v0.1.3: encoding remediation - restore 11 core files to clean UTF-8 + add check:encoding-health guard

v0.1.2: schema live migration completion — id-aliases frozen:true + COMPATIBILITY 1.0.0 row annotated
v0.1.1: Gitea transport surface de-MCP — REST+swagger sole canon (adapter recipes, terminology map, review probes)
2026-09-16 13:13:18 +08:00 · 2026-09-15 15:09:47 +08:00 · 2026-09-15 09:59:04 +08:00
30 changed files with 641 additions and 479 deletions
@@ -8,7 +8,7 @@ the corpus internally consistent and publish-ready.
 The corpus does not assume any specific forge (GitHub / Gitea / GitLab),
 ticketing, or CI system. System-specific behavior lives behind an explicit
 adapter contract (`core/adapters/`), so the same core can be adopted by any
-octopus instance — or any other agent platform — with its own adapters.
+octopus instance 鈥?or any other agent platform 鈥?with its own adapters.
 ## Layout
@@ -20,7 +20,7 @@ octopus instance — or any other agent platform — with its own adapters.
 | `core/templates/` | Artifact templates (DAG, iteration docs) |
 | `core/schemas/` | JSON schemas under the public namespace `https://eightarms.net/octopus-workflow/schemas/` |
 | `core/adapters/` | Adapter contract: terminology SSOT + Gitea reference implementation |
-| `core/CORE-MANIFEST.json` | Registry of core↔instance mappings and sync semantics (verbatim / verbatimDir / rewritten / split / core-only) |
+| `core/CORE-MANIFEST.json` | Registry of core鈫攊nstance mappings and sync semantics (verbatim / verbatimDir / rewritten / split / core-only) |
 | `examples/` | Organization-agnostic narrative essays referencing the core |
 | `guards/` | Standalone drift guards (bun + node stdlib only) |
@@ -32,6 +32,7 @@ Runnable inside this repo with [bun](https://bun.sh), no install step needed:
 bun run check:core-cohesion    # corpus structural invariants
 bun run check:core-p1          # publish-readiness neutrality (no org-internal links)
 bun run delink:core -- --check # no replaceable org-internal refs remain
 bun run check:encoding-health # core/ text is clean UTF-8 (no GBK mojibake)
 ```
 The instance-side guards (`check-core-parity`, `check-schema-ids`,
@@ -9,8 +9,8 @@ Core 与 octopus 实例（dogfood）之间的兼容性契约。随各 Increment
 | core 版本                                   | 对应 octopus 侧状态                                                                                                                                       | 兼容说明                                                                                                                                                              |
 | ------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | 0.x（Increment 1–4：骨架 + G0–G4 全量迁移） | octopus 实例 `.octopus/` 为消费镜像；core 与 dogfood 内容逐字/改写对齐                                                                                    | core 是 SSOT 权威副本；dogfood 经 `script/core-sync.sh` 单向同步。schema 尚未迁入 core。                                                                              |
-| 0.x（Increment 5：schema $id 迁移四件套）   | dogfood `.octopus/schemas/*.json` 的 `$id` **保持旧命名空间不动**（活系统仍引用）；core 侧 `$id` 已迁至 `https://eightarms.net/octopus-workflow/schemas/` | 双轨期：core schema 与 dogfood schema 是**不同 $id 的两份文件**（manifest 登记为 `rewritten`，不逐字同步）。活归档 run 的 index.json 携带旧 $id，读取侧经别名表解析。 |
+| 0.x（Increment 5：schema $id 迁移四件套）   | dogfood `.octopus/schemas/*.json` 的 `$id` 曾**保持旧命名空间不动**（活系统仍引用）；core 侧 `$id` 已迁至 `https://eightarms.net/octopus-workflow/schemas/` | 双轨期：core schema 与 dogfood schema 是**不同 $id 的两份文件**（manifest 登记为 `rewritten`，不逐字同步）。活归档 run 的 index.json 携带旧 $id，读取侧经别名表解析。**注记（2026-09）：live 迁移已完成——dogfood 侧已切新命名空间，双轨结束**。 |
-| 1.0.0（首个 semver 发布，规划中）           | 发布仓创建；live 迁移（dogfood 侧切新命名空间）完成                                                                                                       | `id-aliases.json` 置 `frozen: true`——$id 一经发布不可变（v3 §G）。别名保留 ≥2 个 major 版本。                                                                         |
+| 1.0.0（首个 semver 发布）                   | 发布仓创建；live 迁移（dogfood 侧切新命名空间）已完成（2026-09）                                                                                          | `id-aliases.json` 已置 `frozen: true`（2026-09）——$id 一经发布不可变（v3 §G）。别名保留 ≥2 个 major 版本。                                                                  |
 ## builtin overlay 语料兼容
@@ -90,7 +90,7 @@ G0–G4 批次已完成全量迁移（14 规则、17 技能整目录、\_shared
 - **HARD**（全 core 生效，含 adapters）：实例主机名、内网 IP 段、实例
  配置路径——实例机密与实例专有地址任何 core 文件不得出现。
 - **SOFT**（`core/adapters/**` 豁免）：`.octopus/`、`packages/octopus`、
-  MCP 工具名、工作树路径等实例绑定内容——adapter 目录是 Gitea 参考
+  后端绑定内容（REST 端点、工作树路径等）——adapter 目录是 Gitea 参考
  实现，允许承载；其余 core 文件不得出现。
 G0 三份规则是从实例规则**逐字复制**的，规则正文里出现实例路径字样属
@@ -9,10 +9,10 @@
 | --- | --- |
 | 工单后端（ticket backend） | Gitea |
 | Tier-2 工件库 | Gitea wiki |
-| 工单评论 API（ticket backend 评论接口） | `gitea_issue_comment__*` |
+| 工单评论 API（ticket backend 评论接口） | Gitea REST 评论端点族：`GET/POST /repos/{owner}/{repo}/issues/{index}/comments`、`PATCH /repos/{owner}/{repo}/issues/comments/{id}` |
-| wiki 读写 API（Tier-2 工件库读写接口） | `gitea_wiki__*` |
+| wiki 读写 API（Tier-2 工件库读写接口） | Gitea REST wiki 端点族：`wiki/pages` GET、`wiki/page/{pageName}` GET/PATCH、`wiki/new` POST（路径前缀 `/api/v1/repos/{owner}/{repo}/`） |
-| 看板移动 API（工单看板列迁移接口） | `gitea_column__move_issue` |
+| 看板移动 API（工单看板列迁移接口） | Gitea REST projects 相关端点（经 `swagger.v1.json` 查询后调用，勿臆造路径） |
-| 项目看板 API（工单面板管理接口） | `gitea_project__*` |
+| 项目看板 API（工单面板管理接口） | Gitea REST projects/columns 端点族：`GET /repos/{owner}/{repo}/projects`、`GET /repos/{owner}/{repo}/projects/{project_id}/columns` |
 | 路由解析工具（Step 0 路由门依赖） | `route_resolver` |
 | 会话工作树路径（并发分支工作区根） | `<worktrees-root>` |
 | 测试命令·变更集（本地前置检查） | `bun run test:changed` |
@@ -2,34 +2,37 @@
 > Gitea adapter 参考实现（Increment 3，自 dogfood 源
 > `_shared/gitea-write-patterns.md` 拆分上提）。本目录承载后端绑定的
-> API 形态（MCP 工具名、REST 端点、curl 形态）；页名规范与寻址语义
+> API 形态（REST 端点 + swagger 契约，curl 形态）；页名规范与寻址语义
 > 是后端中立契约，见 `core/rules/artifact-addressing.md`（本文不重复）。
 > 实例基址由实例配置提供（下文 `<gitea-base-url>`），见
-> `core/adapters/TERMINOLOGY.md`。
+> `core/adapters/TERMINOLOGY.md`。认证一律 `-H "Authorization: token <token>"`；
 > 端点契约以 `<gitea-base-url>/swagger.v1.json` 为唯一正典（按需 jq 提取，
 > 见 `core/skills/gitea-rest/`）。
 Owner/repo 固定为 `Octopus/octopus`。所有 wiki 页名遵循 Core 契约
 `{slug}/{type}-{seq:02d}-{title}`（例外页全枚举见 artifact-addressing.md）。
 ## Wiki URL 构造 — html_url 规则
-**黄金规则：绝不手工拼接 wiki URL。** `gitea_wiki__create_page` /
+**黄金规则：绝不手工拼接 wiki URL。** `POST .../wiki/new`、
-`gitea_wiki__get_page` / `gitea_wiki__list_pages` 响应中的 `html_url`
+`GET .../wiki/page/{mangled-name}`、`GET .../wiki/pages` 响应中的
-字段是唯一权威链接，发布时捕获并原样复用。`page_name` → `html_url`
+`html_url` 字段是唯一权威链接，发布时捕获并原样复用。页名 →
-的变换不可推导（`/`→`%2F`、含斜杠页名带 `.-` 尾缀、CJK 百分号编码），
+`html_url` 的变换不可推导（`/`→`%2F`、含斜杠页名带 `.-` 尾缀、CJK
-必须读 API。
+百分号编码），必须读 API。
 **两种标识符勿混淆**：
 | 标识符 | 是什么 | 用途 |
-| ----------- | ------------------------------------ | ---------------------------------------- |
+| ------ | ------ | ---- |
-| `page_name` | 原始页标识；字面 `/`、无主机、无编码 | wiki MCP 工具的 `page_name`/`title` 参数 |
+| 逻辑页名（`title`） | 原始页标识；字面 `/`、无主机、无编码 | 写侧：`POST .../wiki/new` 的 `title`；`PATCH` 省略 `title` 保名 |
 | mangled `pageName`（`sub_url`） | 后端改写的存储名（含 `%2F` 编码与 `.-` 尾缀） | 读侧/改侧路径参数：先 `GET .../wiki/pages` 拿 `sub_url`，**原样**用于 `wiki/page/{pageName}`，绝不手工拼 |
 | `html_url` | 后端生成的完整可点击 URL | markdown 链接、`target_url`、PR 正文 |
 **去向**：
 - **工件索引位置列** — 一个单元格同时存两者：
-  ``[`{page_name}`]({html_url})``。链接文本供读侧调
+  ``[`{page_name}`]({html_url})``。链接文本供读侧回读该页，href 供人
-  `gitea_wiki__get_page`，href 供人点击（见 Pattern 10）。
+  点击（见 Pattern 10）。
 - **commit-status `target_url`** — 终报页的 `html_url`（见 Pattern 8）。
 - **页内交叉链接** — 用 `html_url`。
@@ -37,38 +40,56 @@ Owner/repo 固定为 `Octopus/octopus`。所有 wiki 页名遵循 Core 契约
 ## Pattern 1: create-wiki-page
 ```bash
 curl -fsS -X POST "<gitea-base-url>/api/v1/repos/Octopus/octopus/wiki/new" \
  -H "Authorization: token <token>" -H "Content-Type: application/json" \
  -d '{
    "title": "{slug}/{type}-{seq:02d}-{title}",
    "content_base64": "<base64(内容)>",
    "message": "{可选 commit message}"
  }'
 ```
-gitea_wiki__create_page(owner="Octopus", repo="octopus",
+
-  title="{slug}/{type}-{seq:02d}-{title}",
+**base64 陷阱（强制注明）**：wiki 写接口只认 `content_base64`；传
-  content="{内容}",
+`content` 会被静默忽略（无报错、返回 2xx，页面存成 0 字节）。正文必须
-  message="{可选 commit message}")
+先 base64 编码，且发布后回读确认非空。
 ```
 **发布→验证（强制）**：发布后立刻回读确认存在且内容一致：
-```
+```bash
-gitea_wiki__get_page(owner="Octopus", repo="octopus", page_name="{同 title}")
+# 1. 列页拿 mangled sub_url（绝不手工拼 mangled name）
 curl -fsS -H "Authorization: token <token>" \
  "<gitea-base-url>/api/v1/repos/Octopus/octopus/wiki/pages"
 # 2. 用返回的 sub_url 原样读页
 curl -fsS -H "Authorization: token <token>" \
  "<gitea-base-url>/api/v1/repos/Octopus/octopus/wiki/page/{sub_url}"
 ```
-404 / 内容不一致 → 修复后重发。页名冲突（409）→ 该页已存在，改用
+404 / 内容为空或不一致 → 修复后重发。页名冲突（409）→ 该页已存在，
-Pattern 2 update，绝不另发新页。响应的 `html_url` 立即捕获复用。
+改用 Pattern 2 update，绝不另发新页。响应的 `html_url` 立即捕获复用。
 ## Pattern 2: update-wiki-page
-```
+```bash
-gitea_wiki__update_page(owner="Octopus", repo="octopus",
+curl -fsS -X PATCH "<gitea-base-url>/api/v1/repos/Octopus/octopus/wiki/page/{sub_url}" \
-  page_name="{页名}",
+  -H "Authorization: token <token>" -H "Content-Type: application/json" \
-  content="{新内容}",
+  -d '{
-  message="{commit message}")
+    "content_base64": "<base64(新内容)>",
    "message": "{commit message}"
  }'
 ```
-更新后再回读验证；409 冲突 → 拉最新内容手工合并后重试。
+路径参数用 mangled `sub_url`（先 `GET .../wiki/pages` 获取，原样使用）。
 **省略 `title` 保持页名不变**——只发 `content_base64`+`message`。
 同样只认 `content_base64`（`content` 会静默存 0 字节页）。更新后再回读
 验证；409 冲突 → 拉最新内容手工合并后重试。
 ## Pattern 3: create-issue
-```
+```bash
-gitea_issue__create(owner="Octopus", repo="octopus",
+curl -fsS -X POST "<gitea-base-url>/api/v1/repos/Octopus/octopus/issues" \
-  title="{标题}", body="{正文}", labels=["{label}"])
+  -H "Authorization: token <token>" -H "Content-Type: application/json" \
  -d '{"title":"{标题}","body":"{正文}","labels":[{label_id}]}'
 ```
 ### 工单交叉链接（强制）
@@ -86,9 +107,10 @@ gitea_issue__create(owner="Octopus", repo="octopus",
 ## Pattern 4: update-issue
-```
+```bash
-gitea_issue__update(owner="Octopus", repo="octopus",
+curl -fsS -X PATCH "<gitea-base-url>/api/v1/repos/Octopus/octopus/issues/{index}" \
-  index={issue_number}, body="{正文}", state="{open|closed}", ...)
+  -H "Authorization: token <token>" -H "Content-Type: application/json" \
  -d '{"body":"{正文}","state":"{open|closed}"}'
 ```
 原位更新正文（checklist 勾选、live 状态表维护）；关闭工单即触发
@@ -96,9 +118,10 @@ gitea_issue__update(owner="Octopus", repo="octopus",
 ## Pattern 5: add-issue-comment
-```
+```bash
-gitea_issue_comment__create(owner="Octopus", repo="octopus",
+curl -fsS -X POST "<gitea-base-url>/api/v1/repos/Octopus/octopus/issues/{index}/comments" \
-  index={issue_number}, body="{评论正文}")
+  -H "Authorization: token <token>" -H "Content-Type: application/json" \
  -d '{"body":"{评论正文}"}'
 ```
 首次评论后捕获返回的 `comment_id`——后续对同一逻辑评论的更新必须走
@@ -107,33 +130,42 @@ Pattern 6 原位 edit，绝不再 create。用于：评审综合（Synthesis）
 ## Pattern 6: edit-issue-comment
-```
+```bash
-gitea_issue_comment__edit(owner="Octopus", repo="octopus",
+curl -fsS -X PATCH "<gitea-base-url>/api/v1/repos/Octopus/octopus/issues/comments/{comment_id}" \
-  comment_id={comment_id}, body="{新正文}")
+  -H "Authorization: token <token>" -H "Content-Type: application/json" \
  -d '{"body":"{新正文}"}'
 ```
 单评论聚合不变量（工件索引、当前状态表等）的执行手段。
 ## Pattern 7: move-issue-to-column
-```
+看板列迁移（Todo → In Progress → Review → Done）。projects/columns
-gitea_column__move_issue(owner="Octopus", repo="octopus",
+发现用 REST；「把工单移到列」的操作端点语义复杂，经 swagger 查询后
-  project_id={project_id}, column_id={column_id}, index={issue_number})
+调用，不臆造路径：
 ```
-看板列迁移（Todo → In Progress → Review → Done）。
+```bash
 # 列出 repo 级 projects（projects 仅 repo 级，无 org/user 级端点）
 curl -fsS -H "Authorization: token <token>" \
  "<gitea-base-url>/api/v1/repos/Octopus/octopus/projects"
 # 列某 project 的 columns
 curl -fsS -H "Authorization: token <token>" \
  "<gitea-base-url>/api/v1/repos/Octopus/octopus/projects/{project_id}/columns"
 # 移动工单到列：先经 swagger.v1.json 查询 projects 相关端点后调用
 curl -s <gitea-base-url>/swagger.v1.json -o /tmp/gitea-sw.json
 jq -r '.paths | keys[]' /tmp/gitea-sw.json | grep projects
 ```
 ## Pattern 7.5: move-issue-to-pipeline-stage
 管线阶段板列（Pipeline Stages board column）承载阶段迁移——阶段转移
 落到板列，**不落** `## 当前状态` 行（该表只承载 PR / 评审 / CI 行与
-非阶段阻塞项）。列序列按管线阶段定义；移动用 Pattern 7 同款
+非阶段阻塞项）。列序列按管线阶段定义；移动与 Pattern 7 同款
-`gitea_column__move_issue`，column 由 `gitea_project__list` /
+（projects/columns 经 REST + swagger 发现，同上）。
 `gitea_column__list` 发现。
-## Pattern 8: post-commit-status（REST 回退）
+## Pattern 8: post-commit-status
-MCP 工具缺席时用 REST 直发 commit status（评审综合的 Tier-2 落点）：
+commit status 直发 REST（评审综合的 Tier-2 落点）：
 ```bash
 curl -X POST "<gitea-base-url>/api/v1/repos/Octopus/octopus/statuses/{sha}" \
@@ -153,16 +185,19 @@ merge 前读回验证：`GET /commits/{PR_SHA}/status`。
 ## Pattern 9: create-iteration-board
-```
+```bash
-gitea_project__create(owner="Octopus", repo="octopus",
+# 建 project（board）：先经 swagger 查询 create 端点契约
-  title="{slug} — Iteration {N}", description="…")
+curl -s <gitea-base-url>/swagger.v1.json -o /tmp/gitea-sw.json
-gitea_column__create(owner="Octopus", repo="octopus",
+jq '.paths["/repos/{owner}/{repo}/projects"].post' /tmp/gitea-sw.json
-  project_id={project_id}, title="Todo")
+# 随后 POST 建板（title="{slug} — Iteration {N}", description="…"）
-# … In Progress / Review / Done 同款
+# 再对每列（Todo / In Progress / Review / Done）：
 jq '.paths["/repos/{owner}/{repo}/projects/{project_id}/columns"].post' /tmp/gitea-sw.json
 # 随后 POST 建列
 ```
-DAG 聚合 agent 在单门 PASS 后建板；工单正文模板带 `## Node Reference`
+projects 仅 repo 级。DAG 聚合 agent 在单门 PASS 后建板；工单正文模板带
-（指向 `{epic-slug}/dag`）、`## Acceptance Criteria`、`## Parent`。
+`## Node Reference`（指向 `{epic-slug}/dag`）、`## Acceptance Criteria`、
 `## Parent`。
 ## Pattern 10: artifact-index（工单 ↔ 工件索引）
@@ -170,14 +205,15 @@ DAG 聚合 agent 在单门 PASS 后建板；工单正文模板带 `## Node Refer
 索引（反向链接 + compaction 恢复主路径；语义不变量见
 `core/rules/artifact-addressing.md` §4）：
-```
+```bash
 # 1. 找源工单（PR body / commit 的 Closes #N，或 DAG 父映射）；无则跳过
 # 2. 评论已存在？
-gitea_issue_comment__list(owner="Octopus", repo="octopus", index={issue_number})
+curl -fsS -H "Authorization: token <token>" \
  "<gitea-base-url>/api/v1/repos/Octopus/octopus/issues/{index}/comments"
 #    → 扫 body 以 "## 工件索引" 开头的评论（遗留前缀 "## Pipeline 工件追踪表"
 #      原位升级，不重复发）
-# 3a. 不存在 → gitea_issue_comment__create 初始化
+# 3a. 不存在 → POST .../issues/{index}/comments 初始化
-# 3b. 存在   → gitea_issue_comment__edit 原位编辑（复用 comment_id）
+# 3b. 存在   → PATCH .../issues/comments/{comment_id} 原位编辑（复用 comment_id）
 ```
 **索引表模板**（每工件一行；技能只增改自己的行，绝不删他技的行）：
@@ -191,11 +227,11 @@ gitea_issue_comment__list(owner="Octopus", repo="octopus", index={issue_number})
    | DAG | 任务图 | v1 (frozen) | [`{epic-slug}/dag`]({html_url}) | CORE |
 **位置列填充规则**：单元格 = markdown 链接 ``[`{page_name}`]({html_url})``；
-链接文本（page_name，字面 `/`）供读侧 `gitea_wiki__get_page`；href
+链接文本（逻辑页名，字面 `/`）供读侧先 `GET .../wiki/pages` 拿 `sub_url`
-（html_url）供人点击，必须取自 API 响应，严禁拼接。
+后回读该页；href（html_url）供人点击，必须取自 API 响应，严禁拼接。
 **重读优先级**：`CORE` = compaction 后必读（重读集 = 全部 CORE 行）；
-`ON-Demand` → `ON-DEMAND` = 按需；`ARCHIVE` = 已归档不读。
+`ON-DEMAND` = 按需；`ARCHIVE` = 已归档不读。
 **归档动作（archive-at-close）**：工单关闭时由关闭方 agent 原位 edit
 本评论——表格上方加归档横幅（`> **状态**: ✅ 已归档 — issue #{N} 关闭于
@@ -12,7 +12,12 @@ Owner/repo 固定 `Octopus/octopus`。compaction 恢复从 Pattern 6
 ## Pattern 1: read-wiki-page
 ```
-gitea_wiki__get_page(owner="Octopus", repo="octopus", page_name="{slug}/{page_title}")
+# 1. 列 wiki 页拿 mangled sub_url（绝不手工拼 mangled name）
 curl -fsS -H "Authorization: token <token>" \
  "<gitea-base-url>/api/v1/repos/Octopus/octopus/wiki/pages"
 # 2. 用返回的 sub_url 原样读页（含 %2F 编码与 .- 尾缀）
 curl -fsS -H "Authorization: token <token>" \
  "<gitea-base-url>/api/v1/repos/Octopus/octopus/wiki/page/{mangled-name}"
 ```
 常用页名（全量文法 + 例外枚举见 `core/rules/artifact-addressing.md` §2）：
@@ -45,7 +50,7 @@ gitea_wiki__get_page(owner="Octopus", repo="octopus", page_name="{slug}/{page_ti
 `{slug}/roadmap/{page}`、`{slug}/shared/{file}`、
 `{slug}/reviews/{roadmap|design-space|plan}/final/report`。
-**本地回退（wiki MCP 工具不可用）**：读本地 wiki 克隆（实例路径见
+**本地回退（REST 不可达时）**：读本地 wiki 克隆（实例路径见
 TERMINOLOGY.md）。wiki 文件名 URL 编码（`/`→`%2F`，`.md` 前可能带
 `.-`），用 glob 而非固定路径解析：
@@ -56,7 +61,8 @@ glob(pattern="*{slug}*{page-title}*.md", path="<local-wiki-clone>/{repo}-wiki/")
 ## Pattern 2: read-issue
 ```
-gitea_issue__get(owner="Octopus", repo="octopus", index={issue_number})
+curl -fsS -H "Authorization: token <token>" \
