10b0c..55af39341a 100644 --- a/packages/lsp/lsp-stdio/src/connection.ts +++ b/packages/lsp/lsp-stdio/src/connection.ts @@ -4,8 +4,8 @@ * server→client requests: it answers `workspace/configuration` from static * config, and rejects `workspace/applyEdit` (this host never applies edits or * runs commands). It caps stderr, surfaces framing/decoder failures as a - * fatal close, and exposes tree-scoped termination through the handle so the - * instance owns teardown; group/tree mechanics live in the subprocess + * fatal close, and exposes managed-range termination through the handle so the + * instance owns teardown; range mechanics live in the subprocess * Service Provider. * @module @deepseek-ai/dsh-lsp-stdio/connection */ @@ -29,9 +29,9 @@ export interface ConnectionSpec { /** Largest stderr tail retained for diagnostics. */ readonly maxStderrBytes: number /** - * The subprocess spec's `graceMs`: the SIGTERM→SIGKILL window of - * {@link LspConnection.terminate}'s escalation, and the bound for draining - * pipes a surviving helper still holds after the server exits. + * The subprocess spec's `graceMs`: available to the provider's termination + * procedure and used to bound draining pipes a survivor still holds after + * the server exits. */ readonly killGraceMs: number /** Static answer to every `workspace/configuration` item. */ @@ -88,7 +88,7 @@ export class LspConnection { this.decoder = new MessageDecoder(spec.maxMessageBytes) // stdin/stdout are piped protocol streams this endpoint frames itself; // stderr is a collected diagnostic tail (no spill — the bounded tail IS - // the contract). The seam owns detachment and tree-scoped signalling. + // the contract). The seam owns managed-range signalling and quiescence. this.handle = spawner({ argv: [spec.command, ...spec.args], cwd: spec.cwd, @@ -209,15 +209,15 @@ export class LspConnection { return this.nextId } - /** Terminate the server's process tree (the seam's SIGTERM→grace→SIGKILL escalation; idempotent). */ + /** Start the provider's idempotent termination procedure for the server's managed range. */ terminate(): void { this.handle.terminate() } /** - * Wait until the owned process tree has exited. + * Wait until the provider-managed range is empty. * @param signal - optional bound for the wait. - * @returns `true` when the tree exited, or `false` when the signal aborted first. + * @returns `true` when the range is empty, or `false` when the signal aborted first. */ async waitForProcessTreeExit(signal?: AbortSignal): Promise { return await this.handle.waitForExit(signal) diff --git a/packages/lsp/lsp-stdio/src/index.ts b/packages/lsp/lsp-stdio/src/index.ts index ebc54702da..abd7ab35c5 100644 --- a/packages/lsp/lsp-stdio/src/index.ts +++ b/packages/lsp/lsp-stdio/src/index.ts @@ -72,9 +72,9 @@ export interface LspLocalServerConfig { maxStderrBytes?: number /** Largest source file this host will open (bytes). Default 4000000. */ maxDocumentBytes?: number - /** Graceful `shutdown`/`exit` budget before escalation (ms). Default 5000. */ + /** Graceful `shutdown`/`exit` budget before provider termination (ms). Default 5000. */ shutdownTimeoutMs?: number - /** Request-cancel and SIGTERM→SIGKILL grace (ms). Default 2000. */ + /** Grace supplied to subprocess termination and output draining (ms). Default 2000. */ killGraceMs?: number } diff --git a/packages/lsp/lsp-stdio/src/instance.ts b/packages/lsp/lsp-stdio/src/instance.ts index 2028129de7..88e80b88b0 100644 --- a/packages/lsp/lsp-stdio/src/instance.ts +++ b/packages/lsp/lsp-stdio/src/instance.ts @@ -269,8 +269,8 @@ export class LspInstance { } /** - * Reject queued work, attempt graceful `shutdown`/`exit`, then escalate SIGTERM→SIGKILL, awaiting - * process close so nothing outlives disposal. + * Reject queued work, attempt graceful `shutdown`/`exit`, then request the + * provider's termination procedure and await process close and range quiescence. */ async dispose(): Promise { await this.startTeardown() @@ -288,7 +288,7 @@ export class LspInstance { try { await this.gracefulShutdown(shutdownDeadline.signal) } catch { - // Graceful shutdown failed or timed out; process-tree cleanup below remains authoritative. + // Graceful shutdown failed or timed out; managed-range cleanup below remains authoritative. } finally { shutdownDeadline[Symbol.dispose]() } @@ -303,10 +303,9 @@ export class LspInstance { } /** - * Terminate the tree (the seam escalates SIGTERM→`killGraceMs`→SIGKILL), - * then await leader and helper exit. The awaits are unbounded on purpose: - * the seam's escalation already committed to SIGKILL, so quiescence — not - * another timer — is the postcondition disposal owes its callers. + * Start the provider's termination procedure, then await command transport + * and managed-range exit. The awaits are unbounded on purpose: quiescence, + * not another consumer timer, is the postcondition disposal owes its callers. */ private async forceTerminate(): Promise { this.connection.terminate() diff --git a/packages/lsp/lsp-stdio/tests/instance.spec.ts b/packages/lsp/lsp-stdio/tests/instance.spec.ts index 9efc091919..a2dcebcc8f 100644 --- a/packages/lsp/lsp-stdio/tests/instance.spec.ts +++ b/packages/lsp/lsp-stdio/tests/instance.spec.ts @@ -312,7 +312,7 @@ describe('LspInstance disposal', () => { await expect(instance.dispose()).resolves.toBeUndefined() }) - it('awaits a surviving process-tree helper on every concurrent dispose', async () => { + it('awaits a surviving managed-range helper on every concurrent dispose', async () => { const marker = join(root, 'helper.pid') const helper = 'process.on("SIGTERM",()=>{});setInterval(()=>{},1000);' const script = 'const{spawn}=require("node:child_process");const{writeFileSync}=require("node:fs");' diff --git a/packages/shell/bash-local/README.i18n.yaml b/packages/shell/bash-local/README.i18n.yaml index 82a7387566..e7e0526ec3 100644 --- a/packages/shell/bash-local/README.i18n.yaml +++ b/packages/shell/bash-local/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/shell/bash-local/README.md -README.md: 5e62ea24676f3bedf32b1b48f8618d703d5fb462 -README.zh.md: 92f842a777aebec2e2cb6a8c54966e46202531f1 +README.md: 7bdaa7442e7d4166ecae6328d2456ddc22a01cbc +README.zh.md: bf33c9d1108be92ffadcd60363d4d773f7591071 diff --git a/packages/shell/bash-local/README.md b/packages/shell/bash-local/README.md index 5e62ea2467..7bdaa7442e 100644 --- a/packages/shell/bash-local/README.md +++ b/packages/shell/bash-local/README.md @@ -2,7 +2,7 @@ English | [中文](README.zh.md) -Local Service Provider for the `@deepseek-ai/dsh-shell` executor seam over the [`@deepseek-ai/dsh-subprocess`](../../subprocess/subprocess/README.md) service: `LocalBashExecutor` spawns `bash -c ` per call as a managed process group through `ctx.subprocess`, and owns everything bash-shaped — command defaulting and caps, timeout/cancel classification, the model-friendly terminal environment, and the model-facing stdout/stderr merge for background reads. Group mechanics (bounded spill-backed output, credential scrub, kill escalation, disposal) are the subprocess service's. +Local Service Provider for the `@deepseek-ai/dsh-shell` executor seam over the [`@deepseek-ai/dsh-subprocess`](../../subprocess/subprocess/README.md) service: `LocalBashExecutor` spawns `bash -c ` per call in a provider-managed range through `ctx.subprocess`, and owns everything bash-shaped — command defaulting and caps, timeout/cancel classification, the model-friendly terminal environment, and the model-facing stdout/stderr merge for background reads. Managed-range mechanics (bounded spill-backed output, credential scrub, termination, disposal) are the subprocess service's. The package root exports the default and named `LocalBashExecutor` plugin plus its `Config`. @@ -17,14 +17,14 @@ The package root exports the default and named `LocalBashExecutor` plugin plus i maxTimeoutMs: 600000 # cap for per-call overrides maxOutputBytes: 64000 # per-stream in-memory cap; overflow spills to disk maxSpillBytes: 67108864 # per-stream full-output spill cap - graceMs: 3000 # kill escalation and post-exit pipe-drain grace + graceMs: 3000 # subprocess termination and post-exit pipe-drain grace ``` ## Behavior - **Spawn per call, no shell state** — every call is a fresh non-login `bash -c` with no rc files. - **The composition entry is a layer, not the last word** — when a settings provider is composed, this executor registers the capability's [`bash` namespace](../shell/README.md) with the entry above as its base, so a user section in `settings.yaml` layers over it and the next command runs with the new budgets. Values the schema cannot judge (positive and finite, the `graceMs` timer bound) are refused at the write, leaving the running executor on its last good section; without a provider, or after one detaches, the composition entry is what runs. -- **Configured budgets over managed groups** — `resolve()` fills `workdir`/`timeoutMs`/`stdoutMaxBytes` from config, and every spawn hands the service explicit byte caps, spill cap, and `graceMs`. The grace must be positive, finite, and no greater than [`MAX_TIMER_DELAY_MS`](../../util/timeout/README.md), so Node can represent it with one timer. Process-group kills, post-exit pipe draining, tail retention, and bounded spill files are [`dsh-subprocess-local`](../../subprocess/subprocess-local/README.md) mechanics. A foreground `ShellExecRequest.stdoutMaxBytes` can raise stdout's capture budget for one trusted caller; stderr and background runs still use `maxOutputBytes`. +- **Configured budgets over managed ranges** — `resolve()` fills `workdir`/`timeoutMs`/`stdoutMaxBytes` from config, and every spawn hands the service explicit byte caps, spill cap, and `graceMs`. The grace must be positive, finite, and no greater than [`MAX_TIMER_DELAY_MS`](../../util/timeout/README.md), so Node can represent it with one timer. Provider-owned termination, post-exit pipe draining, tail retention, and bounded spill files are [`dsh-subprocess-local`](../../subprocess/subprocess-local/README.md) mechanics. A foreground `ShellExecRequest.stdoutMaxBytes` can raise stdout's capture budget for one trusted caller; stderr and background runs still use `maxOutputBytes`. - **Timeout and cancel classification** — `run()` fuses its config-clamped timeout with the caller's signal through one deadline; only the executor's own timeout reports `timedOut`, an upstream cancel reports `aborted`, and a self-signaled command reports neither ([timeout-library Agent Note](../../../.