refactor: apply repository naming contract
Apply the accepted pre-release package, service, type, directory, and role renames as one repository-wide change.
This commit is contained in:
Tianyi Cui
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-07-20-error-cause-chain-diagnostics.md
|
||||
2026-07-20-error-cause-chain-diagnostics.md: d1944b3b435f2e1c64e1612adf0e61dd8e7401ff
|
||||
2026-07-20-error-cause-chain-diagnostics.zh.md: cd493f99388282189c807353b32fec15f1007f87
|
||||
2026-07-20-error-cause-chain-diagnostics.md: 4fb5eb99f83419cab490018fe69649d60b184058
|
||||
2026-07-20-error-cause-chain-diagnostics.zh.md: 690f32419b11cc54ccb9f381c9837b6d4f77ac34
|
||||
|
||||
@@ -34,4 +34,4 @@ A TUI run against an unreachable DeepSeek endpoint failed with the single notice
|
||||
- Durable `turn/end` error messages include cause detail. Existing snapshot fixtures replay byte-identically because their scripted errors carry no `cause` (for such errors `errorChain(err)` equals `err.message`); only unit-test expectation strings changed. A fixture recorded from a real transport failure would carry the chain.
|
||||
- `errorChain` renders `message` without the class name (`String(error)` rendered `Error: <message>`), so a bare `TypeError` in a log line loses its type label unless its message is empty (then the name is the fallback). The chain detail was judged worth more than the class name at these diagnostic boundaries.
|
||||
- `dsh-stdio` output for failed turns is no longer silent; piped consumers that parsed the transcript see new `[turn …]` lines.
|
||||
- Remaining `renderThrown` copies in `dsh-subagent`, `dsh-workflow`, `dsh-skill`, and `dsh-workflow-workerthread` still render without the chain; they wrap package-local errors that carry their own messages, and can adopt `errorChain` when their diagnostics prove insufficient.
|
||||
- Remaining `renderThrown` copies in `dsh-subagent`, `dsh-workflow`, `dsh-skill`, and `dsh-workflow-worker-thread` still render without the chain; they wrap package-local errors that carry their own messages, and can adopt `errorChain` when their diagnostics prove insufficient.
|
||||
|
||||
@@ -34,4 +34,4 @@ TUI 连接不可达的 DeepSeek 端点时，失败只显示一条 `fetch failed`
|
||||
- 持久化的 `turn/end` 错误消息包含 cause 细节。现有快照 fixture（测试前置数据）字节级一致地回放，因为其脚本化错误不带 `cause`（对这类错误 `errorChain(err)` 等于 `err.message`）；只有单元测试的期望字符串有变化。从真实传输失败录制的 fixture 会携带完整链。
|
||||
- `errorChain` 渲染 `message` 而不带类名（`String(error)` 会渲染 `Error: <message>`），因此日志行里的裸 `TypeError` 会丢失类型标签，除非消息为空（此时回退到类名）。在这些诊断边界上，链细节被判断为比类名更有价值。
|
||||
- `dsh-stdio` 对失败轮次的输出不再沉默；解析 transcript 的管道消费方会看到新的 `[turn …]` 行。
|
||||
- `dsh-subagent`、`dsh-workflow`、`dsh-skill`、`dsh-workflow-workerthread` 里剩余的 `renderThrown` 副本仍不渲染链；它们包装的是自带消息的包内错误，等诊断信息证明不足时再采用 `errorChain`。
|
||||
- `dsh-subagent`、`dsh-workflow`、`dsh-skill`、`dsh-workflow-worker-thread` 里剩余的 `renderThrown` 副本仍不渲染链；它们包装的是自带消息的包内错误，等诊断信息证明不足时再采用 `errorChain`。
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.md
|
||||
2026-07-21-compaction-summary-prefix-cache-reuse.md: fb6524846f837b783423b3ed0e043cd4e1f7849d
|
||||
2026-07-21-compaction-summary-prefix-cache-reuse.zh.md: 96adc31d6d6c50b4e6bfee32a5b89388a33a6939
|
||||
2026-07-21-compaction-summary-prefix-cache-reuse.md: 08ceb820ee415cbac9aded7a6b4f55933dc64cf3
|
||||
2026-07-21-compaction-summary-prefix-cache-reuse.zh.md: cd502c806f37f6b7fcb5d2834b3684bb210e419a
|
||||
|
||||
@@ -29,17 +29,17 @@ Auto-compaction always anchors at the surface head, so the shadowed region is th
|
||||
- **Keep the summarizer system prompt but reuse the rest** — rejected: the system slot is the very first token region a provider caches on, so a distinct summarizer system prompt invalidates the whole prefix regardless of what follows. Only moving the directive off the front recovers the cache.
|
||||
- **Send only the shadowed region without the `system`/`tools` head** — rejected: a differently-headed sequence still diverges from the cached request at the first token, so it caches no better while losing the framing the summary needs.
|
||||
- **Omit `tools` from the summarization request** (the model never calls one) — rejected: tool schemas are part of the cached token sequence; omitting them misaligns every following token and defeats reuse.
|
||||
- **A dedicated `assistant/chunk`-emitting summarization sub-session for snapshot replay** — rejected: the durable `compact/summary` event records the successful local call's position and complete output, while its explicit call marker prevents replay from treating template or remote output as a local stream.
|
||||
- **A dedicated `assistant/chunk`-emitting summarization sub-session for snapshot replay** — rejected: the durable `compaction/summary` event records the successful local call's position and complete output, while its explicit call marker prevents replay from treating template or remote output as a local stream.
|
||||
|
||||
## Consequences
|
||||
|
||||
- **`dsh-compact-basic`** owns `SummarizationInput`; the protected `summarize(input, agent, signal?)` hook signature changed (acceptable pre-release), and `region.ts` gained `buildSummarizationInput` folding `deriveEventMessage` over the shadowed seqs behind the header prefix.
|
||||
- **Dead render surface removed.** The old flattening path (`renderTranscript` / `renderContentBlocks` and its spec in `dsh-compact`) had no remaining consumer and was deleted with its export.
|
||||
- **README model experience** for `dsh-compact-basic` now documents the auxiliary request as the replayed prefix plus a trailing compaction-instruction message, and its KV-cache effect as reuse of the warm conversation prefix.
|
||||
- **`dsh-compaction-basic`** owns `SummarizationInput`; the protected `summarize(input, agent, signal?)` hook signature changed (acceptable pre-release), and `region.ts` gained `buildSummarizationInput` folding `deriveEventMessage` over the shadowed seqs behind the header prefix.
|
||||
- **Dead render surface removed.** The old flattening path (`renderTranscript` / `renderContentBlocks` and its spec in `dsh-compaction`) had no remaining consumer and was deleted with its export.
|
||||
- **README model experience** for `dsh-compaction-basic` now documents the auxiliary request as the replayed prefix plus a trailing compaction-instruction message, and its KV-cache effect as reuse of the warm conversation prefix.
|
||||
- **The framed checkpoint output is unchanged**, so the landed `user/message` and every conversation-request snapshot are unaffected; only the auxiliary request's shape changed.
|
||||
|
||||
## Testing
|
||||
|
||||
- **Unit:** `compact-basic.spec.ts` asserts the auxiliary call forwards `system`/`tools`/leading messages and appends the compaction instruction as the final message, and that `compactRegion` replays the latest routed header prefix. Existing content assertions read the summarizer input through the replayed messages rather than a transcript string.
|
||||
- **Unit:** `compaction-basic.spec.ts` asserts the auxiliary call forwards `system`/`tools`/leading messages and appends the compaction instruction as the final message, and that `compactRegion` replays the latest routed header prefix. Existing content assertions read the summarizer input through the replayed messages rather than a transcript string.
|
||||
- **Loop:** `compact-loop-repro.spec.ts` classifies the summarization request by the compaction instruction in its trailing user message, and the overflow-recovery tests continue to pin conversation-vs-summary request counts across the real loop.
|
||||
- **Snapshot:** keyless replay reconstructs one canonical successful stream from a marked `compact/summary`; the [compaction-seam note](../feature/2026-06-18-compaction-capability-seam.md) owns the durable marker contract.
|
||||
- **Snapshot:** keyless replay reconstructs one canonical successful stream from a marked `compaction/summary`; the [compaction-seam note](../feature/2026-06-18-compaction-capability-seam.md) owns the durable marker contract.
|
||||
|
||||
@@ -29,17 +29,17 @@ Status: implemented
|
||||
- **保留摘要器系统提示词但复用其余部分**——否决：system 槽位正是提供方最先做缓存的 token 区域，因此一个不同的摘要器系统提示词无论后面跟着什么都会使整个前缀失效。只有把指令移离前端才能恢复缓存。
|
||||
- **只发送被遮蔽区域而不带 `system`/`tools` 头部**——否决：头部不同的序列在第一个 token 处仍然与已缓存请求分叉，因此缓存效果并不更好，反而丢失了摘要所需的框架。
|
||||
- **从摘要请求中省略 `tools`**（模型从不调用任何工具）——否决：工具 schema 是已缓存 token 序列的一部分；省略它们会让后续每个 token 失去对齐，破坏复用。
|
||||
- **为快照回放专门建立一个发出 `assistant/chunk` 的摘要子会话**——否决：持久的 `compact/summary` 事件会记录成功本地调用的位置和完整输出，而显式调用标记可防止回放把模板或远程输出当作本地流。
|
||||
- **为快照回放专门建立一个发出 `assistant/chunk` 的摘要子会话**——否决：持久的 `compaction/summary` 事件会记录成功本地调用的位置和完整输出，而显式调用标记可防止回放把模板或远程输出当作本地流。
|
||||
|
||||
## 后果
|
||||
|
||||
- **`dsh-compact-basic`** 拥有 `SummarizationInput`；受保护的 `summarize(input, agent, signal?)` 钩子签名发生变化（发布前可接受），并且 `region.ts` 新增了 `buildSummarizationInput`，它在 header 前缀之后对被遮蔽的 seq 折叠 `deriveEventMessage`。
|
||||
- **移除无用的渲染表面。** 旧的拍平路径（`renderTranscript` / `renderContentBlocks` 及其在 `dsh-compact` 中的 spec）已无消费方，连同其导出一并删除。
|
||||
- **README 的 Model Experience** 现在把 `dsh-compact-basic` 的辅助请求记述为回放的前缀加上一条尾部压缩指令消息，并把其 KV Cache 效果记述为复用已预热的对话前缀。
|
||||
- **`dsh-compaction-basic`** 拥有 `SummarizationInput`；受保护的 `summarize(input, agent, signal?)` 钩子签名发生变化（发布前可接受），并且 `region.ts` 新增了 `buildSummarizationInput`，它在 header 前缀之后对被遮蔽的 seq 折叠 `deriveEventMessage`。
|
||||
- **移除无用的渲染表面。** 旧的拍平路径（`renderTranscript` / `renderContentBlocks` 及其在 `dsh-compaction` 中的 spec）已无消费方，连同其导出一并删除。
|
||||
- **README 的 Model Experience** 现在把 `dsh-compaction-basic` 的辅助请求记述为回放的前缀加上一条尾部压缩指令消息，并把其 KV Cache 效果记述为复用已预热的对话前缀。
|
||||
- **带框架的检查点输出未改变**，因此落地的 `user/message` 和每个对话请求快照都不受影响；只有辅助请求的形状发生了变化。
|
||||
|
||||
## 测试
|
||||
|
||||
- **单元：** `compact-basic.spec.ts` 断言辅助调用转发 `system`/`tools`/前导消息，并把压缩指令作为最后一条消息追加，且 `compactRegion` 回放最新的已路由 header 前缀。现有的内容断言通过回放的消息而非 transcript 字符串来读取摘要器输入。
|
||||
- **单元：** `compaction-basic.spec.ts` 断言辅助调用转发 `system`/`tools`/前导消息，并把压缩指令作为最后一条消息追加，且 `compactRegion` 回放最新的已路由 header 前缀。现有的内容断言通过回放的消息而非 transcript 字符串来读取摘要器输入。
|
||||
- **循环：** `compact-loop-repro.spec.ts` 依据摘要请求尾部 user 消息中的压缩指令对其分类，溢出恢复测试则继续在真实循环中固定对话请求与摘要请求的数量。
|
||||
- **快照：** 无密钥回放会从带标记的 `compact/summary` 重建一条规范成功流；[compaction-seam Agent Note](../feature/2026-06-18-compaction-capability-seam.md) 负责持久标记约定。
|
||||
- **快照：** 无密钥回放会从带标记的 `compaction/summary` 重建一条规范成功流；[compaction-seam Agent Note](../feature/2026-06-18-compaction-capability-seam.md) 负责持久标记约定。
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-07-24-empty-model-response-is-retryable.md
|
||||
2026-07-24-empty-model-response-is-retryable.md: 16e4a79ec64a1abb5489690f5e064ccb104ec5bc
|
||||
2026-07-24-empty-model-response-is-retryable.zh.md: a6bd3ed5a5f98a1f617be984cea1c9b1a847cfb4
|
||||
2026-07-24-empty-model-response-is-retryable.md: 021c368a25ce8dd277ba431fa905c0621b752fd0
|
||||
2026-07-24-empty-model-response-is-retryable.zh.md: 67809931f959086a4525cec4c879af190e653d4a
|
||||
|
||||
@@ -6,7 +6,7 @@ English | [中文](2026-07-24-empty-model-response-is-retryable.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
Providers occasionally return a degenerate completion: a well-formed stream that carries a terminal `stop` finish and zero content blocks — no text, no reasoning, no tool calls. If an adapter maps this shape to a successful `{kind: 'stop'}` finish, the loop logs an empty `assistant/message` and ends the turn as `completed`. Retry never runs, no failure reaches the caller, and a driver such as goal-session consumes a round without progress.
|
||||
Providers occasionally return a degenerate completion: a well-formed stream that carries a terminal `stop` finish and zero content blocks — no text, no reasoning, no tool calls. If an adapter maps this shape to a successful `{kind: 'stop'}` finish, the loop logs an empty `assistant/message` and ends the turn as `completed`. Retry never runs, no failure reaches the caller, and a driver such as goal-round-driver consumes a round without progress.
|
||||
|
||||
## Decision
|
||||
|
||||
|
||||
@@ -6,7 +6,7 @@ Status: implemented
|
||||
|
||||
## 问题
|
||||
|
||||
提供方偶尔会返回一种退化的 completion：流本身格式完好，以终止性的 `stop` 结束，却没有任何内容块——没有文本、没有推理（reasoning）、没有工具调用。如果适配器把这种形态映射为成功的 `{kind: 'stop'}` 结束，主循环就会记录一条空的 `assistant/message`，并把该轮次以 `completed` 结束。系统不会重试，失败也不会向调用方暴露，而像 goal-session 这样的驱动方会消耗一个 Round，却没有取得任何进展。
|
||||
提供方偶尔会返回一种退化的 completion：流本身格式完好，以终止性的 `stop` 结束，却没有任何内容块——没有文本、没有推理（reasoning）、没有工具调用。如果适配器把这种形态映射为成功的 `{kind: 'stop'}` 结束，主循环就会记录一条空的 `assistant/message`，并把该轮次以 `completed` 结束。系统不会重试，失败也不会向调用方暴露，而像 goal-round-driver 这样的驱动方会消耗一个 Round，却没有取得任何进展。
|
||||
|
||||
## 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 .agents/notes/implemented/bug-fix/2026-07-28-web-gui-feedback-loop.md
|
||||
2026-07-28-web-gui-feedback-loop.md: fa7fcee80dc91ad7ec4a9a994927daa2cc293baa
|
||||
2026-07-28-web-gui-feedback-loop.md: dad85c37dac19c04c15ecb34c210c5376299d50f
|
||||
2026-07-28-web-gui-feedback-loop.zh.md: ea83441efa83ad0c93e8cb1f0daf71ecfeabb69e
|
||||
|
||||
@@ -18,7 +18,7 @@ The prompt makes the agent, rather than the user, own the hidden startup contrac
|
||||
|
||||
The `apps/web` development script and Vite configuration reject serve mode before opening a port. Their diagnostics identify `apps/web` as a build-only shell, explain that only `dsh web` injects `window.__DSH_BOOT__`, and name the production and HMR entry paths. Vite build mode remains unchanged.
|
||||
|
||||
No server restart or replacement is required merely because static artifacts changed. The host reads `index.html` and static assets on each request, while client bundles are also served from their current files with `no-cache`; a refresh of the existing URL is therefore the acceptance path after the relevant shell and plugin bundles are rebuilt. Starting a separate server proves only that a separate server works. If the user explicitly requests another long-running server, the existing managed background-task contract owns its lifecycle and completion notices; shell `&` is not an alternative lifecycle.
|
||||
No server restart or replacement is required merely because static artifacts changed. The host reads `index.html` and static assets on each request, while client bundles are also served from their current files with `no-cache`; a refresh of the existing URL is therefore the acceptance path after the relevant shell and plugin bundles are rebuilt. Starting a separate server proves only that a separate server works. If the user explicitly requests another long-running server, the existing managed background-job contract owns its lifecycle and completion notices; shell `&` is not an alternative lifecycle.
|
||||
|
||||
## Verification
|
||||
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-07-29-human-transcript-append-origin.md
|
||||
2026-07-29-human-transcript-append-origin.md: fe60ab6e745fdc08d84deb4a6e2e4fe8168a23e8
|
||||
2026-07-29-human-transcript-append-origin.zh.md: 02a0d714d509e5057eee616b1721c360f60d110d
|
||||
2026-07-29-human-transcript-append-origin.md: 5e9b5c254d54a7eb189f353f44cd6eb18c1bc2df
|
||||
2026-07-29-human-transcript-append-origin.zh.md: d4845cb9c577c989acf9fd9e451e8ca0793133b6
|
||||
|
||||
@@ -6,7 +6,7 @@ English | [中文](2026-07-29-human-transcript-append-origin.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
The terminal and the host history gateway both treated the model-visible surface as the human transcript. A successful compaction replaces a surface range with one checkpoint node, so the moment that replacement landed the terminal dropped every message it shadowed — conversation the user had already read — and re-ran that destructive rebuild on any later replacement. The same confusion reached pagination: `maxMessages` counted every `user/message` and `assistant/message` in the window, so a model-only replacement copy consumed a page slot the human never filled, and the cut could land between a compaction's log-only `compact/summary` event and the replacement that cites it.
|
||||
The terminal and the host history gateway both treated the model-visible surface as the human transcript. A successful compaction replaces a surface range with one checkpoint node, so the moment that replacement landed the terminal dropped every message it shadowed — conversation the user had already read — and re-ran that destructive rebuild on any later replacement. The same confusion reached pagination: `maxMessages` counted every `user/message` and `assistant/message` in the window, so a model-only replacement copy consumed a page slot the human never filled, and the cut could land between a compaction's log-only `compaction/summary` event and the replacement that cites it.
|
||||
|
||||
Nothing was lost from the log. `Session.events` still held every original message and full tool result; the surface only decides what the model is sent next. The defect was entirely in the projection.
|
||||
|
||||
@@ -16,9 +16,9 @@ Model and human projections are separate, and the event's own marker decides whi
|
||||
|
||||
The terminal replays the transcript from append-origin surface events and keeps a shadowed step's tool cards paired through `transcriptToolCallIds`, which reads the append-origin `assistant/message` rather than surface membership. A landed compaction contributes one dim `… earlier context was compacted …` row at its own log position: the marker reports where the model stopped seeing that history instead of erasing it. The framed checkpoint payload never renders, and both paths classify a surface event by the same marker, so a compaction that arrives live and the same log replayed after resume produce the same transcript. Only replay re-derives `tool/call` pairing: a call event carries no marker of its own and inherits membership from the `assistant/message` that advertised it, which the live listener has necessarily just rendered.
|
||||
|
||||
A checkpoint is recognized through the compaction seam's own contract — `isCompactCheckpointSource`, the backend-independent marker `CompactService` requires on the replacement user message — so the terminal depends on the declared vocabulary, not on the shape of the replacement. `dsh-session-reference` already consumes that predicate to project another session's log; this is the same question asked by a different reader. Other replacements are silent: a pruned `tool/result` and a regenerated `assistant/message` rewrite one node for the model and mark no boundary in the conversation.
|
||||
A checkpoint is recognized through the compaction seam's own contract — `isCompactCheckpointSource`, the backend-independent marker `CompactionEngine` requires on the replacement user message — so the terminal depends on the declared vocabulary, not on the shape of the replacement. `dsh-session-reference` already consumes that predicate to project another session's log; this is the same question asked by a different reader. Other replacements are silent: a pruned `tool/result` and a regenerated `assistant/message` rewrite one node for the model and mark no boundary in the conversation.
|
||||
|
||||
`session.history` counts only append-origin messages toward `maxMessages`. Each page remains one contiguous raw event range, so a compaction's `compact/summary` event stays on the page of the replacement that cites it.
|
||||
`session.history` counts only append-origin messages toward `maxMessages`. Each page remains one contiguous raw event range, so a compaction's `compaction/summary` event stays on the page of the replacement that cites it.
|
||||
|
||||
No persisted event, RPC envelope, compaction transaction, or model-visible surface changed, and no migration is required.
|
||||
|
||||
@@ -36,7 +36,7 @@ The terminal's [archived live compaction progress decision](../../archived/featu
|
||||
|
||||
**Persist a second display transcript.** Rejected: the append-only log already contains the authoritative source material, so a parallel record buys nothing and adds migration and consistency work.
|
||||
|
||||
**Derive the marker from the `compact/*` bracket instead of the checkpoint.** Rejected for the transcript: the bracket is a pair of time-point markers around an operation, while the transcript needs the position where the surface actually changed. The bracket is the right source for progress and duration, which this change does not render.
|
||||
**Derive the marker from the `compaction/*` bracket instead of the checkpoint.** Rejected for the transcript: the bracket is a pair of time-point markers around an operation, while the transcript needs the position where the surface actually changed. The bracket is the right source for progress and duration, which this change does not render.
|
||||
|
||||
**Classify events by re-folding the log, as `session-query` does for search (`current` / `shadowed` / `log-only`).** Rejected: a fold answers a whole-log question, while a projection asks a per-event one that the event's own marker already answers in constant time.
|
||||
|
||||
@@ -46,8 +46,8 @@ Compaction no longer erases terminal history; a session compacted several times
|
||||
|
||||
`rebuildTranscript` now materializes a component per append-origin event in the whole log, and it runs on mount, on a terminal color-scheme change, and on every reasoning toggle. Compaction used to bound that work for exactly the long sessions compaction serves, so the cost now grows with session length instead of with the surface. That is the trade the fix exists to make — preserved history is the point — but a windowing or reuse strategy belongs to whoever first measures a slow rebuild, not to a later profiler wondering why the work grew.
|
||||
|
||||
`dsh-tui` gains a dependency on the `dsh-compact` seam for one pure predicate, mirroring `dsh-session-reference`'s existing use. The terminal still needs no compaction backend at runtime.
