@fitlab-ai/agent-infra 0.9.12 → 0.9.13

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

@@ -9,7 +9,7 @@ description: >
 # 设计技术方案
 > `--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 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。
+若入口业务操作数包含 `--orchestrated`，绑定 `{execution-flag}` = `--orchestrated` 并原样转发给 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`、`new-requirement` 或 `upstream-fact-doubt`；started 与 completed 使用同一组值。
 
 ## 行为边界 / 关键规则
 
@@ -44,7 +44,7 @@ agent-infra-internal task-snapshot {task-id} --format text
 确认前置条件和轮次后、本轮第一个产出动作之前执行：
 
 ```bash
-agent-infra-internal task-event {task-id} plan.started --agent {standard-agent-token}
+agent-infra-internal task-event {task-id} plan.started --agent {standard-agent-token} --initiator {trigger-initiator} --request-id {request-id} --reason-code {reason-code}
 ```
 
 ## 执行步骤
@@ -114,7 +114,14 @@ agent-infra-internal task-event {task-id} plan.started --agent {standard-agent-t
   - 用新值覆盖 frontmatter 的 `effort` 字段
   - 在本轮方案产物 `{plan-artifact}` 中追加 `## 工作量重估` 段，记录一条：`effort {old} → {new} (rationale: {基于本轮方案的简短依据})`
   若重估值与当前值一致，跳过：不写入 `## 工作量重估` 段。后续 Flow A 同步会读取可能更新过的 frontmatter，并自动把新值同步到 Issue。
-- 完成业务内容更新后执行 `agent-infra-internal task-event {task-id} plan.completed --agent {standard-agent-token} --artifact {plan-artifact} {execution-flag}`，由核心原子登记链接、阶段、代理、时间、版本和 Activity Log。
+- 完成本地产物后，先执行本地完成前门禁：
+  ```bash
+  agent-infra-internal task-artifact {task-id} finalize-local --family plan --artifact {plan-artifact}
+  ```
+  - `status=passed`：保存本次返回的 `artifactSha256` 和 `semanticDigest`；finalizer 已记录对应的一次性本地 provenance intent。
+  - `status=failed` 且 `repairable=true`：仅按诊断中的 `replace-line` 操作做一次最小修改，然后完整重跑同一命令；实际字节发生变化才计一次 `repairAttempts`，最多 8 次。
+  - 首次可修复失败的 `semanticDigest` 由 finalizer 保留为基线；重试后的 `status=passed` 必须匹配该基线。基线不匹配、其他失败、无进展或重复诊断：停止，不发布 completed 事件。
+- 使用同一次 `status=passed` 返回的摘要执行 `agent-infra-internal task-event {task-id} plan.completed --agent {standard-agent-token} --initiator {trigger-initiator} --request-id {request-id} --reason-code {reason-code} --artifact {plan-artifact} --artifact-sha256 {artifact-sha256} --semantic-digest {semantic-digest} {execution-flag}`，由核心登记链接、阶段、代理、时间、版本和 Activity Log。
 
 如果 task.md 中存在有效的 `issue_number`，执行以下同步操作（任一失败则跳过并继续）：
 - 调用 `agent-infra-internal platform-issue sync {task-id} --agent {standard-agent-token} --status pending-design-work --fields`

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

@@ -9,7 +9,7 @@ description: >
 # Requirement Analysis Review
 > `--agent` values are defined in `.agents/rules/task-management.md` under “Collaborator Token Specification”.
 
-If the entry operands contain `--orchestrated`, bind `{execution-flag}` to `--orchestrated` and forward it unchanged to both the summary finalizer and completed event; otherwise bind it to an empty value. Never infer it from `orchestration.json`, environment variables, or prior artifacts.
+If the entry operands contain `--orchestrated`, bind `{execution-flag}` to `--orchestrated` and forward it unchanged to both the summary finalizer and completed event; otherwise bind it to an empty value. Never infer it from `orchestration.json`, environment variables, or prior artifacts. Lifecycle events also 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 `review-finding`. Reuse the same values for started and completed.
 
 Review the latest analysis artifact and produce `review-analysis.md` or `review-analysis-r{N}.md`.
 
@@ -39,7 +39,7 @@ agent-infra-internal task-snapshot {task-id} --format text
 
 ## Step Start: Declare the started Event
 
-After resolving the artifact context and before this round's first artifact action, run `agent-infra-internal task-event {task-id} review-analysis.started --agent {standard-agent-token}`.
+After resolving the artifact context and before this round's first artifact action, run `agent-infra-internal task-event {task-id} review-analysis.started --agent {standard-agent-token} --initiator {trigger-initiator} --request-id {request-id} --reason-code {reason-code}`.
 
