docs(notes): archive low-value decision records

.agents/notes/archived/simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+2026-06-20-drop-unconsumed-llm-adapter-change-event.md: ad05be999158a225230b4a1d760983b71075aada
+2026-06-20-drop-unconsumed-llm-adapter-change-event.zh.md: 0efc0193b3d63b7df6e1671afed0d1faebeaa2af

.agents/notes/archived/simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.md

@@ -0,0 +1,37 @@
+# Agent Note: Drop the unconsumed `llm/adapter-change` event
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-06-20-drop-unconsumed-llm-adapter-change-event.zh.md)
+
+## Problem
+
+`LlmService.registerAdapter()` emits `llm/adapter-change` on registration and disposal ([packages/llm/llm/src/index.ts](../../../../packages/llm/llm/src/index.ts)). Grepping `llm/adapter-change` across `packages/*/src` and `examples/*/src` finds only the declaration, emit sites, docs, and tests; no production listener subscribes to it.
+
+This differs from `tools/change` and `system-prompt/change`. Those two events are also unconsumed today, but they are plausible registry-change signals for future live tool/prompt UIs. LLM adapter registration is more of a boot-time implementation detail: adapters are not a user-visible palette and the real model-call interception seam is `llm/stream`. Keeping an adapter-change event with no listener repeats the [drop-the-dead-summary](2026-06-19-drop-mutable-session-summary.md) pattern at a smaller scale.
+
+The event is not free. `registerAdapter()` yields its rollback disposer before emitting `llm/adapter-change` so a throwing listener unwinds the mutation instead of leaking an adapter entry, and the package carries tests for that listener-throw path. That defensive ordering protects a failure mode only tests can trigger.
+
+## Decision
+
+Only `llm/adapter-change` is removed: the declaration in `dsh-llm`'s `interface Events`, the `ctx.emit('llm/adapter-change')` calls, and the "Emits `llm/adapter-change` on registration and disposal" sentence in `LlmService.registerAdapter`'s JSDoc. `registerAdapter()`'s effect generator keeps the mutation and rollback disposer for HMR/disposal but sheds the listener-throw rollback ordering that existed only for the removed event. The adapter-disposer test asserts the returned disposer removes the adapter without subscribing to the event; the listener-throw rollback test is gone with its subject. The event taxonomy in [docs/architecture.md](../../../../docs/architecture.md) and [packages/llm/llm/README.md](../../../../packages/llm/llm/README.md) is updated in the same change.
+
+## Alternatives considered
+
+### Why not remove every registry change event?
+
+A microkernel where registries announce mutations is a coherent convention. `tools/change` and `system-prompt/change` may become useful when a UI can live-refresh available tools or prompt sections. This Agent Note leaves that convention intact where it has a plausible user-facing consumer and cuts only the adapter-change event whose current and likely future consumer is unclear.
+
+If an LLM adapter browser or dynamic model-picker needs this signal later, reintroduce it with that consumer and a clearer payload than "something changed."
+
+## Verification
+
+`llm/adapter-change` and its emits are gone and the regenerated cordis catalog is fresh; HMR-safety holds (disposing a contributing fiber removes the adapter); `tools/change` and `system-prompt/change` remain documented and tested; and the ACP snapshots plus the keyless Headless Loader smoke pin the unchanged production paths.
+
+## Consequences
+
+- **Removing a documented emit event is a public-surface change.** It is in the taxonomy table, so it reads as deliberate API. But "declared and emitted" is not "consumed" — the same distinction that justified dropping the mutable summary. The taxonomy table is updated in the same change, so the docs do not drift.
+- **The registry-change convention becomes uneven.** That is acceptable because LLM adapter registration is not the same user-facing concept as tools or prompt sections. Uneven but honest beats uniform but dead.
+
+This is a small cut, but it retires a standing correctness invariant that guards a consumer that does not exist.

.agents/notes/archived/simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.zh.md

@@ -0,0 +1,37 @@
+# Agent Note: 移除未被消费的 `llm/adapter-change` 事件
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-06-20-drop-unconsumed-llm-adapter-change-event.md) | 中文
+
+## 问题
+
+`LlmService.registerAdapter()` 在注册和 dispose（资源释放）时发出 `llm/adapter-change` 事件（[packages/llm/llm/src/index.ts](../../../../packages/llm/llm/src/index.ts)）。在 `packages/*/src` 和 `examples/*/src` 中搜索 `llm/adapter-change`，只能找到声明、emit 站点、文档和测试；没有任何生产环境的监听器订阅它。
+
+这与 `tools/change` 和 `system-prompt/change` 不同。如今这两个事件同样没有消费方，但它们有望成为未来实时工具/提示词 UI 的注册表变更信号。LLM（大语言模型）适配器注册更像是启动时的实现细节：适配器不是用户可见的选项面板，真正的模型调用拦截 seam 是 `llm/stream`。保留一个没有监听器的适配器变更事件，只是在更小范围内重复[删除无用 summary](2026-06-19-drop-mutable-session-summary.md) 的模式。
+
+这个事件并非零成本。`registerAdapter()` 在发出 `llm/adapter-change` 之前先 yield 回滚 disposer，这样抛出异常的监听器会回退变更而非泄漏适配器条目；包内还有针对该监听器抛出路径的测试。这种防御性排序保护的是一个只有测试才能触发的失败模式。
+
+## 决策
+
+只移除 `llm/adapter-change`：包括 `dsh-llm` 的 `interface Events` 中的声明、`ctx.emit('llm/adapter-change')` 调用，以及 `LlmService.registerAdapter` JSDoc 中“在注册和释放时发出 `llm/adapter-change`”的句子。`registerAdapter()` 的效应生成器为 HMR（热模块替换）/释放保留变更与回滚 disposer，但移除仅因该事件而存在的监听器抛错回滚顺序。适配器 disposer 测试断言返回的 disposer 会移除适配器，不再订阅事件；监听器抛错回滚测试则随其测试对象一起消失。[docs/architecture.md](../../../../docs/architecture.md) 和 [packages/llm/llm/README.md](../../../../packages/llm/llm/README.md) 中的事件分类也在同一变更中更新。
+
+## 曾考虑的替代方案
+
+### 为什么不移除所有注册表变更事件？
+
+由注册表通告变更的微内核是一种一致的约定。当 UI 能够实时刷新可用工具或提示词章节时，`tools/change` 和 `system-prompt/change` 可能会有用。本 Agent Note（agent 决策记录）在存在合理用户侧消费方的位置保留该约定，只删除当前及可能的未来消费方都不明确的适配器变更事件。
+
+如果将来需要 LLM 适配器浏览器或动态模型选择器用到此信号，届时再连同消费方一起重新引入，并提供比「something changed」更清晰的 payload。
+
+## 验证
+
+`llm/adapter-change` 及其 emit 已消失，重新生成的 Cordis 目录保持新鲜；HMR 安全性仍成立（释放贡献该适配器的 fiber 会移除它）；`tools/change` 和 `system-prompt/change` 仍有文档与测试；ACP（Agent Client Protocol）快照和无密钥 Headless Loader 冒烟则固定了未变的生产路径。
+
+## 后果
+
+- **移除一个已文档化的 emit 事件属于公开接口变更。** 它出现在分类体系表中，读起来像有意设计的 API。但「已声明且已发出」不等于「已被消费」——这与移除可变 summary 时的判断依据相同。分类体系表在同一个变更中更新，因此文档不会漂移。
+- **注册表变更约定变得不均匀。** 这是可接受的，因为 LLM 适配器注册与工具或提示词段落不是同一层面的面向用户概念。不均匀但诚实，胜过统一但无用。
+
+这是一个小裁剪，但它退役了一条守护着并不存在的消费方的正确性不变式。

.agents/notes/archived/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+2026-06-20-drop-unconsumed-llm-assembled-surfaces.md: fd3d48e0918f8395b6c94e407b889ec3a6de7fbe
+2026-06-20-drop-unconsumed-llm-assembled-surfaces.zh.md: 83d631329ccddb0f8880f223884ae4dc75a14d09

.agents/notes/archived/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.md

@@ -0,0 +1,40 @@
+# Agent Note: Drop unconsumed assembled LLM convenience surfaces
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-06-20-drop-unconsumed-llm-assembled-surfaces.zh.md)
+
+## Problem
+
+`LlmService` ([packages/llm/llm/src/index.ts](../../../../packages/llm/llm/src/index.ts)) exposes three call surfaces over a model:
+
+- `stream()` — raw `StreamChunk`s, dispatched through the `llm/stream` waterfall.
+- `streamBlocks()` — a "convenience view" that runs the chunks through a `BlockAssembler` and yields completed `ContentBlock`s in stream order ([index.ts:137-144](../../../../packages/llm/llm/src/index.ts)).
+- `generate()` — one fully-assembled `GenerateResult`, dispatched through a second `llm/generate` waterfall ([index.ts:151-157](../../../../packages/llm/llm/src/index.ts)).
+
+The only production consumer of the LLM service is the agent loop, and it uses `stream()` exclusively — feeding raw chunks through its own `BlockAssembler` so it can log chunks for replay fidelity while assembling in parallel ([packages/core/agent-loop/src/loop.ts](../../../../packages/core/agent-loop/src/loop.ts), the `ctx.llm.stream(req)` step). Grepping `streamBlocks` and `ctx.llm.generate` across `packages/*/src` and `examples/*/src` finds no production callers. The references are the service methods, docs, and tests; adapter tests use `generate()` as a convenient driver, but they can hand-drain `stream()` through the same assembler helper without preserving a public production API.
+
+This is the [drop-mutable-session-summary](2026-06-19-drop-mutable-session-summary.md) pattern: assembled-view APIs with tested contracts, consumed by tests rather than production. They were built speculatively for consumers that do not care about token-level deltas, but the one real consumer cares about deltas precisely so it can persist high-fidelity replay data.
+
+`streamBlocks()` drags a dedicated slice of `BlockAssembler` behind it: `flushReady()` and `flushRemaining()` ([packages/llm/llm/src/assembler.ts:138-168](../../../../packages/llm/llm/src/assembler.ts)) plus the `flushed` cursor field exist only to support incremental in-order yield. `generate()` drags `GenerateResult`, `BlockAssembler.result()`, and the `llm/generate` waterfall as a second interception surface over the same underlying stream. The loop's assembler usage is `push()` / `message()` / `usage` / `finish` — not streaming flush or one-shot service assembly.
+
+## Decision
+
+`stream()` is the sole public LLM call surface. Remove `streamBlocks`, `generate`, its event/result types, and assembler helpers used only by that path. Adapter tests assemble the public stream through a local helper, while `BlockAssembler` retains only the operations with production consumers.
+
+## Alternatives considered
+
+**Keep `generate()` as a test-only convenience** — rejected: adapter tests hand-draining `stream()` through the shared assembler exercise the same streaming path production uses, and a public method whose only callers are tests is exactly the dead-surface shape [the drop-mutable-summary precedent](2026-06-19-drop-mutable-session-summary.md) retired. A future consumer that wants assembled blocks without deltas reintroduces a focused helper with that consumer.
+
+## Verification
+
+`streamBlocks`, `generate`, `llm/generate`, and the assembler helpers they alone required are gone with no new dead exports; both real adapters are exercised through `stream()` and the shared assembler; the loop behaves identically (ACP snapshot expected outputs unchanged); and the README, architecture doc, and module docs carry no mention of the removed surfaces.
+
+## Consequences
+
+- **It removes public methods from a core vocabulary package.** A future plugin that wants assembled blocks without deltas would need to call `stream()` and use `BlockAssembler` directly or reintroduce a focused helper with a real consumer. Given the pre-release "foundation over speculative future" stance ([AGENTS.md](../../../../AGENTS.md)), this is the right time to cut test-only public shape.
+- **Adapter tests get a little more explicit.** They lose the ergonomic `generate()` wrapper, but that is useful pressure: tests exercise the same streaming path production uses.
+- **Waterfall users lose `llm/generate`.** No production listener exists. Any future caching/retry/logging plugin should wrap `llm/stream`, which remains the single provider call path.
+
+The size is modest, but it is a clean removal of speculative surface area from the LLM package, leaving one model-call contract for both production and tests.

.agents/notes/archived/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.zh.md

@@ -0,0 +1,40 @@
+# Agent Note: 移除未被消费的 LLM 组装便捷接口
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-06-20-drop-unconsumed-llm-assembled-surfaces.md) | 中文
+
+## 问题
+
+`LlmService`（[packages/llm/llm/src/index.ts](../../../../packages/llm/llm/src/index.ts)）在模型之上暴露了三个调用接口：
+
+- `stream()`：原始 `StreamChunk`，通过 `llm/stream` waterfall（瀑布式事件）分发。
+- `streamBlocks()`：一个「便捷视图」，将分片送入 `BlockAssembler` 并按流顺序产出已组装的 `ContentBlock`（[index.ts:137-144](../../../../packages/llm/llm/src/index.ts)）。
+- `generate()`：一个完整组装的 `GenerateResult`，通过第二条 `llm/generate` waterfall 分发（[index.ts:151-157](../../../../packages/llm/llm/src/index.ts)）。
+
+LLM（大语言模型）服务唯一的生产消费方是 agent loop（智能体循环），它只使用 `stream()`：将原始分片送入自己的 `BlockAssembler`，以便在并行组装的同时记录分片，保证回放保真度（[packages/core/agent-loop/src/loop.ts](../../../../packages/core/agent-loop/src/loop.ts)，`ctx.llm.stream(req)` 步骤）。在 `packages/*/src` 和 `examples/*/src` 中 grep `streamBlocks` 与 `ctx.llm.generate`，找不到任何生产调用方。仅有的引用来自服务方法定义、文档和测试；适配器测试用 `generate()` 作为便捷驱动，但它们完全可以通过同一个 assembler 辅助函数手动消费 `stream()`，无需为此保留一个公开的生产 API。
+
+这属于[删除可变会话 summary](2026-06-19-drop-mutable-session-summary.md) 的同类模式：带有受测契约的组装视图 API，由测试而非生产代码消费。它们是为不关心 token 级增量的消费方推测性构建的，但唯一的真实消费方恰恰关心增量，以便持久化高保真重放数据。
+
+`streamBlocks()` 拖带了 `BlockAssembler` 的一块专用逻辑：`flushReady()` 与 `flushRemaining()`（[packages/llm/llm/src/assembler.ts:138-168](../../../../packages/llm/llm/src/assembler.ts)）以及 `flushed` 游标字段，仅为支持按序增量产出而存在。`generate()` 拖带了 `GenerateResult`、`BlockAssembler.result()` 以及 `llm/generate` waterfall——在同一底层流之上的第二个拦截面。agent loop 对 assembler 的使用仅限于 `push()` / `message()` / `usage` / `finish`，不涉及流式 flush 或一次性服务组装。
+
+## 决策
+
+`stream()` 是唯一的公开 LLM 调用接口。移除 `streamBlocks`、`generate`、其事件/结果类型，以及仅被该路径使用的 assembler 辅助方法。适配器测试通过本地辅助函数对公开流进行组装；`BlockAssembler` 仅保留有生产消费方的操作。
+
+## 曾考虑的替代方案
+
+**保留 `generate()` 作为仅供测试的便捷方法**：否决。适配器测试通过共享 assembler 手动消费 `stream()`，走的是与生产完全相同的流式路径；一个唯一调用方只有测试的公开方法，正是 [drop-mutable-summary 先例](2026-06-19-drop-mutable-session-summary.md)所淘汰的死接口形态。未来如果有消费方需要不带增量的组装块，届时再为该消费方引入一个聚焦的辅助方法。
+
+## 验证
+
+`streamBlocks`、`generate`、`llm/generate` 及仅供它们使用的 assembler 辅助函数均已移除，且未产生新的无用导出；两个真实适配器都通过 `stream()` 和共享 assembler 接受测试；循环行为保持一致（ACP（Agent Client Protocol）快照预期输出未变）；README、架构文档和模块文档也不再提及已删除表面。
+
+## 后果
+
+- **从一个核心词汇包中移除了公开方法。** 未来如果有插件需要不带增量的组装块，它需要直接调用 `stream()` 并使用 `BlockAssembler`，或在有真实消费方时重新引入一个聚焦的辅助方法。鉴于预发布阶段「基础优先于预设未来」的立场（[AGENTS.md](../../../../AGENTS.md)），现在正是裁剪仅供测试的公开接口的合适时机。
+- **适配器测试变得更显式。** 它们失去了便捷的 `generate()` 包装层，但这是有益的压力：测试走的是与生产相同的流式路径。
+- **waterfall 使用者失去 `llm/generate`。** 不存在生产监听者。未来的缓存/重试/日志插件应包装 `llm/stream`，它仍然是唯一的提供方调用路径。
+
+改动规模不大，但它从 LLM 包中干净地移除了预设的接口面积，为生产和测试留下唯一一份模型调用契约。

