v0.1.7: export drift clearance — release checklist 7.7 three-leg desktop feed dispatch + verify-feed.ts fail-loud validation (main-repo commit 867502fec), implement SKILL Producer test preflight core-neutral block (main-repo commit 4a149fccf); clears both pending content-drift findings

README.md

@@ -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`,

core/adapters/gitea/patterns.md

@@ -138,31 +138,6 @@ curl -fsS -X PATCH "<gitea-base-url>/api/v1/repos/Octopus/octopus/issues/comment
 
 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
-发现用 REST；「把工单移到列」的操作端点语义复杂，经 swagger 查询后
-调用，不臆造路径：
-
-```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；移动与 Pattern 7 同款
-（projects/columns 经 REST + swagger 发现，同上）。
-
 ## Pattern 8: post-commit-status
 
 commit status 直发 REST（评审综合的 Tier-2 落点）：
@@ -183,22 +158,6 @@ context 公式：`pipeline/review-{stage}`（`code` / `review-dag` /
 `audit-process`）。token 从实例配置读取（此处 `<token>` 占位）。
 merge 前读回验证：`GET /commits/{PR_SHA}/status`。
 
-## Pattern 9: create-iteration-board
-
-```bash
-# 建 project（board）：先经 swagger 查询 create 端点契约
-curl -s <gitea-base-url>/swagger.v1.json -o /tmp/gitea-sw.json
-jq '.paths["/repos/{owner}/{repo}/projects"].post' /tmp/gitea-sw.json
-# 随后 POST 建板（title="{slug} — Iteration {N}", description="…"）
-# 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
-```
-
-projects 仅 repo 级。DAG 聚合 agent 在单门 PASS 后建板；工单正文模板带
-`## Node Reference`（指向 `{epic-slug}/dag`）、`## Acceptance Criteria`、
-`## Parent`。
-
 ## Pattern 10: artifact-index（工单 ↔ 工件索引）
 
 技能发布工件后，在源工单维护 **`## 工件索引` 评论**——单一原位编辑的

core/adapters/gitea/reading.md

@@ -80,7 +80,7 @@ curl -fsS -H "Authorization: token <token>" \
 
 ## Pattern 4: read-project-column-issues
 
-看板列工单队列。project/column 发现：
+看板列工单队列（只读）。project/column 发现：
 
 ```
 curl -fsS -H "Authorization: token <token>" \
@@ -89,9 +89,7 @@ curl -fsS -H "Authorization: token <token>" \
   "<gitea-base-url>/api/v1/repos/Octopus/octopus/projects/{project_id}/columns"
 ```
 
-「把工单移到列」等复杂操作：经 `swagger.v1.json`
+projects 仅 repo 级（无 org/user 级端点）。
-（`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）
 

core/checklists/audit-process.md

@@ -179,6 +179,7 @@ creating thin wrapper checklist files would add no value.
 | 8.5 | 防范范围收窄：明令禁止「只看重点/从简」类弱化措辞（IEEE 1028-2008 完整性）  | ☐ | ☐ | |
 | 8.6 | 留痕：审计产物落盘到结构化文件，而非仅存于对话                        | ☐ | ☐ | |
 | 8.7 | 闭环：存在重审循环与收敛/审批终止条件（ISO 19011:2018 跟踪与关闭）         | ☐ | ☐ | |
+| 8.8 | 流程自身测试为绿：Orchestrator（bash 可用）在派发审计员**之前**机械运行流程自身的测试套件与守卫门（`bun run test:parallel` 全量分片 + `check:*` 守卫族，如 core-parity / encoding-health / derived-artifacts），并把命令、基线 SHA 与结果摘要落盘到 `<runs-root>/audit/reviews/audit-process/process-tests-green.md`（Tier 1）；审计员（只读，无 bash）核对该记录存在于当前基线且为绿——任何红测试/红守卫本身即流程缺陷，按 findings 登记（缺陷逃逸案例：红测试存活 3 轮审计、无任何维度运行过测试套件，[org-internal #4787]） | ☐ | ☐ | 运行归 Orchestrator、核对归审计员（角色边界：`core/skills/_shared/review-orchestrator-rules.md` §No bash for Explorer sub-agents） |
 
 ---
 

core/checklists/release.md

@@ -1,6 +1,6 @@
 # Release 检查清单
 
-> 发版前自检。Release Manager 在 Phase 1 和 Phase 6 完整过一遍。
+> 发版前自检。Producer (Worker) 在 Phase 1 和 Phase 6 完整过一遍。
 
 > **维度命名空间（dimension namespace）**: 本清单中的维度代码（如 TST/BEH/GATE/REG）是**清单局部（checklist-local）**标识符，仅在本文档内唯一；其他清单可能对相同字母串绑定不同概念（如 code-review.md 的 TST=Test Quality、verification.md 的 TST=Test Suite Completeness、port.md 的 TST=Test Porting）。跨清单引用时必须带清单限定（如 code-review.md TST 5.8），不得使用裸代码。
 
