Merge branch 'master' into codex/agent-session-jsonl-location

.agents/skills/dsh-translate-docs/SKILL.md

@@ -14,7 +14,7 @@ These are authoritative; read them at the source so this skill never drifts out
 - **[docs/i18n/README.md](../../../docs/i18n/README.md)** — the pairing contract: the three-file pair (`foo.md`, `foo.zh.md`, `foo.i18n.yaml`), the consistency record's both-side blob hashes, the language-switcher lines, scope/exclusions, and the rollout manifest.
 - **[docs/i18n/translation-rules.md](../../../docs/i18n/translation-rules.md)** — how to translate: faithfulness, structure preservation, terminology discipline, typography (MUST/SHOULD levels).
 - **[docs/i18n/terminology.md](../../../docs/i18n/terminology.md)** — the terminology table, binding in both directions. Load it BEFORE translating, not when a term feels uncertain; the terms you don't notice are the ones that drift.
-- **[docs/i18n/translation-prompt.md](../../../docs/i18n/translation-prompt.md)** — the automated pipeline's machine-consumed template. Agents using this skill do not render it; keep rules shared with this skill synchronized.
+- **[docs/i18n/translation-prompt.md](../../../docs/i18n/translation-prompt.md)** — the automated pipeline's machine-consumed template. Agents using this skill do not render it; the renderer injects `translation-rules.md` so rules have only one home.
 - **[dsh-prose-standard](../dsh-prose-standard/SKILL.md)** — required prose coverage and editorial judgment. Apply it to both sides without adding or dropping source propositions.
 
 ## Find the work
@@ -42,8 +42,9 @@ Do not process every file the same way:
 - **Pass 1 — write, don't transpose.** Read a semantic unit, then restate it as a native technical author in the nearest [style sample's](../../../docs/i18n/style-samples.md) register. Preserve the required frame without forcing sentence-by-sentence correspondence.
 - **Pass 2 — verify against the source, clause by clause.** Fidelity is checked here, not written in: confirm nothing was added or dropped, every term follows the table, and each code span survived verbatim. Fix by rewriting the sentence natively, not by patching words into it.
 - Write only the final text to the file, never drafts or notes.
-- Every term in [terminology.md](../../../docs/i18n/terminology.md) renders exactly as specified, in both directions, including first-occurrence annotations. A term the table misses: translate only with a citable precedent from a major Chinese OSS/vendor doc; otherwise keep the English and add it to the PR's 「待定术语」 list with your suggested rendering. Never invent a rendering inline — that decision belongs to a human and then to the table.
+- Every term in [terminology.md](../../../docs/i18n/terminology.md) renders exactly as specified. For a Chinese target, use the Chinese and first-occurrence columns; an unlisted term needs a citable Chinese OSS/vendor precedent or stays English under 「待定术语」. For an English target, use the English column and an established English technical term; preserve an ambiguous source term with a short gloss and list it as pending. Never invent a rendering inline.
 - Code blocks are byte-identical across the pair, comments included. Relative links keep their `.md` targets; only the switcher line links `.zh.md`.
+- The pairing gate checks heading depths, fenced blocks, table row and column counts, list kinds, ordered-list starts, list item counts, and link targets. In Pass 2, manually verify list and table order, noncanonical list numbering, inline code, emphasis, meaning, terminology, and tone.
 
 ## Finish the pair
 
@@ -51,9 +52,9 @@ Do not process every file the same way:
 2. Record consistency: `pnpm run verify-translation-pairing --write` recomputes and records both sides' full blob hashes in `foo.i18n.yaml`. The yaml diff in your PR is the reviewable statement "I confirmed these two say the same thing" — only run it after you actually have.
 3. New batch landed? Add the `.md` paths to `required` in [scripts/translation-pairing.manifest.json](../../../scripts/translation-pairing.manifest.json) so the gate ratchets forward.
 
-## Verify — the gate, not your eyes
+## Verify the mechanical and human halves
 
-Run `pnpm run verify-translation-pairing`, then the rest of the Markdown gates (`pnpm run verify-md-wrap && pnpm run verify-md-links`, or full `pnpm run doc-sync` before the PR). Fix what they report; do not hand-check what they cover. What they can NOT check — whether the two sides truly say the same thing, terminology judgment calls, tone — is exactly what the PR reviewer will read for, so keep the PR reviewable: state which pairs are new vs minimally updated, and list 「待定术语」 prominently.
+Run `pnpm run verify-translation-pairing`, then the rest of the Markdown gates (`pnpm run verify-md-wrap && pnpm run verify-md-links`, or full `pnpm run doc-sync` before the PR). Fix what they report and manually verify the obligations listed in Pass 2 that the gates do not encode. Keep the PR reviewable: state which pairs are new versus minimally updated and list 「待定术语」 prominently.
 
 ## How to respond to translation review
 

.github/workflows/ci.yml

@@ -160,10 +160,9 @@ jobs:
       - name: Run complete keyless Python suite
         run: uv run --python 3.10 --group test --project python/sdk pytest
 
-  # Windows build lane: install + `pnpm run build` (tsc -b + tsdown) on native
-  # Windows. Windows path/shell support is still partial, so this lane covers
-  # the build surface only — tests and gates are not run here yet. Wired into
-  # all-checks-passed so a native-Windows build regression cannot land silently.
+  # Blocking Windows build lane: keep the already-green native build protected
+  # while the broader observational gate matrix below exposes the remaining
+  # portability work without blocking mainline merges.
   windows-build:
     runs-on: windows-2025
     name: windows / build
@@ -183,11 +182,89 @@ jobs:
       - name: Build (tsc -b + tsdown)
         run: pnpm run build
 
+  # Observational, non-blocking Windows static, lint, and artifact lanes. Coverage
+  # and snapshot stay Linux-only until their platform-specific runtime failures
+  # have dedicated support. Run the gates from native PowerShell: an MSYS parent
+  # would change the environment being measured. This job intentionally stays
+  # out of all-checks-passed.needs.
+  windows-gates:
+    continue-on-error: true
+    runs-on: windows-2025
+    name: windows node 24 / ${{ matrix.lane }}
+    env:
+      DSH_GATE_CONCURRENCY: ${{ matrix.gate_concurrency }}
+      DSH_PUBLINT_CONCURRENCY: ${{ matrix.publint_concurrency }}
+      DSH_ESLINT_CACHE: ${{ matrix.eslint_cache }}
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - lane: static
+            command: pnpm run check:ci:static
+            gate_concurrency: '4'
+            publint_concurrency: '8'
+            eslint_cache: ''
+          - lane: lint
+            command: pnpm run check:ci:lint
+            gate_concurrency: '1'
+            publint_concurrency: '8'
+            eslint_cache: '1'
+          - lane: artifacts
+            command: pnpm run check:ci:artifacts
+            gate_concurrency: '3'
+            publint_concurrency: '8'
+            eslint_cache: ''
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Enable Developer Mode (symlink support)
+        shell: pwsh
+        run: >-
+          reg add "HKLM\SOFTWARE\Microsoft\Windows\CurrentVersion\AppModelUnlock"
+          /t REG_DWORD /f /v "AllowDevelopmentWithoutDevLicense" /d "1"
+
+      - uses: actions/setup-node@v6
+        with:
+          node-version: ${{ env.PRIMARY_NODE_VERSION }}
+
+      - name: Enable corepack (pnpm)
+        shell: pwsh
+        run: corepack enable
+
+      - name: Resolve pnpm store path
+        id: pnpm-store
+        shell: pwsh
+        run: '"path=$(pnpm store path --silent)" >> $env:GITHUB_OUTPUT'
+
+      - uses: actions/cache@v4
+        with:
+          path: ${{ steps.pnpm-store.outputs.path }}
+          key: ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-${{ hashFiles('pnpm-lock.yaml') }}
+          restore-keys: |
+            ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-
+
+      - name: Install (immutable)
+        shell: pwsh
+        run: pnpm install --frozen-lockfile
+
+      - uses: actions/cache@v4
+        if: matrix.lane == 'lint'
+        with:
+          path: .cache/eslint
+          key: ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-eslint-${{ hashFiles('pnpm-lock.yaml', 'eslint.config.mjs', 'tsconfig.json', 'packages/*/*/tsconfig.json', 'examples/*/tsconfig.json') }}
+          restore-keys: |
+            ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-eslint-
+
+      - name: Run gates
+        shell: pwsh
+        run: ${{ matrix.command }}
+
   # Single stable required check for branch protection: require "all checks
   # passed" instead of enumerating matrix legs whose names change as lanes and
-  # node versions evolve. Every other job in THIS workflow must be listed in
-  # `needs` (`needs` cannot reach across workflow files; e2e.yml stays its own
-  # check). `if: always()` is load-bearing: without it a failed dependency
+  # node versions evolve. Every blocking job in THIS workflow must be listed in
+  # `needs`; explicitly observational jobs such as windows-gates stay out
+  # (`needs` cannot reach across workflow files; e2e.yml stays its own check).
+  # `if: always()` is load-bearing: without it a failed dependency
   # would SKIP this job, and GitHub counts a skipped required check as passing
   # — so this job always runs and fails on any non-success result, including
   # 'cancelled' and 'skipped'.

README.i18n.yaml

@@ -3,4 +3,4 @@
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write
 README.md: 53dd3896eb15800125673e7c44f7de02daca9376
-README.zh.md: 2119dabf0ae2d2e16e274e44fda7cbbaec146dc9
+README.zh.md: ab826f62658248249ec18c57b35c0065c0f909d1

README.zh.md

@@ -2,7 +2,7 @@
 
 [English](README.md) | 中文
 
-**DeepSeek Harness SDK** 是用于构建 agent harness 的 SDK，采取基于插件的设计。
+**DeepSeek Harness SDK** 是用于构建 agent harness（智能体框架）的 SDK，采取基于插件的设计。
 
 ## 开发
 

docs/development.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
-development.md: 376df72c14b59b8ac8e42b31f19442040d6a47a7
-development.zh.md: 676df50a8a1ab2eff3ec829b5d55904626fa3f5e
+development.md: b3c338f03f548b4de4b676850732731323d611f1
+development.zh.md: 20f5c585dd378a7b0a3bd6b0af8ebf7dc5e0fd3c

docs/development.md

@@ -19,7 +19,7 @@ Install dependencies from the repo root:
 pnpm install
 ```
 
-The install also runs the root `postinstall` script, which installs lefthook from the repo dev dependency through `scripts/install-lefthook.mjs`; the wrapper uses lefthook's reviewed `--force` mode so linked worktrees with an existing `core.hooksPath` do not fail normal `pnpm run …` commands.
+The install also runs the root `postinstall` script, which installs lefthook from the repo dev dependency through `scripts/install-lefthook.mjs`; the wrapper script uses lefthook's reviewed `--force` mode so linked worktrees with an existing `core.hooksPath` do not fail normal `pnpm run …` commands.
 
 If hooks are missing because dependencies were restored from cache or `postinstall` was skipped, install them manually:
 
@@ -59,7 +59,7 @@ DEEPSEEK_BASE_URL=https://... # optional
 lefthook is configured in `lefthook.yml` as an early local checkpoint before review:
 
 - `pre-commit` runs staged-file ESLint fixes, `pnpm run typecheck`, and the vendor manifest guard.
-- `pre-push` runs `pnpm run check:pre-push`, whose scheduler runs unit tests, snapshot tests, build, module-graph freshness, and the member gates of `pnpm run hygiene` and `pnpm run doc-sync` concurrently.
+- `pre-push` runs `pnpm run check:pre-push`, whose scheduler runs runtime-closure verification, unit tests, duplication detection, snapshot tests, build, module-graph freshness, and the member gates of `pnpm run hygiene` and `pnpm run doc-sync` concurrently.
 
 The vendor manifest guard checks that changes under `vendor/*/src` are staged with the matching `vendor/README.md` manifest update. See `vendor/README.md` before editing vendored code.
 

docs/development.zh.md

@@ -9,7 +9,7 @@
 - Node.js 支持 22.19+ 与 24+。CI 覆盖 22.19、24 和 26；见 [Node 引擎下限 RFC](rfc/implemented/process/2026-07-06-node-engine-floor.md)。
 - 启用了 Corepack 的 pnpm。仓库在 `package.json` 中固定使用 `pnpm@11.7.0`；如果 `pnpm --version` 无法通过 Corepack 解析，请先运行 `corepack enable`。
 - Git。
-- 可选：一个 DeepSeek API key，用于 REPL/ACP agent（智能体）演示和真实 API 的 e2e 测试。
+- 可选：一个 DeepSeek API key，用于 REPL/ACP（Agent Client Protocol） agent（智能体）演示和真实 API 的 e2e 测试。
 
 ## 首次搭建
 
@@ -58,8 +58,8 @@ DEEPSEEK_BASE_URL=https://... # optional
 
 lefthook 在 `lefthook.yml` 中配置，作为评审前的本地早期检查点：
 
-- `pre-commit` 运行对暂存文件的 ESLint 修复、`pnpm run typecheck` 和 vendor manifest 守卫；
-- `pre-push` 运行 `pnpm run check:pre-push`，其调度器并发运行单元测试、快照测试、构建、module-graph 新鲜度，以及 `pnpm run hygiene` 与 `pnpm run doc-sync` 的各成员门禁。
+- `pre-commit` 运行对暂存文件的 ESLint 修复、`pnpm run typecheck` 和 vendor manifest（元数据清单）守卫；
+- `pre-push` 运行 `pnpm run check:pre-push`，其调度器并发运行 runtime-closure 校验、单元测试、重复代码检查、快照测试、构建、module-graph 新鲜度，以及 `pnpm run hygiene` 与 `pnpm run doc-sync` 的各成员门禁。
 
 vendor manifest 守卫检查 `vendor/*/src` 下的改动是否连同对应的 `vendor/README.md` manifest 更新一起暂存。请在编辑 vendor 代码前先阅读 `vendor/README.md`。
 

docs/i18n/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
-README.md: 3a5965ab60a7bdb6345b6abe6815f7090fa98fe1
-README.zh.md: 8e62b53ffefa25ad0bbf713889a2ec2ecdb7027a
+README.md: 17bb1eeb67b4f5119a698fca23f12490c9378a7f
+README.zh.md: c957a82bf420a942e2249942a2d9afc54ad950cf

docs/i18n/README.md

@@ -17,16 +17,16 @@ This repo's documentation is read by people and agents both inside and outside t
 
   Blob hashes, not commit hashes, so the record is computable for files edited in the same PR (`git hash-object foo.md`) and consistency is a pure content comparison. The recorded hash also recovers the exact last-confirmed text of either side (`git cat-file -p <hash>`), so an out-of-sync pair is updated by diffing the edited side against its last-confirmed state and patching the counterpart minimally — never by re-translating whole files. After bringing the pair back in line, `pnpm run verify-translation-pairing --write` re-records both hashes; that yaml diff is the reviewable act of confirming consistency.
 - **Language switcher.** Both files link to each other immediately after their H1 heading: the English file carries `English | [中文](foo.zh.md)` and the Chinese file carries `[English](foo.md) | 中文`.
-- **Structure mirrors the counterpart.** Heading depths and order, list kinds, table columns, link targets, and verbatim code blocks match one to one across the pair — see [translation-rules.md](translation-rules.md) for the full preservation rules. Existing Markdown gates apply to `.zh.md` files unchanged (`verify-md-wrap`, `verify-md-links`).
+- **Structure mirrors the counterpart.** Heading depths and order, list kinds, ordered-list starts, list item counts, table row and column counts, link targets, and verbatim code blocks match one to one across the pair — see [translation-rules.md](translation-rules.md) for the full preservation rules. Existing Markdown gates apply to `.zh.md` files unchanged (`verify-md-wrap`, `verify-md-links`).
 
 ## The gate: verify-translation-pairing
 
 `pnpm run verify-translation-pairing` (part of `doc-sync`, so CI and the pre-push hook run it) enforces the contract mechanically:
 
 1. Every file listed as `required` in [scripts/translation-pairing.manifest.json](../../scripts/translation-pairing.manifest.json) has a complete pair.
-2. Every pair that exists at all — required or not — is complete and consistent: all three files present, each side's current blob hash equals the recorded one (editing either side without re-confirming the pair goes red), both sides carry the language switcher, and the structural signatures match in order — heading depths, verbatim code blocks (info string and content), table column counts, list kinds, and every link target apart from the switcher.
+2. Every pair that exists at all — required or not — is complete and consistent: all three files present, each side's current blob hash equals the recorded one (editing either side without re-confirming the pair goes red), both sides carry the language switcher, and the structural signatures match in order — heading depths, verbatim code blocks (info string and content), table row and column counts, list kinds, ordered-list starts, item counts, and every link target apart from the switcher.
 3. Files listed as `excluded` have no `.zh.md` and no `.i18n.yaml` at all.
-4. Every date-named document (`yyyy-mm-dd-*.md`) dated on or after the manifest's `requiredSince` cutoff has a complete pair — new documents merge bilingual from birth.
+4. Every date-named document (`yyyy-mm-dd-*.md`) dated on or after the manifest's `requiredSince` cutoff has a complete pair — new date-named RFCs merge bilingual from birth.
 
 `pnpm run verify-translation-pairing --list` prints the current pairing state of every document in scope — missing, out-of-sync, or ok — and is the work list for translation batches. It never fails; it reports.
 
@@ -49,4 +49,4 @@ The gate's limit, stated plainly: **a green gate means the pair was confirmed co
 
 ## Division of labor
 
-Counterparts here are produced by an agent running [dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md) and reviewed by a human — inference is cheap here, review attention is the scarce resource. The gate exists so that neither the agent nor the reviewer has to remember the contract: pair completeness, consistency, and structure are checked mechanically, and review attention goes to translation quality and terminology, where human judgment is the whole point.
+Counterparts here are produced by an agent running [dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md) and reviewed by a human — inference is cheap here, review attention is the scarce resource. The gate checks pair completeness, recorded hashes, switchers, and its documented structural signature. Review still owns translation quality, terminology, and structural requirements that the signature does not encode. The prompt contract is executable: [scripts/translation-prompt.ts](../../scripts/translation-prompt.ts) renders the canonical rules into either direction and strictly parses the three-field XML response, while `verify-translation-prompt` exercises both render directions, the checked-in example, and the CDATA split rule in `doc-sync`.

docs/i18n/README.zh.md

@@ -2,12 +2,12 @@
 
 [English](README.md) | 中文
 
-本仓库的文档会被公司内外的人和 agent（智能体）阅读，因此 README 与 docs 目录树以英文和简体中文双语维护。本页定义配对契约、强制门禁与推进策略；[translation-rules.md](translation-rules.md) 定义如何翻译；[terminology.md](terminology.md) 是术语真源。进仓的 agent 工作流见 [.agents/skills/dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md)。
+本仓库的文档会被公司内外的人和 agent（智能体）阅读，因此 README 与 docs 目录树以英文和简体中文双语维护。本页定义配对契约、强制门禁与推进策略；[translation-rules.md](translation-rules.md) 定义如何翻译；[terminology.md](terminology.md) 是术语真源。仓库内置的 agent 工作流见 [.agents/skills/dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md)。
 
 ## 配对契约
 
 - **两种语言同权。**一篇文档可以先用任一语言撰写和评审——先写中文的 RFC 与先写英文的一样正当——另一侧由它翻译而来。两个文件谁也不高于谁；约束它们的是二者必须说同样的话。
-- **一对文档是三个同目录文件。**英文 `foo.md`、中文 `foo.zh.md`，加一份一致性记录 `foo.i18n.yaml`，都在同一目录。不用语言目录，不用独立翻译仓库，不用中英混排的单文件。配对整体合入：PR 永远不会只带一种语言而缺其余两个文件。
+- **一对文档是三个同目录文件。**英文 `foo.md`、中文 `foo.zh.md`，加一份一致性记录 `foo.i18n.yaml`，都在同一目录。不用语言目录，不用独立翻译仓库，不用中英混排的单文件。配对整体合入：PR（Pull Request）永远不会只带一种语言而缺其余两个文件。
 - **一致性记录。**`foo.i18n.yaml` 保存两侧文件在上一次被确认「说同样的话」时各自的完整 git blob hash：
 
   ```yaml
@@ -17,15 +17,16 @@
 
