refactor(skill): scope provider invalidation

.agents/notes/implemented/feature/2026-07-27-skill-catalog-hot-refresh.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-27-skill-catalog-hot-refresh.md
-2026-07-27-skill-catalog-hot-refresh.md: 61f6690cb00546664e36d3916c98caf2dcc1b79f
-2026-07-27-skill-catalog-hot-refresh.zh.md: f174d27f88c861cd3d951c1379f7ebaf72888f27
+2026-07-27-skill-catalog-hot-refresh.md: 8a53195dd8c4880c5cfa758ccf666ae88b2e1030
+2026-07-27-skill-catalog-hot-refresh.zh.md: 8cf55534460d2926be706353afd2019fad1bb45d

.agents/notes/implemented/feature/2026-07-27-skill-catalog-hot-refresh.md

@@ -12,7 +12,7 @@ Filesystem updates are also non-atomic from the observer's perspective. An edito
 
 ## Decision
 
-The skill capability separates catalog membership from instruction-body loading. `ctx.skills.snapshot()` returns summaries plus a completeness bit, while `ctx.skills.invalidateProvider(provider)` dirties only the exact registered provider and discards completed catalog caches. A provider or runtime generation change during discovery retries before returning. Incomplete observations are not cached. A stale provider callback after disposal or replacement is a no-op because invalidation uses object identity.
+The skill capability separates catalog membership from instruction-body loading. `ctx.skills.snapshot()` returns summaries plus a completeness bit. `ctx.skills.registerProvider(factory)` gives the synchronous factory one registration-scoped `{ signal, invalidate }` control: `invalidate()` dirties only that exact active registration and discards completed catalog caches, while the signal aborts when registration fails or is disposed. A provider or runtime generation change during discovery retries before returning. Incomplete observations are not cached. A late invalidation after disposal or replacement is a no-op because the capability has been revoked.
 
 `@deepseek-ai/dsh-skill-local` directly depends on Chokidar and observes catalog-relevant host paths. Existing roots watch direct skill bundle directories, flat Markdown entries, and direct `SKILL.md` entry files. Additions, removals, and directory changes invalidate membership; file changes support frontmatter `name` and `description` refresh. Resource files below a bundle are ignored. Events in one microtask batch coalesce to one invalidation. Project watchers use a bounded least-recently-observed set.
 
@@ -26,7 +26,7 @@ Instruction bodies keep progressive disclosure. Every `skill(name)` call asks th
 
 ## Verification
 
-Registry tests pin exact invalidation, contained observer failures, incomplete snapshots, generation retries, and stale-name rejection. Local-provider tests cover bundle and flat-file creation, removal, rename, root creation/deletion/recreation, description changes, body-only edits, first-party observation, symlinks, polling options, watcher failures, event coalescing, bounded projects, teardown, and transient reads. Tool tests pin full replacement messages, empty tombstones, digest stability for body-only edits, incomplete-state retention, visibility, and resume metadata. TUI tests pin last-complete retention, authoritative empty removal, latest-wins refresh, teardown, and the already-open slash-draft race; a real Loader/PTY smoke adds a local skill after startup and observes its completion without restarting. A keyless assembled agent-spine snapshot creates a project skill through model-facing filesystem tools, observes its replacement catalog on the next request, and loads its current body with the real `skill` tool.
+Registry tests pin registration-scoped invalidation, revocation, signal abort, contained observer failures, incomplete snapshots, generation retries, and stale-name rejection. Local-provider tests cover bundle and flat-file creation, removal, rename, root creation/deletion/recreation, description changes, body-only edits, first-party observation, symlinks, polling options, watcher failures, event coalescing, bounded projects, teardown, and transient reads. Tool tests pin full replacement messages, empty tombstones, digest stability for body-only edits, incomplete-state retention, visibility, and resume metadata. TUI tests pin last-complete retention, authoritative empty removal, latest-wins refresh, teardown, and the already-open slash-draft race; a real Loader/PTY smoke adds a local skill after startup and observes its completion without restarting. A keyless assembled agent-spine snapshot creates a project skill through model-facing filesystem tools, observes its replacement catalog on the next request, and loads its current body with the real `skill` tool.
 
