diff --git a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.i18n.yaml
index 56c9e53319..b6788a47ef 100644
--- a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md
-2026-06-21-mandatory-app-attribution-headers.md: a8ffe91c431cdc7907626bbc3eaf8096035777de
-2026-06-21-mandatory-app-attribution-headers.zh.md: ac4affce583d5d81253f320ff022f670d4d66cc8
+2026-06-21-mandatory-app-attribution-headers.md: ad9d65805c8f0c96bd811b5036310d019760627e
+2026-06-21-mandatory-app-attribution-headers.zh.md: 3021c7fcca00f2e929d997625c303f9a27dbf673
diff --git a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md
index a8ffe91c43..ad9d65805c 100644
--- a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md
+++ b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md
@@ -32,7 +32,7 @@ The provider-neutral identity is owned by `dsh-llm` (`packages/llm/llm/src/attri
 
 - product token for `User-Agent`: `deepseek-harness` (continuity with the pre-Agent Note wire value and the repo/org identity)
 - version: read from the owning package's manifest via `createRequire`, never a hand-copied constant
-- app URL: `https://github.com/deepseek-ai/deepseek-harness-sdk` - the planned public home; a `FIXME` in `attribution.ts` blocks release until that repository actually exists
+- app URL: `https://github.com/deepseek-ai/deepseek-harness-sdk` - the planned public home, which must exist before release
 
 The default is mandatory and non-empty. White-label deployments pass their own `AppIdentity` to `attributionHeaders(identity)` - the override seam is the function parameter, with no deployment config plumbing until a consumer needs it - and omission falls back to the harness default rather than suppressing attribution. There is no per-request API for the model, user prompt, session id, cwd, user email, API key owner, or local machine identity to influence these fields.
 
@@ -77,7 +77,7 @@ The landed contract:
 
 **Providers see that traffic comes from the harness.** That is the point, but it means deployments that previously blended into generic SDK traffic become identifiable. Mitigation: send only static public product data and let forks/white-label deployments pass their own `AppIdentity`.
 
-**The app URL points at a repository that does not exist yet.** `deepseek-ai/deepseek-harness-sdk` is the planned public home; until it is created the URL is a dangling promise. The `FIXME` marker on the constant blocks a release from shipping with it unresolved (see `docs/development.md` marker semantics).
+**The app URL points at a repository that does not exist yet.** `deepseek-ai/deepseek-harness-sdk` is the planned public home; until it is created the URL is a dangling promise that blocks release.
 
 **Header support differs by client library.** The hand-rolled adapter sets headers directly; the pi-ai-backed adapter depends on pi-ai continuing to honor `StreamOptions.headers` (merged last over provider defaults). The wire-level mock-server tests are the guard: if a pi-ai upgrade stops delivering the header, the suite goes red. This is useful pressure on the abstraction: a provider adapter that cannot set mandatory headers cannot fully implement the harness LLM contract.
 
diff --git a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.zh.md b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.zh.md
index ac4affce58..3021c7fcca 100644
--- a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.zh.md
+++ b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.zh.md
@@ -32,7 +32,7 @@ LLM（大语言模型）提供方请求应当标识发出请求的产品。这
 
 - `User-Agent` 的产品 token：`deepseek-harness`（与 Agent Note 之前的线路值及仓库/组织身份保持连续性）
 - 版本：通过 `createRequire` 从所属包的 manifest（元数据清单）读取，绝不手动复制常量
-- 应用 URL：`https://github.com/deepseek-ai/deepseek-harness-sdk`——计划中的公开主页；`attribution.ts` 中的 `FIXME` 标记在该仓库实际存在之前阻塞发布
+- 应用 URL：`https://github.com/deepseek-ai/deepseek-harness-sdk`——计划中的公开主页，且必须在发布前实际存在
 
 默认值是强制的且非空。白标部署通过向 `attributionHeaders(identity)` 传入自己的 `AppIdentity` 来覆盖——覆盖 seam 就是函数参数，在有消费方需要之前不做部署配置管道——省略时回退到 harness 默认值而非抑制归属。没有逐请求 API 允许模型、用户提示词、会话 id、cwd、用户邮箱、API key 所有者或本地机器身份影响这些字段。
 
@@ -77,7 +77,7 @@ LLM（大语言模型）提供方请求应当标识发出请求的产品。这
 
 **提供方看到流量来自 harness。** 这正是目的，但意味着此前混在通用 SDK 流量中的部署变得可识别。缓解措施：仅发送静态公开产品数据，并允许 fork/白标部署传入自己的 `AppIdentity`。
 
-**应用 URL 指向一个尚不存在的仓库。** `deepseek-ai/deepseek-harness-sdk` 是计划中的公开主页；在它创建之前，该 URL 是一个悬空承诺。常量上的 `FIXME` 标记阻塞发布，不允许带着未解决的问题出门（见 `docs/development.md` 标记语义）。
+**应用 URL 指向一个尚不存在的仓库。** `deepseek-ai/deepseek-harness-sdk` 是计划中的公开主页；在它创建之前，该 URL 是一个阻塞发布的悬空承诺。
 
 **不同客户端库的头部支持有差异。** 手写适配器直接设置头部；基于 pi-ai 的适配器依赖 pi-ai 继续尊重 `StreamOptions.headers`（最后合并覆盖提供方默认值）。线路级 mock 服务器测试是守卫：如果 pi-ai 升级后不再投递该头部，套件会变红。这对抽象施加了有益的压力：一个无法设置强制头部的提供方适配器不能完整实现 harness 的 LLM 契约。
 
diff --git a/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.i18n.yaml
index 48d3522a70..072823d0dc 100644
--- a/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md
-2026-07-02-tool-render-intent-union.md: d82141f519bff66df000f1316093aacd38b8e42b
-2026-07-02-tool-render-intent-union.zh.md: e145908e019e71765a475b0ca9d22414e9b42d23
+2026-07-02-tool-render-intent-union.md: 67607b2848305439513503d7e03ad5e2a2e4020a
+2026-07-02-tool-render-intent-union.zh.md: 9cbab75ce87f6d313ca4b6ac8dda043733361f0d
diff --git a/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md
index d82141f519..67607b2848 100644
--- a/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md
+++ b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md
@@ -14,7 +14,7 @@ A tool declares how its calls render in a UI (an editor's tool-call card) throug
 - Which combinations are *valid* is unwritten: a `terminal` call that also sets `content` means "description above the card"; a generic call that sets `terminal` is meaningless but representable. The type permits nonsense.
 - There is no way to express the one file-tool affordance an editor most wants — a **diff card** (`{path, oldText, newText}`, which Zed renders as an inline diff / new-file preview). `ToolCallPresentation.content` is the *LLM* `ContentBlock[]` vocabulary (text/image), so a tool literally cannot ask for a diff.
 
-The existing `FIXME(tool-presentation)` in `packages/core/tools/src/index.ts` named the fix: "redesign the type so a tool declares its render INTENT once (e.g. a tagged union over card kinds) rather than a bag of optional fields the bridge stitches together." An earlier rejected collapse-tool-owned-presentation proposal deferred it explicitly: rich rendering "should return later as a tagged render-intent union after there are at least two real tools and two real consumers to validate the vocabulary." That bar is met by multiple producer families plus the TUI and host/client-runtime (Web) consumers.
+An earlier rejected collapse-tool-owned-presentation proposal deferred rich rendering until it could "return later as a tagged render-intent union after there are at least two real tools and two real consumers to validate the vocabulary." That bar is met by multiple producer families plus the TUI and host/client-runtime (Web) consumers.
 
 ## Decision
 
diff --git a/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.zh.md b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.zh.md
index e145908e01..9cbab75ce8 100644
--- a/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.zh.md
+++ b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.zh.md
@@ -14,7 +14,7 @@ Status: implemented
 - 哪些组合是*合法的*没有文档说明：一个设置了 `content` 的 `terminal` 调用意味着「卡片上方的描述」；一个设置了 `terminal` 的 generic 调用毫无意义但类型上可表达。类型允许无意义的状态存在。
 - 无法表达编辑器最需要的文件工具能力：**diff 卡片**（`{path, oldText, newText}`，Zed 将其渲染为内联 diff / 新文件预览）。`ToolCallPresentation.content` 使用的是 *LLM（大语言模型）* 的 `ContentBlock[]` 词汇（text/image），工具根本无法请求 diff 展示。
 
-`packages/core/tools/src/index.ts` 中已有的 `FIXME(tool-presentation)` 指出了修复方向：「重新设计类型，让工具一次性声明其渲染意图（例如按卡片种类的带标签联合类型），而非一堆由 bridge 拼接的可选字段。」一个早先被否决的折叠工具自有呈现提案明确推迟了此事：富渲染「应当在至少有两个真实工具和两个真实消费方验证词汇之后，以带标签 render-intent 联合类型的形式回归。」该条件已由多个生产者族，加上 TUI 与宿主/客户端运行时（Web）这些消费方满足。
+一个早先被否决的折叠工具自有呈现提案把富渲染推迟到它能够「在至少有两个真实工具和两个真实消费方验证词汇之后，以带标签 render-intent 联合类型的形式回归」之时。该条件已由多个生产者族，加上 TUI 与宿主/客户端运行时（Web）这些消费方满足。
 
 ## 决策
 
diff --git a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.i18n.yaml
index 8a2190b500..26354042d7 100644
--- a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md
-2026-07-05-prompt-variables-and-tool-guidance-ownership.md: 94f5fa409e7b539b48750d12576c7a342a30c9ba
-2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md: 341b3a89f423c9cc7d2fc56f1ea25a1985680d0d
+2026-07-05-prompt-variables-and-tool-guidance-ownership.md: a3b5021daf323971308760bde4f97651db8edbda
+2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md: 490d41302ea4f4e14e11e301acbf47170f95cace
diff --git a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md
index 94f5fa409e..a3b5021daf 100644
--- a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md
+++ b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md
@@ -10,7 +10,7 @@ The assembled system prompt had four defects, all of one family: facts the harne
 
 **The model could not know its own name.** `AgentOptions.model` drives every request, but no prompt text carried it — and nothing COULD carry it: sections in `dsh-system-prompt` were context-global while the model name is per-agent, and `assemble()` took no per-agent input at all.
 
-**Tool guidance was hand-written prose in leaf YAML.** The bash/subagent/todo_write usage guidance lived in the coding-agent and ACP persona strings — two drifting copies (the ACP one was already abridged) — while `dsh-tool-fs` and `dsh-tool-web` owned their guidance as `ctx.systemPrompt.section()` contributions. Loading or dropping a tool plugin meant editing every deployment's persona by hand; both YAMLs carried a `FIXME(config-comments)` apologizing for a symptom of the split, and the old terminal welcome banner hand-enumerated the tool set too.
+**Tool guidance was hand-written prose in leaf YAML.** The bash/subagent/todo_write usage guidance lived in the coding-agent and ACP persona strings — two drifting copies (the ACP one was already abridged) — while `dsh-tool-fs` and `dsh-tool-web` owned their guidance as `ctx.systemPrompt.section()` contributions. Loading or dropping a tool plugin meant editing every deployment's persona by hand, and the old terminal welcome banner hand-enumerated the tool set too.
 
 **The persona rendered after tool guidance.** The loop string-joined `agent.options.systemPrompt` AFTER the assembled sections, so the model read "Use the read tool…" before "You are a coding agent" — backwards relative to the identity-first convention (Claude Code, Codex) and a second composition path besides the section pipeline.
 
diff --git a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md
index 341b3a89f4..490d41302e 100644
--- a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md
+++ b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md
@@ -10,7 +10,7 @@ Status: implemented
 
 **模型无法知道自己的名字。** `AgentOptions.model` 驱动每个请求，但没有任何提示词文本携带它——也不可能携带：`dsh-system-prompt` 中的 section 是上下文全局的，而模型名称是 per-agent 的，`assemble()` 根本不接受任何 per-agent 输入。
 
-**工具指导是 leaf YAML 中的手写行文。** bash/subagent/todo_write 的使用指导存放在 coding-agent 和 ACP persona 字符串里——两份漂移的副本（ACP 那份已经被删减）——而 `dsh-tool-fs` 和 `dsh-tool-web` 则通过 `ctx.systemPrompt.section()` 贡献各自的指导。加载或卸载一个工具插件意味着手动编辑每个部署的 persona；两份 YAML 都带着一条 `FIXME(config-comments)` 为这种分裂的症状道歉，旧终端欢迎横幅也手动枚举了工具集。
+**工具指导是 leaf YAML 中的手写行文。** bash/subagent/todo_write 的使用指导存放在 coding-agent 和 ACP persona 字符串里——两份漂移的副本（ACP 那份已经被删减）——而 `dsh-tool-fs` 和 `dsh-tool-web` 则通过 `ctx.systemPrompt.section()` 贡献各自的指导。加载或卸载一个工具插件意味着手动编辑每个部署的 persona，旧终端欢迎横幅也手动枚举了工具集。
 
 **Persona 渲染在工具指导之后。** agent loop（智能体循环）将 `agent.options.systemPrompt` 字符串拼接在已组装的 section 之后，于是模型先读到「Use the read tool…」再读到「You are a coding agent」——与 identity-first 约定（Claude Code、Codex）相反，且是 section 流水线之外的第二条组合路径。
 
diff --git a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.i18n.yaml
index d326b413bb..2926746ee1 100644
--- a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md
-2026-07-05-reconstructable-requests.md: 2f559a3052b9fb84f788975a64799e4f020b0d3e
-2026-07-05-reconstructable-requests.zh.md: 26abdc024a166856e51ebf09f086c7868fc8236d
+2026-07-05-reconstructable-requests.md: ebca9b99cad791159302da9c2bbce9f4df147aab
+2026-07-05-reconstructable-requests.zh.md: 91ef3fd04502f2c2f092da60a8bd909cf7fa25df
diff --git a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md
index 2f559a3052..ebca9b99ca 100644
--- a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md
+++ b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md
@@ -53,4 +53,3 @@ Like MiniCode, the conversation advances append-only and resets only when model-
 - Tool-result trimming (planned) needs no new mechanism: a logged single-entry surface replace (`start === end`) carrying a trimmed `tool/result` under the same `callId` — compaction-family, replay-correct, cache-bust batched by the same pressure logic.
 - Session logs grow one `request/header` snapshot per loop instance plus snapshots on real changes. This is larger than a delta codec but small beside chunk-heavy logs and retains one replay representation. `SESSION_FORMAT_VERSION` stays `0`; legacy delta events are rejected rather than migrated.
 - Snapshot expected outputs changed once (every transcript gains its header events); the fs-writing fixtures are stored in the normalized authored form with cwd-relative tool arguments, because replay only round-trips cwd-independent argument paths.
-- FIXME(call-config-shape): revisit `LlmCallConfig`'s exact field set — which fields are genuinely epoch-level for cache purposes (`model` certainly; the sampling scalars sit there out of caution), and where provider-specific extras (reasoning options, extra body params) belong when an adapter needs them.
diff --git a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.zh.md b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.zh.md
index 26abdc024a..91ef3fd045 100644
--- a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.zh.md
+++ b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.zh.md
@@ -53,4 +53,3 @@ Status: implemented
 - 工具结果裁剪（计划中）无需新机制：一个已记录的单条目 surface replace（`start === end`），携带同一 `callId` 下裁剪后的 `tool/result`——属压缩家族，回放正确，缓存击穿由相同的压力逻辑批量处理。
 - 会话日志每个循环实例增长一个 `request/header` 快照，并在真正变更时增加快照。它比 delta 编解码器更大，但相对分片密集型日志仍然很小，并只保留一种回放表示。`SESSION_FORMAT_VERSION` 保持 `0`；旧的 delta 事件被拒绝而非迁移。
 - 快照预期输出变更一次（每个 transcript（文本记录）增加其 header 事件）；写入文件系统的 fixture（测试前置数据）以规范化的撰写形式存储，工具参数使用 cwd 相对路径，因为回放只对 cwd 无关的参数路径做往返。
-- FIXME(call-config-shape)：重新审视 `LlmCallConfig` 的确切字段集——哪些字段对缓存而言真正属于 epoch 级别（`model` 毫无疑问；采样标量出于谨慎放在那里），以及当适配器需要时，提供方特定的额外项（推理（reasoning）选项、额外 body 参数）应归属何处。
diff --git a/.agents/notes/implemented/bug-fix/2026-07-29-pnpm-setup-runner-isolation.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-29-pnpm-setup-runner-isolation.i18n.yaml
index fb5ee5debc..b1bdfe74c2 100644
--- a/.agents/notes/implemented/bug-fix/2026-07-29-pnpm-setup-runner-isolation.i18n.yaml
+++ b/.agents/notes/implemented/bug-fix/2026-07-29-pnpm-setup-runner-isolation.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-07-29-pnpm-setup-runner-isolation.md
-2026-07-29-pnpm-setup-runner-isolation.md: 743535d0394cbea0374c412ba6968910ce858de4
-2026-07-29-pnpm-setup-runner-isolation.zh.md: 1e51070f88dead17b9d3f5625e337c558786aba2
+2026-07-29-pnpm-setup-runner-isolation.md: 74b672b3f90ea445ad1a8e283a5904056059b2f8
+2026-07-29-pnpm-setup-runner-isolation.zh.md: 32c667dc09e561504e8e053bf2a338ed2190d9e8
diff --git a/.agents/notes/implemented/bug-fix/2026-07-29-pnpm-setup-runner-isolation.md b/.agents/notes/implemented/bug-fix/2026-07-29-pnpm-setup-runner-isolation.md
index 743535d039..74b672b3f9 100644
--- a/.agents/notes/implemented/bug-fix/2026-07-29-pnpm-setup-runner-isolation.md
+++ b/.agents/notes/implemented/bug-fix/2026-07-29-pnpm-setup-runner-isolation.md
@@ -6,7 +6,7 @@ English | [中文](2026-07-29-pnpm-setup-runner-isolation.zh.md)
 
 ## Problem
 
-`pnpm/action-setup@v4` defaults its install destination to `~/setup-pnpm` and replaces that directory during setup. The self-hosted CI failover runs six GitHub Actions runner services under one VM user, so concurrent jobs shared the same destination. In [run 30375670773](https://github.com/deepseek-harness/deepseek-harness/actions/runs/30375670773), three jobs entered pnpm setup within 73 milliseconds; one setup removed another process's current working directory and two jobs failed in Node's `uv_cwd` initialization. A retry on another runner passed, making the failure timing-dependent rather than a repository-test regression.
+`pnpm/action-setup@v4` defaults its install destination to `~/setup-pnpm` and replaces that directory during setup. The self-hosted CI failover runs six GitHub Actions runner services under one VM user, so concurrent jobs shared the same destination. In the reproducing run, three jobs entered pnpm setup within 73 milliseconds; one setup removed another process's current working directory and two jobs failed in Node's `uv_cwd` initialization. A retry on another runner passed, making the failure timing-dependent rather than a repository-test regression.
 