   用 blob hash 而不是 commit hash，这样同一个 PR 里改动的文件也能算出记录（`git hash-object foo.md`），一致性是纯内容比较。记录的 hash 还能还原任一侧上次确认时的确切文本（`git cat-file -p <hash>`），所以失去同步的配对是「把被改的一侧与其上次确认状态做 diff、再最小化地修补另一侧」——从不整篇重译。两侧对齐后，`pnpm run verify-translation-pairing --write` 重新记录两个 hash；那份 yaml diff 就是「确认一致」这个动作本身，可以被评审。
 - **语言切换行。**两个文件在各自 H1 标题之后立即互链：英文文件带 `English | [中文](foo.zh.md)`，中文文件带 `[English](foo.md) | 中文`。
-- **结构与另一侧一一对应。**标题深度与顺序、列表类型、表格列、链接目标与逐字节一致的代码块在配对两侧一一对应——完整保持规则见 [translation-rules.md](translation-rules.md)。既有 Markdown 门禁对 `.zh.md` 文件原样生效（`verify-md-wrap`、`verify-md-links`）。
+- **结构与另一侧一一对应。**标题深度与顺序、列表类型、有序列表起始编号、列表项数量、表格行列数、链接目标与逐字节一致的代码块在配对两侧一一对应——完整保持规则见 [translation-rules.md](translation-rules.md)。既有 Markdown 门禁对 `.zh.md` 文件原样生效（`verify-md-wrap`、`verify-md-links`）。
 
 ## 门禁：verify-translation-pairing
 
-`pnpm run verify-translation-pairing`（`doc-sync` 的一环，因此 CI 和 pre-push 钩子都会运行）机械地强制执行这份契约：
+`pnpm run verify-translation-pairing`（`doc-sync`（文档同步门禁）的一环，因此 CI 和 pre-push 钩子都会运行）机械地强制执行这份契约：
 
 1. [scripts/translation-pairing.manifest.json](../../scripts/translation-pairing.manifest.json) 中 `required` 列出的每个文件都有完整配对。
-2. 任何已存在的配对——无论是否 required——都完整且一致：三个文件齐全、每一侧的当前 blob hash 等于记录值（改了任一侧而没重新确认配对就变红）、双方都带语言切换行、结构签名按序一致——标题深度、逐字节一致的代码块（信息字符串与内容）、表格列数、列表类型，以及除切换行之外的每个链接目标。
+2. 任何已存在的配对——无论是否 required——都完整且一致：三个文件齐全、每一侧的当前 blob hash 等于记录值（改了任一侧而没重新确认配对就变红）、双方都带语言切换行、结构签名按序一致——标题深度、逐字节一致的代码块（信息字符串与内容）、表格行列数、列表类型、有序列表起始编号、列表项数量，以及除切换行之外的每个链接目标。
 3. 列为 `excluded` 的文件完全没有 `.zh.md`，也没有 `.i18n.yaml`。
+4. 凡文件名符合 `yyyy-mm-dd-*.md` 且日期不早于 manifest（元数据清单）中 `requiredSince` 分界日期的文档，都必须有完整配对——新建的日期命名 RFC 从创建起便须配齐中英文。
 
 `pnpm run verify-translation-pairing --list` 打印范围内每篇文档的当前配对状态——missing、out-of-sync 或 ok——是翻译批次的工作清单。它从不失败；它只报告。
 
@@ -44,8 +45,8 @@
 - `docs/i18n/terminology.md` 与 [style-samples.md](style-samples.md)——二者本身即为中英对照文档。
 - [translation-prompt.md](translation-prompt.md)——自动翻译流水线的 prompt 模板；正文逐字进入模型请求，配对翻译会改变流水线行为。
 
-**推进**：以日期命名的文档（`yyyy-mm-dd-*.md`，即 RFC），只要标注日期等于或晚于 manifest 的 `requiredSince` 分界日期，合入时就必须配齐双语文件。更早日期的文件属于待翻清单（backlog），包括分界前夜创建的文件。RFC 文件名记录首次提出日期，因此倒填日期绕过分界属于评审可见的违规。manifest 中的 `required` 列表是当前执行红线，并非全量覆盖这一最终目标。翻译批次将路径加入 `required`，使门禁只向前收紧。未列入的文档仍可通过 `--list` 查看，而任何已存在的配对都受完整契约约束。后续修改必须同步更新两侧，因此 `required` 的扩展速度不能超过翻译评审的承载能力。
+**推进**：以日期命名的文档（`yyyy-mm-dd-*.md`，即 RFC），只要标注日期等于或晚于 manifest 的 `requiredSince` 分界日期，合入时就必须配齐双语文件。更早日期的文件属于 backlog（待翻清单），包括分界前夜创建的文件。RFC 文件名记录首次提出日期，因此倒填日期绕过分界属于评审可见的违规。manifest 中的 `required` 列表是当前执行红线，并非全量覆盖这一最终目标。翻译批次将路径加入 `required`，使门禁只向前收紧。未列入的文档仍可通过 `--list` 查看，而任何已存在的配对都受完整契约约束。后续修改必须同步更新两侧，因此 `required` 的扩展速度不能超过翻译评审的承载能力。
 
 ## 分工
 
-这里的对侧译文由运行 [dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md) 的 agent 产出、由人评审——在这里推理（inference）很便宜，评审注意力才是稀缺资源。门禁的存在让 agent 和评审者都不必记住契约：配对完整性、一致性和结构由机械检查兜底，评审注意力投向翻译质量与术语——这正是人的判断的用武之地。
+对侧译文由运行 [dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md) 的 agent 生成，再由人评审：在这里推理（inference）很便宜，评审注意力才是稀缺资源。门禁负责检查配对是否完整、记录的 hash、语言切换行以及本文列出的结构签名；翻译质量、术语和签名未涵盖的结构要求仍由评审把关。prompt 契约也有可执行实现：[scripts/translation-prompt.ts](../../scripts/translation-prompt.ts) 会把权威规则渲染到英译中或中译英的 prompt 中，并严格解析包含三个字段的 XML 响应；`doc-sync` 中的 `verify-translation-prompt` 会检查两个渲染方向、仓库内示例与 CDATA 拆分规则。

docs/i18n/style-samples.md

@@ -1,8 +1,8 @@
 # 翻译语体样例（style samples）
 
-本文件是翻译语体的校准锚点：每组样例是一段英文原文与一段人工定稿的中文译文，覆盖本仓库文档的主要文体。**译文的语体以这些样例为准**——它们的效力高于任何对语气的文字描述。翻译或评审时对照最接近的文体样例；样例与规则冲突时，样例胜出。本文件中英对照、自成双语，不参与配对（见 [README.md](README.md) 排除清单）。
+本文件是翻译语体的校准锚点：每组样例是一段英文原文与一段人工定稿的中文译文，覆盖本仓库文档的主要文体。**译文的语体以这些样例为准**——文体样例的效力高于对语气的文字描述，但术语表、忠实性与结构规则仍然优先。翻译或评审时对照最接近的文体样例。本文件中英对照、自成双语，不参与配对（见 [README.md](README.md) 排除清单）。
 
-维护方式：人工评审校准出新的金标段落后追加到对应文体；样例只增不改，改动需评审人签字（PR 评审即签字）。
+维护方式：人工评审校准出新的金标段落后追加到对应文体；发现语义、结构或术语错误时直接修正。新增或修正样例都需经过 PR 评审。
 
 ## ① 架构叙述
 
@@ -16,7 +16,7 @@
 
 > This document covers **behavior**; type shapes live in [core-data-structures/](../core-data-structures/core.md), the per-event/service reference in the [generated catalog](../cordis-catalog/events.md), per-package contracts in the package READMEs ([map](../../packages/README.md)).
 
-本文档描述整体行为逻辑；类型定义存放于 [core-data-structures/](../core-data-structures/core.md)；各类事件、服务的详细参考见[生成目录](../cordis-catalog/events.md)；各 package 对外约束协议写在对应包的 README（[索引](../../packages/README.md)）。
+本文档描述整体行为逻辑；类型定义存放于 [core-data-structures/](../core-data-structures/core.md)；各类事件、服务的详细参考见[生成目录](../cordis-catalog/events.md)；各包（package）的对外契约写在相应的 README 中（[索引](../../packages/README.md)）。
 
 ## ② 防御模式规则
 
@@ -26,11 +26,11 @@
 
 > **Dispose must reach quiescence, not just request it** — A teardown that issues kills/aborts but returns before the work stops leaves orphans. Make cleanup async and await the children's exit (kill → await `done`), and close listener/notification registries BEFORE killing so late completions stay silent. Tests prove disposal waited (pid gone right after `await fiber.dispose()`), not merely that the process eventually dies.
 
-**销毁操作必须等待所有任务完全停稳，不能仅下发终止指令就返回**——若销毁逻辑仅发送终止、中断信号，但不等任务停止就直接退出，会产生孤儿进程。清理逻辑需设为异步，等待所有子任务彻底退出（先下发终止信号，再等待执行完成）；在执行终止操作前先关闭监听器与通知注册表，让延迟到达的完成事件不再触发任何通知。测试要验证销毁流程确实完成等待：执行完 `await fiber.dispose()` 后进程 PID 立即消失，不能仅校验进程最终会自行消亡。
+**dispose（资源释放）必须等待所有任务完全停稳，不能仅下发终止指令就返回**：如果清理过程只发出终止或中断信号，却不等任务停止就返回，就会留下孤儿进程。清理应采用异步方式，等待所有子任务彻底退出（先发出终止信号，再等待退出）；发出信号前应先关闭监听器与通知注册表，使延迟到达的完成事件不再触发通知。测试要证明 dispose 的确等到清理完成：执行完 `await fiber.dispose()` 后进程 PID 立即消失，不能只检查进程最终会自行消亡。
 
 > **Async state is not synchronous state** — `agent.send()` does not flip status before returning; a background task's completion races turn boundaries; `reader.close()` fires for both EOF and disposal. Never gate control flow on a status you only just requested — drive lifecycle off the events/promises that actually fire (`agent/status`, `task.done`), and observe the transition (saw `running` THEN `idle`) rather than counting actions you assume map 1:1 to turns.
 
-**异步状态不等同于同步瞬时状态**——调用 `agent.send()` 不会在返回前同步更新状态；后台任务完成时机与轮次边界存在竞态；调用 `reader.close()` 既可能是读到文件末尾，也可能是资源销毁触发。切勿仅凭刚查询到的状态来阻断流程；生命周期逻辑应基于真实触发的事件与 promise 驱动（`agent/status`、`task.done`），观测完整状态切换（先 `running`、再 `idle`），而非主观认定操作和执行轮次一一对应（主循环会批量处理排队消息）。
+**异步状态不等同于同步瞬时状态**：调用 `agent.send()` 不会在返回前同步更新状态；后台任务的完成时间与轮次边界存在竞态；`reader.close()` 既会在读到文件末尾时触发，也会在资源释放时触发。切勿把刚刚发起的状态变更当成已经生效，据此控制流程；生命周期逻辑应以实际触发的事件和已完成的 promise（`agent/status`、`task.done`）为准，并观察完整的状态变化（先 `running`，再 `idle`），不要根据操作次数推断操作与轮次一一对应。
 
 ## ③ 测试政策清单
 
@@ -40,15 +40,15 @@
 
 > We are DeepSeek — do not ration real-API tests. A no-key test proves the plumbing; only a with-key run proves the agent works against a real model. Write many: real prompts that write files, multi-turn conversations, tool use, cancellation mid-stream. Cheapest and highest-value are **smoke tests** that boot the real example, send one real prompt, and check the world — they catch the "green unit tests, broken product" class that mocks structurally cannot. The self-skip exists only so secretless CI and keyless contributors aren't blocked; it is not a cost signal.
 
-我们是 DeepSeek：真实接口相关测试不得刻意缩减用例数量。无密钥测试仅能验证底层通路；只有携带有效密钥执行的用例，才能确认 agent 可正常对接真实模型。请大量编写此类测试：包含文件写入类真实提示词、多轮对话、工具调用、流式中途取消等场景。
+我们是 DeepSeek：真实接口相关测试不得刻意缩减用例数量。无密钥测试仅能验证底层通路；只有携带有效密钥执行的用例，才能确认 agent（智能体）可正常对接真实模型。请大量编写此类测试：包含文件写入类真实提示词、多轮对话、工具调用、流式中途取消等场景。
 
-成本最低、收益最高的是**冒烟测试**：拉起完整真实示例，发送一条真实提示并校验整体运行状态。这类用例能捕获一类问题——单元测试全部绿灯，但产品实际运行故障，单靠 mock 完全无法发现这类缺陷。
+成本最低、收益最高的是**冒烟测试**：拉起完整真实示例，发送一条真实提示，并检查文件、进程等外部可观察结果。这类用例能捕获一类问题——单元测试全部绿灯，但产品实际运行故障，单靠 mock 完全无法发现这类缺陷。
 
 自带自动跳过逻辑，仅用于保障无密钥 CI 环境、无权限贡献者不会被流程拦截，不代表可以以此为由削减真实接口测试投入。
 
 > **Prefer the real implementation over a mock** — Mock only the genuinely expensive or non-deterministic boundary (the LLM adapter, the network, the clock); keep everything downstream real. A hand-rolled stand-in proves the bridge moves bytes, not that the shipping tool behaves as asserted — the two drift while the test stays green.
 
-**优先使用真实实现，而非 mock 替身**——仅对开销极大、结果不确定的边界模块做 mock（LLM 适配器、网络、时钟），其余下游组件全部使用真实实现。手写的 mock 替身只能验证数据通路能传输字节，无法保证线上工具符合预期逻辑；长期下来业务逻辑与 mock 实现会出现偏差，但测试仍会显示通过。
+**优先使用真实实现，而非 mock 替身**——仅对开销极大、结果不确定的边界模块做 mock（LLM（大语言模型）适配器、网络、时钟），其余下游组件全部使用真实实现。手写的 mock 替身只能验证数据通路能传输字节，无法保证线上工具符合预期逻辑；长期下来业务逻辑与 mock 实现会出现偏差，但测试仍会显示通过。
 
 ## ④ 机制描述
 
@@ -60,7 +60,7 @@
 
 > The gate's limit, stated plainly: a green gate means the pair was confirmed consistent at these exact contents, not that the confirmation was sound. It checks hashes and shape; it cannot judge whether the two sides actually say the same thing — that is the reviewer's half of the contract. A re-recorded pair with a sloppy counterpart passes the gate; it must not pass review.
 
