docs(notes): archive low-value decision records

.agents/notes/archived/AGENTS.md

@@ -0,0 +1,7 @@
+# AGENTS.md — Archived Agent Notes
+
+Archived Agent Note triplets under the kind directories are frozen historical snapshots, not current authority. Never edit, reformat, translate, repair, delete, or move a sealed artifact; use an active Agent Note or current documentation for new decisions and facts.
+
+The archival change may only relocate a complete English/Chinese/sidecar triplet, insert the identical `Archived: YYYY-MM-DD` line below both `Status: implemented` lines, re-record the sidecar, and repair or delete inbound links. Do not inspect, verify, or repair links out of archived notes.
+
+Run the [`dsh-archive-agent-notes`](../../skills/dsh-archive-agent-notes/SKILL.md) workflow and append new artifact hashes with `pnpm run verify-archived-agent-notes --write`. The normal verifier rejects changed or missing sealed artifacts, incomplete triplets, unknown kind folders, and invalid archive metadata.

.agents/notes/archived/architecture/2026-06-20-extract-example-app-packages.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-extract-example-app-packages.md: 06466aa575a535afe0ba614fb2c2c5b3e857aeab
+2026-06-20-extract-example-app-packages.zh.md: ccd8eae1524210d75770248566810423280df3b0

.agents/notes/archived/architecture/2026-06-20-extract-example-app-packages.md

@@ -0,0 +1,58 @@
+# Agent Note: Extract example apps into packages
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-06-20-extract-example-app-packages.zh.md)
+
+## Problem
+
+An example folder is supposed to be *thin* — the variable wiring of a demo, not the demo's machinery. Before this change it was thick. Each example carried a hand-rolled `start.ts` boot bootstrap, an infra preamble (`timer`, and — for the stdio demos — `logger` + `hmr`), nested includes of three shared YAML fragments (`base.yml` / `base-core.yml` / `acp-agent/acp-tail.yml`), and per-example `agent-loop`/persistence/system-prompt config. The actual app — the spine of services every agent needs — was spread across the leaf and those includes.
+
+The leaf configs also owned coupled front doors. ACP requires stdout purity and creates agents through `session/new`; terminal and Headless apps pre-create `main` but have different process I/O contracts. Prose warnings were the only guard against combining these incorrectly, while three `start.ts` files duplicated the Loader bootstrap and lifecycle code.
+
+## Decision
+
+Each example is now **mostly an invocation of an app package**, splitting the wiring along the existing [interface / implementation / consumer seam](2026-06-13-capability-seams.md): the **app package owns the composition**, the leaf `cordis.yml` owns only the **swappable choices** (which LLM adapter, which bash executor, model, prompt, persistence root).
+
+- **`@deepseek-ai/dsh-agent-spine-demo`** ([packages/examples/agent-spine-demo](../../../../packages/examples/agent-spine-demo)) composes the providerless, executor-less, UI-less spine and forwards the loop's agent-list config. Its dependency on the concrete loop is intentional because this package composes the spine rather than extending it; swapping the loop means supplying another bundle.
+- **`@deepseek-ai/dsh-tui-demo`**, **`@deepseek-ai/dsh-cli-demo`**, and **`@deepseek-ai/dsh-acp-demo`** bake in their process roles. TUI includes the full-screen UI and a pre-created `main`; Headless includes the one-shot driver and a pre-created `main`; ACP includes the bridge and no pre-created agent. All three include JSONL persistence and omit stdout loggers.
+- **`start.ts` is gone.** Each app package exposes a bin; the `demo:*` scripts invoke it. Loader boot, `.env` loading, and fail-loud guards live in the shared [`@deepseek-ai/dsh-app-boot`](../../../../packages/ui/app-boot) package (unit-tested under the per-file coverage gate — see [share the app bins' boot glue](../simplification/2026-07-04-share-app-bin-boot-glue.md)); the thin self-executing entries are driven by keyless Loader-path tests.
+- **Each leaf `cordis.yml` collapses** to backends, optional product tools, and one app entry carrying the app config. TUI and Headless route model/session choices onto a pre-created agent; ACP routes the initial provider/model onto its bridge.
+- **`base.yml`, `base-core.yml`, and `acp-agent/acp-tail.yml` are retired** — the spine they shared now lives in `dsh-agent-spine-demo`.
+
+`bash-local` and the LLM adapter stay **leaf choices**: the bundle ships `tool-bash` (the consumer schema), the leaf picks the executor implementation, so a sandboxed executor or replay adapter swaps in without touching the app.
+
+### Amendment on implementation: `hmr` stays a leaf entry
+
+The proposal listed `hmr` among the interactive app's baked-in front-door cluster. Validating against the code, baking `hmr` into the app package fights Cordis in two ways, so it ships as a **leaf `cordis.yml` entry** instead:
+
+1. `@cordisjs/plugin-hmr` is a Loader-only, subprocess-only dev plugin — it requires the live `loader` service and its internal module access, so it can only run in the real `demo:*`/bin subprocess, never in the in-process unit/coverage tier.
+2. The in-process test tier (vitest) cannot even *import* the vendored `hmr` module (its class-decorator `@Inject` form fails under Vite's transform), so a package whose `apply` statically imported it could never satisfy the per-file 100% coverage gate on its headline function.
+
+Crucially, `hmr` is not a stdout-purity footgun: a stray entry in the ACP config does not corrupt JSON-RPC frames. Every shipped app omits a stdout console logger; the app or protocol driver alone owns stdout.
+
+## Alternatives considered
+
+### Why not keep the wiring in shared YAML includes?
+
+The old `base*.yml`/`acp-tail.yml` includes already deduped the *config*, but a YAML include cannot **encapsulate** the front-door coupling — it can only describe it in a comment and trust every leaf to obey. It also cannot own a `bin`, so the boot glue stayed copied across three `start.ts` files. A package turns "the ACP app never logs to stdout" from a prose warning into a property of the artifact: there is no logger entry in the leaf to get wrong.
+
+## Verification
+
+- Example directories contain only their config, README, and tests: `start.ts`, the infrastructure preamble, and the shared YAML includes are gone.
+- `demo:tui`, `demo:headless`, and `demo:acp` invoke the app-package bins.
+- Each new package has a README and per-file 100% coverage; each app package also has a keyless real-Loader-path bin smoke that catches export-shape failures described in [postmortem 0001](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md).
+- The ACP replay suite boots through the app-package bin, so protocol wiring and assembled backend behavior cross the real Loader boundary.
+
+## Consequences
+
+- **The bare-plugin-tree pedagogy.** The spine lives behind a bundle, so seeing the whole tree means opening `dsh-agent-spine-demo`. The app package's README carries that teaching weight.
+- **A layer of indirection.** "What does this demo load?" becomes a package read, not a single YAML scan.
+
+## Related
+
+- Supersedes [Make the shared example base providerless](../../rejected/architecture/2026-06-20-providerless-example-base.md): renaming `base.yml` to the providerless core is moot once the spine moves into `dsh-agent-spine-demo` and the `base*.yml` files are deleted.
+- Builds on the [capability-seams](2026-06-13-capability-seams.md) interface/implementation/consumer split — backends and presentation stay leaf choices; the spine is the shared bundle.
+- Complements [Reorganize packages into a modular hierarchy](2026-06-20-package-hierarchy.md): the new app/core packages slot into existing groups under that hierarchy (`core` for the reusable spine bundle, `ui` for the app-specific front doors).
+- The later [redundant-agent removal](../simplification/2026-07-20-remove-stdio-and-echo-agents.md) owns the final TUI/Headless split and removes the line-oriented and mock-only leaves.

.agents/notes/archived/architecture/2026-06-20-extract-example-app-packages.zh.md

@@ -0,0 +1,58 @@
+# Agent Note: 将示例应用提取为独立包
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-06-20-extract-example-app-packages.md) | 中文
+
+## 问题
+
+示例目录本应是*精简的*——只包含演示的可变接线，而非演示的基础设施。在此次变更之前，它是臃肿的。每个示例都携带一份手写的 `start.ts` 启动引导、一段基础设施前导（`timer`，以及 stdio 演示所需的 `logger` + `hmr`（热模块替换））、三个共享 YAML 片段的嵌套引用（`base.yml` / `base-core.yml` / `acp-agent/acp-tail.yml`），还有各示例自身的 `agent-loop`/持久化/系统提示词配置。真正的应用——每个 agent（智能体）都需要的服务主干——散落在叶子配置和那些 include 中。
+
+叶子配置还拥有耦合的前门。ACP（Agent Client Protocol）要求 stdout 纯净，并通过 `session/new` 创建 agent；终端应用和 Headless 应用则预创建 `main`，但进程 I/O 契约不同。防止错误组合的唯一屏障是文档中的文字警告，而三个 `start.ts` 文件重复着 Loader 引导和生命周期代码。
+
+## 决策
+
+每个示例现在**主要是对一个应用包（package）的调用**，沿着既有的[接口 / 实现 / 消费方 seam](2026-06-13-capability-seams.md) 拆分接线：**应用包拥有组合**，叶子 `cordis.yml` 只拥有**可替换的选择**（哪个 LLM（大语言模型）适配器、哪个 bash 执行器、模型、提示词、持久化根目录）。
+
+- **`@deepseek-ai/dsh-agent-spine-demo`**（[packages/examples/agent-spine-demo](../../../../packages/examples/agent-spine-demo)）组合了不含提供方、不含执行器、不含 UI 的主干，并转发 agent loop（智能体循环）的 agent 列表配置。它对具体 loop 的依赖是有意为之，因为该包组合的是主干而非扩展主干；替换 loop 意味着提供另一个 bundle。
+- **`@deepseek-ai/dsh-tui-demo`**、**`@deepseek-ai/dsh-cli-demo`** 和 **`@deepseek-ai/dsh-acp-demo`** 各自内置其进程角色。TUI 包含全屏 UI 和预创建的 `main`；Headless 包含 one-shot driver 和预创建的 `main`；ACP 包含 bridge 且不预创建 agent。三者都包含 JSONL 持久化，并省略 stdout logger。
+- **`start.ts` 已移除。** 每个应用包都暴露一个 bin；`demo:*` 脚本调用它。Loader 引导、`.env` 加载和快速失败守卫位于共享的 [`@deepseek-ai/dsh-app-boot`](../../../../packages/ui/app-boot) 包（在逐文件覆盖率门禁下有单元测试——见[共享应用 bin 的启动胶水](../simplification/2026-07-04-share-app-bin-boot-glue.md)）；精简的自执行入口由 keyless 的 Loader 路径测试驱动。
+- **每个叶子 `cordis.yml` 精简为**后端、可选产品工具，以及一个承载应用配置的 app 条目。TUI 和 Headless 把模型/会话选择路由到预创建的 agent；ACP 把初始提供方/模型路由到 bridge。
+- **`base.yml`、`base-core.yml` 和 `acp-agent/acp-tail.yml` 已退役**——它们共享的主干现在位于 `dsh-agent-spine-demo` 中。
+
+`bash-local` 和 LLM 适配器仍然是**叶子选择**：bundle 提供 `tool-bash`（消费方 schema），叶子选择执行器实现，因此沙箱执行器或回放适配器无需触碰应用即可替换。
+
+### 实现修正：`hmr` 保留为叶子条目
+
+提案最初将 `hmr` 列入交互式应用内置的前门集群。对照代码验证后发现，将 `hmr` 内置到应用包中会在两个方面与 Cordis 冲突，因此改为作为**叶子 `cordis.yml` 条目**交付：
+
+1. `@cordisjs/plugin-hmr` 是一个仅限 Loader、仅限子进程的开发插件——它需要活跃的 `loader` 服务及其内部模块访问权限，因此只能在真实的 `demo:*`/bin 子进程中运行，不能在进程内的单元/覆盖率测试层运行。
+2. 进程内测试层（vitest）甚至无法*导入* vendor 的 `hmr` 模块（其 class-decorator `@Inject` 形式在 Vite 的 transform 下会失败），因此一个 `apply` 静态导入了它的包永远无法满足其主函数的逐文件 100% 覆盖率门禁。
+
+关键在于，`hmr` 不是 stdout 纯净隐患：ACP 配置中误加该条目不会破坏 JSON-RPC 帧。所有已交付应用都省略 stdout 控制台 logger；stdout 只归应用或协议 driver 所有。
+
+## 曾考虑的替代方案
+
+### 为什么不继续用共享 YAML include 来管理接线？
+
+旧的 `base*.yml`/`acp-tail.yml` include 已经去重了*配置*，但 YAML include 无法**封装**前门耦合——它只能在注释中描述，并信任每个叶子遵守。它也无法拥有 `bin`，因此启动胶水一直在三个 `start.ts` 文件中重复。包将「ACP 应用绝不向 stdout 输出日志」从文字警告变成了产物的属性：叶子中不存在可以写错的 logger 条目。
+
+## 验证
+
+- 示例目录只包含配置、README 和测试：`start.ts`、基础设施前导和共享 YAML include 已移除。
+- `demo:tui`、`demo:headless` 和 `demo:acp` 调用应用包的 bin。
+- 每个新包都有 README 和逐文件 100% 覆盖率；每个应用包还有一个 keyless 的真实 Loader 路径 bin 冒烟测试，用于捕获[事后分析 0001](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md) 中描述的导出形状故障。
+- ACP 回放套件通过应用包的 bin 启动，因此协议接线与组装后的后端行为都跨越真实的 Loader 边界。
+
+## 后果
+
+- **裸插件树的教学性。** 主干现在隐藏在 bundle 之后，查看完整树意味着打开 `dsh-agent-spine-demo`。应用包的 README 承担了这份教学职责。
+- **多了一层间接。**「这个演示加载了什么？」从扫描单个 YAML 变成了阅读一个包。
+
+## 相关
+
+- 取代[使共享示例基础配置与提供方无关](../../rejected/architecture/2026-06-20-providerless-example-base.md)：一旦主干移入 `dsh-agent-spine-demo` 且 `base*.yml` 文件被删除，将 `base.yml` 重命名为无提供方核心便不再有意义。
+- 基于[能力 seam](2026-06-13-capability-seams.md)的接口/实现/消费方拆分——后端和展示层保持为叶子选择；主干是共享 bundle。
+- 与[将包重组为模块化层级结构](2026-06-20-package-hierarchy.md)互补：新的 app/core 包按该层级结构归入既有分组（`core` 放可复用的主干 bundle，`ui` 放应用特有的前门）。
+- 后续的[冗余 agent 移除](../simplification/2026-07-20-remove-stdio-and-echo-agents.md)拥有最终的 TUI/Headless 拆分，并移除行式与仅 mock 的叶子。

.agents/notes/archived/architecture/2026-07-03-filesystem-directory-listing-seam.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
+2026-07-03-filesystem-directory-listing-seam.md: eb2650daf567d4bd98ed8553a4b743f5a01d945c
+2026-07-03-filesystem-directory-listing-seam.zh.md: 4bcda9f093f22c06348d4c69c4de3bd62f216f8e

.agents/notes/archived/architecture/2026-07-03-filesystem-directory-listing-seam.md

@@ -0,0 +1,54 @@
+# Agent Note: Add direct directory listing to the filesystem seam
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-03-filesystem-directory-listing-seam.zh.md)
+
+## Problem
+
+`@deepseek-ai/dsh-fs` is the provider seam for filesystem access, with local and future non-local backends behind the same `ctx.fs` contract. Before this change it could resolve paths, stat targets, read text, stream text, write text, and edit text. That was enough for model-facing file tools, but not for non-model-facing consumers that need to enumerate directories without importing `node:fs`.
+
+The immediate pressure came from skill loading: reading an individual `SKILL.md` can already go through `ctx.get('fs')`, but discovering which skill roots contain `<name>/SKILL.md` or `<name>.md` still needs directory enumeration. Adding directory listing only in `dsh-skill` would either keep a direct Node dependency there or invent a one-off local helper outside the filesystem provider stack.
+
+This decision adds the provider capability without a model-facing `ls`/`list` tool or skill-discovery change. Those consumers require separate UX, prompt, and policy decisions.
+
+## Decision
+
+Add `FileSystem.listDir(target, signal?)` to `@deepseek-ai/dsh-fs`.
+
+`listDir` lists one directory level only. It returns direct children in stable name order and includes:
+
+- `name`: the child basename.
+- `type`: `file`, `directory`, or `other`.
+- `target`: the resolved child `FsTarget`.
+- `version`: cheap metadata when available.
+- `size`: regular-file size when available.
+
+It never reads file contents. Recursive traversal, globbing, pagination, search, file watching, and model-facing rendering are intentionally out of scope.
+
+The local backend implements this through `readdir({ withFileTypes: true })`, `resolveLocalTarget`, and metadata `stat`/`realpath` probes. The result order is deterministic (`name.localeCompare`) to keep prompt/listing output stable for future consumers and improve prefix-cache reuse.
+
+Broken or disappeared children may be represented as `type: 'other'` without `version`/`size`; they do not abort the whole listing. Permission or backend I/O failures while listing the directory or resolving/probing child metadata fail the whole listing with structured `FsError` codes:
+
+- `FS_NOT_FOUND` for missing targets.
+- `FS_NOT_DIRECTORY` for existing non-directory targets.
+- `FS_PERMISSION_DENIED` for permission failures.
+- `FS_IO_ERROR` for other backend I/O failures.
+- `FS_ABORTED` for aborted calls.
+
+## Alternatives considered
+
+**Add a model-facing list tool with the seam.** Rejected because its prompt, schema, and rendering contracts are independent of the provider primitive.
+
+**Keep directory enumeration in each consumer.** Rejected. That would bind product packages such as `dsh-skill` to Node/local filesystem behavior and bypass policy/remote/sandboxed backends.
+
+**Make `listDir` recursive or glob-shaped.** Rejected for now. Skill-root discovery only needs direct children, and a simple direct listing is the smallest backend contract future consumers can safely compose.
+
+**Skip children that fail metadata resolution.** Rejected. The API promises resolved child targets, so permission/IO failures while resolving a child are contract failures. Broken or disappeared children are the exception because they can still be represented without claiming a live resolved file.
+
+## Consequences
+
+Every filesystem backend must now implement one additional provider primitive. That is deliberate foundation work while the harness is still unreleased, but it does mean future sandboxed/remote backends need to define equivalent direct-child listing behavior.
+
+The capability remains provider-facing. Until a consumer lands, ACP/model sessions will still need existing tools such as `bash` for directory listing. The absence of a model-facing `listdir` tool is expected, not a wiring failure.

.agents/notes/archived/architecture/2026-07-03-filesystem-directory-listing-seam.zh.md

@@ -0,0 +1,54 @@
+# Agent Note: 为文件系统 seam 添加直接目录列举能力
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-03-filesystem-directory-listing-seam.md) | 中文
+
+## 问题
+
+`@deepseek-ai/dsh-fs` 是文件系统访问的提供方 seam，本地后端与未来的非本地后端共享同一个 `ctx.fs` 契约。在本次变更之前，它能解析路径、stat 目标、读取文本、流式读取文本、写入文本和编辑文本。这对面向模型的文件工具已经足够，但对于需要枚举目录而又不想直接导入 `node:fs` 的非模型侧消费方来说还不够。
+
+直接的压力来自 skill（技能）加载：读取单个 `SKILL.md` 已经可以走 `ctx.get('fs')`，但发现哪些 skill 根目录包含 `<name>/SKILL.md` 或 `<name>.md` 仍需要目录枚举。如果仅在 `dsh-skill` 中添加目录列举，要么保留对 Node 的直接依赖，要么在文件系统提供方栈之外发明一个一次性的本地辅助函数。
+
+本决策只添加提供方能力，不涉及面向模型的 `ls`/`list` 工具或 skill 发现机制的变更。那些消费方需要独立的 UX、提示词与策略决策。
+
+## 决策
+
+在 `@deepseek-ai/dsh-fs` 中添加 `FileSystem.listDir(target, signal?)`。
+
+`listDir` 仅列举一层目录。它以稳定的名称顺序返回直接子项，包含以下字段：
+
+- `name`：子项的 basename；
+- `type`：`file`、`directory` 或 `other`；
+- `target`：已解析的子项 `FsTarget`；
+- `version`：可用时返回的轻量元数据；
+- `size`：可用时返回的常规文件大小。
+
+它从不读取文件内容。递归遍历、glob 匹配、分页、搜索、文件监听和面向模型的渲染均有意不在范围内。
+
+本地后端通过 `readdir({ withFileTypes: true })`、`resolveLocalTarget` 以及元数据 `stat`/`realpath` 探测来实现。结果顺序是确定性的（`name.localeCompare`），以保持未来消费方的提示词/列表输出稳定，并提高前缀缓存复用率。
+
+损坏或已消失的子项可以表示为 `type: 'other'`（不带 `version`/`size`）；它们不会中止整个列举。在列举目录或解析/探测子项元数据时遇到权限或后端 I/O 故障，则以结构化的 `FsError` 错误码使整个列举失败：
+
+- `FS_NOT_FOUND`：目标不存在；
+- `FS_NOT_DIRECTORY`：目标存在但不是目录；
+- `FS_PERMISSION_DENIED`：权限不足；
+- `FS_IO_ERROR`：其他后端 I/O 故障；
+- `FS_ABORTED`：调用被中止。
+
+## 曾考虑的替代方案
+
+**在添加 seam 的同时添加面向模型的 list 工具。** 否决。其提示词、schema 和渲染契约与提供方原语相互独立。
+
+**让每个消费方自行枚举目录。** 否决。这会将 `dsh-skill` 等产品包绑定到 Node/本地文件系统行为上，绕过策略/远程/沙箱后端。
+
+**让 `listDir` 支持递归或 glob 形式。** 暂时否决。skill 根发现只需要直接子项，而简单的单层列举是未来消费方可以安全组合的最小后端契约。
+
+**跳过元数据解析失败的子项。** 否决。API 承诺返回已解析的子项 target，因此解析子项时的权限/IO 故障属于契约失败。损坏或已消失的子项是例外，因为它们仍可在不声称拥有一个活跃已解析文件的前提下被表示。
+
+## 后果
+
+每个文件系统后端现在必须多实现一个提供方原语。这是 harness 尚未发布时有意为之的基础工作，但也意味着未来的沙箱/远程后端需要定义等价的直接子项列举行为。
+
+该能力仍停留在提供方层面。在消费方落地之前，ACP（Agent Client Protocol）/模型会话仍需使用 `bash` 等既有工具来列举目录。缺少面向模型的 `listdir` 工具是预期行为，而非接线错误。

.agents/notes/archived/architecture/2026-07-23-unified-session-query-service.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
+2026-07-23-unified-session-query-service.md: f69836f60dfd73f9d8490687294b8407e53e9b32
+2026-07-23-unified-session-query-service.zh.md: bf25f4337dc8696ae54ffb16a7dd74437d45858b

.agents/notes/archived/architecture/2026-07-23-unified-session-query-service.md

@@ -0,0 +1,40 @@
+# Agent Note: Unified session query service
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-23-unified-session-query-service.zh.md)
+
+## Problem
+
+Exact reads, semantic filters, relationship traces, and full-text search operate on the same live-preferred session corpus. Exposing full-text search under a second context key makes consumers and app compositions treat one capability as two services, even though the SQLite implementation is the only backend-specific part.
+
+The interface package already owns the shared record, filter, trace, search-request, cursor, and error contracts. A provider registry or coordinator would add runtime selection semantics unsupported by any current consumer.
+
+## Decision
+
+`SessionQueryService` is the single abstract service registered as `ctx.sessionQuery`. It concretely implements listing, title and event reads, surface reads, filtering, and relationship tracing through its backend-independent `SessionCorpus`. Its only abstract methods are `searchSessions()` and `searchEvents()`.
+
+`SessionQuerySqlite` extends that service and is the sole concrete backend. One mounted instance therefore exposes every operation through `ctx.sessionQuery`; its inherited exact operations use the shared corpus implementation, while its SQLite-owned lifecycle observes sources, reconciles the derived FTS index, ranks matches, and owns cursor generations. The interface package has no standalone concrete plugin, search-provider registry, or second context key.
+
+SQLite reconciliation is one quiescent serialized state machine. It passes the caller's exact abort signal into durable snapshot listing and inspection, awaits each started backend operation itself, and checks cancellation after every await and before starting the next source or index operation. Cancellation therefore cannot release the serializer while an ignored or cooperative backend call is still cleaning up, and it cannot start a subsequent listing, inspection, reconciliation, or query after the signal is observed.
+
+Backend configuration includes the inherited `readWindowMax` setting alongside its own index path, journal mode, page limits, and snippet limit. First-party apps that need session queries mount the SQLite backend and place its disposable index beside their configured persistence root.
+
+This service topology supersedes the separate-key portion of the [exact query decision](../feature/2026-07-10-session-query-service.md) and [SQLite search decision](../feature/2026-07-10-sqlite-session-query-provider.md); their corpus, query, tokenizer, reconciliation, and safety decisions remain in force.
+
+## Alternatives considered
+
+- **Keep `ctx.sessionQuery` and `ctx.sessionSearch` separate** — rejected because both expose operations over one logical corpus, force consumers to discover two keys, and let apps accidentally mount only a partial query surface.
+- **Keep a concrete base service and let the SQLite plugin register or mutate two search methods** — rejected because method availability would depend on plugin order and teardown, and the service would need a provider registration protocol for one implementation.
+- **Move every query implementation into the SQLite package** — rejected because exact reads, filters, and traces require no index and are shared behavior that belongs with their provider-independent contracts.
+
+## Consequences
+
+Consumers inject one service and can combine exact and full-text operations without a second capability lookup. A production composition must choose a concrete backend even when one consumer currently calls only inherited exact methods; tests may use a minimal subclass when backend behavior is outside their scope.
+
+The unified object deliberately retains two internal observation strategies: exact operations read authoritative live/persisted sources per call, while full-text operations reconcile a disposable index. Sharing the context key does not make the derived index authoritative or couple exact-read availability to an FTS query.
+
+Queued cancellation remains prompt. Cancellation during active asynchronous source observation waits for that started operation to settle, which makes rejection a quiescence boundary and preserves single-file execution for a following search. Synchronous SQLite statements remain non-preemptible and are bracketed by signal checks.
+
+Unit coverage pins inherited and abstract behavior on one key, SQLite coverage exercises both operation families on the concrete backend, and the real Loader path verifies that one exported plugin registers the combined service.