@@ -74,3 +74,24 @@
 | 6.1 | Tagged commit 可构建                | ☐    | ☐      |      |
 | 6.2 | 测试全部通过                        | ☐    | ☐      |      |
 | 6.3 | 回到了原始分支                      | ☐    | ☐      |      |
+
+---
+
+## 7. 产物发布（DIST — Artifact Distribution，octopus 项目）
+
+> 对应 `.octopus/skills/release/SKILL.md` Phase 4b（#2003 退役 CI publish
+> 管线后的手工发布流程）。**主仓库 tag + release 对象 ≠ 发布完成**——CLI
+> 二进制、公开镜像、桌面 feed 三层外圈全部就位才算。本清单从磁盘读取，
+> 作为技能注入被截断时的兜底事实源（v0.25.0 发布时技能注入截断恰好切掉
+> Phase 4b，导致外圈整层遗漏——本节由此设立）。
+
+| #   | 检查项                                   | 通过 | 不通过 | 备注 |
+| --- | ---------------------------------------- | ---- | ------ | ---- |
+| 7.1 | 12 平台 CLI 二进制已构建（tag 的干净 checkout，`bun packages/octopus/script/build.ts`），全部 smoke test 输出版本号 | ☐ | ☐ | Windows 无 `python3` 命令，zip 归档需垫 shim 或手动补齐 |
+| 7.2 | 12 个归档已挂到主仓库 release（zip×6 + tar.gz×6） | ☐ | ☐ | |
+| 7.3 | （可选，Gitea-only 口径可跳过）npm/docker/AUR 外部 registry 已发或明确跳过 | ☐ | ☐ | `OCTOPUS_GITEA_ONLY=true` |
+| 7.4 | `sync-public-assets.sh` 已跑：公共镜像 `Octopus/octopus-release` 的 `v{version}` release 有 12 资产 | ☐ | ☐ | 大 POST 出站不通时经服务器 localhost 中继 |
+| 7.5 | `sync-public-install.sh` 已跑：install/install.ps1/README 同步到镜像 main（注意 cp 目标是**根 README.md**，不是 scripts/ 副本） | ☐ | ☐ | |
+| 7.6 | `verify-public-sync.sh` PASSED | ☐ | ☐ | |
+| 7.7 | Desktop feed 三腿已派发（mac 走 `desktop-mac.yml` dispatch；win/linux 各一次 `desktop-feed.yml` dispatch），`bun packages/desktop/script/verify-feed.ts --version <ver> --channel <beta|prod>` PASS（三平台 yml 全量校验：`latest.yml`/`latest-linux.yml`/`latest-mac.yml` 的 `version:` == CLI 版本 + size 对资产逐项核对 + 匿名可达） | ☐ | ☐ | #6378 起以 verify-feed.ts 为准（v0.31.0 漏腿事故 #6375 的 fail-loud 补丁）；concurrency 组已按 platform 分离；stable 通道 feed 缺失见 #6376 |
+| 7.8 | README 下载链接抽查（install 脚本 raw、资产直链、docs 相对链接）匿名可达 | ☐ | ☐ | v0.18 遗留 wiki 坏链由此发现 |

core/rules/issue-checklist-sync.md

@@ -46,9 +46,9 @@ Rules:
   surfaced by checklist annotations alone — do NOT add live-status rows for
   them. PR / review / CI transitions carry BOTH a checklist annotation AND
   a live-status row.
-- **Stage rows live on the board, not here**: pipeline stage transitions are
+- **No stage rows here**: pipeline stage transitions are NOT represented by
-  represented by the Pipeline Stages board column (shared write-patterns
+  `## 当前状态` rows — they surface through checklist annotations at skill
-  Pattern 7.5), NOT by `## 当前状态` rows. Keep only the
+  exits. Keep only the
   status-sync-automated rows (PR / 代码评审 / CI) and non-stage
   blockers/deferrals.
 - Update in place (same section heading `## 当前状态`), never append a second copy.

core/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": {

core/schemas/review-status.schema.json

@@ -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"

core/schemas/reviewer-output.schema.json

@@ -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",
@@ -31,6 +31,7 @@
     },
     "quantitative_summary": {
       "type": "object",
+      "description": "Every check the reviewer executed this round (PASS and FAIL counted in total_checks; NA reported via na_count). The verdict field must follow these counts per the thresholds documented on verdict — a synthesis consumer recalculates pass_rate from passed/total_checks and treats a mismatch as a malformed artifact.",
       "required": ["total_checks", "passed", "failed", "pass_rate"],
       "properties": {
         "total_checks": { "type": "integer", "minimum": 1 },
@@ -74,12 +75,13 @@
           },
           "severity": {
             "type": "string",
-            "enum": ["BLOCKER", "MAJOR", "MINOR", "INFO"]
+            "enum": ["BLOCKER", "MAJOR", "MINOR", "INFO"],
+            "description": "BLOCKER: breaks an acceptance criterion, hangs/leaks, or opens an abuse channel — the artifact must not land as-is. MAJOR: a real defect on a non-blocking path, or a test/lock blind to a plausible regression (a mutation would escape). MINOR: quality/drift issue with a cheap local fix (naming, duplication, small docs gap); no behavioral risk. INFO: observation, accepted-risk note, or follow-up ticket material — no action required this round. Calibration rule: severity grades the FINDING's impact, not the reviewer's confidence; low-confidence suspicions go to INFO with the evidence, never inflated to MAJOR."
           },
           "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",

core/schemas/runs-bundle.schema.json

@@ -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"] },

core/schemas/runs-index.schema.json

@@ -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"],

core/schemas/runs-meta.schema.json

@@ -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"],

core/schemas/workflow-routing.schema.json

@@ -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" }
       }

core/skills/_shared/review-pipeline-phases.md

@@ -41,11 +41,6 @@ in `_shared/gitea-write-patterns.md`.
 