 ## Steps
 
@@ -80,7 +80,7 @@ Bind and reuse this structured mapping from that one response:
 {unresolved-minor} = stageStatus.unresolvedFindingCounts.minor
 ```
 
-The intent atomically finalizes the report summary and returns the same ledger snapshot. Do not call `stage-status`, replace placeholders manually, or rescan the finding list. After a failure, the model may edit the same controlled artifact and rerun the same intent only when the shared rule's mechanical gates pass; reassess convergence after every failure. The final complete result determines the verdict and counts from that same snapshot: `stageStatus.canAdvance=true` with an Approved conclusion permits cross-stage advancement; `stageStatus.canAdvance=false` still requires `agent-infra-internal task-event {task-id} review-analysis.completed --agent {standard-agent-token} --artifact {review-artifact} --verdict {approved|changes-requested|rejected} --blockers {unresolved-blockers} --major {unresolved-major} --minor {unresolved-minor} --manual-validation {n} {execution-flag}`, using `changes-requested` and routing to same-stage revision/review (use `rejected` when the report explicitly rejects). On failure, model stop, lack of progress, or the emergency cap, do not publish a completion event or cross-stage command; use the `repair-stop` scenario in `reference/output-templates.md` to show existing summary/findings, the artifact, actual repair attempts, the last diagnostic, and the stop reason.
+The intent atomically finalizes the report summary and returns the same ledger snapshot. Do not call `stage-status`, replace placeholders manually, or rescan the finding list. After a failure, the model may edit the same controlled artifact and rerun the same intent only when the shared rule's mechanical gates pass; reassess convergence after every failure. The final complete result determines the verdict and counts from that same snapshot: `stageStatus.canAdvance=true` with an Approved conclusion permits cross-stage advancement; `stageStatus.canAdvance=false` still requires `agent-infra-internal task-event {task-id} review-analysis.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}`, using `changes-requested` and routing to same-stage revision/review (use `rejected` when the report explicitly rejects). On failure, model stop, lack of progress, or the emergency cap, do not publish a completion event or cross-stage command; use the `repair-stop` scenario in `reference/output-templates.md` to show existing summary/findings, the artifact, actual repair attempts, the last diagnostic, and the stop reason.
 
 `manual-validation` is the data source for the `Manual-validation` count folded into review rows in `ai task log`; do not add a parallel manual-verification field.
 

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

@@ -9,7 +9,7 @@ description: >
 # 需求分析审查
 > `--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。
+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。
 
 审查最新需求分析产物，并产出 `review-analysis.md` 或 `review-analysis-r{N}.md`。
 
@@ -41,7 +41,7 @@ agent-infra-internal task-snapshot {task-id} --format text
 
 ## 步骤开始：声明 started 事件
 
-确认前置条件和产物上下文后、本轮第一个产出动作之前执行 `agent-infra-internal task-event {task-id} review-analysis.started --agent {standard-agent-token}`。
+确认前置条件和产物上下文后、本轮第一个产出动作之前执行 `agent-infra-internal task-event {task-id} review-analysis.started --agent {standard-agent-token} --initiator {trigger-initiator} --request-id {request-id} --reason-code {reason-code}`。
 
 ## 执行步骤
 ### 1. 验证前置条件
@@ -83,7 +83,7 @@ agent-infra-internal task-snapshot {task-id} --format text
 {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-analysis.completed --agent {standard-agent-token} --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-analysis.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。
 
 `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-code/SKILL.en.md

@@ -9,7 +9,7 @@ description: >
 # Code Review
 > `--agent` values are defined in `.agents/rules/task-management.md` under “Collaborator Token Specification”.
 
-If the entry operands contain `--orchestrated`, bind `{execution-flag}` to `--orchestrated` and forward it unchanged to both the summary finalizer and completed event; otherwise bind it to an empty value. Never infer it from `orchestration.json`, environment variables, or prior artifacts.
+If the entry operands contain `--orchestrated`, bind `{execution-flag}` to `--orchestrated` and forward it unchanged to both the summary finalizer and completed event; otherwise bind it to an empty value. Never infer it from `orchestration.json`, environment variables, or prior artifacts. Lifecycle events also 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 `review-finding`. Reuse the same values for started and completed.
 
 Review the latest code round and produce `review-code.md` or `review-code-r{N}.md`.
 
@@ -50,7 +50,7 @@ Before the state check is complete, do not make external-state assertions such a
 
 ## Step Start: Write the started Marker
 
-After resolving the artifact context and before this round's first artifact action, run `agent-infra-internal task-event {task-id} review-code.started --agent {standard-agent-token}`.
+After resolving the artifact context and before this round's first artifact action, run `agent-infra-internal task-event {task-id} review-code.started --agent {standard-agent-token} --initiator {trigger-initiator} --request-id {request-id} --reason-code {reason-code}`.
 
 ## Steps
 
@@ -109,10 +109,10 @@ Update task.md:
   {unresolved-minor} = stageStatus.unresolvedFindingCounts.minor
   ```
 
