@fitlab-ai/agent-infra 0.12.0 → 0.12.2

package/templates/.agents/skills/review-plan/SKILL.zh-CN.md

@@ -9,7 +9,7 @@ description: >
 # 技术方案审查
 > `--agent` 取值见 `.agents/rules/task-management.md`「合作者 token 规范」。
 
-若入口业务操作数包含 `--orchestrated`，绑定 `{execution-flag}` = `--orchestrated` 并原样转发给 summary finalizer 与 completed 事件；否则绑定为空。不得从 `orchestration.json`、环境变量或历史产物推断该标记。生命周期事件还必须携带显式触发信息：编排调用使用 `{trigger-initiator}=orchestrator`，否则使用 `model`；`{request-id}` 是本任务与本轮产物的稳定单行标识，`{reason-code}` 使用 `user-request` 或 `review-finding`；started 与 completed 使用同一组值。
+生命周期事件必须携带显式触发信息：普通技能调用使用 `model`；仅用户明确要求时使用 `human`。`{request-id}` 是本任务与本轮产物的稳定单行标识，`{reason-code}` 使用 `user-request` 或 `review-finding`；started 与 completed 使用同一组值。
 
 审查最新技术方案产物，并产出 `review-plan.md` 或 `review-plan-r{N}.md`。
 
@@ -90,7 +90,7 @@ agent-infra-internal task-artifact {task-id} init --family review-plan --artifac
 
 ### 6. 更新任务状态
 
-报告完成后，先调用 `agent-infra-internal task-review {task-id} preflight --stage plan --artifact {review-artifact} {execution-flag}`，不得先写入账本。失败后直接修正正式产物并重跑；只有 preflight 通过后，才逐条调用 `agent-infra-internal task-ledger {task-id} finding-upsert --stage plan --review-artifact {review-artifact} --ordinal {n} --severity {blocker|major|minor} --evidence {review-artifact}#{anchor}`，或复核上一轮响应时调用 `finding-review --id {ledger-id} --status {confirmed|closed|open|needs-human-decision} --evidence {相称证据}`。不得扫描编号或手写账本行。全部账本写入完成后调用 `agent-infra-internal task-review {task-id} finalize-summary --stage plan --artifact {review-artifact} {execution-flag}`；不能把失败类型或 `changed=false` 当作自动授权。
+报告完成后，先调用 `agent-infra-internal task-review {task-id} preflight --stage plan --artifact {review-artifact}`，不得先写入账本。失败后直接修正正式产物并重跑；只有 preflight 通过后，才逐条调用 `agent-infra-internal task-ledger {task-id} finding-upsert --stage plan --review-artifact {review-artifact} --ordinal {n} --severity {blocker|major|minor} --evidence {review-artifact}#{anchor}`，或复核上一轮响应时调用 `finding-review --id {ledger-id} --status {confirmed|closed|open|needs-human-decision} --evidence {相称证据}`。不得扫描编号或手写账本行。全部账本写入完成后调用 `agent-infra-internal task-review {task-id} finalize-summary --stage plan --artifact {review-artifact}`；不能把失败类型或 `changed=false` 当作自动授权。
 