-明确门禁校验边界：门禁校验通过，仅代表两份文档哈希与结构完全匹配，不代表译文内容准确无误。门禁仅校验哈希与结构，无法判断双语表意是否统一——译文质量把关是评审人的责任。即便译文粗糙、表意偏差，只要哈希匹配，门禁就会放行，但这类 PR 绝不能通过人工评审。
+门禁的边界很明确：通过门禁只说明两侧文件当前的 blob hash 与伴随记录吻合，并且结构签名一致，也就是说，这组内容曾被确认一致；它不代表这次确认可靠。门禁无法判断两种语言是否真正表达了相同的意思；这部分契约要由评审人把关。即使译文粗糙、表意有误，重新记录配对后仍能通过门禁，但绝不能通过人工评审。
 
 ## ⑥ RFC 论证
 
@@ -70,9 +70,9 @@
 
 ## ⑦ 推进策略（长段拆分示范）
 
-> **Rollout**: new documents don't wait for a batch — a date-named document dated on or after the manifest's `requiredSince` cutoff must merge with its pair, so everything new is bilingual from birth. For the back-catalog, the `required` list in the manifest is the enforcement frontier, not the goal. […] Pairing a document is a commitment: every later edit to either side must carry the counterpart along, so grow the frontier at the pace translation review is actually resourced, not ahead of it.
+> **Rollout**: date-named RFCs don't wait for a batch — one dated on or after the manifest's `requiredSince` cutoff must merge with its pair, so each new date-named RFC is bilingual from birth. For the back-catalog, the `required` list in the manifest is the enforcement frontier, not the goal. […] Pairing a document is a commitment: every later edit to either side must carry the counterpart along, so grow the frontier at the pace translation review is actually resourced, not ahead of it.
 
-**推进**：新增文档不再走批量分批翻译流程。以日期命名的文档，若其标注日期等于或晚于 manifest 里 `requiredSince` 分界时间，提交合入时必须配套对应的双语译文文件——所有新文档从创建起就要求中英双语齐备。针对存量旧文档：manifest 内的强制翻译列表只是当下执行红线，并非最终目标。（……）文档完成双语配对等同于一份长期约束承诺：后续只要修改任一版本，就必须同步更新对应另一语种文件。因此强制翻译范围的推进节奏，要匹配翻译评审实际可投入人力，切勿超前铺开。
+**推进**：日期命名的 RFC 无需等待批量翻译。只要文件名中的日期不早于 manifest（元数据清单）的 `requiredSince` 分界日期，合入时就必须配齐中英文，因此此类 RFC 从创建起就要求双语齐备。对于存量文档，manifest 中的 `required` 列表只是当前的执行红线，并非最终目标。（……）一旦文档完成配对，后续修改任一侧都必须同步更新另一侧。因此，应根据实际可投入的翻译评审能力逐步扩展执行红线，不能超前。
 
 ## 从样例提炼的要点
 

docs/i18n/terminology.md

@@ -33,7 +33,7 @@
 | English | 中文 | 首次出现 | 不要译作 | 备注 |
 |---|---|---|---|---|
 | agent | agent | agent（智能体） | | |
-| agent harness | agent harness | | | agent 组合词（agent harness/workflow/loop/skill 等）整体保留英文；未括注过 agent 时首现按 agent 行处理 |
+| agent harness | agent harness | agent harness（智能体框架） | | agent 组合词（agent harness/workflow/loop/skill 等）整体保留英文；未括注过 agent 时首现按对应组合词或 agent 行处理 |
 | agent loop | agent loop | agent loop（智能体循环） | | |
 | backlog | backlog | backlog（待翻清单） | | 仅在双语翻译语境里括注`待翻清单` |
 | blob hash | blob hash | | | `git hash-object` 的结果 |
@@ -76,6 +76,7 @@
 | backend | 后端 | | | |
 | background task | 后台任务 | | | |
 | block | 块 | | | |
+| build target | 构建目标 | | | |
 | cancel | 取消 | | | |
 | capability | 能力 | | | |
 | checkpoint | 检查点 | | | |
@@ -104,7 +105,7 @@
 | extension point | 扩展点 | | | 注意与 `seam` 区分 |
 | fail-fast | 快速失败 | | | |
 | fenced code block | 围栏代码块 | | | 沿用 MDN 中文翻译 |
-| fingerprint | 指纹 | | | i18n 配对机制用语：`.zh.md` 首行记录英文源 blob hash 的注释 |
+| fingerprint | 指纹 | | | 通用内容指纹；双语配对机制使用 sidecar record 记录两侧 blob hash |
 | finish reason | 结束原因 | | | |
 | foreground run | 前台运行 | | | |
 | freshness | 新鲜度 | | | 沿用 MDN 中文翻译；在本项目中指译文相对源文的同步状态 |
@@ -171,3 +172,5 @@
 | vocabulary | 词汇 | | | |
 | wire format | 协议格式 | 协议格式（wire format） | | |
 | workflow | 工作流 | | | |
+| wrapper | 包装层 | | | 软件层或 SDK 包装层 |
+| wrapper script | 包装脚本 | | | 可执行脚本包装层 |

docs/i18n/translation-prompt.md

@@ -1,24 +1,27 @@
 # Translation prompt (pipeline asset)
 
-本文件是自动翻译流水线的 prompt 模板；自 `# Translation Prompt` 起的正文逐字进入模型请求，因此不参与双语配对（见 [README.md](README.md) 排除清单）。渲染时，[terminology.md](terminology.md) 整表填入 `{{terminology}}`。[style-samples.md](style-samples.md) 定义文体，模板内嵌的 Examples 仅抽样问题类型；两者冲突时以文体样例为准。修改本文件即修改翻译行为，需按正常 PR 评审。
+本文件是自动翻译流水线使用的 prompt 模板；从 `# Translation Prompt` 开始的正文会逐字进入模型请求，因此本文件不参与双语配对（见 [README.md](README.md) 排除清单）。渲染时会把 [translation-rules.md](translation-rules.md) 全文填入 `{{translation_rules}}`，把 [terminology.md](terminology.md) 整表填入 `{{terminology}}`，以免模板另存一份规则而日后失去同步。[style-samples.md](style-samples.md) 定义文体，模板中的 Examples 只用于说明典型问题；术语表、忠实性和结构规则优先于样例，样例只在这些硬性约束内决定文体。修改本文件会改变翻译行为，需正常经过 PR 评审。
 
 ## 占位符契约
 
-流水线渲染模板时替换以下占位符，除此之外不做任何文本处理：
+流水线渲染模板时替换以下占位符，除此之外不改写系统消息：
 
 | 占位符 | 填入内容 | 来源 |
 |---|---|---|
 | `{{source_lang}}` | 源语言名（`English` / `Chinese`） | 由改动侧文件推断：`.zh.md` 被改则为 `Chinese` |
 | `{{target_lang}}` | 目标语言名（`Chinese` / `English`） | 与 `{{source_lang}}` 相对 |
+| `{{translation_rules}}` | [translation-rules.md](translation-rules.md) 全文（Markdown 原文） | 渲染时读取仓库当前版本，不缓存 |
 | `{{terminology}}` | [terminology.md](terminology.md) 的完整表格（Markdown 原文） | 渲染时读取仓库当前版本，不缓存 |
-| `{{source_filename}}` | 源文档的 basename（如 `foo.md`） | 由流水线从待译文件路径取得 |
-| `{{source_filename_zh}}` | 中文侧 basename（如 `foo.zh.md`） | 由 `{{source_filename}}` 派生 |
+| `{{source_filename}}` | 源文档的 basename（如 `foo.md` 或 `foo.zh.md`） | 由流水线从待译文件路径取得 |
+| `{{source_filename_zh}}` | 中文侧 basename（如 `foo.zh.md`） | 英文源追加 `.zh`；中文源使用自身 basename |
 
-流水线仅支持上表占位符，并按整篇文档翻译。它不支持 `{{to}}`、`{{title_prompt}}`、`{{summary_prompt}}`、`{{terms_prompt}}`、`{{imt_style_guide}}` 或 `%%` 分段协议；输出采用下方三段 XML。
+例如，英译中时若源文件是 `foo.md`，`{{source_filename}}` 填 `foo.md`，`{{source_filename_zh}}` 填 `foo.zh.md`；中译英时若源文件是 `foo.zh.md`，两个占位符都填 `foo.zh.md`。
+
+流水线只识别上表中的占位符，并且一次翻译整篇文档。它不支持 `{{to}}`、`{{title_prompt}}`、`{{summary_prompt}}`、`{{terms_prompt}}`、`{{imt_style_guide}}` 或 `%%` 分段协议。输出必须是一个以 `<dsh-translation-response>` 为根元素的 XML 文档；三个子元素中的 Markdown 内容都放在 CDATA 中。内容出现 `]]>` 时写成 `]]]]><![CDATA[>`，XML 解析后仍会还原为原文。
 
 ## Few-shot 金标
 
-流水线的 few-shot 是**整文档级**的中英对照，不是模板内嵌的句子级正误例（那是最小抽样）。few-shot 集取自以下 5 组人工定稿的配对文档，以仓库当前版本为准、随仓库更新：
+流水线使用**整篇文档**的中英对照作为 few-shot，不是模板内嵌的句子级正误例。以下 5 组配对文档均经过人工评审，并以仓库当前版本为准，随仓库一同更新：
 
 - `README.md` ↔ `README.zh.md`
 - `docs/development.md` ↔ `docs/development.zh.md`
@@ -26,136 +29,58 @@
 - `docs/i18n/translation-rules.md` ↔ `docs/i18n/translation-rules.zh.md`
 - `docs/rfc/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.md` ↔ 对应 `.zh.md`
 
-注入方式：在系统消息（本模板）之后、待译文档之前，每组作为一轮示例对话——user 消息为源文档全文，assistant 消息为定稿译文全文（不带三段 XML 包装；只有真实请求要求三段输出）。上下文紧张时按上列顺序从后往前裁剪组数。这 5 组也是评审校准锚点（见 [style-samples.md](style-samples.md)），改动任何一组即改变流水线行为。
+注入时按当前翻译方向选择每组的源侧与目标侧：user 消息包含源文档全文，assistant 消息采用模板正文规定的 XML 协议；`translation` 与 `final` 都放入目标文档全文，`review` 填 `- [None] No corrections.`。CDATA 遵循上文的 `]]>` 拆分规则。上下文不足时，按上列顺序从后往前删减示例组数。这 5 组也是评审校准锚点；改动任何一组都会改变流水线行为。
 