-  The intent atomically finalizes the report summary and returns the same ledger snapshot. Do not call `stage-status`, replace placeholders manually, or rescan the finding list. After a failure, the model may edit the same controlled artifact and rerun the same intent only when the shared rule's mechanical gates pass; reassess convergence after every failure. The final complete result determines the verdict and counts from that same snapshot: `stageStatus.canAdvance=true` with an Approved conclusion permits cross-stage advancement; `stageStatus.canAdvance=false` still requires `agent-infra-internal task-event {task-id} review-code.completed --agent {standard-agent-token} --artifact {review-artifact} --verdict {approved|changes-requested|rejected} --blockers {unresolved-blockers} --major {unresolved-major} --minor {unresolved-minor} --manual-validation {n} {execution-flag}`, using `changes-requested` and routing to same-stage revision/review (use `rejected` when the report explicitly rejects). On failure, model stop, lack of progress, or the emergency cap, do not publish a completion event or cross-stage command; use the `repair-stop` scenario in `reference/output-templates.md` to show existing summary/findings, the artifact, actual repair attempts, the last diagnostic, and the stop reason
+  The intent atomically finalizes the report summary and returns the same ledger snapshot. Do not call `stage-status`, replace placeholders manually, or rescan the finding list. After a failure, the model may edit the same controlled artifact and rerun the same intent only when the shared rule's mechanical gates pass; reassess convergence after every failure. The final complete result determines the verdict and counts from that same snapshot: `stageStatus.canAdvance=true` with an Approved conclusion permits cross-stage advancement; `stageStatus.canAdvance=false` still requires `agent-infra-internal task-event {task-id} review-code.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}`, using `changes-requested` and routing to same-stage revision/review (use `rejected` when the report explicitly rejects). On failure, model stop, lack of progress, or the emergency cap, do not publish a completion event or cross-stage command; use the `repair-stop` scenario in `reference/output-templates.md` to show existing summary/findings, the artifact, actual repair attempts, the last diagnostic, and the stop reason
 - Only when `canAdvance=true`, the verdict is Approved, and `T == R^{tree}`, write `last_reviewed_commit: {R}`. Clear an old value for an Approved snapshot with uncommitted differences; otherwise preserve the existing value and do not advance it
 - For an Approved exit, collect PR and all-check facts as defined in `reference/output-templates.md`: route uncommitted/unpushed code to `commit`, no PR to `create-pr` (except no-PR flow), non-terminal checks to `watch-pr`, and route to `complete-task` only when `HEAD == last_reviewed_commit == PR head` with checks `passed|no-required`; never route by review round alone
-- After handling `last_reviewed_commit`, run `agent-infra-internal task-event {task-id} review-code.completed --agent {standard-agent-token} --artifact {review-artifact} --verdict {approved|changes-requested|rejected} --blockers {unresolved-blockers} --major {unresolved-major} --minor {unresolved-minor} --manual-validation {n} {execution-flag}`
+- After handling `last_reviewed_commit`, run `agent-infra-internal task-event {task-id} review-code.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}`
 
 Always include the `Manual-validation: {n}` field in the done log, including when it is 0.
 `manual-validation` is the data source for the `Manual-validation` count folded into review rows in `ai task log`; do not add a parallel manual-verification field.