.agents/notes/archived/simplification/2026-06-20-prune-dead-seam-methods.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+2026-06-20-prune-dead-seam-methods.md: 4f292803ff34e504502d8b2b427ebbc769088968
+2026-06-20-prune-dead-seam-methods.zh.md: 325d41536d21686b95618d5d92ef8a946f7b8ddb

.agents/notes/archived/simplification/2026-06-20-prune-dead-seam-methods.md

@@ -0,0 +1,44 @@
+# Agent Note: Prune dead methods from the persistence seam
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-06-20-prune-dead-seam-methods.zh.md)
+
+> **Implementation note:** Only `SessionPersistence.has()` and `.delete()` were removed. `BashExecutor.get()` and `.list()` remain because removing their one-line lookup surface required substantially more completion-tracking machinery in consumers. Their id branding is covered by the [branded-ids Agent Note](../architecture/2026-06-20-branded-ids.md).
+
+## Problem
+
+A capability seam ([interface / implementation / consumer](../architecture/2026-06-13-capability-seams.md)) carries abstract methods that no consumer calls. The seam exists to let implementations and consumers evolve independently — but a method no consumer programs against is not a seam, it is speculative surface every implementation must still implement and test.
+
+### `SessionPersistence.has()` and `.delete()`
+
+The abstract service declared its operations beyond create/append: `load`, `list`, `has`, `delete`. Production consumers use `load()` and `list()` for resume and session discovery, while no production caller uses persistence `has()` or `delete()`. The similarly named in-memory collection calls in protocol and UI code are unrelated. The only callers of persistence `has`/`delete` were the contract suites and per-backend specs.
+
+`has()` was not just unused: it added a tracked-vs-untracked coordinator probe and a contract branch even though `loadStored(id)` already owns durable existence checks. `delete()` dragged the `deleteStored` backend hook that every backend had to implement. This is the [drop-mutable-session-summary](2026-06-19-drop-mutable-session-summary.md) pattern: a contract test exercised both, but no shipping code asks "is this session persisted?" or removes one.
+
+## Decision
+
+The methods nothing consumes are removed — from the abstract seam, the implementation, and the contract/spec suites that existed only to exercise them:
+
+- `SessionPersistence.has()` / `.delete()` are gone: the abstract declarations, the coordinator's `has`/`delete`/`deleteCore`, and the `PersistenceBackend.deleteStored` hook (jsonl + sqlite each implemented `deleteStored` only to satisfy the hook — those implementations went too). The backends are the [dual-backend](../architecture/2026-06-14-session-persistence.md) design and otherwise out of scope; removing a hook they implemented for no consumer is part of removing the hook, not a backend redesign.
+- Every doc and source-comment reference is updated to the surviving four-method, `list()`-only contract — not only literal `has(`/`delete(`/`deleteStored` spellings but `{@link has}`/`{@link delete}` JSDoc links and "six public methods" counts — across the seam and backend READMEs, [docs/architecture.md](../../../../docs/architecture.md), the [session-persistence](../architecture/2026-06-14-session-persistence.md) and [write-coordinator](../architecture/2026-06-18-shared-persistence-write-coordinator.md) Agent Notes, and the coordinator/backends JSDoc.
+
+## Alternatives considered
+
+### Why not keep them as "the seam should be complete"?
+
+The instinct that a persistence seam "should" offer delete is real — and it is exactly the speculative-completeness the pre-release stance warns against ([AGENTS.md](../../../../AGENTS.md): optimize for the correct foundation, not for hypothetical callers you do not have). `delete()` is one method to re-add the day a consumer needs it: a session-management UI that deletes old sessions will want it — add it then, designed against that UI's real needs (soft-delete? cascade? confirmation?), not guessed now.
+
+Re-adding a seam method with a live consumer is cheap and better-designed than the speculative version, because the consumer pins the contract. Carrying it unused means every implementation (and every future backend) must implement and test a method that does nothing.
+
+## Verification
+
+`has`/`delete`/`deleteStored` are gone from the persistence seam, impl, and contract suites with no new dead exports; the remaining operations (`create`/`append`/`load`/`list`) are untouched, with persistence-backed session queries and crash recovery behaving identically; and the seam README and `docs/architecture.md` list only the surviving methods.
+
+## Consequences
+
+- **`delete()` is the kind of operation a product eventually wants.** True — but "eventually" is the point. Deleting it now and re-adding it against a real consumer is strictly better than shipping a guessed contract. The dual backends each shed a `deleteStored` impl, which is a bounded edit in otherwise-out-of-scope packages.
+- **Low coupling.** The removal is confined to the persistence seam + impl + tests; no cross-package consumer references the removed methods, so there is no ripple beyond the docs.
+
+Modest size, but it converts the seam from "what an implementation must provide for nobody" back to "exactly what a consumer uses."

.agents/notes/archived/simplification/2026-06-20-prune-dead-seam-methods.zh.md

@@ -0,0 +1,44 @@
+# Agent Note: 从持久化 seam 中移除无用方法
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-06-20-prune-dead-seam-methods.md) | 中文
+
+> **实现说明：** 仅移除了 `SessionPersistence.has()` 和 `.delete()`。`BashExecutor.get()` 和 `.list()` 仍然保留，因为删除它们的单行查找表面会要求消费方增加显著更多的完成跟踪机制。其 id 品牌化由[品牌化 id Agent Note（agent 决策记录）](../architecture/2026-06-20-branded-ids.md)负责。
+
+## 问题
+
+能力 seam（[接口 / 实现 / 消费方](../architecture/2026-06-13-capability-seams.md)）承载了没有消费方调用的抽象方法。seam 的存在是为了让实现和消费方独立演进——但没有消费方以之编程的方法不是 seam，而是每个实现仍必须实现和测试的推测性表面。
+
+### `SessionPersistence.has()` 与 `.delete()`
+
+该抽象服务在 create/append 之外声明了更多操作：`load`、`list`、`has`、`delete`。生产消费方用 `load()` 和 `list()` 完成恢复与会话发现，而没有任何生产调用方使用持久化的 `has()` 或 `delete()`。协议和 UI 代码中名称相似的内存集合调用与此无关。持久化 `has`/`delete` 的唯一调用者是契约测试套件和各后端的 spec。
+
+`has()` 不仅未被使用：在 `loadStored(id)` 已负责持久化存在性检查的情况下，它仍增加了协调器的已跟踪/未跟踪探测和一个契约分支。`delete()` 则拖入每个后端都必须实现的 `deleteStored` 后端钩子。这属于[删除可变会话 summary](2026-06-19-drop-mutable-session-summary.md) 的同类模式：契约测试覆盖了两者，但已发布代码从不会询问“这个会话是否已持久化？”或删除某个会话。
+
+## 决策
+
+没有消费方使用的方法被移除——从抽象 seam、实现，以及仅为覆盖它们而存在的契约/spec 测试套件中移除：
+
+- `SessionPersistence.has()` / `.delete()` 已移除：抽象声明、协调器的 `has`/`delete`/`deleteCore`，以及 `PersistenceBackend.deleteStored` 钩子均消失（jsonl 和 sqlite 都只是为了满足该钩子才实现 `deleteStored`，这些实现也一并移除）。后端属于[双后端](../architecture/2026-06-14-session-persistence.md)设计，其他方面不在范围内；删除它们为没有消费方的钩子所做的实现，是删除钩子的一部分，而非重新设计后端。
+- 所有文档和源码注释引用都已更新为保留下来的四方法、仅含 `list()` 的契约——不仅包括字面上的 `has(`/`delete(`/`deleteStored` 拼写，还包括 `{@link has}`/`{@link delete}` JSDoc 链接和“六个公共方法”的计数——涉及 seam 和后端 README、[docs/architecture.md](../../../../docs/architecture.md)、[会话持久化](../architecture/2026-06-14-session-persistence.md)与[写入协调器](../architecture/2026-06-18-shared-persistence-write-coordinator.md) Agent Note，以及协调器/后端 JSDoc。
+
+## 曾考虑的替代方案
+
+### 为什么不以「seam 应当完整」为由保留？
+
+「持久化 seam 理应提供 delete」这种直觉是真实的——但它恰恰是预发布阶段所警惕的投机性完整（[AGENTS.md](../../../../AGENTS.md)：为正确的基础优化，而非为你并不拥有的假想调用者优化）。`delete()` 是一个方法，等消费方真正需要时再加回来即可：一个删除旧会话的会话管理 UI 会需要它——到那时再加，基于该 UI 的真实需求来设计（软删除？级联？确认？），而非现在猜测。
+
+在有活跃消费方的情况下重新添加一个 seam 方法，成本低且设计更优，因为消费方锚定了契约。在无人使用的情况下保留它，意味着每个实现（以及未来的每个后端）都必须实现和测试一个无实际作用的方法。
+
+## 验证
+
+`has`/`delete`/`deleteStored` 已从持久化 seam、实现和契约测试套件中移除，没有新增无用导出；剩余操作（`create`/`append`/`load`/`list`）未受影响，基于持久化的会话查询和崩溃恢复行为完全一致；seam README 和 `docs/architecture.md` 仅列出存留的方法。
+
+## 后果
+
+- **`delete()` 是产品最终会需要的操作。** 确实如此，但「最终」正是关键。现在删除、将来基于真实消费方重新添加，严格优于发布一份猜测的契约。两个后端各自减少了一个 `deleteStored` 实现，这是在本次范围之外的包中的有限改动。
+- **低耦合。** 移除局限于持久化 seam + 实现 + 测试；没有跨包消费方引用被移除的方法，因此除文档外没有涟漪效应。
+
+规模不大，但它将 seam 从「实现必须为无人提供什么」恢复为「恰好是消费方使用的东西」。

.agents/notes/archived/simplification/2026-07-04-drop-inert-request-knobs.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+2026-07-04-drop-inert-request-knobs.md: d4ef5f00caf3b2f580877374adaf6ddcd84e7326
+2026-07-04-drop-inert-request-knobs.zh.md: dfb57080e91039d48b9c173bf958c583005c3c32

.agents/notes/archived/simplification/2026-07-04-drop-inert-request-knobs.md

@@ -0,0 +1,36 @@
+# Agent Note: Drop `GenerateOptions.prefill` and `ToolSchema.strict` — request knobs with no working end-to-end path
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-04-drop-inert-request-knobs.zh.md)
+
+## Problem
+
+Two request-contract knobs rode the whole request pipeline, yet neither could do anything:
+
+- **`prefill`** (`packages/llm/llm/src/types.ts`) had no production setter — the loop assembles `model`/`system`/`tools`/`messages` plus `sessionId`/`signal`, and the compaction backend adds only `maxTokens` — and BOTH adapters rejected it: `packages/llm/llm-deepseek/src/serialize.ts` and `packages/llm/llm-pi-ai/src/adapter.ts` each threw `LlmError('UNSUPPORTED')` on a non-undefined `prefill`. The field's entire observable behavior was two throws, each pinned by one adapter test. DeepSeek's chat-prefix completion is a Beta feature on a base URL neither adapter targets.
+- **`strict`** (`ToolSchema`, same file) was threaded through `DefineToolOptions`/`defineTool` (`packages/core/tools/src/schema.ts`), the registry's `schemas()` allowlist (`packages/core/tools/src/index.ts`), the deepseek wire mapping (`packages/llm/llm-deepseek/src/serialize.ts`, whose wire-type note recorded that strict mode requires the `/beta` base URL the adapter does not use), a per-tool payload-patching pass in `packages/llm/llm-pi-ai/src/adapter.ts`, and a conditional `Strict:` row in the tool-catalog renderer (`scripts/gen-tool-catalog.ts`). No shipped tool set it — `rg` across every `tool-*` package src and `examples/` found zero `strict:` producers; the only setters were dsh-tools unit tests.
+
+Both knobs were adapter-symmetric, so removal shed them from both twins together — the [twin-adapter design](../architecture/2026-06-13-twin-llm-adapters.md) is untouched.
+
+## Decision
+
+- `prefill` is removed from `GenerateOptions`, along with both adapters' UNSUPPORTED guards, the tests pinning the throws, the paste line in [core.md](../../../../docs/core-data-structures/core.md), and the adapter README rows documenting the rejection. The cookbook's UNSUPPORTED guidance ([adding-an-llm-adapter.md](../../../../docs/cookbook/adding-an-llm-adapter.md)) states the rule generically — a `GenerateOptions` field your provider cannot honor throws `LlmError(..., 'UNSUPPORTED')` — instead of using prefill as the example. The [content-block vocabulary Agent Note](../architecture/2026-06-11-content-block-vocabulary.md)'s consequences record prefill as producer-gated rather than as having a home, per [implemented/AGENTS.md](../AGENTS.md).
+- `strict` is removed from `ToolSchema`, `DefineToolOptions`, `defineTool`, the `schemas()` allowlist, the deepseek serializer branch and its wire-type field, and the tool-catalog renderer's `Strict:` row. The pi-ai payload fixup is simplified to the unconditional scrub of pi-ai's own per-tool strict default (pi-ai stamps `strict: false` on every serialized tool; the hand-rolled twin sends no such field, so the scrub survives for wire parity, pinned by its serializer test). The setter tests and the core.md paste line are gone; both `GenerateOptions` and `ToolSchema` keep their rows in `scripts/type-equiv.manifest.json`, since each type survives minus a field.
+
+This Agent Note deliberately does NOT touch `temperature`, `stop`, or `maxTokens`: those are honored end-to-end by both adapters and are the natural first targets of a request-mutating hook plugin on `agent/request`.
+
+## Alternatives considered
+
+### Why not keep them?
+
+"An explicit UNSUPPORTED throw is honest contract behavior" — but a knob whose only implementation across both twins is rejection promises nothing, and deleting it upgrades the failure mode: an accidental setter becomes a compile error instead of a runtime throw. "Strict schema adherence is an officially documented provider feature with complete plumbing" — but a knob is not product surface until a shipped tool sets it AND an endpoint honors it; today neither is true. Each returns with its first real producer: `prefill` together with an adapter that implements chat-prefix completion (and a stated policy for adapters that do not), `strict` together with a tool that wants it and a beta-endpoint story.
+
+## Verification
+
+`rg prefill` returns only Agent Note records (this one and the [content-block vocabulary Agent Note](../architecture/2026-06-11-content-block-vocabulary.md)'s producer-gated consequence); a tool-schema-scoped `rg strict` returns only this Agent Note, the surviving pi-ai scrub, and unrelated prose such as `strictEqual`. Both adapters' contract tests pass without the guards, and the pi-ai fixup still scrubs the library's strict default — wire parity pinned by its serializer tests.
+
+## Consequences
+
+The shipped hook bridges set no request fields at all, and a request-mutating plugin (an `agent/request` waterfall listener) reaches for `temperature`/`stop` (kept, working), not a field adapters reject. If chat-prefix completion or strict mode become product features, the re-add lands with the adapter/endpoint work, where the contract can say what actually happens rather than "everyone throws".