 **Orchestrator actions**:
 
-0. **Move the source issue to the `review` column** on the Pipeline Stages
-   board per `_shared/gitea-write-patterns.md` Pattern 7.5. Skip if no
-   source issue exists. The review stage is a single board column covering
-   all review targets (DAG single gate / code review / audit-process).
-
 0.5. **Initialize the review-status file** (round 1 only). The Orchestrator
    creates `<runs-root>/{slug}/reviews/{stage}/status.json` before dispatching
    round 1, with the full schema-required field set
@@ -111,6 +106,13 @@ in `_shared/gitea-write-patterns.md`.
      `core/skills/_shared/review-orchestrator-rules.md` — Default
      Explorer Permissions).
    - Temperature: 0.1 (deterministic output).
+   - StructuredOutput mount ([org-internal #5658]): pass `format: { type:
+     "json_schema", schema: <the reviewer-output.schema.json contents you
+     read at prompt build time> }` on the task dispatch — the reviewer's
+     final emission is schema-enforced (malformed verdict/severity/summary
+     args are rejected with field-path repair feedback inside the reviewer's
+     own loop). The findings FILE remains the canonical Tier-1 artifact; the
+     structured output mirrors it as a self-check.
 
 4. Wait for all {REVIEWER_OR_AUDITOR}s to complete. Each reviewer writes its
    dimension result to the skill's configured findings sink:
@@ -171,6 +173,11 @@ in `_shared/gitea-write-patterns.md`.
      `tier1-local` skills; `/tmp/octopus/...` for `tier2-comment` skills)
    - `permissions`: read + write + edit + bash + glob + grep (all allow)
    - `temperature`: 0.1
+   - `format` ([org-internal #5658]): `{ type: "json_schema", schema: <the
+     synthesis.schema.json contents you read> }` — the Synthesizer's final
+     emission is schema-enforced (malformed verdict/dimension args rejected
+     with field-path repair feedback in-loop). The posted fenced JSON block
+     remains the canonical artifact; the structured output mirrors it.
    - Foreground (the Orchestrator waits for completion).
 
 3. The Synthesizer:
@@ -324,8 +331,15 @@ After the {REVISION_ROLE} completes revision:
   round, or the diff touches a frozen cross-session contract) —
   `<instance-root>/workflow-routing.yaml` `review.max_rounds` ([org-internal #3567], process-diet
   P0b). At budget without convergence: STOP, register the remaining
-  BLOCKER/MAJOR findings as TD registry rows, verdict FAIL if any BLOCKER
+  BLOCKER/MAJOR findings as TD registry rows, then compute the verdict
-  remains else PASS — the debt is carried by those TD registry rows
+  with the shared three-tier ladder (`core/schemas/synthesis.schema.json`
+  `overall_verdict` + `core/skills/_shared/review-orchestrator-rules.md`
+  rule 3): FAIL if any BLOCKER or FAIL dimension remains, else WARN,
+  PASS only if every remaining dimension is PASS ([org-internal #4786]:
+  the prior binary "else PASS" wording silently upgraded WARN-eligible
+  outcomes to PASS; a PASS round has already stopped at the convergence
+  table above, so the residual tail lands WARN or FAIL). The debt is
+  carried by those TD registry rows
   (see `review-code/SKILL.md` Phase D). This
   supersedes the 2026-08-25 [org-internal #3380] calibration (p50=2, p95=5, n=66): the runs
   past round 3 are the marathon tail this budget exists to cut; their residue

core/skills/_shared/review-reviewer-prompt.md

@@ -32,6 +32,18 @@ Label: {DIMENSION_NAME}
 
 ## Instructions
 
+### Gate records are deterministic inputs ([org-internal #5656] N-04)
+
+When the work item carries gate records (`gate` tool results — metadata
+`exit_code`, `duration_ms`, `ci_run_id`), those records ARE the command
+outcomes for mechanical questions (tests/typecheck/lint): cite the exit code
+verbatim (`gate <id> (<tier>): exit_code=<n> -> green|red` — canonical block
+in `packages/octopus/src/gate/consume.ts`) and never substitute a model's
+narration of command output. A claim that disagrees with a record's
+exit_code is a finding (record wins); a mechanical claim with no record is
+unverifiable — request the citation. A green verdict-cache hit
+(`metadata.verdict_cache.key`) counts the same as a fresh run.
+
 {READ_FIRST_STEPS}
 4. For each checklist item, determine whether the {ARTIFACT_NOUN} satisfies it.
    Every checklist item must receive a PASS or FAIL verdict.
@@ -46,6 +58,21 @@ Label: {DIMENSION_NAME}
    (reviewer_count > 1), use the slot-prefixed form {DIM}R{k}-F{NNN} with your
    1-based slot k (e.g. TOPOR1-F001) so parallel slot files never collide on id.
 {CONTRADICTION_RULE}
+6b. Code graph availability (worktree sessions): if `codegraph_status` is
+   unavailable or reports no index for the tree under review (typical when
+   reviewing from a session worktree whose per-worktree `.codegraph/` index
+   has not finished building — see `<instance-root>/rules/code-graph.md`), do NOT
+   silently substitute grep+read for structural questions ("who calls /
+   what depends on / where defined"). Instead:
+   - For symbols on the MAIN branch side (baselines, design refs, cross-session
+     frozen contracts), you MAY query the main checkout's index (path given in
+     your dispatch preamble) and cite `main:<path>:<line>`.
+   - If no index is reachable at all, mark the affected checklist items NA
+     with reason "codegraph unavailable — structural check degraded to grep"
+     and emit one INFO finding (id `{DIM}-F001`-style, in your dimension's own
+     code) recording the degradation, so the Synthesizer can surface it.
+   Findings derived purely from grep+read when a graph query was required are
+   treated as low-confidence and may be waived in synthesis.
 7. Assign severity strictly:
 {SEVERITY_DEFINITIONS}
 8. Count every PASS and FAIL. Compute pass_rate = passed / total_checks.