  "<gitea-base-url>/api/v1/repos/Octopus/octopus/issues/{issue_number}"
 ```
 读工单详情、正文、元数据（label、assignee、milestone、state）。
@@ -64,20 +70,28 @@ gitea_issue__get(owner="Octopus", repo="octopus", index={issue_number})
 ## Pattern 3: read-issue-comments
 ```
-gitea_issue_comment__list(owner="Octopus", repo="octopus", index={issue_number})
+curl -fsS -H "Authorization: token <token>" \
  "<gitea-base-url>/api/v1/repos/Octopus/octopus/issues/{issue_number}/comments?page=N&limit=50"
 ```
 分页用 `page`/`limit`（上限 50），响应头 `x-total-count` 给总数。
 读工单全部评论（评审结果、状态备注、讨论线程）。
 ## Pattern 4: read-project-column-issues
 看板列工单队列。project/column 发现：
 ```
-gitea_column__list_issues(owner="Octopus", repo="octopus",
+curl -fsS -H "Authorization: token <token>" \
-  project_id={project_id}, column_id={column_id})
+  "<gitea-base-url>/api/v1/repos/Octopus/octopus/projects"
 curl -fsS -H "Authorization: token <token>" \
  "<gitea-base-url>/api/v1/repos/Octopus/octopus/projects/{project_id}/columns"
 ```
-看板列工单队列。project/column 发现：`gitea_project__list` +
+「把工单移到列」等复杂操作：经 `swagger.v1.json`
-`gitea_column__list`。
+（`jq '.paths | keys[]' | grep projects`）查询 projects 相关端点后调用，
 不要臆造具体端点路径。projects 仅 repo 级（无 org/user 级端点）。
 ## Pattern 5: read-review-status（CLI）
@@ -103,17 +117,24 @@ success，1 = 有 failure/error。
 而非猜测页名路径：
 ```
-gitea_issue__get(owner="Octopus", repo="octopus", index={issue_number})
+# 1. 读源工单
-gitea_issue_comment__list(owner="Octopus", repo="octopus", index={issue_number})
+curl -fsS -H "Authorization: token <token>" \
-# 找 body 以 "## 工件索引"（遗留 "## Pipeline 工件追踪表"）开头的评论
+  "<gitea-base-url>/api/v1/repos/Octopus/octopus/issues/{issue_number}"
-gitea_wiki__get_page(owner="Octopus", repo="octopus", page_name=page_name)
+# 2. 拉评论列表，找 body 以 "## 工件索引"（遗留 "## Pipeline 工件追踪表"）开头的评论
 curl -fsS -H "Authorization: token <token>" \
  "<gitea-base-url>/api/v1/repos/Octopus/octopus/issues/{issue_number}/comments?page=N&limit=50"
 # 3. 按 CORE 行位置列逐个读工件页：先 GET .../wiki/pages 拿 sub_url（mangled
 #    name），再原样请求
 curl -fsS -H "Authorization: token <token>" \
  "<gitea-base-url>/api/v1/repos/Octopus/octopus/wiki/page/{mangled-name}"
 ```
 **位置列提取规则**：单元格形如 ``[`{page_name}`]({html_url})`` ——
 取**链接文本**（首个 `[` 与 `]` 之间、剥反引号）作为 page_name，不是
 href（含 `%2F`/`.-`，API 不认）。裸 page_name 单元格（无链接包裹）也
 接受：整格即 page_name。形如 `#comment-{id}` 的值改用
-`gitea_issue_comment__list` 读，不得喂给 `gitea_wiki__get_page`。
+`GET .../issues/{index}/comments` 拉工单评论列表后按 id 取，不得当作
 wiki 页名去读 wiki 端点。
 **重读规则**：重读集 = 全部 `CORE` 行；`ON-DEMAND` 行仅当前任务需要
 时读；绝不读 `ARCHIVE` 行。索引缺失（历史工单）→ 回退 issue body +
@@ -40,7 +40,8 @@ error, returns empty, or you cannot otherwise access a required resource, you
 MUST report the failure honestly. NEVER fabricate, invent, or hallucinate a
 plausible-looking result to fill the gap.
- An honest "I could not call `gitea_wiki__get_page`, so I cannot review
+- An honest "I could not reach the wiki read API (`GET
  <gitea-base-url>/api/v1/repos/{owner}/{repo}/wiki/pages`), so I cannot review
  dimension Y" is always correct. An honest failure beats a confident fiction.
 - Producing a complete, specific-looking structured result — review JSON with
  findings, severity levels, and file references, all invented — without a
@@ -52,5 +53,6 @@ plausible-looking result to fill the gap.
  it, you do not know it — say so.
 Origin: [org-internal #2115] root cause 5 / [org-internal #2118] — deepseek-v4-flash reviewers fabricated
-full review JSON when the `gitea_wiki__*` tools were unavailable to subagents.
+full review JSON when the wiki tool surface (MCP tooling at the time, now
 retired) was unavailable to subagents.
@@ -1,7 +1,7 @@
 {
  "namespace": "https://eightarms.net/octopus-workflow/schemas/",
-  "frozen": false,
+  "frozen": true,
-  "note": "发布仓创建时置 frozen: true——$id 一经发布不可变（v3 §G）；别名保留 ≥2 个 major 版本",
+  "note": "已置 frozen: true（live 迁移完成，2026-09）——$id 一经发布不可变（v3 §G）；别名保留 ≥2 个 major 版本",
  "aliases": [
    {
      "old": "https://eightarms.net/fourbroad/octopus/.octopus/schemas/port-analysis.schema.json",
@@ -2,7 +2,7 @@
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://eightarms.net/octopus-workflow/schemas/port-analysis.schema.json",
  "title": "Port Analysis Reviewer Output",
-  "description": "Schema for per-dimension port-analysis reviewer findings. Used by the large-port-pipeline source analysis review (Phase B1.5). The port source-analysis pipeline uses a deliberate three-value severity contract 鈥?BLOCKER / MAJOR / MINOR 鈥?and never emits INFO (matching implement/reference/large-port-pipeline.md and source-analysis.md, which name only those three). This is a documented exception to the canonical four-value set (BLOCKER / MAJOR / MINOR / INFO) in reviewer-output.schema.json and synthesis.schema.json.",
+  "description": "Schema for per-dimension port-analysis reviewer findings. Used by the large-port-pipeline source analysis review (Phase B1.5). The port source-analysis pipeline uses a deliberate three-value severity contract — BLOCKER / MAJOR / MINOR — and never emits INFO (matching implement/reference/large-port-pipeline.md and source-analysis.md, which name only those three). This is a documented exception to the canonical four-value set (BLOCKER / MAJOR / MINOR / INFO) in reviewer-output.schema.json and synthesis.schema.json.",
  "type": "object",
  "required": ["dimension", "findings"],
  "properties": {
@@ -19,7 +19,7 @@
    "max_rounds": {
      "type": "integer",
      "default": 3,
-      "description": "Per-skill bound: `review-artifact` skill (process target) = 3 (the roadmap/design/plan targets were archived 2026-08-21, [org-internal #3072] phase 3); `review-code` = 2 default / 3 high-risk (`workflow-routing.yaml` `review.max_rounds`, [org-internal #3567]). `review-dag` (the review-artifact skill's DAG single-gate target) binds per depth from `dag_metrics.review_depth`: D1 鈮?, D2 鈮?, D3 鈮?, D4 鈮? 鈥?D4 reaches round 4, exceeding the shared `review-artifact` default, so the DAG per-depth cap takes precedence (see review-artifact/SKILL.md review-dag Phase D MAX_ROUNDS). Set explicitly by the skill; default 3 is a fallback only."
+      "description": "Per-skill bound: `review-artifact` skill (process target) = 3 (the roadmap/design/plan targets were archived 2026-08-21, [org-internal #3072] phase 3); `review-code` = 2 default / 3 high-risk (`workflow-routing.yaml` `review.max_rounds`, [org-internal #3567]). `review-dag` (the review-artifact skill's DAG single-gate target) binds per depth from `dag_metrics.review_depth`: D1 ≤2, D2 ≤3, D3 ≤3, D4 ≤4 — D4 reaches round 4, exceeding the shared `review-artifact` default, so the DAG per-depth cap takes precedence (see review-artifact/SKILL.md review-dag Phase D MAX_ROUNDS). Set explicitly by the skill; default 3 is a fallback only."
    },
    "converged": {
      "type": "boolean"
@@ -17,7 +17,7 @@
    "reviewer_slot": {
      "type": "integer",
      "minimum": 1,
-      "description": "1-based slot of this reviewer WITHIN its dimension, when dim_split assigns >1 reviewer to the dimension (e.g. review-dag D3 TOPO:2, D4 TOPO:2 鈥?dim_split per `workflow-routing.yaml` dag.size_derivation.review_depth). Multi-reviewer dimensions write one file per slot: findings-{DIMENSION_CODE}-r{k}.json. Omitted for single-reviewer dimensions (file stays findings-{DIMENSION_CODE}.json). Preserves per-reviewer attribution for the retrospective overlap analysis ([org-internal #2996] step 1a)."
+      "description": "1-based slot of this reviewer WITHIN its dimension, when dim_split assigns >1 reviewer to the dimension (e.g. review-dag D3 TOPO:2, D4 TOPO:2 — dim_split per `workflow-routing.yaml` dag.size_derivation.review_depth). Multi-reviewer dimensions write one file per slot: findings-{DIMENSION_CODE}-r{k}.json. Omitted for single-reviewer dimensions (file stays findings-{DIMENSION_CODE}.json). Preserves per-reviewer attribution for the retrospective overlap analysis ([org-internal #2996] step 1a)."
    },
    "reviewer_count": {
      "type": "integer",
@@ -79,7 +79,7 @@
          "checklist_ref": {
            "type": "string",
            "pattern": "^[A-Z0-9]{2,6} \\d+(\\.\\d+)+(\\s*\\([^\\)]*\\))?(\\s*/\\s*[A-Z0-9]{2,6} \\d+(\\.\\d+)+(\\s*\\([^\\)]*\\))?)*$",
-            "description": "Checklist item reference, e.g. COR 1.1, INV 1.3, SEC 3.7.1, STD 8.4 鈥?dimension/section code followed by item number(s)."
+            "description": "Checklist item reference, e.g. COR 1.1, INV 1.3, SEC 3.7.1, STD 8.4 — dimension/section code followed by item number(s)."
          },
          "location": {
            "type": "string",
@@ -11,7 +11,7 @@
    "index": true,
    "working_notes": {
      "type": "string",
-      "description": "Final content of runs/{slug}/working-notes.md ([org-internal #2600]), inlined at archive time when the file exists. The one Tier 1 artifact whose CONTENT (not just digest) rides in the bundle 鈥?the run's narrative memory (decisions, dead ends, reviewer feedback), consumed by later retro probes and the notes-injection degradation path ([org-internal #2601]). Absent when the run kept no working notes."
+      "description": "Final content of runs/{slug}/working-notes.md ([org-internal #2600]), inlined at archive time when the file exists. The one Tier 1 artifact whose CONTENT (not just digest) rides in the bundle — the run's narrative memory (decisions, dead ends, reviewer feedback), consumed by later retro probes and the notes-injection degradation path ([org-internal #2601]). Absent when the run kept no working notes."
    },
    "review_history": {
      "type": "array",
@@ -55,7 +55,7 @@
        "stage": {
          "type": "string",
          "minLength": 1,
-          "description": "Review stage identifier matching the reviews/{stage}/ directory (e.g. code, review-dag, audit-process 鈥?the live values; design-space is a retired historical value)."
+          "description": "Review stage identifier matching the reviews/{stage}/ directory (e.g. code, review-dag, audit-process — the live values; design-space is a retired historical value)."
        },
        "rounds": { "type": "integer", "minimum": 1, "description": "Number of executed rounds." },
        "final_verdict": { "type": "string", "enum": ["PASS", "WARN", "FAIL"] },
@@ -109,7 +109,7 @@
      "type": "object",
      "additionalProperties": true,
      "required": ["slug", "state", "created_at"],
-      "description": "Legacy profile (schema_version 1 or absent): historical bundles AND current live-workspace runs 鈥?runs-meta.schema.json / runs-index.schema.json pin schema_version 1 today. Core fields type-checked when present; extra context properties (route/pr/node/kind/...) tolerated as-is. The v2 strict profile (below) is the migration target: it becomes the profile for new runs once the live-workspace schemas are bumped to emit schema_version 2 with the context bag.",
+      "description": "Legacy profile (schema_version 1 or absent): historical bundles AND current live-workspace runs — runs-meta.schema.json / runs-index.schema.json pin schema_version 1 today. Core fields type-checked when present; extra context properties (route/pr/node/kind/...) tolerated as-is. The v2 strict profile (below) is the migration target: it becomes the profile for new runs once the live-workspace schemas are bumped to emit schema_version 2 with the context bag.",
      "properties": {
        "schema_version": { "type": "integer", "minimum": 1 },
        "slug": { "type": "string", "pattern": "^[a-z0-9][a-z0-9-]*$" },
@@ -132,7 +132,7 @@
      "type": "object",
      "additionalProperties": false,
      "required": ["schema_version", "slug", "state", "created_at", "updated_at", "ticket"],
-      "description": "Strict profile (schema_version 2): closed core field set. Run-specific context (route/pr/node/task_node/...) goes in the context bag 鈥?the ONLY place for non-core fields.",
+      "description": "Strict profile (schema_version 2): closed core field set. Run-specific context (route/pr/node/task_node/...) goes in the context bag — the ONLY place for non-core fields.",
      "allOf": [
        {
          "if": { "properties": { "state": { "const": "archived" } }, "required": ["state"] },
@@ -2,7 +2,7 @@
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://eightarms.net/octopus-workflow/schemas/runs-index.schema.json",
  "title": "Tier 1 Run Artifact Index",
-  "description": "Schema for runs/{slug}/index.json 鈥?the artifact manifest for a Tier 1 local structured run. This is the compact-recovery entry point after compaction (compact never deletes local files). Parallel to, not a replacement for, the Tier 2 '## 宸ヤ欢绱㈠紩' issue comment. Authoritative layout: templates/runs-layout.md. Boundary rule: rules/two-tier-artifacts.md.",
+  "description": "Schema for runs/{slug}/index.json — the artifact manifest for a Tier 1 local structured run. This is the compact-recovery entry point after compaction (compact never deletes local files). Parallel to, not a replacement for, the Tier 2 '## 工件索引' issue comment. Authoritative layout: templates/runs-layout.md. Boundary rule: rules/two-tier-artifacts.md.",
  "type": "object",
  "additionalProperties": false,
  "required": ["schema_version", "slug", "artifacts"],
@@ -24,7 +24,7 @@
    "artifacts": {
      "type": "array",
      "items": { "$ref": "#/$defs/artifact" },
-      "description": "One entry per Tier 1 artifact in this run. Tier 2 artifacts (Gitea issue comments, wiki pages, commit status, PRs) are NEVER listed here 鈥?this index is Tier 1 only."
+      "description": "One entry per Tier 1 artifact in this run. Tier 2 artifacts (Gitea issue comments, wiki pages, commit status, PRs) are NEVER listed here — this index is Tier 1 only."
    }
  },
  "$defs": {
@@ -55,7 +55,7 @@
            "browser-evidence",
            "other"
          ],
-          "description": "Artifact category. 'meta'/'index' for the manifest files themselves; stage categories for produced artifacts. 'review-synthesis' marks a synthesis result artifact (round verdict) as distinct from 'synthesis-prompt' (the Phase B task prompt) and 'review-status' (the lifecycle file). 'precondition-gate' marks the review-code mechanical-green gate log. 'working-notes' is the cross-stage narrative memory file ([org-internal #2600]) 鈥?one file per run, appended by every role at close, registered once (stage/produced_by null: multi-stage, multi-role). 'browser-evidence' marks a browser evidence pack manifest ([org-internal #4497] N-03, browser/{session-id}/manifest.json 鈥?shared/pack-manifest-v1)."
+          "description": "Artifact category. 'meta'/'index' for the manifest files themselves; stage categories for produced artifacts. 'review-synthesis' marks a synthesis result artifact (round verdict) as distinct from 'synthesis-prompt' (the Phase B task prompt) and 'review-status' (the lifecycle file). 'precondition-gate' marks the review-code mechanical-green gate log. 'working-notes' is the cross-stage narrative memory file ([org-internal #2600]) — one file per run, appended by every role at close, registered once (stage/produced_by null: multi-stage, multi-role). 'browser-evidence' marks a browser evidence pack manifest ([org-internal #4497] N-03, browser/{session-id}/manifest.json — shared/pack-manifest-v1)."
        },
        "schema": {
          "type": ["string", "null"],
@@ -2,7 +2,7 @@
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://eightarms.net/octopus-workflow/schemas/runs-meta.schema.json",
  "title": "Tier 1 Run Metadata",
-  "description": "Schema for runs/{slug}/meta.json 鈥?run metadata for a Tier 1 local structured run. Authoritative layout: templates/runs-layout.md. Boundary rule: rules/two-tier-artifacts.md. State transitions active -> archived at close (archive-at-close).",
+  "description": "Schema for runs/{slug}/meta.json — run metadata for a Tier 1 local structured run. Authoritative layout: templates/runs-layout.md. Boundary rule: rules/two-tier-artifacts.md. State transitions active -> archived at close (archive-at-close).",
  "type": "object",
  "additionalProperties": false,
  "required": [
@@ -89,12 +89,12 @@
    "created_at": {
      "type": "string",
      "format": "date-time",
-      "description": "RFC 3339 timestamp 鈥?run creation."
+      "description": "RFC 3339 timestamp — run creation."
    },
    "updated_at": {
      "type": "string",
      "format": "date-time",
-      "description": "RFC 3339 timestamp 鈥?last metadata mutation."
+      "description": "RFC 3339 timestamp — last metadata mutation."