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

@@ -9,7 +9,7 @@ description: >
 # 代码审查
 > `--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。
+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。
 
 审查最新代码轮次，并产出 `review-code.md` 或 `review-code-r{N}.md`。
 
@@ -50,7 +50,7 @@ agent-infra-internal task-snapshot {task-id} --format text
 
 ## 步骤开始：声明 started 事件
 
-确认前置条件和产物上下文后、本轮第一个产出动作之前执行 `agent-infra-internal task-event {task-id} review-code.started --agent {standard-agent-token}`。
+确认前置条件和产物上下文后、本轮第一个产出动作之前执行 `agent-infra-internal task-event {task-id} review-code.started --agent {standard-agent-token} --initiator {trigger-initiator} --request-id {request-id} --reason-code {reason-code}`。
 
 ## 执行步骤
 ### 1. 验证前置条件
@@ -107,10 +107,10 @@ agent-infra-internal task-snapshot {task-id} --format text
   {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-code.completed --agent {standard-agent-token} --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-code.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
 - 仅当 `canAdvance=true`、本轮结论为 Approved 且 `T == R^{tree}` 时写入 `last_reviewed_commit: {R}`；Approved 快照包含未提交差异时清除旧值。否则保留既有值，不得推进或清空
 - Approved 出口继续按 `reference/output-templates.md` 采集 PR 与全部 checks 事实：未提交/未推送走 `commit`，无 PR 走 `create-pr`（无 PR 流程除外），checks 未终态走 `watch-pr`，仅 `HEAD == last_reviewed_commit == PR head` 且 checks 为 `passed|no-required` 时走 `complete-task`；不得仅按审查轮次分流
-- 完成 `last_reviewed_commit` 处理后执行 `agent-infra-internal task-event {task-id} review-code.completed --agent {standard-agent-token} --artifact {review-artifact} --verdict {approved|changes-requested|rejected} --blockers {unresolved-blockers} --major {unresolved-major} --minor {unresolved-minor} --manual-validation {n} {execution-flag}`
+- 完成 `last_reviewed_commit` 处理后执行 `agent-infra-internal task-event {task-id} review-code.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}`
 
 完成日志必须始终写入 `Manual-validation: {n}` 字段，0 也保留。
 `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-plan/SKILL.en.md

@@ -9,7 +9,7 @@ description: >
 # Technical Plan Review
 > `--agent` values are defined in `.agents/rules/task-management.md` under “Collaborator Token Specification”.
 
-If the entry operands contain `--orchestrated`, bind `{execution-flag}` to `--orchestrated` and forward it unchanged to both the summary finalizer and completed event; otherwise bind it to an empty value. Never infer it from `orchestration.json`, environment variables, or prior artifacts.
+If the entry operands contain `--orchestrated`, bind `{execution-flag}` to `--orchestrated` and forward it unchanged to both the summary finalizer and completed event; otherwise bind it to an empty value. Never infer it from `orchestration.json`, environment variables, or prior artifacts. Lifecycle events also 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 `review-finding`. Reuse the same values for started and completed.
 
 Review the latest plan artifact and produce `review-plan.md` or `review-plan-r{N}.md`.
 
@@ -39,7 +39,7 @@ agent-infra-internal task-snapshot {task-id} --format text
 
 ## Step Start: Write the started Marker
 
-After resolving the artifact context and before this round's first artifact action, run `agent-infra-internal task-event {task-id} review-plan.started --agent {standard-agent-token}`.
+After resolving the artifact context and before this round's first artifact action, run `agent-infra-internal task-event {task-id} review-plan.started --agent {standard-agent-token} --initiator {trigger-initiator} --request-id {request-id} --reason-code {reason-code}`.
 
