@fitlab-ai/agent-infra 0.9.11 → 0.9.13

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

@@ -9,13 +9,14 @@ 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`.
 
 ## Boundary / Critical Rules
 
 - This skill reviews code and writes a report; it does not modify product code
+- Before generating task or lifecycle Markdown that will be synchronized to an Issue, read `.agents/rules/sync-content-generation.md` and apply its producer-side constraints; the sync path does not parse or rewrite the body
 - After executing this skill, you **must** immediately update task.md
 
 Version stamp rule: when creating or updating `task.md` frontmatter, read `.agents/rules/version-stamp.md` first and write or refresh `agent_infra_version`.
@@ -49,7 +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
 
@@ -70,11 +71,11 @@ Read the highest-round code artifact and, if present, the highest-round fix arti
 ### 4. Perform the Review
 
 Follow `.agents/workflows/feature-development.yaml` and inspect the full change context:
-- Capture the reviewed commit `R=$(git rev-parse HEAD)` exactly once; reuse R for this round's report, snapshot tree, and task review fact, and do not re-read HEAD later as a substitute
-- Call `agent-infra-internal platform-pr inspect {task-id}`. When a bound PR provides a base SHA, set the diff base to `D=$(git merge-base "$R" "{base-sha}")`. Without a PR, set `D=$R` only when tracked or untracked worktree changes exist. A clean worktree without a bound PR has no reliable complete committed range: stop and require a bound PR instead of reviewing an empty diff
+- Resolve the task's bound delivery remote/base and read the target SHA once at review start, `M=$(git ls-remote --refs {remote} refs/heads/{baseRef})`; then capture the reviewed commit `R=$(git rev-parse HEAD)` once and compute `D=$(git merge-base "$R" "$M")`. Save M/D/R as historical evidence and never overwrite them with a later live target value
+- If the delivery target cannot be resolved or its target commit is unavailable, stop and record the target error; M/D/R must come from one fact-collection round and must not be replaced by PR-existence evidence
 - `git diff --binary "$D" -- <post-review-globs>` covers committed and uncommitted tracked changes from D to the current worktree
 - `git ls-files -o --exclude-standard -z -- <post-review-globs>` for untracked new files
-- Write `mode=worktree`, `baseline=R`, and `diffBase=D` to a temporary JSON file, then call `agent-infra-internal git-workflow snapshot --input {file}` to generate a reviewed diff fingerprint `F` for the complete committed range and a reviewed snapshot tree `T` for the current worktree; write R, D, F, and T into the report
+- Write `mode=worktree`, `baseline=R`, and `diffBase=D` to a temporary JSON file, then call `agent-infra-internal git-workflow snapshot --input {file}` to generate a reviewed diff fingerprint `F` for the complete committed range and a reviewed snapshot tree `T` for the current worktree; write M, R, D, F, and T into the report
 
 > After collecting those facts, read `.agents/rules/review-method.md`, use them as readiness evidence, and run Passes 2–5 for traceability, risk lenses, counterevidence, and classification; the report must record all five passes.
 > Detailed review criteria, severity rules, and reviewer expectations live in `reference/review-criteria.md`. Read `reference/review-criteria.md` before reviewing.
@@ -98,7 +99,7 @@ Create `.agents/workspace/active/{task-id}/{review-artifact}`.
 
 Update task.md:
 - After the report, submit each new finding with `agent-infra-internal task-ledger {task-id} finding-upsert --stage code --review-artifact {review-artifact} --ordinal {n} --severity {blocker|major|minor} --evidence {review-artifact}#{anchor}`; submit prior-response dispositions with `finding-review --id {ledger-id} --status {confirmed|closed|open|needs-human-decision} --evidence {evidence}`. When escalating to `needs-human-decision`, append `--needs-implementation true|false` using the judgment recorded in the detail block. Do not scan ids or edit ledger rows
-- After all ledger writes, call `agent-infra-internal task-review {task-id} finalize-summary --stage code --artifact {review-artifact} {execution-flag}` exactly once
+- After all ledger writes, make the initial call to `agent-infra-internal task-review {task-id} finalize-summary --stage code --artifact {review-artifact} {execution-flag}`; after a failure, follow `.agents/rules/local-artifact-repair.md` to decide whether to edit and rerun, and never treat an error type or `changed=false` as automatic authorization
 
   Bind and reuse this structured mapping from that one response:
 
@@ -108,10 +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. If finalization fails or a response field is missing, stop before the completion event. Derive the verdict and next-step branch from the same response's `stageStatus.canAdvance`; only `canAdvance=true` permits Approved
+  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.
@@ -121,7 +122,7 @@ If task.md contains a valid `issue_number`, perform these sync actions (skip and
 - Run `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}`
 - Run `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {review-artifact} --agent {standard-agent-token}`
 
-Before writing the summary, the finalization intent checks decision-detail ids; it auto-removes a duplicate only when exactly one formal `[needs-human-decision]` block remains and every other same-id block is clearly short and informal, then reruns the read-only check. Ambiguous duplicates fail closed. If this check or repair fails, stop before the completion event.
+Before writing the summary, the finalization intent checks decision-detail ids; any visible duplicate returns a structured failure and preserves the artifact bytes, while the model decides whether a minimal edit is safe under the shared rule. If the safety gates fail, diagnostics repeat, no byte-level progress occurs, or the emergency cap is reached, stop before the completion event; the stop path must still show the existing review result instead of hiding the artifact.
 