    },
    "closed_at": {
      "type": ["string", "null"],
@@ -2,7 +2,7 @@
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://eightarms.net/octopus-workflow/schemas/workflow-routing.schema.json",
  "title": "Workflow Routing Table",
-  "description": "Schema for workflow-routing.yaml 鈥?type-driven (Kind/*) process selection. Referenced by rules/workflow-routing.md and the auto-approve rule. When this schema and the rules markdown disagree, the YAML (validated by this schema) is authoritative.",
+  "description": "Schema for workflow-routing.yaml — type-driven (Kind/*) process selection. Referenced by rules/workflow-routing.md and the auto-approve rule. When this schema and the rules markdown disagree, the YAML (validated by this schema) is authoritative.",
  "type": "object",
  "additionalProperties": false,
  "required": ["version", "default", "routes"],
@@ -23,7 +23,7 @@
  "$defs": {
    "stage": {
      "type": "string",
-      "description": "A pipeline stage identifier 鈥?the 5 live gates (post-[org-internal #3072] phase 3, 2026-08-21): review-dag, review-code, verify, audit-process, merge-pr. Production-phase names (requirements, design, roadmap, implement) and the 7 retired stage ids (roadmap-exit, review-roadmap, requirements-exit, design-exit, review-design-space, review-iteration-plan, plan-iterations) are no longer valid anywhere 鈥?the sizing block that consumed the phase names was retired the same ruling.",
+      "description": "A pipeline stage identifier — the 5 live gates (post-[org-internal #3072] phase 3, 2026-08-21): review-dag, review-code, verify, audit-process, merge-pr. Production-phase names (requirements, design, roadmap, implement) and the 7 retired stage ids (roadmap-exit, review-roadmap, requirements-exit, design-exit, review-design-space, review-iteration-plan, plan-iterations) are no longer valid anywhere — the sizing block that consumed the phase names was retired the same ruling.",
      "enum": ["review-dag", "review-code", "verify", "audit-process", "merge-pr"]
    },
    "entry": {
@@ -56,20 +56,20 @@
        "preflight": {
          "type": "array",
          "items": { "$ref": "#/$defs/preflightItem" },
-          "description": "Evidence-based producer pre-flight checklist ([org-internal #2599]) 鈥?landed by a human from retrospective PRE-FLIGHT PROPOSAL rows. Absent/empty = no injection. Cap is governed by preflight.max_items (policy), not the schema."
+          "description": "Evidence-based producer pre-flight checklist ([org-internal #2599]) — landed by a human from retrospective PRE-FLIGHT PROPOSAL rows. Absent/empty = no injection. Cap is governed by preflight.max_items (policy), not the schema."
        },
        "notes": { "type": "string" },
        "effort": {
          "type": "string",
          "enum": ["low", "high", "max"],
-          "description": "Reasoning-effort hint for this route (llm-latency phase 2): maps onto the active model's variant table when it exposes one (GLM-5.2+ low/high/max); fail-open otherwise. Reserve `low` for genuinely lightweight routes (direct-edit, no pipeline) 鈥?reasoning dominates GLM-5.3 generation latency."
+          "description": "Reasoning-effort hint for this route (llm-latency phase 2): maps onto the active model's variant table when it exposes one (GLM-5.2+ low/high/max); fail-open otherwise. Reserve `low` for genuinely lightweight routes (direct-edit, no pipeline) — reasoning dominates GLM-5.3 generation latency."
        }
      }
    },
    "preflightPolicy": {
      "type": "object",
      "additionalProperties": false,
-      "description": "Thresholds for the retro 鈫?routes.{Kind}.preflight evidence loop ([org-internal #2599]). Authoritative values live here; the retrospective consults this block, it does not restate the numbers.",
+      "description": "Thresholds for the retro → routes.{Kind}.preflight evidence loop ([org-internal #2599]). Authoritative values live here; the retrospective consults this block, it does not restate the numbers.",
      "properties": {
        "max_items": { "type": "integer", "minimum": 1 },
        "min_sample": { "type": "integer", "minimum": 0 },
@@ -86,7 +86,7 @@
        "item": { "type": "string", "description": "One checklist line the Producer verifies before implementing." },
        "evidence": {
          "type": "string",
-          "description": "Retro reference justifying the item, e.g. 'retro [org-internal #2599]: COR 脳 unhandled-null, 5/8 first-round FAILs on Kind/Bug'."
+          "description": "Retro reference justifying the item, e.g. 'retro [org-internal #2599]: COR × unhandled-null, 5/8 first-round FAILs on Kind/Bug'."
        },
        "added_cycle": {
          "type": "string",
@@ -97,7 +97,7 @@
    "filing": {
      "type": "object",
      "additionalProperties": false,
-      "description": "Filing policy (绔嬫/鐧昏绛栫暐). sprint-mode ([org-internal #3007]): when true, verify Phase 5.5 promotes registry rows to tickets in sprint mode only. work-ticket-wip-cap ([org-internal #3005] G3): open non-TD work tickets beyond this count require scheduling evidence, else they stay registry rows.",
+      "description": "Filing policy (立案/登记策略). sprint-mode ([org-internal #3007]): when true, verify Phase 5.5 promotes registry rows to tickets in sprint mode only. work-ticket-wip-cap ([org-internal #3005] G3): open non-TD work tickets beyond this count require scheduling evidence, else they stay registry rows.",
      "properties": {
        "sprint-mode": {
          "type": "boolean",
@@ -113,7 +113,7 @@
    "review": {
      "type": "object",
      "additionalProperties": false,
-      "description": "Review round budget (process-diet P0b, [org-internal #3567]/TD-564): a tail cut, not the norm 鈥?at budget without convergence, STOP; residual findings flow to the TD registry. High risk = a BLOCKER survived a round or the diff touches a frozen cross-session contract.",
+      "description": "Review round budget (process-diet P0b, [org-internal #3567]/TD-564): a tail cut, not the norm — at budget without convergence, STOP; residual findings flow to the TD registry. High risk = a BLOCKER survived a round or the diff touches a frozen cross-session contract.",
      "required": ["max_rounds"],
      "properties": {
        "max_rounds": {
@@ -152,7 +152,7 @@
        "preflight": {
          "type": "array",
          "items": { "$ref": "#/$defs/preflightItem" },
-          "description": "Evidence-based pre-flight checklist for the DAG route ([org-internal #2905] 鏂规 3) 鈥?same item shape as routes.{Kind}.preflight ([org-internal #2599]). Landed by a human from retrospective PRE-FLIGHT PROPOSAL rows, including the 'REQ 脳 late-discovery' root cause (requirements found only after the DAG froze: DAG oversize signals, demo-period feedback). Consumed by analyze-dag (the route's entry skill) before decomposition. Absent/empty = no injection. Optional 鈥?deliberately NOT in dagRoute.required (spec-02 搂2.8 frozen required array unchanged). Cap governed by preflight.max_items (policy), not the schema."
+          "description": "Evidence-based pre-flight checklist for the DAG route ([org-internal #2905] 方案 3) — same item shape as routes.{Kind}.preflight ([org-internal #2599]). Landed by a human from retrospective PRE-FLIGHT PROPOSAL rows, including the 'REQ × late-discovery' root cause (requirements found only after the DAG froze: DAG oversize signals, demo-period feedback). Consumed by analyze-dag (the route's entry skill) before decomposition. Absent/empty = no injection. Optional — deliberately NOT in dagRoute.required (spec-02 §2.8 frozen required array unchanged). Cap governed by preflight.max_items (policy), not the schema."
        }
      }
    },
@@ -183,7 +183,7 @@
        "replaces": {
          "type": "array",
          "items": { "type": "string" },
-          "description": "Historical documentation of which legacy gates the single gate replaced ([org-internal #3072] phase 3 retired them) 鈥?free-form strings, not the live stage vocabulary."
+          "description": "Historical documentation of which legacy gates the single gate replaced ([org-internal #3072] phase 3 retired them) — free-form strings, not the live stage vocabulary."
        },
        "depth_from": { "type": "string", "enum": ["size_derivation"] },
        "never_trim": { "type": "boolean" }
@@ -201,7 +201,7 @@
          "items": { "type": "string", "enum": ["Kind/Epic", "Kind/Feature"] },
          "uniqueItems": true,
          "minItems": 1,
-          "description": "Ticket kinds whose DAG children reference them as ## 鐖剁骇 / Parent ([org-internal #3061] Phase 2 / TD-388: Kind/Feature added alongside Kind/Epic)."
+          "description": "Ticket kinds whose DAG children reference them as ## 父级 / Parent ([org-internal #3061] Phase 2 / TD-388: Kind/Feature added alongside Kind/Epic)."
        },
        "parent_aggregator": { "type": "boolean" }
      }
@@ -68,11 +68,12 @@ in `_shared/gitea-write-patterns.md`.
   in the Orchestrator instead of letting {DIMENSION_COUNT} parallel subagents
   each rediscover the gap:
-   - **Primary path**: confirm `gitea_wiki__*` tools are registered (the
+   - **Primary path**: confirm the Gitea REST API is reachable — probe
-     Orchestrator checks its own tool catalog; these tools are forwarded to
+      `GET <gitea-base-url>/api/v1/repos/{owner}/{repo}/wiki/pages` with
-     reviewer subagents when registered — [org-internal #2116] raised the tool cap 50→100 so
+      `-H "Authorization: token <token>"` (a 200 or 403 response means
-     they are present in normal runs). If available → continue to step 2.
+      reachable; anything else — timeout, connection refused, 5xx — is
-   - **Fallback path** (when `gitea_wiki__*` is NOT registered, e.g. a
+      unreachable). If reachable → continue to step 2.
    - **Fallback path** (when REST is unreachable, e.g. a
      cross-repo scenario [org-internal #2115]): verify the **local wiki clone** at
     `<wiki-clone-root>/{repo}-wiki/` is readable —
     `glob(pattern="*.md", path="<wiki-clone-root>/{repo}-wiki/")`. If the clone
@@ -82,12 +83,13 @@ in `_shared/gitea-write-patterns.md`.
   - **Both unavailable → FAIL FAST**: post a `failure` commit status (state
     `"failure"`, context `pipeline/{REVIEW_TYPE}`, description naming the
     missing capability) and abort — do NOT enter parallel dispatch. Report the
-     gap so the environment can be fixed (register the wiki MCP server, or
+      gap so the environment can be fixed (restore Gitea REST reachability —
      token validity, network route — or
      populate `<wiki-clone-root>/{repo}-wiki/`).
-   This probe is belt-and-suspenders: RC1 (tool cap, [org-internal #2116]) already fixed the
+    This probe is belt-and-suspenders: it exists so a future
-   primary cause of missing `gitea_wiki__*` in subagents. It exists so a future
+    environment regression (REST unreachable, stale token) fails gracefully
-   environment regression fails gracefully with one clear message instead of N
+    with one clear message instead of N
    silent subagent aborts.
 2. Post an initial pending commit status via REST:
@@ -471,7 +473,9 @@ not the round-1 full set.
 3.5. **Gitea approval timing (mandatory when the PR needs a human approval
   gate)**: if the flow requests approval from a human reviewer on Gitea,
-   register the reviewer FIRST via `gitea_pull__add_reviewer`, wait for the
+    register the reviewer FIRST via
    `POST <gitea-base-url>/api/v1/repos/{owner}/{repo}/pulls/{index}/requested_reviewers`,
    wait for the
    `REQUEST_REVIEW` registration to be recorded, and only THEN ask the human
   to approve. Approving before the reviewer is registered produces
   `official: false` on the approval — the gate treats the PR as unapproved
@@ -65,7 +65,8 @@ Label: {DIMENSION_NAME}
 ## What You Must NOT Do
- Do NOT fabricate results. If a tool you need (e.g. `gitea_wiki__get_page`,
+- Do NOT fabricate results. If a tool you need (e.g. the Gitea REST call
  `GET <gitea-base-url>/api/v1/repos/{owner}/{repo}/wiki/pages`,
  `read`, `codegraph_*`) is unavailable, errors, or returns empty, report the
  failure honestly — emit a finding stating the dimension could not be
  reviewed due to the missing tool. NEVER invent findings, severities, or
@@ -1,6 +1,6 @@
 ---
 name: gitea-rest
-description: Use ONLY when an agent must call the Gitea REST API over HTTP (curl / fetch / HttpClient) 鈥?not for other gitea tooling (the retired gitea-mcp wrapper / gitea_* MCP tools). Covers auth schemes + token scopes, pagination, error format, this fork's specifics, copy-paste recipes for the daily loop (issues, PRs, comments, labels, releases, raw files), and the on-demand recipe for extracting any endpoint's definition from the auto-generated swagger spec (`/swagger.v1.json`) instead of keeping an endpoint catalog in context. This is the only supported Gitea API path 鈥?the gitea-mcp wrapper is retired.
+description: Use ONLY when an agent must call the Gitea REST API over HTTP (curl / fetch / HttpClient) — not for other gitea tooling (the retired gitea-mcp wrapper / gitea_* MCP tools). Covers auth schemes + token scopes, pagination, error format, this fork's specifics, copy-paste recipes for the daily loop (issues, PRs, comments, labels, releases, raw files), and the on-demand recipe for extracting any endpoint's definition from the auto-generated swagger spec (`/swagger.v1.json`) instead of keeping an endpoint catalog in context. This is the only supported Gitea API path — the gitea-mcp wrapper is retired.
 triggers:
  # Direct Gitea HTTP/REST. Composite "gitea rest"/"gitea api" to avoid
  # colliding with other gitea tooling.
@@ -11,20 +11,20 @@ triggers:
  - /api/v1
  - gitea swagger
  - swagger.v1.json
-  - 璋?gitea api
+  - 调gitea api
-  - gitea 鎺ュ彛
+  - gitea 接口
  - gitea rest api
 role: Producer
 ---
-> Core 涓珛鐗堬紙Increment 6a 鏀瑰啓锛夈€傛湰鏂囦欢鍚屾椂浣滀负 gitea adapter 鐨?**reference implementation** 绀轰緥锛坒rontmatter 鍘熸牱锛夛紱瀹炰緥鏈瀵圭収 `core/adapters/TERMINOLOGY.md`銆?
+> Core 中立版（Increment 6a 改写）。本文件同时作为 gitea adapter 的 **reference implementation** 示例（frontmatter 原样）；实例术语对照 `core/adapters/TERMINOLOGY.md`。
-# Gitea REST 鈥?conventions + on-demand endpoint lookup
+# Gitea REST — conventions + on-demand endpoint lookup
 Gitea ships a JSON REST API under **`/api/v1`**. The instance also publishes an
-**auto-generated OpenAPI spec at `/swagger.v1.json`** (~889KB, 316 endpoints) 鈥?
+**auto-generated OpenAPI spec at `/swagger.v1.json`** (~889KB, 316 endpoints) — 
 never load it whole into context; extract single endpoint definitions with jq
 (see "Endpoint lookup"). The spec is generated from this fork's code, so it is
-always current 鈥?no manually maintained catalog can drift.
+always current — no manually maintained catalog can drift.
 ## Quick start
@@ -37,7 +37,7 @@ curl -fsS -H "$AUTH" $BASE/api/v1/version    # => {"version":"1.22.0"}
 Inside a workspace container: `WORKSPACE_GIT_TOKEN` already carries the
 provisioned token, and the instance host resolves to the VPC-internal address
-(no EIP bandwidth cap) 鈥?use it as `TOKEN` directly.
+(no EIP bandwidth cap) — use it as `TOKEN` directly.
 ## Authentication
@@ -47,7 +47,7 @@ provisioned token, and the instance host resolves to the VPC-internal address
 | OAuth2 JWT            | `Authorization: bearer <jwt>`              | OAuth2-app token.                               |
 | Basic                 | `Authorization: Basic <base64(user:pass)>` | Server must enable it; 2FA needs `X-Gitea-OTP`. |
- Query-param token (`?token=`) is deprecated 鈥?avoid.
+- Query-param token (`?token=`) is deprecated — avoid.
 - `Sudo: <username>` header acts as another user (admin only).
 - Keep tokens out of git and out of process argv where possible: read from a
  file/env into a shell var at call time, not in a committed script.
@@ -55,21 +55,21 @@ provisioned token, and the instance host resolves to the VPC-internal address
 ## Token scopes (write implies read)
 Categories: `issue`, `repository`, `organization`, `user`, `notification`,
-`package`, `admin`, `misc`, `activitypub` 鈥?each as `read:X` / `write:X`.
+`package`, `admin`, `misc`, `activitypub` — each as `read:X` / `write:X`.
-HTTP method sets the level: **GET 鈫?read**, **POST/PUT/PATCH/DELETE 鈫?write**.
+HTTP method sets the level: **GET → read**, **POST/PUT/PATCH/DELETE → write**.
 A scope miss returns `403` with `token does not have at least one of required
-scope(s)...` 鈥?re-issue the token rather than widening other permissions.
+scope(s)...` — re-issue the token rather than widening other permissions.
 The full agent loop (push commits, create/merge PRs, comment) needs at minimum
 **`write:repository` + `write:issue`**. Workspace container tokens are
-provisioned `read:repository` by default 鈥?write operations fail with 403
+provisioned `read:repository` by default — write operations fail with 403
 until the operator widens the scope.
 ## Pagination
 - `page` (1-based, default 1), `limit` (default 30, **hard cap 50**).
 - `X-Total-Count` response header = total results.
- `Link: <url?page=2>; rel="next"` 鈥?walk `next` links until absent.
+- `Link: <url?page=2>; rel="next"` — walk `next` links until absent.
 - Some endpoints (commits, pulls) also set `X-Page` / `X-PerPage` /
  `X-PageCount` / `X-HasMore`.
@@ -78,12 +78,12 @@ until the operator widens the scope.
 Every error is `{"message":"...","url":".../api/swagger"}` with the matching
 status: `400` bad arg, `403` permission/scope, `404` not found or wrong BASE,
 `409` already exists, `413` too large, `422` malformed JSON / missing field.
-There is **no rate limiting** on `/api/v1` 鈥?don't expect `X-RateLimit-*`.
+There is **no rate limiting** on `/api/v1` — don't expect `X-RateLimit-*`.
 ## Endpoint lookup (swagger, on demand)
 For any endpoint not covered by the recipes below, pull the spec once per
-session and jq out just the definition you need (50鈥?00 tokens each):
+session and jq out just the definition you need (50–200 tokens each):
 ```sh
 curl -s $BASE/swagger.v1.json -o /tmp/gitea-sw.json
@@ -109,7 +109,7 @@ curl -fsS -X POST "$BASE/api/v1/repos/$OWNER/$REPO/issues" -H "$AUTH" -H 'Conten
  -d '{"title":"Bug: X fails","body":"steps...","labels":[12]}'
 ```
-**Comment on an issue / PR** (same path for both 鈥?PRs are issues by index)
+**Comment on an issue / PR** (same path for both — PRs are issues by index)
 ```sh
 curl -fsS -X POST "$BASE/api/v1/repos/$OWNER/$REPO/issues/42/comments" -H "$AUTH" \
@@ -130,48 +130,48 @@ curl -fsS -X POST "$BASE/api/v1/repos/$OWNER/$REPO/pulls/7/merge" -H "$AUTH" -H
  -d '{"Do":"merge","MergeTitleField":"feat: add X","MergeMessageField":"closes #7"}'
 ```
-**Merge returned 405? Read the response body 鈥?two distinct causes:**
+**Merge returned 405? Read the response body — two distinct causes:**
- `{"message":"head branch is behind the base branch"}` 鈥?the keep-mergeable
+- `{"message":"head branch is behind the base branch"}` — the keep-mergeable
  bot advanced main after your push, or Gitea's mergeable cache is stale.
  Fix: `git fetch origin main && git merge origin/main && git push` the head
-  branch, wait ~2s, retry the merge. (Recurring on this server 鈥?seen 3 PRs
+  branch, wait ~2s, retry the merge. (Recurring on this server — seen 3 PRs
  in a row on 2026-08-23.)
- `{"message":"The PR is already merged"}` 鈥?**treat as success**. The merge
+- `{"message":"The PR is already merged"}` — **treat as success**. The merge
  landed during a previous "failed" attempt (racy async recompute). Confirm
  with `GET .../pulls/7 | jq '.merged, .merge_commit_sha'` before assuming
  failure. Never re-push/re-create the PR on this signal.
-**Auth hygiene** 鈥?always pass the token via the `Authorization` header
+**Auth hygiene** — always pass the token via the `Authorization` header
 (`-H "Authorization: token $TOKEN"`), never embedded in a remote URL
 (`https://user:token@host/...`): it persists into `.git/config` and shell
 history. If a token leaks into a remote URL, rewrite the remote
 (`git remote set-url`) and rotate.
-**List PRs / changed files** 鈥?`GET .../pulls?state=open`, `GET .../pulls/7/files`
+**List PRs / changed files** — `GET .../pulls?state=open`, `GET .../pulls/7/files`
-**Search issues across repos** 鈥?`GET $BASE/api/v1/repos/issues/search?q=&type=pulls`
+**Search issues across repos** — `GET $BASE/api/v1/repos/issues/search?q=&type=pulls`
-**List labels** 鈥?`GET .../labels?limit=50 | jq '.[] | {name,color}'` (label create/update via POST/PATCH on the same path)
+**List labels** — `GET .../labels?limit=50 | jq '.[] | {name,color}'` (label create/update via POST/PATCH on the same path)
-**Raw file contents** 鈥?`GET .../raw/README.md` (plain text; the `contents/{path}` variant returns base64 in `.content`)
+**Raw file contents** — `GET .../raw/README.md` (plain text; the `contents/{path}` variant returns base64 in `.content`)
-**Create a release** 鈥?`POST .../releases {"tag_name":"v1.2.0","target":"main",...}`
+**Create a release** — `POST .../releases {"tag_name":"v1.2.0","target":"main",...}`
-**Create a wiki page** 鈥?`POST .../wiki/new {"title":"My Page","content_base64":"<b64>","message":"add page"}`. **`content_base64` is the ONLY field that writes body text** 鈥?this fork **silently ignores** the upstream-style `content` field on wiki create/update (no error, `201` returned, page saved 0 bytes; evidence [org-internal #3944]: commits f5eaf18/4f0217d/bad5880). `content` is valid only on the file API, never on wiki.
