@fitlab-ai/agent-infra 0.11.6 → 0.11.8

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

@@ -23,7 +23,7 @@ description: >
 
 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
+- 审查候选资格或 `HD-N` 判断时，先读取 `.agents/rules/decision-qualification.md`，逐项复核产物中的三张资格审计决策表、资格快照、digest 和 QCR；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
@@ -66,24 +66,23 @@ agent-infra-internal task-snapshot {task-id} --format text
 
 要求存在：
 - `.agents/workspace/active/{task-id}/task.md`
-- 至少一个实现产物：`code.md` 或 `code-r{N}.md`
+- 可解析的任务分支与 Git 审查目标。实现产物属于可选上下文，不得作为审查资格门槛。
 
 ### 2. 解析审查上下文
 
-运行 `agent-infra-internal task-artifact {task-id} inspect --family review-code`。仅当结果为 `ready` 时继续。若 `selection.disposition` 为 `reuse`，复用 `selection.artifact`，不得执行 started、init 或写入新产物，并直接进入完成校验与下一步提示。其他状态从 `inputs` 取得最新 `{code-artifact}`，从 `next.round` / `next.name` 取得 `{review-round}` / `{review-artifact}`；不得自行扫描轮次或拼装文件名。随后执行 started 事件并复核返回身份。
+运行 `agent-infra-internal task-artifact {task-id} inspect --family review-code`。仅当结果为 `ready` 时继续。若 `selection.disposition` 为 `reuse`，复用 `selection.artifact`，不得执行 started、init 或写入新产物，并直接进入完成校验与下一步提示。其他状态从 `inputs` 读取可用的最新 `{code-artifact}` 和 `{plan-artifact}`，从 `next.round` / `next.name` 取得 `{review-round}` / `{review-artifact}`；不得自行扫描轮次或拼装文件名。若没有 code 或 plan artifact，直接审查 Git 差异，并在报告中说明缺少的上下文。随后执行 started 事件并复核返回身份。
 
 ### 3. 阅读实现与修复上下文
 
-读取步骤 2 返回的最新 `{code-artifact}`。读取后，把本轮实际检视的 code artifact 按文件名回填到报告 `审查输入` 段；无法可靠取得时留空，不要伪造。
+读取步骤 2 返回的可用 code 与 plan 上下文。把实际读取的 artifact 文件名写入报告 `审查输入` 段；未提供的 artifact 说明为缺失，不要伪造。实现产物缺失时，仍以 Git 审查差异作为审查对象。
 
 ### 4. 执行审查
 
-遵循 `.agents/workflows/feature-development.yaml`，并同时检查完整变更上下文：
+遵循 `.agents/workflows/feature-development.yaml`，并同时检查完整变更上下文。HD-1 已裁定受审范围内的改动必须先提交：在声明 started 前检查 post-review 路径；存在已跟踪或未跟踪改动时停止并提示先提交，不创建审查报告。报告身份必须绑定干净工作树的确切 HEAD commit：
 - 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 M、R、D、F、T 全部写入报告
+- `git diff --binary "$D" "$R" -- <post-review-globs>` 覆盖 `D` 到 `R` 的已提交跟踪变更；未提交或未跟踪的受审路径按 HD-1 先提交后再开始审查
+- 把 `mode=worktree`、`baseline=R`、`diffBase=D` 写入临时 JSON，调用 `agent-infra-internal git-workflow snapshot --input {file}` 一次生成已提交范围的审查差异指纹 `F` 与快照树 `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`。
@@ -127,7 +126,7 @@ agent-infra-internal task-artifact {task-id} init --family review-code --artifac
 
   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
+- Approved 出口按 `reference/output-templates.md` 选择唯一场景，并使用对应的 `agent-client next-steps` helper 生成下一步命令。
 - 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。
@@ -153,13 +152,13 @@ agent-infra-internal task-verify {task-id} review-code.completed --artifact {rev
 - 退出码 1（校验失败）-> 根据输出修复问题后重新运行校验
 - 退出码 2（网络中断）-> 停止执行并告知用户需要人工介入
 
-将校验输出保留在回复中作为当次验证输出。没有当次校验输出，不得声明完成。
+按 `.agents/rules/validation-output.md` 展示当次校验摘要；没有当次校验输出，不得声明完成。
 