.agents/notes/archived/architecture/2026-07-23-unified-session-query-service.zh.md

@@ -0,0 +1,40 @@
+# Agent Note: 统一会话查询服务
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-23-unified-session-query-service.md) | 中文
+
+## 问题
+
+精确读取、语义过滤、关系追踪与全文搜索都作用于同一个实时源优先的会话语料库。将全文搜索暴露在第二个上下文键下，会让消费方与应用组合把同一项查询功能视为两个服务，尽管只有 SQLite 实现是后端特有的部分。
+
+接口包已经拥有共享的记录、过滤、追踪、搜索请求、游标与错误契约。提供方注册表或协调器会引入运行时选择语义，而目前没有任何消费方支持这种语义。
+
+## 决策
+
+`SessionQueryService` 是注册为 `ctx.sessionQuery` 的唯一抽象服务。它通过后端无关的 `SessionCorpus` 具体实现列表查询、标题与事件读取、表层读取、过滤和关系追踪。仅有 `searchSessions()` 与 `searchEvents()` 两个方法为抽象方法。
+
+`SessionQuerySqlite` 扩展该服务，并且是唯一的具体后端。因此，一个挂载实例便可通过 `ctx.sessionQuery` 暴露全部操作；其继承的精确操作使用共享的语料库实现，而由 SQLite 管理的生命周期负责观察数据源、对齐派生 FTS 索引、对匹配项排序并管理游标代际。接口包不提供独立的具体插件、搜索提供方注册表或第二个上下文键。
+
+SQLite 的对齐过程是一个具备静止性保证的串行状态机。它将调用方的原始中止信号传给持久化快照列表与检查操作，直接等待每个已经启动的后端操作，并在每次等待后以及启动下一个数据源或索引操作前检查是否已取消。因此，即使后端忽略取消或正在配合清理，串行器也不会提前释放；观察到中止信号后，也不会再启动后续的列表、检查、对齐或查询操作。
+
+后端配置除了自身的索引路径、日志模式、分页限制与文本片段长度上限外，还包含继承的 `readWindowMax` 设置。需要会话查询的第一方应用挂载 SQLite 后端，并将其可丢弃索引放在已配置的持久化根目录旁。
+
+这一服务拓扑取代了[精确查询决策](../feature/2026-07-10-session-query-service.md)和 [SQLite 搜索决策](../feature/2026-07-10-sqlite-session-query-provider.md)中关于分离上下文键的部分；其中关于语料库、查询、分词器、对齐与安全性的决策仍然有效。
+
+## 已考虑的替代方案
+
+- **保留相互独立的 `ctx.sessionQuery` 与 `ctx.sessionSearch`**：不予采纳，因为二者都针对同一逻辑语料库提供操作，迫使消费方识别两个键，还可能让应用误挂载一组不完整的查询接口。
+- **保留具体的基础服务，再由 SQLite 插件注册或修改两个搜索方法**：不予采纳，因为方法是否可用将取决于插件顺序与资源释放时机，而且该服务需要为唯一的实现定义一套提供方注册协议。
+- **将所有查询实现移入 SQLite 包**：不予采纳，因为精确读取、过滤与追踪不需要索引，并且都属于应与提供方无关契约放在一起的共享行为。
+
+## 后果
+
+消费方只需注入一个服务，无需再次查找其他功能，便可组合精确操作与全文操作。生产环境的组合必须选择一个具体后端，即使当前某个消费方只调用继承的精确方法；如果后端行为不在测试范围内，测试可以使用最小子类。
+
+统一后的对象有意保留两种内部观察策略：精确操作在每次调用时读取权威的实时源或持久化源，全文操作则使可丢弃索引与数据源对齐。共用上下文键不会让派生索引成为权威来源，也不会使精确读取的可用性依赖 FTS 查询。
+
+排队阶段的取消仍会及时生效。在异步数据源观察已经开始后取消时，调用方会等待该操作完成清理后才收到拒绝；因此拒绝本身构成静止边界，并保证后续搜索仍按单一串行流程执行。同步 SQLite 语句无法在执行中被抢占，服务会在其前后检查中止信号。
+
+单元测试在同一个键上同时固定继承实现与抽象方法的契约，SQLite 测试在具体后端上覆盖两类操作，真实 Loader 路径则验证单个导出的插件能够注册组合后的服务。

.agents/notes/archived/architecture/2026-07-24-dsh-commander-argument-adapter.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
+2026-07-24-dsh-commander-argument-adapter.md: a5f6e580b91c0de1cdb433e1973bdff960384f06
+2026-07-24-dsh-commander-argument-adapter.zh.md: 4321ab154996c9b23ce58175b112234c92013cb8

.agents/notes/archived/architecture/2026-07-24-dsh-commander-argument-adapter.md

@@ -0,0 +1,54 @@
+# Agent Note: Parse `dsh` argv through one Commander adapter
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-24-dsh-commander-argument-adapter.zh.md)
+
+## Problem
+
+The `dsh` CLI entry (`apps/cli`) parsed argv in three hand-rolled idioms that did not compose and gave no `--help`/`--version`. `bin.ts` dispatched by raw inspection — `argv[0] === 'web'`, then `argv.includes('-p') || argv.includes('--prompt')`, else TUI — which is positional-blind: a prompt flag or a config path in the wrong position could misroute the mode, and `argv.includes('-p')` could not tell a real flag from an incidental token. `headless.ts` and `web.ts` each ran their own `node:util` `parseArgs` with inline host/port validation, and `dsh-app-boot` carried `parseResumeArg`, a ~30-line bespoke scanner reimplementing flag/`=`-form/value/repeat handling for `--resume`. Usage was a single hardcoded `usage: dsh -p "task"` line; there was no version flag and no rendered help.
+
+## Decision
+
+Argv is parsed once, in `apps/cli/src/args.ts`, through a Commander adapter (the same parser the SDK bins — `create-sdk`, `dsh-scripts` — already standardize on). `parseDshArgs(argv, version)` returns a discriminated `DshInvocation` union of the three real modes: `{ mode: 'tui', config?, resume? }`, `{ mode: 'headless', prompt }`, or `{ mode: 'web', host?, port?, dev }`. It does **not** model help/version/errors as data: Commander owns those, printing usage or the diagnostic and exiting at the point of failure. `exitOverride()` turns each into a thrown `CommanderError` carrying the intended code (0 for help/version, 1 for a parse or domain error), which one `try/catch` in `parseDshArgs` turns into `process.exit`.
+
+`bin.ts` calls the adapter once and switches on `mode` (closed union, `satisfies never` default), dynamic-importing only the chosen mode's module; only a valid, non-help invocation reaches the switch, so it has no help/version/error cases. Each mode module consumes already-parsed values: `runTui(config, resume)`, `runHeadless(task)`, `runWeb(host, port, dev, workspaceRoot)` — none re-reads argv. It is **one Commander program**: the default surface (no subcommand) carries option-only flags — `--config <path>`, `-p/--prompt <task>`, `--resume <id>` — and `web` is a real `program.command('web')` subcommand. The default surface takes no positional argument, which is what lets `web` be a real subcommand without a positional collision, so `dsh --help` lists `web` natively (no hand-pasted command text). The default action and the `web` action set the resolved mode, then bail via `command.error(...)` (print + exit 1) on the domain checks Commander cannot express: `--prompt` selects headless and rejects an empty task or a `--config`/`--resume` alongside it rather than silently dropping a TUI input; an empty `--resume=` id fails loud (agent-loop treats `''` as no-resume). Commander parses the default-surface options on either side of the `web` token into `program.opts()`; since `web` shares none of them, the `web` action rejects a leaked `--config`/`-p`/`--resume` (`dsh web -p x`, `dsh --config c.yml web`) rather than silently serving and dropping it. `dsh web`'s `--host`/`--port` are unvalidated pass-through overrides: the adapter assigns no default and does no validation, only `Number`-coercing the port string (the schema wants a number). The `dsh-host-webserver` schemastery `Config` (`host` a `127.0.0.1`/`0.0.0.0` literal union, `port` a natural ≤ 65535) is the single source of both the default (the shipped `apps/cli/cordis.yml` `webserver` row stands when a flag is absent) and validity — `AppCLIEntry` patches an explicit flag straight into that row, so a bad host/port fails loud at the schema on boot, not at parse. `--dev` mounts the client HMR driver and bundle watch, and `--workspace-root <path>` is a plain pass-through to `AppCLIEntry` (the parent directory for name-created workspaces). A repeated `--resume`, or a following flag captured as a `--resume`/`--prompt` value, is Commander's standard behavior (last-wins / next-token) and is left alone; a bad id fails loud downstream when the session cannot load. `--version` reads this app's `package.json`.
+
+`dsh` takes no positional argument. `--config <path>` names an alternate cordis tree to boot instead of the shipped default; it exists only so the demo/test call sites (`demo:cordis`, `demo:code-mode`, the keyless PTY smokes) can point the shipped bin at an example tree. A bare `dsh` boots the shipped tree plus the `~/.dsh/config.yaml` personal overlay; a real user never passes `--config`.
+
+CLI parsing lives entirely in `apps/cli`. `dsh-app-boot` holds the boot/env/config/personal-overlay helpers and no argv scanner.
+
+## Session resume through the boot context
+
+`dsh --resume <id>` is the one way to resume a persisted session, with no environment variable. `runTui` provides the parsed id on the boot context through `boot`'s `prepare(ctx)` hook — `ctx.provide(RESUME_SESSION_ID_KEY, id)` (a `dsh-app-boot` export, value `'resumeSessionId'`) — and the shipped tui-agent/cordis configs read it as a bare identifier: `resumeSessionId: !!js "typeof resumeSessionId === 'string' ? resumeSessionId : undefined"`. The expression is quoted because YAML otherwise parses the `?`/`:` as a mapping; the `typeof` guard tolerates a launcher that never provides the slot. The `/resume` in-place handoff (`process.execve`) rebuilds its re-exec argv from the parsed values as `dsh --resume=<id> [--config <path>]`.
+
+## One terminal front door: `dsh`
+
+`dsh` is the only terminal entry point; the `dsh-tui-demo` package ships the TUI app bundle plugin the shipped config mounts, and no bin of its own. `demo:cordis`, `demo:code-mode`, and both the tui-agent and cordis-agent keyless PTY smokes launch through `apps/cli/src/bin.ts` with `--config <path>`. `dsh`'s TTY guard (refuse piped stdio before booting, pointing at `dsh -p` for automation) is pinned by `apps/cli/tests/built-bin.e2e.ts`, which runs the built `lib/bin.js` under plain Node with piped stdio (`apps/cli/tests` is in the e2e vitest include). `cli-demo`, `acp-demo`, and `jsonrpc-demo` keep their own bins because each is a distinct surface (headless, ACP, JSON-RPC) `dsh` does not provide.
+
+## Package topology
+
+The argument surface stays inside `apps/cli`, the assembly tier, not a `packages/*` library: it is this one app's routing, not a reusable seam. `dsh-app-boot` shrinks to boot glue with no CLI-parsing responsibility. `commander@^15` is added to `apps/cli/package.json`, matching the SDK bins' pin.
+
+## Alternatives considered
+
+**Keep `node:util` `parseArgs` and only unify the dispatch** — rejected: `parseArgs` has no subcommand model, no rendered help, and no version flag, so `web` routing and `--help`/`--version` would stay hand-rolled. The repo already chose Commander for its other CLIs; a second parser idiom for `dsh` alone is the fragmentation this change removes.
+
+**Keep `parseResumeArg` as a shared helper and feed it Commander's residual args** — rejected: the whole point is to retire the bespoke scanner. Commander parses `--resume` (space and `=` forms, missing-value, position-independence) natively; keeping a parallel hand-written path for the one flag would preserve the duplication the change exists to end.
+
+**A bare `dsh <config>` positional for the alternate tree** — rejected: a root positional and a real `web` subcommand cannot coexist in one Commander program (the subcommand claims the first positional). A positional would force `web` into a reserved-first-token dispatch to a separate parser and a hand-maintained `web` line in `--help`. Only the demo/test sites ever need to name an alternate tree, so a `--config` flag serves them while leaving the default surface positional-free — `web` is then a normal subcommand in one program with native `--help`.
+
+**Make the argument surface a `packages/*` seam** — rejected: nothing outside `dsh` consumes it, and capability seams are not split preemptively. The Commander adapter is `apps/cli`'s own concern.
+
+**Keep `RESUME_SESSION_ID` as the resume bridge** — rejected: with `--resume` parsed into a value the bin already holds, threading it through an environment variable the config re-reads is indirection with no benefit, and it left the demo bin a second, env-only resume path. Providing the id on the boot context is the same channel `boot`'s `prepare` hook already uses for `tuiResumeHost`.
+
+**Keep the `dsh-tui-demo` bin** — rejected: it duplicated `dsh --config <path>` exactly, and keeping it forced the demo-only `RESUME_SESSION_ID` fallback to stay alive. Its plugin is what the configs actually mount; only the front-door bin was redundant, and `dsh` is the one terminal entry point.
+
+## Testing
+
+`apps/cli/tests/args.spec.ts` (new; `apps/*/tests` added to the vitest include and `apps/cli/tests` to `tsconfig.host.json`) covers the adapter at the level that matters: mode routing by shape (including `web --dev` and the host/port pass-through), the exit-code behavior for the adapter's fail-loud checks (empty resume/prompt, `--prompt` mixed with a config/`--resume`, unknown option, stray positional), and `--help`/`--version`, captured through a `process.exit` spy. Host/port validity is the webserver schema's job, exercised on boot by the web smoke, not the adapter spec. Both PTY smoke groups in `examples/tui-agent/tests/tui-keyless-smoke.e2e.ts` now drive the real `apps/cli/src/bin.ts`: the `tui-agent` group boots an example tree through `--config`, and the `dsh CLI` group covers default boot, personal overlay, invalid config, the `--resume` config intake, the `process.execve` in-place resume handoff, and the source-path prompt. `examples/cordis-agent/tests/keyless-smoke.e2e.ts` likewise launches through `dsh`. `packages/ui/app-boot/tests/app-boot.spec.ts` drops its `parseResumeArg`/`replaceResumeArg` blocks; the TUI unit and snapshot fixtures use the `dsh --resume {session}` resume command.
+
+## Consequences
+
+`dsh` has rendered `--help`/`--version` and consistent fail-loud parse errors, and mode routing does not depend on flag position. Argv parsing lives in one place with one parser idiom shared with the SDK bins, at the cost of a `commander` dependency on `apps/cli` and Commander's parse semantics (its error strings, its `exitOverride` contract) sitting on the CLI's front door. `dsh-app-boot` owns no CLI-parsing surface; a consumer needing `--resume`-style parsing composes Commander. Session resume rides the boot context rather than an environment variable, and `dsh` is the single terminal front door — the `dsh-tui-demo` package is a plugin bundle a config mounts.

.agents/notes/archived/architecture/2026-07-24-dsh-commander-argument-adapter.zh.md

@@ -0,0 +1,54 @@
+# Agent Note: 通过单个 Commander 适配器解析 `dsh` 的 argv
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-24-dsh-commander-argument-adapter.md) | 中文
+
+## 问题
+
+`dsh` 的 CLI（命令行界面）入口（`apps/cli`）以三种手写方式解析 argv，这些方式无法组合，也不提供 `--help`/`--version`。`bin.ts` 通过原始检查进行分发：先判断 `argv[0] === 'web'`，再判断 `argv.includes('-p') || argv.includes('--prompt')`，否则走 TUI。这种方式对位置不敏感：位置错误的 prompt 标志或配置路径可能把模式路由错，而 `argv.includes('-p')` 无法区分真正的标志和偶然出现的 token。`headless.ts` 和 `web.ts` 各自运行自己的 `node:util` `parseArgs`，并内联校验 host/port，而 `dsh-app-boot` 携带 `parseResumeArg`——一个约 30 行的定制扫描器，为 `--resume` 重新实现了标志、`=` 形式、取值和重复的处理。用法说明只有一行硬编码的 `usage: dsh -p "task"`；既没有版本标志，也没有渲染出的帮助信息。
+
+## 决策
+
+argv 只在 `apps/cli/src/args.ts` 中解析一次，并使用 Commander 适配器（SDK bin `create-sdk`、`dsh-scripts` 已经统一采用的同一解析器）。`parseDshArgs(argv, version)` 返回仅包含三种实际模式的判别式 `DshInvocation` 联合类型：`{ mode: 'tui', config?, resume? }`、`{ mode: 'headless', prompt }` 或 `{ mode: 'web', host?, port?, dev }`。它**不会**将帮助、版本信息或错误建模为数据：这些情况由 Commander 处理，在触发处打印用法或诊断信息并退出。`exitOverride()` 会将每种情况转为抛出的 `CommanderError`，并携带预期退出码（帮助或版本为 0，解析错误或领域错误为 1）；唯一一处 `try/catch` 位于 `parseDshArgs` 中，捕获错误后调用 `process.exit`。
+
+`bin.ts` 只调用适配器一次，并对 `mode` 做分支切换（封闭联合类型，默认分支为 `satisfies never`），仅动态导入所选模式对应的模块；只有合法的非帮助请求才会进入这段分支逻辑，因此其中没有帮助、版本或错误分支。每个模式模块只消费已解析好的值：`runTui(config, resume)`、`runHeadless(task)`、`runWeb(host, port, dev, workspaceRoot)`，都不会再次读取 argv。整个 CLI 由**单个 Commander 程序**实现：默认接口（不使用子命令时）只包含选项标志——`--config <path>`、`-p/--prompt <task>`、`--resume <id>`——而 `web` 是通过 `program.command('web')` 定义的真正子命令。默认接口不接受位置参数，因此 `web` 可以成为真正的子命令且不会发生位置参数冲突，`dsh --help` 也会原生列出 `web`，无需手工拼接命令文本。默认命令和 `web` 子命令的处理函数会设置解析得到的模式，随后对 Commander 无法表达的领域校验调用 `command.error(...)` 立即终止（打印信息并以退出码 1 退出）：`--prompt` 选择 headless 模式；如果任务为空，或调用中还包含 `--config` 或 `--resume`，它会拒绝调用，而不会静默丢弃 TUI 输入；空的 `--resume=` id 会显式失败（agent-loop 把 `''` 视为不恢复）。Commander 会将 `web` token 前后的默认接口选项都解析进 `program.opts()`；由于 `web` 不与默认接口共用任何选项，`web` 子命令的处理函数会拒绝误入的 `--config`/`-p`/`--resume`（`dsh web -p x`、`dsh --config c.yml web`），而不是静默启动服务并丢弃这些选项。`dsh web` 的 `--host`/`--port` 是未经校验、直接透传的覆盖值：适配器既不设置默认值，也不执行校验，只使用 `Number` 将端口字符串转换为数字（schema 要求该值为数字）。`dsh-host-webserver` 的 schemastery `Config`（`host` 是 `127.0.0.1`/`0.0.0.0` 字面量联合类型，`port` 是不大于 65535 的自然数）是默认值与有效性的唯一真源：未提供标志时，随产品提供的 `apps/cli/cordis.yml` 中 `webserver` 配置项保持原值；`AppCLIEntry` 将显式标志的值直接写入该配置项，因此无效的 host/port 会在启动时触发 schema 校验并显式失败，而不是在参数解析阶段失败。`--dev` 会挂载客户端 HMR（热模块替换）驱动，并启用构建产物监视，`--workspace-root <path>` 则是直接透传给 `AppCLIEntry` 的选项（按名称创建 workspace 时使用的父目录）。重复提供 `--resume`，或后续标志被捕获为 `--resume` 或 `--prompt` 的值，都是 Commander 的标准行为（最后一次取值生效／将下一 token 作为值），本适配器不作干预；无效 id 会在下游无法加载会话时显式失败。`--version` 读取本应用的 `package.json`。
+
+`dsh` 不接受位置参数。`--config <path>` 指定一份替代 Cordis 配置树，系统启动该配置树而不是随产品提供的默认配置树；该标志仅用于让演示和测试调用点（`demo:cordis`、`demo:code-mode`、无密钥 PTY 冒烟测试）通过随产品提供的 bin 启动一份示例树。直接运行 `dsh` 会启动随产品提供的配置树，并叠加 `~/.dsh/config.yaml` 个人覆盖；实际用户从不传入 `--config`。
+
+CLI 解析完全位于 `apps/cli` 中。`dsh-app-boot` 提供启动、环境变量、配置和个人覆盖辅助函数，不包含 argv 扫描器。
+
+## 通过启动上下文恢复会话
+
+`dsh --resume <id>` 是恢复持久化会话的唯一方式，无需环境变量。`runTui` 通过 `boot` 的 `prepare(ctx)` 钩子，在启动上下文中提供已解析的 id：`ctx.provide(RESUME_SESSION_ID_KEY, id)`（`dsh-app-boot` 的一项导出，值为 `'resumeSessionId'`）；随产品提供的 tui-agent/cordis 配置将该值作为裸标识符读取：`resumeSessionId: !!js "typeof resumeSessionId === 'string' ? resumeSessionId : undefined"`。这个表达式需要加引号，否则 YAML 会把 `?` 和 `:` 解析为映射；`typeof` 守卫使从未提供该槽位的启动器也能正常运行。`/resume` 原地交接（`process.execve`）根据已解析的值将重新执行时的 argv 构造成 `dsh --resume=<id> [--config <path>]`。
+
+## 唯一的终端入口：`dsh`
+
+`dsh` 是唯一的终端入口；`dsh-tui-demo` 包（package）提供 TUI 应用组合插件，随产品提供的配置会挂载该插件，而该包不提供自己的 bin。`demo:cordis`、`demo:code-mode` 以及 tui-agent 和 cordis-agent 的无密钥 PTY 冒烟测试都通过 `apps/cli/src/bin.ts` 启动，并传入 `--config <path>`。`dsh` 的 TTY 守卫会在启动前拒绝标准输入输出接入管道的调用，并提示自动化场景使用 `dsh -p`；`apps/cli/tests/built-bin.e2e.ts` 锁定了这一行为：该测试将标准输入输出接入管道，并通过普通 Node 运行构建后的 `lib/bin.js`（e2e Vitest 的 include 包含 `apps/cli/tests`）。`cli-demo`、`acp-demo` 和 `jsonrpc-demo` 保留各自的 bin，因为它们分别提供 `dsh` 所没有的独立接口（headless、ACP（Agent Client Protocol）、JSON-RPC）。
+
+## 包拓扑
+
+参数解析留在 `apps/cli`（组装层）内，而不是 `packages/*` 库中：它是这一个应用自身的路由，而非可复用的 seam。`dsh-app-boot` 收缩为纯粹的 boot 胶水代码，不再承担 CLI 解析职责。`commander@^15` 被加入 `apps/cli/package.json`，与 SDK bin 锁定的版本一致。
+
+## 考虑过的替代方案
+
+**保留 `node:util` `parseArgs`，只统一分发。** 已否决：`parseArgs` 没有子命令模型、没有渲染出的帮助、也没有版本标志，因此 `web` 路由和 `--help`/`--version` 仍将保持手写。本仓库其他 CLI 已经选择了 Commander；单独为 `dsh` 引入第二套解析器方式，正是这次变更要消除的碎片化。
+
+**保留 `parseResumeArg` 作为共享辅助函数，并向它喂入 Commander 的残余参数。** 已否决：整件事的核心就是要退役这个定制扫描器。Commander 原生解析 `--resume`（空格和 `=` 形式、缺值、位置无关性）；为这一个标志保留一条平行的手写路径，只会保留这次变更要终结的重复。
+
+**使用裸 `dsh <config>` 位置参数指定替代配置树。** 已否决：根级位置参数与真正的 `web` 子命令无法在同一个 Commander 程序中共存（子命令会占用第一个位置参数）。位置参数会迫使系统把位于首位的 `web` 作为保留 token 分发给另一个解析器，并手工维护一行 `web` 文本，供 `--help` 显示。只有演示和测试调用点需要指定替代配置树，因此 `--config` 标志既能满足这些调用点，又能让默认接口不包含位置参数；这样，`web` 就能在单个程序中成为普通子命令，并由原生 `--help` 展示。
+
+**把参数解析做成 `packages/*` 的 seam。** 已否决：`dsh` 之外没有任何消费方使用它，而能力 seam 不应被提前拆分。这个 Commander 适配器是 `apps/cli` 自身的事务。
+
+**保留 `RESUME_SESSION_ID` 作为恢复通道**：不予采纳。`--resume` 已被解析成 bin 当前持有的值；若再通过环境变量传递并由配置重新读取，只会引入无益的间接层，还会使演示 bin 保留第二条仅依赖环境变量的恢复路径。在启动上下文中提供 id，与 `boot` 的 `prepare` 钩子为 `tuiResumeHost` 提供值所采用的是同一通道。
+
+**保留 `dsh-tui-demo` bin**：不予采纳。它与 `dsh --config <path>` 的功能完全重复；保留它还会迫使演示专用的 `RESUME_SESSION_ID` 回退路径继续存在。配置实际挂载的是该包的插件；冗余的只有作为终端入口的 bin，而 `dsh` 是唯一的终端入口。
+
+## 测试
+
+`apps/cli/tests/args.spec.ts`（新增；`apps/*/tests` 加入 vitest include，`apps/cli/tests` 加入 `tsconfig.host.json`）覆盖适配器的关键行为：根据参数形态进行模式路由（包括 `web --dev` 和 host/port 透传），并通过 `process.exit` spy 捕获适配器的显式报错检查（恢复 id 或提示词为空、`--prompt` 与配置或 `--resume` 混用、未知选项、多余的位置参数）以及 `--help`/`--version` 的退出码。host/port 的有效性由 webserver schema 负责，并由 web 冒烟测试在启动时验证，不属于适配器测试的覆盖范围。`examples/tui-agent/tests/tui-keyless-smoke.e2e.ts` 中的两组 PTY 冒烟测试现在都驱动真实的 `apps/cli/src/bin.ts`：`tui-agent` 组通过 `--config` 启动示例树，`dsh CLI` 组覆盖默认启动、个人覆盖、无效配置、配置对 `--resume` 的接收、通过 `process.execve` 原地恢复交接，以及包含源码路径的系统提示词。`examples/cordis-agent/tests/keyless-smoke.e2e.ts` 同样通过 `dsh` 启动。`packages/ui/app-boot/tests/app-boot.spec.ts` 移除其 `parseResumeArg` 和 `replaceResumeArg` 测试块；TUI 单元测试和快照 fixture（测试前置数据）使用 `dsh --resume {session}` 恢复命令。
+
+## 影响
+
+`dsh` 会渲染 `--help`/`--version`，并以一致方式显式报告解析错误；模式路由不依赖标志位置。argv 解析集中在一处，并与 SDK bin 共用一套解析器方式，代价是 `apps/cli` 依赖 `commander`，且 Commander 的解析语义（错误字符串和 `exitOverride` 契约）成为 CLI 入口的一部分。`dsh-app-boot` 不提供任何 CLI 解析接口；需要 `--resume` 式解析的消费方通过组合 Commander 来实现。会话恢复通过启动上下文完成，而不使用环境变量；`dsh` 是唯一的终端入口；`dsh-tui-demo` 包是由配置挂载的插件组合包。

.agents/notes/archived/bug-fix/2026-07-20-code-mode-result-card-completeness.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
+2026-07-20-code-mode-result-card-completeness.md: aff755e40b238e7ee448013fe0063bb26450fffe
+2026-07-20-code-mode-result-card-completeness.zh.md: 275e870c4be73e1adaa485f4e9fb979054fbf7c2

.agents/notes/archived/bug-fix/2026-07-20-code-mode-result-card-completeness.md

@@ -0,0 +1,40 @@
+# Agent Note: Keep the Code Mode result card complete
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-20-code-mode-result-card-completeness.zh.md)
+
+## Problem
+
+The outer `run_code` tool persisted complete rendered content, but its UI presenter ignored that content and rebuilt the card body from a logs-only `presentationMeta` projection. A result-only run appeared correct because an empty presenter body let consumers fall back to `tool/result.content`. Once the program emitted a log, the presenter supplied non-empty content, that fallback stopped, and the returned value disappeared from the completed card. A spill policy's final head/tail preview was vulnerable to the same split ownership whenever captured logs made the stale projection non-empty.
+
+Nested Code calls never owned cards, so producing metadata for the outer call solely to reconstruct one incomplete card also obscured the intended one-card boundary.
+
+## Decision
+
+The canonical tool registry pipeline owns the final model-facing outer content. On success, the `run_code` output renderer renders captured logs followed by the return value or the explicit no-output marker. Runtime failures and pre-execution policy denials are normalized into error content by `ToolRegistry` without invoking that renderer. A post-execute block runs after successful rendering and replaces the result with error content; other post-execute policy and spill decisions may replace content before persistence.
+
+`run_code` omits `presentResult`. The established generic result fallback keeps the pending program title and renders the raw final `tool/result.content`; that durable, replayable, post-policy projection is the card's only result-content source. The host API proxy therefore omits a separate result view instead of serializing the same content in both `event.data.content` and `view.view.content`. The redundant logs-only `presentationMeta` projection remains removed.
+
+Nested dispatch remains unchanged. Calls marked by `exec.parent` emit `tool/code-dispatch` events (full rendered content) but no `tool/call` or `tool/result` surface cards, so one outer `run_code` invocation still produces exactly one card.
+
+## Testing
+
+Tool unit coverage drives logs-only, result-only, logs-plus-result, no-output, spilled-result, and failure outcomes through the canonical registry, then pins the durable content and absence of a result presenter. A host-mux regression uses a call-only presenter to prove the result frame carries raw content exactly once and no view. These cases prove stale metadata cannot replace final content without making the host duplicate that content.
+
+The keyless ACP backend and TUI Code Mode snapshots execute one outer program that performs two nested bash calls, logs `captured output`, and returns `CODE_ONE+CODE_TWO`. The persisted ACP log pins the complete result; the TUI surface shows one completed outer card containing both lines and no nested cards.
+
+## Alternatives considered
+
+**Append the return value to logs metadata.** Rejected because metadata would duplicate the renderer, need a second stable formatting contract for every JSON root, and still miss post-policy content replacement or spill previews.
+
+**Merge presenter metadata with `result.content`.** Rejected because the rendered content already contains the logs; merging would duplicate them and require brittle deduplication.
+
+**Forward `result.content` through a generic result presenter.** Rejected because the durable event already carries that content and UI consumers already have a generic raw-content fallback. The host mux serializes a tool-owned result view beside the event, so forwarding would duplicate the rendered content in one frame merely to recreate the fallback; the default worker alone admits a 64 MiB variable-payload budget before rendering.
+
+**Create one card per nested dispatch.** Rejected because intermediate values are intentionally execution-local and never model-facing. Multiple cards would expose an implementation trace instead of the single Code Mode operation the model and user invoked.
+
+## Consequences
+
+TUI and JSON-RPC/Web display the same complete content the model receives and replay persists, including post-policy spill previews, through their generic result fallback. The host API retains the pending program title without duplicating the raw result in a separate view payload. New `run_code` results no longer carry the optional logs metadata, but this requires no session-format bump: existing records remain valid because presentation reads their durable rendered content.

