docs: fix review findings — residual ordinals, hypothetical IPC row, citation-rule amendments
Purge the residual task/phase ordinals review caught ((T2), (queue cut 1) ×3, T6, P-I, 'this cut' ×6 including battery-expansion finds in two untouched notes and a workflow JSDoc); drop the 'externally logged as Decision 21' parenthetical and rename the remaining bare decision-21 mentions; mark the gui-layering IPC bridge row as a hypothetical example; restore the GATE_NOTICE doc-typecheck clause and the py-types 'measured' provenance; say subprocess-backed in filesystem.md; add the picker note path. Amend the citations note: merged-PR evidence anchors in Agent Notes are sanctioned, and the candidate gate patterns gain the four shapes the sweep missed. All nine touched pairs re-recorded.
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/architecture/2026-07-19-gui-layering-and-rpc-protocol.md
|
||||
2026-07-19-gui-layering-and-rpc-protocol.md: f3aea8360ea1db9b29da01f143daf30cd969b0e5
|
||||
2026-07-19-gui-layering-and-rpc-protocol.zh.md: 27b5401960a31ee3cedf2366d3b7f4efc527d482
|
||||
2026-07-19-gui-layering-and-rpc-protocol.md: 7997a682c8745f7b3d0a9721acfa9355603f9b2e
|
||||
2026-07-19-gui-layering-and-rpc-protocol.zh.md: cb36b5cb725128e1c5067e5e69e52aa851668e52
|
||||
|
||||
@@ -218,7 +218,7 @@ All four quadrant full forms pass through `onEnvelope`; the base implementation
|
||||
| `InProcessApiClient` | apiproxy itself | the injected `{ fetch }` handler | **The isomorphic point**: `new InProcessApiClient(toFetchHandler(api))` never touches the network yet runs the real wire serialization/zod/SSE framing; carrier tests and callers can exercise the protocol without opening a port, while product `dsh run` drives core directly |
|
||||
| `WebApiClient` | dsh-client-connection | `globalThis.fetch` uplink + one same-origin WebSocket downlink per logical stream | the browser shape; physical boundary in the [WebSocket downlink carrier](2026-08-04-websocket-downlink-carrier.md) |
|
||||
| `FixtureApiClient` | dsh-client-connection | unused (protocol-layer override) | serverless UI development (`?fixture`): overrides the `callUnary`/`openMux`/`openHost`/`respond` virtuals and is itself the fake server (frame rpcIds minted by it, semantics self-consistent) |
|
||||
| IPC bridge subclass | apps/electron | IPC serialization round trip | swaps only doFetch; contract and base class unchanged |
|
||||
| IPC bridge subclass (hypothetical example — no such shell exists) | an Electron shell | IPC serialization round trip | would swap only doFetch; contract and base class unchanged |
|
||||
|
||||
## How to extend (operational checklists)
|
||||
|
||||
|
||||
@@ -216,7 +216,7 @@ export type ResponseValue<K> =
|
||||
| `InProcessApiClient` | apiproxy 本包 | 注入的 `{ fetch }` handler | **同构点**：`new InProcessApiClient(toFetchHandler(api))` 全程不过网络但真跑 wire 序列化/zod/SSE 帧；载体测试与调用方可以在不打开端口的情况下运行这套协议，而产品 `dsh run` 直接驱动 core |
|
||||
| `WebApiClient` | dsh-client-connection | `globalThis.fetch` 上行 + 每逻辑流一条同源 WebSocket 下行 | 浏览器形态；物理边界见 [WebSocket 下行载体](2026-08-04-websocket-downlink-carrier.md) |
|
||||
| `FixtureApiClient` | dsh-client-connection | 不用（协议层覆写） | 无 server 的 UI 开发（`?fixture`）：覆写 `callUnary`/`openMux`/`openHost`/`respond` 虚方法，自己就是假 server（帧 rpcId 由它 mint，语义自洽） |
|
||||
| IPC 桥子类 | apps/electron | IPC 序列化往返 | 仅换 doFetch，约定/基类零改 |
|
||||
| IPC 桥子类（假想示例——尚无此形态） | Electron 壳 | IPC 序列化往返 | 只需换 doFetch，约定/基类零改 |
|
||||
|
||||
## 怎么扩展（操作清单）
|
||||
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.md
|
||||
2026-07-25-web-input-machine-and-slash-pipeline.md: 345a08188fc6a4f2b951e8f9cd9d3a5b953a5e34
|
||||
2026-07-25-web-input-machine-and-slash-pipeline.zh.md: d454003036dd322ec3366c66293120cb2997de8d
|
||||
2026-07-25-web-input-machine-and-slash-pipeline.md: 1aca87530d4dcf1709f484cd471d8887c632f55b
|
||||
2026-07-25-web-input-machine-and-slash-pipeline.zh.md: 958b519e7f291033410b932ccca623d87954738d
|
||||
|
||||
@@ -78,7 +78,7 @@ A trigger/menu/pick pipeline with zero knowledge of "commands":
|
||||
|
||||
### Plain-text references: text outcomes and lexicon decoration
|
||||
|
||||
skill/@subagent references skip the placeholder + occurrence identity chain — the plain-text-reference decision (externally logged as Decision 21): a pick inserts the literal `/name ` `@name ` text straight into the draft, with the chip visual purely derived:
|
||||
skill/@subagent references skip the placeholder + occurrence identity chain — the plain-text-reference decision: a pick inserts the literal `/name ` `@name ` text straight into the draft, with the chip visual purely derived:
|
||||
|
||||
- PickOutcome gains a `{text}` arm; the new scoped bail event `slash/input-insert-text` `{text, span}` (the same contract as the other three: draftRev CAS, returning true ⟺ an actual rewrite); facade.insertText goes through setDraft concatenation — zero machine changes.
