@fitlab-ai/agent-infra 0.9.12 → 0.9.14

package/templates/.agents/skills/review-analysis/config/verify.zh-CN.json

@@ -17,24 +17,7 @@
     },
     "artifact": {
       "file_pattern": "review-analysis.md|review-analysis-r{N}.md",
-      "required_sections": [
-        "审查摘要",
-        "检视覆盖声明",
-        "需求分析专项覆盖",
-        "追踪矩阵",
-        "问题清单",
-        "非阻塞建议",
-        "人工校验项",
-        "结论与建议",
-        "状态核对",
-        "证据原文",
-        "自我质疑",
-        "审查分歧账本回写"
-      ],
-      "required_patterns": [
-        "^### 审查决定$",
-        "^\\$ "
-      ]
+      "schema": "review-analysis"
     },
     "decision-details": {},
     "review-summary": {

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

@@ -1,5 +1,7 @@
 # Review Report Template
 
+> Before writing this report, use `task-artifact init --family review-analysis` to create the skeleton and preserve every `artifact-section` marker; the skeleton contains no review conclusion.
+
 Use this template when writing `review-analysis.md` or `review-analysis-r{N}.md`.
 
 ## Output Template
@@ -12,11 +14,31 @@ Use this template when writing `review-analysis.md` or `review-analysis-r{N}.md`
 - **Review Input**:
   - `{analysis-artifact}` (the highest-round requirement-analysis artifact actually reviewed, e.g. `analysis-r2.md`; leave blank if it cannot be reliably determined)
 
-## State Check
+## Review Summary
 
-> Paste the raw state-check command output; each command starts with `$ `.
+## Qualification Audit Review
 
-## Review Summary
+> Use `.agents/rules/decision-qualification.md` to review the five tables: constraint dependencies, candidate qualification, classification results, upstream relations, and dependency snapshot.
+
+### Constraint Dependencies
+| constraint_id | constraint_digest | role | evidence |
+| --- | --- | --- | --- |
+
+### Candidate Qualification
+| candidate_id | status | impact | constraint_ids | evidence |
+| --- | --- | --- | --- | --- |
+
+### Classification Results
+| decision_id | classification | evidence |
+| --- | --- | --- |
+
+### Upstream Relations
+| upstream_family | upstream_artifact | upstream_round | upstream_sha256 | relation |
+| --- | --- | --- | --- | --- |
+
+### Dependency Snapshot
+| task_input_digest | non_constraint_input_digest | upstream_artifact_digest |
+| --- | --- | --- |
 
 - **Reviewer**: {reviewer-name}
 - **Review Time**: {timestamp}
@@ -24,7 +46,7 @@ Use this template when writing `review-analysis.md` or `review-analysis-r{N}.md`
 - **Overall Verdict**: {Approved / Changes Requested / Rejected}
 - **Findings (AI-actionable)**: {unresolved-blockers} blockers, {unresolved-major} majors, {unresolved-minor} minors / **Manual validation**: 0
 
-## Review Coverage Declaration
+## Inspection Coverage
 
 | pass_id | scope | evidence | result | gaps_or_assumptions |
 |---------|-------|----------|--------|---------------------|
@@ -34,7 +56,7 @@ Use this template when writing `review-analysis.md` or `review-analysis-r{N}.md`
 |---------|------------------|--------|--------|
 | {registry token} | {trigger or non-trigger evidence} | {yes / no / not-applicable} | {lens result} |
 
-## Requirement Analysis Coverage
+## Requirements Analysis Coverage
 
 | perspective_id | applicability | reviewed_scope | evidence | result_or_gap |
 |----------------|---------------|----------------|----------|---------------|
@@ -92,7 +114,7 @@ Use this template when writing `review-analysis.md` or `review-analysis-r{N}.md`
 **File**: `{file-path}:{line-number}`
 **Suggestion**: {improvement suggestion}
 
-## Non-blocking Advisories
+## Non-blocking Suggestions
 
 > Record only future optimizations that do not affect the current artifact's completeness, correctness, or acceptance. Advisories do not enter the disagreement ledger, finding counts, or verdict.
 
@@ -111,27 +133,42 @@ Use this template when writing `review-analysis.md` or `review-analysis-r{N}.md`
 > If this round has no Manual validation items, keep the section heading and write "None".
 
 
-## Review Disagreement Ledger Writeback
+## Conclusion and Recommendation
 
-> Record the structured intents to submit: use `task-ledger finding-upsert` for new findings and `finding-review` for prior responses. The core allocates `AN-N` and validates transitions; do not edit task.md table rows.
-> Every finding escalated to `needs-human-decision` must include a self-contained detail block per `.agents/rules/human-decision-context.md`, with evidence pointing to that stable anchor.
+### Approval Decision
+- [ ] Approved
+- [ ] Changes Requested
+- [ ] Rejected
+
+### Next Steps
+{recommended next step}
+
+## State Check
 
-## Evidence
+> Record the state-check command, review scope, key result, and uncovered parts; each command starts with `$ `.
+> Follow `.agents/rules/evidence-reporting.md`: record review scope, key result, and uncovered parts; do not paste complete successful stdout.
 
-> Pair each "I verified X" claim with the corresponding raw tool output; the gate only checks that this section exists and at least one `$ ` line is present. Every Blocker must be backed by a reproducible command (rg/grep/sed/nl) and its raw output; a judgment that cannot be reproduced must be downgraded or moved to Self-Doubt.
+## Raw Evidence
+
+> Follow `.agents/rules/evidence-reporting.md`: pair each claim with a `$ ` command and proportionate result summary; Blockers, failures, blocking conditions, or disputes require a reproducible command, exact location, and decisive excerpt; a judgment that cannot be reproduced must be downgraded or moved to Self-Doubt.
 
 - Claim: {verified claim}
 ```text
 $ {command}
-{raw output}
+{result summary or decisive excerpt}
 ```
 
-## Self-Doubt
+## Self-critique
 
 > Explicitly declare conclusions, inferences, and assumptions in this review that were **not directly verified**; downstream can rebut them on this basis. Write "None" if there are none.
 
 - {an unverified conclusion or inference; note why it was not verified and the impact if it is overturned}
 
+## Review Disagreement Ledger Write-back
+
+> Record the structured intents to submit: use `task-ledger finding-upsert` for new findings and `finding-review` for prior responses. The core allocates `AN-N` and validates transitions; do not edit task.md table rows.
+> Every finding escalated to `needs-human-decision` must include a self-contained detail block per `.agents/rules/human-decision-context.md`, with evidence pointing to that stable anchor.
+
 ## Highlights
 
 - {what went well}
@@ -140,14 +177,4 @@ $ {command}
 
 - [ ] Implementation matches the technical plan
 - [ ] No unintended scope expansion
-
-## Conclusion and Recommendation
-
-### Approval Decision
-- [ ] Approved
-- [ ] Changes Requested
-- [ ] Rejected
-
-### Next Steps
-{recommended next step}
 ```

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

@@ -1,5 +1,7 @@
 # 审查报告模板
 
+> 写入本报告前，先用 `task-artifact init --family review-analysis` 创建骨架，并保留每个 `artifact-section` marker；骨架不包含审查结论。
+
 编写 `review-analysis.md` 或 `review-analysis-r{N}.md` 时使用本模板。
 
 ## 输出模板
@@ -12,11 +14,31 @@
 - **审查输入**：
   - `{analysis-artifact}`（本轮实际检视的最高轮需求分析产物，如 `analysis-r2.md`；无法可靠取得则留空）
 
-## 状态核对
+## 审查摘要
 
-> 粘贴状态核对命令原文；每条命令以 `$ ` 开头。
+## 资格审计复核
 
-## 审查摘要
+> 按 `.agents/rules/decision-qualification.md` 复核：约束依赖、候选资格、分类结果、上游关系和依赖快照五张表。
+
+### 约束依赖
+| constraint_id | constraint_digest | role | evidence |
+| --- | --- | --- | --- |
+
+### 候选资格
+| candidate_id | status | impact | constraint_ids | evidence |
+| --- | --- | --- | --- | --- |
+
+### 分类结果
+| decision_id | classification | evidence |
+| --- | --- | --- |
+
+### 上游关系
+| upstream_family | upstream_artifact | upstream_round | upstream_sha256 | relation |
+| --- | --- | --- | --- | --- |
+
+### 依赖快照
+| task_input_digest | non_constraint_input_digest | upstream_artifact_digest |
+| --- | --- | --- |
 
 - **审查者**：{reviewer-name}
 - **审查时间**：{timestamp}
@@ -111,19 +133,29 @@
 > 如本轮无人工校验项，保留段落标题并写「（无）」。
 
 
-## 审查分歧账本回写
+## 结论与建议
 
-> 本段记录将提交的结构化意图：新 finding 用 `task-ledger finding-upsert`，上一轮响应复核用 `finding-review`；由核心分配 `AN-N` 并校验状态机，禁止手写 task.md 表格。
-> 凡升级为 `needs-human-decision` 的 finding，必须按 `.agents/rules/human-decision-context.md` 在本报告中提供自足详情块，并让 evidence 指向该稳定锚点。
+### 审查决定
+- [ ] 通过
+- [ ] 需要修改
+- [ ] 拒绝
+
+### 下一步
+{recommended next step}
+
+## 状态核对
+
+> 记录状态核对命令、审查范围、关键结果和未覆盖部分；每条命令以 `$ ` 开头。
+> 按 `.agents/rules/evidence-reporting.md` 同时记录审查范围、关键结果和未覆盖部分；正常成功不粘贴完整 stdout。
 
 ## 证据原文
 
-> 每条“我验证了 X”断言都要配对对应 tool output 原文；gate 仅校验本段存在和至少一行 `$ `。每条 Blocker 必须配可复现命令（rg/grep/sed/nl）及其原文；无法复现的判断须降级或移入「自我质疑」。
+> 遵循 `.agents/rules/evidence-reporting.md`：每条断言配对 `$ ` 命令和相称结果摘要；Blocker、失败、阻塞或争议必须保留可复现命令、准确位置和决定性摘录；无法复现的判断须降级或移入「自我质疑」。
 
 - 断言：{verified claim}
 ```text
 $ {command}
-{raw output}
+{result summary or decisive excerpt}
 ```
 
 ## 自我质疑
@@ -132,6 +164,11 @@ $ {command}
 
 - {未直接验证的结论或推断；说明为何未验证、若被推翻的影响}
 
+## 审查分歧账本回写
+
+> 本段记录将提交的结构化意图：新 finding 用 `task-ledger finding-upsert`，上一轮响应复核用 `finding-review`；由核心分配 `AN-N` 并校验状态机，禁止手写 task.md 表格。
+> 凡升级为 `needs-human-decision` 的 finding，必须按 `.agents/rules/human-decision-context.md` 在本报告中提供自足详情块，并让 evidence 指向该稳定锚点。
+
 ## 亮点
 
 - {what went well}
@@ -140,14 +177,4 @@ $ {command}
 
 - [ ] 实现与技术方案一致
 - [ ] 没有意外的范围扩张
-
-## 结论与建议
-
-### 审查决定
-- [ ] 通过
-- [ ] 需要修改
-- [ ] 拒绝
-
-### 下一步
-{recommended next step}
 ```

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

@@ -9,12 +9,17 @@ 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
 
+### Persisted Report Evidence
+
+Before generating the review report, read `.agents/rules/evidence-reporting.md`. Normal inspection records the command, scope, structured result, actual conclusion, and uncovered parts; findings, blocking conditions, or disputes retain reproducible locations and decisive excerpts, while identity fields remain exact.
+
+- When reviewing candidate qualification or `HD-N`, read `.agents/rules/decision-qualification.md` and check the five qualification-audit tables, digests, QCR, and upstream relations; do not treat a process label as identity authentication
 - 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
@@ -34,7 +39,7 @@ Version stamp rule: when creating or updating `task.md` frontmatter, read `.agen
 
 After loading workflow / skill / rules instructions, and before any task-state judgment or user-visible conclusion, run the state check first. Reading instruction files does not count as an external-state action or conclusion.
 
-Run these commands and paste the raw output into this round's `## State Check` section:
+Run these commands and record the task/artifact scope, key result, and uncovered parts in this round's `## State Check` section; do not paste complete directory listings or task tails on normal success. Retain decisive raw lines only for failures, blocking conditions, identity mismatches, or disputes:
 
 ```bash
 agent-infra-internal task-snapshot {task-id} --format text
@@ -50,7 +55,7 @@ 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
 
@@ -91,6 +96,14 @@ Complete the code implementation coverage in `reference/report-template.md`. App
 
 ### 5. Write the Review Report
 
+Before writing this round's `{review-artifact}`, create the controlled review skeleton:
+
+```bash
+agent-infra-internal task-artifact {task-id} init --family review-code --artifact {review-artifact} --locale en
+```
+
+The skeleton does not generate a verdict, findings, or counts; complete review content is required before summary finalization. If structural finalization returns one provably safe error, call `task-artifact {task-id} repair --family review-code --artifact {review-artifact} --expected-sha256 {artifact-sha256} --expected-semantic-digest {semantic-digest}`, then rerun the original finalizer.
+
 Create `.agents/workspace/active/{task-id}/{review-artifact}`.
 
 > The report format and severity layout live in `reference/report-template.md`. Read `reference/report-template.md` before writing the review.
@@ -109,10 +122,10 @@ 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

@@ -9,12 +9,17 @@ 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
 
+### 持久化报告证据
+
+生成审查报告时，先读取 `.agents/rules/evidence-reporting.md`。正常检视记录命令、范围、结构化结果、实际结论和未覆盖部分；finding、阻塞或争议保留可复现位置与决定性摘录，身份字段必须精确保留。
+
+- 审查候选资格或 `HD-N` 判断时，先读取 `.agents/rules/decision-qualification.md`，逐项复核产物中的五张资格审计表、digest、QCR 和上游关系；不得把流程标签当作身份认证
 - 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
@@ -34,7 +39,7 @@ description: >
 
 在加载 workflow / skill / rules 指令之后、做任何任务状态判断或用户可见结论之前，必须先执行状态核对。指令类文件读取不算对外动作或结论。
 
-运行以下命令，并把原文粘贴到本轮产物的 `## 状态核对` 段：
+运行以下命令，并在本轮产物的 `## 状态核对` 段记录任务/产物范围、关键结果和未覆盖部分；正常成功不粘贴完整目录清单或 `task.md` 尾部。失败、阻塞、身份不一致或争议时，附决定性原文行：
 
 ```bash
 agent-infra-internal task-snapshot {task-id} --format text
@@ -50,7 +55,7 @@ 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
@@ -90,6 +95,14 @@ agent-infra-internal task-snapshot {task-id} --format text
 
 ### 5. 编写审查报告
 
+在首次写入本轮 `{review-artifact}` 前，先创建受控审查骨架：
+
+```bash
+agent-infra-internal task-artifact {task-id} init --family review-code --artifact {review-artifact}
+```
+
+骨架不生成审查结论、发现或计数；完成审查内容后才能进入 summary finalizer。结构 finalizer 返回可证明的单个错误时，使用其 SHA 和 semantic digest 调用 `task-artifact {task-id} repair --family review-code --artifact {review-artifact} --expected-sha256 {artifact-sha256} --expected-semantic-digest {semantic-digest}`，再重跑原 finalizer。
+
 创建 `.agents/workspace/active/{task-id}/{review-artifact}`。
 
 > 报告格式和严重程度布局见 `reference/report-template.md`。写报告前先读取 `reference/report-template.md`。
@@ -107,10 +120,10 @@ 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-code/config/verify.en.json