.agents/notes/archived/bug-fix/2026-07-20-code-mode-result-card-completeness.zh.md

@@ -0,0 +1,40 @@
+# Agent Note: 保证 Code Mode 结果卡片内容完整
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-20-code-mode-result-card-completeness.md) | 中文
+
+## 问题
+
+外层 `run_code` 工具会持久化完整的渲染内容，但其 UI 展示器忽略了这些内容，转而根据仅含日志的 `presentationMeta` 投影重新构建卡片正文。仅有结果的运行看似正确，是因为展示器正文为空时，消费方会回退到 `tool/result.content`。只要程序输出一条日志，展示器就会提供非空内容，回退随即停止，返回值便会从完成态卡片中消失。当已捕获的日志使陈旧投影变为非空时，输出落盘策略最终生成的头尾预览也会受到同一职责拆分的影响。
+
+嵌套 Code 调用从不生成自己的卡片。因此，仅仅为了重建这一张不完整卡片而给外层调用生成元数据，还掩盖了每次外层调用只生成一张卡片的预期边界。
+
+## 决策
+
+规范的工具注册表流水线负责最终面向模型的外层内容。成功时，`run_code` 输出渲染器先渲染已捕获的日志，然后渲染返回值或显式的无输出标记。运行时失败和执行前策略拒绝由 `ToolRegistry` 归一化为错误内容，过程中不会调用该渲染器。Post-execute 阻断发生在成功渲染之后，并把结果替换为错误内容；其他 post-execute 策略与输出落盘决策可以在持久化之前替换内容。
+
+`run_code` 不提供 `presentResult`。既有的通用结果回退机制会保留待完成的程序标题，并渲染原始的最终 `tool/result.content`；这一持久、可回放且经过 post-policy 处理的投影是卡片中结果内容的唯一来源。宿主 API 代理因此不提供单独的结果视图，而不会在 `event.data.content` 与 `view.view.content` 中重复序列化同一内容。冗余的仅含日志的 `presentationMeta` 投影继续保持移除状态。
+
+嵌套分发保持不变。带有 `exec.parent` 标记的调用会发出 `tool/code-dispatch` 事件（携带完整渲染内容），但不会生成与 `tool/call` 或 `tool/result` 对应的界面卡片，因此一次外层 `run_code` 调用仍然只会生成一张卡片。
+
+## 测试
+
+工具单元测试通过规范注册表覆盖仅有日志、仅有结果、日志与结果并存、无输出、结果落盘和失败的结果，然后固定持久内容以及结果展示器不存在这一事实。宿主 mux 回归测试使用仅有调用的展示器，证明结果帧恰好携带一次原始内容，且不含视图。这些案例证明陈旧元数据无法替换最终内容，同时不会让宿主重复该内容。
+
+无密钥的 ACP（Agent Client Protocol）后端快照与 TUI Code Mode 快照会执行一个外层程序：程序进行两次嵌套 bash 调用，记录 `captured output`，并返回 `CODE_ONE+CODE_TWO`。ACP 持久化日志固定完整结果；TUI 界面只显示一张完成态外层卡片，其中包含这两行内容，且没有嵌套卡片。
+
+## 备选方案
+
+**把返回值追加到日志元数据：**不予采纳。元数据会与渲染器重复，并且需要为每一种 JSON 根另行维护稳定的格式化契约；post-policy 内容替换或输出落盘预览仍然会被遗漏。
+
+**把展示元数据与 `result.content` 合并：**不予采纳。渲染内容已经包含日志；合并会造成重复，还需要依赖脆弱的去重逻辑。
+
+**通过通用结果展示器转发 `result.content`：**不予采纳。持久事件已经携带该内容，UI 消费方也已有通用的原始内容回退机制。宿主 mux 会在事件旁序列化工具拥有的结果视图，因此转发仅仅是为了重建该回退机制，却会在一个帧中重复渲染内容；仅默认 worker 在渲染前允许 64 MiB 的可变载荷预算。
+
+**为每次嵌套分发创建一张卡片：**不予采纳。中间值有意只存在于执行期间，永远不面向模型。多张卡片会暴露实现轨迹，而不是模型与用户调用的单次 Code Mode 操作。
+
+## 影响
+
+TUI 与 JSON-RPC／Web 通过通用结果回退机制显示与模型接收及回放持久化相同的完整内容，其中包括 post-policy 输出落盘预览。宿主 API 保留待完成的程序标题，同时不在单独的视图负载中重复原始结果。新的 `run_code` 结果不再携带可选的日志元数据，但无需提升会话格式版本：现有记录仍然有效，因为展示逻辑会读取其中持久化的渲染内容。

.agents/notes/archived/bug-fix/2026-07-22-collapsed-sidebar-control-rail.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
+2026-07-22-collapsed-sidebar-control-rail.md: 6b61f5c64f3f1db19a2e242e9d9f054f30cb470c
+2026-07-22-collapsed-sidebar-control-rail.zh.md: b487950fc2c261060c44ad5b0ddc5820ca326006

.agents/notes/archived/bug-fix/2026-07-22-collapsed-sidebar-control-rail.md

@@ -0,0 +1,30 @@
+# Agent Note: A collapsed sidebar retains its control rail
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-22-collapsed-sidebar-control-rail.zh.md)
+
+## Problem
+
+The sidebar close action persisted a zero width preference, and the layout mapped that preference to a zero-width grid track. The only sidebar toggle and the settings entry both lived inside that clipped track, so closing the sidebar removed every visible recovery control. Reloading preserved the closed preference and reproduced the lockout.
+
+## Decision
+
+The layout maps a closed sidebar (persisted width `0`) to the fixed `SIDEBAR_COLLAPSED` width of 56px: a 24px icon column between the sidebar's 16px horizontal paddings. The sidebar track is fixed-width in the solver — open or collapsed it never concedes to viewport pressure (only details shrinks, then auto-closes) — and the rail retains its right border while the stored expanded width remains untouched.
+
+`AppFrame` marks the sidebar collapsed from the persisted width preference rather than from the resolved track width, removes the resize handle while collapsed, and passes `collapsed` to the sidebar slot as owner props from the render site. Collapse and expand animate: the frame transitions `grid-template-columns` (and the remaining handle its `left`) on the deepsuite sider curve — `--ds-ease-in-out` over `--ds-transition-duration-slow`, both supplied by ui-theme's base sheet; transitions pause during drags and under `prefers-reduced-motion`.
+
+`SidebarRoot` reads the owner `collapsed` prop and transitions as a slide + crossfade: the expanded content freezes at its width (inline style) and fades out in place over 150ms while the sliding grid column clips it — nothing reflows mid-slide. At settle the wide-only content (brand, labels, input, session tree) unmounts — dropping the sessions subscription and leaving the rendered and accessibility trees — and the control rows snap to the rail (open toggle, new session, new workspace, search, the same top-down order as their expanded rows) fading in as the slide ends. Each rail control keeps its expanded counterpart's behavior (the search icon expands the sidebar and focuses the search box after the slide), carries a tooltip, and the toggle rests as the whale mark with the panel icon on hover. The search query lives with the root and survives the round trip.
+
+## Alternatives considered
+
+- **Render an expand button over the center column** — rejected because it recovers only the toggle, not the persistent settings area, and splits sidebar chrome across two package owners.
+- **Keep a zero-width grid track and let the rail overflow it** — rejected because the rail would overlap the center column and leave hit testing and responsive geometry disconnected from the grid.
+- **Keep the complete sidebar tree mounted and hide it with clipping** — rejected because hidden controls remain in the semantic tree and continue subscribing and rendering even though only two controls belong in the collapsed state.
+
+## Consequences
+
+- A collapsed sidebar reserves 56px instead of yielding the entire width to the center column. Expanding restores the persisted width and drag behavior.
+- The settings entry remains visible but retains its existing placeholder behavior; this change does not introduce an account or settings screen.
+- Layout solver tests pin the compact width, sidebar component tests pin the visible controls, and the keyless real-bundle web smoke test pins collapse and recovery through the assembled client.

.agents/notes/archived/bug-fix/2026-07-22-collapsed-sidebar-control-rail.zh.md

@@ -0,0 +1,30 @@
+# Agent Note: 侧边栏折叠后保留控制栏
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-22-collapsed-sidebar-control-rail.md) | 中文
+
+## 问题
+
+侧边栏关闭操作会持久化宽度偏好 `0`，布局再将该偏好映射为宽度为零的网格轨道。侧边栏唯一的开关与设置入口都位于这个被裁切的轨道内，因此关闭侧边栏会移除所有可见的恢复控件。页面重新加载时仍会读取关闭偏好，从而再次陷入无法恢复的状态。
+
+## 决策
+
+布局将关闭的侧边栏（持久化宽度为 `0`）映射为固定的 `SIDEBAR_COLLAPSED` 宽度 56px：在侧边栏两侧各 16px 的水平内边距之间放置一列 24px 的图标控件。侧边栏轨道在求解器中是定宽的——无论展开还是折叠都不向视口压力让步（只有 details 会收缩、继而自动关闭）；控制栏保留右侧边框，已存储的展开宽度保持不变。
+
+`AppFrame` 根据持久化的宽度偏好标记侧边栏是否折叠，而不是根据求解后的轨道宽度来判断；折叠时移除尺寸调整手柄，并在渲染点把 `collapsed` 作为 owner props 传给侧边栏插槽。折叠与展开带动画：frame 对 `grid-template-columns`（以及余下手柄的 `left`）应用 deepsuite 侧栏曲线过渡——`--ds-ease-in-out` 配 `--ds-transition-duration-slow`，两个变量由 ui-theme 的 base 表提供；拖拽期间和 `prefers-reduced-motion` 下过渡暂停。
+
+`SidebarRoot` 读取 owner 的 `collapsed` 属性，过渡是滑动 + 交叉淡变：展开内容以内联样式冻结在原宽度、150ms 原地淡出，滑动中的网格列裁切它——滑动途中不发生任何重排。settle 时宽态专属内容（品牌标识、文字标签、输入框、会话树）卸载——随之退订会话列表并离开渲染树与可访问性树——控件行落位到控制栏（打开开关、新建会话、新建工作区、搜索，自上而下与展开态各行顺序一致），随滑动结束淡入。每个控制栏控件保持与展开态对应控件一致的行为（搜索图标展开侧边栏并在滑动结束后聚焦搜索框）并带 tooltip；开关静止时显示鲸鱼标，悬停切换为面板图标。搜索关键词由根组件持有，折叠往返后保留。
+
+## 曾考虑的替代方案
+
+- **在中心列上方渲染展开按钮**：不予采纳，因为这只能恢复开关，无法保留常驻设置区域，同时还会让侧边栏 UI 由两个包（package）分别持有。
+- **保留宽度为零的网格轨道，让控制栏溢出显示**：不予采纳，因为控制栏会与中心列重叠，还会使命中测试和响应式几何关系脱离网格布局。
+- **保持完整侧边栏树挂载，并通过裁切将其隐藏**：不予采纳，因为隐藏控件仍留在语义树中，而且会继续订阅和渲染，尽管折叠状态下只需要两个控件。
+
+## 后果
+
+- 折叠的侧边栏占用 56px，而不是把全部宽度让给中心列。展开时恢复持久化宽度与拖动行为。
+- 设置入口持续可见，但保留既有占位行为；本次改动不提供账户或设置页面。
+- 布局求解器测试固定紧凑宽度，侧边栏组件测试固定可见控件，基于真实构建产物的无密钥 Web 冒烟测试则通过组装后的客户端固定折叠与恢复行为。

.agents/notes/archived/bug-fix/2026-07-23-demo-web-builds-client-bundles.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
+2026-07-23-demo-web-builds-client-bundles.md: abd031c4ee6aeb7ed8c0baa61dfac16e5d64cc33
+2026-07-23-demo-web-builds-client-bundles.zh.md: 70604b344b5607b01815382da316805a9beaf27e

.agents/notes/archived/bug-fix/2026-07-23-demo-web-builds-client-bundles.md

@@ -0,0 +1,28 @@
+# Agent Note: demo:web builds the client plugin bundles
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-23-demo-web-builds-client-bundles.zh.md)
+
+## Problem
+
+`dsh web` serves each web-client plugin's bundle from `GET /plugins/<id>/client.js`, resolving the path from the package's `exports["./client"]` (`lib/client.js`). Those bundles are produced only by the root `pnpm run build` (`tsc -b` then the per-package `tsdown.client.ts` configs); the Vite `build:web` step builds the frontend shell alone. `demo:web` and the README's Web UI instructions ran only `build:web`, so on a checkout without a prior full build every plugin bundle 404s, the client loader marks every plugin failed, and the boot screen shows "Failed to load plugins". The frontend shell built fine, hiding the missing artifact behind a runtime browser failure.
+
+## Decision
+
+`demo:web` runs `npm run build` before `npm run build:web`, so the plugin `lib/client.js` bundles exist before `dsh web` serves them. The README's Web UI section runs `pnpm run build && pnpm run build:web` for the installed `~/.dsh/source` checkout, which the installer never builds.
+
+## Verification
+
+After the full build, all eight `/plugins/<id>/client.js` endpoints return 200 and a headless Chromium load of `http://127.0.0.1:3080` renders the shell with no "Failed to load plugins" state.
+
+## Alternatives considered
+
+**Build the bundles inside `dsh web` at startup.** The app runs from source via tsx and owns no build step; folding an artifact build into the server boot crosses the source/artifact separation and slows every launch.
+
+**Widen the tsdown root config to emit client bundles from `pnpm run build:web`.** `build:web` is the Vite frontend build; the client bundles are a separate tsdown pass over `lib/types`. Merging the two conflates the shell build with the package build and still leaves the root `build` as the only producer.
+
+## Consequences
+
+`demo:web` now pays the full `tsc -b && tsdown` cost on every invocation instead of only the Vite build. That is the price of a runnable web demo from a clean tree; a caller who already built can invoke `dsh web` directly.

.agents/notes/archived/bug-fix/2026-07-23-demo-web-builds-client-bundles.zh.md

@@ -0,0 +1,28 @@
+# Agent Note: demo:web 构建客户端插件的打包产物
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-23-demo-web-builds-client-bundles.md) | 中文
+
+## Problem
+
+`dsh web` 通过 `GET /plugins/<id>/client.js` 提供每个 web 客户端插件的打包产物，其路径由包的 `exports["./client"]`（`lib/client.js`）解析得到。这些打包产物只由根目录的 `pnpm run build`（先 `tsc -b`，再执行各包的 `tsdown.client.ts` 配置）生成；Vite 的 `build:web` 步骤只构建前端外壳。`demo:web` 与 README 的 Web UI 说明只运行了 `build:web`，因此在未预先完整构建的检出上，每个插件的打包产物都返回 404，客户端 loader 将所有插件标记为失败，启动界面显示 "Failed to load plugins"。前端外壳能正常构建，把缺失的产物掩藏在浏览器运行时的失败背后。
+
+## Decision
+
+`demo:web` 在 `npm run build:web` 之前先运行 `npm run build`，使插件的 `lib/client.js` 打包产物在 `dsh web` 提供它们之前已经存在。README 的 Web UI 小节针对已安装的 `~/.dsh/source` 检出运行 `pnpm run build && pnpm run build:web`，因为安装器从不构建它。
+
+## Verification
+
+完整构建后，全部八个 `/plugins/<id>/client.js` 端点均返回 200，无头 Chromium 加载 `http://127.0.0.1:3080` 能渲染出外壳，不再出现 "Failed to load plugins" 状态。
+
+## Alternatives considered
+
+**在 `dsh web` 启动时构建打包产物。** 该应用通过 tsx 从源码运行，本身没有构建步骤；把产物构建塞进服务器启动流程会越过源码与产物的分离，并拖慢每次启动。
+
+**扩大 tsdown 根配置，使 `pnpm run build:web` 也产出客户端打包产物。** `build:web` 是 Vite 前端构建；客户端打包产物是对 `lib/types` 的另一趟独立 tsdown 处理。把两者合并会混淆外壳构建与包构建，而且根目录的 `build` 仍是唯一的产出者。
+
+## Consequences
+
+`demo:web` 现在每次调用都要付出完整的 `tsc -b && tsdown` 代价，而不再只是 Vite 构建。这是从干净的代码树运行 web 演示所要付出的代价；已经完成构建的调用方可以直接调用 `dsh web`。

.agents/notes/archived/bug-fix/2026-07-23-thinking-row-disclosure-target.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
+2026-07-23-thinking-row-disclosure-target.md: 9f748b6d76b9ddfe657e56da9f9e7f576b05599e
+2026-07-23-thinking-row-disclosure-target.zh.md: e33c951ca33e032e2eb2d306d90979d1e8471a17

.agents/notes/archived/bug-fix/2026-07-23-thinking-row-disclosure-target.md

@@ -0,0 +1,30 @@
+# Agent Note: Thinking rows use one disclosure target
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-23-thinking-row-disclosure-target.zh.md)
+
+## Problem
+
+A collapsed reasoning entry presents `Think` and its one-line reasoning summary as one visual row, but an icon-only disclosure control leaves both visible labels inert. Applying title expansion to every tool row would instead break the generic tool-row contract, where the row opens details and only the leading control expands arguments.
+
+## Decision
+
+`ToolRow` exposes the opt-in `expandOnRowClick` policy. `ThinkRow` enables it so the title and reasoning summary form one accessible disclosure target; pointer clicks, Enter, and Space toggle the same component-local expanded state. Tool rows that do not opt in retain row-to-details selection and leading-control argument expansion.
+
+## Verification
+
+The component spec pins both Think click targets and the unchanged generic tool-row handoff. The keyless browser fixture loads the real sidebar and conversation bundles, opens an authored reasoning session, clicks the summary and title, and checks the disclosure state and expanded body.
+
+## Alternatives considered
+
+**Expand every tool row from its title.** Generic tool rows use row clicks for details selection, so sharing this behavior would conflate two controls.
+
+**Keep icon-only disclosure.** The smallest hit target remains disconnected from the labels that describe the hidden content.
+
+**Render separate title and summary buttons.** Two controls for one expanded state add duplicate focus stops and ambiguous semantics.
+
+## Consequences
+
+Thinking rows gain a larger pointer target and keyboard disclosure semantics without changing other tool interactions. The generic row component carries one optional policy because disclosure ownership differs between reasoning and tool calls.

.agents/notes/archived/bug-fix/2026-07-23-thinking-row-disclosure-target.zh.md

@@ -0,0 +1,30 @@
+# Agent Note: thinking 行使用单一展开目标
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-23-thinking-row-disclosure-target.md) | 中文
+
+## 问题
+
+折叠的推理（reasoning）条目在同一视觉行中呈现 `Think` 和单行推理摘要，但仅图标可展开会让两个可见标签都无法交互。若让所有工具行均可通过标题展开，又会破坏通用工具行的契约：整行负责打开详情，只有前导控件负责展开参数。
+
+## 决策
+
+`ToolRow` 提供显式启用的 `expandOnRowClick` 策略。`ThinkRow` 启用该策略，让标题和推理摘要组成单一且无障碍的展开目标；鼠标点击、Enter 和 Space 都切换同一个组件本地展开状态。未启用该策略的工具行仍由整行完成详情选择，由前导控件展开参数。
+
+## 验证
+
+组件测试固定两个 Think 点击目标以及未改变的通用工具行交接行为。无密钥浏览器 fixture（测试前置数据）加载真实的侧边栏与会话 bundle，打开包含推理内容的既定会话，点击摘要与标题，并检查展开状态和展开后的正文。
+
+## 考虑过的替代方案
+
+**让每个工具行都可通过标题展开。** 通用工具行将整行点击用于详情选择，共享这一行为会混淆两个控件。
+
+**保留仅图标展开。** 最小的点击目标仍与描述隐藏内容的标签脱节。
+
+**把标题和摘要分别渲染为按钮。** 两个控件共享一个展开状态，会增加重复的焦点停靠点并产生含糊语义。
+
+## 后果
+
+thinking 行获得更大的鼠标点击目标和键盘展开语义，同时不改变其他工具交互。通用行组件承担一个可选策略，因为推理与工具调用的展开所有权不同。

.agents/notes/archived/bug-fix/2026-07-26-intent-draft-same-tick-echo.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
+2026-07-26-intent-draft-same-tick-echo.md: 3ef91b123f9abe0817bf5f7e1ad48e2e6f1e2cb3
+2026-07-26-intent-draft-same-tick-echo.zh.md: d890a68f4b9c83713b7a52c44ecb6bcd16265669

.agents/notes/archived/bug-fix/2026-07-26-intent-draft-same-tick-echo.md

@@ -0,0 +1,28 @@
+# Agent Note: Intent draft echoes in the same tick
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-26-intent-draft-same-tick-echo.zh.md)
+
+## Problem
+
+The hero composer ("Let's start building") is a controlled textarea whose value is the frontend Session Intent's retained prompt, read from the sessions **list** snapshot (`EmptyState` binds `intent.prompt` via `useSessions`). Typing routed through `SessionManager.updateIntent → Session.updatePendingPrompt`, which flushes the **Session's own** notifier synchronously — but the list snapshot the composer actually renders from only heard about the change through the intent watch subscription in `startIntent`, which calls `markDirty()`, a microtask-deferred flush.
+
+A deferred echo violates the controlled-input contract documented on the Notifier (see the [web client architecture note](../architecture/2026-07-19-gui-web-client-architecture.md)): React compares the DOM value against the still-stale snapshot during the same tick as `onChange` and rolls the textarea back. With plain typing this shows as caret jumps; with an IME it corrupts input — every composition update gets rolled back and re-applied against a stale value, so typing Pinyin "nihao" commits fragments like "nnini hni hani hao你好". The resident composer (`ConversationRoot`) was not affected: its draft lives in the chat store (sync flush) or comes from `updateSessionPrompt`, which reads the Session snapshot directly rather than the list projection.
+
+## Decision
+
+`SessionManager.updateIntent` calls `this.notifier.notifyNow()` after `updatePendingPrompt`, flushing the list snapshot in the same tick as the change event. This matches the Notifier's channel rule: a direct echo of a user gesture whose controlled input renders from this snapshot uses `notifyNow`; the intent watch keeps `markDirty` for every other (async) intent transition.
+
+## Alternatives considered
+
+**Change the intent watch callback in `startIntent` to `notifyNow`.** Wrong channel for that seam: the watch also fires on frame-driven Session changes (publication, send phases), and the architecture note bans `notifyNow` for frame-driven sources because it collapses batching.
+
+**Have `EmptyState` read the prompt from the Session snapshot instead of the list.** Restructures the slot contract (EmptyState is deliberately bound to the standard `useSessions` feed and has no session scope yet — the frontend Session is page-local) for no gain over flushing the projection it already reads.
+
+**Suppress the rollback in `InputBar` with local uncontrolled state.** Hides the symptom, forfeits the single-source-of-truth draft (the retained prompt must survive workspace retargeting and send/retry), and leaves every other list-snapshot-controlled input exposed.
+
+## Consequences
+
+Typing in the hero composer, IME composition included, echoes synchronously. `updateIntent` on a no-intent state stays a no-op with no notification. The web workspace-flow snapshot's composer helper now asserts the same-tick echo instead of waiting for it, so a regression to a deferred echo fails the keyless snapshot gate; a runtime unit test pins the same contract at the manager seam.

.agents/notes/archived/bug-fix/2026-07-26-intent-draft-same-tick-echo.zh.md

@@ -0,0 +1,28 @@
+# Agent Note: Intent draft echoes in the same tick
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-26-intent-draft-same-tick-echo.md) | 中文
+
+## Problem
+
+hero composer（「Let's start building」）是一个受控（controlled）的 textarea，它的值取自前端 Session Intent 保留下来的提示词，读自会话**列表**快照（`EmptyState` 通过 `useSessions` 绑定 `intent.prompt`）。输入经由 `SessionManager.updateIntent → Session.updatePendingPrompt`，后者会同步刷新 **Session 自身的** notifier——但 composer 实际渲染所依据的那份列表快照，只能通过 `startIntent` 中的 intent watch 订阅得知这次变更，而该订阅调用的是 `markDirty()`，即一次延迟到微任务的刷新。
+
+延迟的回显违反了 Notifier 上所记录的受控输入契约（见 [web 客户端架构笔记](../architecture/2026-07-19-gui-web-client-architecture.md)）：React 在与 `onChange` 相同的 tick 内，把 DOM 值与仍然陈旧的快照相比对，随后把 textarea 回滚。普通输入时，这表现为光标跳动；使用输入法（IME）时，它会损坏输入——每一次 composition 更新都会被回滚，并针对陈旧的值重新应用，因此输入拼音「nihao」会提交出类似「nnini hni hani hao你好」这样的片段。resident composer（`ConversationRoot`）不受影响：它的草稿存放在 chat store 中（同步刷新），或来自 `updateSessionPrompt`，后者直接读取 Session 快照，而不是列表投影。
+
+## Decision
+
+`SessionManager.updateIntent` 在 `updatePendingPrompt` 之后调用 `this.notifier.notifyNow()`，从而在与变更事件相同的 tick 内刷新列表快照。这符合 Notifier 的通道规则：当某个用户手势的受控输入正是从该快照渲染时，对它的直接回显使用 `notifyNow`；而 intent watch 对其余所有（异步的）intent 状态转换仍保留 `markDirty`。
+
+## Alternatives considered
+
+**把 `startIntent` 中的 intent watch 回调改为 `notifyNow`。** 对那个 seam 而言是错误的通道：该 watch 也会在帧驱动的 Session 变更（发布、发送阶段）时触发，而架构笔记禁止对帧驱动的来源使用 `notifyNow`，因为那会瓦解批处理。
+
+**让 `EmptyState` 从 Session 快照而非列表读取提示词。** 这会重构槽位契约（EmptyState 有意绑定到标准的 `useSessions` 数据源，且尚无 session 作用域——前端 Session 是页面本地的），相比刷新它本就读取的那份投影并无收益。
+
+**在 `InputBar` 中用本地的非受控状态抑制回滚。** 这只是掩盖症状，放弃了单一真源的草稿（保留下来的提示词必须在工作区重定向以及发送／重试后依然存在），并让其余每一个由列表快照控制的输入都暴露在同一问题之下。
+
+## Consequences
+
+在 hero composer 中输入（包括输入法 composition 在内）会同步回显。在无 intent 的状态上调用 `updateIntent` 仍是一次空操作，不发出任何通知。web workspace-flow 快照的 composer 辅助函数现在断言的是同一 tick 内的回显，而不是等待它，因此一旦回退成延迟回显，就会让无密钥快照门禁失败；一个运行时单元测试在 manager 这一 seam 处钉住了同一份契约。

.agents/notes/archived/feature/2026-06-30-subagent-observe-enrich.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
+2026-06-30-subagent-observe-enrich.md: 7140616ac4a9725652ed779cba3d4232b6b5127b
+2026-06-30-subagent-observe-enrich.zh.md: 5cf81e9ace48650b834f2cf5e8ec7cc81b8b0e4d

.agents/notes/archived/feature/2026-06-30-subagent-observe-enrich.md

@@ -0,0 +1,32 @@
+# Agent Note: Subagent lifecycle enrichment — lastAssistantMessage (observe-only)
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-06-30-subagent-observe-enrich.zh.md)
+
+## Problem
+
+The hooks subsystem ([interception seams Agent Note](2026-06-30-interception-seams.md)) lets a plugin observe and gate the agent at lifecycle points. Claude Code and Codex both expose **SubagentStart / SubagentStop** hooks, and CC's carry the subagent's final message. The harness already emits `subagent/start` and `subagent/end` lifecycle events ([the subagent capability-seam](2026-06-21-subagent-capability-seam.md)), but their payloads were minimal (`provider`, `id`, and on end `stopReason`) — not enough for a hooks bridge to report WHAT a subagent produced without separately reaching for the live run.
+
+This Agent Note enriches the end payload. It is deliberately **observe-only**: no control-flow change and no waterfall. A run-affecting subagent-stop decision (continuation, injection that changes the run) is a separate, larger redesign and stays out of scope.
+
+## Decision
+
+**Add `lastAssistantMessage` — the child's final output — to `SubagentRunEndInfo`.** On the settle path it is the readonly typed `SubagentResult.output`, so an observer sees what the child produced without holding the run. On an infrastructure rejection where no `SubagentResult` exists, it is absent and the event reports `stopReason: 'error'`. Providers and listeners are trusted same-process collaborators and honor the borrowed immutable payload contract.
+
+Both events stay plain **`emit`s**. Async `SubagentService.start()` attaches result observation to the ready provider run, emits `subagent/start`, and then returns the run; an in-process listener can therefore reach the published child via `ctx.agents.get(info.id)`, while a remote provider need not have a local registry entry. A rejected provider start emits neither event. The callbacks remain observe-only and per-listener containment keeps one bad subscriber from stranding a live run or starving later listeners.
+
+## Alternatives considered
+
+**An `agentType` subagent-kind label** (the harness analogue of CC's `subagent_type`) on the request + both lifecycle payloads — an earlier draft shipped it; dropped in review because it is a Claude-Code concept that does not fit our own seam (nothing here interprets it, and the only consumer was a CC-dialect bridge). The CC bridge instead feeds Claude Code's own default matcher value `"general-purpose"` for its SubagentStart/Stop `agent_type` matcher, so this Agent Note ships ONE enrichment: `lastAssistantMessage`.
+
+**A control-flow `subagent/end`** — deferred; see below.
+
+## Why observe-only, and what is deferred
+
+A control-flow `subagent/end` (an awaited waterfall returning a stop/continue decision, like the other interception seams) would require: reshaping `subagent/end` from emit to waterfall, restructuring `SubagentService.start` to await listeners before settling, and implementing the `resume` capability in the in-process provider so a "continue" can actually re-run the child. That belongs to the background/steering subagent redesign the [capability-seam Agent Note](2026-06-21-subagent-capability-seam.md) already defers (the same redesign that unifies long-running-tool handling across subagents and bash). This Agent Note ships the observe-only enrichment a hooks bridge needs today; `FIXME(subagent-continuation)` / `TODO` anchors mark where the control-flow version would land if and when that redesign happens.
+
+## Consequences
+
+A hooks bridge (or a native plugin) can now forward the child's `lastAssistantMessage` to a SubagentStop handler by subscribing to the existing emits — no new control-flow surface. The vocabulary addition is documented in [docs/core-data-structures/subagent.md](../../../../docs/core-data-structures/subagent.md) (the events prose) and the two subagent READMEs; the catalog is regenerated. No production behavior changes — the events fire exactly as before, with one more (optional) field on the end payload — so no snapshot or e2e change is needed.