|
||||
`dsh-tui` gains a dependency on the `dsh-compaction` seam for one pure predicate, mirroring `dsh-session-reference`'s existing use. The terminal still needs no compaction backend at runtime.
|
||||
|
||||
Two behaviors changed with their tests. The surface-replacement terminal test previously pinned erasure ("hides shadowed tool calls") and now pins preservation plus exactly one marker, including a pruned result copy, a regenerated assistant message, and a foreign plugin's replacement all rendering nothing. The compaction snapshot scenario wrote a `workspace-context` source while claiming to pin compaction; it now writes a real checkpoint source, and its three fixtures are re-recorded to show the preserved prompt, the full tool card, and the marker.
|
||||
Two behaviors changed with their tests. The surface-replacement terminal test previously pinned erasure ("hides shadowed tool calls") and now pins preservation plus exactly one marker, including a pruned result copy, a regenerated assistant message, and a foreign plugin's replacement all rendering nothing. The compaction snapshot scenario wrote a `agent-instructions` source while claiming to pin compaction; it now writes a real checkpoint source, and its three fixtures are re-recorded to show the preserved prompt, the full tool card, and the marker.
|
||||
|
||||
The live/replay equivalence above is fixture-pinned, not only asserted here: `surface-replayed-compaction` mounts with the replacement already stored and records byte-identical to the live path's `surface-after-compaction-wide`. Changing either path breaks that equality, which is the point — the resume projection is what regressed for users, and the two fixtures must move together.
|
||||
|
||||
@@ -6,7 +6,7 @@ Status: implemented
|
||||
|
||||
## 问题
|
||||
|
||||
终端与宿主历史网关都把模型可见的 surface 当作 transcript（文本记录）。一次成功的压缩（compaction）会用一个检查点节点替换一段 surface 范围，因此该替换一落地，终端就丢弃了它所遮蔽的每条消息——那些是用户已经读过的对话——并在此后任何替换到来时重新执行这次破坏性重建。同样的混淆也波及分页：`maxMessages` 统计窗口内的每个 `user/message` 和 `assistant/message`，于是仅供模型使用的替换副本占用了一个人类从未填充的页面额度，而切分点还可能落在压缩的仅日志 `compact/summary` 事件与引用它的替换之间。
|
||||
终端与宿主历史网关都把模型可见的 surface 当作 transcript（文本记录）。一次成功的压缩（compaction）会用一个检查点节点替换一段 surface 范围，因此该替换一落地，终端就丢弃了它所遮蔽的每条消息——那些是用户已经读过的对话——并在此后任何替换到来时重新执行这次破坏性重建。同样的混淆也波及分页：`maxMessages` 统计窗口内的每个 `user/message` 和 `assistant/message`，于是仅供模型使用的替换副本占用了一个人类从未填充的页面额度，而切分点还可能落在压缩的仅日志 `compaction/summary` 事件与引用它的替换之间。
|
||||
|
||||
日志本身没有丢失任何内容。`Session.events` 仍保存着每条原始消息和完整的工具结果；surface 只决定接下来发送给模型的内容。缺陷完全在投影层。
|
||||
|
||||
@@ -16,9 +16,9 @@ Status: implemented
|
||||
|
||||
终端从追加来源的 surface 事件回放 transcript，并通过 `transcriptToolCallIds` 让被遮蔽步骤的工具卡片保持配对：该函数读取追加来源的 `assistant/message`，而不是 surface 成员关系。已落地的压缩会在其自身日志位置贡献一行暗色 `… earlier context was compacted …`：这行标记报告模型从何处起不再看到那段历史，而不是把它抹掉。带框的检查点载荷从不渲染，且两条路径都按同一个标记对 surface 事件分类，因此实时到达的压缩与恢复后回放同一份日志会产生相同的 transcript。只有回放会重新推导 `tool/call` 的配对关系：调用事件自身不携带标记，其归属继承自公布它的 `assistant/message`，而实时监听器必然刚刚渲染过后者。
|
||||
|
||||
检查点通过压缩 seam 自身的约定来识别——`isCompactCheckpointSource`，即 `CompactService` 要求替换用户消息携带的、与后端无关的标记——因此终端依赖的是已声明的词汇，而不是替换的形态。`dsh-session-reference` 已经在用该谓词投影另一个会话的日志；这里只是另一个读者提出同样的问题。其他替换保持静默：被裁剪的 `tool/result` 与重新生成的 `assistant/message` 只是为模型重写一个节点，并不在对话中标出边界。
|
||||
检查点通过压缩 seam 自身的约定来识别——`isCompactCheckpointSource`，即 `CompactionEngine` 要求替换用户消息携带的、与后端无关的标记——因此终端依赖的是已声明的词汇，而不是替换的形态。`dsh-session-reference` 已经在用该谓词投影另一个会话的日志；这里只是另一个读者提出同样的问题。其他替换保持静默：被裁剪的 `tool/result` 与重新生成的 `assistant/message` 只是为模型重写一个节点，并不在对话中标出边界。
|
||||
|
||||
`session.history` 只把追加来源的消息计入 `maxMessages`。每一页仍是一段连续的原始事件区间，因此压缩的 `compact/summary` 事件会与引用它的替换留在同一页。
|
||||
`session.history` 只把追加来源的消息计入 `maxMessages`。每一页仍是一段连续的原始事件区间，因此压缩的 `compaction/summary` 事件会与引用它的替换留在同一页。
|
||||
|
||||
持久事件、RPC 信封、压缩事务与模型可见的 surface 都没有变化，也不需要迁移。
|
||||
|
||||
@@ -36,7 +36,7 @@ Status: implemented
|
||||
|
||||
**持久化第二份展示用 transcript。** 被否决：仅追加的日志已经包含权威源材料，平行 transcript 换不来任何东西，反而增加迁移与一致性工作。
|
||||
|
||||
**用 `compact/*` 括号而不是检查点来推导标记。** 就 transcript 而言被否决：括号是围绕一次操作的一对时间点标记，而 transcript 需要的是 surface 真正发生变化的位置。括号适合作为进度与耗时的来源，而本次变更并不渲染这些。
|
||||
**用 `compaction/*` 括号而不是检查点来推导标记。** 就 transcript 而言被否决：括号是围绕一次操作的一对时间点标记，而 transcript 需要的是 surface 真正发生变化的位置。括号适合作为进度与耗时的来源，而本次变更并不渲染这些。
|
||||
|
||||
**像 `session-query` 为搜索所做的那样重新折叠日志来分类事件（`current`／`shadowed`／`log-only`）。** 被否决：折叠回答的是整份日志的问题，而投影问的是逐事件的问题，事件自身的标记已能以常数时间给出答案。
|
||||
|
||||
@@ -46,8 +46,8 @@ Status: implemented
|
||||
|
||||
`rebuildTranscript` 现在会为整份日志中的每个追加来源事件物化一个组件，并在挂载时、终端配色方案变化时以及每次切换推理（reasoning）时运行。压缩此前正好为压缩所服务的那些长会话限制了这项工作量，因此这份开销现在随会话长度增长，而不再随 surface 增长。这正是本次修复要做的取舍——保留历史才是目的——但窗口化或复用策略属于第一个真正测到重建变慢的人，而不属于日后某个疑惑工作量为何增长的性能分析者。
|
||||
|
||||
`dsh-tui` 为一个纯谓词新增了对 `dsh-compact` seam 的依赖，与 `dsh-session-reference` 现有用法一致。终端在运行时仍然不需要任何压缩后端。
|
||||
`dsh-tui` 为一个纯谓词新增了对 `dsh-compaction` seam 的依赖，与 `dsh-session-reference` 现有用法一致。终端在运行时仍然不需要任何压缩后端。
|
||||
|
||||
两项行为随其测试一起改变。表层替换的终端测试此前钉住的是抹除（「隐藏被遮蔽的工具调用」），现在钉住的是保留加恰好一行标记，其中被裁剪的结果副本、重新生成的 assistant 消息以及来自其他插件的替换都不渲染任何内容。压缩快照场景此前声称钉住压缩，却写入了 `workspace-context` 来源；现在它写入真实的检查点来源，并重新录制三份 fixture（测试前置数据），以显示被保留的提示、完整的工具卡片和那行标记。
|
||||
两项行为随其测试一起改变。表层替换的终端测试此前钉住的是抹除（「隐藏被遮蔽的工具调用」），现在钉住的是保留加恰好一行标记，其中被裁剪的结果副本、重新生成的 assistant 消息以及来自其他插件的替换都不渲染任何内容。压缩快照场景此前声称钉住压缩，却写入了 `agent-instructions` 来源；现在它写入真实的检查点来源，并重新录制三份 fixture（测试前置数据），以显示被保留的提示、完整的工具卡片和那行标记。
|
||||
|
||||
上文的实时／回放等价性由 fixture 钉住，而不只是在此断言：`surface-replayed-compaction` 在挂载时替换已经存在，其录制结果与实时路径的 `surface-after-compaction-wide` 逐字节一致。改动任一路径都会破坏这项相等——这正是要点：回放投影才是当初对用户造成回归的部分，两份 fixture 必须一起变动。
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-07-30-multi-select-custom-answer-composition.md
|
||||
2026-07-30-multi-select-custom-answer-composition.md: 581beec89a0f0018ec2df687f5dfe1b1b5b86d22
|
||||
2026-07-30-multi-select-custom-answer-composition.md: db5be2dbed1108ff63c1fddb166be1de934f98d3
|
||||
2026-07-30-multi-select-custom-answer-composition.zh.md: 796d379312483be5063a3a5d67dd6a0d0e37803e
|
||||
|
||||
@@ -6,7 +6,7 @@ English | [中文](2026-07-30-multi-select-custom-answer-composition.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
The user-interaction result vocabulary carries selected option labels and optional custom text in separate fields, but its original semantics made them mutually exclusive for every question. On a multi-select question, opening or typing the custom answer discarded labels the user had already selected. The TUI returned only the custom text, and the Web host rejected a client response that preserved both fields.
|
||||
The user-questions result vocabulary carries selected option labels and optional custom text in separate fields, but its original semantics made them mutually exclusive for every question. On a multi-select question, opening or typing the custom answer discarded labels the user had already selected. The TUI returned only the custom text, and the Web host rejected a client response that preserved both fields.
|
||||
|
||||
## Decision
|
||||
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-07-30-web-transcript-log-ordered-projection.md
|
||||
2026-07-30-web-transcript-log-ordered-projection.md: f2eda6983ab88a420a4506be7766320dc5da0fa2
|
||||
2026-07-30-web-transcript-log-ordered-projection.zh.md: 84b01c606debcce36fa626898417b0992d54f1a8
|
||||
2026-07-30-web-transcript-log-ordered-projection.md: 102bdab27eddab8f3f61390b0025c0d6ce0c3edc
|
||||
2026-07-30-web-transcript-log-ordered-projection.zh.md: 8e05c70e2cbc8329dd7693028238178c4c4a167e
|
||||
|
||||
@@ -18,7 +18,7 @@ Node order is seq-monotonic by construction, and three things follow. The log-on
|
||||
|
||||
`foldDegraded` is gone from `ConversationSnapshot`, and with it the padding sentinels, the `baseSeq` arithmetic they needed, and `degradedSeqs()`. They existed only to satisfy the core fold's `seq === index` assertion and to survive its throw; the fold they describe is no longer run. Deleting the flag is part of the fix, not cleanup after it — `degradedSeqs()` was already almost the log-ordered projection, reached after a thrown error instead of intended.
|
||||
|
||||
The marker's summary text, replaced-item count, and estimated shadowed-token count come from the checkpoint's cited `compact/summary` event, never from the framed checkpoint payload, which is an instruction envelope written for the model. A window cut that left that event outside makes those fields unavailable, the same soft-fall as a call-less tool result, and a later page supplying the event resolves them.
|
||||
The marker's summary text, replaced-item count, and estimated shadowed-token count come from the checkpoint's cited `compaction/summary` event, never from the framed checkpoint payload, which is an instruction envelope written for the model. A window cut that left that event outside makes those fields unavailable, the same soft-fall as a call-less tool result, and a later page supplying the event resolves them.
|
||||
|
||||
The [manual compaction command](../feature/2026-07-30-queued-manual-compaction.md) returns the summary event's seq as the successful `CommandResult.sourceEventSeq`, and `command/done` persists that optional reference. Chat pairs only a successful named `/compact` command whose reference equals exactly one loaded `CompactionSummaryNode.summaryEventSeq`. The running command first renders `compact · Compacting context…`; after the checkpoint lands, the same React key renders one collapsed `compact` disclosure at the checkpoint's flow position with the count and token estimate. Input rejection, no compactable history, cancellation, and failure remain generic command rows with complete handler-authored text. Automatic compaction has no command reference and keeps the standalone context-compacted marker.
|
||||
|
||||
@@ -28,16 +28,16 @@ The explicit event reference matters because manual compaction permits durable c
|
||||
|
||||
Recognition needs all three conditions, as in the terminal: `event.type === 'user/message'`, the compaction seam's checkpoint plugin source, **and** `isReplacementSurfaceEvent(event)`. A plugin-sourced `user/message` that *appends* is injected context — a session-reference card — not a compaction.
|
||||
|
||||
What is unreachable from a `packages/client/*` program is `dsh-compact`'s **root**, not the package. The root reaches `dsh-session`'s root, whose cordis `Context` merge declares the host `sessions: SessionStore` against the client's `sessions: ISessions` — `TS2717`, the one-program-per-side rule in [development.md](../../../../docs/development.md#typescript-project-layout) — and that holds for a type-only import too, because the collision is a compiler fact rather than a bundler one.
|
||||
What is unreachable from a `packages/client/*` program is `dsh-compaction`'s **root**, not the package. The root reaches `dsh-session`'s root, whose cordis `Context` merge declares the host `sessions: SessionStore` against the client's `sessions: ISessions` — `TS2717`, the one-program-per-side rule in [development.md](../../../../docs/development.md#typescript-project-layout) — and that holds for a type-only import too, because the collision is a compiler fact rather than a bundler one.
|
||||
|
||||
The repo's answer to exactly this is a cordis-free leaf subpath, and this change adds one: `COMPACT_CHECKPOINT_SOURCE` and `isCompactCheckpointSource` now live in `packages/compact/compact/src/checkpoint.ts`, which imports no cordis and augments no module (the `dsh-commands/brand` / `dsh-llm/message` shape), and the root re-exports both so every host-side consumer — the terminal's chat helpers, `dsh-session-reference`'s projection — is unchanged. The adapter pins its literal to that declaration with a type-only import:
|
||||
The repo's answer to exactly this is a cordis-free leaf subpath, and this change adds one: `COMPACT_CHECKPOINT_SOURCE` and `isCompactCheckpointSource` now live in `packages/compaction/compaction/src/checkpoint.ts`, which imports no cordis and augments no module (the `dsh-commands/brand` / `dsh-llm/message` shape), and the root re-exports both so every host-side consumer — the terminal's chat helpers, `dsh-session-reference`'s projection — is unchanged. The adapter pins its literal to that declaration with a type-only import:
|
||||
|
||||
```ts
|
||||
import type { CompactCheckpointSource } from '@deepseek-ai/dsh-compact/checkpoint'
|
||||
const COMPACT_PLUGIN: CompactCheckpointSource['plugin'] = 'compact'
|
||||
import type { CompactionCheckpointSource } from '@deepseek-ai/dsh-compaction/checkpoint'
|
||||
const COMPACT_PLUGIN: CompactionCheckpointSource['plugin'] = 'compact'
|
||||
```
|
||||
|
||||
Renaming the Service Definition's plugin id is now a compile error in the client: `TS2322: Type '"compact"' is not assignable to type '"compaction"'`. The import must stay **type-only** — a value import of any `@deepseek-ai` package that is neither a platform module nor an inline-safe wire layer is rejected by the client purity gate (`packages/client/tsdown.client.ts`), whose own message records that type-only imports are erased and never reach it. A type-only leaf import needs both a `tsconfig.base.json` `paths` entry and `{"path": "../../compact/compact"}` in `packages/client/runtime/tsconfig.json` `references`: composite `rootDir` rules apply to erased imports as well, and without the reference the diagnostic is `TS6059`/`TS6307`.
|
||||
Renaming the Service Definition's plugin id is now a compile error in the client: `TS2322: Type '"compact"' is not assignable to type '"compaction"'`. The import must stay **type-only** — a value import of any `@deepseek-ai` package that is neither a platform module nor an inline-safe wire layer is rejected by the client purity gate (`packages/client/tsdown.client.ts`), whose own message records that type-only imports are erased and never reach it. A type-only leaf import needs both a `tsconfig.base.json` `paths` entry and `{"path": "../../compaction/compaction"}` in `packages/client/runtime/tsconfig.json` `references`: composite `rootDir` rules apply to erased imports as well, and without the reference the diagnostic is `TS6059`/`TS6307`.
|
||||
|
||||
`packages/client/ui-conversation/tests/conversation-node-definitions.client.spec.ts` is the behavioral half, driving the compaction Definition with checkpoint and provenance records and proving that an older page can fill missing summary data. The Definition's type-only leaf import keeps the client isolated from the compact package root and the host-side `Context` merges reachable through it.
|
||||
|
||||
@@ -49,7 +49,7 @@ The unmerged manual-compaction-queueing branch fixes the same interleaving bug b
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
**Value-import the predicate** from the new leaf and add `dsh-compact` to the client `INLINE_SAFE` allowlist. Rejected: the client needs the plugin id, not the predicate — a type is enough, and an erased import never reaches the purity gate, so nothing has to be admitted to it. The allowlist would only matter for a value import, and there it is a poor trade: `INLINE_SAFE` matches on specifier *prefix*, so admitting the package admits its cordis-importing root along with the leaf.
|
||||
**Value-import the predicate** from the new leaf and add `dsh-compaction` to the client `INLINE_SAFE` allowlist. Rejected: the client needs the plugin id, not the predicate — a type is enough, and an erased import never reaches the purity gate, so nothing has to be admitted to it. The allowlist would only matter for a value import, and there it is a poor trade: `INLINE_SAFE` matches on specifier *prefix*, so admitting the package admits its cordis-importing root along with the leaf.
|
||||
|
||||
**A bare shape rule** — any replacement `user/message` is a compaction. Rejected: correct today only because compaction is the sole producer of replacement `user/message`s, with nothing to catch it if that changes. The pinning spec costs one file and removes exactly that risk.
|
||||
|
||||
@@ -61,7 +61,7 @@ The unmerged manual-compaction-queueing branch fixes the same interleaving bug b
|
||||
|
||||
**Pair the nearest `/compact` row with the next checkpoint.** Rejected: context injection may land between them, and concurrent or malformed lifecycle records must degrade without stealing another checkpoint. The command result instead names the authoritative summary event, and ambiguous references pair nothing.
|
||||
|
||||
**Parse the English settlement text for item and token counts.** Rejected: handler copy is presentation text, not a stable data contract. The marker reads the structured `compact/summary` payload already owning both values.
|
||||
**Parse the English settlement text for item and token counts.** Rejected: handler copy is presentation text, not a stable data contract. The marker reads the structured `compaction/summary` payload already owning both values.