 ## Steps
 
@@ -80,7 +80,7 @@ Bind and reuse this structured mapping from that one response:
 {unresolved-minor} = stageStatus.unresolvedFindingCounts.minor
 ```
 
-The intent atomically finalizes the report summary and returns the same ledger snapshot. Do not call `stage-status`, replace placeholders manually, or rescan the finding list. After a failure, the model may edit the same controlled artifact and rerun the same intent only when the shared rule's mechanical gates pass; reassess convergence after every failure. The final complete result determines the verdict and counts from that same snapshot: `stageStatus.canAdvance=true` with an Approved conclusion permits cross-stage advancement; `stageStatus.canAdvance=false` still requires `agent-infra-internal task-event {task-id} review-plan.completed --agent {standard-agent-token} --artifact {review-artifact} --verdict {approved|changes-requested|rejected} --blockers {unresolved-blockers} --major {unresolved-major} --minor {unresolved-minor} --manual-validation {n} {execution-flag}`, using `changes-requested` and routing to same-stage revision/review (use `rejected` when the report explicitly rejects). On failure, model stop, lack of progress, or the emergency cap, do not publish a completion event or cross-stage command; use the `repair-stop` scenario in `reference/output-templates.md` to show existing summary/findings, the artifact, actual repair attempts, the last diagnostic, and the stop reason.
+The intent atomically finalizes the report summary and returns the same ledger snapshot. Do not call `stage-status`, replace placeholders manually, or rescan the finding list. After a failure, the model may edit the same controlled artifact and rerun the same intent only when the shared rule's mechanical gates pass; reassess convergence after every failure. The final complete result determines the verdict and counts from that same snapshot: `stageStatus.canAdvance=true` with an Approved conclusion permits cross-stage advancement; `stageStatus.canAdvance=false` still requires `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}`, using `changes-requested` and routing to same-stage revision/review (use `rejected` when the report explicitly rejects). On failure, model stop, lack of progress, or the emergency cap, do not publish a completion event or cross-stage command; use the `repair-stop` scenario in `reference/output-templates.md` to show existing summary/findings, the artifact, actual repair attempts, the last diagnostic, and the stop reason.
 
 `manual-validation` is the data source for the `Manual-validation` count folded into review rows in `ai task log`; do not add a parallel manual-verification field.
 

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。
+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。
 
 审查最新技术方案产物，并产出 `review-plan.md` 或 `review-plan-r{N}.md`。
 
@@ -41,7 +41,7 @@ agent-infra-internal task-snapshot {task-id} --format text
 
 ## 步骤开始：声明 started 事件
 
-确认前置条件和产物上下文后、本轮第一个产出动作之前执行 `agent-infra-internal task-event {task-id} review-plan.started --agent {standard-agent-token}`。
+确认前置条件和产物上下文后、本轮第一个产出动作之前执行 `agent-infra-internal task-event {task-id} review-plan.started --agent {standard-agent-token} --initiator {trigger-initiator} --request-id {request-id} --reason-code {reason-code}`。
 
 ## 执行步骤
 ### 1. 验证前置条件
@@ -83,7 +83,7 @@ agent-infra-internal task-snapshot {task-id} --format text
 {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} --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} {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。
 
 `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/run-manual-validation/SKILL.en.md

@@ -8,6 +8,8 @@ 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.
+
 ## Task Context Resolution
 
 The entry point may omit the task ref; explicit task scope accepts only `--task <ref>` or `-t <ref>`, and positional task refs are not interpreted. Parse `--scope`, `--timeout`, and `--format` before `--`, preserve the user command after `--` verbatim, then call `agent-infra-internal task-context resolve {task-scope}`. Pass through resolution failures without scanning tasks locally. The internal `task-validate` protocol continues to use a positional task ref.
@@ -32,10 +34,10 @@ agent-infra-internal task-snapshot {task-id} --format text
 
 1. Read `reference/discovery-and-execution.md` and parse the input mode. Stop before started without an artifact for invalid or partial input.