 从该次返回值绑定并复用以下结构化映射：
 
@@ -100,7 +100,7 @@ agent-infra-internal task-artifact {task-id} init --family review-plan --artifac
 {unresolved-minor} = stageStatus.unresolvedFindingCounts.minor
 ```
 
-该 intent 原子最终化报告摘要并返回同一次账本快照；不得再调用 `stage-status`、手工替换占位符或扫描问题清单。失败后，模型只能在共享规则的机械安全门通过时修改同一个受控 artifact，并完整重跑相同 intent；每次失败都重新判断是否收敛。最终一次完整成功返回决定同一快照的 verdict 和计数：`stageStatus.canAdvance=true` 且结论为 Approved 时允许跨阶段推进；`stageStatus.canAdvance=false` 时仍须执行 `agent-infra-internal task-event {task-id} review-plan.completed --agent {standard-agent-token} --initiator {trigger-initiator} --request-id {request-id} --reason-code {reason-code} --artifact {review-artifact} --verdict {approved|changes-requested|rejected} --blockers {unresolved-blockers} --major {unresolved-major} --minor {unresolved-minor} --manual-validation {n} {execution-flag}`，使用 `changes-requested` 并路由到同阶段修订/复审（报告明确拒绝时使用 `rejected`）。失败、模型停止、无进展或紧急熔断时，不发布完成事件或跨阶段命令，但必须按 `reference/output-templates.md` 的 `repair-stop` 场景展示已有 summary/findings、artifact、实际修复次数、最后诊断和停止原因。
+该 intent 原子最终化报告摘要并返回同一次账本快照；不得再调用 `stage-status`、手工替换占位符或扫描问题清单。失败后，模型只能在共享规则的机械安全门通过时修改同一个受控 artifact，并完整重跑相同 intent；每次失败都重新判断是否收敛。最终一次完整成功返回决定同一快照的 verdict 和计数：`stageStatus.canAdvance=true` 且结论为 Approved 时允许跨阶段推进；`stageStatus.canAdvance=false` 时仍须执行 `agent-infra-internal task-event {task-id} review-plan.completed --agent {standard-agent-token} --initiator {trigger-initiator} --request-id {request-id} --reason-code {reason-code} --artifact {review-artifact} --verdict {approved|changes-requested|rejected} --blockers {unresolved-blockers} --major {unresolved-major} --minor {unresolved-minor} --manual-validation {n}`，使用 `changes-requested` 并路由到同阶段修订/复审（报告明确拒绝时使用 `rejected`）。失败、模型停止、无进展或紧急熔断时，不发布完成事件或跨阶段命令，但必须按 `reference/output-templates.md` 的 `repair-stop` 场景展示已有 summary/findings、artifact、实际修复次数、最后诊断和停止原因。
 
 `manual-validation` 是 `ai task log` 中 review 行「人工校验点」（EN `Manual-validation`）计数的数据源；不要新增并行人工验证字段。
 

package/templates/.agents/skills/review-pr/SKILL.en.md

@@ -135,7 +135,7 @@ After closure, re-run step 1 for the next canonical round; never start the new r
 
 ### 6. Write back the publication result and task state
 
-- **Task-anchored path**: write the actual publication status in the `pr-review-rN.md` "Publication Result" section. Record the Review ID/URL for `applied` / `no-op`; for a failed write with a durable journal entry, record `blocked` / `failed`, the error code, and recovery action. Then close the local Activity Log with the verdict/counts frozen in step 3:
+- **Task-anchored path**: write the actual publication status in the `pr-review-rN.md` "Publication Result" section. Record the Review ID/URL for `applied` / `no-op`; for a failed write with a durable journal entry, record `blocked` / `failed`, the error code, and recovery action. Then close the local review state with the verdict/counts frozen in step 3:
 
   ```bash
   agent-infra-internal task-activity {task-id} pr-review-complete --agent {agent} \
@@ -143,13 +143,13 @@ After closure, re-run step 1 for the next canonical round; never start the new r
     --blockers {blockers} --major {major} --minor {minor}
   ```
 
-  `task-activity` generates `Verdict: <result>, blockers: N, major: N, minor: N → {pr-review-artifact}` from the typed payload and atomically writes the Activity Log, `## Review Feedback` link, and version stamp through `writeTask`. It never changes `current_step` or puts receipt/head/Review URL into the NOTE.
+  `task-activity` generates `Verdict: <result>, blockers: N, major: N, minor: N → {pr-review-artifact}` from the typed payload and atomically writes the structured review state, `## Review Feedback` link, and version stamp through `writeTask`. It appends the log when safe and otherwise returns a diagnostic. It never changes `current_step` or puts receipt/head/Review URL into the NOTE.
 
 - **One-shot path (no task)**: record the actual publication status in the `pr-review-rN.md` "Publication Result" section. Record the Review ID/URL on success, or the error and lack of automatic recovery on failure. Do not call `task-activity`.
 
 ### 7. Re-sync after write-back (task-anchored path)
 
-Step 6 rewrote the local `pr-review-rN.md` "Publication Result" section and task.md (Activity Log), while step 4 synced the older snapshot. Attempt the syncs again in order; record failures as warnings for `complete-task` to restore before archiving:
+Step 6 rewrote the local `pr-review-rN.md` "Publication Result" section and task.md (review state and available log), while step 4 synced the older snapshot. Attempt the syncs again in order; record failures as warnings for `complete-task` to restore before archiving:
 
 ```bash
 agent-infra-internal platform-comment sync {task-id} --kind task --agent {agent}
@@ -186,7 +186,7 @@ Pick the single exit branch per `reference/output-guidance.md` (local review com
 - [ ] Published the formal Review, durably recorded its pending publication, or accurately recorded a one-shot publication failure
 - [ ] Synced the Issue artifact/task comments or recorded their pending recovery on the task-anchored path
 - [ ] Ran the completion verification (`task-verify` or `verify-artifact`)
-- [ ] Updated task.md and appended the Activity Log entry (task-anchored path)
+- [ ] Updated task.md review state and recorded log diagnostics when applicable
 
 ## Stop
 

package/templates/.agents/skills/review-pr/SKILL.zh-CN.md

@@ -135,7 +135,7 @@ agent-infra-internal task-activity {task-id} pr-review-terminate --agent {agent}
 
 ### 6. 回写发布结果与任务状态
 
-- **任务锚定路径**：把 publish 的实际状态写入 `pr-review-rN.md`「发布结果」段。`applied` / `no-op` 时记录 Review ID/URL；写入失败且已有任务账本记录时写 `blocked` / `failed`、错误码和恢复动作。随后以步骤 3 冻结的同一组 verdict/counts 闭合本地活动日志：
+- **任务锚定路径**：把 publish 的实际状态写入 `pr-review-rN.md`「发布结果」段。`applied` / `no-op` 时记录 Review ID/URL；写入失败且已有任务账本记录时写 `blocked` / `failed`、错误码和恢复动作。随后以步骤 3 冻结的同一组 verdict/counts 闭合本地审查状态：
 