.agents/notes/archived/simplification/2026-07-04-drop-inert-request-knobs.zh.md

@@ -0,0 +1,36 @@
+# Agent Note: 移除 `GenerateOptions.prefill` 与 `ToolSchema.strict`——无端到端可用路径的请求旋钮
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-04-drop-inert-request-knobs.md) | 中文
+
+## 问题
+
+两个请求契约旋钮贯穿了整条请求流水线，却都无法产生任何效果：
+
+- **`prefill`**（`packages/llm/llm/src/types.ts`）没有生产级的 setter：agent loop（智能体循环）组装的是 `model`/`system`/`tools`/`messages` 加 `sessionId`/`signal`，上下文压缩（context compaction）后端只追加 `maxTokens`；而且两个适配器都拒绝它：`packages/llm/llm-deepseek/src/serialize.ts` 和 `packages/llm/llm-pi-ai/src/adapter.ts` 各自在 `prefill` 非 undefined 时抛出 `LlmError('UNSUPPORTED')`。该字段的全部可观测行为就是两个 throw，各由一条适配器测试固定。DeepSeek 的 chat-prefix completion 是一个 Beta 功能，运行在两个适配器都未指向的 base URL 上。
+- **`strict`**（`ToolSchema`，同一文件）穿过了 `DefineToolOptions`/`defineTool`（`packages/core/tools/src/schema.ts`）、注册表的 `schemas()` 允许列表（`packages/core/tools/src/index.ts`）、deepseek 协议格式（wire format）映射（`packages/llm/llm-deepseek/src/serialize.ts`，其 wire-type 注释记录了 strict 模式需要适配器未使用的 `/beta` base URL）、`packages/llm/llm-pi-ai/src/adapter.ts` 中的逐工具 payload 修补逻辑，以及 tool-catalog 渲染器（`scripts/gen-tool-catalog.ts`）中的条件 `Strict:` 行。没有任何已发布的工具设置过它——在所有 `tool-*` 包的 src 和 `examples/` 中执行 `rg` 搜索，`strict:` 的生产者为零；唯一的 setter 出现在 dsh-tools 单元测试中。
+
+两个旋钮在适配器间是对称的，因此移除操作将它们从两个孪生适配器中一并剥离——[孪生适配器设计](../architecture/2026-06-13-twin-llm-adapters.md)不受影响。
+
+## 决策
+
+- 从 `GenerateOptions` 中移除 `prefill`，同时移除两个适配器的 UNSUPPORTED 守卫、固定抛错行为的测试、[core.md](../../../../docs/core-data-structures/core.md) 中的粘贴行，以及记录该拒绝行为的适配器 README 表格行。实操手册中的 UNSUPPORTED 指导（[adding-an-llm-adapter.md](../../../../docs/cookbook/adding-an-llm-adapter.md)）改为通用表述规则——提供方无法遵守的 `GenerateOptions` 字段应抛出 `LlmError(..., 'UNSUPPORTED')`——而不再以 prefill 为例。[内容块词汇 Agent Note（agent 决策记录）](../architecture/2026-06-11-content-block-vocabulary.md)的后果按照 [implemented/AGENTS.md](../AGENTS.md)，将 prefill 记录为由生产者门控，而不是已有归属。
+- 从 `ToolSchema`、`DefineToolOptions`、`defineTool`、`schemas()` 允许列表、deepseek 序列化分支及其 wire-type 字段，以及工具目录渲染器的 `Strict:` 行中移除 `strict`。pi-ai 的 payload 修补逻辑简化为对 pi-ai 自身逐工具 strict 默认值的无条件清除（pi-ai 在每个序列化的工具上打 `strict: false`；手写的孪生适配器不发送此字段，因此清除逻辑为保持协议格式对等而保留，由其序列化器测试固定）。setter 测试和 core.md 粘贴行已移除；`GenerateOptions` 与 `ToolSchema` 在 `scripts/type-equiv.manifest.json` 中保留各自的行，因为两个类型只是少了一个字段，本身仍然存在。
+
+本 Agent Note 刻意不触及 `temperature`、`stop` 或 `maxTokens`：两个适配器都会端到端遵守它们，而且它们自然是 `agent/request` 上修改请求的钩子插件首批目标。
+
+## 曾考虑的替代方案
+
+### 为什么不保留？
+
+「显式的 UNSUPPORTED throw 是诚实的契约行为」——但一个在两个孪生适配器中唯一的实现就是拒绝的旋钮，什么也没承诺；删除它反而升级了失败模式：意外的 setter 变成编译错误而非运行时 throw。「Strict schema 遵循是官方文档记载的提供方功能，且管道完整」——但一个旋钮在有已发布的工具设置它并且有端点兑现它之前，不构成产品表面；今天两者都不成立。它们各自随首个真实 producer 回归：`prefill` 随实现了 chat-prefix completion 的适配器（以及对不支持该功能的适配器的明确策略）一起回来；`strict` 随需要它的工具和 beta 端点方案一起回来。
+
+## 验证
+
+`rg prefill` 只返回 Agent Note 记录（本文及[内容块词汇 Agent Note](../architecture/2026-06-11-content-block-vocabulary.md)中由生产者门控的后果）；限定在工具 schema 范围内的 `rg strict` 只返回本 Agent Note、保留下来的 pi-ai 清理逻辑，以及 `strictEqual` 等无关正文。两个适配器的契约测试都能在没有守卫的情况下通过，pi-ai 修正仍会清理库的 strict 默认值——其 serializer 测试固定了线协议一致性。
+
+## 后果
+
+已发布的钩子桥接不设置任何请求字段，而请求变更插件（`agent/request` waterfall（瀑布式事件）监听器）使用的是 `temperature`/`stop`（保留且可用），而非适配器拒绝的字段。如果 chat-prefix completion 或 strict 模式成为产品功能，重新添加将随适配器/端点工作一起落地，届时契约能说明实际发生了什么，而不是「所有人都 throw」。

.agents/notes/archived/simplification/2026-07-04-drop-unconsumed-web-observation-surface.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+2026-07-04-drop-unconsumed-web-observation-surface.md: e63df08e486862b5bbb37db1e2c15b6d7e9d67e2
+2026-07-04-drop-unconsumed-web-observation-surface.zh.md: f9d1c09f90ec5065f25d4941dc319cff817caf97

.agents/notes/archived/simplification/2026-07-04-drop-unconsumed-web-observation-surface.md

@@ -0,0 +1,35 @@
+# Agent Note: Drop the unconsumed web observation surface — the `providers-change` event and the status methods
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-04-drop-unconsumed-web-observation-surface.zh.md)
+
+## Problem
+
+`WebService` exposes an observation surface no production code observes:
+
+- **`web/providers-change`** (`packages/web/web/src/index.ts`) is declared and emitted on every provider registration and disposal, and each registration effect's rollback yield is ordered BEFORE the emit solely so a throwing change listener unwinds the registration. No listener exists outside the package's own two unit tests (one of which exists to pin that rollback ordering).
+- **`searchStatus()` / `fetchStatus()` and the `WebCapabilityStatus` union** (same package) have zero production callers: `dsh-tool-web` executes directly through `ctx.web.search()`/`fetch()` and surfaces unavailability as the structured `WebError` codes the seam throws at execution time (`packages/web/tool-web/src/search.ts`, `packages/web/tool-web/src/fetch.ts`); the only status callers are the web packages' own tests. The prose in `packages/web/tool-web/README.md` and [architecture.md](../../../../docs/architecture.md) claims the tool "reads only the aggregated `searchStatus()`/`fetchStatus()`" — drift that survives only because nothing checks prose against call sites.
+
+The seam's own design starves both surfaces of consumers: tool registration follows product ENABLEMENT, not provider availability (`packages/web/tool-web/src/index.ts`), and provider selection resolves at execution time, never cached — so there is no cache to invalidate, no registration set to recompute, and no caller that needs an availability probe distinct from executing and routing the structured error. HMR cleanup is carried by the effect disposers themselves.
+
+This mirrors [drop the unconsumed `llm/adapter-change` event](2026-06-20-drop-unconsumed-llm-adapter-change-event.md), which removed the same notification shape, the same rollback-before-emit machinery, and the same listener-throw test from `LlmService`. That Agent Note's keep/cut criterion — keep `tools/change` for its plausible user-facing tool-list consumer, cut the boot-time backend-registry signal — puts a web-provider registry squarely on the cut side; the status methods are the same judgment applied to a pull surface instead of a push one.
+
+## Decision
+
+Remove the registry-change event, aggregated status methods and type, and their dedicated tests. Provider-private status remains for execution-time selection. Caller-facing coverage now asserts successful execution or structured selection errors, and the owning web docs describe that on-call contract.
+
+## Alternatives considered
+
+### Why not keep it?
+
+The web seam Agent Note specified both deliberately — the event as a minimal HMR-visibility signal, the status methods as the tool's aggregated diagnostics — and a future provider-status panel is imaginable. But the same Agent Note's other choices starved them: derived-on-call selection and enablement-based registration leave no consumer that CAN need either, the shipped tool demonstrates the real pattern (execute and route the structured error), and the drifted README sentence shows the promised consumer never materialized. Per AGENTS.md "Agent Notes are proposals, not golden truth", these are the parts of that proposal the code has since shown to over-reach; a future observer reintroduces the smallest signal or query it actually consumes, shaped by that consumer.
+
+## Verification
+
+No `providers-change`, `searchStatus`, `fetchStatus`, or `WebCapabilityStatus` spelling survives outside Agent Note history; the catalog is fresh (`verify-cordis-catalog` green); registration/disposal HMR-safety tests prove cleanup through execution behavior; and the tool-web README plus the architecture paragraph describe the execution-time error-routing contract the tool actually has.
+
+## Consequences
+
+A future provider-picker UI or diagnostics panel that wants change notifications or a status query re-adds the smallest surface it consumes; the identical judgment, and its reversal condition, is already recorded on the llm precedent.

.agents/notes/archived/simplification/2026-07-04-drop-unconsumed-web-observation-surface.zh.md

@@ -0,0 +1,35 @@
+# Agent Note: 移除未被消费的 web 观测接口——`providers-change` 事件与 status 方法
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-04-drop-unconsumed-web-observation-surface.md) | 中文
+
+## 问题
+
+`WebService` 暴露了一组没有任何生产代码观测的观测接口：
+
+- **`web/providers-change`**（`packages/web/web/src/index.ts`）在每次提供方注册和 dispose（资源释放）时声明并发出，且每个注册 effect 的回滚 yield 被刻意排在 emit 之前，唯一目的是让抛出异常的 change listener 能回退注册。在该包自身的两个单元测试之外没有任何 listener（其中一个测试的存在仅仅是为了固定那个回滚顺序）。
+- **`searchStatus()` / `fetchStatus()` 与 `WebCapabilityStatus` 联合类型**（同一包）没有生产调用方：`dsh-tool-web` 直接通过 `ctx.web.search()`/`fetch()` 执行，并把不可用性呈现为 seam 在执行时抛出的结构化 `WebError` code（`packages/web/tool-web/src/search.ts`、`packages/web/tool-web/src/fetch.ts`）；唯一的 status 调用方是 web 包自己的测试。`packages/web/tool-web/README.md` 和 [architecture.md](../../../../docs/architecture.md) 中的正文声称工具“只读取聚合的 `searchStatus()`/`fetchStatus()`”——这种漂移之所以存续，只是因为没有机制对照调用位置检查正文。
+
+seam 自身的设计使这两个接口天然没有消费方：工具注册跟随产品 ENABLEMENT 而非提供方可用性（`packages/web/tool-web/src/index.ts`），提供方选择在执行时解析且从不缓存——因此没有需要失效的缓存、没有需要重算的注册集合、也没有调用方需要一个有别于「执行并路由结构化错误」的可用性探测。HMR（热模块替换）清理由 effect disposer 自身承载。
+
+这与[删除无人消费的 `llm/adapter-change` 事件](2026-06-20-drop-unconsumed-llm-adapter-change-event.md)相呼应；后者从 `LlmService` 移除了相同的通知形状、相同的 emit 前回滚机制和相同的监听器抛错测试。该 Agent Note（agent 决策记录）的保留/删除标准是：为可能面向用户的工具列表消费方保留 `tools/change`，删除启动时后端注册表信号。按这一标准，web 提供方注册表明确属于删除一侧；status 方法则是把同一判断应用于拉取表面，而非推送表面。
+
+## 决策
+
+移除注册表变更事件、聚合 status 方法与类型，以及它们的专属测试。提供方私有的 status 保留用于执行时选择。面向调用方的覆盖率现在断言成功执行或结构化的选择错误，web 文档描述该按需调用契约。
+
+## 曾考虑的替代方案
+
+### 为什么不保留？
+
+web seam Agent Note 刻意规定了两者——事件作为最小 HMR 可见性信号，status 方法作为工具的聚合诊断——未来也可以设想提供方状态面板。但同一 Agent Note 的其他选择让它们失去了生存条件：调用时派生选择和基于启用状态的注册，使任何消费方都不可能需要其中任一项；已发布工具展示了真实模式（执行并路由结构化错误）；发生漂移的 README 句子则表明承诺中的消费方从未出现。按照 AGENTS.md 所述“Agent Note 是提案，而非绝对真理”，代码后来证明提案中的这些部分超出了需要；未来的观察者应根据真实消费方的形状，重新引入它实际消费的最小信号或查询。
+
+## 验证
+
+除 Agent Note 历史外，不再存在 `providers-change`、`searchStatus`、`fetchStatus` 或 `WebCapabilityStatus` 拼写；目录保持新鲜（`verify-cordis-catalog` 为绿色）；注册/释放 HMR 安全性测试通过执行行为证明清理；tool-web README 和架构段落也描述了工具实际拥有的执行时错误路由契约。
+
+## 后果
+
+未来若有提供方选择器 UI 或诊断面板需要变更通知或 status 查询，它将重新添加自身所消费的最小接口；相同的判断及其反转条件已记录在 LLM（大语言模型）先例中。

.agents/notes/archived/simplification/2026-07-04-prune-producerless-vocabulary-variants.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+2026-07-04-prune-producerless-vocabulary-variants.md: c1544fa9d72c994518f690d482a62d506ff3f83e
+2026-07-04-prune-producerless-vocabulary-variants.zh.md: e48f55c49d35d4a675f0d9540dab034bcb864cd3