 ## Decision
 
diff --git a/.agents/notes/implemented/bug-fix/2026-07-29-pnpm-setup-runner-isolation.zh.md b/.agents/notes/implemented/bug-fix/2026-07-29-pnpm-setup-runner-isolation.zh.md
index 1e51070f88..32c667dc09 100644
--- a/.agents/notes/implemented/bug-fix/2026-07-29-pnpm-setup-runner-isolation.zh.md
+++ b/.agents/notes/implemented/bug-fix/2026-07-29-pnpm-setup-runner-isolation.zh.md
@@ -6,7 +6,7 @@ Status: implemented
 
 ## 问题
 
-`pnpm/action-setup@v4` 的安装目标目录默认为 `~/setup-pnpm`，并会在设置期间替换该目录。自托管 CI 故障切换在同一个 VM 用户下运行六个 GitHub Actions runner 服务，因此并发作业会共用同一目标目录。在 [run 30375670773](https://github.com/deepseek-harness/deepseek-harness/actions/runs/30375670773) 中，三个作业在 73 毫秒内进入 pnpm 设置；其中一个设置过程删除了另一个进程的当前工作目录，导致两个作业在 Node 的 `uv_cwd` 初始化阶段失败。换到另一台 runner 重试后通过，说明该故障取决于时序，并非仓库测试回归。
+`pnpm/action-setup@v4` 的安装目标目录默认为 `~/setup-pnpm`，并会在设置期间替换该目录。自托管 CI 故障切换在同一个 VM 用户下运行六个 GitHub Actions runner 服务，因此并发作业会共用同一目标目录。在复现运行中，三个作业在 73 毫秒内进入 pnpm 设置；其中一个设置过程删除了另一个进程的当前工作目录，导致两个作业在 Node 的 `uv_cwd` 初始化阶段失败。换到另一台 runner 重试后通过，说明该故障取决于时序，并非仓库测试回归。
 
 ## 决策
 
diff --git a/.agents/notes/implemented/bug-fix/2026-08-06-api-key-format-validation.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-08-06-api-key-format-validation.i18n.yaml
index e1c3ac3ef8..f4f105e124 100644
--- a/.agents/notes/implemented/bug-fix/2026-08-06-api-key-format-validation.i18n.yaml
+++ b/.agents/notes/implemented/bug-fix/2026-08-06-api-key-format-validation.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-06-api-key-format-validation.md
-2026-08-06-api-key-format-validation.md: e9ca76ede06080f2b868f6436998d163e642adbc
-2026-08-06-api-key-format-validation.zh.md: 5666a884d4c9478291072375681d8d3526b2632a
+2026-08-06-api-key-format-validation.md: 2174cb466c6af72f15005ce1ba3dec8100de6f2f
+2026-08-06-api-key-format-validation.zh.md: f9b7d6518fedc42e5264c46beaa1a78619139c58
diff --git a/.agents/notes/implemented/bug-fix/2026-08-06-api-key-format-validation.md b/.agents/notes/implemented/bug-fix/2026-08-06-api-key-format-validation.md
index e9ca76ede0..2174cb466c 100644
--- a/.agents/notes/implemented/bug-fix/2026-08-06-api-key-format-validation.md
+++ b/.agents/notes/implemented/bug-fix/2026-08-06-api-key-format-validation.md
@@ -14,13 +14,11 @@ Pasting a key containing an emoji, CJK text, or a full-width punctuation mark in
 
 Whitespace passed every check. `ProviderEditor` tested `keyDraft.length`, so a key of three spaces was stored and then authenticated as `Bearer` plus blanks. Neither adapter checked a credential- or environment-sourced key — the path the Models page writes, and therefore the path users actually take.
 
-Sources: deepseek-harness#1594 and #1595; dsh-external#247, #249, #266, and #210.
-
 ## Decision
 
 One rule defines a legal key: **after trimming, non-empty, and every character within `[\x21-\x7E]`** — printable ASCII, space excluded.
 
-This single predicate covers every input the sources list: empty, leading and trailing whitespace, interior whitespace, C0 control characters, emoji, CJK text, and full-width punctuation. It is also exactly the constraint that produced the ByteString failure, so the two issues close on one definition rather than on two coincidentally related fixes.
+This single predicate covers every reported input: empty, leading and trailing whitespace, interior whitespace, C0 control characters, emoji, CJK text, and full-width punctuation. It is also exactly the constraint that produced the ByteString failure, so the failures share one definition rather than two coincidentally related fixes.
 
 A second, narrower rule catches a pasted environment line: input matching `^[A-Z][A-Z0-9_]*=[^=]` or wrapped in matching quotes is refused. Restricting the prefix to upper-case keeps real keys clear of it — `sk-` forms break the identifier match at the hyphen — and requiring a non-`=` character after the separator keeps base64 padding clear of it too. It reports the same format failure as an illegal character rather than its own message: the reader's next move is identical either way, so a separate line would name a cause without changing what to do.
 
@@ -76,7 +74,7 @@ The client cannot import any of this: client packages reference only client pack
 
 **Running the shape heuristic in the resolvers too.** Symmetric, and it would stop a pasted environment line written directly into `.env`. Rejected for the lockout described above: a false positive in a resolver leaves the user no working path, while a false positive in the browser leaves the environment open.
 
-**Probing the provider at save time to prove the key works.** It would close the complaint the sources actually open with — a save that reports success and fails at the first turn. Rejected as out of scope and, on the code as it stood, unbuildable: `discoverModels` short-circuits to the installed catalog before any network call for exactly the providers pi-ai ships catalogs for, so it verified nothing about the key, and the DeepSeek card has no probe at all. A verifier's value is distinguishing "key rejected" from "cannot reach", which is the distinction this change makes reliable; building it first would have produced a verifier unable to tell its own outcomes apart. Comparable products also do not verify on save, so a blocking network call there would be an unexpected behavior rather than a missing one.
+**Probing the provider at save time to prove the key works.** It would close the original complaint — a save that reports success and fails at the first turn. Rejected as out of scope and, on the code as it stood, unbuildable: `discoverModels` short-circuits to the installed catalog before any network call for exactly the providers pi-ai ships catalogs for, so it verified nothing about the key, and the DeepSeek card has no probe at all. A verifier's value is distinguishing "key rejected" from "cannot reach", which is the distinction this change makes reliable; building it first would have produced a verifier unable to tell its own outcomes apart. Comparable products also do not verify on save, so a blocking network call there would be an unexpected behavior rather than a missing one.
 
 ## Consequences
 
diff --git a/.agents/notes/implemented/bug-fix/2026-08-06-api-key-format-validation.zh.md b/.agents/notes/implemented/bug-fix/2026-08-06-api-key-format-validation.zh.md
index 5666a884d4..f9b7d6518f 100644
--- a/.agents/notes/implemented/bug-fix/2026-08-06-api-key-format-validation.zh.md
+++ b/.agents/notes/implemented/bug-fix/2026-08-06-api-key-format-validation.zh.md
@@ -14,13 +14,11 @@ Status: implemented
 
 空白字符能通过每一道检查。`ProviderEditor` 判的是 `keyDraft.length`，于是三个空格构成的 Key 会被存下，随后以 `Bearer` 加若干空格去认证。两个适配器都不检查来自凭据或环境的 Key——而那正是 Models 页写入的路径，也就是用户真正走的路径。
 
-来源：deepseek-harness#1594 与 #1595；dsh-external#247、#249、#266、#210。
-
 ## Decision
 
 一条规则定义什么是合法 Key：**trim 之后非空，且每个字符都落在 `[\x21-\x7E]`**——可打印 ASCII，不含空格。
 
-这一个断言覆盖了来源列出的全部输入：空值、首尾空白、中间空白、C0 控制字符、emoji、中文、全角标点。它同时正是造成 ByteString 失败的那条约束，所以两个 issue 收敛于同一个定义，而不是两个恰好相关的修复。
+这一个断言覆盖了所有已报告的输入：空值、首尾空白、中间空白、C0 控制字符、emoji、中文、全角标点。它同时正是造成 ByteString 失败的那条约束，所以这些故障收敛于同一个定义，而不是两个恰好相关的修复。
 
 第二条更窄的规则用于识别整行粘贴的环境变量：匹配 `^[A-Z][A-Z0-9_]*=[^=]` 或首尾成对引号的输入会被拒绝。把前缀限定为全大写可以让真实 Key 与之绝缘——`sk-` 这类形态会在连字符处中断标识符匹配——而要求分隔符之后必须是非 `=` 字符，则让 base64 的 padding 也与之绝缘。它报出的是与非法字符相同的那条格式失败，而不是自己的一句：读到它的人下一步动作完全一样，因此单列一句只会点出一个原因，却不改变该怎么做。
 
@@ -76,7 +74,7 @@ Status: implemented
 
 **让形状启发式也在 resolver 中运行。** 更对称，且能拦住直接写进 `.env` 的整行环境变量。因上文所述的锁死风险而否决：resolver 中的一次误判会让用户无路可走，浏览器中的一次误判则仍留有环境变量这条路。
 
-**在保存时探测 provider 以证明 Key 可用。** 它能关掉来源真正开篇抱怨的那件事——保存报成功、第一轮才失败。因超出范围而否决，且在当时的代码上无法建成：对 pi-ai 恰好自带 catalog 的那些 provider，`discoverModels` 会在任何网络调用之前短路到内置 catalog，因而对 Key 什么都验证不了；而 DeepSeek 卡片根本没有探测。验证器的价值在于分清「Key 被拒」与「无法连通」，而这正是本次改动让其变得可靠的区分；先建验证器只会得到一个分不清自身结果的验证器。同类产品也不在保存时验证，因此保存时的阻断式网络调用会是一个意外行为，而非一处缺失。
+**在保存时探测 provider 以证明 Key 可用。** 它能关掉最初报告的那件事——保存报成功、第一轮才失败。因超出范围而否决，且在当时的代码上无法建成：对 pi-ai 恰好自带 catalog 的那些 provider，`discoverModels` 会在任何网络调用之前短路到内置 catalog，因而对 Key 什么都验证不了；而 DeepSeek 卡片根本没有探测。验证器的价值在于分清「Key 被拒」与「无法连通」，而这正是本次改动让其变得可靠的区分；先建验证器只会得到一个分不清自身结果的验证器。同类产品也不在保存时验证，因此保存时的阻断式网络调用会是一个意外行为，而非一处缺失。
 
 ## Consequences
 
diff --git a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.i18n.yaml b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.i18n.yaml
index c981d84400..9e195a4b1d 100644
--- a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.i18n.yaml
+++ b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md
-2026-06-18-compaction-capability-seam.md: 26e6e2468c7bea661d85c8fb994adf8b109105ee
-2026-06-18-compaction-capability-seam.zh.md: 8f9cd1f6bc31e648a5b923e816cad75ebc1a0bd8
+2026-06-18-compaction-capability-seam.md: 8dcbe74429a620027a570124383442b969c12196
+2026-06-18-compaction-capability-seam.zh.md: 27b63f29c2e6f35637185b47c882ae42e5d41088
diff --git a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md
index 26e6e2468c..8dcbe74429 100644
--- a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md
+++ b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md
@@ -131,4 +131,4 @@ The lifecycle boundary makes crash state unambiguous:
 - **Loop:** Tests pin pre-step after the preceding `step/end` and before the next `step/start`, actual `agent/request` routing, closed failed steps, fresh retry numbering, and complete thrown/in-band overflow → compaction → reconstructed retry composition.
 - **Manual:** Maintenance serialization, marker ordering, injection retention, live/stale orphan classification, cancellation, close/flush failures, command mapping, and the queued TUI journey are pinned without a model key.
 - **With-key e2e:** A real model and bash session with lowered limits triggers compaction, records a complete `compact/start…end` pair, shrinks the surface, and finishes the task.
-- **Snapshot gap:** Runaway-turn compaction cannot yet replay because the summarization call records no `assistant/chunk` events or `sessionId`; interleaved summarization-call replay remains follow-up work.
+- **Snapshot gap:** The summarization call is session-associated and logs `compact/summary`, but ordinary transcript replay does not derive its auxiliary response; keyless assembled coverage therefore needs an explicit replay override.
diff --git a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md
index 8f9cd1f6bc..27b63f29c2 100644
--- a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md
+++ b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md
@@ -131,4 +131,4 @@ compact/end      → log-only. Releases the lock (carries `error` on a recoverab
 - **循环测试：** 测试固定 pre-step 发生在前一个 `step/end` 之后、下一个 `step/start` 之前，使用实际 `agent/request` 路由，关闭失败步骤，分配新的重试编号，并覆盖完整的抛出/带内溢出 → 压缩 → 重建重试组合。
 - **手动测试：** 无需模型密钥即可固定 maintenance 串行化、标记顺序、注入保留、活动／陈旧未匹配标记分类、取消、闭合／flush 失败、命令映射以及排队 TUI 流程。
 - **带密钥 e2e：** 真实模型和 bash 会话在降低的限制下触发压缩，记录完整的 `compact/start…end` 对，缩小 surface，并完成任务。
-- **快照缺口：** 失控轮次压缩尚无法回放，因为摘要调用未记录 `assistant/chunk` 事件或 `sessionId`；交错摘要调用的回放仍是后续工作。
+- **快照缺口：** 摘要调用与会话关联并记录 `compact/summary`，但普通 transcript（文本记录）回放不会派生其辅助响应；因此，要实现无密钥的组装态覆盖，就必须显式提供回放 override。
diff --git a/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.i18n.yaml b/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.i18n.yaml
index 6b0ce3f378..8a92dd2fd1 100644
--- a/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.i18n.yaml
+++ b/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.md
-2026-07-26-todo-parallel-in-progress.md: 2805ef894050d1b1cffe06fce59a4984d463f8d1
-2026-07-26-todo-parallel-in-progress.zh.md: 16b32daa05b10f24eacde4cec9622b2159cdef09
+2026-07-26-todo-parallel-in-progress.md: 8d047f33ab1aebd8c0de2a0a5e90e7efb1b28154
+2026-07-26-todo-parallel-in-progress.zh.md: 26b7081e7b4e3688a46a2857da91ba45328532a9
diff --git a/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.md b/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.md
index 2805ef8940..8d047f33ab 100644
--- a/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.md
+++ b/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.md
@@ -37,7 +37,7 @@ The durable-log invariant deliberately does NOT follow the flag. A log written w
 
 ## The display surfaces are part of the change
 
-Lifting the cap makes a list shape reachable that no renderer had ever received, so this branch stacks on the [web todo display](2026-07-23-web-todo-display.md) rather than landing beside it: both change `tool-todo`, and the GUI is where a parallel plan becomes visible. Two web sites derived their one-line summary with `todos.find(t => t.status === 'in_progress')` — the collapsed plan-strip header and the `todo_write` row — and under the old cap that `find` was total, since at most one item could match. With several active it silently dropped every active item but the first: a four-item plan with three running tasks collapsed to the name of one, and the row read `1/4 已完成 · <one task>` while two others were in flight. The expanded list was always correct (it maps every item), which is why neither PR's tests caught it — only the collapsed header and the row lost information. The panel redesign in [#740](https://github.com/deepseek-harness/deepseek-harness/pull/740) has since replaced the collapsed header's named hint with `·`-joined per-status counts (localized, `1 completed · 2 in progress · 1 pending`, zero-count segments omitted), which reports parallel work correctly and needs no name to truncate; the row is the one site this branch still had to fix.
+Lifting the cap makes a list shape reachable that no renderer had ever received, so this branch stacks on the [web todo display](2026-07-23-web-todo-display.md) rather than landing beside it: both change `tool-todo`, and the GUI is where a parallel plan becomes visible. Two web sites derived their one-line summary with `todos.find(t => t.status === 'in_progress')` — the collapsed plan-strip header and the `todo_write` row — and under the old cap that `find` was total, since at most one item could match. With several active it silently dropped every active item but the first: a four-item plan with three running tasks collapsed to the name of one, and the row read `1/4 已完成 · <one task>` while two others were in flight. The expanded list was always correct (it maps every item), which is why neither PR's tests caught it — only the collapsed header and the row lost information. The panel redesign replaced the collapsed header's named hint with `·`-joined per-status counts (localized, `1 completed · 2 in progress · 1 pending`, zero-count segments omitted), which reports parallel work correctly and needs no name to truncate; the row is the one site this branch still had to fix.
 
 The row takes `planSummary` in `toolviews/plan-summary.ts`. It names the first active item and counts the rest, so the row reports how many tasks are running instead of implying one. Naming every active item was rejected: the row is a single line, and an unbounded join would overflow it — the count degrades predictably where a list does not. The derivation sits inside the toolviews domain rather than in `contract/`, the inter-domain face: the panel computes its own counts inline and shares nothing with the row, so a contract module would declare a sharing relationship that no longer exists.
 
diff --git a/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.zh.md b/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.zh.md
index 16b32daa05..26b7081e7b 100644
--- a/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.zh.md
+++ b/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.zh.md
@@ -37,7 +37,7 @@ Status: implemented
 
 ## 展示面是本次改动的一部分
 
-解除上限使一种此前任何渲染器都不曾收到的列表形状变得可达，因此本分支 stack（栈叠）在 [web todo 展示](2026-07-23-web-todo-display.md)之上，而不是与之并行落地：两者都改 `tool-todo`，而 GUI 正是并行计划变得可见的地方。web 有两处用 `todos.find(t => t.status === 'in_progress')` 推导单行摘要——折叠态的计划横条表头与 `todo_write` 工具行——在旧上限下这个 `find` 是完备的，因为最多只能有一个条目匹配。一旦有多个活跃项，它会静默丢掉除第一个之外的全部活跃条目：一个四条目、三个任务在跑的计划折叠后只显示其中一个的名字，工具行读作 `1/4 已完成 · <一个任务>`，而另外两个仍在进行。展开态的列表始终正确（它遍历每个条目），这也是两个 PR 的测试都没抓到它的原因——只有折叠表头与工具行丢失了信息。其后 [#740](https://github.com/deepseek-harness/deepseek-harness/pull/740) 的面板重做已把折叠表头的具名提示换成以 `·` 连接的各状态计数（本地化后形如 `1 已完成 · 2 进行中 · 1 待处理`，计数为零的段落省略），它能正确报告并行工作，且不需要任何可被截断的名字；工具行才是本分支仍需修的那一处。
+解除上限使一种此前任何渲染器都不曾收到的列表形状变得可达，因此本分支 stack（栈叠）在 [web todo 展示](2026-07-23-web-todo-display.md)之上，而不是与之并行落地：两者都改 `tool-todo`，而 GUI 正是并行计划变得可见的地方。web 有两处用 `todos.find(t => t.status === 'in_progress')` 推导单行摘要——折叠态的计划横条表头与 `todo_write` 工具行——在旧上限下这个 `find` 是完备的，因为最多只能有一个条目匹配。一旦有多个活跃项，它会静默丢掉除第一个之外的全部活跃条目：一个四条目、三个任务在跑的计划折叠后只显示其中一个的名字，工具行读作 `1/4 已完成 · <一个任务>`，而另外两个仍在进行。展开态的列表始终正确（它遍历每个条目），这也是两个 PR 的测试都没抓到它的原因——只有折叠表头与工具行丢失了信息。面板重做把折叠表头的具名提示换成以 `·` 连接的各状态计数（本地化后形如 `1 已完成 · 2 进行中 · 1 待处理`，计数为零的段落省略），它能正确报告并行工作，且不需要任何可被截断的名字；工具行才是本分支仍需修的那一处。
 
 工具行改用 `toolviews/plan-summary.ts` 中的 `planSummary`。它给出第一个活跃条目，并计数其余活跃项，因此工具行报告的是有多少任务在跑，而不是暗示只有一个。列出全部活跃条目被否决了：工具行是单行，无上界的拼接会溢出——在列表做不到的地方，计数能够可预测地降级。该推导放在 toolviews 域内而非 `contract/`（域间共享面）：面板自行内联计算其计数，与工具行不共享任何东西，因此放进 contract 会声明一种已不存在的共享关系。
 
diff --git a/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.i18n.yaml b/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.i18n.yaml
index f06403d181..1ceb5a5213 100644
--- a/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.i18n.yaml
+++ b/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.md
-2026-07-30-queued-manual-compaction.md: 4b7a905712a01948146b8830dfc037185162eefc
-2026-07-30-queued-manual-compaction.zh.md: 15a42de3536f2da5304e77ce3cb282029856ba6d
+2026-07-30-queued-manual-compaction.md: 5100808ada4b7b284228113584e577d46ff91101
+2026-07-30-queued-manual-compaction.zh.md: 29c3b921d0d59527aa1d8af1c91d085b52045377
diff --git a/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.md b/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.md
index 4b7a905712..5100808ada 100644
--- a/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.md
+++ b/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.md
@@ -75,7 +75,7 @@ Once a transaction has appended its start, every later failure makes one closing
 
 ### Reference implementation boundaries
 
-[PR #835](https://github.com/deepseek-harness/deepseek-harness/pull/835) was used as a reference implementation for the command, reservation, tests, and snapshot shape, but was not merged. Its process-local `WeakSet` lock and locked/unlocked method splits were considered and not adopted because the durable bracket is the single reachable lock.
+An unmerged reference implementation informed the command, reservation, tests, and snapshot shape. Its process-local `WeakSet` lock and locked/unlocked method splits were considered and not adopted because the durable bracket is the single reachable lock.
 
