@fitlab-ai/agent-infra 0.11.6 → 0.11.7

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 |
 |---------------------|-----------|-----------------|-------------------|----------|----------|---------|-------------------|---------|---------------|

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

@@ -26,7 +26,7 @@
 
 ## 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 |
@@ -40,13 +40,9 @@
 | 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
 
@@ -66,7 +62,7 @@
 
 > 场景 A（`ordinary`）：保留上表，记录 `Mini-ATAM: not-applicable` 及可复核理由，并删除场景 B 的表格。
 >
-> 场景 B（`architecture-significant`）：保留上表和以下五张表，并删除场景 A 的说明。
+> 场景 B（`architecture-significant`）：保留上表和以下架构评估表，并删除场景 A 的说明。
 
 | quality_scenario_id | source_id | business_driver | quality_attribute | priority | stimulus | context | expected_response | measure | result_or_gap |
 |---------------------|-----------|-----------------|-------------------|----------|----------|---------|-------------------|---------|---------------|

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

@@ -166,6 +166,8 @@ agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact
   agent-infra-internal task-verify {task-id} review-pr.completed --artifact {pr-review-artifact} --format text
   ```
 
+Present the verification summary per `.agents/rules/validation-output.md`, retaining necessary failure, blocked, and soft-warning diagnostics.
+
 - **One-shot path**:
 
   ```bash

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

@@ -166,6 +166,8 @@ agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact
   agent-infra-internal task-verify {task-id} review-pr.completed --artifact {pr-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。
+
 - **一次性路径**：
 
   ```bash

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

@@ -47,7 +47,7 @@ Branch-only has no `{task-id}`: skip this step and record `not-applicable (branc
 4. Allocate an `{evidence-file}` for each validation target and invoke every executable item separately with `agent-infra-internal task-validate {task-ref} --scope snapshot --format json --evidence-file {evidence-file} -- {command...}`. Only make a second explicit inplace invocation for that item when evidence proves it is required, using its evidence file. 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} --initiator {trigger-initiator} --request-id {request-id} --reason-code {reason-code} --artifact {artifact}`. When an Issue exists, run only `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}`; do not publish the validation artifact as an Issue comment.
-7. Run `agent-infra-internal task-verify {task-id} validation-run.completed --artifact {artifact} --format text`; fix failures and rerun it.
+7. Run `agent-infra-internal task-verify {task-id} validation-run.completed --artifact {artifact} --format text`; fix failures and rerun it, then present the summary per `.agents/rules/validation-output.md` with necessary diagnostics.
 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`.
 
 ## Scenario B: Branch-Only Fallback

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

@@ -47,7 +47,7 @@ branch-only 无 `{task-id}`，跳过本步，并在产物 `## 状态核对` 记
 4. 为每个验证目标分配 `{evidence-file}`，分别调用 `agent-infra-internal task-validate {task-ref} --scope snapshot --format json --evidence-file {evidence-file} -- {command...}`；只有证据表明必须原位时才对该项进行第二次显式 inplace 调用并写入对应 evidence 文件。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} --initiator {trigger-initiator} --request-id {request-id} --reason-code {reason-code} --artifact {artifact}`。存在 Issue 时仅运行 `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}`；验证 artifact 不发布为 Issue 评论。
-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。
+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，并按 `.agents/rules/validation-output.md` 展示摘要和必要诊断。
 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`。
 
 ## 场景 B：branch-only 降级

package/templates/.agents/skills/run-task/SKILL.en.md

@@ -17,7 +17,7 @@ The orchestrator delegates only and never executes a stage skill itself. First r
 2. Use the current host's native child spawn, wait, and result interfaces. Task-bound sandboxes execute ordinary task orchestration locally in the current worktree; Codex controller `open`, `verify`, and `close` remain restricted broker operations. Retain task binding and checks for real external process operations.
 3. Before each loop, run `agent-infra-internal task-lifecycle {task-id} recover-started --agent {client} --auto`. The client adapter owns recovery capability and stop-evidence validation; an unsupported adapter or a run that needs no recovery returns `no-op`. Continue only after `no-op` or `applied`. Stop on every other result; a later operator invocation retries from persisted state without routing or dispatching a child.
 4. 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.
-5. 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. Run `route`. On `completed`, run `agent-infra-internal task-verify {task-id} run-task.completed --format text`, present its summary per `.agents/rules/validation-output.md` while retaining necessary diagnostics, and stop. Only a `running` result with non-null `next` supplies action, role, round, artifact, requested model, and requested effort.
 6. Call `prepare --client {client} --requested-model {requestedModel} --requested-reasoning-effort {requestedReasoningEffort}` with route's exact policy. The client adapter runs host preflight. Report actual task, policy, or host failures.
 7. After prepare, run `task-orchestration <task-ref> dispatch` before spawning a fresh native child with route's model/effort. Pass the short task ref, skill, `--orchestrated`, and stage identity. The child calls `await-activation --stage ... --round ... --artifact ... --role ...` to associate its actual identity before executing. Code-task creates the local checkpoint; do not delegate a separate commit stage or push. Retain existing write locks without introducing a new lock protocol around native spawn.
 8. Record actual start and terminal results through the current host's native lifecycle events and result interfaces. A timed-out wait does not imply success. Pause on actual identity, transport, or terminal failures. After the stage and child finish, call `advance`; repeat step 3 only while running.

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

@@ -17,7 +17,7 @@ description: >
 2. 使用当前宿主的原生子 Agent 启动、等待与结果接口。task-bound sandbox 在当前 worktree 本地执行普通任务编排；Codex controller 的 `open`、`verify`、`close` 继续通过受限 broker 执行。保留任务绑定与真实外部进程操作检查。
 3. 每次进入循环时先调用 `agent-infra-internal task-lifecycle {task-id} recover-started --agent {client} --auto`。客户端适配器负责恢复能力和停止证据校验；没有该能力或无需恢复时返回 `no-op`。仅在结构化结果为 `no-op` 或 `applied` 时继续，其他结果安全停止；下一次人为调用按持久化状态幂等重试，不 route、不派发 child。
 4. 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。
-5. 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. 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；按 `.agents/rules/validation-output.md` 展示摘要并保留必要诊断。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。
 6. 调用 `prepare --client {client} --requested-model {requestedModel} --requested-reasoning-effort {requestedReasoningEffort}`，使用 route 返回的精确策略。客户端适配器执行宿主 preflight；任务身份、策略或宿主检查失败时记录实际诊断。
 7. prepare 成功后，在调用 fresh 原生子 Agent 前执行 `task-orchestration <task-ref> dispatch`，显式指定 route 返回的 model/effort；传递短任务引用、skill 名、`--orchestrated` 与 stage/round/artifact/role。child 调用 `await-activation --stage ... --round ... --artifact ... --role ...`，确认当前阶段与实际 child 关联后执行。代码阶段通过 code-task 创建本地 checkpoint；禁止单独委派 commit 阶段或推送。保留已有写锁，不把实际 spawn 纳入新建锁协议。
 8. 通过当前宿主的原生生命周期事件和结果接口记录实际启动及终态。timed-out wait 不推断成功；身份、传输或异常终态失败如实暂停。阶段结果和 child 完成后调用 `advance`；只有 `running` 才重复步骤 3。

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

@@ -90,6 +90,8 @@ Run the verification gate:
 agent-infra-internal task-verify {task-id} watch-pr.completed --format text
 ```
 