core/skills/_shared/roles/coordinator.yaml

@@ -1,4 +1,4 @@
-> Core 中立版（Increment 6a 改写，原 deferHard verbatim）。编号与条目结构严格不变（C-2 不变量）；实例术语按 `core/adapters/TERMINOLOGY.md` 绑定。
+# > Core 中立版（Increment 6a 改写，原 deferHard verbatim）。编号与条目结构严格不变（C-2 不变量）；实例术语按 `core/adapters/TERMINOLOGY.md` 绑定。
 name: Coordinator
 purpose: >
   Pool dispatch coordinator (billing-v2 [org-internal #4041] §7, REQ-F-012): a wake-driven,

core/skills/_shared/roles/producer.yaml

@@ -1,4 +1,4 @@
-> Core 中立版（Increment 6a 改写，原 deferHard verbatim）。编号与条目结构严格不变（C-2 不变量）；实例术语按 `core/adapters/TERMINOLOGY.md` 绑定。
+# > Core 中立版（Increment 6a 改写，原 deferHard verbatim）。编号与条目结构严格不变（C-2 不变量）；实例术语按 `core/adapters/TERMINOLOGY.md` 绑定。
 name: Producer
 purpose: >
   Write production artifacts — requirements, design, plans, code, fixes,

core/skills/_shared/roles/reviewer.yaml

@@ -1,4 +1,4 @@
-> Core 中立版（Increment 6a 改写，原 deferHard verbatim）。编号与条目结构严格不变（C-2 不变量）；实例术语按 `core/adapters/TERMINOLOGY.md` 绑定。
+# > Core 中立版（Increment 6a 改写，原 deferHard verbatim）。编号与条目结构严格不变（C-2 不变量）；实例术语按 `core/adapters/TERMINOLOGY.md` 绑定。
 name: Reviewer
 purpose: >
   Review one dimension of an artifact against its checklist, read-only.

core/skills/_shared/roles/tool.yaml

@@ -1,4 +1,4 @@
-> Core 中立版（Increment 6a 改写，原 deferHard verbatim）。编号与条目结构严格不变（C-2 不变量）；实例术语按 `core/adapters/TERMINOLOGY.md` 绑定。
+# > Core 中立版（Increment 6a 改写，原 deferHard verbatim）。编号与条目结构严格不变（C-2 不变量）；实例术语按 `core/adapters/TERMINOLOGY.md` 绑定。
 name: Tool
 purpose: >
   Specialized tool agent for image interpretation and other vision/utility

core/skills/_shared/roles/verifier.yaml

@@ -1,4 +1,4 @@
-> Core 中立版（Increment 6a 改写，原 deferHard verbatim）。编号与条目结构严格不变（C-2 不变量）；实例术语按 `core/adapters/TERMINOLOGY.md` 绑定。
+# > Core 中立版（Increment 6a 改写，原 deferHard verbatim）。编号与条目结构严格不变（C-2 不变量）；实例术语按 `core/adapters/TERMINOLOGY.md` 绑定。
 name: Verifier
 purpose: >
   Run the iteration's DoD matrix, integration tests, NFR validation, and

core/skills/_shared/synthesis_task.md

@@ -198,6 +198,14 @@
 - **Rule 4 — Aggregation, not reinterpretation**: You MUST NOT soften, rephrase,
   or downgrade reviewer findings. If a reviewer writes "BLOCKER", it stays
   "BLOCKER" in synthesis.
+
+1c. **Pass-rate recalc post-check (MANDATORY, [org-internal #5658])**: for
+   every dimension, recompute `pass_rate = passed / total_checks` from its
+   `quantitative_summary` and compare with the reported value. On a mismatch:
+   keep the raw file unchanged, use the RECOMPUTED value in the synthesis
+   digest, and note the mismatch — a reviewer-output whose `pass_rate` does
+   not match its own counts is a malformed artifact (the schema description
+   says exactly this; this step is the enforcement).
 - **Rule 5 — Anonymous findings preservation**: If two reviewers independently
   flag the same issue from different dimensions, preserve both entries. Do not
   deduplicate by discarding one — cross-dimension agreement is itself a signal.
@@ -209,6 +217,11 @@
 Return ONLY this summary as your final message. Do NOT include the full
 synthesis JSON — it is already posted to the pipeline PR / source issue
 comment (for audit-process runs, the wiki page `audit/{date}/round{N}/synthesis`).
+
+When your dispatch carries `format` (StructuredOutput mount, [org-internal
+[org-internal #5658]]): the structured output is the MIRROR self-check of this summary (same
+schema, schema-enforced), not a second artifact — the posted fenced JSON block
+and this summary remain canonical.
 Persist this summary verbatim to
 `<runs-root>/{slug}/reviews/{stage}/round{N}/synthesis-return.md` before
 returning (step 9 above — worker-report persistence [org-internal #2847]).