|
||||
|
||||
## Consequences
|
||||
|
||||
|
||||
@@ -18,7 +18,7 @@ surface 顺序还让另外两个问题成为结构性的。一次替换之后它
|
||||
|
||||
`foldDegraded` 从 `ConversationSnapshot` 消失，随之消失的是哨兵填充、它们所需的 `baseSeq` 算术，以及 `degradedSeqs()`。它们的存在只为满足核心 fold 的 `seq === index` 断言并在其抛错时存活；它们所描述的 fold 已不再运行。删除该标志是修复的一部分，而非修复之后的清理——`degradedSeqs()` 本身已几乎就是按日志顺序的投影，只是作为抛错后的落点而非本意到达。
|
||||
|
||||
标记的摘要文本、被替换条目数量和估算的被遮蔽 token 数量都来自检查点引用的 `compact/summary` 事件，绝不取自成框的检查点载荷——那是为模型撰写的指令信封。窗口切分把该事件留在窗口外时这些字段不可用，与无调用的工具结果同一种软退让；后续补上该事件的分页会解析出它们。
|
||||
标记的摘要文本、被替换条目数量和估算的被遮蔽 token 数量都来自检查点引用的 `compaction/summary` 事件，绝不取自成框的检查点载荷——那是为模型撰写的指令信封。窗口切分把该事件留在窗口外时这些字段不可用，与无调用的工具结果同一种软退让；后续补上该事件的分页会解析出它们。
|
||||
|
||||
[手动压缩命令](../feature/2026-07-30-queued-manual-compaction.md)会把摘要事件的 seq 作为成功结果的 `CommandResult.sourceEventSeq` 返回，`command/done` 则持久化这项可选引用。Chat 只会配对成功且名称为 `/compact`、其引用恰好等于唯一一个已加载 `CompactionSummaryNode.summaryEventSeq` 的命令。运行中的命令先渲染为 `compact · Compacting context…`；检查点落地后，同一个 React key 会在检查点的消息流位置渲染一条收起的 `compact` 展开项，并显示条目数量和 token 估算值。输入被拒绝、没有可压缩历史、取消和失败时仍使用通用命令行，并保留处理器撰写的完整文本。自动压缩没有命令引用，继续使用独立的上下文已压缩标记。
|
||||
|
||||
@@ -28,16 +28,16 @@ surface 顺序还让另外两个问题成为结构性的。一次替换之后它
|
||||
|
||||
识别需要三个条件同时成立，与终端一致：`event.type === 'user/message'`、压缩缝隙的检查点插件来源，**以及** `isReplacementSurfaceEvent(event)`。一条 append 的插件来源 `user/message` 是注入上下文——跨会话引用卡片——不是压缩。
|
||||
|
||||
从 `packages/client/*` 程序无法到达的是 `dsh-compact` 的**根部**，而不是这个包。根部会到达 `dsh-session` 的根部，后者的 cordis `Context` 合并声明了宿主侧 `sessions: SessionStore`，与客户端的 `sessions: ISessions` 冲突——`TS2717`，即 [development.md](../../../../docs/development.md#typescript-project-layout) 中每侧一个 program 的规则；这一点对仅类型导入同样成立，因为该冲突是编译器事实而非打包器事实。
|
||||
从 `packages/client/*` 程序无法到达的是 `dsh-compaction` 的**根部**，而不是这个包。根部会到达 `dsh-session` 的根部，后者的 cordis `Context` 合并声明了宿主侧 `sessions: SessionStore`，与客户端的 `sessions: ISessions` 冲突——`TS2717`，即 [development.md](../../../../docs/development.md#typescript-project-layout) 中每侧一个 program 的规则；这一点对仅类型导入同样成立，因为该冲突是编译器事实而非打包器事实。
|
||||
|
||||
本仓库对这一情形的既有答案是不含 cordis 的叶子子路径，本次变更就新增了一个：`COMPACT_CHECKPOINT_SOURCE` 与 `isCompactCheckpointSource` 现在住在 `packages/compact/compact/src/checkpoint.ts`，它不导入 cordis、也不增强任何模块（即 `dsh-commands/brand` / `dsh-llm/message` 的形状），而包根重新导出两者，因此每个宿主侧消费方——终端的 chat helper、`dsh-session-reference` 的投影——都不需改动。适配器用仅类型导入把它的字面量钉在该声明上：
|
||||
本仓库对这一情形的既有答案是不含 cordis 的叶子子路径，本次变更就新增了一个：`COMPACT_CHECKPOINT_SOURCE` 与 `isCompactCheckpointSource` 现在住在 `packages/compaction/compaction/src/checkpoint.ts`，它不导入 cordis、也不增强任何模块（即 `dsh-commands/brand` / `dsh-llm/message` 的形状），而包根重新导出两者，因此每个宿主侧消费方——终端的 chat helper、`dsh-session-reference` 的投影——都不需改动。适配器用仅类型导入把它的字面量钉在该声明上：
|
||||
|
||||
```ts
|
||||
import type { CompactCheckpointSource } from '@deepseek-ai/dsh-compact/checkpoint'
|
||||
const COMPACT_PLUGIN: CompactCheckpointSource['plugin'] = 'compact'
|
||||
import type { CompactionCheckpointSource } from '@deepseek-ai/dsh-compaction/checkpoint'
|
||||
const COMPACT_PLUGIN: CompactionCheckpointSource['plugin'] = 'compact'
|
||||
```
|
||||
|
||||
重命名 Service Definition 的插件 id 现在会在客户端产生编译错误：`TS2322: Type '"compact"' is not assignable to type '"compaction"'`。该导入必须保持**仅类型**——任何既非平台模块又非 inline-safe wire 层的 `@deepseek-ai` 包值导入都会被客户端纯度门禁（`packages/client/tsdown.client.ts`）拒绝，而它自己的报错信息就记录着仅类型导入会被擦除、永不抵达该门禁。仅类型的叶子导入同时需要 `tsconfig.base.json` 的一条 `paths` 条目和 `packages/client/runtime/tsconfig.json` `references` 中的 `{"path": "../../compact/compact"}`：composite 的 `rootDir` 规则同样适用于被擦除的导入，缺少该引用时的诊断是 `TS6059`/`TS6307`。
|
||||
重命名 Service Definition 的插件 id 现在会在客户端产生编译错误：`TS2322: Type '"compact"' is not assignable to type '"compaction"'`。该导入必须保持**仅类型**——任何既非平台模块又非 inline-safe wire 层的 `@deepseek-ai` 包值导入都会被客户端纯度门禁（`packages/client/tsdown.client.ts`）拒绝，而它自己的报错信息就记录着仅类型导入会被擦除、永不抵达该门禁。仅类型的叶子导入同时需要 `tsconfig.base.json` 的一条 `paths` 条目和 `packages/client/runtime/tsconfig.json` `references` 中的 `{"path": "../../compaction/compaction"}`：composite 的 `rootDir` 规则同样适用于被擦除的导入，缺少该引用时的诊断是 `TS6059`/`TS6307`。
|
||||
|
||||
`packages/client/ui-conversation/tests/conversation-node-definitions.client.spec.ts` 是行为侧的另一半，用检查点与溯源记录驱动压缩 Definition，并证明后续加载的旧分页可以补齐缺失的摘要数据。Definition 仅类型导入该叶子路径，使客户端继续与 compact 包根及经由它可达的宿主侧 `Context` 合并隔离。
|
||||
|
||||
@@ -49,7 +49,7 @@ const COMPACT_PLUGIN: CompactCheckpointSource['plugin'] = 'compact'
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
**从新叶子值导入该谓词**，并把 `dsh-compact` 加入客户端 `INLINE_SAFE` 白名单。已拒绝：客户端需要的是插件 id，不是谓词——一个类型就够了，而被擦除的导入根本不会抵达纯度门禁，因此无需向它放行任何东西。白名单只在值导入时才有意义，而在那里它是笔糟糕的交换：`INLINE_SAFE` 按模块说明符*前缀*匹配，因此放行该包会连它那个会导入 cordis 的根部一起放行。
|
||||
**从新叶子值导入该谓词**，并把 `dsh-compaction` 加入客户端 `INLINE_SAFE` 白名单。已拒绝：客户端需要的是插件 id，不是谓词——一个类型就够了，而被擦除的导入根本不会抵达纯度门禁，因此无需向它放行任何东西。白名单只在值导入时才有意义，而在那里它是笔糟糕的交换：`INLINE_SAFE` 按模块说明符*前缀*匹配，因此放行该包会连它那个会导入 cordis 的根部一起放行。
|
||||
|
||||
**一条纯形状规则**——任何 replacement `user/message` 都是压缩。已拒绝：它今天正确只因为压缩是 replacement `user/message` 的唯一生产者，一旦这点改变便无任何机制能捕获。那个 pin 测试只花一个文件，就精确消除了这一风险。
|
||||
|
||||
@@ -61,7 +61,7 @@ const COMPACT_PLUGIN: CompactCheckpointSource['plugin'] = 'compact'
|
||||
|
||||
**把最近的 `/compact` 行与下一个检查点配对。** 已拒绝：两者之间可能落入上下文注入，并发或格式异常的生命周期记录也必须降级而不误取其他检查点。命令结果则指明权威摘要事件；引用存在歧义时不配对任何内容。
|
||||
|
||||
**解析英文结算文本中的条目数量和 token 数量。** 已拒绝：处理器文案是呈现文本，而非稳定的数据约定。标记读取本已持有这两个值的结构化 `compact/summary` 载荷。
|
||||
**解析英文结算文本中的条目数量和 token 数量。** 已拒绝：处理器文案是呈现文本，而非稳定的数据约定。标记读取本已持有这两个值的结构化 `compaction/summary` 载荷。
|
||||
|
||||
## Consequences
|
||||
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-07-31-fork-anchor-floors-to-event-seq.md
|
||||
2026-07-31-fork-anchor-floors-to-event-seq.md: 2cc8d66942442aca69c930be880cc41d56bced13
|
||||
2026-07-31-fork-anchor-floors-to-event-seq.zh.md: 75fc1885f344e88c9ded575bc4aea58562e55673
|
||||
2026-07-31-fork-anchor-floors-to-event-seq.md: 760e73266570b149966be6af8264cd3699ffb7e0
|
||||
2026-07-31-fork-anchor-floors-to-event-seq.zh.md: c25a69462b7cbff4a6194d24793982479cae24e4
|
||||
|
||||
@@ -14,7 +14,7 @@ The host's cut rule was never the obstacle. An aborted turn ends with a logged `
|
||||
|
||||
## Decision
|
||||
|
||||
`SessionsService.fork` floors `atSeq` before the RPC. The fractional-seq convention belongs to `dsh-client-runtime`, which mints it in both the live and replay projections, so the same package converts it back to a real event seq at the wire boundary instead of every UI caller remembering to. Integer anchors are unaffected.
|
||||
`SessionRuntime.fork` floors `atSeq` before the RPC. The fractional-seq convention belongs to `dsh-client-runtime`, which mints it in both the live and replay projections, so the same package converts it back to a real event seq at the wire boundary instead of every UI caller remembering to. Integer anchors are unaffected.
|
||||
|
||||
Flooring lands inside the anchor's own turn rather than clipping backward: every turn opens with `turn/start`, so `turnEnd.seq - 1` cannot itself be an earlier turn's `turn/end`. The host's first-`turn/end`-at-or-after rule then closes on the turn the reader clicked, matching the whole-turn semantics the message-level fork button already promised for completed turns.
|
||||
|
||||
|
||||
@@ -14,7 +14,7 @@ host 的切分规则从来不是障碍。被中止的轮次会记录一条 reaso
|
||||
|
||||
## 决策
|
||||
|
||||
`SessionsService.fork` 在发起 RPC 前对 `atSeq` 向下取整。分数 seq 这个约定属于 `dsh-client-runtime`，实时投影和回放投影都由它生成，因此也由同一个包在跨出 wire 边界时把它换回真实事件 seq，而不是要求每个 UI 调用方各自记得转换。整数锚点不受影响。
|
||||
`SessionRuntime.fork` 在发起 RPC 前对 `atSeq` 向下取整。分数 seq 这个约定属于 `dsh-client-runtime`，实时投影和回放投影都由它生成，因此也由同一个包在跨出 wire 边界时把它换回真实事件 seq，而不是要求每个 UI 调用方各自记得转换。整数锚点不受影响。
|
||||
|
||||
向下取整落在锚点自身所在的轮次内，不会回退：每一轮都以 `turn/start` 开头，所以 `turnEnd.seq - 1` 不可能是上一轮的 `turn/end`。host 随后按「首个位于锚点或其之后的 `turn/end`」收口，命中的正是读者点击的那一轮，与消息级 fork 按钮在已完成轮次上一贯承诺的整轮语义一致。
|
||||
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-07-31-same-basename-workspace-adoption.md
|
||||
2026-07-31-same-basename-workspace-adoption.md: 1192558632fdc8bd732ea59f0eca5051f49f5d2c
|
||||
2026-07-31-same-basename-workspace-adoption.zh.md: 722e747e0bd03da42a5f2555ee2fb3e46522cca2
|
||||
2026-07-31-same-basename-workspace-adoption.md: a634972448d8a3fea3d08c5713602cec0584a44e
|
||||
2026-07-31-same-basename-workspace-adoption.zh.md: f66946842e82ec38601192dd536eabfb9a0ffd69
|
||||
|
||||
@@ -10,7 +10,7 @@ A Workspace is identified by its stable id and canonical directory path, while i
|
||||
|
||||
## Decision
|
||||
|
||||
`ctx.workspace.create(path, title?)` treats canonical path as the only uniqueness key. Repeating the same path remains idempotent and preserves the registered title. Different canonical paths create different Workspace records and may share a title; when no title is supplied, each record still derives its title from `basename(path)` without suffixing or rewriting it.
|
||||
`ctx.workspaceRegistry.create(path, title?)` treats canonical path as the only uniqueness key. Repeating the same path remains idempotent and preserves the registered title. Different canonical paths create different Workspace records and may share a title; when no title is supplied, each record still derives its title from `basename(path)` without suffixing or rewriting it.
|
||||
|
||||
The Host's `workspace.create({ path })` adoption route inherits that rule. The Workspace manager, picker, grouping tree, selection, rename, deletion, and Session creation continue to use `WorkspaceId`, so equal labels neither merge records nor redirect an operation. The sidebar hover card exposes each canonical path when the labels need disambiguation.
|
||||
|
||||
|
||||
@@ -10,7 +10,7 @@ Workspace 的身份由其稳定 id 和规范目录路径确定，标题则是可
|
||||
|
||||
## 决策
|
||||
|
||||
`ctx.workspace.create(path, title?)` 仅以规范路径作为唯一性键。重复传入同一路径仍保持幂等，并保留已注册的标题。不同的规范路径会创建不同的 Workspace 记录，且可以共用标题；未提供标题时，每条记录仍从 `basename(path)` 派生标题，不添加后缀，也不改写标题。
|
||||
`ctx.workspaceRegistry.create(path, title?)` 仅以规范路径作为唯一性键。重复传入同一路径仍保持幂等，并保留已注册的标题。不同的规范路径会创建不同的 Workspace 记录，且可以共用标题；未提供标题时，每条记录仍从 `basename(path)` 派生标题，不添加后缀，也不改写标题。
|
||||
|
||||
Host 的 `workspace.create({ path })` 接纳入口沿用该规则。Workspace 管理器、选择器、分组树、选择、重命名、删除和 Session 创建仍使用 `WorkspaceId`，因此相同标签既不会合并记录，也不会把操作指向其他记录。需要区分相同标签时，侧边栏悬停详情卡会显示各自的规范路径。
|
||||
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-01-ask-user-delegated-caller-guard.md
|
||||
2026-08-01-ask-user-delegated-caller-guard.md: 0350a7383f7ace6ecd742c98db18f8b977720cf9
|
||||
2026-08-01-ask-user-delegated-caller-guard.zh.md: 811a550bacc6f9019fdd08c7b555bc11753a9477
|
||||
2026-08-01-ask-user-delegated-caller-guard.md: ed4bfae1b647cdbb58e9f09abe544a9ac58b6bf5
|
||||
2026-08-01-ask-user-delegated-caller-guard.zh.md: 79ace1beb10c8f1d6d524018cdc8d4e1c612b5cc
|
||||
|
||||
@@ -8,11 +8,11 @@ English | [中文](2026-08-01-ask-user-delegated-caller-guard.zh.md)
|
||||
|
||||
A one-shot subagent that calls `ask_user_question` can block indefinitely. The call waits for a human answer, but the child has no independently owned human channel, so the child's completion and the parent waiting on that completion both stall.
|
||||
|
||||
Durable session lineage cannot decide whether an answerer exists. A child session may later be resumed as a new top-level runtime root, while a live runtime-owned child may carry a zero or absent durable delegation depth. Error guidance at the shared seam must also fit every consumer: `exit_plan_mode` uses `ctx.userInteraction.ask()` without calling `ask_user_question`.
|
||||
Durable session lineage cannot decide whether an answerer exists. A child session may later be resumed as a new top-level runtime root, while a live runtime-owned child may carry a zero or absent durable delegation depth. Error guidance at the shared seam must also fit every consumer: `exit_plan_mode` uses `ctx.userQuestions.ask()` without calling `ask_user_question`.
|
||||
|
||||
## Decision
|
||||
|
||||
When `AskUserQuestionRequest.agent` is present, `UserInteractionService.ask()` authenticates the exact live agent through `ctx.agents` and admits it only when `ctx.agents.roots()` contains that instance. A missing registry or stale same-id object fails with `CALLER_NOT_LIVE`; a live agent owned by another live agent fails with `DELEGATED_CALLER`. The check runs after the existing aborted and empty-batch guards and before intent validation or provider dispatch, so an owned child never creates a UI wait.
|
||||
When `AskUserQuestionRequest.agent` is present, `UserQuestionService.ask()` authenticates the exact live agent through `ctx.agents` and admits it only when `ctx.agents.roots()` contains that instance. A missing registry or stale same-id object fails with `CALLER_NOT_LIVE`; a live agent owned by another live agent fails with `DELEGATED_CALLER`. The check runs after the existing aborted and empty-batch guards and before intent validation or provider dispatch, so an owned child never creates a UI wait.
|
||||
|
||||
Runtime ownership is the authority. A lineage-bearing session resumed without an owner is a runtime root and may ask; a live child remains ineligible even when its durable `delegationDepth` is zero. Agentless programmatic calls retain the existing provider path.
|
||||
|
||||
@@ -24,7 +24,7 @@ This safety boundary is independent of the browser's composer election. The prop
|
||||
|
||||
**Use `session.header.delegationDepth > 0`.** Rejected because durable lineage survives resume and does not attest the current process-local owner. It rejects valid resumed roots and can admit a live child whose durable header is incomplete.
|
||||
|
||||
**Reject only inside `dsh-tool-ask-user`.** Rejected because `exit_plan_mode` and direct callers share `ctx.userInteraction.ask()`. The service is the narrow operation boundary common to every human-interaction consumer.
|
||||
**Reject only inside `dsh-tool-ask-user`.** Rejected because `exit_plan_mode` and direct callers share `ctx.userQuestions.ask()`. The service is the narrow operation boundary common to every human-interaction consumer.
|
||||
|
||||
**Tell the child to delegate upward or wait for forwarding.** Rejected because one-shot delegation exposes no child-to-parent request channel and no answer-forwarding protocol. The only guaranteed return path is the child's final result.
|
||||
|
||||
|
||||
@@ -8,11 +8,11 @@ Status: implemented
|
||||
|
||||
一次性 subagent 调用 `ask_user_question` 时可能无限阻塞。该调用会等待人类回答，但子级没有由自身独立拥有的人类交互通道，因此子级无法完成，等待其完成的父级也会随之停滞。
|
||||
|
||||
持久化会话谱系无法判断应答者是否存在。子会话之后可能恢复为新的顶层运行时根，而运行时中归属于其他 agent（智能体）的存活子级，其持久化委托深度却可能为零或缺失。共享 seam 上的错误指引还必须适用于每个消费方：`exit_plan_mode` 会使用 `ctx.userInteraction.ask()`，但不会调用 `ask_user_question`。
|
||||
持久化会话谱系无法判断应答者是否存在。子会话之后可能恢复为新的顶层运行时根，而运行时中归属于其他 agent（智能体）的存活子级，其持久化委托深度却可能为零或缺失。共享 seam 上的错误指引还必须适用于每个消费方：`exit_plan_mode` 会使用 `ctx.userQuestions.ask()`，但不会调用 `ask_user_question`。
|
||||
|
||||
## 决策
|
||||
|
||||
如果存在 `AskUserQuestionRequest.agent`，`UserInteractionService.ask()` 会通过 `ctx.agents` 验证该 agent 就是注册表中的存活实例，并且只在 `ctx.agents.roots()` 包含该实例时才允许调用。缺失注册表或传入仅 id 相同的陈旧对象时，以 `CALLER_NOT_LIVE` 失败；存活 agent 归属于另一个存活 agent 时，以 `DELEGATED_CALLER` 失败。该检查位于现有的已中止和空批次守卫之后、意图校验或提供方分派之前，因此归属于其他 agent 的子级绝不会触发 UI 等待。
|
||||
如果存在 `AskUserQuestionRequest.agent`，`UserQuestionService.ask()` 会通过 `ctx.agents` 验证该 agent 就是注册表中的存活实例，并且只在 `ctx.agents.roots()` 包含该实例时才允许调用。缺失注册表或传入仅 id 相同的陈旧对象时，以 `CALLER_NOT_LIVE` 失败；存活 agent 归属于另一个存活 agent 时，以 `DELEGATED_CALLER` 失败。该检查位于现有的已中止和空批次守卫之后、意图校验或提供方分派之前，因此归属于其他 agent 的子级绝不会触发 UI 等待。
|
||||
|
||||
以运行时所有权为权限依据。携带谱系的会话在无所有者的情况下恢复时就是运行时根，可以提问；存活子级即使持久化 `delegationDepth` 为零，仍无资格提问。不带 agent 的程序化调用继续沿用现有提供方路径。
|
||||
|
||||
@@ -24,7 +24,7 @@ Status: implemented
|
||||
|
||||
**使用 `session.header.delegationDepth > 0`。** 不予采用：持久化谱系会在恢复后继续存在，却不能证明当前进程内所有者。该方案会拒绝有效的已恢复根，也可能放行持久化 header 不完整的存活子级。
|
||||
|
||||
**仅在 `dsh-tool-ask-user` 内拒绝。** 不予采用：`exit_plan_mode` 与直接调用方共用 `ctx.userInteraction.ask()`。服务是所有人机交互消费方共同经过的最窄操作边界。
|
||||
**仅在 `dsh-tool-ask-user` 内拒绝。** 不予采用：`exit_plan_mode` 与直接调用方共用 `ctx.userQuestions.ask()`。服务是所有人机交互消费方共同经过的最窄操作边界。
|
||||
|
||||
**让子级向上委托或等待转发。** 不予采用：一次性委托没有公开从子级向父级请求的通道，也没有回答转发协议。唯一有保证的返回路径是子级的最终结果。
|
||||
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-03-cli-signal-shutdown-escalation.md
|
||||
2026-08-03-cli-signal-shutdown-escalation.md: 173d06482cd8a1fcbb985763cc313e3f9b170bc6
|
||||
2026-08-03-cli-signal-shutdown-escalation.md: 0373a93314e0478bc8d0a8feff126295051cc2a0
|
||||
2026-08-03-cli-signal-shutdown-escalation.zh.md: 88ca7cad25444afc908e83c6aa82bdd21c46d627
|
||||
|
||||
@@ -12,7 +12,7 @@ A user then reproduced the headless command hanging immediately after the observ
|
||||
|
||||
The latch then turned that telemetry defect into an unkillable CLI: normal completion was already awaiting the single-shot root disposal; the first SIGINT joined the same pending disposal and set the signal latch; later SIGINTs returned at the latch, so the process had no remaining escape. A signal received before normal completion had the same unbounded wait. Web used the same latch shape.
|
||||
|
||||
Telemetry's own timeouts cannot prove that the whole plugin tree settles. Any current or future disposer can wedge, and the process boundary must preserve both a graceful first attempt and a user-controlled way out.
|
||||
SessionTelemetryBackend's own timeouts cannot prove that the whole plugin tree settles. Any current or future disposer can wedge, and the process boundary must preserve both a graceful first attempt and a user-controlled way out.
|
||||
|
||||
## Decision
|
||||
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-03-hmr-initial-scan-boot-deadlock.md
|
||||
2026-08-03-hmr-initial-scan-boot-deadlock.md: 1a70fbafc74a1bf7024c675ddad82acefc995b72
|
||||
2026-08-03-hmr-initial-scan-boot-deadlock.md: e578b4d5fa973ee8f4986e570264c328f58bedc1
|
||||
2026-08-03-hmr-initial-scan-boot-deadlock.zh.md: 7123e423aab1293d138a1c24cb0dded00a83c89a
|
||||
|
||||
@@ -34,7 +34,7 @@ With both in place a failing boot follows the intended path: the single apply fa
|
||||
|
||||
A config file edit landing inside the watcher's startup scan window is now picked up by the next `change` event rather than the scan itself; steady-state reload behavior is unchanged.
|
||||
|
||||
One latent gap remains: a config edit made during a *failing* initial apply can still queue a refresh that the rollback's HMR teardown waits on — the same deadlock shape with a human-scale trigger window of one failing boot. If that ever bites, the fix is refresh-task cancellation at HMR teardown.
|
||||
One latent gap remains: a config edit made during a *failing* initial apply can still queue a refresh that the rollback's HMR teardown waits on — the same deadlock shape with a human-scale trigger window of one failing boot. If that ever bites, the fix is refresh-job cancellation at HMR teardown.
|
||||
|
||||
## Testing
|
||||
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-05-context-meter-blind-to-compaction.md
|
||||
2026-08-05-context-meter-blind-to-compaction.md: b90208eda25101aeb55130cd1b6563dbfaee8a9a
|
||||
2026-08-05-context-meter-blind-to-compaction.zh.md: 85387c50ebc981fc2f7f02d07432da677f69ef90
|
||||
2026-08-05-context-meter-blind-to-compaction.md: daf11b41236943d5fb35e9363c128ce470c7f4e9
|
||||
2026-08-05-context-meter-blind-to-compaction.zh.md: cf011d9d4abda003c3ab3d37227a9ebd4e1a4557
|
||||
|
||||
@@ -6,7 +6,7 @@ English | [中文](2026-08-05-context-meter-blind-to-compaction.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
The composer's [context meter](../feature/2026-08-05-composer-context-meter-breakdown.md) took its ring, percentage, and `~used / capacity` header from `contextPressure.pressureTokens`, the newest provider-reported prompt size. That number moves only when a request reports usage, and compaction reports none: `compact-basic` summarizes through a direct `ctx.llm.stream()` call and appends `compact/start`, `compact/summary`, the replacement `user/message`, and `compact/end` — no `assistant/message`, no usage chunk.