|
||||
- Sources get an optional `lexicon?(session)` hook: a synchronous hot-snapshot name roster, with `undefined` = data not warm — zero decoration, never triggering a fetch (the render path stays synchronous and side-effect-free); the paired optional `subscribeLexicon?(session, listener)` hook is the invalidation channel for rolls that change after warm (catalog settles, children spawn/exit). The controller aggregates the rolls into its `lexicon` snapshot store (re-polling on each source notification); sources registered after scope birth are warmed and folded in via the service's live-controller broadcast.
|
||||
|
||||
@@ -78,7 +78,7 @@ occurrence 表与 chip 三投影：
|
||||
|
||||
### 纯文本引用：text outcome 与 lexicon 装饰
|
||||
|
||||
skill/@subagent 引用不走占位符 + occurrence 身份链——纯文本引用决策（外部记录为决策 21）：pick 直接把 `/name ` `@name ` 原文插进 draft，chip 视觉纯派生：
|
||||
skill/@subagent 引用不走占位符 + occurrence 身份链——纯文本引用决策：pick 直接把 `/name ` `@name ` 原文插进 draft，chip 视觉纯派生：
|
||||
|
||||
- PickOutcome 增 `{text}` arm；新 scoped bail 事件 `slash/input-insert-text` `{text, span}`（与另三个同约定：draftRev CAS、返回 true ⟺ 实际改写）；facade.insertText 走 setDraft 拼接，机器零改动。
|
||||
- source 可选 `lexicon?(session)` 钩子：同步热快照名录，`undefined` = 数据未热——零装饰、永不触发 fetch（渲染路径保持同步无副作用）；配对的可选 `subscribeLexicon?(session, listener)` 钩子是名录在 warm 之后仍会变化（目录 settle、子代生灭）时的失效通道。controller 把各名录聚合进自己的 `lexicon` snapshot store（每次 source 通知重拉）；scope 出生后才注册的 source 由 service 广播给活 controller，补 warm 并并入名录。
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md
|
||||
2026-06-21-subagent-capability-seam.md: 82010b4d11d2de5fc00f892b05e73807530e9cbf
|
||||
2026-06-21-subagent-capability-seam.zh.md: dc4e35e9ca6de8790b26bda1aeca30af00db5e1d
|
||||
2026-06-21-subagent-capability-seam.md: 72f17d7566aa982a5710e466cb4f740906ef167b
|
||||
2026-06-21-subagent-capability-seam.zh.md: 8205a6e2eab3bdaddf25b582c590034e2cf2f8dd
|
||||
|
||||
@@ -62,7 +62,7 @@ Each in-process subagent runs in its **own `Session`** (own id, `parentSession`
|
||||
|
||||
### Provider selection is config, not model-facing
|
||||
|
||||
`dsh-tool-subagent` binds to exactly one provider name (`Config.provider`); the model sees only `{ description, prompt }`. To expose more than one transport, load the tool plugin more than once, each bound to a different provider and a distinct `toolName` (the tool registry rejects a duplicate name). The *service* holds the multi-provider registry; the *tool* picks one — no provider/type parameter in the schema this cut.
|
||||
`dsh-tool-subagent` binds to exactly one provider name (`Config.provider`); the model sees only `{ description, prompt }`. To expose more than one transport, load the tool plugin more than once, each bound to a different provider and a distinct `toolName` (the tool registry rejects a duplicate name). The *service* holds the multi-provider registry; the *tool* picks one — the schema carries no provider/type parameter.
|
||||
|
||||
## Testing
|
||||
|
||||
@@ -72,5 +72,5 @@ Registry and tool tests replace only the nondeterministic child boundary with a
|
||||
|
||||
- **Recursion.** Without a bound, an in-process child can see the delegation tool and recurse. The in-process backends implement the optional absolute depth limit and scoped live-global `toolFilter`; ACP advertises both capabilities off and rejects such a request. The [subagent composition-controls Agent Note](2026-07-12-subagent-persona-tool-filter-and-depth.md) owns their exact semantics and security limits.
|
||||
- **Blocking the parent turn.** Foreground collection holds the parent's step open for the child's full duration. Background delegation uses the shared `ctx.tasks` runtime and generic `task_*` tools, the same collection mechanism as background bash; the subagent seam itself remains task-agnostic.