core/skills/codegraph-setup/SKILL.md

@@ -1,33 +1,14 @@
 ---
 name: codegraph-setup
 description: >
-  Use ONLY when installing, configuring, initializing, or troubleshooting CodeGraph
+  Use ONLY when installing, configuring, initializing, or troubleshooting
-  (@colbymchenry/codegraph — https://github.com/colbymchenry/codegraph) in the
+  CodeGraph (@colbymchenry/codegraph) in the octopus environment.
-  octopus environment. Covers global CLI install, per-project `.codegraph/`
-  indexing, and maintenance commands (status, sync, upgrade, uninstall). MCP
-  wiring into octopus.jsonc is handled by the kickoff pipeline
-  (`octopus kickoff` or `/kickoff`). Also use when a project session reports a
-  missing/stale `.codegraph/` index.
 triggers:
   - codegraph
   - code graph
-  - codegraph setup
-  - codegraph install
-  - codegraph init
-  - .codegraph
-  - codegraph_explore
-  - codegraph_node
-  - codegraph_callers
-  - codegraph_status
-  - install codegraph
-  # Chinese — bare nouns for code-graph concepts. The English "codegraph" brand
-  # name above already covers mixed-language phrasings; these cover pure Chinese.
   - 代码图
-  - 代码图谱
   - 代码索引
   - 索引代码
-  - 装代码图
-  - 初始化代码图
 role: Producer
 ---
 

core/skills/gitea-rest/SKILL.md

@@ -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.

core/skills/headless-session-ops/SKILL.md

@@ -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`).

core/skills/image-interpret/SKILL.md

@@ -3,7 +3,7 @@ name: image-interpret
 description: >
   Use ONLY when the agent needs to read or analyze an image (screenshot,
   design mockup, UI capture, .png/.jpg/.webp file) but the active model lacks
-  vision capability. Delegates to the Image Interpreter role (vision-capable
+  vision capability. Delegates to the Tool role (image interpretation) (vision-capable
   model) which returns a structured text spec — layout regions, colors (hex),
   spacing (px), typography, component hierarchy, and responsive breakpoints.
   Do not use for non-image tasks or when the active model already supports
@@ -31,7 +31,7 @@ role: Tool
 
 You (the calling agent) cannot read images — your model has no vision. Any
 task that requires *seeing* a visual artifact must be delegated to the
-**Image Interpreter** role, which runs on a vision-capable model and returns a
+**Tool** role (image interpretation), which runs on a vision-capable model and returns a
 structured text description you can act on.
 
 Trigger situations:
@@ -64,7 +64,7 @@ Trigger situations:
    )
    ```
 
-4. **Consume the returned text spec.** The Image Interpreter returns a
+4. **Consume the returned text spec.** The Tool sub-agent (image interpretation) returns a
    structured description only — it cannot write code or artifacts. Use the
    returned spec to drive your own work (code generation, design review,
    planning).
@@ -74,7 +74,7 @@ Trigger situations:
 
 ## Notes
 
-- The Image Interpreter is **read-only** — it describes images, it does not edit
+- The Tool sub-agent (image interpretation) is **read-only** — it describes images, it does not edit
   files or write code.
 - One delegation per distinct visual question. Batch multiple images into a
   single delegation only when they must be compared.

core/skills/implement/SKILL.md

@@ -127,6 +127,20 @@ Rules:
 
 Each execution mode below defines its own Tester focus and any mode-specific orchestration overrides.
 
+**Producer test preflight** (before writing any test):
+
+1. **No absolute-path targets outside the test's own fixture/instance dir** — target fixtures or instance-relative paths instead. Where behavior is
+   platform-dependent (path resolution differs Windows/Linux), assert the
+   platform-specific expectation explicitly; a platform mismatch must fail,
+   never pass by accident.
+2. **Polling/wait-for loops must be bounded AND non-vacuous** — bound the
+   loop AND assert the body executed at least once (e.g. an iteration
+   counter asserted after the loop), so a timeout-cut never yields a false
+   green.
+
+Anchor: CI job 112302 (PR [org-internal #6409] first head red — nonexistent absolute path
+drill + 15s-bound vacuous loop).
+
 ## Greenfield vs. Brownfield
 
 **Greenfield** (new project): Create new files following the design. Project conventions are defined by the design document.

core/skills/implement/reference/implement-mode.md

@@ -179,10 +179,6 @@ Available work items:
 
 #### Phase 1 — Parse Context
 
-> **Pipeline stage**: if the source issue exists, move it to the `implement`
-> column on the Pipeline Stages board per `_shared/gitea-write-patterns.md`
-> Pattern 7.5. Skip if no source issue exists.
-
 Read the upstream artifacts to build a complete implementation context.
 Resolve inputs per the DAG-route read map (Preconditions above); standalone
 modes read the request/bug report instead:
@@ -499,11 +495,6 @@ issue exists.
    retired — each one re-triggered the full CI surface for near-zero re-tested
    risk.
 
-> **Kanban column lifecycle**: automated (`POST <gitea-base-url>/api/v1/repos/{owner}/{repo}/issues` → Backlog,
-> `POST .../pulls` → Review; no manual moves). Single shared reference:
-> `_shared/gitea-write-patterns.md` Pattern 7.5; column semantics: wiki
-> `kanban-lifecycle`.
-
 ---
 
 #### Phase 5 — Report

core/skills/project-kickoff/SKILL.md

@@ -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）`)

core/skills/release/SKILL.md

@@ -1,25 +1,23 @@
 ---
 name: release
 description: >
-  Use ONLY when ready to cut a release. The Release Manager (Worker) inspects
+  Use ONLY when ready to cut a release. The Producer (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€?
 # 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,
@@ -28,16 +26,16 @@ produced here is the input to project-specific deployment workflows.
 
 ## Agent Role
 
-The release is owned and executed by the **Release Manager** (Worker).
+The release is owned and executed by the **Producer** (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 `.octopus/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
+compacting). The Producer 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.
 