 2. Run `agent-infra-internal task-artifact {task-id} inspect --family validation-run` and read the latest review-code manual-validation items. Then run `agent-infra-internal platform-pr inspect {task-id}` and use the reference status matrix to discover, merge, and number items. Only automatic mode stops before started when reliable sources are empty or the sole possible source is unreadable; valid explicit mode always continues with the user command as effective work.
-3. Take the round and artifact name from the core result. After confirming valid explicit work or a non-empty discovered list, run `agent-infra-internal task-event {task-id} validation-run.started --agent {standard-agent-token}` and classify each item as `executable|unavailable|unknown|unsafe|unresolved`.
+3. Take the round and artifact name from the core result. After confirming valid explicit work or a non-empty discovered list, run `agent-infra-internal task-event {task-id} validation-run.started --agent {standard-agent-token} --initiator {trigger-initiator} --request-id {request-id} --reason-code {reason-code}` and classify each item as `executable|unavailable|unknown|unsafe|unresolved`.
 4. Invoke every executable item separately with `agent-infra-internal task-validate {task-ref} --scope snapshot --format json -- {command...}`. Only make a second explicit inplace invocation for that item when evidence proves it is required. If no item is executable, run no fabricated command but still produce coverage-gap evidence.
 5. Read `reference/report-template.md`, create `validation-run.md|validation-run-r{N}.md`, and record the input mode, discovered list, per-item results, CLI JSON allowlist, and sanitized summaries.
-6. Run `agent-infra-internal task-event {task-id} validation-run.completed --agent {standard-agent-token} --artifact {artifact}`. When an Issue exists, run `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}` and then `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {artifact} --agent {standard-agent-token}`.
+6. Run `agent-infra-internal task-event {task-id} validation-run.completed --agent {standard-agent-token} --initiator {trigger-initiator} --request-id {request-id} --reason-code {reason-code} --artifact {artifact}`. When an Issue exists, run `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}` and then `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {artifact} --agent {standard-agent-token}`.
 7. Run `agent-infra-internal task-verify {task-id} validation-run.completed --artifact {artifact} --format text`; fix failures and rerun it.
 8. Report the evidence path, coverage gaps, and verification result; explicitly leave the decision to run `complete-manual-validation` to the maintainer. Read `.agents/rules/next-step-output.md` and end with `Completed at`.
 

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

@@ -8,6 +8,8 @@ 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。
+
 ## 任务上下文解析
 
 入口可省略 task ref；显式 task scope 仅接受 `--task <ref>` 或 `-t <ref>`，不再解释位置 task ref。先解析 `--scope`、`--timeout`、`--format`，在 `--` 后原样保留用户命令，再调用 `agent-infra-internal task-context resolve {task-scope}`。解析失败时透传非零退出码，不自行扫描任务。内部 `task-validate` 协议仍使用位置 task ref。
@@ -32,10 +34,10 @@ agent-infra-internal task-snapshot {task-id} --format text
 
 1. 读取 `reference/discovery-and-execution.md`，解析输入模式；非法或半截输入在 started 前停止，不写产物。
 2. 运行 `agent-infra-internal task-artifact {task-id} inspect --family validation-run`，读取最新 review-code 人工校验项；再运行 `agent-infra-internal platform-pr inspect {task-id}`，按 reference 的状态矩阵发现、归并并编号。仅在自动模式下，可靠来源无项或唯一可能来源不可读时才在 started 前停止；合法显式模式始终以用户命令作为有效工作继续。
-3. 从核心结果取得轮次和产物名；确认存在有效显式工作或非空发现清单后，运行 `agent-infra-internal task-event {task-id} validation-run.started --agent {standard-agent-token}`，并逐项分类为 `executable|unavailable|unknown|unsafe|unresolved`。
+3. 从核心结果取得轮次和产物名；确认存在有效显式工作或非空发现清单后，运行 `agent-infra-internal task-event {task-id} validation-run.started --agent {standard-agent-token} --initiator {trigger-initiator} --request-id {request-id} --reason-code {reason-code}`，并逐项分类为 `executable|unavailable|unknown|unsafe|unresolved`。
 4. 每个可执行项分别调用 `agent-infra-internal task-validate {task-ref} --scope snapshot --format json -- {command...}`；只有证据表明必须原位时才对该项进行第二次显式 inplace 调用。零项可执行时不运行伪造命令，但仍继续产出覆盖缺口证据。
 5. 读取 `reference/report-template.md`，创建 `validation-run.md|validation-run-r{N}.md`；记录输入模式、发现清单、逐项结果、CLI JSON allowlist 与去敏摘要。
-6. 运行 `agent-infra-internal task-event {task-id} validation-run.completed --agent {standard-agent-token} --artifact {artifact}`。存在 Issue 时依次运行 `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}` 和 `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {artifact} --agent {standard-agent-token}`。