.agents/notes/archived/simplification/2026-07-04-prune-producerless-vocabulary-variants.md

@@ -0,0 +1,34 @@
+# Agent Note: Prune producer-less vocabulary variants (block cache hints, the `agent` message source, the `continuation` turn trigger)
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-04-prune-producerless-vocabulary-variants.zh.md)
+
+## Problem
+
+The merge-extensible vocabulary maps are designed to grow by declaration merging, and the codebase already states the admission policy on `TurnEndReasonMap` (`packages/core/session/src/types.ts`): a variant like `refusal` is "deliberately omitted until" an adapter or loop first emits it. Three declared vocabulary items violated that policy — each had no producer and no consumer, and two had not even a test:
+
+- **`CacheHint` and its `cache?: CacheHint` block fields** on `TextBlock`/`ToolResultBlock` (`packages/llm/llm/src/types.ts`; the image block carried a third such field, which left with it — see [the drop-image Agent Note](2026-07-04-drop-image-content-block.md)). Nothing constructed a block with `cache:` anywhere — src, tests, and doc pastes all came up empty — and neither adapter read `.cache`: DeepSeek prompt caching is automatic, so the adapters map `prompt_cache_hit_tokens` OUT of responses without ever sending a hint IN. This was Anthropic-style `cache_control` surface with no provider that could honor it.
+- **`MessageSourceMap.agent`** (`{ kind: 'agent'; agentId: string }`, same file). Zero constructors, tests included. Its intended producer shipped without it: the subagent backends send the parent's prompt to the child with no `source`, so it logs as `{ kind: 'user' }`, and the generic envelope renderer interpolates `source.kind` without ever routing on it.
+- **`TurnTriggerMap.continuation`** (`packages/core/session/src/types.ts`). The loop structurally cannot emit it — continuation happens *within* a turn as further steps, never as a new turn — and it constructs only `message` and `injection` triggers. The only writer was one hand-built test fixture needing an arbitrary non-message trigger (`packages/support/llm-replay/tests/llm-replay.spec.ts`), which an `injection` trigger serves equally; the only production trigger reader, the ACP bridge, filters on `kind === 'message'`.
+
+## Decision
+
+`CacheHint`, its `cache?` block fields, the `agent` message-source variant, and the `continuation` turn-trigger variant are deleted: the shipped vocabulary carries none of them. The llm-replay fixture uses an `injection` trigger (any non-`message` trigger serves its purpose). The type-equiv pastes in [core.md](../../../../docs/core-data-structures/core.md) and [session.md](../../../../docs/core-data-structures/session.md) match the pruned maps — both symbols keep their rows in `scripts/type-equiv.manifest.json`, since each map survives minus a member — and the [content-block vocabulary Agent Note](../architecture/2026-06-11-content-block-vocabulary.md)'s consequences record cache hints as producer-gated rather than as having a home, per [implemented/AGENTS.md](../AGENTS.md).
+
+Each variant returns the day it gains a real producer, exactly as the maps are designed to grow: a caching feature re-adds `cache` together with the adapter that transmits it; subagent attribution re-adds `agent` together with the backend that stamps it and a consumer that routes on it; an auto-continue feature that genuinely starts new turns re-adds `continuation` with the plugin that emits it.
+
+## Alternatives considered
+
+### Why not keep them?
+
+The [content-block vocabulary Agent Note](../architecture/2026-06-11-content-block-vocabulary.md) listed "cache hints … have a home" as a design consequence, and reserved slots do advertise intent. But an empty slot is contract surface every implementation and consumer must consider (must my adapter honor `cache`? must my renderer route `agent` sources?), and the sibling map's own JSDoc already rejects reservation-without-emitter — `refusal` and `max_turn_requests` are named as variants to add *when something first emits them*, not declared in advance. Holding already-declared dead variants to the same standard makes the vocabulary mean something: if it is in the map, something produces it.
+
+## Verification
+
+`rg` for `CacheHint`, the `agent` message-source spelling, and the `continuation` trigger spelling returns only Agent Note records (this one, and [the drop-image Agent Note](2026-07-04-drop-image-content-block.md)'s account of the image block's own `cache` field); the llm-replay fixture asserts the same replay behavior with an `injection` trigger; the core-data-structures pastes and the type-equiv manifest are in sync.
+
+## Consequences
+
+Nothing operational changed — nothing could construct these values. The mirror-event removals ([the boundary-mirror Agent Note](2026-06-20-remove-agent-boundary-mirror-events.md), [the stream-chunk Agent Note](2026-07-02-remove-stream-chunk-mirror.md)) touch only transient `agent/*` events, never the durable vocabulary, so there is no collision. Elsewhere the admission policy already holds: `rejected`, `prompt/blocked`, and `hook/invoked`/`hook/result` each have live producers — this Agent Note extends the same bar to the three variants that lacked one. The image block's own `cache?` field belongs to [the drop-image Agent Note](2026-07-04-drop-image-content-block.md), which removed it together with the block; this Agent Note covers the two fields on the block types that remain.

.agents/notes/archived/simplification/2026-07-04-prune-producerless-vocabulary-variants.zh.md

@@ -0,0 +1,34 @@
+# Agent Note: 裁剪无生产者的词汇变体（块缓存提示、`agent` 消息来源、`continuation` 轮次触发器）
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-04-prune-producerless-vocabulary-variants.md) | 中文
+
+## 问题
+
+可合并扩展的词汇映射表设计上通过声明合并来增长，代码库已在 `TurnEndReasonMap`（`packages/core/session/src/types.ts`）上明确了准入策略：像 `refusal` 这样的变体「在适配器或循环首次发出它之前，有意不纳入」。三个已声明的词汇项违反了该策略——每个都既无生产者也无消费方，其中两个甚至没有测试：
+
+- **`TextBlock`/`ToolResultBlock` 上的 `CacheHint` 及其 `cache?: CacheHint` 块字段**（`packages/llm/llm/src/types.ts`；图像块曾有第三个此类字段，已随图像块一同移除——参见[删除图像 Agent Note（agent 决策记录）](2026-07-04-drop-image-content-block.md)）。任何地方都没有构造带 `cache:` 的块——src、测试和文档粘贴均为空——两个适配器也都不读取 `.cache`：DeepSeek 的提示词缓存是自动的，因此适配器会从响应中映射出 `prompt_cache_hit_tokens`，却从不向请求中发送 hint。这是没有任何提供方能够遵守的 Anthropic 风格 `cache_control` 表面。
+- **`MessageSourceMap.agent`**（`{ kind: 'agent'; agentId: string }`，同一文件）。零个构造点，包括测试在内。它预期的生产者在实现时并未使用它：subagent 后端将父级的提示词发送给子级时不带 `source`，因此记录为 `{ kind: 'user' }`，通用信封渲染器在插值 `source.kind` 时也从未对其做路由。
+- **`TurnTriggerMap.continuation`**（`packages/core/session/src/types.ts`）。agent loop（智能体循环）在结构上不可能发出它——continuation 发生在一个轮次*内部*作为后续步骤，而非作为新轮次——循环只构造 `message` 和 `injection` 触发器。唯一的写入者是一个手工构建的测试 fixture（测试前置数据），它只需要一个任意的非消息触发器（`packages/support/llm-replay/tests/llm-replay.spec.ts`），`injection` 触发器同样满足需求；唯一的生产环境触发器读取方 ACP（Agent Client Protocol）桥接层只过滤 `kind === 'message'`。
+
+## 决策
+
+`CacheHint`、其 `cache?` 块字段、`agent` 消息来源变体和 `continuation` 轮次触发器变体均已删除：已发布词汇不再携带它们。llm-replay fixture 使用 `injection` 触发器（任何非 `message` 触发器都能满足其用途）。[core.md](../../../../docs/core-data-structures/core.md) 和 [session.md](../../../../docs/core-data-structures/session.md) 中的 type-equiv 粘贴与裁剪后的 map 匹配——两个符号仍保留在 `scripts/type-equiv.manifest.json` 中的行，因为每个 map 都只是少了一个成员而继续存在——并且[内容块词汇 Agent Note](../architecture/2026-06-11-content-block-vocabulary.md)的后果按照 [implemented/AGENTS.md](../AGENTS.md)，将 cache hint 记录为由生产者门控，而不是已有归属。
+
+每个变体在获得真正的生产者之日回归，这正是映射表设计的增长方式：缓存功能连同传输它的适配器一起重新添加 `cache`；subagent 归属连同打标的后端和路由它的消费方一起重新添加 `agent`；真正启动新轮次的自动续行功能连同发出它的插件一起重新添加 `continuation`。
+
+## 曾考虑的替代方案
+
+### 为什么不保留它们？
+
+[内容块词汇 Agent Note](../architecture/2026-06-11-content-block-vocabulary.md)曾把“cache hint……有了归属”列为设计后果，预留槽位也确实能表明意图。但空槽位是每个实现和消费方都必须考虑的契约表面（我的适配器是否必须遵守 `cache`？我的 renderer 是否必须路由 `agent` 来源？），而相邻 map 自身的 JSDoc 已经拒绝“无 emitter 先预留”——`refusal` 和 `max_turn_requests` 被点名为*首次有内容发出它们时*再添加的变体，而不是提前声明。让已经声明但无用的变体遵守同一标准，才能使词汇真正有意义：只要它位于 map 中，就必须有内容生产它。
+
+## 验证
+
+对 `CacheHint`、`agent` 消息来源拼写和 `continuation` 触发器拼写运行 `rg`，只会返回 Agent Note 记录（本文，以及[删除图像 Agent Note](2026-07-04-drop-image-content-block.md)对图像块自身 `cache` 字段的说明）；llm-replay fixture 使用 `injection` 触发器断言相同的重放行为；核心数据结构粘贴和 type-equiv 清单保持同步。
+
+## 后果
+
+操作行为没有变化——原本就没有内容能够构造这些值。镜像事件移除（[边界镜像 Agent Note](2026-06-20-remove-agent-boundary-mirror-events.md)、[流分片 Agent Note](2026-07-02-remove-stream-chunk-mirror.md)）只触及瞬态 `agent/*` 事件，从不触及持久词汇，因此不存在冲突。其他位置已经遵守准入策略：`rejected`、`prompt/blocked` 和 `hook/invoked`/`hook/result` 都有实时生产者——本 Agent Note 将同一门槛扩展到缺少生产者的三个变体。图像块自身的 `cache?` 字段归属[删除图像 Agent Note](2026-07-04-drop-image-content-block.md)，后者将其与该块一同移除；本 Agent Note 覆盖剩余块类型上的两个字段。

.agents/notes/archived/simplification/2026-07-04-prune-write-only-fs-surface.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+2026-07-04-prune-write-only-fs-surface.md: e1b6bb6bd9721120015aaced8ffae84048396b60
+2026-07-04-prune-write-only-fs-surface.zh.md: 2f8135b2b1fa9892270a110ea3c3112e6ea20700

.agents/notes/archived/simplification/2026-07-04-prune-write-only-fs-surface.md

@@ -0,0 +1,33 @@
+# Agent Note: Prune write-only fields and a dead routing knob from the fs seam
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-04-prune-write-only-fs-surface.zh.md)
+
+## Problem
+
+The [fs seam split](2026-06-26-fsspec-style-fs-seam.md) moved read routing and policy out of the backend into `dsh-tool-fs` and `dsh-fs-policy`. Four pieces of surface kept the pre-split shape — populated on every call, read by nobody:
+
+1. **`STREAM_MIN_SIZE` + `FsIoInternals.streamMinSize` in `dsh-fs-local`** — *removed ahead of this change by the no-hardcoded-tunables audit, which made the routing bound `dsh-tool-fs`'s `readStreamMinSize` config; recorded here as part of the full prune.* Originally (`packages/fs/fs-local/src/fsio.ts`, re-exported from `packages/fs/fs-local/src/index.ts`): zero readers anywhere, including fs-local's own source and tests. The backend has no read routing — `readWholeText`/`streamWholeText` are separate primitives the caller chooses between — and the real routing constant lives in the consumer (`packages/fs/tool-fs/src/read.ts`, compared against `info.size`). Two mirrors of the 10 MiB fact; the backend's was dead, and the knob's JSDoc claimed a "read routing" override that did not exist.
+2. **`FsTarget.inputPath`** (`packages/fs/fs/src/types.ts`): every backend and every test fake had to fabricate a "diagnostics only" value with zero production readers — the policy plugin and every error message use `targetKey`/`displayPath`. The `listDir` producer exposed the semantic wobble: directory children got the bare entry name, which was nobody's "input".
+3. **`FsEditOutcome.replacements` + `.replaceAll`** (`packages/fs/fs/src/types.ts`): `replacements` had zero production readers (the single-match policy itself stays — it is enforced by the `FS_AMBIGUOUS_EDIT`/`FS_EDIT_NOT_FOUND` throws inside the backend, whose error message keeps the internal count); `replaceAll` was read only by `formatEditOutput` in `packages/fs/tool-fs/src/edit.ts` — as an echo of the `replace_all` argument the tool already holds. Shrunk, `FsEditOutcome` is `{ version, before, after }`, parallel to `FsWriteOutcome`'s genuinely backend-discovered fields.
+4. **`FileReadOutcome.limit` + `.version`** (`packages/fs/tool-fs/src/read-render.ts`): populated by the read tool, but `formatReadOutput` renders `offset`/`lines`/`totalLines`/`truncatedByBytes` only, and the `fs/observed` emit uses `info.version` directly rather than an outcome copy.
+
+## Decision
+
+Delete the fs-local constant, its re-export, and the `streamMinSize` knob (the remaining `FsIoInternals` knobs are genuinely used by the atomic-write tests); drop `inputPath` from `FsTarget`; shrink `FsEditOutcome` to `{ version, before, after }` and pass `replaceAll` to `formatEditOutput` from the parsed args; drop `limit`/`version` from `FileReadOutcome`. The [filesystem.md](../../../../docs/core-data-structures/filesystem.md) pastes, `packages/fs/fs/README.md`, and the test fakes that had to fabricate the removed fields shrink with the types.
+
+## Alternatives considered
+
+### Why not keep them?
+
+A future permission/containment layer might want the pre-resolution path for error text — but it would want the *request*, which every call site still holds. "N occurrences replaced" might become model-facing text — a behavior change to design when wanted, and the backend-internal count survives for its error message. A read footer might display `limit` — everything the footer shows already derives from `lines`/`totalLines`. Meanwhile every current and future backend (remote, native) would have to fabricate wire fields nobody consumes, and every test fake would have to satisfy them.
+
+## Verification
+
+The removed surfaces are gone — `STREAM_MIN_SIZE`/`streamMinSize` in `dsh-fs-local`, `FsTarget.inputPath`, `FsEditOutcome.replacements`/`.replaceAll`, and `FileReadOutcome.limit`/`.version` — while the request-side `replaceAll` (`FsEditRequest`) and the version fields on the other outcome types are untouched; the test fakes shrank with the types. `formatEditOutput`'s emitted text is unchanged for both `replace_all` branches, so no snapshot expected output churned.
+
+## Consequences
+
+Backends gain no new obligations; they shed four fields nobody consumed. The fs discovery work (glob/grep tools) touches the same `dsh-fs` type files — a textual, not design, overlap that reconciles mechanically.