   ```bash
   agent-infra-internal task-activity {task-id} pr-review-complete --agent {agent} \
@@ -143,13 +143,13 @@ agent-infra-internal task-activity {task-id} pr-review-terminate --agent {agent}
     --blockers {blockers} --major {major} --minor {minor}
   ```
 
-  `task-activity` 由 typed payload 生成 `Verdict: <结论>, blockers: N, major: N, minor: N → {pr-review-artifact}`，并经 `writeTask` 原子完成 Activity Log、`## 审查反馈` 链接与版本戳刷新；不改 `current_step`，也不把 receipt/head/Review URL 写入 NOTE。
+  `task-activity` 由 typed payload 生成 `Verdict: <结论>, blockers: N, major: N, minor: N → {pr-review-artifact}`，并经 `writeTask` 原子完成结构化审查状态、`## 审查反馈` 链接与版本戳刷新；日志可安全追加时一并写入，否则返回诊断；不改 `current_step`，也不把 receipt/head/Review URL 写入 NOTE。
 
 - **一次性路径（无任务）**：把实际发布状态写入 `pr-review-rN.md`「发布结果」段；成功时记录 Review ID/URL，失败时记录错误与不可自动恢复的限制。不调用 `task-activity`。
 
 ### 7. 发布后回写再同步（任务锚定路径）
 
-步骤 6 已改写本地 `pr-review-rN.md`「发布结果」段与 task.md（活动日志），而步骤 4 同步的是旧快照。依次尝试再同步；失败记录 warning，由 `complete-task` 在归档前补齐：
+步骤 6 已改写本地 `pr-review-rN.md`「发布结果」段与 task.md（审查状态及可用日志），而步骤 4 同步的是旧快照。依次尝试再同步；失败记录 warning，由 `complete-task` 在归档前补齐：
 
 ```bash
 agent-infra-internal platform-comment sync {task-id} --kind task --agent {agent}
@@ -186,7 +186,7 @@ agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact
 - [ ] 正式 Review 已发布、任务账本已记录待恢复操作，或一次性路径已如实记录发布失败
 - [ ] 任务锚定路径的 Issue artifact/task 评论已同步，或失败已记录待恢复
 - [ ] 已完成校验（`task-verify` 或 `verify-artifact`）
-- [ ] 已更新 task.md 并追加 Activity Log（任务锚定路径）
+- [ ] 已更新 task.md 中的审查状态并记录日志诊断（如适用）
 
 ## 停止
 

package/templates/.agents/skills/run-manual-validation/SKILL.en.md

@@ -8,7 +8,7 @@ description: >
 
 # Run Manual Validation
 
-Lifecycle events require explicit trigger data: use `{trigger-initiator}=orchestrator` for orchestration and `model` otherwise; `{request-id}` is a stable single-line identifier for this task and artifact round, and `{reason-code}` is `user-request` or `validation-rerun`. Reuse the same values for started and completed.
+Lifecycle events require explicit trigger data: ordinary skill invocation uses `model`; use `human` only when the user explicitly requests it. `{request-id}` is a stable single-line identifier for this task and artifact round, and `{reason-code}` use `user-request` or `validation-rerun`. Reuse the same values for started and completed.
 
 ## Task Context Resolution
 

package/templates/.agents/skills/run-manual-validation/SKILL.zh-CN.md

@@ -8,7 +8,7 @@ description: >
 
 # 运行人工校验
 
-生命周期事件必须携带显式触发信息：编排调用使用 `{trigger-initiator}=orchestrator`，否则使用 `model`；`{request-id}` 是本任务与本轮产物的稳定单行标识，`{reason-code}` 使用 `user-request` 或 `validation-rerun`；started 与 completed 使用同一组值。
+生命周期事件必须携带显式触发信息：普通技能调用使用 `model`；仅用户明确要求时使用 `human`。`{request-id}` 是本任务与本轮产物的稳定单行标识，`{reason-code}` 使用 `user-request` 或 `validation-rerun`；started 与 completed 使用同一组值。
 
 ## 任务上下文解析
 

package/templates/.agents/skills/update-agent-infra/scripts/sync-templates.js

@@ -251,11 +251,10 @@ function normalizeAgentClientConfig(cfg) {
     }
     const keys = Object.keys(candidate);
     if (
-      (keys.length !== 3 && keys.length !== 4)
+      keys.length !== 3
       || !own(candidate, 'id')
       || !own(candidate, 'enabled')
       || !own(candidate, 'installInSandbox')
-      || (keys.length === 4 && !own(candidate, 'orchestration'))
     ) {
       return failure('INVALID_AGENT_CLIENTS', entryPath);
     }
@@ -266,52 +265,9 @@ function normalizeAgentClientConfig(cfg) {
     if (typeof candidate.enabled !== 'boolean' || typeof candidate.installInSandbox !== 'boolean') {
       return failure('INVALID_AGENT_CLIENTS', entryPath);
     }
-    let orchestration;
-    if (own(candidate, 'orchestration')) {
-      const policy = candidate.orchestration;
-      if (
-        !policy
-        || typeof policy !== 'object'
-        || Array.isArray(policy)
-        || Object.keys(policy).length !== 2
-        || !own(policy, 'executor')
-        || !own(policy, 'reviewer')
-      ) {
-        return failure('INVALID_AGENT_CLIENTS', `${entryPath}.orchestration`);
-      }
-      const parseExact = (value, path) => {
-        if (typeof value !== 'string' || value.length === 0 || value.trim() !== value) {
-          return failure('INVALID_AGENT_CLIENTS', path);
-        }
-        return value;
-      };
-      const parseRole = (role, rolePath) => {
-        if (
-          !role
-          || typeof role !== 'object'
-          || Array.isArray(role)
-          || Object.keys(role).length !== 2
-          || !own(role, 'model')
-          || !own(role, 'reasoningEffort')
-        ) {
-          return failure('INVALID_AGENT_CLIENTS', rolePath);
-        }
-        const model = parseExact(role.model, `${rolePath}.model`);
-        if (typeof model !== 'string') return model;
-        const reasoningEffort = parseExact(role.reasoningEffort, `${rolePath}.reasoningEffort`);
-        if (typeof reasoningEffort !== 'string') return reasoningEffort;
-        return { model, reasoningEffort };
-      };
-      const executor = parseRole(policy.executor, `${entryPath}.orchestration.executor`);
-      if (executor.errorCode) return executor;
-      const reviewer = parseRole(policy.reviewer, `${entryPath}.orchestration.reviewer`);
-      if (reviewer.errorCode) return reviewer;
-      orchestration = { executor, reviewer };
-    }
     entries.set(candidate.id, {
       enabled: candidate.enabled,
-      installInSandbox: candidate.installInSandbox,
-      ...(orchestration ? { orchestration } : {})