|
||||
- **Live progress.** This cut surfaces only lifecycle + final result; a per-chunk child→parent update stream is deferred with the background redesign.
|
||||
- **Live progress.** Only lifecycle + the final result surface; a per-chunk child→parent update stream is deferred with the background redesign.
|
||||
- **ACP client surface.** Proxying `fs`/`terminal` from the ACP child back to the parent (a shared-workspace mode) is future work; the first cut advertises neither, so the child self-serves in its own process.
|
||||
|
||||
@@ -62,7 +62,7 @@ bash seam（[能力 seam](../architecture/2026-06-13-capability-seams.md)）在
|
||||
|
||||
### 提供方选择是配置，不面向模型
|
||||
|
||||
`dsh-tool-subagent` 绑定到恰好一个提供方名称（`Config.provider`）；模型只看到 `{ description, prompt }`。若要暴露多种传输方式，请多次加载该工具插件，每次绑定不同的提供方和不同的 `toolName`（工具注册表拒绝重名）。*服务*持有多提供方注册表；*工具*选择其中一个——本版 schema 中没有提供方/type 参数。
|
||||
`dsh-tool-subagent` 绑定到恰好一个提供方名称（`Config.provider`）；模型只看到 `{ description, prompt }`。若要暴露多种传输方式，请多次加载该工具插件，每次绑定不同的提供方和不同的 `toolName`（工具注册表拒绝重名）。*服务*持有多提供方注册表；*工具*选择其中一个——schema 中没有提供方/type 参数。
|
||||
|
||||
## 测试
|
||||
|
||||
@@ -72,5 +72,5 @@ bash seam（[能力 seam](../architecture/2026-06-13-capability-seams.md)）在
|
||||
|
||||
- **递归。** 如果不设限制，进程内子 agent 能看到委派工具并递归调用。进程内后端实现了可选的绝对深度限制和有作用域的实时全局 `toolFilter`；ACP 声明这两项能力为关闭状态，并拒绝此类请求。[subagent 组合控制 Agent Note](2026-07-12-subagent-persona-tool-filter-and-depth.md) 负责定义它们的确切语义和安全边界。
|
||||
- **阻塞父轮次。** 前台收集在子 agent 的整个持续时间内保持父 agent 的步骤打开。后台委派使用共享的 `ctx.tasks` 运行时与通用 `task_*` 工具，与后台 bash 共用同一套收集机制；subagent seam 本身仍不感知任务。
|
||||
- **实时进度。** 本版仅暴露生命周期事件与最终结果；逐分片的子→父更新流推迟到后台重新设计时一并处理。
|
||||
- **实时进度。** 仅暴露生命周期事件与最终结果；逐分片的子→父更新流推迟到后台重新设计时一并处理。
|
||||
- **ACP 客户端接口。** 将 ACP 子 agent 的 `fs`/`terminal` 代理回父 agent（共享工作区模式）是后续工作；首版不声明这两项能力，子 agent 在自己的进程中自行服务。
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-06-22-acp-subagent-backend.md
|
||||
2026-06-22-acp-subagent-backend.md: 211030a6ecc9b6f673174ba410415c7bd80818ef
|
||||
2026-06-22-acp-subagent-backend.zh.md: 2dde3d96329cc47d9c7cca08e1d25764c32f8ebe
|
||||
2026-06-22-acp-subagent-backend.md: 41a60bc8e73cbda1d382226acfbd9c0a4b146fa6
|
||||
2026-06-22-acp-subagent-backend.zh.md: 6aea991c2b4ab783b5f8c43ecb9529df07269d3f
|
||||
|
||||
@@ -18,7 +18,7 @@ Each `start` spawns a new child, runs exactly one ACP session (`initialize` →
|
||||
|
||||
### Minimal client stub
|
||||
|
||||
The client advertises NO optional capabilities (no `fs`, no `terminal`): the child self-serves file/terminal access in its own process. `session/update` notifications are consumed — the backend accumulates `agent_message_chunk` text as the result output and ignores the rest (thoughts, tool-call cards) in this cut, which surfaces only the child's final answer. `session/request_permission` is auto-answered by a configured policy (`reject` declines every prompt, `allow` approves via the first allow-shaped option) — the first cut surfaces no prompt to a human. Proxying `fs`/`terminal` back to the parent (a shared-workspace mode) remains future work, as the seam Agent Note noted.
|
||||
The client advertises NO optional capabilities (no `fs`, no `terminal`): the child self-serves file/terminal access in its own process. `session/update` notifications are consumed — the backend accumulates `agent_message_chunk` text as the result output and ignores the rest (thoughts, tool-call cards), so only the child's final answer surfaces. `session/request_permission` is auto-answered by a configured policy (`reject` declines every prompt, `allow` approves via the first allow-shaped option) — no prompt is surfaced to a human. Proxying `fs`/`terminal` back to the parent (a shared-workspace mode) remains future work, as the seam Agent Note noted.