 ### 8. 告知用户
 
 > 仅在校验通过后执行本步骤。
 
-> **重要：分支名 ≠ 字段值**。以下 4 个标签是用户输出模板的分类（场景 A/B/C/D），**不是**产物 `**总体结论**：` 字段的取值。产物字段只取 3 个规范值之一（`通过` / `需要修改` / `拒绝`，或 EN 对应 `Approved` / `Changes Requested` / `Rejected`）；写成 `通过但有问题`、`通过 / 需要修改` 等组合短语会被 verify gate 拦下。
+> **重要：场景名 ≠ 字段值**。以下 A/B/C 是结果输出场景，R 只展示生命周期停止时已有的结果；它们都不是产物 `**总体结论**：` 字段的取值。产物字段只取 3 个规范值之一（`通过` / `需要修改` / `拒绝`，或 EN 对应 `Approved` / `Changes Requested` / `Rejected`）。
 
 必须先判断结果，再只选择一个输出分支：
 - `stageStatus.canAdvance=true` -> 通过
@@ -168,7 +167,7 @@ agent-infra-internal task-verify {task-id} review-code.completed --artifact {rev
 
 manual-validation 的数量不参与分支选择，只作为人工校验计数显示。
 
-> 完整的 4 分支输出模板、判断规则和禁止条款见 `reference/output-templates.md`。向用户汇报审查结论前先读取 `reference/output-templates.md`。
+> 完整的 A/B/C 输出模板、判断规则和禁止条款见 `reference/output-templates.md`。向用户汇报审查结论前先读取 `reference/output-templates.md`。
 
 > 渲染最终输出前先读取 `.agents/rules/next-step-output.md` 并落实其两类规则：(1) 「下一步」命令的 `{task-ref}` 渲染为当前任务短号 `NN`（取值与回退见该文件），其他 `{task-id}` 占位（报告标题、路径）保持完整 TASK-id 形式；(2) 在面向用户输出的绝对最后一行追加 `Completed at` 收尾行（成功、错误、早退等任何面向用户输出都适用，不限于校验通过的成功态）。
 

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

@@ -24,9 +24,7 @@
       "stage": "code"
     },
     "review-fact": {},
-    "activity-log": {
-      "expected_action_pattern": "(Review Code|Code Review) \\(Round \\d+\\)"
-    },
+    "activity-log": {},
     "platform-sync": {
       "when": "platform_issue_identity_exists"
     }

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

@@ -24,9 +24,7 @@
       "stage": "code"
     },
     "review-fact": {},
-    "activity-log": {
-      "expected_action_pattern": "(Review Code|Code Review) \\(Round \\d+\\)"
-    },
+    "activity-log": {},
     "platform-sync": {
       "when": "platform_issue_identity_exists"
     }

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

@@ -2,21 +2,20 @@
 
 Read this file before presenting the final review result to the user.
 
-> This file describes the four **user reply** categories (Branches A/B/C/D) used in the "Inform User" step. It is **not** the value of the review-code artifact's `**Overall Verdict**:` field — that field is fixed to one of three canonical tokens (`Approved` / `Changes Requested` / `Rejected`, or zh-CN `通过` / `需要修改` / `拒绝`). Do not mix the two.
+> This file describes three result scenarios (A/B/C) used in the "Inform User" step. Scenario R displays existing results when lifecycle finalization stops; it is not a verdict category. The review-code artifact's `**Overall Verdict**:` field remains one of three canonical tokens (`Approved` / `Changes Requested` / `Rejected`, or zh-CN `通过` / `需要修改` / `拒绝`).
 
 ## Choose Exactly One Output Branch
 
 Select from `stage-status` (**manual-validation and advisory counts do not participate**):
 1. if `stageStatus.canAdvance=true`, use Branch A
-2. if `stageStatus.canAdvance=false` and there are no blockers, use Branch B
-3. if `Blocker > 0` and the work can be repaired in a focused refinement pass, use Branch C
-4. if the task requires major redesign, broad reimplementation, or a restart, use Branch D
+2. if the verdict is changes requested and findings can be addressed locally, use Branch B regardless of blocker count
+3. if the task requires major redesign, broad reimplementation, or a restart, use Branch C
 
 Prohibitions:
 - never skip the branch-selection step
 - never mix text from different branches
 - if `Blocker > 0`, never output an approval template
-- never count manual-validation findings as blockers / major issues / minor issues, and never use them to trigger Branch B/C/D
+- never count manual-validation findings as blockers / major issues / minor issues, and never use them to trigger Branch B/C
 - 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.
 
@@ -40,13 +39,12 @@ If the summary cannot be parsed safely, set `{last-readable-review-result}` to "
 
 ### 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` / verified `pr_delivery_fact`; 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. 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).
-- Existing PR with PR head != `R`: Branch A1 (commit/push).
-- PR head = `R` with `pending|failed|cancelled` checks or temporarily unavailable platform state: Branch A3 (watch); never show completion.
-- PR head = `R` with `passed|no-required` checks: Branch A4 (complete).
+- No PR: use Branch A3 (complete) when `prFlow=disabled`; otherwise use Branch A1 (create PR).
+- Existing PR with PR head != `R`: Branch A1 (create or update the PR).
+- PR head = `R` with `pending|failed|cancelled` checks or temporarily unavailable platform state: Branch A2 (watch); never show completion.
+- PR head = `R` with `passed|no-required` checks: Branch A3 (complete).
 
 Common Branch A summary:
 
@@ -54,21 +52,9 @@ Common Branch A summary:
 Task {task-id} review completed. Verdict: approved.
 - Blockers: 0 | Major: 0 | Minor: 0 | Manual-validation: {e} | Human-decision: {h}
 [- Review report: .agents/workspace/active/{task-id}/{review-artifact}]
-
-[When manual-validation > 0, append this final line:]
-Reminder: manual-validation findings must be carried in the PR description as a "manual verification required" checklist and should not trigger /code-task.
-```
-
-#### Branch A1: Commit or Push
-
-Populate `{next-step-commands}` for this scenario by running `agent-infra-internal agent-client next-steps --skill commit --task-ref {task-ref}`.
-
-```text
-Next step - commit or push the code:
-{next-step-commands}
 ```
 
-#### Branch A2: Create a Pull Request
+#### Branch A1: Create a Pull Request
 
 Populate `{next-step-commands}` for this scenario by running `agent-infra-internal agent-client next-steps --skill create-pr --task-ref {task-ref}`.
 
@@ -77,7 +63,7 @@ Next step - create a Pull Request:
 {next-step-commands}
 ```
 
-#### Branch A3: Watch All Checks
+#### Branch A2: Watch All Checks
 
 Populate `{next-step-commands}` for this scenario by running `agent-infra-internal agent-client next-steps --skill watch-pr --task-ref {task-ref}`.
 
@@ -86,7 +72,7 @@ Next step - watch PR checks:
 {next-step-commands}
 ```
 
-#### Branch A4: Complete and Archive
+#### Branch A3: Complete and Archive
 
 Populate `{next-step-commands}` for this scenario by running `agent-infra-internal agent-client next-steps --skill complete-task --task-ref {task-ref}`.
 
@@ -95,52 +81,43 @@ Next step - complete and archive the task:
 {next-step-commands}
 ```
 
-### Branch B: Changes Requested (Major / Minor)
+### Branch B: Local Fixes Needed
 
-Populate `{next-step-commands}` for this scenario by running `agent-infra-internal agent-client next-steps --skill code-task --task-ref {task-ref}`.
+Use this scenario for findings that can be fixed locally, regardless of blocker count. Fill in `{blockers}`, `{major}`, and `{minor}` with the unresolved counts. When `h > 0`, show the pending human-decision block required by `.agents/rules/next-step-output.md`; after those decisions, generate the re-review command with the `review-code` helper and do not show `code-task`. When `h = 0`, generate the repair command with the `code-task` helper.
+
+When `h = 0`, populate `{next-step-commands}` by running `agent-infra-internal agent-client next-steps --skill code-task --task-ref {task-ref}`:
 
 ```text
 Task {task-id} review completed. Verdict: changes requested.
-- Blockers: 0 | Major: {n} | Minor: {n} | Manual-validation: {e} | Human-decision: {h}
+- Blockers: {blockers} | Major: {major} | Minor: {minor} | Manual-validation: {e} | Human-decision: {h}
 - Review report: .agents/workspace/active/{task-id}/{review-artifact}
 
 Next step - fix the findings:
 {next-step-commands}
 
-[When manual-validation > 0, append this final line:]
-Reminder: manual-validation findings must be carried in the PR description as a "manual verification required" checklist and should not trigger /code-task.
 ```
 
-### Branch C: Changes Requested
+When `h > 0`, run `agent-infra-internal agent-client next-steps --skill review-code --task-ref {task-ref}` to generate `{next-step-commands}` for use after resolving the human decisions; show the required decision block before the command.
 
-Populate `{next-step-commands}` for this scenario by running `agent-infra-internal agent-client next-steps --skill code-task --task-ref {task-ref}`.
+## Manual-validation Reminder
 
-```text
-Task {task-id} review completed. Verdict: changes requested.
-- Blockers: {n} | Major: {n} | Minor: {n} | Manual-validation: {e} | Human-decision: {h}
-- Review report: .agents/workspace/active/{task-id}/{review-artifact}
+For scenarios A/B/C, append this reminder after the selected scenario when `{e} > 0`. Do not use it for scenario R.
 
-Next step - fix the findings:
-{next-step-commands}
-
-[When manual-validation > 0, append this final line:]
+```text
 Reminder: manual-validation findings must be carried in the PR description as a "manual verification required" checklist and should not trigger /code-task.
 ```
 
-### Branch D: Rejected
+### Branch C: Rejected and Re-design
 
 Populate `{next-step-commands}` for this scenario by running `agent-infra-internal agent-client next-steps --skill plan-task --task-ref {task-ref}`.
 
 ```text
 Task {task-id} review completed. Verdict: rejected, re-design the technical plan.
-- Blockers: {n} | Major: {n} | Minor: {n} | Manual-validation: {e} | Human-decision: {h}
+- Blockers: {blockers} | Major: {major} | Minor: {minor} | Manual-validation: {e} | Human-decision: {h}
 - Review report: .agents/workspace/active/{task-id}/{review-artifact}
 
 Next step - re-design the technical plan:
 {next-step-commands}
 
 > Note: Rejected means the implementation direction needs to be reworked end-to-end, not patched locally. Core artifact lifecycle branch #7 refuses a direct `/code-task` and requires a fresh plan first.
-
-[When manual-validation > 0, append this final line:]
-Reminder: manual-validation findings must be carried in the PR description as a "manual verification required" checklist and should not trigger /code-task.
 ```

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

@@ -2,21 +2,20 @@
 
 在向用户汇报最终审查结论之前先读取本文件。
 
-> 本文件描述的是**用户回执文本**的 4 个分类（场景 A/B/C/D），用于「向用户汇报结论」步骤。它**不是** review-code 产物的 `**总体结论**：` 字段值——字段值固定为 3 个规范 token（`通过` / `需要修改` / `拒绝`，或 EN 对应 `Approved` / `Changes Requested` / `Rejected`）。两者不可混用。
+> 本文件描述的是「向用户汇报结论」的 3 个结果场景（A/B/C）。场景 R 只用于生命周期未完成时展示已有结果，不属于审查结论分类。产物的 `**总体结论**：` 字段仍只取 3 个规范值（`通过` / `需要修改` / `拒绝`，或 EN 对应 `Approved` / `Changes Requested` / `Rejected`）。
 
 ## 选择唯一输出场景
 
 按 `stage-status` 结果判断（**注意：manual-validation 和 advisory 数量不参与判断**）：
 1. 如果 `stageStatus.canAdvance=true`，使用场景 A
-2. 如果 `stageStatus.canAdvance=false` 且无 blocker，使用场景 B
-3. 如果 `Blocker > 0`，且问题可以通过一次聚焦修复解决，使用场景 C
-4. 如果任务需要重大重构、大范围重写或整体重来，使用场景 D
+2. 如果结论为需要修改且 findings 可局部修复，使用场景 B（不按 blocker 数量拆分）
+3. 如果任务需要重大重构、大范围重写或整体重来，使用场景 C
 
 禁止规则：
 - 不要跳过场景判断步骤
 - 不要混用不同场景的文案
 - 只要 `Blocker > 0`，就绝对不能输出通过模板
-- manual-validation 项绝对不能被计入 blocker / major / minor 计数，也不能用作触发场景 B/C/D 的依据
+- manual-validation 项绝对不能被计入 blocker / major / minor 计数，也不能用作触发场景 B/C 的依据
 - 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。
 
@@ -40,13 +39,12 @@
 
 ### 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` / 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：
+通过后不得按轮次路由。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）。
-- 已有 PR 但 PR head != `R`：场景 A1（提交/推送）。
-- PR head = `R`，checks 为 `pending|failed|cancelled` 或平台暂不可用：场景 A3（监控），不得输出完成命令。
-- PR head = `R`，checks 为 `passed|no-required`：场景 A4（完成）。
+- 无 PR：`prFlow=disabled` 用场景 A3（完成）；PR flow 开启时用场景 A1（创建 PR）。
+- 已有 PR 但 PR head != `R`：场景 A1（创建或更新 PR）。
+- PR head = `R`，checks 为 `pending|failed|cancelled` 或平台暂不可用：场景 A2（监控），不得输出完成命令。
+- PR head = `R`，checks 为 `passed|no-required`：场景 A3（完成）。
 
 场景 A 的共同摘要：
 
@@ -55,20 +53,9 @@
 - 阻塞项：0 | 主要问题：0 | 次要问题：0 | 人工校验点：{e} | 人工裁决：{h}
 [- 审查报告：.agents/workspace/active/{task-id}/{review-artifact}]
 
-[当 manual-validation > 0 时，在最后附加一行：]
-提醒：manual-validation 项需在 PR description 的「待人工验证」清单中承接，不应触发 /code-task。
-```
-
-#### 场景 A1：提交或推送
-
-使用 `agent-infra-internal agent-client next-steps --skill commit --task-ref {task-ref}` 生成本场景的 `{next-step-commands}`。
-
-```text
-下一步 - 提交或推送代码：
-{next-step-commands}
 ```
 
-#### 场景 A2：创建 Pull Request
+#### 场景 A1：创建 Pull Request
 
 使用 `agent-infra-internal agent-client next-steps --skill create-pr --task-ref {task-ref}` 生成本场景的 `{next-step-commands}`。
 
@@ -77,7 +64,7 @@
 {next-step-commands}
 ```
 
-#### 场景 A3：监控全部 checks
+#### 场景 A2：监控全部 checks
 
 使用 `agent-infra-internal agent-client next-steps --skill watch-pr --task-ref {task-ref}` 生成本场景的 `{next-step-commands}`。
 
@@ -86,7 +73,7 @@
 {next-step-commands}
 ```
 
-#### 场景 A4：完成并归档
+#### 场景 A3：完成并归档
 
 使用 `agent-infra-internal agent-client next-steps --skill complete-task --task-ref {task-ref}` 生成本场景的 `{next-step-commands}`。
 
@@ -95,45 +82,31 @@
 {next-step-commands}
 ```
 
-### 场景 B：需要修改（major / minor）
+### 场景 B：需要局部修订
 
-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}`。
+无论 findings 中是否包含 blocker，只要可以局部修复或按需修复，都使用同一个场景。阻塞项、主要问题和次要问题分别填写实际未解决计数。若 `h > 0`，遵循 `.agents/rules/next-step-output.md` 展开裁决待办；裁决完成后用 `review-code` helper 重新检视，不输出 `code-task` 命令。若 `h = 0`，使用 `code-task` helper 修复 findings。
 
-```text
-任务 {task-id} 代码审查完成。结论：需要修改。
-- 阻塞项：0 | 主要问题：{n} | 次要问题：{n} | 人工校验点：{e} | 人工裁决：{h}
-- 审查报告：.agents/workspace/active/{task-id}/{review-artifact}
-
-下一步 - 修复问题：
-{next-step-commands}
-
-[当 manual-validation > 0 时，在最后附加一行：]
-提醒：manual-validation 项需在 PR description 的「待人工验证」清单中承接，不应触发 /code-task。
-```
-
-### 场景 C：需要修改
-
-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}`。
+`h = 0` 时运行 `agent-infra-internal agent-client next-steps --skill code-task --task-ref {task-ref}` 生成 `{next-step-commands}`：
 