 ## Alternatives considered
 
@@ -35,6 +35,8 @@ Registry tests pin exact invalidation, contained observer failures, incomplete s
 - **Hash or version every `SKILL.md` body** — rejected because the model initially sees only names and descriptions, and the provider already rereads the body on each tool call. Body revisions would create catalog traffic without changing routing and would not justify rewriting historical tool results.
 - **Watch every bundle resource** — rejected because references, scripts, and assets are loaded on demand and do not affect the category list. Broad recursive watching would add invalidations, descriptor pressure, and platform variability without improving routing.
 - **Publish partial or failed discovery as the new catalog** — rejected because a transient read failure is not evidence of deletion. The completeness bit lets the model-facing consumer preserve its last-good catalog until a full observation succeeds.
+- **Keep `invalidateProvider(provider)` public** — rejected because it exposes a registry mutation method and makes callers resupply an identity the registry already owns. The factory-issued closure binds invalidation to one registration and becomes inert on disposal, so observers need neither registry access nor provider identity.
+- **Extract a generic Cordis file-watching service now** — deferred until another consumer establishes the reusable service contract. The local provider marks its Chokidar and missing-root observation boundary for that extraction; skill-path filtering and the call to the provider's invalidation closure remain skill-specific.
 
 ## Consequences
 
@@ -43,4 +45,4 @@ Registry tests pin exact invalidation, contained observer failures, incomplete s
 - Catalog messages are append-only, logged, whole-list snapshots. They preserve earlier reusable tokens; replacements retire stale names explicitly, at token cost proportional to the current catalog on each actual digest change.
 - Body-only edits produce no catalog message. A subsequent tool call sees current content, while prior tool results remain an accurate record of what the model previously loaded.
 - Missing-root polling and Chokidar add one maintained runtime dependency, host watcher resources, bounded detection latency, and deployment tunables. The bounded project set and teardown contract contain those costs.
-- Remote or future mutable providers remain responsible for calling `invalidateProvider()` from their own observation mechanism; the registry does not impose a universal watcher or TTL.
+- Remote or future mutable providers retain their own registration-scoped invalidation closure and call it from their observation mechanism; the registry does not impose a universal watcher or TTL.

.agents/notes/implemented/feature/2026-07-27-skill-catalog-hot-refresh.zh.md

@@ -12,7 +12,7 @@ skill（技能）摘要是模型的路由输入，但本地 skill 可在会话
 
 ## 决策
 
-skill 服务将目录成员关系与指令正文加载分离。`ctx.skills.snapshot()` 返回摘要及一个完整性位；`ctx.skills.invalidateProvider(provider)` 只会将精确的已注册提供方标记为脏，并丢弃已经完成的目录缓存。在发现期间，如果提供方或运行时 generation 发生变化，系统会先重试再返回。不完整的观察结果不会缓存。提供方在资源释放或被替换后到达的陈旧回调不会执行任何操作，因为失效操作使用对象身份。
+skill 服务将目录成员关系与指令正文加载分离。`ctx.skills.snapshot()` 返回摘要及一个完整性位。`ctx.skills.registerProvider(factory)` 会向同步工厂提供一项注册作用域内的 `{ signal, invalidate }` 控制能力：`invalidate()` 只会将该精确活动注册标记为脏，并丢弃已完成目录缓存；注册失败或释放时，信号会中止。在发现期间，如果提供方或运行时 generation 发生变化，系统会先重试再返回。不完整的观察结果不会缓存。资源释放或替换后的延迟失效操作不会执行任何操作，因为该能力已被撤销。
 
 `@deepseek-ai/dsh-skill-local` 直接依赖 Chokidar，并观察与目录相关的宿主路径。已有根目录会监视其直属 skill bundle 目录、平铺的 Markdown 条目和直属 `SKILL.md` 条目文件。新增、移除和目录变更会使成员关系失效；文件变更还支持刷新 frontmatter 中的 `name` 和 `description`。bundle 内更深层的资源文件会被忽略。同一微任务批次中的事件会合并为一次失效。项目 watcher 使用有界集合，并按最久未观察顺序淘汰。
 