 That reference also carried client-side replacement-anchor machinery to preserve transcript placement. The log-ordered transcript projection already consumes compaction from event order and does not consult mutable surface positions, so those anchors were considered and not adopted.
 
diff --git a/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.zh.md b/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.zh.md
index 15a42de353..29c3b921d0 100644
--- a/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.zh.md
+++ b/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.zh.md
@@ -75,7 +75,7 @@ DSH 有意在调用摘要器前记录 `compact/start`。缓慢或崩溃的尝试
 
 ### 参考实现边界
 
-[PR #835](https://github.com/deepseek-harness/deepseek-harness/pull/835) 用作命令、预留、测试与快照结构的参考实现，但未被合并。它的进程本地 `WeakSet` 锁与 locked／unlocked 方法拆分经过评估后未被采用，因为持久标记对是唯一可达的锁。
+一个未合并的参考实现为命令、预留、测试与快照结构提供了参考。它的进程本地 `WeakSet` 锁与 locked／unlocked 方法拆分经过评估后未被采用，因为持久标记对是唯一可达的锁。
 
 该参考实现还包含客户端侧替换锚点机制，用于保留 transcript（文本记录）位置。按日志顺序排列的 transcript 投影已经从事件顺序消费压缩，并且不会查询可变 surface 位置，因此这些锚点经过评估后未被采用。
 
diff --git a/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.i18n.yaml b/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.i18n.yaml
index eea7ced3d2..40e24e9ac2 100644
--- a/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.i18n.yaml
+++ b/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.md
-2026-08-02-pwsh-tool-bash-parity.md: 945d2d5243162fe8e7fb3f76cbc3bcf0b5c2fdee
-2026-08-02-pwsh-tool-bash-parity.zh.md: f537e313a0c895927c6e2319b11b98619a70d461
+2026-08-02-pwsh-tool-bash-parity.md: e35a903892d5d50a0d3ca12b23daa53f26d6aade
+2026-08-02-pwsh-tool-bash-parity.zh.md: d7a68f0cab5281b25c3321e7ffff61c358b21a0a
diff --git a/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.md b/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.md
index 945d2d5243..e35a903892 100644
--- a/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.md
+++ b/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.md
@@ -14,7 +14,7 @@ The first Windows-native foundation shipped `dsh-tool-pwsh` as a deliberately mi
 
 - **Rendering adopts the bash story verbatim**: stdout, a marked `[stderr]` section, truncation notices with spill paths, `(no output)` for an empty body, and exit markers only for non-zero exits — a clean exit produces no marker. The description and the `tool:pwsh` prompt section state this precisely ("Non-zero exits are reported as `[exit code: N]` markers"), deliberately not copying the bash prompt's "every result" phrasing, which its own renderer contradicts.
 - **`run_in_background` is wired through the generic task runtime** exactly like the bash tool: preflight, owner registration, `task_output`/`task_kill` control, and the same outcome mapping. `pwsh-local`'s already-mirrored `start()` handle backs it.
-- **The `DSH_*` environment is shared, not duplicated**: `BashEnvRegistry` moved out of `dsh-tool-bash` into a new tool-independent `@deepseek-ai/dsh-bash-env` package (`ctx.bashEnv` + built-ins + the session-persistence contributor), and both shell tools inject it. Contributors apply to pwsh calls exactly as they do to bash calls, resolving the bash tool's `FIXME(bash-env-ownership)`.
+- **The `DSH_*` environment is shared, not duplicated**: `BashEnvRegistry` moved out of `dsh-tool-bash` into a new tool-independent `@deepseek-ai/dsh-bash-env` package (`ctx.bashEnv` + built-ins + the session-persistence contributor), and both shell tools inject it. Contributors apply to pwsh calls exactly as they do to bash calls; shared environment ownership therefore sits outside either model-facing shell tool.
 - **Windows reality is pinned where bash has no analog**: every command runs under a UTF-8 output preamble so the Windows PowerShell 5.1 fallback cannot garble non-ASCII output through the UTF-8-decoding collector, and the prompts teach that Windows forced termination settles as exit 1 without a signal marker.
 - **Out of scope, unchanged**: sandbox escalation (waits for a Windows-confining executor) and persistent PTY shells (backends are Linux/macOS-only; ConPTY is roadmap work). The pwsh-specific terminal card with an exit pill shipped separately in the [pwsh UI presentation matches bash](2026-08-05-pwsh-ui-bash-parity.md) decision.
 
diff --git a/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.zh.md b/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.zh.md
index f537e313a0..d7a68f0cab 100644
--- a/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.zh.md
+++ b/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.zh.md
@@ -14,7 +14,7 @@ Status: implemented
 
 - **渲染完全采用 bash 故事**：stdout、带标记的 `[stderr]` 段、带 spill 路径的截断通知、空体渲染 `(no output)`、退出 marker 仅限非零退出——干净退出不产生 marker。描述与 `tool:pwsh` prompt section 精确陈述这一点（"Non-zero exits are reported as `[exit code: N]` markers"），刻意不复制 bash prompt 中与其自身渲染矛盾的 "every result" 措辞。
 - **`run_in_background` 经通用任务运行时接线**，与 bash 工具完全一致：预检、owner 注册、`task_output`/`task_kill` 控制与相同的结果映射。其背后是 `pwsh-local` 早已镜像好的 `start()` 句柄。
-- **`DSH_*` 环境共享而非复制**：`BashEnvRegistry` 从 `dsh-tool-bash` 迁入新的工具无关包 `@deepseek-ai/dsh-bash-env`（`ctx.bashEnv` + 内置事实 + session-persistence contributor），两个 shell 工具都注入它。contributor 对 pwsh 调用与 bash 调用一视同仁，并消化了 bash 工具的 `FIXME(bash-env-ownership)`。
+- **`DSH_*` 环境共享而非复制**：`BashEnvRegistry` 从 `dsh-tool-bash` 迁入新的工具无关包 `@deepseek-ai/dsh-bash-env`（`ctx.bashEnv` + 内置事实 + session-persistence contributor），两个 shell 工具都注入它。contributor 对 pwsh 调用与 bash 调用一视同仁；因此，共享环境的所有权不属于任何一个面向模型的 shell 工具。
 - **Windows 现实在 bash 无对应处钉死**：每条命令都在 UTF-8 输出 preamble 下运行，使 Windows PowerShell 5.1 兜底无法经 UTF-8 解码的 collector 破坏非 ASCII 输出；prompt 教授 Windows 强制终止以无 signal 的 exit 1 结算。
 - **范围外，不变**：sandbox 升级（等待 Windows-confining 执行器）与持久 PTY shell（后端仅限 Linux/macOS；ConPTY 属路线图）。带退出 pill 的 pwsh 专属 terminal 卡已随 [pwsh UI 呈现与 bash 对齐](2026-08-05-pwsh-ui-bash-parity.md) 决策另行交付。
 
diff --git a/.agents/notes/implemented/feature/2026-08-05-pwsh-ui-bash-parity.i18n.yaml b/.agents/notes/implemented/feature/2026-08-05-pwsh-ui-bash-parity.i18n.yaml
index dcb3a9406b..51401adfdc 100644
--- a/.agents/notes/implemented/feature/2026-08-05-pwsh-ui-bash-parity.i18n.yaml
+++ b/.agents/notes/implemented/feature/2026-08-05-pwsh-ui-bash-parity.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-05-pwsh-ui-bash-parity.md
-2026-08-05-pwsh-ui-bash-parity.md: 6bbdb0e6bc69ef1af03a6a9146f83b84754cb2a6
-2026-08-05-pwsh-ui-bash-parity.zh.md: 75f3a3ddec002acaa1755c81114b0f122ab80593
+2026-08-05-pwsh-ui-bash-parity.md: 815b448b894e9c53b4c4a2076f6b94fdd316dd35
+2026-08-05-pwsh-ui-bash-parity.zh.md: 967c5a9e1409028043dc5028fdca640ddfeb1acc
diff --git a/.agents/notes/implemented/feature/2026-08-05-pwsh-ui-bash-parity.md b/.agents/notes/implemented/feature/2026-08-05-pwsh-ui-bash-parity.md
index 6bbdb0e6bc..815b448b89 100644
--- a/.agents/notes/implemented/feature/2026-08-05-pwsh-ui-bash-parity.md
+++ b/.agents/notes/implemented/feature/2026-08-05-pwsh-ui-bash-parity.md
@@ -6,7 +6,7 @@ English | [中文](2026-08-05-pwsh-ui-bash-parity.zh.md)
 
 ## Problem
 
-The [pwsh tool bash parity decision](../../implemented/feature/2026-08-02-pwsh-tool-bash-parity.md) made `dsh-tool-pwsh` behaviorally interchangeable with `dsh-tool-bash` for execution, markers, and background tasks, but explicitly deferred the human-visible half: a completed pwsh foreground call presented as a generic `console`-fenced card while the bash tool's completed call presented as a terminal card with a parsed exit-status pill. The roadmap that owned this gap ([Windows defaults to pwsh](../../proposed/feature/2026-08-01-windows-pwsh-default.md)) named "pwsh TUI/GUI rendering" as stage 2 — but the TUI package was removed ([`ed30088adb`](https://github.com/deepseek-harness/deepseek-harness/commit/ed30088adb)), leaving the Web surface as the only UI the gap affects.
+The [pwsh tool bash parity decision](../../implemented/feature/2026-08-02-pwsh-tool-bash-parity.md) made `dsh-tool-pwsh` behaviorally interchangeable with `dsh-tool-bash` for execution, markers, and background tasks, but explicitly deferred the human-visible half: a completed pwsh foreground call presented as a generic `console`-fenced card while the bash tool's completed call presented as a terminal card with a parsed exit-status pill. The roadmap that owned this gap ([Windows defaults to pwsh](../../proposed/feature/2026-08-01-windows-pwsh-default.md)) named "pwsh TUI/GUI rendering" as stage 2, but the TUI package was removed, leaving the Web surface as the only UI the gap affects.
 
 ## Decision
 
diff --git a/.agents/notes/implemented/feature/2026-08-05-pwsh-ui-bash-parity.zh.md b/.agents/notes/implemented/feature/2026-08-05-pwsh-ui-bash-parity.zh.md
index 75f3a3ddec..967c5a9e14 100644
--- a/.agents/notes/implemented/feature/2026-08-05-pwsh-ui-bash-parity.zh.md
+++ b/.agents/notes/implemented/feature/2026-08-05-pwsh-ui-bash-parity.zh.md
@@ -6,7 +6,7 @@ Status: implemented
 
 ## Problem
 
-[pwsh 工具与 bash 对齐决策](../../implemented/feature/2026-08-02-pwsh-tool-bash-parity.md) 让 `dsh-tool-pwsh` 在执行、marker 与后台任务上行为可互换，但明确推迟了面向人类的一半：完成的 pwsh 前台调用呈现为通用 `console` 围栏卡片，而 bash 工具的完成调用呈现为带解析退出状态 pill 的 terminal 卡。拥有此缺口的路线图（[Windows 默认改用 pwsh](../../proposed/feature/2026-08-01-windows-pwsh-default.md)）把 "pwsh TUI/GUI 渲染" 列为阶段 2——但 TUI 包已被移除（[`ed30088adb`](https://github.com/deepseek-harness/deepseek-harness/commit/ed30088adb)），Web 表面成为该缺口唯一影响的 UI。
+[pwsh 工具与 bash 对齐决策](../../implemented/feature/2026-08-02-pwsh-tool-bash-parity.md) 让 `dsh-tool-pwsh` 在执行、marker 与后台任务上行为可互换，但明确推迟了面向人类的一半：完成的 pwsh 前台调用呈现为通用 `console` 围栏卡片，而 bash 工具的完成调用呈现为带解析退出状态 pill 的 terminal 卡。拥有此缺口的路线图（[Windows 默认改用 pwsh](../../proposed/feature/2026-08-01-windows-pwsh-default.md)）把 "pwsh TUI/GUI 渲染" 列为阶段 2，但 TUI 包已被移除，使 Web 表面成为该缺口唯一影响的 UI。
 
 ## Decision
 
diff --git a/.agents/notes/implemented/process/2026-07-13-documentation-site-projection.i18n.yaml b/.agents/notes/implemented/process/2026-07-13-documentation-site-projection.i18n.yaml
index 7fa4d3fbba..07e0a89d0f 100644
--- a/.agents/notes/implemented/process/2026-07-13-documentation-site-projection.i18n.yaml
+++ b/.agents/notes/implemented/process/2026-07-13-documentation-site-projection.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-13-documentation-site-projection.md
-2026-07-13-documentation-site-projection.md: f19d9b309aa22821a75086dc07ee302097631ba0
-2026-07-13-documentation-site-projection.zh.md: cc5e94e709f0639fd35ad81165b199cc5c9effc0
+2026-07-13-documentation-site-projection.md: d9af915754fa6a1df51a27d18d412597472aaa73
+2026-07-13-documentation-site-projection.zh.md: 5b6de4b3425b6d20335a0f8055468ced414d4034
diff --git a/.agents/notes/implemented/process/2026-07-13-documentation-site-projection.md b/.agents/notes/implemented/process/2026-07-13-documentation-site-projection.md
index f19d9b309a..d9af915754 100644
--- a/.agents/notes/implemented/process/2026-07-13-documentation-site-projection.md
+++ b/.agents/notes/implemented/process/2026-07-13-documentation-site-projection.md
@@ -18,7 +18,9 @@ Canonical Markdown remains in the repository tier that owns it. Product-facing g
 
 Locale home projections retain only the canonical YAML frontmatter. The repository-facing body can keep its H1 and bilingual source links, while the VitePress home theme owns the rendered hero and features and the site navigation owns locale switching.
 
-The projector parses Markdown links without reserializing the document. A link to another published source becomes a site-relative route; a link to an unpublished repository file becomes a GitHub source link; a repository image is copied into the generated tree and referenced from there ([why](2026-08-06-doc-site-carries-its-images.md)). Missing relative targets fail projection. Unit tests pin these transformations, and `docs:check` runs the projector tests plus a production VitePress build as part of `doc-sync` and the parallel documentation gates.
+The projector parses Markdown links without reserializing the document. A link to another published source becomes a site-relative route; a link to an unpublished repository file becomes a source link under the public `deepseek-ai/deepseek-harness-sdk` home; a repository image is copied into the generated tree and referenced from there ([why](2026-08-06-doc-site-carries-its-images.md)). Missing relative targets fail projection. Unit tests pin these transformations, and `docs:check` runs the projector tests plus a production VitePress build as part of `doc-sync` and the parallel documentation gates.
+
+`verify-public-repository-links` rejects internal repository remotes from tracked files. Public source links use the public home, while work tracking stays in repository metadata and source carries a TODO only when the local boundary matters to maintainers.
 
 `website/AGENTS.md` is the only maintained Markdown file in the website subtree. The projector test enumerates tracked and unignored files and rejects any other website Markdown, so site-specific locale, route, API, or generated source copies cannot bypass the publication manifest.
 
diff --git a/.agents/notes/implemented/process/2026-07-13-documentation-site-projection.zh.md b/.agents/notes/implemented/process/2026-07-13-documentation-site-projection.zh.md
index cc5e94e709..5b6de4b342 100644
--- a/.agents/notes/implemented/process/2026-07-13-documentation-site-projection.zh.md
+++ b/.agents/notes/implemented/process/2026-07-13-documentation-site-projection.zh.md
@@ -18,7 +18,9 @@ Status: implemented
 
 各 locale 的首页投影只保留权威 YAML frontmatter。面向仓库的正文可以保留其 H1 和双语源文件链接，而 VitePress 首页主题负责渲染 hero 与功能区，网站导航负责切换 locale。
 
-投影器解析 Markdown 链接，但不会重新序列化文档。指向另一个已发布源文件的链接会变成站内相对路由；指向未发布仓库文件的链接会变成 GitHub 源文件链接；仓库图片会被拷贝进生成树并从那里引用（[原因](2026-08-06-doc-site-carries-its-images.md)）。相对目标不存在时，投影会失败。单元测试会锁定这些转换行为，`docs:check` 则运行投影器测试和 VitePress 生产构建，并将二者纳入 `doc-sync` 和并行文档门禁。
+投影器解析 Markdown 链接，但不会重新序列化文档。指向另一个已发布源文件的链接会变成站内相对路由；指向未发布仓库文件的链接会变成公开 `deepseek-ai/deepseek-harness-sdk` 主页下的源文件链接；仓库图片会被拷贝进生成树并从那里引用（[原因](2026-08-06-doc-site-carries-its-images.md)）。相对目标不存在时，投影会失败。单元测试会锁定这些转换行为，`docs:check` 则运行投影器测试和 VitePress 生产构建，并将二者纳入 `doc-sync` 和并行文档门禁。
+
+`verify-public-repository-links` 会拒绝已跟踪文件中的内部仓库远程链接。公开源文件链接使用公开主页，而工作跟踪留在仓库元数据中；只有本地边界对维护者有意义时，源文件才保留 TODO。
 
 `website/AGENTS.md` 是网站子树中唯一维护的 Markdown 文件。投影器测试会枚举所有已跟踪文件和未被忽略的未跟踪文件，并拒绝网站中的任何其他 Markdown，因此网站专用的 locale、路由、API 或生成源文件副本无法绕过发布 manifest。
 
diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml
index 8ccd5ca13e..1dc5d79676 100644
--- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml
+++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md
-2026-07-22-evidence-based-larger-hosted-runners.md: d46b8291ec05e997728da76354354f9e36bd2fb4
-2026-07-22-evidence-based-larger-hosted-runners.zh.md: f43712859d8351ffff45c7b6d5eb2b65015ee4c3
+2026-07-22-evidence-based-larger-hosted-runners.md: 53cc86efce9061c8f9836a17cb35ebb128085b7a
+2026-07-22-evidence-based-larger-hosted-runners.zh.md: 0484548c76cb7eed11dc4235ef024a700499ef6a
diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md
index d46b8291ec..53cc86efce 100644
--- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md
+++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md
@@ -26,7 +26,7 @@ The artifact boundary remains explicit. `scripts/publint-all.ts` calls publint's
 
 Windows shares one 32-core setup across the blocking build and production site plus observational built-artifact contracts. Linux owns the duplicate lint, coverage, and snapshot inventories because running those observational copies on Windows extends the paid critical path without adding a blocking platform claim.
 
-An [exact-head all-size benchmark](https://github.com/deepseek-harness/deepseek-harness/actions/runs/29908491351) ran the complete unsharded primary Node aggregate on every Linux pool before the eager-build correction:
+An exact-head all-size benchmark ran the complete unsharded primary Node aggregate on every Linux pool before the eager-build correction:
 
 | Complete Linux primary | 4 cores | 8 cores | 16 cores | 32 cores | 64 cores | 96 cores |
 |---|---:|---:|---:|---:|---:|---:|
@@ -40,13 +40,13 @@ The same benchmark measured the required Windows build surfaces across every pro
 |---|---:|---:|---:|---:|---:|---:|
 | Active time | 152 s | 104 s | 104 s | 92 s | 103 s | 110 s |
 
-Repository work gains little above 16 Windows cores, but the 32-core pool can start the complete outer inventory together. A [retargeted production validation](https://github.com/deepseek-harness/deepseek-harness/actions/runs/29907581119/attempts/2) completed the full one-box Windows inventory in 173 seconds, including coverage and snapshot replay, so Windows remains consolidated.
+Repository work gains little above 16 Windows cores, but the 32-core pool can start the complete outer inventory together. A retargeted production validation completed the full one-box Windows inventory in 173 seconds, including coverage and snapshot replay, so Windows remains consolidated.
 
-The larger client package graph makes cache mechanics and scheduler pressure part of the measured workload. In [one exact-head candidate run](https://github.com/deepseek-harness/deepseek-harness/actions/runs/29912577681), Linux spent 39 seconds in repository gates but 69 seconds in the complete job, while Windows spent 117 seconds in repository gates and 228 seconds in the complete job. The Windows pnpm cache downloaded its 154 MB archive in about two seconds but spent 27 seconds extracting it, followed by a 23-second install and a 14-second post-job save. A [cacheless all-size trace](https://github.com/deepseek-harness/deepseek-harness/actions/runs/29913033155) completed the same 32-core Windows install in 27 seconds. A future larger-runner rollout therefore needs complete-job measurements rather than gate-only timing.
+The larger client package graph makes cache mechanics and scheduler pressure part of the measured workload. In one exact-head candidate run, Linux spent 39 seconds in repository gates but 69 seconds in the complete job, while Windows spent 117 seconds in repository gates and 228 seconds in the complete job. The Windows pnpm cache downloaded its 154 MB archive in about two seconds but spent 27 seconds extracting it, followed by a 23-second install and a 14-second post-job save. A cacheless all-size trace completed the same 32-core Windows install in 27 seconds. A future larger-runner rollout therefore needs complete-job measurements rather than gate-only timing.
 