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md)). - **Model-friendly terminal env** — `NO_COLOR=1 TERM=dumb PAGER=cat GIT_PAGER=cat` prevents pagers and ANSI color from garbling results. These values merge as ordinary env under the service's credential scrub and `DSH_*` channel rules; an explicit caller entry still wins. See the [stdin/env Agent Note](../../../.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-api.md) and [managed environment Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md). - **Background processes** — `start()` returns a live `ShellProcess` handle immediately with no timeout, and `readOutput()` merges offset-based stdout/stderr reads into one consuming delta, placing stderr under a `[stderr]` marker when present. A running process belongs to the subprocess service, survives executor reloads, and is killed and joined on service disposal. Job ids, ownership, polling, and notices belong to the generic [`ctx.jobs` runtime](../../jobs/jobs/README.md), which the tool layer registers the handle with. @@ -41,7 +41,7 @@ No direct invalidation; the named consumer owns any request-prefix changes. - **Unconfined by itself** — this executor always runs commands with the harness process's authority; deployments needing confinement compose [`dsh-bash-sandbox`](../bash-sandbox/README.md), while per-call allow/deny/ask policy belongs on `tools/pre-execute`. - **No persistent shell or PTY** — every call starts a fresh non-login `bash -c`; cwd-only persistence and interactive terminal sessions remain deferred until a real workflow requires them. -- **POSIX-only** — the `bash` binary is hardcoded, and the underlying service's group semantics are POSIX; Windows is unsupported. +- **POSIX-only** — the `bash` binary is hardcoded, so this executor is not composed on Windows. - **A background spawn-failure note is single-delivery** — the subprocess service buffers no output for a process that never ran, so the executor injects `spawn failed: …` into exactly one `readOutput()` delta; a reader that discards that delta cannot recover it. Scrub-heuristic and spill-retention caveats live with [`dsh-subprocess-local`](../../subprocess/subprocess-local/README.md), which owns those mechanics. diff --git a/packages/shell/bash-local/README.zh.md b/packages/shell/bash-local/README.zh.md index 92f842a777..bf33c9d110 100644 --- a/packages/shell/bash-local/README.zh.md +++ b/packages/shell/bash-local/README.zh.md @@ -2,7 +2,7 @@ [English](README.md) | 中文 -`@deepseek-ai/dsh-shell` 执行器 seam 的本地 Service Provider，构建在 [`@deepseek-ai/dsh-subprocess`](../../subprocess/subprocess/README.zh.md) 服务之上：`LocalBashExecutor` 每次调用都通过 `ctx.subprocess` 把 `bash -c ` 作为受管进程组 spawn，并负责所有 Bash 层职责（命令默认值补全与上限、超时与取消分类、适合模型的终端环境，以及后台读取时面向模型的 stdout/stderr 合并）。以 spill 文件兜底的有界输出、凭据清除、kill 升级和 dispose（资源释放）等进程组机制则由 subprocess 服务负责。 +`@deepseek-ai/dsh-shell` 执行器 seam 的本地 Service Provider，构建在 [`@deepseek-ai/dsh-subprocess`](../../subprocess/subprocess/README.zh.md) 服务之上：`LocalBashExecutor` 每次调用都通过 `ctx.subprocess` 在 provider-managed range 中 spawn `bash -c `，并负责所有 Bash 层职责（命令默认值补全与上限、超时与取消分类、适合模型的终端环境，以及后台读取时面向模型的 stdout/stderr 合并）。以 spill 文件兜底的有界输出、凭据清除、终止和 dispose（资源释放）等 managed-range 机制则由 subprocess 服务负责。 包根目录导出默认与具名的 `LocalBashExecutor` 插件及其 `Config`。 @@ -17,14 +17,14 @@ maxTimeoutMs: 600000 # cap for per-call overrides maxOutputBytes: 64000 # per-stream in-memory cap; overflow spills to disk maxSpillBytes: 67108864 # per-stream full-output spill cap - graceMs: 3000 # kill escalation and post-exit pipe-drain grace + graceMs: 3000 # subprocess termination and post-exit pipe-drain grace ``` ## 行为 - **每次调用都 spawn，不保留 shell 状态**：每次调用都启动新的非登录 `bash -c`，且不读取 rc 文件。 - **组装条目是一层，而不是最终值**：当组装中存在 settings 提供方时，本执行器以上面的条目为 base 注册该能力的 [`bash` 命名空间](../shell/README.zh.md)，因此 `settings.yaml` 中的用户段会叠加其上，下一条命令即按新预算运行。schema 无法判定的值（正有限、`graceMs` 的定时器上界）会在写入时被拒绝，运行中的执行器保持它最后一份可用的段；没有提供方、或提供方脱离之后，运行的就是组装条目。 -- **在受管进程组之上应用配置预算**：`resolve()` 从配置补全 `workdir`／`timeoutMs`／`stdoutMaxBytes`，每次 spawn 都向服务传入显式的字节上限、spill 上限与 `graceMs`。该宽限期须为正有限值，且不得大于 [`MAX_TIMER_DELAY_MS`](../../util/timeout/README.zh.md)，这样 Node 就能用一个定时器表示它。进程组终止、退出后管道排空、尾部保留与有界 spill 文件是 [`dsh-subprocess-local`](../../subprocess/subprocess-local/README.zh.md) 的机制。前台 `ShellExecRequest.stdoutMaxBytes` 可为某个受信任调用方提高单次 stdout 捕获预算；stderr 和后台运行仍使用 `maxOutputBytes`。 +- **在 managed range 之上应用配置预算**：`resolve()` 从配置补全 `workdir`／`timeoutMs`／`stdoutMaxBytes`，每次 spawn 都向服务传入显式的字节上限、spill 上限与 `graceMs`。该宽限期须为正有限值，且不得大于 [`MAX_TIMER_DELAY_MS`](../../util/timeout/README.zh.md)，这样 Node 就能用一个定时器表示它。Provider-owned termination、退出后管道排空、尾部保留与有界 spill 文件是 [`dsh-subprocess-local`](../../subprocess/subprocess-local/README.zh.md) 的机制。前台 `ShellExecRequest.stdoutMaxBytes` 可为某个受信任调用方提高单次 stdout 捕获预算；stderr 和后台运行仍使用 `maxOutputBytes`。 - **超时与取消分类**：`run()` 通过同一个 deadline 把经配置钳位的超时与调用方的信号融合；只有执行器自身的超时报告 `timedOut`，上游取消报告 `aborted`，自身因信号终止的命令两者皆不报告（见[超时库 Agent Note](../../../.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.zh.md)）。 - **适合模型的终端环境**：`NO_COLOR=1 TERM=dumb PAGER=cat GIT_PAGER=cat` 防止分页器与 ANSI 颜色破坏结果。这些值作为普通 env 合并，遵循服务的凭据清除与 `DSH_*` 通道规则；调用方的显式条目依旧优先。详见 [stdin/env Agent Note](../../../.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-api.zh.md) 与 [受管环境 Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-agent-session-identity-and-log-location.zh.md)。 - **后台进程**：`start()` 会立即返回活动的 `ShellProcess` 句柄且不应用超时；`readOutput()` 把基于偏移量的 stdout/stderr 读取合并为一条消费式增量，并在存在 stderr 时将其置于 `[stderr]` 标记下。运行中的进程属于 subprocess 服务，可在执行器重载后存活，并在服务 dispose 时被终止且等待退出。job id、所有权、轮询和通知属于通用 [`ctx.jobs` 运行时](../../jobs/jobs/README.zh.md)，工具层会在其中注册该句柄。 @@ -41,7 +41,7 @@ - **自身不提供隔离**：此执行器始终以 harness 进程的权限运行命令；需要隔离的部署可以组合 [`dsh-bash-sandbox`](../bash-sandbox/README.zh.md)，每次调用的 allow/deny/ask 策略则属于 `tools/pre-execute`。 - **没有持久 shell 或 PTY**：每次调用都启动新的非登录 `bash -c`；仅持久化 cwd 与交互式终端会话均继续暂缓，直到真实工作流需要它们。 -- **仅支持 POSIX**：`bash` 二进制已硬编码，底层服务的进程组语义也是 POSIX 的；不支持 Windows。 +- **仅支持 POSIX**：`bash` 二进制已硬编码，因此本执行器不会在 Windows 上组装。 - **后台 spawn 失败提示只交付一次**：subprocess 服务不会为从未真正运行的进程缓冲任何输出，因此执行器把 `spawn failed: …` 注入恰好一个 `readOutput()` 增量；丢弃了该增量的读取方无法再恢复它。 凭据清除启发式规则与 spill 保留的注意事项随 [`dsh-subprocess-local`](../../subprocess/subprocess-local/README.zh.md) 记录；这些机制归它所有。 diff --git a/packages/shell/bash-local/src/index.ts b/packages/shell/bash-local/src/index.ts index 6c37c5b794..dbfd90ed22 100644 --- a/packages/shell/bash-local/src/index.ts +++ b/packages/shell/bash-local/src/index.ts @@ -31,7 +31,7 @@ export const ENV_OVERRIDES = { GIT_PAGER: 'cat', } as const -/** Default SIGTERM→SIGKILL grace period (the `graceMs` config; matches OpenCode's 3s). */ +/** Default subprocess termination and output-drain grace (the `graceMs` config; matches OpenCode's 3s). */ const DEFAULT_GRACE_MS = 3_000 /** Default per-stream spill cap (the `maxSpillBytes` config). */ @@ -49,7 +49,7 @@ export interface Config { maxOutputBytes?: number /** Per-stream spill-file cap; larger streams retain only their in-memory tail. */ maxSpillBytes?: number - /** Grace period for kill escalation and inherited pipes; at most `MAX_TIMER_DELAY_MS`. */ + /** Grace for subprocess termination and inherited-pipe draining; at most `MAX_TIMER_DELAY_MS`. */ graceMs?: number } @@ -94,8 +94,8 @@ export function assertServiceableBashConfig(config: Config): void { /** * Local bash executor over `ctx.subprocess`. Bounded output, spill files, and - * process-group SIGTERM→SIGKILL escalation are the subprocess service's - * mechanics; this executor supplies their configured budgets per spawn, so a + * provider-owned managed-range termination are the subprocess service's + * mechanics; this executor supplies the configured budgets per spawn, so a * still-running background process stays managed (killed and joined at * composition teardown) even across an executor reload. */ @@ -245,7 +245,7 @@ export class LocalBashExecutor extends ShellExecutor { /** * Start an explicit argv with the background lifecycle, environment, output, - * cancellation, and process-tree ownership semantics of this executor. + * cancellation, and managed-range ownership semantics of this executor. * Subclasses use this after replacing the public command's shell argv at an * execution boundary. * @param spec - resolved execution settings and caller-owned command metadata. diff --git a/packages/shell/pwsh-local/README.i18n.yaml b/packages/shell/pwsh-local/README.i18n.yaml index a7712c1df6..cc1fee06f8 100644 --- a/packages/shell/pwsh-local/README.i18n.yaml +++ b/packages/shell/pwsh-local/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/shell/pwsh-local/README.md -README.md: 2eccc59b919d1f729eef52a42581f4da0f1d9e60 -README.zh.md: b7072ebd9be4e148cedd4edd6c20b12536814856 +README.md: 788495ebc5bb4d498d53eada8fb5401bb3639b43 +README.zh.md: 65297a0606f62c769b8ae219066e1ecce32d1b82 diff --git a/packages/shell/pwsh-local/README.md b/packages/shell/pwsh-local/README.md index 2eccc59b91..788495ebc5 100644 --- a/packages/shell/pwsh-local/README.md +++ b/packages/shell/pwsh-local/README.md @@ -2,7 +2,7 @@ English | [中文](README.zh.md) -Local PowerShell Service Provider for the `@deepseek-ai/dsh-shell` executor seam over the [`@deepseek-ai/dsh-subprocess`](../../subprocess/subprocess/README.md) service: `PwshLocalExecutor` spawns `pwsh -NoLogo -NoProfile -NonInteractive -Command ` per call as a managed process through `ctx.subprocess`, and owns everything PowerShell-shaped — executable resolution, command defaulting and caps, timeout/cancel classification, the model-friendly terminal environment, and the model-facing stdout/stderr merge for background reads. Group mechanics (bounded spill-backed output, credential scrub, kill escalation, disposal) are the subprocess service's. +Local PowerShell Service Provider for the `@deepseek-ai/dsh-shell` executor seam over the [`@deepseek-ai/dsh-subprocess`](../../subprocess/subprocess/README.md) service: `PwshLocalExecutor` spawns `pwsh -NoLogo -NoProfile -NonInteractive -Command ` per call in a provider-managed range through `ctx.subprocess`, and owns everything PowerShell-shaped — executable resolution, command defaulting and caps, timeout/cancel classification, the model-friendly terminal environment, and the model-facing stdout/stderr merge for background reads. Managed-range mechanics (bounded spill-backed output, credential scrub, termination, disposal) are the subprocess service's. The command string rides as ONE argv element to `-Command`: PowerShell itself parses the text, and no intermediate shell exists, so there is no shell-quoting layer to escape (the `bash -c` string domain has no equivalent here). Native Win32 paths (`C:\...