.agents/notes/archived/feature/2026-06-30-subagent-observe-enrich.zh.md

@@ -0,0 +1,32 @@
+# Agent Note: Subagent 生命周期丰富化——lastAssistantMessage（仅观察）
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-06-30-subagent-observe-enrich.md) | 中文
+
+## 问题
+
+钩子子系统（[拦截 seam Agent Note](2026-06-30-interception-seams.md)）允许插件在生命周期节点观察和拦截 agent（智能体）。Claude Code 和 Codex 都暴露了 **SubagentStart / SubagentStop** 钩子，且 CC 的钩子携带 subagent 的最终消息。harness 已经发出 `subagent/start` 和 `subagent/end` 生命周期事件（[subagent 能力 seam](2026-06-21-subagent-capability-seam.md)），但其载荷极为精简（`provider`、`id`，以及 end 时的 `stopReason`），不足以让钩子桥接层在不单独访问活跃 run 的情况下报告 subagent 产出了什么。
+
+本 Agent Note 丰富 end 载荷。它刻意限定为**仅观察**：不改变控制流，不引入 waterfall（瀑布式事件）。影响 run 的 subagent-stop 决策（续行、改变 run 的注入）属于另一个更大的重设计，不在本 Agent Note 范围内。
+
+## 决策
+
+**在 `SubagentRunEndInfo` 中添加 `lastAssistantMessage`——子 agent 的最终输出。** 在正常结束路径上，它是只读的类型化 `SubagentResult.output`，观察者无需持有 run 即可看到子 agent 产出了什么。在基础设施拒绝（不存在 `SubagentResult`）的情况下，该字段缺失，事件报告 `stopReason: 'error'`。提供方与监听方是受信任的同进程协作者，遵守借用不可变载荷的契约。
+
+两个事件仍为普通 **`emit`**。异步的 `SubagentService.start()` 将结果观察附加到就绪的提供方 run 上，发出 `subagent/start`，然后返回该 run；进程内监听方因此可以通过 `ctx.agents.get(info.id)` 访问已发布的子 agent，而远程提供方无需在本地注册表中有对应条目。提供方启动被拒绝时不发出任何事件。回调保持仅观察，且逐监听方隔离确保一个异常订阅者不会阻塞活跃 run 或饿死后续监听方。
+
+## 曾考虑的替代方案
+
+**`agentType` subagent 类别标签**（CC 的 `subagent_type` 在 harness 中的对应物），放在请求与两个生命周期载荷上。早期草案曾包含它；评审中移除，因为它是 Claude Code 的概念，不适合我们自己的 seam（此处没有任何逻辑解释它，唯一消费方是 CC 方言桥接层）。CC 桥接层改为直接为其 SubagentStart/Stop 的 `agent_type` matcher 填入 Claude Code 自身的默认值 `"general-purpose"`，因此本 Agent Note 只交付**一项**丰富化：`lastAssistantMessage`。
+
+**控制流式 `subagent/end`**：推迟；见下文。
+
+## 为何仅观察，以及推迟了什么
+
+控制流式 `subagent/end`（一个被 await 的 waterfall，返回停止/继续决策，与其他拦截 seam 一致）需要：将 `subagent/end` 从 emit 改为 waterfall、重构 `SubagentService.start` 使其在结算前 await 监听方、在进程内提供方中实现 `resume` 能力以便「继续」能真正重新运行子 agent。这属于[能力 seam Agent Note](2026-06-21-subagent-capability-seam.md) 已推迟的后台/steering（中途引导）subagent 重设计（同一个重设计还将统一 subagent 与 bash 之间的长时间运行工具处理）。本 Agent Note 交付钩子桥接层当前所需的仅观察丰富化；`FIXME(subagent-continuation)` / `TODO` 锚点标记了控制流版本在重设计发生时的落点。
+
+## 后果
+
+钩子桥接层（或原生插件）现在可以通过订阅既有 emit 将子 agent 的 `lastAssistantMessage` 转发给 SubagentStop 处理器，无需新的控制流接口。词汇新增记录在 [docs/core-data-structures/subagent.md](../../../../docs/core-data-structures/subagent.md)（事件行文部分）与两个 subagent README 中；catalog 已重新生成。生产行为无变化——事件触发方式与之前完全一致，end 载荷上多了一个可选字段——因此无需更新快照或 e2e 测试。

.agents/notes/archived/feature/2026-07-21-dsh-system-prompt-source-path.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-dsh-system-prompt-source-path.md: 9581966d10693e1ccbdce1a860314a34387e225e
+2026-07-21-dsh-system-prompt-source-path.zh.md: 392fcd44d988d483306effc34d4aaf4211803b4e

.agents/notes/archived/feature/2026-07-21-dsh-system-prompt-source-path.md

@@ -0,0 +1,38 @@
+# Agent Note: dsh tells the agent where its own source lives
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-21-dsh-system-prompt-source-path.zh.md)
+
+## Problem
+
+The `dsh` CLI is the self-referential surface: its `cordis` toolset lets the agent inspect and modify the very harness runtime it runs in. But the agent had no way to learn where that source lives on disk. `dsh` is normally symlinked onto PATH and launched from an arbitrary working directory — the project under work — so neither the cwd nor `argv` reliably points at the harness checkout. Without the path, "read your own source" is guesswork.
+
+## Decision
+
+The `dsh` launcher (`apps/cli/src/tui.ts`) computes the harness checkout root from its own module URL — `fileURLToPath(new URL('../../..', import.meta.url))`, three hops up from `apps/cli/{src,lib}` — so it resolves to the real source location however `dsh` is launched (a PATH symlink, an arbitrary cwd). After `boot()` settles the tree, the launcher calls the new `addHarnessSourceSection(ctx, sourceRoot)` helper from `dsh-app-boot`, which registers a global `harness:source` prompt section reading `Your own source code is the checkout at <path>; you can read it there to learn how dsh works and how to extend it.` The section orders at `-99`, just after the harness identity opener (`-100`) and before the deployment persona (`0`).
+
+The testable logic lives in `dsh-app-boot`, not in `apps/cli`, because `apps/*` are not coverage-gated and `packages/*` are. Resolving the optional `systemPrompt` service, registering the section, and returning the disposer belong where per-file 100% coverage applies; the launcher keeps only the thin glue — compute the path, call the helper — covered by the CLI's PTY e2e. When the booted tree has no `systemPrompt` service the helper is a no-op returning `undefined`.
+
+## Scope
+
+Only the `dsh` CLI adds this. The demo bins (`dsh-cli-demo`, `dsh-acp-demo`) boot their committed trees verbatim and gain no source section: they are not the self-modification surface, and their checkout root is not a fact the model needs.
+
+## HMR
+
+The section is registered against the booted `systemPrompt` service's own fiber (through `ctx.get('systemPrompt')`), so a dev HMR reload of the system-prompt plugin drops it until the next boot. Production HMR watches the config, not the built lib, so this is a dev-only wrinkle and acceptable.
+
+## Alternatives considered
+
+**Register the section inside the system-prompt service constructor.** It would then appear in every deployment, not just the self-referential CLI, and the source root would have to be threaded through config to reach the constructor. The path is a launcher fact, so the launcher owns injecting it.
+
+**Keep the whole thing in `apps/cli/src/tui.ts`.** Apps are not coverage-gated, so the registration and absent-service branches would ship untested. Extracting the tested helper into `dsh-app-boot` keeps the gate meaningful; the launcher glue is exercised by the CLI's keyless PTY smoke.
+
+**Add a cordis.yml config field for the path.** The path is not a deployment choice — it is mechanically the launcher's own location. A config field invites a stale hand-entered path and adds a knob with no legitimate variation.
+
+**Resolve from `process.cwd()` or `process.argv[1]`.** The cwd is the user's project, and a PATH symlink makes `argv[1]` the symlink path; `import.meta.url` is the only handle on the real source location.
+
+## Consequences
+
+The agent's system prompt now names its own checkout, so the `cordis` toolset can read and edit harness source with no discovery step. `dsh-app-boot` gains a type-only dependency on `dsh-system-prompt` (peer + dev, matching the acp package's side-effect type import) for the `ctx.get('systemPrompt')` declaration merge; there is no runtime dependency. The section is model-visible text, pinned verbatim in an app-boot unit test and asserted end to end through the CLI's keyless PTY smoke — which boots `dsh` against the scripted config, runs a turn, and reads the path back out of the persisted `request/header` system prompt. The line sits before per-request content, so it does not perturb the KV cache across turns.

.agents/notes/archived/feature/2026-07-21-dsh-system-prompt-source-path.zh.md

@@ -0,0 +1,38 @@
+# Agent Note: dsh 告知 agent 其自身源码所在位置
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-21-dsh-system-prompt-source-path.md) | 中文
+
+## Problem
+
+`dsh` CLI 是自我引用的接口：其 `cordis` 工具包让 agent（智能体）得以查看并修改它自身运行其上的 harness（智能体框架）运行时。但 agent 此前无从得知这份源码在磁盘上的位置。`dsh` 通常以符号链接的形式挂到 PATH 上，并从任意工作目录（正在处理的项目）启动，因此无论是 cwd 还是 `argv` 都无法可靠地指向 harness 检出目录。缺了这个路径，"读取你自己的源码"便只能靠猜。
+
+## Decision
+
+`dsh` 启动器（`apps/cli/src/tui.ts`）从它自身的模块 URL 计算 harness 检出根目录——`fileURLToPath(new URL('../../..', import.meta.url))`，从 `apps/cli/{src,lib}` 向上三级——因此无论 `dsh` 以何种方式启动（PATH 符号链接、任意 cwd），它都能解析到真实的源码位置。在 `boot()` 使插件树就位之后，启动器调用来自 `dsh-app-boot` 的新辅助函数 `addHarnessSourceSection(ctx, sourceRoot)`，它注册一个全局 `harness:source` 提示词段，内容为 `Your own source code is the checkout at <path>; you can read it there to learn how dsh works and how to extend it.`。该段的 order 为 `-99`，恰在 harness 身份开场（`-100`）之后、部署 persona（`0`）之前。
+
+可测试的逻辑放在 `dsh-app-boot` 而非 `apps/cli` 中，因为 `apps/*` 不受覆盖率门禁约束，而 `packages/*` 受约束。解析可选的 `systemPrompt` 服务、注册该段、返回 dispose（资源释放）器，这些都属于按文件 100% 覆盖率生效的地方；启动器只保留那层薄薄的黏合——计算路径、调用辅助函数——由 CLI 的 PTY e2e 覆盖。当就位的插件树没有 `systemPrompt` 服务时，该辅助函数是一个返回 `undefined` 的空操作。
+
+## Scope
+
+只有 `dsh` CLI 会加入这一段。demo bin（`dsh-cli-demo`、`dsh-acp-demo`）原样引导它们已提交的插件树，不会获得 source 段：它们不是自我修改的接口，其检出根目录也不是模型需要知道的事实。
+
+## HMR
+
+该段是针对就位后的 `systemPrompt` 服务自身的 fiber 注册的（通过 `ctx.get('systemPrompt')`），因此对 system-prompt 插件做一次开发态 HMR（热模块替换）重载会丢弃它，直到下一次引导为止。生产环境的 HMR 监视的是配置而非构建产物 lib，所以这只是一个仅限开发态的小瑕疵，可以接受。
+
+## Alternatives considered
+
+**在 system-prompt 服务的构造函数内注册该段。** 那样它会出现在每一个部署中，而不只是自我引用的 CLI，而且源码根目录还得穿过配置才能到达构造函数。这个路径是启动器的事实，所以由启动器负责注入它。
+
+**把整件事都留在 `apps/cli/src/tui.ts` 里。** apps 不受覆盖率门禁约束，因此注册逻辑与服务缺失分支会以未受测的形式发布。把受测的辅助函数抽取到 `dsh-app-boot` 让门禁保持有效；启动器的黏合部分由 CLI 的无密钥 PTY 冒烟测试演练。
+
+**为该路径新增一个 cordis.yml 配置键。** 这个路径不是一项部署选择——它在机制上就是启动器自身的位置。配置键会招致手工填入的路径变陈旧，并新增一个没有合理变化空间的旋钮。
+
+**从 `process.cwd()` 或 `process.argv[1]` 解析。** cwd 是用户的项目，而 PATH 符号链接会使 `argv[1]` 成为符号链接自身的路径；`import.meta.url` 是唯一能抓住真实源码位置的把手。
+
+## Consequences
+
+agent 的系统提示词现在会写明它自己的检出目录，因此 `cordis` 工具包无需一个发现步骤就能读取并编辑 harness 源码。`dsh-app-boot` 为 `ctx.get('systemPrompt')` 的声明合并新增了一个对 `dsh-system-prompt` 的仅类型依赖（peer dependency（对等依赖）+ dev，与 acp 包的副作用型类型 import 模式一致）；不存在运行时依赖。该段是模型可见文本，在 app-boot 单元测试中逐字锁定，并通过 CLI 的无密钥 PTY 冒烟测试端到端断言——该测试以脚本化配置引导 `dsh`、运行一个轮次，再从持久化的 `request/header` 系统提示词中把路径读回来。这一行位于按请求变化的内容之前，所以它不会在多个轮次间扰动 KV Cache。

.agents/notes/archived/feature/2026-07-21-tui-banner-brand-gradient.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-banner-brand-gradient.md: 3516b0dcf9b6949721ec3e0d062f2d135da21083
+2026-07-21-tui-banner-brand-gradient.zh.md: 6fd0f140d474d26860eef77d64d5df550709d940

.agents/notes/archived/feature/2026-07-21-tui-banner-brand-gradient.md

@@ -0,0 +1,40 @@
+# Agent Note: TUI banner brand gradient
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-21-tui-banner-brand-gradient.zh.md)
+
+## Problem
+
+The TUI startup banner rendered the product name `DEEPSEEK` in the palette's flat accent color, which carries no brand identity and does not resemble the wordmark on deepseek.com. The request was to make the banner match the site logo's blue gradient specifically — not to recolor the rest of the coding harness.
+
+The banner is the one surface where that matters, and it conflicts with a load-bearing invariant: the TUI palette is deliberately theme-agnostic. It uses only standard 16-color ANSI (SGR) codes and attributes so a user's terminal scheme remaps every color; the `themeViolations()` snapshot gate rejects any RGB, extended-palette, or explicit-background cell. A smooth logo-matching gradient cannot be built from 16 palette colors, so reproducing it requires 24-bit truecolor, which the gate flags by design.
+
+## Decision
+
+The banner paints `DEEPSEEK` with a per-letter 24-bit truecolor foreground sweeping the deepseek.com brand gradient — `#4D6BFE` → `#3982FF` → `#2498FF` — via piecewise-linear interpolation across those three stops; `HARNESS` stays bold with the default foreground. The gradient is foreground-only, so it stays legible on any terminal background, and it is confined to the banner's product name. This is the sole sanctioned exception to the theme-agnostic palette; every other surface remains standard-ANSI and theme-adaptive.
+
+The gradient is gated on `resolved.color && resolved.truecolor`. When truecolor is unavailable the banner falls back to the existing flat bright-blue accent, so nothing about the theme-agnostic guarantee or the recorded snapshots changes unless truecolor is explicitly in play.
+
+`truecolor` is a validated `Config` field with no schema default. When it is unset, `apply()` auto-detects it at the process boundary from `COLORTERM` (`truecolor` or `24bit`); an explicit config value always wins. Detection reads `process.env` only in `apply()` — never in the pure `resolveTuiConfig` resolver — keeping the resolver a pure function of its input.
+
+The gradient stops are fixed brand identity, treated like a protocol constant, so they are hardcoded in the plugin rather than exposed as a tunable. Whether truecolor is *enabled* is terminal- and deployment-varying, so that is the validated `Config` field. The banner text is UI-only and never reaches a model request, so no session event is required.
+
+## Testing
+
+A dedicated `banner-gradient` terminal snapshot pins the real per-letter RGB output in an xterm emulator (`fg=#4d6bfe`…`#2498ff`, each letter bold). The shared `checkpoint()` helper takes a `bannerGradient` flag: for that one checkpoint it asserts the theme violations are non-empty and that every violation ends in `rgb-fg` — i.e. truecolor is present but confined to the banner foreground, with no background or extended-palette leak. Every other checkpoint keeps the strict `themeViolations()` `.toEqual([])` assertion, so the fence is mechanically enforced. A `tui.spec.ts` unit test mounts with `color`+`truecolor` enabled to cover the header's gradient branch and the `gradientText`/`brandColorAt` helpers.
+
+## Alternatives considered
+
+**A theme-safe stepped gradient built from the 16-color palette.** Approximating the sweep with bright-blue palette variants would keep the banner fully theme-agnostic and avoid touching the gate. It was rejected by the requester: 16 fixed colors cannot reproduce the smooth logo gradient, and the request was explicitly to match the site wordmark.
+
+**Recoloring the whole harness palette blue.** The original phrasing was "update the harness color to blue." That was narrowed to the banner only; a global blue palette would break theme-agnosticism everywhere, not just on one brand surface.
+
+**Always emitting truecolor.** Many terminals lack 24-bit support and would render the raw or degraded codes. Gating on detection with an ANSI fallback keeps the banner correct everywhere while still showing the gradient where it works.
+
+**Detecting truecolor inside `resolveTuiConfig`.** The resolver is a pure defaulting step and must not read `process.env`. Environment probing belongs at the process boundary in `apply()`, so `mountTui`/`createTuiChat` stay driven purely by their config input and remain fully testable with a fake terminal.
+
+## Consequences
+
+The banner now carries the DeepSeek brand identity on truecolor terminals while the theme-agnostic guarantee holds everywhere else — and even on the banner itself when truecolor is unavailable. The cost is one narrow, documented crack in the theme-agnostic invariant: a fixed-color surface that will not adapt to a user's terminal scheme, accepted because it is brand identity and foreground-only, so it stays legible on both light and dark backgrounds. The crack is fenced by the `banner-gradient` snapshot assertion, which confines truecolor to the banner foreground and fails if any other RGB, extended-palette, or background color ever appears.

.agents/notes/archived/feature/2026-07-21-tui-banner-brand-gradient.zh.md

@@ -0,0 +1,40 @@
+# Agent Note: TUI 启动横幅品牌渐变
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-21-tui-banner-brand-gradient.md) | 中文
+
+## 问题
+
+TUI 启动横幅原本用调色板的扁平强调色渲染产品名 `DEEPSEEK`，它不承载任何品牌标识，也不像 deepseek.com 上的字标。需求明确是让横幅匹配站点 logo 的蓝色渐变——而不是给整个 coding harness 重新上色。
+
+横幅是唯一在意这件事的界面，而它与一条承重不变量冲突：TUI 调色板刻意做到主题无关。它只使用标准 16 色 ANSI（SGR）代码与属性，好让用户的终端配色方案能够重映射每一种颜色；`themeViolations()` 快照门禁会拒绝任何 RGB、扩展调色板或显式背景色的单元格。用 16 种调色板颜色无法拼出平滑的、与 logo 一致的渐变，因此复现它需要 24 位真彩色（truecolor），而门禁按设计会将其标记出来。
+
+## 决策
+
+横幅用逐字母的 24 位真彩色前景色渲染 `DEEPSEEK`，沿 deepseek.com 品牌渐变——`#4D6BFE` → `#3982FF` → `#2498FF`——在这三个色标之间做分段线性插值；`HARNESS` 保持加粗并使用默认前景色。渐变仅作用于前景色，因此在任何终端背景上都保持可读，并且被限制在横幅的产品名内。这是主题无关调色板唯一获准的例外；其余每个界面都保持标准 ANSI 且随主题自适应。
+
+渐变以 `resolved.color && resolved.truecolor` 为开关。当真彩色不可用时，横幅回退到既有的扁平亮蓝强调色，因此除非显式启用真彩色，主题无关保证与已录制的快照都不会改变。
+
+`truecolor` 是一个经校验的 `Config` 字段，schema 不设默认值。当它未设置时，`apply()` 会在进程边界从 `COLORTERM`（`truecolor` 或 `24bit`）自动探测；显式的配置值始终优先。探测只在 `apply()` 中读取 `process.env`——绝不在纯粹的 `resolveTuiConfig` 解析器中——从而让解析器保持为其输入的纯函数。
+
+渐变色标是固定的品牌标识，被当作协议常量对待，因此硬编码在插件里，而不作为可调项暴露。是否*启用*真彩色则随终端与部署而变，所以那才是经校验的 `Config` 字段。横幅文本仅面向界面，永不进入任何模型请求，因此不需要会话事件。
+
+## 测试
+
+一个专门的 `banner-gradient` 终端快照在 xterm 模拟器中固定了真实的逐字母 RGB 输出（`fg=#4d6bfe`…`#2498ff`，每个字母加粗）。共享的 `checkpoint()` 辅助函数接受一个 `bannerGradient` 标志：仅对该 checkpoint，它断言主题违规项非空，且每一项都以 `rgb-fg` 结尾——即真彩色确实存在，但被限制在横幅前景色，没有背景色或扩展调色板的泄漏。其余每个 checkpoint 都保持严格的 `themeViolations()` `.toEqual([])` 断言，因此这道围栏是机械强制的。一个 `tui.spec.ts` 单元测试在同时启用 `color` 与 `truecolor` 时挂载，以覆盖 header 的渐变分支以及 `gradientText`/`brandColorAt` 辅助函数。
+
+## 曾考虑的替代方案
+
+**用 16 色调色板拼出的主题安全阶梯渐变。** 用亮蓝的调色板变体近似这段渐变可以让横幅完全保持主题无关，并避免触碰门禁。它被需求方否决了：16 种固定颜色无法复现平滑的 logo 渐变，而需求明确是匹配站点字标。
+
+**给整个 harness 调色板重新上蓝色。** 最初的说法是"把 harness 颜色改成蓝色"。它被收窄到只改横幅；全局蓝色调色板会在各处而非仅一个品牌界面上破坏主题无关性。
+
+**始终发射真彩色。** 许多终端不支持 24 位，会渲染出原始或降级的代码。以探测为开关并配以 ANSI 回退，能让横幅在各处都正确，同时仍在支持的地方展示渐变。
+
+**在 `resolveTuiConfig` 内探测真彩色。** 该解析器是纯粹的默认值填充步骤，绝不能读取 `process.env`。环境探测属于 `apply()` 中的进程边界，从而让 `mountTui`/`createTuiChat` 完全由其配置输入驱动，并在使用假终端时保持完全可测。
+
+## 后果
+
+现在横幅会在真彩色终端上承载 DeepSeek 品牌标识，而主题无关保证在其余各处依然成立——甚至当真彩色不可用时在横幅自身上也成立。代价是主题无关不变量上一道狭窄且有记录的裂缝：一个不会随用户终端配色方案自适应的固定颜色界面，之所以接受，是因为它是品牌标识且仅作用于前景色，从而在浅色与深色背景上都保持可读。这道裂缝由 `banner-gradient` 快照断言把守，它将真彩色限制在横幅前景色，一旦其他任何 RGB、扩展调色板或背景色出现就会失败。

.agents/notes/archived/feature/2026-07-21-tui-borderless-banner.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-borderless-banner.md: 09fe713544134865687162c4624090b8e9aa3ebf
+2026-07-21-tui-borderless-banner.zh.md: b11c6d3c8cd327d7779617b4a7939ce55d8b765c

.agents/notes/archived/feature/2026-07-21-tui-borderless-banner.md

@@ -0,0 +1,47 @@
+# Agent Note: The banner returns, borderless
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-21-tui-borderless-banner.zh.md)
+
+## Problem
+
+An intermediate no-banner design removed the boxed startup banner: it deleted `HeaderComponent` and its sweep, moved the model into the footer, dropped the session id, and rendered `welcome` as the transcript's first line. The user's verdict reversed that: bring the banner back — "just remove the border". The four-row box frame was the objectionable chrome, not the identifying facts it carried (model, session id) nor the sweep-in motion.
+
+## Decision
+
+- `HeaderComponent` and its left-to-right sweep return, but render **borderless**: no `╭─╮`/`╰─╯` corners and no `│` side bars. Each line is a single leading space plus `truncateToWidth`-clipped content, so the sweep's width clip can never tear an escape sequence and no fixed frame is drawn. The reveal advances through about 24 frames at 15 ms each.
+- The header carries the title (`DEEPSEEK HARNESS`), a `<model>  •  <session-id>` detail line, and — when `welcome` is set — a muted subtitle. With `welcome` unset the header is title + detail only: there is no fixed or random slogan.
+- The model **also** stays in the footer's left segment, so the driving model remains glanceable after the transient banner scrolls out of view.
+- `welcome` reverts to a banner subtitle; the transcript-first-line notice is removed from `rebuildTranscript`.
+- The sweep animates only when `welcome` is unset. A configured `welcome` renders the whole banner immediately, keeping fixtures and snapshots frame-deterministic. The sweep starts after `ui.start()` succeeds and is cleared through the same `detachListeners` path via `stopBannerReveal`, which also resets the clip so a header disposed mid-sweep re-renders whole.
+
+This note owns the current result of the discarded startup variants: random slogans with a per-character typewriter, a boxed whole-banner sweep, and no banner. The example composition does not set `welcome`; deployments and deterministic fixtures may still provide one. The model's persistent footer home from the no-banner variant remains.
+
+## Alternatives considered
+
+**Keep the box but thin it or use lighter glyphs.** Rejected: the instruction was "just remove the border"; any surrounding glyph is the frame chrome the user objected to.
+
+**Keep a random or fixed slogan when `welcome` is unset.** Rejected because repeated flavor copy becomes wallpaper and the per-character reveal was slow while animating only one line. An unset welcome therefore produces no subtitle, and the whole banner supplies the startup motion.
+
+**Remove the banner entirely.** Rejected because the persistent footer is a good home for the model but not for the full identifying detail, while putting `welcome` in the transcript makes presentation configuration behave like conversation content.
+
+**Reveal the banner top-down.** Rejected because four row-sized steps read as a flicker. The horizontal width clip uses the terminal span for smooth motion and reuses the ANSI-aware truncation path.
+
+**Drop the model from the footer now that the banner shows it again.** Rejected: the banner is transient and scrolls away with the transcript, while the footer keeps the model visible for the whole session; that persistent location is deliberately preserved.
+
+**Leave the session id out of the banner.** Rejected: with the box gone the detail line costs one row, and the user asked for the banner "as before", which carried `model • session-id`.
+
+## Consequences
+
+- Boot output with `welcome` unset is animation-dependent again (the sweep); configured welcomes stay frame-deterministic, so every snapshot and scripted fixture keeps a fixed subtitle.
+- The demo no longer supplies instructional welcome filler; an unset `welcome` means a subtitle-free banner, while the config remains the deterministic escape hatch for deployments and fixtures.
+- The model now appears twice at boot — banner detail and footer — intended redundancy: the banner is transient, the footer persistent.
+- `/clear` empties the transcript but not the header, so the banner and its configured subtitle survive `/clear`, unlike a transcript-based welcome line.
+- All pi-tui terminal snapshots and the examples/tui-agent replay snapshots re-recorded (`test:snapshot:refresh`): banner rows return with no box glyphs; footer rows keep the model prefix.
+- Anything that anchored on banner absence re-anchors on its presence: the PTY smoke boots on the detail line's `main-session-` id (revealed late in the sweep) and asserts `DEEPSEEK`/`HARNESS` present with no box corners.
+
+## Testing
+
+`packages/ui/tui/tests/tui.spec.ts` pins: the borderless banner sweeps to natural completion — no box corners, title and `main-session` detail present — with at least one clipped mid-sweep frame; a configured `welcome` renders the whole banner with no clipped frame; the unset-welcome banner has no subtitle; and dispose clears the sweep interval mid-sweep. Independent color-scheme cases cover reported light/dark transitions, a same-scheme no-op, and a terminal that throws on the DSR query write; `applyColorScheme` relies on `setStatus` to rederive the editor border instead of repeating the dead assignment that had broken per-file coverage. The tui-agent and dsh-CLI PTY smokes boot on the `main-session-` detail marker and assert no box corners. Snapshots verify the full frames.