 Host setup remains part of any comparison. A standard Node 26 job once spent 36 of its 67 seconds in `Set up job`, while `actions/setup-node` spent 46.56 seconds printing cached Windows environment details after finding Node in the hosted toolcache. A Linux candidate also spent 18 seconds registering a 50 KB Bubblewrap package because the hosted image scanned 202,507 package-database files. [`scripts/prepare-ci-bubblewrap.sh`](../../../../scripts/prepare-ci-bubblewrap.sh) instead verifies and extracts the pinned payload into the ephemeral runner directory, runs a functional confinement probe, and overlaps that preparation with dependency installation.
 
-Inner and outer worker limits are separate controls. An [exact-head 32-worker ESLint experiment](https://github.com/deepseek-harness/deepseek-harness/actions/runs/29918329463) slowed lint to 52.28 seconds and coverage to 42.71 seconds, where an adapter idle-timeout test failed. A later 8-gate trace reduced coverage to 35.17 seconds but delayed the production-site build until the aggregate reached 41.06 seconds. Core count therefore does not justify copying an equally large worker limit.
+Inner and outer worker limits are separate controls. An exact-head 32-worker ESLint experiment slowed lint to 52.28 seconds and coverage to 42.71 seconds, where an adapter idle-timeout test failed. A later 8-gate trace reduced coverage to 35.17 seconds but delayed the production-site build until the aggregate reached 41.06 seconds. Core count therefore does not justify copying an equally large worker limit.
 
 The process-bound coverage project contains exactly five suite files. Thirty-two forks crashed Node 24's CJS lexer twice, and a later 16-fork run reproduced the worker loss and invalid coverage result. The single Vitest invocation therefore uses threads for the broad inventory and reserves forks for suites that exercise process-global state, `process` APIs, or timing-sensitive process I/O. That narrow fork inventory includes the local bash process-plumbing suite and the pi-ai adapter suite because aggregate contention changed timing observations in both. These failures make deterministic coverage, not advertised cores, the upper bound on worker selection.
 
diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md
index f43712859d..0484548c76 100644
--- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md
+++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md
@@ -26,7 +26,7 @@ Linux 主流程使用 3 个相互独立的 32 核作业。覆盖率单独运行
 
 Windows 以一次 32 核环境设置同时承载阻塞性构建、生产网站和观测性的构建产物契约。重复的 lint、覆盖率和快照清单由 Linux 承担，因为在 Windows 上运行这些观测性副本会延长付费关键路径，却不会新增任何阻塞性平台契约。
 
-一次[分支头精确的全规格基准测试](https://github.com/deepseek-harness/deepseek-harness/actions/runs/29908491351)在修正构建尽早启动逻辑前，对每种 Linux 池都运行了完整且未分片的主 Node 聚合流程：
+一次分支头精确的全规格基准测试在修正构建尽早启动逻辑前，对每种 Linux 池都运行了完整且未分片的主 Node 聚合流程：
 
 | Linux 完整主流程 | 4 核 | 8 核 | 16 核 | 32 核 | 64 核 | 96 核 |
 |---|---:|---:|---:|---:|---:|---:|
@@ -40,13 +40,13 @@ Windows 以一次 32 核环境设置同时承载阻塞性构建、生产网站
 |---|---:|---:|---:|---:|---:|---:|
 | 活动耗时 | 152 秒 | 104 秒 | 104 秒 | 92 秒 | 103 秒 | 110 秒 |
 
-Windows 仓库工作在超过 16 核后收益很小，但 32 核池可以让完整的外层清单同时启动。一次[重新定向的生产验证](https://github.com/deepseek-harness/deepseek-harness/actions/runs/29907581119/attempts/2)在 173 秒内完成了单机 Windows 完整清单，其中包括覆盖率和快照回放，因此 Windows 继续采用合并执行方式。
+Windows 仓库工作在超过 16 核后收益很小，但 32 核池可以让完整的外层清单同时启动。一次重新定向的生产验证在 173 秒内完成了单机 Windows 完整清单，其中包括覆盖率和快照回放，因此 Windows 继续采用合并执行方式。
 
-客户端包依赖图增大后，缓存机制和调度器压力也成为实测工作负载的一部分。在[一次分支头精确的候选运行](https://github.com/deepseek-harness/deepseek-harness/actions/runs/29912577681)中，Linux 的仓库门禁耗时 39 秒，完整作业耗时 69 秒；Windows 的仓库门禁耗时 117 秒，完整作业耗时 228 秒。Windows pnpm 缓存的 154 MB 归档下载耗时约 2 秒，但解压耗时 27 秒，随后安装耗时 23 秒，作业结束后的保存又耗时 14 秒。一次[无缓存的全规格运行轨迹](https://github.com/deepseek-harness/deepseek-harness/actions/runs/29913033155)在 27 秒内完成了同一台 32 核 Windows 运行器上的安装。因此，未来若要启用大型运行器，需要测量完整作业，而不能只测门禁耗时。
+客户端包依赖图增大后，缓存机制和调度器压力也成为实测工作负载的一部分。在一次分支头精确的候选运行中，Linux 的仓库门禁耗时 39 秒，完整作业耗时 69 秒；Windows 的仓库门禁耗时 117 秒，完整作业耗时 228 秒。Windows pnpm 缓存的 154 MB 归档下载耗时约 2 秒，但解压耗时 27 秒，随后安装耗时 23 秒，作业结束后的保存又耗时 14 秒。一次无缓存的全规格运行轨迹在 27 秒内完成了同一台 32 核 Windows 运行器上的安装。因此，未来若要启用大型运行器，需要测量完整作业，而不能只测门禁耗时。
 
 任何比较都必须计入主机设置。一个标准 Node 26 作业曾在总共 67 秒的耗时中，把 36 秒用在 `Set up job` 上；`actions/setup-node` 从托管 toolcache 找到 Node 后，仍花费 46.56 秒输出缓存的 Windows 环境详情。一个 Linux 候选作业还在注册 50 KB 的 Bubblewrap 包时耗时 18 秒，因为托管映像扫描了 202,507 个包数据库文件。[`scripts/prepare-ci-bubblewrap.sh`](../../../../scripts/prepare-ci-bubblewrap.sh) 改为验证固定版本的 payload 并将其解压到临时运行器目录，执行功能性隔离探针，并让这项准备工作与依赖安装重叠执行。
 
-内层与外层工作线程上限是相互独立的控制机制。一次[分支头精确、使用 32 个工作线程的 ESLint 实验](https://github.com/deepseek-harness/deepseek-harness/actions/runs/29918329463)使 lint 耗时增至 52.28 秒、覆盖率耗时增至 42.71 秒；同一次运行中，一项适配器空闲超时测试失败。后来一次同时运行 8 项门禁的运行轨迹将覆盖率耗时降至 35.17 秒，但生产网站构建被延后，直到聚合流程耗时达到 41.06 秒时才完成。因此，不能仅凭核心数照搬同等规模的工作线程上限。
+内层与外层工作线程上限是相互独立的控制机制。一次分支头精确、使用 32 个工作线程的 ESLint 实验使 lint 耗时增至 52.28 秒、覆盖率耗时增至 42.71 秒；同一次运行中，一项适配器空闲超时测试失败。后来一次同时运行 8 项门禁的运行轨迹将覆盖率耗时降至 35.17 秒，但生产网站构建被延后，直到聚合流程耗时达到 41.06 秒时才完成。因此，不能仅凭核心数照搬同等规模的工作线程上限。
 
 进程约束的覆盖率项目恰好包含 5 个套件文件。32 个 fork 曾两次导致 Node 24 的 CJS 词法分析器崩溃，后来一次使用 16 个 fork 的运行又复现了工作进程丢失和无效的覆盖率结果。因此，单次 Vitest 调用会对大范围测试清单使用线程，只为涉及进程全局状态、`process` API 或对时间敏感的进程 I/O 的套件保留 fork。这份有限的 fork 清单包括本地 bash 进程通路套件和 pi-ai 适配器套件，因为聚合争用改变了二者的时序观测结果。这些故障表明，选择工作线程数量时，上限取决于能否得到确定的覆盖率结果，而非标称核心数。
 
diff --git a/.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.i18n.yaml b/.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.i18n.yaml
index be725fc905..ac859f10dd 100644
--- a/.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.i18n.yaml
+++ b/.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.md
-2026-07-26-briefed-minimal-translation-updates.md: a47251376771165d0eb229aaa0fb7f63589d7d77
-2026-07-26-briefed-minimal-translation-updates.zh.md: c3c1b4e845b5a45acde55884b883b1dd1e570d77
+2026-07-26-briefed-minimal-translation-updates.md: afd990b7b63adfd0e66a4726975b678d044e7cad
+2026-07-26-briefed-minimal-translation-updates.zh.md: dcdb253746041a7928ab7a544ae427293bc3f2de
diff --git a/.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.md b/.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.md
index a472513767..afd990b7b6 100644
--- a/.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.md
+++ b/.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.md
@@ -12,7 +12,7 @@ The [bilingual pairing contract](2026-07-02-bilingual-docs-and-pairing-gate.md)
 
 Pair updates run on a generated briefing instead of the guidance corpus; only new pairs still run the whole-document workflow, which is unchanged.
 
-- **`pnpm run gen-translation-brief [--apply] [pair...]`** ([scripts/gen-translation-brief.ts](../../../../scripts/gen-translation-brief.ts), assembly in [scripts/translation-brief.ts](../../../../scripts/translation-brief.ts)) prints, per out-of-sync pair, the authored side's diff from its recorded last-confirmed blob to the working tree plus the change mapped at the narrowest safely aligned granularity, deterministically widening on mapping failure: a change confined to the pair's byte-identical code fences is computed outright (`--apply` splices it into the counterpart and validates the result against the pairing gate's structural signature before writing); otherwise changed Markdown units (headings, paragraphs, table rows, list items, code fences, block quotes, HTML blocks, thematic breaks, link definitions — matched by container-scoped kind sequences) each carry their last-confirmed source, current source, and current counterpart text with line numbers; units that do not align fall back to depth-matched heading sections; and when sections do not align either, or both sides drifted, the briefing says so and withholds the mapping instead of guessing. Terminology rows are matched against the changed spans only (word-boundary English matching with plural inflections), and for Chinese targets the briefing tracks each relevant term's document-wide first occurrence — when an edit moves it, the vacated and receiving spans join the briefing with an explanatory note, since the 首次出现 annotation must move with it. The unit mapping, code splice, and first-occurrence mechanics adopt the planner design from the [incremental prompt-pipeline work](https://github.com/deepseek-harness/deepseek-harness/pull/684), whose provider-backed bake-off independently validated the same scope ladder for the automated pipeline. The briefing is the translator's whole working set; the full sources of truth remain the escalation path for decisions the briefing cannot answer.
+- **`pnpm run gen-translation-brief [--apply] [pair...]`** ([scripts/gen-translation-brief.ts](../../../../scripts/gen-translation-brief.ts), assembly in [scripts/translation-brief.ts](../../../../scripts/translation-brief.ts)) prints, per out-of-sync pair, the authored side's diff from its recorded last-confirmed blob to the working tree plus the change mapped at the narrowest safely aligned granularity, deterministically widening on mapping failure: a change confined to the pair's byte-identical code fences is computed outright (`--apply` splices it into the counterpart and validates the result against the pairing gate's structural signature before writing); otherwise changed Markdown units (headings, paragraphs, table rows, list items, code fences, block quotes, HTML blocks, thematic breaks, link definitions — matched by container-scoped kind sequences) each carry their last-confirmed source, current source, and current counterpart text with line numbers; units that do not align fall back to depth-matched heading sections; and when sections do not align either, or both sides drifted, the briefing says so and withholds the mapping instead of guessing. Terminology rows are matched against the changed spans only (word-boundary English matching with plural inflections), and for Chinese targets the briefing tracks each relevant term's document-wide first occurrence — when an edit moves it, the vacated and receiving spans join the briefing with an explanatory note, since the 首次出现 annotation must move with it. The unit mapping, code splice, and first-occurrence mechanics adopt the planner design from the incremental prompt-pipeline work; its provider-backed bake-off independently validated the same scope ladder for the automated pipeline. The briefing is the translator's whole working set; the full sources of truth remain the escalation path for decisions the briefing cannot answer.
 - **The update path in [dsh-translate-docs](../../../skills/dsh-translate-docs/SKILL.md)** consumes the briefing: mechanical (code-fence-only) changes are applied with `--apply`, no subagent; prose diffs go to a subagent whose prompt is the briefing, not the corpus; verification is clause-by-clause on the changed spans, not the whole document.
 - **The pairing gate takes pair arguments.** `verify-translation-pairing [pair...]` checks just the named pairs (any of a pair's three files, or the bare stem, names it); the corpus-wide sweep remains the no-argument form that `doc-sync` and CI run. `--write` now requires naming the confirmed pairs — bare `--write` refuses, and re-recording everything is an explicit `--write --all` — because the old bare form silently blessed every drifted pair in the tree, including ones the caller never looked at, and a prose-only drift would then stay green forever. Each record's comment names its own scoped command. Before recording, `--write` stores each side's exact bytes with `git hash-object -w --stdin` and pins the blob under a content-addressed local `refs/dsh/translation-pairing/snapshots/` ref; an uncommitted last-confirmed snapshot is therefore available to the briefing generator's later `git cat-file`, not merely named by a hash that Git cannot resolve or left vulnerable to garbage collection.
 
diff --git a/.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.zh.md b/.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.zh.md
index c3c1b4e845..dcdb253746 100644
--- a/.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.zh.md
+++ b/.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.zh.md
@@ -12,7 +12,7 @@ Status: implemented
 
 配对更新基于生成的简报（briefing）运行，而非基于指导语料；只有新建配对仍走整篇文档工作流，后者保持不变。
 
-- **`pnpm run gen-translation-brief [--apply] [pair...]`**（[scripts/gen-translation-brief.ts](../../../../scripts/gen-translation-brief.ts)，组装逻辑在 [scripts/translation-brief.ts](../../../../scripts/translation-brief.ts)）针对每个失去同步的配对，打印被改一侧从其记录在案的上次确认 blob 到当前工作区的 diff，并附上以能安全对齐的最窄粒度映射的这次改动，映射失败时粒度确定性地逐级放宽：仅落在配对中逐字节一致的围栏代码块内的改动会直接算出（`--apply` 会把它拼接进对侧文件，并在写入前用配对门禁的结构签名校验所得结果）；否则，每个有改动的 Markdown 单元（标题、段落、表格行、列表项、围栏代码块、块引用、HTML 块、分隔线、链接定义；匹配依据是以容器为作用域的种类序列）都带上各自的上次确认源文、当前源文与当前对侧文本及行号；无法对齐的单元回退到按深度匹配的标题章节；当章节也无法对齐或两侧同时漂移时，简报会明说这一点并省略映射，而不是靠猜。术语表行只与改动块匹配（英文术语按词边界匹配，含复数变形）；当目标侧是中文时，简报还会跟踪每个相关术语在整篇文档中的首次出现：一旦某次编辑使其移位，腾出的与接收的两处区间就会附一条解释性说明加入简报，因为「首次出现」括注必须随之移动。单元映射、代码拼接与首次出现机制采纳了[增量提示词流水线工作](https://github.com/deepseek-harness/deepseek-harness/pull/684)中的规划器设计；该项工作中接入提供方的对比评测，已为自动流水线独立验证了同一套范围阶梯。简报就是译者的全部工作集；简报回答不了的决策，仍以完整的真源文档作为升级求证路径。
+- **`pnpm run gen-translation-brief [--apply] [pair...]`**（[scripts/gen-translation-brief.ts](../../../../scripts/gen-translation-brief.ts)，组装逻辑在 [scripts/translation-brief.ts](../../../../scripts/translation-brief.ts)）针对每个失去同步的配对，打印被改一侧从其记录在案的上次确认 blob 到当前工作区的 diff，并附上以能安全对齐的最窄粒度映射的这次改动，映射失败时粒度确定性地逐级放宽：仅落在配对中逐字节一致的围栏代码块内的改动会直接算出（`--apply` 会把它拼接进对侧文件，并在写入前用配对门禁的结构签名校验所得结果）；否则，每个有改动的 Markdown 单元（标题、段落、表格行、列表项、围栏代码块、块引用、HTML 块、分隔线、链接定义；匹配依据是以容器为作用域的种类序列）都带上各自的上次确认源文、当前源文与当前对侧文本及行号；无法对齐的单元回退到按深度匹配的标题章节；当章节也无法对齐或两侧同时漂移时，简报会明说这一点并省略映射，而不是靠猜。术语表行只与改动块匹配（英文术语按词边界匹配，含复数变形）；当目标侧是中文时，简报还会跟踪每个相关术语在整篇文档中的首次出现：一旦某次编辑使其移位，腾出的与接收的两处区间就会附一条解释性说明加入简报，因为「首次出现」括注必须随之移动。单元映射、代码拼接与首次出现机制采纳了增量提示词流水线工作的规划器设计；该项工作中接入提供方的对比评测，已为自动流水线独立验证了同一套范围阶梯。简报就是译者的全部工作集；简报回答不了的决策，仍以完整的真源文档作为升级求证路径。
 - **[dsh-translate-docs](../../../skills/dsh-translate-docs/SKILL.md) 中的更新路径**消费这份简报：机械类改动（只涉及围栏代码块）用 `--apply` 应用，不动用 subagent；行文类 diff 交给 subagent，其提示词就是简报本身，而非指导语料；核验只对改动块逐句进行，不覆盖整篇文档。
 - **配对门禁接受配对参数。**`verify-translation-pairing [pair...]` 只检查被点名的配对（配对三个文件中的任意一个，或其裸词干，都能指代该配对）；全语料扫描仍是 `doc-sync`（文档同步门禁）与 CI 运行的无参数形式。`--write` 现在要求点名已确认的配对：裸 `--write` 会拒绝执行，重新记录全部配对必须显式写 `--write --all`；原因是旧的裸形式会默默为树中每一个漂移的配对背书，包括调用者从未看过的那些，纯行文层面的漂移于是可以永远保持绿灯。每份记录的注释都写明针对该配对自身的按对命令。写下记录之前，`--write` 用 `git hash-object -w --stdin` 存入每一侧的精确字节，并在内容寻址的本地 `refs/dsh/translation-pairing/snapshots/` ref 下固定该 blob；未提交的上次确认快照因此能被简报生成器之后的 `git cat-file` 取回，而不只是留下一个 Git 无法解析的 hash 名称或暴露于垃圾回收。
 
diff --git a/.agents/notes/implemented/process/2026-07-27-wine-windows-gates-experiment.i18n.yaml b/.agents/notes/implemented/process/2026-07-27-wine-windows-gates-experiment.i18n.yaml
index 4786909a7f..19945a6580 100644
--- a/.agents/notes/implemented/process/2026-07-27-wine-windows-gates-experiment.i18n.yaml
+++ b/.agents/notes/implemented/process/2026-07-27-wine-windows-gates-experiment.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-27-wine-windows-gates-experiment.md
-2026-07-27-wine-windows-gates-experiment.md: 640c8e455b1a35ea4ac83454227147b9979316dc
-2026-07-27-wine-windows-gates-experiment.zh.md: 67f59a93d1b1fad98e36e6f9c51bc77abb9e3d07
+2026-07-27-wine-windows-gates-experiment.md: 1b01fe00dc1588482442a3cedc35eefa7fdb0975
+2026-07-27-wine-windows-gates-experiment.zh.md: b50739f5b63c5836248c94927037e38900abc84f
diff --git a/.agents/notes/implemented/process/2026-07-27-wine-windows-gates-experiment.md b/.agents/notes/implemented/process/2026-07-27-wine-windows-gates-experiment.md
index 640c8e455b..1b01fe00dc 100644
--- a/.agents/notes/implemented/process/2026-07-27-wine-windows-gates-experiment.md
+++ b/.agents/notes/implemented/process/2026-07-27-wine-windows-gates-experiment.md
@@ -14,7 +14,7 @@ The question the experiment answered: can a plain Linux runner produce an equiva
 
 The required pull-request `windows` job in [ci.yml](../../../../.github/workflows/ci.yml) (`windows node 24 / wine blocking`) runs the blocking gate commands on `ubuntu-latest` under Wine with real Windows binaries: a checksum-verified win-x64 Node.js executes `tsc -b`, `tsdown`, and the VitePress production build, so the win32 branches of the toolchain — backslash path handling, `CreateProcess` spawn semantics, PE loading of `@esbuild/win32-x64`, and the rolldown/rollup MSVC `.node` addons — actually execute. The master `serial-windows` job is untouched: the complete native-kernel inventory, including the observational portability gates this lane does not run, still executes on real `windows-2025` on every master push.
 