 ---
 
@@ -46,11 +44,11 @@ nothing 鈥?re-read the release checklist state and git log to resume.
 Before starting the release:
 
 - [ ] Working tree is clean (`git status` has no uncommitted changes).
-- [ ] `core/checklists/release.md` is accessible.
+- [ ] `.octopus/checklists/release.md` is accessible.
 
 ---
 
-## Phase 1 鈥?Pre-release Gate
+## Phase 1 — Pre-release Gate
 
 Run each check against the live project. Stop and report failures.
 
@@ -65,82 +63,82 @@ 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 REST `POST .../issues` 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`
+  batch PR via the `land-batch` skill (`.octopus/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 +146,7 @@ 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 +155,19 @@ 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 +191,14 @@ 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 +208,12 @@ 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 +222,10 @@ 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 +233,7 @@ 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 +249,24 @@ 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 +280,15 @@ 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 +301,17 @@ 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 "$GITEA_TOKEN" | docker login <instance-registry-host> -u <user> --password-stdin`.
+    `echo "$GITEA_TOKEN" | docker login eightarms.net -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
    ```
@@ -323,7 +321,7 @@ credentials in the environment.
    ```bash
    OCTOPUS_VERSION={version} OCTOPUS_RELEASE={release-id} \
      GH_REPO=Octopus/octopus GITEA_TOKEN=<pat> \
-     bun <harness-package>/script/build.ts
+     bun packages/octopus/script/build.ts
    ```
    `build.ts` attaches the 12 release assets to the draft release.
 
@@ -339,14 +337,14 @@ credentials in the environment.
 4. **Undraft the release** (makes it public):
    ```bash
    curl -fsS -X PATCH \
-     "<instance-base-url>/api/v1/repos/Octopus/octopus/releases/{release-id}" \
+     "https://eightarms.net/api/v1/repos/Octopus/octopus/releases/{release-id}" \
      -H "Authorization: token $GITEA_TOKEN" \
      -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}" \
+   curl -sS "https://eightarms.net/api/v1/repos/Octopus/octopus/releases/tags/v{version}" \
      -H "Authorization: token $GITEA_TOKEN" | jq '.assets | length'
    ```
 
@@ -368,18 +366,23 @@ credentials in the environment.
 
 ---
 
-## Phase 5 鈥?Rollback Plan
+## Phase 5 — Rollback Plan
 
 Document how to undo this release:
 
 1. **Git rollback**:
    - `git tag -d v{version}` (if not yet pushed).
    - `git revert {commit_hash}` (if already merged).
-   - If the release includes DB migrations, confirm the `down` migration exists.
+   - If the release includes DB migrations, confirm the `down` migration exists
+     **when the project's migration tooling provides one**. This repo's Drizzle
+     convention is forward-only (`migration.sql` + `snapshot.json`, no `down`
+     files) — there, record the reversal plan (manual SQL / restore) or mark the
+     change irreversible instead of waiting on a `down` file that never comes.
 2. **Data rollback** (if applicable):
-   - For each migration, confirm the `down` migration exists and has been tested.
+   - For each migration, confirm the `down` migration exists and has been tested
+     where the tooling offers one; otherwise document the manual reversal steps.
    - If the release changes data format without a reversible migration, mark
-     `鈿狅笍 IRREVERSIBLE DATA CHANGE`.
+     `⚠️ IRREVERSIBLE DATA CHANGE`.
 
 ```markdown
 ## Rollback Plan
@@ -390,7 +393,7 @@ git tag -d v{version}
 # or: git revert {hash}
 
 ### Data Rollback
-- Migration `{name}`: down {exists / NOT FOUND}
+- Migration `{name}`: down {exists / NOT FOUND / N/A — forward-only tooling}
 - {additional risks}
 
 ### Rollback Triggers
@@ -403,7 +406,7 @@ 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 +414,15 @@ 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 +430,21 @@ 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**: `.octopus/skills/retrospective/SKILL.md` (optional — run on any project state)
 ```
 
 ---
 
 ## References
 
-- `core/checklists/release.md` 鈥?Release checklist
+- `.octopus/checklists/release.md` — Release checklist
 - Semver spec: https://semver.org
 - Conventional Commits: https://www.conventionalcommits.org

core/skills/review-artifact/SKILL.md

@@ -97,10 +97,7 @@ The stage IDs remain as-is — they are used by the stage registry and auto-appr
 This skill follows the standardized parallel-review pipeline. The full mechanics are in:
 
 - `<!-- inject: ../_shared/review-pipeline-phases.md -->` — Phase A through Phase E
-  - **Phase A step 0**: move the source issue to the `review` column on the
+  (canonical orchestrator actions for the shared flow)
-    Pipeline Stages board per `_shared/gitea-write-patterns.md` Pattern 7.5
-    (see `_shared/review-pipeline-phases.md` for the canonical orchestrator
-    actions — step 0 is now part of the shared flow).
 - `<!-- inject: ../_shared/review-orchestrator-rules.md -->` — mandatory orchestrator rules
 - `<!-- inject: ../_shared/review-final-report-template.md -->` — final report format
 - `<!-- inject: ../_shared/review-revision-prompt.md -->` — Phase C revision prompt template
@@ -187,6 +184,15 @@ The audit target is the **SDLC factory itself** — the set of skills, checklist
 - [ ] `core/skills/` exists and contains at least one `SKILL.md`.
 - [ ] `core/checklists/audit-process.md` is accessible.
 - [ ] `core/schemas/` contains the shared review schemas (`reviewer-output`, `synthesis`, `review-status`).
+- [ ] **Process-tests-green gate ([org-internal #4787] STD 8.8)**: before dispatching
+  auditors, the Orchestrator (bash-capable; Explorer auditors have none by
+  construction) runs the process's own suite and guards — from
+  `<harness-package>`: `bun run test:parallel`, plus the repo-root `check:*`
+  guard family — and writes the commands, baseline SHA, and per-command result
+  summary to `<runs-root>/audit/reviews/audit-process/process-tests-green.md`
+  (Tier 1). The read-only STD 8.8 auditor verifies that record against the
+  current baseline; any red test/guard is itself a process defect and MUST be
+  filed as a finding.
 