|
||||
The composer's [context meter](../feature/2026-08-05-composer-context-meter-breakdown.md) took its ring, percentage, and `~used / capacity` header from `contextPressure.pressureTokens`, the newest provider-reported prompt size. That number moves only when a request reports usage, and compaction reports none: `compaction-basic` summarizes through a direct `ctx.llm.stream()` call and appends `compaction/start`, `compaction/summary`, the replacement `user/message`, and `compaction/end` — no `assistant/message`, no usage chunk.
|
||||
|
||||
So the meter was frozen across the one action taken to change it. Driving a real `compactNow` through the agent loop:
|
||||
|
||||
@@ -43,4 +43,4 @@ The panel's composition rows still do not sum to the header, and now for one cle
|
||||
|
||||
## Testing
|
||||
|
||||
`packages/llm/token-meter/tests/token-usage-projection.spec.ts` covers the carry-forward across surface growth and a compaction (the sample holding still while the projection shrinks) and the zero clamp when heuristic error would drive the figure negative. `packages/client/ui-conversation/tests/context-meter.client.spec.tsx` pins the ring reading the projected figure, and `chat-stats.spec.tsx` pins `contextOccupancy`'s preference and its fallback. The end-to-end numbers above came from driving `BasicCompactService.compactNow` through a real `AgentLoop` with the projection registry mounted.
|
||||
`packages/llm/token-meter/tests/token-usage-projection.spec.ts` covers the carry-forward across surface growth and a compaction (the sample holding still while the projection shrinks) and the zero clamp when heuristic error would drive the figure negative. `packages/client/ui-conversation/tests/context-meter.client.spec.tsx` pins the ring reading the projected figure, and `chat-stats.spec.tsx` pins `contextOccupancy`'s preference and its fallback. The end-to-end numbers above came from driving `BasicCompactionEngine.compactNow` through a real `AgentLoop` with the projection registry mounted.
|
||||
|
||||
@@ -6,7 +6,7 @@ Status: implemented
|
||||
|
||||
## 问题
|
||||
|
||||
composer 的[上下文仪表](../feature/2026-08-05-composer-context-meter-breakdown.md)的圆环、百分比与 `~已用 / 容量` 标题都取自 `contextPressure.pressureTokens`，即提供方报告的最新提示词规模。这个数字只在某个请求报告用量时才会移动，而压缩（compaction）不报告用量：`compact-basic` 通过直连的 `ctx.llm.stream()` 调用生成摘要，只追加 `compact/start`、`compact/summary`、用作替换的 `user/message` 和 `compact/end`——没有 `assistant/message`，也没有用量分片。
|
||||
composer 的[上下文仪表](../feature/2026-08-05-composer-context-meter-breakdown.md)的圆环、百分比与 `~已用 / 容量` 标题都取自 `contextPressure.pressureTokens`，即提供方报告的最新提示词规模。这个数字只在某个请求报告用量时才会移动，而压缩（compaction）不报告用量：`compaction-basic` 通过直连的 `ctx.llm.stream()` 调用生成摘要，只追加 `compaction/start`、`compaction/summary`、用作替换的 `user/message` 和 `compaction/end`——没有 `assistant/message`，也没有用量分片。
|
||||
|
||||
于是在唯一一个专门用来改变它的操作面前，这块仪表纹丝不动。通过真实的 agent loop（智能体循环）驱动一次 `compactNow`：
|
||||
|
||||
@@ -43,4 +43,4 @@ AFTER compact: ring=4% header=~4227/100000 rows=[system 18, tools 0, messag
|
||||
|
||||
## 测试
|
||||
|
||||
`packages/llm/token-meter/tests/token-usage-projection.spec.ts` 覆盖了投影值在表层增长与一次压缩期间的延续更新（样本保持不动而投影值缩小），以及启发式误差会把数字压到负数时的零钳制。`packages/client/ui-conversation/tests/context-meter.client.spec.tsx` 钉住圆环读取投影值这一点，`chat-stats.spec.tsx` 钉住 `contextOccupancy` 的优先级与回退。上面那组端到端数字来自在挂载了投影注册表的真实 `AgentLoop` 上驱动 `BasicCompactService.compactNow`。
|
||||
`packages/llm/token-meter/tests/token-usage-projection.spec.ts` 覆盖了投影值在表层增长与一次压缩期间的延续更新（样本保持不动而投影值缩小），以及启发式误差会把数字压到负数时的零钳制。`packages/client/ui-conversation/tests/context-meter.client.spec.tsx` 钉住圆环读取投影值这一点，`chat-stats.spec.tsx` 钉住 `contextOccupancy` 的优先级与回退。上面那组端到端数字来自在挂载了投影注册表的真实 `AgentLoop` 上驱动 `BasicCompactionEngine.compactNow`。
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-06-api-key-format-validation.md
|
||||
2026-08-06-api-key-format-validation.md: 356891c01c003f26d8edd092ebde8887e17d2448
|
||||
2026-08-06-api-key-format-validation.zh.md: e996b6bf407b1849f8ffcd8fec31b060e38f9223
|
||||
2026-08-06-api-key-format-validation.md: e2dcb91cba703cf95994426c67c4203effad290a
|
||||
2026-08-06-api-key-format-validation.zh.md: e74cb58ee0e0be9ec9ec30123e7eeffa3f3db657
|
||||
|
||||
@@ -46,7 +46,7 @@ The rule applies to a value that was *provided*; deciding whether one was provid
|
||||
|
||||
Both adapters also need the identical "refuse a stored credential" diagnosis, differing only by package prefix. `LlmError` is declared in the Service Definition's `index.ts`, so `assertUsableApiKey(raw, pkg, ref)` lives there beside it and neither adapter carries a local copy. The predicate module stays dependency-free: importing `LlmError` into `api-key.ts` would cycle with `index.ts`'s re-export of it.
|
||||
|
||||
The client cannot import any of this: client packages reference only client packages, so `packages/client/ui-models` mirrors the predicate in its own `apiKey.ts` and owns the localized messages, exactly as `validateDeepSeekModels` mirrors the host's `catalogModel` schema. Each side names the other in a comment.
|
||||
The client cannot import any of this: client packages reference only client packages, so `packages/client/ui-settings-models` mirrors the predicate in its own `apiKey.ts` and owns the localized messages, exactly as `validateDeepSeekModels` mirrors the host's `catalogModel` schema. Each side names the other in a comment.
|
||||
|
||||
### What each surface does
|
||||
|
||||
@@ -56,7 +56,7 @@ The client cannot import any of this: client packages reference only client pack
|
||||
| `llm-deepseek` `resolveApiKey` | Normalizes what the credentials seam or environment returns, rejecting with `INVALID_CREDENTIAL` naming the Models page and never echoing the key. |
|
||||
| `llm-pi-ai` `resolveApiKey` | Normalizes the credential and environment paths. A profile naming no credential still returns `undefined`, so ambient and OAuth routes are unaffected. |
|
||||
| `llm-pi-ai` `discoverModels` | Normalizes before building the header, so an illegal key is a credential fault rather than an unreachable endpoint. A probe carrying no key stays unauthenticated. |
|
||||
| `ui-models` | Mirrors the charset rule, adds the shape heuristic, trims `keyDraft` before probe and `credentials.set`, and fixes the `stringAt` emptiness test. A blank field remains a no-op that submits; a field holding only whitespace is a field-level failure. Submit **and the endpoint interrogation** are both gated, so a refused key never spends a round trip to be told what the field already says, and the failure renders on the field, matching the existing `modelFailure` pattern. |
|
||||
| `ui-settings-models` | Mirrors the charset rule, adds the shape heuristic, trims `keyDraft` before probe and `credentials.set`, and fixes the `stringAt` emptiness test. A blank field remains a no-op that submits; a field holding only whitespace is a field-level failure. Submit **and the endpoint interrogation** are both gated, so a refused key never spends a round trip to be told what the field already says, and the failure renders on the field, matching the existing `modelFailure` pattern. |
|
||||
|
||||
`ProviderEditor` serves both the DeepSeek and pi-ai layouts, so one client change covers both providers. `CustomProviderCard` carries the same judgement for a hand-declared route.
|
||||
|
||||
@@ -64,7 +64,7 @@ The client cannot import any of this: client packages reference only client pack
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
**A validation module shared by client and host.** Rejected by the source-plane layout: client packages reference only client packages plus `vendor/cordis` and `support/invariants`, and widening that to reach a host package would collide the two `Context` merges the split exists to keep apart. Mirroring a one-line predicate with a test on each side is the established shape here.
|
||||
**A validation module shared by client and host.** Rejected by the source-plane layout: client packages reference only client packages plus `vendor/cordis` and `runtime-diagnostics/invariants`, and widening that to reach a host package would collide the two `Context` merges the split exists to keep apart. Mirroring a one-line predicate with a test on each side is the established shape here.
|
||||
|
||||
**A per-adapter thrower in each of `llm-deepseek` and `llm-pi-ai`.** The first plan gave each adapter its own, differing only by the package prefix in the message, with a duplication-gate exemption to excuse the pair. Rejected before implementation: `LlmError` is declared in the Service Definition, so that package can own the diagnosis outright, and an exemption there would have hidden exactly the duplication it was covering for.
|
||||
|
||||
@@ -96,6 +96,6 @@ The costliest way to get this wrong would have been to treat absence as invalidi
|
||||
|
||||
`packages/llm/llm-deepseek/tests/` covers the stored-credential path end to end in `dynamic-config.spec.ts`, through the real credentials seam rather than a stub. `packages/llm/llm-pi-ai/tests/` covers the discovery probe, including that a probe with no key sends no `authorization` header.
|
||||
|
||||
`packages/client/ui-models/tests/` pins `apiKeyFailure` over the same table plus the paste-shape cases, and drives both cards: a blank field submits without writing a credential, a whitespace-only field fails on the field, an illegal or wrapped key blocks submit and the interrogation alike, a padded key is trimmed before `credentials.set` and before an interrogation, and a hand-declared route can be created with no key at all.
|
||||
`packages/client/ui-settings-models/tests/` pins `apiKeyFailure` over the same table plus the paste-shape cases, and drives both cards: a blank field submits without writing a credential, a whitespace-only field fails on the field, an illegal or wrapped key blocks submit and the interrogation alike, a padded key is trimmed before `credentials.set` and before an interrogation, and a hand-declared route can be created with no key at all.
|
||||
|
||||
The user-visible terminal state is pinned where it is actually assembled: `examples/headless-agent/tests/headless.snapshot.ts` runs the one-shot app against a stored key no header can carry, over the same keyless composition its missing-credential sibling uses, and records that the turn ends on `INVALID_CREDENTIAL` with an actionable message carrying neither the key nor the word `ByteString`. A package test could not have shown that, and the web e2e covers only the browser half.
|
||||
|
||||
@@ -46,7 +46,7 @@ Status: implemented
|
||||
|
||||
两个适配器同样都需要那句完全相同的「拒绝一个已存储凭据」的诊断，差别仅在包名前缀。`LlmError` 声明在 Service Definition 的 `index.ts` 中，因此 `assertUsableApiKey(raw, pkg, ref)` 就住在它旁边，两个适配器都不再各留一份。断言模块本身保持零依赖：把 `LlmError` 引入 `api-key.ts` 会与 `index.ts` 对它的再导出成环。
|
||||
|
||||
客户端无法引入其中任何一个：client 包只 reference client 包，因此 `packages/client/ui-models` 在自己的 `apiKey.ts` 中镜像这个断言并持有本地化文案，正如 `validateDeepSeekModels` 镜像 host 侧的 `catalogModel` schema。两侧在注释中互相指名。
|
||||
客户端无法引入其中任何一个：client 包只 reference client 包，因此 `packages/client/ui-settings-models` 在自己的 `apiKey.ts` 中镜像这个断言并持有本地化文案，正如 `validateDeepSeekModels` 镜像 host 侧的 `catalogModel` schema。两侧在注释中互相指名。
|
||||
|
||||
### 各处分别做什么
|
||||
|
||||
@@ -56,7 +56,7 @@ Status: implemented
|
||||
| `llm-deepseek` `resolveApiKey` | 归一化凭据 seam 或环境返回的值，以 `INVALID_CREDENTIAL` 拒绝，消息指明模型设置页，绝不回显 Key。 |
|
||||
| `llm-pi-ai` `resolveApiKey` | 归一化凭据与环境路径。不指定任何凭据的 profile 仍返回 `undefined`，ambient 与 OAuth 路由不受影响。 |
|
||||
| `llm-pi-ai` `discoverModels` | 在构造 header 之前归一化，使非法 Key 成为凭据故障而非端点不可达。不带 Key 的探测保持未鉴权。 |
|
||||
| `ui-models` | 镜像字符集规则，加入形状启发式，在探测与 `credentials.set` 之前 trim `keyDraft`，并修正 `stringAt` 的空值判断。留空的输入框仍是可以提交的空操作；只含空白的输入框则是字段级失败。提交**与端点探测**同时受拦截，因此被拒绝的密钥不会白花一次往返去换取字段上已经写明的答案；失败呈现在字段上，与既有的 `modelFailure` 模式一致。 |
|
||||
| `ui-settings-models` | 镜像字符集规则，加入形状启发式，在探测与 `credentials.set` 之前 trim `keyDraft`，并修正 `stringAt` 的空值判断。留空的输入框仍是可以提交的空操作；只含空白的输入框则是字段级失败。提交**与端点探测**同时受拦截，因此被拒绝的密钥不会白花一次往返去换取字段上已经写明的答案；失败呈现在字段上，与既有的 `modelFailure` 模式一致。 |
|
||||
|
||||
`ProviderEditor` 同时服务 DeepSeek 与 pi-ai 两种布局，因此一处客户端改动覆盖两个提供方。`CustomProviderCard` 为手工声明的路由承载同一套判定。
|
||||
|
||||
@@ -64,7 +64,7 @@ Status: implemented
|
||||
|
||||
## 曾考虑的替代方案
|
||||
|
||||
**由 client 与 host 共享一个校验模块。** 被 source plane 布局否决：client 包只 reference client 包外加 `vendor/cordis` 与 `support/invariants`，把它放宽到够得着 host 包会撞上这一分割本就要隔开的两份 `Context` 合并。在两侧各镜像一行断言并各配一份测试，是此处的既定形态。
|
||||
**由 client 与 host 共享一个校验模块。** 被 source plane 布局否决：client 包只 reference client 包外加 `vendor/cordis` 与 `runtime-diagnostics/invariants`，把它放宽到够得着 host 包会撞上这一分割本就要隔开的两份 `Context` 合并。在两侧各镜像一行断言并各配一份测试，是此处的既定形态。
|
||||
|
||||
**在 `llm-deepseek` 与 `llm-pi-ai` 中各留一个抛错 helper。** 最初的计划正是各留一份，差别仅在消息中的包名前缀，并配一个重复检测豁免来放行这一对。在实现之前即被否决：`LlmError` 声明在 Service Definition 中，因此该包完全可以自己拥有这句诊断，而那里的一个豁免恰恰会掩盖它本要遮掩的重复。
|
||||
|
||||
@@ -96,6 +96,6 @@ Status: implemented
|
||||
|
||||
`packages/llm/llm-deepseek/tests/` 在 `dynamic-config.spec.ts` 中经真实凭据 seam（而非 stub）端到端覆盖已存储凭据路径。`packages/llm/llm-pi-ai/tests/` 覆盖探测路径，包括不带 Key 的探测不会发出 `authorization` 标头。
|
||||
|
||||
`packages/client/ui-models/tests/` 以同一张表加上形状用例钉住 `apiKeyFailure`，并驱动两张卡片：留空的输入框可提交且不写入凭据、只含空白的输入框在字段上失败、非法或被包裹的 Key 同时拦截提交与探测、带首尾空白的 Key 在 `credentials.set` 与探测之前被 trim，以及手工声明的路由可以完全不带 Key 创建。
|
||||
`packages/client/ui-settings-models/tests/` 以同一张表加上形状用例钉住 `apiKeyFailure`，并驱动两张卡片：留空的输入框可提交且不写入凭据、只含空白的输入框在字段上失败、非法或被包裹的 Key 同时拦截提交与探测、带首尾空白的 Key 在 `credentials.set` 与探测之前被 trim，以及手工声明的路由可以完全不带 Key 创建。
|
||||
|
||||
用户可见的终态则钉在它真正被组装的位置：`examples/headless-agent/tests/headless.snapshot.ts` 让 one-shot 应用在一个 HTTP 标头无法承载的已存密钥下运行，复用其 missing-credential 兄弟场景的同一套无密钥 composition，并记录该轮次以 `INVALID_CREDENTIAL` 结束、消息可操作且既不含密钥也不含 `ByteString` 字样。包级测试无法证明这一点，而 web e2e 只覆盖了浏览器那一半。
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-06-host-backed-web-preferences.md
|
||||
2026-08-06-host-backed-web-preferences.md: d56a8d2e330b214a1922997e3cc7165fd0fb31e4
|
||||
2026-08-06-host-backed-web-preferences.zh.md: 593646fe0845c20fb09cb7d115e6fa558226506e
|
||||
2026-08-06-host-backed-web-preferences.md: cb3222e3edc9a5382b2c54eb9953b6b952b86b11
|
||||
2026-08-06-host-backed-web-preferences.zh.md: 08208daa683b7cc67e3ad4efd9a79f15ef82c7a3
|
||||
|
||||
@@ -8,7 +8,7 @@ English | [中文](2026-08-06-host-backed-web-preferences.zh.md)
|
||||
|
||||
The Web Appearance, Language, and busy-Enter preferences lived in browser `localStorage`. Browser storage is scoped to an origin, so reopening `dsh web` on another port selected a different partition and lost choices even though both processes used the same DSH home. These are user-level product preferences; session selection, drafts, disclosure state, and other transient browser state remain page-local.
|
||||
|
||||
The first theme implementation moved only Appearance to Host settings but awaited its initial RPC before providing `ThemeService`. A slow or unavailable settings request therefore suspended the assembled page. It also subscribed after the read, could miss an invalidation in that window, did not carry namespace revisions on writes, and allowed queued writes from a disposed plugin to reach the Host.
|
||||
The first theme implementation moved only Appearance to Host settings but awaited its initial RPC before providing `ThemeRuntime`. A slow or unavailable settings request therefore suspended the assembled page. It also subscribed after the read, could miss an invalidation in that window, did not carry namespace revisions on writes, and allowed queued writes from a disposed plugin to reach the Host.
|
||||
|
||||
## Decision
|
||||
|
||||
|
||||
@@ -8,7 +8,7 @@ Status: implemented
|
||||
|
||||
Web 的 Appearance、Language 和繁忙态 Enter 偏好原本存在浏览器 `localStorage` 中。浏览器存储以 origin 为作用域，因此换一个端口重新打开 `dsh web` 会选中另一个存储分区并丢失选择，即使两个进程使用同一个 DSH home。这些是用户级产品偏好；会话选择、草稿、折叠展开状态和其他瞬态浏览器状态仍保留在页面内。
|
||||
|
||||
第一版主题实现只把 Appearance 移入 Host settings，但会在提供 `ThemeService` 之前等待初始 RPC。缓慢或不可用的 settings 请求因而会挂起组装后的页面。该实现还在读取后才建立订阅，可能错过此窗口内的失效通知；它写入时不携带 namespace revision，并且允许已释放插件所排队的写入到达 Host。
|
||||
第一版主题实现只把 Appearance 移入 Host settings，但会在提供 `ThemeRuntime` 之前等待初始 RPC。缓慢或不可用的 settings 请求因而会挂起组装后的页面。该实现还在读取后才建立订阅，可能错过此窗口内的失效通知；它写入时不携带 namespace revision，并且允许已释放插件所排队的写入到达 Host。
|
||||
|
||||
## 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 .agents/notes/implemented/bug-fix/2026-08-06-onboarding-step-owned-takeover-chrome.md
|
||||
2026-08-06-onboarding-step-owned-takeover-chrome.md: 97f5335412f256bf7e60f36731c9e0c4475ee99e
|
||||
2026-08-06-onboarding-step-owned-takeover-chrome.zh.md: 10adb8e5bd5e90cfc7c18fb68e5e5fbf5214994a
|
||||
2026-08-06-onboarding-step-owned-takeover-chrome.md: 80d2dbbb94c3bf49dab58b394ecec0181fb7ccf2
|
||||
2026-08-06-onboarding-step-owned-takeover-chrome.zh.md: f67c3960185fe5d71e93f3bbf404fa5480cae11f
|
||||
|
||||
@@ -32,4 +32,4 @@ A future step that registers without wrapping its visible content in `Onboarding
|
||||
|
||||
## Testing
|
||||
|
||||
`packages/client/ui-primitives/tests/onboarding-surface.client.spec.tsx` pins the primitive: body portal around the content, mask/stage class presence, `#root` inert held for exactly the mount lifetime, and the no-`#root` composition. `packages/client/ui-settings-general/tests/settings-root.client.spec.tsx` pins the inverted shell contract: no takeover chrome and no inert while a mounted step renders nothing. `apps/web/tests/onboarding-deepseek-config.e2e.ts` gains the defect's assembled regression pin: a configured world reloads while every `settings.describe` response is held open at the browser's network boundary — widening the steps' deciding window from loopback-invisible to hundreds of milliseconds, which is what keeps the assertions non-vacuous — and an 8 ms in-page sampler proves the takeover chrome never mounts and `#root` never turns inert. The file's existing scenarios and the step specs (`ui-settings-general`, `ui-models`) pass unchanged — the mask selector and geometry pins survive because the stylesheet moved verbatim.
|
||||
`packages/client/ui-primitives/tests/onboarding-surface.client.spec.tsx` pins the primitive: body portal around the content, mask/stage class presence, `#root` inert held for exactly the mount lifetime, and the no-`#root` composition. `packages/client/ui-settings-general/tests/settings-root.client.spec.tsx` pins the inverted shell contract: no takeover chrome and no inert while a mounted step renders nothing. `apps/web/tests/onboarding-deepseek-config.e2e.ts` gains the defect's assembled regression pin: a configured world reloads while every `settings.describe` response is held open at the browser's network boundary — widening the steps' deciding window from loopback-invisible to hundreds of milliseconds, which is what keeps the assertions non-vacuous — and an 8 ms in-page sampler proves the takeover chrome never mounts and `#root` never turns inert. The file's existing scenarios and the step specs (`ui-settings-general`, `ui-settings-models`) pass unchanged — the mask selector and geometry pins survive because the stylesheet moved verbatim.