`) pass through unchanged. @@ -19,7 +19,7 @@ The package root exports the default and named `PwshLocalExecutor` plugin, its ` maxTimeoutMs: 600000 # cap for per-call overrides maxOutputBytes: 64000 # per-stream in-memory cap; overflow spills to disk maxSpillBytes: 67108864 # per-stream full-output spill cap - graceMs: 3000 # kill escalation and post-exit pipe-drain grace + graceMs: 3000 # subprocess termination and post-exit pipe-drain grace pwshPath: C:\Program Files\PowerShell\7\pwsh.exe # explicit executable; else well-known locations, then PATH ``` @@ -31,7 +31,7 @@ The Windows counterpart of `dsh-bash-local`, deliberately mirroring its semantic - **The composition entry is a layer, not the last word** — when a settings provider is composed, this executor registers the capability's [`bash` namespace](../shell/README.md) with the entry above as its base, so a user section in `settings.yaml` layers over it and the next command runs with the new budgets. The namespace is shared with the POSIX family because a host composes exactly one provider of `ctx.shell`; a document written on either platform keeps resolving on the other. Values the schema cannot judge (positive and finite, the `graceMs` timer bound) are refused at the write, leaving the running executor on its last good section. - **UTF-8 output pinned** — every command runs with `[Console]::OutputEncoding` and `$OutputEncoding` set to UTF-8 first, so the Windows PowerShell 5.1 fallback (or any host whose console code page is not UTF-8) cannot garble non-ASCII output: the subprocess collector decodes bytes as UTF-8. Input encoding is left at the host default; pwsh 7 defaults to UTF-8 and is unaffected. - **Executable resolution** — `resolvePwshPath` prefers an explicit `pwshPath`, then on Windows probes PowerShell 7's install location, every PATH entry (Microsoft Store installs; surrounding quotes stripped), and Windows PowerShell 5.1 as a legacy last resort, checking each candidate with an lstat probe that accepts a real file or a link-shaped reparse point (a Store app execution alias stat-fails against its target's ACL, but lstat sees the alias itself); elsewhere it falls back to a bare `pwsh` resolved through PATH. Resolution is a pure function of `(configured, env, platform)`; it runs at construction and again only when a stored `pwshPath` differs from the one the current executable was resolved from, so an unrelated settings change never re-probes the filesystem. -- **Configured budgets over managed groups** — `resolve()` fills `workdir`/`timeoutMs`/`stdoutMaxBytes` from config, and every spawn hands the service explicit byte caps, spill cap, and `graceMs`. The grace must be positive, finite, and no greater than [`MAX_TIMER_DELAY_MS`](../../util/timeout/README.md), so Node can represent it with one timer. Tree termination (taskkill on Windows, process-group signals on POSIX), the post-exit pipe-drain grace, tail-keep truncation, and bounded spill files are [`dsh-subprocess-local`](../../subprocess/subprocess-local/README.md) mechanics. A foreground `ShellExecRequest.stdoutMaxBytes` can raise stdout's capture budget for one trusted caller; stderr and background runs still use `maxOutputBytes`. +- **Configured budgets over managed ranges** — `resolve()` fills `workdir`/`timeoutMs`/`stdoutMaxBytes` from config, and every spawn hands the service explicit byte caps, spill cap, and `graceMs`. The grace must be positive, finite, and no greater than [`MAX_TIMER_DELAY_MS`](../../util/timeout/README.md), so Node can represent it with one timer. Provider-owned termination, post-exit pipe draining, tail retention, and bounded spill files are [`dsh-subprocess-local`](../../subprocess/subprocess-local/README.md) mechanics. A foreground `ShellExecRequest.stdoutMaxBytes` can raise stdout's capture budget for one trusted caller; stderr and background runs still use `maxOutputBytes`. - **Timeout and cancel classification** — `run()` fuses its config-clamped timeout with the caller's signal through one deadline; only the executor's own timeout reports `timedOut`, an upstream cancel reports `aborted`, and a self-terminated command reports neither ([timeout-library Agent Note](../../../.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md)). Windows reports forced termination as exit 1 without a signal, so signal-stamped facts (`signal`, `killed` status) are POSIX-only there; the timeout/abort classification is platform-independent. - **Model-friendly terminal env** — `NO_COLOR=1 PAGER=cat GIT_PAGER=cat` (no `TERM=dumb`: that is a POSIX concept; `NO_COLOR` is honored by modern PowerShell renderers) merged as ordinary env under the service's credential scrub and `DSH_*` channel rules; an explicit caller entry still wins. - **Background processes** — `start()` returns a live `ShellProcess` handle immediately, no timeout applies, and the handle's `readOutput()` merges the service's offset-based stdout/stderr reads into one marked-section delta with a consuming cursor. A still-running process belongs to the subprocess service, so it survives executor reloads and dies (killed and joined) with the service's disposal. Everything task-shaped (ids, ownership, polling, notices) lives in the generic [`ctx.jobs` runtime](../../jobs/jobs/README.md), which the tool layer registers the handle with — this executor never sees a session or a registry. diff --git a/packages/shell/pwsh-local/README.zh.md b/packages/shell/pwsh-local/README.zh.md index b7072ebd9b..65297a0606 100644 --- a/packages/shell/pwsh-local/README.zh.md +++ b/packages/shell/pwsh-local/README.zh.md @@ -2,7 +2,7 @@ [English](README.md) | 中文 -`@deepseek-ai/dsh-shell` 执行器 seam 的本地 PowerShell Service Provider，基于 [`@deepseek-ai/dsh-subprocess`](../../subprocess/subprocess/README.zh.md) 服务：`PwshLocalExecutor` 每次调用以受管进程的方式通过 `ctx.subprocess` spawn `pwsh -NoLogo -NoProfile -NonInteractive -Command `，并负责所有 PowerShell 相关事项——可执行文件解析、命令默认化与上限、超时/取消分类、面向模型的终端环境，以及后台读取的 stdout/stderr 合并。进程组机制（有界 spill 输出、凭据清理、终止升级、dispose（资源释放））属于 subprocess 服务。 +`@deepseek-ai/dsh-shell` 执行器 seam 的本地 PowerShell Service Provider，基于 [`@deepseek-ai/dsh-subprocess`](../../subprocess/subprocess/README.zh.md) 服务：`PwshLocalExecutor` 每次调用都通过 `ctx.subprocess` 在 provider-managed range 中 spawn `pwsh -NoLogo -NoProfile -NonInteractive -Command `，并负责所有 PowerShell 相关事项——可执行文件解析、命令默认化与上限、超时/取消分类、面向模型的终端环境，以及后台读取的 stdout/stderr 合并。Managed-range 机制（有界 spill 输出、凭据清理、终止、dispose（资源释放））属于 subprocess 服务。 命令字符串作为单个 argv 元素传给 `-Command`：由 PowerShell 自己解析文本，不存在中间 shell，因此没有需要转义的 shell 引号层（这里不存在与 `bash -c` 字符串域对应的层）。原生 Win32 路径（`C:\...`）原样通过。 @@ -19,7 +19,7 @@ maxTimeoutMs: 600000 # cap for per-call overrides maxOutputBytes: 64000 # per-stream in-memory cap; overflow spills to disk maxSpillBytes: 67108864 # per-stream full-output spill cap - graceMs: 3000 # kill escalation and post-exit pipe-drain grace + graceMs: 3000 # subprocess termination and post-exit pipe-drain grace pwshPath: C:\Program Files\PowerShell\7\pwsh.exe # explicit executable; else well-known locations, then PATH ``` @@ -31,7 +31,7 @@ - **组装条目是一层，而不是最终值**——当组装中存在 settings 提供方时，本执行器以上面的条目为 base 注册该能力的 [`bash` 命名空间](../shell/README.zh.md)，因此 `settings.yaml` 中的用户段会叠加其上，下一条命令即按新预算运行。该命名空间与 POSIX 家族共用，因为一个宿主只组装一个 `ctx.shell` 提供方；在任一平台写下的文档在另一平台仍能解析。schema 无法判定的值（正有限、`graceMs` 的定时器上界）会在写入时被拒绝，运行中的执行器保持它最后一份可用的段。 - **UTF-8 输出固定**——每条命令都先以 UTF-8 设置 `[Console]::OutputEncoding` 与 `$OutputEncoding`，因此 Windows PowerShell 5.1 兜底（或任何控制台代码页非 UTF-8 的主机）不会破坏非 ASCII 输出：subprocess 收集器以 UTF-8 解码字节。输入编码保持宿主默认；pwsh 7 默认为 UTF-8，不受影响。 - **可执行文件解析**——`resolvePwshPath` 优先显式 `pwshPath`，然后在 Windows 上依次探测 PowerShell 7 安装位置、每个 PATH 条目（Microsoft Store 安装；剥离两端引号）以及作为遗留兜底的 Windows PowerShell 5.1，逐一用 lstat 探测检查（接受真实文件或链接形态的重解析点：Store 的 app execution alias 对其目标 stat 会因 ACL 失败，但 lstat 能看到别名本身）；其他平台回退为通过 PATH 解析的裸 `pwsh`。解析是 `(configured, env, platform)` 的纯函数；它在构造时执行，此后仅当存储的 `pwshPath` 与当前可执行文件所依据的值不同才再次执行，因此无关的设置变更绝不会重新探测文件系统。 -- **受管进程组之上的配置预算**——`resolve()` 从配置填充 `workdir`/`timeoutMs`/`stdoutMaxBytes`，每次 spawn 都向服务提供显式字节上限、spill 上限与 `graceMs`。该宽限期须为正有限值，且不得大于 [`MAX_TIMER_DELAY_MS`](../../util/timeout/README.zh.md)，这样 Node 就能用一个定时器表示它。进程树终止（Windows 用 taskkill，POSIX 用进程组信号）、退出后管道排空宽限、保尾截断与有界 spill 文件是 [`dsh-subprocess-local`](../../subprocess/subprocess-local/README.zh.md) 的机制。前台 `ShellExecRequest.stdoutMaxBytes` 可为单个受信调用方提高 stdout 捕获预算；stderr 与后台运行仍使用 `maxOutputBytes`。 +- **Managed range 之上的配置预算**——`resolve()` 从配置填充 `workdir`/`timeoutMs`/`stdoutMaxBytes`，每次 spawn 都向服务提供显式字节上限、spill 上限与 `graceMs`。该宽限期须为正有限值，且不得大于 [`MAX_TIMER_DELAY_MS`](../../util/timeout/README.zh.md)，这样 Node 就能用一个定时器表示它。Provider-owned termination、退出后管道排空、保尾截断与有界 spill 文件是 [`dsh-subprocess-local`](../../subprocess/subprocess-local/README.zh.md) 的机制。前台 `ShellExecRequest.stdoutMaxBytes` 可为单个受信调用方提高 stdout 捕获预算；stderr 与后台运行仍使用 `maxOutputBytes`。 - **超时与取消分类**——`run()` 通过一个 deadline 融合按配置上限截取的超时与调用方信号；只有执行器自身超时报告 `timedOut`，上游取消报告 `aborted`，自我终止的命令两者都不报告（见 [timeout 库 Agent Note](../../../.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.zh.md)）。Windows 将强制终止报告为退出码 1 且无信号，因此带信号标记的事实（`signal`、`killed` 状态）在那里仅限 POSIX；超时/取消分类与平台无关。 - **面向模型的终端环境**——`NO_COLOR=1 PAGER=cat GIT_PAGER=cat`（没有 `TERM=dumb`：那是 POSIX 概念；现代 PowerShell 渲染器遵循 `NO_COLOR`），作为普通 env 在服务的凭据清理与 `DSH_*` 通道规则之下合并；显式调用方条目仍然优先。 - **后台进程**——`start()` 立即返回存活的 `ShellProcess` 句柄，不设超时；句柄的 `readOutput()` 把服务基于偏移的 stdout/stderr 读取合并为一条按分段标记、通过消费游标推进的增量。仍在运行的进程属于 subprocess 服务，因此它跨执行器重载存活，并随服务 dispose（被终止并 join）。一切任务相关职责（job id、所有权、轮询、通知）都在通用 [`ctx.jobs` 运行时](../../jobs/jobs/README.zh.md) 中，由工具层把句柄注册进去——本执行器从不接触会话或注册表。 