 No `.artifacts/{slug}/` inputs are required — the audit reads `<instance-root>/` itself. Audit outputs are published as Gitea wiki pages under `audit/{date}/`.
 
@@ -201,7 +207,7 @@ No `.artifacts/{slug}/` inputs are required — the audit reads `<instance-root>
 | 5 | FLOW | Pipeline Cohesion | FLOW 5.1–5.6 | Preconditions + output sections of every `SKILL.md` |
 | 6 | SCH | Schema Contract | SCH 6.1–6.5 | `core/schemas/*.json` + skills that reference them |
 | 7 | DUP | Duplication & Drift | DUP 7.1–7.4 | ALL `SKILL.md` + ALL `checklists/*.md` |
-| 8 | STD | Audit Standards (ISO/IEEE) | STD 8.1–8.7 | `review-*` skills, `review-artifact` (target: `audit-process`) itself |
+| 8 | STD | Audit Standards (ISO/IEEE) | STD 8.1–8.8 | `review-*` skills, `review-artifact` (target: `audit-process`) itself |
 | 9 | AGT | AGENTS.md Conformance | AGT 9.1–9.5 | ALL `SKILL.md` + `AGENTS.md` |
 | 10 | TRC | Traceability | TRC 10.1–10.5 | `review-*` skills, schemas, status artifacts |
 

core/skills/review-code/SKILL.md

@@ -458,7 +458,7 @@ table).
 <!-- section:phase-a -->
 ## Phase A — Parallel Review
 
-> **Canonical mechanics**: `core/skills/_shared/review-pipeline-phases.md` — keep this section in sync with the canonical Phase A–E flow. This section adds review-code-specific constants (10 dimensions, severity definitions, risk tiers, output mode, standalone-bugfix mode). Step 0 (move source issue to `review` column on Pipeline Stages board per Pattern 7.5) is inherited from the shared Phase A orchestrator actions; see `_shared/review-pipeline-phases.md`.
+> **Canonical mechanics**: `core/skills/_shared/review-pipeline-phases.md` — keep this section in sync with the canonical Phase A–E flow. This section adds review-code-specific constants (10 dimensions, severity definitions, risk tiers, output mode, standalone-bugfix mode); orchestrator actions are inherited from the shared Phase A flow.
 
 ### Standalone Bugfix Mode — Orchestrator Dispatch
 
@@ -530,6 +530,13 @@ fallback is retired with the design pipeline, [org-internal #3072] phase 3):
      emits the reviewer's output; it does NOT touch the code under review, so
      rule #7 auditor independence holds.)
    - Temperature: 0.1 (deterministic output).
+   - StructuredOutput mount ([org-internal #5658]): pass `format: { type: "json_schema",
+     schema: <the reviewer-output.schema.json contents you read at prompt
+     build time> }` on the Task dispatch — the reviewer's final emission is
+     schema-enforced (malformed verdict/severity/summary args are rejected
+     with field-path repair feedback inside the reviewer's own loop). The
+     findings FILE remains the canonical Tier-1 artifact; the structured
+     output mirrors it as a self-check.
 
    **Worktree-path rule (mandatory)**: Every file path in the reviewer prompt
    (`{FILE_SECTIONS}`, design reference paths, artifact paths) MUST be the
@@ -545,6 +552,21 @@ fallback is retired with the design pipeline, [org-internal #3072] phase 3):
    observed in the 2026-07 auto-approve retrospective (5-round convergence,
    67.7% rework fraction).
 
+   **Code-graph availability preamble (worktree sessions, [org-internal #4187])**: the main
+   checkout's `.codegraph/` index does NOT cover a session worktree
+   ([org-internal #2561]/TD-006). Before dispatch, the Orchestrator checks the worktree's
+   own index: run `codegraph_status` against the worktree root, or check for
+   `<worktree-root>/.codegraph/codegraph.db` (a bare `init.log` without the
+   db means the background `session-worktree.sh create` init is still running).
+   Include in each reviewer's dispatch preamble: (a) the worktree index state
+   (ready / building / absent), and (b) when absent or still building, the
+   ABSOLUTE path of the main checkout (which has its own `.codegraph/`) so
+   DGN/COR reviewers can query MAIN-side symbols (design baselines, frozen
+   cross-session contracts) from the main checkout's index and cite them as
+   `main:<path>:<line>`. Reviewers apply rule 6b of
+   `_shared/review-reviewer-prompt.md` (NA + INFO finding) when no index is
+   reachable at all — grep-only structural claims must never pass silently.
+
 4. Wait for all reviewers to complete. Each reviewer writes its finding JSON to
    `<runs-root>/{slug}/reviews/code/round{N}/findings-{DIMENSION_CODE}.json`
     (Tier 1 local, validated by `core/schemas/reviewer-output.schema.json`). After all
@@ -860,7 +882,7 @@ After the Developer completes revision:
 
 **Convergence criteria**: see `core/skills/_shared/review-pipeline-phases.md` Phase D for the canonical table (stop conditions). `{MAX_ROUNDS}` is per-skill — code review binds the routing budget: **2** rounds default, **3** for high risk (a BLOCKER survived a round, or the diff touches a frozen cross-session contract) — `<instance-root>/workflow-routing.yaml` `review.max_rounds` ([org-internal #3567]). The code-review-specific addition is inheritance of the shared INFO-disposition rule. The shared Round-3 Escalation Guardrail is scoped to the `review-artifact` skill targets only and does not apply here.
 