+      installInSandbox: candidate.installInSandbox
     });
   }
   if (AGENT_CLIENT_IDS.some((id) => !entries.has(id))) {
@@ -676,22 +632,6 @@ function mergeTemplateSources(baseRoot, sources, report) {
   };
 }
 
-function writeIfChanged(projectRoot, targetPath, content, reportBucket) {
-  const fullPath = path.join(projectRoot, targetPath);
-  const exists = fs.existsSync(fullPath);
-
-  if (exists && fs.readFileSync(fullPath, 'utf8') === content) {
-    reportBucket.unchanged.push(targetPath);
-    return;
-  }
-
-  const dir = path.dirname(fullPath);
-  if (!fs.existsSync(dir)) fs.mkdirSync(dir, { recursive: true });
-  fs.writeFileSync(fullPath, content, 'utf8');
-
-  (exists ? reportBucket.updated : reportBucket.generated).push(targetPath);
-}
-
 function syncCustomSkillSources(projectRoot, sources, report, templateSkillNames) {
   const skillsDir = path.join(projectRoot, '.agents/skills');
   const syncedSkills = new Map();
@@ -1102,7 +1042,7 @@ function syncTemplates(projectRoot, templateRootOverride) {
     && !Array.isArray(cfg.files.managedBaselines)
     ? { ...cfg.files.managedBaselines }
     : {};
-  let baselinesChanged = false;
+
 
   for (const target of Object.keys(managedBaselines)) {
     if (
@@ -1111,7 +1051,6 @@ function syncTemplates(projectRoot, templateRootOverride) {
       && !allClientManaged.some((entry) => assetMatches(entry, target))
     ) {
       delete managedBaselines[target];
-      baselinesChanged = true;
     }
   }
 
@@ -1206,7 +1145,6 @@ function syncTemplates(projectRoot, templateRootOverride) {
         if (!fs.existsSync(candidatePath)) {
           if (Object.prototype.hasOwnProperty.call(managedBaselines, candidate)) {
             delete managedBaselines[candidate];
-            baselinesChanged = true;
           }
           continue;
         }
@@ -1232,7 +1170,6 @@ function syncTemplates(projectRoot, templateRootOverride) {
         }
         if (Object.prototype.hasOwnProperty.call(managedBaselines, candidate)) {
           delete managedBaselines[candidate];
-          baselinesChanged = true;
         }
       }
       removeEmptyDirs(target);
@@ -1252,7 +1189,6 @@ function syncTemplates(projectRoot, templateRootOverride) {
       report.managed.removed.push(entry);
       if (Object.prototype.hasOwnProperty.call(managedBaselines, entry)) {
         delete managedBaselines[entry];
-        baselinesChanged = true;
       }
     } else {
       report.managed.protected.push({
@@ -1321,7 +1257,6 @@ function syncTemplates(projectRoot, templateRootOverride) {
 
     if (rawBaseline !== undefined && baseline === null) {
       delete managedBaselines[target];
-      baselinesChanged = true;
     }
     if (baseline === null && localHash !== null && localHash !== templateHash) {
       report.managed.conflicts.push({
@@ -1362,7 +1297,6 @@ function syncTemplates(projectRoot, templateRootOverride) {
       bucket.unchanged.push(target);
       if (managedBaselines[target] !== templateHash) {
         managedBaselines[target] = templateHash;
-        baselinesChanged = true;
       }
       return false;
     }
@@ -1371,7 +1305,6 @@ function syncTemplates(projectRoot, templateRootOverride) {
     if (!fs.existsSync(dir)) fs.mkdirSync(dir, { recursive: true });
     fs.writeFileSync(dstFull, content);
     managedBaselines[target] = templateHash;
-    baselinesChanged = true;
     if (Object.prototype.hasOwnProperty.call(bucket, 'written')) {
       (exists ? bucket.written : bucket.created).push(target);
     } else {
@@ -1417,7 +1350,6 @@ function syncTemplates(projectRoot, templateRootOverride) {
       report.managed.removed.push(renderedTarget);
       if (Object.prototype.hasOwnProperty.call(managedBaselines, renderedTarget)) {
         delete managedBaselines[renderedTarget];
-        baselinesChanged = true;
       }
       continue;
     }
@@ -1479,7 +1411,6 @@ function syncTemplates(projectRoot, templateRootOverride) {
       if (localHash === null) {
         if (Object.prototype.hasOwnProperty.call(managedBaselines, target)) {
           delete managedBaselines[target];
-          baselinesChanged = true;
         }
         continue;
       }
@@ -1492,7 +1423,6 @@ function syncTemplates(projectRoot, templateRootOverride) {
         report.managed.removed.push(target);
         if (Object.prototype.hasOwnProperty.call(managedBaselines, target)) {
           delete managedBaselines[target];
-          baselinesChanged = true;
         }
         removeEmptyDirs(path.dirname(dstFull));
         continue;
@@ -1608,7 +1538,6 @@ function syncTemplates(projectRoot, templateRootOverride) {
             if (baseline !== null && localHash === baseline) {
               fs.unlinkSync(path.join(projectRoot, projFile));
               delete managedBaselines[projFile];
-              baselinesChanged = true;
               report.managed.removed.push(projFile);
             } else {
               report.managed.protected.push({
@@ -1715,7 +1644,6 @@ function syncTemplates(projectRoot, templateRootOverride) {
   if (Object.keys(managedBaselines).length > 0) {
     cfg.files.managedBaselines = managedBaselines;
   } else {
-    if (Object.prototype.hasOwnProperty.call(cfg.files, 'managedBaselines')) baselinesChanged = true;
     delete cfg.files.managedBaselines;
   }
   cfg.templateVersion = version;

package/templates/.agents/skills/watch-pr/SKILL.en.md

@@ -61,7 +61,7 @@ process.stdout.write(`${JSON.stringify(previous)}\n`);
 ' {task-id}
 ```
 
-Then run `platform-pr summary-context` and compare the retained repository/resource identity with the authoritative snapshot; discard a mismatch and mark the increment unconfirmed. Rebuild the task-bound `pr-change-report.json` for the authoritative PR head using the shared PR change-report contract, and refresh the single summary with a body containing one `<!-- canonical-pr-change-report -->` placeholder via `summary-sync --change-report-file ... --result no_op --strict`. Complete-PR statistics keep the current base/head/merge-base/patch and existing totals. Only when the prior report is valid, the PR identity matches, and the heads differ, describe the separate head-to-head tree diff using `git diff --find-renames --numstat {previous-head} {current-head}`, `--name-status`, and `--summary`. Do not substitute a merge-base diff for this range or add increment totals to the full PR. If no valid prior head exists, state that it is unconfirmed; do not infer from complete-PR statistics or fill in zeroes. Matching heads mean there was no new head transition.
+Then run `platform-pr summary-context` and compare the retained repository/resource identity with the authoritative snapshot; discard a mismatch and mark the increment unconfirmed. Rebuild the task-bound `pr-change-report.json` for the authoritative PR head using the shared PR change-report contract, and refresh the single summary with structured summary JSON via `summary-sync --change-report-file ... --result no_op --strict`. Preserve the actual test, review, and manual validation states; do not depend on later events or final verification. Complete-PR statistics keep the current base/head/merge-base/patch and existing totals. Only when the prior report is valid, the PR identity matches, and the heads differ, describe the separate head-to-head tree diff using `git diff --find-renames --numstat {previous-head} {current-head}`, `--name-status`, and `--summary`. Do not substitute a merge-base diff for this range or add increment totals to the full PR. If no valid prior head exists, state that it is unconfirmed; do not infer from complete-PR statistics or fill in zeroes. Matching heads mean there was no new head transition.
 