.agents/notes/archived/feature/2026-07-21-tui-borderless-banner.zh.md

@@ -0,0 +1,47 @@
+# Agent Note: 横幅回归，无边框
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-21-tui-borderless-banner.md) | 中文
+
+## Problem
+
+一个中间的无横幅设计删掉了带框的启动横幅：它删除了 `HeaderComponent` 及其扫入动画，把模型移入页脚，丢弃了会话 id，并把 `welcome` 渲染为 transcript 的第一行。用户的裁决把这一切反转：把横幅拿回来——"just remove the border"。令人反感的装饰是那四行盒子边框，而不是它承载的识别信息（模型、会话 id），也不是扫入动效。
+
+## Decision
+
+- `HeaderComponent` 及其从左到右的扫入动画回归，但以**无边框**方式渲染：没有 `╭─╮`/`╰─╯` 边角，也没有 `│` 侧边。每一行都是一个前导空格加上经 `truncateToWidth` 裁剪的内容，因此扫入的宽度裁剪永远不会撕裂转义序列，也不绘制任何固定边框。扫入大约经过 24 帧完成，每帧间隔 15 ms。
+- 头部承载标题（`DEEPSEEK HARNESS`）、一条 `<model>  •  <session-id>` 详情行，以及——当设置了 `welcome` 时——一条弱化的副标题。`welcome` 未设置时头部只有标题加详情：不含固定或随机标语。
+- 模型**同时**保留在页脚的左段，因此在短暂的横幅滚出视野后，会话使用的模型仍可一瞥可见。
+- `welcome` 恢复为横幅副标题；transcript 第一行的通知从 `rebuildTranscript` 中移除。
+- 仅当 `welcome` 未设置时才播放扫入动画。配置了 `welcome` 会立即渲染整个横幅，使 fixture 和快照保持帧确定性。扫入在 `ui.start()` 成功后启动，并经与之前相同的 `detachListeners` 路径通过 `stopBannerReveal` 清理；后者还会重置裁剪，使扫入中途被销毁的头部重新完整渲染。
+
+本 Agent Note 统一记录几种已弃用启动方案的当前结论：带逐字打字机效果的随机标语、带边框的整幅横幅扫入动画，以及完全移除横幅。示例组装不设置 `welcome`；部署和确定性 fixture 仍可提供该值。无横幅方案为模型设置的常驻页脚位置继续保留。
+
+## Alternatives considered
+
+**保留盒子但做细或改用更轻的字符。** 否决：指令是 "just remove the border"；任何环绕的字符都是用户所反对的边框装饰。
+
+**在未设置 `welcome` 时保留随机或固定标语。** 否决：反复出现的氛围文案很快失去信息价值，而逐字揭示仅为一行制作动画，速度又慢。因此，未设置 `welcome` 时不显示副标题，由整个横幅提供启动动效。
+
+**完全移除横幅。** 否决：常驻页脚很适合显示模型，却无法承载完整识别详情；把 `welcome` 放入 transcript 还会使展示配置表现成对话内容。
+
+**自上而下揭示横幅。** 否决：按四行分成四步看起来像闪烁。横向宽度裁剪利用终端横向空间实现平滑动效，并复用 ANSI 感知的截断路径。
+
+**既然横幅重新显示模型，就把模型从页脚移除。** 否决：横幅是短暂的，会随 transcript 滚走，而页脚在整个会话中保持模型可见；这个常驻位置被刻意保留。
+
+**将会话 id 留在横幅之外。** 否决：盒子去掉后详情行只占一行，且用户要求横幅"和以前一样"，而以前它承载 `model • session-id`。
+
+## Consequences
+
+- `welcome` 未设置时的启动输出再次依赖动画（扫入）；配置了欢迎语则保持帧确定性，因此每个快照和脚本 fixture 都保留一个固定副标题。
+- demo 不再提供教学性质的欢迎填充文案；`welcome` 未设置就表示横幅没有副标题，而该配置仍是部署和 fixture 获得确定性输出的配置手段。
+- 模型现在在启动时出现两次——横幅详情与页脚——这是有意的冗余：横幅短暂，页脚常驻。
+- `/clear` 清空 transcript 但不清头部，因此横幅及其配置的副标题在 `/clear` 后存活，不同于基于 transcript 的欢迎行。
+- 全部 pi-tui 终端快照与 examples/tui-agent 回放快照重新录制（`test:snapshot:refresh`）：横幅行以无盒子字符方式回归；页脚行保留模型前缀。
+- 一切锚定横幅缺失的内容改为锚定其存在：PTY 冒烟测试以详情行的 `main-session-` id 为启动标记（它在扫入后段才被揭示），并断言 `DEEPSEEK`/`HARNESS` 出现且无盒子角。
+
+## Testing
+
+`packages/ui/tui/tests/tui.spec.ts` 固定：无边框横幅扫入至自然完成——无盒子角、标题与 `main-session` 详情出现——且至少有一帧扫入中途被裁剪；配置的 `welcome` 完整渲染横幅且无裁剪帧；未设置 `welcome` 的横幅无副标题；销毁会在扫入中途清掉扫入定时器。独立的配色方案用例覆盖终端报告的浅色/深色转换、相同方案下的空操作，以及写入 DSR 查询时抛出异常的终端；`applyColorScheme` 依靠 `setStatus` 重新推导编辑器边框，而不再重复那个导致逐文件覆盖率未达标的无效赋值。tui-agent 与 dsh CLI 的 PTY 冒烟测试以 `main-session-` 详情标记为启动标记并断言无盒子角。快照验证完整帧。

.agents/notes/archived/feature/2026-07-21-tui-footer-cache-hit-rate.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-footer-cache-hit-rate.md: 9e6ec734030088f063c049312ea345dc07303554
+2026-07-21-tui-footer-cache-hit-rate.zh.md: ec761df2cb9cad1dd922082f4ff1a8bb25cbdd69

.agents/notes/archived/feature/2026-07-21-tui-footer-cache-hit-rate.md

@@ -0,0 +1,42 @@
+# Agent Note: TUI footer shows the session cache hit rate
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-21-tui-footer-cache-hit-rate.zh.md)
+
+## Problem
+
+The footer summed the session's token usage as `↑<input> ↓<output>`, where `↑` is the uncached input reported by the model. `TokenUsage` counts are disjoint: billed prompt tokens are `inputTokens` (uncached) plus `cacheReadTokens` and `cacheWriteTokens`. With only the uncached number visible, a user could not tell how much of each turn's prompt the provider cache served — the signal that most directly reflects whether the reused request prefix is paying off. On a long session dominated by cache reads the `↑` figure stays small and hides that the prompt is large but cheap.
+
+## Decision
+
+The footer appends `cache <rate>%` after `↑<input> ↓<output>`, where the rate is the share of billed prompt tokens served from the provider cache.
+
+- `TokenTotals` accumulates the four disjoint buckets (`input`, `output`, `cacheRead`, `cacheWrite`). `addUsage` folds one call's `TokenUsage` into the totals, treating a missing `cacheReadTokens`/`cacheWriteTokens` as zero.
+- `cacheHitRate(totals)` is `round(cacheRead / (input + cacheRead + cacheWrite) * 100)`, and `undefined` before any input is billed. `FooterComponent` omits the whole `  cache N%` segment while the rate is `undefined`, so an empty session shows no meaningless zero.
+- `↑` keeps meaning uncached input, not billed input: the disjoint-bucket convention holds across the footer, and the cache percent supplies the reuse signal the raw counts cannot.
+- Totals are rebuilt on mount by `sessionTokens`, which sums usage over `assistant/message` events (never `assistant/chunk`, to avoid double counting), and updated live from each `assistant/message` event that carries usage.
+
+## Alternatives considered
+
+**Show billed input (`input + cacheRead + cacheWrite`) as `↑` instead of a separate percent.** Rejected: it would redefine `↑` away from the disjoint `inputTokens` bucket the rest of the harness reports, and it would still hide the reuse share the user actually wants; a derived percent adds the signal without overloading the count.
+
+**Compute the rate against all tokens (`input + output + cache`).** Rejected: output tokens are never cache-served, so folding them into the denominator understates the rate for no meaning; cache hit rate is a property of the prompt.
+
+**Drop `cacheWrite` from the denominator.** Rejected: cache writes are billed input the provider spent to populate the cache, so excluding them overstates the hit rate on a writing turn. DeepSeek reports no cache-write metric today, but the formula stays general and the write path is covered.
+
+**Render `cache 0%` on an empty session.** Rejected: the billed input is `0`, the ratio is `0/0`, and a `0%` badge on a fresh session is a lie about a value that does not exist yet; the segment stays hidden until input is billed.
+
+**Give the metric its own right-aligned footer element beside `tools:`.** Rejected: it derives from the adjacent token counts and reads best in the `input → output → cache` order; grouping it left also keeps the lower-priority `tools:` indicator as the element that clips first under width pressure, matching the footer's existing layout priority.
+
+## Consequences
+
+- The left group grew by `  cache N%`, so on a narrow footer the right-side `tools:` state clips sooner. This follows the footer's pre-existing left-priority truncation and is an accepted trade-off.
+- The metric is best-effort live UI state derived from `assistant/message` usage: rebuilt from the session on mount, updated live, and never persisted.
+- `packages/ui/tui/src/index.ts` stays at 100 % per-file coverage.
+- The `examples/tui-agent` terminal snapshots carry the segment: a turn with cache reads renders e.g. `cache 49%`, and a first cold turn renders `cache 0%`.
+
+## Testing
+
+`packages/ui/tui/tests/tui.spec.ts` drives the footer through the real `createTuiChat`: an empty session renders `↑0 ↓0` with no cache segment (the hidden path), a cold turn (`inputTokens` only) renders `cache 0%`, and a live warm turn carrying `cacheReadTokens` and `cacheWriteTokens` updates it to `cache 60%` while no longer showing `cache 0%`. The `examples/tui-agent` snapshot suite replays green against the recorded expected output.

.agents/notes/archived/feature/2026-07-21-tui-footer-cache-hit-rate.zh.md

@@ -0,0 +1,42 @@
+# Agent Note: TUI 页脚展示会话缓存命中率
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-21-tui-footer-cache-hit-rate.md) | 中文
+
+## Problem
+
+页脚原本把会话的 token 用量汇总为 `↑<input> ↓<output>`，其中 `↑` 是模型上报的未缓存输入。`TokenUsage` 的各项计数互不重叠：计费的输入 token 由 `inputTokens`（未缓存）加上 `cacheReadTokens` 与 `cacheWriteTokens` 构成。只暴露未缓存的那个数字，用户就无从判断每轮提示词有多少由提供方缓存承接——而这恰是最能反映复用的请求前缀是否奏效的信号。在以缓存读取为主的长会话里，`↑` 始终很小，掩盖了提示词其实很大但很便宜的事实。
+
+## Decision
+
+页脚在 `↑<input> ↓<output>` 之后追加 `cache <rate>%`，该比率是计费输入 token 中由提供方缓存承接的占比。
+
+- `TokenTotals` 累加四个互不重叠的桶（`input`、`output`、`cacheRead`、`cacheWrite`）。`addUsage` 把单次调用的 `TokenUsage` 折入总量，缺失的 `cacheReadTokens`/`cacheWriteTokens` 视为零。
+- `cacheHitRate(totals)` 为 `round(cacheRead / (input + cacheRead + cacheWrite) * 100)`，在尚无输入计费前返回 `undefined`。比率为 `undefined` 时 `FooterComponent` 整段略去 `  cache N%`，因此空会话不会显示无意义的零。
+- `↑` 仍表示未缓存输入，而非计费输入：页脚全程遵守互不重叠的桶约定，缺失的复用信号由缓存百分比补足。
+- 挂载时由 `sessionTokens` 重建总量，它对带 usage 的 `assistant/message` 事件求和（绝不用 `assistant/chunk`，以免重复计数）；此后每条携带 usage 的 `assistant/message` 事件都会实时更新。
+
+## Alternatives considered
+
+**把计费输入（`input + cacheRead + cacheWrite`）作为 `↑`，不单列百分比。** 否决：这会让 `↑` 偏离 harness 其余部分上报的互不重叠 `inputTokens` 桶，且仍旧藏住用户真正想要的复用占比；派生一个百分比既补上信号，又不给计数加载额外含义。
+
+**用全部 token（`input + output + cache`）作分母计算比率。** 否决：输出 token 从不由缓存承接，把它折进分母只会无意义地拉低比率；缓存命中率是提示词的属性。
+
+**从分母里去掉 `cacheWrite`。** 否决：缓存写入是提供方为填充缓存而付费的计费输入，剔除它会在写入的那一轮高估命中率。DeepSeek 目前不上报缓存写入指标，但公式保持通用，写入路径也有覆盖。
+
+**在空会话上渲染 `cache 0%`。** 否决：此时计费输入为 `0`，比值是 `0/0`，在全新会话上打出 `0%` 是对一个尚不存在的值撒谎；在输入计费之前该段一直隐藏。
+
+**给该指标单独一个右对齐的页脚元素，紧挨 `tools:`。** 否决：它派生自相邻的 token 计数，按 `input → output → cache` 的顺序阅读最顺；左置分组还让优先级更低的 `tools:` 指示成为宽度紧张时最先被裁剪的元素，与页脚既有的布局优先级一致。
+
+## Consequences
+
+- 左段增加了 `  cache N%`，因此窄终端上右侧的 `tools:` 状态更早被裁剪。这沿用页脚既有的左段优先裁剪策略，是可接受的取舍。
+- 该指标是从 `assistant/message` 的 usage 派生的尽力而为实时 UI 状态：挂载时从会话重建、随后实时更新、从不持久化。
+- `packages/ui/tui/src/index.ts` 保持 100% 单文件覆盖率。
+- `examples/tui-agent` 终端快照带有该段：有缓存读取的一轮渲染为如 `cache 49%`，首个冷启动轮次渲染为 `cache 0%`。
+
+## Testing
+
+`packages/ui/tui/tests/tui.spec.ts` 通过真实的 `createTuiChat` 驱动页脚：空会话渲染 `↑0 ↓0` 且无缓存段（隐藏路径），冷启动一轮（仅 `inputTokens`）渲染 `cache 0%`，随后实时的热轮次携带 `cacheReadTokens` 与 `cacheWriteTokens`，把它更新为 `cache 60%` 且不再显示 `cache 0%`。`examples/tui-agent` 快照套件对已录制的预期输出回放通过。

.agents/notes/archived/feature/2026-07-21-tui-reload-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-reload-command.md: e491e8f4510128b7fda03d41bc1d13e4dfdc9f5e
+2026-07-21-tui-reload-command.zh.md: ed96c689fe4ba700f5b6836d7b7727e0252737a2

.agents/notes/archived/feature/2026-07-21-tui-reload-command.md

@@ -0,0 +1,36 @@
+# Agent Note: The /reload command re-reads loader configs on demand
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-21-tui-reload-command.zh.md)
+
+## Problem
+
+HMR's file watcher only reacts to in-place `change` events under its configured roots (the config leaf's directory in the shipped demos). Editors that replace files by rename (BSD `sed -i`, `git checkout`) produce no event, and runtimes without the HMR entry have no config reload path at all. During development that means restarting the TUI to apply a config edit the watcher missed. Widening the watch roots to the whole repo was considered and rejected in discussion: dense package sharing makes module-level HMR a remount-most-of-the-tree operation with unpredictable externals boundaries.
+
+## Decision
+
+`dsh-tui` gains an **experimental, dev-only** `/reload` slash command: it walks `ctx.loader.entries()` and calls `refresh()` on every file-backed subtree (`Include`), i.e. the exact code path the HMR watcher's config-change branch drives, invoked manually and watcher-independent. Unchanged files are no-ops (content comparison in `Include.read`); invalid files warn and keep the running tree (the hot-reload-resilience contract); include `patches` — including the dsh CLI's personal overlay — re-apply on every re-read.
+
+The TUI reaches the Loader **structurally** (`ctx.loader` via a local type, not `inject`): tests and embedders run the TUI without a Loader, where `/reload` degrades to a warning notice instead of failing the mount. Module-source hot reload stays watcher-owned; `/reload` refreshes configs only.
+
+## Alternatives considered
+
+**Widening the HMR watch roots to `packages/`/`apps/`.** Rejected for now: plugin-source changes reload every dependent plugin's fiber, and the repo's dense shared packages (`dsh-session`, `dsh-llm`, `dsh-tools`) make that a teardown of the spine and the UI mid-session — a restart in disguise with partial-reload hazards. A manual config-scope command captures the safe, predictable subset.
+
+**Declaring `loader` in `inject`.** Rejected: it would make the Loader a hard dependency of the TUI, breaking every Loader-less composition (unit harness, embedders) for a dev convenience.
+
+**A `cordis_reload` model-facing tool in dsh-tool-cordis.** Rejected: this is an operator action for the human at the terminal, not a capability the model should trigger; the cordis toolset's mount/unmount surface already covers the model's runtime-modification story.
+
+## Consequences
+
+- `/reload` appears in the help line, autocomplete (marked EXPERIMENTAL (dev)), and the two help-rendering snapshots (re-recorded).
+- The command reports tree count and completion as transcript notices; per-file failures surface only in loader logs, which the TUI does not display — acceptable for a dev-only surface, noted in the completion message.
+- A re-entrancy guard serializes reloads: `/reload` while one is in flight is refused with a warning, keeping the loader's unmutexed tree-update pass single-writer; the guard releases on completion or failure.
+- `/reload` runs only while the agent is idle: a reload can dispose and re-mount entries, which under an active turn could tear tools or the adapter out from under in-flight calls. The check is advisory (a send can race in after it) but removes the common footgun.
+- If `refresh()`'s never-reject contract ever changes, the command reports the failure instead of leaving an unhandled rejection.
+
+## Testing
+
+`packages/ui/tui/tests/tui.spec.ts` pins: `/reload` refreshes every file-backed subtree and skips plain entries (structural fake Loader), reports completion, refuses re-entry while a gated refresh is in flight and runs again after release, releases the guard on the failure arm, refuses a running agent and runs again at idle, reports a rejecting refresh, and degrades to a warning without a Loader — including mounted as a real plugin fiber, where a throwing service lookup would escape. Verified live in tmux against the real tree: probe edit → reload applies; invalid edit → reload keeps the running tree.

.agents/notes/archived/feature/2026-07-21-tui-reload-command.zh.md

@@ -0,0 +1,36 @@
+# Agent Note: /reload 命令按需重读 loader 配置
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-21-tui-reload-command.md) | 中文
+
+## Problem
+
+HMR 的文件监听器只对其配置根目录（示例中即配置叶子所在目录）下的就地 `change` 事件起反应。以重命名方式替换文件的编辑器（BSD `sed -i`、`git checkout`）不产生事件，而没有挂载 HMR 配置项的运行时则完全没有配置重载路径。开发时这意味着监听器漏掉一次配置编辑就得重启 TUI。曾考虑把监听根目录扩大到整个仓库，讨论后否决：包之间的密集共享使模块级 HMR 变成「重挂大半棵树」的操作，externals 边界也不可预测。
+
+## Decision
+
+`dsh-tui` 增加一个**实验性、仅供开发**的 `/reload` 斜杠命令：遍历 `ctx.loader.entries()`，对每个文件后端的子树（`Include`）调用 `refresh()`——即 HMR 监听器配置变更分支所走的同一条代码路径，改为手动触发、不依赖监听器。未变化的文件是无操作（`Include.read` 做内容比较）；无效文件记录警告并保留运行中的树（热重载韧性契约）；include 的 `patches`——包括 dsh CLI 的个人 overlay——在每次重读时重新应用。
+
+TUI 以**结构方式**访问 Loader（通过局部类型访问 `ctx.loader`，而非 `inject`）：测试和嵌入方在没有 Loader 的情况下运行 TUI，此时 `/reload` 退化为一条警告通知而不是挂载失败。模块源码热重载仍由监听器负责；`/reload` 只刷新配置。
+
+## Alternatives considered
+
+**把 HMR 监听根目录扩大到 `packages/`/`apps/`。** 暂缓否决：插件源码变更会重载每个依赖插件的 fiber，而仓库中密集共享的包（`dsh-session`、`dsh-llm`、`dsh-tools`）使其等同于会话中途拆掉主干和 UI——伪装成热重载的重启，还带部分重载的隐患。手动的、只覆盖配置范围的命令抓住了安全、可预测的那个子集。
+
+**在 `inject` 中声明 `loader`。** 否决：那会让 Loader 成为 TUI 的硬依赖，为了一个开发便利破坏所有无 Loader 的组合（单元测试 harness、嵌入方）。
+
+**在 dsh-tool-cordis 里做一个面向模型的 `cordis_reload` 工具。** 否决：这是终端前人类操作者的动作，不是模型应当触发的能力；cordis 工具集的 mount/unmount 表面已经覆盖模型的运行时修改需求。
+
+## Consequences
+
+- `/reload` 出现在帮助行、自动补全（标注 EXPERIMENTAL (dev)）和两个渲染帮助的快照中（已重新录制）。
+- 命令以 transcript 通知报告树数量与完成；单文件失败只出现在 loader 日志里，TUI 不显示——对仅供开发的表面可以接受，完成消息中已注明。
+- 重入保护串行化重载：前一次进行中时 `/reload` 会被拒绝并提示警告，使 loader 无互斥的树更新过程保持单写者；保护在完成或失败时释放。
+- `/reload` 只在 agent 空闲时运行：重载可能卸载并重新挂载配置项，在活跃轮次下这会把工具或适配器从进行中的调用脚下抽掉。检查是建议性的（检查后仍可能有 send 竞争进来），但消除了常见的坑。
+- 若 `refresh()` 的永不 reject 契约将来改变，命令会报告失败而不是留下未处理的 rejection。
+
+## Testing
+
+`packages/ui/tui/tests/tui.spec.ts` 固定：`/reload` 刷新每个文件后端子树并跳过普通配置项（结构化的假 Loader）、报告完成、在门控的刷新进行中拒绝重入并在释放后可再次运行、失败分支同样释放保护、拒绝运行中的 agent 并在空闲后可再次运行、报告 reject 的 refresh、无 Loader 时退化为警告——包括作为真实插件 fiber 挂载的情形，在那里会抛出的服务查找会泄露出去。已在 tmux 中对真实配置树实机验证：探针编辑 → reload 生效；无效编辑 → reload 保留运行中的树。

.agents/notes/archived/feature/2026-07-21-tui-steering-queue-badge.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-steering-queue-badge.md: 37e8a11c0dd30a0674107ff33d51a31d92385ada
+2026-07-21-tui-steering-queue-badge.zh.md: 6ef412b26a32c3aa359215404ca81635fca776c1

.agents/notes/archived/feature/2026-07-21-tui-steering-queue-badge.md

@@ -0,0 +1,40 @@
+# Agent Note: TUI status line badges queued steering messages
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-21-tui-steering-queue-badge.zh.md)
+
+## Problem
+
+While a turn runs, an editor submission calls `agent.steer()` and joins the steering queue behind the running turn ([front-door Agent Note](2026-07-17-dedicated-full-screen-tui-front-door.md)). The running status line ended only with the `Enter sends steering, Esc cancels` hint, so pressing Enter gave no feedback that the message landed or how many were waiting to reach the model. A user steering several times could not tell the queue from a dropped keystroke.
+
+## Decision
+
+The agent's inbox is the authoritative steering queue but is not observable from the TUI, so the badge is a live count reconstructed from the public `agent/queued` and `steering/message` events rather than a projection of the queue itself.
+
+- The running status line composes through `formatTurnStatus`, which inserts a `${queued} queued · ` badge before the `Enter sends steering, Esc cancels` hint when `queued > 0` and shows the plain hint at zero; the phase label and elapsed timing before it are the [verbose status line](2026-07-21-tui-verbose-status-line.md)'s.
+- `createTuiChat` owns a `pendingSteering` counter: `+1` on each `agent/queued` for this agent whose `info.steering` is set, `-1` (floored at zero) on each `steering/message` session event as the loop drains one, and reset to zero whenever the agent leaves `running`.
+- The count refreshes onto the live `Loader` through `setMessage`; the refresh is a no-op while idle because the loader exists only during a running turn.
+- The reset lives in the `agent/status` transition, not in `setStatus`, because `setStatus` also runs on mid-turn palette changes and must not clear a live count.
+
+## Alternatives considered
+
+**Derive the count from the session log alone** (enqueued minus drained, recomputed on replay). Rejected: a cancellation clears the inbox without logging a drain, so the log cannot distinguish a drained message from a discarded one; the reset-on-non-running anchor is simpler and self-correcting each turn.
+
+**Reset inside `setStatus`.** Rejected: `setStatus` re-runs on `applyColorScheme` mid-turn, which would wrongly zero a live count; the status transition is the only place a turn actually ends.
+
+**Drop the decrement clamp.** Rejected: loop-authored steering (e.g. continuation reasons) logs `steering/message` with no matching user-queued increment, which would drive the count negative; the zero floor keeps the badge a lower bound rather than a lie.
+
+**Make the wording or a threshold configurable.** Rejected: the no-hardcoded-tunables rule targets deployment-varying behavior, not brand copy; the `welcome`/hint strings are already fixed presentation.
+
+## Consequences
+
+- The badge is best-effort live UI state, not a logged surface: it is rebuilt from events and reset each turn, never persisted, so a resumed running turn starts its badge from zero.
+- A cancellation mid-queue clears the badge cleanly through the non-running reset, and a drain past zero is a no-op — neither can strand a stale count.
+- A loop continuation that keeps the agent `running` while re-enqueuing undrained late steering can transiently over-count until the next idle reset; the badge is advisory, so the window is acceptable.
+- `packages/ui/tui/src/index.ts` stays at 100 % per-file coverage.
+
+## Testing
+
+`packages/ui/tui/tests/tui.spec.ts` drives the running status frame through the real `createTuiChat`: the plain hint at zero, a foreign-agent queue ignored, the increment to `2 queued`, a non-steering queue left untouched, the decrement as each message drains, the clamp on a drain past zero, and the reset when the turn ends. Verified live in tmux — the badge showed `3 queued` after three `agent.steer()` calls, then `1 queued` as two drained.

.agents/notes/archived/feature/2026-07-21-tui-steering-queue-badge.zh.md

@@ -0,0 +1,40 @@
+# Agent Note: TUI 状态行标示排队中的 steering 消息
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-21-tui-steering-queue-badge.md) | 中文
+
+## Problem
+
+轮次运行期间，编辑器提交会调用 `agent.steer()`，在运行中的轮次后面加入 steering（中途引导）队列（[前门 Agent Note](2026-07-17-dedicated-full-screen-tui-front-door.md)）。运行时的状态行只以 `Enter sends steering, Esc cancels` 提示收尾，因此按下 Enter 后没有任何反馈表明消息已入队、也看不出有多少条正在等待送达模型。连续 steering 多次的用户无法把队列和被吞掉的按键区分开。
+
+## Decision
+
+agent（智能体）的收件箱（inbox）才是权威的 steering 队列，但 TUI 无法观测它，因此徽标是从公开的 `agent/queued` 与 `steering/message` 事件重建出的实时计数，而非对队列本身的投影。
+
+- 运行时的状态行经 `formatTurnStatus` 组装：`queued > 0` 时在 `Enter sends steering, Esc cancels` 提示前插入 `${queued} queued · ` 徽标，为零时是纯提示文本；其前的阶段标签与耗时归[详细状态行](2026-07-21-tui-verbose-status-line.md)所有。
+- `createTuiChat` 持有一个 `pendingSteering` 计数器：每收到一个针对本 agent 且 `info.steering` 为真的 `agent/queued` 就 `+1`，agent loop（智能体循环）每排空一条时随对应的 `steering/message` 会话事件 `-1`（下限为零），agent 一旦离开 `running` 状态即重置为零。
+- 计数通过 `setMessage` 刷新到实时的 `Loader` 上；空闲时刷新是空操作，因为 loader 只在运行中的轮次期间存在。
+- 重置放在 `agent/status` 状态切换里，而非 `setStatus` 中，因为 `setStatus` 在轮次中途的颜色方案变化时也会运行，绝不能清掉一个实时计数。
+
+## Alternatives considered
+
+**仅从会话日志推导计数**（入队数减去排空数，回放时重算）。否决：取消会清空 inbox 而不记录排空，因此日志无法区分一条消息是被排空还是被丢弃；「离开运行态即重置」这个锚点更简单，且每轮自我校正。
+
+**在 `setStatus` 内重置。** 否决：`setStatus` 会在轮次中途的 `applyColorScheme` 时重新运行，会错误地把实时计数清零；状态切换才是轮次真正结束的唯一位置。
+
+**去掉递减的下限钳制。** 否决：agent loop 自行产生的 steering（如 continuation 续跑原因）会记录 `steering/message`，却没有对应的用户入队递增，这会把计数压到负数；零下限让徽标成为下界，而非谎报。
+
+**把措辞或某个阈值做成配置。** 否决：「插件里不许硬编码可调参数」规则针对的是随部署变化的行为，不是品牌文案；`welcome`/提示字符串本就是固定的展示文案。
+
+## Consequences
+
+- 徽标是尽力而为的实时 UI 状态，不写入日志：它由事件重建、每轮重置、从不持久化，因此恢复（resume）出的运行中轮次徽标从零开始。
+- 队列中途取消会经由「离开运行态即重置」干净地清掉徽标，排空到零以下则是空操作——两者都不会残留一个陈旧计数。
+- 如果 agent loop 续跑时让 agent 保持 `running`、同时把未排空的迟到 steering 重新入队，则可能短暂多计，直到下一次空闲重置；徽标只作参考，因此这个窗口可以接受。
+- `packages/ui/tui/src/index.ts` 保持 100% 的单文件覆盖率。
+
+## Testing
+
+`packages/ui/tui/tests/tui.spec.ts` 通过真实的 `createTuiChat` 驱动运行时状态帧：为零时的纯提示、忽略他方 agent 的入队、递增到 `2 queued`、非 steering 的入队保持不变、每条消息排空时的递减、排空到零以下时的钳制、以及轮次结束时的重置。已在 tmux 中实机验证——三次 `agent.steer()` 调用后徽标显示 `3 queued`，随后两条排空时显示 `1 queued`。

.agents/notes/archived/feature/2026-07-21-tui-verbose-status-line.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-verbose-status-line.md: 9ed396b0dbf4325d6fdd2a4f20f8d81b5b408171
+2026-07-21-tui-verbose-status-line.zh.md: 14c9b36646e226715156ba8db8f62cd6090ce9a0

.agents/notes/archived/feature/2026-07-21-tui-verbose-status-line.md

@@ -0,0 +1,37 @@
+# Agent Note: The running status line shows the turn phase and elapsed time
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-21-tui-verbose-status-line.zh.md)
+
+## Problem
+
+While a turn ran, the [full-screen TUI](2026-07-17-dedicated-full-screen-tui-front-door.md) showed a single static "Working" spinner. It conveyed neither how long the current step had taken nor what the agent was doing — waiting on the model, thinking, streaming a response, or running tools — so a slow or stalled turn was indistinguishable from a fast one.
+
+## Decision
+
+- While a turn runs, the status line above the editor shows a derived phase label with elapsed time, keeping the trailing `— Enter sends steering, Esc cancels` hint. The four phases and their labels are `waiting` → "Waiting for the first token", `thinking` → "Thinking", `responding` → "Responding", and `executing` → "Executing tools".
+- The phase is presentation state the TUI derives from live session events, not a session event or agent status of its own. `step/start` enters `waiting`; an `assistant/chunk` reasoning delta or reasoning block-start enters `thinking`; a text delta or text block-start enters `responding`; a `tool/call` enters `executing`. The event map is merge-extensible, so every other event kind falls through a default and leaves the phase unchanged.
+- The label reports two clocks — `<phase> <phase-elapsed> · total <step-elapsed>` — except `waiting`, which shows only the step total. The phase clock resets on a genuine phase change or a new step; the step clock resets on `step/start`. Durations format as `8s` below a minute and `1m05s` at or above one. Tool time between `step/end` and the next `step/start` accrues to the finishing step's total.
+- A single `RunningStatus` controller — the loader, the phase, the two baselines, and a refresh timer — exists only while a turn runs. A one-second `setInterval` refreshes the elapsed time; a phase event refreshes it immediately. `clearStatus` clears the interval, stops the loader, and drops the controller, so any transition to idle or disposed leaves no live timer, matching the [borderless banner](2026-07-21-tui-borderless-banner.md)'s timer hygiene. A mid-turn palette rebuild (`setStatus` re-derives the editor border on a terminal color-scheme change) carries the phase and both baselines across, so a running status never snaps back to `waiting`.
+
+## Alternatives considered
+
+**Emit the phase as a session event or agent status.** Rejected: the phase is a presentation detail the TUI reconstructs from events already logged. A durable, model-visible phase would demand a new session event under the model-visible ⟺ logged rule, for no model benefit.
+
+**Reuse pi-tui's `Loader` animation timer to refresh the elapsed text.** Not available: the vendored `Loader` animates only its spinner glyph, and its dist is not ours to change. The TUI owns a separate one-second interval, cleared on teardown.
+
+**Infer the phase from tool-drain or streaming-component state.** Rejected: the `step/start`, `assistant/chunk`, and `tool/call` lifecycle events are cleaner signals, already handled in the same live listener, and avoid coupling the status line to other components.
+
+**Show only elapsed time, or only the phase.** Rejected: both are wanted — the per-phase time answers what the agent is doing, the per-step total answers how long the step has taken.
+
+## Consequences
+
+- The status line reads, for example, `Thinking 4s · total 8s — Enter sends steering, Esc cancels`, so the agent's current activity and step duration are legible and a stall is visible.
+- Phase detection is best-effort presentation: an unhandled future chunk or event kind leaves the last phase in place and never throws.
+- Exactly one `setInterval` runs per active turn, cleared with the controller on every idle or disposed transition and on shutdown.
+
+## Testing
+
+`packages/ui/tui/tests/tui.spec.ts` pins each phase label against its triggering event (`step/start`, reasoning and text deltas and block-starts, `tool/call`), that a new step reopens the wait window, that the elapsed time advances on the controller's own timer past one second, that a step beyond a minute renders `1m…`, that a mid-turn color-scheme change preserves the phase and elapsed time, and that a live event arriving before the turn runs moves no status. Verified live in tmux.