|
||||
|
||||
### No start-time capabilities
|
||||
|
||||
|
||||
@@ -18,7 +18,7 @@ subagent seam（[seam Agent Note](2026-06-21-subagent-capability-seam.md)）的
|
||||
|
||||
### 最小化客户端桩
|
||||
|
||||
客户端不声明任何可选能力（无 `fs`、无 `terminal`）：子 agent 在自己的进程中自行处理文件/终端访问。`session/update` 通知被消费：后端将 `agent_message_chunk` 文本累积为结果输出，在本阶段忽略其余内容（思考、工具调用卡片），仅暴露子 agent 的最终回答。`session/request_permission` 由配置的策略自动应答（`reject` 拒绝所有提示，`allow` 通过第一个表示允许的选项批准）——本阶段不向人类暴露任何权限提示。将 `fs`/`terminal` 代理回父进程（共享工作区模式）仍为后续工作，如 seam Agent Note 所述。
|
||||
客户端不声明任何可选能力（无 `fs`、无 `terminal`）：子 agent 在自己的进程中自行处理文件/终端访问。`session/update` 通知被消费：后端将 `agent_message_chunk` 文本累积为结果输出，忽略其余内容（思考、工具调用卡片），因此仅暴露子 agent 的最终回答。`session/request_permission` 由配置的策略自动应答（`reject` 拒绝所有提示，`allow` 通过第一个表示允许的选项批准）——不向人类暴露任何权限提示。将 `fs`/`terminal` 代理回父进程（共享工作区模式）仍为后续工作，如 seam Agent Note 所述。
|
||||
|
||||
### 无启动时能力
|
||||
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-05-dynamic-workflows.md
|
||||
2026-07-05-dynamic-workflows.md: 4dc8744f7505aeb84a14dbf5ad0cc8cb5783d234
|
||||
2026-07-05-dynamic-workflows.zh.md: 5d3f5b014ff4532050bb0afd5464f7ec5e91a323
|
||||
2026-07-05-dynamic-workflows.md: 3e491478286eb77b56872fcbbdd5ebb6b62a5545
|
||||
2026-07-05-dynamic-workflows.zh.md: 7888d83f981a96ac5eb31d5ca6f1f8d0b4930ec7
|
||||
|
||||
@@ -52,7 +52,7 @@ An output schema makes a schema-valid committed capture mandatory for successful
|
||||
|
||||
Worker-side logic runs through an in-process `MessageChannel` so V8 coverage measures it. Unit tests cover script helpers, fatal and nullable failures, JSON boundaries, caps, cancellation, child ownership, and structured output through real loops. A built-bin smoke runs the separately bundled `lib/worker.cjs` under plain Node, a with-key e2e drives real child agents, and model-facing workflow behavior is snapshot-covered through its owning example.
|
||||
|
||||
## Deferred (documented non-goals of this cut)
|
||||
## Deferred (documented non-goals)
|
||||
|
||||
- **Background collection** (start tool → run id → completion notice → collect), designed alongside bash/subagent background unification.
|
||||
- **Journaling + resume** (`resumeFromRunId`, cached agent() prefixes) — implementing it reintroduces CC's determinism bans as a script-contract tightening (scripts may read the clock today).
|
||||
|
||||
@@ -52,7 +52,7 @@ harness 可以将一个任务委派给一个子 agent（`dsh-tool-subagent`）
|
||||
|
||||
worker 侧逻辑通过进程内 `MessageChannel` 运行，使 V8 覆盖率能够度量它。单元测试覆盖脚本辅助函数、fatal 与 nullable 失败、JSON 边界、上限、取消、子 agent 所有权和通过真实循环的结构化输出。构建后二进制文件的冒烟测试在纯 Node 下运行单独打包的 `lib/worker.cjs`，带密钥的 e2e 驱动真实子 agent，面向模型的工作流行为通过其所属示例进行快照覆盖。
|
||||
|
||||
## 延迟（本轮明确的非目标）
|
||||
## 延迟（明确的非目标）
|
||||
|
||||
- **后台收集**（启动工具 → run id → 完成通知 → 收集），与 bash/subagent 后台统一一起设计。
|
||||
- **日志化 + 恢复**（`resumeFromRunId`、缓存的 agent() 前缀）：实现它会以脚本约定收紧的形式重新引入 CC 的确定性禁令（脚本目前可以读取时钟）。
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-08-user-explicit-skill-invocation.md
|
||||
2026-08-08-user-explicit-skill-invocation.md: 55001ec2b352bba6f37dd937f64ec8b10853bffb
|
||||
2026-08-08-user-explicit-skill-invocation.zh.md: 5e9eb90502a178c4171899247ebac9bec965c89f
|
||||
2026-08-08-user-explicit-skill-invocation.md: 74d9f01f191005db6d3d283a3c56f5ee664447f8
|
||||
2026-08-08-user-explicit-skill-invocation.zh.md: 0f7c9e1261dda796d988c17ddf7199b74be4133e
|
||||
|
||||
@@ -6,7 +6,7 @@ English | [中文](2026-08-08-user-explicit-skill-invocation.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
A `disable-model-invocation: true` skill is user-only by design: it never enters the model-facing catalog and the `skill` tool refuses to load it. Its only legitimate entry point is an explicit user gesture — yet the web client had none. `skill.list` filtered to the model-and-user intersection (hiding user-only skills from the menu), an entered `/name` line rode into the default prompt sink as plain text, and the model it reached was forbidden to load the skill — so it degraded to `read`-ing the SKILL.md file or ignoring the gesture (issue #1470). Even for ordinary skills, the decision-21 plain-text reference made user invocation a collaboration cue the model could ignore, not a guarantee.