+**Create a wiki page** — `POST .../wiki/new {"title":"My Page","content_base64":"<b64>","message":"add page"}`. **`content_base64` is the ONLY field that writes body text** — this fork **silently ignores** the upstream-style `content` field on wiki create/update (no error, `201` returned, page saved 0 bytes; evidence [org-internal #3944]: commits f5eaf18/4f0217d/bad5880). `content` is valid only on the file API, never on wiki.
-**Read / edit / delete a wiki page** 鈥?`GET|PATCH|DELETE .../wiki/page/{pageName}`. **Read by the mangled name, not the logical title**: this fork rewrites stored filenames for titles containing `/`, spaces, or `:` (slash percent-encoded into the filename + a `.-` suffix 鈥?see [org-internal #3218]), so `GET /wiki/page/bugfix-3204/bugfix-report` 404s. Always `GET .../wiki/pages` first and use the returned `sub_url` **verbatim** (it already carries the `%2F` encoding and `.-` suffix). PATCH/DELETE take the same mangled `pageName`. For PATCH, **omit `title` to keep the page name** and send only `content_base64`+`message` (fixed in gitea `dev-421-g7ff56aec08`, [org-internal #3510] 鈥?before that a title-less PATCH silently renamed the page to `unnamed.md` and later edits deleted target pages). Same trap as create: a PATCH carrying `content` instead of `content_base64` returns `200` with a **0-byte page** ([org-internal #3944]) 鈥?always base64-encode the body and verify non-empty via a follow-up `GET`.
+**Read / edit / delete a wiki page** — `GET|PATCH|DELETE .../wiki/page/{pageName}`. **Read by the mangled name, not the logical title**: this fork rewrites stored filenames for titles containing `/`, spaces, or `:` (slash percent-encoded into the filename + a `.-` suffix — see [org-internal #3218]), so `GET /wiki/page/bugfix-3204/bugfix-report` 404s. Always `GET .../wiki/pages` first and use the returned `sub_url` **verbatim** (it already carries the `%2F` encoding and `.-` suffix). PATCH/DELETE take the same mangled `pageName`. For PATCH, **omit `title` to keep the page name** and send only `content_base64`+`message` (fixed in gitea `dev-421-g7ff56aec08`, [org-internal #3510] — before that a title-less PATCH silently renamed the page to `unnamed.md` and later edits deleted target pages). Same trap as create: a PATCH carrying `content` instead of `content_base64` returns `200` with a **0-byte page** ([org-internal #3944]) — always base64-encode the body and verify non-empty via a follow-up `GET`.
 ## This fork's specifics
- **Projects are repo-level only** 鈥?no `/orgs/.../projects` or `/users/.../projects` REST endpoints.
+- **Projects are repo-level only** — no `/orgs/.../projects` or `/users/.../projects` REST endpoints.
- **Aggregated inline review comments**: no single list-all endpoint 鈥?list
+- **Aggregated inline review comments**: no single list-all endpoint — list
  reviews, then fetch each review's `/comments`.
- Wiki REST = 6 method脳path combos on 4 paths (`new`, `page/{pageName}`
+- Wiki REST = 6 method×path combos on 4 paths (`new`, `page/{pageName}`
  GET/PATCH/DELETE, `pages`, `revisions/{pageName}`). This fork has **no**
  upstream `raw/{pageName}` or `pages/{pageName}` single-page endpoints, and
  `page/{pageName}` only matches the mangled filename (see the wiki recipe
-  above and [org-internal #3218]) 鈥?clone the wiki git repo (default branch `main`) only if
+  above and [org-internal #3218]) — clone the wiki git repo (default branch `main`) only if
  you need history beyond `/wiki/revisions` or bulk filename surgery.
 - The authoritative route table is `routers/api/v1/api.go` in the Gitea
  source; the human-readable docs UI is `<BASE>/api/swagger`.
@@ -180,4 +180,4 @@ history. If a token leaks into a remote URL, rewrite the remote
 Prefer `HttpClient` from `@effect/platform` with the same headers (see
 `rules/effect-rules` on the wiki). Outside Effect, `curl` / `Bun.fetch` are
-fine 鈥?the wire format is identical.
+fine — the wire format is identical.
@@ -1,94 +1,94 @@
 ---
 name: headless-session-ops
 description: >
-  Use ONLY when an agent must autonomously launch a headless main session 鈥?
+  Use ONLY when an agent must autonomously launch a headless main session — 
  create a session and drive agent generation over the HTTP `prompt_async`
-  endpoint with NO persistent client attached (Web UI / TUI absent) 鈥?OR
+  endpoint with NO persistent client attached (Web UI / TUI absent) — OR
  lifecycle-manage such a session afterwards: health-check polling, hung-stream
  diagnosis (state=generating + frozen message count), abort + re-wake rescue,
-  provider quota-wall recovery (worker killed mid-task by a usage limit 鈥?
+  provider quota-wall recovery (worker killed mid-task by a usage limit — 
  detect, re-wake on a known-good provider, inject facts), and fact-baseline
  injection to correct a stale worldview in a woken worker.
  This is the path used by in-session agents spawning sibling sessions,
  `octopus run --attach` non-interactive mode, and cron / CI drivers. Covers
-  the 3-step flow (create session 鈫?POST prompt_async WITH a known-good
+  the 3-step flow (create session → POST prompt_async WITH a known-good
-  `model` 鈫?poll `/session/:id/message` to verify generation), how to REUSE
+  `model` → poll `/session/:id/message` to verify generation), how to REUSE
  the current session's model for the new session, the model-field
  requirement, the directory default (current session's directory unless
  targeting another repo), and the ticket-driven recipe (launch a session
  seeded from issue #N). Do NOT use when a persistent client (Web UI / TUI)
-  is driving the session 鈥?those use the synchronous `prompt` endpoint and
+  is driving the session — those use the synchronous `prompt` endpoint and
  always send `model`.
 triggers:
-  # English 鈥?the brand phrases for headless launch.
+  # English — the brand phrases for headless launch.
  - headless session
  - launch session
  - prompt_async
  - prompt async
  - autonomous session
-  # English 鈥?the failure mode (agent sees a stalled session and needs to know why).
+  # English — the failure mode (agent sees a stalled session and needs to know why).
  - session not generating
  - session generation stuck
-  # English 鈥?ticket-driven launch.
+  # English — ticket-driven launch.
  - launch session for issue
  - launch session for ticket
  - spawn session for ticket
-  # English 鈥?patrol mode (delayed self-wake polling loops, [org-internal #3937]).
+  # English — patrol mode (delayed self-wake polling loops, [org-internal #3937]).
  - patrol loop
  - patrol mode
  - delayed wake
-  # Chinese 鈥?bare noun phrases (matches() is a contiguous substring).
+  # Chinese — bare noun phrases (matches() is a contiguous substring).
-  - 鎷夎捣涓讳細璇?
+  - 拉起主会话
-  - 鎷夎捣浼氳瘽
+  - 拉起会话
-  - 鑷不浼氳瘽
+  - 自治会话
-  - 鏃犲ご浼氳瘽
+  - 无头会话
-  # Chinese 鈥?patrol mode ([org-internal #3937]).
+  # Chinese — patrol mode ([org-internal #3937]).
-  - 宸℃妯″紡
+  - 巡检模式
-  - 寤惰繜鍞ら啋
+  - 延迟唤醒
-  - 浼氳瘽涓嶇敓鎴?
+  - 会话不生成
-  - 浼氳瘽鍗℃
+  - 会话卡死
-  - 涓哄伐鍗曟媺璧蜂細璇?
+  - 为工单拉起会话
-  - 宸ュ崟鎷夎捣浼氳瘽
+  - 工单拉起会话
-  # English 鈥?lifecycle (hung rescue, stale-worldview correction, [org-internal #2459]).
+  # English — lifecycle (hung rescue, stale-worldview correction, [org-internal #2459]).
  - abort session
  - revive session
  - session rescue
  - fact baseline
-  # English 鈥?quota-wall recovery ([org-internal #3669]): worker killed by provider usage limit.
+  # English — quota-wall recovery ([org-internal #3669]): worker killed by provider usage limit.
  - quota wall
  - usage limit reached
  - quota exhausted
  - switch provider
-  # Chinese 鈥?lifecycle ops ([org-internal #2459]).
+  # Chinese — lifecycle ops ([org-internal #2459]).
-  - 鍞ら啋浼氳瘽
+  - 唤醒会话
-  - 浼氳瘽鎸傛
+  - 会话挂死
-  - 浜嬪疄鍩虹嚎
+  - 事实基线
-  # Chinese 鈥?quota-wall recovery ([org-internal #3669]).
+  # Chinese — quota-wall recovery ([org-internal #3669]).
-  - 閰嶉澧?
+  - 配额墙
-  - 閰嶉鑰楀敖
+  - 配额耗尽
-  - 鐢ㄩ噺涓婇檺
+  - 用量上限
-  - 鎹緵搴斿晢
+  - 换供应商
 role: Producer
 ---
-> Core 涓珛鐗堬紙Increment 6a 鏀瑰啓锛屽師 deferHard verbatimDir锛夈€傛満鍒躲€佺粨鏋勪笌 frontmatter 淇濇寔锛涘疄渚嬫湳璇紙宸ュ叿鍚嶃€佽矾寰勩€佸伐鍗曞彿锛夋寜 `core/adapters/TERMINOLOGY.md` 缁戝畾鍒板叿浣撳疄渚嬨€?
+> Core 中立版（Increment 6a 改写，原 deferHard verbatimDir）。机制、结构与 frontmatter 保持；实例术语（工具名、路径、工单号）按 `core/adapters/TERMINOLOGY.md` 绑定到具体实例。
 # Headless Main Session Launch (prompt_async)
 Launch a **main session for a specific issue / work item from a headless
-context** 鈥?no Web UI, no TUI, just HTTP. This is the "fire-and-forget" path: an
+context** — no Web UI, no TUI, just HTTP. This is the "fire-and-forget" path: an
 agent inside another session, a cron job, a CI script, or `octopus run --attach`
 non-interactive mode all land here when they need to spin up a session that
 actually generates.
-## Directory convention 鈥?independent session in the current workspace, no worktree
+## Directory convention — independent session in the current workspace, no worktree
 The default is an **independent session sharing the current session's
-directory** 鈥?the repo you are already working in. No new worktree, no
+directory** — the repo you are already working in. No new worktree, no
 checkout, no extra `bun install` or `.codegraph/` rebuild. Session creation
 and worktree discipline are **orthogonal**: this skill only opens a session
 record pointed at a directory; whether the launched session later creates its
 own worktree is a _workflow_ decision (per the worktree-discipline rule) it
-makes when it starts actual work 鈥?not something the launcher does. One
+makes when it starts actual work — not something the launcher does. One
 exception: the **ticket-driven recipe** below, where claim-first ([org-internal #2297])
 requires the launcher to push the workflow branch before launch, making a
 pre-built worktree the claim carrier + ready workspace (see Pitfall #10
@@ -100,7 +100,7 @@ carve-out). So, unless a different repo / path is specifically targeted,
  from your own session record via `GET /session/$LAUNCHER_SID`). The new
  session runs independently in that same workspace. Pass an explicit
  different `?directory=` only when the new session must work in another
-  **repo** 鈥?never a worktree of the same repo. The Web UI sidebar groups
+  **repo** — never a worktree of the same repo. The Web UI sidebar groups
  sessions by directory (`sidebar-project.tsx` per-workspace
  `workspaceSessions(directory)`, fetched via `session.list({ directory })`),
  so a session pointed at a worktree disappears from the workspace the creator
@@ -109,23 +109,23 @@ carve-out). So, unless a different repo / path is specifically targeted,
 - **No current session** (cron / CI / bare script): the server-side fallback
  when `?directory=` is omitted is the **server process's `process.cwd()`**
  (`server/routes/instance/httpapi/middleware/workspace-routing.ts:76`), which
-  is wherever the server was started 鈥?unreliable. In that context `?directory=`
+  is wherever the server was started — unreliable. In that context `?directory=`
  remains effectively required.
- **Dispatch convention 鈥?directory = code location, not tracker repo.** When
+- **Dispatch convention — directory = code location, not tracker repo.** When
  launching a session for a ticket, set `?directory=` to the **main workspace**
  checkout that holds the **code the ticket edits**, which may differ from the
  repo where the ticket is tracked. Example: `<owner>/<backend-repo>#<n>` is filed in
-  the ticket-tracker repo but edits the main repo's workflow files 鈫?the
+  the ticket-tracker repo but edits the main repo's workflow files → the
  session's `?directory=` is the **code checkout root**
  (`<workspace-root>/<org>/<repo>`), not the tracker repo checkout. Never point
-  `?directory=` at a ticket worktree 鈥?the worktree goes in the claim comment +
+  `?directory=` at a ticket worktree — the worktree goes in the claim comment +
  seed prompt, not the directory field (sidebar visibility, see bullet 1). The
  owner-check (`GET /session?directory=$DIR`) is scoped per directory, so
  rooting the session at the correct code checkout is also what makes the
  duplicate-session guard meaningful. Server-side backstop ([org-internal #3190]): creating a
  session whose directory IS a linked git worktree answers with an
  `X-Session-Directory-Warning` response header and a server warn log naming
-  the owning main repo 鈥?if you see that header, the session will be invisible
+  the owning main repo — if you see that header, the session will be invisible
  to `GET /session?directory=<mainRepo>` owner-checks; re-check your launch
  parameters before proceeding.
@@ -135,10 +135,10 @@ carve-out). So, unless a different repo / path is specifically targeted,
 > corrected the misdiagnosed [org-internal #1691], see comment 9205). Code citations below were
 > verified against `<harness-package>` at HEAD.
-## The `model` field 鈥?always provide a known-good model (read this first)
+## The `model` field — always provide a known-good model (read this first)
 `prompt_async` is **fire-and-forget**: after HTTP returns 204 (or 202 when the
-message is queued behind a wedge/zombie session 鈥?no live runner in that
+message is queued behind a wedge/zombie session — no live runner in that
 process), the server runs the full agent loop in a separate fiber. **Always
 include an explicit `model`
 in the payload, and reuse the current session's model for it** (see the next
@@ -154,7 +154,7 @@ section). Two reasons:
   //                         ^^^^^^^^^ agent  ^^^^^^^^^^^^^^^^^ session/default
   ```
-   So omission does **not** produce a clean validation error 鈥?it silently
+   So omission does **not** produce a clean validation error — it silently
   resolves to the agent's model, the session's last-used model, or the
   provider default (`currentModel`, `prompt.ts:824-838`).
@@ -164,15 +164,15 @@ section). Two reasons:
   (`prompt.ts:1399`, `:804-822`). In the **async** handler that error is caught
   by the delivery fork's failure handling (`forkPromptDelivery` in
   `handlers/session.ts`) and never reaches the HTTP
-   caller 鈥?so the session looks healthy (HTTP 204, user message persisted) yet
+   caller — so the session looks healthy (HTTP 204, user message persisted) yet
   **never generates**. This is exactly the "silent stall" observed empirically
   in [org-internal #1695]: a session with a 1-message transcript (user only) and frozen
   `time.updated`.
 | payload                                      | result                                                                                                                               |
 | -------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------ |
-| `{agent, parts}` 鈥?no `model`                | 204/202; model filled by fallback; if the resolved model is unusable 鈫?**apparent silent stall** (no error surfaced, no generation). |
+| `{agent, parts}` — no `model`                | 204/202; model filled by fallback; if the resolved model is unusable → **apparent silent stall** (no error surfaced, no generation). |
-| `{agent, model:{providerID,modelID}, parts}` | 204/202; deterministic generation within seconds (verified: "1+1 绛変簬 2銆? in ~6s).                                                  |
+| `{agent, model:{providerID,modelID}, parts}` | 204/202; deterministic generation within seconds (verified: "1+1 等于 2。 in ~6s).                                                  |
 > **Iron Law:** every `prompt_async` payload MUST carry a **known-good** `model`,
 > and the safest known-good model is **the one driving this session right now**
@@ -181,14 +181,14 @@ section). Two reasons:
 **Field-name gotcha when copying a model:** the prompt payload's `ModelRef` uses
 `{ providerID, modelID }` (`prompt.ts:1852-1855`), but the **session record's**
-model uses `{ id, providerID, variant }` (`session.ts:256-260`) 鈥?i.e. `modelID`
+model uses `{ id, providerID, variant }` (`session.ts:256-260`) — i.e. `modelID`
 is called `id`. When you reuse a model read from a session record, remap
-`model.id 鈫?modelID` (see recipe below). User-message `info.model` already uses
+`model.id → modelID` (see recipe below). User-message `info.model` already uses
 `modelID` (`message.ts:403-407`).
 ## Reuse the current session's model (recommended default)
-The model powering the launching session is proven to work 鈥?reuse it. Discover
+The model powering the launching session is proven to work — reuse it. Discover
 it by whichever path fits your context:
 - **You are an in-session agent** (most common): read it straight from your own
@@ -196,27 +196,27 @@ it by whichever path fits your context:
  > "You are powered by the model named **{modelID}** (provider: **{providerID}**)."
-  e.g. `modelID = "glm-5.2"`, `providerID = "zai-coding-plan"`锛堟浘鍚?
+  e.g. `modelID = "glm-5.2"`, `providerID = "zai-coding-plan"`（曾名
-  zhipuai-coding-plan锛?026-08 鏇村悕锛?
+  zhipuai-coding-plan，2026-08 更名）
 - **Programmatic / no system prompt** (cron, CI, sibling caller): `GET` the
  launching session's record and read `.model`:
  ```sh
  curl -s "$BASE/session/$LAUNCHER_SID?directory=$DIR" \
-    | jq '.model'   # 鈫?{ "id": "glm-5.2", "providerID": "zai-coding-plan", "variant": ... }
+    | jq '.model'   # → { "id": "glm-5.2", "providerID": "zai-coding-plan", "variant": ... }
  ```
-  Then **remap** `model.id 鈫?modelID` when building the payload.
+  Then **remap** `model.id → modelID` when building the payload.
 - **Verify the provider is actually connected** before launching (cheap
-  insurance 鈥?the model only generates if its provider is live):
+  insurance — the model only generates if its provider is live):
  ```sh
  curl -s "$BASE/provider?directory=$DIR" | jq '.connected | index("<current providerID>")'
-  # 鈫?null = provider NOT connected (do NOT launch); 0..n = connected
+  # → null = provider NOT connected (do NOT launch); 0..n = connected
  ```
  or call the `list-models` tool. Note: model-level availability is only
-  knowable at runtime 鈥?a _configured_ model can still fail (subscription-tier
+  knowable at runtime — a _configured_ model can still fail (subscription-tier
  or region errors); `GET /config/providers` lists _configured_ models, not
  usable ones. The safest pre-flight is "provider connected" + reusing the
  current session's model, which is generating by definition. There is **no
@@ -226,9 +226,9 @@ it by whichever path fits your context:
 - A reachable octopus HTTP instance (e.g. `http://127.0.0.1:4096`).
 - The target directory (passed as `?directory=`). Defaults to the current
-  session's directory for in-session launches 鈥?see the Directory convention
+  session's directory for in-session launches — see the Directory convention
  above; only specify a different one explicitly when targeting another repo.
- A known-good `model` (reuse the current session's 鈥?see above). Model IDs
+- A known-good `model` (reuse the current session's — see above). Model IDs
  must match the provider config in `<config-home>/octopus/octopus.jsonc`;
  credentials live in the octopus account keyring (not env), so an isolated
  HOME cannot reuse them.
@@ -242,27 +242,27 @@ BASE=http://127.0.0.1:4096
 DIR=/data/octopus
 ```
-### Step 1 鈥?Create the session
+### Step 1 — Create the session
 ```sh
 SID=$(curl -s -X POST "$BASE/session?directory=$DIR" \
  -H 'content-type: application/json' \
-  -d '{"title":"#N 鈥?<short description>","agent":"builder"}' | jq -r .id)
+  -d '{"title":"#N — <short description>","agent":"builder"}' | jq -r .id)
 echo "session=$SID"
 ```
 - `POST /session` returns `Session.Info` with `.id` (`groups/session.ts:207-211`).
 - `?directory=` points at the repo root. For in-session launches it defaults to
-  the **current session's directory** (Directory convention above) 鈥?keep it
+  the **current session's directory** (Directory convention above) — keep it
  that way so the new session stays visible in the creator's sidebar; pass an
  explicit path only when targeting a different repo (a worktree of the same
-  repo is NOT a directory target 鈥?hand it over via the seed prompt), and
+  repo is NOT a directory target — hand it over via the seed prompt), and
  always pass it from cron / CI where no current session exists (server falls
  back to its own `process.cwd()` otherwise).