.agents/notes/archived/feature/2026-07-21-tui-verbose-status-line.zh.md

@@ -0,0 +1,37 @@
+# Agent Note: 运行状态行展示轮次阶段与已用时长
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-21-tui-verbose-status-line.md) | 中文
+
+## 问题
+
+在轮次运行期间，[全屏 TUI](2026-07-17-dedicated-full-screen-tui-front-door.md) 只显示一个静态的 "Working" loader 动画。它既不表明当前步骤已耗时多久，也不表明 agent（智能体）正在做什么——等待模型、思考、流式输出回复，还是运行工具——因此运行缓慢或卡住的轮次与运行很快的轮次无从区分。
+
+## 决策
+
+- 轮次运行期间，编辑器上方的状态行显示一个派生的阶段标签及已用时长，并保留末尾的 `— Enter sends steering, Esc cancels` 提示。四个阶段及其标签为 `waiting` → "Waiting for the first token"、`thinking` → "Thinking"、`responding` → "Responding"、`executing` → "Executing tools"。
+- 阶段是 TUI 从实时会话事件派生出的呈现状态，而非它自有的会话事件或 agent 状态。`step/start` 进入 `waiting`；`assistant/chunk` 的 reasoning 分片或 reasoning 块开始（`block-start`）进入 `thinking`；text 分片或 text 块开始进入 `responding`；`tool/call` 进入 `executing`。该事件映射可合并扩展，因此其余任何事件类型都落入默认分支，保持阶段不变。
+- 标签汇报两个时钟——`<phase> <phase-elapsed> · total <step-elapsed>`——但 `waiting` 只显示步骤总时长。阶段时钟在真正发生阶段切换或进入新步骤时重置；步骤时钟在 `step/start` 时重置。时长在不足一分钟时格式化为 `8s`，达到或超过一分钟时格式化为 `1m05s`。`step/end` 与下一个 `step/start` 之间的工具时间计入结束步骤的总时长。
+- 单一的 `RunningStatus` 控制器——loader、阶段、两个基准时刻以及一个刷新定时器——仅在轮次运行期间存在。一个每秒触发的 `setInterval` 刷新已用时长；阶段事件则立即刷新。`clearStatus` 清除该 interval、停止 loader 并丢弃控制器，因此任何向 idle 或 disposed 的转变都不会遗留活动定时器，与[无边框横幅](2026-07-21-tui-borderless-banner.md)的定时器清理保持一致。轮次进行中的调色板重建（终端颜色方案变化时 `setStatus` 会重新派生编辑器边框）会将阶段与两个基准时刻一并沿用过来，因此运行中的状态绝不会退回 `waiting`。
+
+## 曾考虑的替代方案
+
+**将阶段作为会话事件或 agent 状态发出。** 已否决：阶段是 TUI 从已记录事件重建出的呈现细节。一个持久、模型可见的阶段会依据 model-visible ⟺ logged 规则要求新增一个会话事件，而对模型没有任何好处。
+
+**复用 pi-tui 的 `Loader` 动画定时器来刷新已用时长文本。** 不可行：`Loader` 是 vendored 依赖，只驱动其加载动画字形，其 dist 不归我们改动。TUI 自持一个独立的每秒 interval，并在拆卸时清除。
+
+**从工具耗尽或流式组件状态推断阶段。** 已否决：`step/start`、`assistant/chunk` 和 `tool/call` 这些生命周期事件是更干净的信号，已在同一个实时监听器中处理，且避免让状态行与其他组件耦合。
+
+**只显示已用时长，或只显示阶段。** 已否决：两者都需要——按阶段的时长回答 agent 在做什么，按步骤的总时长回答该步骤已耗时多久。
+
+## 后果
+
+- 状态行例如显示 `Thinking 4s · total 8s — Enter sends steering, Esc cancels`，从而 agent 的当前活动与步骤时长一目了然，卡顿也随之可见。
+- 阶段检测是尽力而为的呈现：未处理的未来分片或事件类型会保持上一个阶段不变，绝不抛错。
+- 每个活动轮次恰好运行一个 `setInterval`，在每次向 idle 或 disposed 的转变以及关停时随控制器一并清除。
+
+## 测试
+
+`packages/ui/tui/tests/tui.spec.ts` 针对触发事件锁定每个阶段标签（`step/start`、reasoning 与 text 的分片及块开始、`tool/call`），并锁定新步骤会重新开启等待窗口、已用时长在控制器自有定时器上超过一秒后递增、超过一分钟的步骤渲染为 `1m…`、轮次进行中的颜色方案变化会保留阶段与已用时长，以及轮次开始前到达的实时事件不移动任何状态。已在 tmux 中实机验证。

.agents/notes/archived/feature/2026-07-23-trajectory-step-cell.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
+2026-07-23-trajectory-step-cell.md: 871f02d72b74bb6dbeb782fde3b639b237cf71e1
+2026-07-23-trajectory-step-cell.zh.md: 3ebb4becd569242bfdea222df6d042a4c00ad096

.agents/notes/archived/feature/2026-07-23-trajectory-step-cell.md

@@ -0,0 +1,36 @@
+# Agent Note: Trajectory step cell and turn list chrome
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-23-trajectory-step-cell.zh.md)
+
+## Problem
+
+The trajectory tab needs a reusable step row and turn-list chrome that can show expanded assistant blocks, own-duration times, Message token columns, and in-flight work. Without folding session event times into conversation nodes and expanding blocks into cells, the UI cannot match the product chrome.
+
+## Decision
+
+[`@deepseek-ai/dsh-client-ui-trajectory`](../../../../packages/client/ui-trajectory/README.md) owns the presentational trajectory list chrome:
+
+- [`TrajectoryCell`](../../../../packages/client/ui-trajectory/src/client/TrajectoryCell.tsx) — 38px step row with kinds User / Message / Tool (no Think, Call, or Result rows). Reasoning blocks are skipped (no block-level clock). Each `tool-call` + paired `tool-result` folds into one Tool row (`name ·` truncated args) whose Time is `result.time − callTime` when both are known. Message rows carry Input/Output/Think token columns from `assistant.usage`. Own-duration Time uses `+Ns` / `+N.1s`, or `—` when absent. Selected state draws a 2px inset `--dsw-alias-brand-primary-new-colorprimary-new-color` ring (`selected` prop) and is not wired to chat selection.
+- [`TrajectoryTurn`](../../../../packages/client/ui-trajectory/src/client/TrajectoryTurn.tsx) / header / group header — sticky Turn bar paints full-bleed `ghost-active-fill`; title/columns and the Message/Step body sit in a centered `max-width: 880px` lane. Cell trailing columns share the Turn header geometry (`320 = 4×71 + 3×12`); cells use pad 20/8.
+- [`deriveTrajectoryLayout`](../../../../packages/client/ui-trajectory/src/client/layout.ts) expands assistant `blocks[]` into cells, pairs tool-calls with `tool-result` by `callId` into Tool, folds `partial` and `runningCalls` (deduped), hangs usage on Message only (including the empty fallback when there is no text block), and builds group descriptions as wall-span + tool histogram (`1.5s bash×6`). `user/message` has no wire turn, so each User row is enclosed in the next assistant/steering turn, else the in-flight `partial` turn, else `lastAssistantTurn + 1` (or `1`). Context nodes emit no cell but still advance the Message duration cursor.
+
+[`ConversationNode`](../../../../packages/client/runtime/src/client/sessions/conversation.ts) carries `time` from `SessionEvent.time`; `ToolResultNode.callTime` and `RunningToolCall.time` come from the paired `tool/call`. Duration rules: User `+0s`; Message = assistant.time − previous surface time (including skipped context); Tool = result.time − callTime when both known; in-flight Tool = `—`. Group header duration is earliest→latest absolute time in the group (wall span; Tool contributes start and start+duration).
+
+## Alternatives considered
+
+**Keep a Think cell for reasoning blocks.** Rejected: a single `assistant/message.time` cannot yield Think own-duration without chunk-level clocks; omit the row rather than show `—`.
+
+**Keep separate Call and Result rows.** Rejected: Result had no own duration to show; one Tool row carries the call→result interval.
+
+**Cumulative elapsed from session/turn start.** Rejected; the Time column is each row's own duration.
+
+**Hang usage on the first expanded row.** Rejected; usage attaches to Message only.
+
+**Show in-flight tool durations via Date.now().** Deferred; in-flight Time stays `—`.
+
+## Consequences
+
+The Trajectory tab can render expanded finalized and in-flight rows with own-duration times once fold emits `time`. Behavior-shaped coverage lives in `packages/client/ui-trajectory/tests/{cell,layout,views}.spec.tsx`. Chat selection deep-links and finer block-level clocks remain deferred.

.agents/notes/archived/feature/2026-07-23-trajectory-step-cell.zh.md

@@ -0,0 +1,36 @@
+# Agent Note: Trajectory 步骤单元格与轮次列表 chrome
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-23-trajectory-step-cell.md) | 中文
+
+## Problem
+
+trajectory 标签页需要可复用的步骤行与轮次列表 chrome，以展示展开后的 assistant 块、自身耗时、Message token 列，以及进行中的工作。若不将会话事件时间折叠进会话节点，并将块展开为单元格，UI 就无法对齐产品 chrome。
+
+## Decision
+
+[`@deepseek-ai/dsh-client-ui-trajectory`](../../../../packages/client/ui-trajectory/README.md) 拥有展示型 trajectory 列表 chrome：
+
+- [`TrajectoryCell`](../../../../packages/client/ui-trajectory/src/client/TrajectoryCell.tsx) — 高 38px 的步骤行，类型为 User / Message / Tool（无 Think、Call、Result 行）。reasoning 块跳过（无块级时钟）。每对 `tool-call` + `tool-result` 折成一行 Tool（`name ·` 加截断参数），Time 在两端皆知时为 `result.time − callTime`。Message 行携带来自 `assistant.usage` 的 Input/Output/Think token 列。自身耗时 Time 使用 `+Ns` / `+N.1s`，缺失时为 `—`。选中态绘制 2px 内嵌的 `--dsw-alias-brand-primary-new-colorprimary-new-color` 环（`selected` prop），且未接线到 chat 选中。
+- [`TrajectoryTurn`](../../../../packages/client/ui-trajectory/src/client/TrajectoryTurn.tsx) / header / group header — 粘性 Turn 条背景通栏铺 `ghost-active-fill`；标题／列标与 Message/Step 主体落在居中的 `max-width: 880px` 内容道。单元格右侧列与 Turn 标头共用几何（`320 = 4×71 + 3×12`）；cell pad 20/8。
+- [`deriveTrajectoryLayout`](../../../../packages/client/ui-trajectory/src/client/layout.ts) 将 assistant `blocks[]` 展开为单元格，按 `callId` 将 tool-call 与 tool-result 配对为 Tool，折叠 `partial` 与 `runningCalls`（去重），仅将用量挂在 Message 上（含无 text 块时的空回退行），并以墙钟跨度 + 工具直方图构建分组描述（`1.5s bash×6`）。`user/message` 无线上 turn，故每条 User 行归入下一 assistant/steering 的 turn，否则归入进行中的 `partial` turn，否则为 `lastAssistantTurn + 1`（或 `1`）。context 节点不产出单元格，但仍推进 Message 耗时游标。
+
+[`ConversationNode`](../../../../packages/client/runtime/src/client/sessions/conversation.ts) 携带来自 `SessionEvent.time` 的 `time`；`ToolResultNode.callTime` 与 `RunningToolCall.time` 来自配对的 `tool/call`。耗时规则：User 为 `+0s`；Message = assistant.time − 上一表面时间（含跳过的 context）；Tool = 在两者皆知时 result.time − callTime；进行中 Tool = `—`。分组标头耗时为组内最早→最晚绝对时间（墙钟跨度；Tool 贡献起点与起点+自身耗时）。
+
+## Alternatives considered
+
+**为 reasoning 块保留 Think 单元格。** 否决：单条 `assistant/message.time` 无法给出 Think 自身耗时（除非上 chunk 级时钟）；与其显示 `—`，不如省略该行。
+
+**保留分开的 Call 与 Result 行。** 否决：Result 没有可展示的自身耗时；一行 Tool 承载 call→result 区间。
+
+**自会话／轮次起点累计耗时。** 否决；Time 列是每行自身的耗时。
+
+**将用量挂在展开后的第一行。** 否决；用量仅附着于 Message。
+
+**用 Date.now() 显示进行中工具的耗时。** 延后；进行中的 Time 保持为 `—`。
+
+## Consequences
+
+一旦 fold 发出 `time`，Trajectory 标签页即可渲染带自身耗时的已定稿与进行中展开行。行为导向的覆盖位于 `packages/client/ui-trajectory/tests/{cell,layout,views}.spec.tsx`。chat 选中深链与更细的块级时钟仍延后。

.agents/notes/archived/feature/2026-07-24-new-session-clears-to-empty-state.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
+2026-07-24-new-session-clears-to-empty-state.md: c9b57fec3aa093062847aacba4d01b877edf4bd5
+2026-07-24-new-session-clears-to-empty-state.zh.md: 82a4f8b1e933d6aa3531556e8be4839b204ea562

.agents/notes/archived/feature/2026-07-24-new-session-clears-to-empty-state.md

@@ -0,0 +1,24 @@
+# Agent Note: New Session clears onto the empty-state launch
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-24-new-session-clears-to-empty-state.zh.md)
+
+## Problem
+
+Sidebar "New Session" created and opened a blank session immediately, so the center column showed `ConversationRoot` with an empty transcript and the resident composer. The Figma NEW SESSION screen (`EmptyState` + shared `InputBar` hero) only rendered when `sessions.current` was already undefined, so the launch page was unreachable from the primary creation control.
+
+## Decision
+
+`SessionsService.clear()` wipes the persisted selection and `list.current`. Top-level sidebar creation entries (`onCreate()` with no cwd — New Session and New Workspace) call `clear()` so `AppFrame` renders `conversation.empty`. The empty state's first send still runs `conversation.startSession` (create → open → send) and reuses the same `InputBar` component as the resident composer (`variant="hero"`). Per-project "+" (`onCreate(cwd)`) keeps create-then-open until the empty-state picker can accept a seeded cwd.
+
+## Alternatives considered
+
+**Keep create-then-open for New Session and add a second empty chrome inside ConversationRoot when the transcript is empty.** Rejected: that duplicates the launch InputBar and breaks the empty→content ruling that one InputBar moves position rather than swapping components.
+
+**Route New Session through a dedicated route or slot outside selection.** Rejected for this pass: `conversation.empty` already owns the launch UI; clearing `current` is the existing empty branch.
+
+## Consequences
+
+New Session no longer mints a host session until the first send. Reloading after clear stays on the empty state. Project-scoped "+" still creates immediately. `EmptyState` stacks the Figma hero (Input_Bottom 75:8208) as fish + title, a Menu-backed workspace chip above the card, then shared `InputBar` (`variant="hero"`, max-width 800, r20 card matching the composer — not a taller r24 hero), with a soft ellipse glow (figma 313:14109) centered behind the picker + card and width-locked to the card (`1051/776` asset ratio) so it scales with it. The chip uses the soft interactive hover fill + 12px radius from 75:8208 and opens MenuDropdown (figma 122:9481; `--dsw-specific-menu` + `--dsw-shadow-lv3`): basename rows with folder icons and a trailing check, then a separator and "New Workspace" whose submenu (figma 419:16920) offers "Use a existing folder" and "Create new". Use a existing folder opens the path Dialog (figma 451:18655 copy — "Enter an existing folder path" / Open Folder) over a full-viewport mask (`--dsw-alias-bg-mask-1` + `--dsw-mask-blur`) and sets the chip cwd. Create new opens the same Dialog chrome to name a folder under `host.describe().cwd`; success runs `sessions.createWorkspace` → host `session.create` (mkdir recursive) → `sessions.open`, so a default session lands in the new workspace. `InputBar` paints the bottom chrome (attach / Plan / Read-only / model) with local native `<select>` state only — host plan, access, and model seams remain unwired.

.agents/notes/archived/feature/2026-07-24-new-session-clears-to-empty-state.zh.md

@@ -0,0 +1,24 @@
+# Agent Note: New Session clears onto the empty-state launch
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-24-new-session-clears-to-empty-state.md) | 中文
+
+## Problem
+
+侧栏「New Session」会立即创建并打开空白会话，因此中间栏显示带空 transcript（文本记录）与常驻 composer 的 `ConversationRoot`。Figma 的 NEW SESSION 屏（`EmptyState` + 共用的 `InputBar` hero）仅在 `sessions.current` 已为 undefined 时渲染，因而主创建控件无法到达启动页。
+
+## Decision
+
+`SessionsService.clear()` 清除持久化选中项与 `list.current`。顶层侧栏创建入口（无 cwd 的 `onCreate()`——New Session 与 New Workspace）调用 `clear()`，使 `AppFrame` 渲染 `conversation.empty`。空态的首次发送仍走 `conversation.startSession`（create → open → send），并复用与常驻 composer 相同的 `InputBar` 组件（`variant="hero"`）。按项目的「+」（`onCreate(cwd)`）继续 create-then-open，直到空态选择器能接受预填的 cwd。
+
+## Alternatives considered
+
+**为 New Session 保留 create-then-open，并在 transcript 为空时于 ConversationRoot 内再加一套空态 chrome。** 否决：这会重复启动页的 InputBar，并破坏 empty→content 的约定——同一 InputBar 应移动位置，而非互换组件。
+
+**将 New Session 路由到选中状态之外的专用 route 或 slot。** 本轮否决：`conversation.empty` 已拥有启动 UI；清除 `current` 即是既有的空态分支。
+
+## Consequences
+
+New Session 在首次发送前不再创建 host 会话。clear 后重新加载仍停留在空态。项目范围的「+」仍立即创建。`EmptyState` 按 Figma 堆叠英雄区（Input_Bottom 75:8208）：鱼标 + 标题、卡片上方由 Menu 驱动的工作区 chip，再接共用的 `InputBar`（`variant="hero"`，max-width 800，与 composer 一致的 r20 卡片——而非更高的 r24 英雄区），选择器与卡片背后居中铺一层柔光椭圆（figma 313:14109），宽度按卡片锁定为 `1051/776` asset 比例，随卡片缩放。Chip 采用 75:8208 的柔和交互 hover 填充与 12px 圆角，并打开 MenuDropdown（figma 122:9481；`--dsw-specific-menu` + `--dsw-shadow-lv3`）：带文件夹图标与尾随勾选的 basename 行，分隔线后是 "New Workspace"，其子菜单（figma 419:16920）提供 "Use a existing folder" 与 "Create new"。Use a existing folder 打开路径 Dialog（figma 451:18655 copy — "Enter an existing folder path" / Open Folder），置于全视口遮罩（`--dsw-alias-bg-mask-1` + `--dsw-mask-blur`）之上，并设置 chip 的 cwd。Create new 打开同一套 Dialog chrome，在 `host.describe().cwd` 下命名文件夹；成功则走 `sessions.createWorkspace` → host `session.create`（mkdir recursive）→ `sessions.open`，在新 workspace 中默认落下一会话。`InputBar` 绘制底栏 chrome（attach / Plan / Read-only / model），仅用本地原生 `<select>` 状态——host 侧的 plan、access、model 接缝仍未接线。