 ## 模板正文
 
 ````text
 # Translation Prompt
 
-You are a senior technical translator specializing in LLM and agent development documentation. Your task is to translate the given source document from {{source_lang}} to {{target_lang}}, producing natural, professional technical prose.
-
-## Quality Requirements
-
-### Structure and Format Preservation
-- Output a complete translated document that maintains exactly the same structure as the source: heading hierarchy, list shape, table columns, link targets, and code blocks.
-- Fenced code blocks must be byte-identical to the source, including ALL comments inside them. Do NOT translate comments inside code blocks. This is a hard rule with no exceptions.
-- Inline code spans (commands, flags, paths, API names, version numbers) must be kept verbatim. Never translate or reformat them.
-- Every relative link must point to the same target as in the source. Link text is translated; link targets are not.
-- Language switcher line: the source document's filename is `{{source_filename}}`. When translating into Chinese, write `[English]({{source_filename}}) | 中文` immediately after the H1 heading. When translating into English, write `English | [中文]({{source_filename_zh}})` immediately after the H1. Emit this line even when the source file has no switcher yet (a brand-new pair); when the source does have one, flip the link direction — never copy it unchanged.
-- After a closing bold marker `**`, insert a space before the next character when that character is a Latin letter or digit. Never insert a space before full-width (Chinese) punctuation.
-
-### Tone and Style
-- The translation must read as if originally written in the target language by a native speaker. If an expression sounds like a word-for-word rendering from the source language, rephrase it.
-- Write in a professional, formal tone appropriate for developer documentation. Never use colloquial or casual expressions.
-- Use polite imperative forms where the text instructs the reader to do something.
-- Keep the author's register: concise stays concise, detailed stays detailed.
-
-### Sentence Structure
-- Break long sentences with commas or semicolons. Avoid run-on sentences.
-- Prefer active voice. Convert passive constructions to active if it reads more naturally.
-- Translate meaning, not words. Restructure sentences where the target language grammar requires it.
-- Do not invent words or expressions that do not exist in natural technical writing of the target language.
-
-### Word Choice
-- Prefer precise, formal vocabulary over casual or colloquial alternatives.
-- When multiple synonyms exist, choose the one most commonly used in professional technical documentation of the target language.
-- Avoid slang, internal jargon, or overly literal translations that would not be recognized by the general developer audience.
-- Do not use the same word to translate two different source-language terms that carry distinct meanings.
-- Avoid repeating the same verb in close proximity; vary word choice for readability.
-
-#### When translating into Chinese
-- When a number modifies a noun, always include a Chinese classifier or measure word (量词). For example: "three-package seam" → "由三个 package 构成的 seam", not "三 package seam".
-
-### Punctuation
-
-#### When translating into Chinese
-- Use full-width Chinese punctuation in prose: `，。：；？！（）「」`.
-- Strongly prefer replacing all em-dashes (——) with colons, periods, commas, or parentheses. Keep an em-dash only if no other punctuation works at all.
-- Use enumeration commas (、) between parallel items, not regular commas.
-- List item endings: use semicolons or no punctuation. Do not end list items with commas.
-- Put one half-width space between Chinese text and Latin words/numbers.
-- For RFC 2119 keywords (MUST, MUST NOT, SHOULD, MAY), render the corresponding Chinese term in italics: *必须*、*禁止*、*应当*、*可以*.
-
-#### When translating into English
-- Use half-width English punctuation and standard English spacing. Preserve full-width punctuation only in verbatim Chinese text.
-- Convert enumeration commas (、) to English commas; convert 「」 quotes to English double quotes.
-- Render the terminology table's English column the same way the Chinese column binds the other direction: listed terms use exactly the table's English form; first-occurrence glosses do not carry over (English prose never glosses an English term with Chinese).
-- Chinese topic-comment sentences and dropped subjects become explicit English subjects; prefer concise declaratives over nominalizations.
-- Do not transliterate Chinese engineering idioms literally: render the underlying concept (误报 → false positive, 执行红线 → enforcement frontier), consulting the terminology table first.
-- Keep the register of institutional developer documentation: contractions are acceptable, marketing language and hedging (very, quite, simply) are not.
-
-## Terminology
-
-A terminology table is provided below. Follow it strictly:
-- Render every listed term exactly as specified.
-- First occurrence: write as shown in the "首次出现" column (with parenthetical gloss). Subsequent occurrences: write only the part before the parentheses.
-- If a term has already been glossed as part of a compound term, do not gloss it again when it appears alone later.
-- NEVER use translations listed in the "不要译作" column.
-- For technical terms not in the table: keep them in the source language. Do not invent a translation. This rule applies to terminology only; for general prose, freely restructure and paraphrase for natural expression.
+You are a senior technical translator specializing in LLM and agent development documentation. Translate the complete source document from {{source_lang}} to {{target_lang}} as natural, professional technical prose.
 
-{{terminology}}
+## Binding Translation Rules
 
-## Output Format
+The canonical repository rules below are injected verbatim. Apply every direction-appropriate requirement. In those rules, the authored document is the source for this request and the generated document is its counterpart.
 
-Produce your output in three XML sections:
+{{translation_rules}}
 
-```xml
-<translation>
-(Complete translation of the source document)
-</translation>
-
-<review>
-(Self-review notes, one correction per line with category tag, e.g.)
-- [Tone] "旁挂记录" → "伴随记录"（生造词）
-- [Sentence] 第 3 段补充逗号断句
-- [Punctuation] 两处破折号替换为冒号
-- 无修正
-</review>
-
-<final>
-(Final translation after corrections)
-</final>
-```
+## Request-Specific Structure
 
-## Self-Review Instructions
+- The source basename is `{{source_filename}}`. When translating into Chinese, write `[English]({{source_filename}}) | 中文` immediately after the H1. When translating into English, write `English | [中文]({{source_filename_zh}})` immediately after the H1.
+- Emit the switcher for a new pair and flip an existing switcher; never copy it unchanged.
 
-After writing `<translation>`, re-read it in the target language only, without looking at the source. Check by category:
+## Binding Terminology
 
-**Structure**
-- Is the heading hierarchy, list shape, and code block content identical to the source?
-- Are ALL comments inside code blocks left untranslated (byte-identical to source)?
-- Is the language switcher line correctly flipped (not copied from source)?
-- Are link targets preserved and bold markers followed by a space?
+Apply the current table below exactly as required by the injected translation rules.
 
-**Tone & Style**
-- Does every sentence read as if originally written by a native speaker?
-- Is there any colloquial, casual, or overly informal phrasing?
+{{terminology}}
 
-**Sentence Structure**
-- Are there run-on sentences that need breaking?
-- Are there stiff passive constructions that should be converted to active voice?
+## Output Format
 
-**Word Choice**
-- Are there overly literal translations that sound unnatural?
-- Is the same target-language word used to translate two distinct source concepts?
-- Is any slang or internal jargon present?
+Return exactly one well-formed XML document with this root and these three child elements. Do not wrap it in a Markdown code fence. Put all Markdown and review text inside CDATA. If any content contains the CDATA terminator, split it as `]]]]><![CDATA[>` so XML parsing reconstructs the original `]]>` sequence.
 
-**Terminology**
-- Are first-occurrence glosses correctly applied (not missing, not repeated)?
-- Are any "不要译作" forbidden translations present?
-- Are unlisted terms correctly kept in the source language?
+```xml
+<dsh-translation-response version="1">
+<translation><![CDATA[
+(Complete first-pass translation)
+]]></translation>
+<review><![CDATA[
+- [Tone] Replaced a literal rendering with the established target-language phrasing.
+- [Terminology] Applied the binding sidecar record term.
+]]></review>
+<final><![CDATA[
+(Complete corrected translation)
+]]></final>
+</dsh-translation-response>
+```
 
-**Punctuation** (when target is Chinese)
-- Are there em-dashes that should be replaced with colons, periods, or commas?
-- Are list items ending with commas instead of semicolons?
-- Are RFC 2119 keywords rendered in italics?
+## Self-Review Instructions
 
-Record corrections in `<review>` with category tags. Then output the corrected version in `<final>`. If no corrections are needed, write "无修正" in `<review>` and copy the translation unchanged into `<final>`.
+After writing `<translation>`, re-read it in the target language without looking at the source. Then apply the injected translation rules as a clause-by-clause comparison against the source and record actual corrections in English inside `<review>`. Apply every recorded correction in `<final>`. If no correction is needed, write only `- [None] No corrections.` in `<review>` and copy `<translation>` unchanged into `<final>`.
 
 ## Examples
 
-Below are representative examples of common problems and their corrections. Follow the "Good" versions.
+Follow the Good versions; these sentence-level examples illustrate error categories, not the assistant-message wire format.
 
 ### Colloquial verb → Professional verb
 - Source: `The repo pins pnpm@11.7.0 in package.json`
@@ -177,40 +102,40 @@ Below are representative examples of common problems and their corrections. Foll
 - Bad: `旁挂记录两侧 blob hash，使一致性可检查`
 - Good: `伴随记录保存两侧 blob hash，使一致性可检查`
 
-### Em-dash → Colon/period
-- Source: `FIXME — an issue that should block a new release. A release should not ship with an open FIXME unless reviewers explicitly agree the change can be merged anyway.`
-- Bad: `FIXME——应当阻塞新版本发布的问题。除非评审者明确同意可以照常合入，发布不应带着未解决的 FIXME 出门。`
-- Good: `FIXME：应当阻塞新版本发布的问题。除非评审者明确同意该更改可以合并，否则发布版本不应包含未解决的 FIXME。`
-
 ### Overly literal → Meaningful rendering
 - Source: `awkward phrasing is easier to hear without the source anchoring you`
 - Bad: `没有源文锚着，别扭的表述更容易被听出来`
 - Good: `不对照原文时，更容易察觉别扭的表达`
 
-### Terminology — do not translate what should be kept in English
+### Terminology — keep the binding English form
 - Source: `typed service seams, and explicit extension points`
 - Bad: `类型化的服务 seam（扩展点）与显式扩展点`
 - Good: `类型化的服务 seam 与显式扩展点`
 
-### Slang/jargon → Professional phrasing
+### Slang → Professional phrasing
 - Source: `The committed agent workflow lives in .agents/skills/dsh-translate-docs`
 - Bad: `进仓的 agent 工作流见 .agents/skills/dsh-translate-docs`
 - Good: `仓库内置的 agent 工作流见 .agents/skills/dsh-translate-docs`
 
-### "For humans" — translate the intent, not the word
-- Source: `For humans, start with the development guide`
-- Bad: `对于人工读者，请先从开发指南开始`（"人工读者"生硬）
-- Good: `面向开发者：请先阅读开发指南`（"开发者"自然，且中文里冒号在此处更自然）
+### Chinese → English — idiomatic subject and predicate
+- Source: `门禁绿并不代表译文内容正确。`
+- Bad: `The gate green does not represent that the translation content is correct.`
+- Good: `A green gate does not mean the translation is correct.`
 
-### Code block comments — NEVER translate
+### Code block comments — never translate
 - Source code block contains: `# REPL agent demo (needs DEEPSEEK_API_KEY)`
 - Bad: `# REPL agent 演示（需要 DEEPSEEK_API_KEY）`
-- Good: `# REPL agent demo (needs DEEPSEEK_API_KEY)` (keep exactly as-is, byte-for-byte)
+- Good: `# REPL agent demo (needs DEEPSEEK_API_KEY)` (byte-identical)
+
+### Language switcher — English to Chinese
+- Source: `English | [中文](README.zh.md)`
+- Bad: `English | [中文](README.zh.md)`
+- Good: `[English](README.md) | 中文`
 
-### Language switcher — flip direction
-- Source file (English) has: `English | [中文](README.zh.md)`
-- Bad (copying source unchanged): `English | [中文](README.zh.md)`
-- Good (flipped for Chinese file): `[English](README.md) | 中文`
+### Language switcher — Chinese to English
+- Source: `[English](README.md) | 中文`
+- Bad: `[English](README.md) | 中文`
+- Good: `English | [中文](README.zh.md)`
 
 ---
 

docs/i18n/translation-rules.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
-translation-rules.md: 3e99aa5432ccd904f702238e9b802a9ed9bf6832
-translation-rules.zh.md: 1d8dcb04f1015af2db46c2e25b44f5cd147b6ecc
+translation-rules.md: fb6aa9ac05bebe68ff9213af99f64457bdb1ad6f
+translation-rules.zh.md: 04dd0a704e19502c676ea0966437870c5af0624f

docs/i18n/translation-rules.md

@@ -6,27 +6,27 @@ How to translate between the two sides of a documentation pair in this repo. Bot
 
 ## Faithfulness
 
-- The counterpart MUST say what the authored side says — no added behavior, prerequisites, warnings, version claims, or examples, and no dropped ones. If the pair disagrees on substance, neither language wins by default: fix the side that is wrong, then bring the other along in the same change.
-- The counterpart SHOULD read as natural technical writing in its own language, not word-by-word gloss. Translate meaning, restructure sentences where the target grammar wants it, and keep the author's register — terse stays terse.
+- The counterpart *MUST* say what the authored side says — no added behavior, prerequisites, warnings, version claims, or examples, and no dropped ones. If the pair disagrees on substance, neither language wins by default: fix the side that is wrong, then bring the other along in the same change.
+- The counterpart *SHOULD* read as natural technical writing in its own language, not word-by-word gloss. Translate meaning, restructure sentences where the target grammar wants it, and keep the author's register — terse stays terse.
 - Do not translate the untranslatable: if a sentence resists natural rendering because it leans on an idiom of the source language, translate the idea, not the idiom.
 
 ## Voice
 
-- The register is calibrated by [style-samples.md](style-samples.md) — human-approved gold pairs, one per document genre. The counterpart MUST match the register of the nearest sample; where a sample and a prose rule here disagree, the sample wins. The target is institutional technical Chinese: complete sentences, declarative, neither chatty nor academic.
+- The register is calibrated by [style-samples.md](style-samples.md) — human-approved gold pairs, one per document genre. The counterpart MUST match the target-language side of the nearest sample; where its voice and a prose voice rule disagree, the sample wins. Chinese targets use institutional technical Chinese; English targets use concise professional developer prose.
 - Write as a native technical author restating the content, not as a translator transposing sentences. Then verify against the source clause by clause: nothing added, nothing dropped — fluency never justifies losing a clause.
-- Give sentences an explicit agent: where the English uses a passive or an abstract subject, name the actor (系统、门禁、评审人).
-- Prefer established Chinese engineering idiom over calques (误报／漏检 for false positive/negative, 执行红线 for enforcement frontier); localize metaphors instead of transplanting them, and unpack English noun chains into verb clauses.
+- Give sentences an explicit actor when the target language would otherwise obscure it; for Chinese, replace vague passives or abstract subjects with the actual actor (系统、门禁、评审人).
+- Prefer established target-language engineering idiom over calques (误报／漏检 for false positive/negative, 执行红线 for enforcement frontier); localize metaphors instead of transplanting them, and unpack noun chains where the target language requires it.
 - Split long paragraphs by semantic unit — one idea per paragraph. Paragraph boundaries MAY differ from the source; the structural signature does not count paragraphs.
-- Category nouns render in Chinese with a first-mention English annotation (实操手册（cookbook）); literal directory or file references stay code-formatted English.
+- When translating into Chinese, category nouns use Chinese with a first-mention English annotation (实操手册（cookbook）); when translating into English, use the conventional English category name. Literal directory or file references stay code-formatted English.
 
 ## Structure preservation
 
-Shape is enforced by the pairing gate, so the writer never trades fluency against it — write naturally inside the frame. The paired files MUST match one to one in:
+The pairing gate checks heading depths, fenced code blocks, table row and column counts, list kinds, ordered-list starts, list item counts, and link targets. Preserve the rest of the frame manually; the paired files MUST match one to one in:
 