 ### 7. Verification Gate
 

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

@@ -9,13 +9,14 @@ 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`。
 
 ## 行为边界 / 关键规则
 
 - 本技能只审查代码并写报告，不修改业务代码
+- 生成会同步到 Issue 的任务或生命周期 Markdown 前，先读取 `.agents/rules/sync-content-generation.md` 并遵循其中的生成端约束；同步端不解析或改写正文
 - 执行本技能后，你**必须**立即更新 task.md
 
 版本戳规则：创建或更新 `task.md` frontmatter 时，先读取 `.agents/rules/version-stamp.md`，并写入或刷新 `agent_infra_version`。
@@ -49,7 +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
@@ -69,11 +70,11 @@ agent-infra-internal task-snapshot {task-id} --format text
 ### 4. 执行审查
 
 遵循 `.agents/workflows/feature-development.yaml`，并同时检查完整变更上下文：
-- 一次性记录审查提交 `R=$(git rev-parse HEAD)`；本轮报告、快照树和任务审查事实都复用该 R，禁止稍后重新读取 HEAD 代替
-- 调用 `agent-infra-internal platform-pr inspect {task-id}`：已绑定 PR 且返回 base SHA 时，令差异基线 `D=$(git merge-base "$R" "{base-sha}")`；无 PR 时仅在存在已跟踪或未跟踪工作区变化的前提下令 `D=$R`。无 PR 且工作区干净时无法可靠确定完整提交范围，必须停止并要求先绑定 PR，不得用空 diff 继续审查
+- 在审查开始时解析任务绑定的 delivery remote/base，并一次性读取目标分支 SHA `M=$(git ls-remote --refs {remote} refs/heads/{baseRef})`；随后一次性记录审查提交 `R=$(git rev-parse HEAD)`，计算 `D=$(git merge-base "$R" "$M")`。报告保存 M/D/R，不能用后续实时目标值覆盖本轮历史证据
+- 若 delivery target 无法解析或目标 commit 不可用，停止并记录 target 错误；M/D/R 必须来自同一轮事实采集，不以 PR 是否存在替代 delivery target 证据
 - `git diff --binary "$D" -- <post-review-globs>` 覆盖 `D` 到当前工作区的已提交与未提交跟踪变更
 - `git ls-files -o --exclude-standard -z -- <post-review-globs>` 覆盖未跟踪新文件
-- 把 `mode=worktree`、`baseline=R`、`diffBase=D` 写入临时 JSON，调用 `agent-infra-internal git-workflow snapshot --input {file}` 一次生成覆盖完整提交范围的审查差异指纹 `F` 与当前工作区审查快照树 `T`；把 `R`、`D`、`F`、`T` 全部写入报告
+- 把 `mode=worktree`、`baseline=R`、`diffBase=D` 写入临时 JSON，调用 `agent-infra-internal git-workflow snapshot --input {file}` 一次生成覆盖完整提交范围的审查差异指纹 `F` 与当前工作区审查快照树 `T`；把 M、R、D、F、T 全部写入报告
 
 > 上述事实采集完成后，先读取 `.agents/rules/review-method.md`，以其作为 readiness 证据并按 Pass 2–5 完成追踪、风险镜头、反证和归类；报告必须记录全部五遍覆盖。
 > 详细审查标准、严重程度划分和 reviewer 关注点见 `reference/review-criteria.md`。执行此步骤前先读取 `reference/review-criteria.md`。
@@ -96,7 +97,7 @@ agent-infra-internal task-snapshot {task-id} --format text
 ### 6. 更新任务状态
 
 - 报告完成后，新 finding 逐条调用 `agent-infra-internal task-ledger {task-id} finding-upsert --stage code --review-artifact {review-artifact} --ordinal {n} --severity {blocker|major|minor} --evidence {review-artifact}#{anchor}`；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}`。升级为 `needs-human-decision` 时，按详情块中的判断追加 `--needs-implementation true|false`。不得扫描编号或手写账本行
-- 全部账本写入完成后只调用一次 `agent-infra-internal task-review {task-id} finalize-summary --stage code --artifact {review-artifact} {execution-flag}`
+- 全部账本写入完成后首次调用 `agent-infra-internal task-review {task-id} finalize-summary --stage code --artifact {review-artifact} {execution-flag}`；失败后是否继续编辑并重跑，必须遵循 `.agents/rules/local-artifact-repair.md`，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：
 
@@ -106,10 +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。最终化失败或返回字段缺失时，停止在完成事件之前。以同一次返回的 `stageStatus.canAdvance` 决定 verdict 和下一步；仅 `canAdvance=true` 可用 Approved
+  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。
@@ -119,7 +120,7 @@ agent-infra-internal task-snapshot {task-id} --format text
 - 调用 `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}`
 - 调用 `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {review-artifact} --agent {standard-agent-token}`
 