-Dependencies install natively on Linux with `supportedArchitectures` extended to win32-x64, which materializes the Windows platform packages in the same store; the cmd-shim layer is bypassed by invoking each tool's JavaScript entrypoint directly, the same processes `run-gates` ultimately spawns. `nodeLinker: hoisted` is load-bearing, not stylistic: the independent prototype in [PR #689](https://github.com/deepseek-harness/deepseek-harness/pull/689) kept pnpm's default isolated layout — including a faithful offline Windows-pnpm re-install over a Linux-prefetched store — and Windows Node under Wine still could not resolve `@esbuild/win32-x64` or load the koffi prebuild through the isolated symlink chain, failing before any repository gate ran. A flat layout with real files is what makes the gates reachable at all; #689's checksum pinning is adopted, while its Windows-pnpm-installs-the-tree goal is explicitly given up (the install contract stays Linux-tested here).
+Dependencies install natively on Linux with `supportedArchitectures` extended to win32-x64, which materializes the Windows platform packages in the same store; the cmd-shim layer is bypassed by invoking each tool's JavaScript entrypoint directly, the same processes `run-gates` ultimately spawns. `nodeLinker: hoisted` is load-bearing, not stylistic: an independent prototype kept pnpm's default isolated layout — including a faithful offline Windows-pnpm re-install over a Linux-prefetched store — and Windows Node under Wine still could not resolve `@esbuild/win32-x64` or load the koffi prebuild through the isolated symlink chain, failing before any repository gate ran. A flat layout with real files is what makes the gates reachable at all; the prototype's checksum pinning is adopted, while its Windows-pnpm-installs-the-tree goal is explicitly given up (the install contract stays Linux-tested here).
 
 The lane holds the wall clock of the Linux CI jobs through four levers: the master-refreshed pnpm store cache (restore-only, same key as the Linux jobs), Wine provisioning (apt install, Windows Node download, `wineboot`) running concurrently with `pnpm install`, the two blocking surfaces running concurrently — the same shape `run-gates` gives them on native Windows — and an apt-archive cache keyed on the runner image, seeded from master by the `wine apt cache` job so every pull request restores from the default-branch scope.
 
@@ -32,7 +32,7 @@ Measured on 2026-07-27, warm caches, pull-request trigger, standard 2-core `ubun
 
 **A full Windows guest under QEMU/KVM inside the Linux runner.** Real NT kernel, so full fidelity including case-insensitive NTFS and ConPTY — but tens of minutes of image download and unattended install before the first gate runs (40m19s measured end-to-end on the sibling experiment branch `exp/kvm-windows-ci`). Promotable only with disk-image caching that pressures the Actions cache budget.
 
-**Windows pnpm performing the install under Wine ([PR #689](https://github.com/deepseek-harness/deepseek-harness/pull/689)).** The higher-fidelity variant of this same idea: MinGit and pnpm staged into the prefix, a Linux prefetch filling the store, then `pnpm install --offline` run by Windows Node so the install contract itself executes as win32. It reached the install but not the gates — Wine's networking could not reach the registry directly, and the isolated `node_modules` layout defeated resolution of the Windows platform packages even after a clean offline install. This lane trades that fidelity away (hoisted layout, Linux-side install) to reach the gates; the two records are complementary halves of the same verdict.
+**Windows pnpm performing the install under Wine.** The higher-fidelity variant of this same idea: MinGit and pnpm staged into the prefix, a Linux prefetch filling the store, then `pnpm install --offline` run by Windows Node so the install contract itself executes as win32. It reached the install but not the gates — Wine's networking could not reach the registry directly, and the isolated `node_modules` layout defeated resolution of the Windows platform packages even after a clean offline install. This lane trades that fidelity away (hoisted layout, Linux-side install) to reach the gates; the two records are complementary halves of the same verdict.
 
 **Filesystem-semantics lanes on Linux (casefolded ext4, filename lint).** Catches the highest-frequency Windows breakage class for near-zero cost but proves nothing about win32 binaries. Explored as the sibling experiment branch `exp/casefold-windows-ci`; complementary to, not competitive with, this lane.
 
diff --git a/.agents/notes/implemented/process/2026-07-27-wine-windows-gates-experiment.zh.md b/.agents/notes/implemented/process/2026-07-27-wine-windows-gates-experiment.zh.md
index 67f59a93d1..b50739f5b6 100644
--- a/.agents/notes/implemented/process/2026-07-27-wine-windows-gates-experiment.zh.md
+++ b/.agents/notes/implemented/process/2026-07-27-wine-windows-gates-experiment.zh.md
@@ -14,7 +14,7 @@ Pull request 的 Windows 通道旨在验证两个阻断性 win32 表面，即 wo
 
 [ci.yml](../../../../.github/workflows/ci.yml) 中必需的 pull request `windows` 作业（`windows node 24 / wine blocking`）在 `ubuntu-latest` 上通过 Wine 用真实 Windows 二进制运行阻断门禁命令：校验和验证过的 win-x64 Node.js 执行 `tsc -b`、`tsdown` 与 VitePress 生产构建，因此工具链的 win32 分支——反斜杠路径处理、`CreateProcess` 派生语义、`@esbuild/win32-x64` 的 PE 加载、以及 rolldown/rollup 的 MSVC `.node` 插件——都真正执行。master 的 `serial-windows` 作业原封不动：完整的原生内核清单，包括本通道不运行的观察性可移植性门禁，仍在每次 master push 时于真实 `windows-2025` 上执行。
 
-依赖在 Linux 上原生安装，`supportedArchitectures` 扩展到 win32-x64，使 Windows 平台包物化进同一个 store；通过直接调用各工具的 JavaScript 入口绕开 cmd-shim 层，这正是 `run-gates` 最终派生的那些进程。`nodeLinker: hoisted` 是承重的，不是风格问题：[PR #689](https://github.com/deepseek-harness/deepseek-harness/pull/689) 的独立原型保留了 pnpm 默认的 isolated 布局——包括在 Linux 预取的 store 上忠实地用 Windows pnpm 离线重装——而 Wine 下的 Windows Node 依然无法穿过 isolated 符号链接链解析 `@esbuild/win32-x64` 或加载 koffi 预编译产物，在任何仓库门禁运行前就失败了。扁平的真实文件布局才让门禁变得可达；本通道采纳了 #689 的校验和固定，同时明确放弃其「Windows pnpm 安装依赖树」的目标（安装契约在此仍由 Linux 侧验证）。
+依赖在 Linux 上原生安装，`supportedArchitectures` 扩展到 win32-x64，使 Windows 平台包物化进同一个 store；通过直接调用各工具的 JavaScript 入口绕开 cmd-shim 层，这正是 `run-gates` 最终派生的那些进程。`nodeLinker: hoisted` 是承重的，不是风格问题：一个独立原型保留了 pnpm 默认的 isolated 布局——包括在 Linux 预取的 store 上忠实地用 Windows pnpm 离线重装——而 Wine 下的 Windows Node 依然无法穿过 isolated 符号链接链解析 `@esbuild/win32-x64` 或加载 koffi 预编译产物，在任何仓库门禁运行前就失败了。扁平的真实文件布局才让门禁变得可达；本通道采纳了该原型的校验和固定，同时明确放弃其「Windows pnpm 安装依赖树」的目标（安装契约在此仍由 Linux 侧验证）。
 
 该通道靠四个杠杆把墙钟时间保持在与 Linux CI 作业相当的水平：master 刷新的 pnpm store 缓存（只恢复，与 Linux 作业同键）、Wine 供给（apt 安装、Windows Node 下载、`wineboot`）与 `pnpm install` 并发运行、两个阻断表面并发运行——与 `run-gates` 在原生 Windows 上给它们的形状相同——以及按 runner 镜像为键的 apt 归档缓存，由 master 的 `wine apt cache` 作业播种，使每个 pull request 都能从默认分支作用域恢复。
 
@@ -32,7 +32,7 @@ Pull request 的 Windows 通道旨在验证两个阻断性 win32 表面，即 wo
 
 **在 Linux runner 内用 QEMU/KVM 跑完整 Windows 客户机。** 真实 NT 内核，保真度完整，包括大小写不敏感的 NTFS 与 ConPTY——但首个门禁运行前要花数十分钟下载镜像并做无人值守安装（兄弟实验分支 `exp/kvm-windows-ci` 实测端到端 40 分 19 秒）。只有配上会挤压 Actions 缓存预算的磁盘镜像缓存才可投入使用。
 
-**在 Wine 下由 Windows pnpm 执行安装（[PR #689](https://github.com/deepseek-harness/deepseek-harness/pull/689)）。** 同一想法的更高保真度变体：把 MinGit 与 pnpm 放进 prefix，用 Linux 预取填充 store，再由 Windows Node 运行 `pnpm install --offline`，让安装契约本身以 win32 身份执行。它到达了安装但没到达门禁——Wine 的网络无法直接访问 registry，且 isolated 的 `node_modules` 布局即便在干净的离线安装后也挫败了 Windows 平台包的解析。本通道牺牲这份保真度（hoisted 布局、Linux 侧安装）来换取门禁可达；两份记录是同一裁决互补的两半。
+**在 Wine 下由 Windows pnpm 执行安装。** 同一想法的更高保真度变体：把 MinGit 与 pnpm 放进 prefix，用 Linux 预取填充 store，再由 Windows Node 运行 `pnpm install --offline`，让安装契约本身以 win32 身份执行。它到达了安装但没到达门禁——Wine 的网络无法直接访问 registry，且 isolated 的 `node_modules` 布局即便在干净的离线安装后也挫败了 Windows 平台包的解析。本通道牺牲这份保真度（hoisted 布局、Linux 侧安装）来换取门禁可达；两份记录是同一裁决互补的两半。
 
 **Linux 上的文件系统语义通道（casefold ext4、文件名 lint）。** 以近零成本捕获最高频的 Windows 故障类别，但对 win32 二进制什么也证明不了。作为兄弟实验分支 `exp/casefold-windows-ci` 探索；与本通道互补而非竞争。
 
diff --git a/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.i18n.yaml b/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.i18n.yaml
index 1a179748f9..77003539ac 100644
--- a/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.i18n.yaml
+++ b/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.md
-2026-07-31-installer-adopts-existing-checkout.md: de3cd052f94a0d5256c7687e9a1a38ee69fd2caf
-2026-07-31-installer-adopts-existing-checkout.zh.md: 2e8be804b4af6151e77e36f8b109616aab3a18e9
+2026-07-31-installer-adopts-existing-checkout.md: 3a213a6232e57f305910240505983421dcd288ad
+2026-07-31-installer-adopts-existing-checkout.zh.md: 7cdcd5549fb2bca2a6cb11f0cf2867687565ae79
diff --git a/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.md b/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.md
index de3cd052f9..3a213a6232 100644
--- a/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.md
+++ b/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.md
@@ -46,6 +46,6 @@ A container adopting an outside clone is also no longer self-contained: deleting
 
 ## Testing
 
-`scripts/install.sh` has no automated test, and this change does not add one: the user directed that `install.spec.ts` be left out of scope. That is a known gap on a shipped user-facing path, and the `/var` resolution defect above is exactly the class of bug a test would have caught first. The standing [`FIXME(install-ts)`](../../../../scripts/install.sh) asking for this workflow to move into a tested TypeScript entrypoint is correspondingly more pressing.
+`scripts/install.sh` now has a real-shell PTY regression suite in `apps/cli/tests/install-script.spec.ts`, covering adoption and curl-style paths with stubbed dependencies. Curl-style installs default to the public `deepseek-ai/deepseek-harness-sdk` source, while replacing the installer with pnpm/npx remains separate work.
 
 Verification was manual, through a throwaway harness driving the real script with a stubbed `pnpm`: adopting a standalone clone; adopting from a linked worktree into its existing container; an explicit `DSH_SOURCE` still opting back into cloning; a dirty tree adopting silently with no prompt or warning while its uncommitted file stays behind; a non-git checkout failing with guidance; and a `curl`-style clone install asserting the built layout, which is the regression that caught the unresolved-`REPO_ROOT` defect. The interactive path was exercised under tmux from a dirty checkout, confirming the run reaches the launcher with no adoption prompt and ends with `dsh` running from the new staging worktree while the original checkout keeps its branch and its uncommitted file.
diff --git a/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.zh.md b/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.zh.md
index 2e8be804b4..7cdcd5549f 100644
--- a/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.zh.md
+++ b/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.zh.md
@@ -46,6 +46,6 @@ Status: implemented
 
 ## Testing
 
-`scripts/install.sh`没有自动化测试，本次变更也未添加：用户明确要求把`install.spec.ts`排除在范围之外。这是一条已交付的、面向用户的安装路径上的已知缺口，而上文那个`/var`解析缺陷，恰恰属于测试本应最先捕获的那类 bug。相应地，要求把这套流程迁移到有测试覆盖的 TypeScript 入口的既有[`FIXME(install-ts)`](../../../../scripts/install.sh)也变得更为紧迫。
+`scripts/install.sh` 现有一套位于 `apps/cli/tests/install-script.spec.ts` 的真实 shell PTY 回归测试，使用 stub 依赖覆盖接管路径和 curl 风格路径。curl 风格安装默认使用公开的 `deepseek-ai/deepseek-harness-sdk` 源，而以 pnpm/npx 替换安装器仍是另一项工作。
 
 验证是手工完成的，通过一个一次性测试装置以打桩的`pnpm`驱动真实脚本：接管独立克隆；从 linked worktree 接管进其已有容器；显式`DSH_SOURCE`仍回到克隆路径；工作树不干净时静默接管、既不提示也不警告，且其未提交文件留在原处；非 git 检出失败并给出指引；以及`curl`式克隆安装断言所构建的布局——正是这项回归测试捕获了`REPO_ROOT`未解析的缺陷。交互路径在 tmux 下从一个不干净的检出走通，确认整个过程不出现接管提示即可到达启动器，最终`dsh`从新的 staging worktree 运行，而原检出保持其分支不变、未提交文件仍在。
diff --git a/.agents/notes/implemented/process/2026-08-06-doc-site-carries-its-images.i18n.yaml b/.agents/notes/implemented/process/2026-08-06-doc-site-carries-its-images.i18n.yaml
index 32b51699e2..8ba8380bf1 100644
--- a/.agents/notes/implemented/process/2026-08-06-doc-site-carries-its-images.i18n.yaml
+++ b/.agents/notes/implemented/process/2026-08-06-doc-site-carries-its-images.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-08-06-doc-site-carries-its-images.md
-2026-08-06-doc-site-carries-its-images.md: 9109808874579b79d85c2e22b0987110f41ddc42
-2026-08-06-doc-site-carries-its-images.zh.md: d601112e8870150c363d8533e85ef86e7f3f8ffc
+2026-08-06-doc-site-carries-its-images.md: 4078a9b6251cf67456590ae25602a9f288c88dc1
+2026-08-06-doc-site-carries-its-images.zh.md: a9afb138d45d1ab991963b997e408477cf88110b
diff --git a/.agents/notes/implemented/process/2026-08-06-doc-site-carries-its-images.md b/.agents/notes/implemented/process/2026-08-06-doc-site-carries-its-images.md
index 9109808874..4078a9b625 100644
--- a/.agents/notes/implemented/process/2026-08-06-doc-site-carries-its-images.md
+++ b/.agents/notes/implemented/process/2026-08-06-doc-site-carries-its-images.md
@@ -20,7 +20,7 @@ Only a regular file whose real path stays inside the repository is copied; anyth
 
 `docsSourceFiles()` reports the placed images alongside the Markdown, so the dev server's watcher re-projects when a screenshot is replaced instead of serving the previous copy until something touches the page.
 
-`placeImage` is optional because `rewriteMarkdown` is also called directly by its spec, where no generated tree exists. Without it the old GitHub-raw behavior stands, which keeps that seam honest: the fallback is still the correct answer for a consumer that only rewrites text.
+`placeImage` is optional because `rewriteMarkdown` is also called directly by its spec, where no generated tree exists. Without it the GitHub-raw fallback points at the public source home, which keeps that seam honest for a consumer that only rewrites text.
 
 Canonical Markdown keeps writing ordinary repository-relative image paths, so the same file renders on GitHub and on the site. No document carries a site-absolute URL to satisfy VitePress.
 
@@ -36,7 +36,7 @@ Canonical Markdown keeps writing ordinary repository-relative image paths, so th
 
 Images in published documentation now work regardless of who is reading or whether the repository is public, and the site build has no runtime dependency on GitHub for them. The generated tree grows by one copy of each referenced image per locale — the four screenshots in the model-provider guide add roughly 270 KB per locale.
 
-Images referenced from *unpublished* documents are untouched: they still resolve to GitHub raw, and still fail for a private repository. Nothing consumes them today, and a document that is not on the site has no site build to carry its assets.
+Images referenced from *unpublished* documents are untouched. A text-only projection resolves them against the public source home; a document that is not on the site has no site build to carry its assets.
 
 ## Testing
 
diff --git a/.agents/notes/implemented/process/2026-08-06-doc-site-carries-its-images.zh.md b/.agents/notes/implemented/process/2026-08-06-doc-site-carries-its-images.zh.md
index d601112e88..a9afb138d4 100644
--- a/.agents/notes/implemented/process/2026-08-06-doc-site-carries-its-images.zh.md
+++ b/.agents/notes/implemented/process/2026-08-06-doc-site-carries-its-images.zh.md
@@ -20,7 +20,7 @@ Status: implemented
 
 `docsSourceFiles()` 会连同被安置的图片一起上报，于是替换截图时开发服务器的 watcher 会重新投影，而不是一直服务旧副本直到有人碰一下页面。
 
-`placeImage` 之所以可选，是因为 `rewriteMarkdown` 也被它自己的 spec 直接调用，而那里并不存在生成树。不传它时保持原有的 GitHub raw 行为，这也让该接缝保持诚实：对只改写文本的消费方而言，这个回退仍是正确答案。
+`placeImage` 之所以可选，是因为 `rewriteMarkdown` 也被它自己的 spec 直接调用，而那里并不存在生成树。不传它时，GitHub raw 回退会指向公开源主页；这让该 seam 对只改写文本的消费方保持诚实。
 
 正本 Markdown 照旧写普通的仓库相对图片路径，因此同一份文件在 GitHub 上和站点上都能正常显示。没有任何文档为了迁就 VitePress 而写站内绝对 URL。
 
@@ -36,7 +36,7 @@ Status: implemented
 
 已发布文档中的图片，现在无论谁在阅读、无论仓库是否公开都能显示，站点构建也不再为图片依赖 GitHub 的运行时可达性。生成树会为每个 locale 各增加一份被引用图片的副本——配置模型指南里的四张截图，每个 locale 约 270 KB。
 
-**未发布**文档引用的图片不受影响：它们仍解析到 GitHub raw，对私有仓库仍然失败。今天没有任何消费方用到它们，而不在站点上的文档也没有站点构建可以承载其资源。
+**未发布**文档引用的图片不受影响。纯文本投影会相对于公开源主页解析它们；不在站点上的文档没有站点构建可以承载其资源。
 
 ## Testing
 
diff --git a/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.i18n.yaml b/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.i18n.yaml
index fe97a7b717..202a27ed1e 100644
--- a/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.i18n.yaml
+++ b/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md
-2026-06-19-acp-snapshot-tests.md: e118ada58230fe31fbb2a6bffb83e5612757ab1f
-2026-06-19-acp-snapshot-tests.zh.md: e292dbf3bf3c4c5198dc77d122bb6b8c36014ebf
+2026-06-19-acp-snapshot-tests.md: c7b95bd68027705b99d850d596405e56eea0dfca
+2026-06-19-acp-snapshot-tests.zh.md: 43d43262684920cae5feedb5f2eb109db00f9f8c
diff --git a/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md b/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md
index e118ada582..c7b95bd680 100644
--- a/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md
+++ b/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md
@@ -80,6 +80,6 @@ Tool determinism comes from a generated cwd, scrubbed environment, fresh non-log
 
 ## Consequences
 
-The tier adds reviewed per-scenario input, session, stdout, optional override, and optional workspace fixtures, plus one file for each distinct pinned prompt and tool-schema sequence. Workspace seeds are copied into the generated cwd for both record and replay. In return the tier provides deterministic keyless coverage through the real Loader and tool composition. Most retained scenarios exercise the assembled backend rather than ACP; the [automation-only ACP decision](../simplification/2026-07-23-acp-automation-only-protocol.md#snapshot-boundary) keeps that corpus here and defers any move to a transport-neutral headless suite as an independent testing change (the suite-level FIXME marks it).
+The tier adds reviewed per-scenario input, session, stdout, optional override, and optional workspace fixtures, plus one file for each distinct pinned prompt and tool-schema sequence. Workspace seeds are copied into the generated cwd for both record and replay. In return the tier provides deterministic keyless coverage through the real Loader and tool composition. Most retained scenarios exercise the assembled backend rather than ACP; the [automation-only ACP decision](../simplification/2026-07-23-acp-automation-only-protocol.md#snapshot-boundary) keeps that corpus here until it can move to a transport-neutral headless suite without losing coverage.
 