diff --git a/packages/shell/pwsh-local/src/index.ts b/packages/shell/pwsh-local/src/index.ts index b7a2d9f915..0760912c63 100644 --- a/packages/shell/pwsh-local/src/index.ts +++ b/packages/shell/pwsh-local/src/index.ts @@ -48,7 +48,7 @@ export const ENV_OVERRIDES = { export const ENCODING_PREAMBLE = '[Console]::OutputEncoding = [System.Text.UTF8Encoding]::new($false); $OutputEncoding = [System.Text.UTF8Encoding]::new($false); ' -/** Default SIGTERM→SIGKILL grace period (the `graceMs` config). */ +/** Default subprocess termination and output-drain grace (the `graceMs` config). */ const DEFAULT_GRACE_MS = 3_000 /** Default per-stream spill cap (the `maxSpillBytes` config). */ @@ -66,7 +66,7 @@ export interface Config { maxOutputBytes?: number /** Per-stream spill-file cap; larger streams retain only their in-memory tail. */ maxSpillBytes?: number - /** Grace period for kill escalation and inherited pipes; at most `MAX_TIMER_DELAY_MS`. */ + /** Grace for subprocess termination and inherited-pipe draining; at most `MAX_TIMER_DELAY_MS`. */ graceMs?: number /** * Explicit pwsh executable. When omitted, well-known Windows install @@ -122,7 +122,7 @@ export function assertServiceablePwshConfig(config: Config): void { /** * Local PowerShell executor over `ctx.subprocess`. Bounded output, spill - * files, and process-tree termination are the subprocess service's mechanics; + * files, and managed-range termination are the subprocess service's mechanics; * this executor supplies their configured budgets per spawn. */ export class PwshLocalExecutor extends ShellExecutor { diff --git a/packages/shell/pwsh-local/tests/executor.spec.ts b/packages/shell/pwsh-local/tests/executor.spec.ts index e26211b268..dab4c4a245 100644 --- a/packages/shell/pwsh-local/tests/executor.spec.ts +++ b/packages/shell/pwsh-local/tests/executor.spec.ts @@ -2,7 +2,7 @@ * Real-process tests for `@deepseek-ai/dsh-pwsh-local`: the LOCAL subprocess * service plus a REAL pwsh executable, exercised through the executor seam * (`resolve` → `run`/`start`). These verify the world — actual PowerShell - * runs, output capture, truncation and spill, deadlines, kill escalation, and + * runs, output capture, truncation and spill, deadlines, termination, and * the background-handle contract. The suite self-skips when no usable `pwsh` * resolves (a CI accommodation for hosts without PowerShell); the pure unit tests * (config validation, executable resolution) run on every platform. PowerShell @@ -400,7 +400,7 @@ describe.skipIf(!hasPwsh)('PwshLocalExecutor.start (background process handles)' expect(lf(read.delta)).toContain('[stderr]') }) - it('kill() terminates the process tree: true once, false after settlement', async () => { + it('kill() terminates the managed range: true once, false after settlement', async () => { const { bash } = await setup() const proc = bash.start(bash.resolve({ command: 'Start-Sleep -Seconds 60' })) expect(proc.kill()).toBe(true) diff --git a/packages/subagent/subagent-acp/README.i18n.yaml b/packages/subagent/subagent-acp/README.i18n.yaml index 4aaf1b7552..0a82434228 100644 --- a/packages/subagent/subagent-acp/README.i18n.yaml +++ b/packages/subagent/subagent-acp/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/subagent/subagent-acp/README.md -README.md: 3bccddbca021bed1f8bf5766b9575f3bd7441669 -README.zh.md: 7ae89ece0ce4282ad5b9a20142a2ba9b111f6d88 +README.md: eeeaa9350103761b1507c54d3bb48de97d735906 +README.zh.md: d70e30f7b85fbb052101ef7cc43adc2970630295 diff --git a/packages/subagent/subagent-acp/README.md b/packages/subagent/subagent-acp/README.md index 3bccddbca0..eeeaa93501 100644 --- a/packages/subagent/subagent-acp/README.md +++ b/packages/subagent/subagent-acp/README.md @@ -14,7 +14,7 @@ The returned run id is minted in the parent namespace. The child server's sessio After publication, the provider sends the prompt and collects streamed `agent_message_chunk` text into `SubagentResult.output`. A prompt/transport failure resolves with `stopReason: 'error'`, or `aborted` when the required request signal or disposal requested cancellation. -`dispose()` is idempotent. It removes the signal listener, requests ACP cancellation when possible, then runs this backend's own teardown ladder (`disposeAcpChild`) over the seam's verbs: close stdin and wait `disposeEofGraceMs` for cooperative quiescence, then invoke the handle's `terminate()` escalation (SIGTERM, the spawn grace, SIGKILL — Windows force-terminates directly) and await the subprocess owner's whole-tree exit proof. Every run uses a fresh process; process pooling is not implemented. +`dispose()` is idempotent. It removes the signal listener, requests ACP cancellation when possible, then runs this backend's own teardown ladder (`disposeAcpChild`) over the seam's verbs: close stdin and wait `disposeEofGraceMs` for cooperative quiescence, then invoke the handle's provider-owned `terminate()` procedure and await managed-range exit. Every run uses a fresh process; process pooling is not implemented. ## Capabilities and context @@ -31,7 +31,7 @@ ACP advertises no start-time capabilities because this process cannot enforce th | `permission` | `reject` | Auto-answer permission requests by rejecting or choosing the first `allow_once` or `allow_always` option. | | `env` | `{}` | Explicit child environment layered over a credential-scrubbed parent environment. | | `disposeEofGraceMs` | `6000` | Positive grace after stdin EOF before platform termination; it cannot exceed [`MAX_TIMER_DELAY_MS`](../../util/timeout/README.md). | -| `disposeGraceMs` | `3000` | Positive POSIX grace after SIGTERM before SIGKILL (Windows force-terminates directly); it cannot exceed [`MAX_TIMER_DELAY_MS`](../../util/timeout/README.md). | +| `disposeGraceMs` | `3000` | Positive grace supplied to subprocess termination and output draining; it cannot exceed [`MAX_TIMER_DELAY_MS`](../../util/timeout/README.md). | ```yaml - id: subagent-acp @@ -57,7 +57,7 @@ ACP advertises no start-time capabilities because this process cannot enforce th ## Process boundary -The child spawns through the [`dsh-subprocess`](../../subprocess/subprocess/README.md) seam: credential-shaped ambient variables and ambient `DSH_*` names are removed by the shared scrub, then explicit `config.env` values merge after it (an intended `DEEPSEEK_API_KEY` survives, and a `DSH_*` deployment fact such as `DSH_PERMISSION_MODE` reaches the child the same way — the scrub drops only its stale ambient namesake), stderr is inherited to the parent's own stream, and disposal applies this plugin's EOF window before the subprocess-owned SIGTERM→SIGKILL escalation and whole-tree join. The ACP wire is the real serialization boundary; same-process subagent values are not defensively cloned. +The child spawns through the [`dsh-subprocess`](../../subprocess/subprocess/README.md) seam: credential-shaped ambient variables and ambient `DSH_*` names are removed by the shared scrub, then explicit `config.env` values merge after it (an intended `DEEPSEEK_API_KEY` survives, and a `DSH_*` deployment fact such as `DSH_PERMISSION_MODE` reaches the child the same way — the scrub drops only its stale ambient namesake), stderr is inherited to the parent's own stream, and disposal applies this plugin's EOF window before the subprocess provider's termination procedure and managed-range join. The ACP wire is the real serialization boundary; same-process subagent values are not defensively cloned. The package has no default export. Cordis loader unwrapping would otherwise hide the named `inject` metadata; see [postmortem 0001](../../../docs/postmortem/0001-acp-default-export-drops-inject.md). diff --git a/packages/subagent/subagent-acp/README.zh.md b/packages/subagent/subagent-acp/README.zh.md index 7ae89ece0c..d70e30f7b8 100644 --- a/packages/subagent/subagent-acp/README.zh.md +++ b/packages/subagent/subagent-acp/README.zh.md @@ -14,7 +14,7 @@ ACP（Agent Client Protocol）提供方会在全新的子进程中运行每个 s 发布后，提供方发送提示词，并把流式 `agent_message_chunk` 文本收集到 `SubagentResult.output`。提示词/传输失败会以 `stopReason: 'error'` 兑现；如果必需的请求信号或 dispose（资源释放）请求了取消，则以 `aborted` 兑现。 -`dispose()` 是幂等的。它会移除信号监听器，在可行时请求 ACP 取消，然后使用该 seam 定义的操作运行本后端自有的拆卸阶梯（`disposeAcpChild`）：先关闭 stdin 并等待 `disposeEofGraceMs` 让子进程协作式完全停稳，再触发句柄的 `terminate()` 升级（SIGTERM、spawn 宽限期、SIGKILL——Windows 直接强制终止），并等待子进程责任方给出整棵进程树的退出证明。每次运行都使用全新进程；尚未实现进程池。 +`dispose()` 是幂等的。它会移除信号监听器，在可行时请求 ACP 取消，然后使用该 seam 定义的操作运行本后端自有的拆卸阶梯（`disposeAcpChild`）：先关闭 stdin 并等待 `disposeEofGraceMs` 让子进程协作式完全停稳，再触发句柄由 provider 拥有的 `terminate()` 过程并等待 managed range 退出。每次运行都使用全新进程；尚未实现进程池。 ## 能力与上下文 @@ -31,7 +31,7 @@ ACP 不声明任何启动时能力，因为当前进程无法强制执行远程 | `permission` | `reject` | 自动回答权限请求：拒绝，或选择第一个 `allow_once` 或 `allow_always` 选项。 | | `env` | `{}` | 显式子进程环境，叠加到已清理凭据的父进程环境之上。 | | `disposeEofGraceMs` | `6000` | stdin EOF 之后、平台终止之前的宽限时间须为正值，且不得大于 [`MAX_TIMER_DELAY_MS`](../../util/timeout/README.zh.md)。 | -| `disposeGraceMs` | `3000` | POSIX 在 SIGTERM 后、SIGKILL 前的宽限时间（Windows 直接强制终止），须为正值且不得大于 [`MAX_TIMER_DELAY_MS`](../../util/timeout/README.zh.md)。 | +| `disposeGraceMs` | `3000` | 提供给 subprocess 终止与输出排空的宽限期须为正值，且不得大于 [`MAX_TIMER_DELAY_MS`](../../util/timeout/README.zh.md)。 | ```yaml - id: subagent-acp @@ -57,7 +57,7 @@ ACP 不声明任何启动时能力，因为当前进程无法强制执行远程 ## 进程边界 -子进程经由 [`dsh-subprocess`](../../subprocess/subprocess/README.zh.md) seam spawn：共享的凭据清除先移除疑似凭据的环境变量和环境中已有的 `DSH_*` 名称，显式 `config.env` 值在清除之后合并（有意转发的 `DEEPSEEK_API_KEY` 会保留下来，`DSH_PERMISSION_MODE` 这类 `DSH_*` 部署事实也以同样的方式到达子进程——清除只丢弃其陈旧的同名环境值），stderr 会继承到父进程自身的流，dispose 则先应用本插件的 EOF 时间窗，再由子进程责任方执行 SIGTERM→SIGKILL 升级并等待整棵进程树退出。ACP 协议格式（wire format）是真正的序列化边界；同进程 subagent 值不会为防御目的而克隆。 +子进程经由 [`dsh-subprocess`](../../subprocess/subprocess/README.zh.md) seam spawn：共享的凭据清除先移除疑似凭据的环境变量和环境中已有的 `DSH_*` 名称，显式 `config.env` 值在清除之后合并（有意转发的 `DEEPSEEK_API_KEY` 会保留下来，`DSH_PERMISSION_MODE` 这类 `DSH_*` 部署事实也以同样的方式到达子进程——清除只丢弃其陈旧的同名环境值），stderr 会继承到父进程自身的流，dispose 则先应用本插件的 EOF 时间窗，再由 subprocess provider 执行其终止过程并等待 managed range 停稳。ACP 协议格式（wire format）是真正的序列化边界；同进程 subagent 值不会为防御目的而克隆。 本包没有默认导出。否则 Cordis loader 的解包会隐藏具名 `inject` 元数据；见[事故复盘（postmortem）0001](../../../docs/postmortem/0001-acp-default-export-drops-inject.zh.md)。 diff --git a/packages/subagent/subagent-acp/src/index.ts b/packages/subagent/subagent-acp/src/index.ts index 4b526279ba..0b4ad14baa 100644 --- a/packages/subagent/subagent-acp/src/index.ts +++ b/packages/subagent/subagent-acp/src/index.ts @@ -55,11 +55,11 @@ export interface Config { /** * Grace period (ms) for the child's EOF-driven quiesce on dispose — its * window to flush persistence and tear down its own nested subprocesses - * before the parent escalates to a signal. Must not exceed + * before the parent invokes provider termination. Must not exceed * `MAX_TIMER_DELAY_MS`. */ disposeEofGraceMs?: number - /** Termination-escalation grace (ms); must not exceed `MAX_TIMER_DELAY_MS`. */ + /** Grace for subprocess termination and output draining (ms); must not exceed `MAX_TIMER_DELAY_MS`. */ disposeGraceMs?: number } diff --git a/packages/subagent/subagent-acp/src/run.ts b/packages/subagent/subagent-acp/src/run.ts index 5ba7bc1718..a4b80a6d99 100644 --- a/packages/subagent/subagent-acp/src/run.ts +++ b/packages/subagent/subagent-acp/src/run.ts @@ -58,19 +58,18 @@ export interface AcpRunSpec { /** * Grace period (ms) for the child's EOF-driven quiesce in * {@link SubagentRun.dispose} — the window to flush persistence and tear down - * its OWN nested subprocesses before the parent escalates to a signal. The + * its OWN nested subprocesses before the parent invokes provider termination. The * plugin fills this from its `disposeEofGraceMs` config. */ disposeEofGraceMs: number /** - * Termination-escalation grace (ms) in {@link SubagentRun.dispose}; POSIX - * waits this long after `SIGTERM` before `SIGKILL`, while Windows - * force-terminates directly. The plugin fills it from `disposeGraceMs`. + * Grace supplied to subprocess termination and output draining in + * {@link SubagentRun.dispose}. The plugin fills it from `disposeGraceMs`. */ disposeGraceMs: number /** * Spawn function from the subprocess seam (`ctx.subprocess.spawn`), so the - * child rides the shared scrub, tree-scoped teardown, and service-owned + * child rides the shared scrub, managed-range teardown, and service-owned * lifetime instead of a package-local child_process path. */ spawn: (spec: SubprocessSpawnSpec) => SubprocessHandle @@ -85,13 +84,13 @@ export interface AcpRunSpec { onError?: (error: Error, stopReason: SubagentStopReason) => void } -/** EOF grace for child flush and nested-process teardown; wider than the signal grace below. */ +/** EOF grace for child flush and nested-process teardown; wider than the termination grace below. */ export const DEFAULT_DISPOSE_EOF_GRACE_MS = 6_000 -/** Default POSIX grace between SIGTERM and SIGKILL on dispose (the `disposeGraceMs` config). */ +/** Default subprocess termination and output-drain grace (the `disposeGraceMs` config). */ export const DEFAULT_DISPOSE_GRACE_MS = 3_000 -/** Bounded whole-tree exit wait: polls the handle's tree liveness until it exits or `ms` elapses. */ +/** Bounded managed-range wait: polls the handle until its owned range exits or `ms` elapses. */ async function treeExitsWithin(child: SubprocessHandle, ms: number): Promise { const controller = new AbortController() const timer = setTimeout(() => { controller.abort() }, ms) @@ -104,10 +103,9 @@ async function treeExitsWithin(child: SubprocessHandle, ms: number): Promise {} diff --git a/packages/subagent/subagent-claude-code/src/process.ts b/packages/subagent/subagent-claude-code/src/process.ts index e9c3d81156..a01b4c560f 100644 --- a/packages/subagent/subagent-claude-code/src/process.ts +++ b/packages/subagent/subagent-claude-code/src/process.ts @@ -40,7 +40,7 @@ export function sdkEnvironmentOverlay( /** * Translate one official SDK spawn request to the shared process owner. * @param options - command, arguments, workspace, environment, and forwarded signal from the SDK. - * @param graceMs - process-tree termination grace. + * @param graceMs - subprocess termination and output-drain grace. * @returns the fully explicit shared subprocess request. */ export function claudeSpawnSpec( @@ -73,7 +73,7 @@ export class ManagedClaudeCodeProcess implements SpawnedProcess { /** * Project a managed process with piped stdin and stdout. - * @param child - shared handle that remains the process-tree authority. + * @param child - shared handle that remains the managed-range authority. */ constructor(private readonly child: SubprocessHandle) { this.stdin = child.stdin as NonNullable @@ -93,7 +93,7 @@ export class ManagedClaudeCodeProcess implements SpawnedProcess { ) } - /** Whether the SDK has requested managed tree termination. */ + /** Whether the SDK has requested managed-range termination. */ get killed(): boolean { return this.killRequested } @@ -114,8 +114,8 @@ export class ManagedClaudeCodeProcess implements SpawnedProcess { } /** - * Route the SDK's termination request to the tree-scoped process owner. - * @param _signal - SDK-selected signal; the shared seam owns its escalation ladder. + * Route the SDK's termination request to the managed-range owner. + * @param _signal - SDK-selected signal; the provider owns its termination procedure. * @returns false only after exit or a previous termination request. */ kill(_signal: NodeJS.Signals): boolean { diff --git a/packages/subagent/subagent-claude-code/src/run.ts b/packages/subagent/subagent-claude-code/src/run.ts index 3b0a19073d..4b74d9041a 100644 --- a/packages/subagent/subagent-claude-code/src/run.ts +++ b/packages/subagent/subagent-claude-code/src/run.ts @@ -1,7 +1,7 @@ /** * One-shot Claude Code lifecycle: invoke the official Agent SDK, place its * real CLI process under the shared subprocess owner, map only strict SDK - * success to completion, and dispose to whole-tree quiescence. + * success to completion, and dispose to managed-range quiescence. * * @module @deepseek-ai/dsh-subagent-claude-code/run */ @@ -36,7 +36,7 @@ import { ManagedClaudeCodeProcess, } from './process.ts' -/** Default POSIX grace between subprocess termination tiers. */ +/** Default subprocess termination and output-drain grace. */ export const DEFAULT_DISPOSE_GRACE_MS = 3_000 /** Claude Code permission modes that cannot wait for a human response. */ @@ -154,7 +154,7 @@ export interface ClaudeCodeRunSpec { readonly permissionMode: ClaudeCodePermissionMode /** Explicit deployment/test environment layered after shared scrubbing. */ readonly env: Record - /** Subprocess termination grace passed to the shared process-tree owner. */ + /** Grace passed to the shared subprocess owner. */ readonly disposeGraceMs: number /** Shared subprocess service spawn operation. */ readonly spawn: (spec: SubprocessSpawnSpec) => SubprocessHandle @@ -259,10 +259,10 @@ export async function consumeClaudeQuery( } /** - * Close the official query, terminate the managed process tree, and wait for - * the subprocess owner to prove it is gone. + * Close the official query, start managed-range termination, and wait for the + * subprocess owner to prove the range is empty. * @param query - official SDK query, when creation reached that point. - * @param child - live shared-service handle that owns the CLI process tree; + * @param child - live shared-service handle that owns the CLI managed range; * spawn-failed handles settle at the startup boundary instead. */ export async function disposeClaudeCodeChild( diff --git a/packages/subagent/subagent-codex/README.i18n.yaml b/packages/subagent/subagent-codex/README.i18n.yaml index 0f8ed31eab..6345a1581e 100644 --- a/packages/subagent/subagent-codex/README.i18n.yaml +++ b/packages/subagent/subagent-codex/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/subagent/subagent-codex/README.md -README.md: 975f353b9f1bc6fab61a4c0eb40ebaf50c436623 -README.zh.md: 2ea256afb3bb8fdfe57fd555b6db10522a709a56 +README.md: a0ae6a2f614e20dce0b20220706f63b5a993a8cf +README.zh.md: 4562285158283ba239182642565f83479331e343 diff --git a/packages/subagent/subagent-codex/README.md b/packages/subagent/subagent-codex/README.md index 975f353b9f..a0ae6a2f61 100644 --- a/packages/subagent/subagent-codex/README.md +++ b/packages/subagent/subagent-codex/README.md @@ -6,7 +6,7 @@ This package registers a Profile-named Codex subagent provider whose default nam ## Start and ownership -`start(request)` accepts only a non-empty sequence of text blocks and derives the child cwd from the parent Session. It then spawns the fixed command through [`dsh-subprocess`](../../subprocess/subprocess/README.md), performs `initialize` → `initialized`, maps the Profile-selected mode into official `thread/start` approval/reviewer/sandbox fields beside `{ cwd, ephemeral: true }`, and publishes the run only after Codex returns a valid ephemeral thread. A failure or cancellation before publication closes the wire, terminates the managed process tree, waits for it to exit, and rejects `start()`. Non-cancellation rejections expose only the fixed `initialize` or `thread-start` stage plus an already observed process outcome; raw product and Host errors remain on internal cause chains. +`start(request)` accepts only a non-empty sequence of text blocks and derives the child cwd from the parent Session. It then spawns the fixed command through [`dsh-subprocess`](../../subprocess/subprocess/README.md), performs `initialize` → `initialized`, maps the Profile-selected mode into official `thread/start` approval/reviewer/sandbox fields beside `{ cwd, ephemeral: true }`, and publishes the run only after Codex returns a valid ephemeral thread. A failure or cancellation before publication closes the wire, invokes managed-range termination, waits for the range to empty, and rejects `start()`. Non-cancellation rejections expose only the fixed `initialize` or `thread-start` stage plus an already observed process outcome; raw product and Host errors remain on internal cause chains. The published `run.result` starts exactly one turn. It accepts only notifications for that run's thread and turn, then waits for the authoritative `turn/completed` terminal notification. The latest `agentMessage` with `phase: "final_answer"` wins; when Codex emits no explicit final phase, the latest message with `phase: null` is the compatibility fallback. Commentary never replaces either answer, and a successful turn with no nonblank answer settles as an error. @@ -14,7 +14,7 @@ For command and file approvals, the unattended provider selects a non-approval d Local cancellation wins the result race and maps to `aborted`. For failed turns, the diagnostic preserves all eleven string and five object variants in the Codex 0.147.0 `codexErrorInfo` union; the four connection/stream variants retain a numeric `httpStatusCode` when supplied, while `activeTurnNotSteerable` does not expose `turnKind`. The diagnostic also names `turn-start`, `turn`, or `process`, independently includes available exit code and signal, and uses `unknown` for unrecognized or malformed values without copying raw fields. `contextWindowExceeded` remains `max-tokens`; every other remote interruption or failure remains `error`, and the provider produces no `refusal`. A contributing permission decision follows the structured failure line. Successful and locally cancelled runs omit both facts. -`dispose()` is idempotent: it requests a best-effort `turn/interrupt` with both current ids when they are known, closes the JSON-RPC wire, ends stdin, invokes the shared process-tree termination escalation, waits for whole-tree exit, and detaches the stderr observer. Independent cleanup rejection uses the fixed `teardown` stage and any available process outcome. When startup and rollback both fail, the top-level aggregate message preserves both safe stage lines while the raw failures remain internal. +`dispose()` is idempotent: it requests a best-effort `turn/interrupt` with both current ids when they are known, closes the JSON-RPC wire, ends stdin, invokes the subprocess provider's termination procedure, waits for managed-range exit, and detaches the stderr observer. Independent cleanup rejection uses the fixed `teardown` stage and any available process outcome. When startup and rollback both fail, the top-level aggregate message preserves both safe stage lines while the raw failures remain internal. ## Capabilities and context @@ -27,7 +27,7 @@ The provider advertises no optional start-time capabilities and reports `inherit | `providerName` | `codex` | Non-empty registry name on `ctx.subagents`; each mounted instance needs a unique value. | | `env` | `{}` | Explicit child environment layered over the subprocess seam's credential-scrubbed parent environment. | | `permissionMode` | `never` | Native non-interactive approval and sandbox mode fixed for every thread from this Provider instance. | -| `disposeGraceMs` | `3000` | Positive finite grace in milliseconds, no greater than [`MAX_TIMER_DELAY_MS`](../../util/timeout/README.md), between the shared process-tree owner's termination tiers; disposal then waits for whole-tree exit. | +| `disposeGraceMs` | `3000` | Positive finite grace in milliseconds, no greater than [`MAX_TIMER_DELAY_MS`](../../util/timeout/README.md), supplied to subprocess termination and output draining; disposal then waits for managed-range exit. | | `permissionMode` value | `thread/start` fields | Native behavior | |---|---|---| diff --git a/packages/subagent/subagent-codex/README.zh.md b/packages/subagent/subagent-codex/README.zh.md index 2ea256afb3..4562285158 100644 --- a/packages/subagent/subagent-codex/README.zh.md +++ b/packages/subagent/subagent-codex/README.zh.md @@ -6,7 +6,7 @@ ## 启动与所有权 -`start(request)` 只接受非空的文本块序列，并根据父会话确定子级 cwd。随后，它通过 [`dsh-subprocess`](../../subprocess/subprocess/README.zh.md) spawn 固定命令，依次执行 `initialize` → `initialized`，把 Profile 选择的模式映射为官方 `thread/start` approval／reviewer／sandbox 字段并与 `{ cwd, ephemeral: true }` 一起发送，且仅在 Codex 返回有效的临时线程后才发布此次运行。若在发布前发生失败或取消，它会关闭通信链路、终止受管进程树并等待其退出，然后拒绝 `start()` 调用。非取消拒绝只公开固定的 `initialize` 或 `thread-start` 阶段及已经观测到的进程结果；原始产品与 Host 错误只保留在内部 cause 链中。 +`start(request)` 只接受非空的文本块序列，并根据父会话确定子级 cwd。随后，它通过 [`dsh-subprocess`](../../subprocess/subprocess/README.zh.md) spawn 固定命令，依次执行 `initialize` → `initialized`，把 Profile 选择的模式映射为官方 `thread/start` approval／reviewer／sandbox 字段并与 `{ cwd, ephemeral: true }` 一起发送，且仅在 Codex 返回有效的临时线程后才发布此次运行。若在发布前发生失败或取消，它会关闭通信链路、启动 managed-range 终止并等待该范围为空，然后拒绝 `start()` 调用。非取消拒绝只公开固定的 `initialize` 或 `thread-start` 阶段及已经观测到的进程结果；原始产品与 Host 错误只保留在内部 cause 链中。 已发布的 `run.result` 恰好启动一个轮次。它只接受与此次运行的线程和轮次匹配的通知，随后等待权威的终止通知 `turn/completed`。以最后一条 `phase: "final_answer"` 的 `agentMessage` 为准；若 Codex 没有发出明确的最终阶段，则以最后一条 `phase: null` 的消息作为兼容性回退。过程说明绝不会取代上述任一答案；成功完成的轮次若没有非空白答案，结果也会判为错误。 @@ -14,7 +14,7 @@ 本地取消会在结果竞态中胜出并映射为 `aborted`。对于失败轮次，诊断会保留 Codex 0.147.0 `codexErrorInfo` 联合中的全部十一种字符串与五种对象 variant；四种连接／stream variant 会在上游提供时保留数值 `httpStatusCode`，而 `activeTurnNotSteerable` 不公开 `turnKind`。诊断还会注明 `turn-start`、`turn` 或 `process`，分别包含可用的退出码与信号，并对无法识别或格式错误的值使用 `unknown`，且不复制原始字段。`contextWindowExceeded` 仍映射为 `max-tokens`；其他任何远端中断或失败仍映射为 `error`，且该提供方不会产生 `refusal`。参与失败的权限决定会跟在结构化失败行之后。成功与本地取消都不附带这两类事实。 -`dispose()`（资源释放）具有幂等性：如果当前的两个标识符均已知，它会尽力请求 `turn/interrupt`，关闭 JSON-RPC 通信链路，结束标准输入，调用共享的进程树逐级终止机制，等待整棵进程树退出，并移除 stderr observer。独立清理拒绝使用固定的 `teardown` 阶段与可用进程结果。当启动与回滚同时失败时，顶层聚合消息会保留两条安全阶段说明，而原始失败仍只在内部可见。 +`dispose()`（资源释放）具有幂等性：如果当前的两个标识符均已知，它会尽力请求 `turn/interrupt`，关闭 JSON-RPC 通信链路，结束标准输入，调用 subprocess provider 的终止过程，等待 managed range 退出，并移除 stderr observer。独立清理拒绝使用固定的 `teardown` 阶段与可用进程结果。当启动与回滚同时失败时，顶层聚合消息会保留两条安全阶段说明，而原始失败仍只在内部可见。 ## 能力与上下文 @@ -27,7 +27,7 @@ | `providerName` | `codex` | `ctx.subagents` 中的非空注册名称；每个已挂载实例都需要唯一值。 | | `env` | `{}` | 显式指定的子进程环境，叠加在由子进程 seam 清除凭证后的父环境之上。 | | `permissionMode` | `never` | 为该提供方实例的每个线程固定原生非交互审批与沙箱模式。 | -| `disposeGraceMs` | `3000` | 共享进程树责任方各终止层级之间的宽限期，单位为毫秒且须为正有限值，并不得大于仓库共享的 [`MAX_TIMER_DELAY_MS`](../../util/timeout/README.zh.md)；随后资源释放会等待整棵进程树退出。 | +| `disposeGraceMs` | `3000` | 提供给 subprocess 终止与输出排空的宽限期，单位为毫秒且须为正有限值，并不得大于仓库共享的 [`MAX_TIMER_DELAY_MS`](../../util/timeout/README.zh.md)；随后资源释放会等待 managed range 退出。 | | `permissionMode` 值 | `thread/start` 字段 | 原生行为 | |---|---|---| diff --git a/packages/subagent/subagent-codex/src/index.ts b/packages/subagent/subagent-codex/src/index.ts index 79fbdab078..6089a69d75 100644 --- a/packages/subagent/subagent-codex/src/index.ts +++ b/packages/subagent/subagent-codex/src/index.ts @@ -43,7 +43,7 @@ export interface Config { env?: Record /** Native non-interactive permission mode fixed for this Provider instance. */ permissionMode?: CodexPermissionMode - /** Grace in milliseconds for app-server process-tree termination. */ + /** Grace in milliseconds for app-server termination and output draining. */ disposeGraceMs?: number } diff --git a/packages/subagent/subagent-codex/src/invariant.ts b/packages/subagent/subagent-codex/src/invariant.ts index ec9a6302c4..0c350fffa7 100644 --- a/packages/subagent/subagent-codex/src/invariant.ts +++ b/packages/subagent/subagent-codex/src/invariant.ts @@ -16,7 +16,7 @@ export const inject = ['invariants'] /** * No runtime invariant: lifecycle pairing belongs to the shared subagent - * service and process-tree ownership belongs to the subprocess service. + * service and managed-range ownership belongs to the subprocess service. */ const install: InvariantInstaller = () => {} diff --git a/packages/subagent/subagent-codex/src/run.ts b/packages/subagent/subagent-codex/src/run.ts index 9db5d7086c..025cbb42d9 100644 --- a/packages/subagent/subagent-codex/src/run.ts +++ b/packages/subagent/subagent-codex/src/run.ts @@ -1,7 +1,7 @@ /** * One-shot Codex child lifecycle: spawn the real app-server through the * subprocess seam, publish only after initialization and ephemeral thread - * creation, flatten post-publication failures, and dispose to whole-tree + * creation, flatten post-publication failures, and dispose to managed-range * quiescence. * * @module @deepseek-ai/dsh-subagent-codex/run @@ -31,7 +31,7 @@ import { type CodexWireFailureFacts, } from './wire.ts' -/** Default POSIX grace between subprocess termination tiers. */ +/** Default subprocess termination and output-drain grace. */ export const DEFAULT_DISPOSE_GRACE_MS = 3_000 interface CodexPackageManifest { @@ -141,7 +141,7 @@ export interface CodexRunSpec { readonly permissionMode: CodexPermissionMode /** Explicit deployment/test environment layered after the shared scrub. */ readonly env: Record - /** Subprocess termination grace passed to the shared process-tree owner. */ + /** Grace passed to the shared subprocess owner. */ readonly disposeGraceMs: number /** Shared subprocess service spawn operation. */ readonly spawn: (spec: SubprocessSpawnSpec) => SubprocessHandle @@ -177,10 +177,10 @@ export function textTask(prompt: readonly ContentBlock[]): string[] { } /** - * Close the private wire, terminate the managed process tree, and wait for the - * subprocess owner to prove it is gone. + * Close the private wire, start managed-range termination, and wait for the + * subprocess owner to prove the range is empty. * @param wire - private app-server protocol connection. - * @param child - shared-service handle that owns the process tree. + * @param child - shared-service handle that owns the managed range. */ export async function disposeCodexChild( wire: CodexAppServerWire, diff --git a/packages/subagent/subagent-codex/tests/subagent-codex.spec.ts b/packages/subagent/subagent-codex/tests/subagent-codex.spec.ts index 38c93dee23..58aa8798a6 100644 --- a/packages/subagent/subagent-codex/tests/subagent-codex.spec.ts +++ b/packages/subagent/subagent-codex/tests/subagent-codex.spec.ts @@ -2296,7 +2296,7 @@ describe('disposeCodexChild', () => { .resolves.toBeUndefined() }) - it('handles a spawn-level failure with no process tree', async () => { + it('handles a spawn-level failure with no managed range', async () => { const child = fakeChild({ pid: -1, doneError: new Error('spawn failed'), diff --git a/packages/subagent/subagent/src/out-of-process.ts b/packages/subagent/subagent/src/out-of-process.ts index abb6dd50e7..edaf0286ef 100644 --- a/packages/subagent/subagent/src/out-of-process.ts +++ b/packages/subagent/subagent/src/out-of-process.ts @@ -5,7 +5,7 @@ * working-directory resolution (config override, else the delegating parent * session's workspace), the never-reject result settlement, and the standard * run-handle publication. Backends compose these with their own wire drivers; - * the process machinery itself (spawn, env scrub, tree-scoped teardown) + * the process machinery itself (spawn, env scrub, managed-range teardown) * belongs to the `dsh-subprocess` seam. * * @module @deepseek-ai/dsh-subagent/out-of-process diff --git a/packages/subprocess/README.i18n.yaml b/packages/subprocess/README.i18n.yaml index cb27192356..a240b04ac4 100644 --- a/packages/subprocess/README.i18n.yaml +++ b/packages/subprocess/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/subprocess/README.md -README.md: 1b516c36d81a51fc2e0023d69f748cb4b46f36a4 -README.zh.md: cb83d0a9d417114f20e8fbd970f57c5d917f736f +README.md: dfb5763d3ac867ddd5b941d5619bf88a2da73cda +README.zh.md: 3f0e7f930133468dcb83ef47e5ec35c67f44ce63 diff --git a/packages/subprocess/README.md b/packages/subprocess/README.md index 1b516c36d8..dfb5763d3a 100644 --- a/packages/subprocess/README.md +++ b/packages/subprocess/README.md @@ -2,12 +2,12 @@ English | [中文](README.zh.md) -The shared process substrate for one execution world: executable lookup, fully-specified managed child-process trees with raw or collected stdio, and one deep terminal-process primitive that owns PTY allocation, foreground groups, and provider-observable session cleanup. Command defaulting, shell semantics, deadlines, protocol framing, readiness, and presentation stay with consumers — the [bash executors](../shell/README.md), [LSP host](../lsp/README.md), [PTY shell backend](../terminal/README.md), and [ACP subagent backend](../subagent/README.md). See the [subprocess seam Agent Note](../../.agents/notes/implemented/architecture/2026-07-26-subprocess-seam.md). +The shared process substrate for one execution world: executable lookup, fully specified provider-managed ranges with raw or collected stdio, and one deep terminal-process primitive that owns PTY allocation, foreground groups, and provider-observable session cleanup. Command defaulting, shell semantics, deadlines, protocol framing, readiness, and presentation stay with consumers — the [bash executors](../shell/README.md), [LSP host](../lsp/README.md), [PTY shell backend](../terminal/README.md), and [ACP subagent backend](../subagent/README.md). See the [subprocess seam Agent Note](../../.agents/notes/implemented/architecture/2026-07-26-subprocess-seam.md). | Package | ctx key | Role | |---|---|---| | [`subprocess`](subprocess/README.md) (`@deepseek-ai/dsh-subprocess`) | `ctx.subprocess` | Service Definition: executable lookup, ordinary managed spawns, the terminal-process primitive, handle lifecycles, and shared environment/output vocabulary | -| [`subprocess-local`](subprocess-local/README.md) (`@deepseek-ai/dsh-subprocess-local`) | — | Local Service Provider: detached process trees, bounded collection/spill, `node-pty`, foreground/session inspection, tree signalling, and terminate-and-join disposal | +| [`subprocess-local`](subprocess-local/README.md) (`@deepseek-ai/dsh-subprocess-local`) | — | Local Service Provider: native and fallback managed ranges, bounded collection/spill, `node-pty`, foreground/session inspection, signalling, and terminate-and-join disposal | | [`win32-process`](win32-process/README.md) (`@deepseek-ai/dsh-win32-process`) | — | Windows-only low-level library: the single Koffi owner for sandbox and ordinary process creation, inherited/anonymous-pipe stdio, suspended Job assignment, polling, waits, and handle cleanup | The service owns process lifetime across consumer reloads; consumers own what a process means (a bash command, a future non-shell runner) and every default that shapes one. diff --git a/packages/subprocess/README.zh.md b/packages/subprocess/README.zh.md index cb83d0a9d4..3f0e7f9301 100644 --- a/packages/subprocess/README.zh.md +++ b/packages/subprocess/README.zh.md @@ -2,12 +2,12 @@ [English](README.md) | 中文 -这里集中提供一个执行世界的共享进程基底：可执行文件查找、具有原始或收集式 stdio 的完全明确指定的受管子进程树，以及一项底层终端进程原语，负责 PTY 分配、前台进程组和提供方仍可观察到的会话成员清理。命令默认值补全、shell 语义、时限、协议分帧、就绪状态与呈现留在消费方：[bash 执行器](../shell/README.zh.md)、[LSP 主机](../lsp/README.zh.md)、[PTY shell 后端](../terminal/README.zh.md)与 [ACP（Agent Client Protocol）subagent 后端](../subagent/README.zh.md)。参见 [subprocess seam Agent Note](../../.agents/notes/implemented/architecture/2026-07-26-subprocess-seam.zh.md)。 +这里集中提供一个执行世界的共享进程基底：可执行文件查找、具有原始或收集式 stdio 的完整 provider-managed range，以及一项底层终端进程原语，负责 PTY 分配、前台进程组和 provider 仍可观察到的会话成员清理。命令默认值补全、shell 语义、时限、协议分帧、就绪状态与呈现留在消费方：[bash 执行器](../shell/README.zh.md)、[LSP 主机](../lsp/README.zh.md)、[PTY shell 后端](../terminal/README.zh.md)与 [ACP（Agent Client Protocol）subagent 后端](../subagent/README.zh.md)。参见 [subprocess seam Agent Note](../../.agents/notes/implemented/architecture/2026-07-26-subprocess-seam.zh.md)。 | 包 | ctx 键 | 角色 | |---|---|---| | [`subprocess`](subprocess/README.zh.md)（`@deepseek-ai/dsh-subprocess`） | `ctx.subprocess` | Service Definition：可执行文件查找、普通受管 spawn、终端进程原语、句柄生命周期，以及共享的环境／输出词汇 | -| [`subprocess-local`](subprocess-local/README.zh.md)（`@deepseek-ai/dsh-subprocess-local`） | 无 | 本地 Service Provider：detached 进程树、有界收集／spill、`node-pty`、前台／会话检查、进程树信号发送，以及先终止再等待退出的 dispose（资源释放） | +| [`subprocess-local`](subprocess-local/README.zh.md)（`@deepseek-ai/dsh-subprocess-local`） | 无 | 本地 Service Provider：native 与 fallback managed range、有界收集／spill、`node-pty`、前台／会话检查、信号发送，以及先终止再等待退出的 dispose（资源释放） | | [`win32-process`](win32-process/README.zh.md)（`@deepseek-ai/dsh-win32-process`） | 无 | 仅限 Windows 的底层库：sandbox 与 ordinary process creation、继承／匿名管道 stdio、suspended Job 分配、polling、wait 与句柄清理的唯一 Koffi owner | 即使消费方重载，进程生命周期仍由服务负责管理；消费方负责定义进程的含义（一条 bash 命令、未来的非 shell 运行器），以及决定塑造该进程的每一项默认值。 diff --git a/packages/subprocess/subprocess-local/src/index.ts b/packages/subprocess/subprocess-local/src/index.ts index 5d30fa50ba..1e77a36b97 100644 --- a/packages/subprocess/subprocess-local/src/index.ts +++ b/packages/subprocess/subprocess-local/src/index.ts @@ -165,10 +165,9 @@ export class LocalSubprocessRuntime extends SubprocessRuntime { handle = bindManagedProcess(spec, launch, binding) } this.live.add(handle) - // Release ownership only once the whole TREE is gone, not at direct-child - // settlement — a TERM-trapping helper that outlives the leader must stay - // owned so teardown can still escalate it. For the common no-survivor - // case waitForExit resolves immediately after settlement. + // Release ownership only once the managed range is empty, not at spawned- + // command settlement. A surviving helper remains owned until provider + // termination and observation reach quiescence. const release = (): Promise => handle.waitForExit().then(() => { this.live.delete(handle) }) void handle.done.then(release, release).catch(() => {}) diff --git a/packages/subprocess/subprocess-local/src/spawn.ts b/packages/subprocess/subprocess-local/src/spawn.ts index b579fb022a..7dcb054d06 100644 --- a/packages/subprocess/subprocess-local/src/spawn.ts +++ b/packages/subprocess/subprocess-local/src/spawn.ts @@ -1,6 +1,6 @@ /** - * Process plumbing for the local subprocess service: detached process-tree - * spawn with per-stream stdio dispositions, tail-keep collection with spill + * Process plumbing for the local subprocess service: ordinary process launch + * with per-stream stdio dispositions, tail-keep collection with spill * files, provider-owned range signalling, and common termination scheduling. * POSIX owners stage TERM before KILL; Windows owners terminate immediately. * This layer reacts to an abort signal; callers own deadlines, teardown @@ -420,7 +420,7 @@ function fallbackOwner( } /** - * Bind platform launch facts to the existing stdio, outcome, abort, and escalation lifecycle. + * Bind platform launch facts to the existing stdio, outcome, abort, and termination lifecycle. * @param spec - fully resolved argv, cwd, stdio, grace, cancellation, environment. * @param launch - platform child streams, direct outcome, and managed-range owner. * @param internals - test-only spill-directory override. @@ -539,8 +539,8 @@ export function bindManagedProcess( if (directOutcome !== undefined) settle(directOutcome) }) function cleanup(): void { - // graceTimer deliberately NOT cleared: the SIGKILL escalation must be - // able to reach tree survivors after the direct child settles. + // graceTimer deliberately NOT cleared: the forced termination call must + // still reach range survivors after the spawned command settles. if (pipeDrainTimer !== undefined) clearTimeout(pipeDrainTimer) } }) diff --git a/packages/subprocess/subprocess-local/src/windows-job.ts b/packages/subprocess/subprocess-local/src/windows-job.ts index 3de46915da..717c28dc6a 100644 --- a/packages/subprocess/subprocess-local/src/windows-job.ts +++ b/packages/subprocess/subprocess-local/src/windows-job.ts @@ -39,19 +39,33 @@ export function probeWindowsJob(internals: WindowsJobInternals = {}): boolean { class WindowsJobOwner implements BoundProcessOwner { private stopped = false + private runnerClosed = false private readonly observation: Promise constructor(private readonly runner: ReturnType) { - this.observation = new Promise((resolve) => { - runner.once('close', () => { - this.stopped = true - resolve() + this.observation = new Promise((resolve, reject) => { + runner.once('close', (exitCode, signal) => { + this.runnerClosed = true + if (exitCode === 0 && signal === null) { + this.stopped = true + resolve() + return + } + const status = signal !== null + ? `signal ${signal}` + : exitCode === null + ? 'without an exit status' + : `exit code ${String(exitCode)}` + reject(new Error( + `subprocess-local: Windows Job runner exited with ${status} before proving its managed range empty`, + )) }) }) + void this.observation.catch(() => {}) } signal(_signal: NodeJS.Signals): void { - if (this.stopped) return + if (this.stopped || this.runnerClosed) return try { if (this.runner.connected) { this.runner.send({ type: 'terminate' }, (error) => { diff --git a/packages/subprocess/subprocess-local/tests/fixtures/fake-job-runner.ts b/packages/subprocess/subprocess-local/tests/fixtures/fake-job-runner.ts index c3971b5077..2dd5451f03 100644 --- a/packages/subprocess/subprocess-local/tests/fixtures/fake-job-runner.ts +++ b/packages/subprocess/subprocess-local/tests/fixtures/fake-job-runner.ts @@ -7,10 +7,11 @@ const request = consumeRunnerRequest(requestPath) appendRunnerEvent(eventsPath, { type: 'started', pid: process.pid }) const configuredExit = Number(request.argv[1]) +// Events carry target results; zero means the runner completed its own observation. if (Number.isSafeInteger(configuredExit)) { setTimeout(() => { appendRunnerEvent(eventsPath, { type: 'exit', exitCode: configuredExit, signal: null }) - process.exitCode = configuredExit + process.exitCode = 0 }, 10) } else { const hold = setInterval(() => {}, 1_000) @@ -21,7 +22,7 @@ if (Number.isSafeInteger(configuredExit)) { appendRunnerEvent(eventsPath, { type: 'exit', exitCode: 1, signal: null }) clearInterval(hold) if (process.connected) process.disconnect() - process.exitCode = 1 + process.exitCode = 0 } process.on('message', (message: unknown) => { if (message !== null && typeof message === 'object' && (message as { type?: unknown }).type === 'terminate') terminate() diff --git a/packages/subprocess/subprocess-local/tests/native-windows.spec.ts b/packages/subprocess/subprocess-local/tests/native-windows.spec.ts index c89b46581a..98427dfc16 100644 --- a/packages/subprocess/subprocess-local/tests/native-windows.spec.ts +++ b/packages/subprocess/subprocess-local/tests/native-windows.spec.ts @@ -114,6 +114,8 @@ describe.skipIf(!windowsNative)('Windows Job native containment', () => { handle.stdout?.once('end', resolve) handle.stdout?.once('error', reject) }) + // A Readable reports `end` only after the consumer drains any buffered bytes. + handle.stdout.resume() const descendant = await waitForPid(pidFile) try { await expect(handle.done).resolves.toEqual({ exitCode: 42, signal: null }) diff --git a/packages/subprocess/subprocess-local/tests/windows-job.spec.ts b/packages/subprocess/subprocess-local/tests/windows-job.spec.ts index 0d69a52331..4e1d03c055 100644 --- a/packages/subprocess/subprocess-local/tests/windows-job.spec.ts +++ b/packages/subprocess/subprocess-local/tests/windows-job.spec.ts @@ -60,6 +60,33 @@ describe('Windows Job runner adapter', () => { launch.owner.signal('SIGKILL') }) + it.each([ + { exitCode: 127, signal: null, status: 'exit code 127' }, + { exitCode: null, signal: 'SIGTERM' as NodeJS.Signals, status: 'signal SIGTERM' }, + { exitCode: null, signal: null, status: 'without an exit status' }, + ])('rejects range settlement when the runner exits with $status', async ({ exitCode, signal, status }) => { + const child = new EventEmitter() as ChildProcess + const kill = vi.fn(() => true) + Object.assign(child, { pid: 432, connected: false, kill }) + let eventsPath = '' + const run = vi.fn((_command: string, args: readonly string[]) => { + eventsPath = args[args.indexOf('--events') + 1] as string + appendRunnerEvent(eventsPath, { type: 'started', pid: 432 }) + return child + }) as unknown as typeof spawn + const launch = launchWindowsJob(spec(['fake-target']), { spawn: run, runnerInvocation: ['fake-runner'] }) + const directFailure = launch.direct.catch((error: unknown) => error) + + child.emit('close', exitCode, signal) + + await expect(launch.owner.waitForExit()).rejects.toThrow( + `Windows Job runner exited with ${status} before proving its managed range empty`, + ) + await expect(directFailure).resolves.toBeInstanceOf(Error) + launch.owner.signal('SIGKILL') + expect(kill).not.toHaveBeenCalled() + }) + it('falls back to killing the runner when IPC delivery is unavailable or fails', async () => { for (const mode of ['callback-error', 'disconnected', 'throw'] as const) { const child = new EventEmitter() as ChildProcess diff --git a/packages/subprocess/subprocess/README.i18n.yaml b/packages/subprocess/subprocess/README.i18n.yaml index 398e87e81c..decbfdc80f 100644 --- a/packages/subprocess/subprocess/README.i18n.yaml +++ b/packages/subprocess/subprocess/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/subprocess/subprocess/README.md -README.md: 61aec9024427a6530f4e877c2fd35cdf301af169 -README.zh.md: 4740bef7062162f444cdf7b713ed4a5c52fc02be +README.md: 20f2edea5d29e152ae01a968b81cbc79e9bb69e5 +README.zh.md: ea4801de670a90b6b158830a7f8b19ea936c6e5c diff --git a/packages/subprocess/subprocess/README.md b/packages/subprocess/subprocess/README.md index 61aec90244..20f2edea5d 100644 --- a/packages/subprocess/subprocess/README.md +++ b/packages/subprocess/subprocess/README.md @@ -10,7 +10,7 @@ The subprocess seam (`ctx.subprocess`) is the process half of one execution worl - Spawn working directories and executable paths belong to the provider's execution world. `resolveExecutable(command, env?, signal?)` verifies absolute commands or resolves bare names against that world's scrubbed PATH plus explicit overrides. - The spec is fully explicit — argv, cwd, per-stream stdio dispositions, grace — because deployment-varying defaults belong to the caller's config, not to a hidden subprocess-service default (the `dsh-shell` request/spec split is the owning template). `argv` is never shell-interpreted; a consumer that wants a shell passes `['bash', '-c', command]` itself. - Stdio is Node-shaped per stream: `'pipe'` hands the caller the raw stream for its own protocol framing (LSP JSON-RPC, ACP ndjson), `'inherit'` passes the parent descriptor through for diagnostics, and collect mode (`{ maxBytes, spill? }`) buffers a bounded tail with an optional full-stream spill file. Collect readers take whole-stream byte offsets and never consume, so independent readers cannot steal one another's deltas; a read whose offset slid out of the in-memory tail is `lossy` and points at the spill file when one exists. Collected output stays readable after settlement. -- Termination and waiting use one provider-managed range. `terminate()` — the only termination verb — starts the provider's documented procedure (idempotent, driven by the spec's abort signal too, and a no-op once the range is empty), while `waitForExit(signal?)` observes that same range so a consumer-owned teardown ladder holds each tier on real quiescence. Staged providers may use `graceMs` between graceful and forced steps; immediate providers do not delay. Each provider documents how it defines, signals, and observes the range, including weaker fallbacks; the [local provider](../subprocess-local/README.md) owns its systemd, Job, process-group, and `taskkill` details. The wait rejects when a selected owner can no longer observe its range; the manager reacts but never classifies why (callers own deadlines, teardown ladders, and cause classification). +- Termination and waiting use one provider-managed range. `terminate()` — the only termination verb — starts the provider's documented procedure (idempotent, driven by the spec's abort signal too, and a no-op once the range is empty), while `waitForExit(signal?)` observes that same range so consumer teardown can await real quiescence. Staged providers may use `graceMs` between graceful and forced steps; immediate providers do not delay. Each provider documents how it defines, signals, and observes the range, including weaker fallbacks; the [local provider](../subprocess-local/README.md) owns its systemd, Job, process-group, and `taskkill` details. The wait rejects when a selected owner can no longer observe its range; the manager reacts but never classifies why (callers own deadlines, teardown ladders, and cause classification). - `spawnTerminal(spec)` is the only non-pipe primitive. Its handle owns a real PTY, UTF-8 text I/O, foreground-process-group inspection/signalling, and one awaited `terminate()` operation that reaches quiescence for every session member the provider can still observe and settles in-flight handle calls; providers document substrate-specific observability limits. The spec signal cancels allocation only; the published handle owns its lifetime. The output stream ends after queued output when the top-level process exits, and a live transport failure rejects `done`. These operations remain one substrate primitive because ordinary pipes cannot allocate a controlling terminal or clean terminal-session members; readiness, scrollback, and owner policy remain in the PTY consumer. - `scrubbedParentEnv()` / `SENSITIVE_ENV_PATTERN` are the one shared scrub definition: ambient credential-shaped and `DSH_*` names are dropped, and explicit `env` merges after the scrub. The local ordinary and terminal spawns both apply it; SDK-managed transports that own their spawn may import it directly. - Disposal of the service terminates all still-running managed processes and awaits their exit. diff --git a/packages/subprocess/subprocess/README.zh.md b/packages/subprocess/subprocess/README.zh.md index 4740bef706..ea4801de67 100644 --- a/packages/subprocess/subprocess/README.zh.md +++ b/packages/subprocess/subprocess/README.zh.md @@ -10,7 +10,7 @@ - spawn 工作目录和可执行文件路径属于提供方的执行世界。`resolveExecutable(command, env?, signal?)` 验证绝对命令，或根据该执行世界清理后的 PATH 加显式覆盖来解析裸名称。 - spec 完全显式（argv、cwd、按流划分的 stdio 处置方式（disposition）、宽限期），因为随部署变化的默认值属于调用方的配置，而不属于某个隐藏的子进程服务默认值（`dsh-shell` 的 request/spec 拆分是这条规则的所属模板）。`argv` 绝不经过 shell 解释；需要 shell 的消费方自行传入 `['bash', '-c', command]`。 - stdio 按流采用 Node 风格：`'pipe'` 把原始流交给调用方做自己的协议分帧（LSP 的 JSON-RPC、ACP（Agent Client Protocol）的 ndjson），`'inherit'` 直通父进程描述符以承载诊断输出，收集模式（collect）`{ maxBytes, spill? }` 则缓冲一段有界尾部，外加可选的完整流 spill 文件。收集模式的读取器接受全流字节偏移量且从不消费，因此独立的读取器不会抢走彼此的增量；偏移量滑出内存尾部窗口的读取标记为 `lossy`，并在 spill 文件存在时指向它。收集到的输出在结算后仍可读取。 -- 终止与等待使用同一个 provider-managed range。`terminate()`（唯一的终止动词）启动 provider 记录的终止过程（幂等，也由 spec 的 abort 信号驱动，并在范围为空后成为空操作）；`waitForExit(signal?)` 观察同一范围，使消费方自有的拆卸阶梯能在真正完全停稳后才进入下一层。分阶段 provider 可以用 `graceMs` 分隔温和与强制步骤，立即终止的 provider 不会等待。每个 provider 记录该范围的定义、信号与观察方式，包括较弱 fallback；[本地 provider](../subprocess-local/README.zh.md)拥有 systemd、Job、进程组与 `taskkill` 的具体说明。所选 owner 不再能观察范围时，该等待会 reject；管理器只响应中止，但绝不判定原因（deadline、拆卸阶梯与原因分类归调用方所有）。 +- 终止与等待使用同一个 provider-managed range。`terminate()`（唯一的终止动词）启动 provider 记录的终止过程（幂等，也由 spec 的 abort 信号驱动，并在范围为空后成为空操作）；`waitForExit(signal?)` 观察同一范围，使消费方拆卸可以等待真正完全停稳。分阶段 provider 可以用 `graceMs` 分隔温和与强制步骤，立即终止的 provider 不会等待。每个 provider 记录该范围的定义、信号与观察方式，包括较弱 fallback；[本地 provider](../subprocess-local/README.zh.md)拥有 systemd、Job、进程组与 `taskkill` 的具体说明。所选 owner 不再能观察范围时，该等待会 reject；管理器只响应中止，但绝不判定原因（deadline、拆卸阶梯与原因分类归调用方所有）。 - `spawnTerminal(spec)` 是唯一的非管道原语。其句柄负责真实 PTY、UTF-8 文本 I/O、前台进程组检查／信号发送，以及一项须等待的 `terminate()` 操作；该操作会使提供方仍可观察到的每个会话成员完全停稳，并结算在途句柄调用；提供方会记录执行基底特有的可观察性限制。spec 信号只取消分配；句柄一经发布，便负责自身生命周期。顶层进程退出时，输出流在已排队输出之后结束；仍处于活动状态的传输若发生故障，会使 `done` 拒绝。这些操作保留为一项执行基底原语，因为普通管道无法分配控制终端或清理终端会话成员；就绪状态、scrollback 和所有者策略仍归 PTY 消费方所有。 - `scrubbedParentEnv()` / `SENSITIVE_ENV_PATTERN` 是唯一一份共享的环境清理定义：环境中形似凭据的名称与 `DSH_*` 名称都会被丢弃，显式 `env` 在清除之后合并。本地的普通 spawn 与终端 spawn 都应用该定义；拥有自身 spawn 的 SDK 管理传输可直接导入它。 - 服务自身的 dispose（资源释放）会终止所有仍在运行的受管进程并等待其退出。 diff --git a/packages/subprocess/subprocess/src/index.ts b/packages/subprocess/subprocess/src/index.ts index 8fc9773df7..c6a452bbec 100644 --- a/packages/subprocess/subprocess/src/index.ts +++ b/packages/subprocess/subprocess/src/index.ts @@ -90,9 +90,9 @@ declare module '@deepseek-ai/cordis' { * streams are handed to the caller raw and never buffered here. * - {@link SubprocessHandle.terminate} (and the spec's abort signal) starts the * provider's documented procedure against its managed range. - * {@link SubprocessHandle.waitForExit} observes that same range so a - * consumer-owned teardown ladder can hold each tier on real quiescence; each - * provider documents its identity, signalling, and observability limits. + * {@link SubprocessHandle.waitForExit} observes that same range so consumer + * teardown can await real quiescence; each provider documents its identity, + * signalling, and observability limits. * - Disposal of the service terminates all still-running managed processes * and awaits their exit. * - {@link spawnTerminal} owns terminal allocation, text transport, diff --git a/packages/subprocess/subprocess/src/types.ts b/packages/subprocess/subprocess/src/types.ts index c2b43f919f..0ef3f5f981 100644 --- a/packages/subprocess/subprocess/src/types.ts +++ b/packages/subprocess/subprocess/src/types.ts @@ -89,9 +89,9 @@ export interface SubprocessSpawnSpec { */ graceMs: number /** - * Abort signal — starts the terminate escalation on the managed range when - * it fires. The caller owns deadlines and cause classification; this seam - * only reacts to the abort. + * Abort signal — starts the provider's termination procedure on the managed + * range when it fires. The caller owns deadlines and cause classification; + * this seam only reacts to the abort. */ signal?: AbortSignal | undefined /** diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index 5e19c20113..d5ebe108c6 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -387,7 +387,7 @@ const SERVICE_ROLES: ServiceRole[] = [ mode: 'seam', implementations: ['subprocess-local', 'subprocess-e2b'], consumers: ['bash-local', 'bash-sandbox', 'terminal-bash', 'lsp-stdio', 'subagent-acp', 'subagent-codex', 'subagent-claude-code'], - note: 'The bash executors, the PTY shell backend, the LSP host, and the out-of-process ACP, Codex, and Claude Code subagent backends spawn through ctx.subprocess; the service owns process coordinates, tree/session lifetime, stdio dispositions, terminal mechanics, and kill escalation.', + note: 'The bash executors, the PTY shell backend, the LSP host, and the out-of-process ACP, Codex, and Claude Code subagent backends spawn through ctx.subprocess; the service owns process coordinates, managed-range/session lifetime, stdio dispositions, terminal mechanics, and provider-defined termination.', }, { key: 'shell',