 - heading hierarchy (same levels, same order — heading TEXT is translated),
 - list shape and numbering,
 - tables (same columns, same row order; header cells translated per terminology),
-- fenced code blocks — **byte-identical, including comments**; code is part of the verified surface (` ```ts ` blocks compile under `doc-typecheck`), and an edited comment is drift the fence-count gate cannot see,
+- fenced code blocks — **byte-identical, including comments**; the pairing signature compares their info strings and contents, and ` ```ts ` blocks compile under `doc-typecheck`,
 - inline code spans (commands, flags, config keys, file paths, event names, API names, version numbers) — verbatim, never translated or reformatted,
 - links and anchors: every relative link MUST point at the same target in both files — by convention the `.md` path, not the `.zh.md` sibling — so links never dangle when one pair lands before its neighbors. The ONLY zh-specific link is the language switcher. Link TEXT is translated; the target is not.
 
@@ -34,9 +34,9 @@ The repo's Markdown conventions apply to `.zh.md` files unchanged: one physical
 
 ## Terminology
 
-- [terminology.md](terminology.md) is the source of truth in both directions. Before translating, load it; while translating, every term it lists MUST be rendered exactly as it specifies, including its first-occurrence annotations (e.g. `agent（智能体）` on first mention, plain `agent` after) and its "不要译作" prohibitions. When the Chinese side is authored first, the English counterpart uses the table's English column the same way.
-- A technical term NOT in the table MAY be translated only when a major Chinese-language OSS or vendor doc has an established rendering for it (K8s/Vue/MDN Chinese docs, 微软简中风格指南, big-tech project docs). Cite the precedent in the PR.
-- A term with NO established precedent MUST stay in English in the translation and MUST be listed in the PR description under 「待定术语」(pending terms) with a suggested rendering for the reviewer to decide. MUST NOT invent a Chinese rendering inline — an unprecedented translation creates exactly the ambiguity the terminology table exists to prevent. Decided terms then land in [terminology.md](terminology.md) in the same PR or a follow-up.
+- [terminology.md](terminology.md) is the source of truth in both directions. Before translating, load it; every listed term MUST follow its row and its "不要译作" prohibitions. A Chinese target uses the "中文" column and its "首次出现" annotation; an English target uses the "English" column without adding a Chinese gloss.
+- For a Chinese target, an unlisted technical term MAY use an established rendering from a major Chinese-language OSS or vendor source (K8s/Vue/MDN Chinese docs, 微软简中风格指南, big-tech project docs), cited in the PR. Without such precedent it MUST stay in English and be listed under 「待定术语」(pending terms) with a suggested rendering.
+- For an English target, use the established English technical term. If the source term has no unambiguous established equivalent, preserve it with a short explanatory gloss and list it under pending terms. Neither direction may invent a rendering inline; a decided term enters [terminology.md](terminology.md) in the same PR or a follow-up.
 
 ## Typography
 
@@ -44,6 +44,7 @@ These rules govern the Chinese side; the English side follows the repo's normal
 
 - MUST put one half-width space between Chinese text and Latin words, and between Chinese text and numerals: `每个 plugin 注册 3 个 tool`。No space between a full-width punctuation mark and anything.
 - MUST use full-width (Chinese) punctuation in Chinese prose: `，。：；？！（）「」`. Half-width punctuation stays inside code spans, inside complete English sentences quoted as-is, and in numbers (`3.5`, `1,024`).
+- Chinese prose *SHOULD* prefer colons, periods, commas, or parentheses over em dashes. Keep an em dash only when no other punctuation preserves the sentence naturally.
 - Enumeration commas: a Chinese list of parallel items uses 顿号（、）, not commas.
 - MUST NOT use full-width digits or full-width Latin letters — `１２３` never, `123` always.
 - Proper nouns keep their canonical casing: GitHub, TypeScript, DeepSeek — never `github`/`Github` unless quoting code.
@@ -54,7 +55,7 @@ These rules govern the Chinese side; the English side follows the repo's normal
 
 - A pair is done when a bilingual engineer reading either file alone gets everything a reader of the other gets — same facts, same caveats, same tone — and nothing extra.
 - Before handing off, self-check the result against this file and re-read the counterpart ALONE, without the source side by side; awkward phrasing is easier to hear without the source anchoring you.
-- The mechanical contract (consistency record, switcher, structure, wrap, links) is checked by `pnpm run verify-translation-pairing` and the rest of `doc-sync` — run them; do not hand-verify what a gate covers.
+- Run `pnpm run verify-translation-pairing` and the rest of `doc-sync` for records, switchers, heading depths, code blocks, table row and column counts, list kinds, ordered-list starts, list item counts, links, and repository Markdown rules. Manually verify list and table order, noncanonical list numbering, inline code, emphasis, meaning, terminology, and tone.
 
 ## References
 

docs/i18n/translation-rules.zh.md

@@ -12,21 +12,21 @@
 
 ## 行文
 
-- 语体以 [style-samples.md](style-samples.md) 为校准锚点——人工定稿的金标样例按文体各一组，译文必须对齐最接近的样例语体；样例与本文条款冲突时，以样例为准。目标语体是规范的技术制度文：完整主谓、确定语气，不口语化也不学术腔。
+- 语体以 [style-samples.md](style-samples.md) 为校准锚点。人工定稿的金标样例按文体各一组，译文必须参照文体最接近的样例，采用其中目标语言一侧的语体；如果样例与本文的行文规则冲突，以样例为准。译成中文时，采用规范的技术制度文；译成英文时，采用简洁、专业的开发者文档语体。
 - 以母语技术作者的身份重述内容，而不是逐句转写的译者。写完后逐句对照原文核验：不添加、不遗漏——流畅永远不是丢掉语义成分的理由。
-- 给句子补显式执行主体：英文的被动句和抽象主语，中文写成「系统、门禁、评审人」等实际执行者做主语。
-- 优先使用中文工程惯用语而非直译（false positive/negative→误报／漏检、enforcement frontier→执行红线）；隐喻做本地化替换而不是移植，英文名词链展开为动词句。
+- 如果直译会让执行主体含糊，请明确写出实际执行者；译成中文时，应由「系统、门禁、评审人」等实际执行者作主语，避免含糊的被动句或抽象主语。
+- 优先采用目标语言中通行的工程表达，避免生硬直译（false positive/negative→误报／漏检、enforcement frontier→执行红线）；隐喻应自然改写，名词链则按目标语言的习惯拆开。
 - 长段按语义单元拆分，一段一件事。段落边界可以与原文不同；结构签名不比对段落数。
-- 类别名词说中文并在首现括注英文（实操手册（cookbook））；指目录或文件本身时保留代码体英文。
+- 翻译为中文时，类别名词使用中文并在首现括注英文（实操手册（cookbook））；翻译为英文时，使用通行的英文类别名。指目录或文件本身时保留代码体英文。
 
 ## 结构保持
 
-结构一致性由配对门禁负责校验，译者无需为保持结构而牺牲行文的流畅：在既定框架内自然书写即可。配对的两个文件必须在以下方面一一对应：
+配对门禁会检查标题深度、围栏代码块、表格行列数、列表类型、有序列表起始编号、列表项数量与链接目标；门禁未覆盖的结构仍需人工核对。两个配对文件必须在以下方面一一对应：
 
 - 标题层级（相同级别、相同顺序；标题的**文字**要翻译）；
 - 列表形态与编号；
 - 表格（相同的列、相同的行序；表头单元格按术语表翻译）；
-- 围栏代码块：**逐字节一致，包括注释**。代码属于受验证的范围（` ```ts ` 块要通过 `doc-typecheck` 编译），而被改动的注释是代码块计数门禁看不见的漂移；
+- 围栏代码块：**逐字节一致，包括注释**。配对签名比对信息字符串与内容，` ```ts ` 块还要通过 `doc-typecheck` 编译；
 - 行内代码（命令、flag、配置键、文件路径、事件名、API 名、版本号）：原样保留，从不翻译或重排；
 - 链接与锚点：每个相对链接在两个文件中必须指向相同的目标（按约定是 `.md` 路径而非 `.zh.md` 兄弟文件），这样即使某对文档先于相邻文件落地，链接也不会悬空。唯一的 zh 特有链接是语言切换行。链接**文字**翻译；链接目标不翻。
 
@@ -34,18 +34,19 @@
 
 ## 术语
 
-- [terminology.md](terminology.md) 是双向的术语真源。翻译前请先加载它；翻译过程中，表内的每个术语都*必须*严格按表中规定的译法呈现，包括首次出现的括注（如首现写 `agent（智能体）`，之后写 `agent`）与「不要译作」的禁项。中文先行撰写时，英文对侧同样按表中英文列使用术语。
-- 表中**没有**的技术术语，只有当某个主要中文 OSS 或厂商文档已有成型译法时（K8s／Vue／MDN 中文文档、微软简中风格指南、大厂项目文档）才*可以*翻译。请在 PR 中注明先例出处。
-- **没有**成型先例的术语，译文中*必须*保留英文，并且*必须*在 PR 描述的「待定术语」下列出，附上建议译法交评审者定夺。*禁止*就地发明中文译法，因为无先例的翻译恰恰会制造术语表要防止的歧义。确定下来的术语随后在同一个 PR 或后续 PR 中进入 [terminology.md](terminology.md)。
+- [terminology.md](terminology.md) 是双向的术语真源。翻译前请先加载它；表内术语必须遵守对应行与「不要译作」禁项。译成中文时，采用「中文」列，并按「首次出现」列括注；译成英文时，采用「English」列，不加中文括注。
+- 译成中文时，术语表未收录的技术术语只有在主流中文 OSS 文档或厂商资料中已有通行译法时才可以翻译（K8s／Vue／MDN 中文文档、微软简中风格指南、大厂项目文档），并须在 PR 中注明出处；否则必须保留英文，并在 PR 描述的「待定术语」中给出建议译法。
+- 译成英文时，采用通行的英文技术术语。如果源术语没有明确的通行对应词，则保留原词、附上简短说明，并列入「待定术语」。两个方向都不得自行创造译法；确定后的术语须在同一个 PR 或后续 PR 中加入 [terminology.md](terminology.md)。
 
 ## 排版
 
 本节规则约束中文一侧；英文一侧遵循仓库常规的 Markdown 约定（根 `AGENTS.md`）。以下中西文混排规则遵循 [MDN 简体中文翻译指南](https://github.com/mdn/translated-content/blob/main/docs/zh-cn/translation-guide.md)、[Kubernetes 中文本地化指南](https://kubernetes.io/zh-cn/docs/contribute/localization_zh/)、[Vue.js 中文翻译须知](https://github.com/vuejs-translations/docs-zh-cn/wiki/%E7%BF%BB%E8%AF%91%E9%A1%BB%E7%9F%A5) 与[中文文案排版指北](https://github.com/sparanoid/chinese-copywriting-guidelines)的跨项目共识，其根据是 [W3C clreq](https://www.w3.org/TR/clreq/) 与 GB/T 15834—2011：
 
-- *必须*在中文与拉丁词之间、中文与数字之间各留一个半角空格：`每个 plugin 注册 3 个 tool`。全角标点与任何字符之间不加空格。
-- 中文行文*必须*使用全角（中文）标点：`，。：；？！（）「」`。半角标点保留在代码内、按原样引用的完整英文句子内、以及数字内（`3.5`、`1,024`）。
+- 必须在中文与拉丁词之间、中文与数字之间各留一个半角空格：`每个 plugin 注册 3 个 tool`。全角标点与任何字符之间不加空格。
+- 中文行文必须使用全角（中文）标点：`，。：；？！（）「」`。半角标点保留在代码内、按原样引用的完整英文句子内、以及数字内（`3.5`、`1,024`）。
+- 中文行文*应当*优先使用冒号、句号、逗号或括号，尽量不用破折号；只有其他标点都无法自然表达时才保留破折号。
 - 顿号：中文的并列项之间使用顿号（、），而非逗号。
-- *禁止*使用全角数字或全角拉丁字母：永远不写 `１２３`，永远写 `123`。
+- 禁止使用全角数字或全角拉丁字母：永远不写 `１２３`，永远写 `123`。
 - 专有名词保持规范大小写：GitHub、TypeScript、DeepSeek。除非引用代码，否则绝不写 `github`／`Github`。
 - 第二人称用「你」，不用「您」（与 Vue、Kubernetes 中文约定及本仓库的直接语气一致）。
 - 强调标记（`**加粗**`、`*斜体*`）落在与对侧相同的文字段上。中文没有斜体，渲染效果可能看不出差别，不要用引号或其他装饰替代。
@@ -54,7 +55,7 @@
 
 - 一对文档的完成标准：一位双语工程师只读其中任一文件，能获得与另一文件读者完全相同的信息（相同的事实、相同的告诫、相同的语气），并且没有任何多余的内容。
 - 交付前，请对照本文自查一遍，并**单独通读对侧文件**，不与源侧对照；不对照原文时，更容易察觉别扭的表达。
-- 机械契约（一致性记录、切换行、结构、折行、链接）由 `pnpm run verify-translation-pairing` 和 `doc-sync` 的其余门禁检查。请运行门禁；门禁已覆盖的内容无需手工核对。
+- 请运行 `pnpm run verify-translation-pairing` 与 `doc-sync` 的其余门禁。这些门禁会检查一致性记录、切换行、标题深度、代码块、表格行列数、列表类型、有序列表起始编号、列表项数量、链接及仓库 Markdown 规则；列表与表格的顺序、非常规列表编号、行内代码、强调标记、语义、术语和语体仍需人工核对。
 
 ## 参考资料
 

docs/rfc/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.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
-2026-07-02-bilingual-docs-and-pairing-gate.md: 1e96622e7fb5694ab61772d68744394ef1aeb53a
-2026-07-02-bilingual-docs-and-pairing-gate.zh.md: c752d76f12f556ce190bf80c4f3a531c0821be8e
+2026-07-02-bilingual-docs-and-pairing-gate.md: 68c0f3bbc0472b0c96f9d64fc6b1b24ac7008795
+2026-07-02-bilingual-docs-and-pairing-gate.zh.md: 2cf8f9b9c17d8a521d8674833e909b34f315cfe0

docs/rfc/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.md

@@ -12,7 +12,7 @@ This repo's README and docs tree are read by people and agents inside and outsid
 
 - **Paired sibling files with equal authority.** A documentation pair is three sibling files: English `foo.md`, Chinese `foo.zh.md`, and a consistency record `foo.i18n.yaml`. Neither language is canonical — a document may be authored and reviewed Chinese-first and translated to English afterwards, or the reverse; what binds the pair is that both sides must say the same thing, and pairs merge whole (both languages plus the record, never one alone). Policy: [docs/i18n/README.md](../../../i18n/README.md); translation rules: [docs/i18n/translation-rules.md](../../../i18n/translation-rules.md); terminology source of truth: [docs/i18n/terminology.md](../../../i18n/terminology.md).
 - **A sidecar record of both blob hashes makes consistency checkable.** `foo.i18n.yaml` holds the full git blob hash of each side as of the last confirmed-consistent state. An edit to either side without re-confirming the pair is then mechanically detectable as a pure content comparison — no history lookup — and the hashes are computable for files edited in the same PR, which a commit-hash record is not. Re-recording (`verify-translation-pairing --write`) produces a reviewable yaml diff: confirming consistency is an explicit, visible act in the PR.
-- **`verify-translation-pairing` joins `doc-sync`.** The gate ([scripts/verify-translation-pairing.ts](../../../../scripts/verify-translation-pairing.ts)) enforces: required pairs exist, every existing pair is complete (all three files) and consistent (both hashes match, switcher links both ways, structural signatures identical), and excluded (generated or bilingual-by-construction) files stay unpaired. The `required` list in [scripts/translation-pairing.manifest.json](../../../../scripts/translation-pairing.manifest.json) is a ratchet: each merged translation batch adds its files, so coverage only grows.
+- **`verify-translation-pairing` joins `doc-sync`.** The gate ([scripts/verify-translation-pairing.ts](../../../../scripts/verify-translation-pairing.ts)) enforces: required pairs exist, every existing pair is complete (all three files) and consistent (both hashes match, switcher links both ways, structural signatures identical), excluded (generated or bilingual-by-construction) files stay unpaired, and date-named documents on or after the manifest's `requiredSince` cutoff have complete pairs. The `required` list in [scripts/translation-pairing.manifest.json](../../../../scripts/translation-pairing.manifest.json) is a ratchet: each merged translation batch adds its files, so coverage only grows.
 - **Translation is agent work with human review.** The committed workflow is [.agents/skills/dsh-translate-docs](../../../../.agents/skills/dsh-translate-docs/SKILL.md), following the same pattern as [dsh-code-review](../../../../.agents/skills/dsh-code-review/SKILL.md): the skill carries the workflow and defers to the docs as sources of truth.
 
 ## Alternatives considered
@@ -34,5 +34,5 @@ Paired sibling files with locale suffixes are the dominant Chinese big-tech conv
 - Every pair adds a third file to the tree. The record is machine-written (`--write`), so the cost is directory noise, not maintenance effort; in exchange, "who confirmed these consistent, and when" is answerable from git blame on the yaml.
 - When the two sides disagree, no mechanical rule picks a winner — the PR review does. That is the price of equal authority, accepted deliberately: the alternative (a canonical language) forbids Chinese-first authoring.
 - Generated docs (`cordis-catalog/`, `tool-catalog/`, `module-graph.md`) are excluded for now; the planned follow-up is to teach their generators to emit Chinese alongside English, at which point they leave the exclusion list.
-- Rollout is incremental by design: documents outside `required` are visible backlog (`--list`), not red CI, so pairs land in reviewable batches without a big-bang PR. New documents are the exception — a date-named document dated on/after the manifest's `requiredSince` cutoff merges bilingual or not at all, so the backlog only ever shrinks.
+- Rollout is incremental by design: documents outside `required` are visible backlog (`--list`), not red CI, so pairs land in reviewable batches without a big-bang PR. A date-named document dated on or after the manifest's `requiredSince` cutoff merges bilingual or not at all, so new date-named RFCs do not enlarge that backlog.
 - The recorded hashes double as the update tool (`git cat-file -p <hash>` recovers either side's last-confirmed text for a minimal diff-based update), so re-translation of whole files is never forced by the mechanism.

docs/rfc/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.zh.md

@@ -11,9 +11,9 @@ Status: implemented
 ## 决策
 
 - **配对兄弟文件，两种语言同权。** 一对文档由三个兄弟文件组成：英文 `foo.md`、中文 `foo.zh.md`，以及一份一致性记录 `foo.i18n.yaml`。没有哪种语言是正典：一篇文档可以先用中文撰写和评审、之后再译成英文，反之亦可；约束配对的是：两侧必须表达相同的内容，且配对整体合并（两种语言加记录，绝不单独落一侧）。政策见 [docs/i18n/README.md](../../../i18n/README.md)；翻译规则见 [docs/i18n/translation-rules.md](../../../i18n/translation-rules.md)；术语真源见 [docs/i18n/terminology.md](../../../i18n/terminology.md)。
-- **伴随记录保存两侧 blob hash，使一致性可检查。** `foo.i18n.yaml` 保存两侧文件在上一次确认一致时各自的完整 git blob hash。此后修改了任一侧而未重新确认配对，都能被机械检测出来（纯内容比较，无需查询历史），而且同一个 PR 内改动的文件也能计算出 hash，commit hash 式的记录做不到这一点。重新记录（`verify-translation-pairing --write`）会产生一份可评审的 yaml diff：确认一致在 PR 中是一个显式、可见的动作。
-- **`verify-translation-pairing` 加入 `doc-sync`。** 门禁（[scripts/verify-translation-pairing.ts](../../../../scripts/verify-translation-pairing.ts)）强制执行以下规则：required 的配对必须存在；任何已存在的配对必须完整（三个文件齐全）且一致（两个 hash 匹配、切换行双向互链、结构签名一致）；被排除的文件（生成物或本身即双语的）保持不配对。[scripts/translation-pairing.manifest.json](../../../../scripts/translation-pairing.manifest.json) 中的 `required` 清单只进不退：每个合并的翻译批次将自己的文件加入其中，覆盖面只增不减。
-- **翻译是 agent 的工作，由人评审。** 仓库内置的工作流是 [.agents/skills/dsh-translate-docs](../../../../.agents/skills/dsh-translate-docs/SKILL.md)，与 [dsh-code-review](../../../../.agents/skills/dsh-code-review/SKILL.md) 模式相同：skill 承载工作流，并将文档作为真源。
+- **伴随记录保存两侧 blob hash，使一致性可检查。** `foo.i18n.yaml` 保存两侧文件在上一次确认一致时各自的完整 git blob hash。此后修改了任一侧而未重新确认配对，都能被机械检测出来（纯内容比较，无需查询历史），而且同一个 PR（Pull Request）内改动的文件也能计算出 hash，commit hash 式的记录做不到这一点。重新记录（`verify-translation-pairing --write`）会产生一份可评审的 yaml diff：确认一致在 PR 中是一个显式、可见的动作。
+- **`verify-translation-pairing` 加入 `doc-sync`。** 门禁（[scripts/verify-translation-pairing.ts](../../../../scripts/verify-translation-pairing.ts)）强制执行以下规则：required 的配对必须存在；任何已存在的配对必须完整（三个文件齐全）且一致（两个 hash 匹配、切换行双向互链、结构签名一致）；被排除的文件（生成物或本身即双语的）不得配对；凡文件名以日期开头且日期不早于 manifest（元数据清单）中 `requiredSince` 分界日期的文档，也必须有完整配对。[scripts/translation-pairing.manifest.json](../../../../scripts/translation-pairing.manifest.json) 中的 `required` 清单只进不退：每个合并的翻译批次将自己的文件加入其中，覆盖面只增不减。
+- **翻译是 agent 的工作，由人评审。** 仓库内置的工作流是 [.agents/skills/dsh-translate-docs](../../../../.agents/skills/dsh-translate-docs/SKILL.md)，与 [dsh-code-review](../../../../.agents/skills/dsh-code-review/SKILL.md) 模式相同：skill（技能）承载工作流，并将文档作为真源。
 
 ## 曾考虑的替代方案
 
@@ -34,5 +34,5 @@ Status: implemented
 - 每个配对给目录树多添一个文件。记录由机器写入（`--write`），代价是目录噪音而非维护负担；换来的是「谁在何时确认过这对文档一致」可以从 yaml 的 git blame 直接回答。
 - 两侧说法冲突时，没有机械规则裁决谁赢，由 PR 评审裁决。这是同权的代价，且是有意接受的：另一个选项（正典语言）会禁止中文先行撰写。