 This Agent Note relates to but does not supersede the [proposed determinism Agent Note](../../proposed/testing/2026-06-11-deterministic-and-stress-testing.md): that proposal's "universal replay fixture" re-derives session *message history* after every test (an internal-consistency invariant), whereas these snapshots pin assembled behavior plus the external automation output. They are complementary until the backend corpus moves off ACP.
diff --git a/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.zh.md b/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.zh.md
index e292dbf3bf..43d4326268 100644
--- a/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.zh.md
+++ b/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.zh.md
@@ -80,6 +80,6 @@ Status: implemented
 
 ## 后果
 
-该测试层为每个场景增加经过评审的输入、会话、stdout、可选 override 和可选 workspace fixture，并为每个不同的已固定提示词序列、每个不同的已固定工具 schema 序列各增加一个文件。记录与回放都会把 workspace seed 复制到生成的 cwd。作为回报，该层通过真实 Loader 和工具组合提供确定性的无密钥覆盖。保留下来的大多数场景测试的是组装后的后端而非 ACP；[仅面向自动化的 ACP 决策](../simplification/2026-07-23-acp-automation-only-protocol.md#snapshot-boundary)将该语料保留在此处，并把向传输无关 headless 套件的任何迁移推迟为一项独立的测试变更（套件级 FIXME 标记了这一点）。
+该测试层为每个场景增加经过评审的输入、会话、stdout、可选 override 和可选 workspace fixture，并为每个不同的已固定提示词序列、每个不同的已固定工具 schema 序列各增加一个文件。记录与回放都会把 workspace seed 复制到生成的 cwd。作为回报，该层通过真实 Loader 和工具组合提供确定性的无密钥覆盖。保留下来的大多数场景测试的是组装后的后端而非 ACP；[仅面向自动化的 ACP 决策](../simplification/2026-07-23-acp-automation-only-protocol.md#snapshot-boundary)将该语料保留在此处，直至它能够在不损失覆盖的情况下迁移到传输无关的 headless 套件。
 
 本 Agent Note 与[拟议的确定性 Agent Note](../../proposed/testing/2026-06-11-deterministic-and-stress-testing.md)相关，但不取代它：该提案的“通用回放 fixture”在每次测试后重新派生会话*消息历史*（内部一致性不变量），而这些快照固定组装后的行为与外部自动化输出。在后端语料迁出 ACP 之前，两者相互补充。
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 821948f873..46ab8e892f 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -30,7 +30,7 @@ env:
 
 jobs:
 
-  # FIXME: Re-enable the three hosted serial reference jobs before cutting a release.
+  # TODO(hosted-serial-ci): Re-enable the three hosted serial reference jobs before release.
   # The self-hosted standby remains active on every master push.
 
   # Three enterprise jobs isolate coverage, static analysis, and the
diff --git a/docs/cordis-tutorial/01-first-plugin.i18n.yaml b/docs/cordis-tutorial/01-first-plugin.i18n.yaml
index 4e829dcb8f..29e0266689 100644
--- a/docs/cordis-tutorial/01-first-plugin.i18n.yaml
+++ b/docs/cordis-tutorial/01-first-plugin.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write docs/cordis-tutorial/01-first-plugin.md
-01-first-plugin.md: c44e7f95fb11d5337ecfaf4251c8b2f2b9b14680
-01-first-plugin.zh.md: 9461884d312ad2e64af12fa42952a986e1ad5d8a
+01-first-plugin.md: 4359dfe4883f12e9cb242cf3009827fd7864768c
+01-first-plugin.zh.md: 62ccb7e5d37beb5b9636439e563cea6eaa1044a0
diff --git a/docs/cordis-tutorial/01-first-plugin.md b/docs/cordis-tutorial/01-first-plugin.md
index c44e7f95fb..4359dfe488 100644
--- a/docs/cordis-tutorial/01-first-plugin.md
+++ b/docs/cordis-tutorial/01-first-plugin.md
@@ -92,4 +92,4 @@ One caveat worth knowing early: a config entry whose module cannot be **resolved
 
 Next: [Lifecycle and effects](02-lifecycle-and-effects.md) — what happens when a plugin unloads.
 
-[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-harness/deepseek-harness)
+[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-ai/deepseek-harness-sdk)
diff --git a/docs/cordis-tutorial/01-first-plugin.zh.md b/docs/cordis-tutorial/01-first-plugin.zh.md
index 9461884d31..62ccb7e5d3 100644
--- a/docs/cordis-tutorial/01-first-plugin.zh.md
+++ b/docs/cordis-tutorial/01-first-plugin.zh.md
@@ -92,4 +92,4 @@ export function apply(ctx: Context) {
 
 下一章：[生命周期与 effect](02-lifecycle-and-effects.md)：插件卸载时会发生什么。
 
-[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-harness/deepseek-harness)
+[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-ai/deepseek-harness-sdk)
diff --git a/docs/cordis-tutorial/02-lifecycle-and-effects.i18n.yaml b/docs/cordis-tutorial/02-lifecycle-and-effects.i18n.yaml
index deed723c39..12793267e2 100644
--- a/docs/cordis-tutorial/02-lifecycle-and-effects.i18n.yaml
+++ b/docs/cordis-tutorial/02-lifecycle-and-effects.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write docs/cordis-tutorial/02-lifecycle-and-effects.md
-02-lifecycle-and-effects.md: f1b39e06e9d25c51ab2d76503025e2b6ffe90c73
-02-lifecycle-and-effects.zh.md: 2e98e3af6d2f2b1b9cbb8ea38559bc1ffbf7e43b
+02-lifecycle-and-effects.md: 7b195b63a1e8730f27b9dd9af8af6a68a588cee9
+02-lifecycle-and-effects.zh.md: 4a3f83dedd5c95c7fcb5c1aebbbb8cb2e849b9cf
diff --git a/docs/cordis-tutorial/02-lifecycle-and-effects.md b/docs/cordis-tutorial/02-lifecycle-and-effects.md
index f1b39e06e9..7b195b63a1 100644
--- a/docs/cordis-tutorial/02-lifecycle-and-effects.md
+++ b/docs/cordis-tutorial/02-lifecycle-and-effects.md
@@ -95,4 +95,4 @@ One ordering caveat: disposers start in reverse registration order, but multiple
 
 Next: [Services](03-services.md) — how plugins share capabilities.
 
-[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-harness/deepseek-harness)
+[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-ai/deepseek-harness-sdk)
diff --git a/docs/cordis-tutorial/02-lifecycle-and-effects.zh.md b/docs/cordis-tutorial/02-lifecycle-and-effects.zh.md
index 2e98e3af6d..4a3f83dedd 100644
--- a/docs/cordis-tutorial/02-lifecycle-and-effects.zh.md
+++ b/docs/cordis-tutorial/02-lifecycle-and-effects.zh.md
@@ -95,4 +95,4 @@ PENDING → LOADING → ACTIVE → UNLOADING → DISPOSED
 
 下一章：[服务](03-services.md)：插件如何共享功能。
 
-[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-harness/deepseek-harness)
+[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-ai/deepseek-harness-sdk)
diff --git a/docs/cordis-tutorial/03-services.i18n.yaml b/docs/cordis-tutorial/03-services.i18n.yaml
index b116270811..2849ed8858 100644
--- a/docs/cordis-tutorial/03-services.i18n.yaml
+++ b/docs/cordis-tutorial/03-services.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write docs/cordis-tutorial/03-services.md
-03-services.md: 5848132c6ad18338fa893954d45fc20005db6199
-03-services.zh.md: 0f599f082573364e6ad38278e1914d8faf67faa1
+03-services.md: 562b49ede0aa4cc1d58c4d6af7c7d5d1ebb2e4b1
+03-services.zh.md: 964f7e3654614d136b8765bb727f85a5a05587a8
diff --git a/docs/cordis-tutorial/03-services.md b/docs/cordis-tutorial/03-services.md
index 5848132c6a..562b49ede0 100644
--- a/docs/cordis-tutorial/03-services.md
+++ b/docs/cordis-tutorial/03-services.md
@@ -95,4 +95,4 @@ Service names live in one flat namespace per application. Prefix or namespace yo
 
 Next: [Events](04-events.md) — communication without a shared service.
 
-[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-harness/deepseek-harness)
+[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-ai/deepseek-harness-sdk)
diff --git a/docs/cordis-tutorial/03-services.zh.md b/docs/cordis-tutorial/03-services.zh.md
index 0f599f0825..964f7e3654 100644
--- a/docs/cordis-tutorial/03-services.zh.md
+++ b/docs/cordis-tutorial/03-services.zh.md
@@ -95,4 +95,4 @@ export function apply(ctx: Context) {
 
 下一章：[事件](04-events.md)：无需共享服务即可通信。
 
-[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-harness/deepseek-harness)
+[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-ai/deepseek-harness-sdk)
diff --git a/docs/cordis-tutorial/04-events.i18n.yaml b/docs/cordis-tutorial/04-events.i18n.yaml
index 6d21e5ff1b..e7dc182114 100644
--- a/docs/cordis-tutorial/04-events.i18n.yaml
+++ b/docs/cordis-tutorial/04-events.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write docs/cordis-tutorial/04-events.md
-04-events.md: 18f39dc1b693e5fb7e1793ec4b7dcac9cf24db95
-04-events.zh.md: 3fdafb50303f49dca179bcaea32db211a66241f6
+04-events.md: 28ccb85d657afaabb5c6b4b1e9b10d6cf8710918
+04-events.zh.md: f78c971dcd9674d2a256c41000b627aecb2a572a
diff --git a/docs/cordis-tutorial/04-events.md b/docs/cordis-tutorial/04-events.md
index 18f39dc1b6..28ccb85d65 100644
--- a/docs/cordis-tutorial/04-events.md
+++ b/docs/cordis-tutorial/04-events.md
@@ -141,4 +141,4 @@ The harness uses waterfalls for decisions that cooperating plugins may wrap or a
 
 Next: [Configuration](05-config.md) — plugin options from `cordis.yml`.
 
-[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-harness/deepseek-harness)
+[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-ai/deepseek-harness-sdk)
diff --git a/docs/cordis-tutorial/04-events.zh.md b/docs/cordis-tutorial/04-events.zh.md
index 3fdafb5030..f78c971dcd 100644
--- a/docs/cordis-tutorial/04-events.zh.md
+++ b/docs/cordis-tutorial/04-events.zh.md
@@ -141,4 +141,4 @@ harness 使用 waterfall 处理协作插件可以包装或回答的决策：[`ag
 
 下一章：[配置](05-config.md)：来自 `cordis.yml` 的插件选项。
 
-[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-harness/deepseek-harness)
+[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-ai/deepseek-harness-sdk)
diff --git a/docs/cordis-tutorial/05-config.i18n.yaml b/docs/cordis-tutorial/05-config.i18n.yaml
index db300b1745..7db45165c4 100644
--- a/docs/cordis-tutorial/05-config.i18n.yaml
+++ b/docs/cordis-tutorial/05-config.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write docs/cordis-tutorial/05-config.md
-05-config.md: 8d4043e33a58fc425d82d9846ff82473bcdef4c1
-05-config.zh.md: e9463bd34e9c72dbae7b1ceb9907e35edf7b773b
+05-config.md: 834bb140cc1ff976acc8f21c8f54a7fb02636eac
+05-config.zh.md: f5cc6ac1ca4fa02eba6a1b015b9f6ae3b1a925fc
diff --git a/docs/cordis-tutorial/05-config.md b/docs/cordis-tutorial/05-config.md
index 8d4043e33a..834bb140cc 100644
--- a/docs/cordis-tutorial/05-config.md
+++ b/docs/cordis-tutorial/05-config.md
@@ -81,4 +81,4 @@ The loader used in this repo supports a `!!js` tag for config values that must b
 
 Next: [Composition and HMR](06-composition-and-hmr.md) — treating `cordis.yml` as the application.
 
-[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-harness/deepseek-harness)
+[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-ai/deepseek-harness-sdk)
diff --git a/docs/cordis-tutorial/05-config.zh.md b/docs/cordis-tutorial/05-config.zh.md
index e9463bd34e..f5cc6ac1ca 100644
--- a/docs/cordis-tutorial/05-config.zh.md
+++ b/docs/cordis-tutorial/05-config.zh.md
@@ -81,4 +81,4 @@ ValidationError: invalid config:
 
 下一章：[组合与 HMR（热模块替换）](06-composition-and-hmr.md)：将 `cordis.yml` 视为应用。
 
-[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-harness/deepseek-harness)
+[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-ai/deepseek-harness-sdk)
diff --git a/docs/cordis-tutorial/06-composition-and-hmr.i18n.yaml b/docs/cordis-tutorial/06-composition-and-hmr.i18n.yaml
index f7abfca742..44b59db26a 100644
--- a/docs/cordis-tutorial/06-composition-and-hmr.i18n.yaml
+++ b/docs/cordis-tutorial/06-composition-and-hmr.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write docs/cordis-tutorial/06-composition-and-hmr.md
-06-composition-and-hmr.md: 66d6a9d93fe39baa881940ba32388979e2678505
-06-composition-and-hmr.zh.md: 7c0a94b0abcc0f153f59391fd009f1e0b40500e5
+06-composition-and-hmr.md: f138918a2d217ed98fdfd4e56dffddc14e3397f0
+06-composition-and-hmr.zh.md: a678e86735c6d9e3b4f3cd0dfa46a2a64079c762
diff --git a/docs/cordis-tutorial/06-composition-and-hmr.md b/docs/cordis-tutorial/06-composition-and-hmr.md
index 66d6a9d93f..f138918a2d 100644
--- a/docs/cordis-tutorial/06-composition-and-hmr.md
+++ b/docs/cordis-tutorial/06-composition-and-hmr.md
@@ -110,4 +110,4 @@ needs-timer is PENDING — a required service is missing
 
 Next: [Into the harness](07-into-the-harness.md) — the same patterns against real harness services.
 
-[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-harness/deepseek-harness)
+[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-ai/deepseek-harness-sdk)
diff --git a/docs/cordis-tutorial/06-composition-and-hmr.zh.md b/docs/cordis-tutorial/06-composition-and-hmr.zh.md
index 7c0a94b0ab..a678e86735 100644
--- a/docs/cordis-tutorial/06-composition-and-hmr.zh.md
+++ b/docs/cordis-tutorial/06-composition-and-hmr.zh.md
@@ -110,4 +110,4 @@ needs-timer is PENDING — a required service is missing
 
 下一章：[进入 harness](07-into-the-harness.md)：把相同模式用于真实的 harness 服务。
 
-[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-harness/deepseek-harness)
+[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-ai/deepseek-harness-sdk)
diff --git a/docs/cordis-tutorial/07-into-the-harness.i18n.yaml b/docs/cordis-tutorial/07-into-the-harness.i18n.yaml
index 5faa0bf213..f3dde47f3a 100644
--- a/docs/cordis-tutorial/07-into-the-harness.i18n.yaml
+++ b/docs/cordis-tutorial/07-into-the-harness.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write docs/cordis-tutorial/07-into-the-harness.md
-07-into-the-harness.md: 6ec42c50fe5059955734fe7bc46117538dafaffc
-07-into-the-harness.zh.md: 903adb903aa4c4355b92eb34e89f218a0295767c
+07-into-the-harness.md: e02f8f8d55b3fbe9087d46f8f50baeecb592c1c6
+07-into-the-harness.zh.md: 5f770267e8f3db04cd9cb0e92b6a6278cf05d5e4
diff --git a/docs/cordis-tutorial/07-into-the-harness.md b/docs/cordis-tutorial/07-into-the-harness.md
index 6ec42c50fe..e02f8f8d55 100644
--- a/docs/cordis-tutorial/07-into-the-harness.md
+++ b/docs/cordis-tutorial/07-into-the-harness.md
@@ -104,4 +104,4 @@ Where to go next:
 - The generated [services](../cordis-catalog/services.md) and [events](../cordis-catalog/events.md) catalogs — everything you can inject and listen to.
 - [Architecture](../architecture.md) — the system map these plugins live in.
 
-[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-harness/deepseek-harness)
+[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-ai/deepseek-harness-sdk)
diff --git a/docs/cordis-tutorial/07-into-the-harness.zh.md b/docs/cordis-tutorial/07-into-the-harness.zh.md
index 903adb903a..5f770267e8 100644
--- a/docs/cordis-tutorial/07-into-the-harness.zh.md
+++ b/docs/cordis-tutorial/07-into-the-harness.zh.md
@@ -104,4 +104,4 @@ logger 会先触发：`tools/result` 在结果物化过程中发出，发生在
 - 生成的[服务](../cordis-catalog/services.md)与[事件](../cordis-catalog/events.md)目录：可以注入和监听的所有内容。
 - [架构](../architecture.md)：这些插件所处的系统地图。
 
-[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-harness/deepseek-harness)
+[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-ai/deepseek-harness-sdk)
diff --git a/docs/cordis-tutorial/index.i18n.yaml b/docs/cordis-tutorial/index.i18n.yaml
index 256bc4f629..496a3fffa5 100644
--- a/docs/cordis-tutorial/index.i18n.yaml
+++ b/docs/cordis-tutorial/index.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write docs/cordis-tutorial/index.md
-index.md: af622ad4e35829c6283c40f1b0019d7959dac973
-index.zh.md: 0b7684a9532a1efdcc3ea2d067da23852d146e2f
+index.md: a20976706f520416236ca759ee33649d1601eaa9
+index.zh.md: f6989521d4b7dffac6114867cc12371af4e4316f
diff --git a/docs/cordis-tutorial/index.md b/docs/cordis-tutorial/index.md
index af622ad4e3..a20976706f 100644
--- a/docs/cordis-tutorial/index.md
+++ b/docs/cordis-tutorial/index.md
@@ -13,7 +13,7 @@ If you want the condensed concept reference instead of a walkthrough, read the [
 You need a clone of this repository with dependencies installed — the [quick start](../user/guide/quickstart.md) covers prerequisites. No API key is needed for this tutorial; every example runs keylessly.
 
 ```sh
-git clone https://github.com/deepseek-harness/deepseek-harness.git
+git clone https://github.com/deepseek-ai/deepseek-harness-sdk.git
 cd deepseek-harness
 pnpm install
 ```
@@ -55,4 +55,4 @@ The examples use three TypeScript features beyond ordinary modern JavaScript:
 
 Chapter 5 also uses an `interface` to describe a configuration object's fields and a generic type such as `Schema<Config>` to say which object shape a schema validates. You can copy those declarations as shown; the surrounding text explains what each one connects.
 