.agents/notes/archived/simplification/2026-07-04-prune-write-only-fs-surface.zh.md

@@ -0,0 +1,33 @@
+# Agent Note: 从 fs seam 中移除只写字段与一个无效的路由旋钮
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-04-prune-write-only-fs-surface.md) | 中文
+
+## 问题
+
+[fs seam 拆分](2026-06-26-fsspec-style-fs-seam.md)将读取路由与策略从后端移至 `dsh-tool-fs` 和 `dsh-fs-policy`。有四处接口保留了拆分前的形态——每次调用都填充，却无人读取：
+
+1. **`dsh-fs-local` 中的 `STREAM_MIN_SIZE` + `FsIoInternals.streamMinSize`**——*在本次变更之前已被「禁止硬编码可调参数」审计移除，该审计将路由阈值改为 `dsh-tool-fs` 的 `readStreamMinSize` 配置；此处记录是为了完整呈现整次清理。* 原始位置（`packages/fs/fs-local/src/fsio.ts`，从 `packages/fs/fs-local/src/index.ts` 重导出）：包括 fs-local 自身源码和测试在内，全仓库零读取者。后端没有读取路由——`readWholeText`/`streamWholeText` 是调用方自行选择的两个独立原语——真正的路由常量位于消费方（`packages/fs/tool-fs/src/read.ts`，与 `info.size` 比较）。同一个 10 MiB 事实的两份镜像；后端那份是死代码，且该旋钮的 JSDoc 声称提供一个实际不存在的「read routing」覆盖。
+2. **`FsTarget.inputPath`**（`packages/fs/fs/src/types.ts`）：每个后端和每个测试 mock 都必须为这个「仅供诊断」的字段编造一个值，而生产环境零读取者——策略插件和所有错误消息使用的是 `targetKey`/`displayPath`。`listDir` 的生产者暴露了语义上的摇摆：目录子项得到的是裸条目名，这不是任何人的「input」。
+3. **`FsEditOutcome.replacements` + `.replaceAll`**（`packages/fs/fs/src/types.ts`）：`replacements` 生产环境零读取者（单匹配策略本身保留——它由后端内部 `FS_AMBIGUOUS_EDIT`/`FS_EDIT_NOT_FOUND` 抛出来强制执行，错误消息保留了内部计数）；`replaceAll` 仅被 `packages/fs/tool-fs/src/edit.ts` 中的 `formatEditOutput` 读取——作为工具本身已持有的 `replace_all` 参数的回声。精简后，`FsEditOutcome` 变为 `{ version, before, after }`，与 `FsWriteOutcome` 中真正由后端发现的字段对齐。
+4. **`FileReadOutcome.limit` + `.version`**（`packages/fs/tool-fs/src/read-render.ts`）：由读取工具填充，但 `formatReadOutput` 只渲染 `offset`/`lines`/`totalLines`/`truncatedByBytes`，且 `fs/observed` 事件发射直接使用 `info.version` 而非 outcome 的副本。
+
+## 决策
+
+删除 fs-local 常量、其再导出和 `streamMinSize` 配置项（其余 `FsIoInternals` 配置项确实由原子写入测试使用）；从 `FsTarget` 删除 `inputPath`；将 `FsEditOutcome` 收窄为 `{ version, before, after }`，并把解析参数中的 `replaceAll` 传给 `formatEditOutput`；从 `FileReadOutcome` 删除 `limit`/`version`。[filesystem.md](../../../../docs/core-data-structures/filesystem.md) 中的粘贴、`packages/fs/fs/README.md`，以及不得不虚构已删除字段的测试 fake 都随类型一同收窄。
+
+## 曾考虑的替代方案
+
+### 为什么不保留？
+
+未来的权限/隔离层可能需要解析前的路径来生成错误文本——但它需要的是*请求*，每个调用点仍然持有请求。「替换了 N 处」可能成为面向模型的文本——这是一个需要时再设计的行为变更，且后端内部的计数为其错误消息而保留。读取页脚可能展示 `limit`——但页脚展示的一切已经可以从 `lines`/`totalLines` 推导。与此同时，每个现有和未来的后端（远程、原生）都必须编造无人消费的协议字段，每个测试 mock 都必须满足它们。
+
+## 验证
+
+已删除表面不复存在——`dsh-fs-local` 中的 `STREAM_MIN_SIZE`/`streamMinSize`、`FsTarget.inputPath`、`FsEditOutcome.replacements`/`.replaceAll`，以及 `FileReadOutcome.limit`/`.version`——而请求侧 `replaceAll`（`FsEditRequest`）和其他 outcome 类型上的版本字段保持不变；测试 fake 随类型一同收窄。`formatEditOutput` 在两个 `replace_all` 分支中生成的文本都没有变化，因此没有快照预期输出发生改动。
+
+## 后果
+
+后端不增加新义务，反而卸下了四个无人消费的字段。fs 发现功能（glob/grep 工具）涉及相同的 `dsh-fs` 类型文件——这是文本层面而非设计层面的重叠，可以机械地合并解决。

.agents/notes/archived/simplification/2026-07-04-remove-agent-steering-mirror.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+2026-07-04-remove-agent-steering-mirror.md: 0d7c7f8ac9592033423156d38f3bbe6d037afd07
+2026-07-04-remove-agent-steering-mirror.zh.md: be30e0add3a2d7392cb7a59ed4bc425ec0ad5588

.agents/notes/archived/simplification/2026-07-04-remove-agent-steering-mirror.md

@@ -0,0 +1,34 @@
+# Agent Note: Remove the `agent/steering` mirror emit
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-04-remove-agent-steering-mirror.zh.md)
+
+## Problem
+
+`agent/steering` was the last remaining transient mirror of a durable session event. The loop's steering drain appends the durable `steering/message { turn, content, source }` and, on the very next line, emitted `agent/steering(agent, turn, content, source)` — the identical fact as a fire-and-forget event (`packages/core/agent-loop/src/loop.ts`, `drainSteering`). It had zero production listeners: the only subscriber anywhere was a loop regression test asserting the emit carried `source` — the same fact the durable event already records one line above.
+
+`agent/steering` duplicated the immediately preceding durable `steering/message` with the same payload. `agent/queued` remains the live-only signal because it fires before persistence and covers work that may be cancelled before entering the log.
+
+Steering carries real production traffic — the hook bridges' turn-continuation decisions inject their reasons through `inbox.steer()`, landing as durable `steering/message` events that the hook-matrix expected outputs pin — and every one of those consumers observes the durable event. Nothing observed the mirror.
+
+## Decision
+
+`agent/steering` is removed from the agent event taxonomy: the declaration in `packages/core/agent/src/types.ts` (and its mention in the live-events JSDoc list there), the emit in `drainSteering` (whose then-unused `ctx` parameter went with it), the row in `packages/core/agent/README.md`, and the emit line in the loop-pseudocode blocks (the `packages/core/agent-loop/src/loop.ts` module doc and [architecture.md](../../../../docs/architecture.md)); the cordis catalog is regenerated without it. The one regression test pins source preservation on the durable `steering/message` event — the fact it pins lives on the log.
+
+Three implemented Agent Notes stated the retention, and each is amended per [implemented/AGENTS.md](../AGENTS.md) to point here as the record of the removal: the [boundary Agent Note](2026-06-20-remove-agent-boundary-mirror-events.md)'s retained-list entry, the [stream-chunk Agent Note](2026-07-02-remove-stream-chunk-mirror.md)'s scope clause, and the [event-domain-semantics Agent Note](../architecture/2026-06-30-event-domain-semantics.md)'s transient-emit enumeration.
+
+## Alternatives considered
+
+### Why not keep it?
+
+"It is a control signal, not a boundary" — but the taxonomy's operative distinction is mirrored-vs-live-only, not control-vs-boundary, and this event mirrored. A consumer that wants enqueue-time notification has `agent/queued` (with its steering flag); a consumer that wants drain-time notification is by definition asking for the moment `steering/message` is appended, which `session/event` delivers with the same payload plus durability. The rejected [retire-mid-turn-steering Agent Note](../../rejected/simplification/2026-06-20-retire-mid-turn-steering.md) defended the steering *capability* — `steer()`, the durable event, continuation forcing — all of which this removal keeps untouched.
+
+## Verification
+
+The `agent/steering` spelling survives only in Agent Note prose (this Agent Note, the three amended Agent Notes above, and the frozen [rejected steering-capability Agent Note](../../rejected/simplification/2026-06-20-retire-mid-turn-steering.md), whose text records the proposal it declined); the catalog is regenerated; the retargeted test pins source preservation on `steering/message`.
+
+## Consequences
+
+Zero production listeners existed to migrate, and both live-notification needs keep surviving homes: enqueue-time on `agent/queued` (with its `steering` flag), drain-time on `session/event` as the durable `steering/message` lands.

.agents/notes/archived/simplification/2026-07-04-remove-agent-steering-mirror.zh.md

@@ -0,0 +1,34 @@
+# Agent Note: 移除 `agent/steering` 镜像 emit
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-04-remove-agent-steering-mirror.md) | 中文
+
+## 问题
+
+`agent/steering` 是最后一个仍存在的、对持久会话事件的瞬态镜像。agent loop（智能体循环）的 steering（中途引导）drain 逻辑先追加持久事件 `steering/message { turn, content, source }`，紧接着下一行就 emit `agent/steering(agent, turn, content, source)`——同一个事实以 fire-and-forget 事件的形式重复发出（`packages/core/agent-loop/src/loop.ts`，`drainSteering`）。它在生产环境中没有任何监听者：唯一的订阅方是一个 agent loop 回归测试，断言 emit 携带了 `source`——而这同一个事实已经由上一行的持久事件记录。
+
+`agent/steering` 以相同的 payload 重复了紧接其前的持久事件 `steering/message`。`agent/queued` 仍保留为纯瞬态信号，因为它在持久化之前触发，覆盖了可能在进入日志前被取消的工作。
+
+Steering 承载真实生产流量——钩子 bridge 的轮次延续决策通过 `inbox.steer()` 注入其理由，最终成为由钩子矩阵预期输出固定的持久 `steering/message` 事件——而这些消费方无一例外都观察持久事件。没有任何内容观察镜像。
+
+## 决策
+
+`agent/steering` 已从 agent 事件分类中移除：包括 `packages/core/agent/src/types.ts` 中的声明（以及其中实时事件 JSDoc 列表对它的提及）、`drainSteering` 中的 emit（当时已无用的 `ctx` 参数也随之移除）、`packages/core/agent/README.md` 中的表格行，以及循环伪代码块（`packages/core/agent-loop/src/loop.ts` 模块文档和 [architecture.md](../../../../docs/architecture.md)）中的 emit 行；Cordis 目录重新生成后不再包含它。唯一的回归测试改为在持久 `steering/message` 事件上固定来源保留行为——所固定的事实存在于日志上。
+
+三份已实现 Agent Note（agent 决策记录）曾说明保留该事件；按照 [implemented/AGENTS.md](../AGENTS.md)，每份记录都已修改并指向本文作为移除记录：包括[边界 Agent Note](2026-06-20-remove-agent-boundary-mirror-events.md) 的保留列表条目、[流分片 Agent Note](2026-07-02-remove-stream-chunk-mirror.md) 的范围条款，以及[事件域语义 Agent Note](../architecture/2026-06-30-event-domain-semantics.md) 的瞬态 emit 枚举。
+
+## 曾考虑的替代方案
+
+### 为什么不保留？
+
+“它是控制信号，不是边界”——但该分类的实际区分是镜像/仅实时，而非控制/边界，并且该事件确实是镜像。希望在入队时收到通知的消费方可以使用 `agent/queued`（及其 steering 标记）；希望在排空时收到通知的消费方，本质上是在要求获知 `steering/message` 被追加的时刻，而 `session/event` 会交付相同 payload 并附带持久性。遭拒绝的[退役轮次中途 steering Agent Note](../../rejected/simplification/2026-06-20-retire-mid-turn-steering.md)所捍卫的是 steering *功能*——`steer()`、持久事件、强制延续——本次移除不会触及其中任何一项。
+
+## 验证
+
+`agent/steering` 拼写只存在于 Agent Note 正文中（本 Agent Note、上方三份已修改 Agent Note，以及已冻结的[遭拒绝 steering 功能 Agent Note](../../rejected/simplification/2026-06-20-retire-mid-turn-steering.md)，其正文记录了它所否决的提案）；目录已重新生成；重新定向的测试在 `steering/message` 上固定来源保留行为。
+
+## 后果
+
+生产环境中没有需要迁移的监听者，两种瞬态通知需求各有归宿：入队时由 `agent/queued`（带 `steering` flag）承载，drain 时由 `session/event` 在持久事件 `steering/message` 落地时承载。

.agents/notes/archived/simplification/2026-07-04-share-app-bin-boot-glue.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+2026-07-04-share-app-bin-boot-glue.md: 8b2aeef73ecfc07f3102f852d4b0a44b336b7d92
+2026-07-04-share-app-bin-boot-glue.zh.md: ed5146030ca8d23a653497d6c097ad6c3b4445b1

.agents/notes/archived/simplification/2026-07-04-share-app-bin-boot-glue.md

@@ -0,0 +1,28 @@
+# Agent Note: Share the app bins' boot glue instead of maintaining twin copies
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-04-share-app-bin-boot-glue.zh.md)
+
+## Problem
+
+The stdio and ACP bins duplicated environment loading, fail-loud handling, entry validation, and boot logic, including subtle Loader failure behavior. Their copies had already drifted and lived in self-executing files excluded from unit coverage, making their helper exports unusable.
+
+## Decision
+
+The helpers live once, in [`@deepseek-ai/dsh-app-boot`](../../../../packages/ui/app-boot) (`packages/ui/app-boot`, in the `ui` group because the bins are published artifacts whose runtime dependency must itself be published, not `support/`): `resolveConfigPath` (snapshot-aware, the single path resolver for both bins), `loadEnv`, `installFailLoud`, `assertEntriesLoaded`, and `boot`, each parameterized by the bin's diagnostic prefix and injectable at its side-effect seams (the warn sink, the process slice) so the unit suite covers every branch — including `boot()` driven in-process against the real Loader with relative-specifier configs, both the settled-tree happy path and the fiber-less-entry rejection. The package carries the per-file 100% coverage gate; the loader-failure lore has one home.
+
+Each `bin.ts` is a thin self-executing composition over the shared helpers plus its app-specific lifecycle (the ACP bin: replay-mode env skipping and the stdin-EOF dispose; the stdio bin: nothing extra). The bins stay coverage-excluded and export nothing; the published-artifact guards are unchanged — the built-bin smokes still run each bin under plain node in a node_modules-shaped temp dir (now symlinking `ui/app-boot` too) and still assert the missing-config non-zero exit, per the "real entry path means the published artifact" defensive pattern. The [extract-example-app-packages Agent Note](../architecture/2026-06-20-extract-example-app-packages.md)'s bin-ownership facts are amended accordingly.
+
+## Alternatives considered
+
+### Why not keep the duplication?
+
+The bins were framed as independently-owned published artifacts, and a new package carries fixed overhead (manifest, README, tsconfig reference, publint surface) comparable to the deduplicated line count. But app-vs-app sharing was never weighed by the Agent Note that created the bins — it consolidated three example `start.ts` copies INTO the bins and stopped there; the drift was observed fact; and the coverage-gap argument is independent of the dedup argument: this was the only nontrivial runtime logic in the repo exempt from the per-file 100% gate. The recorded fallback (extracting only the pure logic into per-app modules) would have ended the exemption but kept two homes for the lore.
+
+## Consequences
+
+- A boot-glue change (a new guard, a resolution fix) lands once and both published bins inherit it; the bins cannot drift apart again.
+- `dsh-app-boot` stays dependency-light (cordis + the loader/include pair) — it is boot machinery, not app surface.
+- The bins' own files are near-trivial compositions; everything with branches lives under the coverage gate.