 - `agent` is `builder` (the main agent). Sub-agents (explorer/worker) are
-  spawned within a session 鈥?never named here.
+  spawned within a session — never named here.
-### Step 2 鈥?Deliver the seed prompt (CRITICAL: include a known-good `model`)
+### Step 2 — Deliver the seed prompt (CRITICAL: include a known-good `model`)
 ```sh
 curl -s -X POST "$BASE/session/$SID/prompt_async?directory=$DIR" \
@@ -278,17 +278,17 @@ curl -s -X POST "$BASE/session/$SID/prompt_async?directory=$DIR" \
  body** when processing starts now (idle session, live runner, noReply
  injection, or waiting-question preemption), **202** when the message is
  queued behind a session that is generating with no live runner in this
-  process (wedge/zombie shape 鈥?stored and re-driven on restart drain or the
+  process (wedge/zombie shape — stored and re-driven on restart drain or the
  next runner), **202** when `delay_sec` defers delivery to an in-memory
-  delayed wake ([org-internal #3937] A 鈥?see "宸℃妯″紡 / Patrol mode" below), and **409**
+  delayed wake ([org-internal #3937] A — see "巡检模式 / Patrol mode" below), and **409**
  when the session is paused (message NOT stored) or the maintenance-mode
  hold queue is full.
 - **Global route alternative ([org-internal #4307]):** when the client only knows the
  sessionID (no `?directory=` routing), `POST /prompt_async` (no path prefix)
  resolves the instance from the app database by the body's `sessionID` and
-  delegates to the same delivery core 鈥?same 204/202/409 semantics, same
+  delegates to the same delivery core — same 204/202/409 semantics, same
  `delay_sec` contract, body is the session-scoped payload plus a required
-  `sessionID` field. Unknown sessionID 鈫?404 naming the session-scoped
+  `sessionID` field. Unknown sessionID → 404 naming the session-scoped
  route. This is the natural fit for the completion-report POST (fixed port,
  no directory context).
 - `delay_sec` (optional, integer 0..86400, else 400) schedules the prompt for
@@ -297,16 +297,16 @@ curl -s -X POST "$BASE/session/$SID/prompt_async?directory=$DIR" \
  at intake. **Precedence ([org-internal #3937] review):** `delay_sec` applies only when the
  intake would otherwise start processing now (immediate class). For the
  queued-behind-wedge 202 member and under maintenance queue mode it is
-  stripped 鈥?retention semantics win (the server logs the drop; the delay is
+  stripped — retention semantics win (the server logs the drop; the delay is
-  NOT honored). Pending wakes are **in-memory only 鈥?a server restart abandons
+  NOT honored). Pending wakes are **in-memory only — a server restart abandons
  them**; a patrol loop must therefore tolerate a missed wake and re-arm.
-  Never use `sleep <big>; curl ...` in a bash tool call to wait 鈥?that blocks
+  Never use `sleep <big>; curl ...` in a bash tool call to wait — that blocks
  the turn with zero output (the [org-internal #3937] incident shape); the bash tool now
  warns on bare sleeps > 120s (long-sleep guard, [org-internal #3937] C).
 - `model` is `{ providerID, modelID }` or the shorthand string
-  `"providerID/modelID"` (split on the FIRST `/`; accepted since [org-internal #4307] 鈥?
+  `"providerID/modelID"` (split on the FIRST `/`; accepted since [org-internal #4307] — 
  e.g. `"zai-coding-plan/glm-5.2"`). **Do not omit it.** Fill the values from
-  your own session's model (see "Reuse the current session's model" above) 鈥?
+  your own session's model (see "Reuse the current session's model" above) — 
  never hardcode a specific model. A string without a `/` is rejected with
  400 naming both accepted forms.
 - When the seed prompt contains newlines/quotes, build the payload from a file
@@ -315,87 +315,87 @@ curl -s -X POST "$BASE/session/$SID/prompt_async?directory=$DIR" \
  jq -n --rawfile p seed.txt '{agent:"builder",model:{providerID:"<current providerID>",modelID:"<current modelID>"},parts:[{type:"text",text:$p}]}'
  ```
-### Step 3 鈥?Verify the session actually generated (do NOT assume success)
+### Step 3 — Verify the session actually generated (do NOT assume success)
-HTTP 204/202 鈮?generation success. Poll until an `assistant` message appears. The
+HTTP 204/202 ≠generation success. Poll until an `assistant` message appears. The
-endpoint is **`/session/:id/message` 鈥?SINGULAR**, and it returns a bare array
+endpoint is **`/session/:id/message` — SINGULAR**, and it returns a bare array
 whose elements are `{ info, parts }` with `role` at `.info.role`
-(`groups/session.ts:88,183-194`). Poll the **tail with `limit=1`** 鈥?the
+(`groups/session.ts:88,183-194`). Poll the **tail with `limit=1`** — the
-no-`limit` form loads the ENTIRE transcript server-side (O(messages脳parts) per
+no-`limit` form loads the ENTIRE transcript server-side (O(messages×parts) per
 poll; pitfall #14's 478-message session paid it on every health check), while
 `limit=1` returns just the newest message (REQ-F-010 windowing, `message.ts`
 `page()`):
 ```sh
-# wait 5鈥?0s, then poll the TAIL 鈥?never the full transcript
+# wait 5–10s, then poll the TAIL — never the full transcript
 curl -s "$BASE/session/$SID/message?directory=$DIR&limit=1" \
  | jq '{latest_role: .[0].info.role, latest_id: .[0].info.id}'
 ```
-Verdict: `latest_role == "assistant"` 鈫?the first generation completed (the
+Verdict: `latest_role == "assistant"` → the first generation completed (the
 seed is `user`; the newest message flips to `assistant` only once the model
-answered 鈥?an errored turn also persists an assistant message carrying the 鈿狅笍
+answered — an errored turn also persists an assistant message carrying the ⚠️
 usage-limit part, [org-internal #2912], so check the tail text before declaring success).
-Stays `user` across 2鈥? polls spaced 10鈥?0 s 鈫?**apparent silent stall**;
+Stays `user` across 2–3 polls spaced 10–30 s → **apparent silent stall**;
 almost certainly the model did not resolve to a usable one (fallback landed
 badly, or you omitted `model`). Redeliver Step 2 with an explicit known-good
 `model`. Need everything newer than a known point? Page forward with
-`after=<cursor>&limit=N` and follow the `X-Next-Cursor` response header 鈥?
+`after=<cursor>&limit=N` and follow the `X-Next-Cursor` response header — 
 just never omit `limit`.
-> 鈿狅笍 Do NOT write `/messages` (plural) 鈥?that path does not exist for listing.
+> ⚠️ Do NOT write `/messages` (plural) — that path does not exist for listing.
 > (`POST /session/:id/message`, same singular path but POST, is the synchronous
 > prompt endpoint; don't confuse the two.)
 ## Launch a session for a specific ticket (#N)
 The common case: an agent (or cron/CI) spins up a fresh main session to work a
-tracked issue 鈥?seed prompt composed **from the issue body**, launched on the
+tracked issue — seed prompt composed **from the issue body**, launched on the
 current session's model. **Step-0 owner check is MANDATORY ([org-internal #1803])**: four data
 sources (session-title scan, assignee/claim, open PRs, remote branches); any
-live claim 鈫?ABORT the launch (`session-scope-guard.md` points here for that
+live claim → ABORT the launch (`session-scope-guard.md` points here for that
-pre-step). Full recipe 鈥?owner-check scan script with `X-Total-Count` /
+pre-step). Full recipe — owner-check scan script with `X-Total-Count` /
 `X-Has-More` pagination handling ([org-internal #3190]), claim-first atomic 3-step ([org-internal #2297],
 + one-command provisioning via `script/claim-provision.sh`, [org-internal #3642]),
 seed-prompt MUSTs, backend duplicate-ticket hard guard ([org-internal #1989], on by default
 [org-internal #2350]), launch + poll commands: `reference/ticket-recipe.md` (read BEFORE
 creating any ticket-driven session).
-## Completion-report protocol (瀹屾垚鍥炴姤鍗忚, [org-internal #2374])
+## Completion-report protocol (完成回报协议, [org-internal #2374])
 `prompt_async` is fire-and-forget **for the launcher too**: without this
 protocol the orchestrator has NO push channel and must poll forever ([org-internal #2366]).
 The worker actively reports `status=done|blocked|handoff` back into the
 orchestrator's session via `prompt_async`, with an issue-comment fallback.
-Default report format is `branch=<ref>`-based 鈥?workers never open PRs
+Default report format is `branch=<ref>`-based — workers never open PRs
 (TD-678/[org-internal #4425]); `pr=#N` appears only on `uncoordinated` self-opens.
 Hard constraints: a headless worker MUST NOT call the `question` tool
-([org-internal #2378] 鈥?directional/irreversible decisions are `status=blocked` reports,
+([org-internal #2378] — directional/irreversible decisions are `status=blocked` reports,
 then STOP), and MUST NOT self-merge its PR / self-close the issue / touch
-`main` ([org-internal #2386] 鈥?keep the PR open; the orchestrator merges and closes). Full
+`main` ([org-internal #2386] — keep the PR open; the orchestrator merges and closes). Full
-protocol 鈥?orchestrator-side seed block (verbatim template), worker-side
+protocol — orchestrator-side seed block (verbatim template), worker-side
 steps, decision-authority layering: `reference/completion-report.md` (read
 BEFORE composing a seed prompt for any worker you need to hear back from).
 ## Post-launch lifecycle: health check, hung rescue, stale-worldview correction ([org-internal #2459])
-Launching is half the job 鈥?a headless worker can hang silently or wake with
+Launching is half the job — a headless worker can hang silently or wake with
-a stale worldview. Health check = two polls 30鈥?0 s apart (`.state` + `progress`
+a stale worldview. Health check = two polls 30–60 s apart (`.state` + `progress`
 + message count); `state=generating` with ALL counters frozen across BOTH
-samples = hung 鈫?abort FIRST (`POST /session/:id/abort`), then re-wake with a
+samples = hung → abort FIRST (`POST /session/:id/abort`), then re-wake with a
-known-good model + the anti-re-hang clause. Stale worldview 鈫?fact-baseline
+known-good model + the anti-re-hang clause. Stale worldview → fact-baseline
 injection (only the CURRENT authority injects; if YOU might be the stale one,
-verify identity against the durable record first). Full runbooks 鈥?verdict
+verify identity against the durable record first). Full runbooks — verdict
 table + [org-internal #3215] dual-sample rule, abort + re-wake sequence, fact-baseline
 structure, authorization asymmetry: `reference/lifecycle-ops.md` (read when
-managing a launched session). Quota wall 鈥?the worker's turn killed by a
+managing a launched session). Quota wall — the worker's turn killed by a
 terminal usage-limit error (looks like silent completion: no report, ticket
-stalled) 鈥?has its own runbook: detection signals (finish=error 鈿狅笍 tail,
+stalled) — has its own runbook: detection signals (finish=error ⚠️ tail,
 provider quota markers), provider-switch re-wake, fact-baseline template,
 pre-dispatch provider check: `reference/quota-wall-recovery.md` ([org-internal #3669], evidence
 [org-internal #3627]; read when a worker goes silent mid-task).
-## 宸℃妯″紡 / Patrol mode (delayed self-wake, [org-internal #3937])
+## 巡检模式 / Patrol mode (delayed self-wake, [org-internal #3937])
 A patrol loop periodically nudges a headless session without holding a
 connection or burning a turn on a blocking sleep. Since [org-internal #3937] A the server
@@ -414,82 +414,82 @@ curl -s -X POST "$BASE/session/$SID/prompt_async?directory=$DIR" \
 Rules of the road:
- **202 + `delay_sec` 鈮?queued-behind-wedge 202.** Both are 202, but the
+- **202 + `delay_sec` ≠queued-behind-wedge 202.** Both are 202, but the
  delayed wake holds the prompt in memory and delivers it exactly once when
  the delay elapses (session must have been idle at intake; `0` equals
-  omission 鈫?immediate 204 path). If the session was NOT idle at intake, the
+  omission → immediate 204 path). If the session was NOT idle at intake, the
  intake keeps the queued semantics and `delay_sec` is ignored (logged
-  server-side) 鈥?the same precedence as maintenance queue mode, where the
+  server-side) — the same precedence as maintenance queue mode, where the
  intake is retained and `delay_sec` never delays the flush.
- **Paused at wake 鈫?dropped, not stored.** The wake's `prompt()` rejects and
+- **Paused at wake → dropped, not stored.** The wake's `prompt()` rejects and
  the server publishes an error event; the message is never stored. A patrol
  driver should check session state before assuming delivery.
- **Restart abandons pending wakes.** They are in-memory server fibers 鈥?no
+- **Restart abandons pending wakes.** They are in-memory server fibers — no
  persistence, no drain. After any server restart the patrol driver owns
  re-arming the next wake; treat a missed wake as expected, not as an error.
 - **Latest wake wins, per session ([org-internal #4069]).** Arming `delay_sec` on a session
  that already has a pending wake SUPERSEDES it: the previous countdown is
  cancelled, only the latest wake fires. Re-arming each turn is the intended
-  patrol pattern 鈥?a superseded wake never delivers its prompt and publishes
+  patrol pattern — a superseded wake never delivers its prompt and publishes
-  no error. (Pre-[org-internal #4069] stacks both FIFO 鈥?on old binaries, re-arm only after
+  no error. (Pre-[org-internal #4069] stacks both FIFO — on old binaries, re-arm only after
  the previous wake fired.)
 - **Never emulate a delay with the bash tool.** `sleep 900; curl ...` blocks
  the turn with zero output and gets manually aborted as a hang (the [org-internal #3937]
  incident). The bash tool now prepends a `<shell_warning>` on bare sleeps
-  beyond 120s ([org-internal #3937] C) 鈥?treat that warning as a redirect to this section.
+  beyond 120s ([org-internal #3937] C) — treat that warning as a redirect to this section.
 ## Do NOT use this skill when
- A **persistent client** (Web UI / interactive TUI) is attached 鈥?those use the
+- A **persistent client** (Web UI / interactive TUI) is attached — those use the
  synchronous `prompt` endpoint (it blocks until generation completes) and send
  `model` automatically. Using `prompt_async` there gains nothing and loses the
  in-line response. This includes the rescue runbook: a hung session driven by
  a persistent client is the client user's to handle (refresh / re-prompt from
-  the UI) 鈥?abort + re-wake targets headless / managed sessions only.
+  the UI) — abort + re-wake targets headless / managed sessions only.
- You want the response **inline** in the same HTTP call 鈥?`prompt_async` is
+- You want the response **inline** in the same HTTP call — `prompt_async` is
  fire-and-forget; use the synchronous `prompt` endpoint instead.
 ## Common pitfalls
 | #   | Pitfall                                                                                                                                                                                                                                                                     | Fix                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      |
 | --- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| 1   | Omitting `model` / relying on the fallback 鈫?apparent silent stall (most common)                                                                                                                                                                                            | Always send a known-good `model:{providerID,modelID}` 鈥?reuse the current session's                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      |
+| 1   | Omitting `model` / relying on the fallback → apparent silent stall (most common)                                                                                                                                                                                            | Always send a known-good `model:{providerID,modelID}` — reuse the current session's                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      |
-| 2   | Listing endpoint written `/messages` (plural) 鈫?404                                                                                                                                                                                                                         | Use `/session/:id/message` (singular); returns a bare array, role at `.info.role`                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
+| 2   | Listing endpoint written `/messages` (plural) → 404                                                                                                                                                                                                                         | Use `/session/:id/message` (singular); returns a bare array, role at `.info.role`                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
-| 3   | Copying the session record's model verbatim into the payload                                                                                                                                                                                                                | Remap field names: session `.model.id` 鈫?payload `modelID` (session uses `id`, payload uses `modelID`)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
+| 3   | Copying the session record's model verbatim into the payload                                                                                                                                                                                                                | Remap field names: session `.model.id` → payload `modelID` (session uses `id`, payload uses `modelID`)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
 | 4   | Stale `octopus` binary rejects newer config schema (`Unrecognized key`)                                                                                                                                                                                                     | Use the source CLI `bun run ./src/index.ts ...`; the config itself is valid                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              |
-| 5   | Missing `?directory=` query param                                                                                                                                                                                                                                           | In-session launch: default to the current session's directory. Cron/CI (no current session): pass the repo root explicitly 鈥?server falls back to its own `process.cwd()`                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
+| 5   | Missing `?directory=` query param                                                                                                                                                                                                                                           | In-session launch: default to the current session's directory. Cron/CI (no current session): pass the repo root explicitly — server falls back to its own `process.cwd()`                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
-| 6   | Using synchronous `prompt` for headless launch                                                                                                                                                                                                                              | `prompt` blocks until done 鈥?wrong for fire-and-forget; use `prompt_async`                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
+| 6   | Using synchronous `prompt` for headless launch                                                                                                                                                                                                                              | `prompt` blocks until done — wrong for fire-and-forget; use `prompt_async`                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
 | 7   | Shell-escaping errors in a multi-line seed prompt                                                                                                                                                                                                                           | Build the payload with `jq -n --rawfile` from a file                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
-| 8   | Verifying models via `GET /model` 鈥?no such endpoint (404)                                                                                                                                                                                                                  | Use `GET /provider` 鈫?`.connected` (provider live check); `list-models` tool also works. `GET /config/providers` lists _configured_ models only                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
+| 8   | Verifying models via `GET /model` — no such endpoint (404)                                                                                                                                                                                                                  | Use `GET /provider` → `.connected` (provider live check); `list-models` tool also works. `GET /config/providers` lists _configured_ models only                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
-| 9   | Launching a session for a ticket another live session already owns 鈫?conflicting diffs, duplicate work ([org-internal #1744]/[org-internal #1753])                                                                                                                                                        | Run the Step-0 owner check (`GET /session` title scan + worktree/branch/PR scan); ABORT and report on conflict                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           |
+| 9   | Launching a session for a ticket another live session already owns → conflicting diffs, duplicate work ([org-internal #1744]/[org-internal #1753])                                                                                                                                                        | Run the Step-0 owner check (`GET /session` title scan + worktree/branch/PR scan); ABORT and report on conflict                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           |
-| 10  | Creating a worktree / fresh checkout for the new session (unnecessary `bun install` + `.codegraph/` rebuild cost)                                                                                                                                                           | Don't 鈥?for _general_ launches: a session is a conversation pointed at a directory, so reuse the current workspace; worktree creation is a separate _workflow_ decision the launched session makes if/when it starts a workflow. **Ticket-recipe carve-out ([org-internal #2297]):** the ticket's work happens in a dedicated worktree anyway (worktree discipline), and claim-first pushes the workflow branch before launch 鈥?so the launcher pre-builds the worktree as the claim carrier + ready workspace, and the session reuses it (cost is front-loaded, not wasted). The worktree path goes in the claim comment + seed prompt; `?directory=` stays on the creator's workspace |
+| 10  | Creating a worktree / fresh checkout for the new session (unnecessary `bun install` + `.codegraph/` rebuild cost)                                                                                                                                                           | Don't — for _general_ launches: a session is a conversation pointed at a directory, so reuse the current workspace; worktree creation is a separate _workflow_ decision the launched session makes if/when it starts a workflow. **Ticket-recipe carve-out ([org-internal #2297]):** the ticket's work happens in a dedicated worktree anyway (worktree discipline), and claim-first pushes the workflow branch before launch — so the launcher pre-builds the worktree as the claim carrier + ready workspace, and the session reuses it (cost is front-loaded, not wasted). The worktree path goes in the claim comment + seed prompt; `?directory=` stays on the creator's workspace |
-| 11  | Launching a worker and never hearing back 鈥?orchestrator polls a few times, stops, loses visibility ([org-internal #2374])                                                                                                                                                                 | Append the completion-report block to the seed prompt (Completion-report protocol section): worker `prompt_async`s a one-line status back into the orchestrator session on done/blocked/handoff, with issue-comment fallback                                                                                                                                                                                                                                                                                                                                                                                                                                             |
+| 11  | Launching a worker and never hearing back — orchestrator polls a few times, stops, loses visibility ([org-internal #2374])                                                                                                                                                                 | Append the completion-report block to the seed prompt (Completion-report protocol section): worker `prompt_async`s a one-line status back into the orchestrator session on done/blocked/handoff, with issue-comment fallback                                                                                                                                                                                                                                                                                                                                                                                                                                             |
-| 12  | Headless worker calls the `question` tool 鈫?no attached client: the question deadlocks in a queue, or `auto_approve` silently auto-approves a direction-setting decision ([org-internal #2378])                                                                                            | NEVER call `question` from a headless worker. Decision boundary (Completion-report protocol section): directional/irreversible decision 鈫?`status=blocked` report + one-line decision point, then STOP; the orchestrator is the sole human-decision entry point                                                                                                                                                                                                                                                                                                                                                                                                          |
+| 12  | Headless worker calls the `question` tool → no attached client: the question deadlocks in a queue, or `auto_approve` silently auto-approves a direction-setting decision ([org-internal #2378])                                                                                            | NEVER call `question` from a headless worker. Decision boundary (Completion-report protocol section): directional/irreversible decision → `status=blocked` report + one-line decision point, then STOP; the orchestrator is the sole human-decision entry point                                                                                                                                                                                                                                                                                                                                                                                                          |
-| 13  | Headless worker self-merges its PR / self-closes the issue once the PR looks ready, despite a seed instruction to keep it open ([org-internal #2386]; N-02 [org-internal #2367] / N-03 [org-internal #2368], commits `d1565c99` / `040f21b7`)                                                                            | Self-merge / self-close / touching `main` are irreversible directional actions 鈫?blocked by the Decision boundary. PR ready 鈫?keep it OPEN, report `status=done branch=<ref>`; the orchestrator opens/admits the PR, merges and closes uniformly                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
+| 13  | Headless worker self-merges its PR / self-closes the issue once the PR looks ready, despite a seed instruction to keep it open ([org-internal #2386]; N-02 [org-internal #2367] / N-03 [org-internal #2368], commits `d1565c99` / `040f21b7`)                                                                            | Self-merge / self-close / touching `main` are irreversible directional actions → blocked by the Decision boundary. PR ready → keep it OPEN, report `status=done branch=<ref>`; the orchestrator opens/admits the PR, merges and closes uniformly                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
-| 14  | Trusting `state=generating` as "alive" 鈥?a hung stream goes unrescued (session A, 2026-08-16: `generating` 6+ min, count frozen at 478)                                                                                                                                     | Poll state AND message count twice 30鈥?0 s apart; frozen count = hung 鈫?abort + re-wake (Post-launch lifecycle section)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
+| 14  | Trusting `state=generating` as "alive" — a hung stream goes unrescued (session A, 2026-08-16: `generating` 6+ min, count frozen at 478)                                                                                                                                     | Poll state AND message count twice 30–60 s apart; frozen count = hung → abort + re-wake (Post-launch lifecycle section)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
-| 15  | Re-sending a wake prompt to a hung session and waiting 鈥?queued prompts are never consumed while the stream is dead                                                                                                                                                         | Abort FIRST (`POST /session/:id/abort` 鈫?200, verify `idle`), THEN re-send; a prompt queued before the abort may still never fire 鈥?always re-deliver                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
+| 15  | Re-sending a wake prompt to a hung session and waiting — queued prompts are never consumed while the stream is dead                                                                                                                                                         | Abort FIRST (`POST /session/:id/abort` → 200, verify `idle`), THEN re-send; a prompt queued before the abort may still never fire — always re-deliver                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
-| 16  | A worker woken from restart / long idle acts on its stale worldview 鈥?re-dispatches superseded work or claims authority it no longer holds (2026-08-16: revived worker re-ran an already-published FAIL verify; ops session announced an inherited "orchestrator" takeover) | Fact-baseline injection (Post-launch lifecycle section): authoritative facts + invalidated assumptions + one concrete re-assignment. Only the CURRENT authority injects; a session that suspects IT is stale verifies identity against the durable record first (`rules/compact.md` identity clause)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
+| 16  | A worker woken from restart / long idle acts on its stale worldview — re-dispatches superseded work or claims authority it no longer holds (2026-08-16: revived worker re-ran an already-published FAIL verify; ops session announced an inherited "orchestrator" takeover) | Fact-baseline injection (Post-launch lifecycle section): authoritative facts + invalidated assumptions + one concrete re-assignment. Only the CURRENT authority injects; a session that suspects IT is stale verifies identity against the durable record first (`rules/compact.md` identity clause)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
-| 17  | Worker goes silent mid-task: provider quota wall killed the turn (usage limit / 429) 鈥?no completion-report, no blocked report; from the issue side indistinguishable from silent completion (2026-08-29 [org-internal #3627]: opencode-go `weekly usage limit reached` after the 13:18 Round-1 FAIL; ticket stalled until manually re-woken) | Detect via tail probe (`finish=error` + 鈿狅笍 usage-limit part, `metadata.reason` in the quota family) + `GET /provider` quota markers; re-wake on a known-good provider with the fact-baseline template 鈥?`reference/quota-wall-recovery.md` ([org-internal #3669]). Prevent: pre-dispatch provider check + the seed's 閰嶉鑷姤 clause (`reference/completion-report.md`, [org-internal #3669]) 鈥?quota exhaustion is a `status=blocked reason=quota-exhausted` report, not a silent death |
+| 17  | Worker goes silent mid-task: provider quota wall killed the turn (usage limit / 429) — no completion-report, no blocked report; from the issue side indistinguishable from silent completion (2026-08-29 [org-internal #3627]: opencode-go `weekly usage limit reached` after the 13:18 Round-1 FAIL; ticket stalled until manually re-woken) | Detect via tail probe (`finish=error` + ⚠️ usage-limit part, `metadata.reason` in the quota family) + `GET /provider` quota markers; re-wake on a known-good provider with the fact-baseline template — `reference/quota-wall-recovery.md` ([org-internal #3669]). Prevent: pre-dispatch provider check + the seed's 配额自报 clause (`reference/completion-report.md`, [org-internal #3669]) — quota exhaustion is a `status=blocked reason=quota-exhausted` report, not a silent death |
 ## Known limitation (separate from this workaround)
 A missing `model` producing an **apparent silent stall** (no surfaced error, no
 generation) is an observability / robustness gap. Current code does NOT
-hard-require `model` 鈥?it fills it via a fallback chain (`prompt.ts:858`) and any
+hard-require `model` — it fills it via a fallback chain (`prompt.ts:858`) and any
 resolution failure surfaces as a published `Session.Event.Error` on the
 synchronous path (`prompt.ts:804-822`), but the **async** `prompt_async` handler
 catches that cause (`forkPromptDelivery` in `handlers/session.ts`) so the HTTP
 caller never sees it. The proper fix is to surface the error (or reject unusable
 models at the boundary) so a stalled session is diagnosable. Until then, **always
-provide an explicit known-good `model`** 鈥?this skill is the documented
+provide an explicit known-good `model`** — this skill is the documented
-workaround (see [org-internal #1695] "閬楃暀 minor").
