Merge remote-tracking branch 'origin/master' into worktree/web-session-model-selector
# Conflicts: # apps/cli/package.json # apps/web/tests/smoke-real.e2e.ts # apps/web/tests/snapshots/fresh-round-trip/ui.expected.md # apps/web/tests/snapshots/seeded-history/ui.expected.md # docs/config-catalog.md # packages/client/connection/tests/fake-api.ts # packages/client/runtime/src/client/index.ts # packages/client/runtime/src/client/sessions/conversation.ts # packages/client/runtime/src/client/sessions/session.ts # packages/client/runtime/tests/fake-api.ts # packages/client/ui-conversation/src/client/apply.ts # packages/client/ui-conversation/src/client/contract/slots.ts # packages/client/ui-conversation/src/client/index.ts # packages/client/ui-conversation/src/client/skeleton/ConversationRoot.tsx # packages/client/ui-conversation/src/client/skeleton/InputBar.tsx # packages/client/ui-conversation/tests/chat-stats-bash-sample.spec.tsx # packages/client/ui-conversation/tests/chat-toolview-slot.spec.tsx # packages/client/ui-conversation/tests/chat-view.spec.tsx # packages/client/ui-conversation/tests/gate-branch-tails.spec.tsx # packages/client/ui-conversation/tests/input-bar.spec.tsx # packages/client/ui-conversation/tests/skeleton.spec.tsx # packages/host/apiproxy/README.md # packages/host/apiproxy/src/api-proxy.ts # pnpm-lock.yaml # scripts/verify-package-readme-model-experience.ts # tsconfig.base.json
This commit is contained in:
Yichen Jiang
@@ -6,6 +6,8 @@ These Agent Notes describe shipped decisions. Follow the [root instructions](../
|
||||
|
||||
Keep paths, symbols, defaults, and mechanisms current in the same change that alters them. Rewrite stale facts in place; do not append change history.
|
||||
|
||||
When a shipped note is unlikely to guide future work, archive its complete triplet through [`dsh-archive-agent-notes`](../../skills/dsh-archive-agent-notes/SKILL.md) instead of continuing to maintain it.
|
||||
|
||||
### This is not a license to rewrite the *decision*
|
||||
|
||||
Update factual realization in place. A reversal of the decision or its rationale requires a new Agent Note and cross-link; a fully superseded old note may be deleted only through the consolidation rule in the [Agent Note contract](../README.md).
|
||||
|
||||
@@ -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
|
||||
2026-06-11-content-block-vocabulary.md: 9aad01cee6083b1f380be66869af3137a07d9f1f
|
||||
2026-06-11-content-block-vocabulary.zh.md: 5720f0742a0729a3f98e4b05ab37acf97ae78db5
|
||||
2026-06-11-content-block-vocabulary.md: d926c28e7e197aff28c7b1c09d085febf866832b
|
||||
2026-06-11-content-block-vocabulary.zh.md: 6361f00abe109bffdb5bd3ff5652df67d6b3c8a1
|
||||
|
||||
@@ -23,6 +23,6 @@ In-session context injection (`context/message`) and mid-turn steering (`steerin
|
||||
|
||||
- Reasoning has a core home without provider-specific shapes.
|
||||
- Multimodal blocks return only with coordinated adapter, UI, and compaction support; see [the drop-image Agent Note](../simplification/2026-07-04-drop-image-content-block.md).
|
||||
- Cache hints and assistant prefill remain absent until a shipping adapter can honor them; see the [producer-less variants](../simplification/2026-07-04-prune-producerless-vocabulary-variants.md) and [inert request knobs](../simplification/2026-07-04-drop-inert-request-knobs.md) Agent Notes.
|
||||
- Cache hints and assistant prefill remain absent until a shipping adapter can honor them; see the [producer-less variants](../../archived/simplification/2026-07-04-prune-producerless-vocabulary-variants.md) and [inert request knobs](../../archived/simplification/2026-07-04-drop-inert-request-knobs.md) Agent Notes.
|
||||
- Every adapter pays a translation cost; the first real adapters have since validated the streaming protocol, and new adapters should continue proving their provider-specific mapping in adapter-local tests.
|
||||
- IDs that cross package boundaries are branded (`CallId`, the shared agent/session `SessionId`) — nominal typing at zero runtime cost.
|
||||
|
||||
@@ -23,6 +23,6 @@ harness 需要一套统一的内部消息语言，供 agent loop（智能体循
|
||||
|
||||
- 推理（reasoning）在核心层有了归属，无需依赖提供方特有的结构。
|
||||
- 多模态块只有在适配器、UI 和上下文压缩（context compaction）三方协同支持后才会回归；见 [drop-image Agent Note](../simplification/2026-07-04-drop-image-content-block.md)。
|
||||
- 缓存提示与 assistant prefill 在有实际适配器能兑现之前保持缺席；见[无生产者的词汇变体](../simplification/2026-07-04-prune-producerless-vocabulary-variants.md)与[无端到端可用路径的请求旋钮](../simplification/2026-07-04-drop-inert-request-knobs.md) Agent Note。
|
||||
- 缓存提示与 assistant prefill 在有实际适配器能兑现之前保持缺席；见[无生产者的词汇变体](../../archived/simplification/2026-07-04-prune-producerless-vocabulary-variants.md)与[无端到端可用路径的请求旋钮](../../archived/simplification/2026-07-04-drop-inert-request-knobs.md) Agent Note。
|
||||
- 每个适配器都需承担翻译成本；首批真实适配器已验证了流式输出协议，新适配器应继续在适配器本地测试中验证其提供方特有的映射。
|
||||
- 跨包（package）边界的 ID 使用品牌类型（`CallId`、agent 与会话共享的 `SessionId`）——零运行时开销的名义类型。
|
||||
|
||||
@@ -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
|
||||
2026-06-14-session-persistence.md: 52434930bb662b0c97e61f7c2f69b67c309b6317
|
||||
2026-06-14-session-persistence.zh.md: 143b58d32191108d7ba24b489bd4f898b1547aab
|
||||
2026-06-14-session-persistence.md: 75e13b860f621ed407849b3b4c62ff7287ab4812
|
||||
2026-06-14-session-persistence.zh.md: a6bd400a053779c742940236737447d1687622de
|
||||
|
||||
@@ -15,11 +15,11 @@ The [event-sourced model](2026-06-11-event-sourced-sessions.md) makes the append
|
||||
Persistence is an abstract **capability seam** ([capability seams](2026-06-13-capability-seams.md), the `dsh-bash` template), not loop or core logic:
|
||||
|
||||
1. **Interface** (`dsh-session-persistence`, `ctx.sessionPersistence`) — an abstract `SessionPersistence` service: `create`/`append`/`load`/`list`. Its persisted unit IS the existing `SessionEvent` (`{ type, seq, time, data }`), reused verbatim — no conversion type.
|
||||
2. **Implementation** (`dsh-session-persistence-jsonl`) — an append-only logical JSONL log per session (a `SessionHeader` line then one `SessionEvent` per line, verbatim **including `assistant/chunk`**), encoded as [checksummed Zstandard frames by default](2026-07-19-zstandard-jsonl-session-logs.md) or raw lines by configuration.
|
||||
2. **Implementation** (`dsh-session-persistence-jsonl`) — an append-only logical JSONL log per session: a `SessionHeader` line followed by storage records that losslessly represent the contiguous `SessionEvent` stream. Eligible `assistant/chunk` delta runs use packed rows by default; [checksummed Zstandard frames](2026-07-19-zstandard-jsonl-session-logs.md) are the default physical encoding, with raw lines configurable.
|
||||
|
||||
Key choices recorded here because they are durable, contested, and surprising:
|
||||
|
||||
- **The canonical durable log persists every `SessionEvent` verbatim, including `assistant/chunk`.** `deriveMessages()` skips chunks, and a chunk-filtered rollout (Codex's `policy.rs`) is tempting — but `seq = log.length` and the load-validation `events[i].seq === i` require a *contiguous* log; filtering chunks out would leave holes and break both the contract and resume. A chunk-filtered projection is possible later as a derived view with its own renumbering, but it is NOT the canonical log.
|
||||
- **The canonical durable log persists every `SessionEvent` losslessly, including `assistant/chunk`.** JSONL storage may encode a consecutive delta run as one packed row, but `load` reconstructs the exact event boundaries, sequence numbers, and timestamps. `deriveMessages()` skips chunks, and a chunk-filtered rollout (Codex's `policy.rs`) is tempting — but `seq = log.length` and the load-validation `events[i].seq === i` require a *contiguous* logical log; filtering chunks out would leave holes and break both the contract and resume. A chunk-filtered projection is possible later as a derived view with its own renumbering, but it is NOT the canonical log.
|
||||
- **Append-only; a crashed turn is closed, never truncated.** Flushed events are never rewritten. The [semantic checkpoint policy](../bug-fix/2026-07-21-semantic-session-checkpoints.md) drains the request before model dispatch, a recorded top-level call before tool dispatch, and the complete response/result batch after a step; the loop drains the final turn boundary. Because one interrupted turn may contain substantial valid work, `load` preserves its contiguous, parseable events and appends risk-classified error results for unanswered assistant calls, a missing `step/end`, and `turn/end` with `{ kind: 'interrupted' }`. The synthetic results keep resumed provider transcripts valid. Only an incomplete final record is discarded; a parse error or sequence gap at or before the last real `turn/end` is corruption and makes the session unloadable.
|
||||
- **File backend canonical, DB backend a proven drop-in.** `SessionEvent` maps 1:1 onto a row `(session_id, seq, type, time, data)` — `append` is INSERT (in a transaction asserting the contiguous-seq contract), `load` is SELECT … ORDER BY seq. `dsh-session-persistence-sqlite` is exactly this: a `SessionPersistence` subclass with no interface change (opencode runs this exact shape on SQLite/WAL), and it passes the same `runPersistenceContract` suite as the JSONL backend — so the contract holds both backends to identical semantics (lazy materialization, interrupted-turn close on load, contiguous-seq), expressed once over file bytes and once over rows. Its database carries a dedicated application id and monotonic schema version. A pristine file creates all tables and stamps both header values in one transaction; an unversioned file with any user-defined schema object or application identity, a foreign current-version identity, and every non-current version reject before journal-mode mutation.
|
||||
- **Metadata is out-of-log.** Format version, cwd, and lineage are storage concerns, not replayable conversation state, so they live in a `SessionHeader` owned by `dsh-session` and attached to a `Session` via a new readonly `session.header` — never in `SessionEventMap`, never reaching `deriveMessages()`. `createdAt` is non-negative safe-integer Unix epoch milliseconds: live creation and persistence registration reject fractional values, JSONL validates the decoded header, and SQLite stores it in a strict `INTEGER` column. The alternative (a merge-extensible `session/meta` event as log line 0) was rejected: an in-log event would ride along with a seeded/forked session for free, but metadata is not replayable state, so the explicit out-of-log header seam is the cleaner cost. (The header was originally split into an immutable `SessionHeader` plus a mutable `SessionSummary` whose union was `SessionMeta`; the mutable summary was later removed as dead state — see [Drop the mutable session summary](../simplification/2026-06-19-drop-mutable-session-summary.md).)
|
||||
@@ -33,4 +33,4 @@ Format versioning: the header carries a `version`; `load` rejects any non-curren
|
||||
|
||||
## Consequences
|
||||
|
||||
Two new packages and the metadata seam in `dsh-session` (`session.header`, the `create(id?, options?)` signature). Bought: durable resume/fork, a read/replay path, crash tolerance, and host-side session access over the existing event-sourced log, with the backend swappable behind one interface. The reusable `runPersistenceContract` suite holds every backend to the same append-only, contiguous-seq, lazy-materialization, integer-metadata, and serializability semantics. Persisting the full log also settles event fidelity: `assistant/chunk` remains verbatim. SQLite initialization either commits its complete owned schema and header identity or leaves no partial schema to strand on the next open.
|
||||
Two new packages and the metadata seam in `dsh-session` (`session.header`, the `create(id?, options?)` signature). Bought: durable resume/fork, a read/replay path, crash tolerance, and host-side session access over the existing event-sourced log, with the backend swappable behind one interface. The reusable `runPersistenceContract` suite holds every backend to the same append-only, contiguous-seq, lazy-materialization, integer-metadata, and serializability semantics. Persisting the full logical log also settles event fidelity: every `assistant/chunk` survives exactly even when JSONL packs several into one storage row. SQLite initialization either commits its complete owned schema and header identity or leaves no partial schema to strand on the next open.
|
||||
|
||||
@@ -15,11 +15,11 @@ Status: implemented
|
||||
持久化是一个抽象的**能力 seam**（[能力 seam](2026-06-13-capability-seams.md)，`dsh-bash` 模板），而非循环或核心逻辑：
|
||||
|
||||
1. **接口**（`dsh-session-persistence`，`ctx.sessionPersistence`）：一个抽象的 `SessionPersistence` 服务，提供 `create`/`append`/`load`/`list`。其持久化单元就是现有的 `SessionEvent`（`{ type, seq, time, data }`），原样复用，无转换类型。
|
||||
2. **实现**（`dsh-session-persistence-jsonl`）：每个会话一个仅追加的逻辑 JSONL 日志（一行 `SessionHeader`，之后每行一个 `SessionEvent`，逐字节保留，**包括 `assistant/chunk`**），默认编码为[带校验和的 Zstandard 帧](2026-07-19-zstandard-jsonl-session-logs.md)，也可通过配置使用原始行。
|
||||
2. **实现**（`dsh-session-persistence-jsonl`）：每个会话一个仅追加的逻辑 JSONL 日志：先是一行 `SessionHeader`，随后是无损表示连续 `SessionEvent` 流的存储记录。符合条件的 `assistant/chunk` 增量连续段默认使用打包行；[带校验和的 Zstandard 帧](2026-07-19-zstandard-jsonl-session-logs.md)是默认物理编码，也可通过配置使用原始行。
|
||||
|
||||
以下关键选择记录于此，因为它们是持久性的、有争议的、且出人意料的：
|
||||
|
||||
- **规范的持久日志逐字节保留每个 `SessionEvent`，包括 `assistant/chunk`。** `deriveMessages()` 跳过分片，而过滤分片的方案（Codex 的 `policy.rs`）很有吸引力，但 `seq = log.length` 以及加载验证 `events[i].seq === i` 要求日志是*连续*的；过滤掉分片会留下空洞，同时破坏契约和恢复功能。基于分片过滤的投影可以作为派生视图在后续实现（带有自己的重新编号），但它不是规范日志。
|
||||
- **规范的持久日志无损保留每个 `SessionEvent`，包括 `assistant/chunk`。** JSONL 存储可以将一段连续的增量事件编码为一条打包行，但 `load` 会重建精确的事件边界、序号与时间戳。`deriveMessages()` 跳过分片，而过滤分片的方案（Codex 的 `policy.rs`）很有吸引力，但 `seq = log.length` 以及加载验证 `events[i].seq === i` 要求*连续*的逻辑日志；过滤掉分片会留下空洞，同时破坏契约和恢复功能。基于分片过滤的投影可以作为派生视图在后续实现（带有自己的重新编号），但它不是规范日志。
|
||||
- **仅追加；崩溃的轮次被关闭，而非截断。** 已刷写的事件永不被重写。[语义检查点策略](../bug-fix/2026-07-21-semantic-session-checkpoints.md)会在模型分发前排空请求、在工具分发前排空已记录的顶层调用，并在步骤结束后排空完整的响应/结果批次；循环则排空最终轮次边界。由于一个被中断的轮次可能包含大量有效工作，`load` 保留其连续、可解析的事件，并为未应答的 assistant 调用追加按风险分类的错误结果、补一个缺失的 `step/end`，以及带 `{ kind: 'interrupted' }` 的 `turn/end`。合成的结果保证恢复后的提供方 transcript（文本记录）仍然有效。只有不完整的最后一条记录会被丢弃；在最后一个真实 `turn/end` 处或之前出现解析错误或序号间隙，属于数据损坏，会使该会话不可加载。
|
||||
- **文件后端为规范实现，数据库后端为经过验证的直接替换。** `SessionEvent` 1:1 映射到一行 `(session_id, seq, type, time, data)`：`append` 是 INSERT（在一个断言连续 seq 契约的事务中），`load` 是 SELECT … ORDER BY seq。`dsh-session-persistence-sqlite` 正是如此：一个 `SessionPersistence` 子类，接口无变化（opencode 在 SQLite/WAL 上运行的正是这个形状），且通过与 JSONL 后端相同的 `runPersistenceContract` 测试套件。该契约以相同的语义约束两个后端（惰性物化、加载时关闭中断轮次、连续 seq），一次表达在文件字节上，一次表达在数据库行上。其数据库拥有专用的 application id 与单调递增的 schema 版本。系统会在一个事务中为全新文件创建所有表并写入这两个 header 值；未版本化文件若带有任何用户定义的 schema 对象或应用标识、当前版本文件若带有外部应用标识，以及任何非当前版本文件，都会在修改日志模式之前被拒绝。
|
||||
- **元数据在日志之外。** 格式版本、cwd 和谱系是存储关注点，不是可回放的对话状态，因此它们存放在 `dsh-session` 拥有的 `SessionHeader` 中，并通过新的只读属性 `session.header` 附加到 `Session` 上——永远不进入 `SessionEventMap`，永远不到达 `deriveMessages()`。`createdAt` 是以 Unix epoch 毫秒表示的非负安全整数：运行时创建和持久化注册会拒绝小数值，JSONL 会验证解码后的 header，SQLite 则将其存入严格的 `INTEGER` 列。替代方案（一个可合并扩展的 `session/meta` 事件作为日志第 0 行）被否决：日志内事件会随 seed/fork 的会话免费携带，但元数据不是可回放状态，因此显式的日志外 header seam 是更干净的代价。（header 最初被拆分为不可变的 `SessionHeader` 加可变的 `SessionSummary`，二者的联合类型为 `SessionMeta`；可变 summary 后来因属于死状态而被移除——见 [移除可变会话摘要](../simplification/2026-06-19-drop-mutable-session-summary.md)。）
|
||||
@@ -33,4 +33,4 @@ Status: implemented
|
||||
|
||||
## 后果
|
||||
|
||||
新增两个包（package），以及 `dsh-session` 中的元数据 seam（`session.header`，`create(id?, options?)` 签名）。收益：持久恢复/fork、读取/回放路径、崩溃容忍，以及基于现有事件溯源日志的宿主侧会话访问，后端在一个接口之后可替换。可复用的 `runPersistenceContract` 测试套件以相同的仅追加、连续 seq、惰性物化、整数元数据与可序列化语义约束每个后端。持久化完整日志还确定了事件保真度：`assistant/chunk` 保持逐字节不变。SQLite 初始化要么提交完整的自有 schema 与 header 标识，要么不留下任何会使下次打开受阻的部分 schema。
|
||||
新增两个包（package），以及 `dsh-session` 中的元数据 seam（`session.header`，`create(id?, options?)` 签名）。收益：持久恢复/fork、读取/回放路径、崩溃容忍，以及基于现有事件溯源日志的宿主侧会话访问，后端在一个接口之后可替换。可复用的 `runPersistenceContract` 测试套件以相同的仅追加、连续 seq、惰性物化、整数元数据与可序列化语义约束每个后端。持久化完整的逻辑日志还确定了事件保真度：即使 JSONL 将多个 `assistant/chunk` 打包到一条存储行中，每个事件也会精确保留。SQLite 初始化要么提交完整的自有 schema 与 header 标识，要么不留下任何会使下次打开受阻的部分 schema。
|
||||
|
||||
@@ -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
|
||||
2026-06-17-filesystem-capability-seam.md: 08e8d52b314eb10e2c7ec444dd61a96d8621e032
|
||||
2026-06-17-filesystem-capability-seam.zh.md: 6f4889234516ee134c9873781a874b5f1a3644ac
|
||||
2026-06-17-filesystem-capability-seam.md: fee0161e5e8397ac1d1c0e2850efad840c65d971
|
||||
2026-06-17-filesystem-capability-seam.zh.md: ee50b36d25315c3d8daed4502bc248977f9e6011
|
||||
|
||||
@@ -32,7 +32,7 @@ The read-before-write/edit and observed-state policy is a fourth package, `@deep
|
||||
|
||||
The first backend is deliberately local-only: `dsh-fs-local` implements `ctx.fs` against the host filesystem. Future sibling backends can provide sandboxed, remote, virtual, or project-scoped filesystems behind the same interface.
|
||||
|
||||
The first consumer is deliberately text-file-only: `dsh-tool-fs` exposes model-facing `read`, `write`, and `edit` tools for UTF-8 text files. Future consumers can add directory listing, search/glob, binary-safe operations, file watching, or higher-level project operations without changing the local backend package, as long as the needed capability exists on `ctx.fs`. Direct directory listing was later added by [Add direct directory listing to the filesystem seam](2026-07-03-filesystem-directory-listing-seam.md).
|
||||
The first consumer is deliberately text-file-only: `dsh-tool-fs` exposes model-facing `read`, `write`, and `edit` tools for UTF-8 text files. Future consumers can add directory listing, search/glob, binary-safe operations, file watching, or higher-level project operations without changing the local backend package, as long as the needed capability exists on `ctx.fs`. Direct directory listing was later added by [Add direct directory listing to the filesystem seam](../../archived/architecture/2026-07-03-filesystem-directory-listing-seam.md).
|
||||
|
||||
Filesystem permissions and sandboxing are not implied by this split. The local backend resolves relative paths from its configured base directory, but containment policy is a separate decision: either a stricter `ctx.fs` implementation enforces it, or a permission/sandbox plugin wraps `tools/execute` and vetoes calls before they reach the consumer.
|
||||
|
||||
@@ -95,7 +95,7 @@ Literal edit is a provider primitive (`editText`), not composed in `tool-fs` fro
|
||||
|
||||
The policy plugin, not `ctx.fs`, gates on prior observation: an `edit` requires a prior observation by the owner (else `FS_NOT_OBSERVED`), and the recorded version is passed to `editText` as the CAS basis. With the policy plugin absent, `ctx.fs` alone is a complete unconstrained seam (unconditional write/edit); the tool is never method-coupled to the policy.
|
||||
|
||||
Filesystem contract failures are thrown as `FsError extends HarnessError`, and the tool registry converts them into `isError` tool results with structured `{ name, code }` metadata. `dsh-fs` owns this vocabulary rather than each tool inventing messages. The codes are `FS_NOT_FOUND`, `FS_NOT_TEXT`, `FS_STALE_VERSION`, `FS_NOT_OBSERVED`, `FS_NOT_REGULAR_FILE`, `FS_AMBIGUOUS_EDIT`, `FS_EDIT_NOT_FOUND`, and `FS_ABORTED`. (An earlier draft included `FS_PARTIAL_OBSERVATION`; freshness-based authorization has no partial/full distinction, so it was dropped. Directory-listing-specific codes were added later by [Add direct directory listing to the filesystem seam](2026-07-03-filesystem-directory-listing-seam.md).)
|
||||
Filesystem contract failures are thrown as `FsError extends HarnessError`, and the tool registry converts them into `isError` tool results with structured `{ name, code }` metadata. `dsh-fs` owns this vocabulary rather than each tool inventing messages. The codes are `FS_NOT_FOUND`, `FS_NOT_TEXT`, `FS_STALE_VERSION`, `FS_NOT_OBSERVED`, `FS_NOT_REGULAR_FILE`, `FS_AMBIGUOUS_EDIT`, `FS_EDIT_NOT_FOUND`, and `FS_ABORTED`. (An earlier draft included `FS_PARTIAL_OBSERVATION`; freshness-based authorization has no partial/full distinction, so it was dropped. Directory-listing-specific codes were added later by [Add direct directory listing to the filesystem seam](../../archived/architecture/2026-07-03-filesystem-directory-listing-seam.md).)
|
||||
|
||||
## Tool consumer behavior
|
||||
|
||||
|
||||
@@ -32,7 +32,7 @@ harness 已有一个具体的 `bash` 能力 seam（`dsh-bash` / `dsh-bash-local`
|
||||
|
||||
第一个后端有意仅限本地：`dsh-fs-local` 基于宿主文件系统实现 `ctx.fs`。未来的兄弟后端可在同一接口之后提供沙箱、远程、虚拟或项目作用域的文件系统。
|
||||
|
||||
第一个消费方有意仅限文本文件：`dsh-tool-fs` 暴露面向模型的 `read`、`write` 和 `edit` 工具，处理 UTF-8 文本文件。未来的消费方可以添加目录列表、搜索/glob、二进制安全操作、文件监视或更高层的项目操作，只要 `ctx.fs` 上存在所需能力，就无需改动本地后端包。直接目录列表后来由[为文件系统 seam 添加直接目录列举能力](2026-07-03-filesystem-directory-listing-seam.md)添加。
|
||||
第一个消费方有意仅限文本文件：`dsh-tool-fs` 暴露面向模型的 `read`、`write` 和 `edit` 工具，处理 UTF-8 文本文件。未来的消费方可以添加目录列表、搜索/glob、二进制安全操作、文件监视或更高层的项目操作，只要 `ctx.fs` 上存在所需能力，就无需改动本地后端包。直接目录列表后来由[为文件系统 seam 添加直接目录列举能力](../../archived/architecture/2026-07-03-filesystem-directory-listing-seam.md)添加。
|
||||
|
||||
文件系统权限和沙箱并非此拆分所隐含。本地后端从其配置的基目录解析相对路径，但隔离策略是独立的决策：要么由更严格的 `ctx.fs` 实现强制执行，要么由权限/沙箱插件包装 `tools/execute` 并在调用到达消费方之前否决。
|
||||
|
||||
@@ -95,7 +95,7 @@ harness 已有一个具体的 `bash` 能力 seam（`dsh-bash` / `dsh-bash-local`
|
||||
|
||||
策略插件（而非 `ctx.fs`）对先前观测进行门控：`edit` 要求 owner 有先前观测（否则报 `FS_NOT_OBSERVED`），记录的版本作为 CAS 基础传给 `editText`。在策略插件缺席时，`ctx.fs` 本身是一个完整的无约束 seam（无条件写入/编辑）；工具从不与策略方法耦合。
|
||||
|
||||
文件系统契约失败以 `FsError extends HarnessError` 抛出，工具注册表将其转换为带结构化 `{ name, code }` 元数据的 `isError` 工具结果。`dsh-fs` 拥有此词汇，而非由每个工具各自发明消息。错误码包括 `FS_NOT_FOUND`、`FS_NOT_TEXT`、`FS_STALE_VERSION`、`FS_NOT_OBSERVED`、`FS_NOT_REGULAR_FILE`、`FS_AMBIGUOUS_EDIT`、`FS_EDIT_NOT_FOUND` 和 `FS_ABORTED`。（早期草案包含 `FS_PARTIAL_OBSERVATION`；基于新鲜度的授权没有 partial/full 区分，因此已删除。目录列表相关的错误码后来由[为文件系统 seam 添加直接目录列举能力](2026-07-03-filesystem-directory-listing-seam.md)添加。）
|
||||
文件系统契约失败以 `FsError extends HarnessError` 抛出，工具注册表将其转换为带结构化 `{ name, code }` 元数据的 `isError` 工具结果。`dsh-fs` 拥有此词汇，而非由每个工具各自发明消息。错误码包括 `FS_NOT_FOUND`、`FS_NOT_TEXT`、`FS_STALE_VERSION`、`FS_NOT_OBSERVED`、`FS_NOT_REGULAR_FILE`、`FS_AMBIGUOUS_EDIT`、`FS_EDIT_NOT_FOUND` 和 `FS_ABORTED`。（早期草案包含 `FS_PARTIAL_OBSERVATION`；基于新鲜度的授权没有 partial/full 区分，因此已删除。目录列表相关的错误码后来由[为文件系统 seam 添加直接目录列举能力](../../archived/architecture/2026-07-03-filesystem-directory-listing-seam.md)添加。）
|
||||
|
||||
## 工具消费方行为
|
||||
|
||||
|
||||
@@ -1,57 +0,0 @@
|
||||
# Agent Note: Extract example apps into packages
|
||||
|
||||
Status: implemented
|
||||
|
||||
English | [中文](2026-06-20-extract-example-app-packages.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
An example folder is supposed to be *thin* — the variable wiring of a demo, not the demo's machinery. Before this change it was thick. Each example carried a hand-rolled `start.ts` boot bootstrap, an infra preamble (`timer`, and — for the stdio demos — `logger` + `hmr`), nested includes of three shared YAML fragments (`base.yml` / `base-core.yml` / `acp-agent/acp-tail.yml`), and per-example `agent-loop`/persistence/system-prompt config. The actual app — the spine of services every agent needs — was spread across the leaf and those includes.
|
||||
|
||||
The leaf configs also owned coupled front doors. ACP requires stdout purity and creates agents through `session/new`; terminal and Headless apps pre-create `main` but have different process I/O contracts. Prose warnings were the only guard against combining these incorrectly, while three `start.ts` files duplicated the Loader bootstrap and lifecycle code.
|
||||
|
||||
## Decision
|
||||
|
||||
Each example is now **mostly an invocation of an app package**, splitting the wiring along the existing [interface / implementation / consumer seam](2026-06-13-capability-seams.md): the **app package owns the composition**, the leaf `cordis.yml` owns only the **swappable choices** (which LLM adapter, which bash executor, model, prompt, persistence root).
|
||||
|
||||
- **`@deepseek-ai/dsh-agent-spine-demo`** ([packages/examples/agent-spine-demo](../../../../packages/examples/agent-spine-demo)) composes the providerless, executor-less, UI-less spine and forwards the loop's agent-list config. Its dependency on the concrete loop is intentional because this package composes the spine rather than extending it; swapping the loop means supplying another bundle.
|
||||
- **`@deepseek-ai/dsh-tui-demo`**, **`@deepseek-ai/dsh-cli-demo`**, and **`@deepseek-ai/dsh-acp-demo`** bake in their process roles. TUI includes the full-screen UI and a pre-created `main`; Headless includes the one-shot driver and a pre-created `main`; ACP includes the bridge and no pre-created agent. All three include JSONL persistence and omit stdout loggers.
|
||||
- **`start.ts` is gone.** Each app package exposes a bin; the `demo:*` scripts invoke it. Loader boot, `.env` loading, and fail-loud guards live in the shared [`@deepseek-ai/dsh-app-boot`](../../../../packages/ui/app-boot) package (unit-tested under the per-file coverage gate — see [share the app bins' boot glue](../simplification/2026-07-04-share-app-bin-boot-glue.md)); the thin self-executing entries are driven by keyless Loader-path tests.
|
||||
- **Each leaf `cordis.yml` collapses** to backends, optional product tools, and one app entry carrying the app config. TUI and Headless route model/session choices onto a pre-created agent; ACP routes the initial provider/model onto its bridge.
|
||||
- **`base.yml`, `base-core.yml`, and `acp-agent/acp-tail.yml` are retired** — the spine they shared now lives in `dsh-agent-spine-demo`.
|
||||
|
||||
`bash-local` and the LLM adapter stay **leaf choices**: the bundle ships `tool-bash` (the consumer schema), the leaf picks the executor implementation, so a sandboxed executor or replay adapter swaps in without touching the app.
|
||||
|
||||
### Amendment on implementation: `hmr` stays a leaf entry
|
||||
|
||||
The proposal listed `hmr` among the interactive app's baked-in front-door cluster. Validating against the code, baking `hmr` into the app package fights Cordis in two ways, so it ships as a **leaf `cordis.yml` entry** instead:
|
||||
|
||||
1. `@cordisjs/plugin-hmr` is a Loader-only, subprocess-only dev plugin — it requires the live `loader` service and its internal module access, so it can only run in the real `demo:*`/bin subprocess, never in the in-process unit/coverage tier.
|
||||
2. The in-process test tier (vitest) cannot even *import* the vendored `hmr` module (its class-decorator `@Inject` form fails under Vite's transform), so a package whose `apply` statically imported it could never satisfy the per-file 100% coverage gate on its headline function.
|
||||
|
||||
Crucially, `hmr` is not a stdout-purity footgun: a stray entry in the ACP config does not corrupt JSON-RPC frames. Every shipped app omits a stdout console logger; the app or protocol driver alone owns stdout.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
### Why not keep the wiring in shared YAML includes?
|
||||
|
||||
The old `base*.yml`/`acp-tail.yml` includes already deduped the *config*, but a YAML include cannot **encapsulate** the front-door coupling — it can only describe it in a comment and trust every leaf to obey. It also cannot own a `bin`, so the boot glue stayed copied across three `start.ts` files. A package turns "the ACP app never logs to stdout" from a prose warning into a property of the artifact: there is no logger entry in the leaf to get wrong.
|
||||
|
||||
## Verification
|
||||
|
||||
- Example directories contain only their config, README, and tests: `start.ts`, the infrastructure preamble, and the shared YAML includes are gone.
|
||||
- `demo:tui`, `demo:headless`, and `demo:acp` invoke the app-package bins.
|
||||
- Each new package has a README and per-file 100% coverage; each app package also has a keyless real-Loader-path bin smoke that catches export-shape failures described in [postmortem 0001](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md).
|
||||
- The ACP replay suite boots through the app-package bin, so protocol wiring and assembled backend behavior cross the real Loader boundary.
|
||||
|
||||
## Consequences
|
||||
|
||||
- **The bare-plugin-tree pedagogy.** The spine lives behind a bundle, so seeing the whole tree means opening `dsh-agent-spine-demo`. The app package's README carries that teaching weight.
|
||||
- **A layer of indirection.** "What does this demo load?" becomes a package read, not a single YAML scan.
|
||||
|
||||
## Related
|
||||
|
||||
- Supersedes [Make the shared example base providerless](../../rejected/architecture/2026-06-20-providerless-example-base.md): renaming `base.yml` to the providerless core is moot once the spine moves into `dsh-agent-spine-demo` and the `base*.yml` files are deleted.
|
||||
- Builds on the [capability-seams](2026-06-13-capability-seams.md) interface/implementation/consumer split — backends and presentation stay leaf choices; the spine is the shared bundle.
|
||||
- Complements [Reorganize packages into a modular hierarchy](2026-06-20-package-hierarchy.md): the new app/core packages slot into existing groups under that hierarchy (`core` for the reusable spine bundle, `ui` for the app-specific front doors).
|
||||
- The later [redundant-agent removal](../simplification/2026-07-20-remove-stdio-and-echo-agents.md) owns the final TUI/Headless split and removes the line-oriented and mock-only leaves.
|
||||
@@ -1,57 +0,0 @@
|
||||
# Agent Note: 将示例应用提取为独立包
|
||||
|
||||
Status: implemented
|
||||
|
||||
[English](2026-06-20-extract-example-app-packages.md) | 中文
|
||||
|
||||
## 问题
|
||||
|
||||
示例目录本应是*精简的*——只包含演示的可变接线，而非演示的基础设施。在此次变更之前，它是臃肿的。每个示例都携带一份手写的 `start.ts` 启动引导、一段基础设施前导（`timer`，以及 stdio 演示所需的 `logger` + `hmr`（热模块替换））、三个共享 YAML 片段的嵌套引用（`base.yml` / `base-core.yml` / `acp-agent/acp-tail.yml`），还有各示例自身的 `agent-loop`/持久化/系统提示词配置。真正的应用——每个 agent（智能体）都需要的服务主干——散落在叶子配置和那些 include 中。
|
||||
|
||||
叶子配置还拥有耦合的前门。ACP（Agent Client Protocol）要求 stdout 纯净，并通过 `session/new` 创建 agent；终端应用和 Headless 应用则预创建 `main`，但进程 I/O 契约不同。防止错误组合的唯一屏障是文档中的文字警告，而三个 `start.ts` 文件重复着 Loader 引导和生命周期代码。
|
||||
|
||||
## 决策
|
||||
|
||||
每个示例现在**主要是对一个应用包（package）的调用**，沿着既有的[接口 / 实现 / 消费方 seam](2026-06-13-capability-seams.md) 拆分接线：**应用包拥有组合**，叶子 `cordis.yml` 只拥有**可替换的选择**（哪个 LLM（大语言模型）适配器、哪个 bash 执行器、模型、提示词、持久化根目录）。
|
||||
|
||||
- **`@deepseek-ai/dsh-agent-spine-demo`**（[packages/examples/agent-spine-demo](../../../../packages/examples/agent-spine-demo)）组合了不含提供方、不含执行器、不含 UI 的主干，并转发 agent loop（智能体循环）的 agent 列表配置。它对具体 loop 的依赖是有意为之，因为该包组合的是主干而非扩展主干；替换 loop 意味着提供另一个 bundle。
|
||||
- **`@deepseek-ai/dsh-tui-demo`**、**`@deepseek-ai/dsh-cli-demo`** 和 **`@deepseek-ai/dsh-acp-demo`** 各自内置其进程角色。TUI 包含全屏 UI 和预创建的 `main`；Headless 包含 one-shot driver 和预创建的 `main`；ACP 包含 bridge 且不预创建 agent。三者都包含 JSONL 持久化，并省略 stdout logger。
|
||||
- **`start.ts` 已移除。** 每个应用包都暴露一个 bin；`demo:*` 脚本调用它。Loader 引导、`.env` 加载和快速失败守卫位于共享的 [`@deepseek-ai/dsh-app-boot`](../../../../packages/ui/app-boot) 包（在逐文件覆盖率门禁下有单元测试——见[共享应用 bin 的启动胶水](../simplification/2026-07-04-share-app-bin-boot-glue.md)）；精简的自执行入口由 keyless 的 Loader 路径测试驱动。
|
||||
- **每个叶子 `cordis.yml` 精简为**后端、可选产品工具，以及一个承载应用配置的 app 条目。TUI 和 Headless 把模型/会话选择路由到预创建的 agent；ACP 把初始提供方/模型路由到 bridge。
|
||||
- **`base.yml`、`base-core.yml` 和 `acp-agent/acp-tail.yml` 已退役**——它们共享的主干现在位于 `dsh-agent-spine-demo` 中。
|
||||
|
||||
`bash-local` 和 LLM 适配器仍然是**叶子选择**：bundle 提供 `tool-bash`（消费方 schema），叶子选择执行器实现，因此沙箱执行器或回放适配器无需触碰应用即可替换。
|
||||
|
||||
### 实现修正：`hmr` 保留为叶子条目
|
||||
|
||||
提案最初将 `hmr` 列入交互式应用内置的前门集群。对照代码验证后发现，将 `hmr` 内置到应用包中会在两个方面与 Cordis 冲突，因此改为作为**叶子 `cordis.yml` 条目**交付：
|
||||
|
||||
1. `@cordisjs/plugin-hmr` 是一个仅限 Loader、仅限子进程的开发插件——它需要活跃的 `loader` 服务及其内部模块访问权限，因此只能在真实的 `demo:*`/bin 子进程中运行，不能在进程内的单元/覆盖率测试层运行。
|
||||
2. 进程内测试层（vitest）甚至无法*导入* vendor 的 `hmr` 模块（其 class-decorator `@Inject` 形式在 Vite 的 transform 下会失败），因此一个 `apply` 静态导入了它的包永远无法满足其主函数的逐文件 100% 覆盖率门禁。
|
||||
|
||||
关键在于，`hmr` 不是 stdout 纯净隐患：ACP 配置中误加该条目不会破坏 JSON-RPC 帧。所有已交付应用都省略 stdout 控制台 logger；stdout 只归应用或协议 driver 所有。
|
||||
|
||||
## 曾考虑的替代方案
|
||||
|
||||
### 为什么不继续用共享 YAML include 来管理接线？
|
||||
|
||||
旧的 `base*.yml`/`acp-tail.yml` include 已经去重了*配置*，但 YAML include 无法**封装**前门耦合——它只能在注释中描述，并信任每个叶子遵守。它也无法拥有 `bin`，因此启动胶水一直在三个 `start.ts` 文件中重复。包将「ACP 应用绝不向 stdout 输出日志」从文字警告变成了产物的属性：叶子中不存在可以写错的 logger 条目。
|
||||
|
||||
## 验证
|
||||
|
||||
- 示例目录只包含配置、README 和测试：`start.ts`、基础设施前导和共享 YAML include 已移除。
|
||||
- `demo:tui`、`demo:headless` 和 `demo:acp` 调用应用包的 bin。
|
||||
- 每个新包都有 README 和逐文件 100% 覆盖率；每个应用包还有一个 keyless 的真实 Loader 路径 bin 冒烟测试，用于捕获[事后分析 0001](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md) 中描述的导出形状故障。
|
||||
- ACP 回放套件通过应用包的 bin 启动，因此协议接线与组装后的后端行为都跨越真实的 Loader 边界。
|
||||
|
||||
## 后果
|
||||
|
||||
- **裸插件树的教学性。** 主干现在隐藏在 bundle 之后，查看完整树意味着打开 `dsh-agent-spine-demo`。应用包的 README 承担了这份教学职责。
|
||||
- **多了一层间接。**「这个演示加载了什么？」从扫描单个 YAML 变成了阅读一个包。
|
||||
|
||||
## 相关
|
||||
|
||||
- 取代[使共享示例基础配置与提供方无关](../../rejected/architecture/2026-06-20-providerless-example-base.md)：一旦主干移入 `dsh-agent-spine-demo` 且 `base*.yml` 文件被删除，将 `base.yml` 重命名为无提供方核心便不再有意义。
|
||||
- 基于[能力 seam](2026-06-13-capability-seams.md)的接口/实现/消费方拆分——后端和展示层保持为叶子选择；主干是共享 bundle。
|
||||
- 与[将包重组为模块化层级结构](2026-06-20-package-hierarchy.md)互补：新的 app/core 包按该层级结构归入既有分组（`core` 放可复用的主干 bundle，`ui` 放应用特有的前门）。
|
||||
- 后续的[冗余 agent 移除](../simplification/2026-07-20-remove-stdio-and-echo-agents.md)拥有最终的 TUI/Headless 拆分，并移除行式与仅 mock 的叶子。
|
||||
@@ -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
|
||||
2026-06-20-generic-long-running-tool-runtime.md: 0b901fcf928b900bd3a32f911e6e54a6a98076e2
|
||||
2026-06-20-generic-long-running-tool-runtime.zh.md: e2860e3a91c06ec5110cd671b288e35c5d117f5d
|
||||
2026-06-20-generic-long-running-tool-runtime.md: 313d687b49da0d08b0ec321bcb655b642f7a5af3
|
||||
2026-06-20-generic-long-running-tool-runtime.zh.md: 6be129b7b16ff01d73dc94f7ce6d299ee2c10e55
|
||||
|
||||
@@ -19,7 +19,7 @@ The `tasks/` package group owns background-task semantics:
|
||||
|
||||
Long-running tools are producers. `dsh-tool-bash` adapts a `BashProcess` into incremental output and process cancellation; `dsh-tool-subagent` adapts a child run into final output and child disposal. The execution seams remain independent of sessions and the task registry.
|
||||
|
||||
`TaskService` is a concrete, process-local service. TODO(task-service-backend): separate its public contract from the implementation when a second backend defines the required lifecycle; a systemd-backed runtime is one plausible driver, but this PR does not speculate about its durability, reconnect, ownership, or observation semantics.
|
||||
`TaskService` is the abstract seam in `@deepseek-ai/dsh-tasks`; the process-local registry is `LocalTaskService` in `@deepseek-ai/dsh-tasks-local` (the [task-registry seam Agent Note](2026-07-26-task-registry-seam.md) records that split).
|
||||
|
||||
## Runtime contract
|
||||
|
||||
@@ -103,7 +103,7 @@ Separate bash and subagent output/stop tools duplicate ids, isolation, cleanup,
|
||||
|
||||
### An immediate abstract task-runtime backend
|
||||
|
||||
The current `TaskStart.run()` contract passes in-process callbacks and exact `Agent` objects. A durable backend changes identity, restart, ownership, and observation semantics, so extracting an interface before a second implementation exists would freeze the wrong boundary.
|
||||
The current `TaskStart.run()` contract passes in-process callbacks and exact `Agent` objects. A durable backend changes identity, restart, ownership, and observation semantics, so at introduction time the registry stayed one concrete service rather than freezing the wrong boundary. The [task-registry seam Agent Note](2026-07-26-task-registry-seam.md) later separated the contract from the process-local implementation without changing these in-process semantics.
|
||||
|
||||
### Consumer-owned authorization or cleanup events
|
||||
|
||||
|
||||
@@ -19,7 +19,7 @@ Status: implemented
|
||||
|
||||
长时间运行工具是生产方。`dsh-tool-bash` 将 `BashProcess` 适配为增量输出与进程取消；`dsh-tool-subagent` 将子运行适配为最终输出与子运行释放。执行 seam 保持独立，不依赖会话或任务注册表。
|
||||
|
||||
`TaskService` 是一个具体的进程内服务。TODO(task-service-backend)：当第二个后端明确所需生命周期后，将其公共契约与实现分离；systemd 驱动的运行时是一种可能方案，但本 PR（Pull Request）不臆测其持久性、重连、所有权或观察语义。
|
||||
`TaskService` 是 `@deepseek-ai/dsh-tasks` 中的抽象 seam；进程内注册表是 `@deepseek-ai/dsh-tasks-local` 中的 `LocalTaskService`（该拆分记录在[任务注册表 seam Agent Note](2026-07-26-task-registry-seam.md)中）。
|
||||
|
||||
## 运行时契约
|
||||
|
||||
@@ -103,7 +103,7 @@ bash seam 暴露 `resolve`、`run` 和 `start`。`start(spec)` 返回一个 `Bas
|
||||
|
||||
### 立即抽象任务运行时后端
|
||||
|
||||
当前 `TaskStart.run()` 契约传入进程内回调与确切的 `Agent` 对象。持久化后端会改变身份、重启、所有权与观察语义，因此在第二种实现出现前抽取接口，会固化错误的边界。
|
||||
当前 `TaskStart.run()` 契约传入进程内回调与确切的 `Agent` 对象。持久化后端会改变身份、重启、所有权与观察语义，因此在引入之时注册表保持为单一具体服务，而非固化错误的边界。[任务注册表 seam Agent Note](2026-07-26-task-registry-seam.md)后来在不改变这些进程内语义的前提下，将契约与进程内实现分离。
|
||||
|
||||
### 由消费方负责授权或清理事件
|
||||
|
||||
|
||||
@@ -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
|
||||
2026-06-20-extract-example-app-packages.md: f2853db3f454d71572be003cfbf4f6dfd8377cdd
|
||||
2026-06-20-extract-example-app-packages.zh.md: 58d3d95996b1dacbc12178b46524374429df71ed
|
||||
2026-06-21-bounded-llm-request-recovery.md: 22a56dc6d69340ca1b5f7b77edb4731066c9b2f5
|
||||
2026-06-21-bounded-llm-request-recovery.zh.md: 09ebce376a206591ac766067cc41497b74ed1545
|
||||
@@ -2,6 +2,8 @@
|
||||
|
||||
Status: implemented
|
||||
|
||||
English | [中文](2026-06-21-bounded-llm-request-recovery.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
`dsh-llm` can report provider failures either by throwing during adapter dispatch or iteration or by ending with `finish { kind: 'error' | 'aborted' }`. The final adapter boundary tags thrown failures so `dsh-agent-loop` can distinguish them from middleware and result-processing defects, and the loop normalizes both delivery forms into `agent/request-error` after closing the failed step. The default decision is `fail`; `dsh-compact-basic` is the only shipped recovery listener, and it retries a canonical context-window overflow only after compaction proves that the durable surface shrank.