 ```text
 任务 {task-id} 代码审查完成。结论：需要修改。
-- 阻塞项：{n} | 主要问题：{n} | 次要问题：{n} | 人工校验点：{e} | 人工裁决：{h}
+- 阻塞项：{blockers} | 主要问题：{major} | 次要问题：{minor} | 人工校验点：{e} | 人工裁决：{h}
 - 审查报告：.agents/workspace/active/{task-id}/{review-artifact}
 
 下一步 - 修复问题：
 {next-step-commands}
 
-[当 manual-validation > 0 时，在最后附加一行：]
-提醒：manual-validation 项需在 PR description 的「待人工验证」清单中承接，不应触发 /code-task。
 ```
 
-### 场景 D：拒绝
+`h > 0` 时运行 `agent-infra-internal agent-client next-steps --skill review-code --task-ref {task-ref}` 生成裁决完成后的 `{next-step-commands}`；在命令前展示规则要求的人工裁决待办块。
+
+### 场景 C：拒绝并重新设计
 
 使用 `agent-infra-internal agent-client next-steps --skill plan-task --task-ref {task-ref}` 生成本场景的 `{next-step-commands}`。
 
 ```text
 任务 {task-id} 代码审查完成。结论：拒绝，需要重新设计方案。
-- 阻塞项：{n} | 主要问题：{n} | 次要问题：{n} | 人工校验点：{e} | 人工裁决：{h}
+- 阻塞项：{blockers} | 主要问题：{major} | 次要问题：{minor} | 人工校验点：{e} | 人工裁决：{h}
 - 审查报告：.agents/workspace/active/{task-id}/{review-artifact}
 
 下一步 - 重新设计技术方案：
@@ -141,6 +114,12 @@
 
 > 注意：Rejected 表示实现方向需要整体重做，不是局部修复。核心 artifact lifecycle 的分支 #7 会拒绝直接 `/code-task`，要求先重新方案设计。
 
-[当 manual-validation > 0 时，在最后附加一行：]
+```
+
+## 人工校验提醒
+
+场景 A/B/C 的输出中，如果 `{e} > 0`，在所选场景内容之后附加以下提醒；场景 R 不使用此提醒：
+
+```text
 提醒：manual-validation 项需在 PR description 的「待人工验证」清单中承接，不应触发 /code-task。
 ```

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

@@ -4,7 +4,7 @@
 
 Use this template when writing `review-code.md` or `review-code-r{N}.md`.
 
-> The `Review Input` field provides reader-facing traceability. Lifecycle identity uses the input frozen by `review-code.started` and the completion receipt; it is not parsed from this report body.
+> The `Review Input` field provides reader-facing traceability and may be empty. Review identity is proven by the report's exact HEAD/diff snapshot, a valid `review-code.completed` completion fact, and an Activity Log done row referencing this report. Code and plan artifacts are optional context.
 
 ## Output Template
 
@@ -13,8 +13,9 @@ Use this template when writing `review-code.md` or `review-code-r{N}.md`.
 
 - **Review Round**: Round {review-round}
 - **Artifact File**: `{review-artifact}`
-- **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)
+- **Review Input** (example: `code.md`):
+  - `{code-artifact}` (the highest-round implementation artifact actually read; record “missing” when absent and still review the Git diff)
+  - `{plan-artifact}` (the plan actually read; record “missing” when absent)
 
 ## Review Summary
 
@@ -32,7 +33,7 @@ Use this template when writing `review-code.md` or `review-code-r{N}.md`.
 
 ## Qualification Audit Review
 
-> Use `.agents/rules/decision-qualification.md` to review the five tables: constraint dependencies, candidate qualification, classification results, upstream relations, and dependency snapshot.
+> Include this section only when this stage actually reviews candidate qualification, constraint dependencies, or human-decision eligibility. In that case, review all three decision tables and the qualification snapshot per `.agents/rules/decision-qualification.md`; otherwise omit this section entirely.
 
 ### Constraint Dependencies
 | constraint_id | constraint_digest | role | evidence |
@@ -46,13 +47,9 @@ Use this template when writing `review-code.md` or `review-code-r{N}.md`.
 | 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 |
-| --- | --- | --- |
+### Qualification Snapshot
+| task_input_digest | non_constraint_input_digest |
+| --- | --- |
 
 ## Inspection Coverage
 

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

@@ -4,7 +4,7 @@
 
 编写 `review-code.md` 或 `review-code-r{N}.md` 时使用本模板。
 
-> “审查输入”字段用于读者追溯。生命周期身份以 `review-code.started` 冻结的输入和完成 receipt 为准，不从本报告正文解析。
+> “审查输入”字段用于读者追溯，可为空。审查身份以报告中的确切 HEAD / diff snapshot、有效 `review-code.completed` completion fact 和指向本报告的 Activity Log done 行共同证明；code、plan artifact 仅作可选上下文。
 
 ## 输出模板
 
@@ -13,8 +13,9 @@
 
 - **审查轮次**：第 {review-round} 轮
 - **产物文件**：`{review-artifact}`
-- **审查输入**：
-  - `{code-artifact}`（本轮实际检视的最高轮实现产物——含如存在的最高轮修复产物，如 `code-r2.md`；无法可靠取得则留空）
+- **审查输入**（示例：`code.md`）：
+  - `{code-artifact}`（实际读取的最高轮实现产物；无该产物时写“缺失”，但仍审查 Git 差异）
+  - `{plan-artifact}`（实际读取的方案；无该产物时写“缺失”）
 
 ## 审查摘要
 
@@ -32,7 +33,7 @@
 
 ## 资格审计复核
 
-> 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。
+> 仅当本阶段实际复核了候选资格、约束依赖或人工裁决资格时填写本节，并按 `.agents/rules/decision-qualification.md` 完整复核三张决策表和资格快照；否则删除整个审计段。
 
 ### 约束依赖
 | constraint_id | constraint_digest | role | evidence |
@@ -46,13 +47,9 @@
 | 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 |
-| --- | --- | --- |
+### 资格快照
+| task_input_digest | non_constraint_input_digest |
+| --- | --- |
 
 ## 检视覆盖声明
 

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

@@ -30,13 +30,13 @@ Follow the `code-review` step in `.agents/workflows/feature-development.yaml`.
 
 Read `.agents/rules/review-method.md` first and apply its five-pass protocol, risk lenses, and finding evidence contract. Finding, manual-validation, advisory, and `needs-human-decision` state semantics remain governed by `.agents/rules/review-handshake.md`. This file adds only code-stage criteria.
 
-Also inspect `git diff`, the latest code artifact, latest technical-plan review artifact, and `task.md` Activity Log so the report reflects the full change context.
+Also inspect `git diff`, available implementation and plan-review artifacts, and the `task.md` Activity Log so the report reflects the full change context. If implementation or plan artifacts are missing, record the context gap and continue reviewing the Git diff; their absence must not block review.
 
 ## Five Code-stage Passes
 
 | pass_id | code-stage action |
 |---------|-------------------|
-| pass-1 | Read the complete diff, untracked files, implementation/plan artifacts, task source, and raw test results |
+| pass-1 | Read the complete diff, available implementation/plan artifacts, task source, and raw test results; record missing artifact context and continue with the Git diff |
 | pass-2 | Map acceptance/plan → implementation → verification and record changed lines, call context, state/data flow, and uncovered areas |
 | pass-3 | Review overall design before per-file semantics; evaluate every shared registry trigger and read each matched reference in full |
 | pass-4 | Check guards, call constraints, test coverage, and narrower impact boundaries as counterevidence |

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

@@ -30,13 +30,13 @@
 
 先读取 `.agents/rules/review-method.md`，按其五遍协议、风险镜头和 finding 证据契约执行；finding、manual-validation、advisory 与 `needs-human-decision` 的状态语义以 `.agents/rules/review-handshake.md` 为准。本文件只补充代码实现阶段的专项判断。
 
-同时检查 `git diff`、最新实现产物、最新技术方案审查产物和 `task.md` Activity Log，确保报告反映完整的变更上下文。
+同时检查 `git diff`、可用的实现与方案审查产物和 `task.md` Activity Log，确保报告反映完整的变更上下文。实现或方案产物缺失时记录上下文缺口并继续审查 Git 差异，不得拒绝审查。
 
 ## 代码阶段五遍动作
 
 | pass_id | code-stage action |
 |---------|-------------------|
-| pass-1 | 读取完整 diff、未跟踪文件、实现/方案产物、任务来源和测试原始结果 |
+| pass-1 | 读取完整 diff、可用实现/方案产物、任务来源和测试原始结果；记录缺失的产物上下文并继续审查 Git 差异 |
 | pass-2 | 建立验收/方案—实现—验证映射，并记录 changed lines、调用上下文、状态/数据流和未覆盖区域 |
 | pass-3 | 先检查整体设计，再检查逐文件语义；判断共享注册表的每个触发器并完整加载命中 reference |
 | pass-4 | 检查保护条件、调用约束、测试覆盖和更窄影响范围等反证 |

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

@@ -23,7 +23,7 @@ This stage consumes only the canonical path fact parsed by core from the latest
 
 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
+- When reviewing candidate qualification or `HD-N`, read `.agents/rules/decision-qualification.md` and check the three qualification-audit decision tables, snapshot, digests, and QCR; do not treat a process label as identity authentication
 - 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.
@@ -111,6 +111,8 @@ Before writing the summary, the finalization intent checks decision-detail ids;
 agent-infra-internal task-verify {task-id} review-plan.completed --artifact {review-artifact} --format text
 ```
 