+6. 运行 `agent-infra-internal task-event {task-id} validation-run.completed --agent {standard-agent-token} --initiator {trigger-initiator} --request-id {request-id} --reason-code {reason-code} --artifact {artifact}`。存在 Issue 时依次运行 `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}` 和 `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {artifact} --agent {standard-agent-token}`。
 7. 运行 `agent-infra-internal task-verify {task-id} validation-run.completed --artifact {artifact} --format text`；未通过则修复后重跑。
 8. 告知用户证据路径、覆盖缺口和验证结果；明确仍需维护者判断是否执行 `complete-manual-validation`。读取 `.agents/rules/next-step-output.md`，最后一行输出 `Completed at`。
 

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

@@ -48,13 +48,13 @@ Resolve the target PR number `{pr#}` and an optional `{task-id}` via these deter
 
 Before running this step, read `reference/monitor-and-heal.md` and `.agents/rules/pr-checks-commands.md`.
 
-Initialize `repairCommits=[]` and `rebaseAttempts=0`. Run `agent-infra-internal platform-checks watch {task-id} --interval-seconds 30 --deadline-seconds 1800`, then route only by `readiness.state`: `ready` to step 7, `conflicting|checks-failed` to step 3, and `pending|timed-out|cancelled` to step 4.
+Initialize `repairCommits=[]` and `rebaseAttempts=0`. Before readiness in every round, run `platform-pr summary-context`, 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`. `--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 the refresh, run `agent-infra-internal platform-checks watch {task-id} --interval-seconds 30 --deadline-seconds 1800`, then route only by `readiness.state`: `ready` to step 7, `conflicting|checks-failed` to step 3, and `pending|timed-out|cancelled` to step 4.
 
 ### 3. Self-Heal Loop
 
 Before running this step, read the "Self-Heal Decision Tree" of `reference/monitor-and-heal.md` and "Resolve a Failing Run id and Pull Logs" of `.agents/rules/pr-checks-commands.md`.
 
-For `checks-failed`, minimally fix a locatable code-layer failure, test, and publish through the existing commit/push intents. For `conflicting`, follow the reference's same-repository, clean-tree, head/base identity, rebase, full-test, and `git-workflow push-rebased` exact-lease flow, capped at two attempts. Append only remotely verified SHAs, then watch the new head again; any failed safety check goes to step 4.
+For `checks-failed`, minimally fix a locatable code-layer failure, test, and publish through the existing commit/push intents. For `conflicting`, follow the reference's same-repository, clean-tree, head/base identity, rebase, full-test, and `git-workflow push-rebased` exact-lease flow, capped at two attempts. Append only remotely verified SHAs; after any external push, self-heal commit, or rebase changes the head, refresh the report and summary before watching the new head again; any failed safety check goes to step 4.
 
 ### 4. Help Exit (Produce-Then-Stop)
 

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

@@ -48,13 +48,13 @@ description: >
 
 执行此步骤前，先读取 `reference/monitor-and-heal.md` 与 `.agents/rules/pr-checks-commands.md`。
 
-进入本轮时初始化 `repairCommits=[]` 与 `rebaseAttempts=0`。调用 `agent-infra-internal platform-checks watch {task-id} --interval-seconds 30 --deadline-seconds 1800`，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。
+进入本轮时初始化 `repairCommits=[]` 与 `rebaseAttempts=0`。每轮 readiness 前先调用 `platform-pr summary-context`，按共享 PR change-report contract 以当前权威 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。`--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。刷新完成后调用 `agent-infra-internal platform-checks watch {task-id} --interval-seconds 30 --deadline-seconds 1800`，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。
 
 ### 3. 自愈循环
 
 执行此步骤前，先读取 `reference/monitor-and-heal.md` 的「自愈决策树」与 `.agents/rules/pr-checks-commands.md` 的「解析失败 run id 并拉日志」。
 
-`checks-failed` 只对可定位代码层失败做最小修复和测试，再用既有 commit/push intent 发布。`conflicting` 严格执行 reference 的同仓库、干净工作树、head/base 身份、rebase、完整测试与 `git-workflow push-rebased` 精确 lease 流程；上限 2 次。仅记录远端复核成功的 SHA，随后重新监控新 head；任一安全检查失败转步骤 4。
+`checks-failed` 只对可定位代码层失败做最小修复和测试，再用既有 commit/push intent 发布。`conflicting` 严格执行 reference 的同仓库、干净工作树、head/base 身份、rebase、完整测试与 `git-workflow push-rebased` 精确 lease 流程；上限 2 次。仅记录远端复核成功的 SHA；任何外部 push、自愈 commit 或 rebase 改变 head 后，先按本轮报告→摘要顺序刷新，再重新监控新 head；任一安全检查失败转步骤 4。
 
 ### 4. 求助出口（产出后停止）
 

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

@@ -11,6 +11,12 @@ After the watch command, route by structured `readiness.state`:
 - `conflicting`: the platform explicitly reports a head/base conflict → rebase healing in SKILL step 3.
 - `pending|timed-out|cancelled`: no reliable success fact exists → SKILL step 4.
 
+## 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.
+
+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.
+
 ## Self-Heal Decision Tree
 