 `--strict` preserves report or summary refresh failures as `failed/blocked` instead of treating warnings as success. A report or summary refresh failure must not enter the ready/complete exit; use step 4. After a successful refresh, consume `nextAction` from the structured `summary-sync` result: `review-code` exits readiness/self-heal and follows the code-review branch in step 7; only `watch-pr` continues to `agent-infra-internal platform-checks watch {task-id} --interval-seconds 30 --deadline-seconds 1800`. Missing or invalid `nextAction` follows the refresh-failure exit; do not infer `watch-pr`. Route readiness only by `readiness.state`: `ready` to step 7, `conflicting|checks-failed` to step 3, and `pending|timed-out|cancelled` to step 4.
 

package/templates/.agents/skills/watch-pr/SKILL.zh-CN.md

@@ -61,7 +61,7 @@ process.stdout.write(`${JSON.stringify(previous)}\n`);
 ' {task-id}
 ```
 
-随后调用 `platform-pr summary-context`，比较暂存的 repository/resource identity 与当前权威 snapshot；不匹配时丢弃旧 head 并标记增量未确认。按共享 PR change-report contract 用当前权威 PR head 重建任务绑定的 `pr-change-report.json`，再用含唯一 `<!-- canonical-pr-change-report -->` 占位符的正文调用 `summary-sync --change-report-file ... --result no_op --strict` 刷新同一条摘要。完整 PR 仍使用当前 base/head/merge-base/patch 与现有 totals。只有在上一报告有效、PR identity 相同且两个 head 不同的情况下，才用 `git diff --find-renames --numstat {previous-head} {current-head}`、`--name-status`、`--summary` 描述独立的 head→head 树差异；不使用 merge-base 替代该范围，不把增量 totals 加入完整 PR。无有效上一 head 时写明未确认，不从完整 PR 推算或填零；head 相同只说明没有新的 head 转换。
+随后调用 `platform-pr summary-context`，比较暂存的 repository/resource identity 与当前权威 snapshot；不匹配时丢弃旧 head 并标记增量未确认。按共享 PR change-report contract 用当前权威 PR head 重建任务绑定的 `pr-change-report.json`，用结构化摘要 JSON 调用 `summary-sync --change-report-file ... --result no_op --strict` 刷新同一条摘要；保留测试、Review 和人工校验的真实状态，不能依赖后续事件或最终验证。完整 PR 仍使用当前 base/head/merge-base/patch 与现有 totals。只有在上一报告有效、PR identity 相同且两个 head 不同的情况下，才用 `git diff --find-renames --numstat {previous-head} {current-head}`、`--name-status`、`--summary` 描述独立的 head→head 树差异；不使用 merge-base 替代该范围，不把增量 totals 加入完整 PR。无有效上一 head 时写明未确认，不从完整 PR 推算或填零；head 相同只说明没有新的 head 转换。
 
 `--strict` 将报告或摘要刷新失败保留为 `failed/blocked`，不得把 warning 当作成功；刷新失败时不得进入 ready/complete 出口，按步骤 4 记录阻塞。刷新成功后，消费 `summary-sync` 结构化结果的 `nextAction`：`review-code` 立即结束 readiness/self-heal 路径，按步骤 7 的代码审查分支退出；`watch-pr` 才继续调用 `agent-infra-internal platform-checks watch {task-id} --interval-seconds 30 --deadline-seconds 1800`。缺失或 invalid `nextAction` 按刷新失败处理，不推断为 `watch-pr`。readiness 只按结构化 `readiness.state` 分流：`ready` 进入步骤 7，`conflicting` 或 `checks-failed` 进入步骤 3，`pending|timed-out|cancelled` 进入步骤 4。
 

package/templates/.agents/skills/watch-pr/reference/monitor-and-heal.en.md

@@ -13,11 +13,11 @@ After the watch command, route by structured `readiness.state`:
 
 ## Summary Refresh Boundary
 
-Before readiness in every round, and after an external push, self-heal commit, or successful rebase changes the PR head, rerun `summary-context` → mechanical report and six-check precheck → `platform-pr change-report` → `summary-sync --change-report-file ... --result no_op --strict` with exactly one `<!-- canonical-pr-change-report -->` placeholder. `--strict` preserves report or summary refresh failures as `failed/blocked` so warnings cannot reach the ready/complete route. The core revalidates the sidecar against the authoritative PR snapshot, task-intent digest, and complete patch; missing, stale, invalid, bypassed, or raced publication must not continue to a ready/complete route and must enter the help exit with a warning.
+Before readiness in every round, and after an external push, self-heal commit, or successful rebase changes the PR head, rerun `summary-context` → mechanical report and six-check precheck → `platform-pr change-report` → update the full PR summary JSON per `.agents/rules/pr-sync.md` → `summary-sync --change-report-file ... --result no_op --strict`. `--strict` preserves report or summary refresh failures as `failed/blocked`. The core revalidates the sidecar and reads back the remote body; missing, stale, invalid, incomplete, or raced publication must not continue to a ready/complete route.
 
-When rebuilding the precheck, each of the six `rationale` fields must state the corresponding high-level finding and include at least one path, line range, and concise `detail` as evidence. `change-composition` must describe where responsibilities are concentrated; compatibility, legacy-path, redundancy, and scope checks must state their actual results separately, without reused generic boilerplate. Use the deployed skill's language for rationales and evidence details; Chinese skill deployments must use Chinese.