-最终化 intent 会在写入摘要前检查详情块 ID；只有“一个正式 `[needs-human-decision]` 块 + 明确的简短非正式重复块”才会自动删除重复块并重新做只读检查，无法唯一判断时失败关闭。该检查或自动修复失败时，停止在完成事件之前。
+最终化 intent 会在写入摘要前检查详情块 ID；任何可见重复都返回结构化失败并保持 artifact 字节不变，由模型按共享规则判断是否进行最小编辑。无法通过安全门、诊断重复、没有实际字节变化或达到紧急熔断时，停止在完成事件之前；停止路径仍必须展示已有审查结果，不得吞掉 artifact 内容。
 
 ### 7. 完成校验
 

package/templates/.agents/skills/review-code/reference/output-templates.en.md

@@ -20,9 +20,27 @@ Prohibitions:
 - generate `{next-step-commands}` for the selected branch through the shared helper
 - The count line shows 5 numbers. Manual-validation (`{e}`) does not affect selection. `Human-decision` (`{h}`) counts this stage's `needs-human-decision` rows; because those rows are unresolved, `{h} > 0` means `canAdvance=false`. Expand the "Pending human-decision pre-block" from `.agents/rules/next-step-output.md` and show revision and re-review paths only.
 
+### Branch R: Finalization stopped with results visible
+
+When the finalizer fails, or the model stops because of a safety gate, lack of progress, repeated diagnostics, or the emergency cap, use this branch. Do not call the shared helper or output cross-stage commands.
+
+```text
+Task {task-id} review results were generated, but lifecycle advancement stopped.
+- Review artifact: .agents/workspace/active/{task-id}/{review-artifact}
+- Last valid summary/findings: {last-readable-review-result}
+- Local repair attempts: {repairAttempts}
+- Last diagnostic: {last-structured-diagnostic}
+- Stop reason: {stop-reason}
+- Completion event: not published | Cross-stage commands: not generated
+
+Note: only lifecycle advancement stopped; the existing review result remains available. Handle it manually or rerun the current review skill.
+```
+
+If the summary cannot be parsed safely, set `{last-readable-review-result}` to "summary could not be parsed safely" and retain the artifact path and raw structured diagnostic; do not infer counts or add a conclusion.
+
 ### Branch A: Approved with No Findings
 
-Do not route by review round. Compare reviewed snapshot tree `T` with the tree of baseline `R`, then read `prFlow` / `pr_number`; when a PR exists, call `agent-infra-internal platform-checks inspect {task-id}`. Select exactly one mutually exclusive exit:
+Do not route by review round. Compare reviewed snapshot tree `T` with the tree of baseline `R`, then read `prFlow` / verified `pr_delivery_fact`; when a PR exists, call `agent-infra-internal platform-checks inspect {task-id}`. Select exactly one mutually exclusive exit:
 
 - `T != R^{tree}`: Branch A1 (commit).
 - `T == R^{tree}` without a PR: Branch A4 for `prFlow=disabled`, otherwise Branch A2 (create PR).

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

@@ -20,9 +20,27 @@
 - 所选场景必须通过统一 helper 生成 `{next-step-commands}`
 - 计数行固定显示 5 个数字。manual-validation（`{e}`）不影响分支；`人工裁决`（`{h}`）是本阶段 `needs-human-decision` 行数，属于未闭环账本状态，因此 `{h} > 0` 时 `canAdvance=false`，必须按 `.agents/rules/next-step-output.md` 的「人工裁决待办前置块」展开详情，并只输出修订与复审路径。
 
+### 场景 R：最终化停止但结果可见
+
+当 finalizer 失败，或模型因安全门、无进展、重复诊断或紧急熔断停止时，使用本场景，不调用统一 helper，也不输出跨阶段命令。
+
+```text
+任务 {task-id} 审查结果已生成，但生命周期未推进。
+- 审查产物：.agents/workspace/active/{task-id}/{review-artifact}
+- 最后有效 summary/findings：{last-readable-review-result}
+- 本地修复次数：{repairAttempts}
+- 最后诊断：{last-structured-diagnostic}
+- 停止原因：{stop-reason}
+- 完成事件：未发布 | 跨阶段命令：未生成
+
+说明：本次仅停止生命周期推进，已有审查结果仍可查看。请先进行人工处理，或重新运行当前审查技能。
+```
+
+如果 summary 无法安全解析，`{last-readable-review-result}` 必须改为“摘要不可安全解析”，并保留 artifact 路径和原始结构化诊断；不得推算计数或补写结论。
+
 ### 场景 A：通过且无问题
 
-通过后不得按轮次路由。先比较审查快照树 `T` 与基线 `R` 的树，再读取任务的 `prFlow` / `pr_number`；存在 PR 时调用 `agent-infra-internal platform-checks inspect {task-id}`。只选择以下一个互斥出口：
+通过后不得按轮次路由。先比较审查快照树 `T` 与基线 `R` 的树，再读取任务的 `prFlow` / verified `pr_delivery_fact`；存在 PR 时调用 `agent-infra-internal platform-checks inspect {task-id}`。只选择以下一个互斥出口：
 