|
||||
|
||||
@@ -32,4 +32,4 @@
|
||||
|
||||
## 测试
|
||||
|
||||
`packages/client/ui-primitives/tests/onboarding-surface.client.spec.tsx` 钉住原语行为：包裹内容的 body portal、遮罩／展示层类名存在、`#root` 的 `inert` 恰好持续挂载生命周期，以及无 `#root` 的组合。`packages/client/ui-settings-general/tests/settings-root.client.spec.tsx` 钉住反转后的外壳约定：已挂载步骤什么都不渲染时，无接管界面框架、无 inert。`apps/web/tests/onboarding-deepseek-config.e2e.ts` 新增本缺陷的整装回归钉：已配置世界刷新页面，同时在浏览器网络边界扣住所有 `settings.describe` 响应——把步骤的判定窗口从 loopback 下不可见拉宽到数百毫秒，这正是断言保持非空洞的关键——页内 8ms 采样器证明接管界面框架从未挂载、`#root` 从未变为 inert。该文件的既有场景与步骤 spec（`ui-settings-general`、`ui-models`）原样通过——样式表逐字迁移，遮罩选择器与几何钉子得以幸存。
|
||||
`packages/client/ui-primitives/tests/onboarding-surface.client.spec.tsx` 钉住原语行为：包裹内容的 body portal、遮罩／展示层类名存在、`#root` 的 `inert` 恰好持续挂载生命周期，以及无 `#root` 的组合。`packages/client/ui-settings-general/tests/settings-root.client.spec.tsx` 钉住反转后的外壳约定：已挂载步骤什么都不渲染时，无接管界面框架、无 inert。`apps/web/tests/onboarding-deepseek-config.e2e.ts` 新增本缺陷的整装回归钉：已配置世界刷新页面，同时在浏览器网络边界扣住所有 `settings.describe` 响应——把步骤的判定窗口从 loopback 下不可见拉宽到数百毫秒，这正是断言保持非空洞的关键——页内 8ms 采样器证明接管界面框架从未挂载、`#root` 从未变为 inert。该文件的既有场景与步骤 spec（`ui-settings-general`、`ui-settings-models`）原样通过——样式表逐字迁移，遮罩选择器与几何钉子得以幸存。
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-06-token-surface-unpriced-replace-compatibility.md
|
||||
2026-08-06-token-surface-unpriced-replace-compatibility.md: 77b778fba695f560eb68af6da2f416e61ccff181
|
||||
2026-08-06-token-surface-unpriced-replace-compatibility.zh.md: 0aff9db9b95e8670d85c8239dc2313b4e20f321c
|
||||
2026-08-06-token-surface-unpriced-replace-compatibility.md: cf672a426f20fa65aea9b7b6391a002d41631b4c
|
||||
2026-08-06-token-surface-unpriced-replace-compatibility.zh.md: d3249cb7f4f35b073dd59f2f200c07245160b580
|
||||
|
||||
@@ -6,7 +6,7 @@ English | [中文](2026-08-06-token-surface-unpriced-replace-compatibility.zh.md
|
||||
|
||||
## Problem
|
||||
|
||||
The `contextPressure` and `contextBreakdown` projections keep a running surface-token total plus at most one pending shadow-price claim, so their persisted checkpoints stay O(1) over a session's life. Current replace producers append a `compact/summary` or `compact/prune` metering event immediately before the replacement; its `shadowedTokenCount` prices the exact replaced range, and `foldSurfaceProjection` turns that into the signed delta.
|
||||
The `contextPressure` and `contextBreakdown` projections keep a running surface-token total plus at most one pending shadow-price claim, so their persisted checkpoints stay O(1) over a session's life. Current replace producers append a `compaction/summary` or `compaction/prune` metering event immediately before the replacement; its `shadowedTokenCount` prices the exact replaced range, and `foldSurfaceProjection` turns that into the signed delta.
|
||||
|
||||
Sessions recorded before the shadow-price protocol log replacements with no adjacent metering event. The O(1) state cannot reconstruct the replaced range's price, and the fold treated every unpriced replacement as a contract violation and threw — so replaying such a session died at its first replacement (`token surface: replace at seq … has no adjacent shadow price`), leaving the session permanently unopenable.
|
||||
|
||||
|
||||
@@ -6,7 +6,7 @@ Status: implemented
|
||||
|
||||
## 问题
|
||||
|
||||
`contextPressure` 与 `contextBreakdown` 两个投影只维护一份滚动累计的表层 token 总量，外加至多一条待结算的影子价格（shadow price）声明，因此其持久化检查点在会话整个生命周期内保持 O(1)。当前的替换生产方会紧贴在替换之前追加一条 `compact/summary` 或 `compact/prune` 计量事件；其 `shadowedTokenCount` 对被替换区间精确计价，`foldSurfaceProjection` 再把它换算成有符号增量。
|
||||
`contextPressure` 与 `contextBreakdown` 两个投影只维护一份滚动累计的表层 token 总量，外加至多一条待结算的影子价格（shadow price）声明，因此其持久化检查点在会话整个生命周期内保持 O(1)。当前的替换生产方会紧贴在替换之前追加一条 `compaction/summary` 或 `compaction/prune` 计量事件；其 `shadowedTokenCount` 对被替换区间精确计价，`foldSurfaceProjection` 再把它换算成有符号增量。
|
||||
|
||||
影子价格协议引入之前录制的会话，其日志中的替换没有相邻的计量事件。O(1) 状态无法重建被替换区间的价格，而折叠此前把每一次未计价替换都当作约定违规并抛出异常，于是回放这类会话会在第一处替换就中断（`token surface: replace at seq … has no adjacent shadow price`），会话从此永远无法打开。
|
||||
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-07-cancel-convergence-wake-latch.md
|
||||
2026-08-07-cancel-convergence-wake-latch.md: de18dce87e28eaf0548eebd0d054d4ca7b59d0a6
|
||||
2026-08-07-cancel-convergence-wake-latch.md: 3dc928a170457816cb262659a5cf3c0900b6a13b
|
||||
2026-08-07-cancel-convergence-wake-latch.zh.md: 7ff536b58ed7eabf52f474a61e73b2f5cc93ae06
|
||||
|
||||
@@ -10,7 +10,7 @@ English | [中文](2026-08-07-cancel-convergence-wake-latch.zh.md)
|
||||
|
||||
## Decision
|
||||
|
||||
The `running` phase carries a `wakeRequested` latch, mirroring the existing `maintenance` phase field. `wakeDriver()` latches whenever the current activity cannot deliver the wake — a maintenance task never reads the queue, and an aborted activity converges without restarting — while a live driver needs no latch because it claims queued work itself. The exiting activity replays the latch at its own convergence boundary (`kick`'s `finally` and `runMaintenance`'s `finally`): this placement guarantees `turn/end N` lands before the replayed driver opens `turn/start N+1`, and that `whenIdle()` sees the replayed driver through its `activityDone` loop. The replay sites run only while `inbox.hasPending`, so a latched wake removed from the inbox before convergence does not start an empty driver. A wake sent while the agent is already idle keeps its turn boundary even when its message is cleared before the driver claims — that `idle → running → idle` transition is an observable contract: the goal-session driver's pause/disarm fallback fires on the `idle` transition after a cancelled reservation (moving the guard into `wakeDriver()` suppresses that boundary). `cancel()` without `keepInbox` clears the latch together with the inbox.
|
||||
The `running` phase carries a `wakeRequested` latch, mirroring the existing `maintenance` phase field. `wakeDriver()` latches whenever the current activity cannot deliver the wake — a maintenance task never reads the queue, and an aborted activity converges without restarting — while a live driver needs no latch because it claims queued work itself. The exiting activity replays the latch at its own convergence boundary (`kick`'s `finally` and `runMaintenance`'s `finally`): this placement guarantees `turn/end N` lands before the replayed driver opens `turn/start N+1`, and that `whenIdle()` sees the replayed driver through its `activityDone` loop. The replay sites run only while `inbox.hasPending`, so a latched wake removed from the inbox before convergence does not start an empty driver. A wake sent while the agent is already idle keeps its turn boundary even when its message is cleared before the driver claims — that `idle → running → idle` transition is an observable contract: the goal-round-driver driver's pause/disarm fallback fires on the `idle` transition after a cancelled reservation (moving the guard into `wakeDriver()` suppresses that boundary). `cancel()` without `keepInbox` clears the latch together with the inbox.
|
||||
|
||||
The `signal.aborted` discriminator is load-bearing: it separates pre-abort queued work — which `keepInbox` parks for a later wake (the `keepInbox` parking contract) — from post-abort explicit wakes, which must run after convergence.
|
||||
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-07-code-mode-executor-collapse.md
|
||||
2026-08-07-code-mode-executor-collapse.md: 3b64675f90f830628dcde427d4388153ec7accf1
|
||||
2026-08-07-code-mode-executor-collapse.zh.md: 51b35ad44b9758805784834d1d036ba374140dd9
|
||||
2026-08-07-code-mode-executor-collapse.md: abfba369a2f6482f72d7224f6762f3ac75c8234e
|
||||
2026-08-07-code-mode-executor-collapse.zh.md: 691d900400778f5a064bf4d13c753ee433e7131b
|
||||
|
||||
@@ -12,7 +12,7 @@ The package contract names this exact anti-pattern: schema omission is not enfor
|
||||
|
||||
## Decision
|
||||
|
||||
`ToolRegistry` resolves callable definitions through a new private `resolveExecution(name, scope, nested)` that applies the mode collapse at the operation boundary that owns it. When `modeFor(scope)` resolves to `code`, a model-direct call (`nested = false`) may only name the reserved `run_code` transport; every native name resolves to `undefined` and surfaces as the executor's existing `UNKNOWN_TOOL` error, whose message names the route back through `run_code` because the name IS declared to this model (an already-aborted caller signal keeps the cancellation contract: `ABORTED_BEFORE_DISPATCH`, with the visible tool's finalizer applied). The effective scope mode includes declarations inherited from an agent preset, so its wire schema and execution permissions remain aligned. A collapsed call terminates at `createExecution` — the first stage of `prepare` — BEFORE the extensible policy pipeline, so `tools/pre-execute` listeners, approval `ask`, and guards never observe a call that is deterministically denied; a human is never prompted to approve it. A nested sub-dispatch (`nested = true` — a `parent` token set, which only the `run_code` SDK binding sets in production code) may call any visible tool, so programs keep every binding the generated SDK declared.
|
||||
`ToolRuntime` resolves callable definitions through a new private `resolveExecution(name, scope, nested)` that applies the mode collapse at the operation boundary that owns it. When `modeFor(scope)` resolves to `code`, a model-direct call (`nested = false`) may only name the reserved `run_code` transport; every native name resolves to `undefined` and surfaces as the executor's existing `UNKNOWN_TOOL` error, whose message names the route back through `run_code` because the name IS declared to this model (an already-aborted caller signal keeps the cancellation contract: `ABORTED_BEFORE_DISPATCH`, with the visible tool's finalizer applied). The effective scope mode includes declarations inherited from an agent preset, so its wire schema and execution permissions remain aligned. A collapsed call terminates at `createExecution` — the first stage of `prepare` — BEFORE the extensible policy pipeline, so `tools/pre-execute` listeners, approval `ask`, and guards never observe a call that is deterministically denied; a human is never prompted to approve it. A nested sub-dispatch (`nested = true` — a `parent` token set, which only the `run_code` SDK binding sets in production code) may call any visible tool, so programs keep every binding the generated SDK declared.
|
||||
|
||||
Four execution-path lookups — `executionMode`, `dispatchToolBody`, `postExecute`, `normalizeDispatchResult` — go through `resolveExecution`. `createExecution` applies the same collapse via the shared `collapses(name, nested)` predicate so it can distinguish a collapsed call from a genuinely unknown name before the policy pipeline. The public registry view (`get`) and SDK projection (`schemas`) keep their semantics: presentation, inspection, and binding enumeration still see the full visible set. The wire (`wireSchemas`) and the executor now agree. A collapsed call with non-JSON-serializable arguments reports the parameter `TypeError` (the invalid-args contract), not `UNKNOWN_TOOL` — the body still never runs and policy still does not.
|
||||
|
||||
@@ -41,6 +41,6 @@ No provider guarantees interception of unadvertised names; the reported session
|
||||
- `mode: 'code'` now enforces what it announces: a model-direct native call becomes `UNKNOWN_TOOL`, which the model can correct by routing through `run_code` (a pre-aborted call still resolves `ABORTED_BEFORE_DISPATCH`, per the cancellation contract).
|
||||
- `both` and `native` behavior is unchanged; SDK sub-dispatches are unchanged (the `parent` token is the discriminator).
|
||||
- A collapsed call is rejected at `prepare`, BEFORE the extensible policy pipeline: pre-execute listeners, approval `ask`, and guards never observe it. `executionMode` also fails closed (`exclusive`), so scheduling has no observable difference.
|
||||
- Native-tool guidance sections (`tool:read`, `tool:write`, `tool:bash`, etc.) remain in the system prompt because they describe capabilities available through the generated SDK as well as native function calls, and several carry cross-tool routing policy (`read` over `bash cat`, `read` before `write` for the default fs-policy, `subagent` over `workflow`) that no single tool description can hold. The executor collapse, not prompt filtering, prevents model-direct native calls.
|
||||
- Native-tool guidance sections (`tool:read`, `tool:write`, `tool:bash`, etc.) remain in the system prompt because they describe capabilities available through the generated SDK as well as native function calls, and several carry cross-tool routing policy (`read` over `bash cat`, `read` before `write` for the default fs-observation-policy, `subagent` over `workflow`) that no single tool description can hold. The executor collapse, not prompt filtering, prevents model-direct native calls.
|
||||
- The prompt STATES the collapse, in the `tools:code-only` section ordered ahead of the 100-199 guidance band. Those sections name their tool without qualifying how it is reached, so a model that read only them emitted a native call, received `UNKNOWN_TOOL` for a tool the same prompt declared, and concluded the deployment was inconsistent rather than correcting itself. The denial carries the route for the same reason. `both` renders the rule empty: its native calls do execute, so stating it there would be false — which is why `both-mode-turn` no longer shares `code-mode-turn`'s expected prompt.
|
||||
- Any future composite transport that sets a `parent` token opts its sub-dispatches into the full table, matching the nested-call semantics the token already documents.
|
||||
|
||||
@@ -12,7 +12,7 @@ Status: implemented
|
||||
|
||||
## 决策
|
||||
|
||||
`ToolRegistry` 通过新增的私有 `resolveExecution(name, scope, nested)` 解析可执行定义，在拥有该决策的操作边界上应用模式塌缩。当 `modeFor(scope)` 解析为 `code` 时，模型直呼（`nested = false`）只允许命名保留的 `run_code` 传输工具；任何原生名字都解析为 `undefined`，并以执行器既有的 `UNKNOWN_TOOL` 错误呈现，其消息会指出改走 `run_code` 的正确路径——因为这个名字对当前模型而言是**已声明过**的（已中止的调用方 signal 保留取消契约：`ABORTED_BEFORE_DISPATCH`，并应用可见工具的 finalizer）。有效的 scope 模式包括从 agent preset 继承的声明，因此其 wire schema 与执行权限保持一致。被塌缩的调用在 `createExecution`（`prepare` 的第一阶段）即终止——在可扩展策略流水线之前，因此 `tools/pre-execute` 监听器、approval `ask` 与 guard 永远不会观察到一个注定被拒绝的调用，人类也不会被提示去批准它。嵌套子调用（`nested = true`——即设置了 `parent` token，生产代码中只有 `run_code` SDK 绑定会设置）可以调用任意可见工具，因此程序保留生成 SDK 声明的全部绑定。
|
||||
`ToolRuntime` 通过新增的私有 `resolveExecution(name, scope, nested)` 解析可执行定义，在拥有该决策的操作边界上应用模式塌缩。当 `modeFor(scope)` 解析为 `code` 时，模型直呼（`nested = false`）只允许命名保留的 `run_code` 传输工具；任何原生名字都解析为 `undefined`，并以执行器既有的 `UNKNOWN_TOOL` 错误呈现，其消息会指出改走 `run_code` 的正确路径——因为这个名字对当前模型而言是**已声明过**的（已中止的调用方 signal 保留取消契约：`ABORTED_BEFORE_DISPATCH`，并应用可见工具的 finalizer）。有效的 scope 模式包括从 agent preset 继承的声明，因此其 wire schema 与执行权限保持一致。被塌缩的调用在 `createExecution`（`prepare` 的第一阶段）即终止——在可扩展策略流水线之前，因此 `tools/pre-execute` 监听器、approval `ask` 与 guard 永远不会观察到一个注定被拒绝的调用，人类也不会被提示去批准它。嵌套子调用（`nested = true`——即设置了 `parent` token，生产代码中只有 `run_code` SDK 绑定会设置）可以调用任意可见工具，因此程序保留生成 SDK 声明的全部绑定。
|
||||
|
||||
执行链路的四处查表——`executionMode`、`dispatchToolBody`、`postExecute`、`normalizeDispatchResult`——改走 `resolveExecution`。`createExecution` 通过共享的 `collapses(name, nested)` 谓词应用同一塌缩，以便在策略流水线之前区分被塌缩的调用与真正未知的名字。公共注册表视图（`get`）与 SDK 投影（`schemas`）语义不变：展示、检查与绑定枚举仍看到完整可见集合。通告（`wireSchemas`）与执行器现在一致。带非 JSON 可序列化参数的塌缩调用报告参数 `TypeError`（invalid-args 契约），而非 `UNKNOWN_TOOL`——函数体仍不会运行，策略也不会执行。
|
||||
|
||||
@@ -41,6 +41,6 @@ guard 是可选的插件扩展；安全不变量不能依赖部署恰好组装
|
||||
- `mode: 'code'` 现在兑现其通告：模型直呼原生工具变为 `UNKNOWN_TOOL`，模型可以通过改走 `run_code` 自行纠正（已中止的调用仍按取消契约解析为 `ABORTED_BEFORE_DISPATCH`）。
|
||||
- `both` 与 `native` 行为不变；SDK 子调用不变（判别信号是 `parent` token）。
|
||||
- 被塌缩的调用在 `prepare` 阶段即被拒绝——在可扩展策略流水线之前：pre-execute 监听器、approval `ask` 与 guard 永远不会观察到它。`executionMode` 同样 fail-closed（`exclusive`），调度无可观察差异。
|
||||
- 原生工具指引段（`tool:read`、`tool:write`、`tool:bash` 等）保留在系统提示词中，因为它们同时描述了通过生成 SDK 及原生函数调用可用的能力，其中若干段还承载着任何单个工具描述都装不下的跨工具路由策略（`read` 优先于 `bash cat`、默认 fs-policy 要求先 `read` 再 `write`、一两个委派用 `subagent` 而非 `workflow`）。防止模型直呼原生工具的是执行器塌缩，而非提示词过滤。
|
||||
- 原生工具指引段（`tool:read`、`tool:write`、`tool:bash` 等）保留在系统提示词中，因为它们同时描述了通过生成 SDK 及原生函数调用可用的能力，其中若干段还承载着任何单个工具描述都装不下的跨工具路由策略（`read` 优先于 `bash cat`、默认 fs-observation-policy 要求先 `read` 再 `write`、一两个委派用 `subagent` 而非 `workflow`）。防止模型直呼原生工具的是执行器塌缩，而非提示词过滤。
|
||||
- 提示词会**声明**这条塌缩，位于排在 100–199 指导段之前的 `tools:code-only` 段。那些段只写出工具名而不限定其可达方式，因此只读到它们的模型会发出原生调用，为一个同一份提示词刚刚声明过的工具收到 `UNKNOWN_TOOL`，进而判定部署不一致，而不是自行纠正。拒绝信息给出正确路径也是同一原因。`both` 下该规则渲染为空：它的原生调用确实会执行，在那里声明就是假话——这也是 `both-mode-turn` 不再与 `code-mode-turn` 共用期望提示词的原因。
|
||||
- 未来任何设置 `parent` token 的组合传输，其子调用自动走全表，与该 token 已有的嵌套调用语义一致。
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-09-filesystem-absence-observation.md
|
||||
2026-08-09-filesystem-absence-observation.md: e01719651f54cafc86a3972690507b1ee9b95cc9
|
||||
2026-08-09-filesystem-absence-observation.zh.md: 126f85e95b1debbccddf82fda432d31a69250388
|
||||
2026-08-09-filesystem-absence-observation.md: 40338c4806607b262b93222b4a73a34538414e51
|
||||
2026-08-09-filesystem-absence-observation.zh.md: ee8964454ea7e52a8246af78f26cd787267a946b
|
||||
|
||||
@@ -14,7 +14,7 @@ Treating a failed read as permission to create also exposes a second boundary. B
|
||||
|
||||
`dsh-fs` owns an explicit observation union: `{ kind: 'present', version: FsVersion } | { kind: 'absent' }`. The `fs/observed` event carries that union. Successful reads and mutations emit present; a metadata miss from `read` or the `str_replace_editor` `view`, `str_replace`, or `insert` command emits absent synchronously before returning `FS_NOT_FOUND`. Other read failures do not manufacture absence.
|
||||
|
||||
`dsh-fs-policy` stores three logical states per owner and target without injecting or calling `ctx.fs`: missing map entry is unseen, `absent` is confirmed absence, and `present(version)` is a replacement/edit basis. Write maps unseen and absent to the existing `createIfAbsent` intent and present to `replaceIfVersion`. Edit maps unseen to `FS_NOT_OBSERVED`, absent to `FS_NOT_FOUND`, and present to its version guard. A successful create or mutation replaces absence with its produced present version.
|
||||
`dsh-fs-observation-policy` stores three logical states per owner and target without injecting or calling `ctx.fs`: missing map entry is unseen, `absent` is confirmed absence, and `present(version)` is a replacement/edit basis. Write maps unseen and absent to the existing `createIfAbsent` intent and present to `replaceIfVersion`. Edit maps unseen to `FS_NOT_OBSERVED`, absent to `FS_NOT_FOUND`, and present to its version guard. A successful create or mutation replaces absence with its produced present version.
|
||||
|
||||
Every provider must enforce `createIfAbsent` at the publication point, not only at its initial probe. `dsh-fs-local` stages and fsyncs in a private sibling directory, then hard-links the staged file to the destination; after a failed link it inspects the destination entry so a regular-file collision returns `FS_NOT_OBSERVED`, a non-regular entry returns `FS_NOT_REGULAR_FILE`, and a failure against a still-missing target returns `FS_IO_ERROR`. `dsh-fs-e2b` uses remote `ln -T` with an explicit created/existing result and derives the committed target version from metadata obtained before the non-cancellable commit. Replacements and bare unconditional writes retain their existing publication paths.
|
||||
|
||||
@@ -23,7 +23,7 @@ This decision does not claim cross-process linearizability for `replaceIfVersion
|
||||
## Alternatives considered
|
||||
|
||||
- **Delete the cached version when a read returns not found.** Rejected because it conflates unseen with confirmed absence, cannot give edit the correct `FS_NOT_FOUND` result, and erases the state transition the event is meant to communicate.
|
||||
- **Have `dsh-fs-policy` call `stat` before choosing an intent.** Rejected because it makes the event-only policy depend on a provider, adds I/O to every decision, and still leaves a TOCTOU gap before publication.