.agents/notes/archived/simplification/2026-07-04-share-app-bin-boot-glue.zh.md

@@ -0,0 +1,28 @@
+# Agent Note: 共享应用 bin 的启动胶水代码，而非维护两份副本
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-04-share-app-bin-boot-glue.md) | 中文
+
+## 问题
+
+stdio 和 ACP（Agent Client Protocol）两个 bin 各自重复了环境加载、fail-loud 处理、入口校验与启动逻辑，包括微妙的 Loader 失败行为。两份副本已经发生漂移，且位于自执行文件中、被排除在单元测试覆盖率之外，导致其导出的辅助函数无法被复用。
+
+## 决策
+
+辅助函数只存在一处：[`@deepseek-ai/dsh-app-boot`](../../../../packages/ui/app-boot)（`packages/ui/app-boot`，归入 `ui` 分组，因为 bin 是已发布产物，其运行时依赖本身也必须是已发布的包，而非 `support/`）。包含：`resolveConfigPath`（快照感知，两个 bin 共用的唯一路径解析器）、`loadEnv`、`installFailLoud`、`assertEntriesLoaded` 与 `boot`，每个函数都通过 bin 的诊断前缀参数化，并在其副作用 seam（warn sink、process slice）处支持注入，使单元测试套件能覆盖每个分支——包括 `boot()` 在进程内驱动真实 Loader、使用相对路径 specifier 配置的场景，既覆盖已稳定树的正常路径，也覆盖无 fiber 入口的拒绝路径。该包启用逐文件 100% 覆盖率门禁；Loader 失败的相关知识只有一个归属地。
+
+每个 `bin.ts` 都是在共享辅助函数之上加应用特有生命周期的精简自执行组合（ACP bin：重放模式环境变量跳过和 stdin EOF 释放；stdio bin：没有额外逻辑）。这些 bin 仍排除在覆盖率之外且不导出任何内容；已发布产物守卫保持不变——按照“真实入口路径即已发布产物”的防御模式，已构建 bin 冒烟仍在具有 node_modules 形状的临时目录中用纯 node 运行每个 bin（现在也会符号链接 `ui/app-boot`），并继续断言缺失配置时以非零状态退出。[提取示例应用包 Agent Note（agent 决策记录）](../architecture/2026-06-20-extract-example-app-packages.md)中的 bin 归属事实已据此修改。
+
+## 曾考虑的替代方案
+
+### 为何不保留重复？
+
+这些 bin 当时被定位为归属相互独立的已发布产物，而新包会带来固定开销（清单、README、tsconfig 引用、publint 表面），与去重的行数相当。但创建 bin 的 Agent Note 从未权衡应用间共享——它把三份示例 `start.ts` 副本合并进 bin 后便止步于此；漂移是已经观察到的事实；覆盖率缺口的理由也独立于去重理由：这是仓库中唯一免受逐文件 100% 门禁约束的非平凡运行时逻辑。记录的后备方案（只将纯逻辑提取到各应用模块）会结束豁免，但会继续让相关知识拥有两个归属。
+
+## 后果
+
+- 启动胶水代码的变更（新增守卫、修复路径解析）只需落地一次，两个已发布 bin 自动继承；bin 之间不会再次漂移。
+- `dsh-app-boot` 保持轻量依赖（cordis + loader/include 对）——它是启动机制，不是应用表面积。
+- bin 自身的文件几乎是平凡的组合；所有含分支的逻辑都在覆盖率门禁之下。

.agents/notes/archived/simplification/2026-07-04-trim-acp-bridge-unreachable-surface.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+2026-07-04-trim-acp-bridge-unreachable-surface.md: 2b0e6bba085f30959cd3c33362cd369ca7aec422
+2026-07-04-trim-acp-bridge-unreachable-surface.zh.md: ab924775588e61841f835bfe73ccae6d9886fd2a

.agents/notes/archived/simplification/2026-07-04-trim-acp-bridge-unreachable-surface.md

@@ -0,0 +1,29 @@
+# Agent Note: Trim unreachable ACP bridge surface — the branding knobs and the kind-sniffing fallback
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-04-trim-acp-bridge-unreachable-surface.zh.md)
+
+> The handshake-identity simplification remains current. The generic-card fallback was removed when [ACP became automation-only](2026-07-23-acp-automation-only-protocol.md); UI transports retain the provider-neutral presentation contract.
+
+## Problem
+
+Two pieces of `dsh-acp` surface were unreachable from any shipped configuration:
+
+1. **`AcpConfig.agentName` / `agentVersion`** (`packages/acp/acp/src/index.ts`). The shipped app package hands the bridge only its agent target (`packages/examples/acp-demo/src/index.ts`), so no leaf `cordis.yml` — the only production config surface — could set the knobs at all; they were settable solely by direct-mounting the bridge, which only a unit test did. Every snapshot expected output — the hook-matrix scenarios included — pins the schema defaults (`deepseek-harness-acp` / `0.0.1`). The pair also carried a live `TODO(double-default)`: the literals existed twice (schema `.default(...)` plus `??` fallbacks), with the TODO asking to pick one home.
+2. **The `toolKindFor` name heuristic** (same file) special-cased `bash*`/`read*`/`write`/`edit*` tool names in the generic-fallback path. Since the [render-intent union](../architecture/2026-07-02-tool-render-intent-union.md), every first-party tool those arms matched ships its own `presentCall` carrying its kind, and the presenter-less production tools (`subagent`, `subagent_fork`) fell through to `other` anyway. The arms were production-reachable only when a tool declined to present its own call — a `presentCall` that THROWS (the containment fallback), or model arguments that fail the tool's schema so `defineTool`'s `presentCall` wrapper returns `undefined` (e.g. a `bash` call missing the required `description`) — and the bridge's own module doc states the design rule the heuristic violated: "the bridge never special-cases tool names".
+
+## Decision
+
+Hardcode the existing handshake identity `{ name: 'deepseek-harness-acp', version: '0.0.1' }` at initialization and remove the unreachable config fields and duplicate defaults. The original implementation also replaced `toolKindFor` with neutral `'other'` at both presenter fallbacks; ACP no longer projects tool cards, so that fallback has left the transport entirely. Initialize tests and snapshots pin the handshake.
+
+## Alternatives considered
+
+### Why not keep them?
+
+Branding can return when the app package exposes it to deployments. Inferring presentation from unknown tool names violates the render-intent contract; neutral fallback cards also preserve raw input for malformed calls and broken presenters.
+
+## Consequences
+
+The bridge exposes no branding knobs. UI transports own generic presentation fallback without tool-name inference, while ACP carries no tool-card surface.

.agents/notes/archived/simplification/2026-07-04-trim-acp-bridge-unreachable-surface.zh.md

@@ -0,0 +1,29 @@
+# Agent Note: 裁剪不可达的 ACP 桥接层表面——品牌配置项与 kind 嗅探回退
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-04-trim-acp-bridge-unreachable-surface.md) | 中文
+
+> 握手标识简化仍然有效。通用卡片回退已随 [ACP 转为仅面向自动化](2026-07-23-acp-automation-only-protocol.md)一并移除；UI 传输层保留提供方无关的展示契约。
+
+## 问题
+
+`dsh-acp` 有两处对外表面在任何已交付的配置中都不可达：
+
+1. **`AcpConfig.agentName` / `agentVersion`**（`packages/acp/acp/src/index.ts`）。已发布应用包只向 bridge 传递其 agent 的提供方/模型目标（`packages/examples/acp-demo/src/index.ts`），因此没有任何叶子 `cordis.yml`——唯一的生产配置表面——能够设置这些配置项；只有直接挂载 bridge 才能设置它们，而这种做法只存在于一个单元测试中。每份快照预期输出——包括钩子矩阵场景——都固定 schema 默认值（`deepseek-harness-acp` / `0.0.1`）。这对配置项还带有一个尚未解决的 `TODO(double-default)`：字面量存在两次（schema `.default(...)` 加 `??` 后备值），TODO 要求为它们选择一个归属。
+2. **`toolKindFor` 名称启发式**（同一文件）在通用回退路径中对 `bash*`/`read*`/`write`/`edit*` 工具名做了特殊处理。自[render-intent 联合类型](../architecture/2026-07-02-tool-render-intent-union.md)以来，这些分支匹配到的每个第一方工具都自带 `presentCall` 并携带其 kind，而没有 presenter 的生产工具（`subagent`、`subagent_fork`）本来就落入 `other`。这些分支只有在工具拒绝自行呈现调用时才在生产中可达：`presentCall` 抛出异常（容错回退），或模型参数未通过工具 schema 导致 `defineTool` 的 `presentCall` 包装层返回 `undefined`（例如 `bash` 调用缺少必需的 `description`）。而桥接层自身的模块文档明确声明了该启发式所违反的设计规则："桥接层绝不对工具名做特殊处理"。
+
+## 决策
+
+在初始化时硬编码现有的握手标识 `{ name: 'deepseek-harness-acp', version: '0.0.1' }`，移除不可达的配置字段与重复默认值。最初的实现还在两个 presenter 回退处将 `toolKindFor` 替换为中性的 `'other'`；ACP 不再投影工具卡片，因此该回退已完全离开传输层。初始化测试和快照固定握手标识。
+
+## 曾考虑的替代方案
+
+### 为什么不保留？
+
+品牌配置可以在 app 包将其暴露给部署环境时再回来。从未知工具名推断呈现方式违反了 render-intent 契约；中性回退卡片还能为格式错误的调用和损坏的 presenter 保留原始输入。
+
+## 后果
+
+桥接层不暴露品牌配置项。UI 传输层拥有不做工具名推断的通用展示回退，而 ACP 不承载任何工具卡片表面。

.agents/notes/archived/simplification/2026-07-12-drop-unconsumed-skill-provider-events.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+2026-07-12-drop-unconsumed-skill-provider-events.md: 88ce8d01dfbae8347e8671b52597f45735d6890e
+2026-07-12-drop-unconsumed-skill-provider-events.zh.md: ac4e3ff0277867e3b68d9b5c8f999b8819166ae4

.agents/notes/archived/simplification/2026-07-12-drop-unconsumed-skill-provider-events.md

@@ -0,0 +1,30 @@
+# Agent Note: Drop unconsumed skill provider events
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-12-drop-unconsumed-skill-provider-events.zh.md)
+
+## Problem
+
+Two skill-registry notifications are produced but have no production listener. The generated producer/consumer matrix and exact event-name searches find only declarations, emit sites, tests, generated catalogs, and prose for `skill/provider-added` and `skill/provider-removed`.
+
+Skill discovery reads the current provider map on demand, provider registration synchronously clears completed catalogs, and the post-await revision check prevents stale discovery from entering the cache. No sibling plugin waits for a skill provider through these events, unlike the live `subagent/provider-added` consumer that tolerates concurrent sibling loading.
+
+`tools/change` and `system-prompt/change` are explicitly outside this proposal. Existing simplification decisions retain them as intentional observation points for live tool and prompt UIs, and self-referential mounted plugins already use `tools/change`. This proposal also leaves `subagent/provider-added`/`removed` unchanged because `tool-subagent` has a production lifecycle consumer.
+
+## Decision
+
+The skill registry declares and emits no provider-membership events. Provider registration and disposal remain direct effect-owned state changes that synchronously invalidate completed catalogs; lookup and discovery read the current provider map on demand. Tests observe cleanup through provider lookup and collected output rather than lifecycle notifications.
+
+The generated event catalog, API catalog, and producer/consumer matrix omit the deleted notifications. The skill-system Agent Note and package documentation describe registration through its direct effect-owned state and cache-invalidation contract.
+
+## Alternatives considered
+
+**Keep skill-provider notifications for future plugins.** A third-party plugin could observe provider availability, but direct provider registration and on-demand lookup are the extension contract; no current consumer needs a push signal. If a future sibling-load race appears, it can introduce a notification with the identity and readiness semantics that consumer requires, as the subagent registry did.
+
+## Consequences
+
+The generated event matrix contains no row for `skill/provider-added` or `skill/provider-removed`. Skill discovery, direct runtime registration, provider effect rollback/disposal, cache invalidation, and registry lookup cleanup remain; listener-triggered rollback disappears with the events. `tools/change`, `system-prompt/change`, and the consumed subagent provider lifecycle events are unchanged.
+
+Pre-release consumers lose skill-provider observation points while retaining both ways to contribute skills: direct runtime registration and provider registration. A future consumer that needs live provider availability must add a purpose-built notification with the identity and readiness semantics it actually requires.