 - `T != R^{tree}`：场景 A1（提交）。
 - `T == R^{tree}` 且无 PR：`prFlow=disabled` 用场景 A4（完成），否则用场景 A2（创建 PR）。

package/templates/.agents/skills/review-code/reference/report-template.en.md

@@ -21,8 +21,10 @@ Use this template when writing `review-code.md` or `review-code-r{N}.md`.
 - **Reviewer**: {reviewer-name}
 - **Review Time**: {timestamp}
 - **Scope**: {file-count and major modules}
-- **Review Baseline Commit**: {raw reviewed commit R captured once for this round; must equal this round's HEAD}
-- **Reviewed Diff Base**: {raw D used for the complete diff/fingerprint; the merge-base of R and the PR base SHA when a PR is bound, otherwise R}
+- **Review Target Commit**: {target branch SHA M read once from the task-bound remote/base at review start; never overwritten by a later live target}
+- **Reviewed Head**: {local HEAD R captured once for this round; must equal this round's HEAD}
+- **Review Baseline Commit**: {compatibility display of R; must equal Reviewed Head}
+- **Reviewed Diff Base**: {D used for the complete diff/fingerprint; must equal merge-base(R, saved M)}
 - **Reviewed Diff Fingerprint**: {fingerprint field from git-workflow snapshot}
 - **Reviewed Snapshot Tree**: {tree field from git-workflow snapshot}
 - **Overall Verdict**: {Approved / Changes Requested / Rejected} (pick exactly one; combined phrases will fail the verify gate)

package/templates/.agents/skills/review-code/reference/report-template.zh-CN.md

@@ -21,8 +21,10 @@
 - **审查者**：{reviewer-name}
 - **审查时间**：{timestamp}
 - **审查范围**：{file-count and major modules}
-- **审查基线提交**：{本轮一次性捕获的审查提交 R 原文；必须等于本轮 HEAD}
-- **审查差异基线**：{用于完整 diff/fingerprint 的 D 原文；已绑定 PR 时为 R 与 PR base SHA 的 merge-base，否则为 R}
+- **审查目标提交**：{本轮一次性从任务绑定 remote/base 读取的目标分支 SHA M；不可被后续实时目标覆盖}
+- **审查已检视提交**：{本轮一次性捕获的本地 HEAD R；必须等于本轮 HEAD}
+- **审查基线提交**：{R 的兼容显示字段；必须与审查已检视提交相同}
+- **审查差异基线**：{用于完整 diff/fingerprint 的 D；必须等于 merge-base(R, saved M)}
 - **审查差异指纹**：{git-workflow snapshot 输出的 fingerprint 字段}
 - **审查快照树**：{git-workflow snapshot 输出的 tree 字段}
 - **总体结论**：{通过 / 需要修改 / 拒绝}（恰取一个；禁止写组合短语，否则 verify gate 失败）

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

@@ -9,13 +9,14 @@ 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`.
 
 ## Boundary / Critical Rules
 
 - This skill only reviews plan artifacts and writes a report; it does not modify product code.
+- Before generating task or lifecycle Markdown that will be synchronized to an Issue, read `.agents/rules/sync-content-generation.md` and apply its producer-side constraints; the sync path does not parse or rewrite the body
 - After executing this skill, you **must** immediately update task.md.
 
 Version stamp rule: when creating or updating `task.md` frontmatter, read `.agents/rules/version-stamp.md` first and write or refresh `agent_infra_version`.
@@ -38,7 +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
 
@@ -69,7 +70,7 @@ Create `.agents/workspace/active/{task-id}/{review-artifact}`.
 
 ### 6. Update Task Status
 
-After the report, submit each new finding with `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}`; submit prior-response dispositions with `finding-review --id {ledger-id} --status {confirmed|closed|open|needs-human-decision} --evidence {evidence}`. Do not scan ids or edit ledger rows. After all ledger writes, call `agent-infra-internal task-review {task-id} finalize-summary --stage plan --artifact {review-artifact} {execution-flag}` exactly once.
+After the report, submit each new finding with `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}`; submit prior-response dispositions with `finding-review --id {ledger-id} --status {confirmed|closed|open|needs-human-decision} --evidence {evidence}`. Do not scan ids or edit ledger rows. After all ledger writes, make the initial call to `agent-infra-internal task-review {task-id} finalize-summary --stage plan --artifact {review-artifact} {execution-flag}`; after a failure, follow `.agents/rules/local-artifact-repair.md` to decide whether to edit and rerun, and never treat an error type or `changed=false` as automatic authorization.
 
 Bind and reuse this structured mapping from that one response:
 
@@ -79,13 +80,13 @@ 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. If finalization fails or a response field is missing, stop before the completion event. Derive the verdict and next-step branch from the same response's `stageStatus.canAdvance`: only `canAdvance=true` permits `approved`; otherwise use `changes-requested` or `rejected`. Then run `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}`.
+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.
 
 If task.md has a valid `issue_number`, run `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}`, then `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {review-artifact} --agent {standard-agent-token}`.
 
-Before writing the summary, the finalization intent checks decision-detail ids; it auto-removes a duplicate only when exactly one formal `[needs-human-decision]` block remains and every other same-id block is clearly short and informal, then reruns the read-only check. Ambiguous duplicates fail closed. If this check or repair fails, stop before the completion event.
+Before writing the summary, the finalization intent checks decision-detail ids; any visible duplicate returns a structured failure and preserves the artifact bytes, while the model decides whether a minimal edit is safe under the shared rule. If the safety gates fail, diagnostics repeat, no byte-level progress occurs, or the emergency cap is reached, stop before the completion event; the stop path must still show the existing review result instead of hiding the artifact.
 