|
||||
A `disable-model-invocation: true` skill is user-only by design: it never enters the model-facing catalog and the `skill` tool refuses to load it. Its only legitimate entry point is an explicit user gesture — yet the web client had none. `skill.list` filtered to the model-and-user intersection (hiding user-only skills from the menu), an entered `/name` line rode into the default prompt sink as plain text, and the model it reached was forbidden to load the skill — so it degraded to `read`-ing the SKILL.md file or ignoring the gesture (issue #1470). Even for ordinary skills, the plain-text reference made user invocation a collaboration cue the model could ignore, not a guarantee.
|
||||
|
||||
## Decision
|
||||
|
||||
@@ -14,7 +14,7 @@ User-explicit invocation is a host-side pre-step injection, uniform for every us
|
||||
|
||||
- `dsh-tool-skill` registers a second `agent/pre-step` listener (beside its catalog listener, the same seam `workspace-instructions` and the runtime-context snapshot ride): it scans the step's claimed messages for whitespace-bounded `/name` tokens — anywhere in the text, the same word-boundary shape the transcript chip decoration uses — collects first-seen-deduplicated names, loads each through `ctx.skills.get`, checks `isUserInvocable` on the loaded definition (the single lookup that produces what is injected), renders it with the shared `renderSkillContent`, and appends the injections after every other injection of the step: background first (workspace rules, runtime policy, catalog), the material the model must act on last, closest to its answer. Registration order pins the placement — the gesture listener registers before the catalog listener, so the waterfall hands it the catalog-bearing list to extend.
|
||||
- Precision is closed-set matching, exactly like slash commands: `/goal` resolves against the command registry, `/name` against the workspace's user-invocable skill directory; a miss stays ordinary prose, so nothing is ever guessed. Only `source.kind === 'user'` messages are scanned — external text cannot forge a gesture. Paths (`/usr/bin`), fractions (`5/8`), and prefixed tokens (`foo/name`) all break the boundary.
|
||||
- The client stays decision 21: a menu pick lands the literal `/name ` and the prompt ships it verbatim; ui-skill implements no adjudication hooks and no reference codec. `skill.list` (now the domain's only RPC) serves every user-invocable skill with `modelInvocable` so menus mark user-only entries. A name shared with a host command resolves to the command — adjudication claims the line client-side before it becomes a prompt.
|
||||
- The client keeps the [plain-text-reference decision](../architecture/2026-07-25-web-input-machine-and-slash-pipeline.md): a menu pick lands the literal `/name ` and the prompt ships it verbatim; ui-skill implements no adjudication hooks and no reference codec. `skill.list` (now the domain's only RPC) serves every user-invocable skill with `modelInvocable` so menus mark user-only entries. A name shared with a host command resolves to the command — adjudication claims the line client-side before it becomes a prompt.
|
||||
- The injection is a `user`-role message carrying the `skill-invocation` source (`{ name, form: 'instructions' }`), so `user/message` logging, the context-injection transcript row (labelled with the skill name), and replay all come free; `renderSkillContent` lives in the `dsh-skill` seam, shared verbatim with the `skill` tool result, and the catalog's closing sentence tells the model to follow an injected block instead of re-loading it.
|
||||
|
||||
Peer-product survey (Pi, OpenCode, Claude Code, Kimi Code, Codex, DeepSeek-Reasonix — local checkouts) was unanimous that user-explicit triggering is programmatic injection with zero model participation; the final shape is closest to Codex's core-side `$name` mention scanning, which likewise frees every front end from implementing recognition.
|
||||
@@ -30,7 +30,7 @@ Peer-product survey (Pi, OpenCode, Claude Code, Kimi Code, Codex, DeepSeek-Reaso
|
||||
|
||||
## Consequences
|
||||
|
||||
- Decision 21's plain-text reference is now the whole client story: the draft carries plain text, chip visuals derive from the lexicon, and the sent text is judged by the host boundary — a hand-typed gesture, a menu pick, and a TUI prompt are indistinguishable and equally deterministic.
|
||||
- The plain-text reference is now the whole client story: the draft carries plain text, chip visuals derive from the lexicon, and the sent text is judged by the host boundary — a hand-typed gesture, a menu pick, and a TUI prompt are indistinguishable and equally deterministic.
|
||||
- Every user-invocable skill invocation costs its full rendered body unconditionally — the price of determinism the peer survey showed everyone pays. Mentioning a known skill name mid-sentence loads it; that is the Codex mention semantic, accepted deliberately.