@@ -17,29 +17,7 @@
     },
     "artifact": {
       "file_pattern": "review-code.md|review-code-r{N}.md",
-      "required_sections": [
-        "Review Summary",
-        "Review Coverage Declaration",
-        "Code Implementation Coverage",
-        "Traceability Matrix",
-        "Findings",
-        "Non-blocking Advisories",
-        "Manual Validation Items",
-        "Conclusion and Recommendations",
-        "State Check",
-        "Evidence",
-        "Self-Doubt",
-        "Review Disagreement Ledger Writeback"
-      ],
-      "required_patterns": [
-        "^### Approval Decision$",
-        "^\\$ ",
-        "^- \\*\\*Overall Verdict\\*\\*[:：]\\s*(?:通过|需要修改|拒绝|Approved|Changes Requested|Rejected)\\s*$",
-        "^- \\*\\*Review Baseline Commit\\*\\*[:：]\\s*\\S",
-        "^- \\*\\*Reviewed Diff Base\\*\\*[:：]\\s*[0-9a-f]{40,64}\\s*$",
-        "^- \\*\\*Reviewed Diff Fingerprint\\*\\*[:：]\\s*sha256:[0-9a-f]{64}\\s*$",
-        "^- \\*\\*Reviewed Snapshot Tree\\*\\*[:：]\\s*[0-9a-f]{40,64}\\s*$"
-      ]
+      "schema": "review-code"
     },
     "decision-details": {},
     "review-summary": {

package/templates/.agents/skills/review-code/config/verify.zh-CN.json

@@ -17,29 +17,7 @@
     },
     "artifact": {
       "file_pattern": "review-code.md|review-code-r{N}.md",
-      "required_sections": [
-        "审查摘要",
-        "检视覆盖声明",
-        "代码实现专项覆盖",
-        "追踪矩阵",
-        "问题清单",
-        "非阻塞建议",
-        "人工校验项",
-        "结论与建议",
-        "状态核对",
-        "证据原文",
-        "自我质疑",
-        "审查分歧账本回写"
-      ],
-      "required_patterns": [
-        "^### 审查决定$",
-        "^\\$ ",
-        "^- \\*\\*总体结论\\*\\*[:：]\\s*(?:通过|需要修改|拒绝|Approved|Changes Requested|Rejected)\\s*$",
-        "^- \\*\\*审查基线提交\\*\\*[:：]\\s*\\S",
-        "^- \\*\\*审查差异基线\\*\\*[:：]\\s*[0-9a-f]{40,64}\\s*$",
-        "^- \\*\\*审查差异指纹\\*\\*[:：]\\s*sha256:[0-9a-f]{64}\\s*$",
-        "^- \\*\\*审查快照树\\*\\*[:：]\\s*[0-9a-f]{40,64}\\s*$"
-      ]
+      "schema": "review-code"
     },
     "decision-details": {},
     "review-summary": {

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

@@ -1,5 +1,7 @@
 # Review Report Template
 
+> Before writing this report, use `task-artifact init --family review-code` to create the skeleton and preserve every `artifact-section` marker; the skeleton contains no review conclusion.
+
 Use this template when writing `review-code.md` or `review-code-r{N}.md`.
 
 ## Output Template
@@ -12,11 +14,31 @@ Use this template when writing `review-code.md` or `review-code-r{N}.md`.
 - **Review Input**:
   - `{code-artifact}` (the highest-round implementation artifact actually reviewed—plus the highest-round fix artifact if present, e.g. `code-r2.md`; leave blank if it cannot be reliably determined)
 
-## State Check
+## Review Summary
 
-> Paste the raw state-check command output; each command starts with `$ `.
+## Qualification Audit Review
 
-## Review Summary
+> Use `.agents/rules/decision-qualification.md` to review the five tables: constraint dependencies, candidate qualification, classification results, upstream relations, and dependency snapshot.
+
+### Constraint Dependencies
+| constraint_id | constraint_digest | role | evidence |
+| --- | --- | --- | --- |
+
+### Candidate Qualification
+| candidate_id | status | impact | constraint_ids | evidence |
+| --- | --- | --- | --- | --- |
+
+### Classification Results
+| decision_id | classification | evidence |
+| --- | --- | --- |
+
+### Upstream Relations
+| upstream_family | upstream_artifact | upstream_round | upstream_sha256 | relation |
+| --- | --- | --- | --- | --- |
+
+### Dependency Snapshot
+| task_input_digest | non_constraint_input_digest | upstream_artifact_digest |
+| --- | --- | --- |
 