 ### 7. Run Completion Gate
 

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

@@ -9,13 +9,14 @@ 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`。
 
 ## 行为边界 / 关键规则
 
 - 本技能只审查方案产物并写报告，不修改业务代码
+- 生成会同步到 Issue 的任务或生命周期 Markdown 前，先读取 `.agents/rules/sync-content-generation.md` 并遵循其中的生成端约束；同步端不解析或改写正文
 - 执行本技能后，你**必须**立即更新 task.md
 
 版本戳规则：创建或更新 `task.md` frontmatter 时，先读取 `.agents/rules/version-stamp.md`，并写入或刷新 `agent_infra_version`。
@@ -40,7 +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
@@ -72,7 +73,7 @@ agent-infra-internal task-snapshot {task-id} --format text
 
 ### 6. 更新任务状态
 
-报告完成后，新 finding 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}`；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只调用一次 `agent-infra-internal task-review {task-id} finalize-summary --stage plan --artifact {review-artifact} {execution-flag}`。
+报告完成后，新 finding 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}`；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首次调用 `agent-infra-internal task-review {task-id} finalize-summary --stage plan --artifact {review-artifact} {execution-flag}`；失败后是否继续编辑并重跑，必须遵循 `.agents/rules/local-artifact-repair.md`，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：
 
@@ -82,13 +83,13 @@ 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。最终化失败或返回字段缺失时，停止在完成事件之前。以同一次返回的 `stageStatus.canAdvance` 决定 verdict 和下一步：仅 `canAdvance=true` 可用 `approved`，否则必须用 `changes-requested` 或 `rejected`。随后执行 `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}`。
+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。
 
 如果 task.md 中存在有效的 `issue_number`，调用 `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}`，再调用 `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {review-artifact} --agent {standard-agent-token}`；失败按 `.agents/rules/issue-sync.md` 记录 warning。
 
-最终化 intent 会在写入摘要前检查详情块 ID；只有“一个正式 `[needs-human-decision]` 块 + 明确的简短非正式重复块”才会自动删除重复块并重新做只读检查，无法唯一判断时失败关闭。该检查或自动修复失败时，停止在完成事件之前。
+最终化 intent 会在写入摘要前检查详情块 ID；任何可见重复都返回结构化失败并保持 artifact 字节不变，由模型按共享规则判断是否进行最小编辑。无法通过安全门、诊断重复、没有实际字节变化或达到紧急熔断时，停止在完成事件之前；停止路径仍必须展示已有审查结果，不得吞掉 artifact 内容。
 
 ### 7. 完成校验
 

package/templates/.agents/skills/review-plan/reference/output-templates.en.md

@@ -18,6 +18,24 @@ Rules:
 - The selected scenario must generate `{next-step-commands}` through the shared helper
 - The count line shows 4 numbers. `Human-decision` (`{h}`) counts this stage's `needs-human-decision` rows; because those rows are unresolved, `{h} > 0` means `canAdvance=false`. Expand the "Pending human-decision pre-block" from `.agents/rules/next-step-output.md` and show revision and re-review paths only.
 
+### Scenario R: Finalization stopped with results visible
+
+When the finalizer fails, or the model stops because of a safety gate, lack of progress, repeated diagnostics, or the emergency cap, use this scenario. Do not call the shared helper or output cross-stage commands.
+
+```text
+Task {task-id} review results were generated, but lifecycle advancement stopped.
+- Review artifact: .agents/workspace/active/{task-id}/{review-artifact}
+- Last valid summary/findings: {last-readable-review-result}
+- Local repair attempts: {repairAttempts}
+- Last diagnostic: {last-structured-diagnostic}
+- Stop reason: {stop-reason}
+- Completion event: not published | Cross-stage commands: not generated
+
+Note: only lifecycle advancement stopped; the existing review result remains available. Handle it manually or rerun the current review skill.
+```
+
+If the summary cannot be parsed safely, set `{last-readable-review-result}` to "summary could not be parsed safely" and retain the artifact path and raw structured diagnostic; do not infer counts or add a conclusion.
+
 ### Scenario A: Approved with no findings
 
 Populate `{next-step-commands}` for this scenario by running `agent-infra-internal agent-client next-steps --skill code-task --task-ref {task-ref}`.

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

@@ -18,6 +18,24 @@
 - 所选场景必须通过统一 helper 生成 `{next-step-commands}`
 - 计数行固定显示 4 个数字。`人工裁决`（`{h}`）是本阶段 `needs-human-decision` 行数；它属于未闭环账本状态，因此 `{h} > 0` 时 `canAdvance=false`，必须按 `.agents/rules/next-step-output.md` 的「人工裁决待办前置块」展开详情，并只输出修订与复审路径。
 