-[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-harness/deepseek-harness)
+[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-ai/deepseek-harness-sdk)
diff --git a/docs/cordis-tutorial/index.zh.md b/docs/cordis-tutorial/index.zh.md
index 0b7684a953..f6989521d4 100644
--- a/docs/cordis-tutorial/index.zh.md
+++ b/docs/cordis-tutorial/index.zh.md
@@ -13,7 +13,7 @@ Cordis 是 DeepSeek Harness SDK 底层的插件框架：它是一个小型运行
 你需要克隆本仓库并安装依赖，具体前置条件见[快速入门](../user/guide/quickstart.md)。本教程不需要 API 密钥；所有示例均可在无密钥环境中运行。
 
 ```sh
-git clone https://github.com/deepseek-harness/deepseek-harness.git
+git clone https://github.com/deepseek-ai/deepseek-harness-sdk.git
 cd deepseek-harness
 pnpm install
 ```
@@ -55,4 +55,4 @@ node --import tsx ../../vendor/cordis/bin.js
 
 第 5 章还会使用 `interface` 描述配置对象的字段，并使用 `Schema<Config>` 这类泛型表示 schema 所校验的对象形状。你可以直接照写这些声明；周围的正文会解释每项声明连接了什么。
 
-[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-harness/deepseek-harness)
+[![](https://img.shields.io/badge/powered_by-dsh-4D6BFE?style=flat-square&logo=deepseek&logoColor=white)](https://github.com/deepseek-ai/deepseek-harness-sdk)
diff --git a/docs/core-data-structures/core.i18n.yaml b/docs/core-data-structures/core.i18n.yaml
index 461d1ef4fc..e79d5dac2f 100644
--- a/docs/core-data-structures/core.i18n.yaml
+++ b/docs/core-data-structures/core.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write docs/core-data-structures/core.md
-core.md: f7cf288715a3aec2f7037f12fc983e3172a77cef
-core.zh.md: c17fd1335503c95e7f7f6f96cc286f567a8384e6
+core.md: dbd584f10b3daf873bc14210472efb6cd315717e
+core.zh.md: 1fe1616a0c96abb4e8b91417cc4eae292416e42a
diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md
index f7cf288715..dbd584f10b 100644
--- a/docs/core-data-structures/core.md
+++ b/docs/core-data-structures/core.md
@@ -530,8 +530,6 @@ The loop builds each request from logged state. `EpochHeader` records call confi
 
 On the wire, a loop-built request reads the `system` slot (the rendered prompt assembly) followed by the derived history — the boundary snapshot, whose tail is the newest `user/message` on a turn's first step and the previous step's tool results on later steps. The dev invariant recomputes exactly this equation against every loop-built request.
 
-FIXME(call-config-shape): revisit which remaining fields are genuinely epoch-level for cache purposes (`model` and the model-owned reasoning effort are explicit; the sampling scalars sit here out of caution).
-
 ```ts type-equiv
 /**
  * Provider, model, reasoning effort, and sampling scalars of one conversation's
diff --git a/docs/core-data-structures/core.zh.md b/docs/core-data-structures/core.zh.md
index c17fd13355..1fe1616a0c 100644
--- a/docs/core-data-structures/core.zh.md
+++ b/docs/core-data-structures/core.zh.md
@@ -536,8 +536,6 @@ interface ToolSchema {
 
 在协议格式上，循环构建的请求先读取 `system` 槽位（渲染后的提示词组装），再读取派生历史——边界快照，其尾部在轮次首步是最新的 `user/message`，在后续步骤是上一步的工具结果。开发不变式针对每个循环构建的请求精确重算此等式。
 
-FIXME(call-config-shape)：重新审视其余哪些字段出于缓存目的确实属于 epoch 层级（`model` 和模型持有的推理强度已明确属于；采样标量目前出于谨慎保留在此）。
-
 ```ts type-equiv
 /**
  * Provider, model, reasoning effort, and sampling scalars of one conversation's
diff --git a/docs/glossary.i18n.yaml b/docs/glossary.i18n.yaml
index 5c6f7d4630..2dfe08c2fd 100644
--- a/docs/glossary.i18n.yaml
+++ b/docs/glossary.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write docs/glossary.md
-glossary.md: 0270a2d0dba558483e8e458a932a27b0151f2c93
-glossary.zh.md: c3584731cc08b23cf7f47c09620a77b7bff65689
+glossary.md: 16409517bff623a80d6e1e00888d95f63b42f780
+glossary.zh.md: fe3138ac81f2681d7fc69cc2aede96edeb7ec176
diff --git a/docs/glossary.md b/docs/glossary.md
index 0270a2d0db..16409517bf 100644
--- a/docs/glossary.md
+++ b/docs/glossary.md
@@ -4,8 +4,6 @@ English | [中文](glossary.zh.md)
 
 Domain vocabulary for the DeepSeek Harness SDK uses one canonical term per concept. Terms link to their entries with standard Markdown anchors; implementation detail stays in package READMEs and Agent Notes.
 
-FIXME(glossary-completeness): Expand this glossary before the first release so it covers the SDK's other core and capability subsystems, not only agent scope.
-
 ## agent-scope
 
 - **scope** — the unit of per-agent registration: a contribution (tool, prompt section, variable, restriction, listener) is either *global* (visible to every agent) or *scoped* (owned by exactly one [scope key](#scope-key)). Two levels, flat: scoped registrations do not inherit down to subagents; subtree behavior is expressed with [lineage](#lineage) data, never scope structure.
diff --git a/docs/glossary.zh.md b/docs/glossary.zh.md
index c3584731cc..fe3138ac81 100644
--- a/docs/glossary.zh.md
+++ b/docs/glossary.zh.md
@@ -4,8 +4,6 @@
 
 DeepSeek Harness SDK 的领域词汇为每个概念规定一个规范术语。各术语通过标准 Markdown 锚点链接到相应条目；实现细节留在各包的 README 与 Agent Note 中。
 
-FIXME(glossary-completeness): 首次发布前扩充本术语表，使其覆盖 SDK 的其他核心与能力子系统，而非仅限于 agent scope。
-
 ## agent-scope
 
 - **scope**：按 agent（智能体）划分的注册单位。一项贡献（工具、提示词片段、变量、限制、监听器）要么是*全局的*（对所有 agent 可见），要么是*带作用域的*（归属于恰好一个 [scope key](#scope-key)）。只有两层，采用扁平结构：带作用域的注册不会向下继承给 subagent；子树行为通过 [lineage](#lineage) 数据表达，从不通过 scope 结构。
diff --git a/docs/user/guide/quickstart.i18n.yaml b/docs/user/guide/quickstart.i18n.yaml
index 27592cdb74..aefb76991f 100644
--- a/docs/user/guide/quickstart.i18n.yaml
+++ b/docs/user/guide/quickstart.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write docs/user/guide/quickstart.md
-quickstart.md: 72cc5a52c33faf81098f747799692b384fcd5f1a
-quickstart.zh.md: ebb831c1e1bec02117c78a4c2426a84af3bb9478
+quickstart.md: 8b84017ad33bf02579891bc4dcf83eaf7ec39022
+quickstart.zh.md: dfb24f8fa194866908406c709d059bf1f6595d59
diff --git a/docs/user/guide/quickstart.md b/docs/user/guide/quickstart.md
index 72cc5a52c3..8b84017ad3 100644
--- a/docs/user/guide/quickstart.md
+++ b/docs/user/guide/quickstart.md
@@ -19,7 +19,7 @@ pnpm -v
 ## Step 1: install and configure the API key
 
 ```sh
-git clone https://github.com/deepseek-harness/deepseek-harness.git
+git clone https://github.com/deepseek-ai/deepseek-harness-sdk.git
 cd deepseek-harness
 pnpm install
 ```
diff --git a/docs/user/guide/quickstart.zh.md b/docs/user/guide/quickstart.zh.md
index ebb831c1e1..dfb24f8fa1 100644
--- a/docs/user/guide/quickstart.zh.md
+++ b/docs/user/guide/quickstart.zh.md
@@ -19,7 +19,7 @@ pnpm -v
 ## 第一步：安装并配置 API key
 
 ```sh
-git clone https://github.com/deepseek-harness/deepseek-harness.git
+git clone https://github.com/deepseek-ai/deepseek-harness-sdk.git
 cd deepseek-harness
 pnpm install
 ```
diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts
index bf4f7ac972..386926e51b 100644
--- a/examples/acp-agent/tests/acp.snapshot.ts
+++ b/examples/acp-agent/tests/acp.snapshot.ts
@@ -90,8 +90,8 @@ async function prepareFsSearchWorkspace(cwd: string): Promise<void> {
   }
 }
 
-// FIXME: Migrate backend-oriented scenarios to the headless stream-json suite;
-// this ACP suite should eventually retain only automation-protocol contracts.
+// TODO(acp-snapshot-ownership): Move backend/product scenarios to headless while
+// retaining ACP protocol contracts here.
 
 function fixtureRecords(name: string): unknown[] {
   return readFileSync(join(SNAPSHOTS_DIR, name, 'session.jsonl'), 'utf8')
diff --git a/examples/mcp-memory/README.i18n.yaml b/examples/mcp-memory/README.i18n.yaml
index f89035cfcc..7e8e5248e4 100644
--- a/examples/mcp-memory/README.i18n.yaml
+++ b/examples/mcp-memory/README.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write examples/mcp-memory/README.md
-README.md: 023e6aefce0e78cbbf52620426376e1dd0a6b8cf
-README.zh.md: 44ace680cd583f41903437a69c62e30817308ba2
+README.md: 792bb31b668b427c8734286878a9ec98071190d8
+README.zh.md: 51020f5288c4fbd245914280b8e7e4772e8cad69
diff --git a/examples/mcp-memory/README.md b/examples/mcp-memory/README.md
index 023e6aefce..792bb31b66 100644
--- a/examples/mcp-memory/README.md
+++ b/examples/mcp-memory/README.md
@@ -36,7 +36,7 @@ Without a repository checkout, download the selected overlay directly:
 mkdir -p "${DSH_HOME:-$HOME/.dsh}"
 curl --fail --location \
   --output "${DSH_HOME:-$HOME/.dsh}/memory.cordis.yml" \
-  https://raw.githubusercontent.com/deepseek-harness/deepseek-harness/master/examples/mcp-memory/memorix.cordis.yml
+  https://raw.githubusercontent.com/deepseek-ai/deepseek-harness-sdk/master/examples/mcp-memory/memorix.cordis.yml
 dsh web --patch "${DSH_HOME:-$HOME/.dsh}/memory.cordis.yml"
 ```
 
diff --git a/examples/mcp-memory/README.zh.md b/examples/mcp-memory/README.zh.md
index 44ace680cd..51020f5288 100644
--- a/examples/mcp-memory/README.zh.md
+++ b/examples/mcp-memory/README.zh.md
@@ -36,7 +36,7 @@ dsh web --patch "$PWD/examples/mcp-memory/memorix.cordis.yml"
 mkdir -p "${DSH_HOME:-$HOME/.dsh}"
 curl --fail --location \
   --output "${DSH_HOME:-$HOME/.dsh}/memory.cordis.yml" \
-  https://raw.githubusercontent.com/deepseek-harness/deepseek-harness/master/examples/mcp-memory/memorix.cordis.yml
+  https://raw.githubusercontent.com/deepseek-ai/deepseek-harness-sdk/master/examples/mcp-memory/memorix.cordis.yml
 dsh web --patch "${DSH_HOME:-$HOME/.dsh}/memory.cordis.yml"
 ```
 
diff --git a/package.json b/package.json
index def6e5bdcb..981ce68707 100644
--- a/package.json
+++ b/package.json
@@ -59,6 +59,7 @@
     "doc-typecheck": "tsx scripts/doc-typecheck.ts",
     "verify-md-wrap": "tsx scripts/verify-md-wrap.ts",
     "verify-md-links": "tsx scripts/verify-md-links.ts",
+    "verify-public-repository-links": "tsx scripts/verify-public-repository-links.ts",
     "verify-doc-refs": "tsx scripts/verify-doc-refs.ts",
     "verify-package-paths": "tsx scripts/verify-package-paths.ts",
     "verify-config-source-ownership": "tsx scripts/verify-config-source-ownership.ts",
diff --git a/packages/client/runtime/src/client/slots.ts b/packages/client/runtime/src/client/slots.ts
index 3698f62aab..9da8755b2d 100644
--- a/packages/client/runtime/src/client/slots.ts
+++ b/packages/client/runtime/src/client/slots.ts
@@ -19,7 +19,7 @@ import type { Context } from 'cordis'
 import { SlotCore } from '@deepseek-ai/dsh-client-ui-slots'
 import type {
   LocaleFace, OwnerOf, SlotEntryDef, SlotMap, SlotRenderer, SlotRendererHost,
-  SlotScope, SlotSpec, StoreDecl, StoredEntry, StoreInstanceLike,
+  SlotScope, SlotSpec, StoreDecl, StoreFactory, StoredEntry, StoreInstanceLike,
 } from '@deepseek-ai/dsh-client-ui-slots'
 
 declare module '@deepseek-ai/dsh-client-ui-slots' {
@@ -35,16 +35,11 @@ export interface RootOwnerProps { children?: never }
 /** Instance key for root-scoped store records (session records key by session id, so the literal cannot collide). */
 const ROOT_INSTANCE_KEY = 'root'
 
-// FIXME(slot-parity): the engine's arbitrated persist extensions — create()
-// takes the scope key (per-session localStorage suffix) and instances expose
-// clearPersisted() — are not yet on ui-slots' StoreHandle/StoreInstanceLike;
-// these local structural faces bridge until fw-slots lifts them.
+/** Canonical type-erased store handle used by the runtime lifecycle map. */
+type EngineStoreHandle = Exclude<StoreDecl, StoreFactory>
 
-/** Store handle face as the engine actually ships it (scope-key-aware create). */
-interface EngineStoreHandle { create(scopeKey?: string): EngineStoreInstance }
-
-/** Engine instance face: the host-contract shape plus persisted-state cleanup. */
-interface EngineStoreInstance extends StoreInstanceLike { clearPersisted(): void }
+/** Canonical engine instance derived from the handle's create contract. */
+type EngineStoreInstance = ReturnType<EngineStoreHandle['create']>
 
 /** Store axis record: one per live handle, dropped when the last holding entry unloads. */
 interface StoreAxisRecord {
diff --git a/packages/cordis/tool-cordis/README.i18n.yaml b/packages/cordis/tool-cordis/README.i18n.yaml
index 0a55bfc7f6..fd2b5443ef 100644
--- a/packages/cordis/tool-cordis/README.i18n.yaml
+++ b/packages/cordis/tool-cordis/README.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write packages/cordis/tool-cordis/README.md
-README.md: eda135d93e2912bbb4e111af40d176409b383b5b
-README.zh.md: 773d4100f1be6c54f491838b65205b85ec61cdbc
+README.md: 9986310160c2b56126155a4c3ef84d66018d31c2
+README.zh.md: d955306e1e5d4154f58c771704782ece44a15c99
diff --git a/packages/cordis/tool-cordis/README.md b/packages/cordis/tool-cordis/README.md
index eda135d93e..9986310160 100644
--- a/packages/cordis/tool-cordis/README.md
+++ b/packages/cordis/tool-cordis/README.md
@@ -85,5 +85,5 @@ Mounting or unmounting a prompt or tool contribution changes later request prefi
 ## Known Limitations and Deferred Work
 
 - **The sandbox is containment for honest code, not a security boundary** — host-realm helpers on the sandbox global are reachable, so mount code can reach Node; load this plugin as deliberately as you would grant a bash tool (see § Trust stance).
-- **The `ctx` façade exposes no `effect()`** — mount code cannot register a bespoke disposer; `on`/`provide`/`tools.register` cover every mount seen so far, and a guarded `effect` waits on a real need (`FIXME(sandbox-effect)`).
+- **The `ctx` façade exposes no `effect()`** — mount code cannot register a bespoke disposer; `on`/`provide`/`tools.register` are the supported cleanup paths.
 - **`vmTimeoutMs` bounds only synchronous evaluation** — an async mount body escapes it; there is no async budget on mount code.
diff --git a/packages/cordis/tool-cordis/README.zh.md b/packages/cordis/tool-cordis/README.zh.md
index 773d4100f1..d955306e1e 100644
--- a/packages/cordis/tool-cordis/README.zh.md
+++ b/packages/cordis/tool-cordis/README.zh.md
@@ -85,5 +85,5 @@ Namespace 插件：命名导出 `name`／`inject`／`Config`／`apply`，无默
 ## 已知限制与暂缓事项
 
 - **沙箱只用于约束诚实代码，并非安全边界**：可以访问沙箱全局变量上的 host realm helper，因此挂载代码可以触达 Node；加载该插件时，应当像授予 bash 工具一样慎重（见 § 信任立场）。
-- **`ctx` façade 不公开 `effect()`**：挂载代码无法注册定制 disposer；`on`／`provide`／`tools.register` 已覆盖目前出现的每项挂载，受保护的 `effect` 会等待真实需求（`FIXME(sandbox-effect)`）。
+- **`ctx` façade 不公开 `effect()`**：挂载代码无法注册定制 disposer；`on`／`provide`／`tools.register` 是受支持的清理路径。
 - **`vmTimeoutMs` 只限制同步求值**：async 挂载主体可逃出该边界；挂载代码没有 async 预算。
diff --git a/packages/cordis/tool-cordis/src/guard.ts b/packages/cordis/tool-cordis/src/guard.ts
index 595dc462e0..22d85936f4 100644
--- a/packages/cordis/tool-cordis/src/guard.ts
+++ b/packages/cordis/tool-cordis/src/guard.ts
@@ -749,7 +749,6 @@ export function isPlugin(value: unknown): value is Plugin {
  * @param plugin - the plugin the mount code returned.
  * @returns an equivalent plugin whose `apply` sees the sandbox context façade.
  */
-// FIXME(sandbox-effect): expose guarded custom effects when a mount needs bespoke cleanup.
 export function guardedPlugin(plugin: Plugin): Plugin {
   if (typeof plugin === 'function') {
     const functionPlugin = plugin as (ctx: Context, config?: unknown) => unknown
diff --git a/packages/hooks/hooks-claude/tests/bridge.spec.ts b/packages/hooks/hooks-claude/tests/bridge.spec.ts
index 1da2771257..244abae423 100644
--- a/packages/hooks/hooks-claude/tests/bridge.spec.ts
+++ b/packages/hooks/hooks-claude/tests/bridge.spec.ts
@@ -225,7 +225,7 @@ describe('hooks-claude bridge — PostToolUse', () => {
     expect(ctxMsg?.type === 'user/message' && ctxMsg.data.content.some(b => b.type === 'text' && b.text.includes('tool was slow'))).toBe(true)
   })
 
-  it('a PreToolUse permissionDecision:ask degrades to ask (the tool is gated, not run)', async () => {
+  it('a PreToolUse permissionDecision:ask fails closed without an approval service', async () => {
     const dir = mkdtempSync(join(tmpdir(), 'dsh-hooks-claude-'))
     dirs.push(dir)
     const s = join(dir, 'ask.sh')
@@ -241,7 +241,7 @@ describe('hooks-claude bridge — PostToolUse', () => {
     agent.followup(createUserMessage({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } }))
     await waitForIdle(ctx, agent)
 