|
||||
- **Have `dsh-fs-observation-policy` call `stat` before choosing an intent.** Rejected because it makes the event-only policy depend on a provider, adds I/O to every decision, and still leaves a TOCTOU gap before publication.
|
||||
- **Let `replaceIfVersion` create when its target disappeared.** Rejected because a positive observation is evidence for replacement, not creation; silently changing that provider intent would bypass the required missing reread and weaken stale protection.
|
||||
- **Keep the deleted-target dead end fail-closed.** Rejected because the model-facing recovery instruction is then false and a normal external cleanup cannot be recovered within the session.
|
||||
|
||||
|
||||
@@ -14,7 +14,7 @@ Status: implemented
|
||||
|
||||
`dsh-fs` 拥有一个显式观测联合类型：`{ kind: 'present', version: FsVersion } | { kind: 'absent' }`。`fs/observed` 事件携带该联合类型。成功的读取与变更发出存在观测；`read` 的元数据未命中，或 `str_replace_editor` 的 `view`、`str_replace`、`insert` 命令发生元数据未命中时，都会在返回 `FS_NOT_FOUND` 前同步发出缺失观测。其他读取失败不会产生缺失观测。
|
||||
|
||||
`dsh-fs-policy` 按所有者与目标存储三种逻辑状态，既不注入也不调用 `ctx.fs`：映射中无条目即未见，`absent` 表示确认缺失，`present(version)` 是替换/编辑基准。写入把未见和缺失映射到现有 `createIfAbsent` 意图，把存在映射到 `replaceIfVersion`。编辑把未见映射到 `FS_NOT_OBSERVED`，把缺失映射到 `FS_NOT_FOUND`，把存在映射到其版本守卫。成功创建或变更后，系统会用其产生的存在版本取代缺失状态。
|
||||
`dsh-fs-observation-policy` 按所有者与目标存储三种逻辑状态，既不注入也不调用 `ctx.fs`：映射中无条目即未见，`absent` 表示确认缺失，`present(version)` 是替换/编辑基准。写入把未见和缺失映射到现有 `createIfAbsent` 意图，把存在映射到 `replaceIfVersion`。编辑把未见映射到 `FS_NOT_OBSERVED`，把缺失映射到 `FS_NOT_FOUND`，把存在映射到其版本守卫。成功创建或变更后，系统会用其产生的存在版本取代缺失状态。
|
||||
|
||||
每个提供方都必须在发布点执行 `createIfAbsent`，不能只在初始探测时执行。`dsh-fs-local` 在私有同级目录中暂存并执行 fsync，再通过硬链接把暂存文件发布到目标位置；链接失败后，它会检查目标条目：与普通文件冲突时返回 `FS_NOT_OBSERVED`，条目非普通时返回 `FS_NOT_REGULAR_FILE`，目标仍然缺失时返回 `FS_IO_ERROR`。`dsh-fs-e2b` 使用远程 `ln -T` 返回明确的已创建/已存在结果，并根据不可取消提交前取得的元数据推导已提交目标的版本。替换操作和裸无条件写入仍沿用现有发布路径。
|
||||
|
||||
@@ -23,7 +23,7 @@ Status: implemented
|
||||
## 曾考虑的替代方案
|
||||
|
||||
- **读取返回未找到时删除缓存版本。** 不予采用，因为这会混淆未见与确认缺失，无法让 edit 返回正确的 `FS_NOT_FOUND` 结果，还会抹去该事件本应传达的状态转换。
|
||||
- **让 `dsh-fs-policy` 在选择意图前调用 `stat`。** 不予采用，因为这会让只依赖事件的策略转而依赖提供方，为每次决策增加 I/O，并且在发布前仍留下 TOCTOU 间隙。
|
||||
- **让 `dsh-fs-observation-policy` 在选择意图前调用 `stat`。** 不予采用，因为这会让只依赖事件的策略转而依赖提供方，为每次决策增加 I/O，并且在发布前仍留下 TOCTOU 间隙。
|
||||
- **允许 `replaceIfVersion` 在目标消失后执行创建。** 不予采用，因为存在观测是执行替换而非创建的依据；静默改变该提供方意图会绕过必须针对缺失目标执行的重新读取，并削弱陈旧保护。
|
||||
- **让删除目标后的死路继续保持 fail-closed。** 不予采用，因为这样会使面向模型的恢复指令失实，而且正常的外部清理操作无法在会话内恢复。
|
||||
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-10-child-agents-join-their-parent-preset.md
|
||||
2026-08-10-child-agents-join-their-parent-preset.md: 4534004ad54df69822872b9595a29443fc3a990b
|
||||
2026-08-10-child-agents-join-their-parent-preset.zh.md: 550a952efefd2490924ed11f7a0e110694571855
|
||||
2026-08-10-child-agents-join-their-parent-preset.md: 5a3d0d1c5e2b492b10a0274204c10e244c37196f
|
||||
2026-08-10-child-agents-join-their-parent-preset.zh.md: 2540b4a9d38c503f14b4f526f4d3902b0d387ec2
|
||||
|
||||
@@ -22,7 +22,7 @@ This is a bind, not a mount, and both differences are load-bearing. The child ge
|
||||
|
||||
`dsh-subagent` reaches the roster through `ctx.get('agentPresets')` with a type-only import and an optional peer dependency — the documented opportunistic-consumption pattern it already uses for `sandboxPolicy` and `approval`.
|
||||
|
||||
Giving the child its parent's tools exposed a second defect the same agent-plane move introduced: `ToolRegistry` exempted SCOPED registrations from a restriction and filtered only the global layer, so once every model-facing row became an ancestor contribution, a child's `toolFilter` stopped constraining anything — and, with the global layer empty, `restrict()` rejected every name it was given as unknown, failing the child outright. The exempt set is the tools a scope registers ITSELF, not the tools that happen to live in the global layer; reading it the second way held only while those two sets coincided. `view()` now filters everything a scope inherits — the global layer and every ancestor layer — and exempts only its own. The own-layer exemption is load-bearing rather than incidental: the delegation runtime registers a child's `report` and structured-output tools into the child's own layer, and a filter naming the capabilities the child may use must not strip the machinery it answers through.
|
||||
Giving the child its parent's tools exposed a second defect the same agent-plane move introduced: `ToolRuntime` exempted SCOPED registrations from a restriction and filtered only the global layer, so once every model-facing row became an ancestor contribution, a child's `toolFilter` stopped constraining anything — and, with the global layer empty, `restrict()` rejected every name it was given as unknown, failing the child outright. The exempt set is the tools a scope registers ITSELF, not the tools that happen to live in the global layer; reading it the second way held only while those two sets coincided. `view()` now filters everything a scope inherits — the global layer and every ancestor layer — and exempts only its own. The own-layer exemption is load-bearing rather than incidental: the delegation runtime registers a child's `report` and structured-output tools into the child's own layer, and a filter naming the capabilities the child may use must not strip the machinery it answers through.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
@@ -44,7 +44,7 @@ Giving the child its parent's tools exposed a second defect the same agent-plane
|
||||
|
||||
`packages/core/tools/tests/scoped.spec.ts` covers the restriction rule directly: a child's filter removes a tool it inherited from an ancestor scope, the child's own registrations survive its own filter, and an ancestor's restriction still reaches every scope nested inside it.
|
||||
|
||||
`packages/subagent/subagent-inprocess/tests/preset-inheritance.spec.ts` asserts the model-visible result through `startInProcessRun()` on a host composition carrying no model-facing rows: the schemas in the child's own request, its parent's prompt section, the recorded header preset, a `toolFilter` applied over the inherited preset tools, and a parent that switched preset while blank — to a DIFFERENT preset, so the assertion distinguishes reading the parent's live scope chain from reading its creation header.
|
||||
`packages/subagent/subagent-in-process-driver/tests/preset-inheritance.spec.ts` asserts the model-visible result through `startInProcessRun()` on a host composition carrying no model-facing rows: the schemas in the child's own request, its parent's prompt section, the recorded header preset, a `toolFilter` applied over the inherited preset tools, and a parent that switched preset while blank — to a DIFFERENT preset, so the assertion distinguishes reading the parent's live scope chain from reading its creation header.
|
||||
|
||||
The assembled-transcript layer is the shipped Web composition's e2e rather than a keyless snapshot. Every runnable example this repo ships composes no preset roster, so the defect is not observable in the snapshot harness at all: a snapshot scenario would first need an example that mounts a roster AND delegates. The Web e2e boots the real `base` + `web-app` patch layers with both shipped presets, which is the assembled evidence the testing policy asks for; the Web browser lane's subagent goldens carry the visible consequence, since a child that records its preset now shows the preset badge its parent shows.
|
||||
|
||||
@@ -56,4 +56,4 @@ Delegation now costs a scope-parent bind per child and nothing else — no extra
|
||||
|
||||
A cold-resumed continuable child joins its parent's CURRENT composition rather than the one its own header records. The window is narrow — the parent must create the child, stay blank, switch preset, and only then wake it, since a resident child never re-joins and a one-shot child never resumes — and the alternative is worse: resolving the child's own recorded id would re-read the roster and hand back the preset-deleted failure mode this join exists to avoid. The child's header still records what it started under, so the divergence is observable rather than silent.
|
||||
|
||||
`ToolRegistry` now reads a restriction's exempt set as "what this scope registers itself" rather than "the global layer", which changes one documented behavior beyond delegation: a tool an ANCESTOR scope contributes is now subject to a descendant's filter, where before only global-layer tools were. Nothing else on the chain loses its exemption — a scope's own registrations stay outside its own filter, which is the property the delegation runtime depends on.
|
||||
`ToolRuntime` now reads a restriction's exempt set as "what this scope registers itself" rather than "the global layer", which changes one documented behavior beyond delegation: a tool an ANCESTOR scope contributes is now subject to a descendant's filter, where before only global-layer tools were. Nothing else on the chain loses its exemption — a scope's own registrations stay outside its own filter, which is the property the delegation runtime depends on.
|
||||
|
||||
@@ -22,7 +22,7 @@ Status: implemented
|
||||
|
||||
`dsh-subagent` 以类型级导入加可选 peer 依赖的方式，通过 `ctx.get('agentPresets')` 触达 roster——这正是它对 `sandboxPolicy` 与 `approval` 已在使用的、有明确文档的机会性消费模式。
|
||||
|
||||
把父方的工具交给子 agent 之后，暴露出同一次 agent 平面搬迁引入的第二个缺陷：`ToolRegistry` 把**作用域级**注册排除在限制之外、只过滤全局层，因此当所有面向模型的行都变成祖先贡献之后，子 agent 的 `toolFilter` 就不再约束任何东西——而且全局层为空时，`restrict()` 会把收到的每个名字都判为未知并直接让子 agent 创建失败。豁免集合应当是作用域**自己注册**的工具，而不是恰好位于全局层的工具；后一种读法只在这两个集合重合时才成立。`view()` 现在过滤作用域继承来的一切——全局层与每个祖先层——只豁免它自己那层。这条自身层豁免是承重的而非顺带的：委派运行时把子 agent 的 `report` 与结构化输出工具注册进子 agent 自己那层，而一个只点名子 agent 可用能力的过滤器绝不能把它回报所依赖的机制一并剥掉。
|
||||
把父方的工具交给子 agent 之后，暴露出同一次 agent 平面搬迁引入的第二个缺陷：`ToolRuntime` 把**作用域级**注册排除在限制之外、只过滤全局层，因此当所有面向模型的行都变成祖先贡献之后，子 agent 的 `toolFilter` 就不再约束任何东西——而且全局层为空时，`restrict()` 会把收到的每个名字都判为未知并直接让子 agent 创建失败。豁免集合应当是作用域**自己注册**的工具，而不是恰好位于全局层的工具；后一种读法只在这两个集合重合时才成立。`view()` 现在过滤作用域继承来的一切——全局层与每个祖先层——只豁免它自己那层。这条自身层豁免是承重的而非顺带的：委派运行时把子 agent 的 `report` 与结构化输出工具注册进子 agent 自己那层，而一个只点名子 agent 可用能力的过滤器绝不能把它回报所依赖的机制一并剥掉。
|
||||
|
||||
## 考虑过的替代方案
|
||||
|
||||
@@ -44,7 +44,7 @@ Status: implemented
|
||||
|
||||
`packages/core/tools/tests/scoped.spec.ts` 直接覆盖该限制规则：子 agent 的过滤器能移除它从祖先作用域继承来的工具、子 agent 自身的注册在自己的过滤器下存活、祖先的限制仍作用于其内嵌套的每个作用域。
|
||||
|
||||
`packages/subagent/subagent-inprocess/tests/preset-inheritance.spec.ts` 在一个不含任何面向模型行的宿主组装上，通过 `startInProcessRun()` 断言模型可见的结果：子 agent 自身请求中的 schema、父方的提示段、记录下来的 header preset、施加在继承来的 preset 工具之上的 `toolFilter`，以及在空白期切换过 preset 的父方——切换到**另一个** preset，这样断言才能区分"读父方活 scope 链"与"读父方创建 header"。
|
||||
`packages/subagent/subagent-in-process-driver/tests/preset-inheritance.spec.ts` 在一个不含任何面向模型行的宿主组装上，通过 `startInProcessRun()` 断言模型可见的结果：子 agent 自身请求中的 schema、父方的提示段、记录下来的 header preset、施加在继承来的 preset 工具之上的 `toolFilter`，以及在空白期切换过 preset 的父方——切换到**另一个** preset，这样断言才能区分"读父方活 scope 链"与"读父方创建 header"。
|
||||
|
||||
组装记录这一层用的是真实 shipped Web 组装的 e2e，而不是无密钥快照。本仓库所有可运行 example 都不组装 preset roster，因此该缺陷在快照 harness 里根本不可观察：要做快照场景，得先有一个既挂载 roster 又发起委派的 example。Web e2e 启动的是真实的 `base` + `web-app` 补丁层与两个 shipped preset，这正是测试政策要求的组装证据；Web 浏览器 lane 的 subagent golden 承载了可见后果——记录了 preset 的子 agent 现在会显示与其父方相同的 preset 徽标。
|
||||
|
||||
@@ -56,4 +56,4 @@ Status: implemented
|
||||
|
||||
冷恢复的可继续子 agent 加入的是父方**当前**的组装，而不是它自己 header 所记录的那份。窗口很窄——父方必须先建子、保持空白、切换 preset，之后才唤醒它；驻留中的子 agent 不会重新加入，一次性子 agent 也不会恢复——而替代方案更糟：按子 agent 自己记录的 id 解析会重读 roster，把这次认父刻意规避掉的"preset 已删除"失败模式又请回来。子 agent 的 header 仍记录它启动时的那份，因此这处分歧是可观察的而非静默的。
|
||||
|
||||
`ToolRegistry` 现在把限制的豁免集合读作"该作用域自己注册的东西"而不是"全局层"，这在委派之外改变了一处既有行为：**祖先**作用域贡献的工具现在会受后代过滤器约束，而此前只有全局层的工具会。链上其余部分的豁免不变——作用域自身的注册仍在自己的过滤器之外，这正是委派运行时所依赖的性质。
|
||||
`ToolRuntime` 现在把限制的豁免集合读作"该作用域自己注册的东西"而不是"全局层"，这在委派之外改变了一处既有行为：**祖先**作用域贡献的工具现在会受后代过滤器约束，而此前只有全局层的工具会。链上其余部分的豁免不变——作用域自身的注册仍在自己的过滤器之外，这正是委派运行时所依赖的性质。
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-10-pre-plugin-theme-bootstrap.md
|
||||
2026-08-10-pre-plugin-theme-bootstrap.md: 276d564dcef60e5130b4b2d0ef7cbc12eeb8b6d6
|
||||
2026-08-10-pre-plugin-theme-bootstrap.zh.md: f9384df6e0ed5bf42c0671b70f484f57080060a0
|
||||
2026-08-10-pre-plugin-theme-bootstrap.md: 006afffc9a07a3abde4131ec972df3be5949ed09
|
||||
2026-08-10-pre-plugin-theme-bootstrap.zh.md: 206390518f3a320e63f699bad6d228010faaf969
|
||||
|
||||
@@ -6,17 +6,17 @@ English | [中文](2026-08-10-pre-plugin-theme-bootstrap.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
The web shell renders `Loading plugins…` before the browser-side plugin tree activates. The theme tokens are already loaded with the shell styles, but `color-scheme` and `body[data-ds-dark-theme]` are not written until ui-theme's ThemeService and ui-layout's ThemePresenter activate; with a persisted dark preference, the loading page therefore renders first with the light palette and then switches to dark.
|
||||
The web shell renders `Loading plugins…` before the browser-side plugin tree activates. The theme tokens are already loaded with the shell styles, but `color-scheme` and `body[data-ds-dark-theme]` are not written until ui-theme's ThemeRuntime and ui-layout's ThemePresenter activate; with a persisted dark preference, the loading page therefore renders first with the light palette and then switches to dark.
|
||||
|
||||
`dshClient.immediately` only includes the bundle in first-stage prefetching; it does not cause the plugin to execute before HTML parsing or the shell's initial render. Changing only the client plugin's loading tier cannot close this window.
|
||||
|
||||
## Decision
|
||||
|
||||
ui-theme's host half transforms each index HTML document through `ctx.httpServer.tapIndex()`, inserting a synchronous inline script immediately after the opening `<body>` tag. The transform registers under an optional `httpServer` injection, so compositions without that service still activate ui-theme and install no transform. When the HTML parser executes the script, the body exists, but the shell's module script and React root have not yet run.
|
||||
ui-theme's host half transforms each index HTML document through `ctx.webServer.tapIndex()`, inserting a synchronous inline script immediately after the opening `<body>` tag. The transform registers under an optional `httpServer` injection, so compositions without that service still activate ui-theme and install no transform. When the HTML parser executes the script, the body exists, but the shell's module script and React root have not yet run.
|
||||
|
||||
The host half registers the [`ui-theme.preference` settings section](2026-08-06-host-backed-web-preferences.md) when a settings provider exists. For each index response, it embeds that schema-validated built-in preference in the inline script; without a settings provider or active registration, it embeds the `system` default. The browser resolves `system` through `prefers-color-scheme`, falling back to light when `matchMedia` is unavailable. It writes only the two pieces of DOM state that ThemePresenter later owns: `document.documentElement.style.colorScheme` and `body[data-ds-dark-theme]`.
|
||||
|
||||
The bootstrap logic recognizes only the built-in `light`, `dark`, and `system` semantics. It registers no listeners and does not resolve third-party themes or token overrides. After the browser-side plugin tree activates, ThemeService remains authoritative for theme state, and ThemePresenter writes the complete resolved result back to the same DOM state and owns subsequent updates and disposal.
|
||||
The bootstrap logic recognizes only the built-in `light`, `dark`, and `system` semantics. It registers no listeners and does not resolve third-party themes or token overrides. After the browser-side plugin tree activates, ThemeRuntime remains authoritative for theme state, and ThemePresenter writes the complete resolved result back to the same DOM state and owns subsequent updates and disposal.
|
||||
|
||||
## Verification
|
||||
|
||||
@@ -26,7 +26,7 @@ ui-theme's unit tests cover activation without either optional Host service, the
|
||||
|
||||
**Hard-code the logic in `apps/web/index.html`.** This would run at the same point, but static HTML cannot embed the current Host setting and would duplicate the preference resolution and DOM fields owned by ui-theme. The Host transform follows the theme plugin's lifecycle and keeps the application shell unaware of the theme domain.
|
||||
|
||||
**Make the ui-theme client bundle synchronous or activate it earlier.** `immediately` controls only prefetching; plugin instantiation still occurs after the shell starts running. Blocking the initial render until ThemeService activates would delay the visible loading and error screens and make the shell depend on the plugin tree it monitors to render failures.
|
||||
**Make the ui-theme client bundle synchronous or activate it earlier.** `immediately` controls only prefetching; plugin instantiation still occurs after the shell starts running. Blocking the initial render until ThemeRuntime activates would delay the visible loading and error screens and make the shell depend on the plugin tree it monitors to render failures.
|
||||
|
||||
**Rely only on CSS `prefers-color-scheme`.** Media queries cannot read an explicit persisted choice, so a user who selects dark while the operating system uses light would still see a flash.
|
||||
|
||||
@@ -34,4 +34,4 @@ ui-theme's unit tests cover activation without either optional Host service, the
|
||||
|
||||
## Consequences
|
||||
|
||||
The loading page's first frame matches the durable built-in preference and defaults to the OS preference when no settings provider is composed. The index transform reads Host settings for every response, while the inline script contains only the selected built-in value and `system` resolution. Changes to the built-in preference semantics or ThemePresenter DOM fields must update both the script and ThemeService. A custom theme still applies fully only after the browser plugins activate; during the loading interval, the page uses the light or dark base palette to which that theme resolves.
|
||||
The loading page's first frame matches the durable built-in preference and defaults to the OS preference when no settings provider is composed. The index transform reads Host settings for every response, while the inline script contains only the selected built-in value and `system` resolution. Changes to the built-in preference semantics or ThemePresenter DOM fields must update both the script and ThemeRuntime. A custom theme still applies fully only after the browser plugins activate; during the loading interval, the page uses the light or dark base palette to which that theme resolves.