+Present the verification summary per `.agents/rules/validation-output.md`, retaining necessary failure, blocked, and soft-warning diagnostics.
+
 ### 8. Tell the User
 
 Use the conclusion branch in `reference/output-templates.md` and render the selected next-step commands through the shared helper.

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

@@ -23,7 +23,7 @@ description: >
 
 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
+- 审查候选资格或 `HD-N` 判断时，先读取 `.agents/rules/decision-qualification.md`，逐项复核产物中的三张资格审计决策表、资格快照、digest 和 QCR；不得把流程标签当作身份认证
 - 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
@@ -114,6 +114,8 @@ agent-infra-internal task-artifact {task-id} init --family review-plan --artifac
 agent-infra-internal task-verify {task-id} review-plan.completed --artifact {review-artifact} --format text
 ```
 
+按 `.agents/rules/validation-output.md` 展示当次校验摘要；失败、阻塞和软警告保留必要诊断。
+
 校验通过后继续告知用户；校验失败则修复报告或 task 状态后重跑。
 
 ### 8. 告知用户

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

@@ -26,7 +26,7 @@ Use this template when writing `review-plan.md` or `review-plan-r{N}.md`.
 
 ## Qualification Audit Review
 
-> Use `.agents/rules/decision-qualification.md` to review the five tables: constraint dependencies, candidate qualification, classification results, upstream relations, and dependency snapshot.
+> Include this section only when this stage actually reviews candidate qualification, constraint dependencies, or human-decision eligibility. In that case, review all three decision tables and the qualification snapshot per `.agents/rules/decision-qualification.md`; otherwise omit this section entirely.
 
 ### Constraint Dependencies
 | constraint_id | constraint_digest | role | evidence |
@@ -40,13 +40,9 @@ Use this template when writing `review-plan.md` or `review-plan-r{N}.md`.
 | 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 |
-| --- | --- | --- |
+### Qualification Snapshot
+| task_input_digest | non_constraint_input_digest |
+| --- | --- |
 
 ## Inspection Coverage
 
@@ -66,7 +62,7 @@ Use this template when writing `review-plan.md` or `review-plan-r{N}.md`.
 
 > Scenario A (`ordinary`): keep the table above, record `Mini-ATAM: not-applicable` with a reviewable reason, and delete the Scenario B tables.
 >
-> Scenario B (`architecture-significant`): keep the table above and the five tables below, and delete the Scenario A guidance.
+> Scenario B (`architecture-significant`): keep the table above and the architecture assessment tables below, and delete the Scenario A guidance.
 
 | quality_scenario_id | source_id | business_driver | quality_attribute | priority | stimulus | context | expected_response | measure | result_or_gap |
 |---------------------|-----------|-----------------|-------------------|----------|----------|---------|-------------------|---------|---------------|