 - **Reviewer**: {reviewer-name}
 - **Review Time**: {timestamp}
@@ -30,7 +52,7 @@ Use this template when writing `review-code.md` or `review-code-r{N}.md`.
 - **Overall Verdict**: {Approved / Changes Requested / Rejected} (pick exactly one; combined phrases will fail the verify gate)
 - **Findings (AI-actionable)**: {unresolved-blockers} blockers, {unresolved-major} majors, {unresolved-minor} minors / **Manual validation**: 0
 
-## Review Coverage Declaration
+## Inspection Coverage
 
 | pass_id | scope | evidence | result | gaps_or_assumptions |
 |---------|-------|----------|--------|---------------------|
@@ -98,7 +120,7 @@ Use this template when writing `review-code.md` or `review-code-r{N}.md`.
 **File**: `{file-path}:{line-number}`
 **Suggestion**: {improvement suggestion}
 
-## Non-blocking Advisories
+## Non-blocking Suggestions
 
 > Record only future optimizations that do not affect the current artifact's completeness, correctness, or acceptance. Advisories do not enter the disagreement ledger, finding counts, or verdict.
 
@@ -117,27 +139,42 @@ Use this template when writing `review-code.md` or `review-code-r{N}.md`.
 > If this round has no Manual validation items, keep the section heading and write "None".
 
 
-## Review Disagreement Ledger Writeback
+## Conclusion and Recommendation
 
-> Record the structured intents to submit: use `task-ledger finding-upsert` for new findings and `finding-review` for prior responses. The core allocates `CD-N` and validates transitions; do not edit task.md table rows.
-> Every finding escalated to `needs-human-decision` must include a self-contained detail block per `.agents/rules/human-decision-context.md`, with evidence pointing to that stable anchor.
+### Approval Decision
+- [ ] Approved
+- [ ] Changes Requested
+- [ ] Rejected
+
+### Next Steps
+{recommended next step}
+
+## State Check
 
-## Evidence
+> Record the state-check command, review scope, key result, and uncovered parts; each command starts with `$ `.
+> Follow `.agents/rules/evidence-reporting.md`: record review scope, key result, and uncovered parts; do not paste complete successful stdout.
 
-> Pair each "I verified X" claim with the corresponding raw tool output; the gate only checks that this section exists and at least one `$ ` line is present. Every Blocker must use reproducible test, call-chain, state-transition, data-flow, specification-conflict, or accurate-location evidence; a judgment that cannot be reproduced must be downgraded or moved to Self-Doubt.
+## Raw Evidence
+
+> Follow `.agents/rules/evidence-reporting.md`: pair each claim with a `$ ` command and proportionate result summary; Blockers, failures, blocking conditions, or disputes require reproducible evidence, exact location, and a decisive excerpt; a judgment that cannot be reproduced must be downgraded or moved to Self-Doubt.
 
 - Claim: {verified claim}
 ```text
 $ {command}
-{raw output}
+{result summary or decisive excerpt}
 ```
 
-## Self-Doubt
+## Self-critique
 
 > Explicitly declare conclusions, inferences, and assumptions in this review that were **not directly verified**; downstream can rebut them on this basis. Write "None" if there are none.
 
 - {an unverified conclusion or inference; note why it was not verified and the impact if it is overturned}
 
+## Review Disagreement Ledger Write-back
+
+> Record the structured intents to submit: use `task-ledger finding-upsert` for new findings and `finding-review` for prior responses. The core allocates `CD-N` and validates transitions; do not edit task.md table rows.
+> Every finding escalated to `needs-human-decision` must include a self-contained detail block per `.agents/rules/human-decision-context.md`, with evidence pointing to that stable anchor.
+
 ## Highlights
 
 - {what went well}
@@ -146,14 +183,4 @@ $ {command}
 
 - [ ] Implementation matches the technical plan
 - [ ] No unintended scope expansion
-
-## Conclusion and Recommendation
-
-### Approval Decision
-- [ ] Approved
-- [ ] Changes Requested
-- [ ] Rejected
-
-### Next Steps
-{recommended next step}
 ```