|
||||
|
||||
@@ -6,17 +6,17 @@ Status: implemented
|
||||
|
||||
## 问题
|
||||
|
||||
Web 壳在浏览器侧插件树激活前呈现 `Loading plugins…`。主题 token 已随壳样式加载，但 `color-scheme` 和 `body[data-ds-dark-theme]` 要等 ui-theme 的 ThemeService 与 ui-layout 的 ThemePresenter 激活后才写入；持久化偏好为深色时，加载页因此先按浅色调色板绘制，再切为深色。
|
||||
Web 壳在浏览器侧插件树激活前呈现 `Loading plugins…`。主题 token 已随壳样式加载，但 `color-scheme` 和 `body[data-ds-dark-theme]` 要等 ui-theme 的 ThemeRuntime 与 ui-layout 的 ThemePresenter 激活后才写入；持久化偏好为深色时，加载页因此先按浅色调色板绘制，再切为深色。
|
||||
|
||||
`dshClient.immediately` 只把 bundle 纳入第一阶段预取，不会让插件在 HTML 解析或壳首次渲染前执行。仅调整客户端插件的加载档位无法关闭这段时间窗口。
|
||||
|
||||
## 决策
|
||||
|
||||
ui-theme 的主机侧通过 `ctx.httpServer.tapIndex()` 转换每份 index HTML，在 `<body>` 起始标签后紧接一段同步内联脚本。该转换通过可选的 `httpServer` 注入注册，因此不含该服务的组合仍会激活 ui-theme，但不会安装转换。HTML 解析器执行该脚本时，body 已存在，而壳的模块脚本与 React 根节点尚未运行。
|
||||
ui-theme 的主机侧通过 `ctx.webServer.tapIndex()` 转换每份 index HTML，在 `<body>` 起始标签后紧接一段同步内联脚本。该转换通过可选的 `httpServer` 注入注册，因此不含该服务的组合仍会激活 ui-theme，但不会安装转换。HTML 解析器执行该脚本时，body 已存在，而壳的模块脚本与 React 根节点尚未运行。
|
||||
|
||||
settings provider 存在时，主机侧会注册 [`ui-theme.preference` settings 分节](2026-08-06-host-backed-web-preferences.md)。它为每份 index 响应把经过 schema 校验的内建偏好嵌入内联脚本；不存在 settings provider 或有效注册时则嵌入默认值 `system`。浏览器通过 `prefers-color-scheme` 解析 `system`，不支持 `matchMedia` 时回退为浅色。脚本只写 ThemePresenter 后续拥有的两项 DOM 状态：`document.documentElement.style.colorScheme` 与 `body[data-ds-dark-theme]`。
|
||||
|
||||
引导逻辑只认识内建的 `light`、`dark`、`system` 语义，不注册监听器，也不解析第三方主题或 token 覆盖。浏览器侧插件树激活后，ThemeService 仍是主题状态的权威来源，ThemePresenter 会把完整解析结果重新写入同一组 DOM 状态并负责后续更新与释放。
|
||||
引导逻辑只认识内建的 `light`、`dark`、`system` 语义，不注册监听器，也不解析第三方主题或 token 覆盖。浏览器侧插件树激活后，ThemeRuntime 仍是主题状态的权威来源，ThemePresenter 会把完整解析结果重新写入同一组 DOM 状态并负责后续更新与释放。
|
||||
|
||||
## 验证
|
||||
|
||||
@@ -26,7 +26,7 @@ ui-theme 的单元测试覆盖不含任一可选 Host 服务时的激活、脚
|
||||
|
||||
**把逻辑固定写进 `apps/web/index.html`。** 这样能在相同时机执行，但静态 HTML 无法嵌入当前 Host 设置，还会复制 ui-theme 拥有的偏好解析和 DOM 字段；Host 转换会跟随主题插件的生命周期，并让应用壳无需了解主题领域。
|
||||
|
||||
**让 ui-theme 客户端 bundle 同步或更早激活。** `immediately` 只控制预取，插件实例化仍发生在壳开始运行之后；把首次渲染阻塞到 ThemeService 激活会延后可见的加载与报错界面，也会让壳的故障呈现依赖被它监测的插件树。
|
||||
**让 ui-theme 客户端 bundle 同步或更早激活。** `immediately` 只控制预取，插件实例化仍发生在壳开始运行之后；把首次渲染阻塞到 ThemeRuntime 激活会延后可见的加载与报错界面，也会让壳的故障呈现依赖被它监测的插件树。
|
||||
|
||||
**只依赖 `prefers-color-scheme` 的 CSS。** 媒体查询无法读取显式持久化选择，因此操作系统为浅色而用户选择深色时仍会闪烁。
|
||||
|
||||
@@ -34,4 +34,4 @@ ui-theme 的单元测试覆盖不含任一可选 Host 服务时的激活、脚
|
||||
|
||||
## 后果
|
||||
|
||||
加载页首帧与持久化内建偏好一致；未组合 settings provider 时则默认采用系统偏好。index 转换会为每份响应读取 Host settings，而内联脚本只包含选定的内建值与 `system` 解析逻辑。内建偏好语义或 ThemePresenter DOM 字段变化时，必须同时更新脚本与 ThemeService。自定义主题仍会在浏览器插件激活后才完整应用；加载期间，页面使用该主题解析后的浅色或深色基础调色板。
|
||||
加载页首帧与持久化内建偏好一致；未组合 settings provider 时则默认采用系统偏好。index 转换会为每份响应读取 Host settings，而内联脚本只包含选定的内建值与 `system` 解析逻辑。内建偏好语义或 ThemePresenter DOM 字段变化时，必须同时更新脚本与 ThemeRuntime。自定义主题仍会在浏览器插件激活后才完整应用；加载期间，页面使用该主题解析后的浅色或深色基础调色板。
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-10-slash-catalog-follows-preset-switch.md
|
||||
2026-08-10-slash-catalog-follows-preset-switch.md: ec85d4a3a6a053e91c368f65ecb12f123c45287d
|
||||
2026-08-10-slash-catalog-follows-preset-switch.zh.md: 9b464dc54c125e2e15433871dc804981d916744d
|
||||
2026-08-10-slash-catalog-follows-preset-switch.md: 4015b2659ff65c676902bac940d493e0f55ffa99
|
||||
2026-08-10-slash-catalog-follows-preset-switch.zh.md: 61ada7e73043bf76eebf3bca3420d665c433f67c
|
||||
|
||||
@@ -6,15 +6,15 @@ English | [中文](2026-08-10-slash-catalog-follows-preset-switch.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
Presets moved the rows that decide what a session's `/` menu contains. The Web composition disables host-plane `skill-local`, `tool-skill`, `plan-mode`, and `command-compact`; a preset supplies them, so which commands and skills exist is a property of the session's composition rather than of the deployment.
|
||||
Presets moved the rows that decide what a session's `/` menu contains. The Web composition disables host-plane `skill-filesystem`, `tool-skill`, `plan-mode`, and `command-compact`; a preset supplies them, so which commands and skills exist is a property of the session's composition rather than of the deployment.
|
||||
|
||||
Both browser catalogs cache per session — `CommandDirectory` in `dsh-client-ui-command`, the single-flight fetch map in `dsh-client-ui-skill` — and the composer warms both at scope birth, under whatever preset the session was created with. The hero chip then lets the user recompose the still-blank session, and neither cache had an invalidation edge for that: `commands/change` is registry-wide and `connection/reset` needs a reconnect. `agentPresets.recompose` re-parents the agent's scope onto a standing mount that may already exist, so it registers nothing and the registry-wide signal never fires for it.
|
||||
Both browser catalogs cache per session — `CommandDirectory` in `dsh-client-ui-commands`, the single-flight fetch map in `dsh-client-ui-skill` — and the composer warms both at scope birth, under whatever preset the session was created with. The hero chip then lets the user recompose the still-blank session, and neither cache had an invalidation edge for that: `commands/change` is registry-wide and `connection/reset` needs a reconnect. `agentPresets.recompose` re-parents the agent's scope onto a standing mount that may already exist, so it registers nothing and the registry-wide signal never fires for it.
|
||||
|
||||
The menu therefore kept serving the composition the session no longer ran. Switching down left `compact`, `plan`, and every project skill listed; switching up left the narrower catalog — the four host-plane rows and the client's own `model` contribution — with no skills at all, which is what the bug report described. The catalog only healed when an unrelated registry change or a reconnect happened to invalidate it.
|
||||
|
||||
## Decision
|
||||
|
||||
The switch's commit point is the logged `agent-preset/selected` event. The preset owner re-emits that commit as the client-safe cordis owner event `agent-preset/selected(sessionId, agentPreset)`, the host stream forwards it verbatim, and each catalog subscribes directly through `ctx.remote.$on`: `ui-command` soft-refreshes the key (the old snapshot keeps serving the open menu until the new one lands), while `ui-skill` invalidates it (aborting an in-flight prewarm, so a warm racing the switch cannot publish the stale catalog).
|
||||
The switch's commit point is the logged `agent-preset/selected` event. The preset owner re-emits that commit as the client-safe cordis owner event `agent-preset/selected(sessionId, agentPreset)`, the host stream forwards it verbatim, and each catalog subscribes directly through `ctx.remote.$on`: `ui-commands` soft-refreshes the key (the old snapshot keeps serving the open menu until the new one lands), while `ui-skill` invalidates it (aborting an in-flight prewarm, so a warm racing the switch cannot publish the stale catalog).
|
||||
|
||||
The owner event is per session and carries no catalog, only the preset id. `ui-agent-preset` folds it into the session row because the `agentPresets.select` echo reaches only the client that issued the switch and the row is what the session header labels itself from (and what the hero chip compares the next pick against).
|
||||
|
||||
@@ -30,11 +30,11 @@ Deriving the owner event from the logged event rather than from the RPC handler'
|
||||
|
||||
## Consequences
|
||||
|
||||
The forwarding allowlist gains the preset owner's typed event, and every catalog a preset decides has one place to subscribe: a future per-session surface derived from the composition invalidates on the same signal instead of inventing another. The owner event remains a second publication of a logged fact, so a future switch path that recomposes without logging would go unannounced. `ui-command` stays soft (the open menu never blanks) while `ui-skill` drops its entry outright, because a skill catalog has no partial-serve mode; a menu opened inside the refetch window shows no skills for that instant rather than the wrong ones.
|
||||
The forwarding allowlist gains the preset owner's typed event, and every catalog a preset decides has one place to subscribe: a future per-session surface derived from the composition invalidates on the same signal instead of inventing another. The owner event remains a second publication of a logged fact, so a future switch path that recomposes without logging would go unannounced. `ui-commands` stays soft (the open menu never blanks) while `ui-skill` drops its entry outright, because a skill catalog has no partial-serve mode; a menu opened inside the refetch window shows no skills for that instant rather than the wrong ones.
|
||||
|
||||
## Testing
|
||||
|
||||
`api-proxy-agent-preset.spec.ts` asserts the committed switch is forwarded once with the session and its new preset; the `ui-agent-preset`, `ui-command`, and `ui-skill` specs assert that direct Remote subscriptions merge the row or repull only the recomposed session. The `agent-preset-selection` web e2e seeds a project skill and, after the hero chip applies `minimal`, asserts the `/` menu drops `compact`, `plan`, and the skill while keeping the host-plane rows — the assembled-application evidence that the panel follows the composition.
|
||||
`api-proxy-agent-preset.spec.ts` asserts the committed switch is forwarded once with the session and its new preset; the `ui-agent-preset`, `ui-commands`, and `ui-skill` specs assert that direct Remote subscriptions merge the row or repull only the recomposed session. The `agent-preset-selection` web e2e seeds a project skill and, after the hero chip applies `minimal`, asserts the `/` menu drops `compact`, `plan`, and the skill while keeping the host-plane rows — the assembled-application evidence that the panel follows the composition.
|
||||
|
||||
That e2e also stopped reading its staged-pick assertion off the serialized session list: the seeded session records `minimal` too, so the substring answered before the switch had landed. It now addresses the live session by id.
|
||||
|
||||
|
||||
@@ -6,15 +6,15 @@ Status: implemented
|
||||
|
||||
## 问题
|
||||
|
||||
preset 把决定 `/` 菜单内容的那些行搬走了。Web 组装禁用了宿主面的 `skill-local`、`tool-skill`、`plan-mode` 和 `command-compact`，改由 preset 提供，因此一个会话有哪些命令和技能，是它自身组成的属性，而不是部署的属性。
|
||||
preset 把决定 `/` 菜单内容的那些行搬走了。Web 组装禁用了宿主面的 `skill-filesystem`、`tool-skill`、`plan-mode` 和 `command-compact`，改由 preset 提供，因此一个会话有哪些命令和技能，是它自身组成的属性，而不是部署的属性。
|
||||
|
||||
浏览器侧两份目录都按会话缓存——`dsh-client-ui-command` 的 `CommandDirectory`，`dsh-client-ui-skill` 的 single-flight 拉取表——并且 composer 在 scope 出生时就按会话创建时的 preset 预热了它们。随后 hero 上的 chip 允许用户重组这个仍为空的会话，而两份缓存都没有对应的失效边：`commands/change` 是注册表级的，`connection/reset` 需要重连。`agentPresets.recompose` 只是把 agent 的 scope 重新挂接到一个可能已经存在的常驻挂载上，不产生任何注册，注册表级信号因此永远不会为它触发。
|
||||
浏览器侧两份目录都按会话缓存——`dsh-client-ui-commands` 的 `CommandDirectory`，`dsh-client-ui-skill` 的 single-flight 拉取表——并且 composer 在 scope 出生时就按会话创建时的 preset 预热了它们。随后 hero 上的 chip 允许用户重组这个仍为空的会话，而两份缓存都没有对应的失效边：`commands/change` 是注册表级的，`connection/reset` 需要重连。`agentPresets.recompose` 只是把 agent 的 scope 重新挂接到一个可能已经存在的常驻挂载上，不产生任何注册，注册表级信号因此永远不会为它触发。
|
||||
|
||||
于是菜单继续提供会话已经不再运行的那套组成。向下切换后 `compact`、`plan` 和全部项目技能仍列在菜单里；向上切换后留在原地的是更窄的目录——四条宿主面行加客户端自己的 `model` 贡献——而且完全没有技能，这正是 bug 报告描述的现象。只有当某个无关的注册表变化或一次重连恰好使其失效时，目录才会自愈。
|
||||
|
||||
## 决策
|
||||
|
||||
这次切换的提交点是落账的 `agent-preset/selected` 事件。preset owner 将该提交重新发为 client-safe 的 cordis owner 事件 `agent-preset/selected(sessionId, agentPreset)`，宿主流原样转发它，两份目录各自通过 `ctx.remote.$on` 直接订阅：`ui-command` 软刷新该键（新快照落地前，旧快照继续服务已打开的菜单），`ui-skill` 让它失效（并中止在途的预热，使一次与切换赛跑的 warm 无法发布过期目录）。
|
||||
这次切换的提交点是落账的 `agent-preset/selected` 事件。preset owner 将该提交重新发为 client-safe 的 cordis owner 事件 `agent-preset/selected(sessionId, agentPreset)`，宿主流原样转发它，两份目录各自通过 `ctx.remote.$on` 直接订阅：`ui-commands` 软刷新该键（新快照落地前，旧快照继续服务已打开的菜单），`ui-skill` 让它失效（并中止在途的预热，使一次与切换赛跑的 warm 无法发布过期目录）。
|
||||
|
||||
该 owner 事件按会话粒度，不携带目录，只带 preset id。`ui-agent-preset` 会把它折进会话行，因为 `agentPresets.select` 的回执只会到达发起切换的那个客户端，而会话头部标签正是以这一行为准（hero chip 比较下一次选择时读的也是它）。
|
||||
|
||||
@@ -30,11 +30,11 @@ preset 把决定 `/` 菜单内容的那些行搬走了。Web 组装禁用了宿
|
||||
|
||||
## 后果
|
||||
|
||||
转发名单加入了 preset owner 的类型化事件，而每一份由 preset 决定的目录从此有了统一的订阅点：将来任何从组成派生的按会话界面，都在同一个信号上失效，而不必再发明一个。owner 事件仍是落账事实的第二次发布，因此将来若出现一条不落账就重组的切换路径，它将无人宣告。`ui-command` 保持软失效（已打开的菜单不会变空），而 `ui-skill` 直接丢弃该项，因为技能目录没有「部分可服务」的状态；在重拉窗口内打开的菜单，那一瞬间显示的是没有技能，而不是错误的技能。
|
||||
转发名单加入了 preset owner 的类型化事件，而每一份由 preset 决定的目录从此有了统一的订阅点：将来任何从组成派生的按会话界面，都在同一个信号上失效，而不必再发明一个。owner 事件仍是落账事实的第二次发布，因此将来若出现一条不落账就重组的切换路径，它将无人宣告。`ui-commands` 保持软失效（已打开的菜单不会变空），而 `ui-skill` 直接丢弃该项，因为技能目录没有「部分可服务」的状态；在重拉窗口内打开的菜单，那一瞬间显示的是没有技能，而不是错误的技能。
|
||||
|
||||
## 测试
|
||||
|
||||
`api-proxy-agent-preset.spec.ts` 断言已提交的切换恰好转发一次，并带上会话与新 preset；`ui-agent-preset`、`ui-command` 与 `ui-skill` 的 spec 断言直接 Remote 订阅会合并会话行或只重拉被重组的会话。`agent-preset-selection` web e2e 播种一个项目技能，并在 hero chip 应用 `minimal` 之后断言 `/` 菜单丢掉了 `compact`、`plan` 和该技能，同时保留宿主面的那几行——这是面板跟随组成的整装应用证据。
|
||||
`api-proxy-agent-preset.spec.ts` 断言已提交的切换恰好转发一次，并带上会话与新 preset；`ui-agent-preset`、`ui-commands` 与 `ui-skill` 的 spec 断言直接 Remote 订阅会合并会话行或只重拉被重组的会话。`agent-preset-selection` web e2e 播种一个项目技能，并在 hero chip 应用 `minimal` 之后断言 `/` 菜单丢掉了 `compact`、`plan` 和该技能，同时保留宿主面的那几行——这是面板跟随组成的整装应用证据。
|
||||
|
||||
同一条 e2e 也不再从序列化后的会话列表里读它的 staged-pick 断言：被播种的会话同样记录着 `minimal`，子串匹配在切换落地之前就会通过。现在它按 id 寻址那个活跃会话。
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-11-bounded-background-task-admission.md
|
||||
2026-08-11-bounded-background-task-admission.md: 24512a87f554cd2d775fe76c5a6e5a700a51f2e4
|
||||
2026-08-11-bounded-background-task-admission.zh.md: dc3abaf4a64a4dc5fe5cacaabd3c29e278874646
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-11-bounded-background-job-admission.md
|
||||
2026-08-11-bounded-background-job-admission.md: 8fa5bec07647947b730c436284da71b83deedb48
|
||||
2026-08-11-bounded-background-job-admission.zh.md: d827e07aacc7bc933474577214d94bab9fe5f5c3
|
||||
@@ -1,22 +1,22 @@
|
||||
# Agent Note: Bounded background task admission
|
||||
# Agent Note: Bounded background job admission
|
||||
|
||||
Status: implemented
|
||||
|
||||
English | [中文](2026-08-11-bounded-background-task-admission.zh.md)
|
||||
English | [中文](2026-08-11-bounded-background-job-admission.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
A model can start background Bash, PowerShell, PTY operations, and one-shot subagents in separate tool calls and later turns. The agent loop's `maxParallelToolCalls` limits only calls still executing inside one step; each background producer returns a task id immediately, so repeated starts can grow live processes or child work without bound.
|
||||
A model can start background Bash, PowerShell, PTY operations, and one-shot subagents in separate tool calls and later turns. The agent loop's `maxParallelToolCalls` limits only calls still executing inside one step; each background producer returns a job id immediately, so repeated starts can grow live processes or child work without bound.
|
||||
|
||||
The process-local task registry already owns the exact task owner and the authoritative lifecycle state, but it retained terminal history beside live records and had no admission policy. Releasing capacity when cancellation was requested would also be incorrect: a `stopping` producer may still own its process, PTY, or child until `TaskHooks.done` settles.
|
||||
The process-local job registry already owns the exact job owner and the authoritative lifecycle state, but it retained terminal history beside live records and had no admission policy. Releasing capacity when cancellation was requested would also be incorrect: a `stopping` producer may still own its process, PTY, or child until `JobHooks.done` settles.
|
||||
|
||||
## Decision
|
||||
|
||||
`LocalTaskService` owns a `maxConcurrentTasksPerOwner` configuration field. It accepts positive safe integers, defaults to `10`, and is available through the provider's Cordis schema, the typed `agent-spine-demo` bundle, and the ACP app configuration. The bundle transports the value; the process-local provider owns its meaning.
|
||||
`LocalJobRegistry` owns a `maxConcurrentJobsPerOwner` configuration field. It accepts positive safe integers, defaults to `10`, and is available through the provider's Cordis schema, the typed `agent-spine-demo` bundle, and the ACP app configuration. The bundle transports the value; the process-local provider owns its meaning.
|
||||
|
||||
The [generic task runtime decision](../architecture/2026-06-20-generic-long-running-tool-runtime.md) owns the shared Task lifecycle and control API; this note owns the process-local admission policy.
|
||||
The [generic job runtime decision](../architecture/2026-06-20-generic-long-running-tool-runtime.md) owns the shared Task lifecycle and control API; this note owns the process-local admission policy.
|
||||
|
||||
`start()` performs admission after the existing task-controller, task-field, and live-owner checks and before `TaskStart.run()`. It derives the active count from the registry's current records instead of storing another counter:
|
||||
`start()` performs admission after the existing task-controller, task-field, and live-owner checks and before `JobStart.run()`. It derives the active count from the registry's current records instead of storing another counter:
|
||||
|
||||
| Record | Occupies capacity | Release fact |
|
||||
|---|---:|---|
|
||||
@@ -24,9 +24,9 @@ The [generic task runtime decision](../architecture/2026-06-20-generic-long-runn
|
||||
| `stopping` | yes | producer `done` settles |
|
||||
| `completed`, `killed`, or `failed` | no | already terminal |
|
||||
|
||||
Owned tasks are bucketed by exact `Agent` object identity, matching owner cleanup. Replacement agents that reuse a session id receive an independent bucket. Tasks without an owner share one service-level bucket, so omitting ownership is not an unlimited bypass.
|
||||
Owned tasks are bucketed by exact `Agent` object identity, matching owner cleanup. Replacement agents that reuse a session id receive an independent bucket. Jobs without an owner share one service-level bucket, so omitting ownership is not an unlimited bypass.
|
||||
|
||||
When the bucket is full, `start()` throws before producer execution and task-id allocation. The diagnostic includes the current limit and tells the model to use `task_kill`, wait until the task finishes stopping, and retry. Rejection creates no execution resource, queue entry, reservation, or public task record; a later successful start receives the next ordinary per-kind id.
|
||||
When the bucket is full, `start()` throws before producer execution and task-id allocation. The diagnostic includes the current limit and tells the model to use `job_kill`, wait until the task finishes stopping, and retry. Rejection creates no execution resource, queue entry, reservation, or public job record; a later successful start receives the next ordinary per-kind id.
|
||||
|
||||
Owner and service disposal keep their existing order: request cancellation, retain `stopping` occupancy while producers release resources, await settlement, then remove records. The admission policy therefore follows the same lifecycle fact used by reads, notices, and cleanup rather than treating a cancellation request as resource release.
|
||||
|
||||
@@ -38,13 +38,13 @@ The task-provider suite covers the default and explicit limits, producer-before
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
**Rely on `maxParallelToolCalls`.** Rejected because a background tool call releases its step slot as soon as it returns a task id; the setting cannot bound work that remains live across later steps and turns.
|
||||
**Rely on `maxParallelToolCalls`.** Rejected because a background tool call releases its step slot as soon as it returns a job id; the setting cannot bound work that remains live across later steps and turns.
|
||||
|
||||
**Release capacity when `task_kill` succeeds.** Rejected because successful cancellation only changes the task to `stopping`. The producer may still hold the resource until `done` settles, so admitting a replacement immediately would exceed the configured live-resource bound.
|
||||
**Release capacity when `job_kill` succeeds.** Rejected because successful cancellation only changes the task to `stopping`. The producer may still hold the resource until `done` settles, so admitting a replacement immediately would exceed the configured live-resource bound.
|
||||
|
||||
**Use one global process bucket.** Rejected because one busy agent would deny unrelated sessions, while unowned host work still needs an explicit bounded bucket. Exact owner identity already defines the cleanup lifecycle and supplies the correct partition.