 - 生成文档（`cordis-catalog/`、`tool-catalog/`、`module-graph.md`）暂被排除；计划中的后续工作是让生成器在输出英文的同时输出中文，届时将这些文件移出排除清单。
-- 推进天然是渐进的：`required` 之外的文档是可见的 backlog（`--list`），而非红色的 CI；因此配对按可评审的批次落地，无需一个巨型 PR。
+- 推进天然是渐进的：`required` 之外的文档是可见的 backlog（待翻清单，`--list`），而非红色的 CI；因此配对按可评审的批次落地，无需一个巨型 PR。凡文件名以日期开头且日期不早于 manifest 中 `requiredSince` 分界日期的文档，都必须配齐双语文件，因此新建的日期命名 RFC 不会增加这份 backlog。
 - 记录的 hash 兼作更新工具（`git cat-file -p <hash>` 能还原任一侧上次确认的文本，用于基于 diff 的最小更新），因此这套机制从不强迫整篇重译。

eslint.config.mjs

@@ -74,7 +74,7 @@ export default tseslint.config(
 
   // --- tests: same rules, minus the friction that fights test ergonomics --
   {
-    files: ['packages/*/*/tests/**/*.ts', 'examples/*/tests/**/*.ts'],
+    files: ['packages/*/*/tests/**/*.ts', 'examples/*/tests/**/*.ts', 'scripts/**/*.spec.ts'],
     extends: [
       ...tseslint.configs.strictTypeChecked,
     ],

package.json

@@ -44,6 +44,7 @@
     "verify-rfc-classification": "tsx scripts/verify-rfc-classification.ts",
     "verify-rfc-format": "tsx scripts/verify-rfc-format.ts",
     "verify-type-equiv": "tsx scripts/verify-type-equiv.ts",
+    "verify-translation-prompt": "tsx scripts/verify-translation-prompt.ts",
     "verify-translation-pairing": "tsx scripts/verify-translation-pairing.ts",
     "verify-doc-budgets": "tsx scripts/verify-doc-budgets.ts",
     "verify-package-readme-limitations": "tsx scripts/verify-package-readme-limitations.ts",
@@ -69,7 +70,7 @@
     "verify-scoped-events": "tsx scripts/gen-scoped-events.ts --check",
     "verify-module-graph": "tsx scripts/gen-module-graph.ts --check",
     "constraints": "tsx scripts/check-workspace-constraints.ts",
-    "doc-sync": "pnpm run doc-typecheck && pnpm run verify-cordis-catalog && pnpm run verify-cordis-api && pnpm run verify-export-jsdoc && pnpm run verify-tool-catalog && pnpm run verify-config-catalog && pnpm run verify-persistence-catalog && pnpm run verify-doc-graphs && pnpm run verify-scoped-events && pnpm run verify-md-wrap && pnpm run verify-md-links && pnpm run verify-doc-refs && pnpm run verify-package-paths && pnpm run verify-package-readme-model-experience && pnpm run verify-mermaid && pnpm run verify-rfc-classification && pnpm run verify-rfc-format && pnpm run verify-type-equiv && pnpm run verify-translation-pairing && pnpm run verify-doc-budgets && pnpm run verify-package-readme-limitations",
+    "doc-sync": "pnpm run doc-typecheck && pnpm run verify-cordis-catalog && pnpm run verify-cordis-api && pnpm run verify-export-jsdoc && pnpm run verify-tool-catalog && pnpm run verify-config-catalog && pnpm run verify-persistence-catalog && pnpm run verify-doc-graphs && pnpm run verify-scoped-events && pnpm run verify-md-wrap && pnpm run verify-md-links && pnpm run verify-doc-refs && pnpm run verify-package-paths && pnpm run verify-package-readme-model-experience && pnpm run verify-mermaid && pnpm run verify-rfc-classification && pnpm run verify-rfc-format && pnpm run verify-type-equiv && pnpm run verify-translation-prompt && pnpm run verify-translation-pairing && pnpm run verify-doc-budgets && pnpm run verify-package-readme-limitations",
     "hygiene": "pnpm run knip && pnpm run publint && pnpm run constraints && pnpm run verify-cordis-config && pnpm run verify-node-next-types && pnpm run verify-runtime-closure",
     "demo:echo": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/echo-agent/cordis.yml",
     "demo:repl": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/coding-agent/cordis.yml",
@@ -99,6 +100,7 @@
     "mermaid": "11.16.0",
     "micromark-extension-gfm": "^3.0.0",
     "publint": "^0.3.21",
+    "saxes": "^6.0.0",
     "tsdown": "^0.22.2",
     "tsx": "^4.22.4",
     "typescript": "^6.0.3",

packages/examples/acp-demo/tests/built-bin.e2e.ts

@@ -95,8 +95,19 @@ let consumer: string | undefined
 let child: ReturnType<typeof spawn> | undefined
 
 afterEach(async () => {
-  if (child !== undefined) { child.kill('SIGKILL'); child = undefined }
-  if (consumer !== undefined) await rm(consumer, { recursive: true, force: true })
+  if (child !== undefined) {
+    const proc = child
+    child = undefined
+    // Windows retains the child's cwd and session-log handles until process
+    // teardown completes, so await exit before removing the temp directory.
+    if (proc.exitCode === null && proc.signalCode === null) {
+      const exited = new Promise<void>((resolve) => { proc.once('exit', () => { resolve() }) })
+      proc.kill('SIGKILL')
+      await exited
+    }
+  }
+  // Windows can briefly retain released handles after exit; retry removal.
+  if (consumer !== undefined) await rm(consumer, { recursive: true, force: true, maxRetries: 10, retryDelay: 100 })
   consumer = undefined
 })
 

packages/examples/stdio-demo/tests/built-bin.e2e.ts

@@ -116,7 +116,8 @@ function runBuiltBin(cwd: string, configArg: string, line: string): Promise<{ st
 let consumer: string | undefined
 
 afterEach(async () => {
-  if (consumer !== undefined) await rm(consumer, { recursive: true, force: true })
+  // Windows can briefly retain released handles after exit; retry removal.
+  if (consumer !== undefined) await rm(consumer, { recursive: true, force: true, maxRetries: 10, retryDelay: 100 })
   consumer = undefined
 })
 

pnpm-lock.yaml

@@ -68,6 +68,9 @@ importers:
       publint:
         specifier: ^0.3.21
         version: 0.3.21
+      saxes:
+        specifier: ^6.0.0
+        version: 6.0.0
       tsdown:
         specifier: ^0.22.2
         version: 0.22.2(oxc-resolver@11.20.0)(publint@0.3.21)(tsx@4.22.4)(typescript@6.0.3)

scripts/gen-config-catalog.ts

@@ -8,7 +8,7 @@
  */
 
 import { globSync, readFileSync, writeFileSync } from 'node:fs'
-import { dirname, resolve } from 'node:path'
+import { dirname, resolve, sep } from 'node:path'
 import ts from 'typescript'
 import { LINK_MAP } from './gen-cordis-catalog.ts'
 import { parseJsDoc, pointer, rawJsDoc } from './jsdoc.ts'
@@ -581,7 +581,7 @@ export function collectConfigCatalog(scanRoot: string = root): CatalogEntry[] {
   // workspace-package imports while individual packages are still being walked.
   const pkgDirByName = new Map<string, string>()
   const manifests: { dir: string; pkg: string }[] = []
-  for (const manifestRel of globSync('packages/*/*/package.json', { cwd: scanRoot }).sort()) {
+  for (const manifestRel of globSync('packages/*/*/package.json', { cwd: scanRoot }).map(path => path.split(sep).join('/')).sort()) {
     const dir = manifestRel.slice(0, -'/package.json'.length)
     const manifest = JSON.parse(readFileSync(resolve(scanRoot, manifestRel), 'utf8')) as { name?: string; os?: string[]; cpu?: string[] }
     const pkg = manifest.name

scripts/gen-cordis-catalog.ts

@@ -6,7 +6,7 @@
  */
 
 import { globSync, readFileSync, writeFileSync } from 'node:fs'
-import { resolve } from 'node:path'
+import { resolve, sep } from 'node:path'
 import ts from 'typescript'
 import { checkParams, checkReturns, parseJsDoc, parseTags, pointer, rawJsDoc, reportViolations, type Mode } from './jsdoc.ts'
 
@@ -129,7 +129,7 @@ function memberSignature(member: ts.TypeElement | ts.ClassElement, sf: ts.Source
 export function collectEvents(scanRoot: string = root): EventEntry[] {
   const entries: EventEntry[] = []
   const violations: string[] = []
-  for (const rel of globSync('packages/*/*/src/*.ts', { cwd: scanRoot }).sort()) {
+  for (const rel of globSync('packages/*/*/src/*.ts', { cwd: scanRoot }).map(s => s.split(sep).join('/')).sort()) {
     const abs = resolve(scanRoot, rel)
     const text = readFileSync(abs, 'utf8')
     if (!text.includes('interface Events')) continue
@@ -183,7 +183,7 @@ export function collectEvents(scanRoot: string = root): EventEntry[] {
 export function collectServices(scanRoot: string = root): ServiceEntry[] {
   const entries: ServiceEntry[] = []
   const violations: string[] = []
-  for (const rel of globSync('packages/*/*/src/index.ts', { cwd: scanRoot }).sort()) {
+  for (const rel of globSync('packages/*/*/src/index.ts', { cwd: scanRoot }).map(s => s.split(sep).join('/')).sort()) {
     const abs = resolve(scanRoot, rel)
     const text = readFileSync(abs, 'utf8')
     if (!text.includes('interface Context')) continue

scripts/gen-persistence-catalog.ts

@@ -7,7 +7,7 @@
  */
 
 import { globSync, readFileSync, writeFileSync } from 'node:fs'
-import { resolve } from 'node:path'
+import { resolve, sep } from 'node:path'
 import ts from 'typescript'
 import { parseJsDoc, pointer, rawJsDoc, reportViolations } from './jsdoc.ts'
 
@@ -117,7 +117,7 @@ export function collectLogEvents(scanRoot: string = root): LogEventEntry[] {
   const violations: string[] = []
   const seen = new Map<string, string>()
   let owningDecl: string | null = null
-  for (const rel of globSync('packages/*/*/src/**/*.ts', { cwd: scanRoot }).sort()) {
+  for (const rel of globSync('packages/*/*/src/**/*.ts', { cwd: scanRoot }).map(s => s.split(sep).join('/')).sort()) {
     const abs = resolve(scanRoot, rel)
     const text = readFileSync(abs, 'utf8')
     if (!text.includes('SessionEventMap')) continue
@@ -194,7 +194,7 @@ export function collectLogEvents(scanRoot: string = root): LogEventEntry[] {
  */
 export function collectSurfaceEventTypes(scanRoot: string = root): string[] {
   const found: { names: string[]; source: string }[] = []
-  for (const rel of globSync('packages/*/*/src/**/*.ts', { cwd: scanRoot }).sort()) {
+  for (const rel of globSync('packages/*/*/src/**/*.ts', { cwd: scanRoot }).map(s => s.split(sep).join('/')).sort()) {
     const abs = resolve(scanRoot, rel)
     const text = readFileSync(abs, 'utf8')
     if (!text.includes('SurfaceEventType')) continue

scripts/package-graph.ts

@@ -6,7 +6,7 @@
  */
 
 import { globSync, readFileSync } from 'node:fs'
-import { dirname, resolve } from 'node:path'
+import { dirname, resolve, sep } from 'node:path'
 
 const SCOPE = '@deepseek-ai/dsh-'
 
@@ -33,7 +33,7 @@ export interface PackageGraphNode {
  */
 export function collectPackageGraph(root: string, groupOrder: readonly string[], gate: string): PackageGraphNode[] {
   const packages: PackageGraphNode[] = []
-  for (const rel of globSync('packages/*/*/package.json', { cwd: root }).sort()) {
+  for (const rel of globSync('packages/*/*/package.json', { cwd: root }).map(path => path.split(sep).join('/')).sort()) {
     const json = JSON.parse(readFileSync(resolve(root, rel), 'utf8')) as {
       name: string
       peerDependencies?: Record<string, string>

scripts/repo-files.ts

@@ -1,7 +1,7 @@
 /** Shared repository file discovery and line-oriented reference scanning. */
 
 import { globSync, readFileSync, realpathSync } from 'node:fs'
-import { relative, resolve } from 'node:path'
+import { relative, resolve, sep } from 'node:path'
 
 /** One authored path plus its canonical target for symlink deduplication. */
 export interface RepoFile {
@@ -37,8 +37,9 @@ export function uniqueRepoFiles(
   const files: RepoFile[] = []
   for (const pattern of patterns) {
     for (const match of globSync(pattern, { cwd: root })) {
-      if (isExcluded(match)) continue
-      const abs = resolve(root, match)
+      const repoPath = match.split(sep).join('/')
+      if (isExcluded(repoPath)) continue
+      const abs = resolve(root, repoPath)
       const real = realpathSync(abs)
       if (seen.has(real)) continue
       seen.add(real)
@@ -65,7 +66,7 @@ export function findReferenceViolations(
   normalize: (raw: string) => string,
   isViolation: (ref: string) => boolean,
 ): ReferenceViolation[] {
-  const file = relative(root, absPath)
+  const file = relative(root, absPath).split(sep).join('/')
   const out: ReferenceViolation[] = []
   const lines = readFileSync(absPath, 'utf8').split('\n')
   for (let i = 0; i < lines.length; i++) {

scripts/rfc-index.ts

@@ -7,7 +7,7 @@
  */
 
 import { readFileSync, readdirSync } from 'node:fs'
-import { resolve } from 'node:path'
+import { resolve, sep } from 'node:path'
 import { globSync } from 'node:fs'
 
 export const rfcRoot = resolve(import.meta.dirname, '../docs/rfc')
@@ -58,7 +58,7 @@ export function walkRfcTree(): { rfcs: Rfc[]; errors: string[] } {
     }
   }
   for (const lifecycle of LIFECYCLES) {
-    for (const match of globSync(`${lifecycle}/**/*.md`, { cwd: rfcRoot }).sort()) {
+    for (const match of globSync(`${lifecycle}/**/*.md`, { cwd: rfcRoot }).map(path => path.split(sep).join('/')).sort()) {
       const segs = match.split('/')
       // Allowlisted file directly at the lifecycle root (e.g. implemented/AGENTS.md).
       if (segs.length === 2 && ROOT_ALLOWLIST.has(segs[1] ?? '')) continue

scripts/run-gates.ts

@@ -96,8 +96,7 @@ function pnpmScript(id: string, script: string, options: Partial<Gate> = {}): Ga
   return {
     id,
     label: options.label ?? script,
-    command: pnpmBin(),
-    args: ['run', script],
+    ...pnpmInvocation(['run', script]),
     ...options,
   }
 }
@@ -106,14 +105,18 @@ function pnpmExec(id: string, args: string[], options: Partial<Gate> = {}): Gate
   return {
     id,
     label: options.label ?? `pnpm exec ${args.join(' ')}`,
-    command: pnpmBin(),
-    args: ['exec', ...args],
+    ...pnpmInvocation(['exec', ...args]),
     ...options,
   }
 }
 
-function pnpmBin(): string {
-  return process.platform === 'win32' ? 'pnpm.cmd' : 'pnpm'
+function pnpmInvocation(args: string[]): Pick<Gate, 'command' | 'args'> {
+  const entrypoint = process.env.npm_execpath
+  if (entrypoint === undefined || entrypoint === '') {
+    throw new Error('run-gates: npm_execpath is unavailable; invoke the runner through a pnpm package script.')
+  }
+  // Windows cannot spawn the pnpm.cmd shim directly; the JavaScript entrypoint keeps every host shell-free.
+  return { command: process.execPath, args: [entrypoint, ...args] }
 }
 
 function nodeOptions(...options: string[]): string {
@@ -194,13 +197,18 @@ function ciStaticGates(): Gate[] {
     pnpmScript('runtime-closure', 'verify-runtime-closure', { label: 'runtime closure' }),
     pnpmScript('constraints', 'constraints'),
     pnpmScript('cordis-config', 'verify-cordis-config', { label: 'Cordis config' }),
-    demoSmokeGate(),
+    ...staticDemoSmokeGates(),
     ...docSyncLeafGates(),
     pnpmScript('module-graph', 'verify-module-graph', { label: 'module graph' }),
     pnpmScript('knip', 'knip'),
   ]
 }
 
+function staticDemoSmokeGates(): Gate[] {
+  // Native Windows session persistence is outside the gates-only support scope.
+  return process.platform === 'win32' ? [] : [demoSmokeGate()]
+}
+
 function ciArtifactGates(): Gate[] {
   return [
     pnpmScript('build', 'build'),
@@ -286,6 +294,7 @@ function docSyncLeafGates(): Gate[] {
     pnpmScript('rfc-classification', 'verify-rfc-classification', { label: 'rfc classification' }),
     pnpmScript('rfc-format', 'verify-rfc-format', { label: 'rfc format' }),
     pnpmScript('type-equivalence', 'verify-type-equiv', { label: 'type equivalence' }),
+    pnpmScript('translation-prompt', 'verify-translation-prompt', { label: 'translation prompt' }),
     pnpmScript('translation-pairing', 'verify-translation-pairing', { label: 'translation pairing' }),
     pnpmScript('doc-budgets', 'verify-doc-budgets', { label: 'doc budgets' }),
     pnpmScript('package-readme-limitations', 'verify-package-readme-limitations', { label: 'package README limitations' }),
@@ -297,8 +306,7 @@ function demoSmokeGate(options: { needs?: string[] } = {}): Gate {
   return {
     id: 'demo-smoke',
     label: 'demo smoke',
-    command: pnpmBin(),
-    args: ['run', 'demo:echo'],
+    ...pnpmInvocation(['run', 'demo:echo']),
     input: 'echo ci smoke\n',
     ...dependencyOptions,
     verify: async (result) => {

scripts/translation-pairing.spec.ts

@@ -0,0 +1,95 @@
+/** Regression tests for the bilingual cutoff and structural signature. */
+
+import { describe, expect, it } from 'vitest'
+import {
+  datedDocumentDate,
+  isIsoDate,
+  parseTranslationMarkdown,
+  parseTranslationPairingManifest,
+  requiresPairByDate,
+  translationStructureDiff,
+  translationStructureSignature,
+} from './translation-pairing.ts'
+
+function signature(markdown: string) {
+  return translationStructureSignature(parseTranslationMarkdown(markdown), 'counterpart.zh.md')
+}
+
+describe('translation pairing manifest', () => {
+  it('accepts a real ISO cutoff and string-array fields', () => {
+    expect(parseTranslationPairingManifest(JSON.stringify({
+      requiredSince: '2026-07-14',
+      required: ['README.md'],
+      excluded: ['docs/generated/'],
+    }))).toEqual({
+      requiredSince: '2026-07-14',
+      required: ['README.md'],
+      excluded: ['docs/generated/'],
+    })
+  })
+
+  it.each(['2026-7-14', '2026-02-29', '2026-13-01', 'not-a-date'])('rejects invalid cutoff %s', (cutoff) => {
+    expect(isIsoDate(cutoff)).toBe(false)
+    expect(() => parseTranslationPairingManifest(JSON.stringify({
+      requiredSince: cutoff,
+      required: [],
+      excluded: [],
+    }))).toThrow('requiredSince must be a valid YYYY-MM-DD date')
+  })
+
+  it('rejects non-string manifest arrays', () => {
+    expect(() => parseTranslationPairingManifest(JSON.stringify({
+      requiredSince: '2026-07-14',
+      required: [42],
+      excluded: [],