+Present the verification summary per `.agents/rules/validation-output.md`, retaining necessary failure, blocked, and soft-warning diagnostics.
+
 Handle the result:
 - exit code 0 (all passed) -> continue to "Inform User"
 - exit code 1 (verification failed) -> fix per the output and re-run the gate

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

@@ -95,7 +95,7 @@ agent-infra-internal task-verify {task-id} watch-pr.completed --format text
 - 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。
 
 ### 7. 告知用户
 

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

@@ -118,8 +118,8 @@ delivery_remote_head:          # Most recent successfully delivered task branch
 
 ### Targets
 
-| target_id | operation_id | target_kind | target_family | target_artifact | target_round | target_sha256 | status | reason_code | updated_at |
-|-----------|--------------|-------------|---------------|-----------------|--------------|---------------|--------|-------------|------------|
+| target_id | operation_id | target_kind | target_family | target_artifact | target_input | target_round | target_sha256 | status | reason_code | updated_at |
+|-----------|--------------|-------------|---------------|-----------------|--------------|--------------|---------------|--------|-------------|------------|
 
 ## Activity Log
 

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

@@ -118,8 +118,8 @@ delivery_remote_head:          # 最近一次成功交付到 remote 的任务分
 
 ### Targets
 
-| target_id | operation_id | target_kind | target_family | target_artifact | target_round | target_sha256 | status | reason_code | updated_at |
-|-----------|--------------|-------------|---------------|-----------------|--------------|---------------|--------|-------------|------------|
+| target_id | operation_id | target_kind | target_family | target_artifact | target_input | target_round | target_sha256 | status | reason_code | updated_at |
+|-----------|--------------|-------------|---------------|-----------------|--------------|--------------|---------------|--------|-------------|------------|
 
 ## 活动日志