.agents/notes/archived/manifest.json

@@ -0,0 +1,140 @@
+{
+  "version": 1,
+  "files": {
+    "architecture/2026-06-20-extract-example-app-packages.i18n.yaml": "sha256:d99b612cc1051c86d883d74737c72e921735e7a28e0b5e6351d3870c664bdcc4",
+    "architecture/2026-06-20-extract-example-app-packages.md": "sha256:9c7aca3a1e9a1ccc3729961663bc649b90076e671cae23e3db8203305983ccce",
+    "architecture/2026-06-20-extract-example-app-packages.zh.md": "sha256:19bd50232d9f25d35aa3f9dc72d9af0df457dd0eaca8b982d5aa625e5b95bcff",
+    "architecture/2026-07-03-filesystem-directory-listing-seam.i18n.yaml": "sha256:636a822f3240e0401cdddad6a21f3454af1c1593fff14d4c9ce6613495f7dac1",
+    "architecture/2026-07-03-filesystem-directory-listing-seam.md": "sha256:809a3c79f4d602607e8fa93aafd1ebccf4fae50c31f1fb1b1e386bb7ad089153",
+    "architecture/2026-07-03-filesystem-directory-listing-seam.zh.md": "sha256:13735cd4c9fe990e6df3b028d6da01da89e94fde454dc0e968e517151cbd4281",
+    "architecture/2026-07-23-unified-session-query-service.i18n.yaml": "sha256:e8733b6543d9602ec206a087d9e89815f041f60fb57e93bee80e1309b9f03067",
+    "architecture/2026-07-23-unified-session-query-service.md": "sha256:28d003686f29ec5e072e51e73da353575bcdcba5af20fefdfad88340e1ddd32c",
+    "architecture/2026-07-23-unified-session-query-service.zh.md": "sha256:cfbe6525bc3b072fbc6db6bdca7a4d8cb4fc5507b1655bebc6af0589ed29ed31",
+    "architecture/2026-07-24-dsh-commander-argument-adapter.i18n.yaml": "sha256:cf99eda0e58b49630d5f95792459d7095666fafbef61f614165d5cdd031b7118",
+    "architecture/2026-07-24-dsh-commander-argument-adapter.md": "sha256:705654c8a43bcd199f72c21a77d24ca8bfa02447aff1c7f3e4e820be61dcd562",
+    "architecture/2026-07-24-dsh-commander-argument-adapter.zh.md": "sha256:3844f02d7659d18caf5d39e1131ed775c789cbf92dc44b4a446c7d6468aa5d00",
+    "bug-fix/2026-07-20-code-mode-result-card-completeness.i18n.yaml": "sha256:1035dae11d049d32ab09fd7d4f950eceae44bf46ba498b3cfaf3c75102b9fb64",
+    "bug-fix/2026-07-20-code-mode-result-card-completeness.md": "sha256:6ca2c9d4df98be18813ef38b7462db880900b5bcd6944fbcd1b8f2258006b93e",
+    "bug-fix/2026-07-20-code-mode-result-card-completeness.zh.md": "sha256:ed85fa7f935e5f525d566bc37a92014614983e649c75de9a9f244939097a7991",
+    "bug-fix/2026-07-22-collapsed-sidebar-control-rail.i18n.yaml": "sha256:98de4a1ae016608b88010d413a204c2d33695f4b1d7217e5d1b705be09c1b669",
+    "bug-fix/2026-07-22-collapsed-sidebar-control-rail.md": "sha256:b58620a3cf203507a5d651b90554bb7897e9d271613dc7c32d0f3bec992475bb",
+    "bug-fix/2026-07-22-collapsed-sidebar-control-rail.zh.md": "sha256:f36ef24f26ead60b01169c8e4a2a01b396c3f4284f14979e4d52b47c9589075c",
+    "bug-fix/2026-07-23-demo-web-builds-client-bundles.i18n.yaml": "sha256:f657e2166a05d6164c1ca65560bdd168ed969f7354217d8ec7a00274fd6c4307",
+    "bug-fix/2026-07-23-demo-web-builds-client-bundles.md": "sha256:a9d8dfcd153b1d10479e9d42848f07adf89398cb685e1a09afafcecff14e36d9",
+    "bug-fix/2026-07-23-demo-web-builds-client-bundles.zh.md": "sha256:dd06828964980798f343b8aafdeded2580b5b2e4c794305221fe73dab0a7eba2",
+    "bug-fix/2026-07-23-thinking-row-disclosure-target.i18n.yaml": "sha256:fd926967311f30ea4a222e88b845f95d74af75d1e94b24ebef59186593b9ca78",
+    "bug-fix/2026-07-23-thinking-row-disclosure-target.md": "sha256:92815c170972b1b91c3d75dd0c846c070805ec1e99ce368b6aae37b048e19869",
+    "bug-fix/2026-07-23-thinking-row-disclosure-target.zh.md": "sha256:0e09f5f5e14d74214e5157ceb5859c866bab6de701c47e2ce5c450866d75aecf",
+    "bug-fix/2026-07-26-intent-draft-same-tick-echo.i18n.yaml": "sha256:c623947c4fa00e6d4b51792c7972ba09582bbcb7605beb373725c0dd666f2c81",
+    "bug-fix/2026-07-26-intent-draft-same-tick-echo.md": "sha256:fa8b1417b2cdd3deecbf8e55bdddd73dd3a8c6e3486fd399b0b8bdf317e56373",
+    "bug-fix/2026-07-26-intent-draft-same-tick-echo.zh.md": "sha256:00ce72552dbaa11562fbc541343a5d33f9449edabbe6dd354eb879a7d4d530f8",
+    "feature/2026-06-30-subagent-observe-enrich.i18n.yaml": "sha256:08c2478ba394429f46c1e87a9f055e88704a9000e5d250d5600c0c85124cb17f",
+    "feature/2026-06-30-subagent-observe-enrich.md": "sha256:0630975c3e325975a932f58a65a178b79c624dc56ebd29e288e96f5a189cfbfa",
+    "feature/2026-06-30-subagent-observe-enrich.zh.md": "sha256:b9fbb44a7d81f4063faf3baaf97c382a2f5106be533feb4de792ee57b766c1a4",
+    "feature/2026-07-21-dsh-system-prompt-source-path.i18n.yaml": "sha256:22efaf3237425fecbac1b40a444454e0fc244a3c85c2f6a14535de22ea777719",
+    "feature/2026-07-21-dsh-system-prompt-source-path.md": "sha256:5fa554932c62a8bbd5a619581710d7f8b6b65d79ec1e340129cda96d279c5ae3",
+    "feature/2026-07-21-dsh-system-prompt-source-path.zh.md": "sha256:995cd593074881c72510a6af3ba80108bbf986d49508cce9f698c2fcb493fd23",
+    "feature/2026-07-21-tui-banner-brand-gradient.i18n.yaml": "sha256:adc228a5e6797096002619ba5bd8c47d49f2d5e98e40dd168ae5e07bc57bc460",
+    "feature/2026-07-21-tui-banner-brand-gradient.md": "sha256:9b14ab1ae88eab598cd0f8d2d1cfbe53cec89a5374e3e3c765b487c91579e1eb",
+    "feature/2026-07-21-tui-banner-brand-gradient.zh.md": "sha256:111dfde012857af10b2f7b9b8a9b9f783522e4ad14dad3ff5e25706b5bbffcbe",
+    "feature/2026-07-21-tui-borderless-banner.i18n.yaml": "sha256:9e80de590085e6e02f0830fedb149289387bb83eaa073c9f99a4eb7af1afba80",
+    "feature/2026-07-21-tui-borderless-banner.md": "sha256:e3237b4de432cd97262a4baf1f64fee6bea48c3180a2e773575f603ed008d44c",
+    "feature/2026-07-21-tui-borderless-banner.zh.md": "sha256:6c65cd654a1aed704d80b5882aba8ae0a2c1090709d672189847f5d0a6f58122",
+    "feature/2026-07-21-tui-footer-cache-hit-rate.i18n.yaml": "sha256:56898ebb26741c83bb1c5de4c6e64bd3ca06b5e3b90ab79107823f19353596eb",
+    "feature/2026-07-21-tui-footer-cache-hit-rate.md": "sha256:c66a1485d21fe6a4b975ffeed56c021c0d9556488bfadc4fb32648b3948c1fea",
+    "feature/2026-07-21-tui-footer-cache-hit-rate.zh.md": "sha256:6fc2efe5817e83a9deb057a2de9b31b4c786700ebf40d38369abb5cefae231d0",
+    "feature/2026-07-21-tui-reload-command.i18n.yaml": "sha256:9be416ccd681aed0781fdfd2c44c4821c1e45f2a0deccb1f2b47d46163bde488",
+    "feature/2026-07-21-tui-reload-command.md": "sha256:b8616457822ae87c90062308bc8c0d2badd5f368092ec65847d0d9520b1ac372",
+    "feature/2026-07-21-tui-reload-command.zh.md": "sha256:c24bfcb0df13977a9c11c4d0fe433169e535b5f764995b668430dbb14a8e6b33",
+    "feature/2026-07-21-tui-steering-queue-badge.i18n.yaml": "sha256:a029da558a6e14e1f13269960b98273ca9af0141579967acfbc19b656775f4a5",
+    "feature/2026-07-21-tui-steering-queue-badge.md": "sha256:9aabd68c8910fdc7e7b05674492ddb8dc9285dd691fe554adcb84026fb846cc8",
+    "feature/2026-07-21-tui-steering-queue-badge.zh.md": "sha256:919fd737866c3700f945751628071dab89eabdbf8f809deab93b9e6fbe2c8c59",
+    "feature/2026-07-21-tui-verbose-status-line.i18n.yaml": "sha256:4371b9a46d713d4180aa5d0b1ecde1ff3cae948380a8f56474c895e6113d7824",
+    "feature/2026-07-21-tui-verbose-status-line.md": "sha256:9dcba19ee725b1593e9413a1da5398c205a258aff2e384acd406bb618e86c7f0",
+    "feature/2026-07-21-tui-verbose-status-line.zh.md": "sha256:203c2abac99cedf7afa2540c925367ba66f00b61b926d1cc86472a603ad2bb07",
+    "feature/2026-07-23-trajectory-step-cell.i18n.yaml": "sha256:fe2e935a0affdef877902a40d9861ef5f55b30f40650469f6a52a4d45a92793f",
+    "feature/2026-07-23-trajectory-step-cell.md": "sha256:185e3b87174cb6d2f2d2271fd2a74b1517d03e8570be602570d027bf6002d106",
+    "feature/2026-07-23-trajectory-step-cell.zh.md": "sha256:51f46be43d2f5c4f78a05ed9aeec92d1f33ac988f45cf24d35528e9c43828ef3",
+    "feature/2026-07-24-new-session-clears-to-empty-state.i18n.yaml": "sha256:978638cbf18bc6dce9fea0817654f41cc307f99004a637b85a63ae2208fe9095",
+    "feature/2026-07-24-new-session-clears-to-empty-state.md": "sha256:b6b71d3883a167056070713e3dffb5046de953bdd218074d17c88e7690e03d83",
+    "feature/2026-07-24-new-session-clears-to-empty-state.zh.md": "sha256:82a80b48337487029acd05a0137d268f0850f46801fa44a0e62733cacd00d5e9",
+    "process/2026-06-11-doc-sync-enforcement.i18n.yaml": "sha256:33b6d5874427bd7a2bd82e7e2f4f482b12448b2464aef15a9c57975edb48554d",
+    "process/2026-06-11-doc-sync-enforcement.md": "sha256:aa2fe83d519fc30d48dff19e596e83c8922aacc9e063e14fe2cc35b769b9100e",
+    "process/2026-06-11-doc-sync-enforcement.zh.md": "sha256:698017bd35f030fdea3eac51df9e43138c48140f504739d687b7251d13fced2b",
+    "process/2026-07-03-documentation-graph-atlas.i18n.yaml": "sha256:b1e1ed4b7865d87f939dbf8c94c0ea1069fdf7af6fa68f695e6c9d6eccbeb123",
+    "process/2026-07-03-documentation-graph-atlas.md": "sha256:b62e92bb12123bfa4c4dac806f584aabb6b60af4c5a6a4ab88f84bb9153e766d",
+    "process/2026-07-03-documentation-graph-atlas.zh.md": "sha256:3485ede4a5e695643bcf9e744a62f8914cff788ae35717dac5eb6bf77e0d65cf",
+    "process/2026-07-21-doc-sync-through-gate-scheduler.i18n.yaml": "sha256:1dbe70d21dd510bec4f2f56ae39d0fdc7290d5648280ca0b67224cd23b3a02a8",
+    "process/2026-07-21-doc-sync-through-gate-scheduler.md": "sha256:b3eb3f2395ad8f1b77f44aa3fdac79856e5d0b6b4873560d0cc87b63de2ea2e0",
+    "process/2026-07-21-doc-sync-through-gate-scheduler.zh.md": "sha256:e262e02c3d08057b83b0d29281eadb92723f0fe5b3f54424528f47be137bc760",
+    "process/2026-07-22-installer-in-repo-skip-clone.i18n.yaml": "sha256:677aa91c3ccd9eda8a658b10410699ac608d3891d2fa32529898a3432fb56660",
+    "process/2026-07-22-installer-in-repo-skip-clone.md": "sha256:4e30c0dd5429db33638a91a30afdd3386ac1a4705bd259a5eef325b5f86cced8",
+    "process/2026-07-22-installer-in-repo-skip-clone.zh.md": "sha256:1d93c99f5a8d56077e766242c33245621626be55cf481d01c83bb5cbbe9a74d7",
+    "process/2026-07-23-browser-demo-gif-recording.i18n.yaml": "sha256:d2ecc01338d82118288398275e370c527a8f2255e06b0cd1300efc320f3716a0",
+    "process/2026-07-23-browser-demo-gif-recording.md": "sha256:17b3f267efa8e99eb0154cb1dc002c44e3299b1dd0e52190921fc327b45b072a",
+    "process/2026-07-23-browser-demo-gif-recording.zh.md": "sha256:e2818d1ecfc23276a4873f8a6333b1b2b92e6c9d2febce3855bb994d3a8fdce1",
+    "simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.i18n.yaml": "sha256:ad3d1263cb0051b885173bf064de62065e2c646ccaae2d7250723da3b4eab90c",
+    "simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.md": "sha256:8fb061d51c8c23b47d2367814bab3623c6d5b972f38d207a273caa9030b579bd",
+    "simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.zh.md": "sha256:2ffeaca91f82844a5616d6dcce6b4af514bb8a7c46f78e47f668b204ac6edc04",
+    "simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.i18n.yaml": "sha256:f01960a5e8fab5e4f284f35ced6b84400aab257b243805db797a9c4a00ff525e",
+    "simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.md": "sha256:0020f6b80e8bea5a8441b5bf7385a9bcfacbe14485f0e77de5d8b4fe3d2f69d0",
+    "simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.zh.md": "sha256:21647760eb06e57f8a38b35196233c634b8284a178b99b14f504a791758e9088",
+    "simplification/2026-06-20-prune-dead-seam-methods.i18n.yaml": "sha256:0594648368c942f429599ac0ff5977d62c89c70a31d4bdbac61b0a30fe15ef3b",
+    "simplification/2026-06-20-prune-dead-seam-methods.md": "sha256:fd3b0eaf600e178eeeef0c6cedc71f2382878733c557f1915d3b47f74a1d0d6d",
+    "simplification/2026-06-20-prune-dead-seam-methods.zh.md": "sha256:4f5feef9331e3a1346bc362ffb39cfa373db2c609041bfeee6d88a10392464b1",
+    "simplification/2026-07-04-drop-inert-request-knobs.i18n.yaml": "sha256:e4c992a27ae0e37e5ef663c2cddf55eefe20387fd6103bebf655834d8e75e9db",
+    "simplification/2026-07-04-drop-inert-request-knobs.md": "sha256:8735c2b868a85b13235e0491a0fa7b9570dd090eef5170324fc5e93782687b67",
+    "simplification/2026-07-04-drop-inert-request-knobs.zh.md": "sha256:78b243f5d580f2a6fbbdb7d26574295d6ed74feb8d9bba34bbcdf4aa87624b5c",
+    "simplification/2026-07-04-drop-unconsumed-web-observation-surface.i18n.yaml": "sha256:30cbf5f573ad9df5140a2bc57181c6465dc3cb0717d192a8bbbb5b1c68a56f29",
+    "simplification/2026-07-04-drop-unconsumed-web-observation-surface.md": "sha256:2d4d4ad2d0b72c602a20af6082392c22c889e4cf455614177fdc9e892069948e",
+    "simplification/2026-07-04-drop-unconsumed-web-observation-surface.zh.md": "sha256:012b4fb2a346e01d5d88a53913a790df713650907ad7987b744bba456be36bbf",
+    "simplification/2026-07-04-prune-producerless-vocabulary-variants.i18n.yaml": "sha256:338c2290ae2cdcbeb758e996970e7f9dc8c36261f076302e358d70508604bac6",
+    "simplification/2026-07-04-prune-producerless-vocabulary-variants.md": "sha256:87a269ba0c849084bf16b546fe8fff3e6bba188d3565b10099721109551ada5a",
+    "simplification/2026-07-04-prune-producerless-vocabulary-variants.zh.md": "sha256:1485426f46ae46bf5c25ab95962cb7edc4dd3b43f3bd2211c0e41f02c505e1fc",
+    "simplification/2026-07-04-prune-write-only-fs-surface.i18n.yaml": "sha256:6c8ed11b067c34f1af060d6c36de3685f3a15874786d811620b57e42c2b8d5c6",
+    "simplification/2026-07-04-prune-write-only-fs-surface.md": "sha256:5602e09004f9f2b81f447abed4de10b18a96df5f44b13fd1cc0c06ffd3ce5b4a",
+    "simplification/2026-07-04-prune-write-only-fs-surface.zh.md": "sha256:086f2cce3dc120f0c31c7dbc1855390f72e3940f2ffa92108de20fa175fff86a",
+    "simplification/2026-07-04-remove-agent-steering-mirror.i18n.yaml": "sha256:24fb3c525cae7334841b7daca4c65783f013aa53910a81d20e092b4dd7081cda",
+    "simplification/2026-07-04-remove-agent-steering-mirror.md": "sha256:3351fef50ba8635e5a3829a39cad24333bf3285799602b0891acdec312aa858f",
+    "simplification/2026-07-04-remove-agent-steering-mirror.zh.md": "sha256:75ad399226bc42950128e410be9666cb3d0b76ca673418f31cd2a57a8f56e513",
+    "simplification/2026-07-04-share-app-bin-boot-glue.i18n.yaml": "sha256:bd64279826444b41f6f1dc5d92fecd974edc3663885470f2eae226978926a59b",
+    "simplification/2026-07-04-share-app-bin-boot-glue.md": "sha256:de0f4dca1e89c0c19d649aa37989df1991376d2cac1a5ec72c1a3ca0dce27e49",
+    "simplification/2026-07-04-share-app-bin-boot-glue.zh.md": "sha256:e014ac4c2b609b70c467540ff0985c59a74df0eaf3062c43ffcaf1ac35d18ce2",
+    "simplification/2026-07-04-trim-acp-bridge-unreachable-surface.i18n.yaml": "sha256:9080af48de70cc519f935896ae90134bcecdf4cee56bb5abb3e909672f2dded3",
+    "simplification/2026-07-04-trim-acp-bridge-unreachable-surface.md": "sha256:c11fbdea4bdd14eba517dc6377f8e59eb73fc05779424f38833cc662baf04fd5",
+    "simplification/2026-07-04-trim-acp-bridge-unreachable-surface.zh.md": "sha256:f1bceae26fdea3fc71d8a0e32530eadb00342590a611b9fbc7ff09d0fc8aa3b8",
+    "simplification/2026-07-12-drop-unconsumed-skill-provider-events.i18n.yaml": "sha256:cb9f223b74ea3ba0279f17d2bfd59033b67d1ea7b525b0ebee01fb9ee74da4be",
+    "simplification/2026-07-12-drop-unconsumed-skill-provider-events.md": "sha256:cc78d0f80438e52e7d928b786101a902a15e4317fb0db2a47833c44520937c60",
+    "simplification/2026-07-12-drop-unconsumed-skill-provider-events.zh.md": "sha256:ccb7146536c8a0f956d4799ddafc7b7cfea264fbc642107bd8aa24f06d88932d",
+    "simplification/2026-07-12-prune-unused-web-seam-fields.i18n.yaml": "sha256:896dea8f5430603c445169fa79bfba997421a76d48fa4336349ec693572e6167",
+    "simplification/2026-07-12-prune-unused-web-seam-fields.md": "sha256:e732eb5eed007e95f40f32eddd8d94cd34f0ce579f1a70b16ca072a48a3989b4",
+    "simplification/2026-07-12-prune-unused-web-seam-fields.zh.md": "sha256:ac427d5cf6525c155b12dc7605954ebe3ce1f3edb6da0d0305e8d79cf475460b",
+    "simplification/2026-07-19-retire-subagent-mock-package.i18n.yaml": "sha256:a7e5e21bf8a3a06bbf1272c677a7fff980e7548459405835416b88f1537bfe92",
+    "simplification/2026-07-19-retire-subagent-mock-package.md": "sha256:3df91519b77efcc413a54927adb2f829e944ce7f827211ac6ae66d4b5e0398a7",
+    "simplification/2026-07-19-retire-subagent-mock-package.zh.md": "sha256:c86d96800abc5aebf2d63694cb2cdcb21867091b2867de44493212f302498889",
+    "simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml": "sha256:602ab8fda1facb04a8f04d088267cbbd0426d607a8cc8c3fc056887f4a2696d9",
+    "simplification/2026-07-19-use-one-session-surface-manager.md": "sha256:267882c357527a12d8581c9d78249819a987c766a74a2d47f351dc5b14bf7d0a",
+    "simplification/2026-07-19-use-one-session-surface-manager.zh.md": "sha256:21c68a432c22209a3c19c8424da8e03fe91415d9ce3753cf17d727663077e4c9",
+    "simplification/2026-07-21-tui-remove-cancel-command.i18n.yaml": "sha256:17ee6e9a3db867b85d8399879c40552a6771b5d7585f7b58e33601428a1309e3",
+    "simplification/2026-07-21-tui-remove-cancel-command.md": "sha256:e90ad809b5ea241a653641f7331893347a1a0be7c677c99cbfc6bba8c907ab19",
+    "simplification/2026-07-21-tui-remove-cancel-command.zh.md": "sha256:94d388753157eb498b9a8dbd9050dc07e5ee893e9b5a07f4c265b2e8e66f6338",
+    "simplification/2026-07-21-tui-todo-write-opt-in.i18n.yaml": "sha256:633975e45444f179e5fcd258d3c4bce924975583505fa97f18cff21861a88ca2",
+    "simplification/2026-07-21-tui-todo-write-opt-in.md": "sha256:7c4c0818f5cb5b1a506dabb71a56b7d79b811e4b912d492865f1404f4d1ece99",
+    "simplification/2026-07-21-tui-todo-write-opt-in.zh.md": "sha256:2c121b8ea03182f7854e7d834b07967fdb6790af6a2a38c1d24bb0ca968496ba",
+    "testing/2026-06-20-remove-redundant-snapshot-log-expected-output.i18n.yaml": "sha256:4177012c0821a8c22499852ecdf096af56d7263cb91c5d9d1bcd552cc26a3e00",
+    "testing/2026-06-20-remove-redundant-snapshot-log-expected-output.md": "sha256:45234e7cc04b6010c6141f8d5924c04547300098f96262d423c50108e7c7011a",
+    "testing/2026-06-20-remove-redundant-snapshot-log-expected-output.zh.md": "sha256:15e5a4ad3dee0bb711480cabe45cd97ec37bbdba19c2c2b47d1e9c203b07a48b",
+    "testing/2026-06-22-fork-snapshot-scenarios.i18n.yaml": "sha256:d9fb0a30bbf58bbd6fcb45c84bee204f3f97a8a4cf7b867eec7320ba8663abf7",
+    "testing/2026-06-22-fork-snapshot-scenarios.md": "sha256:2bd6458490789f68110ec6a7fb6ea55af544f09df854c163fcb83f04a440da98",
+    "testing/2026-06-22-fork-snapshot-scenarios.zh.md": "sha256:f39e26c527dcb92d364b00bd3294f79bb30960ff35a4309bde00563aa594ec08",
+    "testing/2026-07-04-hook-snapshot-matrix.i18n.yaml": "sha256:f8fe2a2893e929d3a0476151f4f44ce9b4c26790aae84f6ddbf365239ce6a0bb",
+    "testing/2026-07-04-hook-snapshot-matrix.md": "sha256:287b9e0d97ea2e79a3ec6175c02ab01ef1314652528d5911a3a971e008094b6e",
+    "testing/2026-07-04-hook-snapshot-matrix.zh.md": "sha256:25b33993da3b8eb94113b90050ac03b72d40bf085bff72b3119d38105a2d7ee2",
+    "testing/2026-07-04-single-source-acp-replay-config.i18n.yaml": "sha256:cdf1ede909bc51792b1dcd74d5928111f75d4aba5020e8b30b3f395887348329",
+    "testing/2026-07-04-single-source-acp-replay-config.md": "sha256:a94352fe79201949e28028abe4c7d932fd0d2e81d869e7d3b58d22f54a649417",
+    "testing/2026-07-04-single-source-acp-replay-config.zh.md": "sha256:bed4dcd236a07192dd3de6c76e4a5c47dd5ec35963ce830bd5521bbb41d3f3a3",
+    "testing/2026-07-06-pin-request-header-content-in-one-scenario.i18n.yaml": "sha256:4f3ebae0faea8a38ffe0d5291a33b3bcf99ed723f8e0cc5cccecbedbf4fb9ce9",
+    "testing/2026-07-06-pin-request-header-content-in-one-scenario.md": "sha256:050bf8044ce22a27a0f57b5cef84ccff0dc45b1a3f6b70aa41950d41038d0702",
+    "testing/2026-07-06-pin-request-header-content-in-one-scenario.zh.md": "sha256:cac75d4475666239bbe0030b90c0fa7cc66024af5b9f8ef217e53018be64890e"
+  }
+}

.agents/notes/archived/process/2026-06-11-doc-sync-enforcement.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
+2026-06-11-doc-sync-enforcement.md: 00fc6e904f1908b5cc4ddbe02b6eecf46b06408b
+2026-06-11-doc-sync-enforcement.zh.md: 9daaf88626d18093f8af7ba9ee5b6ce9e596d011

.agents/notes/archived/process/2026-06-11-doc-sync-enforcement.md

@@ -0,0 +1,33 @@
+# Agent Note: Doc-sync enforcement
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-06-11-doc-sync-enforcement.zh.md)
+
+## Problem
+
+AGENTS.md promises that docs and code stay strictly in sync, but the promise was verified by eyeball. Review caught drift twice — a cookbook example contradicting the type policy, and a README citing the wrong `registerAdapter` call. Out-of-sync docs are worse than no docs, and this codebase is built primarily by agents that follow gates far more reliably than prose (mechanical quality gates). Two classes of doc drift are mechanically checkable: code blocks that no longer compile, and the event-taxonomy table that duplicates the `interface Events` declarations.
+
+## Decision
+
+Two gates, mirroring the existing `scripts/` style (tsx ESM, one job each):
+
+1. **`doc-typecheck`** extracts every fenced ` ```ts ` block from `README.md`, `docs/**`, and `packages/*/README.md`, writes them to a temp project extending the root `tsconfig.json`, and compiles it with `tsc -b`. The temp project reuses the source `paths` map and the root project references, so documentation examples see source while vendored code remains checked under its own tsconfig settings. A block that is a deliberate sketch opts out with an explicit ` ```ts ignore-check ` info string; the script reports the opt-out ratio and fails if it exceeds half, so the escape hatch can't quietly become the norm.
+2. **`verify-event-taxonomy`** extracts the event names from the `interface Events` blocks across `packages/*/src` and from the taxonomy table in `docs/architecture.md`, and asserts the two sets match exactly. Verify, don't generate: the table keeps its hand-written Mode/Purpose columns; only the set of names is checked. (Landing this surfaced three events the table had been missing — `tools/change`, `llm/adapter-change`, `system-prompt/change`.) **Superseded** by [the generated cordis catalog](2026-06-20-generated-cordis-catalog.md): this gate and its `architecture.md` table are retired in favor of the fully-generated `docs/cordis-catalog/events.md` + `docs/cordis-catalog/services.md` and their `verify-cordis-catalog` freshness gate. The other gates here (`doc-typecheck`, and the `verify-md-wrap` amendment below) are unaffected.
+
+Both run via a shared `doc-sync` package.json script that contributors invoke for relevant documentation changes and CI invokes exhaustively. The [fast local Git hooks](2026-07-22-fast-local-git-hooks.md) decision keeps this surface-selected work out of commit and push hooks.
+
+**Amendment (2026-06-17):** a third gate, **`verify-md-wrap`**, was later folded into `doc-sync`. It parses each in-scope Markdown file (`README.md`, `docs/**`, `packages/*/README.md`, plus `AGENTS.md` / `packages/AGENTS.md`) with `mdast-util-from-markdown` + GFM and fails on any `paragraph` node spanning more than one source line, enforcing the docs/AGENTS.md "one physical line per paragraph" writing rule. Same verify-don't-generate principle: it reports hard-wraps and never rewrites, so it adds no formatting churn. `doc-sync` is now three gates.
+
+## Alternatives considered
+
+- **API-extractor golden reports** ([the deferred proposal](../../proposed/process/2026-06-11-api-extractor-reports.md)) — deliberately deferred: low value for an internal monorepo where reviewers already see the source diff, and a heavy, finicky dependency.
+- **Generating the taxonomy table from source** instead of verifying names — rejected as more machinery than the problem warranted; the table kept its hand-written Mode/Purpose columns until [the generated cordis catalog](2026-06-20-generated-cordis-catalog.md) superseded the check entirely.
+
+## Consequences
+
+- Doc drift in the checkable classes fails `doc-sync` and CI instead of waiting for a reviewer to notice. This is an instance of the "mechanical gates over prose" principle.
+- Making doc snippets compile costs a few stub imports/`declare`s; the `ignore-check` ratio must stay low or the gate is theater (the ratio guard enforces this).
+- The taxonomy check is name-only — a wrong Mode or Purpose column still needs human review.
+- API reports remain available to revisit if the packages are ever published externally.

.agents/notes/archived/process/2026-06-11-doc-sync-enforcement.zh.md

@@ -0,0 +1,33 @@
+# Agent Note: Doc-sync 强制
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-06-11-doc-sync-enforcement.md) | 中文
+
+## 问题
+
+AGENTS.md 承诺文档与代码严格同步，但这一承诺此前仅靠人眼核查。评审曾两次发现漂移：一次是实操手册（cookbook）示例与类型策略矛盾，一次是 README 引用了错误的 `registerAdapter` 调用。失去同步的文档比没有文档更糟；而本代码库主要由 agent（智能体）构建，agent 遵守门禁远比遵守行文约定可靠（机械质量门禁）。有两类文档漂移可以被机械检查：不再能编译的代码块，以及与 `interface Events` 声明重复的事件分类体系表。
+
+## 决策
+
+两道门禁，沿用既有的 `scripts/` 风格（tsx ESM，每个脚本一项职责）：
+
+1. **`doc-typecheck`** 从 `README.md`、`docs/**` 和 `packages/*/README.md` 中提取所有 ` ```ts ` 围栏代码块，写入一个继承根 `tsconfig.json` 的临时项目，然后用 `tsc -b` 编译。临时项目复用源码的 `paths` 映射和根 project references，因此文档示例能看到源码，而 vendor 代码仍在其自身的 tsconfig 设置下被检查。刻意作为草图的代码块可通过显式的 ` ```ts ignore-check ` 信息字符串来 opt-out；脚本会报告 opt-out 比例，超过一半即失败，防止该豁免机制悄然成为常态。
+2. **`verify-event-taxonomy`** 从 `packages/*/src` 中的 `interface Events` 块和 `docs/architecture.md` 中的分类体系表分别提取事件名称，断言两个集合完全一致。只校验，不生成：表格保留手写的 Mode/Purpose 列，仅检查名称集合。（落地此门禁时发现了表格遗漏的三个事件：`tools/change`、`llm/adapter-change`、`system-prompt/change`。）**已被取代**：由[生成式 Cordis 目录](2026-06-20-generated-cordis-catalog.md)取代。此门禁及其 `architecture.md` 表格已退役，取而代之的是完全生成的 `docs/cordis-catalog/events.md` + `docs/cordis-catalog/services.md` 及其 `verify-cordis-catalog` 新鲜度门禁。本 Agent Note（agent 决策记录）中的其他门禁（`doc-typecheck` 以及下文修订中的 `verify-md-wrap`）不受影响。
+
+两者都通过 package.json 中共享的 `doc-sync` 脚本运行；贡献者在相关文档变更中调用它，CI 则执行完整检查。[快速本地 Git 钩子](2026-07-22-fast-local-git-hooks.md)决策使这类按变更面选择的工作不进入 commit 和 push 钩子。
+
+**修订（2026-06-17）：** 第三道门禁 **`verify-md-wrap`** 随后被纳入 `doc-sync`。它使用 `mdast-util-from-markdown` + GFM 解析范围内的每个 Markdown 文件（`README.md`、`docs/**`、`packages/*/README.md`，加上 `AGENTS.md` / `packages/AGENTS.md`），如果任何 `paragraph` 节点跨越多个源码行则失败，从而强制执行 docs/AGENTS.md 中「一个段落一个物理行」的写作规则。同样遵循只校验不生成的原则：它报告硬换行但从不重写，因此不会引入格式化噪音。`doc-sync` 现在包含三道门禁。
+
+## 曾考虑的替代方案
+
+- **API-extractor 基准报告**（[已推迟的提案](../../proposed/process/2026-06-11-api-extractor-reports.md)）：有意推迟。对于评审者已能直接看到源码 diff 的内部 monorepo 而言价值有限，且依赖重、配置繁琐。
+- **从源码生成分类体系表**而非仅校验名称：否决，机制比问题本身更重；表格保留了手写的 Mode/Purpose 列，直到[生成式 Cordis 目录](2026-06-20-generated-cordis-catalog.md)完全取代了这项检查。
+
+## 后果
+
+- 可检查类别中的文档漂移会直接使 `doc-sync` 和 CI 失败，而不是等评审人发现。这是「机械门禁优于行文规范」原则的具体应用。
+- 让文档代码片段可编译需要少量 stub import/`declare`；`ignore-check` 比例必须保持低位，否则门禁形同虚设（比例守卫强制执行此约束）。
+- 分类体系检查仅限名称——Mode 或 Purpose 列的错误仍需人工评审。
+- 如果包（package）未来对外发布，API 报告方案仍可重新考虑。

.agents/notes/archived/process/2026-07-03-documentation-graph-atlas.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
+2026-07-03-documentation-graph-atlas.md: 6f2949e3673c43018f961cc954c9925945875f55
+2026-07-03-documentation-graph-atlas.zh.md: 731ae8a97a8437216c706adf86574d1982d7c484

.agents/notes/archived/process/2026-07-03-documentation-graph-atlas.md

@@ -0,0 +1,70 @@
+# Agent Note: Documentation graph index for maintainers and SDK users
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-03-documentation-graph-atlas.zh.md)
+
+## Problem
+
+The repo already had several high-trust documentation surfaces, each on a different axis: [module-graph.md](../../../../docs/module-graph.md) is generated from package `peerDependencies`, the generated [Cordis events](../../../../docs/cordis-catalog/events.md) and [services](../../../../docs/cordis-catalog/services.md) catalogs are generated from Cordis `Events` and `Context` declarations, [tool-catalog.md](../../../../docs/tool-catalog.md) is generated by booting shipped tool plugins, and [core-data-structures/](../../../../docs/core-data-structures/core.md) uses `ts type-equiv` blocks to keep pasted type definitions synchronized with source.
+
+Those references are accurate, but they are mostly catalogs. A maintainer still has to synthesize the relationships: which packages form a capability seam, which app bundles a concrete spine, which event is durable vs live, where a hook or policy plugin can intercept work, and which model-facing tool depends on which service. An SDK user has the same problem from another angle: "Which package do I install or load for the behavior I want, and which event/service/tool do I extend?"
+
+The hooks subsystem makes event producer/consumer topology and interception points much more important, and the filesystem seam makes capability seams, policy vetoes, tool presentation, and SDK assembly paths much more important — relationship graphs scoped to a small bash/todo/subagent surface would have gone stale immediately.
+
+## Decision
+
+Add generated relationship graph docs, indexed at [docs/graph-atlas.md](../../../../docs/graph-atlas.md), produced by focused generators and verified by `pnpm run verify-doc-graphs` / existing catalog freshness checks as part of `doc-sync`.
+
+The index is a relationship layer above the existing catalogs. It does not replace exact references; instead, it links to them and explains how their pieces fit together.
+
+### Maintenance modes
+
+Every graph page declares one maintenance mode:
+
+- **Generated**: all nodes and edges are discovered from source; `--check` fails if the committed artifact is stale.
+- **Hybrid generated**: source discovers the inventory, a small manifest classifies irreducible policy, and a completeness guard fails if discovered items are unclassified.
+- **Curated**: the diagram explains design intent, temporal order, or ownership; it is emitted by the generator so the graph docs remain a regenerated unit, but the content is deliberately authored.
+
+### First shipped index
+
+The index links ten relationship surfaces. Package topology and tool-package affordances live in the existing generated catalogs that already own those facts; the remaining focused diagrams are generated by `scripts/gen-doc-graphs.ts`.
+
+| Graph | Maintenance mode | Source of truth |
+|---|---|---|
+| [module dependency graph](../../../../docs/module-graph.md) | generated | `packages/*/*/package.json` peer dependencies plus package group paths |
+| [tool schema catalog and package map](../../../../docs/tool-catalog.md) | generated | boot-harvested tool schemas plus tool-package service/effect metadata |
+| [capability seams and core services](../../../../docs/capability-seams.md) | hybrid generated | Cordis service declarations plus a role manifest in `gen-doc-graphs.ts` |
+| [tui-agent app composition](../../../../examples/tui-agent/composition.md) | hybrid generated | `examples/tui-agent/cordis.yml` plugin list plus curated app/bundle expansion |
+| [headless-agent app composition](../../../../examples/headless-agent/composition.md) | hybrid generated | `examples/headless-agent/cordis.yml` plugin list plus curated app/bundle expansion |
+| [cordis-agent app composition](../../../../examples/cordis-agent/composition.md) | hybrid generated | `examples/cordis-agent/cordis.yml` plugin list plus curated app/bundle expansion |
+| [acp-agent app composition](../../../../examples/acp-agent/composition.md) | hybrid generated | `examples/acp-agent/cordis.yml` plugin list plus curated app/bundle expansion |
+| [event producer/consumer matrix](../../../../docs/event-producer-consumer.md) | hybrid generated | Cordis event declarations, AST-scanned `ctx.on/emit/parallel/serial/waterfall` sites, and explicit dynamic dispatch overrides |
+| [agent turn and step lifecycle](../../../../docs/agent-lifecycle.md) | curated | architecture.md loop lifecycle, Cordis catalog links, and session event semantics |
+| [tool execution pipeline](../../../../docs/tool-execution-pipeline.md) | curated | tool pipeline semantics and the `tools/execute` waterfall |
+
+### Why generators own the docs
+
+Package topology stays in `gen-module-graph.ts`, and tool-package affordances stay in `gen-tool-catalog.ts`, because those generators already own the canonical facts and freshness gates. `gen-doc-graphs.ts` owns the remaining relationship pages and the index. The tradeoff is that curated diagrams are edited in TypeScript string blocks rather than directly in Markdown. That is acceptable for this first cut because the user-facing artifact is still plain Markdown/Mermaid, and a future change can split the curated pages out if authorship ergonomics matter more than regeneration.
+
+### Completeness guards
+
+The hybrid pages must fail loud when their manifests are stale:
+
+- The module graph reads every package's `peerDependencies` and groups each package by its `packages/<group>/<pkg>` path.
+- The tool catalog boot-harvests shipped tools and renders the package/service/effect map from the same manifest that its completeness guard already checks.
+- The capability seam graph imports the Cordis service collector and asserts every discovered harness `ctx.<key>` is classified in `SERVICE_ROLES`, and every classified key still exists.
+- The event producer/consumer matrix labels itself hybrid because subagent lifecycle events deliberately use `ctx.events.dispatch` for per-listener containment; those dynamic edges are explicit overrides rather than invisible omissions.
+- `verify-mermaid` parses every repo-authored ` ```mermaid ` fence with Mermaid's own parser, so syntax errors fail `doc-sync` locally and in CI instead of showing up as broken GitHub-rendered diagrams.
+
+## Alternatives considered
+
+Committed diagrams use Mermaid because GitHub renders it in Markdown and it adds no new docs build dependency; dense many-to-many data such as event producer/consumer relationships uses Markdown tables instead. **PlantUML, hosted diagram services, and generated SVGs** were considered and deliberately not adopted until Mermaid becomes the limiting factor.
+
+## Consequences
+
+- Maintainers get visual entry points for topology, seams, event flow, lifecycle, and app composition.
+- SDK users get a path from use case to package composition instead of only bottom-up package references.
+- `doc-sync` now includes `verify-doc-graphs` and `verify-mermaid`, so graph drift and Mermaid syntax errors are caught with the other doc freshness gates.
+- Future fs and hooks work has a concrete place to land new complexity: fs should expand the capability docs and tool catalog, while hooks should expand the event matrix and tool execution pipeline.