.agents/notes/archived/simplification/2026-07-12-drop-unconsumed-skill-provider-events.zh.md

@@ -0,0 +1,30 @@
+# Agent Note: 移除无消费方的 skill 提供方事件
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-12-drop-unconsumed-skill-provider-events.md) | 中文
+
+## 问题
+
+skill（技能）注册表产出两个通知事件，但没有生产环境的监听方。生成的生产者/消费方矩阵以及对事件名的精确搜索表明，`skill/provider-added` 与 `skill/provider-removed` 仅出现在声明、emit 站点、测试、生成的 catalog 和行文中。
+
+skill 发现按需读取当前的提供方映射表，提供方注册时同步清除已完成的 catalog，而 await 后的版本检查阻止了陈旧的发现结果进入缓存。没有兄弟插件通过这些事件等待 skill 提供方——与之形成对比的是活跃的 `subagent/provider-added` 消费方，它容忍兄弟并发加载。
+
+`tools/change` 与 `system-prompt/change` 明确不在本提案范围内。既有的简化决策将它们保留为面向实时工具和提示词 UI 的有意观测点，且自引用的已挂载插件已在使用 `tools/change`。本提案同样不改动 `subagent/provider-added`/`removed`，因为 `tool-subagent` 有生产环境的生命周期消费方。
+
+## 决策
+
+skill 注册表不再声明和 emit 提供方成员变更事件。提供方的注册与 dispose（资源释放）仍为 effect 所有的直接状态变更，同步使已完成的 catalog 失效；查找与发现按需读取当前提供方映射表。测试通过提供方查找和收集到的输出来观察清理行为，而非依赖生命周期通知。
+
+生成式事件目录、API 目录和生产者/消费方矩阵均不再包含已删除通知。skill system Agent Note（agent 决策记录）和包文档改为通过其由 effect 直接拥有的状态与 cache 失效契约描述注册。
+
+## 曾考虑的替代方案
+
+**为未来插件保留 skill 提供方通知。** 第三方插件可能想观察提供方的可用性，但直接提供方注册与按需查找才是扩展契约；当前没有消费方需要推送信号。如果将来出现兄弟加载竞态，可以像 subagent 注册表那样，引入一个带有该消费方实际所需的身份与就绪语义的通知。
+
+## 后果
+
+生成的事件矩阵中不再有 `skill/provider-added` 或 `skill/provider-removed` 的行。skill 发现、直接运行时注册、提供方 effect 回滚/dispose、缓存失效与注册表查找清理保持不变；监听方触发的回滚随事件一起消失。`tools/change`、`system-prompt/change` 以及已被消费的 subagent 提供方生命周期事件不受影响。
+
+预发布消费方失去 skill 提供方观测点，但仍保留两种贡献 skill 的方式：直接运行时注册与提供方注册。未来若有消费方需要实时的提供方可用性信息，必须新增一个带有其实际所需的身份与就绪语义的专用通知。

.agents/notes/archived/simplification/2026-07-12-prune-unused-web-seam-fields.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+2026-07-12-prune-unused-web-seam-fields.md: 4ad6dbb2efe314977d5e82f49e849dda9408146d
+2026-07-12-prune-unused-web-seam-fields.zh.md: 58706f1248132606d3d2d27603f7283eae310f66

.agents/notes/archived/simplification/2026-07-12-prune-unused-web-seam-fields.md

@@ -0,0 +1,28 @@
+# Agent Note: Prune unused web seam fields
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-12-prune-unused-web-seam-fields.zh.md)
+
+## Problem
+
+The web capability carries request/result/status values that every shipped implementation populates but no production consumer reads. `WebSearchResult.providerId` and `query` and `WebFetchResult.providerId` are result echoes; `tool-web` formats only content/sources/truncation or final URL/status/body/truncation, and no other runtime reads them. Search providers return `WebProviderStatus.reason`, but resolution checks only `available` and intentionally emits a generic unavailable diagnostic.
+
+`WebFetchRequest.timeoutMs` is likewise never set by a production caller. `tool-web` supplies only the URL, uses the tool definition's timeout plus `exec.signal` for the caller deadline, and relies on the local provider's configured default as a backstop. The unused per-request override forces `web-fetch-local` to expose `maxTimeoutMs`, clamp two timeout sources, and document/test precedence no product path can select. `WebExecContext` is another one-field wrapper: every caller allocates `{ signal }` and every provider immediately unwraps `exec?.signal`; no second execution-control field exists.
+
+## Decision
+
+The web seam omits the search/fetch `providerId` result echoes and search `query` echo; callers already own the request and provider selection. Providers expose availability as a boolean-returning method. Fetch requests have no per-request timeout or `maxTimeoutMs` clamp; the local provider retains its configurable default timeout and the tool retains its own deadline. Provider methods receive a direct optional `AbortSignal` instead of a one-field `WebExecContext` wrapper.
+
+All web implementations and the model-facing tool use the smaller contract. The interface/implementation/consumer package split, provider selection, source citations, final-URL/status data, truncation reporting, and safety limits remain.
+
+## Alternatives considered
+
+**Keep self-describing results, per-request deadlines, and an extensible execution-context object.** Result echoes can help generic telemetry, a request timeout can help trusted programmatic callers, and the wrapper leaves room for future controls. No such consumer/second field exists; carrying duplicate identity, a second deadline policy, and wrap/unwrap plumbing through every provider makes the current contract harder to implement and explain. If telemetry or per-call budget control arrives, it should define which deadline wins, where provider identity is observed, and whether multiple controls justify a context object.
+
+## Consequences
+
+Every retained web request/result field is consumed by production code or required to execute the provider request. Tool-visible search/fetch output, provider fallback, abort behavior, the configured timeout backstop, truncation, and citations remain covered without a request-timeout precedence branch or execution-context wrapper.
+
+Pre-release programmatic callers lose result provenance echoes and per-request fetch deadlines. The provider still has a deployment-configurable timeout and respects cancellation, so the simplification removes configurability rather than a safety bound.

.agents/notes/archived/simplification/2026-07-12-prune-unused-web-seam-fields.zh.md

@@ -0,0 +1,28 @@
+# Agent Note: 裁剪 web seam 中未使用的字段
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-12-prune-unused-web-seam-fields.md) | 中文
+
+## 问题
+
+web 能力携带的 request/result/status 值，虽然每个已交付的实现都会填充，但没有任何生产环境的消费方读取它们。`WebSearchResult.providerId`、`query` 与 `WebFetchResult.providerId` 是结果回显；`tool-web` 只格式化 content/sources/truncation 或最终 URL/status/body/truncation，没有其他运行时读取这些字段。搜索提供方返回 `WebProviderStatus.reason`，但可用性检查只看 `available`，并有意输出一条通用的不可用诊断信息。
+
+`WebFetchRequest.timeoutMs` 同样从未被生产调用方设置。`tool-web` 只提供 URL，使用工具定义的 timeout 加 `exec.signal` 作为调用方截止时间，并依赖本地提供方的配置默认值作为兜底。这个未使用的逐请求覆盖迫使 `web-fetch-local` 暴露 `maxTimeoutMs`、对两个 timeout 来源做 clamp，并为没有任何产品路径能选中的优先级规则编写文档和测试。`WebExecContext` 则是另一个单字段包装层：每个调用方分配 `{ signal }`，每个提供方立即解包 `exec?.signal`；不存在第二个执行控制字段。
+
+## 决策
+
+web seam 移除搜索/抓取结果中的 `providerId` 回显和搜索的 `query` 回显；调用方本身已持有请求和提供方选择信息。提供方以返回布尔值的方法暴露可用性。抓取请求不再有逐请求 timeout 或 `maxTimeoutMs` clamp；本地提供方保留其可配置的默认 timeout，工具保留自身的截止时间。提供方方法直接接收一个可选的 `AbortSignal`，而非单字段的 `WebExecContext` 包装层。
+
+所有 web 实现与面向模型的工具使用更精简的契约。接口/实现/消费方的包（package）拆分、提供方选择、来源引用、最终 URL/状态数据、截断报告与安全限制保持不变。
+
+## 曾考虑的替代方案
+
+**保留自描述结果、逐请求截止时间与可扩展的执行上下文对象。** 结果回显可以帮助通用遥测，请求级 timeout 可以帮助受信的程序化调用方，包装层则为未来的控制字段留出空间。但目前不存在这样的消费方或第二个字段；在每个提供方中携带重复的身份标识、第二套截止时间策略以及包装/解包管道，使当前契约更难实现和解释。如果遥测或逐调用预算控制到来，届时应当定义哪个截止时间优先、在哪里观测提供方身份，以及多个控制字段是否足以证明需要一个上下文对象。
+
+## 后果
+
+保留下来的每个 web request/result 字段，要么被生产代码消费，要么是执行提供方请求所必需的。工具可见的搜索/抓取输出、提供方回退、中止行为、可配置的 timeout 兜底、截断与引用仍然被覆盖，无需请求级 timeout 优先级分支或执行上下文包装层。
+
+预发布阶段的程序化调用方失去了结果来源回显和逐请求的抓取截止时间。提供方仍具备部署级可配置 timeout 并尊重取消信号，因此这次精简移除的是可配置性，而非安全边界。

.agents/notes/archived/simplification/2026-07-19-retire-subagent-mock-package.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+2026-07-19-retire-subagent-mock-package.md: 9fce0d2f8ea20b4f31e2042acba4df34152e3201
+2026-07-19-retire-subagent-mock-package.zh.md: d82650c9e74f8fff1386185f0930762d21a7243f

.agents/notes/archived/simplification/2026-07-19-retire-subagent-mock-package.md

@@ -0,0 +1,35 @@
+# Agent Note: Retire the standalone subagent mock package
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-19-retire-subagent-mock-package.zh.md)
+
+## Problem
+
+`@deepseek-ai/dsh-subagent-mock` was a configurable test double packaged as a workspace plugin. Its only external consumers were the `tool-subagent` unit suite and the tool-catalog generator; no runtime package, example, snapshot configuration, or real provider loaded it.
+
+That narrow fixture carried a manifest, exports, peer and development dependencies, project references, package README obligations, Loader composition tests, module-graph membership, and documentation exceptions. The tool-catalog generator mounted it only to make production consumers register their schemas and never executed a child.
+
+## Decision
+
+The standalone package is deleted. Its scripted child behavior now lives in `packages/subagent/tool-subagent/tests/scripted-provider.ts`, where tests mount the real `SubagentService`, provider registry, tool implementation, and task runtime while replacing only the nondeterministic child boundary.
+
+The local fixture retains deterministic replies, structured results, stop reasons, cancellation before and after publication, conversation-inheritance descriptors, and effect-scoped disposal. Package-specific Schemastery and Loader-export tests disappear because the fixture is no longer a deployable plugin.
+
+The tool-catalog generator registers a minimal local `SubagentProvider` descriptor before mounting `ToolSubagent` or the workflow engine. The descriptor cannot start a child; it exists only to satisfy production load-time dependencies while harvesting schemas from the real consumers.
+
+Workspace project references, package dependencies, lockfile entries, graph metadata, support-package prose, config-catalog entries, and README gate exceptions no longer name the retired package.
+
+## Alternatives considered
+
+**Keep a reusable mock package for future tests.** Reuse never materialized outside one test file and one generator. A future second behavioral consumer can extract a shared fixture after its contract is known; pre-packaging it made test infrastructure look like a supported backend.
+
+**Generate subagent schemas without mounting production consumers.** Hand-constructing or importing schemas would weaken the catalog check that the real registry and tool composition expose the documented shape. A minimal provider descriptor preserves that check without carrying executable fake-backend behavior.
+
+## Consequences
+
+- The workspace has one fewer deployable package and no test-only node in the capability or module graphs.
+- `tool-subagent` tests retain foreground, background-task, lifecycle, cancellation, reply, stop-reason, and structured-result coverage through production services.
+- Tool-catalog output remains generated from production registrations and is byte-for-byte unchanged.
+- Runtime and example packages gain no dependency on test fixtures.

.agents/notes/archived/simplification/2026-07-19-retire-subagent-mock-package.zh.md

@@ -0,0 +1,35 @@
+# Agent Note: 撤销独立的 subagent mock 包
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-19-retire-subagent-mock-package.md) | 中文
+
+## 问题
+
+`@deepseek-ai/dsh-subagent-mock` 曾是一个以工作区插件形式发布的可配置测试替身。它仅有两个外部消费方：`tool-subagent` 单元测试和工具目录生成器；运行时包、示例、快照配置和真实提供方都不会加载它。
+
+这个用途狭窄的 fixture（测试前置数据）需要维护 manifest（元数据清单）、导出、对等依赖（peer dependency）与开发依赖、项目引用、包（package）README 契约、Loader 组合测试、模块图成员关系以及文档例外。工具目录生成器挂载它，只是为了让生产消费方注册 schema，并不会执行子 agent。
+
+## 决策
+
+删除独立包。脚本化子 agent 行为现位于 `packages/subagent/tool-subagent/tests/scripted-provider.ts`；测试挂载真实的 `SubagentService`、提供方注册表、工具实现和任务运行时，只替换具有不确定性的子 agent 边界。
+
+本地 fixture 保留确定性回复、结构化结果、停止原因、发布前后的取消、对话继承描述和作用域化的 dispose（资源释放）覆盖。由于 fixture 不再是可部署插件，删除包专用的 Schemastery 与 Loader 导出测试。
+
+工具目录生成器在挂载 `ToolSubagent` 或工作流引擎之前，注册一个最小本地 `SubagentProvider` 描述。该描述无法启动子 agent；它只用于满足生产消费方的加载时依赖，同时从真实消费方提取 schema。
+
+工作区项目引用、包依赖、锁文件条目、图元数据、支持包说明、配置目录条目和 README 门禁例外不再提及已撤销的包。
+
+## 备选方案
+
+**为未来测试保留可复用 mock 包。** 除一个测试文件和一个生成器外，复用需求始终没有出现。未来产生第二个行为消费方时，可以在共享契约明确后再提取 fixture；提前将其打包会使测试基础设施看起来像受支持的后端。
+
+**不挂载生产消费方，直接生成 subagent schema。** 手工构造或直接导入 schema，会削弱目录门禁对真实注册表与工具组合是否公开文档结构的校验。最小提供方描述能保留该校验，而无需携带可执行的虚假后端行为。
+
+## 影响
+
+- 工作区减少一个可部署包，能力图与模块图也不再包含测试专用节点。
+- `tool-subagent` 测试继续通过生产服务覆盖前台、后台任务、生命周期、取消、回复、停止原因和结构化结果。
+- 工具目录输出仍根据生产注册生成，并保持字节级一致。
+- 运行时包与示例包都不会依赖测试 fixture。

.agents/notes/archived/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+2026-07-19-use-one-session-surface-manager.md: 741e949ee04150cdee3328a2ff04d79688bd484d
+2026-07-19-use-one-session-surface-manager.zh.md: 87502c600c6c2d546ad728819ebbf08f7e55bda3

.agents/notes/archived/simplification/2026-07-19-use-one-session-surface-manager.md

@@ -0,0 +1,38 @@
+# Agent Note: Use one surface manager per session
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-19-use-one-session-surface-manager.zh.md)
+
+## Problem
+
+`Session` maintained two `SurfaceManager` instances over the same append-only event log. One validated seed and append candidates, while a second lazy instance independently folded committed events for `session.surface`, derived messages, compaction, and workspace context. Once the public surface had been read, every later event advanced duplicate node and replacement-generation state without creating a separate authority or failure boundary.
+
+## Decision
+
+Each `Session` owns one eagerly constructed `SurfaceManager`. Seed and append acceptance call `validateNext()` on that manager before committing an event, and `session.surface` returns the same object through this readonly contract:
+
+```ts
+export interface SessionSurface {
+  readonly nodes: readonly number[]
+  readonly replaceGeneration: number
+}
+```
+
+Candidate validation remains atomic. `validateNext()` may synchronize committed log entries, but it only plans the uncommitted candidate. The candidate enters manager state after `log.push()` and the next delta synchronization, so surface validation failures and pre-commit `internal/dispatch` vetoes leave no phantom node or replacement generation.
+
+`foldSurface()` remains the detached full-log replay function for offline validation and reconstruction. It uses the same transitions and agrees with the live manager for every committed prefix without sharing mutable state.
+
+## Alternatives considered
+
+**Keep acceptance and projection state separate.** Separate instances appeared to isolate public reads from validation, but callers already receive borrowed surface state and the declared readonly contract prevents ordinary mutation. Duplicating the manager was not a runtime trust boundary.
+
+**Recompute the public surface from the full log on every access.** This removed duplicate cached state but gave up incremental derivation and made repeated request construction scale with complete session history.
+
+## Consequences
+
+- Acceptance, `session.surface`, derived messages, compaction, and workspace context observe one incremental state.
+- `Session.surface` exposes no validation method, while its object identity and borrowed readonly node array remain stable.
+- A hostile cast can still corrupt borrowed state; JavaScript callers that deliberately bypass the readonly contract remain outside the supported same-process boundary.
+- Surface, seed, dispatch-veto, request-reconstruction, compaction, and workspace-context tests exercise the shared manager and detached replay paths.