|
||||
- The `skill-invocation` source rides `user/message`, so Model-visible ⟺ logged holds with no new event type, and replay/UI read metadata rather than text markers.
|
||||
- Accepted residual of dropping the per-injection preamble: the no-reload framing rides only the catalog, and a workspace whose skills are all user-only never publishes a first catalog — an injection can arrive with no framing at all, and the model may redundantly try the `skill` tool once (the replacement catalog's empty arm carries the sentence; the never-published case does not). Publishing a catalog for framing alone was judged worse than that one recoverable error.
|
||||
|
||||
@@ -6,7 +6,7 @@ Status: implemented
|
||||
|
||||
## 问题
|
||||
|
||||
`disable-model-invocation: true` 的 skill（技能）在设计上就是仅限用户的：它绝不进入面向模型的目录，`skill` 工具也拒绝加载它。它唯一正当的入口是一次显式的用户手势——而 web 客户端此前没有这个入口。`skill.list` 过滤到模型与用户的交集（把仅限用户的 skill 挡在菜单之外），回车提交的 `/name` 一行以纯文本落入默认提示词 sink，而这行文本到达的模型又被禁止加载该 skill——于是退化为模型去 `read` 那份 SKILL.md 文件，或者干脆无视这次手势（issue #1470）。即使对普通 skill，决策 21 的纯文本引用也让用户调用只是模型可以忽略的协作线索，而不是保证。
|
||||
`disable-model-invocation: true` 的 skill（技能）在设计上就是仅限用户的：它绝不进入面向模型的目录，`skill` 工具也拒绝加载它。它唯一正当的入口是一次显式的用户手势——而 web 客户端此前没有这个入口。`skill.list` 过滤到模型与用户的交集（把仅限用户的 skill 挡在菜单之外），回车提交的 `/name` 一行以纯文本落入默认提示词 sink，而这行文本到达的模型又被禁止加载该 skill——于是退化为模型去 `read` 那份 SKILL.md 文件，或者干脆无视这次手势（issue #1470）。即使对普通 skill，纯文本引用也让用户调用只是模型可以忽略的协作线索，而不是保证。
|
||||
|
||||
## 决策
|
||||
|
||||
@@ -14,7 +14,7 @@ Status: implemented
|
||||
|
||||
- `dsh-tool-skill` 注册第二个 `agent/pre-step` 监听器（与其目录监听器并列，也是 `workspace-instructions` 与运行时上下文快照搭乘的同一 seam）：它在该步骤已认领的消息中扫描以空白为界的 `/name` token——文本中任意位置均可，与 transcript（文本记录）chip 装饰所用的词边界形状相同——收集按首见去重的名称，逐个经 `ctx.skills.get` 加载，在已加载定义上检查 `isUserInvocable`（产生注入内容的正是这同一次查找），用共享的 `renderSkillContent` 渲染，并把注入追加在该步骤所有其他注入之后：背景在前（工作区规则、运行时策略、目录），模型必须着手处理的材料在最后、最贴近它的回答。注册顺序钉住了这一位置——手势监听器先于目录监听器注册，因此 waterfall（瀑布式事件）会把携带目录的列表交给它来扩展。
|
||||
- 精确性来自封闭集合匹配，与斜杠命令完全一致：`/goal` 对照命令注册表解析，`/name` 对照工作区的用户可调用 skill 目录解析；未命中即保持为普通行文，因此绝不猜测。只扫描 `source.kind === 'user'` 的消息——外部文本无法伪造手势。路径（`/usr/bin`）、分数（`5/8`）与带前缀的 token（`foo/name`）都会破坏该边界。
|
||||
- 客户端停留在决策 21：菜单 pick 落下字面文本 `/name `，该文本随提示词原样提交；ui-skill 不实现任何裁决钩子，也没有引用 codec。`skill.list`（现在是该领域唯一的 RPC）提供每一个用户可调用的 skill 并携带 `modelInvocable`，供菜单标出仅限用户的条目。与宿主命令同名的名称解析为命令——客户端会在该行成为提示词之前完成裁决并将其认领。
|
||||
- 客户端沿用[纯文本引用决策](../architecture/2026-07-25-web-input-machine-and-slash-pipeline.md)：菜单 pick 落下字面文本 `/name `，该文本随提示词原样提交；ui-skill 不实现任何裁决钩子，也没有引用 codec。`skill.list`（现在是该领域唯一的 RPC）提供每一个用户可调用的 skill 并携带 `modelInvocable`，供菜单标出仅限用户的条目。与宿主命令同名的名称解析为命令——客户端会在该行成为提示词之前完成裁决并将其认领。
|
||||
- 注入是一条携带 `skill-invocation` 来源（`{ name, form: 'instructions' }`）的 `user` 角色消息，因此 `user/message` 落账、上下文注入的 transcript 行（以 skill 名称标注）与回放全部免费获得；`renderSkillContent` 位于 `dsh-skill` seam，由注入和 `skill` 工具结果共用，二者内容逐字相同，目录的结尾一句会告诉模型遵循注入块而不是重新加载。
|
||||
|
||||
同类产品调研（Pi、OpenCode、Claude Code、Kimi Code、Codex、DeepSeek-Reasonix——本地检出）一致表明：用户显式触发都是模型零参与的程序化注入；最终形态最接近 Codex 核心侧的 `$name` mention 扫描——它同样让每一种前端免于自行实现识别。
|
||||
@@ -30,7 +30,7 @@ Status: implemented
|
||||
|
||||
## 后果
|
||||
|
||||
- 决策 21 的纯文本引用如今就是客户端的全部故事：草稿承载纯文本，chip 视觉由 lexicon 派生，发出的文本由宿主边界评判——手动键入的手势、菜单 pick 与 TUI 提示词无从区分，也同样具有确定性。
|
||||
- 纯文本引用如今就是客户端的全部故事：草稿承载纯文本，chip 视觉由 lexicon 派生，发出的文本由宿主边界评判——手动键入的手势、菜单 pick 与 TUI 提示词无从区分，也同样具有确定性。
|
||||
- 每一次用户可调用 skill 的调用都无条件付出其完整渲染正文的成本——这是确定性的代价，同类调研表明所有产品都在支付。在句子中间提到一个已知 skill 名称也会加载它；这就是 Codex 的 mention 语义，属于有意接受。