@@ -26,7 +26,7 @@ TUI 将同一失效通知作为界面状态而非会话历史来消费。`skills
 
 ## 验证
 
-注册表测试固定了精确失效、监听器失败隔离、不完整快照、generation 重试和陈旧名称拒绝。local-provider 测试覆盖 bundle 与平铺文件的创建、移除和重命名，以及根目录创建／删除／重建、描述变更、仅正文编辑、第一方观察、符号链接、轮询选项、watcher 失败、事件合并、项目 watcher 容量上限、资源销毁和暂时读取。工具测试固定了完整替换消息、空 tombstone、仅修改正文时 digest 稳定、不完整状态保留、可见性和恢复元数据。TUI 测试固定了上一份完整结果保留、权威空结果清除、刷新时以最新结果为准、资源销毁和已打开斜杠草稿的竞态；一项使用真实 Loader/PTY 的 smoke 测试会在启动后添加本地 skill，并观察其补全项出现，而无需重启。一个无密钥、装配完成的 agent-spine 快照测试通过面向模型的文件系统工具创建项目 skill，观察下一次请求中的替换目录，并使用真实 `skill` 工具加载当前正文。
+注册表测试固定了注册作用域内的失效、能力撤销、信号中止、监听器失败隔离、不完整快照、generation 重试和陈旧名称拒绝。local-provider 测试覆盖 bundle 与平铺文件的创建、移除和重命名，以及根目录创建／删除／重建、描述变更、仅正文编辑、第一方观察、符号链接、轮询选项、watcher 失败、事件合并、项目 watcher 容量上限、资源销毁和暂时读取。工具测试固定了完整替换消息、空 tombstone、仅修改正文时 digest 稳定、不完整状态保留、可见性和恢复元数据。TUI 测试固定了上一份完整结果保留、权威空结果清除、刷新时以最新结果为准、资源销毁和已打开斜杠草稿的竞态；一项使用真实 Loader/PTY 的 smoke 测试会在启动后添加本地 skill，并观察其补全项出现，而无需重启。一个无密钥、装配完成的 agent-spine 快照测试通过面向模型的文件系统工具创建项目 skill，观察下一次请求中的替换目录，并使用真实 `skill` 工具加载当前正文。
 
 ## 考虑过的替代方案
 
@@ -35,6 +35,8 @@ TUI 将同一失效通知作为界面状态而非会话历史来消费。`skills
 - **为每个 `SKILL.md` 正文计算哈希或版本**：不予采纳，因为模型最初只看到名称和描述，提供方已经在每次工具调用时重新读取正文。正文修订会产生目录流量，却不会改变路由，也不足以成为改写历史工具结果的理由。
 - **监视每个 bundle 资源**：不予采纳，因为参考资料、脚本和产物都是按需加载的，不影响类别列表。宽泛的递归监视会增加失效、描述符压力和平台差异，却不能改善路由。
 - **将部分发现或失败发现发布为新目录**：不予采纳，因为暂时读取失败不能证明文件已删除。完整性位让面向模型的消费方保留最后一次完整目录，直到完整观察成功。
+- **保留公开的 `invalidateProvider(provider)`**：不予采纳，因为这会公开一项注册表变更方法，并要求调用方重复提供注册表已经持有的身份。发给工厂的闭包会将失效绑定到单个注册，并在释放后失去作用，因此观察方既不需要访问注册表，也不需要提供方身份。
+- **现在提取通用 Cordis 文件监视服务**：暂缓，直到另一个消费方确立可复用的服务契约。本地提供方标出了其 Chokidar 和缺失根目录观测边界，以便后续提取；skill 路径过滤以及对提供方失效闭包的调用仍属于 skill 专用逻辑。
 
 ## 影响
 
@@ -43,4 +45,4 @@ TUI 将同一失效通知作为界面状态而非会话历史来消费。`skills
 - 目录消息采用仅追加、日志记录和全量列表快照。它们会保留较早的可重用 token；替换目录会显式停用陈旧名称，每次 digest 实际变化时，token 成本与当前目录大小成正比。
 - 仅修改正文不会产生目录消息。后续工具调用会看到当前内容，而先前工具结果仍准确记录模型之前加载的内容。
 - 缺失根目录轮询和 Chokidar 引入一个有人维护的运行时依赖、宿主 watcher 资源、有界检测延迟和部署可调参数。有界项目集合与资源销毁契约会限制这些成本。
-- 远程或未来的可变提供方仍有责任通过自身观察机制调用 `invalidateProvider()`；注册表不会强制采用通用 watcher 或 TTL。
+- 远程或未来的可变提供方会保留各自注册作用域内的失效闭包，并通过自身观察机制调用它；注册表不会强制采用通用 watcher 或 TTL。