+workaround (see [org-internal #1695] "遗留 minor").
 **Update ([org-internal #2912], 2026-08-20)**: usage-limit turn failures (HTTP 429 /
 FreeUsageLimitError / GoUsageLimitError) are no longer silent shells. When such
 a turn terminates (retry schedule ends or the spin is aborted), the errored
-assistant message persists `finish=error` plus a human-readable 鈿狅笍 text part
+assistant message persists `finish=error` plus a human-readable ⚠️ text part
 carrying provider, limit reason, and reset hint (`metadata: { error: true,
-reason, provider }`) 鈥?visible via `GET /session/:id/message` and rendered in
+reason, provider }`) — visible via `GET /session/:id/message` and rendered in
 the web UI like any assistant text. Pitfall #14's double-poll is still the
 liveness check while a 429 retry spin is IN progress (the spin itself retries
 with backoff until interrupted); the explicit error part only appears once the
@@ -502,13 +502,13 @@ turn ends. The general async-path observability gap above remains tracked by
  - current-model reuse, and corrects the endpoint/claim against current code).
 - Completion-report protocol: **[org-internal #2374]** (worker-side active report back to the
  launching orchestrator session; fallback to issue comment).
- Quota-wall recovery recipe: **[org-internal #3669]** (evidence instance [org-internal #3627]) 鈥?detect a
+- Quota-wall recovery recipe: **[org-internal #3669]** (evidence instance [org-internal #3627]) — detect a
  worker killed by a provider usage limit, re-wake on a known-good provider,
  pre-dispatch prevention.
 - Decision boundary: **[org-internal #2378]** (headless worker MUST NOT call `question`;
  directional decisions go through `status=blocked` reports to the
  orchestrator) and **[org-internal #2386]** (the worker MUST NOT self-merge its PR,
-  self-close the issue, or touch `main` 鈥?the orchestrator merges and closes
+  self-close the issue, or touch `main` — the orchestrator merges and closes
  uniformly).
 - Correction of the prior misdiagnosis: **[org-internal #1691]** (closed Invalid), comment 9205.
 - Synchronous client always sends `model`:
@@ -519,29 +519,29 @@ turn ends. The general async-path observability gap above remains tracked by
 ## References
-**On-demand references** (NOT injected 鈥?read at the declared timing):
+**On-demand references** (NOT injected — read at the declared timing):
- `reference/ticket-recipe.md` 鈥?ticket-driven launch (`Launch a session for a
+- `reference/ticket-recipe.md` — ticket-driven launch (`Launch a session for a
-specific ticket (#N)`): read BEFORE creating any session for issue #N 鈥?
+specific ticket (#N)`): read BEFORE creating any session for issue #N — 
  Step-0 owner check, seed-prompt composition, launch + poll commands.
- `reference/completion-report.md` 鈥?completion-report protocol (瀹屾垚鍥炴姤鍗忚,
+- `reference/completion-report.md` — completion-report protocol (完成回报协议,
  [org-internal #2374]): read BEFORE composing a seed prompt for a worker you need to hear
-  back from 鈥?orchestrator block template, worker-side report steps, decision
+  back from — orchestrator block template, worker-side report steps, decision
  boundary ([org-internal #2378] / [org-internal #2386]), quota self-report clause ([org-internal #3669]).
- `reference/lifecycle-ops.md` 鈥?post-launch lifecycle ([org-internal #2459]): read when
+- `reference/lifecycle-ops.md` — post-launch lifecycle ([org-internal #2459]): read when
-  managing a launched session 鈥?health-check polling, hung-stream diagnosis
+  managing a launched session — health-check polling, hung-stream diagnosis
  (state=generating + frozen counters), abort + re-wake rescue,
  fact-baseline injection, authorization asymmetry.
- `reference/quota-wall-recovery.md` 鈥?quota-wall recovery ([org-internal #3669], evidence
+- `reference/quota-wall-recovery.md` — quota-wall recovery ([org-internal #3669], evidence
  [org-internal #3627]): read when a worker goes silent mid-task (suspected provider usage
-  limit) or BEFORE dispatching a long-running worker 鈥?detection signals
+  limit) or BEFORE dispatching a long-running worker — detection signals
-  (finish=error 鈿狅笍 tail, provider quota markers, log grep patterns),
+  (finish=error ⚠️ tail, provider quota markers, log grep patterns),
  provider-switch re-wake + fact-baseline template, pre-dispatch provider
  check, quota self-report clause.
- `rules/headless-session-ops` wiki page 鈥?authoritative reference (this
+- `rules/headless-session-ops` wiki page — authoritative reference (this
  skill is its runtime carrier; link in the Directory-convention note above).
- `core/rules/session-scope-guard.md` 鈥?owner-check + claim-first rule
+- `core/rules/session-scope-guard.md` — owner-check + claim-first rule
  (the ticket recipe's Step 0 is its launch-time application).
- `core/rules/compact.md` 鈥?identity-verification clause backing the
+- `core/rules/compact.md` — identity-verification clause backing the
  authorization-asymmetry rule (`reference/lifecycle-ops.md`).
@@ -65,8 +65,8 @@ model**.
     and coordinate on the issue before proceeding.
   **c. Open-PR check.** List open PRs referencing `#N` —
-   `工单 API（见 TERMINOLOGY）search(q: "#N", type: "pulls", state: "open")` (API source)
+   `GET <gitea-base-url>/api/v1/repos/issues/search?q="#N"&type=pulls&state=open`
-   or `gitea_pull__list` — and **ABORT** if an open PR already covers the ticket.
+   (API source) — and **ABORT** if an open PR already covers the ticket.
   **d. Remote branch check ([org-internal #2297]).** A local branch is invisible to other
   sessions — check the remote too:
@@ -104,15 +104,15 @@ Phase 2 and Phase 4, not after the fix:
 [Worker: developer] Phase 1 reproduce + Phase 2 root cause
    → write repro-notes (reproduction steps, root cause, bug path,
      expected behavior)
-    ↓ persist: wiki page `{slug}/repro-notes` (gitea_wiki__create_page)
+    ↓ persist: wiki page `{slug}/repro-notes` (`POST .../wiki/new`, body `content_base64`)
 [Worker: tester] read repro-notes → Phase 3 write failing regression test
    (confirms FAIL before fix)
-    ↓ persist: wiki page `{slug}/test-report` (gitea_wiki__create_page, failing test confirmed)
+    ↓ persist: wiki page `{slug}/test-report` (`POST .../wiki/new`, body `content_base64`, failing test confirmed)
 [Worker: developer] Phase 4 fix → run test:changed to green
    → write impl-notes (post-fix behavior contract)
-    ↓ persist: wiki page `{slug}/impl-notes` (gitea_wiki__create_page, post-fix behavior contract)
+    ↓ persist: wiki page `{slug}/impl-notes` (`POST .../wiki/new`, body `content_base64`, post-fix behavior contract)
 [Worker: tester] supplement boundary regression tests → run test:changed
-    ↓ persist: update wiki page `{slug}/test-report` (gitea_wiki__update_page, final)
+    ↓ persist: update wiki page `{slug}/test-report` (`PATCH .../wiki/page/{mangled-name}`, omit `title`, body `content_base64` — final)
    — consumed by the human stakeholder / next iteration planning for DoD regression-test evidence
 ```
@@ -499,8 +499,8 @@ issue exists.
   retired — each one re-triggered the full CI surface for near-zero re-tested
   risk.
-> **Kanban column lifecycle**: automated (`工单 API（见 TERMINOLOGY）create` → Backlog,
+> **Kanban column lifecycle**: automated (`POST <gitea-base-url>/api/v1/repos/{owner}/{repo}/issues` → Backlog,
-> `gitea_pull__create` → Review; no manual moves). Single shared reference:
+> `POST .../pulls` → Review; no manual moves). Single shared reference:
 > `_shared/gitea-write-patterns.md` Pattern 7.5; column semantics: wiki
 > `kanban-lifecycle`.
@@ -234,7 +234,7 @@ After all steps are complete:
 {If the refactoring changes the internal architecture in a way that merits an
 ADR, reference the ADR. **Deprecated:** `.artifacts/{slug}/design/adr/{NNNN}-*.md`
 → ADRs now live on the Gitea wiki at page `{slug}/03-adr-{NNNN}-{title}`,
-readable via `gitea_wiki__get_page`. Or "None".}
+readable via `GET <gitea-base-url>/api/v1/repos/{owner}/{repo}/wiki/page/{mangled-name}`. Or "None".}
 ---
@@ -2,41 +2,41 @@
 name: project-kickoff
 description: >
  Use ONLY when the user asks about project setup, kickoff, or project
-  initialization ("kickoff", "project setup", "椤圭洰鍒濆鍖?, "椤圭洰閰嶇疆").
+  initialization ("kickoff", "project setup", "项目初始化", "项目配置").
  Provides guidance on the octopus project kickoff workflow: checking readiness,
  running /kickoff or octopus kickoff, configuring codegraph, and understanding
-  project scaffolding. Do not use for application-level configuration 鈥?
+  project scaffolding. Do not use for application-level configuration —
  this skill covers the octopus project lifecycle, not user application code.
 triggers:
-  # High-discrimination phrases only ([org-internal #4525]): bare "setup"/"init"/"閰嶇疆" fire
+  # High-discrimination phrases only ([org-internal #4525]): bare "setup"/"init"/"配置" fire
  # on any configuration mention, and the skill gate folds the previous
-  # assistant turn on approval turns 鈥?one stray "閰嶇疆" in a reply re-fires
+  # assistant turn on approval turns — one stray "配置" in a reply re-fires
  # the gate every turn. Keep triggers to phrases that name THIS workflow;
  # generic setup/init questions still route via the description in the
  # skills listing.
  - kickoff
  - project setup
-  - 椤圭洰鍒濆鍖?
+  - 项目初始化
-  - 椤圭洰閰嶇疆
+  - 项目配置
 role: Producer
 ---
-> Core 涓珛鐗堬紙Increment 6a 鏀瑰啓锛屽師 deferHard verbatimDir锛夈€傛満鍒躲€佺粨鏋勪笌 frontmatter 淇濇寔锛涘疄渚嬫湳璇紙宸ュ叿鍚嶃€佽矾寰勩€佸伐鍗曞彿锛夋寜 `core/adapters/TERMINOLOGY.md` 缁戝畾鍒板叿浣撳疄渚嬨€?
+> Core 中立版（Increment 6a 改写，原 deferHard verbatimDir）。机制、结构与 frontmatter 保持；实例术语（工具名、路径、工单号）按 `core/adapters/TERMINOLOGY.md` 绑定到具体实例。
 # Project Kickoff
 ## 1. Overview
-Project kickoff is the octopus project initialization workflow that gets a project from zero to fully configured in one command. It covers readiness detection 鈫?setup 鈫?scaffold 鈫?config 鈫?codegraph init 鈫?skills overlay pull, producing a project that is ready for the full SDLC pipeline without manual configuration steps.
+Project kickoff is the octopus project initialization workflow that gets a project from zero to fully configured in one command. It covers readiness detection → setup → scaffold → config → codegraph init → skills overlay pull, producing a project that is ready for the full SDLC pipeline without manual configuration steps.
 ## 2. When This Skill Activates
 This skill activates when the user's text matches any of the trigger keywords:
- `kickoff` 鈥?asking about the `/kickoff` command or the kickoff workflow
+- `kickoff` — asking about the `/kickoff` command or the kickoff workflow
- `project setup` 鈥?asking how to set up a project in octopus
+- `project setup` — asking how to set up a project in octopus
- `椤圭洰鍒濆鍖朻 / `椤圭洰閰嶇疆` 鈥?asking how to initialize or configure an octopus project (Chinese)
+- `项目初始化` / `项目配置` — asking how to initialize or configure an octopus project (Chinese)
-Generic "setup"/"init"/"閰嶇疆" mentions are deliberately NOT triggers ([org-internal #4525]): they collide with everyday configuration talk, and the hard skill gate folds the previous assistant turn into its match text on approval turns 鈥?a passing "鎴栭厤缃?x: false" in a reply would re-fire the gate every turn. `/init` note: `/init` generates AGENTS.md via LLM; kickoff uses the managed template from `octopus setup` 鈥?the Builder distinguishes based on context.
+Generic "setup"/"init"/"配置" mentions are deliberately NOT triggers ([org-internal #4525]): they collide with everyday configuration talk, and the hard skill gate folds the previous assistant turn into its match text on approval turns — a passing "或配置x: false" in a reply would re-fire the gate every turn. `/init` note: `/init` generates AGENTS.md via LLM; kickoff uses the managed template from `octopus setup` — the Builder distinguishes based on context.
 Typical user intents include: encountering a readiness prompt at session start, wondering how to initialize a project, or wanting to understand the kickoff workflow steps.
@@ -57,43 +57,43 @@ ls .gitea/workflows/ .github/workflows/ 2>/dev/null || echo "[GAP: no CI workflo
 ```
 If no workflows exist, recommend creating `.gitea/workflows/ci.yml` (this repo
-uses Gitea Actions) 鈥?or `.github/workflows/ci.yml` for a GitHub-hosted project
+uses Gitea Actions) — or `.github/workflows/ci.yml` for a GitHub-hosted project
-鈥?with at minimum: typecheck, lint, and test gates. Without CI, every merge is a
+— with at minimum: typecheck, lint, and test gates. Without CI, every merge is a
-manual gate 鈥?type errors, lint regressions, and test failures can land on
+manual gate — type errors, lint regressions, and test failures can land on
 main and go undetected until the next local checkout.
 ## 4. Workflow
 The kickoff workflow runs in four automated steps:
-1. **Check readiness** 鈥?Determine if the project needs setup. Run `checkReadinessWithGitea()` or `octopus kickoff --check-only` to inspect the current state.
+1. **Check readiness** — Determine if the project needs setup. Run `checkReadinessWithGitea()` or `octopus kickoff --check-only` to inspect the current state.
-2. **Run kickoff** 鈥?Execute `/kickoff` from the TUI or `octopus kickoff` from the terminal.
+2. **Run kickoff** — Execute `/kickoff` from the TUI or `octopus kickoff` from the terminal.