|
||||
|
||||
**Queue, preempt, or terminate the oldest task.** Rejected because each policy adds ordering, ownership, and cancellation behavior beyond the requested fail-closed limit. An explicit rejection lets the model decide which work is no longer needed through the existing `task_kill` control.
|
||||
**Queue, preempt, or terminate the oldest task.** Rejected because each policy adds ordering, ownership, and cancellation behavior beyond the requested fail-closed limit. An explicit rejection lets the model decide which work is no longer needed through the existing `job_kill` control.
|
||||
|
||||
**Maintain a mutable active-count map.** Rejected because the registry already holds the authoritative records and statuses. A second count would require rollback and settlement synchronization while providing no user result that a direct derivation lacks.
|
||||
|
||||
@@ -2,21 +2,21 @@
|
||||
|
||||
Status: implemented
|
||||
|
||||
[English](2026-08-11-bounded-background-task-admission.md) | 中文
|
||||
[English](2026-08-11-bounded-background-job-admission.md) | 中文
|
||||
|
||||
## 问题
|
||||
|
||||
模型可以在不同工具调用和后续回合中启动后台 Bash、PowerShell、PTY 操作与一次性 subagent。agent loop 的 `maxParallelToolCalls` 只限制单个步骤中尚未返回的调用；每个后台生产方会立即返回 task id，因此反复启动会让仍存活的进程或子工作无限增长。
|
||||
模型可以在不同工具调用和后续回合中启动后台 Bash、PowerShell、PTY 操作与一次性 subagent。agent loop 的 `maxParallelToolCalls` 只限制单个步骤中尚未返回的调用；每个后台生产方会立即返回 job id，因此反复启动会让仍存活的进程或子工作无限增长。
|
||||
|
||||
进程内任务注册表已经拥有确切任务 owner 与权威生命周期状态，但终止历史和实时记录保存在一起，且没有准入策略。在请求取消时立即释放容量也不正确：处于 `stopping` 的生产方仍可能拥有进程、PTY 或子任务，直到 `TaskHooks.done` 结算。
|
||||
进程内任务注册表已经拥有确切任务 owner 与权威生命周期状态，但终止历史和实时记录保存在一起，且没有准入策略。在请求取消时立即释放容量也不正确：处于 `stopping` 的生产方仍可能拥有进程、PTY 或子任务，直到 `JobHooks.done` 结算。
|
||||
|
||||
## 决策
|
||||
|
||||
`LocalTaskService` 拥有 `maxConcurrentTasksPerOwner` 配置字段。它只接受正的安全整数，默认值为 `10`，并通过 Service provider 的 Cordis schema、typed `agent-spine-demo` 组合包与 ACP 应用配置提供。组合包只传输该值；其含义归进程内 Service provider 所有。
|
||||
`LocalJobRegistry` 拥有 `maxConcurrentJobsPerOwner` 配置字段。它只接受正的安全整数，默认值为 `10`，并通过 Service provider 的 Cordis schema、typed `agent-spine-demo` 组合包与 ACP 应用配置提供。组合包只传输该值；其含义归进程内 Service provider 所有。
|
||||
|
||||
[通用任务运行时决策](../architecture/2026-06-20-generic-long-running-tool-runtime.md)拥有共享 Task 生命周期与控制 API；本记录只拥有进程内准入策略。
|
||||
|
||||
`start()` 在现有任务控制器、任务字段与存活 owner 检查之后、`TaskStart.run()` 之前执行准入。它从注册表当前记录派生活动数量，而不保存另一份计数：
|
||||
`start()` 在现有任务控制器、任务字段与存活 owner 检查之后、`JobStart.run()` 之前执行准入。它从注册表当前记录派生活动数量，而不保存另一份计数：
|
||||
|
||||
| 记录 | 占用容量 | 释放事实 |
|
||||
|---|---:|---|
|
||||
@@ -26,7 +26,7 @@ Status: implemented
|
||||
|
||||
有 owner 的任务按确切 `Agent` 对象身份分桶，与 owner 清理保持一致。复用同一会话 id 的替代 agent 获得独立桶。无 owner 的任务共享一个服务级桶，因此省略 owner 不会成为无界旁路。
|
||||
|
||||
桶已满时，`start()` 会在生产方执行和 task id 分配前抛出异常。诊断包含当前上限，并告诉模型使用 `task_kill`、等待任务完全停稳后再重试。拒绝不会创建执行资源、排队项、预留或公开任务记录；后续成功启动仍会取得按 kind 正常递增的下一个 id。
|
||||
桶已满时，`start()` 会在生产方执行和 job id 分配前抛出异常。诊断包含当前上限，并告诉模型使用 `job_kill`、等待任务完全停稳后再重试。拒绝不会创建执行资源、排队项、预留或公开任务记录；后续成功启动仍会取得按 kind 正常递增的下一个 id。
|
||||
|
||||
owner 与服务释放保留现有顺序：请求取消，在生产方释放资源期间继续让 `stopping` 占位，等待结算，然后移除记录。因此，准入策略遵循读取、通知与清理共同使用的同一生命周期事实，而不会把取消请求误当成资源释放。
|
||||
|
||||
@@ -34,17 +34,17 @@ owner 与服务释放保留现有顺序：请求取消，在生产方释放资
|
||||
|
||||
## 验证
|
||||
|
||||
任务 Service provider 测试覆盖默认与显式上限、生产方执行前拒绝、id 计数器不变、`stopping` 占位、每种终态释放、确切 owner 隔离、同会话替代对象、共享无 owner 桶、非法配置、owner 清理和服务拆除。spine 与 ACP 组合测试固定 typed 转发。一条 keyless ACP 回放以 1 为上限启动真实 Loader 组合，启动一个真实后台 Bash 进程，观察第二次启动返回可操作错误，按返回的 task id 停止第一个任务，并验证被拒绝生产方的标记文件从未生成。
|
||||
任务 Service provider 测试覆盖默认与显式上限、生产方执行前拒绝、id 计数器不变、`stopping` 占位、每种终态释放、确切 owner 隔离、同会话替代对象、共享无 owner 桶、非法配置、owner 清理和服务拆除。spine 与 ACP 组合测试固定 typed 转发。一条 keyless ACP 回放以 1 为上限启动真实 Loader 组合，启动一个真实后台 Bash 进程，观察第二次启动返回可操作错误，按返回的 job id 停止第一个任务，并验证被拒绝生产方的标记文件从未生成。
|
||||
|
||||
## 曾考虑的替代方案
|
||||
|
||||
**依赖 `maxParallelToolCalls`。**否决，因为后台工具调用一返回 task id 就会释放其步骤槽位；该设置无法限制在后续步骤和回合中继续存活的工作。
|
||||
**依赖 `maxParallelToolCalls`。**否决，因为后台工具调用一返回 job id 就会释放其步骤槽位；该设置无法限制在后续步骤和回合中继续存活的工作。
|
||||
|
||||
**在 `task_kill` 成功时释放容量。**否决，因为取消成功只会把任务改为 `stopping`。生产方在 `done` 结算前仍可能持有资源，立即准入替代任务会突破已配置的实时资源上限。
|
||||
**在 `job_kill` 成功时释放容量。**否决，因为取消成功只会把任务改为 `stopping`。生产方在 `done` 结算前仍可能持有资源，立即准入替代任务会突破已配置的实时资源上限。
|
||||
|
||||
**使用一个全局进程桶。**否决，因为一个繁忙 agent 会拒绝无关会话，而无 owner 的宿主工作仍需要一个明确的有界桶。确切 owner 身份已经定义清理生命周期，并提供正确分区。
|
||||
|
||||
**排队、抢占或终止最旧任务。**否决，因为每种策略都会增加超出 fail-closed 上限要求的顺序、所有权和取消行为。显式拒绝让模型通过现有 `task_kill` 控制自行决定哪些工作不再需要。
|
||||
**排队、抢占或终止最旧任务。**否决，因为每种策略都会增加超出 fail-closed 上限要求的顺序、所有权和取消行为。显式拒绝让模型通过现有 `job_kill` 控制自行决定哪些工作不再需要。
|
||||
|
||||
**维护一张可变活动计数表。**否决，因为注册表已经保存权威记录与状态。第二份计数需要回滚和结算同步，却无法提供直接派生所缺少的用户结果。
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-11-preset-authoring-agent-validates-its-own-composition.md
|
||||
2026-08-11-preset-authoring-agent-validates-its-own-composition.md: eb21094f0d859a31d5f16d780cada6818a508b36
|
||||
2026-08-11-preset-authoring-agent-validates-its-own-composition.zh.md: 1db4197673f18979907c46376cbb7102160172b5
|
||||
2026-08-11-preset-authoring-agent-validates-its-own-composition.md: 8fefb3e0fc95ac4d1d2b7c2035f312e25cf107a0
|
||||
2026-08-11-preset-authoring-agent-validates-its-own-composition.zh.md: 7b3efca2ecd83f5a5d236eb02d505a2145dee764
|
||||
|
||||
@@ -8,9 +8,9 @@ English | [中文](2026-08-11-preset-authoring-agent-validates-its-own-compositi
|
||||
|
||||
The `cordis` preset ships `editing-cordis-compositions`, the only guidance an agent has when it authors a preset. Four of its statements were false, and the two that carried the most weight pointed at the rule the skill itself calls "the rule that catches people".
|
||||
|
||||
It named `tool-bash` as the worked example of a row whose name hides a service — "reads like a tool but provides `bashEnv`". `tool-bash` provides nothing; it declares `inject: ['tools', 'bash', 'systemPrompt', 'bashEnv']`, and `bashEnv` comes from the host composition's own `bash-env` row. An agent wrapping `tool-bash` in an `isolate` realm on that advice strands the row waiting for a service its realm hides, and the whole preset fails to mount.
|
||||
It named `tool-bash` as the worked example of a row whose name hides a service — "reads like a tool but provides `bashEnv`". `tool-bash` provides nothing; it declares `inject: ['tools', 'bash', 'systemPrompt', 'bashEnv']`, and `bashEnv` comes from the host composition's own `shell-env` row. An agent wrapping `tool-bash` in an `isolate` realm on that advice strands the row waiting for a service its realm hides, and the whole preset fails to mount.
|
||||
|
||||
Its `isolate` example composed `tasks-local` with `tool-tasks`. `tasks-local` is host-plane, and the shipped compositions say in their own comments that an entry-local realm around `tool-tasks` makes `run_in_background` answer "background tasks unavailable". The example contradicted the file next to it.
|
||||
Its `isolate` example composed `jobs-local` with `tool-jobs`. `jobs-local` is host-plane, and the shipped compositions say in their own comments that an entry-local realm around `tool-jobs` makes `run_in_background` answer "background jobs unavailable". The example contradicted the file next to it.
|
||||
|
||||
It described a string realm label as pooling one instance across subtrees. Labels join realms; `provide()` still throws on the second registration under the same realm symbol, which `standard`'s header comment already stated.
|
||||
|
||||
@@ -34,7 +34,7 @@ The agent reaches the roster service the way `cordis_mount` documents: a tempora
|
||||
|
||||
The guidance keeps `${DSH_HOME:-$HOME/.dsh}/.agent-presets/` as the answer to "where do my presets live" while routing the path an agent actually reads or edits through `list()` or `resolve()`. Stating the path is right for talking to a person and wrong for feeding a file tool: a deployment may configure other roots, and `list()` cannot reveal a user root that holds nothing yet.
|
||||
|
||||
That path is now a property of the package rather than of one launcher. `AgentPresets` derives `<dshHome>/.agent-presets` as a `user` root unless `includeUserRoot` is false, the way [`dsh-skill-local`](../../../../packages/skill/skill-local/README.md) derives `<dshHome>/skills`, and `apps/cli` supplies only the SHIPPED root — the one path an installed app alone can resolve. The asymmetry it replaces cost a bug: with both roots patched in by one launcher, `dsh run` booted a roster with no roots at all and failed resolving `standard` (fixed then by teaching every launcher the patch). The derived root is appended after every configured root, so a shipped id still shadows a home directory claiming it, and `writableRoot()` still prefers an explicitly configured `user` root. It is resolved once at construction: a root set that changed between a `list()` and the `copy()` acting on its answer would author into a directory the caller never saw.
|
||||
That path is now a property of the package rather than of one launcher. `AgentPresets` derives `<dshHome>/.agent-presets` as a `user` root unless `includeUserRoot` is false, the way [`dsh-skill-filesystem`](../../../../packages/skill/skill-filesystem/README.md) derives `<dshHome>/skills`, and `apps/cli` supplies only the SHIPPED root — the one path an installed app alone can resolve. The asymmetry it replaces cost a bug: with both roots patched in by one launcher, `dsh run` booted a roster with no roots at all and failed resolving `standard` (fixed then by teaching every launcher the patch). The derived root is appended after every configured root, so a shipped id still shadows a home directory claiming it, and `writableRoot()` still prefers an explicitly configured `user` root. It is resolved once at construction: a root set that changed between a `list()` and the `copy()` acting on its answer would author into a directory the caller never saw.
|
||||
|
||||
The prohibition on touching the shipped install is promoted from a paragraph inside the authoring steps to a top `## Off-limits` section, extended to cover editing the host composition as a workaround. The new self-validation calls do not weaken it: `copy()` refuses an id any root supplies, and `remove()` refuses a preset that ships with the deployment.
|
||||
|
||||
@@ -45,7 +45,7 @@ Each row was produced by booting the shipped Web composition and calling the too
|
||||
| Composition under test | `list()` `broken` | `standingKeyFor()` |
|
||||
|---|---|---|
|
||||
| row names an absent package | empty | `Cannot find package '@deepseek-ai/dsh-does-not-exist'` |
|
||||
| service row with no realm, name the host supplies | empty | `service "tasks" has been registered at <LocalTaskService>` |
|
||||
| service row with no realm, name the host supplies | empty | `service "tasks" has been registered at <LocalJobRegistry>` |
|
||||
| service row with no realm, name the host does not supply | empty | `row(s) published process-global service(s) [workflows]; …` |
|
||||
| same row inside `isolate` | empty | mounts |
|
||||
| consumer row with no provider | empty | `1 row(s) did not activate: … waiting for workflows` |
|
||||
|
||||
@@ -8,9 +8,9 @@ Status: implemented
|
||||
|
||||
`cordis` preset 随包发布 `editing-cordis-compositions`，它是 agent 创作 preset 时唯一的指导来源。其中四条陈述与事实不符，而分量最重的两条恰好指向该 skill 自称「最容易让人栽跟头的规则」。
|
||||
|
||||
它把 `tool-bash` 当作「行名看不出发布服务」的示例——「看着像工具，其实 provides `bashEnv`」。`tool-bash` 不发布任何服务，它声明 `inject: ['tools', 'bash', 'systemPrompt', 'bashEnv']`，`bashEnv` 来自宿主组装自己的 `bash-env` 行。agent 照此给 `tool-bash` 套上 `isolate` realm，该行会永远等待被自己的 realm 挡住的服务，整个 preset 挂载失败。
|
||||
它把 `tool-bash` 当作「行名看不出发布服务」的示例——「看着像工具，其实 provides `bashEnv`」。`tool-bash` 不发布任何服务，它声明 `inject: ['tools', 'bash', 'systemPrompt', 'bashEnv']`，`bashEnv` 来自宿主组装自己的 `shell-env` 行。agent 照此给 `tool-bash` 套上 `isolate` realm，该行会永远等待被自己的 realm 挡住的服务，整个 preset 挂载失败。
|
||||
|
||||
它的 `isolate` 示例把 `tasks-local` 与 `tool-tasks` 组在一起。`tasks-local` 位于宿主平面，而已发布组装在自己的注释里写明：给 `tool-tasks` 套 entry-local realm 会让 `run_in_background` 回答「background tasks unavailable」。示例与紧挨着它的文件互相矛盾。
|
||||
它的 `isolate` 示例把 `jobs-local` 与 `tool-jobs` 组在一起。`jobs-local` 位于宿主平面，而已发布组装在自己的注释里写明：给 `tool-jobs` 套 entry-local realm 会让 `run_in_background` 回答「background jobs unavailable」。示例与紧挨着它的文件互相矛盾。
|
||||
|
||||
它把字符串 realm label 描述为跨子树共享一个实例。label 只是加入同一 realm，`provide()` 在同一 realm symbol 下第二次注册仍然抛错——`standard` 的头部注释早已如此说明。
|
||||
|
||||
@@ -34,7 +34,7 @@ agent 按 `cordis_mount` 自身文档所述的方式够到 roster 服务：挂
|
||||
|
||||
指导保留 `${DSH_HOME:-$HOME/.dsh}/.agent-presets/` 作为「我的 preset 在哪」的答案，同时把 agent 实际读取或编辑的路径改走 `list()` 或 `resolve()`。写出该路径对人讲是对的，喂给文件工具是错的：部署可以配置其他根目录，而 `list()` 无法揭示一个尚且为空的用户根。
|
||||
|
||||
该路径如今是本包的属性，而非某个启动器的属性。除非 `includeUserRoot` 为 false，`AgentPresets` 自行推导 `<dshHome>/.agent-presets` 作为 `user` 根，正如 [`dsh-skill-local`](../../../../packages/skill/skill-local/README.md) 推导 `<dshHome>/skills`；`apps/cli` 只提供**随附**根——那是唯有已安装 app 才能解析的路径。它取代的那种不对称曾付出过代价：两个根都由单一启动器补入时，`dsh run` 启动的 roster 一个根都没有，解析 `standard` 直接失败（当时的修法是让每个启动器都执行该 patch）。推导出的根追加在全部已配置根之后，因此随附 id 仍会遮蔽占用它的家目录目录，而 `writableRoot()` 仍优先选择显式配置的 `user` 根。它在构造时解析一次：若根目录集合在一次 `list()` 与依据其答案执行的 `copy()` 之间发生变化，写入的将是调用方从未见过的目录。
|
||||
该路径如今是本包的属性，而非某个启动器的属性。除非 `includeUserRoot` 为 false，`AgentPresets` 自行推导 `<dshHome>/.agent-presets` 作为 `user` 根，正如 [`dsh-skill-filesystem`](../../../../packages/skill/skill-filesystem/README.md) 推导 `<dshHome>/skills`；`apps/cli` 只提供**随附**根——那是唯有已安装 app 才能解析的路径。它取代的那种不对称曾付出过代价：两个根都由单一启动器补入时，`dsh run` 启动的 roster 一个根都没有，解析 `standard` 直接失败（当时的修法是让每个启动器都执行该 patch）。推导出的根追加在全部已配置根之后，因此随附 id 仍会遮蔽占用它的家目录目录，而 `writableRoot()` 仍优先选择显式配置的 `user` 根。它在构造时解析一次：若根目录集合在一次 `list()` 与依据其答案执行的 `copy()` 之间发生变化，写入的将是调用方从未见过的目录。
|
||||
|
||||
禁止改动随发布安装的约束，从创作步骤中的一段提升为顶部的 `## Off-limits` 一节，并扩展到禁止改宿主组装绕行。新增的自校验调用不削弱它：`copy()` 拒绝任何根已提供的 id，`remove()` 拒绝随部署发布的 preset。
|
||||
|
||||
@@ -45,7 +45,7 @@ agent 按 `cordis_mount` 自身文档所述的方式够到 roster 服务：挂
|
||||
| 被测组装 | `list()` 的 `broken` | `standingKeyFor()` |
|
||||
|---|---|---|
|
||||
| 行指向不存在的包 | 空 | `Cannot find package '@deepseek-ai/dsh-does-not-exist'` |
|
||||
| 服务行未套 realm，名字宿主已提供 | 空 | `service "tasks" has been registered at <LocalTaskService>` |
|
||||
| 服务行未套 realm，名字宿主已提供 | 空 | `service "tasks" has been registered at <LocalJobRegistry>` |
|
||||
| 服务行未套 realm，名字宿主未提供 | 空 | `row(s) published process-global service(s) [workflows]; …` |
|
||||
| 同一行置于 `isolate` 内 | 空 | 挂载成功 |
|
||||
| 消费者行无人提供服务 | 空 | `1 row(s) did not activate: … waiting for workflows` |
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-11-synchronous-subprocess-exit-cleanup.md
|
||||
2026-08-11-synchronous-subprocess-exit-cleanup.md: fba5014d67f5152d6f8e42b3b41c1bbd20c7ede3
|
||||
2026-08-11-synchronous-subprocess-exit-cleanup.zh.md: 33e13b7a1af9a943a266ea3ec979bf14e24f3802
|
||||
2026-08-11-synchronous-subprocess-exit-cleanup.md: 70b2a95dda22e1e2bf12d76acf9a471a59c7e73b
|
||||
2026-08-11-synchronous-subprocess-exit-cleanup.zh.md: ea0b27583b44926d761a42de34d575800f8a8a13
|
||||
|
||||
@@ -12,7 +12,7 @@ The public subprocess seam correctly promises awaited quiescence during normal d
|
||||
|
||||
## Decision
|
||||
|
||||
`LocalSubprocessService` installs one synchronous Node `exit` listener in its Cordis effect. The same effect removes the listener only after normal disposal settles. Ordinary and terminal handles remain in the service's existing live sets while asynchronous cleanup is pending, so a shorter outer exit bound still sees and force-terminates them. If awaited disposal reports a cleanup failure, the service invokes the same synchronous final operations before clearing the sets and removing the listener.
|
||||
`LocalSubprocessRuntime` installs one synchronous Node `exit` listener in its Cordis effect. The same effect removes the listener only after normal disposal settles. Ordinary and terminal handles remain in the service's existing live sets while asynchronous cleanup is pending, so a shorter outer exit bound still sees and force-terminates them. If awaited disposal reports a cleanup failure, the service invokes the same synchronous final operations before clearing the sets and removing the listener.
|
||||
|
||||
The listener uses local-only final operations that are absent from the public `SubprocessHandle` and `SubprocessTerminalHandle` interfaces:
|
||||
|
||||
|
||||
@@ -12,7 +12,7 @@ Status: implemented
|
||||
|
||||
## Decision
|
||||
|
||||
`LocalSubprocessService`在自身 Cordis effect中安装一个同步 Node `exit` listener。只有正常 dispose结算后，同一 effect才移除该 listener。异步清理仍在等待时，普通和 terminal handle继续保留在服务已有的存活集合中，因此更短的外层退出上限仍能看到并强制终止它们。等待中的 dispose报告清理失败时，服务会在清空集合并移除 listener前调用同一组同步最终操作。
|
||||
`LocalSubprocessRuntime`在自身 Cordis effect中安装一个同步 Node `exit` listener。只有正常 dispose结算后，同一 effect才移除该 listener。异步清理仍在等待时，普通和 terminal handle继续保留在服务已有的存活集合中，因此更短的外层退出上限仍能看到并强制终止它们。等待中的 dispose报告清理失败时，服务会在清空集合并移除 listener前调用同一组同步最终操作。
|
||||
|
||||
该 listener使用本地实现私有的最终操作；公共 `SubprocessHandle`和 `SubprocessTerminalHandle`接口不包含这些操作：
|
||||
|
||||
|
||||
Reference in New Issue
Block a user