|
||||
- `skill-invocation` 来源搭乘 `user/message`，因此「模型可见 ⟺ 已记录」在不新增事件类型的情况下继续成立，回放与 UI 读取的是元数据而非文本标记。
|
||||
- 放弃逐次注入前导语后被接受的残余：no-reload framing 只搭乘目录，而 skill 全部为仅用户的工作区永远不会发布首个目录——注入可能在完全没有 framing 的情况下到达，模型可能多余地调用一次 `skill` 工具（替换目录的空分支携带该句；从未发布的情形没有）。仅为 framing 而发布目录被判定比这一次可恢复的错误更糟。
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-08-09-committed-artifact-citations.md
|
||||
2026-08-09-committed-artifact-citations.md: a34a779977a05b66b1587049ef4a38f0c1cfa0cb
|
||||
2026-08-09-committed-artifact-citations.zh.md: 6eb1810dddfcb38095270d4cdcb00eccef167183
|
||||
2026-08-09-committed-artifact-citations.md: 7d99a27238f25e7084fbbc816787c3c76a62bd89
|
||||
2026-08-09-committed-artifact-citations.zh.md: f09ae024c480d95dc95e39c62fbd1dc31f5b92a1
|
||||
|
||||
@@ -12,8 +12,8 @@ Large design and review sessions leave working shorthand — decision ordinals,
|
||||
|
||||
Durable prose — comments, JSDoc, docs, notes, test comments and titles — cites only committed artifacts, resolvable in-repo without grep archaeology:
|
||||
|
||||
- Name the owning Agent Note (its path at least once per file, a searchable name inline), the doc page path, or a GitHub issue number. PR, commit, branch, and stack positions stay banned per the documentation standard; issues are durable and citable.
|
||||
- A design-session ordinal with a committed owner is replaced by the owner's name — decision 21 lives in the [web input-machine note](../architecture/2026-07-25-web-input-machine-and-slash-pipeline.md) as the plain-text-reference decision. An ordinal without an owner is deleted and its factual clause restated to stand alone.
|
||||
- Name the owning Agent Note (its path at least once per file, a searchable name inline), the doc page path, or a GitHub issue number. PR, commit, branch, and stack positions stay banned in docs and code per the documentation standard; issues are durable and citable, and Agent Notes may cite merged PRs as evidence anchors — the standard routes change stories to commits, PRs, Agent Notes, and postmortems, and a note is that home.
|
||||
- A design-session ordinal whose decision has a committed owner is replaced by the decision's name — the ordinal once logged as "decision 21" is now "the plain-text-reference decision", owned by the [web input-machine note](../architecture/2026-07-25-web-input-machine-and-slash-pipeline.md); the ordinal itself resolves nowhere in-repo and was dropped everywhere. An ordinal without an owner is deleted and its factual clause restated to stand alone.
|
||||
- Fixed regressions are pinned as present-tense counterfactuals ("without X, Y happens"; "a naive X would…"), never as repo history ("used to Y").
|
||||
- Implemented notes state shipped reality: a "deferred to a later PR" claim whose target shipped names the shipped note instead.
|
||||
- Recorded fixtures, snapshots, and archived notes are exempt: recorded model output and sealed history keep their original voice.
|
||||
@@ -23,7 +23,7 @@ One repo-wide purge applied these rules across the prose surfaces, including the
|
||||
## Alternatives considered
|
||||
|
||||
- **Commit the design ledgers and audit documents so the ordinals resolve.** Rejected: session transcripts are working artifacts, not maintained references; committing them would create a parallel, ungated decision corpus beside Agent Notes, and their internal numbering would still drift.