-    // `ask` degrades to deny today (FIXME permissions): the tool does not run and the result is isError.
+    // No approval service is mounted, so `ask` fails closed: the tool does not run and the result is isError.
     expect(ran).toBe(false)
     const result = events(agent).find(e => e.type === 'tool/result')
     expect(result?.type === 'tool/result' && result.data.message.content[0].isError).toBe(true)
diff --git a/packages/llm/llm/README.i18n.yaml b/packages/llm/llm/README.i18n.yaml
index 0ad49faa17..30660e1032 100644
--- a/packages/llm/llm/README.i18n.yaml
+++ b/packages/llm/llm/README.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write packages/llm/llm/README.md
-README.md: d15b2c996d6d47371a3d6c5542eb5c253029dbae
-README.zh.md: d965f15298f09ff9c2a953a69346c4e83136934b
+README.md: ddbc2ea482ca0848fb0ee0813839cf5ff1829bcc
+README.zh.md: 7a3b615d134e27d7c9892d6f411066d89938175b
diff --git a/packages/llm/llm/README.md b/packages/llm/llm/README.md
index d15b2c996d..ddbc2ea482 100644
--- a/packages/llm/llm/README.md
+++ b/packages/llm/llm/README.md
@@ -97,5 +97,5 @@ Pass-through; the registry preserves the assembled request prefix, while the sel
 - **`GenerateOptions` sampling is `temperature`/`maxTokens`/`stop` only** — no `tool_choice`, `top_p`, or penalty fields; the vocabulary grows when a producer lands ([dropped inert knobs](../../../.agents/notes/archived/simplification/2026-07-04-drop-inert-request-knobs.md)).
 - **Producer-gated variants stay out until produced** — `prefill`, per-tool `strict`, block `cache` hints, and the `agent` message-source variant were pruned as producerless ([Agent Note](../../../.agents/notes/archived/simplification/2026-07-04-prune-producerless-vocabulary-variants.md)).
 - **`BlockAssembler` handles core block kinds only** — a plugin-added block type whose stream is never closed by `block-end` makes `blocks()` throw.
-- **`APP_IDENTITY.url` names a repository that does not exist yet** — `FIXME`: creating the public `deepseek-ai/deepseek-harness-sdk` repo gates the first release.
+- **`APP_IDENTITY.url` names a repository that does not exist yet** — the public home must be reachable before release.
 - **`GenerateOptions.sessionId` is a locally-declared brand** — importing dsh-session's `SessionId` would cycle; a future ids-owning package would dissolve the workaround.
diff --git a/packages/llm/llm/README.zh.md b/packages/llm/llm/README.zh.md
index d965f15298..7a3b615d13 100644
--- a/packages/llm/llm/README.zh.md
+++ b/packages/llm/llm/README.zh.md
@@ -97,5 +97,5 @@
 - **`GenerateOptions` 采样只包含 `temperature`／`maxTokens`／`stop`**：没有 `tool_choice`、`top_p` 或 penalty 字段；有产生方落地时词汇才会增长（见 [已删除惰性旋钮](../../../.agents/notes/archived/simplification/2026-07-04-drop-inert-request-knobs.md)）。
 - **受产生方约束的变体在实际产生前不会加入**：`prefill`、每工具 `strict`、块 `cache` 提示与 `agent` 消息源变体因没有产生方而被剪除（见 [Agent Note](../../../.agents/notes/archived/simplification/2026-07-04-prune-producerless-vocabulary-variants.md)）。
 - **`BlockAssembler` 只处理核心块类型**：如果插件添加块类型的流从未由 `block-end` 关闭，`blocks()` 会抛出异常。
-- **`APP_IDENTITY.url` 指向一个尚不存在的仓库**：`FIXME`：创建公开 `deepseek-ai/deepseek-harness-sdk` 仓库是首次发布的前置条件。
+- **`APP_IDENTITY.url` 指向一个尚不存在的仓库**：该公开主页必须在首次发布前可访问。
 - **`GenerateOptions.sessionId` 是本地声明的品牌类型**：导入 dsh-session 的 `SessionId` 会产生循环；未来拥有 id 的包可以消除该权宜之计。
diff --git a/packages/llm/llm/src/attribution.ts b/packages/llm/llm/src/attribution.ts
index cdaea4b96b..79cef011de 100644
--- a/packages/llm/llm/src/attribution.ts
+++ b/packages/llm/llm/src/attribution.ts
@@ -40,8 +40,7 @@ export interface AppIdentity {
 export const APP_IDENTITY: AppIdentity = {
   product: 'deepseek-harness',
   version,
-  // FIXME: create the public deepseek-ai/deepseek-harness-sdk repository this
-  // URL promises before the first release ships attribution pointing at it.
+  // TODO(public-home): Ensure this public source repository exists before release.
   url: 'https://github.com/deepseek-ai/deepseek-harness-sdk',
 }
 
diff --git a/packages/llm/llm/src/call-config.ts b/packages/llm/llm/src/call-config.ts
index 2daa6d1a4c..848654ad3b 100644
--- a/packages/llm/llm/src/call-config.ts
+++ b/packages/llm/llm/src/call-config.ts
@@ -12,6 +12,8 @@ import type { ReasoningEffortId } from './brand.ts'
 /** Process-local identities of request objects assembled by dsh-agent-loop. */
 const AGENT_LOOP_REQUESTS = new WeakSet<GenerateOptions>()
 
+// TODO(call-config-shape): Revisit which fields are epoch-level for cache reuse
+// and where provider-specific request options belong.
 /**
  * Provider, model, reasoning effort, and sampling scalars of one conversation's
  * requests. Every field maps 1:1 onto the same-named `GenerateOptions` field;
diff --git a/packages/sdk/telemetry/README.i18n.yaml b/packages/sdk/telemetry/README.i18n.yaml
index 9baaa2ebff..1604b40bf4 100644
--- a/packages/sdk/telemetry/README.i18n.yaml
+++ b/packages/sdk/telemetry/README.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write packages/sdk/telemetry/README.md
-README.md: 1d33915f36e0af10eedac5f9ab34f2534268a327
-README.zh.md: af54cc2c78cb360d4305eeaf584c8330a0b7efa5
+README.md: c87735a93e7659f2913f4dd325176a8ae40cf29b
+README.zh.md: 24d6e72d988f94cdbc6aa01607edbfc105213267
diff --git a/packages/sdk/telemetry/README.md b/packages/sdk/telemetry/README.md
index 1d33915f36..c87735a93e 100644
--- a/packages/sdk/telemetry/README.md
+++ b/packages/sdk/telemetry/README.md
@@ -14,7 +14,7 @@ Launcher-side telemetry primitives for the dsh-sdk toolchain. This is a plain li
 
 Consent is carried by the telemetry entry in `cordis.yml`, so disabling telemetry is disabling that entry. Telemetry reports by default and is off only when a present telemetry entry is explicitly `disabled`: a missing `cordis.yml` (first `create`), an enabled entry, or a `cordis.yml` with no telemetry entry all report. `DO_NOT_TRACK`/CI always deny. The no-config and absent-entry defaults are configurable on `ConsentResolver`.
 
-The collection endpoint is a fixed constant (`DSH_TELEMETRY_ENDPOINT`); its `.invalid` placeholder must be replaced with the real endpoint before release.
+The collection endpoint is a fixed constant (`DSH_TELEMETRY_ENDPOINT`); its fail-safe `.invalid` placeholder must be replaced with the real endpoint before release.
 
 ## Model Experience
 
diff --git a/packages/sdk/telemetry/README.zh.md b/packages/sdk/telemetry/README.zh.md
index af54cc2c78..24d6e72d98 100644
--- a/packages/sdk/telemetry/README.zh.md
+++ b/packages/sdk/telemetry/README.zh.md
@@ -14,7 +14,7 @@
 
 Consent 由 `cordis.yml` 中的 telemetry 配置项承载，因此禁用 telemetry 就是禁用该配置项。telemetry 默认上报，只有已经存在的 telemetry 配置项被显式设为 `disabled` 时才关闭：缺少 `cordis.yml`（首次 `create`）、配置项已启用，或 `cordis.yml` 中没有 telemetry 配置项时都会上报。`DO_NOT_TRACK`／CI 始终拒绝。无配置与缺少配置项的默认值可以通过 `ConsentResolver` 配置。
 
-收集端点是固定常量（`DSH_TELEMETRY_ENDPOINT`）；发布前必须将其 `.invalid` 占位值替换为真实端点。
+收集端点是固定常量（`DSH_TELEMETRY_ENDPOINT`）；发布前必须将作为安全兜底的 `.invalid` 占位值替换为真实端点。
 
 ## 模型体验
 
diff --git a/packages/sdk/telemetry/src/reporter.ts b/packages/sdk/telemetry/src/reporter.ts
index d41c1db9b7..b7ac75a23f 100644
--- a/packages/sdk/telemetry/src/reporter.ts
+++ b/packages/sdk/telemetry/src/reporter.ts
@@ -16,12 +16,11 @@ import { getOrCreateAnonymousId, type AnonymousId } from './anonymous-id.ts'
 import { SecretRedactor } from './secret-redactor.ts'
 
 /**
- * Placeholder collection endpoint. This is a fixed protocol constant, not a
- * deployment tunable.
- *
- * FIXME(ccyu): replace with the real telemetry endpoint before release. The
- * `.invalid` TLD guarantees delivery fails harmlessly until then.
+ * Fail-safe placeholder collection endpoint. The `.invalid` TLD guarantees
+ * delivery fails harmlessly until a collector is deployed. This is a fixed
+ * protocol constant, not a deployment tunable.
  */
+// TODO(telemetry-endpoint): Replace the placeholder before release.
 export const DSH_TELEMETRY_ENDPOINT = 'https://telemetry.example.invalid/v1/dsh-sdk'
 
 /** Wire-envelope schema version; bump on any incompatible body change. */
diff --git a/scripts/install.sh b/scripts/install.sh
index 5c9d892f73..f290782892 100755
--- a/scripts/install.sh
+++ b/scripts/install.sh
@@ -1,7 +1,7 @@
 #!/bin/sh
 # dsh one-line installer.
 #
-#   curl -fsSL https://raw.githubusercontent.com/deepseek-harness/deepseek-harness/master/scripts/install.sh | sh
+#   curl -fsSL https://raw.githubusercontent.com/deepseek-ai/deepseek-harness-sdk/master/scripts/install.sh | sh
 #
 # It clones the harness under ~/.dsh/source (the master clone at
 # ~/.dsh/source/master), adds a per-install staging worktree at
@@ -47,12 +47,10 @@
 #   DSH_CURRENT      stable symlink to the active worktree (default: $DSH_SOURCE/current)
 #   DSH_BIN_DIR      directory the `dsh` symlink lands in (default: ~/.local/bin)
 #   DSH_HOME         Harness home holding profiles and user patches (default: ~/.dsh)
-# FIXME(install-ts): Move the post-checkout workflow into a tested TypeScript
-# entrypoint; keep this POSIX shell file as the curl/source bootstrap.
 set -eu
 
 DSH_REF=${DSH_REF:-master}
-DSH_REPO=${DSH_REPO:-https://github.com/deepseek-harness/deepseek-harness.git}
+DSH_REPO=${DSH_REPO:-https://github.com/deepseek-ai/deepseek-harness-sdk.git}
 # DSH_SOURCE is the staging-worktree container and the default home of `current`.
 # DSH_MASTER names the main clone: clone mode defaults it inside DSH_SOURCE,
 # while adoption discovers an existing clone anywhere on disk. Remember whether
diff --git a/scripts/project-doc-site.spec.ts b/scripts/project-doc-site.spec.ts
index 6770381526..89e417558c 100644
--- a/scripts/project-doc-site.spec.ts
+++ b/scripts/project-doc-site.spec.ts
@@ -104,7 +104,7 @@ describe('rewriteMarkdown', () => {
       repositoryRef: 'abc123',
     })).toBe(
       '[B](./reference/b.md#part) '
-      + '[source](https://github.com/deepseek-harness/deepseek-harness/blob/abc123/packages/tool.ts#L2) '
+      + '[source](https://github.com/deepseek-ai/deepseek-harness-sdk/blob/abc123/packages/tool.ts#L2) '
       + '[web](https://example.com)\n',
     )
   })
@@ -130,7 +130,7 @@ describe('rewriteMarkdown', () => {
       pages,
       repoRoot: root,
       repositoryRef: 'abc123',
-    })).toBe('![logo](https://raw.githubusercontent.com/deepseek-harness/deepseek-harness/abc123/packages/logo.svg)\n')
+    })).toBe('![logo](https://raw.githubusercontent.com/deepseek-ai/deepseek-harness-sdk/abc123/packages/logo.svg)\n')
   })
 
   it('hands an image to the placer and uses the URL it returns', () => {
@@ -209,7 +209,7 @@ describe('rewriteMarkdown', () => {
       repositoryRef: 'abc123',
     })).toBe(
       '[title](./reference/b.md "b.md") '
-      + '[escaped](https://github.com/deepseek-harness/deepseek-harness/blob/abc123/docs/x(y).md)\n',
+      + '[escaped](https://github.com/deepseek-ai/deepseek-harness-sdk/blob/abc123/docs/x(y).md)\n',
     )
   })
 
diff --git a/scripts/project-doc-site.ts b/scripts/project-doc-site.ts
index 02a64b023a..e3397237a3 100644
--- a/scripts/project-doc-site.ts
+++ b/scripts/project-doc-site.ts
@@ -15,7 +15,7 @@ import { gfm } from 'micromark-extension-gfm'
 import type { Nodes } from 'mdast'
 import { docsPages, type DocsLocale, type DocsPage } from '../website/docs.ts'
 
-const REPOSITORY_URL = 'https://github.com/deepseek-harness/deepseek-harness'
+const REPOSITORY_URL = 'https://github.com/deepseek-ai/deepseek-harness-sdk'
 const root = resolve(import.meta.dirname, '..')
 const generatedRoot = resolve(root, 'website/.generated')
 
@@ -203,7 +203,7 @@ function githubTarget(
   image: boolean,
 ): string {
   const path = repoPath(absPath, repoRoot)
-  if (image) return `https://raw.githubusercontent.com/deepseek-harness/deepseek-harness/${repositoryRef}/${path}${suffix}`
+  if (image) return `https://raw.githubusercontent.com/deepseek-ai/deepseek-harness-sdk/${repositoryRef}/${path}${suffix}`
   const kind = lstatSync(absPath).isDirectory() ? 'tree' : 'blob'
   const lineSuffix = line === undefined ? suffix : `#L${line}`
   return `${REPOSITORY_URL}/${kind}/${repositoryRef}/${path}${lineSuffix}`
diff --git a/scripts/run-gates.spec.ts b/scripts/run-gates.spec.ts
index 84eeeb10bb..6979fb894d 100644
--- a/scripts/run-gates.spec.ts
+++ b/scripts/run-gates.spec.ts
@@ -77,6 +77,12 @@ describe('gate graph validation', () => {
     await expect(runGates(subject, subject.length, execute)).resolves.toHaveLength(subject.length)
   })
 
+  it('keeps the public repository link policy in the documentation gate', () => {
+    const ids = withPnpmEntrypoint(() => gatesForMode('doc-sync').map(subject => subject.id))
+
+    expect(ids).toContain('public-repository-links')
+  })
+
   it.each([
     ['empty', [], /gate graph has no gates/],
     ['duplicate ids', [gate('same'), gate('same')], /duplicate gate id "same"/],
diff --git a/scripts/run-gates.ts b/scripts/run-gates.ts
index 03064cb242..8e6f336e96 100644
--- a/scripts/run-gates.ts
+++ b/scripts/run-gates.ts
@@ -572,6 +572,7 @@ function docSyncLeafGates(options: {
     pnpmScript('scoped-events', 'verify-scoped-events', { label: 'scoped events' }),
     pnpmScript('markdown-wrap', 'verify-md-wrap', { label: 'markdown wrap' }),
     pnpmScript('markdown-links', 'verify-md-links', { label: 'markdown links' }),
+    pnpmScript('public-repository-links', 'verify-public-repository-links', { label: 'public repository links' }),
     pnpmScript('doc-refs', 'verify-doc-refs', { label: 'doc refs' }),
     pnpmScript('package-paths', 'verify-package-paths', { label: 'package paths' }),
     pnpmScript('config-source-ownership', 'verify-config-source-ownership', { label: 'config source ownership' }),
diff --git a/scripts/verify-public-repository-links.spec.ts b/scripts/verify-public-repository-links.spec.ts
new file mode 100644
index 0000000000..615bfa68e2
--- /dev/null
+++ b/scripts/verify-public-repository-links.spec.ts
@@ -0,0 +1,19 @@
+import { describe, expect, it } from 'vitest'
+import { findInternalRepositoryReferences } from './verify-public-repository-links.ts'
+
+describe('public repository link policy', () => {
+  it('rejects internal repository references and accepts the public home', () => {
+    const internalOwner = ['deepseek', 'harness'].join('-')
+    const internalRepository = [internalOwner, internalOwner].join('/')
+    const source = [
+      'https://github.com/deepseek-ai/deepseek-harness-sdk',
+      `https://github.com/${internalRepository}/issues/1`,
+      `${internalOwner}#2`,
+    ].join('\n')
+
+    expect(findInternalRepositoryReferences('subject.md', source)).toEqual([
+      { file: 'subject.md', line: 2 },
+      { file: 'subject.md', line: 3 },
+    ])
+  })
+})
diff --git a/scripts/verify-public-repository-links.ts b/scripts/verify-public-repository-links.ts
new file mode 100644
index 0000000000..a57628e00c
--- /dev/null
+++ b/scripts/verify-public-repository-links.ts
@@ -0,0 +1,68 @@
+/** Reject tracked files that expose the internal repository identity. */
+
+import { execFileSync } from 'node:child_process'
+import { existsSync, lstatSync, readFileSync, readlinkSync } from 'node:fs'
+import { resolve } from 'node:path'
+import { pathToFileURL } from 'node:url'
+
+const root = resolve(import.meta.dirname, '..')
+const internalOwner = ['deepseek', 'harness'].join('-')
+const internalRepository = [internalOwner, internalOwner].join('/')
+const internalIssueShorthand = `${internalOwner}#`
+
+/** One tracked reference to the internal repository. */
+export interface InternalRepositoryReference {
+  /** Repository-relative file path. */
+  file: string
+  /** One-based source line. */
+  line: number
+}
+
+/**
+ * Locate internal-repository references in one text file.
+ * @param file - Repository-relative path used in diagnostics.
+ * @param source - Text to inspect.
+ * @returns every matching source line.
+ */
+export function findInternalRepositoryReferences(file: string, source: string): InternalRepositoryReference[] {
+  const references: InternalRepositoryReference[] = []
+  for (const [index, line] of source.split('\n').entries()) {
+    if (line.includes(internalRepository) || line.includes(internalIssueShorthand)) {
+      references.push({ file, line: index + 1 })
+    }
+  }
+  return references
+}
+
+function trackedFiles(repoRoot: string): string[] {
+  return execFileSync('git', ['ls-files', '-z'], { cwd: repoRoot, encoding: 'utf8' })
+    .split('\0')
+    .filter(file => file !== '')
+}
+
+function scanRepository(repoRoot: string): InternalRepositoryReference[] {
+  const references: InternalRepositoryReference[] = []
+  for (const file of trackedFiles(repoRoot)) {
+    const path = resolve(repoRoot, file)
+    if (!existsSync(path)) continue
+    const stat = lstatSync(path)
+    if (!stat.isFile() && !stat.isSymbolicLink()) continue
+    const source = stat.isSymbolicLink() ? readlinkSync(path) : readFileSync(path, 'utf8')
+    if (source.includes('\0')) continue
+    references.push(...findInternalRepositoryReferences(file, source))
+  }
+  return references
+}
+
+const invokedPath = process.argv[1]
+const isMain = invokedPath !== undefined && import.meta.url === pathToFileURL(resolve(invokedPath)).href
+if (isMain) {
+  const references = scanRepository(root)
+  if (references.length === 0) {
+    console.log('verify-public-repository-links: tracked files expose no internal repository identity.')
+  } else {
+    console.error('verify-public-repository-links: internal repository references found:')
+    for (const reference of references) console.error(`  ${reference.file}:${String(reference.line)}`)
+    process.exitCode = 1
+  }
+}
diff --git a/website/.vitepress/config.ts b/website/.vitepress/config.ts
index da3892eaa2..4dc1a5774b 100644
--- a/website/.vitepress/config.ts
+++ b/website/.vitepress/config.ts
@@ -94,14 +94,14 @@ const sharedTheme: Pick<DefaultTheme.Config, 'search' | 'socialLinks' | 'editLin
     },
   },
   socialLinks: [
-    { icon: 'github', link: 'https://github.com/deepseek-harness/deepseek-harness' },
+    { icon: 'github', link: 'https://github.com/deepseek-ai/deepseek-harness-sdk' },
   ],
   editLink: {
     pattern: ({ frontmatter }: PageData) => {
       const data: unknown = frontmatter
       const editSource: unknown = typeof data === 'object' && data !== null ? Reflect.get(data, 'editSource') : undefined
       if (typeof editSource !== 'string') throw new Error('Projected documentation page has no editSource frontmatter.')
-      return `https://github.com/deepseek-harness/deepseek-harness/edit/master/${editSource}`
+      return `https://github.com/deepseek-ai/deepseek-harness-sdk/edit/master/${editSource}`
     },
     text: '在 GitHub 上编辑此页',
   },
@@ -161,7 +161,7 @@ export default withMermaid({
             const data: unknown = frontmatter
             const editSource: unknown = typeof data === 'object' && data !== null ? Reflect.get(data, 'editSource') : undefined
             if (typeof editSource !== 'string') throw new Error('Projected documentation page has no editSource frontmatter.')
-            return `https://github.com/deepseek-harness/deepseek-harness/edit/master/${editSource}`
+            return `https://github.com/deepseek-ai/deepseek-harness-sdk/edit/master/${editSource}`
           },
           text: 'Edit this page on GitHub',
         },