-3. **What happens** 鈥?A Phase 0 gate, then five sequential phases:
+3. **What happens** — A Phase 0 gate, then five sequential phases:
-   - Phase 0 鈥?**Gitea auth check**: derives the `gitea` block from the git remote origin (persisting missing fields), then verifies the token (`GET /user`) and runs the auth wizard on failure; never aborts kickoff
+   - Phase 0 — **Gitea auth check**: derives the `gitea` block from the git remote origin (persisting missing fields), then verifies the token (`GET /user`) and runs the auth wizard on failure; never aborts kickoff
-   - [1/5] **Setup** 鈥?Creates project directories and writes `AGENTS.md` from the managed template
+   - [1/5] **Setup** — Creates project directories and writes `AGENTS.md` from the managed template
-   - [2/5] **Scaffold** 鈥?Creates the `<instance-root>/` skeleton (`core/skills/` directory + default `octopus.jsonc` template if absent); domain skills content arrives via the [5/5] overlay pull
+   - [2/5] **Scaffold** — Creates the `<instance-root>/` skeleton (`core/skills/` directory + default `octopus.jsonc` template if absent); domain skills content arrives via the [5/5] overlay pull
-   - [3/5] **Config stub + MCP wiring** 鈥?Writes the `mcp.codegraph` block into `octopus.jsonc`
+   - [3/5] **Config stub + MCP wiring** — Writes the `mcp.codegraph` block into `octopus.jsonc`
-   - [4/5] **Codegraph init** 鈥?Initializes and builds the per-project `.codegraph/` index
+   - [4/5] **Codegraph init** — Initializes and builds the per-project `.codegraph/` index
-   - [5/5] **Skills remote + overlay pull** 鈥?Opt-in semantics ([org-internal #4370]); branches by flags when no `overlay.remotes` entry is configured:
+   - [5/5] **Skills remote + overlay pull** — Opt-in semantics ([org-internal #4370]); branches by flags when no `overlay.remotes` entry is configured:
-     - no flags (interactive run) 鈥?**safe default**: nothing is written; a remediation hint is printed (pass `--skills-remote`, or edit `overlay.remotes`), and the readiness skills item stays not-ready
+     - no flags (interactive run) — **safe default**: nothing is written; a remediation hint is printed (pass `--skills-remote`, or edit `overlay.remotes`), and the readiness skills item stays not-ready
-     - `--yes` 鈥?legacy behavior kept: writes the default skills remote, then pulls domain skills content (`octopus skills pull` equivalent)
+     - `--yes` — legacy behavior kept: writes the default skills remote, then pulls domain skills content (`octopus skills pull` equivalent)
-     - `--skills-remote <owner/repo>` (+ optional `--skills-remote-base-url <url>`) 鈥?writes the specified remote instead (ref `main`; base URL defaults to `<instance-base-url>`), then pulls from it
+     - `--skills-remote <owner/repo>` (+ optional `--skills-remote-base-url <url>`) — writes the specified remote instead (ref `main`; base URL defaults to `<instance-base-url>`), then pulls from it
-     - `overlay.remotes` already configured 鈥?the write is skipped (idempotent; an explicit `--skills-remote` is ignored with a warning)
+     - `overlay.remotes` already configured — the write is skipped (idempotent; an explicit `--skills-remote` is ignored with a warning)
-4. **Post-kickoff verification** 鈥?Run `octopus kickoff --check-only` again. After a `--yes` or `--skills-remote` run it reports all 5 items as ready; after a no-flag interactive run it reports 4 of 5 鈥?the skills item stays not-ready until a remote is configured (`--skills-remote`, `--yes`, or a manual `overlay.remotes` edit + `octopus skills pull`).
+4. **Post-kickoff verification** — Run `octopus kickoff --check-only` again. After a `--yes` or `--skills-remote` run it reports all 5 items as ready; after a no-flag interactive run it reports 4 of 5 — the skills item stays not-ready until a remote is configured (`--skills-remote`, `--yes`, or a manual `overlay.remotes` edit + `octopus skills pull`).
 ### First-ticket hint ([org-internal #3061])
 For a brand-new project still validating its concept, open the FIRST ticket as
-`Kind/MVP` 鈥?the interactive no-pipeline mode (decision log + debt register in
+`Kind/MVP` — the interactive no-pipeline mode (decision log + debt register in
 the ticket body). It graduates by relabeling to `Kind/Feature` (analyze-dag
 backfill mode picks up the decision log) when a second session, an external
 contract, or a second consumer of a shared type appears. Do not route early
-concept work into the full pipeline "to be safe" 鈥?the pipeline's coordination
+concept work into the full pipeline "to be safe" — the pipeline's coordination
 machinery is cost, not quality, at zero coordination.
 ## 5. Re-kickoff / Idempotency
-Re-running kickoff on an already-configured project is safe 鈥?every step is idempotent:
+Re-running kickoff on an already-configured project is safe — every step is idempotent:
 - **Setup** skips existing directories
 - **Scaffold** skips existing files
@@ -107,26 +107,26 @@ Re-running kickoff on an already-configured project is safe 鈥?every step is id
 Common issues and their resolutions:
- **`codegraph: command not found`** 鈥?Run the `codegraph-setup` skill, or install via `bun add -g @colbymchenry/codegraph`
+- **`codegraph: command not found`** — Run the `codegraph-setup` skill, or install via `bun add -g @colbymchenry/codegraph`
- **Permission denied** 鈥?Check project directory ownership and write permissions
+- **Permission denied** — Check project directory ownership and write permissions
- **Partially complete state** 鈥?Re-run `/kickoff`; idempotent steps will complete the missing parts without affecting already-completed steps
+- **Partially complete state** — Re-run `/kickoff`; idempotent steps will complete the missing parts without affecting already-completed steps
- **MCP tools not available** 鈥?Verify `mcp.codegraph` exists in `octopus.jsonc`; re-run `octopus kickoff` to write it
+- **MCP tools not available** — Verify `mcp.codegraph` exists in `octopus.jsonc`; re-run `octopus kickoff` to write it
 ## 7. Related Commands
- `/init` 鈥?Generates `AGENTS.md` using an LLM (custom, context-aware); kickoff uses the managed template from `octopus setup`
+- `/init` — Generates `AGENTS.md` using an LLM (custom, context-aware); kickoff uses the managed template from `octopus setup`
- `octopus setup` 鈥?Creates directories + `AGENTS.md` from the managed template; kickoff calls this internally
+- `octopus setup` — Creates directories + `AGENTS.md` from the managed template; kickoff calls this internally
- `octopus scaffold` 鈥?Creates the `<instance-root>/` skeleton (`core/skills/` directory + default `octopus.jsonc` template if absent); run `octopus skills pull` to fetch domain skills content; kickoff calls this internally
+- `octopus scaffold` — Creates the `<instance-root>/` skeleton (`core/skills/` directory + default `octopus.jsonc` template if absent); run `octopus skills pull` to fetch domain skills content; kickoff calls this internally
- `octopus kickoff --check-only` 鈥?Readiness check only, no pipeline execution
+- `octopus kickoff --check-only` — Readiness check only, no pipeline execution
- `octopus kickoff --skills-remote <owner/repo>` 鈥?Explicit opt-in: writes the given skills remote to `overlay.remotes` (ref `main`) and pulls it instead of the default
+- `octopus kickoff --skills-remote <owner/repo>` — Explicit opt-in: writes the given skills remote to `overlay.remotes` (ref `main`) and pulls it instead of the default
- `octopus kickoff --skills-remote-base-url <url>` 鈥?Base URL for `--skills-remote` (requires it); defaults to `<instance-base-url>` when omitted
+- `octopus kickoff --skills-remote-base-url <url>` — Base URL for `--skills-remote` (requires it); defaults to `<instance-base-url>` when omitted
- `octopus kickoff --yes` 鈥?Skips the opt-in confirmation and keeps the legacy behavior of writing the default skills remote (`Octopus/octopus-skills`)
+- `octopus kickoff --yes` — Skips the opt-in confirmation and keeps the legacy behavior of writing the default skills remote (`Octopus/octopus-skills`)
- `codegraph-setup` skill 鈥?For installing the codegraph CLI and initializing the per-project index
+- `codegraph-setup` skill — For installing the codegraph CLI and initializing the per-project index
 ## 8. Reference
- `<harness-package>/src/project-kickoff/readiness.ts` 鈥?`checkReadiness()` implementation (sync 4-item base)
+- `<harness-package>/src/project-kickoff/readiness.ts` — `checkReadiness()` implementation (sync 4-item base)
- `<harness-package>/src/project-kickoff/readiness-gitea.ts` 鈥?`checkReadinessWithGitea()` composed 5-item check (adds gitea auth reachable)
+- `<harness-package>/src/project-kickoff/readiness-gitea.ts` — `checkReadinessWithGitea()` composed 5-item check (adds gitea auth reachable)
- `<harness-package>/src/cli/cmd/kickoff.ts` 鈥?`/kickoff` command handler
+- `<harness-package>/src/cli/cmd/kickoff.ts` — `/kickoff` command handler
- `core/skills/codegraph-setup/SKILL.md` 鈥?CodeGraph setup skill
+- `core/skills/codegraph-setup/SKILL.md` — CodeGraph setup skill
- Project roadmap at `.artifacts/project-kickoff/` (deprecated 鈥?now stored as wiki page `project-kickoff/roadmap/` via `wiki 璇诲啓 API锛堣 TERMINOLOGY锛塦)
+- Project roadmap at `.artifacts/project-kickoff/` (deprecated — now stored as wiki page `project-kickoff/roadmap/` via `wiki 读写 API（见 TERMINOLOGY）`)
@@ -4,22 +4,22 @@ description: >
  Use ONLY when ready to cut a release. The Release Manager (Worker) inspects
  project state (git log, version files, build) to determine the semver bump,
  generate the changelog, tag, and produce a release artifact. Works on any
-  project state 鈥?no pipeline artifacts required.
+  project state — no pipeline artifacts required.
 triggers:
  - release
  - cut release
-  - 鍙戠増
+  - 发版
  - publish release
  - ship release
 role: Producer
 ---
-> Core 涓珛鐗堬紙Increment 6a 鏀瑰啓锛屽師 deferHard verbatimDir锛夈€傛満鍒躲€佺粨鏋勪笌 frontmatter 淇濇寔锛涘疄渚嬫湳璇紙宸ュ叿鍚嶃€佽矾寰勩€佸伐鍗曞彿锛夋寜 `core/adapters/TERMINOLOGY.md` 缁戝畾鍒板叿浣撳疄渚嬨€?
+> Core 中立版（Increment 6a 改写，原 deferHard verbatimDir）。机制、结构与 frontmatter 保持；实例术语（工具名、路径、工单号）按 `core/adapters/TERMINOLOGY.md` 绑定到具体实例。
 # Release
-Prepare and tag a release based on project facts 鈥?git history since the last
+Prepare and tag a release based on project facts — git history since the last
 tag, current version, build status, and dependency health. No dependency on `.artifacts/{slug}/`
-(**deprecated** 鈥?SDLC artifacts now live in the Gitea wiki at `{slug}/...`;
+(**deprecated** — SDLC artifacts now live in the Gitea wiki at `{slug}/...`;
 see `_shared/gitea-read-patterns.md`) or any pipeline skill outputs.
 **This SKILL does not deploy.** Deployment is project-specific (K8s, Docker,
@@ -32,12 +32,12 @@ The release is owned and executed by the **Release Manager** (Worker).
 **Context compaction**: release is a pipeline stage boundary. The main session
 compacts at this clean boundary ONLY when a capacity/projection trigger holds,
-per `core/rules/compact.md` 搂"Stage-boundary compaction" (long multi-stage
+per `core/rules/compact.md` §"Stage-boundary compaction" (long multi-stage
-runs 鈥?DAG Epic orchestration 鈥?keep the legacy every-boundary compaction;
+runs — DAG Epic orchestration — keep the legacy every-boundary compaction;
-short runs 鈥?bugfix / DAG task 鈥?and standalone runs default to NOT
+short runs — bugfix / DAG task — and standalone runs default to NOT
 compacting). The Release Manager itself is single-phase and
 artifact-driven (version files, changelog, tag); a mid-run compaction loses
-nothing 鈥?re-read the release checklist state and git log to resume.
+nothing — re-read the release checklist state and git log to resume.
 ---
@@ -50,7 +50,7 @@ Before starting the release:
 ---
-## Phase 1 鈥?Pre-release Gate
+## Phase 1 — Pre-release Gate
 Run each check against the live project. Stop and report failures.
@@ -65,82 +65,82 @@ Run each check against the live project. Stop and report failures.
   - No new HIGH or CRITICAL CVEs block the release.
   - Pre-existing HIGH/CRITICAL CVEs do NOT block but **MUST be filed as
     tech-debt** before the release lands. File them in TWO TIERS (batching
-     rule, [org-internal #3846] 鈥?a single release audit once fanned out to 14 TDs 鈫?14 PRs 鈫?
+     rule, [org-internal #3846] — a single release audit once fanned out to 14 TDs → 14 PRs → 
     56-84 CI runs on a saturated runner pool): Tier A below is the general
     mechanical-change batching rule; Tier B and the escape hatch follow it.
 <a id="phase-1-tier-a"></a>
-### Tier A 鈥?閫氱敤鏈烘鍙樻洿骞跺崟瑙勫垯 / Universal mechanical-change batching rule
+### Tier A — 通用机械变更并单规则 / Universal mechanical-change batching rule
 Origin [org-internal #3846] (audit-batch pilot, generalized in place): the rule covers ANY
 single-source fan-out of mechanical changes, not just dependency audits.
-Two source types today: (a) dependency bump audits; (b) docs 鎵归噺淇
+Two source types today: (a) dependency bump audits; (b) docs 批量修订
 (batch docs revisions).
-#### 瑙勫垯姝ｆ枃 / Rule text
+#### 规则正文 / Rule text
 - **Core**: mechanical changes of ONE class fanning out from a single
-  source are filed as ONE batch issue + ONE batch PR 鈥?never N脳issue +
+  source are filed as ONE batch issue + ONE batch PR — never N×issue +
-  N脳PR. The batch body keeps one row per item (per-CVE / per-doc mapping),
+  N×PR. The batch body keeps one row per item (per-CVE / per-doc mapping),
  so per-item traceability is unchanged; work the batch as a single PR.
 - **(a) Dependency bump audits** (the [org-internal #3846] origin case): advisories whose
  remediation is a plain version bump (lockfile-only diff, no semver-major
  jump, no overrides/catalog surgery, no API or adapter fallout) are filed
-  together via `宸ュ崟 API锛堣 TERMINOLOGY锛塩reate` with
+  together via `工单 API（见 TERMINOLOGY）create` with
  `title="[{origin}] audit-batch@{version}: mechanical bumps for {N} advisories (TD-{NNN})"`
  and labels `[tech_debt_label_id, severity_label_id, kind_bug_label_id]`
-  (severity = highest in the batch). One row per advisory 鈥?CVE/GHSA ID,
+  (severity = highest in the batch). One row per advisory — CVE/GHSA ID,
-  affected package + from鈫抰o version, severity (CVSS), advisory URL,
+  affected package + from→to version, severity (CVSS), advisory URL,
  recommended remediation, and a per-advisory Reactivation Trigger
  ("resolved when `npm audit` / `bun audit` reports no HIGH/CRITICAL for
-  this advisory") 鈥?so the release-notes `TD-NNN 鈫?#NNNN` mapping stays
+  this advisory") — so the release-notes `TD-NNN → #NNNN` mapping stays
  per-advisory.
- **(b) Docs 鎵归噺淇 (batch docs revisions)**: many small same-class docs
+- **(b) Docs 批量修订 (batch docs revisions)**: many small same-class docs
  corrections discovered in one pass (e.g. a terminology sweep) file as ONE
  issue via the same flow,
  `title="[{origin}] docs-batch: {class} revisions for {N} files"`, with one
  row per file (path, correction, reason); same ONE-batch-PR landing.
 - **Landing**: when members live on separate branches, compose the single
  batch PR via the `land-batch` skill (`core/skills/land-batch/SKILL.md`
-  鈥?cross-branch batch composition, topology B). For dependency-bump
+  — cross-branch batch composition, topology B). For dependency-bump
  batches pass `batch-compose --convergent bun.lock` (script
  `.gitea/scripts/batch-compose.ts`): the regenerable lockfile is exempt
  from path-overlap admission and lockfile-only conflicts are surgically
  resolved to the running head's version.
-#### 閫傜敤杈圭晫 / Applicability boundary
+#### 适用边界 / Applicability boundary
- **闈?mechanical锛堝惈鍒ゆ柇鎴愬垎鐨勫彉鏇达紝涓嶅苟鍗曪級** 鈥?items requiring judgment
+- **非mechanical（含判断成分的变更，不并单）** — items requiring judgment
  (wording decisions, behavior/API changes, review-dependent edits) are
  never batched; file each as its own issue.
- **璺緞閲嶅彔锛坆atch 鎴愬憳瑙︾鐩稿悓鏂囦欢 鈫?涓嶅苟鍗曪紱鍞竴璞佸厤 =
+- **路径重叠（batch 成员触碰相同文件 → 不并单；唯一豁免 =
-  鍙啀鐢熷叡浜枃浠?`bun.lock` 缁?batch-compose `--convergent` 鏀舵暃锛?* 鈥?the sole
+  可再生共享文件`bun.lock` 经batch-compose `--convergent` 收敛）** — the sole
  path-overlap exemption is the regenerable shared lockfile under
  `--convergent`; every other same-file collision stays un-batched.
- **semver-major 璺冲彉 / overrides路catalog 鎵嬫湳 / adapter路peer 鑱斿姩锛堚啋
+- **semver-major 跳变 / overrides·catalog 手术 / adapter·peer 联动（→ 
-  Tier B 鐙珛鍗曪紝缁存寔 per-package锛?* 鈥?these stay per-package Tier B
+  Tier B 独立单，维持 per-package）** — these stay per-package Tier B
  issues. Tier B and the escape hatch (below) survive this generalization
  unchanged.
-#### 闄嶇骇璺緞 / Degradation path
+#### 降级路径 / Degradation path
- **骞跺崟 PR CI 澶辫触 鈫?鎸夐攣鏂囦欢 hunk 鎷嗗寘鍥為€€锛坆isect锛?*: for dependency
+- **并单 PR CI 失败 → 按锁文件 hunk 拆包回退（bisect）**: for dependency
  batches, bisect by splitting lockfile hunks per package back into
-  per-package PRs 鈥?the original Tier A bisect semantics carried over
+  per-package PRs — the original Tier A bisect semantics carried over
-  verbatim (鍚岃涔夛紝娉涘寲鎺緸: every mechanical batch degrades the same way).
+  verbatim (同语义，泛化措辞: every mechanical batch degrades the same way).
 - **Docs batches**: split per file back into per-file PRs.
 - **land-batch composition fallback** (exit codes per
-  `.gitea/scripts/batch-compose.ts`): `3` path-overlap 鈫?split the batch
+  `.gitea/scripts/batch-compose.ts`): `3` path-overlap → split the batch
  along the reported pairs (or land the overlapping member 1:1) and re-run
-  per group; `4` merge conflict / `5` transport/git error 鈫?fall back to
+  per group; `4` merge conflict / `5` transport/git error → fall back to
  1:1 PRs for the whole batch.
 - **Preflight hedge ([org-internal #3846])**: run `bun install --dry-run` before opening
-  a dependency-batch PR 鈥?the resolver accepting the composed version set
+  a dependency-batch PR — the resolver accepting the composed version set
  is a cheap pre-CI rejection of impossible bump combinations.
 Tier B and the escape hatch (unchanged by the generalization):
- **Tier B 鈥?surgery, one issue per package**: semver-major jumps,
+- **Tier B — surgery, one issue per package**: semver-major jumps,
  adapter/peer fallout, or overrides/catalog surgery keep the
  per-package issue: `title="[{origin}] {CVE-ID/GHSA-ID} in {package} (TD-{NNN})"`
  with the same labels; body requirements match the Tier A rows.
@@ -148,7 +148,7 @@ Tier B and the escape hatch (unchanged by the generalization):
  issue when same-day remediation is required (urgent HIGH/CRITICAL).
 De-duplicate against open `tech-debt` issues (match by
-CVE/GHSA ID) before creating. Record the `TD-NNN 鈫?#NNNN` mapping in the
+CVE/GHSA ID) before creating. Record the `TD-NNN → #NNNN` mapping in the
 release notes. See `verify` Phase 5.5 for the tech-debt promotion body
 template and `_shared/gitea-write-patterns.md` Pattern 3.
@@ -157,19 +157,19 @@ template and `_shared/gitea-write-patterns.md` Pattern 3.
 | Check             | Status                                                |
 | ----------------- | ----------------------------------------------------- |
-| Clean workspace   | 鉁?/ 鉂?                                              |
+| Clean workspace   | ✅/ ❌                                              |
 | Branch            | {branch name}                                         |
-| Build             | 鉁?/ 鉂?                                              |
+| Build             | ✅/ ❌                                              |
-| Typecheck + Lint  | 鉁?/ 鉂?                                              |
+| Typecheck + Lint  | ✅/ ❌                                              |
-| Tests             | 鉁?/ 鉂?(N passed, M failed)                           |
+| Tests             | ✅/ ❌(N passed, M failed)                           |
-| Dependency audit  | 鉁?/ 鈿狅笍 N known CVEs (pre-existing) / 鉂?N new CVEs   |
+| Dependency audit  | ✅/ ⚠️ N known CVEs (pre-existing) / ❌N new CVEs   |
 ```
 If any gate fails except known CVEs, stop and report what failed.
 ---
-## Phase 2 鈥?Version Bump
+## Phase 2 — Version Bump
 Determine the new version by inspecting git history since the last tag.
@@ -193,14 +193,14 @@ Determine the new version by inspecting git history since the last tag.
   | `docs:` / `chore:`   | (skip)  | Not user-visible              |
   If no conventional prefix found, infer from the subject line:
-   - "add", "implement", "introduce" 鈫?MINOR
+   - "add", "implement", "introduce" → MINOR
-   - "fix", "resolve", "correct" 鈫?PATCH
+   - "fix", "resolve", "correct" → PATCH
-   - "remove", "drop", "rename" (public API) 鈫?MAJOR
+   - "remove", "drop", "rename" (public API) → MAJOR
 5. **Compute bump**:
-   - If any MAJOR commit 鈫?bump MAJOR.