.agents/notes/archived/simplification/2026-07-19-use-one-session-surface-manager.zh.md

@@ -0,0 +1,38 @@
+# Agent Note: 每个会话只使用一个表层管理器
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-19-use-one-session-surface-manager.md) | 中文
+
+## 问题
+
+`Session` 曾针对同一份仅追加事件日志维护两个 `SurfaceManager` 实例。一个实例负责校验种子事件和追加候选事件，另一个延迟创建的实例则独立折叠已提交事件，供 `session.surface`、派生消息、压缩（compaction）和工作区上下文使用。一旦读取公共表层，之后的每个事件都会推进两份重复的节点状态与替换代数状态，却没有形成独立真源或失败边界。
+
+## 决策
+
+每个 `Session` 主动创建并只持有一个 `SurfaceManager`。种子事件与追加事件的接纳流程在提交事件之前调用该管理器的 `validateNext()`，`session.surface` 则通过以下只读契约返回同一个对象：
+
+```ts
+export interface SessionSurface {
+  readonly nodes: readonly number[]
+  readonly replaceGeneration: number
+}
+```
+
+候选事件校验仍保持原子性。`validateNext()` 可以同步已提交的日志事件，但对尚未提交的候选事件只制定变更计划。候选事件在 `log.push()` 之后、下一次增量同步时才进入管理器状态，因此表层校验失败或提交前 `internal/dispatch` 否决都不会留下虚假节点或替换代数。
+
+`foldSurface()` 仍是离线校验与重建使用的分离式完整日志回放函数。它使用相同的状态转换，并且对每个已提交前缀都与活跃管理器一致，但不共享可变状态。
+
+## 备选方案
+
+**继续分离接纳状态与投影视图。** 两个独立实例看似能够隔离公共读取和校验，但调用方取得的本来就是借用的表层状态，声明的只读契约会阻止普通修改。复制管理器并不能构成运行时信任边界。
+
+**每次读取都根据完整日志重新计算公共表层。** 该方案能消除重复缓存状态，但会放弃增量派生，使每次请求构造都随完整会话历史增长。
+
+## 影响
+
+- 接纳流程、`session.surface`、派生消息、压缩和工作区上下文观察同一份增量状态。
+- `Session.surface` 不暴露校验方法，同时保持对象标识和借用的只读节点数组稳定。
+- 恶意类型断言仍可破坏借用状态；刻意绕过只读契约的 JavaScript 调用方不属于受支持的同进程边界。
+- 表层、种子、调度否决、请求重建、压缩和工作区上下文测试覆盖共享管理器与分离回放路径。

.agents/notes/archived/simplification/2026-07-21-tui-remove-cancel-command.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+2026-07-21-tui-remove-cancel-command.md: eba4ada458cd7926cc06130d081b669da514fe79
+2026-07-21-tui-remove-cancel-command.zh.md: 9954af56682591287abc955d9f2485f02e1ce6b8

.agents/notes/archived/simplification/2026-07-21-tui-remove-cancel-command.md

@@ -0,0 +1,26 @@
+# Agent Note: Drop the TUI `/cancel` slash command
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-21-tui-remove-cancel-command.zh.md)
+
+## Problem
+
+The TUI exposed two identical ways to cancel a running turn: the `Esc` (and `Ctrl+C`) keybinding and a `/cancel` slash command. Both called `agent.cancel('cancelled from terminal')` with the same reason; when idle, `/cancel` only printed a "The agent is already idle." notice while the keybindings stayed silent. The running status line already advertises the keybinding (`Enter sends steering, Esc cancels`), and cancelling by keystroke needs no editor submission, so the slash command was a second, less discoverable path to the same effect — surface area with no behavior of its own.
+
+## Decision
+
+`/cancel` is removed. Cancelling a running turn is a keybinding-only affordance (`Esc`, or `Ctrl+C` while running), which the status-line hint and the `/help` shortcut list already document. The `baseCommands` autocomplete entry, the `/help` command line, the `case '/cancel'` branch in the editor submit handler, and the "already idle" notice it owned are gone; every other slash command (`/help`, `/clear`, `/reasoning`, `/tools`, `/redraw`, `/reload`, `/resume`, `/exit`, `/skill:<name>`) is unchanged. Typing `/cancel` now falls through to the generic `Unknown command:` warning like any other unrecognized slash input.
+
+## Alternatives considered
+
+**Keep `/cancel` as a discoverability alias** — rejected: the running status line and `/help` both name `Esc`, so a typed alias adds a maintained code path and a per-idle-state notice for an action a single keystroke already performs more directly. No consumer needed the editor-submission route to cancellation.
+
+## Testing
+
+`packages/ui/tui/tests/tui.spec.ts` asserts `agent.cancelled` contains `'cancelled from terminal'`, driven by the `Esc`/`Ctrl+C` keystrokes in that turn — the sole cancel affordance. The `errors-and-help` and `disposed-terminal` snapshots pin the `/help` line without `/cancel`; per-file coverage on `packages/ui/tui/src` stays at 100%.
+
+## Consequences
+
+There is no way to cancel a turn by editor submission; cancellation is keybinding-only. This is a net removal of a redundant path and its idle-state notice, matching the single-primitive shape the rest of the stop surface already follows ([public stop surface](2026-06-20-public-agent-stop-surface.md)). Restoring a typed cancel would return with the autocomplete entry, the submit-handler branch, and its own test.

.agents/notes/archived/simplification/2026-07-21-tui-remove-cancel-command.zh.md

@@ -0,0 +1,26 @@
+# Agent Note: Drop the TUI `/cancel` slash command
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-21-tui-remove-cancel-command.md) | 中文
+
+## Problem
+
+TUI 提供了两条完全相同的取消运行中轮次的方式：`Esc`（以及 `Ctrl+C`）键位绑定，和一条 `/cancel` 斜杠命令。两者都以相同的原因调用 `agent.cancel('cancelled from terminal')`；空闲时 `/cancel` 只打印一条 "The agent is already idle." 通知，而键位绑定保持静默。运行状态行本就标示了该键位绑定（`Enter sends steering, Esc cancels`），且按键取消无需提交编辑器，因此这条斜杠命令只是通往同一效果的第二条、且更难被发现的路径——一块本身不含任何行为的界面。
+
+## Decision
+
+`/cancel` 已移除。取消运行中的轮次是一项仅由键位绑定提供的能力（`Esc`，或运行中的 `Ctrl+C`），状态行提示与 `/help` 快捷键清单已对其作出说明。`baseCommands` 自动补全条目、`/help` 命令行、编辑器提交处理函数中的 `case '/cancel'` 分支，以及它拥有的 "already idle" 通知都已删去；其余每一条斜杠命令（`/help`、`/clear`、`/reasoning`、`/tools`、`/redraw`、`/reload`、`/resume`、`/exit`、`/skill:<name>`）保持不变。键入 `/cancel` 会像任何其他无法识别的斜杠输入一样，落入通用的 `Unknown command:` 警告。
+
+## Alternatives considered
+
+**保留 `/cancel` 作为便于发现的别名。** 否决：运行状态行与 `/help` 都已标示 `Esc`，因此一个键入式别名会为一项单个按键已能更直接完成的操作，增加一条需维护的代码路径和一条逐空闲状态的通知。没有任何消费方需要经由编辑器提交来触发取消。
+
+## Testing
+
+`packages/ui/tui/tests/tui.spec.ts` 断言 `agent.cancelled` 包含 `'cancelled from terminal'`，由该轮次中的 `Esc`/`Ctrl+C` 按键驱动——这是唯一的取消能力。`errors-and-help` 与 `disposed-terminal` 快照固定了不含 `/cancel` 的 `/help` 行；`packages/ui/tui/src` 的逐文件覆盖率维持在 100%。
+
+## Consequences
+
+无法再经由编辑器提交取消一个轮次；取消仅由键位绑定提供。这是对一条冗余路径及其空闲状态通知的净移除，与其余停止能力已遵循的单一原语形态一致（[public stop surface](2026-06-20-public-agent-stop-surface.md)）。若要恢复键入式取消，需连同自动补全条目、提交处理函数分支及其专属测试一并回归。

.agents/notes/archived/simplification/2026-07-21-tui-todo-write-opt-in.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+2026-07-21-tui-todo-write-opt-in.md: fd2ad9bb89bd20ffddf4d509e427a34c5ec0cf2b
+2026-07-21-tui-todo-write-opt-in.zh.md: 5b1a7f19a48c87686cfc2052d4ad19ed45ab1fb9

.agents/notes/archived/simplification/2026-07-21-tui-todo-write-opt-in.md

@@ -0,0 +1,28 @@
+# Agent Note: Ship the TUI without `todo_write`; keep it a one-line opt-in
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-21-tui-todo-write-opt-in.zh.md)
+
+## Problem
+
+The shipped tui-agent `cordis.yml` loaded `@deepseek-ai/dsh-tool-todo`, exposing `todo_write` by default. The tool is a task-tracking convenience, not a core coding affordance like `bash` or the `read`/`write`/`edit` fs tools; most TUI sessions never call it, yet shipping it enlarges the wire tool list and system prompt for every turn. Meanwhile the TUI's plan rendering is event-driven: `packages/ui/tui/src/index.ts` listens for the `todo/write` session event and `TodoComponent.render` returns nothing when the list is empty, so the front door already tolerates the tool being absent or present with no runtime coupling to the plugin.
+
+## Decision
+
+The tui-agent `cordis.yml` no longer loads `tool-todo`; `todo_write` is opt-in. The `code-mode.cordis.yml` overlay inherits the base composition, so its generated SDK drops `todo_write` too. Enabling it is one entry — add `@deepseek-ai/dsh-tool-todo` to `cordis.yml` (or a `~/.dsh` personal overlay) — after which the model logs the whole-list `todo/write` snapshot and the TUI renders the plan, unchanged. The `TodoItem` type and the `todo/write` event stay in `@deepseek-ai/dsh-session` and the TUI's plan rendering stays wired, so both the default (disabled) and opt-in (enabled) paths are first-class. The sibling acp-agent, headless-agent, and jsonrpc-agent examples still ship the tool.
+
+## Alternatives considered
+
+**Keep `todo_write` in the shipped TUI default** — rejected: it is an opt-in convenience, not a core tool, and shipping it spends every turn's tool-list and prompt budget on a feature most sessions ignore. The examples that still ship it retain the plugin's real-composition coverage.
+
+**Drop the TUI's plan rendering and todo tests along with the default entry** — rejected: the requirement is to support both the enabled and disabled cases, and the event-driven `TodoComponent` already renders plans with zero plugin coupling, so deleting it would discard a working capability for no gain. The enabled path keeps dedicated coverage instead.
+
+## Testing
+
+`examples/tui-agent/tests/tui.snapshot.ts` mounts `ToolTodo` only when a scenario sets `enableTodo`: only the `todo-plan` scenario does (the enabled-path proof, whose `session.jsonl`/`terminal.expected.txt` pin the rendered plan), while every other scenario runs the default todo-free composition. `tests/harness.ts` makes `ToolTodo` a `todo` opt-in that only `tests/todo-write.e2e.ts` sets, so the with-key todo e2e still drives the real tool while the other suites match the shipped stack. The keyless `tests/tui-keyless-smoke.e2e.ts` boots the real `cordis.yml` and asserts nothing about todo, so the default boot is unaffected.
+
+## Consequences
+
+The default TUI wire tool list and system prompt shrink by one tool; a session that wants task tracking adds one plugin entry. `examples/tui-agent/composition.md` (regenerated) and its leaf-entry table no longer list `tool-todo`, and the curated summary in `scripts/gen-doc-graphs.ts` drops it. The `@deepseek-ai/dsh-tool-todo` package is unchanged and still shipped by the acp/headless/jsonrpc examples, so its coverage requirement is met there. Restoring the default would re-add the one `cordis.yml` entry and flip the snapshot/harness opt-in flags back on.

.agents/notes/archived/simplification/2026-07-21-tui-todo-write-opt-in.zh.md

@@ -0,0 +1,28 @@
+# Agent Note: Ship the TUI without `todo_write`; keep it a one-line opt-in
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-21-tui-todo-write-opt-in.md) | 中文
+
+## Problem
+
+出厂的 tui-agent `cordis.yml` 加载了 `@deepseek-ai/dsh-tool-todo`，默认向模型暴露 `todo_write`。这个工具是一项任务追踪的便利功能，而非像 `bash` 或 `read`/`write`/`edit` 文件系统工具那样的核心编码能力；多数 TUI 会话从不调用它，但出厂加载它会让每一轮的协议工具列表和系统提示词都随之变大。而 TUI 的计划渲染是事件驱动的：`packages/ui/tui/src/index.ts` 监听 `todo/write` 会话事件，`TodoComponent.render` 在列表为空时不返回任何内容，因此这个入口本就能容忍该工具的缺席或存在，与该插件没有任何运行时耦合。
+
+## Decision
+
+tui-agent `cordis.yml` 不再加载 `tool-todo`；`todo_write` 改为可选启用。`code-mode.cordis.yml` 覆盖配置继承基础组合，因此它生成的 SDK 同样不再包含 `todo_write`。启用它只需一条配置项——把 `@deepseek-ai/dsh-tool-todo` 加入 `cordis.yml`（或 `~/.dsh` 的个人覆盖配置）——此后模型照旧记录整份清单的 `todo/write` 快照，TUI 照旧渲染该计划。`TodoItem` 类型与 `todo/write` 事件仍留在 `@deepseek-ai/dsh-session`，TUI 的计划渲染也保持接线，因此默认（禁用）与可选启用（启用）两条路径都是一等公民。同类的 acp-agent、headless-agent、jsonrpc-agent 示例仍然出厂携带该工具。
+
+## Alternatives considered
+
+**在出厂的 TUI 默认配置中保留 `todo_write`。** 否决：它是一项可选启用的便利功能，而非核心工具，出厂加载它会为多数会话都忽略的功能花掉每一轮的工具列表与提示词预算。仍然携带它的示例保留了该插件的真实组合覆盖。
+
+**连同默认配置项一起删掉 TUI 的计划渲染与 todo 测试。** 否决：需求是同时支持启用与禁用两种情形，而事件驱动的 `TodoComponent` 本就在零插件耦合下渲染计划，删掉它等于白白丢弃一项可用能力。取而代之，启用路径保留专门的覆盖。
+
+## Testing
+
+`examples/tui-agent/tests/tui.snapshot.ts` 根据逐场景的 `enableTodo` 开关决定是否挂载 `ToolTodo`：只有 `todo-plan` 场景挂载它（启用路径的证明，其 `session.jsonl`/`terminal.expected.txt` 固定了渲染出的计划），其余每个场景都运行默认的无 todo 组合。`tests/harness.ts` 把 `ToolTodo` 做成一个 `todo` 可选项，只有 `tests/todo-write.e2e.ts` 会开启它，因此带密钥的 todo e2e 仍然驱动真实工具，而其余套件与出厂技术栈保持一致。无密钥的 `tests/tui-keyless-smoke.e2e.ts` 启动真实的 `cordis.yml`，且不对 todo 作任何断言，因此默认启动不受影响。
+
+## Consequences
+
+默认 TUI 的协议工具列表和系统提示词少了一个工具；想要任务追踪的会话加一条插件配置项即可。`examples/tui-agent/composition.md`（已重新生成）及其叶子条目表不再列出 `tool-todo`，`scripts/gen-doc-graphs.ts` 中人工维护的摘要也去掉了它。`@deepseek-ai/dsh-tool-todo` 包本身没有变动，仍由 acp/headless/jsonrpc 示例出厂携带，因此它的覆盖需求在那里得到满足。若要恢复默认，只需重新加入那一条 `cordis.yml` 配置项，并把快照/harness 的可选开关重新打开。