+    }))).toThrow('required must be an array of strings')
+  })
+})
+
+describe('date-based pairing frontier', () => {
+  const cutoff = '2026-07-14'
+
+  it('enforces the cutoff day and every later day, but not the preceding day', () => {
+    expect(requiresPairByDate('docs/rfc/2026-07-13-before.md', cutoff)).toBe(false)
+    expect(requiresPairByDate('docs/rfc/2026-07-14-at-cutoff.md', cutoff)).toBe(true)
+    expect(requiresPairByDate('docs/rfc/2026-07-15-after.md', cutoff)).toBe(true)
+  })
+
+  it('matches only a date at the start of the basename', () => {
+    expect(datedDocumentDate('docs/rfc/2026-07-14-proposal.md')).toBe('2026-07-14')
+    expect(datedDocumentDate('docs/release-notes-2026-07-14-alpha.md')).toBeUndefined()
+    expect(requiresPairByDate('docs/release-notes-2026-07-14-alpha.md', cutoff)).toBe(false)
+  })
+})
+
+describe('translation structural signature', () => {
+  it('accepts matching list kinds, starts, and item counts', () => {
+    const source = signature('3. One\n4. Two\n\n- A\n- B\n')
+    const counterpart = signature('3. 一\n4. 二\n\n- 甲\n- 乙\n')
+    expect(translationStructureDiff(source, counterpart)).toEqual([])
+  })
+
+  it('rejects an altered ordered-list start', () => {
+    const source = signature('3. One\n4. Two\n\n- A\n- B\n')
+    const counterpart = signature('1. 一\n2. 二\n\n- 甲\n- 乙\n')
+    expect(translationStructureDiff(source, counterpart)).toEqual([
+      'list (kind, start, item count) #1 diverges between the pair: "ordered:start=3:items=2" vs "ordered:start=1:items=2"',
+    ])
+  })
+
+  it('rejects a missing list item', () => {
+    const source = signature('- A\n- B\n')
+    const counterpart = signature('- 甲\n')
+    expect(translationStructureDiff(source, counterpart)).toEqual([
+      'list (kind, start, item count) #1 diverges between the pair: "bullet:items=2" vs "bullet:items=1"',
+    ])
+  })
+
+  it('rejects altered table row or column counts', () => {
+    const source = signature('| A | B |\n|---|---|\n| 1 | 2 |\n| 3 | 4 |\n')
+    const counterpart = signature('| 甲 | 乙 |\n|---|---|\n| 一 | 二 |\n')
+    expect(translationStructureDiff(source, counterpart)).toEqual([
+      'table (row x column count) #1 diverges between the pair: "3x2" vs "2x2"',
+    ])
+  })
+})

scripts/translation-pairing.ts

@@ -0,0 +1,164 @@
+/**
+ * Pure parsing and structural helpers for the bilingual-document pairing
+ * gate. Kept separate from the CLI so cutoff and signature behavior can be
+ * regression-tested without reading or mutating the repository tree.
+ */
+
+import { fromMarkdown } from 'mdast-util-from-markdown'
+import { gfmFromMarkdown } from 'mdast-util-gfm'
+import { gfm } from 'micromark-extension-gfm'
+import type { Nodes } from 'mdast'
+
+/** Validated shape of `scripts/translation-pairing.manifest.json`. */
+export interface TranslationPairingManifest {
+  required: string[]
+  excluded: string[]
+  /** Date-named documents on or after this day must merge bilingual. */
+  requiredSince: string
+}
+
+const ISO_DATE = /^\d{4}-\d{2}-\d{2}$/
+const DATED_DOCUMENT = /(?:^|\/)(\d{4}-\d{2}-\d{2})-[^/]*\.md$/
+
+/** Whether a string names one real calendar day in canonical ISO form. */
+export function isIsoDate(value: string): boolean {
+  if (!ISO_DATE.test(value)) return false
+  const date = new Date(`${value}T00:00:00.000Z`)
+  return !Number.isNaN(date.getTime()) && date.toISOString().slice(0, 10) === value
+}
+
+/** Read one manifest string-array field or fail before enforcement starts. */
+function stringArrayField(record: Record<string, unknown>, field: 'required' | 'excluded'): string[] {
+  const value = record[field]
+  if (!Array.isArray(value)) {
+    throw new Error(`translation-pairing.manifest.json: ${field} must be an array of strings`)
+  }
+  const entries: unknown[] = value
+  if (!entries.every((entry): entry is string => typeof entry === 'string')) {
+    throw new Error(`translation-pairing.manifest.json: ${field} must be an array of strings`)
+  }
+  return entries
+}
+
+/** Parse and validate the checked-in bilingual manifest. */
+export function parseTranslationPairingManifest(content: string): TranslationPairingManifest {
+  const value: unknown = JSON.parse(content)
+  if (typeof value !== 'object' || value === null || Array.isArray(value)) {
+    throw new Error('translation-pairing.manifest.json: expected an object')
+  }
+  const record = value as Record<string, unknown>
+  const requiredSince = record.requiredSince
+  if (typeof requiredSince !== 'string' || !isIsoDate(requiredSince)) {
+    throw new Error(`translation-pairing.manifest.json: requiredSince must be a valid YYYY-MM-DD date; got ${JSON.stringify(requiredSince)}`)
+  }
+  return {
+    required: stringArrayField(record, 'required'),
+    excluded: stringArrayField(record, 'excluded'),
+    requiredSince,
+  }
+}
+
+/** Return the leading date of a `yyyy-mm-dd-*.md` basename, if present. */
+export function datedDocumentDate(file: string): string | undefined {
+  return DATED_DOCUMENT.exec(file)?.[1]
+}
+
+/** Whether a date-named document falls on or after the pairing cutoff. */
+export function requiresPairByDate(file: string, requiredSince: string): boolean {
+  const date = datedDocumentDate(file)
+  return date !== undefined && date >= requiredSince
+}
+
+/** The structural surface compared between the two sides of a pair. */
+export interface TranslationStructureSignature {
+  /** Heading depths in document order (h2 -> 2). */
+  headings: number[]
+  /** Fenced code blocks verbatim: info string plus content, in order. */
+  code: string[]
+  /** Row and column count of each table, in order. */
+  tables: string[]
+  /** Kind, ordered-list start, and direct item count of each list, in order. */
+  lists: string[]
+  /** Every link target in order; the language switcher is excluded. */
+  links: string[]
+}
+
+/** Parse Markdown with the same GFM extensions used by the pairing gate. */
+export function parseTranslationMarkdown(content: string): Nodes {
+  return fromMarkdown(content, { extensions: [gfm()], mdastExtensions: [gfmFromMarkdown()] })
+}
+
+/** Whether the tree contains a link to exactly `target`. */
+export function linksTo(tree: Nodes, target: string): boolean {
+  let found = false
+  const visit = (node: Nodes): void => {
+    if (node.type === 'link' && node.url === target) found = true
+    if ('children' in node) for (const child of node.children) visit(child)
+  }
+  visit(tree)
+  return found
+}
+
+/** Collect the ordered structural signature, skipping one switcher target. */
+export function translationStructureSignature(tree: Nodes, switcherTarget: string): TranslationStructureSignature {
+  const sig: TranslationStructureSignature = { headings: [], code: [], tables: [], lists: [], links: [] }
+  const visit = (node: Nodes): void => {
+    switch (node.type) {
+      case 'heading':
+        sig.headings.push(node.depth)
+        break
+      case 'code':
+        sig.code.push(`\`\`\`${node.lang ?? ''}${node.meta ? ` ${node.meta}` : ''}\n${node.value}`)
+        break
+      case 'table':
+        sig.tables.push(`${node.children.length}x${node.children[0]?.children.length ?? 0}`)
+        break
+      case 'list':
+        sig.lists.push(node.ordered
+          ? `ordered:start=${node.start ?? 1}:items=${node.children.length}`
+          : `bullet:items=${node.children.length}`)
+        break
+      case 'link':
+        if (node.url !== switcherTarget) sig.links.push(node.url)
+        break
+      default:
+        // Every other node kind is prose or a container, not part of the signature.
+        break
+    }
+    if ('children' in node) for (const child of node.children) visit(child)
+  }
+  visit(tree)
+  return sig
+}
+
+/** Render a signature element for an error message, truncated for readability. */
+function show(value: string | number | undefined): string {
+  if (value === undefined) return 'nothing'
+  const text = JSON.stringify(value)
+  return text.length > 72 ? `${text.slice(0, 72)}…` : text
+}
+
+/** Return the first divergence for each structural field; empty means equal. */
+export function translationStructureDiff(
+  source: TranslationStructureSignature,
+  zh: TranslationStructureSignature,
+): string[] {
+  const out: string[] = []
+  const fields: [string, (string | number)[], (string | number)[]][] = [
+    ['heading (depth)', source.headings, zh.headings],
+    ['code block', source.code, zh.code],
+    ['table (row x column count)', source.tables, zh.tables],
+    ['list (kind, start, item count)', source.lists, zh.lists],
+    ['link target', source.links, zh.links],
+  ]
+  for (const [field, sourceValues, zhValues] of fields) {
+    const length = Math.max(sourceValues.length, zhValues.length)
+    for (let index = 0; index < length; index++) {
+      if (sourceValues[index] !== zhValues[index]) {
+        out.push(`${field} #${index + 1} diverges between the pair: ${show(sourceValues[index])} vs ${show(zhValues[index])}`)
+        break
+      }
+    }
+  }
+  return out
+}

scripts/translation-prompt.spec.ts

@@ -0,0 +1,76 @@
+/** Regression tests for the executable translation prompt contract. */
+
+import { describe, expect, it } from 'vitest'
+import {
+  parseTranslationResponse,
+  renderTranslationPrompt,
+  renderTranslationResponse,
+} from './translation-prompt.ts'
+
+const document = `# Wrapper
+
+## 模板正文
+
+\`\`\`\`text
+{{source_lang}} to {{target_lang}}
+{{translation_rules}}
+{{terminology}}
+[English]({{source_filename}}) | [中文]({{source_filename_zh}})
+\`\`\`\`
+`
+
+describe('translation prompt rendering', () => {
+  it('renders every supported placeholder without recursively rewriting injected rules', () => {
+    const rendered = renderTranslationPrompt(document, {
+      sourceLanguage: 'English',
+      sourceFilename: 'guide.md',
+      translationRules: 'A literal {{source_lang}} in injected rules.',
+      terminology: '| English | 中文 |',
+    })
+    expect(rendered).toContain('English to Chinese')
+    expect(rendered).toContain('A literal {{source_lang}} in injected rules.')
+    expect(rendered).toContain('[English](guide.md) | [中文](guide.zh.md)')
+  })
+
+  it('rejects a filename whose suffix contradicts the source language', () => {
+    expect(() => renderTranslationPrompt(document, {
+      sourceLanguage: 'Chinese',
+      sourceFilename: 'guide.md',
+      translationRules: 'rules',
+      terminology: 'terms',
+    })).toThrow('does not match source language Chinese')
+  })
+
+  it('rejects malformed template placeholders before injecting rule contents', () => {
+    expect(() => renderTranslationPrompt(document.replace('{{source_lang}}', '{{source-lang}}'), {
+      sourceLanguage: 'English',
+      sourceFilename: 'guide.md',
+      translationRules: 'A literal {{source_lang}} in injected rules.',
+      terminology: '| English | 中文 |',
+    })).toThrow('template contains malformed placeholder syntax')
+  })
+})
+
+describe('translation response XML', () => {
+  it('round-trips Markdown and the CDATA terminator', () => {
+    const response = {
+      translation: '# Draft\n\nA ]]> marker.',
+      review: '- [Tone] Fixed.',
+      final: '# Final\n\nA ]]> marker.',
+    }
+    expect(parseTranslationResponse(renderTranslationResponse(response))).toEqual(response)
+  })
+
+  it('rejects missing, reordered, nested, attributed, or non-CDATA children', () => {
+    expect(() => parseTranslationResponse('<dsh-translation-response version="1"/>')).toThrow('translation, review, and final')
+    expect(() => parseTranslationResponse('<dsh-translation-response version="1"><review><![CDATA[x]]></review></dsh-translation-response>'))
+      .toThrow('expected translation, got review')
+    expect(() => parseTranslationResponse(renderTranslationResponse({ translation: 'x', review: 'y', final: 'z' })
+      .replace('<translation><![CDATA[x]]></translation>', '<translation><b><![CDATA[x]]></b></translation>')))
+      .toThrow('nested element b is not allowed')
+    expect(() => parseTranslationResponse(renderTranslationResponse({ translation: 'x', review: 'y', final: 'z' }).replace('<review>', '<review lang="en">')))
+      .toThrow('review must not have attributes')
+    expect(() => parseTranslationResponse(renderTranslationResponse({ translation: 'x', review: 'y', final: 'z' }).replace('<![CDATA[x]]>', 'x')))
+      .toThrow('all response field content must be inside CDATA')
+  })
+})

scripts/translation-prompt.ts

@@ -0,0 +1,171 @@
+/**
+ * Executable renderer and strict response parser for the committed
+ * documentation-translation prompt contract.
+ */
+
+import { basename } from 'node:path'
+import { SaxesParser } from 'saxes'
+
+/** Placeholder names supported by the committed translation prompt. */
+export const TRANSLATION_PROMPT_PLACEHOLDERS = [
+  'source_lang',
+  'target_lang',
+  'translation_rules',
+  'terminology',
+  'source_filename',
+  'source_filename_zh',
+] as const
+
+type TranslationPromptPlaceholder = (typeof TRANSLATION_PROMPT_PLACEHOLDERS)[number]
+
+/** Languages accepted by the bidirectional prompt. */
+type TranslationLanguage = 'English' | 'Chinese'
+
+/** Inputs that vary for one rendered translation request. */
+export interface TranslationPromptInput {
+  sourceLanguage: TranslationLanguage
+  /** Source basename, including `.md` or `.zh.md`. */
+  sourceFilename: string
+  /** Complete current `translation-rules.md` contents. */
+  translationRules: string
+  /** Complete current `terminology.md` contents. */
+  terminology: string
+}
+
+/** Parsed contents of the three-element XML response. */
+export interface TranslationResponse {
+  translation: string
+  review: string
+  final: string
+}
+
+const PLACEHOLDER = /{{([a-z_]+)}}/g
+const TEMPLATE_OPEN = '## 模板正文\n\n````text\n'
+const TEMPLATE_CLOSE = '\n````'
+const RESPONSE_CHILDREN = ['translation', 'review', 'final'] as const
+
+/** Extract the machine-consumed text fence from `translation-prompt.md`. */
+function extractTranslationPrompt(document: string): string {
+  const start = document.indexOf(TEMPLATE_OPEN)
+  if (start === -1) throw new Error('translation prompt: missing `## 模板正文` text fence')
+  const contentStart = start + TEMPLATE_OPEN.length
+  const end = document.indexOf(TEMPLATE_CLOSE, contentStart)
+  if (end === -1) throw new Error('translation prompt: missing closing four-backtick fence')
+  return document.slice(contentStart, end)
+}
+
+/** Read the placeholder names documented in the prompt's contract table. */
+export function documentedTranslationPromptPlaceholders(document: string): string[] {
+  const preambleEnd = document.indexOf(TEMPLATE_OPEN)
+  if (preambleEnd === -1) throw new Error('translation prompt: missing template body')
+  return [...document.slice(0, preambleEnd).matchAll(/^\| `{{([a-z_]+)}}` \|/gm)].map(match => match[1] ?? '')
+}
+
+/** Render one system prompt from the checked-in template and canonical rules. */
+export function renderTranslationPrompt(document: string, input: TranslationPromptInput): string {
+  if (basename(input.sourceFilename) !== input.sourceFilename) {
+    throw new Error(`translation prompt: sourceFilename must be a basename; got ${JSON.stringify(input.sourceFilename)}`)
+  }
+  const sourceIsChinese = input.sourceFilename.endsWith('.zh.md')
+  if (input.sourceLanguage === 'Chinese' ? !sourceIsChinese : sourceIsChinese || !input.sourceFilename.endsWith('.md')) {
+    throw new Error(`translation prompt: ${input.sourceFilename} does not match source language ${input.sourceLanguage}`)
+  }
+
+  const targetLanguage: TranslationLanguage = input.sourceLanguage === 'English' ? 'Chinese' : 'English'
+  const sourceFilenameZh = sourceIsChinese ? input.sourceFilename : input.sourceFilename.replace(/\.md$/, '.zh.md')
+  const values: Record<TranslationPromptPlaceholder, string> = {
+    source_lang: input.sourceLanguage,
+    target_lang: targetLanguage,
+    translation_rules: input.translationRules,
+    terminology: input.terminology,
+    source_filename: input.sourceFilename,
+    source_filename_zh: sourceFilenameZh,
+  }
+  const template = extractTranslationPrompt(document)
+  const placeholderFreeTemplate = template.replace(PLACEHOLDER, '')
+  if (placeholderFreeTemplate.includes('{{') || placeholderFreeTemplate.includes('}}')) {
+    throw new Error('translation prompt: template contains malformed placeholder syntax')
+  }
+  const names = [...template.matchAll(PLACEHOLDER)].map(match => match[1] ?? '')
+  const unknown = names.filter(name => !TRANSLATION_PROMPT_PLACEHOLDERS.includes(name as TranslationPromptPlaceholder))
+  if (unknown.length > 0) throw new Error(`translation prompt: unsupported placeholder(s): ${[...new Set(unknown)].join(', ')}`)
+  const missing = TRANSLATION_PROMPT_PLACEHOLDERS.filter(name => !names.includes(name))
+  if (missing.length > 0) throw new Error(`translation prompt: template does not use required placeholder(s): ${missing.join(', ')}`)
+
+  return template.replace(PLACEHOLDER, (_token, name: string) => values[name as TranslationPromptPlaceholder])
+}
+
+/** Escape one value so it remains byte-identical inside an XML CDATA field. */
+function escapeTranslationCdata(value: string): string {