+   - If any MAJOR commit → bump MAJOR.
-   - Else if any MINOR commit 鈫?bump MINOR.
+   - Else if any MINOR commit → bump MINOR.
-   - Else 鈫?bump PATCH.
+   - Else → bump PATCH.
 ```markdown
 ## Version Bump
@@ -210,12 +210,12 @@ Determine the new version by inspecting git history since the last tag.
 **New version**: {new version}
 **Type**: MAJOR / MINOR / PATCH
 **Commits since last tag**: {N}
-**Reason**: {justification 鈥?e.g. "2 feat + 3 fix 鈫?MINOR"}
+**Reason**: {justification — e.g. "2 feat + 3 fix → MINOR"}
 ```
 ---
-## Phase 3 鈥?Changelog
+## Phase 3 — Changelog
 Generate the changelog from `git log <last-tag>..HEAD`:
@@ -224,10 +224,10 @@ Generate the changelog from `git log <last-tag>..HEAD`:
   - Scope (if present, e.g. `feat(auth):`).
   - Description (the subject line, past tense, human-readable).
 2. **Group by type**:
-   - **Added** 鈥?`feat:` commits.
+   - **Added** — `feat:` commits.
-   - **Changed** 鈥?modifications to existing behavior (non-breaking).
+   - **Changed** — modifications to existing behavior (non-breaking).
-   - **Fixed** 鈥?`fix:` commits.
+   - **Fixed** — `fix:` commits.
-   - **Breaking** 鈥?`BREAKING CHANGE:` or `!:` commits.
+   - **Breaking** — `BREAKING CHANGE:` or `!:` commits.
 3. **Deduplicate**: squash multiple commits for the same change into one entry
   where it makes narrative sense.
 4. Read the existing root `CHANGELOG.md` (if any) and prepend this release.
@@ -235,7 +235,7 @@ Generate the changelog from `git log <last-tag>..HEAD`:
 Write to root `CHANGELOG.md` (prepend section).
 ```markdown
-## [{version}] 鈥?{YYYY-MM-DD}
+## [{version}] — {YYYY-MM-DD}
 ### Added
@@ -251,24 +251,24 @@ Write to root `CHANGELOG.md` (prepend section).
 ### Breaking
- {breaking change} ({hash}) 鈥?see migration notes above
+- {breaking change} ({hash}) — see migration notes above
 ```
 ---
-## Phase 4 鈥?Tag & Finalize
+## Phase 4 — Tag & Finalize
-1. **Update version file** 鈥?write the new version to the project's version
+1. **Update version file** — write the new version to the project's version
   manifest.
 2. **Commit**: `git add` version file + changelog file, commit with message:
   ```
   release: {version}
   ```
-3. **Tag**: `git tag v{version}` (adjust prefix per project convention 鈥?
+3. **Tag**: `git tag v{version}` (adjust prefix per project convention —
   check existing tags with `git tag -l`).
 4. **Verify tag**: `git tag -l v{version}` confirms the tag exists.
-**Do not push** 鈥?the user must explicitly request pushing to remote.
+**Do not push** — the user must explicitly request pushing to remote.
 ```markdown
 ## Release Artifact
@@ -282,15 +282,15 @@ Write to root `CHANGELOG.md` (prepend section).
 | File           | Change                    |
 | -------------- | ------------------------- |
-| {version file} | {old} 鈫?{new}             |
+| {version file} | {old} → {new}             |
 | CHANGELOG.md   | Prepended {version}       |
 ```
 ---
-## Phase 4b 鈥?Publish Release Artifacts (octopus project, manual)
+## Phase 4b — Publish Release Artifacts (octopus project, manual)
-> Octopus-specific. Other projects: substitute your own artifact pipeline 鈥?
+> Octopus-specific. Other projects: substitute your own artifact pipeline —
 > the goal is identical (turn the tag into downloadable assets).
 The CI publish pipeline (`.gitea/workflows/publish.yml`) was **retired by
@@ -303,17 +303,17 @@ credentials in the environment.
 - Clean checkout of the release commit (tag pushed or about to be pushed).
 - Credentials in env:
-  - `GITEA_TOKEN` 鈥?PAT with `write:repository` (release create/undraft,
+  - `GITEA_TOKEN` — PAT with `write:repository` (release create/undraft,
    tag push) and `write:package` (container registry). The `CI_PAT` secret
    value is the canonical token.
-  - `NODE_AUTH_TOKEN` 鈥?only if publishing to npm.
+  - `NODE_AUTH_TOKEN` — only if publishing to npm.
-  - `AUR_KEY` 鈥?only if pushing the AUR package.
+  - `AUR_KEY` — only if pushing the AUR package.
  - Docker logged in to the Gitea container registry:
    `echo "$GITEA_TOKEN" | docker login <instance-registry-host> -u <user> --password-stdin`.
 ### Steps
-1. **Version + draft release** (idempotent 鈥?skips if already published):
+1. **Version + draft release** (idempotent — skips if already published):
   ```bash
   GITEA_TOKEN=<pat> GH_REPO=Octopus/octopus bun script/version.ts
   ```
@@ -344,7 +344,7 @@ credentials in the environment.
     -H "Content-Type: application/json" -d '{"draft": false}'
   ```
-5. **Verify assets** 鈥?the release must carry 12 assets:
+5. **Verify assets** — the release must carry 12 assets:
   ```bash
   curl -sS "<instance-base-url>/api/v1/repos/Octopus/octopus/releases/tags/v{version}" \
     -H "Authorization: token $GITEA_TOKEN" | jq '.assets | length'
@@ -368,7 +368,7 @@ credentials in the environment.
 ---
-## Phase 5 鈥?Rollback Plan
+## Phase 5 — Rollback Plan
 Document how to undo this release:
@@ -379,7 +379,7 @@ Document how to undo this release:
 2. **Data rollback** (if applicable):
   - For each migration, confirm the `down` migration exists and has been tested.
   - If the release changes data format without a reversible migration, mark
-     `鈿狅笍 IRREVERSIBLE DATA CHANGE`.
+     `⚠️ IRREVERSIBLE DATA CHANGE`.
 ```markdown
 ## Rollback Plan
@@ -403,7 +403,7 @@ git tag -d v{version}
 ---
-## Phase 6 鈥?Post-release Smoke Test
+## Phase 6 — Post-release Smoke Test
 1. Run the project's build command on the tagged commit. Must pass.
 2. Run the test suite. Must pass.
@@ -411,15 +411,15 @@ git tag -d v{version}
 ---
-## Phase 7 鈥?Report
+## Phase 7 — Report
 ```markdown
 ## Release Report
-**Version**: {old} 鈫?{new} (MAJOR / MINOR / PATCH)
+**Version**: {old} → {new} (MAJOR / MINOR / PATCH)
 **Tag**: v{version}
 **Commits**: {N} since last tag ({feat} features, {fix} fixes)
-**Typecheck**: 鉁?| Lint: 鉁?| Tests: 鉁?
+**Typecheck**: ✅| Lint: ✅| Tests: ✅
 ### Changelog
@@ -427,21 +427,21 @@ git tag -d v{version}
 ### Release Artifacts
- Commit: {hash} 鈥?`release: {version}`
+- Commit: {hash} — `release: {version}`
 - Tag: v{version}
 - Changelog: CHANGELOG.md updated
 ---
-**Deploy**: {manual step 鈥?"merge to main triggers CI", etc.}
+**Deploy**: {manual step — "merge to main triggers CI", etc.}
 **Rollback**: see Phase 5 above
-**Next**: `core/skills/retrospective/SKILL.md` (optional 鈥?run on any project state)
+**Next**: `core/skills/retrospective/SKILL.md` (optional — run on any project state)
 ```
 ---
 ## References
- `core/checklists/release.md` 鈥?Release checklist
+- `core/checklists/release.md` — Release checklist
 - Semver spec: https://semver.org
 - Conventional Commits: https://www.conventionalcommits.org
@@ -25,19 +25,22 @@ role: Reviewer
 ## Tool Availability & Path Resolution
 This skill's reviewers (parallel Explorer subagents) read two kinds of files.
-Some runs lack the `gitea_wiki__*` MCP tools (cross-repo scenario, [org-internal #2115]); the
+Some runs cannot reach the Gitea REST API (cross-repo scenario, [org-internal #2115]); the
-fallbacks below keep reviews working without them.
+fallbacks below keep reviews working without it.
-The Orchestrator probes availability **before dispatching reviewers** (Phase A
+The Orchestrator probes REST reachability **before dispatching reviewers** (Phase A
 step 1, `_shared/review-pipeline-phases.md`) and fails fast if neither path is
 usable, so every reviewer has a working read path by the time it runs.
 ### Wiki artifacts (DAG artifact / review reports)
- **Primary**: `wiki 读写 API（见 TERMINOLOGY）(owner, repo, page_name)` — use when the
+- **Primary**: `GET <gitea-base-url>/api/v1/repos/{owner}/{repo}/wiki/page/{mangled-name}`
-  tool is available. `page_name` construction is in
+  — use when REST is reachable. Resolve `{mangled-name}` from
  `GET .../wiki/pages` (`sub_url` — mangled name with `%2F` encoding and
  possible `.-` suffix); never construct it by hand. Page-name resolution
  context is in
  `_shared/gitea-read-patterns.md` Pattern 1.
- **Fallback** (when `gitea_wiki__*` is unavailable): read the **local wiki
+- **Fallback** (when REST is unreachable): read the **local wiki
  clone** at `<wiki-clone-root>/{repo}-wiki/` — a git checkout of the wiki repo,
  kept current. Wiki filenames are URL-encoded (`/` → `%2F`, with a possible
  `.-` before `.md`), so resolve the file with `glob` rather than constructing
@@ -393,7 +396,7 @@ file (concurrent write race):
 - `{BASELINE_SECTION}`:
  ```
  ## Baseline
-  The artifact under review is the DAG at wiki page `{epic-slug}/dag` (read via `gitea_wiki__get_page`). Read it first for orientation. Its `dag_metrics.review_depth` (D1–D4) sets this review's depth and round cap.
+  The artifact under review is the DAG at wiki page `{epic-slug}/dag` (read via `GET <gitea-base-url>/api/v1/repos/{owner}/{repo}/wiki/page/{mangled-name}`, `sub_url` resolved from `GET .../wiki/pages` first). Read it first for orientation. Its `dag_metrics.review_depth` (D1–D4) sets this review's depth and round cap.
  ```
 - `{READ_FIRST_STEPS}`:
  1. Read the DAG artifact at `{epic-slug}/dag` first for orientation.
@@ -974,7 +974,8 @@ After the Developer completes revision:
      `question` tool, passing `stage: "review-code"`:
      > **Gitea approval timing (mandatory when the PR needs a human approval
-      > gate)**: register the reviewer FIRST via `gitea_pull__add_reviewer`,
+      > gate)**: register the reviewer FIRST via
      > `POST <gitea-base-url>/api/v1/repos/{owner}/{repo}/pulls/{index}/requested_reviewers`,
      > wait for the `REQUEST_REVIEW` registration to be recorded, and only
      > THEN ask the human to approve. Approving before the reviewer is
      > registered produces `official: false` on the approval — the gate
@@ -987,7 +988,7 @@ After the Developer completes revision:
      Final verdict: {PASS | WARN | FAIL}
       Converged: {true | false}
-      See full report: wiki page `{slug}/reviews/code/final/report` （DAG task mode: `{epic-slug}/reviews/code/final/report-task-{node-id}`）（via `gitea_wiki__get_page`，`_shared/gitea-read-patterns.md` Pattern 1）
+      See full report: wiki page `{slug}/reviews/code/final/report` （DAG task mode: `{epic-slug}/reviews/code/final/report-task-{node-id}`）（via `GET <gitea-base-url>/api/v1/repos/{owner}/{repo}/wiki/page/{mangled-name}` — `sub_url` resolved from `GET .../wiki/pages` first, `_shared/gitea-read-patterns.md` Pattern 1）
      All review artifacts: ticket #{issue_number} comments + wiki pages under `{slug}/reviews/code/`（DAG task mode: under `{epic-slug}/reviews/code/`, Tier 1 round artifacts under `<runs-root>/{epic-slug}-task-{node-id}/reviews/code/`）
      Inline comments（only when step 2.56 ran；omit for no-PR flows）: `inline: X posted / Y file-level / Z fallback / W failed`
@@ -732,10 +732,10 @@ originating slug in each row so the trail survives.
 independent ticket THEN, carrying the reserved `TD-NNN`:
 ```
-gitea_issue__create(owner="Octopus", repo="octopus",
+POST <gitea-base-url>/api/v1/repos/Octopus/octopus/issues
-  title="[{origin}] Tech debt: {short description} (TD-{NNN})",
+  body: {"title":"[{origin}] Tech debt: {short description} (TD-{NNN})",
-  body=<promotion template below>,
+         "body":<promotion template below>,
-  labels=[tech_debt_label_id, severity_label_id])
+         "labels":[tech_debt_label_id, severity_label_id]}
 ```
 - **Severity → label** (reuse the existing exclusive Priority set):
@@ -820,8 +820,7 @@ AND closed), per `core/rules/testing.md`** (de-duplicate BEFORE filing,
 retro [org-internal #2696]). Query `baseline-failure` issues in ALL states:
 ```
-gitea_issue__list(owner="Octopus", repo="octopus",
+GET <gitea-base-url>/api/v1/repos/Octopus/octopus/issues?labels=baseline-failure&state=all&page=N&limit=50
  labels="baseline-failure", state="all")
 ```
 Match each candidate by **failure signature** — the error/assertion signature
@@ -848,10 +847,10 @@ number `#NNNN` is the tracker handle.
 no existing family matches the signature:
 ```
-gitea_issue__create(owner="Octopus", repo="octopus",
+POST <gitea-base-url>/api/v1/repos/Octopus/octopus/issues
-  title="[{origin}] Baseline failure: {test identifier} (BF-{NNN})",
+  body: {"title":"[{origin}] Baseline failure: {test identifier} (BF-{NNN})",
-  body=<issue body template below>,
+         "body":<issue body template below>,
-  labels=[baseline_failure_label_id, severity_label_id, kind_bug_label_id])
+         "labels":[baseline_failure_label_id, severity_label_id, kind_bug_label_id]}
 ```
 - **Title**: `[{origin}] Baseline failure: {signature summary} (BF-{NNN})`
@@ -965,8 +964,7 @@ AND closed), per `core/rules/testing.md`** (de-duplicate BEFORE filing,
 retro [org-internal #2696]). Query `flaky-test` issues in ALL states:
 ```
-gitea_issue__list(owner="Octopus", repo="octopus",
+GET <gitea-base-url>/api/v1/repos/Octopus/octopus/issues?labels=flaky-test&state=all&page=N&limit=50
  labels="flaky-test", state="all")
 ```
 Match each candidate by **failure signature** — the flakiness mode (timeout /
@@ -991,10 +989,10 @@ incl. closed tickets). `FT-NNN` names the FAMILY.
 no existing family matches the signature:
 ```
-gitea_issue__create(owner="Octopus", repo="octopus",
+POST <gitea-base-url>/api/v1/repos/Octopus/octopus/issues
-  title="[{origin}] Flaky test: {test identifier} (FT-{NNN})",
+  body: {"title":"[{origin}] Flaky test: {test identifier} (FT-{NNN})",
-  body=<issue body template below>,
+         "body":<issue body template below>,
-  labels=[flaky_test_label_id, severity_label_id, kind_testing_label_id])
+         "labels":[flaky_test_label_id, severity_label_id, kind_testing_label_id]}
 ```
 - **Title**: `[{origin}] Flaky test: {signature summary} (FT-{NNN})` — the
@@ -0,0 +1,94 @@
 #!/usr/bin/env bun
 import fs from "node:fs"
 import path from "node:path"
 const ROOT = path.resolve(import.meta.dir, "..")
 const CORE_DIR = path.join(ROOT, "core")
 const SCAN_EXTENSIONS = new Set([".md", ".json", ".ts", ".tsx", ".js", ".mjs", ".cjs", ".yaml", ".yml", ".txt"])
 export const MOJIBAKE_SIGNATURES: { name: string; pattern: RegExp }[] = [
  { name: "em-dash-mojibake", pattern: /\u9225/ },
  { name: "right-arrow-mojibake", pattern: /\u922B/ },
  { name: "check-mark-mojibake", pattern: /\u9257|\u9253/ },
  { name: "cross-mark-mojibake", pattern: /\u9242/ },
  { name: "geq-mojibake", pattern: /\u922E/ },
  { name: "multiplication-mojibake", pattern: /\u8137/ },
  { name: "replacement-char", pattern: /\uFFFD/ },
  { name: "truncated-mojibake", pattern: /[\u9000-\u9FFF]\?/ },
  { name: "gbk-cjk-bigram", pattern: /椤圭|鍒濆|閰嶇|鐨勶|鎷夎|浼氳瘽|鏃犲|淇濇|缁戝|瀹屾|涓珛|鏀瑰啓|瀹炰緥|鎵归|寤惰|璋冨|绀轰|鍘熸|閰嶉|鎹薄|閫昏|椤甸|绔犵|宸插|鍒嗛|鍏抽|鍚岀|鍚庣|鍓嶇|杩斿|杩涘|閫変|鎸夌|鏉冮|鏂囦|鏂囨/ },
 ]
 export interface EncodingViolation {
  file: string
  line: number
  signature: string
  match: string
 }
 export function scanFile(filePath: string): EncodingViolation[] {
  const text = fs.readFileSync(filePath, "utf8")
  const violations: EncodingViolation[] = []
  const lines = text.split(/\r?\n/)
  for (let i = 0; i < lines.length; i++) {
    for (const sig of MOJIBAKE_SIGNATURES) {
      const m = lines[i]!.match(sig.pattern)
      if (m) {
        violations.push({
          file: filePath,
          line: i + 1,
          signature: sig.name,
          match: m[0]!,
        })
      }
    }
  }
  return violations
 }
 export function collectFiles(dir: string): string[] {
  const out: string[] = []
  if (!fs.existsSync(dir)) return out
  const walk = (d: string) => {
    for (const entry of fs.readdirSync(d, { withFileTypes: true })) {
      const full = path.join(d, entry.name)
      if (entry.isDirectory()) walk(full)
      else if (SCAN_EXTENSIONS.has(path.extname(entry.name))) out.push(full)
    }
  }
  walk(dir)
  return out.sort()
 }
 function main(): void {
  if (!fs.existsSync(CORE_DIR)) {
    console.error(`check-encoding-health: core/ directory not found at ${CORE_DIR} — cannot verify (fail-closed)`)
    process.exit(1)
  }
  const files = collectFiles(CORE_DIR)
  if (files.length === 0) {
    console.error(`check-encoding-health: 0 scannable files under ${CORE_DIR} — cannot verify (fail-closed)`)
    process.exit(1)
  }
  const violations: EncodingViolation[] = []
  for (const f of files) {
    try {
      violations.push(...scanFile(f))
    } catch (err) {
      console.error(`check-encoding-health: failed to read ${f}: ${(err as Error).message}`)
      process.exit(1)
    }
  }
  if (violations.length > 0) {
    console.error(`check-encoding-health: ${violations.length} mojibake violation(s) in core/:`)
    for (const v of violations) {
      const rel = path.relative(ROOT, v.file)
      console.error(`  ${rel}:${v.line} [${v.signature}] ${JSON.stringify(v.match)}`)
    }
    process.exit(1)
  }
  console.log(`check-encoding-health: OK (${files.length} files scanned, 0 violations)`)
 }
 if (import.meta.main) main()
@@ -1,6 +1,6 @@
 {
  "name": "octopus-workflow",
-  "version": "0.1.0",
+  "version": "0.1.3",
  "description": "Standalone workflow core: provider-neutral agent workflow corpus (skills / rules / checklists / templates / schemas) with drift guards, extracted from the octopus agent platform.",
  "license": "MIT",
  "private": false,
@@ -9,7 +9,8 @@
  "scripts": {
    "check:core-cohesion": "bun guards/check-core-cohesion.ts",
    "check:core-p1": "bun guards/check-core-p1.ts",
-    "delink:core": "bun guards/delink-core.ts"
+    "delink:core": "bun guards/delink-core.ts",
    "check:encoding-health": "bun guards/check-encoding-health.ts"
  },
  "repository": {
    "type": "git",
Author	SHA1	Message	Date
octopus	4518f41fd4	v0.1.3: encoding remediation - restore 11 core files to clean UTF-8 + add check:encoding-health guard	2026-09-16 13:13:18 +08:00
octopus	445940ea63	v0.1.2: schema live migration completion — id-aliases frozen:true + COMPATIBILITY 1.0.0 row annotated	2026-09-15 15:09:47 +08:00
octopus	18ffce5d29	v0.1.1: Gitea transport surface de-MCP — REST+swagger sole canon (adapter recipes, terminology map, review probes)	2026-09-15 09:59:04 +08:00