 ```text

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

@@ -11,6 +11,12 @@
 - `conflicting`：平台明确当前 head 与 base 冲突 → SKILL 步骤 3 的 rebase 自愈。
 - `pending|timed-out|cancelled`：mergeability/checks 未形成可靠成功事实 → SKILL 步骤 4。
 
+## 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。
+
 ## 自愈决策树
 
 ```text

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

@@ -96,7 +96,24 @@ delivery_remote_head:          # Most recent successfully delivered task branch
 <!-- Workflow degradation, platform sync failures, permission gaps, and related events. Keep the header when empty. -->
 
 | id | time | step | severity | code | status | target | message | action | resolved_at | resolution |
-|----|------|------|----------|------|--------|--------|---------|--------|-------------|------------|
+|----|------|------|----------|------|--------|---------|--------|-------------|------------|------------|
+
+## Rework Intent
+
+| intent_id | finding_id | source_artifact | source_sha256 | target | status | declared_at | consumed_at |
+|-----------|------------|----------------|---------------|--------|--------|-------------|-------------|
+
+## Artifact Invalidation
+
+### Operations
+
+| operation_id | source_family | source_artifact | source_round | source_sha256 | status | processed | total | created_at | updated_at | completed_at | error |
+|--------------|---------------|-----------------|--------------|---------------|--------|-----------|-------|------------|------------|--------------|-------|
+
+### Targets
+
+| target_id | operation_id | target_kind | target_family | target_artifact | target_round | target_sha256 | status | reason_code | updated_at |
+|-----------|--------------|-------------|---------------|-----------------|--------------|---------------|--------|-------------|------------|
 
 ## Activity Log
 

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

@@ -96,7 +96,24 @@ delivery_remote_head:          # 最近一次成功交付到 remote 的任务分
 <!-- 工作流降级、平台同步失败、权限不足等需要后续注意的事件写入此段。无告警时保留表头即可。 -->
 
 | id | time | step | severity | code | status | target | message | action | resolved_at | resolution |
-|----|------|------|----------|------|--------|--------|---------|--------|-------------|------------|
+|----|------|------|----------|------|--------|---------|--------|-------------|------------|------------|
+
+## 返工意图
+
+| intent_id | finding_id | source_artifact | source_sha256 | target | status | declared_at | consumed_at |
+|-----------|------------|----------------|---------------|--------|--------|-------------|-------------|
+
+## 产物失效记录
+
+### Operations
+
+| operation_id | source_family | source_artifact | source_round | source_sha256 | status | processed | total | created_at | updated_at | completed_at | error |
+|--------------|---------------|-----------------|--------------|---------------|--------|-----------|-------|------------|------------|--------------|-------|
+
+### Targets
+
+| target_id | operation_id | target_kind | target_family | target_artifact | target_round | target_sha256 | status | reason_code | updated_at |
+|-----------|--------------|-------------|---------------|-----------------|--------------|---------------|--------|-------------|------------|
 
 ## 活动日志
 

package/templates/.github/workflows/pr-label.yml

@@ -20,36 +20,17 @@ jobs:
       - name: Checkout base branch
         uses: actions/checkout@v7
 
+      - name: Set up Node.js
+        uses: actions/setup-node@v7
+        with:
+          node-version: 22.9.0
+
       - name: Sync in-labels
         env:
           GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           PR_NUMBER: ${{ github.event.pull_request.number }}
-        run: |
-          changed_files=$(gh api "repos/$GITHUB_REPOSITORY/pulls/$PR_NUMBER/files" \
-            --paginate --jq '.[].filename' | jq -Rn '[inputs]')
-
-          should_labels=$(jq -rn \
-            --argjson files "$changed_files" \
-            --argjson mapping "$(jq '.labels.in // {}' .agents/.airc.json)" \
-            '$mapping
-            | to_entries
-            | map(select(.value | any(. as $prefix | $files | any(startswith($prefix)))))
-            | map("in: " + .key)
-            | .[]?')
-
-          set -- \
-            --repo "$GITHUB_REPOSITORY" \
-            --pr "$PR_NUMBER" \
-            --prefix "in: "
-
-          while IFS= read -r label; do
-            [ -z "$label" ] && continue
-            set -- "$@" --target "$label"
-          done <<EOF
-          $should_labels
-          EOF
-
-          .github/scripts/sync-labels-to-set.sh "$@"
+          AGENT_INFRA_VERSION: 0.9.13-alpha.0
+        run: npm exec --yes --package="@fitlab-ai/agent-infra@$AGENT_INFRA_VERSION" -- agent-infra-internal platform-pr sync-in-labels --pr "$PR_NUMBER" --cwd "$GITHUB_WORKSPACE"
 
       - name: Assign PR creator if unassigned
         env: