@fitlab-ai/agent-infra 0.9.12 → 0.9.14

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

@@ -9,16 +9,22 @@ description: >
 # 编码任务
 > `--agent` 取值见 `.agents/rules/task-management.md`「合作者 token 规范」。
 
-若入口业务操作数包含 `--orchestrated`，绑定 `{execution-flag}` = `--orchestrated` 并原样转发给 completed 事件；否则绑定为空。不得从 `orchestration.json`、环境变量或历史产物推断该标记。
+若入口业务操作数包含 `--orchestrated`，绑定 `{execution-flag}` = `--orchestrated` 并原样转发给 completed 事件；否则绑定为空。不得从 `orchestration.json`、环境变量或历史产物推断该标记。生命周期事件还必须携带显式触发信息：编排调用使用 `{trigger-initiator}=orchestrator`，否则使用 `model`；`{request-id}` 是本任务与本轮产物的稳定单行标识，`{reason-code}` 初次实现使用 `user-request`，修复或裁决使用 `review-finding`；started 与 completed 使用同一组值。
 
 根据已批准的技术方案编码任务，并产出 `code.md` 或 `code-r{N}.md`。本技能支持初次实现、基于 `review-code` 反馈的修复，以及人工裁决驱动实现三种模式。
 
 ## 行为边界 / 关键规则
 
+### 持久化报告证据
+
+生成实现报告时，先读取 `.agents/rules/evidence-reporting.md`。成功测试记录命令、目标范围、状态/结构化结果、实际结果和未覆盖部分；失败、阻塞或争议保留复现入口、准确位置和决定性摘录，不默认粘贴完整成功 stdout。
+
+- 涉及候选资格或 `HD-N` 判断时，先读取 `.agents/rules/decision-qualification.md`，基于 task.md 规范化约束/候选完成资格审计，并在实现报告记录五张资格审计表；不得把来源不明或未确认约束自动升级为排除条件
 - 严格遵循最新方案产物：`plan.md` 或 `plan-r{N}.md`
 - 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
 - 实现前读取 `.agents/rules/compatibility-policy.md`；只实现方案明确批准的兼容预算，不以“稳妥”为由保留旧分支、旧结果契约或迁移 shim
 - 修复模式逐条核实最新 `review-code` 的发现：成立则修复，判定为不成立/幻觉则在报告中反驳并记入 unresolved；不擅自扩大到审查未列出的问题；manual-validation 项不在修复范围
+- 实现报告在 `code.completed` 前必须通过 `task-artifact ... finalize-local --family code`；按 `.agents/rules/local-artifact-repair.md` 处理同一报告内可证明安全的最小结构修复，并只把同一次通过结果的摘要传给完成事件
 - 实现中遇到方案未覆盖的关键设计决策时，先调用 `agent-infra-internal task-ledger {task-id} decision-next-id` 取得 `HD-N`，按 `.agents/rules/human-decision-context.md` 写入实现报告的 `## 人工裁决待办` 详情块并判断是否需要实现，再调用 `decision-upsert --id {HD-N} --stage code --artifact {code-artifact} --needs-implementation {true|false}`；不得扫描编号、手写账本行、中途提问或擅自扩范围
 - 不调用 `commit` 技能，也不推送远端；测试通过后直接调用共享 commit core 的 `delivery: { mode: 'local' }` 创建本地 checkpoint。checkpoint 使用 durable intent，只有 checkpoint 与 task 状态同步成功后才发送 `code.completed`
 - 每轮实现都创建新的实现产物，不覆盖旧文件
@@ -43,7 +49,7 @@ 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
@@ -59,7 +65,7 @@ agent-infra-internal task-snapshot {task-id} --format text
 
 ## 步骤开始：声明 started 事件
 
-确认前置条件与模式后、本轮第一个产出动作之前执行 `agent-infra-internal task-event {task-id} code.started --agent {standard-agent-token}`。修复模式追加 `--fix-for {review-artifact}`，裁决模式追加 `--implementation-input {input-id}`。核心根据 artifact context 推导并校验轮次与输入身份；以返回的 `artifactContext` 记录本轮身份。
+确认前置条件与模式后、本轮第一个产出动作之前执行 `agent-infra-internal task-event {task-id} code.started --agent {standard-agent-token} --initiator {trigger-initiator} --request-id {request-id} --reason-code {reason-code}`。修复模式追加 `--fix-for {review-artifact}`，裁决模式追加 `--implementation-input {input-id}`。核心根据 artifact context 推导并校验轮次与输入身份；以返回的 `artifactContext` 记录本轮身份。
 
 ## 执行步骤
 ### 1. 验证前置条件
@@ -87,7 +93,7 @@ agent-infra-internal task-snapshot {task-id} --format text
 
 **必须执行，不得跳过。** 如果 task.md 中存在有效的 `issue_number`，调用 `agent-infra-internal platform-issue sync {task-id} --agent {standard-agent-token} --milestone specific`；里程碑推断、权限降级与幂等写入由 internal core 处理。
 
-> 若跳过或收窄后仍为 `X.Y.x`，步骤 11 的 `task-verify code.completed` 会通过 typed milestone check 截停本轮。
+> 若跳过或收窄后仍为 `X.Y.x`，步骤 12 的 `task-verify code.completed` 会通过 typed milestone check 截停本轮。
 
 ### 4. 确定模式与轮次
 
@@ -144,30 +150,56 @@ echo "$result"
 
 测试通过后，通过 `agent-infra-internal git-workflow commit --input {checkpoint-input}` 调用共享 commit core，输入 `delivery: { "mode": "local" }`、明确 paths、expected HEAD/tree、task ref、agent 和 code round。该调用只创建本地 checkpoint，不访问远端；core 会在 commit 前写入 durable intent，并在 task writer 成功后清理 intent。checkpoint 失败或 task 状态未闭合时，不得发送 `code.completed`。
 
+checkpoint 成功后，若任务存在 `issue_number`，调用 `agent-infra-internal platform-issue sync {task-id} --agent {standard-agent-token} --in-labels from-diff --base {delivery-base-ref}`，由 task-bound `delivery_base_ref` 产生 Issue 的 `in:` target；该同步失败时记录 warning 并停止本轮，不发送 `code.completed`。
+
 排查测试失败或行为不符合预期时，先读取 `.agents/rules/debugging-guide.md`，按其四阶段流程定位根因，禁止盲目改代码重试。
 
 ### 9. 编写实现报告
 
+在首次写入本轮 `{code-artifact}` 前，先创建受控报告骨架：
+
+```bash
+agent-infra-internal task-artifact {task-id} init --family code --artifact {code-artifact}
+```
+
+骨架只包含身份元数据、稳定 section marker 和必需标题；必须填入真实实现与验证内容后才能通过完成门禁。finalizer 返回可证明的单个结构错误时，使用其 SHA 和 semantic digest 调用 `task-artifact {task-id} repair --family code --artifact {code-artifact} --expected-sha256 {artifact-sha256} --expected-semantic-digest {semantic-digest}`，然后完整重跑 finalizer。
+
 创建 `.agents/workspace/active/{task-id}/{code-artifact}`。
 
 > 报告结构、必填章节和完整模板见 `reference/report-template.md`。写报告前先读取 `reference/report-template.md`。
 
-### 10. 更新任务状态
+### 10. 报告完成前门禁
+
+报告写入后、发布 `code.completed` 前，读取并遵循 `.agents/rules/local-artifact-repair.md`，执行：
+
+```bash
+finalizer=$(agent-infra-internal task-artifact {task-id} finalize-local --family code --artifact {code-artifact})
+status=$?
+echo "$finalizer"
+```
+
+- `status=0` 且 `finalizer.status="passed"`：绑定这一次返回的 `{artifact-sha256}` 和 `{semantic-digest}`。
+- `status=1` 且返回 `repairable=true`、诊断明确为当前报告中的单行替换：确认任务、轮次、产物和 provenance 未变化后，只编辑该 `code*.md` 一次，确认字节确实变化，再完整重跑同一命令。
+- 其他失败、无进展、诊断重复或达到 8 次实际报告编辑：停止，不发布 `code.completed`。
+
+不得重新扫描或手工补写摘要；完成事件必须携带本次 `passed` 结果的 `--artifact-sha256 {artifact-sha256} --semantic-digest {semantic-digest}`。
+
+### 11. 更新任务状态
 
 更新 `.agents/workspace/active/{task-id}/task.md`：
 - 审查 `## 需求` 段落，仅把本轮已由代码实现且有测试通过支撑的条目从 `- [ ]` 勾为 `- [x]`
 - 产物链接、阶段与完成日志由 completed 事件统一登记
 - 完成业务内容更新后声明完成事件：
-  - 初次实现：`agent-infra-internal task-event {task-id} code.completed --agent {standard-agent-token} --artifact {code-artifact} --files-modified {n} --tests-passed {n} {execution-flag}`
-  - 修复模式：`agent-infra-internal task-event {task-id} code.completed --agent {standard-agent-token} --artifact {code-artifact} --fix-for {review-artifact} --blockers {n} --major {n} --minor {n} --manual-validation {n} {execution-flag}`
-  - 裁决模式：`agent-infra-internal task-event {task-id} code.completed --agent {standard-agent-token} --artifact {code-artifact} --implementation-input {input-id} --files-modified {n} --tests-passed {n} {execution-flag}`
+  - 初次实现：`agent-infra-internal task-event {task-id} code.completed --agent {standard-agent-token} --initiator {trigger-initiator} --request-id {request-id} --reason-code {reason-code} --artifact {code-artifact} --artifact-sha256 {artifact-sha256} --semantic-digest {semantic-digest} --files-modified {n} --tests-passed {n} {execution-flag}`
+  - 修复模式：`agent-infra-internal task-event {task-id} code.completed --agent {standard-agent-token} --initiator {trigger-initiator} --request-id {request-id} --reason-code {reason-code} --artifact {code-artifact} --artifact-sha256 {artifact-sha256} --semantic-digest {semantic-digest} --fix-for {review-artifact} --blockers {n} --major {n} --minor {n} --manual-validation {n} {execution-flag}`
+  - 裁决模式：`agent-infra-internal task-event {task-id} code.completed --agent {standard-agent-token} --initiator {trigger-initiator} --request-id {request-id} --reason-code {reason-code} --artifact {code-artifact} --artifact-sha256 {artifact-sha256} --semantic-digest {semantic-digest} --implementation-input {input-id} --files-modified {n} --tests-passed {n} {execution-flag}`
 
-如果 task.md 中存在有效的 `issue_number`，执行以下同步操作（任一失败则记录 warning 并继续；Issue 元数据边界仍见 `.agents/rules/issue-sync.md`）：
+如果 task.md 中存在有效的 `issue_number`，执行以下同步操作（状态/评论失败按规则记录 warning；Issue `in:` evidence 同步失败不得发送 `code.completed`；边界见 `.agents/rules/issue-sync.md`）：
 - 调用 `agent-infra-internal platform-issue sync {task-id} --agent {standard-agent-token} --status in-progress`
 - 调用 `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}`
 - 调用 `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {code-artifact} --agent {standard-agent-token}`
 
-### 11. 完成校验
+### 12. 完成校验
 
 运行完成校验，确认任务产物和同步状态符合规范：
 
@@ -182,7 +214,7 @@ agent-infra-internal task-verify {task-id} code.completed --artifact {code-artif
 
 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。
 
-### 12. 告知用户
+### 13. 告知用户
 
 > 仅在校验通过后执行本步骤。
 

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

@@ -17,26 +17,17 @@
     },
     "artifact": {
       "file_pattern": "code.md|code-r{N}.md",
-      "required_sections": [
-        "Implementation Input",
-        "Modified Files",
-        "Key Code Explanation",
-        "Test Results",
-        "Differences from Plan",
-        "Items for Review",
-        "State Check",
-        "Evidence"
-      ],
-      "required_patterns": [
-        "^\\$ "
-      ]
+      "schema": "code"
     },
     "implementation-input": {},
     "activity-log": {
       "expected_action_pattern": "(Code Task|Code) \\(Round \\d+(?:(?:, fix for review-code(?:-r\\d+)?\\.md)|(?:, decision II-[1-9]\\d*))?\\)"
     },
     "review-ledger": {
-      "stage_scope": ["analysis", "plan"]
+      "stage_scope": [
+        "analysis",
+        "plan"
+      ]
     },
     "platform-sync": {
       "when": "issue_number_exists",
@@ -46,6 +37,7 @@
       "verify_task_comment_content": true,
       "verify_issue_type": true,
       "verify_issue_fields": false,
+      "verify_in_labels_computed": true,
       "verify_milestone": true,
       "verify_milestone_specific": true,
       "expected_status_label_key": "inProgress",

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

@@ -17,26 +17,17 @@
     },
     "artifact": {
       "file_pattern": "code.md|code-r{N}.md",
-      "required_sections": [
-        "实现输入",
-        "变更文件",
-        "关键代码说明",
-        "测试结果",
-        "与方案的差异",
-        "供审查关注的内容",
-        "状态核对",
-        "证据原文"
-      ],
-      "required_patterns": [
-        "^\\$ "
-      ]
+      "schema": "code"
     },
     "implementation-input": {},
     "activity-log": {
       "expected_action_pattern": "(Code Task|Code) \\(Round \\d+(?:(?:, fix for review-code(?:-r\\d+)?\\.md)|(?:, decision II-[1-9]\\d*))?\\)"
     },
     "review-ledger": {
-      "stage_scope": ["analysis", "plan"]
+      "stage_scope": [
+        "analysis",
+        "plan"
+      ]
     },
     "platform-sync": {
       "when": "issue_number_exists",
@@ -46,6 +37,7 @@
       "verify_task_comment_content": true,
       "verify_issue_type": true,
       "verify_issue_fields": false,
+      "verify_in_labels_computed": true,
       "verify_milestone": true,
       "verify_milestone_specific": true,
       "expected_status_label_key": "inProgress",

package/templates/.agents/skills/code-task/reference/code-rules.en.md

@@ -16,26 +16,27 @@ Follow the `code` step in `.agents/workflows/feature-development.yaml`.
 **Implementation principles**:
 1. **Follow the plan strictly**: do not deviate from the technical plan
 2. **Work step by step**: execute the planned sequence
-3. **Keep testing continuously**: run the **smoke subset** continuously as work progresses (see the `test` skill)
+3. **Keep testing continuously**: run the **fast smoke subset** continuously as work progresses (see the `test` skill)
 4. **Keep it simple**: do not add unplanned features
 
 ## Run Test Verification
 
 During implementation:
-- **Inner loop**: after each change, run the project's **smoke subset** (see the `test` skill) for fast feedback
+- **Inner loop**: after each change, run the project's **fast smoke subset** (see the `test` skill) for fast feedback without repeating the build
+- **After each implementation step**: run the **smoke subset** to verify the complete build and unit tests
 - **Before writing the code report**: run the **core subset** as final verification so code entering review has passed the complete core checks
 
 > Refer to the `test` skill for project-specific commands; downstream projects without layered scripts should fall back to the full project test command.
 
 If tests fail:
 - analyze the failure first and prioritize fixing issues introduced by this implementation
-- after each fix, re-run at least the smoke subset, then upgrade to core for the next full-pass verification
+- after each fix, re-run at least the fast smoke subset; after completing the implementation step, run smoke, then upgrade to core for the next full-pass verification
 - only stop without producing the implementation artifact when the failure is caused by an external blocker, missing environment, or unclear requirement that cannot be resolved inside the task
 
 Two-way failure handling:
 1. implementation-caused failures:
    - fix the code, tests, docs, or fixtures introduced by this implementation
-   - re-run tests after each fix (smoke for the immediate fix verification, core for the round-level verification)
+   - re-run tests after each fix (fast smoke for the immediate fix verification, smoke for complete-build verification, core for the round-level verification)
    - continue until all required tests pass
 2. external blockers:
    - confirm the failure comes from missing environment, unrelated upstream breakage, or unclear requirements outside this task

package/templates/.agents/skills/code-task/reference/code-rules.zh-CN.md

@@ -16,26 +16,27 @@
 **实现原则**：
 1. **严格遵循方案**：不要偏离技术方案
 2. **按步骤推进**：按计划顺序执行
-3. **持续测试**：实现过程中持续运行 **smoke 子集**（参见 `test` skill）
+3. **持续测试**：实现过程中持续运行 **fast smoke 子集**（参见 `test` skill）
 4. **保持简单**：不要加入未计划的功能
 
 ## 运行测试验证
 
 实现过程中：
-- **内循环**：每次修改后运行项目测试的 **smoke 子集**（参见 `test` skill），快速反馈
+- **内循环**：每次修改后运行项目测试的 **fast smoke 子集**（参见 `test` skill），快速反馈且不重复构建
+- **完成一个实施步骤后**：运行 **smoke 子集**，验证完整构建及单元测试
 - **写实现报告前**：运行 **core 子集**做最终验证，确保进入审查的代码已通过完整的核心测试
 
 > 项目特定命令请参考 `test` skill；不存在分层 script 的下游项目回退到完整项目测试命令。
 
 如果测试失败：
 - 先分析失败原因，并优先修复由本次实现引入的问题
-- 每次修复后重新运行至少 smoke 子集，进入下一轮再升级到 core
+- 每次修复后重新运行至少 fast smoke 子集，完成实施步骤后再运行 smoke，并在进入下一轮前升级到 core
 - 只有当失败由外部阻塞、环境缺失或当前任务内无法澄清的需求问题导致时，才允许在不生成实现产物的情况下停止
 
 双分支失败处理：
 1. 本次实现引入的失败：
    - 修复由本次实现引入的代码、测试、文档或 fixture 问题
-   - 每次修复后重新运行测试（smoke 用于本次修复验证，core 用于本轮整体验证）
+   - 每次修复后重新运行测试（fast smoke 用于本次修复验证，smoke 验证完整构建，core 用于本轮整体验证）
    - 持续处理直到所有必需测试通过
 2. 外部阻塞：
    - 确认失败来自缺失环境、无关的上游损坏，或任务范围外的需求不明确

package/templates/.agents/skills/code-task/reference/dual-mode.en.md

@@ -20,7 +20,7 @@ The core scans `plan.md` / `plan-r{N}.md`, `review-plan.md` / `review-plan-r{N}.
 |---|---|---:|---|
 | no code artifact, and the latest review-plan is exactly `Approved` and references the latest plan | `init` | 0 | initial implementation, output `code.md`; a missing matching approval or `Approved-with-issues` returns an error |
 | latest review-plan is exactly `Approved`, references the latest plan, and the latest code completion receipt does not bind the same plan digest | `init` | 0 | enter a new implementation round. `Approved-with-issues` remains parse-compatible for history but is not cross-stage approval; missing or invalid receipts fail closed |
-| `rev_max < code_max` | `error` | 2 | latest code round is unreviewed; run `review-code` first |
+| the latest review-code completion receipt does not bind the latest code identity/SHA | `error` | 2 | latest code is unreviewed; run `review-code`; code and review-code family rounds may advance independently |
 | latest review-code is Approved and a pending implementation input was decided after that review completed | `decision` | 0 | select the earliest `II-N` and enter decision-driven implementation; false/not-required and consumed inputs do not trigger |
 | latest review-code is Approved with 0/0/0 | `refused` | 1 | already approved; do not run `code-task` again |
 | latest review-code is Approved with major/minor findings | `fix` | 0 | optional fix mode |

package/templates/.agents/skills/code-task/reference/dual-mode.zh-CN.md

@@ -20,7 +20,7 @@ agent-infra-internal task-artifact {task-id} inspect --family code
 |---|---|---:|---|
 | 无 code 产物，且最新 review-plan 精确为 `Approved` 并引用最新 plan | `init` | 0 | 初次实现，产物为 `code.md`；缺少匹配审批或为 `Approved-with-issues` 时返回 error |
 | 最新 review-plan 精确为 `Approved`，且其「审查输入」/「Review Input」字段引用最新 plan，而最新 code 的完成 receipt 未绑定相同 plan 摘要 | `init` | 0 | plan 内容在 code 输入之后获批；进入新一轮实现。`Approved-with-issues` 仅保留历史解析兼容，不构成跨阶段批准；缺失或无效 receipt 失败关闭 |
-| `rev_max < code_max` | `error` | 2 | 最新代码未审查，先运行 `review-code` |
+| 最新 review-code 的完成收据未绑定最新 code identity/SHA | `error` | 2 | 最新代码未审查，先运行 `review-code`；code 与 review-code 的 family 轮次可独立增长 |
 | 最新 review-code 为 Approved 且存在审查完成后产生的 pending 实现输入 | `decision` | 0 | 选择最早 `II-N`，进入裁决驱动实现；false/not-required 与 consumed 输入不触发 |
 | 最新 review-code 为 Approved 且 0/0/0 | `refused` | 1 | 已通过，无需再次运行 `code-task` |
 | 最新 review-code 为 Approved 但有 major/minor | `fix` | 0 | 可选修复模式 |

package/templates/.agents/skills/code-task/reference/fix-mode.en.md

@@ -41,7 +41,9 @@ For each fix:
 1. read the affected files
 2. apply the smallest necessary change
 3. verify the change addresses the review feedback
-4. run the project's **smoke subset** for immediate feedback (see the `test` skill)
+4. run the project's **fast smoke subset** for immediate feedback (see the `test` skill)
+
+After completing the repair round, run the **smoke subset** to verify the complete build and unit tests.
 
 ## Run Test Verification
 

package/templates/.agents/skills/code-task/reference/fix-mode.zh-CN.md

@@ -41,7 +41,9 @@ manual-validation 项不在修复范围。处理规则：
 1. 读取受影响文件
 2. 施加最小必要改动
 3. 验证改动确实解决了审查反馈
-4. 运行项目测试的 **smoke 子集**做即时反馈（参见 `test` skill）
+4. 运行项目测试的 **fast smoke 子集**做即时反馈（参见 `test` skill）
+
+完成本轮修复后，运行 **smoke 子集**，验证完整构建及单元测试。
 
 ## 运行测试验证
 

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

@@ -1,5 +1,7 @@
 # Code Report Template
 
+> Before writing this report, use `task-artifact init` to create the skeleton and preserve every `artifact-section` marker; the skeleton contains no semantic result.
+
 Use this structure when creating `code.md` or `code-r{N}.md`.
 
 ## Output Template
@@ -20,11 +22,31 @@ Use this structure when creating `code.md` or `code-r{N}.md`.
 - **Decision Evidence**: `{decision-evidence or N/A}`
 - **Scope Summary**: {scope of this round's implementation input}
 
-## State Check
+## Qualification Audit
+
+> Use `.agents/rules/decision-qualification.md` and fill these five tables.
+
+### Constraint Dependencies
+| constraint_id | constraint_digest | role | evidence |
+| --- | --- | --- | --- |
+
+### Candidate Qualification
+| candidate_id | status | impact | constraint_ids | evidence |
+| --- | --- | --- | --- | --- |
+
+### Classification Results
+| decision_id | classification | evidence |
+| --- | --- | --- |
 
-> Paste the raw state-check command output; each command starts with `$ `.
+### Upstream Relations
+| upstream_family | upstream_artifact | upstream_round | upstream_sha256 | relation |
+| --- | --- | --- | --- | --- |
 