+### 场景 R：最终化停止但结果可见
+
+当 finalizer 失败，或模型因安全门、无进展、重复诊断或紧急熔断停止时，使用本场景，不调用统一 helper，也不输出跨阶段命令。
+
+```text
+任务 {task-id} 审查结果已生成，但生命周期未推进。
+- 审查产物：.agents/workspace/active/{task-id}/{review-artifact}
+- 最后有效 summary/findings：{last-readable-review-result}
+- 本地修复次数：{repairAttempts}
+- 最后诊断：{last-structured-diagnostic}
+- 停止原因：{stop-reason}
+- 完成事件：未发布 | 跨阶段命令：未生成
+
+说明：本次仅停止生命周期推进，已有审查结果仍可查看。请先进行人工处理，或重新运行当前审查技能。
+```
+
+如果 summary 无法安全解析，`{last-readable-review-result}` 必须改为“摘要不可安全解析”，并保留 artifact 路径和原始结构化诊断；不得推算计数或补写结论。
+
 ### 场景 A：通过且无问题
 
 使用 `agent-infra-internal agent-client next-steps --skill code-task --task-ref {task-ref}` 生成本场景的 `{next-step-commands}`。

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

@@ -16,6 +16,7 @@ Based on the target PR's lifecycle-evidence completeness and change risk, select
 - `pr-review*` is an independent artifact family: it does not join the analysis/plan/code stage chain and never changes `current_step`
 - Only a formal PR Review (head SHA, conclusion, findings, receipt, Issue artifact link) is published on the PR; no second full process copy goes to a regular PR comment
 - The full process copy and the reversible `task.md` mirror are synced only to the linked Issue; `restore-task` keeps its Issue-only contract
+- Before generating artifact Markdown that will be synced to an Issue, read `.agents/rules/sync-content-generation.md` and follow its generator-side constraints; Issue sync remains transparent and does not parse or rewrite the body
 - Never backfill or fabricate `analysis`/`plan`/`code` lifecycle history for an external PR
 - The head SHA is recorded only in `pr-review*` and the formal PR Review; on head drift you must start a new round and never reuse an old conclusion
 - Review depth is driven by evidence completeness and change risk, never by the submitter's identity

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

@@ -16,6 +16,7 @@ description: >
 - `pr-review*` 是独立 artifact family：不接入 analysis/plan/code 阶段依赖链，不修改 `current_step`
 - PR 上只发布正式 PR Review（head SHA、结论、finding、receipt、Issue artifact 链接），不发第二份完整过程原文到 PR 普通评论
 - 完整过程原文与 `task.md` 的可逆镜像只在关联 Issue 上同步；`restore-task` 保持 Issue-only 契约
+- 生成会同步到 Issue 的 artifact Markdown 前，先读取 `.agents/rules/sync-content-generation.md` 并遵循其中的生成端约束；Issue 同步保持透明，不解析或改写正文
 - 不得为外部 PR 倒填或伪造已发生的 `analysis`/`plan`/`code` 生命周期历史
 - head SHA 唯一记录于 `pr-review*` 与正式 PR Review；head 漂移必须进入新轮次，不得沿用旧结论
 - 审查深度由证据完整度和变更风险决定，不由提交者身份决定

package/templates/.agents/skills/review-pr/reference/evidence-grading.en.md

@@ -17,7 +17,7 @@ Evidence scenario classification (S1/S2/S3) → freshness/alignment → risk gra
 
 - Exactly one hit → `unique`; multiple without a unique winner → `ambiguous` (candidate list); zero hits → `none`.
 - Ambiguous hosts fail closed and never enter evidence classification. `pr-review-grade resolve-host --pr <N>` returns a typed `HostResolution`, and `decide` explicitly rejects `ambiguous`.
-- `Closes/Fixes #N` in the PR body (case-insensitive, comma/space separated, lists supported) is parsed by `extractClosingIssueNumbers`; a local `active/*/task.md` `pr_number` hit takes priority over the `issue_number` reverse lookup, and a task hit via both paths deduplicates to a single candidate.
+- `Closes/Fixes #N` in the PR body (case-insensitive, comma/space separated, lists supported) is parsed by `extractClosingIssueNumbers`; a local `active/*/task.md` verified `pr_delivery_fact.identity.number` hit takes priority over the `issue_number` reverse lookup, and a task hit via both paths deduplicates to a single candidate.
 
 ## Evidence Scenario Classification (S1 → S2 → S3)
 
@@ -33,7 +33,7 @@ Evidence scenario classification (S1/S2/S3) → freshness/alignment → risk gra
 ## Freshness and Alignment
 
 - Freshness benchmark = the reviewed head SHA recorded by the latest `pr-review*`, compared character-for-character with the current head: match → `fresh`, otherwise → `stale`.
-- Alignment = freshness is `fresh` and the `issue_number` / `pr_number` match the resolution result.
+- Alignment = freshness is `fresh` and the `issue_number` / verified `pr_delivery_fact.identity.number` match the resolution result.
 - No prior `pr-review*` → `n/a` / `n/a` (first-review special case).
 
 ## Risk Grading (pure evidence)

package/templates/.agents/skills/review-pr/reference/evidence-grading.zh-CN.md

@@ -17,7 +17,7 @@
 
 - 唯一命中 → `unique`；多个且无法唯一 → `ambiguous`（候选列表）；零命中 → `none`。
 - 多宿主歧义即 fail closed：不进入证据分类；由 `pr-review-grade resolve-host --pr <N>` 返回 typed `HostResolution`，`decide` 对 `ambiguous` 显式拒绝。
-- PR body 的 `Closes/Fixes #N`（大小写不敏感、逗号/空格分隔、支持列表）经 `extractClosingIssueNumbers` 解析；本地 `active/*/task.md` 的 `pr_number` 命中优先于 `issue_number` 反查，同一任务经两条路径命中按单候选去重。
+- PR body 的 `Closes/Fixes #N`（大小写不敏感、逗号/空格分隔、支持列表）经 `extractClosingIssueNumbers` 解析；本地 `active/*/task.md` 的 verified `pr_delivery_fact.identity.number` 命中优先于 `issue_number` 反查，同一任务经两条路径命中按单候选去重。
 
 ## 证据场景分类（S1 → S2 → S3）
 
@@ -33,7 +33,7 @@
 ## 新鲜度与对齐
 
 - 新鲜度基准 = 上一轮 `pr-review*` 记录的被审 head SHA，与当前 head 逐字符比对：一致 → `fresh`，否则 → `stale`。
-- 对齐 = freshness 为 fresh 且 `issue_number` / `pr_number` 与解析结果一致。
+- 对齐 = freshness 为 fresh 且 `issue_number` / verified `pr_delivery_fact.identity.number` 与解析结果一致。
 - 无先前 `pr-review*` → `n/a` / `n/a`（首轮特例）。
 
 ## 风险分级（纯证据口径）

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.
@@ -18,6 +20,7 @@ The entry point may omit the task ref; explicit task scope accepts only `--task
 - `complete-manual-validation` remains the maintainer's final registration after coverage is judged sufficient.
 - Never manipulate temporary worktrees, leases, or containers directly; only call `agent-infra-internal task-validate`.
 - Never record tokens, environment variables, full argv, absolute user paths, or raw transcripts in the artifact.
+- Before generating a validation artifact Markdown file that will be synced to an Issue, read `.agents/rules/sync-content-generation.md` and follow its generator-side constraints; Issue sync remains transparent and does not parse or rewrite the body.
 
 ## Step 0: State Check (pre-execution hard gate)
 
@@ -31,10 +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。
@@ -18,6 +20,7 @@ description: >
 - `complete-manual-validation` 仍是维护者确认覆盖充分后的最终登记入口。
 - 禁止直接操作临时 worktree、lease 或 container；只调用 `agent-infra-internal task-validate`。
 - 产物不得记录 token、环境变量、完整 argv、绝对用户路径或原始 transcript。
+- 生成会同步到 Issue 的验证 artifact Markdown 前，先读取 `.agents/rules/sync-content-generation.md` 并遵循其中的生成端约束；Issue 同步保持透明，不解析或改写正文。
 
 ## 第 0 步：状态核对（执行前硬约束）
 
@@ -31,10 +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/run-task/SKILL.en.md

@@ -18,7 +18,7 @@ The orchestrator delegates only and never executes a stage skill itself. First r
 3. Run `task-orchestration {task-id} begin-or-resume --client {client}` with the complete explicit policy. With no explicit policy, core reads that client's configured policy; existing runs use persisted policy. Disk state outside the complete current structure fails closed without rewriting; finish or clear active runs before upgrading. Stop on paused/completed results.
 4. Run `route`. On `completed`, run `agent-infra-internal task-verify {task-id} run-task.completed --format text` and stop. Only a `running` result with non-null `next` supplies action, role, round, artifact, requested model, and requested effort.
 5. Codex runs `codex-lifecycle capability-arm --task-id {task-id}` once. The current loop's real PostToolUse must attest that ordinary tool response. Pass its marker token, the exact routed model, and the exact routed reasoning effort to `prepare --client {client} --requested-model {requestedModel} --requested-reasoning-effort {requestedReasoningEffort} --capability-token {token}`. Core first validates the exact routed model/effort, capability provenance, and controller binding, then captures a read-only snapshot, builds an in-memory prepared receipt, atomically consumes the token, and saves the prepared state with the capability session, turn, and tool-use origin. Activation then verifies that spawn belongs to the same session and turn and uses a distinct tool-use. Other clients use the same prepare without a token. Failure creates no baseline, receipt, or child.
-6. After prepare, run `task-orchestration <task-ref> dispatch` immediately before calling the fresh native child, then use route's exact model/effort and only the short task ref, skill, `--orchestrated`, and stage identity. The trusted hook-spawn first-observation time must fall between dispatch and the deadline. Its first provenance-sensitive command must be `await-activation --stage ... --round ... --artifact ... --role ...`; before `running`, it must not snapshot, emit stage-started, write business files, or start commit. Only explicit `recover-prepared` may clear an expired orphan when the task fingerprint is exact and no matching unconsumed active lifecycle evidence remains.
+6. After prepare, run `task-orchestration <task-ref> dispatch` immediately before calling the fresh native child, then use route's exact model/effort and only the short task ref, skill, `--orchestrated`, and stage identity. The trusted hook-spawn first-observation time must fall between dispatch and the deadline. Its first provenance-sensitive command must be `await-activation --stage ... --round ... --artifact ... --role ...`; before `running`, it must not snapshot, emit stage-started, or write business files. The code stage may create a local checkpoint only through code-task's durable intent core; it must not delegate a separate commit stage or push. Only explicit `recover-prepared` may clear an expired orphan when the task fingerprint is exact and no matching unconsumed active lifecycle evidence remains.
 7. Codex uses SubagentStart/Stop and App Server actual evidence to activate, consume, and seal one receipt; trusted parent fallback must produce the same complete provenance. Timed-out waits do nothing. Advance only a sealed receipt and repeat step 4 only while running.
 8. Create a fresh child each round and never follow up with an old reviewer. Each requested/actual mismatch needs its own host fallback reason. Protocol, capability, receipt hook/evidence binding, source, controller, identity, ledger, or fingerprint failure pauses and fails closed; cross-root package/build/contract or hook/profile content drift is delivered as a warning instead of blocking natural evolution.
 9. On pause or completion, run the matching typed verification and report the structured endpoint.

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

@@ -18,7 +18,7 @@ description: >
 3. 调用 `agent-infra-internal task-orchestration {task-id} begin-or-resume --client {client}` 并转发完整显式策略。完全没有显式策略时由核心读取当前 client 的 `agentClients[].orchestration`；existing run 使用持久化策略。磁盘状态不符合当前完整结构时核心失败关闭且不改写；升级前必须完成或清空 active run。仅当核心返回 `ORCHESTRATION_MODEL_POLICY_REQUIRED` 时，先用 `agent-client model-selection` 展示 complete/partial/interactive-only 来源，再一次收集完整策略；未回答则不创建 run。若为 paused/completed，按结构化结果停止。
 4. 调用 `route` 并读取结构化结果。若返回 `completed`，立即运行 `agent-infra-internal task-verify {task-id} run-task.completed --format text` 并停止；仅当返回 `running` 且 `next` 非空时读取唯一 action、role、round、artifact、`requestedModel` 和 `requestedReasoningEffort`，不得自行推断。
 5. Codex 先调用一次 `agent-infra-internal codex-lifecycle capability-arm --task-id {task-id}`。该普通工具调用必须由当前 loop 的真实 PostToolUse 回写 attestation；把 route 返回的精确 model、effort 和 marker 中 token 一并传给 `prepare --client {client} --requested-model {requestedModel} --requested-reasoning-effort {requestedReasoningEffort} --capability-token {token}`。核心先校验精确的 model/effort、capability provenance 与 controller binding，再只读捕获快照、构造内存中的 prepared receipt，最后原子消费 token 并保存 prepared 状态，同时持久化 capability 的 session、turn、tool-use 来源。activation 再校验 spawn 与该来源属于同一 session/turn，且 spawn 使用独立的 tool-use。其他客户端直接调用同一 prepare（无 token）。任一失败不得创建 baseline、receipt 或 child。
-6. prepare 成功后，在调用 fresh 原生子 Agent 的紧邻前一步执行 `task-orchestration <task-ref> dispatch`，再显式覆盖 route 返回的 model/effort；只传短任务引用、skill 名、`--orchestrated` 与 stage/round/artifact/role。可信 hook-spawn 首次观察时间必须位于 dispatch 与 deadline 之间。child 的第一条 provenance-sensitive 命令必须是 `await-activation --stage ... --round ... --artifact ... --role ...`；返回 running 前禁止 snapshot、阶段 started、业务写入或 commit。超时由核心暂停；崩溃遗留 prepared receipt 只能在 exact workspace fingerprint、无匹配的未消费 active lifecycle evidence 且 deadline 已过时显式 `recover-prepared`。
+6. prepare 成功后，在调用 fresh 原生子 Agent 的紧邻前一步执行 `task-orchestration <task-ref> dispatch`，再显式覆盖 route 返回的 model/effort；只传短任务引用、skill 名、`--orchestrated` 与 stage/round/artifact/role。可信 hook-spawn 首次观察时间必须位于 dispatch 与 deadline 之间。child 的第一条 provenance-sensitive 命令必须是 `await-activation --stage ... --round ... --artifact ... --role ...`；返回 running 前禁止 snapshot、阶段 started 或业务写入；代码阶段的本地 checkpoint 只能通过 code-task 的持久化 intent 核心完成，禁止单独委派 commit 阶段或推送。超时由核心暂停；崩溃遗留 prepared receipt 只能在 exact workspace fingerprint、无匹配的未消费 active lifecycle evidence 且 deadline 已过时显式 `recover-prepared`。
 7. Codex 用 SubagentStart/Stop 与 App Server actual evidence 激活、消费并封存唯一 receipt；受信 parent fallback 仍必须形成相同的完整 provenance。timed-out wait 无动作；只有 empty turns 或协议 `inProgress` 可等待，malformed、身份/传输错误或异常 terminal 均暂停。子 Agent 返回后只对 sealed receipt 调用 `advance`；只有 `running` 才重复步骤 4。
 8. 每轮创建新 child；禁止 follow-up 复用 reviewer。actual model/effort 与 requested 不同时必须有各自的宿主降级理由。protocol、capability、receipt 内 hook/evidence binding、source、controller、身份、账本或 fingerprint 异常都调用 `pause` 并失败关闭；跨根 package/build/contract 或 hook/profile 内容漂移按 warning 交付，不把自然演进差异当成硬失败。
 9. 完成或暂停后运行对应 typed verification，并把结构化 run 摘要、暂停原因、commit 终点或 clean completion evidence 告知用户。