|
||||
|
||||
@@ -0,0 +1,148 @@
|
||||
# Agent Note: LLM（大语言模型）暂时性请求失败的有界恢复
|
||||
|
||||
Status: implemented
|
||||
|
||||
[English](2026-06-21-bounded-llm-request-recovery.md) | 中文
|
||||
|
||||
## 问题
|
||||
|
||||
`dsh-llm` 可能在适配器分发或迭代时抛出异常，也可能以 `finish { kind: 'error' | 'aborted' }` 结束，以这两种形式报告提供方失败。最终适配器边界会标记抛出的失败，使 `dsh-agent-loop` 能将其与中间件和结果处理缺陷区分开。循环关闭失败步骤后，会把两种交付形式统一规范化为 `agent/request-error`。默认决策为 `fail`；`dsh-compact-basic` 是唯一已交付的恢复监听器，它仅在压缩（compaction）证明持久表层已缩减后，才会对规范化的上下文窗口溢出进行重试。
|
||||
|
||||
该边界已能安全地再次发起请求。原始 `assistant/chunk` 事件携带失败的 `turn` 和 `step`；除非某条成功的 `assistant/message` 引用这些事件，否则消息派生会忽略它们。只有终止性 finish 成功且组装完成后，系统才会分发工具调用；重试则会从持久日志开启新的编号步骤。因此，harness 无需引入第二套响应生命周期或暂定输出协议，即可分隔两次尝试。
|
||||
|
||||
此前的边界还留有三个较窄的缺口。
|
||||
|
||||
- 提供方失败只保留消息，通常还会保留一个 code。HTTP 状态、重试延迟和提供方请求 id 会被丢弃，或者只能通过提供方专用错误对象恢复，因此通用恢复机制如果不解析文本，便无法作出决策或解释决策。
|
||||
- 重试的归属因适配器而异。手写 DeepSeek 适配器只尝试一次，pi-ai profile 则可以启用库内部的不透明重试。如果把隐藏的传输重试与 `agent/request-error` 监听器结合，尝试次数会成倍增加，中间失败也不会记入会话日志。
|
||||
- 恢复后的失败没有持久状态事实。失败的步骤和分片仍可重建，但观察者无法得知 agent（智能体）是否在有意退避、将等待多久，以及等待原因。长时间的静默等待看起来与循环停滞无异。
|
||||
|
||||
本决策的目标是从同一个显式提供方／模型请求的暂时性失败中进行有界恢复。提供方或模型故障转移、响应拼接和语义输出修复都属于其他问题，目前没有消费方。
|
||||
|
||||
## 决策
|
||||
|
||||
### 保留失败事实，不嵌入策略
|
||||
|
||||
`@deepseek-ai/dsh-llm` 导出唯一的可 JSON 序列化 `LlmFailure` 载荷：
|
||||
|
||||
```ts ignore-check
|
||||
type ProviderRequestId = Branded<'ProviderRequestId'>
|
||||
|
||||
interface LlmFailure {
|
||||
message: string
|
||||
code: string
|
||||
status?: number
|
||||
providerRetryAfterMs?: number
|
||||
requestId?: ProviderRequestId
|
||||
}
|
||||
```
|
||||
|
||||
`code` 仍是 `HarnessError` 建立的提供方无关机器路由分类体系；新字段是在提供方边界观测到的事实。`ProviderRequestId` 由 `dsh-llm` 拥有并构造，序列化后为提供方发放的字符串。该载荷有意不包含 `retryable`、`failover`、`partialOutput`、提供方、模型、阶段或路由 id 字段。是否可重试属于策略，提供方／模型已位于持久请求头中，部分输出则从失败步骤的 `assistant/chunk` 事件派生。
|
||||
|
||||
`LlmError` 携带 `failure: LlmFailure`，并保持 `failure.code === error.code`。`FinishReasonMap.error` 和 `FinishReasonMap.aborted` 携带同一载荷，而不是并行的失败形状。适配器抛出的 `Error` 保留其精确的对象标识：最终适配器 scope 在调用局部的伴随状态中把规范化事实与该对象关联，然后原样重新抛出；非 `Error` 抛出值则依旧被包装。`llmFailureOf(stream, error)` 会在现有来源检查旁取回这些事实，而没有错误对象的带内 finish 则会成为新的 `LlmError`。这既保留了按错误类型或标识分流的监听器，又使所有最终适配器失败（包括未知 SDK 异常）都获得 `UNKNOWN` 终止载荷。
|
||||
|
||||
agent loop（智能体循环）会保留 `RequestError` 作为该精确的错误对象，并将 `LlmFailure` 作为独立参数传给 `agent/request-error`；它不会改动可能已冻结的第三方错误。在转换带内 finish 以及记录未恢复的 `turn/end.reason` 时，循环也会使用该载荷。
|
||||
|
||||
适配器会先提取结构化事实，再回退到消息检查。它们会验证 HTTP 状态，将 `Retry-After` 的秒数或日期解析为正的有限毫秒延迟，在提供方公开请求 id 时将其品牌化，并区分自身超时与调用方中止。提供方专用 code 和消息可以细化映射，但恢复监听器不会解析它们。
|
||||
|
||||
共享的暂时性 code 集有意保持很小：适配器针对 `RATE_LIMIT` 和 `SERVER` 的映射，远程失败使用的显式 `TIMEOUT` 和 `TRANSPORT` code，以及提供方响应已完成却没有内容块时使用的 `EMPTY_RESPONSE`。两个适配器都会把最后一种情况归类为错误 finish；详见[空模型响应可重试](../bug-fix/2026-07-24-empty-model-response-is-retryable.md)。身份验证、配额、无效请求、上下文溢出、协议、中止和未知失败都保留不同的稳定 code，且默认不属于暂时性失败。新增 code 需要适配器 fixture（测试前置数据）和已记录的策略决策；无需扩展第二个失败类枚举。
|
||||
|
||||
### 将重试策略放在现有失败步骤 seam 上
|
||||
|
||||
`@deepseek-ai/dsh-llm-retry` 是监听 `agent/request-error` 的函数插件。它不引入服务或新的循环分支；agent-loop 包仅会更改通过现有失败步骤恢复控制流携带的数据。
|
||||
|
||||
`agent/request-error` seam 携带当前 `LlmFailure`，以及在这段连续恢复序列中导致再次请求的不可变先前失败列表。`dsh-llm-retry` 只计数 code 位于已配置暂时性集合中的先前失败，`dsh-compact-basic` 则只计数先前的上下文溢出失败。模型请求成功后会清空历史。因此，暂时性失败与上下文溢出交替出现时，两种策略会独立消耗各自预算；最大请求数等于 1 加上已加载恢复策略的有限预算总和。
|
||||
|
||||
该插件在加载时解析并验证以下部署配置：
|
||||
|
||||
```ts ignore-check
|
||||
interface Config {
|
||||
maxTransientRetries?: number
|
||||
initialDelayMs?: number
|
||||
maxDelayMs?: number
|
||||
jitterRatio?: number
|
||||
retryableCodes?: string[]
|
||||
}
|
||||
```
|
||||
|
||||
默认值为两次暂时性重试、500 毫秒初始延迟、10 秒延迟上限、10% 抖动，以及上述五个暂时性 code（`RATE_LIMIT`、`SERVER`、`TIMEOUT`、`TRANSPORT` 和 `EMPTY_RESPONSE`）。计数与延迟边界参考了所调查实现中较保守的一端：[OpenCode 使用两次请求重试，延迟边界为 500 毫秒／10 秒](https://github.com/anomalyco/opencode/blob/9976269ab1accfc9f9dc98a4a688c516934de422/%70ackages/llm/src/route/executor.ts#L36-L39)；[Pi 将三次 agent 级重试与提供方重试分开，且提供方重试默认为零](https://github.com/earendil-works/pi/blob/3da591ab74ab9ab407e72ed882600b2c851fae21/%70ackages/coding-agent/docs/settings.md#L139-L147)；[Codex 使用有限请求／流预算以及五分钟空闲超时](https://github.com/openai/codex/blob/0fb559f0f6e231a88ac02ea002d3ecd248e2b515/codex-rs/model-provider-info/src/lib.rs#L25-L33)。10% 抖动参考 [Codex 的有界抖动](https://github.com/openai/codex/blob/0fb559f0f6e231a88ac02ea002d3ecd248e2b515/codex-rs/codex-client/src/retry.rs#L40-L47)。在没有其他恢复策略时，两次重试表示最多发起三次提供方请求。`maxTransientRetries` 是非负整数，延迟是正的有限数且满足 `initialDelayMs <= maxDelayMs`，`jitterRatio` 位于 `[0, 1]`，code 非空且不重复。这些都是 Cordis 配置字段，而不是隐藏常量，使部署能够选择不同的成本与延迟预算。
|
||||
|
||||
对于预算未耗尽的合格失败，从 1 开始的暂时性重试计数使用有界指数退避。有效的 `providerRetryAfterMs` 只有在不超过 `maxDelayMs` 时才会取代指数退避；提供方延迟更长时，系统会委托给下一监听器，而不会违反提供方指令提前重试。本地退避乘以 `[1 - jitterRatio, 1 + jitterRatio]` 内的注入随机因子，并将最终值限制到 `maxDelayMs`；提供方延迟不加抖动。
|
||||
|
||||
插件拥有一个全生命期 `AbortController`，并跟踪每个活跃的退避回调。每次等待都会融合 waterfall（瀑布式事件）的轮次信号与该生命期信号。effect 清理会先注销监听器，再中止并等待活跃回调；被捕获回调的生命期信号中止时，回调会返回 `fail`，既不能重试，也不能在插件释放后进入其捕获 waterfall 的剩余部分。尽管 Cordis 已捕获该监听器，此设计仍能使 HMR（热模块替换）释放达到完全停稳。
|
||||
|
||||
休眠前，`dsh-llm-retry` 会追加一条不进入表层的 `llm/retry` 会话事件，其中包含轮次、失败步骤、从 1 开始的暂时性重试编号、已配置上限、计划延迟和 `LlmFailure`。该插件拥有 `SessionEventMap` 声明合并；`dsh-session` 继续负责通用持久化，不会吸收可选策略的词汇。事件记录已安排的内容，而不是下一个请求已完成；延迟期间取消随后会在 `turn/end` 中可见。因为该事件的目的是表示运行状态，而不是收集跟踪数据，所以它仅与生产渲染器及回放／快照覆盖一起交付。
|
||||
|
||||
对非暂时性 code、耗尽的策略预算或超出上限的提供方延迟，监听器会调用 `next()`。这保留了与上下文溢出恢复及后续策略插件的组合能力。只有在两个信号下完成延迟后，它才会返回 `{ action: 'retry' }`；轮次取消和插件释放会返回 `fail`，此后仍以循环的取消／释放检查为准。
|
||||
|
||||
agent-spine 演示组合包加载该插件，因此共享的 stdio/TUI、一次性 CLI（命令行界面）和 ACP（Agent Client Protocol）示例组合使用同一有界策略。库消费方仍需显式组合插件：省略该插件时，`agent/request-error` 保持现有的 fail 默认值。
|
||||
|
||||
### 由单一层负责可见的尝试
|
||||
|
||||
适配器每次调用 `stream()` 只执行一次提供方请求。pi-ai 适配器移除公开的 `maxRetries` 和 `maxRetryDelayMs` profile 字段，并禁用库内部重试；手写适配器保持现有的单次尝试行为。这样既避免 SDK 预算成倍放大 agent 预算，又能确保每次暂时性重试都由一个已关闭的失败步骤加 `llm/retry` 表示。
|
||||
|
||||
`ctx.llm.stream()` 仍是原始的单次尝试 waterfall。压缩摘要等直接调用方会收到结构化失败，但不会自动获得重试，因为它们没有 agent 步骤边界，也没有可供分隔尝试的通用持久位置。未来的直接调用消费方可能会需要一个缓冲辅助函数，仅在尚未发出任何分片时重试；本决策不增加此类辅助函数。
|
||||
|
||||
### 在能够终止停滞流的位置施加边界
|
||||
|
||||
每个适配器都公开一个经过验证的 `streamIdleTimeoutMs` 配置字段，默认值采用上文引用的五分钟先例。该间隔不超过 Node 的最大定时器延迟，因此不会被钳制为 1 毫秒。它覆盖每个尚未完成的迭代器 `next()`：从消费方请求下一项开始，到下一条有效 `StreamChunk` 到达为止；消费方在两次 `next()` 调用之间花费的时间不属于提供方空闲时间。
|
||||
|
||||
`@deepseek-ai/dsh-timeout` 公开一个可重新布防的空闲看门狗原语。一个稳定的局部 `AbortController` 会与调用方信号融合，并在整个适配器调用期间传给传输层；每个尚未完成的 `next()` 都会布防看门狗，该调用完成时解除布防，下一次请求数据时再重新布防。超时会使用能力自身拥有的 `TimeoutReason` 中止这个稳定控制器，`finally` 则会清除定时器。适配器将自身看门狗归类为 `TIMEOUT`，将更早发生的上游中止归类为 `ABORTED`。现有的一次性 `deadline()` 不会被描述为滑动计时器。
|
||||
|
||||
边界测试证明两个实际传输层都能终止。手写适配器会中止其 fetch／reader，pi-ai 适配器会把稳定信号映射到 SDK，并证明 SDK 会关闭响应。如果定时器只拒绝消费方 promise，却让请求继续运行，就不满足此契约。
|
||||
|
||||
### 在现有日志中分隔尝试
|
||||
|
||||
一次失败尝试可以在已关闭的步骤中留下 `assistant/chunk` 事件，但绝不会追加 `assistant/message`，也不会分发工具。重试会开启下一个编号步骤，从持久表层重建请求，并生成自己的分片。步骤仍处于打开状态时，UI 可以渲染实时分片；当 `llm/retry` 标识失败步骤，或 `turn/end` 记录终止失败时，UI 再标记或清除这份暂时视图。消息派生仍会忽略失败分片。
|
||||
|
||||
如果恢复预算耗尽，最终失败会连同结构化事实在 `turn/end.reason` 中存储一次。如果暂时性恢复继续，`llm/retry` 就是该次尝试的失败与延迟的持久归属位置。本决策不增加独立的最终错误事件或响应 id 词汇。
|
||||
|
||||
## 不在范围内
|
||||
|
||||
- 自动提供方或模型故障转移。请求已显式选择一个提供方和模型，提供方注册表也有意规定每个提供方只由一个适配器负责。
|
||||
- 在成功的终止性 finish 后重试或继续，或将两次尝试的分片拼接成一条 assistant 消息。
|
||||
- 修复格式错误的工具参数、拒答、内容过滤或其他语义模型输出。
|
||||
- 无界重试、无人值守地持续重试直至取消、熔断器、共享提供方健康状态或跨 agent 重试预算。
|
||||
- 在没有生产消费方的情况下，把 `llm/stream` 改造成响应生命周期或增加便利的生成 API。
|
||||
|
||||
## 考虑过的替代方案
|
||||
|
||||
- **在 `llm/stream` 或提供方 SDK 内部重试**：拒绝采用，因为原始流一旦发出分片便没有持久尝试边界，隐藏的 SDK 重试会成倍放大预算，而且两条路径都无法一致地记录每次失败尝试。
|
||||
- **向 `dsh-llm` 增加响应开始、中断、丢弃、失败和提交事件**：拒绝采用，因为 agent 日志已经分隔原始分片、成功消息和编号尝试。第二套状态机会重复归属关系，又不能支持有界的同路由重试。
|
||||
- **增加逻辑路由、能力矩阵和故障转移选择**：拒绝采用，因为当前请求已经显式指定提供方和模型，每个提供方由一个适配器负责，而且没有当前消费方要求自动回退或能够证明语义兼容性。
|
||||
- **把 `retryable` 或 `failover` 放在 `LlmFailure` 上**：拒绝采用，因为适配器报告事实，部署策略决定动作。同一个 429 可以在交互式组合包中重试，也可以在成本受限的批处理中被拒绝。
|
||||
- **只要调用方仍处于活跃状态就无限重试**：拒绝采用，因为这会让一次请求产生无界成本和延迟。可见状态能使有界等待易于理解，却不能让无限预算变得安全。
|
||||
- **只通过进程 logger 记录重试状态**：拒绝采用，因为进程日志无法重建会话行为，也不能驱动回放后的 UI 状态。
|
||||
- **只保留扁平 code**：拒绝采用，因为重试延迟和提供方请求 id 是结构化的提供方事实，而当不同协议失败共用一个稳定 code 时，诊断还需要 HTTP 状态。
|
||||
|
||||
## 验证
|
||||
|
||||
- `LlmFailure` 是最终适配器抛出失败、错误 finish 和中止 finish 使用的唯一可序列化载荷；在可用时，规范化保留稳定 code、状态、重试延迟、品牌化的提供方请求 id、错误原因，以及调用方中止与适配器超时之间的分类。
|
||||
- 适配器抛出的 `Error` 会以完全相同的对象抵达 `agent/request-error`，其伴随的 `LlmFailure` 则抵达相邻参数；测试保留针对可扩展及冻结第三方错误的现有对象标识断言。
|
||||
- DeepSeek 和 pi-ai 适配器测试覆盖具有代表性的 400、401/403、429、5xx、连接、格式错误／截断流、超时、中止、Retry-After 秒数／日期、请求 id 和未知 SDK 错误路径，恢复策略无需解析消息文本。
|
||||
- Pi 将 SDK 选项固定为零次重试，并针对可重试的提供方响应执行一次可观测的实际网络请求；独立测试确保移除任一边界都会失败。
|
||||
- `agent/request-error` 携带当前失败事实以及不可变的先前已重试失败事实；成功会清除该历史，暂时性失败／上下文溢出交替发生的集成测试证明两种策略只消耗各自的有限预算。
|
||||
- `dsh-llm-retry` 在 Loader 启动时验证每个配置字段，使用 `next()` 委托所有不合格路径，而且在没有其他策略时最多发起 `maxTransientRetries + 1` 次提供方请求。
|
||||
- 退避期间执行 HMR 的测试证明：释放过程会注销监听器、中止并等待其捕获的回调，释放后不发出重试决策，也不留下存活的定时器或 promise。
|
||||
- 纯单元测试覆盖暂时性 code 选择、指数退避和抖动边界、有效及超出上限的 `Retry-After`、耗尽的预算、确定性定时器／随机数 seam，以及退避期间中止。
|
||||
- 真实 agent-loop 测试覆盖分片前失败、部分分片后失败、抛出及带内失败、在新步骤中重试至成功、耗尽后写入结构化 `turn/end.reason`，以及与 `dsh-compact-basic` 上下文溢出恢复的组合。
|
||||
- 部分分片集成测试证明：失败分片仍归属于失败步骤，该步骤不会提交 assistant 消息或工具副作用，成功的重试具有不同的来源信息。
|
||||
- 插件拥有的不进入表层的 `llm/retry` 事件可在 JSONL 和 SQLite 往返后保留，被消息派生忽略，并驱动 TUI 撤回和计划重试渲染。无密钥快照覆盖调度、取消、成功和耗尽；ACP 自动化快照确认，被丢弃的尝试不会通过协议发出，而恢复后的回复会正常发出。
|
||||
- 空闲看门狗测试证明：只有 `next()` 尚未完成时才会重新布防稳定信号；在消费方思考期间及 `finally` 中会解除布防；它与总调用 deadline 以及更早发生的调用方中止分开分类。适配器测试证明该信号会终止底层请求，而不只是与其脱离。
|
||||
- `ctx.llm.stream()` 的直接调用方仍只尝试一次，并收到相同的结构化失败事实。
|
||||
|
||||
## 后果
|
||||
|
||||
- 每次暂时性恢复尝试都以一个已关闭步骤加 `llm/retry` 的形式可见，有界策略还会防止隐藏的 SDK 重试成倍增加成本。即使没有分片到达，重试仍可能造成提供方重复计费；有限的尝试预算只能限制而无法消除此风险。
|
||||
- 提供方 SDK 可能隐藏状态或重试标头。适配器会保留 SDK 公开的稳定事实，否则使用粗粒度 code，而不会让恢复策略解析脆弱的文本。
|
||||
- 持久重试事件扩展了会话协议和 UI 状态机。事件与其消费方一同交付，可避免产生无人使用的遥测词汇；但以后更改 schema 仍需要同步完成持久化和回放工作。
|
||||
- 清除失败步骤的实时分片可能会明显撤回输出。与把丢弃的文本或不完整工具 JSON 呈现为已提交历史相比，这是更好的选择；快照固定这一转换。
|
||||
- 适配器局部的空闲强制机制可以终止停滞的传输，而不会计入消费方思考时间。每个传输边界的契约测试会防止 SDK 漂移。
|
||||
- 多个恢复插件会叠加各自的有限预算。此处它们的分类器互不重叠；重叠的分类器会形成依赖注册顺序的策略，必须由引入它们的插件记录并测试。
|
||||
|
||||
## 相关资料
|
||||
|
||||
- [结构化错误分类体系](../../implemented/architecture/2026-06-11-structured-error-taxonomy.md)负责稳定、可供机器路由的 code 与 cause chaining。
|
||||
- [可重建请求](../../implemented/architecture/2026-07-05-reconstructable-requests.md)使提供方／模型和完整请求输入在分发前持久化。
|
||||
- [超时 deadline 库](../../implemented/architecture/2026-07-06-timeout-deadline-library.md)将共享的 deadline 分类与能力自身拥有的终止操作分开。
|
||||
- [调用后压缩压力与上下文溢出恢复](../../implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md)负责当前已关闭步骤的请求恢复 seam 与有界溢出重试。
|
||||
- [提供方路由的 LLM 适配器](../../implemented/architecture/2026-07-14-provider-routed-llm-adapters.md)负责显式提供方／模型路由与每个提供方仅有一个适配器的不变量。
|
||||
@@ -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
|
||||
2026-06-24-web-capability-seam.md: 4f4e821fec9494fe9ea96894267707d9dd202e4d
|
||||
2026-06-24-web-capability-seam.zh.md: d7c07a8ae0365c321120102a0af401d85d7e2eae
|
||||
2026-06-24-web-capability-seam.md: b705236690859961ed69b307dbb59ebefcbd65ac
|
||||
2026-06-24-web-capability-seam.zh.md: 9b6899c922524350d2eee62140480fd76a450baa
|
||||
|
||||
@@ -34,7 +34,7 @@ Search and fetch are separate tools but one web-access seam. `ctx.web` owns prov
|
||||
|
||||
This keeps the model schema stable without making plugin load order, credential state, or HMR timing part of the model-facing contract. If web search is enabled but no usable search provider exists, `web_search` remains visible and execution fails with a structured `WebError` such as `WEB_PROVIDER_UNAVAILABLE` or `WEB_PROVIDER_CONFIGURED_UNAVAILABLE`. If a provider appears after `dsh-tool-web`, the next execution can use it without changing the schema. If a provider disappears mid-call, execution fails with a structured `WebError` instead of silently choosing another provider or falling through to `UNKNOWN_TOOL`.
|
||||
|
||||
The seam deliberately exposes no observation surface — no registry-change event and no aggregated capability-status query. Unavailability is a fact a caller observes by executing: `search()`/`fetch()` resolve the provider at call time and throw the structured `WebError` that names what failed. [The observation-surface Agent Note](../simplification/2026-07-04-drop-unconsumed-web-observation-surface.md) records that judgment: derived-on-call selection and enablement-based registration leave no consumer that needs a change signal or an availability probe distinct from executing and routing the error, and a future provider-status panel reintroduces the smallest signal or query it actually consumes.
|
||||
The seam deliberately exposes no observation surface — no registry-change event and no aggregated capability-status query. Unavailability is a fact a caller observes by executing: `search()`/`fetch()` resolve the provider at call time and throw the structured `WebError` that names what failed. [The observation-surface Agent Note](../../archived/simplification/2026-07-04-drop-unconsumed-web-observation-surface.md) records that judgment: derived-on-call selection and enablement-based registration leave no consumer that needs a change signal or an availability probe distinct from executing and routing the error, and a future provider-status panel reintroduces the smallest signal or query it actually consumes.
|
||||
|
||||
## Package topology
|
||||
|
||||
|
||||
@@ -34,7 +34,7 @@ Web 访问是一个一等能力 seam，遵循[能力 seam Agent Note](2026-06-13
|
||||
|
||||
这使模型 schema 保持稳定，而不将插件加载顺序、凭证状态或 HMR（热模块替换）时序纳入面向模型的契约。如果 web 搜索已启用但不存在可用的搜索提供方，`web_search` 仍然可见，执行时以结构化的 `WebError`（如 `WEB_PROVIDER_UNAVAILABLE` 或 `WEB_PROVIDER_CONFIGURED_UNAVAILABLE`）失败。如果某个提供方在 `dsh-tool-web` 之后出现，下一次执行即可使用它而无需更改 schema。如果某个提供方在调用过程中消失，执行以结构化的 `WebError` 失败，而不是静默选择另一个提供方或回退到 `UNKNOWN_TOOL`。
|
||||
|
||||
该 seam 刻意不暴露任何观察面——没有注册表变更事件，也没有聚合的能力状态查询。不可用性是调用方通过执行观察到的事实：`search()`/`fetch()` 在调用时解析提供方，并抛出命名了失败原因的结构化 `WebError`。[观察面 Agent Note](../simplification/2026-07-04-drop-unconsumed-web-observation-surface.md) 记录了这一判断：基于调用的派生选择与基于启用的注册使得没有消费方需要变更信号或独立于执行和错误路由的可用性探测；未来的提供方状态面板会重新引入它实际消费的最小信号或查询。
|
||||
该 seam 刻意不暴露任何观察面——没有注册表变更事件，也没有聚合的能力状态查询。不可用性是调用方通过执行观察到的事实：`search()`/`fetch()` 在调用时解析提供方，并抛出命名了失败原因的结构化 `WebError`。[观察面 Agent Note](../../archived/simplification/2026-07-04-drop-unconsumed-web-observation-surface.md) 记录了这一判断：基于调用的派生选择与基于启用的注册使得没有消费方需要变更信号或独立于执行和错误路由的可用性探测；未来的提供方状态面板会重新引入它实际消费的最小信号或查询。
|
||||
|
||||
## 包拓扑
|
||||
|
||||
|
||||
@@ -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
|
||||
2026-06-30-event-domain-semantics.md: 1f3452cce0235718c35d71577d7013f3e647648c
|
||||
2026-06-30-event-domain-semantics.zh.md: ec2da7786e80fb6a0df9ff338d77a50e7b3ef569
|
||||
2026-06-30-event-domain-semantics.md: 75c1cac11d1bfc9aa7fba9c523eab8c0475027e8
|
||||
2026-06-30-event-domain-semantics.zh.md: a412b8735b72274252473f3218e0d57d4f814bde
|
||||
|
||||
@@ -33,7 +33,7 @@ This vocabulary is the foundation for interception decisions, the durable `hook/
|
||||
- The loop no longer emits any boundary mirror; `closeStep` appends `step/end` only and `closeTurn` appends `turn/end` only. `Session.append` owns post-commit observer containment, so a throwing boundary observer cannot change the turn outcome or starve later consumers; an acceptance or internal validation failure still escapes before the boundary enters the log.
|
||||
- Tests that observed boundaries via the removed emits now observe the durable `turn/start`/`turn/end`/`step/start`/`step/end` session events — the behavior they pin (boundary ordering, step counting) is unchanged; only the feed they read moved to the canonical one. The tests that exercised a *throwing turn-boundary emit listener* were deleted, because that code path no longer exists (there is no emit to throw from). Per [AGENTS.md "tests document behavior, not golden truth"](../../../../AGENTS.md), the behavior and its test moved (or died) together.
|
||||
- The loop marks the step open (`stepOpen = true`) only after `append('step/start')` returns. Internal dispatch validation runs before the log push and may reject without opening a step; post-commit `session/event` observer failures are contained inside `Session.append`. The marker therefore represents exactly the committed boundary that owes a later `step/end`.
|
||||
- The full realization of this is [the simplification Agent Note "Stop mirroring durable boundaries as agent events"](../simplification/2026-06-20-remove-agent-boundary-mirror-events.md): all four boundary mirrors are removed and every consumer reads boundaries off `session/event`. `agent/steering` (not a boundary mirror) stayed outside that Agent Note's scope and was removed by its own follow-up, [Remove the `agent/steering` mirror emit](../simplification/2026-07-04-remove-agent-steering-mirror.md) — it mirrored the durable `steering/message`.
|
||||
- The full realization of this is [the simplification Agent Note "Stop mirroring durable boundaries as agent events"](../simplification/2026-06-20-remove-agent-boundary-mirror-events.md): all four boundary mirrors are removed and every consumer reads boundaries off `session/event`. `agent/steering` (not a boundary mirror) stayed outside that Agent Note's scope and was removed by its own follow-up, [Remove the `agent/steering` mirror emit](../../archived/simplification/2026-07-04-remove-agent-steering-mirror.md) — it mirrored the durable `steering/message`.
|
||||
- The cordis events catalog (`docs/cordis-catalog/events.md`) is regenerated to drop the mirror events.
|
||||
|
||||
<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) -->
|
||||
|
||||
@@ -33,7 +33,7 @@ harness 通过 Cordis 事件分类体系扩展 agent loop（智能体循环）
|
||||
- 循环不再 emit 任何边界镜像；`closeStep` 仅追加 `step/end`，`closeTurn` 仅追加 `turn/end`。`Session.append` 负责 post-commit observer 隔离，因此抛出异常的边界 observer 无法改变轮次结果或饿死后续消费方；接受或内部校验失败仍会在边界进入日志之前逃逸。
|
||||
- 之前通过已移除 emit 观察边界的测试，现在观察持久的 `turn/start`/`turn/end`/`step/start`/`step/end` 会话事件——它们固定的行为（边界顺序、步骤计数）不变；只是读取的源移到了规范源。那些测试*抛出异常的轮次边界 emit 监听器*的用例被删除，因为该代码路径不再存在（没有 emit 可供抛出）。按照 [AGENTS.md「测试记录行为，而非黄金真相」](../../../../AGENTS.md)，行为与其测试一同迁移（或一同消亡）。
|
||||
- 循环仅在 `append('step/start')` 返回后才标记步骤已打开（`stepOpen = true`）。内部分发校验在日志推入之前运行，可能在不打开步骤的情况下拒绝；post-commit `session/event` observer 的失败被隔离在 `Session.append` 内部。因此该标记精确表示已提交的、欠一个后续 `step/end` 的边界。
|
||||
- 完整实现见[简化 Agent Note「停止将持久边界镜像为 agent 事件」](../simplification/2026-06-20-remove-agent-boundary-mirror-events.md)：全部四个边界镜像被移除，所有消费方从 `session/event` 读取边界。`agent/steering`（不是边界镜像）不在该 Agent Note 范围内，由其后续 Agent Note [移除 `agent/steering` 镜像 emit](../simplification/2026-07-04-remove-agent-steering-mirror.md) 单独移除——它镜像的是持久的 `steering/message`。
|
||||
- 完整实现见[简化 Agent Note「停止将持久边界镜像为 agent 事件」](../simplification/2026-06-20-remove-agent-boundary-mirror-events.md)：全部四个边界镜像被移除，所有消费方从 `session/event` 读取边界。`agent/steering`（不是边界镜像）不在该 Agent Note 范围内，由其后续 Agent Note [移除 `agent/steering` 镜像 emit](../../archived/simplification/2026-07-04-remove-agent-steering-mirror.md) 单独移除——它镜像的是持久的 `steering/message`。
|
||||
- Cordis 事件目录（`docs/cordis-catalog/events.md`）重新生成以移除镜像事件。
|
||||
|
||||
<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) -->
|
||||
|
||||
@@ -1,53 +0,0 @@
|
||||
# Agent Note: Add direct directory listing to the filesystem seam
|
||||
|
||||
Status: implemented
|
||||
|
||||
English | [中文](2026-07-03-filesystem-directory-listing-seam.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
`@deepseek-ai/dsh-fs` is the provider seam for filesystem access, with local and future non-local backends behind the same `ctx.fs` contract. Before this change it could resolve paths, stat targets, read text, stream text, write text, and edit text. That was enough for model-facing file tools, but not for non-model-facing consumers that need to enumerate directories without importing `node:fs`.
|
||||
|
||||
The immediate pressure came from skill loading: reading an individual `SKILL.md` can already go through `ctx.get('fs')`, but discovering which skill roots contain `<name>/SKILL.md` or `<name>.md` still needs directory enumeration. Adding directory listing only in `dsh-skill` would either keep a direct Node dependency there or invent a one-off local helper outside the filesystem provider stack.
|
||||
|
||||
This decision adds the provider capability without a model-facing `ls`/`list` tool or skill-discovery change. Those consumers require separate UX, prompt, and policy decisions.
|
||||
|
||||
## Decision
|
||||
|
||||
Add `FileSystem.listDir(target, signal?)` to `@deepseek-ai/dsh-fs`.
|
||||
|
||||
`listDir` lists one directory level only. It returns direct children in stable name order and includes:
|
||||
|
||||
- `name`: the child basename.
|
||||
- `type`: `file`, `directory`, or `other`.
|
||||
- `target`: the resolved child `FsTarget`.
|
||||
- `version`: cheap metadata when available.
|
||||
- `size`: regular-file size when available.
|
||||
|
||||
It never reads file contents. Recursive traversal, globbing, pagination, search, file watching, and model-facing rendering are intentionally out of scope.
|
||||
|
||||
The local backend implements this through `readdir({ withFileTypes: true })`, `resolveLocalTarget`, and metadata `stat`/`realpath` probes. The result order is deterministic (`name.localeCompare`) to keep prompt/listing output stable for future consumers and improve prefix-cache reuse.
|
||||
|
||||
Broken or disappeared children may be represented as `type: 'other'` without `version`/`size`; they do not abort the whole listing. Permission or backend I/O failures while listing the directory or resolving/probing child metadata fail the whole listing with structured `FsError` codes:
|
||||
|
||||
- `FS_NOT_FOUND` for missing targets.
|
||||
- `FS_NOT_DIRECTORY` for existing non-directory targets.
|
||||
- `FS_PERMISSION_DENIED` for permission failures.
|
||||
- `FS_IO_ERROR` for other backend I/O failures.
|
||||
- `FS_ABORTED` for aborted calls.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
**Add a model-facing list tool with the seam.** Rejected because its prompt, schema, and rendering contracts are independent of the provider primitive.
|
||||
|
||||
**Keep directory enumeration in each consumer.** Rejected. That would bind product packages such as `dsh-skill` to Node/local filesystem behavior and bypass policy/remote/sandboxed backends.
|
||||
|
||||
**Make `listDir` recursive or glob-shaped.** Rejected for now. Skill-root discovery only needs direct children, and a simple direct listing is the smallest backend contract future consumers can safely compose.
|
||||
|
||||
**Skip children that fail metadata resolution.** Rejected. The API promises resolved child targets, so permission/IO failures while resolving a child are contract failures. Broken or disappeared children are the exception because they can still be represented without claiming a live resolved file.
|
||||
|
||||
## Consequences
|
||||
|
||||
Every filesystem backend must now implement one additional provider primitive. That is deliberate foundation work while the harness is still unreleased, but it does mean future sandboxed/remote backends need to define equivalent direct-child listing behavior.
|
||||
|
||||
The capability remains provider-facing. Until a consumer lands, ACP/model sessions will still need existing tools such as `bash` for directory listing. The absence of a model-facing `listdir` tool is expected, not a wiring failure.
|
||||
@@ -1,53 +0,0 @@
|
||||
# Agent Note: 为文件系统 seam 添加直接目录列举能力
|
||||
|
||||
Status: implemented
|
||||
|
||||
[English](2026-07-03-filesystem-directory-listing-seam.md) | 中文
|
||||
|
||||
## 问题
|
||||
|
||||
`@deepseek-ai/dsh-fs` 是文件系统访问的提供方 seam，本地后端与未来的非本地后端共享同一个 `ctx.fs` 契约。在本次变更之前，它能解析路径、stat 目标、读取文本、流式读取文本、写入文本和编辑文本。这对面向模型的文件工具已经足够，但对于需要枚举目录而又不想直接导入 `node:fs` 的非模型侧消费方来说还不够。
|
||||
|
||||
直接的压力来自 skill（技能）加载：读取单个 `SKILL.md` 已经可以走 `ctx.get('fs')`，但发现哪些 skill 根目录包含 `<name>/SKILL.md` 或 `<name>.md` 仍需要目录枚举。如果仅在 `dsh-skill` 中添加目录列举，要么保留对 Node 的直接依赖，要么在文件系统提供方栈之外发明一个一次性的本地辅助函数。
|
||||
|
||||
本决策只添加提供方能力，不涉及面向模型的 `ls`/`list` 工具或 skill 发现机制的变更。那些消费方需要独立的 UX、提示词与策略决策。
|
||||
|
||||
## 决策
|
||||
|
||||
在 `@deepseek-ai/dsh-fs` 中添加 `FileSystem.listDir(target, signal?)`。
|
||||
|
||||
`listDir` 仅列举一层目录。它以稳定的名称顺序返回直接子项，包含以下字段：
|
||||
|
||||
- `name`：子项的 basename；
|
||||
- `type`：`file`、`directory` 或 `other`；
|
||||
- `target`：已解析的子项 `FsTarget`；
|
||||
- `version`：可用时返回的轻量元数据；
|
||||
- `size`：可用时返回的常规文件大小。
|
||||
|
||||
它从不读取文件内容。递归遍历、glob 匹配、分页、搜索、文件监听和面向模型的渲染均有意不在范围内。
|
||||
|
||||
本地后端通过 `readdir({ withFileTypes: true })`、`resolveLocalTarget` 以及元数据 `stat`/`realpath` 探测来实现。结果顺序是确定性的（`name.localeCompare`），以保持未来消费方的提示词/列表输出稳定，并提高前缀缓存复用率。
|
||||
|
||||
损坏或已消失的子项可以表示为 `type: 'other'`（不带 `version`/`size`）；它们不会中止整个列举。在列举目录或解析/探测子项元数据时遇到权限或后端 I/O 故障，则以结构化的 `FsError` 错误码使整个列举失败：
|
||||
|
||||
- `FS_NOT_FOUND`：目标不存在；
|
||||
- `FS_NOT_DIRECTORY`：目标存在但不是目录；
|
||||
- `FS_PERMISSION_DENIED`：权限不足；
|
||||
- `FS_IO_ERROR`：其他后端 I/O 故障；
|
||||
- `FS_ABORTED`：调用被中止。
|
||||
|
||||
## 曾考虑的替代方案
|
||||
|
||||
**在添加 seam 的同时添加面向模型的 list 工具。** 否决。其提示词、schema 和渲染契约与提供方原语相互独立。
|
||||
|
||||
**让每个消费方自行枚举目录。** 否决。这会将 `dsh-skill` 等产品包绑定到 Node/本地文件系统行为上，绕过策略/远程/沙箱后端。
|
||||
|
||||
**让 `listDir` 支持递归或 glob 形式。** 暂时否决。skill 根发现只需要直接子项，而简单的单层列举是未来消费方可以安全组合的最小后端契约。
|
||||
|
||||
**跳过元数据解析失败的子项。** 否决。API 承诺返回已解析的子项 target，因此解析子项时的权限/IO 故障属于契约失败。损坏或已消失的子项是例外，因为它们仍可在不声称拥有一个活跃已解析文件的前提下被表示。
|
||||
|
||||
## 后果
|
||||
|
||||
每个文件系统后端现在必须多实现一个提供方原语。这是 harness 尚未发布时有意为之的基础工作，但也意味着未来的沙箱/远程后端需要定义等价的直接子项列举行为。
|
||||
|
||||
该能力仍停留在提供方层面。在消费方落地之前，ACP（Agent Client Protocol）/模型会话仍需使用 `bash` 等既有工具来列举目录。缺少面向模型的 `listdir` 工具是预期行为，而非接线错误。
|
||||
@@ -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
|
||||
2026-07-23-unified-session-query-service.md: 676a42017ca42f9e649f6529f84787e7162faac0
|
||||
2026-07-23-unified-session-query-service.zh.md: d4449a415840d61cbb10f88def1062a13e556749
|
||||
2026-07-05-windows-jsonl-durable-publish.md: 38c4adc7a4f85d45e53e70fcac84073ab4e50775
|
||||
2026-07-05-windows-jsonl-durable-publish.zh.md: 8dc77a0ab1b9273cf3f6ecb26916c7861ee81ec4
|
||||
@@ -2,6 +2,8 @@
|
||||
|
||||
Status: implemented
|
||||
|
||||
English | [中文](2026-07-05-windows-jsonl-durable-publish.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
`dsh-session-persistence-jsonl` publishes a session log lazily on the first append. The POSIX protocol writes a temp file, fsyncs it, links it to the final name, fsyncs the parent directory, and then removes the temp link. The parent-directory fsync is part of the durability contract: a crash after the namespace change must not lose the committed final name while leaving callers believing the session log materialized.
|
||||
|
||||
@@ -0,0 +1,35 @@
|
||||
# Agent Note: Windows 原生持久 JSONL 发布
|
||||
|
||||
Status: implemented
|
||||
|
||||
[English](2026-07-05-windows-jsonl-durable-publish.md) | 中文
|
||||
|
||||
## 问题
|
||||
|
||||
`dsh-session-persistence-jsonl` 在首次追加时延迟发布会话日志。POSIX 协议会写入临时文件，对其执行 fsync，将其链接至最终名称，对父目录执行 fsync，然后移除临时链接。对父目录执行 fsync 是持久性契约的一部分：命名空间变更后发生崩溃时，已经提交的最终名称不能丢失，否则调用方会误以为会话日志已经物化。
|
||||
|
||||
Windows 具备原子命名空间操作，但 Node 没有暴露与 POSIX 等价的父目录 fsync 契约。如果把 Windows 目录同步失败视为成功，就会在无提示的情况下削弱持久化后端。因此，Windows 路径需要采用不同的发布原语，而不是在 POSIX 的 `syncDir` 辅助函数中添加条件分支。
|
||||
|
||||
## 决策
|
||||
|
||||
JSONL 后端会在 `materialize()` 内部、任何命名空间变更之前分流。共享代码计算会话目录、最终日志路径，以及编码后的 header 和初始事件批次；随后 POSIX 与 Windows 分别执行各自的发布协议。
|
||||
|
||||
POSIX 保留现有协议：创建根目录、项目目录与会话目录，并对其父目录执行 fsync；写入临时文件并对其执行 fsync；使用 `link()` 发布，确保绝不覆盖已有的最终日志；对会话目录执行 fsync；最后移除多余的临时硬链接。
|
||||
|
||||
Windows 通过持久的暂存发布来创建缺失目录：在固定的 `.dsh-mkdir-` 前缀下创建一个随机同级目录，其名称与目标基本名无关；随后使用 `MoveFileExW(..., MOVEFILE_WRITE_THROUGH)` 将其发布为最终目录名称，且不使用 `MOVEFILE_REPLACE_EXISTING` 或 `MOVEFILE_COPY_ALLOWED`。文件物化先写入临时日志并对其执行 fsync，再以同一个启用写穿透的 `MoveFileExW` 调用将临时文件发布到最终路径，并且同样不允许替换。`koffi` 是覆盖这组 API 所需的最小 Win32 桥接层；`pnpm-workspace.yaml` 允许执行它的安装脚本，因为该包（package）会分发原生 loader 和预构建的平台模块。
|
||||
|
||||
## 考虑过的替代方案
|
||||
|
||||
**忽略 Windows 目录同步失败。** 不予采纳，因为这会在没有强制将已发布的命名空间条目写入稳定存储时，就把首次追加报告为持久化成功。
|
||||
|
||||
**使用 `CreateHardLinkW`。** 不予采纳，因为硬链接依赖文件系统、不能发布目录，并且没有提供写穿透选项。
|
||||
|
||||
**使用替换或事务型 API。** `ReplaceFileW` 的替换语义与拒绝同一 id 冲突的要求相悖，而新应用设计不应使用 Transactional NTFS。
|
||||
|
||||
## 影响
|
||||
|
||||
该后端在各平台上维持同一项外部契约：首次追加要么把完整日志发布到最终名称，要么失败且不覆盖已有日志。平台分流只是实现细节；`SessionPersistence` API 和 JSONL 逻辑记录格式均不改变。后续的 [Zstandard 编码决策](2026-07-19-zstandard-jsonl-session-logs.md)会先作用于不透明字节，然后才由任一平台执行发布。
|
||||
|
||||
Windows 测试会在原生 Windows 上执行真实的 Win32 发布路径。断电行为属于 API 契约属性，单元测试无法证明；可测试的不变量包括：Windows 物化不会调用目录 fsync、最终路径冲突会失败、达到最大长度的目标路径组件仍可物化、临时日志在发布前已经执行 fsync，并且生成的日志可以正常加载。
|
||||
|
||||
两个平台的追加和修复仍使用普通文件句柄 fsync。追加失败后，系统会关闭仅追加句柄，以读写模式重新打开日志，将文件截断到追加前的大小，并对回滚结果执行 fsync，因为 Windows 不允许在仅追加句柄上调用 `ftruncate`。
|
||||
@@ -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
|
||||
2026-07-21-dsh-system-prompt-source-path.md: 4cb89e8124840bba6633235d195e95957245137c
|
||||
2026-07-21-dsh-system-prompt-source-path.zh.md: 90c23bed4a3f95155e323c63a68fe2da09543ea6
|
||||
2026-07-06-tool-result-retention-library.md: 5e42660360e5a23b419c75b9c8006bec459bc322
|
||||
2026-07-06-tool-result-retention-library.zh.md: 6e824667f17b361efb57b173c44f489da2cab3b3
|
||||
@@ -2,6 +2,8 @@
|
||||
|
||||
Status: implemented
|
||||
|
||||
English | [中文](2026-07-06-tool-result-retention-library.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
Several model-facing tools already bound the amount of context they return, but each one owns a different local mechanism and vocabulary: bash keeps a tail plus spill files, web search caps source lists, web fetch caps body content, and `glob` / `grep` discovery needs an inline first page while keeping exact omission metadata for the full result set. A single `truncate(text)` helper cannot cover those cases: item tools need item counts and grouping outside the primitive, while text tools need byte budgets and UTF-8-safe head/tail cuts.
|
||||
|
||||
@@ -0,0 +1,157 @@
|
||||
# Agent Note: 工具结果保留库
|
||||
|
||||
Status: implemented
|
||||
|
||||
[English](2026-07-06-tool-result-retention-library.md) | 中文
|
||||
|
||||
## 问题
|
||||
|
||||
多个面向模型的工具已经限制其返回的上下文量，但每个工具都拥有不同的局部机制和词汇：bash 保留尾部并提供落盘文件；web search 限制来源列表；web fetch 限制正文内容；`glob`／`grep` 发现工具需要在行内提供第一页，同时为完整结果集保留精确的省略元数据。单一的 `truncate(text)` 辅助函数无法覆盖这些情况：条目型工具需要条目计数，并在原语之外分组；文本型工具则需要字节预算和 UTF-8 安全的首尾裁切。
|
||||
|
||||
这些工具需要共享的抽象是**保留**，而不是通用集合。调用方向一个有界对象输入条目或文本分片，稍后取得保留内容与精确的省略元数据。工具专用代码仍负责业务语义：文件分组、行号、退出码、提供方错误状态、落盘文件和面向模型的说明。公共库只负责一个机械问题：「保留了什么，又省略了什么？」
|
||||
|
||||
## 决策
|
||||
|
||||
`@deepseek-ai/dsh-retention` 位于 `packages/util/` 下，与 `dsh-brand` 和 `dsh-timeout` 同级，负责有界的模型可见输出。它是一组纯类与函数构成的库，**不是** Cordis 服务或插件：不接收 `ctx`、不注册任何内容、不持有跨调用状态，也不发出事件。各工具包（package）需要限制输出时直接导入它。
|
||||
|
||||
该库包含两个相互独立的 retainer：
|
||||
|
||||
- `ItemRetainer<T>` 处理有序逻辑单元，例如路径、grep 匹配项或搜索来源。v1 只支持 `head` 保留，同时维持 retainer 形态，以便未来加入其他保留策略。
|
||||
- `TextRetainer` 处理面向字节的文本流，例如 bash stdout／stderr 或 web 响应正文。它支持 `head`、`tail` 和 `headTail` 保留，并在 `finish()` 时维持 UTF-8 边界。
|
||||
|
||||
两个 retainer 都会返回一个小型 `PushDecision`；每次调用 `push()` 后，调用方都能得知该单元／分片是否完整保留，以及累积结果此时是否已被截断。因为调用方会继续输入每一个已观察到的条目／分片，所以省略计数是精确的。
|
||||
|
||||
```ts ignore-check
|
||||
/**
|
||||
* How much content the retainer omitted.
|
||||
*
|
||||
* `unknown` is reserved for callers that omit without a count; the retainers
|
||||
* themselves return `none` or `exact`.
|
||||
*/
|
||||
type Omitted =
|
||||
| { kind: 'none' }
|
||||
| { kind: 'exact'; count: number }
|
||||
| { kind: 'unknown' }
|
||||
|
||||
interface PushDecision {
|
||||
kept: boolean
|
||||
truncated: boolean
|
||||
}
|
||||
|
||||
/**
|
||||
* Final result for ordered logical units.
|
||||
*/
|
||||
interface RetainedItems<T> {
|
||||
items: T[]
|
||||
truncated: boolean
|
||||
seen: number
|
||||
kept: number
|
||||
omitted: Omitted
|
||||
}
|
||||
|
||||
/**
|
||||
* Final result for text streams.
|
||||
*
|
||||
* The returned `text` is safe to send to a formatter; the retainer does not add
|
||||
* tool-specific headers, exit markers, XML tags, or recovery instructions.
|
||||
*/
|
||||
interface RetainedText {
|
||||
text: string
|
||||
truncated: boolean
|
||||
omittedBytes: Omitted
|
||||
}
|
||||
```
|
||||
|
||||
### 策略
|
||||
|
||||
条目保留支持头部窗口。文本保留支持头部、尾部与首尾字节窗口。
|
||||
|
||||
```ts ignore-check
|
||||
type ItemRetentionStrategy =
|
||||
| {
|
||||
/** Keep the first `maxItems` units. Use for `glob`, `grep`, and web sources. */
|
||||
kind: 'head'
|
||||
maxItems: number
|
||||
}
|
||||
|
||||
type TextRetentionStrategy =
|
||||
| {
|
||||
/** Keep the first `maxBytes` bytes. */
|
||||
kind: 'head'
|
||||
maxBytes: number
|
||||
}
|
||||
| {
|
||||
/** Keep the final `maxBytes` bytes. Requires reading to the end. */
|
||||
kind: 'tail'
|
||||
maxBytes: number
|
||||
}
|
||||
| {
|
||||
/** Keep a stable prefix and suffix, omitting the middle. Requires reading to the end. */
|
||||
kind: 'headTail'
|
||||
headBytes: number
|
||||
tailBytes: number
|
||||
}
|
||||
```
|
||||
|
||||
### 工具映射
|
||||
|
||||
`read` 被有意排除在 v1 保留库之外。它的 `read-render` 辅助函数拥有文件专用的分页契约：`offset`／`limit`、行号、`totalLines`、offset 越界错误、逐行预览截断，以及能够在窗口中途停止扫描的所选输出字节上限。这是行窗口渲染器，不是通用保留原语。它未来可以共享中性的提示辅助函数，但不应把已经选定的窗口再传入 `ItemRetainer`。
|
||||
|
||||
下文的 `FsGlobEntry` 与 `FlatGrepMatch` 是预期由发现工具使用的条目形态，不是现有保留库的导出。`FsGlobEntry` 是一个由后端派生的路径；`FlatGrepMatch` 是后端将保留匹配项按文件分组之前的一条未分组 grep 匹配。
|
||||
|
||||
`glob` 收集完整的排序路径列表后，使用 `ItemRetainer<FsGlobEntry>`，并将其配置为 `{ kind: 'head', maxItems: globMaxResults }`。工具在行内保留第一页，并可以通过落盘 seam 保存完整列表。路径映射、跳过的候选项与 `incomplete` 均位于 retainer 之外。
|
||||
|
||||
`grep` 在分组前使用 `ItemRetainer<FlatGrepMatch>`，并将其配置为 `{ kind: 'head', maxItems: grepMaxMatches }`。执行器解析 ripgrep 输出、映射路径、应用逐行预览截断，并输入扁平匹配项。调用 `finish()` 后，工具按文件对保留的匹配项分组；如果行内结果达到上限，还可以通过落盘 seam 保存完整匹配列表。分组不属于 retainer，因为上限针对匹配总数，而不是文件数；逐匹配项的预览截断和 `incomplete` 也与结果级保留相互独立。
|
||||
|
||||
`bash` 可以使用 `TextRetainer`，配置为 `tail` 或 `headTail`，并读取至进程结束。bash 执行器仍负责落盘文件、退出状态、信号、超时与后台任务行为；保留辅助函数只在需要该行为时替换临时实现的内存首尾核算。长时间运行任务的所有权与[通用长时间运行工具的运行时](2026-06-20-generic-long-running-tool-runtime.md)相互独立。
|
||||
|
||||
`web_fetch` 可以使用 `TextRetainer`，配置为 `head` 或 `headTail`；如果提供方必须在内部读取和解码，也可以保留由提供方负责的正文上限。无论采用哪种方式，fetch 结果中的 `truncated` 仍是提供方／工具事实，该库只提供保留文本与省略元数据。
|
||||
|
||||
`web_search` 可以使用 `ItemRetainer<WebSearchSource>`，配置为 `head`。当前提供方通常返回数组，所以这属于事后处理，但仍能统一提示信息。
|
||||
|
||||
### 提示
|
||||
|
||||
该库公开一个中性的提示结构和一个小型格式化钩子，但面向用户的措辞由工具提供。grep 页脚会提示「缩小 pattern、path 或 include」；web fetch 页脚会提示「获取更具体的 URL 或章节」；bash 则可以指向落盘文件。retainer 无法得知这些恢复操作。
|
||||
|
||||
```ts ignore-check
|
||||
interface RetentionNotice {
|
||||
scope: string
|
||||
strategy: 'head' | 'tail' | 'headTail'
|
||||
unit: 'items' | 'bytes' | 'chars' | 'lines'
|
||||
limit: number | { head: number; tail: number }
|
||||
kept: number
|
||||
omitted: Omitted
|
||||
}
|
||||
|
||||
const formatGrepNotice = (notice: RetentionNotice): string =>
|
||||
formatRetentionNotice(
|
||||
notice,
|
||||
({ kept }) => `Results capped at ${kept}. Narrow the pattern, path, or include to see more.`,
|
||||
)
|
||||
```
|
||||
|
||||
格式化钩子刻意保持精简：工具把 `RetentionNotice` 转换为自己的页脚文本。辅助函数可以统一省略措辞，但不负责恢复指引。
|
||||
|
||||
`truncated` 表示 retainer 因预算省略了原本可用的内容，不表示上游结果不完整。工具会为权限失败、跳过的二进制文件、提供方局部失败、不可读候选项、无效 UTF-8，以及其他任何「无法检查」状况保留独立字段。
|
||||
|
||||
## 影响
|
||||
|
||||
**已交付内容。** `@deepseek-ai/dsh-retention` 导出 `ItemRetainer`、`TextRetainer`、结果类型（`RetainedItems`、`RetainedText`）、策略类型（`ItemRetentionStrategy`、`TextRetentionStrategy`）、`Omitted`、`PushDecision`、`RetentionNotice`，以及中性的提示辅助函数 `describeOmitted`／`formatRetentionNotice`，且不依赖 Cordis 或任何工具包。单元测试覆盖具有精确省略计数的条目头部保留、文本头部保留、文本尾部保留、首尾字节保留、零预算、UTF-8 边界处理（2、3、4 字节码位，以及每个裁切位置上的无效起始字节）和未知省略量的措辞。
|
||||
|
||||
**已记录但尚未迁移的内容。** `glob`、`grep`、`bash`、`web_fetch` 与 `web_search` 的映射已记录在[包 README](../../../../packages/util/retention/README.md) 中，但本次改动并未把每个工具都迁移到该库；迁移工作刻意留作独立的后续任务。`read` 被明确记录为不在范围内：其 `read-render` 行窗口契约（`offset`／`limit`、`totalLines`、offset 范围错误、逐行预览截断，以及针对所选窗口的字节上限）不属于通用保留，而一个 `Omitted` 计数也无法同时表达行窗口两侧。
|
||||
|
||||
**该库维持的边界。** `truncated` 表示 retainer 因预算省略了原本可用的内容，绝不表示上游不完整。工具专用状态，包括 `incomplete`、权限失败、提供方局部失败、跳过二进制文件、bash 落盘路径恢复和无效 UTF-8，均留在工具领域字段中、位于 retainer 之外。未来改动迁移某项工具时，该包的 README 与测试必须证明，除了有意改变的提示措辞外，模型可见的结果文本没有变化。
|
||||
|
||||
**接受的取舍。** v1 接口刻意只支持条目的 `head` 保留，以及文本的 `head`／`tail`／`headTail` 保留；窗口、分组预算、感知排序的上限和上游停止控制，要等第二个消费方证明需求后再引入。文本保留按字节计数，以保障进程／正文安全；字符级和行级预览预算继续由具体工具负责。
|
||||
|
||||
## 考虑过的替代方案
|
||||
|
||||
**只进行事后 `truncate(text)`。** 不予采纳：它适合 Codex 的历史／工具输出截断场景，却会丢失条目计数、分组边界、UTF-8 安全的字节窗口与精确省略元数据。
|
||||
|
||||
**使用一个带可插拔回调的通用 `Collector<T>`。** v1 不予采纳，因为它会掩盖两种重要的资源模式。逻辑条目保留按条目计数；文本保留按字节计数并维持 UTF-8 边界。独立的 `ItemRetainer` 与 `TextRetainer` 名称明确表达这种差异，同时保持 API 精简。
|
||||
|
||||
**把 `read` 窗口交给 `ItemRetainer`。** v1 不予采纳：`read` 是当前唯一的窗口消费方，其语义属于文件分页，而不是通用保留。一个 `Omitted` 计数无法表示行窗口两侧，而且 `read` 还携带 `totalLines`、offset 范围错误、逐行预览截断和针对所选输出的字节上限。让 `read-render` 由工具所有，可以避免共享库围绕一项特例膨胀。
|
||||
|
||||
**让截断成为 `ToolExecutionResult` 的一部分。** 不予采纳：工具注册表将不得不理解工具专用的恢复指引、分组、行号、退出状态和提供方语义。保留是由工具的 Native renderer 使用的库；模型可见投影继续由工具所有，而[规范值](2026-07-20-canonical-tool-output-contract.md)可以保留完整的已采集结果。
|
||||
|
||||
**在每个面向模型的工具 schema 中公开上限。** 不作为默认方案：Claude Code 的 grep 公开 `head_limit`／`offset`，但本 harness 会把常规预算保留为部署配置，除非模型确实需要控制分页。未来可以为具体工具增加类似 read 的续传字段；它不属于共享保留原语。
|
||||
@@ -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
|
||||
2026-07-21-tui-verbose-status-line.md: 71584ee91a911cc8652512ec26b00dae8c818f36
|
||||
2026-07-21-tui-verbose-status-line.zh.md: bda3c5e8394f7707916c6fc76045b1a6f38fa95b
|
||||
2026-07-08-tool-output-spill-files.md: 7c0ca90452645d251559be25108d12883210d00e
|
||||
2026-07-08-tool-output-spill-files.zh.md: 917d710eb8650e2797287578edd1b0d62813bbd3
|
||||
@@ -2,6 +2,8 @@
|
||||
|
||||
Status: implemented
|
||||
|
||||
English | [中文](2026-07-08-tool-output-spill-files.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
Tool outputs need bounded model-facing previews, but some oversized results are still useful later. A fetched page body or a verbose tool response should not consume the next model request in full, but the model should be able to inspect the complete formatted result later with existing file-reading tools.
|
||||
|
||||
@@ -0,0 +1,195 @@
|
||||
# Agent Note: 工具输出落盘策略
|
||||
|
||||
Status: implemented
|
||||
|
||||
[English](2026-07-08-tool-output-spill-files.md) | 中文
|
||||
|
||||
## 问题
|
||||
|
||||
工具输出需要有界的模型可见预览，但部分超大结果仍可能在之后有用。抓取的页面正文或冗长的工具响应不应完整占用下一次模型请求，但模型应能使用现有文件读取工具，在之后查看经过格式化的完整结果。
|
||||
|
||||
这项改动之前的行为并不一致。`dsh-bash-local` 已经会在内存尾部溢出时，把完整 stdout／stderr 流写入私有的临时落盘文件；普通文本工具结果则仍以内联形式返回，除非工具自行临时实现上限。[工具结果保留库](2026-07-06-tool-result-retention-library.md)负责预览机制，但不负责存储，也不负责把这些机制应用于最终工具结果的执行流水线策略。
|
||||
|
||||
其形态与超时策略设计一致：工具作者声明规范值与 Native renderer，由策略插件在渲染后的内容上执行部署默认的上下文预算。工具仍可在提供方采集上限处提前落盘；由工具负责的展示落盘可以保留已完整采集的规范值，而只替换展示内容。[规范工具输出契约](2026-07-20-canonical-tool-output-contract.md)规定了这项区分。
|
||||
|
||||
## 决策
|
||||
|
||||
在新的 `packages/spill/` 分组下增加一层轻量落盘存储 seam 和一个默认落盘策略插件：
|
||||
|
||||
| 包（package） | 角色 |
|
||||
|---|---|
|
||||
| `@deepseek-ai/dsh-spill` | 接口：`ctx.spillStore`、词汇类型，不包含存储实现。 |
|
||||
| `@deepseek-ai/dsh-spill-local` | 本地后端：在宿主文件系统中提供私有、会话作用域的文件存储。 |
|
||||
| `@deepseek-ai/dsh-spill-policy` | 工具结果策略插件：包装分发后的最终文本结果，并以保留预览和落盘定位符替换超大结果。 |
|
||||
|
||||
系统不增加专用的面向模型消费方包。消费方是现有 `ctx.tools` 执行流水线：`dsh-spill-policy` 通过 `tools/post-execute` waterfall（瀑布式事件）使用最终工具结果，模型则按照后端随定位符返回的检索提示读取内容。
|
||||
|
||||
### 落盘 seam
|
||||
|
||||
存储 seam 保持最小化：保存文本，并返回定位符与检索提示。
|
||||
|
||||
```ts ignore-check
|
||||
interface SpillStore {
|
||||
saveText(input: SaveTextSpill): Promise<SpillRef>
|
||||
}
|
||||
|
||||
interface SpillSource {
|
||||
toolName: string
|
||||
callId: CallId
|
||||
label: string
|
||||
}
|
||||
|
||||
interface SaveTextSpill {
|
||||
owner: { sessionId: SessionId }
|
||||
source: SpillSource
|
||||
suggestedName: string
|
||||
content: string
|
||||
}
|
||||
|
||||
type SpillLocator = Branded<'SpillLocator'>
|
||||
|
||||
interface SpillRef {
|
||||
locator: SpillLocator
|
||||
bytes: number
|
||||
retrievalHint: string
|
||||
}
|
||||
```
|
||||
|
||||
`SpillLocator` 是一个[品牌化的](../../../../packages/util/brand)模型可见句柄，由后端返回。本地后端将其渲染为文件系统路径；远程或数据库后端可以渲染 URI、键或命令 token。消费方把它视为不透明值，并使用 `retrievalHint` 渲染，而不是假定 `read` 始终是正确的检索机制。`SpillOwner.sessionId` 是保存时的存储命名空间：fork 后的会话会从种子日志继承已有的落盘定位符，无需复制它们或重新取得所有权；fork 后的新落盘使用子会话 id。保留期清理可以连同其他旧会话产物一起使旧定位符失效；落盘 seam 不定义逐会话的清理策略。
|
||||
|
||||
`dsh-spill-local` 只负责存储细节：选择会话作用域的目录、安全名称、防止路径遍历、执行写入，以及返回 `{ locator, bytes, retrievalHint }`。它不负责保留策略、工具结果替换、搜索或文件检查。文件写入 `<root>/session-<hash>/<random>-<safeName>`：`root` 是配置路径，或延迟创建的私有（0700）进程级临时目录；会话子目录是 `sha256(sessionId)` 的短前缀；叶节点由随机十六进制前缀与调用方的 `suggestedName` 组成，后者会被清理成单一路径段（与 JSONL 后端的 `encodeSegment` 一致）。系统使用 `open(path, 'wx', 0o600)` 写入，确保独占且仅所有者可访问，因此预先植入的符号链接无法重定向写入。定位符就是该路径，检索提示则告知模型可以在该路径上使用 `read` 或 `grep`。
|
||||
|
||||
### 落盘策略
|
||||
|
||||
`dsh-spill-policy` 是一个 `tools/post-execute` 结果转换器，只提供一个配置项：
|
||||
|
||||
```ts ignore-check
|
||||
interface Config {
|
||||
/** Omitted means no automatic spill policy. Present means apply to oversized plain text tool results. */
|
||||
maxInlineBytes?: number
|
||||
}
|
||||
```
|
||||
|
||||
省略 `maxInlineBytes` 时，插件不会注册任何内容，是真正的无操作。设置该值后，它会对最终的纯文本工具结果应用默认策略：
|
||||
|
||||
1. 让工具正常运行，通过 `next()` 委托，使下游监听器先结算结果。
|
||||
2. 仅当已接受的最终 `ContentBlock[]` 全部是纯文本时，才将其展平；含任何非文本块的结果保持不变。
|
||||
3. 如果 UTF-8 字节大小不超过 `maxInlineBytes`，保持不变。
|
||||
4. 如果超出上限，使用完整的最终文本调用 `ctx.spillStore.saveText()`。
|
||||
5. 把模型可见结果替换为保留的首尾预览和落盘引用。
|
||||
|
||||
预览属于策略所有的实现默认值：以 `maxInlineBytes` 为上限，使用保留库的 `TextRetainer` 进行首尾分割。只有第二种部署证明有此需求后，未来配置才会公开预览大小。
|
||||
|
||||
替换文本刻意保持通用，因为策略只知道最终格式化的工具结果，不了解工具的内部资源：
|
||||
|
||||
```text
|
||||
<retained preview>
|
||||
|
||||
(Omitted N bytes. Full formatted result stored at: /.../session-.../....txt. Use read with offset/limit, or grep this path to search within it.)
|
||||
```
|
||||
|
||||
如果 `ctx.spillStore.saveText()` 失败（权限、ENOSPC、后端不可用），或调用没有会话所有者，或未加载后端，插件会记录原因并原样返回结果。落盘失败绝不会把成功的工具调用变为 `isError` 结果，也不会隐藏内联结果。
|
||||
|
||||
策略跳过 `read`，以避免形成 `read -> spill file -> read again` 循环。额外的选择退出配置要等确实出现第二个有此需求的工具后再引入。
|
||||
|
||||
## 示例：web_fetch
|
||||
|
||||
`web_fetch` 是首个示例，因为它天然会返回较大的文本结果，而且无需工具专用的落盘代码。该工具本身无需特殊处理：
|
||||
|
||||
```ts ignore-check
|
||||
ctx.tools.register(defineTool({
|
||||
name: 'web_fetch',
|
||||
output: {
|
||||
schema: WEB_FETCH_RESULT_SCHEMA,
|
||||
render: (_args, value) => [{ type: 'text', text: formatFetchOutput(value) }],
|
||||
},
|
||||
async execute(args, exec) {
|
||||
const result = await ctx.web.fetch({ url: args.url }, exec.signal ? { signal: exec.signal } : undefined)
|
||||
return result
|
||||
},
|
||||
}))
|
||||
```
|
||||
|
||||
配置 `dsh-spill-policy` 后，格式化后的大型 fetch 结果会自动保留并落盘。部署通过把提供方资源上限设得高于策略上限来展示此行为：
|
||||
|
||||
```yaml
|
||||
- id: web-fetch-local
|
||||
name: '@deepseek-ai/dsh-web-fetch-local'
|
||||
config:
|
||||
maxBodyChars: 500000
|
||||
|
||||
- id: spill-local
|
||||
name: '@deepseek-ai/dsh-spill-local'
|
||||
|
||||
- id: spill-policy
|
||||
name: '@deepseek-ai/dsh-spill-policy'
|
||||
config:
|
||||
maxInlineBytes: 50000
|
||||
```
|
||||
|
||||
这项分离很重要。`web-fetch-local` 仍负责资源上限（`maxResponseBytes`、`maxBodyChars`），用来保护网络、内存和解码工作。`spill-policy` 只负责结果已经存在后针对模型上下文的上限。如果提供方已经返回 `truncated: true`，落盘文件包含的是工具返回的完整格式化结果，而不是原始网页全文；策略不会做出其他承诺。
|
||||
|
||||
## 与保留和提前落盘的关系
|
||||
|
||||
保留与落盘存储相互独立：
|
||||
|
||||
- `@deepseek-ai/dsh-retention` 负责预览机制（`TextRetainer`、`ItemRetainer` 和省略元数据）。
|
||||
- `@deepseek-ai/dsh-spill` 负责保存最终文本，并返回定位符与检索提示。
|
||||
- `@deepseek-ai/dsh-spill-policy` 在工具流水线中应用默认的最终结果策略，将前两者组合起来。
|
||||
|
||||
最终结果策略不能取代由工具负责的提前落盘。部分有用内容并不存在于最终 `ToolExecutionResult.content` 中：
|
||||
|
||||
- `bash` 的最终输出已经是尾部内容加临时落盘路径；完整的 stdout／stderr 流位于执行器文件中。
|
||||
- `subagent` 的最终输出是子 agent（智能体）的最终回答，而不是子 agent 的执行轨迹。
|
||||
- 未来的工具可能生成从未出现在最终 `ToolExecutionResult.content` 中的运行时产物。
|
||||
|
||||
这些场景可以在后续工作中直接使用 `ctx.spillStore`，不属于首个示例的范围。
|
||||
|
||||
## 非目标
|
||||
|
||||
- v1 不增加面向模型的 `artifact_read` 或 `artifact_search` 工具。
|
||||
- v1 不增加逐工具的保留配置。
|
||||
- 不增加面向模型的超时／截断参数。
|
||||
- 不把 `read` 输出迁移到落盘文件。
|
||||
- 不取代 `web-fetch-local.maxBodyChars` 等提供方／资源上限。
|
||||
- 第一版不统一 bash 临时文件，也不采集 subagent 执行轨迹。
|
||||
|
||||
## 延后事项
|
||||
|
||||
- 用于现有执行器落盘文件的 `saveFile()`／`linkOrCopy`，这是统一 bash 行为所必需的。
|
||||
- 由工具负责的 subagent 执行轨迹落盘（`await run.result`，在 `run.dispose()` 前读取进程内子会话，保存 JSONL）。
|
||||
- 如果内置的 `read` 跳过规则不足，再增加逐工具退出或逐工具策略声明。
|
||||
- 面向 ACP（Agent Client Protocol）或远程环境的远程／数据库存储后端，因为本地路径在这些环境中没有意义。
|
||||
- 旧落盘文件的清理和保留策略，很可能与会话清理绑定。
|
||||
|
||||
## 测试
|
||||
|
||||
- `dsh-spill` 单元测试锁定 seam 契约：注册为 `ctx.spillStore`、每个上下文只允许一种实现，并在 dispose（资源释放）时释放。
|
||||
- `dsh-spill-local` 单元测试覆盖 `saveText`、`encodeSegment` 清理（分隔符／波浪号／完整路径段的点／空值）、会话哈希目录、仅所有者权限、每次保存生成不同路径、配置根目录／私有根目录，以及存储失败时的拒绝。
|
||||
- `dsh-spill-policy` 单元测试通过 `ctx.tools.execute` 驱动真实工具：禁用模式下无操作、替换超大文本、小结果／非文本结果保持不变、跳过 `read`、尽力回退（保存失败／无后端／无所有者），以及下游组合（限制已替换结果、保留 `additionalContexts`）。
|
||||
- `dsh-tool-web` 集成测试驱动 `web_fetch`，其实际执行路径经过 `ctx.tools.execute`，并使用真实的 `spill-local` 后端与策略；测试证明只有刻意加入的落盘提示会改变模型可见文本，而落盘文件保存完整的格式化结果。
|
||||
- `tui-agent` 示例加载 `spill-local` 与 `spill-policy`，因此其无密钥 Loader／PTY 冒烟测试会执行真实加载路径（namespace-plugin 导出形态与 `inject`）。
|
||||
|
||||
## 影响
|
||||
|
||||
默认策略只能看见最终格式化文本。它无法保留已经由提供方限制的内部内容，也无法保留从未成为结果一部分的运行时产物。第一版聚焦最终结果落盘而不是提前落盘，因此可以接受这一限制；由工具负责的提前落盘仍属于后续工作。
|
||||
|
||||
本地后端返回真实路径，使 v1 保持简单并符合已经验证的 agent 工具行为；seam 本身只承诺一个不透明定位符加检索提示，所以远程后端可以返回非文件定位符。
|
||||
|
||||
本地后端的价值取决于现有 `read`／`grep` 工具能否检查返回的本地路径，即使落盘目录位于会话 cwd 之外。目前这一条件成立，因为文件系统策略会记录观察结果并设置写保护，但不会把读取限制在工作区内。未来的工作区限制策略必须显式允许本地落盘路径，或改用检索提示指向受支持读取器的非文件落盘后端。
|
||||
|
||||
**快照缺口。** 目前没有 ACP 快照场景覆盖 transcript（文本记录）可见的 `web_fetch` 落盘提示。ACP 快照 harness 在无密钥环境中回放，无法访问实时 web，而 `web_fetch` 落盘需要一个真实的超上限 HTTP 正文；确定性场景需要一个预置的 loopback fetch 目标，但当前回放树尚未接线（示例根本没有加载 `tool-web`）。该行为改由 `dsh-tool-web` 针对 loopback server 的集成测试覆盖。弥补该缺口属于后续工作：把 `tool-web` 和预置 fetch 目标接入 ACP 示例，然后录制 `web-fetch-spill` 场景。
|
||||
|
||||
如果策略开始负责工具专用语义，就会膨胀得过大。它必须保持狭窄：只处理纯文本最终结果。由工具负责的提前落盘仍留作未来工作。
|
||||
|
||||
## 考虑过的替代方案
|
||||
|
||||
**要求每个工具通过保留声明选择加入。** v1 不予采纳，因为目标是实现类似 Claude Code 通用工具结果持久化的默认行为。只需一个 `maxInlineBytes` 部署配置项即可验证该形态。
|
||||
|
||||
**把 `tool-results` 建成宽泛的工具结果平台。** 不予采纳：宽泛的包名会诱使系统把保留策略、结果替换、预览措辞、搜索和提前落盘合并进一个 seam。可共享的存储部分更小：保存文本，并返回定位符与检索提示。
|
||||
|
||||
**使用 `ctx.fs.writeText` 或面向模型的 `write` 工具。** 不予采纳：工作区文件系统写入带有项目文件语义、写入／编辑策略、观察状态和面向用户的副作用。落盘文件是运行时产物，不是由模型编写的工作区改动。现有 `read` 工具之后可以检查它们，但创建操作属于运行时落盘 seam。
|
||||
|
||||
**让 `web-fetch-local` 不受限地抓取，只依靠 spill-policy。** 不予采纳：spill-policy 在最终工具结果已经存在之后才运行，无法保护网络、内存或解码资源。提供方资源上限仍然必须存在。
|
||||
|
||||
**把保留合并进落盘机制。** 不予采纳：保留与落盘职责不同。`TextRetainer`／`ItemRetainer` 决定保留哪部分预览、又省略了什么；落盘存储只负责保存策略要求的最终文本。
|
||||
@@ -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
|
||||
2026-07-20-canonical-tool-output-contract.md: 8cd7df98758d6d4ac240fea21e7bbe0c89f26d1b
|
||||
2026-07-20-canonical-tool-output-contract.zh.md: 0920e0c2c331a247ecd9a039a05c19c9dd2871bc
|
||||
2026-07-20-canonical-tool-output-contract.md: 6b5cd089fcf206e659c7b67b8a996bfe81d0c333
|
||||
2026-07-20-canonical-tool-output-contract.zh.md: 61b25b14ca6f048b73a51788f112165745ae7106
|
||||
|
||||
@@ -34,7 +34,7 @@ type ToolExecutionResult =
|
||||
|
||||
`tools/post-execute` has two mutually exclusive successful projections. Replacing `content` changes only Native/model presentation and preserves the canonical value and metadata. Replacing `value` revalidates the replacement and recomputes both presentation projections. A block removes the value and becomes a failure. Content replacement is therefore not a confidentiality mechanism: policy that must prevent programmatic access blocks the call or replaces the value.
|
||||
|
||||
Canonical values are execution-local. The agent loop persists `tool/result` with only `content`, `error`, and optional `meta`; Code Mode's `tool/code-dispatch` persists only its bounded summary. Neither event stores the intermediate value, so replay reproduces presentation but cannot reconstruct the programmatic result. When a tool declares `presentationMeta`, it is computed only for a direct surface call; a nested Code dispatch gets no metadata or result card. The outer `run_code` card instead reads final post-policy content and declares no presentation metadata. Generic and tool-owned spill projections similarly skip nested dispatches, whose canonical value never enters model context.
|
||||
Canonical values are execution-local. The agent loop persists `tool/result` with only `content`, `error`, and optional `meta`; Code Mode's `tool/code-dispatch` persists the sub-call's rendered `content` and `isError`. Neither event stores the canonical intermediate value, so replay reproduces presentation but cannot reconstruct the programmatic result. When a tool declares `presentationMeta`, it is computed only for a direct surface call; a nested Code dispatch gets no metadata or result card. The outer `run_code` card instead reads final post-policy content and declares no presentation metadata. Generic and tool-owned spill projections similarly skip nested dispatches, whose canonical value never enters model context.
|
||||
|
||||
The first-party tools preserve their existing Native text while returning domain DTOs:
|
||||
|
||||
|
||||
@@ -34,7 +34,7 @@ type ToolExecutionResult =
|
||||
|
||||
`tools/post-execute` 为成功结果提供两种互斥的投影方式。替换 `content` 只改变 Native／模型展示，并保留规范值和元数据。替换 `value` 会重新校验替代值，并重新计算两份展示投影。阻止操作会移除值并转为失败。因此，替换内容并不是保密机制：必须阻止程序化访问的策略，应当阻止调用或替换值。
|
||||
|
||||
规范值仅存在于执行期间。agent loop（智能体循环）持久化的 `tool/result` 只包含 `content`、`error` 和可选的 `meta`；Code Mode 的 `tool/code-dispatch` 只持久化其有界摘要。两个事件都不存储中间值，因此回放可以重现展示，却无法重建程序化结果。当工具声明 `presentationMeta` 时，系统只会为直接的外层调用计算它；嵌套 Code 分发没有元数据或结果卡片。外层 `run_code` 卡片则读取最终的 post-policy 内容，并且不声明展示元数据。通用以及工具自有的输出落盘投影同样跳过嵌套分发，因为它们的规范值永远不会进入模型上下文。
|
||||
规范值仅存在于执行期间。agent loop（智能体循环）持久化的 `tool/result` 只包含 `content`、`error` 和可选的 `meta`；Code Mode 的 `tool/code-dispatch` 持久化子调用渲染后的 `content` 与 `isError`。两个事件都不存储规范中间值，因此回放可以重现展示，却无法重建程序化结果。当工具声明 `presentationMeta` 时，系统只会为直接的外层调用计算它；嵌套 Code 分发没有元数据或结果卡片。外层 `run_code` 卡片则读取最终的 post-policy 内容，并且不声明展示元数据。通用以及工具自有的输出落盘投影同样跳过嵌套分发，因为它们的规范值永远不会进入模型上下文。
|
||||
|
||||
第一方工具在保持现有 Native 文本不变的同时返回领域 DTO：
|
||||
|
||||
|
||||
@@ -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
|
||||
2026-07-22-unified-send-and-coalesced-user-messages.md: bf0ae468c4783b73e2dbd0e1bc50b9bd2f50cb3f
|
||||
2026-07-22-unified-send-and-coalesced-user-messages.zh.md: 17913d2636e3ee5e5ae69f9c554935ba861d14d9
|
||||
2026-07-22-unified-send-and-coalesced-user-messages.md: 12128d9e57601d0b85d20d1cb4240bb08eadc3cb
|
||||
2026-07-22-unified-send-and-coalesced-user-messages.zh.md: 177d90f7116f7451b8e3c4ccf7d1577ff12ae701
|
||||
|
||||
@@ -41,6 +41,6 @@ Internally, `wakeup` is the “should the model run” signal, so the inbox dist
|
||||
## Related
|
||||
|
||||
- [one-send-one-turn](../simplification/2026-07-17-one-send-one-turn.md) — the one-claimed-message-per-turn rule this builds on.
|
||||
- [remove-agent-steering-mirror](../simplification/2026-07-04-remove-agent-steering-mirror.md) — the precedent for collapsing a mirrored live event.
|
||||
- [remove-agent-steering-mirror](../../archived/simplification/2026-07-04-remove-agent-steering-mirror.md) — the precedent for collapsing a mirrored live event.
|
||||
- [explicit-turn-cancellation](2026-07-16-explicit-turn-cancellation.md) — the cancel-cause signal `keepInbox` extends.
|
||||
- [intent-named-agent-delivery](2026-07-24-intent-named-agent-delivery.md) — the public helpers and fully resolved acceptance interface.
|
||||
|
||||
@@ -41,6 +41,6 @@ agent 的对外驱动接口逐渐长出三个近乎平行的动词——`send`
|
||||
## 相关
|
||||
|
||||
- [one-send-one-turn](../simplification/2026-07-17-one-send-one-turn.md)——本决策所依托的“每轮次只认领一条消息”规则。
|
||||
- [remove-agent-steering-mirror](../simplification/2026-07-04-remove-agent-steering-mirror.md)——折叠镜像实时事件的先例。
|
||||
- [remove-agent-steering-mirror](../../archived/simplification/2026-07-04-remove-agent-steering-mirror.md)——折叠镜像实时事件的先例。
|
||||
- [explicit-turn-cancellation](2026-07-16-explicit-turn-cancellation.md)——`keepInbox` 所扩展的取消原因信号。
|
||||
- [intent-named-agent-delivery](2026-07-24-intent-named-agent-delivery.md)——公开辅助方法以及接受完全解析输入的接口。
|
||||
|
||||
@@ -1,39 +0,0 @@
|
||||
# Agent Note: Unified session query service
|
||||
|
||||
Status: implemented
|
||||
|
||||
English | [中文](2026-07-23-unified-session-query-service.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
Exact reads, semantic filters, relationship traces, and full-text search operate on the same live-preferred session corpus. Exposing full-text search under a second context key makes consumers and app compositions treat one capability as two services, even though the SQLite implementation is the only backend-specific part.
|
||||
|
||||
The interface package already owns the shared record, filter, trace, search-request, cursor, and error contracts. A provider registry or coordinator would add runtime selection semantics unsupported by any current consumer.
|
||||
|
||||
## Decision
|
||||
|
||||
`SessionQueryService` is the single abstract service registered as `ctx.sessionQuery`. It concretely implements listing, title and event reads, surface reads, filtering, and relationship tracing through its backend-independent `SessionCorpus`. Its only abstract methods are `searchSessions()` and `searchEvents()`.
|
||||
|
||||
`SessionQuerySqlite` extends that service and is the sole concrete backend. One mounted instance therefore exposes every operation through `ctx.sessionQuery`; its inherited exact operations use the shared corpus implementation, while its SQLite-owned lifecycle observes sources, reconciles the derived FTS index, ranks matches, and owns cursor generations. The interface package has no standalone concrete plugin, search-provider registry, or second context key.
|
||||
|
||||
SQLite reconciliation is one quiescent serialized state machine. It passes the caller's exact abort signal into durable snapshot listing and inspection, awaits each started backend operation itself, and checks cancellation after every await and before starting the next source or index operation. Cancellation therefore cannot release the serializer while an ignored or cooperative backend call is still cleaning up, and it cannot start a subsequent listing, inspection, reconciliation, or query after the signal is observed.
|
||||
|
||||
Backend configuration includes the inherited `readWindowMax` setting alongside its own index path, journal mode, page limits, and snippet limit. First-party apps that need session queries mount the SQLite backend and place its disposable index beside their configured persistence root.
|
||||
|
||||
This service topology supersedes the separate-key portion of the [exact query decision](../feature/2026-07-10-session-query-service.md) and [SQLite search decision](../feature/2026-07-10-sqlite-session-query-provider.md); their corpus, query, tokenizer, reconciliation, and safety decisions remain in force.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
- **Keep `ctx.sessionQuery` and `ctx.sessionSearch` separate** — rejected because both expose operations over one logical corpus, force consumers to discover two keys, and let apps accidentally mount only a partial query surface.
|
||||
- **Keep a concrete base service and let the SQLite plugin register or mutate two search methods** — rejected because method availability would depend on plugin order and teardown, and the service would need a provider registration protocol for one implementation.
|
||||
- **Move every query implementation into the SQLite package** — rejected because exact reads, filters, and traces require no index and are shared behavior that belongs with their provider-independent contracts.
|
||||
|
||||
## Consequences
|
||||
|
||||
Consumers inject one service and can combine exact and full-text operations without a second capability lookup. A production composition must choose a concrete backend even when one consumer currently calls only inherited exact methods; tests may use a minimal subclass when backend behavior is outside their scope.
|
||||
|
||||
The unified object deliberately retains two internal observation strategies: exact operations read authoritative live/persisted sources per call, while full-text operations reconcile a disposable index. Sharing the context key does not make the derived index authoritative or couple exact-read availability to an FTS query.
|
||||
|
||||
Queued cancellation remains prompt. Cancellation during active asynchronous source observation waits for that started operation to settle, which makes rejection a quiescence boundary and preserves single-file execution for a following search. Synchronous SQLite statements remain non-preemptible and are bracketed by signal checks.
|
||||
|
||||
Unit coverage pins inherited and abstract behavior on one key, SQLite coverage exercises both operation families on the concrete backend, and the real Loader path verifies that one exported plugin registers the combined service.
|
||||
@@ -1,39 +0,0 @@
|
||||
# Agent Note: 统一会话查询服务
|
||||
|
||||
Status: implemented
|
||||
|
||||
[English](2026-07-23-unified-session-query-service.md) | 中文
|
||||
|
||||
## 问题
|
||||
|
||||
精确读取、语义过滤、关系追踪与全文搜索都作用于同一个实时源优先的会话语料库。将全文搜索暴露在第二个上下文键下，会让消费方与应用组合把同一项查询功能视为两个服务，尽管只有 SQLite 实现是后端特有的部分。
|
||||
|
||||
接口包已经拥有共享的记录、过滤、追踪、搜索请求、游标与错误契约。提供方注册表或协调器会引入运行时选择语义，而目前没有任何消费方支持这种语义。
|
||||
|
||||
## 决策
|
||||
|
||||
`SessionQueryService` 是注册为 `ctx.sessionQuery` 的唯一抽象服务。它通过后端无关的 `SessionCorpus` 具体实现列表查询、标题与事件读取、表层读取、过滤和关系追踪。仅有 `searchSessions()` 与 `searchEvents()` 两个方法为抽象方法。
|
||||
|
||||
`SessionQuerySqlite` 扩展该服务，并且是唯一的具体后端。因此，一个挂载实例便可通过 `ctx.sessionQuery` 暴露全部操作；其继承的精确操作使用共享的语料库实现，而由 SQLite 管理的生命周期负责观察数据源、对齐派生 FTS 索引、对匹配项排序并管理游标代际。接口包不提供独立的具体插件、搜索提供方注册表或第二个上下文键。
|
||||
|
||||
SQLite 的对齐过程是一个具备静止性保证的串行状态机。它将调用方的原始中止信号传给持久化快照列表与检查操作，直接等待每个已经启动的后端操作，并在每次等待后以及启动下一个数据源或索引操作前检查是否已取消。因此，即使后端忽略取消或正在配合清理，串行器也不会提前释放；观察到中止信号后，也不会再启动后续的列表、检查、对齐或查询操作。
|
||||
|
||||
后端配置除了自身的索引路径、日志模式、分页限制与文本片段长度上限外，还包含继承的 `readWindowMax` 设置。需要会话查询的第一方应用挂载 SQLite 后端，并将其可丢弃索引放在已配置的持久化根目录旁。
|
||||
|
||||
这一服务拓扑取代了[精确查询决策](../feature/2026-07-10-session-query-service.md)和 [SQLite 搜索决策](../feature/2026-07-10-sqlite-session-query-provider.md)中关于分离上下文键的部分；其中关于语料库、查询、分词器、对齐与安全性的决策仍然有效。
|
||||
|
||||
## 已考虑的替代方案
|
||||
|
||||
- **保留相互独立的 `ctx.sessionQuery` 与 `ctx.sessionSearch`**：不予采纳，因为二者都针对同一逻辑语料库提供操作，迫使消费方识别两个键，还可能让应用误挂载一组不完整的查询接口。
|
||||
- **保留具体的基础服务，再由 SQLite 插件注册或修改两个搜索方法**：不予采纳，因为方法是否可用将取决于插件顺序与资源释放时机，而且该服务需要为唯一的实现定义一套提供方注册协议。
|
||||
- **将所有查询实现移入 SQLite 包**：不予采纳，因为精确读取、过滤与追踪不需要索引，并且都属于应与提供方无关契约放在一起的共享行为。
|
||||
|
||||
## 后果
|
||||
|
||||
消费方只需注入一个服务，无需再次查找其他功能，便可组合精确操作与全文操作。生产环境的组合必须选择一个具体后端，即使当前某个消费方只调用继承的精确方法；如果后端行为不在测试范围内，测试可以使用最小子类。
|
||||
|
||||
统一后的对象有意保留两种内部观察策略：精确操作在每次调用时读取权威的实时源或持久化源，全文操作则使可丢弃索引与数据源对齐。共用上下文键不会让派生索引成为权威来源，也不会使精确读取的可用性依赖 FTS 查询。
|
||||
|
||||
排队阶段的取消仍会及时生效。在异步数据源观察已经开始后取消时，调用方会等待该操作完成清理后才收到拒绝；因此拒绝本身构成静止边界，并保证后续搜索仍按单一串行流程执行。同步 SQLite 语句无法在执行中被抢占，服务会在其前后检查中止信号。
|
||||
|
||||
单元测试在同一个键上同时固定继承实现与抽象方法的契约，SQLite 测试在具体后端上覆盖两类操作，真实 Loader 路径则验证单个导出的插件能够注册组合后的服务。
|
||||
@@ -1,53 +0,0 @@
|
||||
# Agent Note: Parse `dsh` argv through one Commander adapter
|
||||
|
||||
Status: implemented
|
||||
|
||||
English | [中文](2026-07-24-dsh-commander-argument-adapter.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
The `dsh` CLI entry (`apps/cli`) parsed argv in three hand-rolled idioms that did not compose and gave no `--help`/`--version`. `bin.ts` dispatched by raw inspection — `argv[0] === 'web'`, then `argv.includes('-p') || argv.includes('--prompt')`, else TUI — which is positional-blind: a prompt flag or a config path in the wrong position could misroute the mode, and `argv.includes('-p')` could not tell a real flag from an incidental token. `headless.ts` and `web.ts` each ran their own `node:util` `parseArgs` with inline host/port validation, and `dsh-app-boot` carried `parseResumeArg`, a ~30-line bespoke scanner reimplementing flag/`=`-form/value/repeat handling for `--resume`. Usage was a single hardcoded `usage: dsh -p "task"` line; there was no version flag and no rendered help.
|
||||
|
||||
## Decision
|
||||
|
||||
Argv is parsed once, in `apps/cli/src/args.ts`, through a Commander adapter (the same parser the SDK bins — `create-sdk`, `dsh-scripts` — already standardize on). `parseDshArgs(argv, version)` returns a discriminated `DshInvocation` union of the three real modes: `{ mode: 'tui', config?, resume? }`, `{ mode: 'headless', prompt }`, or `{ mode: 'web', host?, port?, dev }`. It does **not** model help/version/errors as data: Commander owns those, printing usage or the diagnostic and exiting at the point of failure. `exitOverride()` turns each into a thrown `CommanderError` carrying the intended code (0 for help/version, 1 for a parse or domain error), which one `try/catch` in `parseDshArgs` turns into `process.exit`.
|
||||
|
||||
`bin.ts` calls the adapter once and switches on `mode` (closed union, `satisfies never` default), dynamic-importing only the chosen mode's module; only a valid, non-help invocation reaches the switch, so it has no help/version/error cases. Each mode module consumes already-parsed values: `runTui(config, resume)`, `runHeadless(task)`, `runWeb(host, port, dev, workspaceRoot)` — none re-reads argv. It is **one Commander program**: the default surface (no subcommand) carries option-only flags — `--config <path>`, `-p/--prompt <task>`, `--resume <id>` — and `web` is a real `program.command('web')` subcommand. The default surface takes no positional argument, which is what lets `web` be a real subcommand without a positional collision, so `dsh --help` lists `web` natively (no hand-pasted command text). The default action and the `web` action set the resolved mode, then bail via `command.error(...)` (print + exit 1) on the domain checks Commander cannot express: `--prompt` selects headless and rejects an empty task or a `--config`/`--resume` alongside it rather than silently dropping a TUI input; an empty `--resume=` id fails loud (agent-loop treats `''` as no-resume). Commander parses the default-surface options on either side of the `web` token into `program.opts()`; since `web` shares none of them, the `web` action rejects a leaked `--config`/`-p`/`--resume` (`dsh web -p x`, `dsh --config c.yml web`) rather than silently serving and dropping it. `dsh web`'s `--host`/`--port` are unvalidated pass-through overrides: the adapter assigns no default and does no validation, only `Number`-coercing the port string (the schema wants a number). The `dsh-host-webserver` schemastery `Config` (`host` a `127.0.0.1`/`0.0.0.0` literal union, `port` a natural ≤ 65535) is the single source of both the default (the shipped `apps/cli/cordis.yml` `webserver` row stands when a flag is absent) and validity — `AppCLIEntry` patches an explicit flag straight into that row, so a bad host/port fails loud at the schema on boot, not at parse. `--dev` mounts the client HMR driver and bundle watch, and `--workspace-root <path>` is a plain pass-through to `AppCLIEntry` (the parent directory for name-created workspaces). A repeated `--resume`, or a following flag captured as a `--resume`/`--prompt` value, is Commander's standard behavior (last-wins / next-token) and is left alone; a bad id fails loud downstream when the session cannot load. `--version` reads this app's `package.json`.
|
||||
|
||||
`dsh` takes no positional argument. `--config <path>` names an alternate cordis tree to boot instead of the shipped default; it exists only so the demo/test call sites (`demo:cordis`, `demo:code-mode`, the keyless PTY smokes) can point the shipped bin at an example tree. A bare `dsh` boots the shipped tree plus the `~/.dsh/config.yaml` personal overlay; a real user never passes `--config`.
|
||||
|
||||
CLI parsing lives entirely in `apps/cli`. `dsh-app-boot` holds the boot/env/config/personal-overlay helpers and no argv scanner.
|
||||
|
||||
## Session resume through the boot context
|
||||
|
||||
`dsh --resume <id>` is the one way to resume a persisted session, with no environment variable. `runTui` provides the parsed id on the boot context through `boot`'s `prepare(ctx)` hook — `ctx.provide(RESUME_SESSION_ID_KEY, id)` (a `dsh-app-boot` export, value `'resumeSessionId'`) — and the shipped tui-agent/cordis configs read it as a bare identifier: `resumeSessionId: !!js "typeof resumeSessionId === 'string' ? resumeSessionId : undefined"`. The expression is quoted because YAML otherwise parses the `?`/`:` as a mapping; the `typeof` guard tolerates a launcher that never provides the slot. The `/resume` in-place handoff (`process.execve`) rebuilds its re-exec argv from the parsed values as `dsh --resume=<id> [--config <path>]`.
|
||||
|
||||
## One terminal front door: `dsh`
|
||||
|
||||
`dsh` is the only terminal entry point; the `dsh-tui-demo` package ships the TUI app bundle plugin the shipped config mounts, and no bin of its own. `demo:cordis`, `demo:code-mode`, and both the tui-agent and cordis-agent keyless PTY smokes launch through `apps/cli/src/bin.ts` with `--config <path>`. `dsh`'s TTY guard (refuse piped stdio before booting, pointing at `dsh -p` for automation) is pinned by `apps/cli/tests/built-bin.e2e.ts`, which runs the built `lib/bin.js` under plain Node with piped stdio (`apps/cli/tests` is in the e2e vitest include). `cli-demo`, `acp-demo`, and `jsonrpc-demo` keep their own bins because each is a distinct surface (headless, ACP, JSON-RPC) `dsh` does not provide.
|
||||
|
||||
## Package topology
|
||||
|
||||
The argument surface stays inside `apps/cli`, the assembly tier, not a `packages/*` library: it is this one app's routing, not a reusable seam. `dsh-app-boot` shrinks to boot glue with no CLI-parsing responsibility. `commander@^15` is added to `apps/cli/package.json`, matching the SDK bins' pin.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
**Keep `node:util` `parseArgs` and only unify the dispatch** — rejected: `parseArgs` has no subcommand model, no rendered help, and no version flag, so `web` routing and `--help`/`--version` would stay hand-rolled. The repo already chose Commander for its other CLIs; a second parser idiom for `dsh` alone is the fragmentation this change removes.
|
||||
|
||||
**Keep `parseResumeArg` as a shared helper and feed it Commander's residual args** — rejected: the whole point is to retire the bespoke scanner. Commander parses `--resume` (space and `=` forms, missing-value, position-independence) natively; keeping a parallel hand-written path for the one flag would preserve the duplication the change exists to end.
|
||||
|
||||
**A bare `dsh <config>` positional for the alternate tree** — rejected: a root positional and a real `web` subcommand cannot coexist in one Commander program (the subcommand claims the first positional). A positional would force `web` into a reserved-first-token dispatch to a separate parser and a hand-maintained `web` line in `--help`. Only the demo/test sites ever need to name an alternate tree, so a `--config` flag serves them while leaving the default surface positional-free — `web` is then a normal subcommand in one program with native `--help`.
|
||||
|
||||
**Make the argument surface a `packages/*` seam** — rejected: nothing outside `dsh` consumes it, and capability seams are not split preemptively. The Commander adapter is `apps/cli`'s own concern.
|
||||
|
||||
**Keep `RESUME_SESSION_ID` as the resume bridge** — rejected: with `--resume` parsed into a value the bin already holds, threading it through an environment variable the config re-reads is indirection with no benefit, and it left the demo bin a second, env-only resume path. Providing the id on the boot context is the same channel `boot`'s `prepare` hook already uses for `tuiResumeHost`.
|
||||
|
||||
**Keep the `dsh-tui-demo` bin** — rejected: it duplicated `dsh --config <path>` exactly, and keeping it forced the demo-only `RESUME_SESSION_ID` fallback to stay alive. Its plugin is what the configs actually mount; only the front-door bin was redundant, and `dsh` is the one terminal entry point.
|
||||
|
||||
## Testing
|
||||
|
||||
`apps/cli/tests/args.spec.ts` (new; `apps/*/tests` added to the vitest include and `apps/cli/tests` to `tsconfig.host.json`) covers the adapter at the level that matters: mode routing by shape (including `web --dev` and the host/port pass-through), the exit-code behavior for the adapter's fail-loud checks (empty resume/prompt, `--prompt` mixed with a config/`--resume`, unknown option, stray positional), and `--help`/`--version`, captured through a `process.exit` spy. Host/port validity is the webserver schema's job, exercised on boot by the web smoke, not the adapter spec. Both PTY smoke groups in `examples/tui-agent/tests/tui-keyless-smoke.e2e.ts` now drive the real `apps/cli/src/bin.ts`: the `tui-agent` group boots an example tree through `--config`, and the `dsh CLI` group covers default boot, personal overlay, invalid config, the `--resume` config intake, the `process.execve` in-place resume handoff, and the source-path prompt. `examples/cordis-agent/tests/keyless-smoke.e2e.ts` likewise launches through `dsh`. `packages/ui/app-boot/tests/app-boot.spec.ts` drops its `parseResumeArg`/`replaceResumeArg` blocks; the TUI unit and snapshot fixtures use the `dsh --resume {session}` resume command.
|
||||
|
||||
## Consequences
|
||||
|
||||
`dsh` has rendered `--help`/`--version` and consistent fail-loud parse errors, and mode routing does not depend on flag position. Argv parsing lives in one place with one parser idiom shared with the SDK bins, at the cost of a `commander` dependency on `apps/cli` and Commander's parse semantics (its error strings, its `exitOverride` contract) sitting on the CLI's front door. `dsh-app-boot` owns no CLI-parsing surface; a consumer needing `--resume`-style parsing composes Commander. Session resume rides the boot context rather than an environment variable, and `dsh` is the single terminal front door — the `dsh-tui-demo` package is a plugin bundle a config mounts.
|
||||
@@ -1,53 +0,0 @@
|
||||
# Agent Note: 通过单个 Commander 适配器解析 `dsh` 的 argv
|
||||
|
||||
Status: implemented
|
||||
|
||||
[English](2026-07-24-dsh-commander-argument-adapter.md) | 中文
|
||||
|
||||
## 问题
|
||||
|
||||
`dsh` 的 CLI（命令行界面）入口（`apps/cli`）以三种手写方式解析 argv，这些方式无法组合，也不提供 `--help`/`--version`。`bin.ts` 通过原始检查进行分发：先判断 `argv[0] === 'web'`，再判断 `argv.includes('-p') || argv.includes('--prompt')`，否则走 TUI。这种方式对位置不敏感：位置错误的 prompt 标志或配置路径可能把模式路由错，而 `argv.includes('-p')` 无法区分真正的标志和偶然出现的 token。`headless.ts` 和 `web.ts` 各自运行自己的 `node:util` `parseArgs`，并内联校验 host/port，而 `dsh-app-boot` 携带 `parseResumeArg`——一个约 30 行的定制扫描器，为 `--resume` 重新实现了标志、`=` 形式、取值和重复的处理。用法说明只有一行硬编码的 `usage: dsh -p "task"`；既没有版本标志，也没有渲染出的帮助信息。
|
||||
|
||||
## 决策
|
||||
|
||||
argv 只在 `apps/cli/src/args.ts` 中解析一次，并使用 Commander 适配器（SDK bin `create-sdk`、`dsh-scripts` 已经统一采用的同一解析器）。`parseDshArgs(argv, version)` 返回仅包含三种实际模式的判别式 `DshInvocation` 联合类型：`{ mode: 'tui', config?, resume? }`、`{ mode: 'headless', prompt }` 或 `{ mode: 'web', host?, port?, dev }`。它**不会**将帮助、版本信息或错误建模为数据：这些情况由 Commander 处理，在触发处打印用法或诊断信息并退出。`exitOverride()` 会将每种情况转为抛出的 `CommanderError`，并携带预期退出码（帮助或版本为 0，解析错误或领域错误为 1）；唯一一处 `try/catch` 位于 `parseDshArgs` 中，捕获错误后调用 `process.exit`。
|
||||
|
||||
`bin.ts` 只调用适配器一次，并对 `mode` 做分支切换（封闭联合类型，默认分支为 `satisfies never`），仅动态导入所选模式对应的模块；只有合法的非帮助请求才会进入这段分支逻辑，因此其中没有帮助、版本或错误分支。每个模式模块只消费已解析好的值：`runTui(config, resume)`、`runHeadless(task)`、`runWeb(host, port, dev, workspaceRoot)`，都不会再次读取 argv。整个 CLI 由**单个 Commander 程序**实现：默认接口（不使用子命令时）只包含选项标志——`--config <path>`、`-p/--prompt <task>`、`--resume <id>`——而 `web` 是通过 `program.command('web')` 定义的真正子命令。默认接口不接受位置参数，因此 `web` 可以成为真正的子命令且不会发生位置参数冲突，`dsh --help` 也会原生列出 `web`，无需手工拼接命令文本。默认命令和 `web` 子命令的处理函数会设置解析得到的模式，随后对 Commander 无法表达的领域校验调用 `command.error(...)` 立即终止（打印信息并以退出码 1 退出）：`--prompt` 选择 headless 模式；如果任务为空，或调用中还包含 `--config` 或 `--resume`，它会拒绝调用，而不会静默丢弃 TUI 输入；空的 `--resume=` id 会显式失败（agent-loop 把 `''` 视为不恢复）。Commander 会将 `web` token 前后的默认接口选项都解析进 `program.opts()`；由于 `web` 不与默认接口共用任何选项，`web` 子命令的处理函数会拒绝误入的 `--config`/`-p`/`--resume`（`dsh web -p x`、`dsh --config c.yml web`），而不是静默启动服务并丢弃这些选项。`dsh web` 的 `--host`/`--port` 是未经校验、直接透传的覆盖值：适配器既不设置默认值，也不执行校验，只使用 `Number` 将端口字符串转换为数字（schema 要求该值为数字）。`dsh-host-webserver` 的 schemastery `Config`（`host` 是 `127.0.0.1`/`0.0.0.0` 字面量联合类型，`port` 是不大于 65535 的自然数）是默认值与有效性的唯一真源：未提供标志时，随产品提供的 `apps/cli/cordis.yml` 中 `webserver` 配置项保持原值；`AppCLIEntry` 将显式标志的值直接写入该配置项，因此无效的 host/port 会在启动时触发 schema 校验并显式失败，而不是在参数解析阶段失败。`--dev` 会挂载客户端 HMR（热模块替换）驱动，并启用构建产物监视，`--workspace-root <path>` 则是直接透传给 `AppCLIEntry` 的选项（按名称创建 workspace 时使用的父目录）。重复提供 `--resume`，或后续标志被捕获为 `--resume` 或 `--prompt` 的值，都是 Commander 的标准行为（最后一次取值生效／将下一 token 作为值），本适配器不作干预；无效 id 会在下游无法加载会话时显式失败。`--version` 读取本应用的 `package.json`。
|
||||
|
||||
`dsh` 不接受位置参数。`--config <path>` 指定一份替代 Cordis 配置树，系统启动该配置树而不是随产品提供的默认配置树；该标志仅用于让演示和测试调用点（`demo:cordis`、`demo:code-mode`、无密钥 PTY 冒烟测试）通过随产品提供的 bin 启动一份示例树。直接运行 `dsh` 会启动随产品提供的配置树，并叠加 `~/.dsh/config.yaml` 个人覆盖；实际用户从不传入 `--config`。
|
||||
|
||||
CLI 解析完全位于 `apps/cli` 中。`dsh-app-boot` 提供启动、环境变量、配置和个人覆盖辅助函数，不包含 argv 扫描器。
|
||||
|
||||
## 通过启动上下文恢复会话
|
||||
|
||||
`dsh --resume <id>` 是恢复持久化会话的唯一方式，无需环境变量。`runTui` 通过 `boot` 的 `prepare(ctx)` 钩子，在启动上下文中提供已解析的 id：`ctx.provide(RESUME_SESSION_ID_KEY, id)`（`dsh-app-boot` 的一项导出，值为 `'resumeSessionId'`）；随产品提供的 tui-agent/cordis 配置将该值作为裸标识符读取：`resumeSessionId: !!js "typeof resumeSessionId === 'string' ? resumeSessionId : undefined"`。这个表达式需要加引号，否则 YAML 会把 `?` 和 `:` 解析为映射；`typeof` 守卫使从未提供该槽位的启动器也能正常运行。`/resume` 原地交接（`process.execve`）根据已解析的值将重新执行时的 argv 构造成 `dsh --resume=<id> [--config <path>]`。
|
||||
|
||||
## 唯一的终端入口：`dsh`
|
||||
|
||||
`dsh` 是唯一的终端入口；`dsh-tui-demo` 包（package）提供 TUI 应用组合插件，随产品提供的配置会挂载该插件，而该包不提供自己的 bin。`demo:cordis`、`demo:code-mode` 以及 tui-agent 和 cordis-agent 的无密钥 PTY 冒烟测试都通过 `apps/cli/src/bin.ts` 启动，并传入 `--config <path>`。`dsh` 的 TTY 守卫会在启动前拒绝标准输入输出接入管道的调用，并提示自动化场景使用 `dsh -p`；`apps/cli/tests/built-bin.e2e.ts` 锁定了这一行为：该测试将标准输入输出接入管道，并通过普通 Node 运行构建后的 `lib/bin.js`（e2e Vitest 的 include 包含 `apps/cli/tests`）。`cli-demo`、`acp-demo` 和 `jsonrpc-demo` 保留各自的 bin，因为它们分别提供 `dsh` 所没有的独立接口（headless、ACP（Agent Client Protocol）、JSON-RPC）。
|
||||
|
||||
## 包拓扑
|
||||
|
||||
参数解析留在 `apps/cli`（组装层）内，而不是 `packages/*` 库中：它是这一个应用自身的路由，而非可复用的 seam。`dsh-app-boot` 收缩为纯粹的 boot 胶水代码，不再承担 CLI 解析职责。`commander@^15` 被加入 `apps/cli/package.json`，与 SDK bin 锁定的版本一致。
|
||||
|
||||
## 考虑过的替代方案
|
||||
|
||||
**保留 `node:util` `parseArgs`，只统一分发。** 已否决：`parseArgs` 没有子命令模型、没有渲染出的帮助、也没有版本标志，因此 `web` 路由和 `--help`/`--version` 仍将保持手写。本仓库其他 CLI 已经选择了 Commander；单独为 `dsh` 引入第二套解析器方式，正是这次变更要消除的碎片化。
|
||||
|
||||
**保留 `parseResumeArg` 作为共享辅助函数，并向它喂入 Commander 的残余参数。** 已否决：整件事的核心就是要退役这个定制扫描器。Commander 原生解析 `--resume`（空格和 `=` 形式、缺值、位置无关性）；为这一个标志保留一条平行的手写路径，只会保留这次变更要终结的重复。
|
||||
|
||||
**使用裸 `dsh <config>` 位置参数指定替代配置树。** 已否决：根级位置参数与真正的 `web` 子命令无法在同一个 Commander 程序中共存（子命令会占用第一个位置参数）。位置参数会迫使系统把位于首位的 `web` 作为保留 token 分发给另一个解析器，并手工维护一行 `web` 文本，供 `--help` 显示。只有演示和测试调用点需要指定替代配置树，因此 `--config` 标志既能满足这些调用点，又能让默认接口不包含位置参数；这样，`web` 就能在单个程序中成为普通子命令，并由原生 `--help` 展示。
|
||||
|
||||
**把参数解析做成 `packages/*` 的 seam。** 已否决：`dsh` 之外没有任何消费方使用它，而能力 seam 不应被提前拆分。这个 Commander 适配器是 `apps/cli` 自身的事务。
|
||||
|
||||
**保留 `RESUME_SESSION_ID` 作为恢复通道**：不予采纳。`--resume` 已被解析成 bin 当前持有的值；若再通过环境变量传递并由配置重新读取，只会引入无益的间接层，还会使演示 bin 保留第二条仅依赖环境变量的恢复路径。在启动上下文中提供 id，与 `boot` 的 `prepare` 钩子为 `tuiResumeHost` 提供值所采用的是同一通道。
|
||||
|
||||
**保留 `dsh-tui-demo` bin**：不予采纳。它与 `dsh --config <path>` 的功能完全重复；保留它还会迫使演示专用的 `RESUME_SESSION_ID` 回退路径继续存在。配置实际挂载的是该包的插件；冗余的只有作为终端入口的 bin，而 `dsh` 是唯一的终端入口。
|
||||
|
||||
## 测试
|
||||
|
||||
`apps/cli/tests/args.spec.ts`（新增；`apps/*/tests` 加入 vitest include，`apps/cli/tests` 加入 `tsconfig.host.json`）覆盖适配器的关键行为：根据参数形态进行模式路由（包括 `web --dev` 和 host/port 透传），并通过 `process.exit` spy 捕获适配器的显式报错检查（恢复 id 或提示词为空、`--prompt` 与配置或 `--resume` 混用、未知选项、多余的位置参数）以及 `--help`/`--version` 的退出码。host/port 的有效性由 webserver schema 负责，并由 web 冒烟测试在启动时验证，不属于适配器测试的覆盖范围。`examples/tui-agent/tests/tui-keyless-smoke.e2e.ts` 中的两组 PTY 冒烟测试现在都驱动真实的 `apps/cli/src/bin.ts`：`tui-agent` 组通过 `--config` 启动示例树，`dsh CLI` 组覆盖默认启动、个人覆盖、无效配置、配置对 `--resume` 的接收、通过 `process.execve` 原地恢复交接，以及包含源码路径的系统提示词。`examples/cordis-agent/tests/keyless-smoke.e2e.ts` 同样通过 `dsh` 启动。`packages/ui/app-boot/tests/app-boot.spec.ts` 移除其 `parseResumeArg` 和 `replaceResumeArg` 测试块；TUI 单元测试和快照 fixture（测试前置数据）使用 `dsh --resume {session}` 恢复命令。
|
||||
|
||||
## 影响
|
||||
|
||||
`dsh` 会渲染 `--help`/`--version`，并以一致方式显式报告解析错误；模式路由不依赖标志位置。argv 解析集中在一处，并与 SDK bin 共用一套解析器方式，代价是 `apps/cli` 依赖 `commander`，且 Commander 的解析语义（错误字符串和 `exitOverride` 契约）成为 CLI 入口的一部分。`dsh-app-boot` 不提供任何 CLI 解析接口；需要 `--resume` 式解析的消费方通过组合 Commander 来实现。会话恢复通过启动上下文完成，而不使用环境变量；`dsh` 是唯一的终端入口；`dsh-tui-demo` 包是由配置挂载的插件组合包。
|
||||
@@ -0,0 +1,6 @@
|
||||
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write
|
||||
2026-07-25-web-client-session-scope-and-provide-channel.md: 063494b56461593015d6de4c2b55a2d1d6a3c676
|
||||
2026-07-25-web-client-session-scope-and-provide-channel.zh.md: cd5d29dfbcd9356a9ea15852d5d27a3660084abf
|
||||
@@ -0,0 +1,137 @@
|
||||
# Agent Note: Web client Agent-scope parity model and the provisioning channel (agents/scope / blank reuse / provide)
|
||||
|
||||
Status: implemented
|
||||
|
||||
English | [中文](2026-07-25-web-client-session-scope-and-provide-channel.zh.md)
|
||||
|
||||
> Scope: the client Agent scope (actx) and targeted events, the client/host materialization parity model, the blank-session bit and reuse (`connectWorkspace`), the per-session provisioning channel (`sessions.provide`), the read-only queue mirror (`session/queued`), and the host wire smalls that carry these capabilities (the summary `blank` column, the `host/session-added` frame field, and the `host/commands-changed` frame). The input state machine and the slash pipeline live in the [input machine note](2026-07-25-web-input-machine-and-slash-pipeline.md); the command business surfaces live in the [command surfaces note](2026-07-25-web-command-surfaces-and-assembly.md).
|
||||
|
||||
## Problem
|
||||
|
||||
The web client had a single global session surface: slots all rendered from the root context, so plugins had no notion of "which agent/session is current"; the draft's true copy was buried inside the Session object, leaving any plugin that wanted to participate in input with nowhere to hook in. To support a command/input system, the platform layer first had to answer:
|
||||
|
||||
- Who owns session interaction state (menus, popups, drafts, in-flight requests), and how two sessions are structurally isolated;
|
||||
- What a "new session" is before the host entity exists — whether the client must forge an independent life for it;
|
||||
- How session-scope components fetch their own session data, instead of props passed down layer by layer;
|
||||
- What a user-abandoned new session leaves behind on the host side, and who collects it.
|
||||
|
||||
Hard constraints: the host is the single source of truth; every registration goes through a `ctx.effect` disposer; the scope mechanism matches the host's Agent scope architecture; model-visible ⟺ already in the session log.
|
||||
|
||||
## Decision
|
||||
|
||||
### The parity model: client and host share one root state axis
|
||||
|
||||
Host-side `session.create(workspaceId)` produces Session + Agent + cwd in one piece (an atomic bundle, never split); the client side is the mirror of that birth — the instant a session row enters the list mirror, the client mints its Agent scope (actx + provide + the full input surface mounted):
|
||||
|
||||
- Session identity is the host's true form from birth: the sessionId arrives via the `session.create` response / the `host/session-added` frame, and every client-side address (the scope tag, slot store keys, RPC addressing) uses that same id.
|
||||
- The materialization moment = the instant the user picks a Workspace (cwd settled): the client calls `session.create({workspaceId})` on the spot and receives the complete entity.
|
||||
- "New Session with no workspace picked" is a **pure view state** (a navigation position) corresponding to no session/scope entity; until the pick, the composer is locked whole (no slash, no plain text).
|
||||
- A "blank session" is just an ordinary materialized session whose log is still empty; to every Agent-scope plugin on the host (goal/plan/skill/…) it is indistinguishable from any session, so slash/plan are all naturally live.
|
||||
|
||||
### Agent scope: the actx is the sole session carrier in the client-side cordis world
|
||||
|
||||
The runtime's `agents/scope.ts` matches the host's `dsh-scope` at the mechanism layer (fiber + tag + filter; no value import: the host package carries the scoped-events `Events` merge, which would collide with the Context merge inside the client program):
|
||||
|
||||
- `createScope(ctx, key)`: a no-op plugin fiber plus `extend({[kScope]: key, [Context.filter]: …})` — the filter lives directly on the actx: untagged listeners receive globally, tagged ones receive only their own scope.
|
||||
- Dispatch is the cordis primitives with thisArg = the actx itself: `actx.bail(actx, event, req)` / `actx.emit(actx, event, payload)`.
|
||||
- `Session.bindScope(actx)`: paired exactly once when resolve mints the scope (rebinding throws; dropScope unbinds), mirroring the host's `Agent.loopCtx` — the Session uses it to dispatch its own scoped events. The reverse actx→Session direction is one hop through `sessions.sessionOf(actx)` (mirroring host plugins' `agent.session` usage).
|
||||
|
||||
Three deliberate divergences from the host dsh-scope:
|
||||
|
||||
- The filter lives on the actx itself rather than a separate carrier: the host wrapper layer guards the business Agent subject against drifting from the scope key (host events inject the Agent itself as the first argument), while client event payloads carry only an id — there is no subject to protect.
|
||||
- Keys compare by branded `SessionId` value rather than object identity: on the host, agent.id === session id (1:1 on the same axis), agent identity directly reuses the `SessionId` brand, and a client scope's identity is its wire id.
|
||||
- The client scope is an **Agent identity** scope, not a live-object scope: during a cold session the host Agent object is already disposed while the client actx stays alive (in view) — the identity axis is in strict parity while object hot/cold is deliberately unsynchronized.
|
||||
|
||||
id→ctx handoff is allowed in only three kinds of places (business providers never hand off):
|
||||
|
||||
- Slot inject factories: the ctx never enters the render layer; the identity the slot framework hands a component is the sessionId, exchanged back into objects/controllers through service maps.
|
||||
- Root coordination services self-addressing: from a projection's sessionId back to the actx via `sessions.scope(id)`.
|
||||
- Root untagged listeners: looking up their own store by the payload's sessionId.
|
||||
|
||||
### Scope lifecycle: anchored to the list mirror — birth is entering view, death is prune
|
||||
|
||||
Session instances share the scope's lifecycle; liveness eligibility = host-listed (one criterion, shared by mint and prune):
|
||||
|
||||
- Birth = a session row entering client view (the list baseline pull / the local `create()` echo / the `host/session-added` frame); a lazy first resolve mints the scope (resolution is a pure function, render-safe).
|
||||
- One prune tears down three things together: the Session instance, the scope fiber (cascading through every consumer hung on the actx), and the session-keyed slot store. The staged session (= `list.current`) is the exception: removed while still on stage, it keeps a frozen read-only view, torn down only once the stage moves away.
|
||||
- Reopening = lazily rebuilding the instance + `open()` pulling history (the host session log is the durable truth).
|
||||
- Remaining TODO: approval/question frames never enter history and cannot be recovered across a prune (the manager-level pendingBuffers cover only the never-instantiated window).
|
||||
|
||||
### The blank bit: the empty session's visible projection, conversion, and reuse
|
||||
|
||||
A session "materialized but with no first prompt" is governed by the summary-derived bit `blank` (a derived column, not a header field; SessionHeader stays immutable):
|
||||
|
||||
- The host criterion: `session.events.length === 0` (zero log events = no user message yet). A live session reads `summarize()` straight from memory; a cold session is always `false` — the lazy-create contract guarantees a never-appended session never enters `persistence.list()` at all (both the JSONL and SQLite backends are verified truly lazy), so blank never touches disk.
|
||||
- The wire carries it in two places: the required `SessionSummary.blank` column, and the required `blank` field on the `host/session-added` frame (always true at creation, letting other tabs enter the same blank-session state into their mirrors).
|
||||
- The client mirror only lowers, never raises (monotonic), flipped from three sources, all reusing existing wire signals:
|
||||
- The sender's own tab: the **successful response** to the first `prompt()` flips false (acceptance proves the user/message is already in the host log — this flip is confirmation, not optimism; `onEngaged` synchronously updates the list mirror, converting the current `New Session` row in place to an ordinary title, adding no list row). A rejected first prompt keeps the session blank: aligned with host authority, still shown as `New Session`, keeping its connectWorkspace reuse eligibility.
|
||||
- Other tabs: the `host/session-status (running:true)` frame flips it — a blank session never runs, so the first running necessarily means no longer blank;
|
||||
- Reconnect alignment: `session.list`'s summary.blank is authoritative, so a tab that missed frames aligns naturally on its next pull; a stale blank:true can never mark a converted session back to blank.
|
||||
- List discipline: the store retains every row; the Workspace browser's grouping, flat view, search, and counts share one visible projection — every non-blank session shows, while blank sessions show only the one with `session.id === sessions.current`, its title forced to `New Session`. After a Workspace switch, the old blank entity stays in the mirror but is hidden from the list while the target Workspace's current blank shows; the user-visible surface therefore holds at most one blank row globally.
|
||||
- The residue ledger takes zero GC: after a refresh, blank sessions come back with the bit intact and are reused on the next same-workspace connect, so the ordinary single-tab path keeps at most one per workspace; after a host restart, blanks leave no disk trace and simply evaporate; the extra empty shells from multi-tab races only become non-current hidden rows, digested by later reuse, with no coordination.
|
||||
|
||||
### connectWorkspace: the sole entry point of New Session
|
||||
|
||||
`workspaces.connectWorkspace(workspaceId): Promise<SessionId>` (owned by WorkspacesService — it holds both the workspace canonical path and the sessions reference):
|
||||
|
||||
- The reuse arm: the list mirror is searched for `blank && cwd == workspace.path` (direct equality on the host realpath canonical form); a hit returns that id directly, creating nothing.
|
||||
- The create arm: on a miss, `session.create({workspaceId})` returns the new id.
|
||||
- An unknown workspaceId fails loud (never silently creating somewhere else).
|
||||
- The resolution guarantee (one contract for both arms): when the promise resolves, the returned id is already in the list store and `sessions.binding(id)` resolves synchronously — `SessionsService.create` projects the list synchronously after RPC success before resolving, so a draft mover can write text into the new scope's machine before open, without waiting for a notifier flush.
|
||||
- The caller takes the id and does its own `sessions.open`; sending the first prompt is an ordinary `session.prompt` — the session already exists, a failure is an ordinary prompt failure, the draft text is still in the machine, and a retry is simply sending again.
|
||||
- The global New Session button defaults to `recentWorkspaceId`: first comparing each Workspace's newest Session `updatedAt`, falling back to the Workspace `createdAt` when it has no Sessions, and keeping host order on ties; only with no Workspace at all does it `sessions.clear()` into the no-session view. Create actions inside a Workspace group still hit that Workspace explicitly.
|
||||
- At startup the runtime subscribes to the first complete baseline: a successfully restored current session is kept in place; otherwise it automatically calls `connectWorkspace(recentWorkspaceId)` and opens the returned blank session. The policy settles only once; a later user-initiated clear is never overridden by auto-selection again, and a connect failure waits for the next baseline projection to retry.
|
||||
- Re-picking the Workspace in the blank Hero also goes through `connectWorkspace`; when the target id differs from the current one, the current input machine's non-empty draft moves to the target scope first, then `sessions.open(nextId)`. The old blank entity is not deleted — it merely leaves the list by no longer being current.
|
||||
|
||||
### Per-session provisioning: the `sessions.provide` standard-kit channel
|
||||
|
||||
The sole provisioning path by which session slot components fetch their own session data. Plugins declare a fixed key map through the static descriptor `sessions.provide({hooks, props, resolve})` (a duplicate key throws at registration); `resolve(binding)` materializes values for a specific session and tears them down with the scope. Web-react's `standardKit` single loop binds the hooks compartment into `use<Name>` selector hooks (`observableHook`→uSES, anti-tearing) and passes the props compartment through as-is.
|
||||
|
||||
Slot scope is the closed set `root | session-maybe | session`:
|
||||
|
||||
- `root` receives only the global standard kit, with no session identity or provisioning.
|
||||
- `session-maybe` follows the current session, but the component instance does not change key when the id appears, disappears, or changes; with no session, `sessionId`, the results of `useSession`/`useInput`, and `inputActions` may all be absent. The unkeyed root `SessionMaybeProvider` drives these updates, while `SessionMaybeProvideInfo` uses the static key map to retain the complete hook/prop shape even with no session.
|
||||
- `session` guarantees that `sessionId`, every hook source, and every prop exist; each strict entry's error boundary is keyed by `sessionId`, so switching sessions recreates that entry and its session store.
|
||||
|
||||
`conversation` is the resident `session-maybe` shell: `ConversationRoot`, HeroShell, the Workspace picker, the composer stack, and the overlay chain's fallback frame retain their React instances across the no-session → blank-session switch; `conversation.session` carries only the strict-session header/view, while the composer and every input slot also stay strict `session`. With no session, the composer stack places the presentation-only `DisabledInputBar` directly; once a session appears, the input body is swapped for the strictly bound InputBar; the textarea may be rebuilt, while the Hero and the layout skeleton are not. The blank → engaging/active transition stays inside the same strict-session subtree, and the InputBar is never rebuilt on a phase flip.
|
||||
|
||||
- The runtime's first built-in entry: the `'session'` hook — `useSession` itself rides the same mechanism, no special-casing.
|
||||
- Concurrent discipline: the render plane reads only from the hooks compartment (uSES consistency guarantee); props-compartment callbacks are used only in event-handler space; descriptor resolution is render-safe (idempotent caching, with prune reaping residue from abandoned renders).
|
||||
- Third-party components take zero value dependencies; types are a one-line type-only import (declaration merging into `SessionStandardProps` / `SessionMaybeStandardProps`).
|
||||
|
||||
### The read-only queue mirror
|
||||
|
||||
- The MuxFrame `session/queued`: the Session holds a read-only inbox mirror (previews truncated; steering retired by source match); queue frames never enter history — pure stream state, cleared on reconnect and refilled from the new baseline; the never-instantiated window is buffered and replayed through the manager pendingBuffers.
|
||||
- Queue semantics: running does not lock input; ordinary messages queue through `session.prompt {mode:'queue'}`, and commands never queue.
|
||||
|
||||
### Host wire smalls
|
||||
|
||||
- The summary `blank` column and the `host/session-added` frame's `blank` field (see the blank bit above).
|
||||
- The SSE frame `host/commands-changed` (a pure invalidation signal); the client routes it into the typed events `commands/changed` and `connection/reset` (broadcast after each connection generation is established; wire-derived caches uniformly treat prior state as stale).
|
||||
- `command.list/execute` and `skill.list` are uniformly single-addressed by `sessionId` (a session always has an Agent; `agentFor`'s resume semantics come ready-made); the command-surface narrative lives in the [command surfaces note](2026-07-25-web-command-surfaces-and-assembly.md).
|
||||
- The `session.create` request shape: workspaceId/cwd as either-or, plus an optional caller-preallocated sessionId (a same-id same-cwd retry is idempotent; a different cwd reports `session-conflict`).
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
| Rejected | One-line reason |
|
||||
|---|---|
|
||||
| A client-local Intent + materialize (published CAS / the pendingPrompt attach transaction / the before-create chain) | The client is forced to simulate the first half-life the host lacks, breeding a pile of state machinery — published CAS, the attach transaction, partial publication |
|
||||
| Host-reserved IDs (a draft Map) | The host merely acknowledges a number; the state machine stays on the client untouched |
|
||||
| A host draft Session (a Session without an Agent) | Every host surface that looks up the Agent must fork for drafts; core would need an attachAgent seam plus late-written header cwd |
|
||||
| Binding an Agent before cwd (ungrouped) | Overturns the readonly header.cwd "created in" invariant, plus the launch-dir side-effect product trap |
|
||||
| Passing session context down through React Context | Plugins should hold one mental model across host and client; the scope mechanism is isomorphic to the host dsh-scope |
|
||||
| A `scopeTarget` carrier + fused dispatcher (mirroring the host `agentEvents`) | The host wrapper layer guards the business Agent subject against drifting from the scope key; client events have no subject to guard — the filter on the actx plus cordis primitives covers every need |
|
||||
| Sessions not holding a ctx (a cordis-free object layer) | A red line born only so the filtering unit tests avoid importing cordis, at the cost of two-hop contribute callbacks plus mutable public fields; the host Agent already holds loopCtx |
|
||||
| Resident Session instances (resident-instance) | The host session log is the durable truth; residency is mere identity convenience, and its misalignment with the scope lifecycle is a source of complexity |
|
||||
| Components receiving wiring-callback bundles (two-layer inject→props pass-down) | The standard-kit channel lets components fetch their own; the public surface converges to hooks + stable props |
|
||||
| Swapping the no-session Hero view for the entire session Conversation | Even with the outer layout unchanged, the Hero, picker, and composer subtrees would remount together, making the whole UI region jump |
|
||||
| Making InputBar itself `session-maybe` | The input state machine, keyboard command surface, and actions would all have to accept absent values; replacing only the disabled input body keeps optionality at the shell boundary |
|
||||
| A dedicated conversion frame | `session-status(running:true)` semantically implies conversion (a blank session never runs); adding a frame buys zero information for one more wire type |
|
||||
|
||||
## Consequences
|
||||
|
||||
- Plugins gain session context isomorphic to the host's: per-session state hangs on the actx and mounts/tears down in one piece with the scope fiber, making leaks structurally impossible; two-session isolation is structurally guaranteed by the scope filter.
|
||||
- The client object layer converges to a wire mirror: session identity, lifecycle, and capability adjudication all defer to the host entity — the input system (the next layer) always faces a session with a real Agent, and providers like slash/skill uniformly address by sessionId directly.
|
||||
- Blank-session governance takes zero dedicated mechanisms: state rides one derived bit, visibility rides the unified list projection (only the current blank shows, as `New Session`), reclamation rides lazy persistence's existing contract (evaporation on restart), and the ordinary ceiling rides same-Workspace reuse.
|
||||
- The cost: the id→ctx handoff discipline and provide's Concurrent discipline are conventions rather than type-enforced, pinned by review and tests; fully disabled input while no workspace is picked is an experience cost the product surface accepts (the price of the single state axis).
|
||||
- Known gaps: approval/question recovery across prune (TODO); model selection returns in live-mutation shape (the host `selectModel` trio is ready-made, awaiting its own branch).
|
||||
@@ -0,0 +1,137 @@
|
||||
# Agent Note: Web client Agent-scope 对等模型与供数通道（agents/scope / blank 复用 / provide）
|
||||
|
||||
Status: implemented
|
||||
|
||||
[English](2026-07-25-web-client-session-scope-and-provide-channel.md) | 中文
|
||||
|
||||
> 范围：client Agent scope（actx）与定向事件、client/host 实体化对等模型、空会话 blank 位与复用（`connectWorkspace`）、per-session 供数通道（`sessions.provide`）、队列只读镜像（`session/queued`），以及承载这些能力的 host wire 小件（summary `blank` 列、`host/session-added` 帧字段、`host/commands-changed` 帧）。输入状态机与 slash 管线见[输入状态机 note](2026-07-25-web-input-machine-and-slash-pipeline.md)；命令业务面见[命令业务面 note](2026-07-25-web-command-surfaces-and-assembly.md)。
|
||||
|
||||
## 问题
|
||||
|
||||
web client 只有一张全局会话面：slot 全部从根 context 渲染，插件拿不到「当前是哪个 agent/session」的语境；draft 真身埋在 Session 对象里，任何要参与输入的插件都无处下手。要支撑命令/输入体系，平台层必须先回答：
|
||||
|
||||
- 会话交互态（菜单、popup、草稿、在途请求）归谁持有，双会话如何结构性隔离；
|
||||
- 「新会话」在 host 实体存在之前是什么——client 要不要为它造一段独立生命；
|
||||
- session-scope 组件如何「自己拿会话数据」，而不是层层下传 props；
|
||||
- 用户放弃的新会话在 host 侧留下什么，谁来收。
|
||||
|
||||
硬约束：host 是唯一真源；一切注册走 `ctx.effect` disposer；scope 机制与 host 的 Agent scope 架构一致；模型可见 ⟺ 已入 session log。
|
||||
|
||||
## 决策
|
||||
|
||||
### 对等模型：client 与 host 同一根状态轴
|
||||
|
||||
host 侧 `session.create(workspaceId)` 一体产出 Session + Agent + cwd（原子大礼包，不拆）；client 侧就是这次出生的镜像——会话行进入 list mirror 的瞬间，client 为它铸 Agent scope（actx + provide + 输入面全套挂上）：
|
||||
|
||||
- 会话身份自出生即为 host 真身：sessionId 由 `session.create` 响应 / `host/session-added` 帧带来，client 侧一切寻址（scope tag、slot store 键、RPC 地址）用的都是同一个 id。
|
||||
- 实体化时点 = 用户选定 Workspace（cwd 确定）的瞬间：client 当场调 `session.create({workspaceId})`，拿到完整实体。
|
||||
- 「New Session 且未选 workspace」是**纯视图态**（一个导航位置），不对应任何 session/scope 实体；选定之前 composer 整体锁死（无 slash、无纯文本）。
|
||||
- 「空会话」就是一个日志还空着的普通实体化会话；对 host 上所有 Agent-scope 插件（goal/plan/skill/…）它与任何会话无异，slash/plan 天然全活。
|
||||
|
||||
### Agent scope：actx 是 client 侧 cordis 世界的唯一会话载体
|
||||
|
||||
runtime `agents/scope.ts` 与 host `dsh-scope` 机制层一致（fiber + tag + filter 过滤；不 value-import：host 包携带 scoped-events 的 `Events` merge，进 client program 撞 Context merge）：
|
||||
|
||||
- `createScope(ctx, key)`：no-op plugin fiber + `extend({[kScope]: key, [Context.filter]: …})`——filter 直接住 actx：untagged listener 全局可收，tagged 只收本 scope。
|
||||
- 派发就是 cordis 原语，thisArg = actx 本身：`actx.bail(actx, event, req)` / `actx.emit(actx, event, payload)`。
|
||||
- `Session.bindScope(actx)`：resolve 铸 scope 时单次配对（重复绑 throw；dropScope unbind），镜像 host `Agent.loopCtx`——Session 用它自行派发 scoped 事件。actx→Session 反向走 `sessions.sessionOf(actx)` 一跳（镜像 host 插件 `agent.session` 用法）。
|
||||
|
||||
与 host dsh-scope 的有意分歧三条：
|
||||
|
||||
- filter 住 actx 自身而非独立 carrier：host 包装层护的是「业务 Agent subject 与 scope key 不漂移」（host 事件首参注入 Agent 本体），client 事件 payload 只带 id、无 subject 可护。
|
||||
- key 用品牌 `SessionId` 值比较而非对象身份：host 里 agent.id === session id（1:1 同轴），agent 身份直接复用 `SessionId` 品牌，client scope 的身份即 wire id。
|
||||
- client 是 **Agent 身份** scope 而非活对象 scope：cold 会话期 host Agent 对象已 dispose 而 client actx 存活（视野内）——身份轴严格对等、对象冷热有意不同步。
|
||||
|
||||
id→ctx 换乘只许三类位置（业务 provider 永不换乘）：
|
||||
|
||||
- slot inject 工厂：ctx 不进渲染层，slot 框架交给组件的身份就是 sessionId，经服务 map 换回对象/controller。
|
||||
- root 协调服务自寻址：从投影的 sessionId 经 `sessions.scope(id)` 找回 actx。
|
||||
- root untagged listener：按 payload 的 sessionId 查自有 store。
|
||||
|
||||
### scope 生命周期：挂靠 list mirror，出生即视野、死亡即 prune
|
||||
|
||||
Session 实例与 scope 同生命周期，存活资格 = host listed（一个判据，mint 与 prune 共用）：
|
||||
|
||||
- 出生 = 会话行进入 client 视野（list 基线拉取 / `create()` 本地回声 / `host/session-added` 帧），lazy 首次 resolve 铸 scope（resolution 纯函数、渲染安全）。
|
||||
- prune 一次同拆三样：Session 实例、scope fiber（级联挂在 actx 上的一切消费者）、session-keyed slot store。staged session（= `list.current`）例外：被移除仍在台上时保留冻结只读视图，stage 移走才拆。
|
||||
- 重开 = lazy 重建实例 + `open()` 拉 history（host session log 是持久真相）。
|
||||
- 遗留 TODO：approval/question 帧不进 history，跨 prune 不可恢复（manager 级 pendingBuffers 只覆盖「从未实例化」窗口）。
|
||||
|
||||
### blank 位：空会话的可见投影、转正与复用
|
||||
|
||||
「实体化但无首讯」的会话经 summary 派生位 `blank` 治理（派生列而非 header 字段，SessionHeader 保持不可变）：
|
||||
|
||||
- host 判据：`session.events.length === 0`（零日志事件 = 尚无用户消息）。live 会话 `summarize()` 内存直读；cold 会话恒 `false`——lazy-create 契约保证 never-appended 会话根本不进 `persistence.list()`（JSONL/SQLite 两后端均已实证真 lazy），blank 从不落盘。
|
||||
- wire 承载两处：`SessionSummary.blank` 必填列；`host/session-added` 帧必填 `blank` 字段（创建时恒 true，供别的 tab 按同一空会话状态入镜像）。
|
||||
- client 镜像只降不升（单调），三来源翻转，全部复用既有 wire 信号：
|
||||
- 发送方本地：首次 `prompt()` 的**成功响应**翻 false（受理即证明 user/message 已入 host 日志——此点翻转是确证而非乐观；`onEngaged` 同步更新列表镜像，当前 `New Session` 行原地转为普通标题，不新增列表行）。首讯被拒则会话保持 blank：与 host 权威对齐、继续显示为 `New Session`、保持 connectWorkspace 复用资格。
|
||||
- 其他端：`host/session-status (running:true)` 帧翻转——blank 会话从不 running，首次 running 必然已非 blank；
|
||||
- 重连对齐：`session.list` 的 summary.blank 是权威，错过帧的端下次拉取自然对齐；陈旧的 blank:true 不能把已转正的会话重新标回 blank。
|
||||
- 列表纪律：store 保留全部行；Workspace browser 的分组、平铺、搜索和计数共用同一可见投影——所有非 blank 会话都显示，blank 会话只显示 `session.id === sessions.current` 的一条，并强制标题为 `New Session`。切换 Workspace 后，旧 blank 实体仍在镜像中但从列表隐藏，目标 Workspace 的 current blank 显示；因此用户可见面全局至多一条 blank 行。
|
||||
- 残留账零 GC：刷新后 blank 会话带位回来，下次同 workspace 复用，普通单端路径使每个 workspace 至多保留一个；host 重启后 blank 无盘痕自然蒸发；多 tab 竞态多出的空壳只会成为非 current 隐藏行，后续复用消化，不做协调。
|
||||
|
||||
### connectWorkspace：New Session 的唯一入口
|
||||
|
||||
`workspaces.connectWorkspace(workspaceId): Promise<SessionId>`（归属 WorkspacesService——它同时持有 workspace 规范 path 与 sessions 引用）：
|
||||
|
||||
- 复用臂：list mirror 中找 `blank && cwd == workspace.path`（host realpath 规范 canon 直等比较），命中直接返回该 id，不新建。
|
||||
- 新建臂：未命中则 `session.create({workspaceId})`，返回新 id。
|
||||
- 未知 workspaceId fail loud（不静默创建到别处）。
|
||||
- 解析保证（两臂同契约）：promise resolve 时返回的 id 已在 list store 且 `sessions.binding(id)` 同步可解析——`SessionsService.create` 在 RPC 成功后同步投影列表再 resolve，使 draft 搬运方可以在 open 之前往新 scope 的 machine 写文本，不等 notifier flush。
|
||||
- 调用方拿 id 自行 `sessions.open`；首讯发送就是普通 `session.prompt`——会话本来就在，失败即普通 prompt 失败，draft 文本还在 machine 里，重试即再次发送。
|
||||
- 全局 New Session 按钮默认取 `recentWorkspaceId`：先比较各 Workspace 内 Session 的最新 `updatedAt`，无 Session 时回退 Workspace `createdAt`，同值保持 Host 顺序；只有完全没有 Workspace 时才 `sessions.clear()` 进入无 session 视图。Workspace 分组内的创建动作仍显式命中该 Workspace。
|
||||
- runtime 启动时订阅首次完整基线：若已有恢复成功的 current session 则保持不动，否则自动 `connectWorkspace(recentWorkspaceId)` 并 open 返回的 blank session。该策略只结算一次；之后用户主动 clear 不会再次被自动选择覆盖，连接失败则等下一次基线投影重试。
|
||||
- blank Hero 中改选 Workspace 也走 `connectWorkspace`；若目标 id 与当前 id 不同，先把当前 input machine 的非空 draft 搬到目标 scope，再 `sessions.open(nextId)`。旧 blank 实体不删除，只因不再 current 而从列表隐藏。
|
||||
|
||||
### per-session 供数：`sessions.provide` 标准件通道
|
||||
|
||||
session slot 组件「自己拿 session 数据」的唯一供数路径。插件以静态描述符 `sessions.provide({hooks, props, resolve})` 声明固定键表（重名 key 注册时 throw），`resolve(binding)` 在确定 session 下物化值并随 scope 拆；web-react `standardKit` 统一循环把 hooks 格绑成 `use<Name>` 选择器 hook（`observableHook`→uSES，防 tearing）、props 格原样透传。
|
||||
|
||||
slot scope 是闭集 `root | session-maybe | session`：
|
||||
|
||||
- `root` 只拿全局标准件，不接收 session 身份或供数。
|
||||
- `session-maybe` 跟随 current session，但组件实例不因 id 有无或切换而换 key；无 session 时 `sessionId`、`useSession`/`useInput` 的选择结果及 `inputActions` 均可缺省。根部无 key 的 `SessionMaybeProvider` 驱动这条更新，`SessionMaybeProvideInfo` 靠静态键表在无 session 时仍保留完整 hook/prop 形状。
|
||||
- `session` 保证 `sessionId`、所有 hook source 与 props 均存在；每个严格 entry 的错误边界以 `sessionId` 为 key，切换 session 会重建该 entry 及其 session store。
|
||||
|
||||
`conversation` 是 `session-maybe` 的常驻外壳：`ConversationRoot`、HeroShell、Workspace picker、composer stack 与 overlay chain 的 fallback 外框在无 session → blank session 的切换中保持 React 实例；`conversation.session` 只承载严格 session 的 header/view，composer 与各输入 slot 也保持严格 `session`。无 session 时 composer stack 直接放纯展示的 `DisabledInputBar`，session 出现后把输入体换成严格绑定的 InputBar；textarea 允许重建，Hero 与布局骨架不重建。blank → engaging/active 仍在同一严格 session subtree 内，InputBar 不因 phase 翻转而重建。
|
||||
|
||||
- runtime 内建第一条：`'session'` hook——`useSession` 本身走同一机制，无特判。
|
||||
- Concurrent 纪律：渲染平面只从 hooks 格读（uSES 一致性保证）；props 格回调只在事件 handler 空间用；描述符解析 render-safe（幂等缓存、废弃渲染残留由 prune 收尸）。
|
||||
- 第三方组件值零依赖，类型一行 type-only import（declaration merging 进 `SessionStandardProps` / `SessionMaybeStandardProps`）。
|
||||
|
||||
### 队列只读镜像
|
||||
|
||||
- MuxFrame `session/queued`：Session 持只读 inbox 镜像（预览截断、steering 按 source 匹配退休）；queue 帧不进 history，纯 stream 态——重连清空、新基线重灌；未实例化窗口经 manager pendingBuffers 缓冲重放。
|
||||
- 队列语义：running 不锁输入；普通消息经 `session.prompt {mode:'queue'}` 排队，命令永不排队。
|
||||
|
||||
### host wire 小件
|
||||
|
||||
- summary `blank` 列与 `host/session-added` 帧 `blank` 字段（见上文 blank 位）。
|
||||
- SSE 帧 `host/commands-changed`（纯失效信号）；client 路由为类型事件 `commands/changed` 与 `connection/reset`（连接代建立后广播，wire 派生缓存一律视旧态为 stale）。
|
||||
- `command.list/execute`、`skill.list` 一律 `sessionId` 单址（会话恒有 Agent，`agentFor` 的 resume 语义现成）；命令面叙述见[命令业务面 note](2026-07-25-web-command-surfaces-and-assembly.md)。
|
||||
- `session.create` 请求形状：workspaceId/cwd 二选一 + 可选调用方预分配 sessionId（同 id 同 cwd 重试幂等，异 cwd 报 `session-conflict`）。
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
| 弃案 | 一行理由 |
|
||||
|---|---|
|
||||
| client-local Intent + materialize（published CAS / pendingPrompt attach 事务 / before-create 链） | client 被迫模拟 host 缺失的前半段生命，养出 published CAS、attach 事务、部分发布一坨状态机 |
|
||||
| host 预留 ID（draft Map） | host 只认了个号，状态机原封留在 client |
|
||||
| host draft Session（有 Session 无 Agent） | 每个查 Agent 的 host 面都要为 draft 分叉；core 要开 attachAgent 缝 + header cwd 后写 |
|
||||
| 无 cwd 先绑 Agent（ungrouped） | header.cwd readonly "created in" 不变性被推翻 + launch-dir 副作用产品坑 |
|
||||
| React Context 层层传会话语境 | 插件在 host/client 两侧应是一个心智模型；scope 机制与 host dsh-scope 同构 |
|
||||
| `scopeTarget` carrier + 融合派发器（镜像 host `agentEvents`） | host 包装层护的是「业务 Agent subject 与 scope key 不漂移」，client 事件无 subject 可护；filter 住 actx + cordis 原语覆盖全部需求 |
|
||||
| Session 不持 ctx（对象层 cordis-free） | 只为筛选单测不引 cordis 而生的红线，代价是 contribute 两跳回调 + 可变公有字段；host Agent 本就持 loopCtx |
|
||||
| Session 实例常驻（resident-instance） | host session log 即持久真相；常驻仅为身份便利，与 scope 生命周期错位是复杂度之源 |
|
||||
| 组件收 wiring 回调包（inject→props 两层下传） | 标准件通道让组件自取；公共面收敛为 hooks + 稳定 props |
|
||||
| Hero 无 session 视图与 session Conversation 整支互换 | 即使外层 layout 不变，Hero、picker 与 composer 子树仍会一起重建，界面产生整块抖动 |
|
||||
| 让 InputBar 自身变成 `session-maybe` | 输入状态机、键盘命令面与动作都被迫接受缺省值；只替换 disabled 输入体能把可选性留在外壳边界 |
|
||||
| 专用「转正」帧 | `session-status(running:true)` 语义蕴含转正（blank 会话从不 running），加帧是 wire 多一型换零信息 |
|
||||
|
||||
## 后果
|
||||
|
||||
- 插件获得与 host 同构的会话语境：per-session 状态挂 actx、随 scope fiber 一次拆装，泄漏结构性不可能；双会话隔离由 scope filter 结构性保证。
|
||||
- client 对象层收敛为 wire 镜像：会话身份、生命周期、能力判别全部以 host 实体为准——输入体系（下一层）面对的永远是「有真 Agent 的会话」，slash/skill 等 provider 一律以 sessionId 直接寻址。
|
||||
- 空会话治理零专用机制：状态靠一个派生位，可见性靠统一列表投影（仅 current blank 以 `New Session` 展示），回收靠 lazy persistence 的既有契约（重启蒸发），常规上限靠同 Workspace 复用。
|
||||
- 代价：id→ctx 换乘纪律、provide 的 Concurrent 纪律都是约定而非类型强制，靠 review 与测试钉住；「未选 workspace」期间输入全禁是产品面接受的体验代价（单一状态轴换来的）。
|
||||
- 已知欠账：approval/question 跨 prune 恢复（TODO）；模型选择以 live-mutation 形状回归（host `selectModel` 三件套现成，等独立分支）。
|
||||
@@ -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
|
||||
2026-07-03-filesystem-directory-listing-seam.md: c7db576ff3c7a56622f90a4400bd9297c9591bef
|
||||
2026-07-03-filesystem-directory-listing-seam.zh.md: 75ee6851127ca6d8c3fc60a66115d521d4627cdc
|
||||
2026-07-25-web-command-surfaces-and-assembly.md: 5188e8c17b31157b1c03203a8d7ba2d8e6a1496b
|
||||
2026-07-25-web-command-surfaces-and-assembly.zh.md: 0134cc10cf4f49b7719d6a0dacb239389776d6ed
|
||||
@@ -0,0 +1,62 @@
|
||||
# Agent Note: Web command business surfaces and assembly (ui-command / ui-skill / ui-subagent)
|
||||
|
||||
Status: implemented
|
||||
|
||||
English | [中文](2026-07-25-web-command-surfaces-and-assembly.zh.md)
|
||||
|
||||
> Scope: the command directory cache and three-kind dispatch (ui-command), the popup selection flow, the two skill / subagent reference sources, and fixture command routing plus assembly acceptance (the slash-flow snapshot). The carrying wire lives in the [session scope note](2026-07-25-web-client-session-scope-and-provide-channel.md); triggers, the menu, and the input machine live in the [input machine note](2026-07-25-web-input-machine-and-slash-pipeline.md).
|
||||
|
||||
## Problem
|
||||
|
||||
The pipeline was ready but command knowledge had no landing spot: host-side `ctx.commands` and `ctx.skills` were complete while the web channel had no command capability. The business layer had to answer:
|
||||
|
||||
- Command UI takes more than one shape (execute on the spot, pop a select box, backfill and keep typing arguments) — how do business packages ship with zero skeleton changes;
|
||||
- When is the directory fetched: pulling on every menu open is too slow, while a resident cache needs invalidation and reconnect stories;
|
||||
- Sessions are always agent-backed (Session + Agent born in the same instant) — by what address does the client command surface honor the host's per-agent effective directory;
|
||||
- Assembly-level acceptance: with the layers split apart, how the user-visible main chain is pinned once they come together.
|
||||
|
||||
## Decision
|
||||
|
||||
### ui-command: a `CommandService` + a session-keyed `CommandDirectory` + a per-session `PopupSelectController`
|
||||
|
||||
- The `ClientSessionContext { sessionId }` projection is self-held in the ui-slash contract (types.ts): sessions are always agent-backed, so session identity is the entire projection of command capability; the wire addresses by `{sessionId}` (both `command.list` and `command.execute`; the host resolves the Agent from the session header).
|
||||
- The directory is compartmented by `SessionId`, with per-key single-flight + an epoch guard (an old pull never overwrites newer state); `commands/changed` soft-invalidates every key (the old snapshot keeps serving while the repull runs in the background), `connection/reset` hard-invalidates every key and rewarms, Enter strong-waits on the current key, and a failure keeps the draft with no downgrade. Prewarming hangs on the source's `warm` hook — once over the full roster at scope birth, which covers the entire session lifecycle (session capability is constant from birth).
|
||||
- `register(contribution)` registers client commands (a descriptor + `available(projection)` + a popupSelect spec); candidate synthesis = the host directory + contribution availability filtering, then the query/position pass, and a host/contribution name clash fails loud.
|
||||
- The three command kinds derive from the registration surfaces; developers never declare positions: a host descriptor with `input` = **leadingInput** (backfill `/name ␣` + claim, keep typing arguments, leading position only); a client-registered popupSelect spec = **popupSelect** (the official select-box shell, business ships zero components); neither = **execute** (run on selection, zero UI).
|
||||
- The dispatch decision table: the menu can trigger all three kinds; Space recognizes only leadingInput (the misfire defense: irreversible side effects keep explicit entry points only); Enter runs execute / opens the shell only on a bare token, while leadingInput tolerates trailing arguments.
|
||||
- The popup from `popupFor(actx)`: search filters locally, select is single-flight, the projection is captured at open, onSelect consumes the token through the consume-token event only on success, a failure is retained for retry, and a session switch merely hides it. The popup shell is a transient layer (never in the state machine): the box holds focus, Enter/↑↓/Escape belong to it, and clicking outside the box dismisses (clicking the textarea also returns focus).
|
||||
|
||||
### Reference sources (seeing only projections plus their own apply closures, on the root ctx)
|
||||
|
||||
- **ui-skill**: `skill.list({sessionId})` addresses by session (the host resolves the project root from the session header); the directory cache is single-flight keyed by sessionId, prewarmed at birth by the `warm` hook and fully cleared by `connection/reset`. A pick produces a text outcome (the literal `/name ` text, Decision 21); `lexicon` supplies the roster from CatalogFetch's settled snapshot (`undefined` while not warm). No match hook (references never enter command adjudication). Skill references ride ordinary prompts as literal text (outside the command plane; tool-skill unchanged, with the session-prefix directory providing the cooperative association).
|
||||
- **ui-subagent**: candidates are zero-RPC (the sessions.list snapshot filtered by parentId/running); a pick produces a text outcome (the literal `@name ` text); `lexicon` derives from the same snapshot (the model-side representation awaits its business workstream).
|
||||
|
||||
### Fixture command routing and assembly
|
||||
|
||||
- The connection fixture adds command routing (fixture + fake-api): the keyless rig can run the complete command flow (directory, execution, popup selection).
|
||||
- The apps/cli assembly mounts all the new packages; the tsconfig path map / reference sets are filled in; catalogs/docs are regenerated with the wire and events.
|
||||
|
||||
### Assembly-level acceptance: the slash-flow snapshot
|
||||
|
||||
`apps/web/tests/slash-flow.snapshot.ts` pins the user-visible main chain (assembled keyless; package mocks are no substitute for the assembled transcript): the composer disabled with no session → creating a Workspace and entering an already-materialized blank session → picking the `/echo` leadingInput from the `/` menu → the command executes but the blank bit does not flip and the list still shows `New Session` → the first ordinary prompt's successful acceptance converts that same row; the same session-bound textarea holds across blank → active. `workspace-flow.snapshot.ts` separately pins blank-row creation/reuse, first-prompt rejection backfill, and — on a Workspace switch before the first prompt — the draft moving across input machines with the old blank row hidden.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
| Rejected | One-line reason |
|
||||
|---|---|
|
||||
| Inline prompt dispatch (command text riding the message into the host for parsing) | Conflates the command and message planes; command execution being independent of the message queue is existing host semantics |
|
||||
| A bridge materializing skills as commands | Skills have their own directory; N registrations would be a detour; the tag form naturally avoids the command plane |
|
||||
| A `skill.invoke` RPC | The host has no such operation; skill references are plain text riding prompts |
|
||||
| A new ContentBlock reference type | Full-chain cost (adapters/UI/compaction); text-as-truth plus structured occurrence records suffices |
|
||||
| Client packages self-reporting command directories | The host is the single source of truth; the client only reads descriptors, with `commands-changed` pushing invalidation |
|
||||
| The `requires: 'none' \| 'agent'` discriminant axis (an agentless directory + dual-addressed queries) | With sessions always agent-backed, the amphibious command has no owner; the whole axis reverts to master's shape, to be reopened on real demand |
|
||||
| Dedicated commandresult / commandpanel slots | Results go through notices; the popup shell is a skeleton-internal overlay; rich result cards sit in the ledger |
|
||||
| An agent-type directory as the `@` source | No type registry exists; the live-session snapshot already covers it |
|
||||
| A PickAction/EnterCommand class family (class-inheritance pick products) | Cross-package runtime values break client bundle purity; pure data interfaces plus closure methods are equivalent |
|
||||
|
||||
## Consequences
|
||||
|
||||
- Shipping a business command = a host registration plus one client `command.register` (popupSelect) or zero registration (execute/leadingInput derive automatically), with zero skeleton changes; the cost is that the three-kind semantics concentrate in ui-command, and a hypothetical fourth kind means changing it.
|
||||
- The resident directory cache plus push invalidation buys zero-latency menus and reliable enter adjudication; the cost is three invalidation paths (the change frame, reconnect, the epoch guard) that all need tests pinning them.
|
||||
- sessionId addressing puts the host's per-agent effective directory (global + scoped shadows) straight on the wire, with the client presenting it as-is.
|
||||
- Known gaps: the popupSelect shell has no shipped business consumer yet (model selection and its kin return with #600's host `selectModel` in live-mutation shape, serving as the onboarding template then); the queue's second cut (per-item Inbox operations), rich result cards, and roster configurability sit in the ledger awaiting their triggers.
|
||||
@@ -0,0 +1,62 @@
|
||||
# Agent Note: Web 命令业务面与装配（ui-command / ui-skill / ui-subagent）
|
||||
|
||||
Status: implemented
|
||||
|
||||
[English](2026-07-25-web-command-surfaces-and-assembly.md) | 中文
|
||||
|
||||
> 范围：命令目录缓存与三型判定（ui-command）、popup 选择流、skill / subagent 两个引用源、fixture 命令路由与装配验收（slash-flow 快照）。承载 wire 见[会话作用域 note](2026-07-25-web-client-session-scope-and-provide-channel.md)；触发/菜单/输入机器见[输入状态机 note](2026-07-25-web-input-machine-and-slash-pipeline.md)。
|
||||
|
||||
## 问题
|
||||
|
||||
管线就绪但没有命令知识的落点：host 侧 `ctx.commands` 与 `ctx.skills` 完整而 web 通道无命令能力。业务层要回答：
|
||||
|
||||
- 命令 UI 不止一种形态（当场执行、弹选择框、回填后继续打参数）——业务包如何零骨架改动上架；
|
||||
- 目录何时拉取：每次开菜单现拉太慢，常驻缓存就要有失效与重连故事；
|
||||
- 会话恒 agent-backed（Session+Agent 同瞬出生），client 命令面以什么地址兑现 host 的 per-agent 有效目录；
|
||||
- 装配级验收：拆开的各层合起来，用户可见主链如何钉住。
|
||||
|
||||
## 决策
|
||||
|
||||
### ui-command：`CommandService` + session 键控 `CommandDirectory` + per-session `PopupSelectController`
|
||||
|
||||
- 投影 `ClientSessionContext { sessionId }` 自持于 ui-slash 契约（types.ts）：会话恒 agent-backed，会话身份即命令能力的全部投影；wire 以 `{sessionId}` 寻址（`command.list` / `command.execute` 均是；host 从会话 header 解析 Agent）。
|
||||
- 目录按 `SessionId` 分格，per-key single-flight + epoch guard（旧拉取永不覆盖新态），`commands/changed` 全 key 软失效（旧快照继续服务、后台重拉）、`connection/reset` 全 key 硬失效并预热，Enter 强等当前 key、失败留草稿不降级。预热挂 source 的 `warm` 钩子——scope 出生时对全 roster 一次，即覆盖整个会话生命周期（会话能力自出生恒定）。
|
||||
- `register(contribution)` 注册 client 命令（descriptor + `available(projection)` + popupSelect spec）；候选合成 = host 目录 + contribution 可用性过滤，再过 query/position，host/contribution 重名 fail loud。
|
||||
- 命令三型按注册面派生，开发者不声明位置：host descriptor 带 `input` = **leadingInput**（回填 `/name ␣` + claim，继续打参数，仅限行首）；client 注册 popupSelect spec = **popupSelect**（官方选择框壳，业务零组件）；两者皆无 = **execute**（选中即执行，零 UI）。
|
||||
- 判定决策表：菜单可触发三型；Space 只认 leadingInput（误触发防线：不可逆副作用只留显式入口）；Enter 裸 token 才 execute/开壳、leadingInput 容忍尾随参数。
|
||||
- `popupFor(actx)` 的 popup：search 本地过滤、select single-flight、open 时捕获投影、onSelect 成功才经 consume-token 事件消 token、失败保留可重试、session 切换只隐藏。popup 壳是瞬态层（不进状态机）：框持焦点、Enter/↑↓/Escape 归它、点框外即 dismiss（点 textarea 同时归还焦点）。
|
||||
|
||||
### 引用源（只见投影 + 自家 apply 闭包的 root ctx）
|
||||
|
||||
- **ui-skill**：`skill.list({sessionId})` 按会话寻址（host 从会话 header 解析项目根）；目录缓存按 sessionId 键控 single-flight，`warm` 钩子出生预热、`connection/reset` 全清。pick 产出 text outcome（`/name ` 原文，决策 21）；`lexicon` 从 CatalogFetch 的 settled 快照给名录（未热 `undefined`）。无 match 钩子（引用不进命令裁决）。skill 引用以原文随普通 prompt 走（命令平面之外；tool-skill 不变，session-prefix 目录提供协作关联）。
|
||||
- **ui-subagent**：候选零 RPC（sessions.list 快照按 parentId/running 过滤）；pick 产出 text outcome（`@name ` 原文）；`lexicon` 同快照派生（模型侧表示待业务立项）。
|
||||
|
||||
### fixture 命令路由与装配
|
||||
|
||||
- connection fixture 补命令路由（fixture + fake-api）：keyless 台架可跑完整命令流（目录、执行、popup 选择）。
|
||||
- apps/cli 装配挂全部新包；tsconfig path map / reference 集补齐；catalog/docs 随 wire 与事件再生成。
|
||||
|
||||
### 装配级验收：slash-flow 快照
|
||||
|
||||
`apps/web/tests/slash-flow.snapshot.ts` 钉住用户可见主链（assembled keyless，包 mock 不替代装配转录）：无 session 时 composer 禁用 → 创建 Workspace 并进入已实体化的 blank session → `/` 菜单选 `/echo` leadingInput → 命令执行但 blank 位不翻转、列表仍显示 `New Session` → 首条普通 prompt 成功受理后同一行转正；同一 session-bound textarea 跨 blank → active 保持。`workspace-flow.snapshot.ts` 另钉住 blank 行创建/复用、首讯拒绝回填，以及首讯前切换 Workspace 时 draft 跨 input machine 搬运且旧 blank 行隐藏。
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
| 弃案 | 一行理由 |
|
||||
|---|---|
|
||||
| prompt 内联派发（命令文本随消息进 host 解析） | 混淆命令/消息平面；命令执行独立于消息队列是既有 host 语义 |
|
||||
| skill 物化为 command 的桥 | skill 自有目录；N 笔注册是绕路；标签形式天然避开命令平面 |
|
||||
| `skill.invoke` RPC | host 无此操作；skill 引用是随 prompt 的普通文本 |
|
||||
| 新 ContentBlock 引用类型 | 全链路成本（adapter/UI/compaction）；文本即真身 + 结构化 occurrence 记录已足够 |
|
||||
| client 各包自报命令目录 | host 是唯一真源；client 只读 descriptor，`commands-changed` 推失效 |
|
||||
| `requires: 'none' \| 'agent'` 判别轴（agentless 目录 + 双址查询） | 会话恒 agent-backed 后两栖命令无 owner；整轴回退 master 形状，待真需求重开 |
|
||||
| 专用 commandresult / commandpanel 坑位 | 结果走 notice；popup 壳是骨架内浮层；富结果卡入台账 |
|
||||
| agent-type 目录做 `@` 源 | 无类型注册表；live-session 快照已覆盖 |
|
||||
| PickAction/EnterCommand 类族（类继承 pick 产物） | 跨包运行时值破坏 client bundle 纯度；纯数据接口 + 闭包方法等价 |
|
||||
|
||||
## 后果
|
||||
|
||||
- 业务命令上架 = host 注册 + client 一笔 `command.register`（popupSelect）或零注册（execute/leadingInput 自动派生），零骨架改动；代价是三型语义集中在 ui-command，假想的第四型意味着改它。
|
||||
- 常驻目录缓存 + 推失效换来菜单零延迟与回车裁决可靠；代价是三条失效路径（change 帧、重连、epoch guard）都需测试钉住。
|
||||
- sessionId 寻址让 host 的 per-agent 有效目录（全局 + scoped shadows）直接上 wire，client 原样呈现。
|
||||
- 已知欠账：popupSelect 壳暂无已上架业务消费者（模型选择等 #600 的 host `selectModel` 以 live-mutation 形态回归，届时作接入样板）；队列第二刀（逐项 Inbox 操作）、富结果卡、roster 可配置性入台账待触发。
|
||||
@@ -0,0 +1,6 @@
|
||||
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write
|
||||
2026-07-25-web-input-machine-and-slash-pipeline.md: acbd132a5fdb97a4098064aae689dfca604ad4b7
|
||||
2026-07-25-web-input-machine-and-slash-pipeline.zh.md: 158650a41b47f98037a1b3e610d9294694c55a8c
|
||||
@@ -0,0 +1,132 @@
|
||||
# Agent Note: Web input state machine, composer slots, and the slash pipeline (ui-conversation input / ui-slash)
|
||||
|
||||
Status: implemented
|
||||
|
||||
English | [中文](2026-07-25-web-input-machine-and-slash-pipeline.zh.md)
|
||||
|
||||
> Scope: the input state machine (the occurrence table + claim watch + the submit transaction), the hub/facade and send orchestration, the three scoped bail events for cross-plugin input rewrites, `/` and `@` trigger detection and the menu pipeline (ui-slash), and the slot system around the composer. It depends on the [session scope note](2026-07-25-web-client-session-scope-and-provide-channel.md)'s sctx / provide / session-maybe and blank entity model; command knowledge (the three kinds, the directory, popups) is untouched here — that is the [command surfaces note](2026-07-25-web-command-surfaces-and-assembly.md)'s territory.
|
||||
|
||||
## Problem
|
||||
|
||||
Two composers, each a law unto itself: hero (EmptyState, the controlled chain writing straight into the Session) and the in-conversation InputBar (a plain controlled textarea) — behavior, draft ownership, and send path all inconsistent. To bring the three trigger families — `/` commands, skill references, `@` references — onto the input surface, these had to be answered:
|
||||
|
||||
- How the three trigger families layer, and who holds knowledge of "commands" versus who stays zero-knowledge;
|
||||
- How the input box expresses "command mode" — derived from the draft text or explicit state? What do backspace, enter, space, and pasting a whole line each mean;
|
||||
- Submission is an asynchronous transaction (an RPC round trip) — how are stale-result backwash, session switching, and React concurrent replay defended;
|
||||
- How reference chips are represented on a plain textarea, and who owns undo / clipboard / paste matching / model serialization;
|
||||
- How cross-plugin input rewrites (menu backfill, reference insertion, token consumption) achieve dependency inversion;
|
||||
- Which React shells must be reused across no session → blank session, and which strict-session input bodies may be replaced.
|
||||
|
||||
Hard constraints: components mount through slots only; presentation artifacts never enter the session log; the keyboard path is IME-safe throughout.
|
||||
|
||||
## Decision
|
||||
|
||||
### The input state machine (`InputMachine`)
|
||||
|
||||
A pure state machine, events in / effects out, clock injected. Four phases (plain / adjudicating / claimed / submitting). Command mode is **never derived from the draft**; the pick paths establish it explicitly at discrete moments; the claim is watched by `draft.startsWith(token)`, with a backspace break releasing automatically; the claim shape is `{token, hint?}` (hint feeds ghost text).
|
||||
|
||||
The event surface (`dispatch(ev)` is the single write entry; one transaction per event):
|
||||
|
||||
- `draft-changed {draft, editRange?}` — the textarea's full draft; editRange narrows the occurrence-shift computation, defaulting to a shared prefix/suffix scan.
|
||||
- `newline {selection}` — the Ctrl+Enter line break (not via the browser's execCommand: under self-managed undo a browser write forks two histories).
|
||||
- `begin-command {claim, span}` / `insert-ref {reference, span}` / `consume-token {guard}` — the machine side of the three bail events; span CAS = draftRev equality.
|
||||
- `set-invalid {invalidIds}` — the style bit for owner-resolution results (not a transaction).
|
||||
- `undo` / `redo` — the self-managed transaction log (a ring of 100; single-character typing merges within injected-clock windows; a successful submit clears the log).
|
||||
- `paste-begin {text, selection, components?, generation?}` — the paste plus hot-snapshot synchronously matched components in one transaction (one Undo returns to before the paste); opens a PasteMatchAttempt.
|
||||
- `paste-upgrade {attemptId, span, reference}` — an asynchronous match upgrade as its own transaction (Undo in two steps); the attempt stays current, and insertedRange shrinks with each upgrade.
|
||||
- `invalidate-paste` — attempt-ending gestures observed at the DOM layer (caret/selection operations and the like).
|
||||
- `enter {mode}` / `adjudicated` / `adjudication-failed` / `submit-settled` / `release` — the submit-transaction plane: a SubmitAttempt (seq + AbortSignal) blocks backwash; success commits and clears the draft; failure rolls back under the drift guard (the enter-time snapshot is backfilled only while the live draft still equals it; if the user has typed again, only a notice fires).
|
||||
|
||||
The effect surface (executed by the shell): `adjudicate` (calls SlashController.adjudicate), `begin-submit` (the claim.submit transaction), `default-sink` (ordinary messages, hub-orchestrated), `notice`.
|
||||
|
||||
The occurrence table and the chip's three projections:
|
||||
|
||||
- Each reference occupies one `U+FFFC` in the draft; a table entry is `{occurrenceId, source, ref, offset, label, clipboardText, invalid?}`; same-named chips stay independent through occurrenceId.
|
||||
- Every edit updates the draft and the table in one transaction: ranges shift; a deletion/replacement intersecting a placeholder acts on the whole chip.
|
||||
- The single-character placeholder makes keyboard atomicity mostly hold natively (the caret has no interior position; Backspace / arrow keys / Shift extension natively take the whole chip); a mouse click on a chip goes backdrop hit → whole-chip setSelectionRange.
|
||||
- The visual projection = label: the backdrop renders the chip at the placeholder offset (the textarea glyph is invisible), with invalid taking the invalid style.
|
||||
- The clipboard/persistence projection = clipboardText: copy/cut expands placeholders inside the selection; the draft-persistence mirror writes the same projection (the chat store always holds plain text; the refresh seed semantics = select-all copy → reopen → paste, with chips degrading to text across a refresh).
|
||||
- The model projection = generated per chip at submit through the source's `codec.serialize` (owned by the submit attempt's signal and stale guard; a missing owner / failure / cancel means no send, never a downgrade to `/name`).
|
||||
|
||||
### Cross-plugin input rewrites: three scoped bail events
|
||||
|
||||
The contract is declared in ui-slash (the bottom of the dependency chain); producers dispatch via `sctx.bail(sctx, ...)`, and the only consuming side is the three listeners the hub hangs on the sctx when building the shell; returning `true` ⟺ the machine passed the phase and CAS guards and actually rewrote (emitting the event ≠ a successful modification; whether Space gets `preventDefault` follows the return value):
|
||||
|
||||
- `slash/input-begin-command` `{claim, span}` — backfill of the command claim adjudicated from a menu pick / Space (dispatched by the SlashController).
|
||||
- `slash/input-insert-reference` `{reference, span}` — reference chip insertion (dispatched by the SlashController).
|
||||
- `slash/input-consume-token` `{guard: span | bare-token}` — consuming the command token after business success (dispatched by the downstream command surfaces).
|
||||
|
||||
Calls that stay un-evented (registry registration → explicit call → await): Input's own draft/submit, asynchronous Enter adjudication, the reference serializer, the asynchronous paste matcher. `@mode bail` has entered the JSDoc parser and the cordis catalog gate (scripts/jsdoc.ts).
|
||||
|
||||
### The slash pipeline (ui-slash: a root `SlashService` + a per-session `SlashController`)
|
||||
|
||||
A trigger/menu/pick pipeline with zero knowledge of "commands":
|
||||
|
||||
- The service holds only the source registry (`SlashSource{trigger: '/'|'@', name, candidates, onPick, matchSpace?, matchEnter?}`; (trigger,name) unique, registration order = group order = polling order) and `sessionOf(sctx)`. Implementing a match hook IS the declaration of participation in space/enter adjudication; the pipeline polls in registration order, the first non-undefined answer wins, and no claimant means the default sink. matchSpace is synchronous (space fires mid-keystroke; hot cache only); matchEnter is asynchronous (it may await the source's own warmup, and a warmup failure rejects).
|
||||
- The controller holds the single authoritative hit (span included; retained for Space after the menu closes), the per-session menu store, the candidate-fetch generation, keyboard arbitration (combobox mode: focus stays in the textarea, ↑↓/Enter/Escape are intercepted and all pass the IME composition guard, with the single exception Shift+Enter unconditionally going first), and pick orchestration (outcome → self-dispatched bail events); at each session scope's birth it runs `warm(projection)` once over the source roster — within that scope the projection holds only the stable sessionId, with no published/capability transitions; the scope disposer tears down the controller.
|
||||
- Trigger-detection word boundaries (`user@host` and URL `/` never trigger) and the guard tiers (plain: `/` everywhere + `@` inline / claimed: `/` suppressed, `@` live / frozen: none) are the frozen pure core.
|
||||
|
||||
### hub / facade: the resident shell and the strict-session input body
|
||||
|
||||
- The hub (trigger/decoration registries + send orchestration) takes the slash/command services as optional `ctx.get()` dependencies: without ui-slash or the command surfaces, input still sends and receives normally — graceful degradation.
|
||||
- Each materialized Session has exactly one `SessionInputShell` (the facade), created and torn down with the session scope; with no session, no input machine is built. `ConversationRoot` is itself the `session-maybe` resident shell, holding HeroShell, the Workspace picker, the composer stack, and the chain-fallback frame.
|
||||
- With no session the shell renders the presentation-only `DisabledInputBar`; once `connectWorkspace` returns a blank session, only the input body is swapped for the strict-session InputBar. The textarea may be rebuilt here, while `ConversationRoot`, the Hero, and the layout skeleton hold; blank → engaging/active stays the same session-bound InputBar, with the textarea never rebuilt on a phase flip.
|
||||
- ConversationRoot's Hero criterion is `sessionId === undefined || (composerPhase === 'blank' && (openState === 'open' || openState === 'loading'))`. The first submit enters engaging synchronously, and a failure keeps the composer and the error context rather than falling back to the blank Hero; the sidebar's blank bit flips false only after a prompt is successfully accepted.
|
||||
- Sending unifies in the hub defaultSink: after an optimistic draft clear it goes only through `session.prompt {mode:'queue'|'steer'}`; backfill happens only when it fails and the live draft is still empty — a user who has kept typing is never overwritten. No Draft materialize or attach transaction exists.
|
||||
- When the blank Hero re-picks the Workspace, the shell calls `connectWorkspace`; if the target session differs, the non-empty draft moves from the current shell to the target shell before the new id is opened, and the old blank session survives but is no longer current.
|
||||
- The Notifier's two-bit contract: `dirty` (snapshot freshness, clearable by an `ensureFresh` pull) and `notifyPending` (notification debt, cleared only by a flush) are mutually independent — a pull must not swallow a push, and object-layer push subscribers (watchTransaction) depend on this guarantee.
|
||||
|
||||
### Plain-text references (Decision 21): text outcomes and lexicon decoration
|
||||
|
||||
skill/@subagent references skip the placeholder + occurrence identity chain — a pick inserts the literal `/name ` `@name ` text straight into the draft, with the chip visual purely derived:
|
||||
|
||||
- PickOutcome gains a `{text}` arm; the new scoped bail event `slash/input-insert-text` `{text, span}` (the same contract as the other three: draftRev CAS, returning true ⟺ an actual rewrite); facade.insertText goes through setDraft concatenation — zero machine changes.
|
||||
- Sources get an optional `lexicon?(session)` hook: a synchronous hot-snapshot name roster, with `undefined` = data not warm — zero decoration, never triggering a fetch (the render path stays synchronous and side-effect-free); the controller aggregates it into the `lexicon()` public surface.
|
||||
- `decorations.scanTextRefs`: a word-boundary scan of the draft (`/name`, `@name` at line start / after whitespace; `x/name` never hits) against the roster; a hit gets the `.textRef` mark (a pure range highlight on the backdrop, same as hlToken); an edit breaking the match shape simply disappears on the next scan.
|
||||
- Sending is the literal text (no more `<skill>` serialization); on the bubble side MessageItem decorates both shapes (the legacy `<skill>` tag + plain-text tokens).
|
||||
- The old occurrence/paste/serialize chain stays on disk in full, undeleted (additive; deletion is a separate future cut). Known limitation kept as-is: with the lexicon not warm at paste / cold start there is no decoration — it lights up only after typing `/` opens the menu once.
|
||||
|
||||
### Per-session provide contributions and the private keyboard surface
|
||||
|
||||
- ui-conversation (the hub doubling as a contributor) supplies through `sessions.provide` the `'input'` hook (machine state + the queue overlay) plus the `inputActions` prop (`setDraft`/`submit`, stable void callbacks).
|
||||
- The public/private boundary: the public provide carries only React-vocabulary members; the keyboard/DOM command surface (track/arbitrate/space/undo/redo/paste/dismissPopup/bindMirror — synchronous return values, disposer semantics) is InputBar-exclusive, passed privately in-package through the InputBar entry's own inject, never leaving the plugin boundary.
|
||||
|
||||
### The slot system
|
||||
|
||||
`conversation` is itself session-maybe; its session content and the composer input slots are strict session, while the Hero Workspace picker stays root. The child slots are all declared by ui-conversation's conversation registration:
|
||||
|
||||
- `conversation.session` (single) — the strict-session header, view ring, and chat store; rebuilt when the session id switches.
|
||||
- `conversation.composer.bar` (single) — the slot for the InputBar itself: the InputBar is a true slot entry (self-registered into its own slot) and the content of the composer chain's fallback; it is not a chain entry — the chain's single election would unmount it on a takeover, breaking textarea DOM survival.
|
||||
- `conversation.input.overlay` — the floating-overlay anchor inside the input card; registrants' inject resolves each one's own per-session controller by the slot sessionId.
|
||||
- `conversation.input.dock` — the stacked strip above the input (QueueDock's read-only queue list lands here), ordered by `order`.
|
||||
- `conversation.composer.dock` — the stats band on the composer's top edge.
|
||||
- `conversation.input.left` / `conversation.input.right` — the tool-row left and right regions.
|
||||
- `conversation.input.plan` / `conversation.input.model` (single) — the tool row's two named control seats; the bar passes only `locked` (owner props), each stays empty until its owning plugin registers, no placeholder fallback.
|
||||
- `conversation.hero.workspace` (root scope) — the Workspace picker shared by the no-session and blank Hero; a pick reuses or creates the target blank session through `connectWorkspace`, moving the draft where necessary before switching current.
|
||||
|
||||
### Testing discipline
|
||||
|
||||
The state machine's entire behavior is covered by pure-JS unit tests (event sequences in, asserting state and effects, zero browser DOM); the interaction matrix is projection-tested row by row. This requirement is precisely what forced the pure-core + service-shell layering.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
| Rejected | One-line reason |
|
||||
|---|---|
|
||||
| An ActiveCommand intermediate state / a registerMode mode registry / deriving command mode from the draft | Claims are established explicitly by the pick paths — no table, no derivation |
|
||||
| Direct bindTarget/bindDraft object wiring | Reverse coupling plus root-singleton cross-session mispairing; scoped bail events preserve dependency inversion with structurally correct routing |
|
||||
| A unified slash/input-apply, or eventing everything | Three independent payloads cover the cross-plugin rewrites; asynchronous paths stay registry-based explicit calls |
|
||||
| contenteditable / a rich-text tree | Poor compatibility; textarea + U+FFFC + the occurrence table covers the full interaction contract |
|
||||
| Dual draft persistence {text, occurrences} | The mirror writing the clipboard projection adds zero new concepts; chip degradation across refresh is acceptable |
|
||||
| The native textarea undo stack | Unreliable under controlled + programmatic writes; the paste two-step undo semantics can only be self-managed |
|
||||
| The InputBar receiving a 16-member wiring-callback bundle | The consumption matrix proved 11 members InputBar-exclusive and 1 a dead member; the standard-kit channel lets components fetch their own, with the keyboard surface passed privately in-package |
|
||||
| Space adjudication also claiming execute-kind commands | The misfire defense: after a space the whole line is an ordinary prompt; irreversible side effects keep explicit entry points only |
|
||||
| A generic tokenPattern decoration mechanism | Structured occurrence records replace pattern scanning |
|
||||
| A placeholder select resident in the tool row | Named seats stay empty until registration; a placeholder clashing with the real implementation is two sources of truth |
|
||||
| All references through U+FFFC chips (the pre-Decision-21 line) | Plain text + derived decoration carries zero identity state; the literal text IS the model projection, sparing undo/clipboard any special cases; the chip chain is kept for scenarios needing indivisible atomicity |
|
||||
|
||||
## Consequences
|
||||
|
||||
- One resident conversation shell carries no-session/blank/active: no session → blank guarantees only the outer frame's React identity, allowing the disabled textarea to be replaced by the strict InputBar; the same blank session → engaging/active keeps the InputBar and the textarea. EmptyState and the controlled intent chain (`sessions.updateIntent`/`updatePendingPrompt`/`workspaces.sendSession`) are deleted along with their last consumer.
|
||||
- The input surface's zero knowledge of commands plus optional dependencies: pure input works without the command packages; `@` references and skill references get free reuse of the same menu/pick pipeline. The cost is that space/enter adjudication is a per-source polling protocol whose answer semantics (sync/async, the meaning of undefined) are a frozen contract.
|
||||
- Transactionalized submission (attempt seq + the drift guard) makes the three defect classes — stale-result backwash, session switching, concurrent replay — structurally impossible, pinned by the matrix tests.
|
||||
- Known gaps: chip fidelity across refresh (paste matching is reusable for it) has no workstream yet; the subagent reference's model representation awaits its business workstream.
|
||||
@@ -0,0 +1,132 @@
|
||||
# Agent Note: Web 输入状态机、composer 坑位与 slash 管线（ui-conversation input / ui-slash）
|
||||
|
||||
Status: implemented
|
||||
|
||||
[English](2026-07-25-web-input-machine-and-slash-pipeline.md) | 中文
|
||||
|
||||
> 范围：输入状态机（occurrence 表 + claim 看护 + 提交事务）、hub/facade 与发送编排、跨插件输入改写的三个 scoped bail 事件、`/` 与 `@` 触发检测与菜单管线（ui-slash）、composer 周边坑位体系。依赖[会话作用域 note](2026-07-25-web-client-session-scope-and-provide-channel.md)的 sctx / provide / session-maybe 与 blank 实体模型；命令知识（三型、目录、popup）零涉——那是[命令业务面 note](2026-07-25-web-command-surfaces-and-assembly.md)的领地。
|
||||
|
||||
## 问题
|
||||
|
||||
两个各自为政的 composer：hero（EmptyState，受控链直写 Session）与会话内 InputBar（普通受控 textarea），行为、draft 所有权、发送路径全不一致。要让 `/` 命令、skill 引用、`@` 引用三类触发进入输入面，必须回答：
|
||||
|
||||
- 三类触发如何分层，谁对"命令"有知识、谁零知识；
|
||||
- 输入框如何表达"命令态"——从 draft 文本推导还是显式状态？退格、回车、空格、整行粘贴各是什么语义；
|
||||
- 提交是异步事务（RPC 往返）——晚到结果回灌、会话切换、React concurrent 重放如何防御；
|
||||
- 引用 chip 在纯 textarea 上如何表示，undo/剪贴板/粘贴匹配/模型序列化各归谁；
|
||||
- 跨插件的输入改写（菜单回填、引用插入、token 消费）如何做到依赖倒置；
|
||||
- 无 session → blank session 时哪些 React 外壳必须复用，哪些严格 session 输入体允许替换。
|
||||
|
||||
硬约束：组件一律经 slots 挂载；呈现物不进 session log；键盘路径全程 IME 安全。
|
||||
|
||||
## 决策
|
||||
|
||||
### 输入状态机（`InputMachine`）
|
||||
|
||||
纯状态机，事件进/效果出，注入时钟。四相 phase（plain / adjudicating / claimed / submitting）。命令态**永不从 draft 推导**，由 pick 路径在离散时刻显式建立；claim 由 `draft.startsWith(token)` 看护、退格破坏自动 release；claim 形状 `{token, hint?}`（hint 供 ghost text）。
|
||||
|
||||
事件面（`dispatch(ev)` 单写入口，每个事件一个 transaction）：
|
||||
|
||||
- `draft-changed {draft, editRange?}`——textarea 全量草稿；editRange 缩小 occurrence 平移计算，缺省前后缀共扫。
|
||||
- `newline {selection}`——Ctrl+Enter 换行（不经浏览器 execCommand：自管 undo 下浏览器写入会分叉双历史）。
|
||||
- `begin-command {claim, span}` / `insert-ref {reference, span}` / `consume-token {guard}`——三个 bail 事件的机器侧；span CAS = draftRev 相等。
|
||||
- `set-invalid {invalidIds}`——owner resolution 结果的样式位（非 transaction）。
|
||||
- `undo` / `redo`——自管 transaction log（环形 100；单字符打字按注入时钟窗合并；提交成功清 log）。
|
||||
- `paste-begin {text, selection, components?, generation?}`——粘贴 + 热快照同步匹配组件同 transaction（Undo 一次回粘贴前）；打开 PasteMatchAttempt。
|
||||
- `paste-upgrade {attemptId, span, reference}`——异步匹配升级为独立 transaction（Undo 两段）；attempt 保持 current，insertedRange 随升级收缩。
|
||||
- `invalidate-paste`——DOM 层观察到的 attempt 终结手势（caret/selection 操作等）。
|
||||
- `enter {mode}` / `adjudicated` / `adjudication-failed` / `submit-settled` / `release`——提交事务平面：SubmitAttempt（seq + AbortSignal）防回灌，成功 commit 清稿，失败带漂移守卫 rollback（回车时快照仅当 live draft 仍等于它才回填；用户已再输入则只发 notice）。
|
||||
|
||||
效果面（shell 执行）：`adjudicate`（调 SlashController.adjudicate）、`begin-submit`（claim.submit 事务）、`default-sink`（普通消息，hub 编排）、`notice`。
|
||||
|
||||
occurrence 表与 chip 三投影：
|
||||
|
||||
- 每颗引用在 draft 中占一个 `U+FFFC`；表项 `{occurrenceId, source, ref, offset, label, clipboardText, invalid?}`；同名 chip 因 occurrenceId 独立。
|
||||
- 一切编辑同 transaction 更新 draft 与表：区间平移；与占位符相交的删除/替换作用于整颗。
|
||||
- 单字符占位使键盘原子性大半原生成立（caret 无内部位；Backspace/方向键/Shift 扩选原生即整颗）；鼠标点 chip 由 backdrop 命中 → 整颗 setSelectionRange。
|
||||
- 视觉投影 = label：backdrop 在占位符 offset 渲染 chip（textarea 字形不可见），invalid 走失效样式。
|
||||
- 剪贴板/持久化投影 = clipboardText：copy/cut 把选区内占位符展开；draft 持久化 mirror 写同一投影（chat store 里永远是普通文本，刷新 seed 语义 = 全选复制→重开→粘贴，chip 跨刷新降级为文本）。
|
||||
- 模型投影 = submit 时经 source `codec.serialize` 逐颗生成（归 submit attempt 的 signal 与 stale guard；owner 缺失/失败/取消则不发送，不降级为 `/name`）。
|
||||
|
||||
### 跨插件输入改写：三个 scoped bail 事件
|
||||
|
||||
契约声明在 ui-slash（依赖最底层），生产者经 `sctx.bail(sctx, ...)` 派发，唯一消费侧是 hub 建 shell 时挂在 sctx 上的三个 listener；返回 `true` ⟺ 机器过 phase + CAS 守卫并实际改写（发出事件 ≠ 修改成功，Space 是否 `preventDefault` 以返回值为准）：
|
||||
|
||||
- `slash/input-begin-command` `{claim, span}`——菜单 pick / Space 裁决出的命令 claim 回填（SlashController 派发）。
|
||||
- `slash/input-insert-reference` `{reference, span}`——引用 chip 插入（SlashController 派发）。
|
||||
- `slash/input-consume-token` `{guard: span | bare-token}`——业务成功后消费命令 token（下游命令面派发）。
|
||||
|
||||
不事件化的调用（registry 注册 → 显式调用 → await）：Input 自身的 draft/submit、Enter 异步裁决、reference serializer、异步 paste matcher。`@mode bail` 已入 JSDoc parser 与 cordis catalog 门禁（scripts/jsdoc.ts）。
|
||||
|
||||
### slash 管线（ui-slash：root `SlashService` + per-session `SlashController`）
|
||||
|
||||
对"命令"零知识的触发/菜单/pick 管线：
|
||||
|
||||
- service 只有 source 注册表（`SlashSource{trigger: '/'|'@', name, candidates, onPick, matchSpace?, matchEnter?}`；(trigger,name) 唯一、注册序 = 组序 = 轮询序）与 `sessionOf(sctx)`。实现 match 钩子即参与空格/回车裁决的声明；管线按注册序轮询，首个非 undefined 应答胜出，无人认领落 default sink。matchSpace 同步（空格在击键中触发，只许热缓存）；matchEnter 异步（可 await 源自身预热，预热失败即 reject）。
|
||||
- controller 持有唯一权威 hit（含 span；菜单关闭后为 Space 保留）、per-session menu store、候选 fetch generation、键盘仲裁（combobox 模式：焦点始终在 textarea，↑↓/Enter/Escape 拦截且全程过 IME composition 守卫，唯一例外 Shift+Enter 无条件先行）、pick 编排（outcome → 自派 bail 事件）；每个 session scope 出生时对 source roster 做一次 `warm(projection)`，projection 在该 scope 内只有稳定的 sessionId，无 published/能力跃迁；scope disposer 拆除 controller。
|
||||
- 触发检测词边界（`user@host`、URL `/` 永不触发）、守卫分档（plain：`/` 到处 + `@` 行内 / claimed：`/` 抑制、`@` 活 / frozen：全无）为冻结纯核。
|
||||
|
||||
### hub / facade：常驻外壳与严格 session 输入体
|
||||
|
||||
- hub（trigger/decoration 注册表 + 发送编排）对 slash/command 服务是可选 `ctx.get()` 依赖：无 ui-slash/命令面时输入正常收发，优雅降级。
|
||||
- 每个实体 Session 只有一个 `SessionInputShell`（facade），随 session scope 创建和拆除；无 session 时不造 input machine。`ConversationRoot` 自身是 `session-maybe` 常驻外壳，持有 HeroShell、Workspace picker、composer stack 与 chain fallback 外框。
|
||||
- 无 session 时外壳渲染纯展示的 `DisabledInputBar`；`connectWorkspace` 返回 blank session 后，仅输入体换成严格 session 的 InputBar。这里允许 textarea 重建，`ConversationRoot`、Hero 与布局骨架保持；blank → engaging/active 仍是同一 session-bound InputBar，textarea 不因 phase 翻转而重建。
|
||||
- ConversationRoot 的 Hero 判据是 `sessionId === undefined || (composerPhase === 'blank' && (openState === 'open' || openState === 'loading'))`。首次 submit 同步进入 engaging，失败也保留 composer 与错误上下文，不退回 blank Hero；sidebar 的 blank 位只在 prompt 成功受理后翻 false。
|
||||
- 发送统一在 hub defaultSink：乐观清稿后只走 `session.prompt {mode:'queue'|'steer'}`；失败且 live draft 仍为空才回填，用户已经继续输入则不覆盖。不存在 Draft materialize 或 attach 事务。
|
||||
- blank Hero 改选 Workspace 时，外壳调用 `connectWorkspace`；目标 session 不同时把非空 draft 从当前 shell 搬到目标 shell，再 open 新 id，旧 blank session 留存但不再 current。
|
||||
- Notifier 双位契约：`dirty`（快照新鲜度，`ensureFresh` 拉取可清）与 `notifyPending`（通知欠账，只有 flush 清）各自独立——拉取不得吞推送，对象层推订阅者（watchTransaction）依赖这一保证。
|
||||
|
||||
### 纯文本引用（决策 21）：text outcome 与 lexicon 装饰
|
||||
|
||||
skill/@subagent 引用不走占位符 + occurrence 身份链——pick 直接把 `/name ` `@name ` 原文插进 draft，chip 视觉纯派生：
|
||||
|
||||
- PickOutcome 增 `{text}` arm；新 scoped bail 事件 `slash/input-insert-text` `{text, span}`（与另三个同契约：draftRev CAS、返回 true ⟺ 实际改写）；facade.insertText 走 setDraft 拼接，机器零改动。
|
||||
- source 可选 `lexicon?(session)` 钩子：同步热快照名录，`undefined` = 数据未热——零装饰、永不触发 fetch（渲染路径保持同步无副作用）；controller 聚合为 `lexicon()` 公面。
|
||||
- `decorations.scanTextRefs`：词边界扫描 draft（行首/空白后的 `/name`、`@name`，`x/name` 永不命中）对照名录，命中即 `.textRef` mark（backdrop 纯 range 高亮，同 hlToken）；编辑破坏匹配形状下次扫描自然消失。
|
||||
- 发送即原文（不再 `<skill>` 序列化）；气泡侧 MessageItem 双形状装饰（legacy `<skill>` 标签 + 纯文本 token）。
|
||||
- 旧 occurrence/paste/serialize 链全部保留在盘未删（additive；删除另成将来一刀）。已知局限维持现状：粘贴/冷启动时 lexicon 未热不装饰，输 `/` 开一次菜单后才亮。
|
||||
|
||||
### per-session 供数贡献与键盘私面
|
||||
|
||||
- ui-conversation（hub 兼贡献者）经 `sessions.provide` 供 `'input'` hook（机器状态 + queue overlay）+ `inputActions` prop（`setDraft`/`submit`，稳定 void 回调）。
|
||||
- 公私分界：公共 provide 只放 React 语汇成员；键盘/DOM 命令面（track/arbitrate/space/undo/redo/paste/dismissPopup/bindMirror——同步返回值、disposer 语义）是 InputBar 独占，走 InputBar entry 自己的 inject 包内私递，不出插件边界。
|
||||
|
||||
### 坑位体系
|
||||
|
||||
`conversation` 本身是 session-maybe；其会话内容与 composer 输入坑位严格 session，Hero Workspace picker 保持 root。子坑均由 ui-conversation 的 conversation 注册声明：
|
||||
|
||||
- `conversation.session`（single）——严格 session 的 header、view ring 与 chat store；session id 切换时重建。
|
||||
- `conversation.composer.bar`（single）——InputBar 本体的坑位：InputBar 是真 slot entry（自家坑自注册），composer chain fallback 的内容；不做 chain entry——chain 单选举会在 takeover 时卸载它，破坏 textarea DOM 存活。
|
||||
- `conversation.input.overlay`——输入卡内浮层锚点；注册者 inject 按 slot sessionId 解析各自 per-session controller。
|
||||
- `conversation.input.dock`——输入上方堆叠条（QueueDock 的队列只读列表落此），order 定序。
|
||||
- `conversation.composer.dock`——composer 上沿统计带。
|
||||
- `conversation.input.left` / `conversation.input.right`——工具行左右区。
|
||||
- `conversation.input.plan` / `conversation.input.model`（single）——工具行两具名控制位；bar 只传 `locked`（owner props），空到 owning 插件注册为止，无占位 fallback。
|
||||
- `conversation.hero.workspace`（root scope）——无 session / blank Hero 共用的 Workspace picker；pick 经 `connectWorkspace` 复用或创建目标 blank session，必要时搬运 draft 后切 current。
|
||||
|
||||
### 测试纪律
|
||||
|
||||
状态机全部行为由纯 JS 单测覆盖（事件序列进、断言状态与效果，零浏览器 DOM）；交互矩阵逐行投影测试。这一要求正是纯核 + 服务壳分层的成因。
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
| 弃案 | 一行理由 |
|
||||
|---|---|
|
||||
| ActiveCommand 中间态 / registerMode 模式注册表 / 从 draft 推导命令态 | claim 由 pick 路径显式建立——无表、无推导 |
|
||||
| bindTarget/bindDraft 对象直连 | 反向耦合 + root 单例跨会话误配；scoped bail 事件保依赖倒置且路由结构性正确 |
|
||||
| 统一 slash/input-apply 或全事件化 | 三个独立 payload 覆盖跨插件改写；异步链路保持 registry 显式调用 |
|
||||
| contenteditable / 富文本树 | 兼容性差；textarea + U+FFFC + occurrence 表覆盖全部交互契约 |
|
||||
| draft 双持久化 {text, occurrences} | mirror 写剪贴板投影零新概念；chip 跨刷新降级可接受 |
|
||||
| 原生 textarea undo 栈 | 受控 + 程序化写入下不可靠；粘贴两段 undo 语义只能自管 |
|
||||
| InputBar 收 16 员 wiring 回调包 | 消费矩阵实证 11 员 InputBar 独占、1 员死成员；标准件通道让组件自取，键盘面包内私递 |
|
||||
| 空格裁决也认领即执行型命令 | 误触发防线：空格后整行是普通 prompt；不可逆副作用只留显式入口 |
|
||||
| 通用 tokenPattern 装饰机制 | 结构化 occurrence 记录取代模式扫描 |
|
||||
| 占位 select 常驻工具行 | 具名坑位空到注册为止；占位件与真实现冲突时是双真相源 |
|
||||
| 引用一律走 U+FFFC chip（决策 21 前旧线） | 纯文本 + 派生装饰零身份状态；原文即模型投影，undo/剪贴板免特判；chip 链保留给需要不可分原子性的场景 |
|
||||
|
||||
## 后果
|
||||
|
||||
- 一个常驻 conversation 外壳承接 no-session/blank/active：无 session → blank 只保证大框架 React identity，允许 disabled textarea 替换为严格 InputBar；同一 blank session → engaging/active 保持 InputBar 与 textarea。EmptyState 与受控 intent 链（`sessions.updateIntent`/`updatePendingPrompt`/`workspaces.sendSession`）随最后消费者一并删除。
|
||||
- 输入面对命令零知识 + 可选依赖：无命令包时纯输入可用；`@` 引用与 skill 引用免费复用同一菜单/pick 管线。代价是空格/回车裁决是逐 source 轮询协议，其应答语义（同步/异步、undefined 含义）为冻结契约。
|
||||
- 提交事务化（attempt seq + 漂移守卫）使晚到结果回灌、会话切换、concurrent 重放三类缺陷结构性不可能，由矩阵测试钉住。
|
||||
- 已知欠账：chip 跨刷新保真（可复用粘贴匹配）未立项；subagent 引用的模型表示待业务立项。
|
||||
@@ -0,0 +1,6 @@
|
||||
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write
|
||||
2026-07-26-packed-chunk-rows-by-default.md: d6a044676604e4a4512a7a6674edb80e120b2f3c
|
||||
2026-07-26-packed-chunk-rows-by-default.zh.md: 184d462d70dcc666a0b38497ead307ce6861382d
|
||||
@@ -0,0 +1,59 @@
|
||||
# Agent Note: Make packed chunk rows the default JSONL layout
|
||||
|
||||
Status: implemented
|
||||
|
||||
English | [中文](2026-07-26-packed-chunk-rows-by-default.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
Provider streams produce many token-sized `assistant/chunk` delta events whose repeated JSON envelopes can outweigh their payloads. The session log must retain each chunk as a distinct logical event: live `session/event` delivery, sequence numbers, `sourceEventSeqs`, replay, cancellation evidence, and UI streaming all depend on those boundaries.
|
||||
|
||||
The JSONL storage seam can reduce that envelope cost without changing the logical log. A run of at least three consecutive same-block delta events fits in one `text-chunks`, `reasoning-chunks`, or `tool-call-chunks` storage row, and decoding reconstructs every original event, timestamp, and sequence number. A credible default must cover runtime writers, app-level config, snapshot producers, and committed fixtures together; otherwise tests avoid the layout that deployments write.
|
||||
|
||||
## Decision
|
||||
|
||||
`dsh-session-persistence-jsonl` resolves an omitted `packChunks` to `true`. The ACP demo wrapper exposes the same default, and every composition that omits the field inherits packed writes. `packChunks: false` remains an explicit write-side diagnostic mode that stores one event per line.
|
||||
|
||||
Reading is unconditional and layout-blind. Packed, unpacked, and mixed files load into the same contiguous `SessionEvent[]`, so the default does not require a session-format version change or an on-disk runtime migration. The option controls newly appended batches only; it never selects a reader mode.
|
||||
|
||||
### Logical events and physical rows
|
||||
|
||||
Packing stays at the `dsh-session` storage seam through `packChunkRuns()` and `decodeStorageRecord()`. The encoder recognizes exact delta-event shapes, preserves unrecognized events verbatim, and packs only runs of at least three. A packed row is storage vocabulary, not a `SessionEventMap` member: it never enters `Session.events` or fires `session/event`.
|
||||
|
||||
The JSONL backend packs each durable append batch. Raw `compression: 'none'` and default Zstandard framing carry the same logical storage records; selecting raw mode for reviewable fixtures does not disable packing. Repository replay readers and normalizers decode the shared row format instead of maintaining snapshot-specific codecs.
|
||||
|
||||
### Canonical snapshot fixtures
|
||||
|
||||
Every committed session-format JSONL fixture uses the canonical packed representation. `scripts/session-fixture-layout.snapshot.ts` discovers tracked `*.jsonl` files and unignored untracked additions repository-wide, selects those whose first record is a `session` header, decodes all body records, and rejects content that differs from `packChunkRuns()` output. The inventory therefore includes ACP, headless, TUI, `apps/web`, parent sessions, child sessions, and future fixture names without a maintained path list.
|
||||
|
||||
ACP and headless snapshot runs harvest the default JSONL backend output. TUI and web record-mode writers apply `packChunkRuns()` to their in-memory events before writing fixtures. The authored `packed-chunks` ACP scenario runs under the ordinary config and retains all three packed row kinds; its contract decodes both its independent source fixture and target fixture before asserting event-for-event equality.
|
||||
|
||||
Focused package tests keep unpacked and mixed-layout inputs for reader compatibility. They do not opt the default snapshot corpus out of the canonical layout.
|
||||
|
||||
### In-flight branch convergence
|
||||
|
||||
The temporary [`scripts/migrate-packed-session-fixtures.ts`](../../../../scripts/migrate-packed-session-fixtures.ts) command lets in-flight branches converge after merging current `master`: `pnpm run migrate:packed-session-fixtures` discovers the same repository-wide fixture set as the permanent gate, preserves each header line, decodes existing mixed records, writes the canonical packed body, proves decoded equality, and proves idempotence. It never calls a model or regenerates transcript and presentation outputs.
|
||||
|
||||
The command remains linked from the testing policy and ACP snapshot README while older branches may carry fixture edits. The [removal proposal](../../proposed/process/2026-07-26-remove-packed-session-fixture-migrator.md) deletes the CLI, package command, this transitional section, and the documentation links, then replaces the permanent gate's command-specific remediation text once a live open-PR inventory shows that every affected branch is merged, closed, or canonical. The shared canonicalizer and snapshot gate remain permanent.
|
||||
|
||||
### Verification contract
|
||||
|
||||
JSONL persistence tests prove that omission writes a packed row, explicit `false` writes one event per line, and both forms load identical events. Canonicalizer unit tests cover header preservation, unpacked conversion, non-session JSONL, already-packed idempotence, and malformed input. The keyless snapshot gate covers every committed fixture and assembled replay path; documentation gates keep config defaults and bilingual contracts aligned.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
**Flip only the backend schema default.** This leaves wrapper defaults, direct TUI/web serializers, existing fixtures, and future fixture policy inconsistent. A default is meaningful only when shipping compositions and the tests representing them share it.
|
||||
|
||||
**Keep snapshots unpacked for readability.** Packed rows retain every fragment and timestamp explicitly, while the shared decoder and normalizer provide logical inspection. Keeping the largest committed consumer on a different layout would make snapshot coverage avoid the shipping write path.
|
||||
|
||||
**Remove `packChunks` and always pack.** One writer is simpler, but one-event-per-line output remains useful for diagnostics and for focused mixed-layout compatibility tests. The explicit opt-out preserves those current consumers without weakening the default.
|
||||
|
||||
**Batch chunks as logical session events.** This reduces event count, but it delays or reshapes live delivery, renumbers provenance, and requires every UI and replay consumer to understand another streaming unit. Physical packing obtains the storage benefit behind the existing persistence interface.
|
||||
|
||||
**Keep the branch migrator permanently.** The read-only canonicalizer and snapshot gate own continuing enforcement. A mutation command has value only while in-flight branches still carry the former fixture layout, so its lifetime is explicitly bounded by the removal proposal.
|
||||
|
||||
## Consequences
|
||||
|
||||
Ordinary JSONL writes and committed fixtures use fewer physical rows while preserving the exact logical event stream. Runtime readers accept every existing layout, and operators retain a deliberate unpacked diagnostic mode. Raw files are less convenient for per-token line processing, and external tools that incorrectly treat every post-header row as a `SessionEvent` encounter storage tags more often; supported readers call `decodeStorageRecord()`.
|
||||
|
||||
The repository carries a large mechanical fixture diff, reviewed through decoded equality and the canonical-layout gate rather than token-by-token line inspection. It also temporarily carries one branch migration command and its links; the separate removal proposal prevents that transition aid from becoming permanent process surface.
|
||||
@@ -0,0 +1,59 @@
|
||||
# Agent Note: 将打包分片行设为默认 JSONL 布局
|
||||
|
||||
Status: implemented
|
||||
|
||||
[English](2026-07-26-packed-chunk-rows-by-default.md) | 中文
|
||||
|
||||
## 问题
|
||||
|
||||
提供方流会产生大量 token 大小的 `assistant/chunk` 增量事件，其重复 JSON 封装可能比载荷本身更大。会话日志必须将每个分片保留为独立的逻辑事件：实时 `session/event` 传递、序号、`sourceEventSeqs`、回放、取消证据和 UI 流式输出都依赖这些边界。
|
||||
|
||||
JSONL 存储 seam 可以在不改变逻辑日志的情况下减少这部分封装开销。一段至少包含 3 个连续、同属一个块的增量事件可以编码为一条 `text-chunks`、`reasoning-chunks` 或 `tool-call-chunks` 存储行，解码则会重建每个原始事件、时间戳和序号。一个可信的默认值必须同时覆盖运行时写入器、应用级配置、快照生成器和签入仓库的 fixture（测试前置数据）；否则测试会绕开部署实际写入的布局。
|
||||
|
||||
## 决策
|
||||
|
||||
`dsh-session-persistence-jsonl` 会将省略的 `packChunks` 解析为 `true`。ACP（Agent Client Protocol）演示包装层公开相同的默认值，所有省略该字段的组合都会继承打包写入。`packChunks: false` 仍是写入侧显式诊断模式，以每事件一行的形式存储。
|
||||
|
||||
读取始终不受选项控制且与布局无关。打包、非打包和混合文件都会加载为相同且连续的 `SessionEvent[]`，因此更改默认值不需要变更会话格式版本，也不需要对磁盘数据执行运行时迁移。该选项只控制新追加的批次，绝不会选择读取器模式。
|
||||
|
||||
### 逻辑事件与物理行
|
||||
|
||||
打包保留在 `dsh-session` 的存储 seam，并通过 `packChunkRuns()` 和 `decodeStorageRecord()` 实现。编码器识别精确的增量事件形态，原样保留无法识别的事件，并且只打包至少包含 3 个事件的连续段。打包行属于存储词汇，不是 `SessionEventMap` 成员：它绝不会进入 `Session.events`，也不会触发 `session/event`。
|
||||
|
||||
JSONL 后端会打包每个持久追加批次。原始模式 `compression: 'none'` 与默认 Zstandard 帧承载相同的逻辑存储记录；为使 fixture 便于评审而选择原始模式，不会禁用打包。仓库中的回放读取器和规范化器会解码共享行格式，而不维护快照专用编解码器。
|
||||
|
||||
### 规范快照 fixture
|
||||
|
||||
每个签入仓库的会话格式 JSONL fixture 都使用规范打包表示。`scripts/session-fixture-layout.snapshot.ts` 会在整个仓库中发现已跟踪的 `*.jsonl` 文件，以及未被忽略的新增未跟踪 JSONL 文件，选择首条记录为 `session` header 的文件，解码所有正文记录，并拒绝与 `packChunkRuns()` 输出不同的内容。因此，该清单无需维护路径列表即可覆盖 ACP、headless、TUI、`apps/web`、父会话、子会话以及未来的 fixture 名称。
|
||||
|
||||
ACP 和 headless 快照运行会采集默认 JSONL 后端的输出。TUI 和 web 的记录模式写入器会在写入 fixture 前，对内存事件应用 `packChunkRuns()`。人工编写的 `packed-chunks` ACP 场景在普通配置下运行，并保留全部 3 种打包行类型；其契约先解码独立的源 fixture 和目标 fixture，再断言二者逐事件相等。
|
||||
|
||||
聚焦的包（package）测试保留非打包和混合布局输入，以验证读取器兼容性。这些测试不会让默认快照语料库豁免规范布局要求。
|
||||
|
||||
### 在途分支收敛
|
||||
|
||||
临时命令 [`scripts/migrate-packed-session-fixtures.ts`](../../../../scripts/migrate-packed-session-fixtures.ts) 让在途分支合并当前 `master` 后可以完成收敛：`pnpm run migrate:packed-session-fixtures` 会发现与永久门禁相同的仓库级 fixture 集合，保留各文件的 header 行，解码现有混合记录，写入规范打包正文，并证明解码结果相等且操作具有幂等性。该命令绝不会调用模型，也不会重新生成 transcript（文本记录）与呈现输出。
|
||||
|
||||
只要较旧分支仍可能携带 fixture 改动，测试政策和 ACP 快照 README 就会继续链接该命令。最新的开放 PR（Pull Request）清单确认每个受影响分支均已合并、关闭或符合规范后，[移除提案](../../proposed/process/2026-07-26-remove-packed-session-fixture-migrator.md)会删除该 CLI、包命令、本过渡章节和文档链接，并替换永久门禁中仅适用于该命令的修复指引。共享规范布局转换器与快照门禁保持永久存在。
|
||||
|
||||
### 验证契约
|
||||
|
||||
JSONL 持久化测试证明：省略选项时会写入打包行，显式传入 `false` 时会按每事件一行的形式写入，两种形式都会加载为完全相同的事件。规范布局转换器单元测试覆盖 header 保留、非打包转换、非会话 JSONL、已打包输入的幂等性和畸形输入。无密钥快照门禁覆盖每个签入仓库的 fixture 和组装后的回放路径；文档门禁则确保配置默认值与双语契约保持一致。
|
||||
|
||||
## 曾考虑的替代方案
|
||||
|
||||
**仅翻转后端 schema 默认值。** 这会让包装层默认值、TUI/web 直接序列化器、现有 fixture 与未来 fixture 政策仍然彼此不一致。只有已交付组合及代表这些组合的测试采用相同默认值时，该默认值才有意义。
|
||||
|
||||
**快照继续使用非打包格式以便阅读。** 打包行仍会显式保留每个片段和时间戳，共享解码器与规范化器则提供逻辑检查。如果让规模最大的签入仓库消费方采用不同布局，快照覆盖就会绕开已交付的写入路径。
|
||||
|
||||
**删除 `packChunks` 并始终打包。** 只保留一个写入器更简单，但每事件一行的输出仍适用于诊断和聚焦的混合布局兼容性测试。显式停用选项在不削弱默认值的同时，保留了这些现有消费方。
|
||||
|
||||
**把分片批量合并为逻辑会话事件。** 这会减少事件数量，但也会延迟或重塑实时传递，改变溯源信息所引用的序号，并要求每个 UI 和回放消费方理解另一种流式单位。物理打包通过现有持久化接口获得存储收益。
|
||||
|
||||
**永久保留分支迁移器。** 只读的规范布局转换器与快照门禁负责持续强制执行。只有在途分支仍携带旧 fixture 布局时，会修改仓库内容的命令才有价值，因此移除提案明确限定了其生命周期。
|
||||
|
||||
## 后果
|
||||
|
||||
常规 JSONL 写入与签入仓库的 fixture 使用更少的物理行，同时精确保留逻辑事件流。运行时读取器接受所有现有布局，操作方也保留有意提供的非打包诊断模式。按 token 逐行处理原始文件较为不便；错误地将 header 后每一行都视为 `SessionEvent` 的外部工具会更频繁地遇到存储 tag，受支持的读取器则会调用 `decodeStorageRecord()`。
|
||||
|
||||
仓库会产生大规模机械 fixture diff；评审应依据解码结果相等这一事实和规范布局门禁，而不是逐行、逐 token 检查。仓库还会暂时保留一个分支迁移命令及其链接；单独的移除提案会防止这项过渡辅助机制成为永久的流程接口。
|
||||
@@ -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
|
||||
2026-07-21-tui-reload-command.md: 89bf2f7bb482d7f3889136c1a6ac9918ba0c4919
|
||||
2026-07-21-tui-reload-command.zh.md: cfea10690af49f2cf484938a3f9f12d954766a71
|
||||
2026-07-26-task-registry-seam.md: 57ac176cf6d2b0a50fcbcfacd77f6a26b462b582
|
||||
2026-07-26-task-registry-seam.zh.md: 252382ac39ebf1e5077fad87fcee2537ae8a9ab3
|
||||
@@ -0,0 +1,35 @@
|
||||
# Agent Note: The task registry is a capability seam (`dsh-tasks` / `dsh-tasks-local`)
|
||||
|
||||
Status: implemented
|
||||
|
||||
English | [中文](2026-07-26-task-registry-seam.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
The [background-task runtime](2026-06-20-generic-long-running-tool-runtime.md) shipped `TaskService` as one concrete package: `@deepseek-ai/dsh-tasks` owned both the `ctx.tasks` contract every producer and control surface programs against and the process-local implementation (the in-memory store, settlement bookkeeping, owner-cleanup effects, teardown). That bundling recouples the two rates of change the repository's [capability-seam rule](2026-06-13-capability-seams.md) separates: swapping the registry's storage or lifecycle backend would churn the same package whose types and `ctx.tasks` surface producers (`dsh-tool-bash`, `dsh-tool-pty`, `dsh-tool-subagent`), the control surface (`dsh-tool-tasks`), and `TaskKindMap` extenders import. Every other swappable capability in the harness — bash, pty, fs, skill, subagent, web, session persistence — already carries the interface / implementation / consumer split; the task registry was the remaining `core`-mode exception, guarded only by a `TODO(task-service-backend)` comment.
|
||||
|
||||
## Decision
|
||||
|
||||
`tasks/` is now a three-package capability family in the bash-trio shape:
|
||||
|
||||
- **`@deepseek-ai/dsh-tasks` (interface)** — the abstract `TaskService extends Service` owning `ctx.tasks`, the eight-method contract (`start`, `list`, `get`, `read`, `kill`, `wait`, `onTaskDone`, `attachSurface`), all vocabulary types (`TaskId`, `TaskKindMap`, `TaskStart`, `TaskHooks`, `TaskOutcome`, `TaskSnapshot`, `TaskRead`, `TaskDoneListener`), and the snapshot invariant companion. The class-level JSDoc states the semantics every implementation owes: registrations outlive producer and surface fibers, owned access is session-fenced, settlement is first-wins with contained listeners, and `start` refuses work while no control surface is attached.
|
||||
- **`@deepseek-ai/dsh-tasks-local` (implementation)** — `LocalTaskService`, the process-local registry moved verbatim: the in-memory store, per-kind counters, waiter bookkeeping, `TASK_WAIT_TIMEOUT` deadline code, owner-cleanup effects, and force-fail teardown. The `dsh-timeout` dependency moves here with it; the seam has no implementation dependencies.
|
||||
- **`@deepseek-ai/dsh-tool-tasks` (consumer)** — unchanged; it injects `'tasks'` and never imports implementation types.
|
||||
|
||||
Compositions load `dsh-tasks-local` where they previously loaded `dsh-tasks` (the CLI cordis.yml row, `agent-spine-demo`, test harnesses, the tool-catalog generator boot). Producer misconfiguration diagnostics ("background tasks unavailable: load …") name `dsh-tasks` — the seam that defines the absent `ctx.tasks` service — and the seam's own surfaces (its README and the direct-mount fence) point at implementations, so the producer message stays correct when another backend becomes the recommended default. Producers, `TaskKindMap` declaration merges, and the control surface keep importing `@deepseek-ai/dsh-tasks` only.
|
||||
|
||||
The seam keeps the in-process contract semantics unchanged: `TaskStart.run()` still passes callbacks and exact `Agent` objects, so a durable or cross-process backend still has design work to do before it can implement this interface (identity, restart, ownership, observation). The split moves that future work out of every consumer's dependency graph; it does not pre-design the backend.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
**Keep the concrete service until a second backend exists (status quo).** This was the original runtime note's position: extracting an interface before a second implementation risks freezing the wrong boundary. It lost because the boundary is no longer speculative — the eight service methods and their semantics have been stable across every producer integration since introduction, they are exactly the surface `dsh-tool-tasks` and the producers already program against, and the repository convention treats swappable capabilities as three packages by default. The residual risk (a durable backend needing contract changes) is unchanged by the split: those changes would land in the seam package either way, and today they would also churn every consumer's implementation dependency.
|
||||
|
||||
**Interface-only extraction inside one package (export an abstract class beside the concrete one).** Rejected because it separates nothing operationally: consumers still depend on the package that carries the implementation and its dependencies, and a replacement backend still cannot ship without the local one in its graph. The package boundary is the unit of independent evolution here.
|
||||
|
||||
**Splitting `types.ts` out but leaving the service concrete.** Rejected for the same reason — the types are not the seam; `ctx.tasks` and its method contract are. Producers need the service key and semantics, not just the shapes.
|
||||
|
||||
## Consequences
|
||||
|
||||
Bought: the task registry now matches the repository-wide seam shape; a durable, remote, or instrumented registry is a sibling package implementing eight abstract methods, and no producer, control surface, or `TaskKindMap` extender changes when one lands. The seam README states the contract; the implementation README owns the lifecycle bookkeeping facts. The registry behavior suite (owner cleanup, settlement, waits, teardown) lives with `dsh-tasks-local`; the seam keeps a stub-subclass test pinning registration under `ctx.tasks` and single-service duplication behavior, plus the probe-based invariant suite.
|
||||
|
||||
Cost: one more package (manifest, tsconfig, README, invariant companion), and compositions must name the implementation package. `abstract` erases at runtime and this package name used to be the mountable registry, so the seam constructor fails loudly when mounted directly — a stale composition row gets "load an implementation such as @deepseek-ai/dsh-tasks-local" at load time instead of a half-registered `ctx.tasks` failing far from the misconfiguration.
|
||||
@@ -0,0 +1,35 @@
|
||||
# Agent Note: 任务注册表是一个能力 seam（`dsh-tasks` / `dsh-tasks-local`）
|
||||
|
||||
Status: implemented
|
||||
|
||||
[English](2026-07-26-task-registry-seam.md) | 中文
|
||||
|
||||
## 问题
|
||||
|
||||
[后台任务运行时](2026-06-20-generic-long-running-tool-runtime.md)交付时把 `TaskService` 做成了单个具体包（package）：`@deepseek-ai/dsh-tasks` 既拥有每个生产方和控制接口面向编程的 `ctx.tasks` 契约，也拥有进程内实现（内存存储、结算簿记、所有者清理 effect、拆除）。这种捆绑重新耦合了仓库[能力 seam 规则](2026-06-13-capability-seams.md)本要分离的两种变化速率：一旦替换注册表的存储或生命周期后端，被搅动的就是同一个包，而生产方（`dsh-tool-bash`、`dsh-tool-pty`、`dsh-tool-subagent`）、控制接口（`dsh-tool-tasks`）和 `TaskKindMap` 扩展方正是从这个包导入类型与 `ctx.tasks` 接口。harness 中其余每项可替换能力——bash、pty、fs、skill（技能）、subagent、web、会话持久化——都已具备接口／实现／消费方三分；任务注册表曾是仅剩的 `core` 模式例外，仅由一条 `TODO(task-service-backend)` 注释把守。
|
||||
|
||||
## 决策
|
||||
|
||||
`tasks/` 如今是一个 bash 三件套形态的三包能力家族：
|
||||
|
||||
- **`@deepseek-ai/dsh-tasks`（接口）**——抽象的 `TaskService extends Service`，拥有 `ctx.tasks`、八个方法的契约（`start`、`list`、`get`、`read`、`kill`、`wait`、`onTaskDone`、`attachSurface`）、全部词汇类型（`TaskId`、`TaskKindMap`、`TaskStart`、`TaskHooks`、`TaskOutcome`、`TaskSnapshot`、`TaskRead`、`TaskDoneListener`），以及快照不变式配套插件。类级 JSDoc 陈述了每个实现都必须兑现的语义：注册的存续期长于生产方与控制接口的 fiber，有所有者的访问以会话为界，结算遵循首次结果优先且监听器错误被隔离，并且在没有附加任何控制接口时 `start` 拒绝启动工作。
|
||||
- **`@deepseek-ai/dsh-tasks-local`（实现）**——`LocalTaskService`，即原样迁移的进程内注册表：内存存储、按 kind 划分的计数器、等待方簿记、`TASK_WAIT_TIMEOUT` deadline 代码、所有者清理 effect，以及强制失败的拆除。`dsh-timeout` 依赖随之迁入此包；seam 包不含任何实现依赖。
|
||||
- **`@deepseek-ai/dsh-tool-tasks`（消费方）**——保持不变；它注入 `'tasks'`，从不导入实现类型。
|
||||
|
||||
各组合在原先加载 `dsh-tasks` 的位置改为加载 `dsh-tasks-local`：CLI（命令行界面）的 cordis.yml 配置项、`agent-spine-demo`、各测试 harness，以及工具目录生成器的启动流程。生产方的配置错误诊断信息（「background tasks unavailable: load …」）点名 `dsh-tasks`——即定义缺失的 `ctx.tasks` 服务的 seam 包；seam 自身的表面（其 README 与直接挂载防线）会指向各实现，因此当另一个后端日后成为推荐默认时，生产方的消息依旧正确。生产方、`TaskKindMap` 声明合并和控制接口仍然只导入 `@deepseek-ai/dsh-tasks`。
|
||||
|
||||
该 seam 保持进程内契约语义不变：`TaskStart.run()` 仍然传入回调和确切的 `Agent` 对象，因此持久化或跨进程后端在能实现此接口之前仍有设计工作要做（身份、重启、所有权、观察）。这次拆分把该项未来工作移出了每个消费方的依赖图；它并不预先设计后端。
|
||||
|
||||
## 曾考虑的替代方案
|
||||
|
||||
**在第二个后端出现之前保持具体服务（维持现状）。**这正是运行时 Agent Note 当初的立场：在第二种实现出现前抽取接口，可能固化错误的边界。该方案落选，因为这条边界已不再是臆测：八个服务方法及其语义自引入以来在每一次生产方集成中都保持稳定，它们正是 `dsh-tool-tasks` 与各生产方已经面向编程的那套接口，而且仓库约定默认将可替换能力拆成三个包。剩余风险（持久化后端可能需要变更契约）不因这次拆分而改变：无论拆分与否，这类变更都会落在 seam 包里；而若维持现状，它们今天还会连带搅动每个消费方的实现依赖。
|
||||
|
||||
**在单个包内仅抽取接口（在具体类旁导出一个抽象类）。**否决，因为它在运作层面并未分离任何东西：消费方依然依赖携带实现及其依赖项的那个包，而替换后端若不把本地实现纳入自身依赖图，就仍然无法发布。在这里，包边界才是独立演进的单位。
|
||||
|
||||
**拆出 `types.ts` 但让服务保持具体。**基于同样的理由否决：类型并不是 seam，`ctx.tasks` 及其方法契约才是。生产方需要的是服务键和语义，而不只是类型形状。
|
||||
|
||||
## 后果
|
||||
|
||||
换来的是：任务注册表如今与全仓库通行的 seam 形态一致；持久化、远程或带插桩的注册表将是一个实现八个抽象方法的兄弟包，这样的注册表落地时，任何生产方、控制接口或 `TaskKindMap` 扩展方都无需改动。seam 包的 README 陈述契约；生命周期簿记方面的事实归实现包的 README 所有。注册表行为测试套件（所有者清理、结算、等待、拆除）随 `dsh-tasks-local` 存放；seam 包保留一个桩子类（stub subclass）测试，固定 `ctx.tasks` 下的注册行为与单一服务的重复注册行为，外加基于探针的不变式测试套件。
|
||||
|
||||
代价是：多出一个包，即多一份 manifest（元数据清单）、tsconfig、README 与不变式配套插件；同时各组合必须点名实现包。`abstract` 在运行时会被擦除，而这个包名过去正是可挂载的具体注册表，因此 seam 的构造函数在被直接挂载时会响亮失败——一条过期的组合配置行会在加载时得到「load an implementation such as @deepseek-ai/dsh-tasks-local」，而不是一个方法残缺的 `ctx.tasks` 在远离错误配置处才失败。
|
||||
@@ -1,6 +0,0 @@
|
||||
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write
|
||||
2026-07-20-code-mode-result-card-completeness.md: 97cd9d722e8252b956e16da03c3b8418451350f3
|
||||
2026-07-20-code-mode-result-card-completeness.zh.md: fea162b073e3473f7a07d4bf054408d28851fea9
|
||||
@@ -1,39 +0,0 @@
|
||||
# Agent Note: Keep the Code Mode result card complete
|
||||
|
||||
Status: implemented
|
||||
|
||||
English | [中文](2026-07-20-code-mode-result-card-completeness.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
The outer `run_code` tool persisted complete rendered content, but its UI presenter ignored that content and rebuilt the card body from a logs-only `presentationMeta` projection. A result-only run appeared correct because an empty presenter body let consumers fall back to `tool/result.content`. Once the program emitted a log, the presenter supplied non-empty content, that fallback stopped, and the returned value disappeared from the completed card. A spill policy's final head/tail preview was vulnerable to the same split ownership whenever captured logs made the stale projection non-empty.
|
||||
|
||||
Nested Code calls never owned cards, so producing metadata for the outer call solely to reconstruct one incomplete card also obscured the intended one-card boundary.
|
||||
|
||||
## Decision
|
||||
|
||||
The canonical tool registry pipeline owns the final model-facing outer content. On success, the `run_code` output renderer renders captured logs followed by the return value or the explicit no-output marker. Runtime failures and pre-execution policy denials are normalized into error content by `ToolRegistry` without invoking that renderer. A post-execute block runs after successful rendering and replaces the result with error content; other post-execute policy and spill decisions may replace content before persistence.
|
||||
|
||||
`run_code` omits `presentResult`. The established generic result fallback keeps the pending program title and renders the raw final `tool/result.content`; that durable, replayable, post-policy projection is the card's only result-content source. The host API proxy therefore omits a separate result view instead of serializing the same content in both `event.data.content` and `view.view.content`. The redundant logs-only `presentationMeta` projection remains removed.
|
||||
|
||||
Nested dispatch remains unchanged. Calls marked by `exec.parent` emit bounded `tool/code-dispatch` diagnostics but no `tool/call` or `tool/result` surface cards, so one outer `run_code` invocation still produces exactly one card.
|
||||
|
||||
## Testing
|
||||
|
||||
Tool unit coverage drives logs-only, result-only, logs-plus-result, no-output, spilled-result, and failure outcomes through the canonical registry, then pins the durable content and absence of a result presenter. A host-mux regression uses a call-only presenter to prove the result frame carries raw content exactly once and no view. These cases prove stale metadata cannot replace final content without making the host duplicate that content.
|
||||
|
||||
The keyless ACP backend and TUI Code Mode snapshots execute one outer program that performs two nested bash calls, logs `captured output`, and returns `CODE_ONE+CODE_TWO`. The persisted ACP log pins the complete result; the TUI surface shows one completed outer card containing both lines and no nested cards.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
**Append the return value to logs metadata.** Rejected because metadata would duplicate the renderer, need a second stable formatting contract for every JSON root, and still miss post-policy content replacement or spill previews.
|
||||
|
||||
**Merge presenter metadata with `result.content`.** Rejected because the rendered content already contains the logs; merging would duplicate them and require brittle deduplication.
|
||||
|
||||
**Forward `result.content` through a generic result presenter.** Rejected because the durable event already carries that content and UI consumers already have a generic raw-content fallback. The host mux serializes a tool-owned result view beside the event, so forwarding would duplicate the rendered content in one frame merely to recreate the fallback; the default worker alone admits a 64 MiB variable-payload budget before rendering.
|
||||
|
||||
**Create one card per nested dispatch.** Rejected because intermediate values are intentionally execution-local and never model-facing. Multiple cards would expose an implementation trace instead of the single Code Mode operation the model and user invoked.
|
||||
|
||||
## Consequences
|
||||
|
||||
TUI and JSON-RPC/Web display the same complete content the model receives and replay persists, including post-policy spill previews, through their generic result fallback. The host API retains the pending program title without duplicating the raw result in a separate view payload. New `run_code` results no longer carry the optional logs metadata, but this requires no session-format bump: existing records remain valid because presentation reads their durable rendered content.
|
||||
@@ -1,39 +0,0 @@
|
||||
# Agent Note: 保证 Code Mode 结果卡片内容完整
|
||||
|
||||
Status: implemented
|
||||
|
||||
[English](2026-07-20-code-mode-result-card-completeness.md) | 中文
|
||||
|
||||
## 问题
|
||||
|
||||
外层 `run_code` 工具会持久化完整的渲染内容，但其 UI 展示器忽略了这些内容，转而根据仅含日志的 `presentationMeta` 投影重新构建卡片正文。仅有结果的运行看似正确，是因为展示器正文为空时，消费方会回退到 `tool/result.content`。只要程序输出一条日志，展示器就会提供非空内容，回退随即停止，返回值便会从完成态卡片中消失。当已捕获的日志使陈旧投影变为非空时，输出落盘策略最终生成的头尾预览也会受到同一职责拆分的影响。
|
||||
|
||||
嵌套 Code 调用从不生成自己的卡片。因此，仅仅为了重建这一张不完整卡片而给外层调用生成元数据，还掩盖了每次外层调用只生成一张卡片的预期边界。
|
||||
|
||||
## 决策
|
||||
|
||||
规范的工具注册表流水线负责最终面向模型的外层内容。成功时，`run_code` 输出渲染器先渲染已捕获的日志，然后渲染返回值或显式的无输出标记。运行时失败和执行前策略拒绝由 `ToolRegistry` 归一化为错误内容，过程中不会调用该渲染器。Post-execute 阻断发生在成功渲染之后，并把结果替换为错误内容；其他 post-execute 策略与输出落盘决策可以在持久化之前替换内容。
|
||||
|
||||
`run_code` 不提供 `presentResult`。既有的通用结果回退机制会保留待完成的程序标题，并渲染原始的最终 `tool/result.content`；这一持久、可回放且经过 post-policy 处理的投影是卡片中结果内容的唯一来源。宿主 API 代理因此不提供单独的结果视图，而不会在 `event.data.content` 与 `view.view.content` 中重复序列化同一内容。冗余的仅含日志的 `presentationMeta` 投影继续保持移除状态。
|
||||
|
||||
嵌套分发保持不变。带有 `exec.parent` 标记的调用会发出有界的 `tool/code-dispatch` 诊断，但不会生成与 `tool/call` 或 `tool/result` 对应的界面卡片，因此一次外层 `run_code` 调用仍然只会生成一张卡片。
|
||||
|
||||
## 测试
|
||||
|
||||
工具单元测试通过规范注册表覆盖仅有日志、仅有结果、日志与结果并存、无输出、结果落盘和失败的结果，然后固定持久内容以及结果展示器不存在这一事实。宿主 mux 回归测试使用仅有调用的展示器，证明结果帧恰好携带一次原始内容，且不含视图。这些案例证明陈旧元数据无法替换最终内容，同时不会让宿主重复该内容。
|
||||
|
||||
无密钥的 ACP（Agent Client Protocol）后端快照与 TUI Code Mode 快照会执行一个外层程序：程序进行两次嵌套 bash 调用，记录 `captured output`，并返回 `CODE_ONE+CODE_TWO`。ACP 持久化日志固定完整结果；TUI 界面只显示一张完成态外层卡片，其中包含这两行内容，且没有嵌套卡片。
|
||||
|
||||
## 备选方案
|
||||
|
||||
**把返回值追加到日志元数据：**不予采纳。元数据会与渲染器重复，并且需要为每一种 JSON 根另行维护稳定的格式化契约；post-policy 内容替换或输出落盘预览仍然会被遗漏。
|
||||
|
||||
**把展示元数据与 `result.content` 合并：**不予采纳。渲染内容已经包含日志；合并会造成重复，还需要依赖脆弱的去重逻辑。
|
||||
|
||||
**通过通用结果展示器转发 `result.content`：**不予采纳。持久事件已经携带该内容，UI 消费方也已有通用的原始内容回退机制。宿主 mux 会在事件旁序列化工具拥有的结果视图，因此转发仅仅是为了重建该回退机制，却会在一个帧中重复渲染内容；仅默认 worker 在渲染前允许 64 MiB 的可变载荷预算。
|
||||
|
||||
**为每次嵌套分发创建一张卡片：**不予采纳。中间值有意只存在于执行期间，永远不面向模型。多张卡片会暴露实现轨迹，而不是模型与用户调用的单次 Code Mode 操作。
|
||||
|
||||
## 影响
|
||||
|
||||
TUI 与 JSON-RPC／Web 通过通用结果回退机制显示与模型接收及回放持久化相同的完整内容，其中包括 post-policy 输出落盘预览。宿主 API 保留待完成的程序标题，同时不在单独的视图负载中重复原始结果。新的 `run_code` 结果不再携带可选的日志元数据，但无需提升会话格式版本：现有记录仍然有效，因为展示逻辑会读取其中持久化的渲染内容。
|
||||
@@ -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
|
||||
2026-07-21-semantic-session-checkpoints.md: 4bca02fe3893ac39621ed79a000ca8f86db4ff67
|
||||
2026-07-21-semantic-session-checkpoints.zh.md: 1f187eb6448a3c9ca6784ec2bddd7295be2706d7
|
||||
2026-07-21-semantic-session-checkpoints.md: 0034cde40e5b07bda1573ca39fb7d51816006140
|
||||
2026-07-21-semantic-session-checkpoints.zh.md: 3351221d7eeaf1353b4adb0fa4c4dc324ec33da5
|
||||
|
||||
@@ -26,4 +26,4 @@ Flushing every event or streaming chunk minimizes loss but turns local append an
|
||||
|
||||
## Consequences
|
||||
|
||||
Hard-crash recovery retains the complete model request, durable tool intent, and complete settled step at the nearest semantic boundary while allowing partial streaming chunks since the previous boundary to remain lossy. Default CLI, TUI, ACP, Python SDK runtime, headless persistence tests, and JSON-RPC compositions mount the policy with their persistence backend. Unit tests cover ordering, cancellation during a checkpoint, fail-closed behavior, nested dispatch, disposal, and Loader shape; a real child process killed with `SIGKILL` proves request and tool-intent recovery through JSONL, and the shared persistence contract proves both recovery classifications across backends. Keyless ACP snapshots prove both that retry-risk guidance reaches resumed history and the next model turn and that graceful cancellation persists the loop's real closing boundaries.
|
||||
Hard-crash recovery retains the complete model request, durable tool intent, and complete settled step at the nearest semantic boundary while allowing partial streaming chunks since the previous boundary to remain lossy. Default CLI, TUI, ACP, Python SDK runtime, headless persistence tests, and JSON-RPC compositions mount the policy with their persistence backend. Unit tests cover ordering, cancellation during a checkpoint, fail-closed behavior, nested dispatch, disposal, and Loader shape; a real child process killed with `SIGKILL` proves request and tool-intent recovery through JSONL, and the shared persistence contract proves both recovery classifications across backends. The crash harness waits for the expected marker contents rather than path existence, so open-before-write visibility cannot trigger the kill early. Keyless ACP snapshots prove both that retry-risk guidance reaches resumed history and the next model turn and that graceful cancellation persists the loop's real closing boundaries.
|
||||
|
||||
@@ -26,4 +26,4 @@ ACP（Agent Client Protocol）应用在一个有序 Cordis effect 中统一持
|
||||
|
||||
## 后果
|
||||
|
||||
发生硬崩溃时，崩溃恢复会在最近的语义边界保留完整的模型请求、持久化的工具意图与完整且已结束的步骤，但允许上一个边界之后的部分流式分片仍可能丢失。默认的 CLI（命令行界面）、TUI、ACP、Python SDK 运行时、headless 持久化测试与 JSON-RPC 组合都会在持久化后端旁加载该策略。单元测试覆盖顺序、检查点期间的取消、失败关闭行为、嵌套分发、dispose（资源释放）与 Loader 形状；一个被 `SIGKILL` 终止的真实子进程通过 JSONL 证明系统可以恢复请求与工具意图，共享持久化契约则证明各后端都支持这两种恢复分类。无密钥 ACP 快照既证明重试风险指引会进入恢复后的历史记录与下一个模型轮次，也证明取消流程正常收尾时，系统会持久化由循环实际生成的闭合边界。
|
||||
发生硬崩溃时，崩溃恢复会在最近的语义边界保留完整的模型请求、持久化的工具意图与完整且已结束的步骤，但允许上一个边界之后的部分流式分片仍可能丢失。默认的 CLI（命令行界面）、TUI、ACP、Python SDK 运行时、headless 持久化测试与 JSON-RPC 组合都会在持久化后端旁加载该策略。单元测试覆盖顺序、检查点期间的取消、失败关闭行为、嵌套分发、dispose（资源释放）与 Loader 形状；一个被 `SIGKILL` 终止的真实子进程通过 JSONL 证明系统可以恢复请求与工具意图，共享持久化契约则证明各后端都支持这两种恢复分类。崩溃 harness 会等待预期的标记内容，而不是仅等待路径存在，因此文件在写入前因打开而可见时，不会导致该 harness 提前终止子进程。无密钥 ACP 快照既证明重试风险指引会进入恢复后的历史记录与下一个模型轮次，也证明取消流程正常收尾时，系统会持久化由循环实际生成的闭合边界。
|
||||
|
||||
@@ -1,29 +0,0 @@
|
||||
# Agent Note: A collapsed sidebar retains its control rail
|
||||
|
||||
Status: implemented
|
||||
|
||||
English | [中文](2026-07-22-collapsed-sidebar-control-rail.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
The sidebar close action persisted a zero width preference, and the layout mapped that preference to a zero-width grid track. The only sidebar toggle and the settings entry both lived inside that clipped track, so closing the sidebar removed every visible recovery control. Reloading preserved the closed preference and reproduced the lockout.
|
||||
|
||||
## Decision
|
||||
|
||||
The layout maps a closed sidebar (persisted width `0`) to the fixed `SIDEBAR_COLLAPSED` width of 56px: a 24px icon column between the sidebar's 16px horizontal paddings. The sidebar track is fixed-width in the solver — open or collapsed it never concedes to viewport pressure (only details shrinks, then auto-closes) — and the rail retains its right border while the stored expanded width remains untouched.
|
||||
|
||||
`AppFrame` marks the sidebar collapsed from the persisted width preference rather than from the resolved track width, removes the resize handle while collapsed, and passes `collapsed` to the sidebar slot as owner props from the render site. Collapse and expand animate: the frame transitions `grid-template-columns` (and the remaining handle its `left`) on the deepsuite sider curve — `--ds-ease-in-out` over `--ds-transition-duration-slow`, both supplied by ui-theme's base sheet; transitions pause during drags and under `prefers-reduced-motion`.
|
||||
|
||||
`SidebarRoot` reads the owner `collapsed` prop and transitions as a slide + crossfade: the expanded content freezes at its width (inline style) and fades out in place over 150ms while the sliding grid column clips it — nothing reflows mid-slide. At settle the wide-only content (brand, labels, input, session tree) unmounts — dropping the sessions subscription and leaving the rendered and accessibility trees — and the control rows snap to the rail (open toggle, new session, new workspace, search, the same top-down order as their expanded rows) fading in as the slide ends. Each rail control keeps its expanded counterpart's behavior (the search icon expands the sidebar and focuses the search box after the slide), carries a tooltip, and the toggle rests as the whale mark with the panel icon on hover. The search query lives with the root and survives the round trip.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
- **Render an expand button over the center column** — rejected because it recovers only the toggle, not the persistent settings area, and splits sidebar chrome across two package owners.
|
||||
- **Keep a zero-width grid track and let the rail overflow it** — rejected because the rail would overlap the center column and leave hit testing and responsive geometry disconnected from the grid.
|
||||
- **Keep the complete sidebar tree mounted and hide it with clipping** — rejected because hidden controls remain in the semantic tree and continue subscribing and rendering even though only two controls belong in the collapsed state.
|
||||
|
||||
## Consequences
|
||||
|
||||
- A collapsed sidebar reserves 56px instead of yielding the entire width to the center column. Expanding restores the persisted width and drag behavior.
|
||||
- The settings entry remains visible but retains its existing placeholder behavior; this change does not introduce an account or settings screen.
|
||||
- Layout solver tests pin the compact width, sidebar component tests pin the visible controls, and the keyless real-bundle web smoke test pins collapse and recovery through the assembled client.
|
||||
@@ -1,29 +0,0 @@
|
||||
# Agent Note: 侧边栏折叠后保留控制栏
|
||||
|
||||
Status: implemented
|
||||
|
||||
[English](2026-07-22-collapsed-sidebar-control-rail.md) | 中文
|
||||
|
||||
## 问题
|
||||
|
||||
侧边栏关闭操作会持久化宽度偏好 `0`，布局再将该偏好映射为宽度为零的网格轨道。侧边栏唯一的开关与设置入口都位于这个被裁切的轨道内，因此关闭侧边栏会移除所有可见的恢复控件。页面重新加载时仍会读取关闭偏好，从而再次陷入无法恢复的状态。
|
||||
|
||||
## 决策
|
||||
|
||||
布局将关闭的侧边栏（持久化宽度为 `0`）映射为固定的 `SIDEBAR_COLLAPSED` 宽度 56px：在侧边栏两侧各 16px 的水平内边距之间放置一列 24px 的图标控件。侧边栏轨道在求解器中是定宽的——无论展开还是折叠都不向视口压力让步（只有 details 会收缩、继而自动关闭）；控制栏保留右侧边框，已存储的展开宽度保持不变。
|
||||
|
||||
`AppFrame` 根据持久化的宽度偏好标记侧边栏是否折叠，而不是根据求解后的轨道宽度来判断；折叠时移除尺寸调整手柄，并在渲染点把 `collapsed` 作为 owner props 传给侧边栏插槽。折叠与展开带动画：frame 对 `grid-template-columns`（以及余下手柄的 `left`）应用 deepsuite 侧栏曲线过渡——`--ds-ease-in-out` 配 `--ds-transition-duration-slow`，两个变量由 ui-theme 的 base 表提供；拖拽期间和 `prefers-reduced-motion` 下过渡暂停。
|
||||
|
||||
`SidebarRoot` 读取 owner 的 `collapsed` 属性，过渡是滑动 + 交叉淡变：展开内容以内联样式冻结在原宽度、150ms 原地淡出，滑动中的网格列裁切它——滑动途中不发生任何重排。settle 时宽态专属内容（品牌标识、文字标签、输入框、会话树）卸载——随之退订会话列表并离开渲染树与可访问性树——控件行落位到控制栏（打开开关、新建会话、新建工作区、搜索，自上而下与展开态各行顺序一致），随滑动结束淡入。每个控制栏控件保持与展开态对应控件一致的行为（搜索图标展开侧边栏并在滑动结束后聚焦搜索框）并带 tooltip；开关静止时显示鲸鱼标，悬停切换为面板图标。搜索关键词由根组件持有，折叠往返后保留。
|
||||
|
||||
## 曾考虑的替代方案
|
||||
|
||||
- **在中心列上方渲染展开按钮**：不予采纳，因为这只能恢复开关，无法保留常驻设置区域，同时还会让侧边栏 UI 由两个包（package）分别持有。
|
||||
- **保留宽度为零的网格轨道，让控制栏溢出显示**：不予采纳，因为控制栏会与中心列重叠，还会使命中测试和响应式几何关系脱离网格布局。
|
||||
- **保持完整侧边栏树挂载，并通过裁切将其隐藏**：不予采纳，因为隐藏控件仍留在语义树中，而且会继续订阅和渲染，尽管折叠状态下只需要两个控件。
|
||||
|
||||
## 后果
|
||||
|
||||
- 折叠的侧边栏占用 56px，而不是把全部宽度让给中心列。展开时恢复持久化宽度与拖动行为。
|
||||
- 设置入口持续可见，但保留既有占位行为；本次改动不提供账户或设置页面。
|
||||
- 布局求解器测试固定紧凑宽度，侧边栏组件测试固定可见控件，基于真实构建产物的无密钥 Web 冒烟测试则通过组装后的客户端固定折叠与恢复行为。
|
||||
@@ -1,27 +0,0 @@
|
||||
# Agent Note: demo:web builds the client plugin bundles
|
||||
|
||||
Status: implemented
|
||||
|
||||
English | [中文](2026-07-23-demo-web-builds-client-bundles.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
`dsh web` serves each web-client plugin's bundle from `GET /plugins/<id>/client.js`, resolving the path from the package's `exports["./client"]` (`lib/client.js`). Those bundles are produced only by the root `pnpm run build` (`tsc -b` then the per-package `tsdown.client.ts` configs); the Vite `build:web` step builds the frontend shell alone. `demo:web` and the README's Web UI instructions ran only `build:web`, so on a checkout without a prior full build every plugin bundle 404s, the client loader marks every plugin failed, and the boot screen shows "Failed to load plugins". The frontend shell built fine, hiding the missing artifact behind a runtime browser failure.
|
||||
|
||||
## Decision
|
||||
|
||||
`demo:web` runs `npm run build` before `npm run build:web`, so the plugin `lib/client.js` bundles exist before `dsh web` serves them. The README's Web UI section runs `pnpm run build && pnpm run build:web` for the installed `~/.dsh/source` checkout, which the installer never builds.
|
||||
|
||||
## Verification
|
||||
|
||||
After the full build, all eight `/plugins/<id>/client.js` endpoints return 200 and a headless Chromium load of `http://127.0.0.1:3080` renders the shell with no "Failed to load plugins" state.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
**Build the bundles inside `dsh web` at startup.** The app runs from source via tsx and owns no build step; folding an artifact build into the server boot crosses the source/artifact separation and slows every launch.
|
||||
|
||||
**Widen the tsdown root config to emit client bundles from `pnpm run build:web`.** `build:web` is the Vite frontend build; the client bundles are a separate tsdown pass over `lib/types`. Merging the two conflates the shell build with the package build and still leaves the root `build` as the only producer.
|
||||
|
||||
## Consequences
|
||||
|
||||
`demo:web` now pays the full `tsc -b && tsdown` cost on every invocation instead of only the Vite build. That is the price of a runnable web demo from a clean tree; a caller who already built can invoke `dsh web` directly.
|
||||
@@ -1,27 +0,0 @@
|
||||
# Agent Note: demo:web 构建客户端插件的打包产物
|
||||
|
||||
Status: implemented
|
||||
|
||||
[English](2026-07-23-demo-web-builds-client-bundles.md) | 中文
|
||||
|
||||
## Problem
|
||||
|
||||
`dsh web` 通过 `GET /plugins/<id>/client.js` 提供每个 web 客户端插件的打包产物，其路径由包的 `exports["./client"]`（`lib/client.js`）解析得到。这些打包产物只由根目录的 `pnpm run build`（先 `tsc -b`，再执行各包的 `tsdown.client.ts` 配置）生成；Vite 的 `build:web` 步骤只构建前端外壳。`demo:web` 与 README 的 Web UI 说明只运行了 `build:web`，因此在未预先完整构建的检出上，每个插件的打包产物都返回 404，客户端 loader 将所有插件标记为失败，启动界面显示 "Failed to load plugins"。前端外壳能正常构建，把缺失的产物掩藏在浏览器运行时的失败背后。
|
||||
|
||||
## Decision
|
||||
|
||||
`demo:web` 在 `npm run build:web` 之前先运行 `npm run build`，使插件的 `lib/client.js` 打包产物在 `dsh web` 提供它们之前已经存在。README 的 Web UI 小节针对已安装的 `~/.dsh/source` 检出运行 `pnpm run build && pnpm run build:web`，因为安装器从不构建它。
|
||||
|
||||
## Verification
|
||||
|
||||
完整构建后，全部八个 `/plugins/<id>/client.js` 端点均返回 200，无头 Chromium 加载 `http://127.0.0.1:3080` 能渲染出外壳，不再出现 "Failed to load plugins" 状态。
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
**在 `dsh web` 启动时构建打包产物。** 该应用通过 tsx 从源码运行，本身没有构建步骤；把产物构建塞进服务器启动流程会越过源码与产物的分离，并拖慢每次启动。
|
||||
|
||||
**扩大 tsdown 根配置，使 `pnpm run build:web` 也产出客户端打包产物。** `build:web` 是 Vite 前端构建；客户端打包产物是对 `lib/types` 的另一趟独立 tsdown 处理。把两者合并会混淆外壳构建与包构建，而且根目录的 `build` 仍是唯一的产出者。
|
||||
|
||||
## Consequences
|
||||
|
||||
`demo:web` 现在每次调用都要付出完整的 `tsc -b && tsdown` 代价，而不再只是 Vite 构建。这是从干净的代码树运行 web 演示所要付出的代价；已经完成构建的调用方可以直接调用 `dsh web`。
|
||||
@@ -1,6 +0,0 @@
|
||||
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write
|
||||
2026-07-23-thinking-row-disclosure-target.md: f698c3cb0b73bf5c65b5d4b5b3f29de3080e0af6
|
||||
2026-07-23-thinking-row-disclosure-target.zh.md: 0fba5c1d8f7beec7300dcd51e118a08d57d0e74f
|
||||
@@ -1,29 +0,0 @@
|
||||
# Agent Note: Thinking rows use one disclosure target
|
||||
|
||||
Status: implemented
|
||||
|
||||
English | [中文](2026-07-23-thinking-row-disclosure-target.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
A collapsed reasoning entry presents `Think` and its one-line reasoning summary as one visual row, but an icon-only disclosure control leaves both visible labels inert. Applying title expansion to every tool row would instead break the generic tool-row contract, where the row opens details and only the leading control expands arguments.
|
||||
|
||||
## Decision
|
||||
|
||||
`ToolRow` exposes the opt-in `expandOnRowClick` policy. `ThinkRow` enables it so the title and reasoning summary form one accessible disclosure target; pointer clicks, Enter, and Space toggle the same component-local expanded state. Tool rows that do not opt in retain row-to-details selection and leading-control argument expansion.
|
||||
|
||||
## Verification
|
||||
|
||||
The component spec pins both Think click targets and the unchanged generic tool-row handoff. The keyless browser fixture loads the real sidebar and conversation bundles, opens an authored reasoning session, clicks the summary and title, and checks the disclosure state and expanded body.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
**Expand every tool row from its title.** Generic tool rows use row clicks for details selection, so sharing this behavior would conflate two controls.
|
||||
|
||||
**Keep icon-only disclosure.** The smallest hit target remains disconnected from the labels that describe the hidden content.
|
||||
|
||||
**Render separate title and summary buttons.** Two controls for one expanded state add duplicate focus stops and ambiguous semantics.
|
||||
|
||||
## Consequences
|
||||
|
||||
Thinking rows gain a larger pointer target and keyboard disclosure semantics without changing other tool interactions. The generic row component carries one optional policy because disclosure ownership differs between reasoning and tool calls.
|
||||
@@ -1,29 +0,0 @@
|
||||
# Agent Note: thinking 行使用单一展开目标
|
||||
|
||||
Status: implemented
|
||||
|
||||
[English](2026-07-23-thinking-row-disclosure-target.md) | 中文
|
||||
|
||||
## 问题
|
||||
|
||||
折叠的推理（reasoning）条目在同一视觉行中呈现 `Think` 和单行推理摘要，但仅图标可展开会让两个可见标签都无法交互。若让所有工具行均可通过标题展开，又会破坏通用工具行的契约：整行负责打开详情，只有前导控件负责展开参数。
|
||||
|
||||
## 决策
|
||||
|
||||
`ToolRow` 提供显式启用的 `expandOnRowClick` 策略。`ThinkRow` 启用该策略，让标题和推理摘要组成单一且无障碍的展开目标；鼠标点击、Enter 和 Space 都切换同一个组件本地展开状态。未启用该策略的工具行仍由整行完成详情选择，由前导控件展开参数。
|
||||
|
||||
## 验证
|
||||
|
||||
组件测试固定两个 Think 点击目标以及未改变的通用工具行交接行为。无密钥浏览器 fixture（测试前置数据）加载真实的侧边栏与会话 bundle，打开包含推理内容的既定会话，点击摘要与标题，并检查展开状态和展开后的正文。
|
||||
|
||||
## 考虑过的替代方案
|
||||
|
||||
**让每个工具行都可通过标题展开。** 通用工具行将整行点击用于详情选择，共享这一行为会混淆两个控件。
|
||||
|
||||
**保留仅图标展开。** 最小的点击目标仍与描述隐藏内容的标签脱节。
|
||||
|
||||
**把标题和摘要分别渲染为按钮。** 两个控件共享一个展开状态，会增加重复的焦点停靠点并产生含糊语义。
|
||||
|
||||
## 后果
|
||||
|
||||
thinking 行获得更大的鼠标点击目标和键盘展开语义，同时不改变其他工具交互。通用行组件承担一个可选策略，因为推理与工具调用的展开所有权不同。
|
||||
@@ -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
|
||||
2026-06-15-code-mode.md: 8e964eeb36e430b58312427e45cf8e4a99582457
|
||||
2026-06-15-code-mode.zh.md: 3de1adfcf287b69ca8307244bde35f286ce4b99d
|
||||
2026-06-15-code-mode.md: 38d1ebdda089f1cfa1c5f3192fa2399b3a00102b
|
||||
2026-06-15-code-mode.zh.md: 2ddccb005b806fee0b1f4d6f79d6473f492a117d
|
||||
|
||||
@@ -40,9 +40,9 @@ This note owns Code Mode's presentation, composition, isolation, and settlement
|
||||
|
||||
### The run_code tool and the dispatch bridge
|
||||
|
||||
Under `'code'` and `'both'` the registry owns `run_code` as a reserved presentation transport with one required parameter, `{ code: string }`. It is represented by a normal `ToolDefinition` for dispatch but stays outside the filterable capability layers, so restrictions cannot accidentally remove Code Mode's only entry point. Calls traverse the complete tool pipeline — `tools/pre-execute` → monotonic guards → `tools/execute` around dispatch → `tools/post-execute` → optional definition-owned `finalizeContent` → immutable `tools/result` notification — exactly like native calls; a permission plugin can inspect the program text before it runs, and final-result observers see the normalized outer outcome. Its `execute(args, exec)`:
|
||||
Under `'code'` and `'both'` the registry owns `run_code` as a reserved presentation transport with two required parameters, `{ code: string; description: string }` (the description labels the call in UIs, the bash precedent). It is represented by a normal `ToolDefinition` for dispatch but stays outside the filterable capability layers, so restrictions cannot accidentally remove Code Mode's only entry point. Calls traverse the complete tool pipeline — `tools/pre-execute` → monotonic guards → `tools/execute` around dispatch → `tools/post-execute` → optional definition-owned `finalizeContent` → immutable `tools/result` notification — exactly like native calls; a permission plugin can inspect the program text before it runs, and final-result observers see the normalized outer outcome. Its `execute(args, exec)`:
|
||||
|
||||
1. **Build bindings.** One run-scoped signal follows outer cancellation and is aborted whenever the run settles. Each visible tool binding snapshots lossless-JSON arguments, waits on the serialization queue, executes with a deterministic call id and the outer token as `parent`, defers returned contexts through the outer execution, and logs `tool/code-dispatch`. Success returns the tool's final canonical JSON value; failure becomes the program-visible `ToolCallError`. Every sub-call retains its own immutable execution identity and traverses the full tool pipeline.
|
||||
1. **Build bindings.** One run-scoped signal follows outer cancellation and is aborted whenever the run settles. Each visible tool binding snapshots lossless-JSON arguments, enters the native-contract dispatch pool (the [live-parallel note](2026-07-26-code-mode-live-parallel-dispatch.md) owns the scheduling design), executes with a deterministic call id and the outer token as `parent`, defers returned contexts through the outer execution, and logs the `tool/code-dispatch-start`/`tool/code-dispatch` pair, the settle side carrying the full rendered result content. Success returns the tool's final canonical JSON value; failure becomes the program-visible `ToolCallError`. Every sub-call retains its own immutable execution identity and traverses the full tool pipeline.
|
||||
2. **Runs the program**: `ctx.codeRuntime.run({ program: args.code, bindings: [{ global: 'tools', functions }], signal: runController.signal })`. The runtime receives the run-scoped signal, not only the caller's outer signal, so any way the outer run settles also aborts work inside the runtime.
|
||||
3. **Settle after quiescence.** When the runtime settles, the bridge aborts outstanding work and drains the dispatch queue before returning. Success returns captured logs and the completion value as canonical output; the registry renders that value into durable `tool/result.content`, which the result card reads directly. A runtime failure becomes `CodeRunFailedError`; backend rejection uses the registry's normal error boundary. Both produce structured error results, and no sub-call can append after `run_code` settles.
|
||||
|
||||
@@ -50,11 +50,11 @@ Under `'code'` and `'both'` the registry owns `run_code` as a reserved presentat
|
||||
|
||||
**Concurrency is serialized.** Each run owns a dispatch queue, so even `Promise.all` executes tool calls in submission order. Settlement abandons queued calls that have not started. Parallelism requires per-tool concurrency-safety metadata.
|
||||
|
||||
**Presentation.** `run_code`'s render intent is decided here per the [render-intent Agent Note](../architecture/2026-07-02-tool-render-intent-union.md): `presentCall` creates a `generic` card with `kind: 'execute'`, the program text as its title, and the same program text as `rawInput`; `run_code` intentionally declares no `presentResult`, so the TUI and host/client runtime (Web) complete that card through their generic raw-content fallback using the final durable `tool/result.content`, including captured logs plus the returned value, failure, or post-policy spill preview. This is not a `terminal` card: that card's semantics are "a shell command in a working directory", which a program is not. See the [result-card completeness note](../bug-fix/2026-07-20-code-mode-result-card-completeness.md).
|
||||
**Presentation.** `run_code`'s render intent is decided here per the [render-intent Agent Note](../architecture/2026-07-02-tool-render-intent-union.md): `presentCall` creates a `generic` card with `kind: 'execute'`, the program text as its title, and the same program text as `rawInput`; `run_code` intentionally declares no `presentResult`, so the TUI and host/client runtime (Web) complete that card through their generic raw-content fallback using the final durable `tool/result.content`, including captured logs plus the returned value, failure, or post-policy spill preview. This is not a `terminal` card: that card's semantics are "a shell command in a working directory", which a program is not. See the [result-card completeness note](../../archived/bug-fix/2026-07-20-code-mode-result-card-completeness.md).
|
||||
|
||||
### Observability: `tool/code-dispatch`
|
||||
|
||||
Each sub-dispatch appends a log-only `tool/code-dispatch` event containing parent and child call ids, tool identity, normalized arguments, and result summary. It remains outside model history but available to persistence and UIs. Appends occur inside the open `run_code` turn. Direct executions without an agent still run but cannot log the event.
|
||||
Each sub-dispatch appends a log-only `tool/code-dispatch-start` event at pool entry and a `tool/code-dispatch` settle event containing parent and child call ids, tool identity, normalized arguments, and the complete rendered `content`/`isError` outcome. It remains outside model history but available to persistence and UIs. Appends occur inside the open `run_code` turn. Direct executions without an agent still run but cannot log the event.
|
||||
|
||||
### The code-runtime seam
|
||||
|
||||
|
||||
@@ -40,9 +40,9 @@ Cloudflare 的 [Code Mode](https://blog.cloudflare.com/code-mode/) 提出了一
|
||||
|
||||
### run_code 工具与分发桥
|
||||
|
||||
在 `'code'` 和 `'both'` 下，注册表拥有 `run_code` 作为保留的呈现传输通道，带一个必需参数 `{ code: string }`。它由一个正常的 `ToolDefinition` 表示以供分发，但位于可过滤的能力层之外，因此限制规则不会意外移除 Code Mode 的唯一入口。调用遍历完整的工具流水线——`tools/pre-execute` → 单调守卫 → `tools/execute` 包裹分发 → `tools/post-execute` → 由定义拥有的可选 `finalizeContent` → 不可变的 `tools/result` 通知——与原生调用完全一致；权限插件可以在程序运行前检查程序文本，最终结果观察者看到的是规范化的外层结果。其 `execute(args, exec)`：
|
||||
在 `'code'` 和 `'both'` 下，注册表拥有 `run_code` 作为保留的呈现传输通道，带两个必需参数 `{ code: string; description: string }`（description 为 UI 标注该调用，沿用 bash 的先例）。它由一个正常的 `ToolDefinition` 表示以供分发，但位于可过滤的能力层之外，因此限制规则不会意外移除 Code Mode 的唯一入口。调用遍历完整的工具流水线——`tools/pre-execute` → 单调守卫 → `tools/execute` 包裹分发 → `tools/post-execute` → 由定义拥有的可选 `finalizeContent` → 不可变的 `tools/result` 通知——与原生调用完全一致；权限插件可以在程序运行前检查程序文本，最终结果观察者看到的是规范化的外层结果。其 `execute(args, exec)`：
|
||||
|
||||
1. **构建绑定。** 一个 run 级别的 signal 跟随外层取消，并在 run 结算时被 abort。每个可见工具绑定都会对无损 JSON 参数创建快照，等待序列化队列，以确定性的 call id 和外层 token 作为 `parent` 执行，通过外层 execution 延后返回的上下文，并记录 `tool/code-dispatch`。成功时返回工具最终的规范 JSON 值；失败则变为程序可见的 `ToolCallError`。每个子调用保留自己不可变的执行标识，并遍历完整的工具流水线。
|
||||
1. **构建绑定。** 一个 run 级别的 signal 跟随外层取消，并在 run 结算时被 abort。每个可见工具绑定都会对无损 JSON 参数创建快照，进入原生契约的分发池（调度设计由[实时并行 Agent Note](2026-07-26-code-mode-live-parallel-dispatch.md) 负责），以确定性的 call id 和外层 token 作为 `parent` 执行，通过外层 execution 延后返回的上下文，并记录 `tool/code-dispatch-start`/`tool/code-dispatch` 事件对，其中结算侧携带完整渲染后的结果内容。成功时返回工具最终的规范 JSON 值；失败则变为程序可见的 `ToolCallError`。每个子调用保留自己不可变的执行标识，并遍历完整的工具流水线。
|
||||
2. **运行程序**：`ctx.codeRuntime.run({ program: args.code, bindings: [{ global: 'tools', functions }], signal: runController.signal })`。运行时接收的是 run 级别的 signal 而非仅调用方的外层 signal，因此外层 run 以任何方式结算都会同时 abort 运行时内部的工作。
|
||||
3. **完全停稳后结算。** 运行时结算后，桥 abort 未完成的工作并排空分发队列后再返回。成功时返回捕获的日志和完成值，将其作为规范输出；注册表再把该值渲染为持久化的 `tool/result.content`，供结果卡片直接读取。运行时失败变为 `CodeRunFailedError`；后端拒绝使用注册表的正常错误边界。两者都产生结构化的错误结果，且 `run_code` 结算后不允许子调用追加。
|
||||
|
||||
@@ -50,11 +50,11 @@ Cloudflare 的 [Code Mode](https://blog.cloudflare.com/code-mode/) 提出了一
|
||||
|
||||
**并发被序列化。** 每次 run 拥有一个分发队列，因此即使 `Promise.all` 也按提交顺序执行工具调用。结算时放弃尚未开始的排队调用。并行化需要每个工具的并发安全元数据。
|
||||
|
||||
**呈现。** `run_code` 的 render intent 按[呈现意图 Agent Note](../architecture/2026-07-02-tool-render-intent-union.md)在此决定：`presentCall` 创建一个 `generic` 卡片，`kind: 'execute'`，以程序文本作为标题，并将同一程序文本作为 `rawInput`；`run_code` 有意不声明 `presentResult`，因此 TUI 和宿主/客户端运行时（Web）会通过通用原始内容回退机制，使用最终持久化的 `tool/result.content` 补全该卡片，其中包括捕获的日志，以及返回值、失败信息或 post-policy 输出落盘预览。这不是 `terminal` 卡片：该卡片的语义是「工作目录中的 shell 命令」，程序不是。参见[结果卡片完整性说明](../bug-fix/2026-07-20-code-mode-result-card-completeness.md)。
|
||||
**呈现。** `run_code` 的 render intent 按[呈现意图 Agent Note](../architecture/2026-07-02-tool-render-intent-union.md)在此决定：`presentCall` 创建一个 `generic` 卡片，`kind: 'execute'`，以程序文本作为标题，并将同一程序文本作为 `rawInput`；`run_code` 有意不声明 `presentResult`，因此 TUI 和宿主/客户端运行时（Web）会通过通用原始内容回退机制，使用最终持久化的 `tool/result.content` 补全该卡片，其中包括捕获的日志，以及返回值、失败信息或 post-policy 输出落盘预览。这不是 `terminal` 卡片：该卡片的语义是「工作目录中的 shell 命令」，程序不是。参见[结果卡片完整性说明](../../archived/bug-fix/2026-07-20-code-mode-result-card-completeness.md)。
|
||||
|
||||
### 可观测性：`tool/code-dispatch`
|
||||
|
||||
每次子分发追加一个仅日志的 `tool/code-dispatch` 事件，包含父子 call id、工具标识、规范化参数和结果摘要。它不进入模型历史，但可供持久化和 UI 使用。追加发生在开放的 `run_code` 轮次内。没有 agent 的直接执行仍然运行，但无法记录该事件。
|
||||
每次子分发在进入分发池时追加一个仅日志的 `tool/code-dispatch-start` 事件，并以一个 `tool/code-dispatch` 结算事件收尾，后者包含父子 call id、工具标识、规范化参数以及完整渲染后的 `content`/`isError` 结果。它不进入模型历史，但可供持久化和 UI 使用。追加发生在开放的 `run_code` 轮次内。没有 agent 的直接执行仍然运行，但无法记录该事件。
|
||||
|
||||
### code-runtime seam
|
||||
|
||||
|
||||
@@ -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
|
||||
2026-07-23-trajectory-step-cell.md: 414c3aac856fb5e60f0e4cf42f8e7b410cdf3413
|
||||
2026-07-23-trajectory-step-cell.zh.md: aa76b422f165ebf6918b3781fdfe38797a34ba51
|
||||
2026-06-24-workspace-context.md: 6acdb6241bcc57250e217cfc8856e8b0598d4622
|
||||
2026-06-24-workspace-context.zh.md: f165d08108931df21697c7895523f10ef816297f
|
||||
@@ -2,6 +2,8 @@
|
||||
|
||||
Status: implemented
|
||||
|
||||
English | [中文](2026-06-24-workspace-context.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
Repository guidance such as `AGENTS.md` belongs in a coding session's effective context so project conventions, build commands, and review rules arrive without repeated user pasting. The stdio and ACP products need the same behavior, isolated by session cwd: a global system-prompt section leaks one workspace's files into another live ACP session.
|
||||
|
||||
@@ -0,0 +1,89 @@
|
||||
# Agent Note: 工作区上下文指令文件
|
||||
|
||||
Status: implemented
|
||||
|
||||
[English](2026-06-24-workspace-context.md) | 中文
|
||||
|
||||
## 问题
|
||||
|
||||
`AGENTS.md` 等仓库指引应当进入编码会话的有效上下文，使项目约定、构建命令和评审规则无需由用户反复粘贴即可生效。stdio 与 ACP（Agent Client Protocol）产品需要具备相同行为，并按会话 cwd 隔离：全局系统提示词章节会把一个工作区的文件泄漏到另一个仍在运行的 ACP 会话中。
|
||||
|
||||
相邻产品形成了值得借鉴的约定，但具体做法各不相同。Codex 原生使用 `AGENTS.md`；Claude Code 使用 `CLAUDE.md`，并采用熟悉的 system-reminder 风格用户上下文；opencode 同时支持这两个名称，每个目录只选一个胜出者，并延迟发现嵌套文件。harness 需要跨工具兼容，同时避免从同一作用域加载重复或互相矛盾的文件。
|
||||
|
||||
生命周期中有两类截然不同的内容。初始适用文件链足够稳定，可以放入请求前缀并受益于提供方前缀缓存。嵌套文件、编辑、候选项切换和移除都发生在会话启动后，应进入持久的仅追加历史，而不是被冻结的前缀。
|
||||
|
||||
## 决策
|
||||
|
||||
该实现在 `packages/context/workspace-context` 中，包（package）名为 `@deepseek-ai/dsh-workspace-context`。它是请求上下文扩展，不是核心服务或文件系统后端。共享 demo 主干与 Host Runtime 根据显式的 `{ maxBytes } | false` 部署选择挂载它；`dsh web` 启用 65,536 字节预算，Host Runtime 的 headless 消费方则禁用它。该插件使用 `agent/session-prefix`、`tools/post-execute` 和可选的 `ctx.fs` 功能。
|
||||
|
||||
插件不会静态注入 `fs`。因此，不带提供方的产品树仍能正常启动；在文件系统提供方出现之前，插件保持无操作。所有生产读取都通过该提供方完成。候选项探测会解析每个路径并对结果执行 stat，因此会跟随最终路径组件的符号链接至其目标：指向普通文件的链接会被加载，缺失路径或非文件目标则确认为不存在。允许仓库拥有的链接跨越信任边界，是对最初不跟随探测方式的刻意反转；[跟随指令符号链接记录](2026-07-21-follow-instruction-symlinks.md)负责说明该决策及其残余风险。会话前缀信号与动态工具执行信号会贯穿解析、元数据探测和流式读取，因此取消不会等待无关的文件系统扫描。解析或 stat 异常归类为不可用：它只跳过该候选项，绝不被解释为已经加载的作用域被删除。
|
||||
|
||||
### 文件名与优先级
|
||||
|
||||
默认的逐目录候选列表是 `['AGENTS.md', 'CLAUDE.md']`。该列表可通过 `instructionFileCandidates` 配置；`AGENTS.md` 是普通的第一候选项，而不是隐藏优先级。一个目录中只加载第一个存在的普通文件候选项。使用默认值时，`AGENTS.md` 是原生文件，`CLAUDE.md` 是兼容性回退。第二个列表 `localInstructionFileCandidates`（默认为 `['AGENTS.local.md', 'CLAUDE.local.md']`）会在同一目录的基础文件后加载叠加式本地覆盖层；[默认本地覆盖层记录](2026-07-21-local-instruction-overlay.md)负责说明该决策。
|
||||
|
||||
候选条目必须是同一目录中的文件名。空条目、`.`／`..`，以及包含 `/` 或 `\` 的条目会被忽略。其他同目录名称可以显式选择加入；规则目录和导入语义不属于本契约。
|
||||
|
||||
用户全局文件固定为 `$DSH_HOME/AGENTS.md`，不受任一候选列表影响，也没有本地覆盖层。`$DSH_HOME` 默认为 `~/.dsh`，与 `~/.codex` 或 `~/.claude` 在 harness 层的 home 角色一致，而不会引入插件专用 home。波浪号展开与默认值位于 `dsh-paths` 中，以便未来的 harness 功能共享同一约定。
|
||||
|
||||
### 基线前缀
|
||||
|
||||
agent loop（智能体循环）实例的第一次请求会让插件通过 `agent/session-prefix` 提供一条 user 角色消息。它先加载用户全局文件，再从 `agent.session.header.cwd` 向上遍历至配置的根标记（默认为 `.git`）以确定项目根目录，随后从根目录至 cwd 的每级目录各加载一个候选项。`.git` 文件与 `.git` 目录都是有效标记，因而能覆盖链接 worktree 和 submodule。找不到标记时，cwd 本身就是根目录。
|
||||
|
||||
插件会在 `await next()` 返回前前置其贡献，因此会话前缀贡献按插件注册顺序出现。在产品主干中，工作区指令的注册先于 skill 目录，所以它排在前面。循环会深度冻结组合后的前缀，将其记录在 `EpochHeader.messagePrefix` 中，并在该实例内逐字复用。它是请求状态，不是 `Session.deriveMessages()` 历史。
|
||||
|
||||
恢复 agent 会创建新的循环实例，并使用当前文件重新组合基线；新的前缀由恢复请求 header 锚定。这样，恢复时可以使用当前基线内容，而无需修改先前实例已经使用过的前缀。
|
||||
|
||||
基线是一条 user 角色的 `<system-reminder>`，包含 `Instructions from: <path>` 章节，以及明确的权威性与优先级说明。这种熟悉的模型可见框架避免引入 harness 专用的 XML 词汇。项目路径相对于根目录；使用默认 home 时，用户全局路径为 `~/.dsh/AGENTS.md`，使用已配置 home 时则为 `$DSH_HOME/AGENTS.md`。文件内容中的字面量 `</system-reminder>` 会被转义。包 README 负责规定当前准确的[提示词形态](../../../../packages/context/workspace-context/README.md#prompt-shape)。
|
||||
|
||||
### 动态发现与刷新
|
||||
|
||||
第一方 `read`、`write` 或 `edit` 调用成功后，`tools/post-execute` 监听器会协调被触及的后代路径链，以及该会话已经知道的每个作用域。新到达的作用域通过 `additionalContexts` 返回，并在下一次请求中使用 `Additional instructions from: <path>` system-reminder。在 Code Mode 下，`run_code` 会把子分发上下文延后至其外层结果，因此同一更新只会在父结果之后追加，而不会在调用中途注入。
|
||||
|
||||
内容编辑会追加 `Updated instructions from: <path>`，说明新内容取代先前内容，并包含当前的完整文件。如果优先级从一个候选项变为另一个，消息还会指出先前路径并说明它不再适用。如果没有候选项保留，插件会追加 `Instructions removed: <path>`，并说明先前加载的指令不再适用。
|
||||
|
||||
动态消息在 `content` 中携带完整的 system-reminder 框架；每个 `context/message` 都作为 user 角色消息逐字抵达模型，核心层不会再添加可选择退出的包装。`context/message.meta` 携带不透明 JSON 状态，该状态会持久化，但绝不会渲染给模型。
|
||||
|
||||
shell 命令不会触发发现。本地 bash 调用会启动全新的 shell，而从任意命令字符串推断已到达路径，需要实现提示词插件并不拥有的 shell 语义。
|
||||
|
||||
### 重复抑制与变更检测
|
||||
|
||||
每个动态工作区上下文事件都会存储带版本的元数据，其形态为 `{ action, scope, path, digest? }`；`digest` 是对已加载内容计算的 SHA-1。模型可见提示词中没有 HTML 注释、隐藏标记，也没有会被解析回状态的标题。
|
||||
|
||||
协调时，插件扫描自身拥有的 `context/message` 事件，并派生每个可见作用域的最新状态。一个简短的逐会话待处理映射只会在不可变的顶层 `tools/result` 证明某个 `additionalContexts` 条目经过所有 post-execute 监听器后仍然保留时开始记录；随后，它覆盖循环将该上下文追加到日志之前的间隔。每个条目记录开启状态的 `{ turn, step }`：如果相同的持久 `context/message` 出现在其序列边界或之后，该条目得到确认并被移除；如果匹配的 `step/end` 先到达，则说明循环丢弃了上下文缓冲区，插件会同时移除待处理条目及其版本缓存快速路径。嵌套的 Code Mode 结果会把变更暂存在父级的不透明执行 token 下，确保一次运行中的重复子分发不会产生重复项；父级结果会回滚这份临时状态，并且只提交外层策略保留的上下文。
|
||||
|
||||
路径和 digest 均未变化时会被抑制。日志中的移除操作是一条墓碑记录，因此重新出现的候选项会成为新的 `set`。恢复操作从持久化元数据继续工作。如果压缩（compaction）从可见表面移除某条指令事件，该状态不再抑制后续加载，这与模型已经无法看见它的事实一致。只有真正纳入字节预算的变更才会进入元数据或待处理状态，因此被省略的文件在之后的触碰中仍有资格加载。
|
||||
|
||||
被冻结的基线会保留一个内存中的 path／digest map 以供比较。后续成功的文件系统触碰会把基线编辑或移除操作追加为动态消息，绝不重写前缀。恢复时重新组合前缀的过程中，插件还会协调可见的动态作用域，因此 agent 离线期间发生的嵌套变更可以在第一次恢复请求前追加更新。
|
||||
|
||||
系统刻意不使用文件监视器。检测发生在下一次成功的结构化文件系统触碰或恢复时的前缀组合。提供方失败不会产生移除；只有该作用域中的全部已配置候选项都成功完成探测后，系统才接受「不存在」这一结论。
|
||||
|
||||
### 字节预算与有界读取
|
||||
|
||||
`maxBytes` 是必填项，分别作用于渲染后的基线或单个动态协调批次；系统不存在隐式或无界的渲染预算。非正数或非有限值会禁用加载。内容超过预算时，系统会先省略较宽泛的文件，再截断最具体的文件。可见的 `Workspace instruction budget ...` 提示会指出被省略和截断的路径与字节数，并且输出绝不超过配置字节数。
|
||||
|
||||
`maxSourceBytes` 是正数的逐文件上限，默认为 1 MiB。loader 会在读取前检查报告的大小，同时仍通过 `streamText()` 消费内容并持续统计 UTF-8 字节数，因此缺失／陈旧的元数据无法迫使其进行无界分配。过大的胜出候选项会被视为不可用，而不是改为同目录中的下一个名称。插件刻意不保留进程级缓存，也绝不保留指令正文。它只为每个有效作用域保存 `{ path, version, digest }`，并将这些状态放在 `WeakMap<Session, Map<scope, state>>` 中：提供方 `FsVersion` 与有效提示词状态同时匹配时跳过读取；版本变化则触发有界读取和 SHA-1 确认。SHA-1 仍是持久化在可见结构化元数据中的跨提供方内容标识；提供方版本只作为内存中的失效快速路径。模型可见变更的缓存转换只有在相应上下文通过完整的工具结果策略链后才会提交；如果该已接受上下文随后与中止步骤一起被丢弃、未能进入日志，缓存转换就会失效。
|
||||
|
||||
## 考虑过的替代方案
|
||||
|
||||
**使用全局 `ctx.systemPrompt.section()`。** 不予采纳，因为同一个 Cordis 上下文可以承载 cwd 不同的多个会话，而仓库所有的文本属于低权威用户上下文，不是最高权威的提供方系统内容。
|
||||
|
||||
**在每次 `agent/pre-step` 时注入基线。** 不予采纳，因为重复注入历史会浪费 token、使重复状态复杂化，并妨碍提供方前缀保持结构稳定。前缀组合提供冻结、已记录且逐实例的基线，动态仅追加消息则负责变更。
|
||||
|
||||
**在一个目录中同时加载 `AGENTS.md` 和 `CLAUDE.md`。** 不予采纳，因为正在迁移的仓库通常会在两个文件中重复指引。按顺序排列的候选项让优先级显式且可配置。
|
||||
|
||||
**解析渲染后的标题或隐藏注释以恢复已加载状态。** 不予采纳，因为指令正文可能包含相同文本，导致无提示的误报。持久化 JSON 元数据提供明确且对模型不可见的状态通道。
|
||||
|
||||
**使用模型总结文件。** 不予采纳，因为指令文件本身已经是经过整理的摘要；再执行一次模型调用既不确定，也可能抹掉边界情况要求。使用带字节预算的确定性全文更简单。
|
||||
|
||||
## 影响
|
||||
|
||||
工作区指引按会话隔离，并由 demo 前端、Web Host 与每一种工具展示模式共享。初始指令受益于稳定的前缀缓存，嵌套与变更内容则保持持久且可回放。通用的 session／agent 上下文契约通过 prompt-submit 与工具执行后的 `additionalContexts` 数组携带 JSON 元数据，而不会把条目展平。
|
||||
|
||||
仓库文本仍是不受信任的输入。低权威 user 角色框架、显式优先级说明和分隔符转义可以降低风险，但无法消除提示词注入。跟随候选符号链接到目标，会把该接口扩大至树外内容；因此，把 `ctx.fs` 限制在可信根目录内的权限与沙箱层才是真正的边界，它们让系统把工作区文件当作数据而不是权威（[跟随指令符号链接记录](2026-07-21-follow-instruction-symlinks.md)负责说明残余风险）。
|
||||
|
||||
系统由事件驱动，而不是文件监视器驱动。除非文件系统变更通过结构化工具完成，否则编辑不会在确切的文件系统变更时刻可见；外部文件变更会在下一次成功的结构化触碰或恢复时被发现。这使设计保持确定性并且与提供方无关。
|
||||
|
||||
## 延后事项
|
||||
|
||||
从 bash 派生路径报告、递归启动扫描、文件监视器、小写默认名称、`.claude/CLAUDE.md`、`.claude/rules/*.md`、导入指令、ACP `additionalDirectories`、信任确认和模型生成摘要均延后处理。项目目录中的 `.local.` 覆盖层现已默认加载（[默认本地覆盖层记录](2026-07-21-local-instruction-overlay.md)负责说明该决策）；用户全局覆盖层、目录规则系统和导入仍需要各自的优先级与信任设计。
|
||||
@@ -1,31 +0,0 @@
|
||||
# Agent Note: Subagent lifecycle enrichment — lastAssistantMessage (observe-only)
|
||||
|
||||
Status: implemented
|
||||
|
||||
English | [中文](2026-06-30-subagent-observe-enrich.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
The hooks subsystem ([interception seams Agent Note](2026-06-30-interception-seams.md)) lets a plugin observe and gate the agent at lifecycle points. Claude Code and Codex both expose **SubagentStart / SubagentStop** hooks, and CC's carry the subagent's final message. The harness already emits `subagent/start` and `subagent/end` lifecycle events ([the subagent capability-seam](2026-06-21-subagent-capability-seam.md)), but their payloads were minimal (`provider`, `id`, and on end `stopReason`) — not enough for a hooks bridge to report WHAT a subagent produced without separately reaching for the live run.
|
||||
|
||||
This Agent Note enriches the end payload. It is deliberately **observe-only**: no control-flow change and no waterfall. A run-affecting subagent-stop decision (continuation, injection that changes the run) is a separate, larger redesign and stays out of scope.
|
||||
|
||||
## Decision
|
||||
|
||||
**Add `lastAssistantMessage` — the child's final output — to `SubagentRunEndInfo`.** On the settle path it is the readonly typed `SubagentResult.output`, so an observer sees what the child produced without holding the run. On an infrastructure rejection where no `SubagentResult` exists, it is absent and the event reports `stopReason: 'error'`. Providers and listeners are trusted same-process collaborators and honor the borrowed immutable payload contract.
|
||||
|
||||
Both events stay plain **`emit`s**. Async `SubagentService.start()` attaches result observation to the ready provider run, emits `subagent/start`, and then returns the run; an in-process listener can therefore reach the published child via `ctx.agents.get(info.id)`, while a remote provider need not have a local registry entry. A rejected provider start emits neither event. The callbacks remain observe-only and per-listener containment keeps one bad subscriber from stranding a live run or starving later listeners.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
**An `agentType` subagent-kind label** (the harness analogue of CC's `subagent_type`) on the request + both lifecycle payloads — an earlier draft shipped it; dropped in review because it is a Claude-Code concept that does not fit our own seam (nothing here interprets it, and the only consumer was a CC-dialect bridge). The CC bridge instead feeds Claude Code's own default matcher value `"general-purpose"` for its SubagentStart/Stop `agent_type` matcher, so this Agent Note ships ONE enrichment: `lastAssistantMessage`.
|
||||
|
||||
**A control-flow `subagent/end`** — deferred; see below.
|
||||
|
||||
## Why observe-only, and what is deferred
|
||||
|
||||
A control-flow `subagent/end` (an awaited waterfall returning a stop/continue decision, like the other interception seams) would require: reshaping `subagent/end` from emit to waterfall, restructuring `SubagentService.start` to await listeners before settling, and implementing the `resume` capability in the in-process provider so a "continue" can actually re-run the child. That belongs to the background/steering subagent redesign the [capability-seam Agent Note](2026-06-21-subagent-capability-seam.md) already defers (the same redesign that unifies long-running-tool handling across subagents and bash). This Agent Note ships the observe-only enrichment a hooks bridge needs today; `FIXME(subagent-continuation)` / `TODO` anchors mark where the control-flow version would land if and when that redesign happens.
|
||||
|
||||
## Consequences
|
||||
|
||||
A hooks bridge (or a native plugin) can now forward the child's `lastAssistantMessage` to a SubagentStop handler by subscribing to the existing emits — no new control-flow surface. The vocabulary addition is documented in [docs/core-data-structures/subagent.md](../../../../docs/core-data-structures/subagent.md) (the events prose) and the two subagent READMEs; the catalog is regenerated. No production behavior changes — the events fire exactly as before, with one more (optional) field on the end payload — so no snapshot or e2e change is needed.
|
||||
@@ -1,31 +0,0 @@
|
||||
# Agent Note: Subagent 生命周期丰富化——lastAssistantMessage（仅观察）
|
||||
|
||||
Status: implemented
|
||||
|
||||
[English](2026-06-30-subagent-observe-enrich.md) | 中文
|
||||
|
||||
## 问题
|
||||
|
||||
钩子子系统（[拦截 seam Agent Note](2026-06-30-interception-seams.md)）允许插件在生命周期节点观察和拦截 agent（智能体）。Claude Code 和 Codex 都暴露了 **SubagentStart / SubagentStop** 钩子，且 CC 的钩子携带 subagent 的最终消息。harness 已经发出 `subagent/start` 和 `subagent/end` 生命周期事件（[subagent 能力 seam](2026-06-21-subagent-capability-seam.md)），但其载荷极为精简（`provider`、`id`，以及 end 时的 `stopReason`），不足以让钩子桥接层在不单独访问活跃 run 的情况下报告 subagent 产出了什么。
|
||||
|
||||
本 Agent Note 丰富 end 载荷。它刻意限定为**仅观察**：不改变控制流，不引入 waterfall（瀑布式事件）。影响 run 的 subagent-stop 决策（续行、改变 run 的注入）属于另一个更大的重设计，不在本 Agent Note 范围内。
|
||||
|
||||
## 决策
|
||||
|
||||
**在 `SubagentRunEndInfo` 中添加 `lastAssistantMessage`——子 agent 的最终输出。** 在正常结束路径上，它是只读的类型化 `SubagentResult.output`，观察者无需持有 run 即可看到子 agent 产出了什么。在基础设施拒绝（不存在 `SubagentResult`）的情况下，该字段缺失，事件报告 `stopReason: 'error'`。提供方与监听方是受信任的同进程协作者，遵守借用不可变载荷的契约。
|
||||
|
||||
两个事件仍为普通 **`emit`**。异步的 `SubagentService.start()` 将结果观察附加到就绪的提供方 run 上，发出 `subagent/start`，然后返回该 run；进程内监听方因此可以通过 `ctx.agents.get(info.id)` 访问已发布的子 agent，而远程提供方无需在本地注册表中有对应条目。提供方启动被拒绝时不发出任何事件。回调保持仅观察，且逐监听方隔离确保一个异常订阅者不会阻塞活跃 run 或饿死后续监听方。
|
||||
|
||||
## 曾考虑的替代方案
|
||||
|
||||
**`agentType` subagent 类别标签**（CC 的 `subagent_type` 在 harness 中的对应物），放在请求与两个生命周期载荷上。早期草案曾包含它；评审中移除，因为它是 Claude Code 的概念，不适合我们自己的 seam（此处没有任何逻辑解释它，唯一消费方是 CC 方言桥接层）。CC 桥接层改为直接为其 SubagentStart/Stop 的 `agent_type` matcher 填入 Claude Code 自身的默认值 `"general-purpose"`，因此本 Agent Note 只交付**一项**丰富化：`lastAssistantMessage`。
|
||||
|
||||
**控制流式 `subagent/end`**：推迟；见下文。
|
||||
|
||||
## 为何仅观察，以及推迟了什么
|
||||
|
||||
控制流式 `subagent/end`（一个被 await 的 waterfall，返回停止/继续决策，与其他拦截 seam 一致）需要：将 `subagent/end` 从 emit 改为 waterfall、重构 `SubagentService.start` 使其在结算前 await 监听方、在进程内提供方中实现 `resume` 能力以便「继续」能真正重新运行子 agent。这属于[能力 seam Agent Note](2026-06-21-subagent-capability-seam.md) 已推迟的后台/steering（中途引导）subagent 重设计（同一个重设计还将统一 subagent 与 bash 之间的长时间运行工具处理）。本 Agent Note 交付钩子桥接层当前所需的仅观察丰富化；`FIXME(subagent-continuation)` / `TODO` 锚点标记了控制流版本在重设计发生时的落点。
|
||||
|
||||
## 后果
|
||||
|
||||
钩子桥接层（或原生插件）现在可以通过订阅既有 emit 将子 agent 的 `lastAssistantMessage` 转发给 SubagentStop 处理器，无需新的控制流接口。词汇新增记录在 [docs/core-data-structures/subagent.md](../../../../docs/core-data-structures/subagent.md)（事件行文部分）与两个 subagent README 中；catalog 已重新生成。生产行为无变化——事件触发方式与之前完全一致，end 载荷上多了一个可选字段——因此无需更新快照或 e2e 测试。
|
||||
@@ -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
|
||||
2026-07-07-session-prefix.md: 322413f541706244a8a9a9113c0b79693fe54ccd
|
||||
2026-07-07-session-prefix.zh.md: 710cfbd2656d132640d39b1d62374ef2d16be612
|
||||
2026-07-07-session-prefix.md: 75113952fc5f3df8da1580d42ed2a385b6135fe8
|
||||
2026-07-07-session-prefix.zh.md: e38bf09298296203b275d6d66a62ef17be7c045d
|
||||
|
||||
@@ -24,7 +24,7 @@ Because composition runs before the boundary snapshot, a composing listener's se
|
||||
|
||||
## Testing
|
||||
|
||||
[Interception tests](../../../../packages/core/agent-loop/tests/interception.spec.ts) pin compose-once reuse without changed headers, prepend order, empty-prefix omission, immutability, composition before pre-step, and the prefix on the routed header; [cancellation tests](../../../../packages/core/agent-loop/tests/cancel.spec.ts) pin discard and recomposition. Session, invariant, token-meter, and compaction tests cover header round trips, request reconstruction, and durable prefix-aware pressure accounting. Snapshot normalization preserves prefix counts, while the [pinned-header scenario](../testing/2026-07-06-pin-request-header-content-in-one-scenario.md) owns content and the default example remains prefix-free. The provider-independent seam needs no dedicated e2e; the with-key [request-cache e2e](../../../../packages/core/agent-loop/tests/request-cache.e2e.ts) covers its cache economics.
|
||||
[Interception tests](../../../../packages/core/agent-loop/tests/interception.spec.ts) pin compose-once reuse without changed headers, prepend order, empty-prefix omission, immutability, composition before pre-step, and the prefix on the routed header; [cancellation tests](../../../../packages/core/agent-loop/tests/cancel.spec.ts) pin discard and recomposition. Session, invariant, token-meter, and compaction tests cover header round trips, request reconstruction, and durable prefix-aware pressure accounting. Snapshot normalization preserves prefix counts, while the [pinned-header scenario](../../archived/testing/2026-07-06-pin-request-header-content-in-one-scenario.md) owns content and the default example remains prefix-free. The provider-independent seam needs no dedicated e2e; the with-key [request-cache e2e](../../../../packages/core/agent-loop/tests/request-cache.e2e.ts) covers its cache economics.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
|
||||
@@ -24,7 +24,7 @@ Status: implemented
|
||||
|
||||
## 测试
|
||||
|
||||
[拦截测试](../../../../packages/core/agent-loop/tests/interception.spec.ts)固定了以下行为：没有变更 header 时的组合一次复用、前置插入顺序、空前缀省略、不可变性、组合在步骤前检查点之前完成，以及已路由 header 上的前缀；[取消测试](../../../../packages/core/agent-loop/tests/cancel.spec.ts)固定了丢弃与重新组合。Session、不变式、token-meter 和压缩测试覆盖 header 往返、请求重建与持久前缀感知的压力核算。快照归一化保留前缀计数，[固定 header 场景](../testing/2026-07-06-pin-request-header-content-in-one-scenario.md)拥有内容，默认示例保持无前缀。与提供方无关的 seam 无需专门 e2e；带密钥的 [request-cache e2e](../../../../packages/core/agent-loop/tests/request-cache.e2e.ts) 覆盖了其缓存经济性。
|
||||
[拦截测试](../../../../packages/core/agent-loop/tests/interception.spec.ts)固定了以下行为：没有变更 header 时的组合一次复用、前置插入顺序、空前缀省略、不可变性、组合在步骤前检查点之前完成，以及已路由 header 上的前缀；[取消测试](../../../../packages/core/agent-loop/tests/cancel.spec.ts)固定了丢弃与重新组合。Session、不变式、token-meter 和压缩测试覆盖 header 往返、请求重建与持久前缀感知的压力核算。快照归一化保留前缀计数，[固定 header 场景](../../archived/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)拥有内容，默认示例保持无前缀。与提供方无关的 seam 无需专门 e2e；带密钥的 [request-cache e2e](../../../../packages/core/agent-loop/tests/request-cache.e2e.ts) 覆盖了其缓存经济性。
|
||||
|
||||
## 曾考虑的替代方案
|
||||
|
||||
|
||||
@@ -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
|
||||
2026-07-21-tui-footer-cache-hit-rate.md: aaee8ed31ff8f20370f490d3ce27c8705cda3e16
|
||||
2026-07-21-tui-footer-cache-hit-rate.zh.md: 67a7aa474d98878a5bc0bc0a76a8c2ccad004e9b
|
||||
2026-07-08-background-subagent-tasks.md: 12b34f2a28cfa311a48904cd5396ec16d9123641
|
||||
2026-07-08-background-subagent-tasks.zh.md: 58f035a14d55bc0b4e7f670111909074c3f53b2b
|
||||
@@ -2,6 +2,8 @@
|
||||
|
||||
Status: implemented
|
||||
|
||||
English | [中文](2026-07-08-background-subagent-tasks.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
The [subagent seam](2026-06-21-subagent-capability-seam.md) returns a `SubagentRun`, but the model-facing tool originally collected every run synchronously. Independent, slow delegations therefore held the parent call open or ran serially.
|
||||
|
||||
@@ -0,0 +1,64 @@
|
||||
# Agent Note: 后台 subagent 任务
|
||||
|
||||
Status: implemented
|
||||
|
||||
[English](2026-07-08-background-subagent-tasks.md) | 中文
|
||||
|
||||
## 问题
|
||||
|
||||
[subagent seam](2026-06-21-subagent-capability-seam.md) 会返回 `SubagentRun`，但原先面向模型的工具会同步收集每一次运行。因此，各自独立的慢速委派要么一直占用父调用，要么按串行方式运行。
|
||||
|
||||
subagent 需要与其他长时间运行的工具相同的启动、收集、列出、停止、归属、通知和清理行为，但不应采用进程流语义。子会话仍是详细记录；父级只需最终答案和任务状态。后台子级的存活时间还会超过启动它的工具调用，因此必须明确其取消和拥有者资源释放契约。
|
||||
|
||||
## 决策
|
||||
|
||||
每个 `dsh-tool-subagent` 实例都可以公开 `run_in_background`，由 `enableRunInBackground` 控制，且默认启用。禁用该功能的实例不包含此参数，并会在执行时拒绝强制传入的后台参数。提供方选择仍属于部署配置，因此一个实例仍然只为一个提供方注册一个名称可区分的工具。
|
||||
|
||||
后台 subagent 使用[通用后台任务运行时](../architecture/2026-06-20-generic-long-running-tool-runtime.md)。`task_output`、`task_list` 和 `task_kill` 负责收集、列出、取消、完成通知和提示词引导；系统不提供 subagent 专用的配套工具。
|
||||
|
||||
前台调用保留其同步契约：等待提供方启动和 `run.result`；仅当状态为 `completed` 时返回最终文本；将其他终止原因映射为出错的工具结果；并且始终在返回前释放该运行。
|
||||
|
||||
对于后台调用，工具会验证父级，并在调用 `ctx.tasks.start()` 前拒绝已中止的执行信号。任务运行时会在调用生产者启动器前，预检控制接口和拥有者清理。该启动器创建独立的 `AbortController` 并启动 `ctx.subagents.start()`；返回 id 之后，工具调用的信号不再拥有该子级。
|
||||
|
||||
任务注册按以下方式映射 subagent seam：
|
||||
|
||||
- `kind` 为 `subagent`，`label` 为模型提供的描述，`owner` 为父 agent（智能体）。
|
||||
- `cancel(reason?)` 中止任务自有的控制器。同一个信号同时覆盖尚未完成的提供方启动和已就绪的子级。
|
||||
- `done` 等待提供方启动、子级结果和 `run.dispose()`。已完成的运行返回最终文本，已中止的运行变为 `killed`，其他停止原因变为 `failed`。启动、结果和资源释放失败会转换为失败结果，而不是被拒绝的任务 Promise。
|
||||
- `readOutput` 不存在。任务存活期间，`task_output` 只返回状态；结算后，它以幂等方式返回最终输出。中间的子级活动仍保留在子会话中。
|
||||
|
||||
## 生命周期
|
||||
|
||||
后台 subagent 归属于其父 agent，不会在拥有者关闭后持久存续。任务运行时将清理附加到对应拥有者的确切作用域。agent 资源释放会取消任务，并在 `AgentHandle.dispose()` 完成前等待启动回滚或子级资源释放，避免泄漏子 agent 和会话。
|
||||
|
||||
完成通知会发送给启动时捕获的确切拥有者。如果拥有者清理过程已经释放了注入目标，该通知将被丢弃；生命周期保证是清理，而不是通知。
|
||||
|
||||
## 模型引导
|
||||
|
||||
通用任务提示词教会模型一套共享的做法：保留 id；继续独立工作，而不是忙等轮询；在回答前收集相关任务；终止无关工作。subagent schema 只补充说明：后台模式返回 task id，且 `task_output` 用于收集结果。无论模型是否遵循提示词，授权和拥有者清理都会强制执行运行时边界。
|
||||
|
||||
## 备选方案
|
||||
|
||||
### subagent 专用的等待、输出和停止工具
|
||||
|
||||
能力专用工具会重复任务协议，再教一套收集与停止习惯，并增加多个提供方实例的复杂度。通用运行时在不改变工具「每个实例对应一个提供方」形态的前提下，提供了所需行为。
|
||||
|
||||
### 在拥有者关闭后存续
|
||||
|
||||
该方案需要持久化的任务状态、子会话恢复、延迟结果交付通道，以及对被遗弃拥有者的处理策略。以拥有者为作用域的清理为进程内工作界定了明确生命周期。持久作业需要单独设计。
|
||||
|
||||
### 隔离客户端不做拥有者检查
|
||||
|
||||
agent 和日志可能以会话为作用域，但任务注册表和可预测 id 属于运行时全局范围。因此，通用拥有者防线同样适用于 subagent 和所有其他生产者。
|
||||
|
||||
### 增量子 transcript 输出
|
||||
|
||||
将子级历史以流式方式写入父级，会模糊日志边界，并使提供方行为分化。此接口只公开最终输出；更丰富的观察应由会话或 UI 工具承担。
|
||||
|
||||
## 测试
|
||||
|
||||
单元测试覆盖固定了停止原因映射、在报告前释放资源、启动与结果失败、对预中止的拒绝、从启动调用信号分离、在提供方就绪前后取消、通过真实任务工具收集、无控制接口的预检防线、运行时缺失失败，以及每实例 schema 开关。快照覆盖固定了面向模型的 schema。
|
||||
|
||||
## 影响
|
||||
|
||||
父级可以并行分派慢速委派任务，并通过与 bash 共用的任务控制来收集结果。子级工作不再占用启动它的工具调用，但在收集、终止或拥有者释放之前可以继续消耗资源。提示词引导鼓励收集；拥有者清理则提供硬性生命周期边界。需要同步委派的部署可以按工具实例禁用后台模式。
|
||||
@@ -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
|
||||
2026-07-22-collapsed-sidebar-control-rail.md: 940fcabf126941cc0e411b01c337e45831e442aa
|
||||
2026-07-22-collapsed-sidebar-control-rail.zh.md: 70ace36fafcb28aa714000262e31c8555d394854
|
||||
2026-07-09-bash-backed-grep-glob-discovery.md: 9c25afb44885ca2519c5d74a3d721b34fe3561de
|
||||
2026-07-09-bash-backed-grep-glob-discovery.zh.md: d0dee8e49e0a500c87afbd59423fb65416c1dcc8
|
||||
@@ -2,6 +2,8 @@
|
||||
|
||||
Status: implemented
|
||||
|
||||
English | [中文](2026-07-09-bash-backed-grep-glob-discovery.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
The harness needs model-facing `glob` and `grep` tools, but making them `ctx.fs` provider methods turns a local product convenience into a universal filesystem backend contract. Local workspace discovery is naturally a process-backed `rg` workflow; remote or virtual filesystem backends may expose their own search API, may not share a local `ripgrep` view, or may not support discovery at all. The v1 should not require every filesystem backend to implement search before the file read/write/edit seam has proven that need.
|
||||
|
||||
@@ -0,0 +1,170 @@
|
||||
# Agent Note: 由 Bash 支持的 grep 与 glob 发现工具
|
||||
|
||||
Status: implemented
|
||||
|
||||
[English](2026-07-09-bash-backed-grep-glob-discovery.md) | 中文
|
||||
|
||||
## 问题
|
||||
|
||||
harness 需要面向模型的 `glob` 和 `grep` 工具，但如果将它们实现为 `ctx.fs` 提供方的方法，就会把本地产品便利功能变成所有文件系统后端都必须实现的契约。本地工作区发现天然适合由进程支持的 `rg` 工作流；远程或虚拟文件系统后端可能公开自己的搜索 API，可能无法共享本地 `ripgrep` 视图，也可能完全不支持发现。文件读取／写入／编辑 seam 尚未证明此需求前，v1 不应要求每个文件系统后端都实现搜索。
|
||||
|
||||
搜索输出还受到两层不同的预算约束。工具需要足够多的原始 `rg` 输出，才能计算稳定的逻辑结果；模型则只能收到有界预览，并在格式化结果超出内联预算时获得恢复路径。通用落盘策略只能看到最终工具结果，因此无法恢复搜索工具已经省略的匹配项。搜索工具必须自行负责保留，并尽力落盘格式化结果。
|
||||
|
||||
## 决策
|
||||
|
||||
`glob` 和 `grep` 是 `@deepseek-ai/dsh-tool-fs-search` 中的条件式面向模型工具，由 bash seam 支持，不会成为新的 `ctx.fs` 提供方方法。加载插件时，该包（package）执行 `command -v rg >/dev/null 2>&1`：先通过 `ctx.bash.resolve(request)` 解析请求，再通过 `ctx.bash.run(spec)` 运行；如果命令以非零状态退出，该包会记录警告，并且既不注册工具，也不注册提示词章节。如果探针无法启动、超时、中止、被终止，或没有产生退出码，插件加载会明确失败，因为这意味着 bash 执行器损坏，而不是可选二进制文件缺失。注册后，执行流程同样依次调用 `ctx.bash.resolve(request)` 与 `ctx.bash.run(spec)`，并使用工具组装的固定 `rg` 命令模板。工具层负责 schema、参数验证、shell 引用、结果解析、结果格式化、保留、格式化结果落盘交接，以及超时声明。bash 执行器负责请求默认值解析与上限控制、子进程执行、进程组终止、环境清理、原始输出捕获，以及在本地、沙箱或远程 bash 实现之间替换后端。
|
||||
|
||||
这些工具不使用 `ctx.bash.start()`，也不创建模型可见的后台任务。从 agent loop（智能体循环）的视角看，它们是普通前台工具：只有当 `rg` 命令退出、超时、中止或失败后，工具调用才返回。`defineTool({ timeoutMs })` 声明协作式工具调用预算，`@deepseek-ai/dsh-timeout-policy` 通过 `exec.signal` 强制执行；工具会在 `resolve()`／`run()` 前将该信号转发给 bash 请求。bash 后端自身的超时仍作为第二层安全上限；先触发的中止生效。
|
||||
|
||||
这些工具使 `path` 与 Claude Code 的搜索工具保持一致，但将解析绑定到 bash workdir，而不是 `ctx.fs`。工具从 `exec.agent?.session.header.cwd` 派生 bash 请求 workdir，与 `dsh-tool-bash` 和 `dsh-tool-fs` 一致；如果会话没有 cwd，它会省略 `request.workdir`，由 bash 实现通过 `resolve()` 应用其配置的 cwd 或进程 cwd。对于 `grep`，`path` 是可选的 ripgrep 目标，可以是文件或目录；省略时使用已解析的 bash workdir。对于 `glob`，`path` 是可选的目录搜索根；省略时同样使用已解析的 bash workdir。相对 `path` 值基于该 workdir 解析。只要可行，返回路径就会显示为相对于已解析 bash workdir 的形式；只有在共置部署中，bash workdir 与文件系统 `read` 根指向同一个工作区时，这些路径才保证可以继续读取。v1 会记录这项部署要求，但不执行跨服务运行时验证。在形成共享工作区／根契约或提供方专用搜索后端之前，远程或虚拟文件系统搜索保持暂缓。
|
||||
|
||||
该包不注入 `fs`，而是注入 `tools`、`systemPrompt` 和 `bash`；它有意读取 `spillStore` 时使用 `ctx.get('spillStore')`，而不使用静态注入，因为格式化结果落盘是可选功能。现有 `@deepseek-ai/dsh-tool-fs` 部署若只需要 `read`／`write`／`edit`，则无需加载 bash。加载搜索功能的部署则必须让 bash 执行器环境可以使用 `rg`，这些工具才会进入模型可见 schema。
|
||||
|
||||
### 包结构
|
||||
|
||||
v1 包保持精简。`@deepseek-ai/dsh-tool-fs-search` 内部的源代码布局如下：
|
||||
|
||||
```text
|
||||
src/index.ts
|
||||
src/glob.ts
|
||||
src/grep.ts
|
||||
src/search-core.ts
|
||||
src/shell-quote.ts
|
||||
```
|
||||
|
||||
`glob.ts` 和 `grep.ts` 各自负责参数验证、命令构造、结果解析、格式化和注册。`shell-quote.ts` 是一个共享辅助模块，因为 shell 引用是两个工具都必须经过的安全边界；`search-core.ts` 是另一个共享模块（实现时对原四文件方案所作的修订）：`SEARCH_*` 错误词汇、bash 运行与原始输出获取、格式化结果落盘交接，以及 workdir 相对显示，在两个工具中完全相同。若在每个工具中重复这套精细管道，正是对称性约定所指出的漏提取问题。命令构造器禁止自行拼凑引用，也不能把未经引用、由模型控制的值直接连接到 shell 命令中。
|
||||
|
||||
### Schema 与配置
|
||||
|
||||
`glob` 公开精简的发现形状：
|
||||
|
||||
```ts
|
||||
interface GlobArgs {
|
||||
pattern: string
|
||||
path?: string
|
||||
}
|
||||
```
|
||||
|
||||
`grep` 公开 OpenCode 风格的最小形状：
|
||||
|
||||
```ts
|
||||
interface GrepArgs {
|
||||
pattern: string
|
||||
path?: string
|
||||
include?: string
|
||||
}
|
||||
```
|
||||
|
||||
常规预算不会进入面向模型的 schema。`@deepseek-ai/dsh-tool-fs-search` 拥有以下带默认值并经过验证的配置字段：
|
||||
|
||||
| 字段 | 默认值 | 作用 |
|
||||
|---|---:|---|
|
||||
| `globMaxResults` | `100` | 内联保留的最大路径数；与 Claude Code 的默认 `GlobTool` 结果上限一致。 |
|
||||
| `grepMaxMatches` | `250` | 内联保留的最大扁平匹配数；与 Claude Code 的默认 `GrepTool` `head_limit` 一致。 |
|
||||
| `grepMaxLineBytes` | `2000` | 每条匹配行预览保留的最大字节数，通过 `TextRetainer({ kind: 'head', maxBytes: grepMaxLineBytes })` 应用。 |
|
||||
| `rawOutputMaxBytes` | `20000000` | 工具会解析的完整原始 `rg` stdout 最大字节数；与 Claude Code 的 ripgrep 原始缓冲区一致。 |
|
||||
| `timeoutMs` | `30000` | 附加到两个工具定义并由 `@deepseek-ai/dsh-timeout-policy` 强制执行的工具调用超时。 |
|
||||
|
||||
`globMaxResults` 和 `grepMaxMatches` 使用 `ItemRetainer({ kind: 'head' })`。`grepMaxLineBytes` 针对每条匹配行使用 `TextRetainer({ kind: 'head', maxBytes: grepMaxLineBytes })`，使预览截断保留 UTF-8 边界。这遵循[工具结果保留库](../architecture/2026-07-06-tool-result-retention-library.md)对发现条目的映射：收集完整结果，在内联结果中保留头部条目，并将路径映射、分组和逐行预览放在保留器外部。v1 的 `grep` 不公开 `case_insensitive`、`head_limit`、`offset`、`count`、多行、上下文行、输出模式或文件类型过滤器。模型如需周边上下文，可使用 `read` 读取匹配文件；如需后续结果，则遵循返回的落盘定位符所给出的检索提示。
|
||||
|
||||
Claude Code 的数值只是两层预算的参考点，并非面向模型 schema 的先例。其专用搜索工具会缓冲最多 20 MB 的原始 ripgrep 输出用于内部处理；在非 WSL 平台上使用 20 秒 ripgrep 超时，在 WSL 上使用 60 秒，之后才在模型看到结果前应用搜索专用上限：`GrepTool` 默认 `head_limit = 250`，并持久化超过 20,000 个字符的格式化结果；`GlobTool` 默认最多 100 条路径，并持久化超过 100,000 个字符的格式化结果。此 Agent Note 采用同样的原始缓冲区和内联数量默认值，将默认搜索超时设为 30 秒，并通过本 harness 的 `ctx.spillStore.saveText()` 路径恢复格式化结果。
|
||||
|
||||
`path` 字段沿用与 Claude Code 相同的区分方式：`grep.path` 是文件或目录形式的 ripgrep 目标，`glob.path` 则是目录搜索根。v1 不为这些工具公开单独的 cwd／workdir 参数。
|
||||
|
||||
`include` 是一个正向 glob 过滤器，不是列表，也不是排除语法。系统会预先拒绝逗号分隔或取反的 include 模式，并返回结构化参数错误。shell 命令中使用的每个模型控制值，包括 `pattern`、`path` 和 `include`，都必须经过包私有的 shell 引用辅助模块。
|
||||
|
||||
### 执行
|
||||
|
||||
`glob` 构建固定的 `rg --files` 命令，并以解析后的目录搜索根为根（提供 `path` 时使用该值，否则使用 bash workdir）：`rg --files --glob <pattern> --sort=modified --no-ignore --hidden`，另加针对 `.git`、`.svn`、`.hg`、`.bzr`、`.jj` 和 `.sl` 的 VCS 元数据排除项。这样既与 Claude Code 的隐藏／忽略文件发现和修改时间排序保持一致，也避免宽泛搜索包含 VCS 内部文件。工具逐行解析路径，只要可行就将结果映射为相对于 bash workdir 的路径，将每条路径推入 `ItemRetainer({ kind: 'head', maxItems: globMaxResults })`；当保留结果达到上限时，它会格式化完整的已排序路径列表，作为落盘产物。
|
||||
|
||||
`grep` 构建固定的逐行 `rg --json` 命令，作用于所提供的文件／目录目标（提供 `path` 时使用该值，否则使用 bash workdir），从而无需按冒号拆分，就能解析文件路径、行号和行文本。它消费 `match` 记录，将格式错误的 JSON 或匹配记录视为 `SEARCH_FAILED`；只要可行，就将结果路径映射为相对于 bash workdir 的路径；通过 `grepMaxLineBytes` 应用逐行预览保留，将每个匹配推入 `ItemRetainer({ kind: 'head', maxItems: grepMaxMatches })`，然后只按文件分组内联输出中保留的预览匹配。落盘产物保存完整的格式化匹配列表，而不是只保存省略的尾部，因此检索提示指向模型已经看到的同一逻辑结果。
|
||||
|
||||
原始 `rg` stdout 是内部传输细节。工具请求 `stdoutMaxBytes: rawOutputMaxBytes`，并通过 `ctx.bash.resolve()` 解析；只有当执行器在该上限内返回未截断的 stdout 时，工具才解析 `stdout.text`。如果 stdout 超过 `rawOutputMaxBytes`，或者执行器仍返回 `stdout.truncated`，工具会以明确的搜索错误失败，要求模型缩小 `pattern`、`path` 或 `include`。工具绝不向模型公开原始 `rg` 输出或 bash 原始落盘路径。
|
||||
|
||||
只有 stdout 是解析源。对于无效模式、注册后运行时 `rg` 消失，以及搜索失败，stderr 作为诊断文本；如果 bash 截断 stderr，工具会使用保留的 stderr 尾部并附加截断说明，不会读取 `stderr.spillPath`。
|
||||
|
||||
如果 `ctx.bash.run()` 因工具超时或调用方取消触发而报告 `aborted`，工具会返回结构化失败，而不是假装没有匹配项。如果 bash 自身的超时先触发，工具同样会以明确的超时消息失败。非零 ripgrep 退出语义由工具负责：退出码 0 表示存在匹配并成功；退出码 1 表示没有匹配但成功；无效模式、运行时 `rg` 消失或无法访问搜索 workdir 则表示失败。
|
||||
|
||||
搜索失败使用包自有的 `HarnessError` 子类与 `SEARCH_*` 代码，而不使用 `FsErrorCode`，因为这些工具不是 `ctx.fs` 提供方操作。v1 的词汇包括 `SEARCH_INVALID_PATTERN`、`SEARCH_FAILED`、`SEARCH_RAW_OUTPUT_OVERFLOW` 和 `SEARCH_ABORTED`。缺少必填字段、空字符串或不支持的取反／列表式 `include` 值等模型参数验证失败，仍作为普通工具参数错误处理。
|
||||
|
||||
### 格式化结果落盘
|
||||
|
||||
`ctx.spillStore` 是可选服务，仅用于面向模型的格式化结果。这是代码库中首个工具自有落盘调用模式；此设计有意为之，因为搜索保留属于条目级策略：`globMaxResults` 限制路径数，`grepMaxMatches` 限制匹配数，而工具此时仍持有完整逻辑结果。通用 `dsh-spill-policy` 会在 `tools/post-execute` 阶段限制最终文本字节数；到那时搜索工具已经省略后续路径或匹配，策略无法恢复它们。
|
||||
|
||||
当搜索产生的逻辑结果数超过内联上限，且 `ctx.spillStore` 存在时，工具会通过 `saveText()` 保存完整的格式化结果。落盘所有者是调用 agent 的会话头 id（`exec.agent?.session.header.id`）；缺少该所有者时，搜索会保留内联结果，并报告完整结果无法保存。落盘来源是工具执行身份：`{ toolName: exec.name, callId: exec.callId, label: 'result' }`。建议文件名为 `grep-results.txt` 和 `glob-results.txt`；落盘后端仍将它们视为提示，而不是路径。
|
||||
|
||||
如果落盘存储不存在、调用没有会话所有者，或保存失败，工具仍返回内联页和页脚，说明完整结果无法保存。格式化结果落盘存储不可用本身绝不能把搜索成功变为 `isError` 结果。
|
||||
|
||||
bash 原始输出流与格式化搜索落盘产物是两个不同的产物。原始 `rg` stdout 只会在所请求的 bash stdout 上限内于内存中解析；格式化落盘产物则是 `ctx.spillStore.saveText()` 生成的稳定、面向模型的恢复定位符。
|
||||
|
||||
### 结果形状
|
||||
|
||||
带有成功格式化落盘的受限 `glob` 结果会返回内联页与落盘通知：
|
||||
|
||||
```text
|
||||
<first N paths>
|
||||
|
||||
(Showing N of M paths. Full sorted result stored at: /.../session-abc123/9f8e7d-glob-results.txt. Use read with offset/limit, or grep this path to search within it.)
|
||||
```
|
||||
|
||||
带有成功格式化落盘的受限 `grep` 结果会返回分组后的预览匹配与落盘通知：
|
||||
|
||||
```text
|
||||
Found N of M matches
|
||||
|
||||
<file>
|
||||
Line 12: ...
|
||||
|
||||
(Full grep result stored at: /.../session-abc123/9f8e7d-grep-results.txt. Use read with offset/limit, or grep this path to search within it.)
|
||||
```
|
||||
|
||||
如果完整逻辑结果未超过内联上限，系统不会创建格式化落盘产物。如果完整逻辑结果过大但无法格式化落盘，页脚会说明结果已受限，完整结果无法保存。`truncated`／省略计数是预算事实，并不表示搜索不完整；超时、无效正则表达式、运行时 `rg` 消失、无法访问 workdir、原始输出溢出、跳过二进制文件和解析失败，仍属于工具领域的错误或不完整字段。
|
||||
|
||||
## 考虑过的替代方案
|
||||
|
||||
**将 `glob`／`grep` 放在 `ctx.fs` 上。** v1 不采用：这会迫使每个文件系统后端增加搜索 API，并使本地 ripgrep 行为成为提供方 seam 的一部分。搜索是有用的产品行为，但不像 `readText` 或 `writeText` 那样属于通用文本存储原语。
|
||||
|
||||
**直接从 `dsh-fs-local` spawn ripgrep。** 此 Agent Note 的 v1 不采用：直接 spawn 提供最简洁的 argv 边界、stdout／stderr 控制与提前停止控制，但会重复 bash seam 已负责的进程执行事项，包括环境清理、进程组终止、超时传播、沙箱／远程执行器替换，以及有界输出捕获。如果 bash 支持的搜索被证明过于依赖 shell 字符串，或必须支持前台流式输出，该方案仍是合理优化。
|
||||
|
||||
**通过 `ctx.bash.start()` 实现流式提前停止。** 不采用：`start()` 会创建模型可见的后台任务语义，包括 task id、所有者 token、`bash_output`、`bash_kill`、完成通知，并且没有内置超时。`grep` 需要前台工具结果，而不是后台 bash 工作流。如果将来必须流式搜索，正确的抽象是在 bash／进程 seam 上增加前台流式进程句柄，而不是借用公开后台任务 API。
|
||||
|
||||
**向模型公开 bash 原始落盘路径。** 不采用：bash 原始落盘路径包含原始 `rg` stdout（对于 grep 即 `rg --json` 记录），并非稳定的格式化搜索结果。搜索只把原始 stdout 当作内部传输；模型恢复使用通过 `ctx.spillStore.saveText()` 保存的格式化结果。
|
||||
|
||||
**先为 bash 输出规范化增加 `spillStore.saveFile()`。** 此 Agent Note 的 v1 不采用：未来规范化 bash 时，`saveFile()` 可以帮助将现有执行器落盘文件移动到会话范围的落盘存储，但搜索只需在生成面向模型的产物前，在内存中获取有界的原始 `rg` stdout。`saveText()` 足以保存格式化搜索结果。
|
||||
|
||||
**依赖通用 `dsh-spill-policy`。** 不采用：通用 post-execute 落盘只能看到最终工具结果。如果 `grep`／`glob` 内联返回第一页，通用策略无法恢复省略的结果。搜索工具必须在返回有界的面向模型文本前，自行保存完整的格式化结果。
|
||||
|
||||
**公开 Claude Code 的完整 `GrepTool` schema。** v1 不采用：`output_mode`、上下文标志、多行、`head_limit`、`offset`、`case_insensitive` 和类型过滤器会使面向模型的接口变成 ripgrep 包装层。本 harness 将常规预算与续传机制保留在部署策略和落盘产物中。
|
||||
|
||||
**保留提前停止搜索，并省略格式化落盘产物。** 此提案不采用：提前停止效率更高，却不给模型检查后续结果的路径。所选 v1 优先保证结果可恢复性与实现简洁性，并以 `timeoutMs`、`rawOutputMaxBytes`、bash 后端上限和格式化落盘产物作为安全后备。
|
||||
|
||||
**先扩展 bash seam，增加原始输出读取器。** 不采用：可移植的 `readRawOutput(ref, maxBytes)` API 会增加引用生命周期、权限和后端存储语义。逐次运行的 `stdoutMaxBytes` 请求是更窄的 seam：搜索要么在 `rawOutputMaxBytes` 内收到完整 stdout，要么明确失败。
|
||||
|
||||
**始终注册，只有执行时才报告缺少 `rg`。** 不采用：模型可见工具 schema 是部署能够尝试该能力的承诺。如果 bash 执行器在加载时找不到 ripgrep，更安全的接口是完全没有 `glob`／`grep` 工具或提示词指引。对于注册后发生环境变化的情况，执行时的 `rg` 缺失分类仍作为防御性回退。
|
||||
|
||||
## 测试
|
||||
|
||||
- 测试覆盖注册时 `rg` 探测（探测成功会注册两个工具和提示词章节；非零探测会跳过工具与提示词章节并发出警告；基础设施探测失败会拒绝插件加载），证明中止的 `exec.signal` 会到达 bash 后端（通过同一引用的 spec 断言和 `SEARCH_ABORTED` 结果），并覆盖命令构造／引用（恶意模式、带空格路径、以短横线开头的值、引号、换行、glob 元字符：既有单元断言，也针对每个恶意值执行真实 `bash -c` 往返）、将 `grep.path` 用作文件与目录目标、将 `glob.path` 用作目录搜索根、无效模式处理、无匹配、格式错误的 `rg --json` 输出、匹配行预览截断、原始输出溢出、超时／中止、格式化落盘成功／失败、包自有 `SEARCH_*` 错误代码，以及无后台任务不变量。
|
||||
- 直接覆盖第一方工具自有落盘先例：落盘后端存在、落盘后端缺失、`saveText()` 失败，以及缺少落盘所有者。
|
||||
- 该包通过真实 Loader 路径覆盖命名空间插件的导出形状（`name`、`inject`、`Config` 和 `apply`，且没有默认导出）。
|
||||
- 真实执行器集成测试（`dsh-bash-local` + 真实 `rg`）验证外部世界：恶意模式保持惰性、逐会话 cwd 解析、VCS 元数据排除、按修改时间排序，以及真实 ripgrep stderr 分类。如果测试进程的 PATH 中没有 `rg`，该测试会自行跳过（这是与无密钥 e2e 跳过相似的 CI 兼容措施）；伪执行器测试覆盖注册和执行时缺少 `rg`，并由逐文件 100% 覆盖率门禁兜底。
|
||||
- transcript 可见落盘通知仍有快照缺口：此功能合入时记录了缺口说明，没有快照。快照层会回放 acp-agent 树；在其中加入搜索插件会改变组装的系统提示词，必须使用真实密钥重新录制每一份预期输出，而实现环境没有密钥。落盘通知的确切 transcript 文本由单元测试固定（`formatGlobOutput`／`formatGrepOutput` 以及通过注册表执行的落盘测试）；下一次拥有密钥的会话应把插件接入 acp-agent 树，并运行一次 `test:snapshot:record`。
|
||||
|
||||
## 后果
|
||||
|
||||
- `glob` 和 `grep` 是 `@deepseek-ai/dsh-tool-fs-search` 中的条件式面向模型工具，不是 `ctx.fs` 提供方方法，也不属于现有 `@deepseek-ai/dsh-tool-fs` 根插件。只有 bash 执行器能找到 `rg` 时才会注册；该包注入 `tools`、`systemPrompt` 和 `bash`，不注入 `fs`，并使 `ctx.spillStore` 保持可选，读取时使用 `ctx.get('spillStore')`。
|
||||
- Schema 严格为 `glob(pattern, path?)` 和 `grep(pattern, path?, include?)`；搜索上限与超时是带默认值并经过验证的 Config 字段（`globMaxResults`、`grepMaxMatches`、`grepMaxLineBytes`、`rawOutputMaxBytes`、`timeoutMs`）。
|
||||
- 工具通过 `ctx.bash.resolve(request)` → `ctx.bash.run(spec)` 执行，转发 `exec.signal`，绝不调用 `ctx.bash.start()`，也绝不公开 bash task id。如果存在 `exec.agent?.session.header.cwd`，bash 请求 workdir 来自该值；解析后的 `spec.workdir` 决定执行与相对路径显示。
|
||||
- 工具向 bash seam 请求 `stdoutMaxBytes: rawOutputMaxBytes`，只解析上限内未截断的 stdout，并将超限或仍被截断的原始输出视为明确的搜索失败；绝不向模型公开原始 `rg` 输出。
|
||||
- 只要可用，过大的完整格式化结果会通过 `ctx.spillStore.saveText()` 保存，而内联结果保持有界；落盘失败、后端缺失或所有者缺失时，系统保留内联结果并报告未保存的剩余内容，绝不会返回 `isError`。
|
||||
- 包 README、生成的配置目录与导出 JSDoc 会记录 Config 字段和 `SEARCH_*` 代码；tui-agent 示例会提供条件式工具插件（acp-agent 树等待完成上述快照重新录制）；fs 组 README 会记录 `rg` 可用性以及 bash／文件系统共置部署要求。
|
||||
|
||||
## 风险
|
||||
|
||||
在宽泛模式下，完整运行的 `grep` 可能比提前停止搜索更慢。v1 为了简化实现并恢复完整结果而接受这项成本，同时通过工具超时、bash 超时、`rawOutputMaxBytes` 和输出上限加以约束。如果实际运行过慢，仍可采用直接 ripgrep 或前台流式替代方案。
|
||||
|
||||
Shell 命令构造是最尖锐的安全边界。`ctx.bash` 接受命令字符串而不是 argv 向量，因此实现必须集中处理 shell 引用，并测试恶意模式、带空格路径、以短横线开头的模式、引号、换行和 glob 元字符。
|
||||
|
||||
v1 假设 bash 与文件系统共置部署。如果 bash 搜索一个工作区，而 `read` 工具基于另一个根解析路径，返回路径可能无法继续读取。该包会记录这项要求，但不在运行时验证。
|
||||
|
||||
落盘定位符由后端负责。当前本地后端返回本地文件系统路径，适用于 `read`／`grep` 能打开这些文件的部署；远程或工作区受限部署可以使用另一种后端，让其定位符和检索提示指向受支持的检索机制。
|
||||
@@ -0,0 +1,6 @@
|
||||
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write
|
||||
2026-07-10-agent-session-identity-and-log-location.md: a55bf276bff998a94f84ec1af078022e4881903c
|
||||
2026-07-10-agent-session-identity-and-log-location.zh.md: 84b8b22187ccd1078ff13e39f4a345efbecfaeac
|
||||
@@ -2,6 +2,8 @@
|
||||
|
||||
Status: implemented
|
||||
|
||||
English | [中文](2026-07-10-agent-session-identity-and-log-location.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
An agent can identify its workspace through `session.header.cwd`, but a model using bash cannot reliably identify the session that owns the call or the durable transcript that records it. Searching `./.sessions` guesses deployment config and JSONL layout; custom roots, alternate persistence backends, resume, forks, and concurrent parent/child agents make that guess unreliable. Hooks have the same need for transcript location, while future plugins may need to expose other harness-owned environment facts to shell commands.
|
||||
|
||||
@@ -0,0 +1,87 @@
|
||||
# Agent Note: 向工具与钩子公开 agent（智能体）会话标识和 JSONL 位置
|
||||
|
||||
Status: implemented
|
||||
|
||||
[English](2026-07-10-agent-session-identity-and-log-location.md) | 中文
|
||||
|
||||
## 问题
|
||||
|
||||
agent 可以通过 `session.header.cwd` 识别其工作区，但使用 bash 的模型无法可靠识别当前调用所属的会话，也无法找到记录该调用的持久 transcript（文本记录）。搜索 `./.sessions` 等同于猜测部署配置和 JSONL 布局；自定义根目录、替代持久化后端、恢复、fork，以及并发运行的父子 agent，都会让这种猜测失效。钩子同样需要 transcript 位置，而未来的插件也可能需要向 shell 命令公开其他由 harness 所有的环境事实。
|
||||
|
||||
这项边界必须维持两个属性：事实的所有者决定如何解析该事实；每个子进程接收每次执行的快照，而不是进程级可变全局状态。尤其是嵌套 harness 不能把环境中的 `DSH_*` 值泄漏给当前 agent、持久化后端或配置均可能不同的子进程。
|
||||
|
||||
## 决策
|
||||
|
||||
在 [`SessionPersistence`](../architecture/2026-06-14-session-persistence.md) seam 上增加同步、无副作用的位置查询：
|
||||
|
||||
```ts
|
||||
import type { SessionHeader } from '@deepseek-ai/dsh-session'
|
||||
|
||||
interface SessionLocation {
|
||||
readonly kind: string
|
||||
readonly path: string
|
||||
}
|
||||
|
||||
interface SessionPersistence {
|
||||
locate(meta: SessionHeader): SessionLocation | undefined
|
||||
}
|
||||
```
|
||||
|
||||
`path` 是指向该后端为 `meta` 保留的专用日志的绝对本地路径；`kind` 标识其表示形式。JSONL 使用解析后的根目录和路径辅助函数返回 `{ kind: 'jsonl', path }`。SQLite 以及任何无法诚实提供逐会话本地产物的后端均返回 `undefined`。该查询不会创建或刷写任何内容，因此即使文件尚不存在，也可以报告延迟创建的目标路径。
|
||||
|
||||
面向模型的 bash 包（package）拥有一个 `ctx.bashEnv` 注册表。贡献方声明稳定名称、它可能返回的每个 `DSH_*` 键、每个键的说明，以及 `resolve(execution: ToolExecution)`。贡献方名称重复、键所有权重复、使用保留键、声明格式错误、运行时输出未声明或输出不是字符串时，系统都会明确失败。注册属于 Cordis effect，并随贡献插件的 fiber 一同移除。`list()` 无需运行解析器即可公开声明，从而让环境接口可供诊断工具和未来的提示词／UI 消费方枚举。
|
||||
|
||||
注册表会为每次前台和后台 bash `ToolExecution` 重新构建受信任的覆盖层：
|
||||
|
||||
- `DSH_HOME` 始终是配置的 Harness home 绝对路径。独立的 [`@deepseek-ai/dsh-paths`](../../../../packages/util/paths/README.md) 工具库规定其优先级：显式 `dshHome`，其次是环境中的 `$DSH_HOME`，最后是 `~/.dsh`。
|
||||
- `DSH_SHELL=1` 始终存在，用于标识由 DeepSeek Harness 管理、面向模型的 bash 子进程。
|
||||
- 执行具有关联 agent 时，`DSH_SESSION_ID` 存在并等于 `agent.session.header.id`。
|
||||
- 内置的持久化转换层提供 `DSH_SESSION_JSONL` 的条件是 `ctx.sessionPersistence.locate(header)` 返回 `kind: 'jsonl'`。
|
||||
|
||||
会话持久化仍然是事实所有者：JSONL 不依赖 tool-bash，也不会自行注册 shell 变量；钩子继续直接使用 `locate()`。tool-bash 是把持久化事实转换为 shell 约定的转换层。其他需要向 shell 公开事实的插件依赖该注册表，并注册各自的键；它们不修改 `process.env`。
|
||||
|
||||
bash seam 导出 `DSH_ENV_PREFIX` 作为唯一的命名空间来源，并派生 `DshEnvironmentKey`，其来源是该常量的 `typeof`。tool-bash 从该常量派生内置名称与模型指引，执行器则使用该常量进行过滤和通道校验。seam 通过 `BashExecRequest.dshEnv`／`BashExecSpec.dshEnv` 单独传递受管理的覆盖层。普通 `env` 仍是钩子所用的通用进程内插件接口，但不能包含受管理的键；对称地，`dshEnv` 不能包含普通键。本地执行器会在 spawn 前拒绝任一错误通道，移除环境中继承的全部受管理键，依次应用普通清理、终端环境和显式 `env`，最后合并受信任的 `dshEnv` 快照。这保证了值缺失表示它当前确实不存在，而不是从外层或先前的 harness 继承而来。面向模型的工具仍忽略模型提供的 `env`／`stdin` 参数。
|
||||
|
||||
bash 工具说明只讲解持久约定：当前 harness 环境事实通过受管理的 `$DSH_*` 变量提供，可以在需要时查看。它不会枚举持久化专用键，也不会添加永久的系统提示词章节。工具 schema 已记录在请求 header 中，工具输出则记录为 `tool/result`，因此无需新增会话事件。
|
||||
|
||||
[Claude Code 和 Codex 钩子桥接层](2026-06-30-hook-bridges.md)在构造 payload 时，从同一持久化 seam 解析 transcript 位置。Codex 使用 `transcript_path: string | null`；Claude Code 保留其字符串字段，并回退为 `''`。钩子查询不会物化或刷写会话。
|
||||
|
||||
## 同类产品调研
|
||||
|
||||
同类产品把稳定标识与物理存储分开处理。Codex 向 spawn 的 shell 注入稳定的 `CODEX_THREAD_ID`，而 recorder 和钩子接口负责提供 transcript 路径。Claude Code 通过结构化的钩子／状态输入提供 `session_id` 和 `transcript_path`。OpenCode 在结构化工具上下文中携带标识；Kimi Code 展开会话占位符；Reasonix 则把活动会话路径保存在控制器上。可移植的规则是：在调用边界注入标识，由存储层解析位置，绝不在并发 harness 中使用进程级的当前会话全局变量。
|
||||
|
||||
## 生命周期与持久化语义
|
||||
|
||||
新会话在第一个轮次之前获得 id，因此它的首次 bash 调用即可读取 `DSH_SESSION_ID` 和 JSONL 目标。JSONL 文件可能要等到第一次成功的轮次结束检查点后才存在，而且在一个轮次仍未结束时，它只包含上次刷写的前缀。`DSH_SESSION_JSONL` 是位置提示，不是授权凭据或新鲜度保证。
|
||||
|
||||
恢复操作复用已加载的 header，因此 id 和位置不变。fork 和 spawn 会创建新的会话 id 与位置。父子调用分别从自己的 `ToolExecution.agent` 解析事实；即使调用重叠，每条命令也会收到不可变快照。替换持久化服务会影响后续收集，因为转换层在执行时查询 `ctx.get('sessionPersistence')`；注册表本身受 effect 作用域约束，并且可安全用于 HMR（热模块替换）。
|
||||
|
||||
`dshHome` 是与会话无关的部署上下文。agent-core 通过 `@deepseek-ai/dsh-paths` 解析出一个值，并将其同时传给 tool-bash 和本地 skill（技能）发现；独立消费方调用同一解析器。如果顶层 `dshHome` 与 `skills.local.dshHome` 均已提供但解析结果不同，组合会失败，而不会公开互相矛盾的 home。持久化可以独立变更，无需把其事实冻结到会话前缀中。
|
||||
|
||||
## 测试
|
||||
|
||||
单元测试覆盖注册表声明校验、effect 释放、逐次执行收集、`dshHome` 优先级，以及本地执行器清理并重建 `DSH_*` 的顺序。请求录制测试覆盖前台／后台快照、无 agent 调用、持久化不存在或为 JSONL、忽略模型 `env`，以及父子隔离。JSONL／SQLite 定位器契约测试与两套钩子桥接测试均锁定 transcript 可用和不可用两种方言。
|
||||
|
||||
一项无密钥的完整循环集成测试会在第一个轮次驱动真实的 agent loop、JSONL 持久化、tool-bash 与 bash-local。子进程打印 `DSH_HOME`、`DSH_SHELL`、会话 id、JSONL 目标和继承的陈旧哨兵值；测试校验当前值、陈旧变量不存在、刷写前文件不存在，并最终检查持久化 header。快照覆盖会锁定录制请求 header 中的通用 bash 说明。该契约属于确定性的本地执行，不涉及模型选择，因此无需带密钥测试。
|
||||
|
||||
## 考虑过的替代方案
|
||||
|
||||
**只提供 id，再用 `find`。** 搜索无法得知自定义根目录或后端布局，并且在多会话环境下存在竞态。
|
||||
|
||||
**只提供绝对路径。** 路径可能不可用、延迟创建或取决于表示形式，不能作为稳定的会话标识。
|
||||
|
||||
**使用全局 `process.env`。** 并发 agent 会互相覆盖，嵌套 harness 也会继承陈旧的当前会话值。
|
||||
|
||||
**把持久化说明放入会话前缀。** 活动服务可以在 HMR 或未来的后端切换中改变，而会话前缀保持冻结；持久化专用指引会因此变得陈旧。
|
||||
|
||||
**使用类型化 waterfall 事件。** 监听器不运行就无法声明所有权，而后续监听器可以无提示地覆盖键。注册表能在注册时检测键冲突，并且保持可枚举。
|
||||
|
||||
**让每个持久化后端直接注册 bash 环境。** 这会反转依赖方向，让存储层依赖某一个消费方，并迫使未使用 bash 的部署也引入它。钩子仍然需要 `locate()`。
|
||||
|
||||
**增加面向模型的 `session_info` 工具。** bash 已经提供查询接口，新增工具只会多出 schema 和一次调用；注册表可以扩展至未来的环境事实，无需为每项事实增加一个工具。
|
||||
|
||||
## 影响
|
||||
|
||||
每个面向模型的 bash 子进程都会收到当前 Harness home 和 shell 标识，关联 agent 的调用还会收到稳定的会话标识。使用 JSONL 后端的调用可以获得可选的目标路径；非文件持久化会如实省略该值。这些子进程中的完整 `DSH_*` 命名空间由 harness 管理：系统移除环境中已有的受管理值、重新加入当前受信任的值，并禁止普通调用方通过 `env` 绕过所有权检查。
|
||||
|
||||
该命名空间可被发现，但并非秘密。路径可能泄露配置的根目录，延迟创建的目标也可能不存在或处于陈旧状态，而且命令可以在自己的 shell 语法中覆盖变量。消费方应把这些值视为关联信息和环境事实，在归属关系重要时校验 transcript 元数据，并依靠沙箱／文件系统策略而不是变量保密性来完成授权。
|
||||
@@ -0,0 +1,6 @@
|
||||
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write
|
||||
2026-07-10-parallel-tool-call-execution.md: c67ae61939a3e7974f9bf729058a57f5576308a1
|
||||
2026-07-10-parallel-tool-call-execution.zh.md: a80317aa951cbf3a9cae0651348c99712a4193d5
|
||||
@@ -2,6 +2,8 @@
|
||||
|
||||
Status: implemented
|
||||
|
||||
English | [中文](2026-07-10-parallel-tool-call-execution.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
An assistant message may contain several sibling `tool-call` blocks. Running them serially adds the latency of independent reads and web requests even though the model has already requested them together.
|
||||
|
||||
@@ -0,0 +1,103 @@
|
||||
# Agent Note: 按单次调用安全性并行执行工具调用
|
||||
|
||||
Status: implemented
|
||||
|
||||
[English](2026-07-10-parallel-tool-call-execution.md) | 中文
|
||||
|
||||
## 问题
|
||||
|
||||
一条 assistant 消息可以包含多个并列的 `tool-call` 块。尽管模型已经同时请求了这些调用，串行执行仍会叠加各个独立读取和 Web 请求的延迟。
|
||||
|
||||
并发属于宿主调度范畴，不是面向模型的工具元数据。循环需要在不硬编码工具名称、不向 JSON Schema 暴露调度策略的前提下，判断哪些调用可以重叠执行。
|
||||
|
||||
会话日志仍是权威记录：每个已启动的调用都有审计事件，都会获得结果；无论完成顺序如何，模型历史都按原始调用顺序观察结果。
|
||||
|
||||
## 决策
|
||||
|
||||
每个工具都可以提供可选的 `isConcurrencySafe(args)` 分类器。该分类器必须是同步纯函数：它只检查当前调用已解析的参数，不执行 I/O 或任何变更。只有显式返回 `true` 才表示选择并行；分类器缺失、参数无效、分类器抛错或返回任何其他值，都会使该调用按独占方式执行。规范类型契约见[工具数据结构](../../../../docs/core-data-structures/tools.md)。
|
||||
|
||||
分类器有意设计为一元函数。返回 `true` 表示工具承诺：此调用可以与任何同样返回 `true` 的并列调用重叠执行。调度器不会比较调用，也不会证明它们的资源访问相容。
|
||||
|
||||
这个一元分类器仍然可以感知输入。工具可以将只读操作分类为并行，将变更操作分类为独占。该接口无法表达「仅当路径不同时，这些写入才安全」之类的关系规则，因此，安全性依赖并列调用的调用仍按独占方式执行。
|
||||
|
||||
`defineTool()` 先验证参数，再调用类型化分类器。无效参数会被归为独占，且只有该调用真正执行时才会产生常规参数错误。`ctx.tools.executionMode(exec)` 会解析当前有效的工具定义，并返回带标签的 `parallel` 或 `exclusive` 模式；未知工具将以安全方式退化为独占。
|
||||
|
||||
使用带标签的模式，而不是公开布尔型调度器 API，使得以后可以表达感知资源的变体，无需改变分类器契约。
|
||||
|
||||
## 调度与顺序
|
||||
|
||||
循环会等待完整的 assistant 消息，对每个调用只解析一次，为每个调用创建独立的 `ToolExecution`，再按模型顺序扫描。连续的并行调用组成一组；每个独占调用单独组成一组，并构成顺序屏障。各组按顺序执行。分类采用惰性方式：每经过一个屏障，调度器都会解析下一个调用；补充并行池之前，还会重新分类每个后续调用。如果注册表变更使该调用变为独占，当前池会先完全排空，然后该调用才作为下一个屏障启动。
|
||||
|
||||
例如：
|
||||
|
||||
```text
|
||||
[parallel read(A), parallel read(B), exclusive write(A), parallel read(C)]
|
||||
|
||||
→ [read(A), read(B)]
|
||||
→ [write(A)]
|
||||
→ [read(C)]
|
||||
```
|
||||
|
||||
`read(A)` 和 `read(B)` 可以重叠执行。`write(A)` 要等两者都完成后才启动，`read(C)` 则要等写入完成后才启动。
|
||||
|
||||
每组都使用一个由 `maxParallelToolCalls` 限制上限的滚动池：循环先按模型顺序启动调用，直到达到上限；每有一个调用结算，就再启动一个。独占组是容量为 1 的池。将上限设为 `1` 可保持串行执行。
|
||||
|
||||
只有派发和工具主体会重叠执行。`tools/pre-execute` 和 `tools/post-execute` 按模型顺序运行，因为中间件可能维护对顺序敏感的状态。`tools/execute` 包装层会环绕并发派发运行，因此必须能在不同执行之间重入。
|
||||
|
||||
每个已启动的调用都会在进入 pre-execute 门禁之前立即追加 `tool/call`。已完成的派发占据模型顺序的槽位；提交游标只有在下一个槽位就绪时，才会追加 `tool/result` 并收集 `additionalContexts`。实时界面可以显示多个待处理调用，但结果和工具执行后的上下文仍按模型顺序排列。
|
||||
|
||||
如果在一组启动前中止，系统不会记录该组的任何调用。如果在一组执行期间中止，系统会停止补充池，等待已启动的调用，按顺序提交其结果，在这些结果之后排空已接受的批次上下文，然后通过现有中止路径结束该步骤。从未启动的调用没有审计事件。
|
||||
|
||||
Code Mode 仍不使用此调度器，因为模型只会发出一个原生 `run_code` 调用。`run_code` 及其内部派发队列仍按串行方式执行；`mode: 'both'` 中的原生并列调用使用常规调度器。
|
||||
|
||||
## 安全契约
|
||||
|
||||
工具返回 `true` 即承诺：其主体可以与其他并行调用同时运行。它不得直接变更父会话或其他由父级拥有的状态；它将输出返回给循环，由循环按模型顺序提交。
|
||||
|
||||
执行期间触及的任何共享状态都必须支持并发。这也包括工具包装层和提供方：它们可以在内部串行化，也可以实施自身容量限制，但必须在并发派发时不破坏状态。
|
||||
|
||||
## 配置与声明
|
||||
|
||||
`maxParallelToolCalls` 是 AgentLoop 的正整数部署上限，由工厂创建的所有 agent（智能体）共享。默认值为 `10`；`1` 保持串行执行。字段和默认值的精确定义见生成的[配置目录](../../../../docs/config-catalog.md)。
|
||||
|
||||
当前实现中的声明保持保守。Web 搜索、Web 获取和文件系统读取选择并行。文件系统写入与编辑、bash 工具、subagent 委派、工作流、用户交互、todo 变更、Code Mode 以及 Cordis 变更工具仍按独占方式执行。subagent 可能共享父级的工作区或外部资源，而一元分类器无法证明并列委派的作用互不重叠。Bash 没有已证明的输入敏感分类器，因此仍按独占方式执行。
|
||||
|
||||
文件系统读取依赖一个范围很窄的记录器例外：其同步观察更新可以不按顺序结算，但写入和编辑在变更前会重新检查已观察的版本，因此陈旧状态只会导致 `FS_STALE_VERSION`。
|
||||
|
||||
## 验证
|
||||
|
||||
单元测试覆盖固定了安全退化的分类、类型化参数验证、分组、屏障、替换注册表后的实时重新分类、滚动上限、独立执行对象、中间件顺序、有序结果与上下文，以及中止排空。第一方测试固定每项并行声明。
|
||||
|
||||
快照覆盖固定了可见的多调用 transcript（文本记录）：待处理调用可以重叠执行，已完成结果仍按模型顺序排列。Code Mode 覆盖固定其串行边界。此调度属于确定性循环行为，因此无需依赖提供方的 e2e 测试。
|
||||
|
||||
## 备选方案
|
||||
|
||||
**保持串行执行。** 这可以避免新的顺序和中止情形，但会保留独立并列调用所产生的不必要延迟。
|
||||
|
||||
**使用一个工具级布尔值。** 固定的 `supportsParallelToolCalls` 标志更小，但无法区分同一工具的只读操作和变更操作。感知参数的分类器保留了这项区分。
|
||||
|
||||
**使用有状态的分类。** 向分类器提供实时 agent、注册表或 I/O 访问，会使决策依赖分类器的运行时机，并在分类与派发之间留下缺口。可变授权和陈旧状态检查仍属于执行时职责。
|
||||
|
||||
**使用感知并列调用或感知资源的分类。** 调度器可以成对比较调用，或让每个调用声明资源读写要求。这样可以并行化不冲突的写入，却要求不相关工具共享资源标识和冲突语义。一元契约选择放弃这部分并发性，并在安全性取决于关系时安全退化。
|
||||
|
||||
**并行执行完整的工具流水线。** 这样可以让循环继续使用公开的单调用 API，但会并发运行 pre-execute 和 post-execute 中间件。现有防护和钩子桥可能承载有序状态，因此只允许派发重叠。
|
||||
|
||||
**公开分阶段方法或调度 waterfall。** 公开的 `prepare` / `dispatch` / `finalize` 方法或 `tools/execution-mode` 事件，会在出现另一个消费方之前扩大扩展接口。循环使用内部调度器视图，而 `executionMode(exec)` 为策略 seam 保留了插入点。
|
||||
|
||||
**在模型流式输出时启动调用。** 这可能进一步降低延迟，但会改变 assistant 消息的权威性、回放以及调用/结果配对。调度器只在 assistant 消息完成后才启动。
|
||||
|
||||
**使用固定大小的窗口。** 如果在启动下一个窗口前等待当前窗口的每个调用，一个缓慢调用就会使容量闲置。滚动池在保持上限的同时避免了这项延迟。
|
||||
|
||||
**向模型暴露并发元数据。** 模型已可以发出并列调用。宿主调度元数据会扩大请求，却无助于工具选择。
|
||||
|
||||
## 影响
|
||||
|
||||
该设计以安全退化为原则，对工具作者而言也很简单，但无法利用必须通过比较并列调用才能确认安全的并发性。工具过于宽泛地选择并行，可能暴露潜在的共享状态竞态。
|
||||
|
||||
在某些情形下，并行调用会先行启动，而串行执行原本会在轮到这些调用之前中止。因此，调度器只记录已启动的调用，在中止时将其排空，且取消后绝不启动替换调用。
|
||||
|
||||
有序提交可能会让快速结果等待较慢的早期并列调用。这保留了回放和模型历史顺序，同时实时界面仍可显示待处理进度。
|
||||
|
||||
并发外部调用可能会争用配额或进程容量。提供方负责自身容量控制；循环上限只限制一个 agent 步骤中的调用数量。
|
||||
|
||||
工具注册是调度边界。调度器会在每个屏障之后以及每次补充池之前重新分类，因此注册表变更会影响尚未启动的调用。已启动的调用保留它们进入池时所依据的调度决策。
|
||||
@@ -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
|
||||
2026-07-10-session-query-service.md: 722f6bf6163278719c3bbb598ed2a2a9d042fb8e
|
||||
2026-07-10-session-query-service.zh.md: ae6fcb78e18afe83784560c493ea93b7ee0bd68c
|
||||
2026-07-10-session-query-service.md: 42d12fe2c5e34e71a6166816857b9ced52a61a95
|
||||
2026-07-10-session-query-service.zh.md: 2c8d322ca6099db1c8ddbb8a02efbc8729e83dbf
|
||||
|
||||
@@ -12,7 +12,7 @@ Full-text search is related but materially larger. Putting provider coordination
|
||||
|
||||
## Decision
|
||||
|
||||
`@deepseek-ai/dsh-session-query` owns the single abstract `ctx.sessionQuery` service over one logical corpus. It concretely implements `listSessions()`, provider-independent `filterSessions(filters)`, `listEvents(sessionId)`, `filterEvents(sessionId, filters)`, bounded `readEvent(request)`, `traceSession(sessionId)`, and `traceEvent(request)`, while concrete backends implement its two full-text methods. The [unified service decision](../architecture/2026-07-23-unified-session-query-service.md) owns that topology, the [SQLite search decision](2026-07-10-sqlite-session-query-provider.md) owns search behavior, and the [tracing decision](2026-07-13-session-query-tracing.md) owns lineage and event-relationship semantics.
|
||||
`@deepseek-ai/dsh-session-query` owns the single abstract `ctx.sessionQuery` service over one logical corpus. It concretely implements `listSessions()`, provider-independent `filterSessions(filters)`, `listEvents(sessionId)`, `filterEvents(sessionId, filters)`, bounded `readEvent(request)`, `traceSession(sessionId)`, and `traceEvent(request)`, while concrete backends implement its two full-text methods. The [unified service decision](../../archived/architecture/2026-07-23-unified-session-query-service.md) owns that topology, the [SQLite search decision](2026-07-10-sqlite-session-query-provider.md) owns search behavior, and the [tracing decision](2026-07-13-session-query-tracing.md) owns lineage and event-relationship semantics.
|
||||
|
||||
The service observes the optional `ctx.sessionPersistence` binding dynamically but retains no persisted cache or invalidation listener. Each cross-corpus list asks the active backend for authoritative metadata, then overlays a fresh live-store list. Matching ids become one `SessionRecord`: the live header wins and `live`/`persisted` independently report source availability. Immutable header disagreement is `SESSION_QUERY_SOURCE_CONFLICT`.
|
||||
|
||||
|
||||
@@ -12,7 +12,7 @@ Status: implemented
|
||||
|
||||
## 决策
|
||||
|
||||
`@deepseek-ai/dsh-session-query` 拥有面向单一逻辑语料库的唯一抽象 `ctx.sessionQuery` 服务。它具体实现 `listSessions()`、提供方无关的 `filterSessions(filters)`、`listEvents(sessionId)`、`filterEvents(sessionId, filters)`、有界的 `readEvent(request)`、`traceSession(sessionId)` 和 `traceEvent(request)`，而具体后端实现其两个全文搜索方法。[统一服务决策](../architecture/2026-07-23-unified-session-query-service.md)拥有这一拓扑，[SQLite 搜索决策](2026-07-10-sqlite-session-query-provider.md)拥有搜索行为，[追踪决策](2026-07-13-session-query-tracing.md)拥有血缘与事件关系语义。
|
||||
`@deepseek-ai/dsh-session-query` 拥有面向单一逻辑语料库的唯一抽象 `ctx.sessionQuery` 服务。它具体实现 `listSessions()`、提供方无关的 `filterSessions(filters)`、`listEvents(sessionId)`、`filterEvents(sessionId, filters)`、有界的 `readEvent(request)`、`traceSession(sessionId)` 和 `traceEvent(request)`，而具体后端实现其两个全文搜索方法。[统一服务决策](../../archived/architecture/2026-07-23-unified-session-query-service.md)拥有这一拓扑，[SQLite 搜索决策](2026-07-10-sqlite-session-query-provider.md)拥有搜索行为，[追踪决策](2026-07-13-session-query-tracing.md)拥有血缘与事件关系语义。
|
||||
|
||||
该服务动态观察可选的 `ctx.sessionPersistence` 绑定，但不保留持久化缓存或失效监听器。每次跨语料库列表操作向活跃后端请求权威元数据，然后叠加一份新鲜的活跃 store 列表。id 匹配的条目合并为一条 `SessionRecord`：活跃 header 优先，`live`/`persisted` 各自独立报告来源可用性。不可变 header 不一致时产生 `SESSION_QUERY_SOURCE_CONFLICT`。
|
||||
|
||||
|
||||
@@ -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
|
||||
2026-07-10-sqlite-session-query-provider.md: 98618a7eb572ce59c5fa5984675c9dc57b3f4289
|
||||
2026-07-10-sqlite-session-query-provider.zh.md: bb3650da907cf86a853f748fa0ee40d5c2168709
|
||||
2026-07-10-sqlite-session-query-provider.md: 372c21241f9ae5d7300165f016db9b36e6b52855
|
||||
2026-07-10-sqlite-session-query-provider.zh.md: dc10a6e6a609809aa6f2b194f262e2642d9545bc
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user