+When rebuilding the precheck, each of the six `rationale` fields must state its actual finding and include at least one item of evidence with a path, line range, and concise `detail`; state compatibility, legacy-path, redundancy, and scope findings separately without generic boilerplate. Use the deployed skill's language for rationales and evidence; Chinese deployments must use Chinese.
 
-Use the six existing `rationale` fields and `Evidence[]` to explain each logical change group: its goal and acceptance-criteria alignment, behavior added or removed, necessity, redundancy or duplication, scope, related tests, and test adequacy. Cite locatable code, test, or documentation evidence; mark unsupported points as unconfirmed. The renderer displays every evidence item. Source line counts, execution/call counts, and workflow unification are distinct claims: diff line counts cannot prove execution-count or workflow-behavior changes, and green CI cannot prove necessity. Analysis must not expand self-heal or refactoring authority.
+Use the candidate content contract in `.agents/skills/create-pr/reference/change-report.md` for functional grouping, per-group fields, unique line attribution, and `needs-review` criteria. Rebuild groups from the current task goal and patch on every refresh; do not reuse prior-head explanations as evidence for the current increment. Reconcile complete-PR statistics separately from the previous valid head → current head increment; explicitly mark the increment unconfirmed when no previous head can be verified. If any group lacks goal alignment, behavior added/removed, necessity, line-count reconciliation, test coverage/cost, or locatable evidence, mark `target-alignment` or `change-composition` as `needs-review` and identify the gap. Reuse the existing `nextAction=review-code` route; structural completeness or green CI must not continue to `watch-pr`.
 
 Keep complete-PR scope bound to the current authoritative base/head/merge-base/patch and its full statistics. Report the increment separately as previous valid report head → current head. Before overwriting the prior sidecar, validate it with `readPrChangeReport`; use its `identity.head.sha` only when its repository/resource identity matches the current PR. Compare the two head trees directly and state both SHAs. Do not substitute a merge-base diff for these endpoints or add increment totals to complete-PR totals. If no prior report exists, it is invalid, or its identity differs, mark the previous head unconfirmed; do not infer values from the full PR or fill in zeroes. Identical SHAs mean the head did not change. After a rebase, compare the old and new head trees. An invalid sidecar makes only the increment unconfirmed; the existing full-PR report flow continues.
 

package/templates/.agents/skills/watch-pr/reference/monitor-and-heal.zh-CN.md

@@ -13,11 +13,11 @@
 
 ## 摘要刷新边界
 
-每轮 readiness 之前，以及外部 push、自愈 commit 或 rebase 成功改变 PR head 之后，必须重新执行 `summary-context` → 机械报告与六项 precheck → `platform-pr change-report` → 含一次 `<!-- canonical-pr-change-report -->` 的 `summary-sync --change-report-file ... --result no_op --strict`。`--strict` 将报告或摘要刷新失败保留为 `failed/blocked`，不允许 warning 穿透到 ready/complete 路由。core 以权威 PR snapshot、任务意图 digest 和完整 patch 重新校验 sidecar；报告缺失、stale、invalid、占位符绕过或发布竞态时，不得继续 ready/complete 路由，转入求助出口并登记 warning。
+每轮 readiness 之前，以及外部 push、自愈 commit 或 rebase 成功改变 PR head 之后，必须重新执行 `summary-context` → 机械报告与六项 precheck → `platform-pr change-report` → 按 `.agents/rules/pr-sync.md` 更新完整 PR 摘要 JSON 并调用 `summary-sync --change-report-file ... --result no_op --strict`。`--strict` 将报告或摘要刷新失败保留为 `failed/blocked`，不允许 warning 穿透到 ready/complete 路由。core 以权威 PR snapshot、任务意图 digest 和完整 patch 重新校验 sidecar，并回读远端正文；报告缺失、stale、invalid、结构不完整或发布竞态时，不得继续 ready/complete 路由，转入求助出口并登记 warning。
 
-每轮重建 precheck 时，六项 `rationale` 都必须是对应检查的实际高层结论，并各带至少一条路径、行号和简短 `detail` 证据；`change-composition` 要说明职责集中位置，兼容、旧路径、冗余和范围检查要分别说明实际结果，禁止复用泛化套话。理由和证据详情遵循当前已部署技能的语言，中文技能必须使用中文。
+每轮重建 precheck 时，除执行下方功能级报告门槛外，六项 `rationale` 都必须陈述对应检查的实际结论，并至少带一条含路径、行号和简短 `detail` 的证据；兼容、旧路径、冗余和范围检查分别说明，不复用泛化套话。理由和证据遵循当前部署语言，中文技能必须使用中文。
 
-按逻辑变化组使用现有六项 `rationale` 和 `Evidence[]` 说明目标/验收对应、行为增减、必要性、冗余或重复、范围、相关测试及测试充分性。列出可定位的代码/测试/文档证据；缺证据时明确写未确认。renderer 会展示每项的全部 evidence。源码行数、执行/调用次数和流程统一是不同结论：diff 行数不能证明执行次数或流程行为变化；CI 全绿也不能证明必要性。不得由分析建议自行扩大自愈或重构权限。