-**Round budget (mandatory, [org-internal #3567])**: when `current_round` reaches the budget (2; 3 for high risk) without convergence, do NOT enter another round. STOP: register every remaining BLOCKER/MAJOR finding as TD registry rows (`rules/ticket-lifecycle.md`), record the verdict (FAIL if any BLOCKER remains, else PASS — the debt is carried by the TD registry rows just registered), and close the loop. A review that cannot converge within budget is a design-level stall wearing review clothes (retro 2026-08-21 / [org-internal #3050]): in DAG task mode, map it to the DAG oversize signals (`<instance-root>/workflow-routing.yaml` `dag.size_derivation.oversize_signals`) and let the aggregator agent drive re-derivation + a `review-dag` re-run; otherwise record the design-level finding on the Epic, or open `{slug}/03-design-amendments` via `wiki 读写 API（见 TERMINOLOGY）` (`_shared/gitea-write-patterns.md` Pattern 1).
+**Round budget (mandatory, [org-internal #3567])**: when `current_round` reaches the budget (2; 3 for high risk) without convergence, do NOT enter another round. STOP: register every remaining BLOCKER/MAJOR finding as TD registry rows (`rules/ticket-lifecycle.md`), record the verdict with the shared three-tier ladder (`core/schemas/synthesis.schema.json` `overall_verdict` + `core/skills/_shared/review-orchestrator-rules.md` rule 3): FAIL if any BLOCKER or FAIL dimension remains, else WARN, PASS only if every remaining dimension is PASS ([org-internal #4786]: the prior binary "else PASS" wording silently upgraded WARN-eligible outcomes to PASS), and close the loop. The debt is carried by the TD registry rows just registered, not by the recorded verdict. A review that cannot converge within budget is a design-level stall wearing review clothes (retro 2026-08-21 / [org-internal #3050]): in DAG task mode, map it to the DAG oversize signals (`<instance-root>/workflow-routing.yaml` `dag.size_derivation.oversize_signals`) and let the aggregator agent drive re-derivation + a `review-dag` re-run; otherwise record the design-level finding on the Epic, or open `{slug}/03-design-amendments` via `wiki 读写 API（见 TERMINOLOGY）` (`_shared/gitea-write-patterns.md` Pattern 1).
 
 **Efficiency optimization**: see `core/skills/_shared/review-pipeline-phases.md` Phase D (same rule — from round 2 onward ([org-internal #2598]), only spawn reviewers for FAIL/WARN/UNRESOLVED dimensions; full sweep every 2 rounds). Round ≥2 reviewer input is delta-scoped to the revised files + their neighbors.
 

core/skills/verify/SKILL.md

@@ -196,10 +196,6 @@ each missing item.
 <!-- section:phase-1 -->
 ## Phase 1 — Load Verification Context
 
-> **Pipeline stage**: if the source issue exists, move it to the `verify`
-> column on the Pipeline Stages board per `_shared/gitea-write-patterns.md`
-> Pattern 7.5. Skip if no source issue exists.
-
 Read the upstream artifacts. DAG task/milestone mode (the live path — see
 the DAG branch below for its read map):
 
@@ -310,6 +306,20 @@ gate fingerprint is keyed on the working tree (SHA + uncommitted state +
 untracked), so it covers pre-push/headless states the same-SHA CI clauses
 cannot.
 
+### 2.0b — Gate Records as Deterministic Inputs ([org-internal #5656] N-04)
+
+Mechanical checks MUST be grounded in gate records (`gate` tool result
+metadata), never in a model's transcription of command output:
+
+- Cite `exit_code` verbatim — canonical block from
+  `packages/octopus/src/gate/consume.ts`: `gate <id> (<tier>):
+  exit_code=<n> -> green|red`, plus `duration_ms` / `ci_run_id` when present.
+- `exit_code === null` (timeout/abort) is NO verdict — rerun required; a
+  pass claim cannot stand on it.
+- A green verdict-cache hit (`metadata.verdict_cache.key`) satisfies the
+  check the same as a fresh run (content-addressed, same fingerprint).
+- Narration drift (claim != record) is itself a verification finding.
+
 ### 2.1 Full Test Suite
 
 ```bash
@@ -1203,10 +1213,7 @@ If the user confirms, invoke the commit workflow per
 
 An iteration is NOT Done until all code is committed in git history.
 
-After the commit gate passes, move the source issue to the `done` column on
+Issue closing follows the lifecycle per `issue-checklist-sync.md` 归档动作.
-the Pipeline Stages board per `_shared/gitea-write-patterns.md` Pattern 7.5.
-Skip if no source issue exists. `done` is a stage column marker; issue
-closing follows the lifecycle per `issue-checklist-sync.md` 归档动作.
 
 To notify workflow completion, call the `signal_stage_done` tool.
 

guards/check-encoding-health.ts

@@ -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()

package.json

@@ -1,6 +1,6 @@
 {
   "name": "octopus-workflow",
-  "version": "0.1.2",
+  "version": "0.1.7",
   "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",