.agents/notes/archived/process/2026-07-03-documentation-graph-atlas.zh.md

@@ -0,0 +1,70 @@
+# Agent Note: 面向维护者与 SDK 用户的文档关系图索引
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-03-documentation-graph-atlas.md) | 中文
+
+## 问题
+
+仓库已经有若干高可信文档表面，各自覆盖不同维度：[module-graph.md](../../../../docs/module-graph.md) 根据包（package）的 `peerDependencies` 生成；生成式 [Cordis 事件](../../../../docs/cordis-catalog/events.md)和[服务](../../../../docs/cordis-catalog/services.md)目录根据 Cordis `Events` 和 `Context` 声明生成；[tool-catalog.md](../../../../docs/tool-catalog.md) 通过启动已发布工具插件生成；[core-data-structures/](../../../../docs/core-data-structures/core.md) 则使用 `ts type-equiv` 块使粘贴的类型定义与源码保持同步。
+
+这些参考文档是准确的，但大多是目录式的。维护者仍需自行综合关系：哪些包构成一个能力 seam、哪个应用组装了具体的主干、哪些事件是持久的而哪些是实时的、钩子或策略插件在哪里可以拦截工作、以及哪个面向模型的工具依赖哪个服务。SDK 用户从另一个角度面临同样的问题：「我想要某种行为，应该安装或加载哪个包？应该扩展哪个事件/服务/工具？」
+
+钩子子系统使事件的生产者/消费方拓扑与拦截点变得更加重要；文件系统 seam 使能力 seam、策略否决、工具呈现与 SDK 组装路径变得更加重要。如果关系图的范围仅限于一个小的 bash/todo/subagent 表面，它们会立即陈旧。
+
+## 决策
+
+新增生成式关系图文档，由聚焦的生成器产出并在 [docs/graph-atlas.md](../../../../docs/graph-atlas.md) 建立索引；作为 `doc-sync` 的一部分，通过 `pnpm run verify-doc-graphs` / 现有目录新鲜度检查进行验证。
+
+该索引是既有目录之上的关系层。它不取代精确的参考文档，而是链接到它们并解释各部分如何组合在一起。
+
+### 维护模式
+
+每个关系图页面声明一种维护模式：
+
+- **Generated（生成）**：所有节点和边均从源码发现；如果已提交的产物陈旧，`--check` 失败。
+- **Hybrid generated（混合生成）**：源码发现清单，一个小型 manifest 对不可约的策略进行分类，完整性守卫在发现的条目未被分类时失败。
+- **Curated（人工策划）**：图表解释设计意图、时序或归属；它由生成器输出以使关系图文档保持为可重新生成的整体，但内容是有意撰写的。
+
+### 首批发布的索引
+
+该索引链接十种关系表面。包拓扑和工具包所提供的功能位于已经拥有这些事实的现有生成式目录中；其余聚焦图表由 `scripts/gen-doc-graphs.ts` 生成。
+
+| 关系图 | 维护模式 | 真源 |
+|---|---|---|
+| [模块依赖图](../../../../docs/module-graph.md) | 生成式 | `packages/*/*/package.json` 的对等依赖（peer dependency）与包分组路径 |
+| [工具 schema 目录与包映射](../../../../docs/tool-catalog.md) | 生成式 | 启动后采集的工具 schema，以及工具包服务/效应元数据 |
+| [能力 seam 与核心服务](../../../../docs/capability-seams.md) | 混合生成式 | Cordis 服务声明，以及 `gen-doc-graphs.ts` 中的角色清单 |
+| [tui-agent 应用组合](../../../../examples/tui-agent/composition.md) | 混合生成式 | `examples/tui-agent/cordis.yml` 插件列表，以及人工维护的应用/bundle 展开 |
+| [headless-agent 应用组合](../../../../examples/headless-agent/composition.md) | 混合生成式 | `examples/headless-agent/cordis.yml` 插件列表，以及人工维护的应用/bundle 展开 |
+| [cordis-agent 应用组合](../../../../examples/cordis-agent/composition.md) | 混合生成式 | `examples/cordis-agent/cordis.yml` 插件列表，以及人工维护的应用/bundle 展开 |
+| [acp-agent 应用组合](../../../../examples/acp-agent/composition.md) | 混合生成式 | `examples/acp-agent/cordis.yml` 插件列表加人工策划的应用/bundle 展开 |
+| [事件生产者/消费方矩阵](../../../../docs/event-producer-consumer.md) | 混合生成式 | Cordis 事件声明、经 AST 扫描的 `ctx.on/emit/parallel/serial/waterfall` 位置，以及显式动态分派覆盖 |
+| [agent 轮次与步骤生命周期](../../../../docs/agent-lifecycle.md) | 人工维护 | architecture.md 循环生命周期、Cordis 目录链接，以及会话事件语义 |
+| [工具执行管线](../../../../docs/tool-execution-pipeline.md) | 人工维护 | 工具管线语义与 `tools/execute` waterfall（瀑布式事件）|
+
+### 为什么由生成器拥有文档
+
+包拓扑留在 `gen-module-graph.ts`，工具-包能力映射留在 `gen-tool-catalog.ts`，因为这些生成器已经拥有权威事实和新鲜度门禁。`gen-doc-graphs.ts` 拥有其余关系页面和索引。代价是人工策划的图表需要在 TypeScript 字符串块中编辑，而非直接编辑 Markdown。对于首版来说这是可接受的，因为面向用户的产物仍然是纯 Markdown/Mermaid；未来如果撰写体验比可重新生成更重要，可以将人工策划的页面拆分出去。
+
+### 完整性守卫
+
+混合生成的页面在其 manifest 陈旧时必须显式报错：
+
+- 模块图读取每个包的 `peerDependencies`，并按 `packages/<group>/<pkg>` 路径对包进行分组。
+- 工具目录通过启动收集已发布的工具，并从同一份 manifest 渲染包/服务/副作用映射（其完整性守卫已在检查该 manifest）。
+- 能力 seam 图导入 Cordis 服务收集器，断言每个发现的 harness `ctx.<key>` 都已在 `SERVICE_ROLES` 中分类，且每个已分类的 key 仍然存在。
+- 事件生产者/消费方矩阵标记为 hybrid，因为 subagent 生命周期事件有意使用 `ctx.events.dispatch` 实现逐监听器隔离；这些动态边是显式覆盖而非无声遗漏。
+- `verify-mermaid` 使用 Mermaid 自身的解析器解析仓库中每个 ` ```mermaid ` 围栏，因此语法错误在本地和 CI 的 `doc-sync` 阶段即被捕获，而非在 GitHub 渲染时才显示为损坏的图表。
+
+## 曾考虑的替代方案
+
+已提交的图表使用 Mermaid，因为 GitHub 在 Markdown 中原生渲染它且不引入新的文档构建依赖；密集的多对多数据（如事件生产者/消费方关系）改用 Markdown 表格。**PlantUML、托管图表服务和生成的 SVG** 曾被考虑，但在 Mermaid 成为瓶颈之前有意不采用。
+
+## 后果
+
+- 维护者获得了拓扑、seam、事件流、生命周期与应用组合的可视化入口。
+- SDK 用户获得了从用例到包组合的路径，而非仅有自底向上的包参考。
+- `doc-sync` 现在包含 `verify-doc-graphs` 和 `verify-mermaid`，因此关系图漂移和 Mermaid 语法错误与其他文档新鲜度门禁一起被捕获。
+- 未来的文件系统和钩子工作有了承载新复杂度的具体位置：文件系统应扩展能力文档和工具目录，钩子应扩展事件矩阵和工具执行流水线。

.agents/notes/archived/process/2026-07-21-doc-sync-through-gate-scheduler.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-doc-sync-through-gate-scheduler.md: ba7eeb75e65e5fc342ad7d3b9055d60a4e6f5770
+2026-07-21-doc-sync-through-gate-scheduler.zh.md: 7723a409e2a5d1ee046869403d9f4aadee10757d

.agents/notes/archived/process/2026-07-21-doc-sync-through-gate-scheduler.md

@@ -0,0 +1,26 @@
+# Agent Note: doc-sync through the gate scheduler
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-21-doc-sync-through-gate-scheduler.zh.md)
+
+## Problem
+
+`pnpm run doc-sync` was a `&&` chain of 24 `pnpm run` subcommands. Each link paid a full pnpm wrapper start (workspace resolution, script lookup, tsx boot) before its script ran; measured on a development host, the 24 script bodies together finish in about 34 seconds while the chained form takes around 3 minutes, and the wrapper stall reproduces on local disk, so every developer and CI lane pays it, not just network-filesystem checkouts. The chain also ran serially even though the member gates are read-only and independent, and it silently drifted from [scripts/run-gates.ts](../../../../scripts/run-gates.ts): `verify-cordis-api` joined the chain when the runtime API catalog landed but was never added to `docSyncLeafGates`, so CI never enforced that catalog's freshness.
+
+## Decision
+
+`doc-sync` in `package.json` delegates to the existing bounded scheduler — `tsx scripts/run-gates.ts doc-sync` — like the `check:ci:*` scripts ([parallel gate scheduling](2026-07-06-parallel-pre-push-gates.md), [current CI topology](2026-07-22-evidence-based-larger-hosted-runners.md)). The `doc-sync` mode expands to exactly `docSyncLeafGates()`, making the leaf list in `run-gates.ts` the single source of truth for the member set. The local mode caps default concurrency at four workers because several doc gates each build a full `ts.Program`; `DSH_GATE_CONCURRENCY` still overrides.
+
+`docSyncLeafGates` includes `verify-cordis-api`, so relevant local documentation checks and CI gate the generated runtime API catalog alongside the other generated docs.
+
+## Alternatives considered
+
+- **Keep the `&&` chain and only fix the missing leaf** — repairs today's drift but keeps two member lists that will drift again, and keeps the 24 serial pnpm wrapper starts.
+- **A dedicated `scripts/doc-sync.ts` importing each verify module in one process** — saves even the per-gate tsx boot, but requires refactoring all 24 scripts from run-at-import to callable entry points and loses the scheduler's per-gate timing, isolation, and failure grouping; the wrapper start the scheduler already avoids is the dominant cost.
+- **Shell loop over `tsx scripts/*.ts`** — avoids pnpm wrapper starts cheaply but adds a second execution vocabulary next to the scheduler CI already uses, with none of its scheduling or reporting.
+
+## Consequences
+
+One `pnpm run doc-sync` now costs one pnpm wrapper start plus the slowest dependency chain of member gates instead of 24 wrapper starts plus the sum of all members. Adding a doc gate is one edit in `docSyncLeafGates` (plus the package script itself for ad hoc runs); `package.json` keeps the per-gate `verify-*` scripts as the vocabulary for running one gate by hand. The scheduler prints per-gate timing, so a slow doc-sync points at the gate that dominates. `pnpm run doc-sync` output is now interleaved scheduler output rather than sequential per-command output; anything parsing that output must key on the `run-gates:` summary lines.

.agents/notes/archived/process/2026-07-21-doc-sync-through-gate-scheduler.zh.md

@@ -0,0 +1,26 @@
+# Agent Note: doc-sync 走门禁调度器
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-21-doc-sync-through-gate-scheduler.md) | 中文
+
+## 问题
+
+`pnpm run doc-sync` 原本是把 24 个 `pnpm run` 子命令用 `&&` 串起来的链。每一环都要先付一次完整的 pnpm 包装层启动（workspace 解析、脚本查找、tsx 启动）才轮到脚本本体；在开发机上实测，24 个脚本本体合计约 34 秒即可跑完，而链式形态耗时约 3 分钟，且包装层的停顿在本地磁盘上同样复现，因此每位开发者和每条 CI 车道都在付这笔开销，并非只有网络文件系统上的检出受影响。这条链还是串行执行的，尽管各成员门禁只读且相互独立；它也在悄悄偏离 [scripts/run-gates.ts](../../../../scripts/run-gates.ts)：运行时 API 目录落地时 `verify-cordis-api` 加入了链，却从未加进 `docSyncLeafGates`，导致 CI 从未把关该目录的新鲜度。
+
+## 决策
+
+`package.json` 中的 `doc-sync` 委托给既有的有界调度器——`tsx scripts/run-gates.ts doc-sync`——与各 `check:ci:*` 脚本的做法一致（[并行门禁调度](2026-07-06-parallel-pre-push-gates.md)、[当前 CI 拓扑](2026-07-22-evidence-based-larger-hosted-runners.md)）。`doc-sync` 模式恰好展开为 `docSyncLeafGates()`，使 `run-gates.ts` 里的叶子列表成为成员集合的唯一真源。本地模式把默认并发上限设为四个 worker，因为多个文档门禁各自要构建完整的 `ts.Program`；`DSH_GATE_CONCURRENCY` 仍可覆盖。
+
+`docSyncLeafGates` 包含 `verify-cordis-api`，因此相关的本地文档检查与 CI 会同其他生成文档一起把关生成的运行时 API 目录。
+
+## 考虑过的替代方案
+
+- **保留 `&&` 链，只补缺失的叶子**——能修好今天的漂移，但保留了两份还会再漂移的成员列表，也保留了 24 次串行的 pnpm 包装层启动。
+- **专门的 `scripts/doc-sync.ts` 在单进程内 import 各校验模块**——连每个门禁的 tsx 启动也能省掉，但需要把全部 24 个脚本从 import 即执行改造成可调用入口，还会失去调度器的按门禁计时、隔离和失败分组；而调度器已经避免的包装层启动才是开销的大头。
+- **用 shell 循环跑 `tsx scripts/*.ts`**——以低成本避开 pnpm 包装层启动，却在 CI 已经使用的调度器旁边增加了第二套执行词汇，且没有它的任何调度与报告能力。
+
+## 结果
+
+一次 `pnpm run doc-sync` 的成本从 24 次包装层启动加全部成员之和，变为一次包装层启动加成员门禁中最慢的依赖链。新增文档门禁只需在 `docSyncLeafGates` 改一处（外加 package script 本身以便手工单独运行）；`package.json` 保留各 `verify-*` 脚本作为手工运行单个门禁的词汇。调度器输出按门禁计时，doc-sync 变慢时能直接指向占大头的门禁。`pnpm run doc-sync` 的输出从逐命令顺序输出变为调度器的交错输出；解析该输出的工具必须以 `run-gates:` 摘要行为准。

.agents/notes/archived/process/2026-07-22-installer-in-repo-skip-clone.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
+2026-07-22-installer-in-repo-skip-clone.md: 607ce3baf842d437b64050a5ef17f3c7e4cffba5
+2026-07-22-installer-in-repo-skip-clone.zh.md: 17260427d514b5fd1c87c1d7faae5b1c8c1d9b0b

.agents/notes/archived/process/2026-07-22-installer-in-repo-skip-clone.md

@@ -0,0 +1,28 @@
+# Agent Note: installer skips the clone when run from inside a checkout
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-22-installer-in-repo-skip-clone.zh.md)
+
+## Problem
+
+`scripts/install.sh` is written for the `curl ... | sh` path: it clones the harness into `~/.dsh/source`, then installs, links, and launches. Contributors who already have a checkout and run the same script directly (`sh scripts/install.sh`) got a second, unrelated clone at `~/.dsh/source` — installing and linking a different tree than the one they were working in, with no way to exercise the local script against the local source.
+
+## Decision
+
+The script detects when it is executing from inside a real checkout and, in that mode, reuses that checkout and skips the clone/update step entirely, leaving the working tree untouched.
+
+Detection keys on `$0`: under `curl ... | sh` the script text arrives on stdin, so `$0` is the shell name and no file path resolves; running a checked-out copy makes `$0` the script file. When `$0` is a readable file whose parent is a `scripts/` directory inside a tree that carries both the `bin/dsh` launcher and `scripts/install.sh`, the script sets `IN_REPO=1` and repoints `DSH_SOURCE` at that repo root. Step 2 then prints a "using existing checkout" line and does nothing else — no `git fetch`, no `git checkout -B`, so the user's working tree and branch are never mutated. `DSH_REF` is advisory and ignored in this mode.
+
+Explicit `DSH_SOURCE` wins over detection: the value is captured before defaulting, and in-repo detection only repoints an unset `DSH_SOURCE` (or one already equal to the detected repo root). Setting `DSH_SOURCE` to a different directory opts back into the normal clone/update path, so the escape hatch to install a separate tree from within a checkout still exists.
+
+## Alternatives considered
+
+**Detect via `git rev-parse --show-toplevel` on the current directory.** Rejected: `curl ... | sh` frequently runs from inside some unrelated git repo (the user's `cwd`), which would false-positive and skip the clone against a tree that is not dsh. Anchoring on `$0`'s own location ties the decision to where the script physically lives, and the `bin/dsh` + `scripts/install.sh` markers confirm it is actually a dsh checkout.
+
+**Always skip the clone whenever run from a file, ignoring `DSH_SOURCE`.** Rejected: a contributor may legitimately run the in-repo script to provision a separate `~/.dsh/source` install; honoring an explicit `DSH_SOURCE` that differs from the checkout preserves that path.
+
+## Consequences
+
+Running `sh scripts/install.sh` from a checkout now installs, links, and launches that checkout instead of cloning a parallel one, which also makes the local script testable against local source. The cost is a detection block that couples to the repo layout (`scripts/` beside `bin/dsh`); if the launcher or script ever moves, the markers must move with it. The behavior is documented in the script header and both README files, and verified by running the four paths (in-repo skip, curl-style clone, explicit `DSH_SOURCE` elsewhere opting back in, explicit `DSH_SOURCE` equal to repo root still skipping).

.agents/notes/archived/process/2026-07-22-installer-in-repo-skip-clone.zh.md

@@ -0,0 +1,28 @@
+# Agent Note: 在检出目录内运行时安装脚本跳过克隆
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-22-installer-in-repo-skip-clone.md) | 中文
+
+## 问题
+
+`scripts/install.sh`是为`curl ... | sh`路径编写的：它把 harness 克隆到`~/.dsh/source`，然后安装、软链接并启动。已经有检出的贡献者若直接运行同一脚本（`sh scripts/install.sh`），会在`~/.dsh/source`得到第二份无关的克隆——安装并软链接的是与他们正在工作的树不同的另一棵树，且无从用本地脚本验证本地源码。
+
+## 决策
+
+脚本会检测自身是否在真实检出内执行；在该模式下，它复用该检出并完全跳过克隆/更新步骤，保持工作树不受影响。
+
+检测依据是`$0`：在`curl ... | sh`下脚本文本经由 stdin 到达，因此`$0`是 shell 名称、无路径可解析；运行已检出的副本会使`$0`成为脚本文件本身。当`$0`是一个可读文件、其父目录是一个`scripts/`目录、且该树同时带有`bin/dsh`启动器和`scripts/install.sh`时，脚本会设置`IN_REPO=1`并把`DSH_SOURCE`重新指向该仓库根。步骤 2 随后打印一行"using existing checkout"并不做其他事——不执行`git fetch`、不执行`git checkout -B`，因此用户的工作树和分支绝不会被改动。`DSH_REF`在该模式下仅供参考、被忽略。
+
+显式的`DSH_SOURCE`优先于检测：该值在默认化之前就被捕获，检测只会重新指向未设置的`DSH_SOURCE`（或已经等于检测到的仓库根的那个）。把`DSH_SOURCE`设为其他目录会重新回到正常的克隆/更新路径，因此在检出目录内安装另一棵独立树的退路依然存在。
+
+## 备选方案
+
+**通过对当前目录执行`git rev-parse --show-toplevel`来检测。** 已否决：`curl ... | sh`常常在某个无关的 git 仓库（用户的`cwd`）内运行，这会误判并对一棵并非 dsh 的树跳过克隆。把决策锚定在`$0`自身的位置，使其绑定到脚本实际所在之处，而`bin/dsh` + `scripts/install.sh`标记则确认它确实是一个 dsh 检出。
+
+**只要从文件运行就总是跳过克隆，忽略`DSH_SOURCE`。** 已否决：贡献者可能合理地运行检出内脚本来配置一份独立的`~/.dsh/source`安装；尊重与检出不同的显式`DSH_SOURCE`保留了该路径。
+
+## 影响
+
+现在从检出目录运行`sh scripts/install.sh`会安装、软链接并启动该检出，而不是克隆一份平行副本，这也让本地脚本可以针对本地源码进行测试。代价是一段与仓库布局耦合的检测逻辑（`scripts/`与`bin/dsh`并列）；若启动器或脚本将来移动，标记必须随之移动。该行为记录在脚本头部和两份 README 中，并通过运行四条路径来验证（检出内跳过、curl 式克隆、显式`DSH_SOURCE`指向他处而回到克隆、显式`DSH_SOURCE`等于仓库根仍跳过）。

.agents/notes/archived/process/2026-07-23-browser-demo-gif-recording.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
+2026-07-23-browser-demo-gif-recording.md: a351f467f7d73fdcd5f8d8ca3cc2f1686244d6b9
+2026-07-23-browser-demo-gif-recording.zh.md: d05aa650dfdb9dd7590b8b2f3c071e34fbcb02ff

.agents/notes/archived/process/2026-07-23-browser-demo-gif-recording.md

@@ -0,0 +1,30 @@
+# Agent Note: Browser demo GIF recording
+
+Status: implemented
+Archived: 2026-07-26
+
+English | [中文](2026-07-23-browser-demo-gif-recording.zh.md)
+
+## Problem
+
+Browser demonstrations have been assembled with one-off capture and encoding commands. That makes timing and output size inconsistent, encourages continuous recordings that obscure the useful state changes, and can blur the boundary between a genuine server or API flow and a fixture. Combining local recording with attachment upload or pull-request editing also gives a media task unrelated remote-write authority.
+
+## Decision
+
+The repository provides the [`record-browser-gif`](../../../skills/record-browser-gif/SKILL.md) skill for local browser-demo artifacts. It uses the available browser-control workflow, establishes whether the requested flow is real, fixture-backed, or otherwise simulated, and captures a small storyboard only after semantically observable UI states. Frames and the output live outside the Git worktree by default.
+
+The bundled `encode_gif.py` helper orders frames lexically, assigns explicit hold durations, uses an `ffmpeg` palette pipeline, and validates source dimensions plus the encoded frame count, dimensions, duration, and byte limit through `ffprobe`. The workflow stops after returning the verified absolute GIF path; uploading the artifact and mutating a pull request, issue, or document remain separate workflows.
+
+## Alternatives considered
+
+**Record continuous video and convert it afterward.** Continuous capture preserves every cursor movement and loading transition but produces larger, noisier artifacts and makes deterministic timing harder. A state storyboard better fits short feature demonstrations where the meaningful evidence is a handful of visible transitions.
+
+**Keep an inline `ffmpeg` recipe in the skill.** Reconstructing quoting, timing manifests, palette filters, overwrite behavior, and post-encode checks in every run is error-prone. A bundled helper keeps those mechanics executable while the skill owns capture judgment.
+
+**Include GitHub attachment and description editing.** Upload and remote mutation require separate authentication, confirmation, and recovery rules. Excluding them keeps invocation of a recording skill local and reversible.
+
+**Use a fixture whenever it is easier to stage.** Fixtures are valid when the requested demonstration is explicitly fixture-backed, but they do not substantiate a real-server or real-API claim. The skill preserves the requested provenance and reports a missing prerequisite instead of silently changing it.
+
+## Consequences
+
+Recordings are small, repeatable local artifacts with explicit provenance and a clean repository boundary. The workflow gives up smooth continuous motion, depends on locally available `ffmpeg` and `ffprobe`, and requires the recorder to identify semantic capture points. The helper is exercised against a four-state browser demonstration and invalid duration input; skill shape and repository links are covered by the skill validator and documentation gates.

.agents/notes/archived/process/2026-07-23-browser-demo-gif-recording.zh.md

@@ -0,0 +1,30 @@
+# Agent Note: 浏览器演示 GIF 录制
+
+Status: implemented
+Archived: 2026-07-26
+
+[English](2026-07-23-browser-demo-gif-recording.md) | 中文
+
+## 问题
+
+浏览器演示一直通过一次性的截取与编码命令制作。这会导致播放节奏和输出大小不一致，容易让录制者选择连续录制，反而掩盖有用的状态变化，还可能模糊真实服务器或 API 流程与 fixture（测试前置数据）之间的界限。将本地录制与附件上传或 PR（Pull Request）编辑合并在同一任务中，还会让本应仅处理媒体的任务获得无关的远程写入权限。
+
+## 决策
+
+仓库提供 [`record-browser-gif`](../../../skills/record-browser-gif/SKILL.md) skill（技能），用于生成本地浏览器演示产物。该 skill 使用当前可用的浏览器控制工作流，先确认请求的流程是真实流程、由 fixture 支撑，还是采用其他模拟方式，再仅在 UI 达到语义上可观察的状态后截取一组精简的分镜帧。帧文件与输出产物默认存放在 Git worktree 之外。
+
+随附的 `encode_gif.py` 辅助脚本按词法顺序排列各帧，为每帧设置明确的停留时长，通过 `ffmpeg` 调色板流水线编码，并借助 `ffprobe` 校验源图像尺寸以及编码结果的帧数、尺寸、时长和字节上限。工作流在返回已验证的 GIF 绝对路径后即结束；上传产物以及修改 PR、issue 或文档仍属于独立的工作流。
+
+## 曾考虑的替代方案
+
+**连续录制视频后再转换。**连续录制能保留每一次光标移动和加载过渡，但会产生体积更大、干扰更多的产物，也更难保持确定的播放时序。状态分镜更适合简短的功能演示，因为有意义的证据只是少数几个可见的状态变化。
+
+**在 skill 中保留内联 `ffmpeg` 配方。**每次运行都重新组装引号转义、时序清单、调色板过滤器、覆盖行为和编码后检查，容易出错。随附的辅助脚本使这些机制保持可执行，skill 则负责判断何时截取画面。
+
+**纳入 GitHub 附件上传与描述编辑。**上传和远程修改需要各自独立的身份认证、确认与恢复规则。将它们排除在外，可以使录制 skill 的调用保持本地且可撤销。
+
+**每当 fixture 更容易布置时就使用它。**当请求明确要求由 fixture 支撑演示时，使用 fixture 是有效的；但它无法为真实服务器或真实 API 的声明提供证据。该 skill 会保持请求指定的演示来源，并在缺少先决条件时报告问题，不会擅自更改来源。
+
+## 后果
+
+录制结果成为体积小、可重复生成的本地产物，明确标注演示来源，并与仓库保持清晰边界。该工作流放弃了流畅的连续动态效果，依赖本机提供的 `ffmpeg` 和 `ffprobe`，并要求录制者识别具有语义意义的截取时点。测试使用四状态浏览器演示与无效时长输入检验辅助脚本；skill 的结构及仓库链接由 skill 校验器和文档门禁覆盖。

.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.