+功能分组、逐组字段、行数唯一归属及 `needs-review` 条件统一遵循 `.agents/skills/create-pr/reference/change-report.md` 的 candidate 内容契约。每次刷新都重新按当前任务目标和 patch 建立功能组，不沿用上一 head 的说明代替本轮证据。完整 PR 统计与上一有效 head → 当前 head 的增量分开核算；没有可验证的上一 head 时明确标为未确认。任何功能组缺少目标对应、行为增减、必要性、行数对账、测试覆盖/成本或定位证据时，将 `target-alignment` 或 `change-composition` 标为 `needs-review` 并指出缺口。沿用现有 `nextAction=review-code` 路由；不得以结构完整或 CI 全绿继续 `watch-pr`。
 
 完整 PR 的范围继续绑定当前权威 base/head/merge-base/patch 与完整统计。增量单独绑定上一有效报告 head → 当前 head：在覆盖旧 sidecar 前，用 `readPrChangeReport` 校验旧报告，只在 repository/resource identity 匹配当前 PR 时采用旧 `identity.head.sha`。对两个 head 做 tree-to-tree diff 并明确列出 SHA，不用 merge-base 替代端点差异，不把增量 totals 加到完整 PR totals。没有旧报告、报告无效或身份不符时标注上一 head 未确认，不从全量推算或填零。两个 SHA 相同只报告 head 未变化；rebase 后仍比较原 head 和新 head 的树差异。sidecar 无效只使增量不可确认，不改变现有 full-PR 报告流程。
 

package/templates/.agents/templates/task.en.md

@@ -13,6 +13,7 @@ start_date:                     # Optional Issue field for Feature: YYYY-MM-DD
 target_date:                    # Optional Issue field for Feature: YYYY-MM-DD
 current_step: requirement-analysis # requirement-analysis | requirement-analysis-review | technical-design | technical-design-review | code | code-review | completed
 assigned_to:                   # claude | codex | antigravity | opencode | human
+lifecycle_execution: '{"version":1,"open":[],"prReview":{"open":null,"terminals":[]}}'
 pr_delivery_fact: '{"version":2,"state":"unbound","reason":"initial"}'
 delivery_remote: origin        # Git remote used to deliver the task branch
 delivery_base_ref: main        # Target branch for the task PR

package/templates/.agents/templates/task.zh-CN.md

@@ -13,6 +13,7 @@ start_date:                     # Feature 可选 Issue 字段：YYYY-MM-DD
 target_date:                    # Feature 可选 Issue 字段：YYYY-MM-DD
 current_step: requirement-analysis # requirement-analysis | requirement-analysis-review | technical-design | technical-design-review | code | code-review | completed
 assigned_to:                   # claude | codex | antigravity | opencode | human
+lifecycle_execution: '{"version":1,"open":[],"prReview":{"open":null,"terminals":[]}}'
 pr_delivery_fact: '{"version":2,"state":"unbound","reason":"initial"}'
 delivery_remote: origin        # 任务分支交付使用的 Git remote
 delivery_base_ref: main        # 任务 PR 的目标分支

package/templates/.claude/settings.json

@@ -30,30 +30,6 @@
         ]
       }
     ],
-    "SubagentStart": [
-      {
-        "matcher": "agent-infra-lifecycle-(executor|reviewer)",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "node \"$(git rev-parse --show-toplevel)/.agents/hooks/lifecycle-delegation.js\" --client claude-code",
-            "timeout": 10
-          }
-        ]
-      }
-    ],
-    "SubagentStop": [
-      {
-        "matcher": "agent-infra-lifecycle-(executor|reviewer)",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "node \"$(git rev-parse --show-toplevel)/.agents/hooks/lifecycle-delegation.js\" --client claude-code",
-            "timeout": 10
-          }
-        ]
-      }
-    ],
     "StopFailure": [
       {
         "matcher": "",

package/templates/.codex/hooks.json

@@ -11,56 +11,6 @@
             "statusMessage": "Checking template version before git commit"
           }
         ]
-      },
-      {
-      "matcher": "^collaborationspawn_agent$",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "node \"$(git rev-parse --show-toplevel)/.agents/hooks/lifecycle-delegation.js\" --client codex --event pre-tool",
-            "timeout": 30,
-            "statusMessage": "Recording Codex lifecycle spawn evidence"
-          }
-        ]
-      }
-    ],
-    "PostToolUse": [
-      {
-      "matcher": "",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "node \"$(git rev-parse --show-toplevel)/.agents/hooks/lifecycle-delegation.js\" --client codex --event post-tool",
-            "timeout": 30,
-            "statusMessage": "Recording Codex lifecycle tool completion"
-          }
-        ]
-      }
-    ],
-    "SubagentStart": [
-      {
-        "matcher": "",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "node \"$(git rev-parse --show-toplevel)/.agents/hooks/lifecycle-delegation.js\" --client codex --event subagent-start",
-            "timeout": 30,
-            "statusMessage": "Recording Codex child identity"
-          }
-        ]
-      }
-    ],
-    "SubagentStop": [
-      {
-        "matcher": "",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "node \"$(git rev-parse --show-toplevel)/.agents/hooks/lifecycle-delegation.js\" --client codex --event subagent-stop",
-            "timeout": 30,
-            "statusMessage": "Recording Codex child stop evidence"
-          }
-        ]
       }
     ]
   }