|
||||
- **A mechanical gate for the banned vocabulary.** Deferred: the vocabulary is unbounded natural language, and the audit's recall batteries need judgment to separate leakage from legitimate prose ("wait" the noun, contrastive "actually", runtime old/new states). A narrow high-precision gate (for example `\(decision \d` and `\(audit [A-Z]\d`) is the candidate if the pattern recurs.
|
||||
- **A mechanical gate for the banned vocabulary.** Deferred: the vocabulary is unbounded natural language, and the audit's recall batteries need judgment to separate leakage from legitimate prose ("wait" the noun, contrastive "actually", runtime old/new states). A narrow high-precision gate (for example `\(decision \d`, `\(audit [A-Z]\d`, `\bcut \d`, `this cut`, a bare `\bT\d\b`, and `P-I`) is the candidate if the pattern recurs; review of the purge itself caught residuals in exactly those last four shapes, so they lead the candidate list.
|
||||
- **Delete the rationale that cited dead artifacts.** Rejected: the factual clauses were preserved or restated; only citations, review choreography, and derivation transcripts were removed, per the prose standard's complete-proposition rule.
|
||||
|
||||
## Verification
|
||||
|
||||
@@ -12,8 +12,8 @@ Status: implemented
|
||||
|
||||
持久行文（注释、JSDoc、文档、Agent Note、测试注释与测试标题）只引用已提交的产物，无需 grep 考古即可在仓库内解析：
|
||||
|
||||
- 点名归属的 Agent Note（其路径在每个文件里至少出现一次，行内用可检索的名称）、文档页面路径，或 GitHub issue 编号。PR、commit、分支与栈位置依文档标准仍在禁止之列；issue 是持久且可引用的。
|
||||
- 有已提交归属文档的设计会话序号替换为该归属文档的名称：决策 21 即 [web 输入状态机 note](../architecture/2026-07-25-web-input-machine-and-slash-pipeline.md) 中的纯文本引用决策。没有归属文档的序号予以删除，其事实性语句改写为可独立成立的表述。
|
||||
- 点名归属的 Agent Note（其路径在每个文件里至少出现一次，行内用可检索的名称）、文档页面路径，或 GitHub issue 编号。PR、commit、分支与栈位置依文档标准在文档与代码中仍在禁止之列；issue 是持久且可引用的，Agent Note 还可引用已合并的 PR 作为证据锚点——文档标准将变更故事归置于 commit、PR、Agent Note 与事后分析，note 正是这一归宿。
|
||||
- 决策有已提交归属文档的设计会话序号替换为该决策的名称——曾以「决策 21」记录的序号如今是「纯文本引用决策」，归属于 [web 输入状态机 note](../architecture/2026-07-25-web-input-machine-and-slash-pipeline.md)；该序号本身在仓库内无从解析，已全部移除。没有归属文档的序号予以删除，其事实性语句改写为可独立成立的表述。
|
||||
- 已修复的回归以现在时反事实句固定下来（「没有 X 就会发生 Y」、「朴素的 X 会……」），绝不写成仓库历史（「过去曾 Y」）。
|
||||
- 已实现的 Agent Note 陈述已交付的现实：「推迟到后续 PR」的说法若其目标已经交付，就改为点名那篇已交付的 note。
|
||||
- 已录制的 fixture（测试前置数据）、快照与已归档的 Agent Note 不受此约束：已录制的模型输出与封存的历史保持原有行文。
|
||||
@@ -23,7 +23,7 @@ Status: implemented
|
||||
## 曾考虑的替代方案
|
||||
|
||||
- **把设计台账与审计文档提交入库，让序号得以解析。**不予采纳：会话 transcript 是工作产物，不是持续维护的参考资料；提交它们会在 Agent Note 之外形成一套平行且不受门禁约束的决策语料，其内部编号也仍会漂移。
|
||||
- **为被禁词汇建一道机械门禁。**暂缓：这类词汇是无界的自然语言，审计中以查全为目标的成批检索需要人工判断，才能把泄漏与正当行文区分开（作名词的「wait」、表转折的「actually」、运行时的新旧状态）。若该模式再次出现，候选方案是一道窄而高查准的门禁（例如 `\(decision \d` 与 `\(audit [A-Z]\d`）。
|
||||
- **为被禁词汇建一道机械门禁。**暂缓：这类词汇是无界的自然语言，审计中以查全为目标的成批检索需要人工判断，才能把泄漏与正当行文区分开（作名词的「wait」、表转折的「actually」、运行时的新旧状态）。若该模式再次出现，候选方案是一道窄而高查准的门禁（例如 `\(decision \d`、`\(audit [A-Z]\d`、`\bcut \d`、`this cut`、裸 `\bT\d\b` 与 `P-I`）；对本次清扫自身的评审恰好在后四种形态中发现残留，因此它们位居候选清单之首。
|
||||
- **删除引用了失效产物的设计理由。**不予采纳：事实性语句都得到保留或改写；依行文标准的完整命题规则，删掉的只有引用、评审编排与推导过程记录。
|
||||
|
||||
## 验证
|
||||
|
||||
Reference in New Issue
Block a user