+  return value.replaceAll(']]>', ']]]]><![CDATA[>')
+}
+
+/** Serialize a response using the exact XML wire contract in the prompt. */
+export function renderTranslationResponse(response: TranslationResponse): string {
+  return [
+    '<dsh-translation-response version="1">',
+    `<translation><![CDATA[${escapeTranslationCdata(response.translation)}]]></translation>`,
+    `<review><![CDATA[${escapeTranslationCdata(response.review)}]]></review>`,
+    `<final><![CDATA[${escapeTranslationCdata(response.final)}]]></final>`,
+    '</dsh-translation-response>',
+  ].join('\n')
+}
+
+/** Parse and validate the exact XML response shape emitted by the model. */
+export function parseTranslationResponse(xml: string): TranslationResponse {
+  const values: TranslationResponse = { translation: '', review: '', final: '' }
+  const stack: string[] = []
+  const cdataFields = new Set<string>()
+  let rootSeen = false
+  let childIndex = 0
+  const fail = (message: string): never => {
+    throw new Error(`translation response: ${message}`)
+  }
+  const parser = new SaxesParser({ xmlns: false })
+
+  parser.on('opentag', (tag) => {
+    if (stack.length === 0) {
+      if (rootSeen) fail('contains more than one root element')
+      if (tag.name !== 'dsh-translation-response') fail(`expected dsh-translation-response root, got ${tag.name}`)
+      const attributes = Object.keys(tag.attributes)
+      if (attributes.length !== 1 || tag.attributes.version !== '1') fail('root must have only version="1"')
+      rootSeen = true
+    } else if (stack.length === 1) {
+      const expected = RESPONSE_CHILDREN[childIndex]
+      if (tag.name !== expected) fail(`expected ${expected ?? 'no more children'}, got ${tag.name}`)
+      if (Object.keys(tag.attributes).length !== 0) fail(`${tag.name} must not have attributes`)
+      childIndex++
+    } else {
+      fail(`nested element ${tag.name} is not allowed`)
+    }
+    stack.push(tag.name)
+  })
+  parser.on('text', (value) => {
+    if (stack.length <= 1 && value.trim() === '') return
+    fail('all response field content must be inside CDATA')
+  })
+  parser.on('cdata', (value) => {
+    const field = stack.at(-1)
+    if (field === undefined || !RESPONSE_CHILDREN.includes(field as (typeof RESPONSE_CHILDREN)[number])) {
+      fail('CDATA is allowed only inside translation, review, or final')
+    }
+    const key = field as (typeof RESPONSE_CHILDREN)[number]
+    values[key] += value
+    cdataFields.add(key)
+  })
+  parser.on('closetag', (tag) => {
+    const expected = stack.pop()
+    if (expected !== tag.name) fail(`closing ${tag.name} does not match ${expected ?? 'nothing'}`)
+  })
+  parser.on('comment', () => fail('comments are not allowed'))
+  parser.on('doctype', () => fail('doctypes are not allowed'))
+  parser.on('processinginstruction', () => fail('processing instructions are not allowed'))
+  parser.on('error', error => fail(`invalid XML: ${error.message}`))
+  parser.write(xml).close()
+
+  if (childIndex !== RESPONSE_CHILDREN.length) fail('translation, review, and final must each appear exactly once and in order')
+  for (const field of RESPONSE_CHILDREN) {
+    if (!cdataFields.has(field)) fail(`${field} must contain a CDATA section`)
+  }
+  return values
+}

scripts/verify-package-readme-limitations.ts

@@ -6,7 +6,7 @@
  */
 
 import { existsSync, globSync, readFileSync } from 'node:fs'
-import { resolve } from 'node:path'
+import { resolve, sep } from 'node:path'
 import { markdownHeadingLines, markdownProseLines } from './markdown.ts'
 
 const root = resolve(import.meta.dirname, '..')
@@ -30,7 +30,7 @@ function isLimitationsLike(headingText: string): boolean {
   )
 }
 
-const packageJsons = globSync('packages/*/*/package.json', { cwd: root }).sort()
+const packageJsons = globSync('packages/*/*/package.json', { cwd: root }).map(path => path.split(sep).join('/')).sort()
 const scannedPackages = new Set(packageJsons.map(path => path.slice(0, -'/package.json'.length)))
 const failures: string[] = []
 

scripts/verify-package-readme-model-experience.ts

@@ -6,7 +6,7 @@
  */
 
 import { existsSync, globSync, readFileSync } from 'node:fs'
-import { relative, resolve } from 'node:path'
+import { relative, resolve, sep } from 'node:path'
 import { markdownHeadingLines, markdownProseLines, type MarkdownProseLine } from './markdown.ts'
 
 const root = resolve(import.meta.dirname, '..')
@@ -146,7 +146,7 @@ for (const line of readFileSync(resolve(root, 'docs/tool-catalog.md'), 'utf8').s
 }
 
 const failures: Failure[] = []
-const packageJsons = globSync('packages/*/*/package.json', { cwd: root }).sort()
+const packageJsons = globSync('packages/*/*/package.json', { cwd: root }).map(path => path.split(sep).join('/')).sort()
 const scannedPackages = new Set(packageJsons.map(path => path.slice(0, -'/package.json'.length)))
 let structuredCount = 0
 let contextSurfaceCount = 0

scripts/verify-translation-pairing.ts

@@ -9,11 +9,16 @@
 
 import { createHash } from 'node:crypto'
 import { existsSync, globSync, readFileSync, writeFileSync } from 'node:fs'
-import { basename, join, resolve } from 'node:path'
-import { fromMarkdown } from 'mdast-util-from-markdown'
-import { gfmFromMarkdown } from 'mdast-util-gfm'
-import { gfm } from 'micromark-extension-gfm'
-import type { Nodes } from 'mdast'
+import { basename, join, resolve, sep } from 'node:path'
+import {
+  datedDocumentDate,
+  linksTo,
+  parseTranslationMarkdown,
+  parseTranslationPairingManifest,
+  requiresPairByDate,
+  translationStructureDiff,
+  translationStructureSignature,
+} from './translation-pairing.ts'
 
 const root = resolve(import.meta.dirname, '..')
 const listMode = process.argv.includes('--list')
@@ -22,14 +27,7 @@ const writeMode = process.argv.includes('--write')
 /** Scope of the bilingual contract: the root README, the docs tree, and the Python SDK tree. */
 const SCOPE_PATTERNS = ['README.md', 'README.zh.md', 'README.i18n.yaml', 'docs/**/*.md', 'docs/**/*.i18n.yaml', 'python/**/*.md', 'python/**/*.i18n.yaml']
 
-/** The enforcement frontier and the never-paired set (docs/i18n/README.md § Scope). */
-interface Manifest {
-  required: string[]
-  excluded: string[]
-  /** Date-named documents (yyyy-mm-dd-*.md, i.e. RFCs) dated on/after this day must merge bilingual. */
-  requiredSince: string
-}
-const manifest = JSON.parse(readFileSync(join(root, 'scripts/translation-pairing.manifest.json'), 'utf8')) as Manifest
+const manifest = parseTranslationPairingManifest(readFileSync(join(root, 'scripts/translation-pairing.manifest.json'), 'utf8'))
 
 /**
  * An excluded entry ending in `/` excludes the whole directory. The trailing
@@ -81,102 +79,10 @@ function renderMeta(source: string, sourceHash: string, zh: string, zhHash: stri
   ].join('\n')
 }
 
-/**
- * The structural signature the two sides must share, as ordered sequences so
- * a swap or a level change is caught, not just a count change. Prose is
- * deliberately absent: the gate checks shape, never wording.
- */
-interface Signature {
-  /** Heading depths in document order (h2 → 2). */
-  headings: number[]
-  /** Fenced code blocks verbatim: info string + content, in order. */
-  code: string[]
-  /** Column count of each table, in order. */
-  tables: number[]
-  /** Each list's kind (ordered vs bullet), in order. */
-  lists: string[]
-  /** Every link target in order, the language switcher's excluded. */
-  links: string[]
-}
-
-/** Whether the tree contains a link to exactly `target` (the switcher check). */
-function linksTo(tree: Nodes, target: string): boolean {
-  let found = false
-  const visit = (node: Nodes): void => {
-    if (node.type === 'link' && node.url === target) found = true
-    if ('children' in node) for (const child of node.children) visit(child)
-  }
-  visit(tree)
-  return found
-}
-
-/** Collect the structural signature, skipping links to `switcherTarget`. */
-function signatureOf(tree: Nodes, switcherTarget: string): Signature {
-  const sig: Signature = { headings: [], code: [], tables: [], lists: [], links: [] }
-  const visit = (node: Nodes): void => {
-    switch (node.type) {
-      case 'heading':
-        sig.headings.push(node.depth)
-        break
-      case 'code':
-        sig.code.push(`\`\`\`${node.lang ?? ''}${node.meta ? ` ${node.meta}` : ''}\n${node.value}`)
-        break
-      case 'table':
-        sig.tables.push(node.children[0]?.children.length ?? 0)
-        break
-      case 'list':
-        sig.lists.push(node.ordered ? 'ordered' : 'bullet')
-        break
-      case 'link':
-        if (node.url !== switcherTarget) sig.links.push(node.url)
-        break
-      default:
-        // Every other node kind is prose or container — not part of the signature.
-        break
-    }
-    if ('children' in node) for (const child of node.children) visit(child)
-  }
-  visit(tree)
-  return sig
-}
-
-/** Render a signature element for an error message, truncated for readability. */
-function show(value: string | number | undefined): string {
-  if (value === undefined) return 'nothing'
-  const text = JSON.stringify(value)
-  return text.length > 72 ? `${text.slice(0, 72)}…` : text
-}
-
-/** First divergence between two signatures, as messages; empty when identical. */
-function signatureDiff(source: Signature, zh: Signature): string[] {
-  const out: string[] = []
-  const fields: [string, (string | number)[], (string | number)[]][] = [
-    ['heading (depth)', source.headings, zh.headings],
-    ['code block', source.code, zh.code],
-    ['table (column count)', source.tables, zh.tables],
-    ['list (kind)', source.lists, zh.lists],
-    ['link target', source.links, zh.links],
-  ]
-  for (const [field, s, z] of fields) {
-    const length = Math.max(s.length, z.length)
-    for (let i = 0; i < length; i++) {
-      if (s[i] !== z[i]) {
-        out.push(`${field} #${i + 1} diverges between the pair: ${show(s[i])} vs ${show(z[i])}`)
-        break
-      }
-    }
-  }
-  return out
-}
-
-function parse(content: string): Nodes {
-  return fromMarkdown(content, { extensions: [gfm()], mdastExtensions: [gfmFromMarkdown()] })
-}
-
 // Enumerate the scope once.
 const files = new Set<string>()
 for (const pattern of SCOPE_PATTERNS) {
-  for (const match of globSync(pattern, { cwd: root })) files.add(match)
+  for (const match of globSync(pattern, { cwd: root })) files.add(match.split(sep).join('/'))
 }
 const translations = [...files].filter(f => f.endsWith('.zh.md')).sort()
 const metas = [...files].filter(f => f.endsWith('.i18n.yaml')).sort()
@@ -218,14 +124,13 @@ for (const req of manifest.required) {
 // 2. Date-named documents (RFCs) dated on/after the requiredSince cutoff merge
 // bilingual: a new RFC lands with its pair or not at all. Deterministic from
 // the filename alone — no git history, so it holds on shallow CI checkouts.
-const DATED = /(?:^|\/)(\d{4}-\d{2}-\d{2})-[^/]*\.md$/
 for (const source of sources) {
   if (isExcluded(source)) continue
-  const dated = DATED.exec(source)
-  if (!dated?.[1] || dated[1] < manifest.requiredSince) continue
+  const date = datedDocumentDate(source)
+  if (!requiresPairByDate(source, manifest.requiredSince) || date === undefined) continue
   const { zh } = pairPaths(source)
   if (!existsSync(join(root, zh))) {
-    errors.push(`${source}: dated ${dated[1]} — documents dated on/after ${manifest.requiredSince} merge bilingual (docs/i18n/README.md); add the counterpart and record the pair`)
+    errors.push(`${source}: dated ${date} — documents dated on/after ${manifest.requiredSince} merge bilingual (docs/i18n/README.md); add the counterpart and record the pair`)
     state.set(source, 'missing')
   }
 }
@@ -273,15 +178,18 @@ for (const source of [...pairAnchors].sort()) {
     continue
   }
 
-  const sourceTree = parse(sourceContent.toString('utf8'))
-  const zhTree = parse(zhContent.toString('utf8'))
+  const sourceTree = parseTranslationMarkdown(sourceContent.toString('utf8'))
+  const zhTree = parseTranslationMarkdown(zhContent.toString('utf8'))
   if (!linksTo(zhTree, basename(source))) {
     errors.push(`${zh}: missing language switcher — no link to ${basename(source)}`)
   }
   if (!linksTo(sourceTree, basename(zh))) {
     errors.push(`${source}: missing language switcher — no link back to ${basename(zh)}`)
   }
-  for (const divergence of signatureDiff(signatureOf(sourceTree, basename(zh)), signatureOf(zhTree, basename(source)))) {
+  for (const divergence of translationStructureDiff(
+    translationStructureSignature(sourceTree, basename(zh)),
+    translationStructureSignature(zhTree, basename(source)),
+  )) {
     errors.push(`${source} ↔ ${zh}: ${divergence}`)
   }
   if (!state.has(source)) state.set(source, 'ok')
@@ -297,8 +205,7 @@ if (listMode) {
   const rows = [...state.entries()].sort((a, b) => order[a[1]] - order[b[1]] || a[0].localeCompare(b[0]))
   for (const [file, status] of rows) {
     const required = manifest.required.includes(file)
-    const date = DATED.exec(file)?.[1]
-    const tag = required ? '  (required)' : date && date >= manifest.requiredSince ? '  (required by date)' : '  (backlog)'
+    const tag = required ? '  (required)' : requiresPairByDate(file, manifest.requiredSince) ? '  (required by date)' : '  (backlog)'
     console.log(`${status.padEnd(11)} ${file}${status === 'missing' ? tag : ''}`)
   }
   const counts = { 'ok': 0, 'out-of-sync': 0, 'missing': 0 }

scripts/verify-translation-prompt.ts

@@ -0,0 +1,56 @@
+/** Verify that the committed translation prompt renders and parses as documented. */
+
+import { readFileSync } from 'node:fs'
+import { join, resolve } from 'node:path'
+import {
+  documentedTranslationPromptPlaceholders,
+  parseTranslationResponse,
+  renderTranslationPrompt,
+  renderTranslationResponse,
+  TRANSLATION_PROMPT_PLACEHOLDERS,
+} from './translation-prompt.ts'
+
+const root = resolve(import.meta.dirname, '..')
+
+function read(path: string): string {
+  return readFileSync(join(root, path), 'utf8')
+}
+
+try {
+  const document = read('docs/i18n/translation-prompt.md')
+  const translationRules = read('docs/i18n/translation-rules.md')
+  const terminology = read('docs/i18n/terminology.md')
+  const documented = documentedTranslationPromptPlaceholders(document)
+  if (documented.join('\n') !== TRANSLATION_PROMPT_PLACEHOLDERS.join('\n')) {
+    throw new Error(`placeholder table must list exactly: ${TRANSLATION_PROMPT_PLACEHOLDERS.join(', ')}`)
+  }
+
+  const englishSource = renderTranslationPrompt(document, {
+    sourceLanguage: 'English',
+    sourceFilename: 'example.md',
+    translationRules,
+    terminology,
+  })
+  const chineseSource = renderTranslationPrompt(document, {
+    sourceLanguage: 'Chinese',
+    sourceFilename: 'example.zh.md',
+    translationRules,
+    terminology,
+  })
+  if (!englishSource.includes('[English](example.md) | 中文')) throw new Error('English-source render does not carry the Chinese switcher instruction')
+  if (!chineseSource.includes('English | [中文](example.zh.md)')) throw new Error('Chinese-source render does not carry the English switcher instruction')
+
+  const example = /```xml\n([\s\S]*?)\n```/.exec(englishSource)?.[1]
+  if (example === undefined) throw new Error('rendered prompt has no XML response example')
+  parseTranslationResponse(example)
+
+  const roundTrip = { translation: 'first ]]> pass', review: '- [None] No corrections.', final: 'final ]]> text' }
+  const parsed = parseTranslationResponse(renderTranslationResponse(roundTrip))
+  if (JSON.stringify(parsed) !== JSON.stringify(roundTrip)) throw new Error('CDATA split rule does not round-trip response content')
+
+  console.log('verify-translation-prompt: both directions render and the XML response contract parses.')
+} catch (error) {
+  const message = error instanceof Error ? error.message : String(error)
+  console.error(`verify-translation-prompt: ${message}`)
+  process.exit(1)
+}

scripts/verify-type-equiv.ts

@@ -5,7 +5,7 @@
  */
 
 import { globSync, readFileSync, existsSync } from 'node:fs'
-import { resolve } from 'node:path'
+import { resolve, sep } from 'node:path'
 import ts from 'typescript'
 
 const root = resolve(import.meta.dirname, '..')
@@ -121,7 +121,7 @@ const keyOf = (x: { doc: string; symbol: string }): string => `${x.doc}::${x.sym
 // as an orphan rather than silently skipped.
 const docSet = new Set<string>()
 for (const pattern of MARKDOWN_GLOBS) {
-  for (const match of globSync(pattern, { cwd: root })) docSet.add(match)
+  for (const match of globSync(pattern, { cwd: root })) docSet.add(match.split(sep).join('/'))
 }
 const blocks: EquivBlock[] = [...docSet].sort().flatMap(extractEquivBlocks)
 

vitest.config.ts

@@ -7,7 +7,7 @@ export default defineConfig({
   // to source; native resolution would fall through to absent `lib/` outputs.
   plugins: [tsconfigPaths({ projects: ['./tsconfig.json'] })],
   test: {
-    include: ['packages/*/*/tests/**/*.spec.ts', 'examples/*/tests/**/*.spec.ts'],
+    include: ['packages/*/*/tests/**/*.spec.ts', 'examples/*/tests/**/*.spec.ts', 'scripts/**/*.spec.ts'],
     coverage: {
       provider: 'v8',
       // Coverage measures OUR runtime source. Types-only files carry no