-## Modified Files
+### Dependency Snapshot
+| task_input_digest | non_constraint_input_digest | upstream_artifact_digest |
+| --- | --- | --- |
+
+## Changed Files
 
 ### New Files
 - `{file-path}` - {description}
@@ -32,7 +54,7 @@ Use this structure when creating `code.md` or `code-r{N}.md`.
 ### Modified Files
 - `{file-path}` - {change summary}
 
-## Key Code Explanation
+## Key Code Notes
 
 ### {Module/Feature Name}
 **File**: `{file-path}:{line-number}`
@@ -58,16 +80,6 @@ Use this structure when creating `code.md` or `code-r{N}.md`.
 ```
 
 
-## Evidence
-
-> 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.
-
-- Claim: {verified claim}
-```text
-$ {command}
-{raw output}
-```
-
 ## Differences from Plan
 
 {describe any deviation from the approved plan}
@@ -80,12 +92,27 @@ $ {command}
 |------|----------|----------|
 | {finding} | {accepted / adjusted / refuted / cannot-judge} | {fix file:line, or counter-evidence file:line / raw command output} |
 
-## Items for Review
+## Review Focus
 
 **Focus areas for reviewers**:
 - {item 1}
 - {item 2}
 
+## State Check
+
+> Record the state-check command, task/artifact scope, key result, and uncovered parts; each command starts with `$ `.
+> Follow `.agents/rules/evidence-reporting.md`: record task/artifact scope, key result, and uncovered parts; do not paste complete successful stdout.
+
+## Raw Evidence
+
+> Follow `.agents/rules/evidence-reporting.md`: pair each claim with a `$ ` command and proportionate result summary; include a decisive raw excerpt only for failures, blocking conditions, or disputes.
+
+- Claim: {verified claim}
+```text
+$ {command}
+{result summary or decisive excerpt}
+```
+
 ## Known Issues
 
 {known issues or follow-up ideas}

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

@@ -1,5 +1,7 @@
 # 实现报告模板
 
+> 写入本报告前，先用 `task-artifact init` 创建对应骨架，并保留每个 `artifact-section` marker；骨架不包含语义结果。
+
 创建 `code.md` 或 `code-r{N}.md` 时，使用以下结构。
 
 ## 输出模板
@@ -20,9 +22,29 @@
 - **裁决证据**：`{decision-evidence 或 N/A}`
 - **需求摘要**：{本轮实现输入的范围摘要}
 
-## 状态核对
+## 资格审计
+
+> 按 `.agents/rules/decision-qualification.md` 填写以下五张表。
+
+### 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 |
+| --- | --- | --- | --- | --- |
 
-> 粘贴状态核对命令原文；每条命令以 `$ ` 开头。
+### 依赖快照
+| task_input_digest | non_constraint_input_digest | upstream_artifact_digest |
+| --- | --- | --- |
 
 ## 变更文件
 
@@ -58,16 +80,6 @@
 ```
 
 
-## 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 `$ `。
-
-- 断言：{verified claim}
-```text
-$ {command}
-{raw output}
-```
-
 ## 与方案的差异
 
 {describe any deviation from the approved plan}
@@ -86,6 +98,21 @@ $ {command}
 - {item 1}
 - {item 2}
 
+## 状态核对
+
+> 记录状态核对命令、任务/产物范围、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 stdout。
+
+## 证据原文
+
+> 遵循 `.agents/rules/evidence-reporting.md`：每条断言配对 `$ ` 命令和相称结果摘要；仅为失败、阻塞或争议附决定性原文摘录。
+
+- 断言：{verified claim}
+```text
+$ {command}
+{result summary or decisive excerpt}
+```
+
 ## 已知问题
 
 {known issues or follow-up ideas}

package/templates/.agents/skills/commit/reference/issue-metadata-sync.en.md

@@ -14,6 +14,8 @@ Call one declarative intent. The internal core owns diff computation, repository
 agent-infra-internal platform-issue sync {task-id} --agent {standard-agent-token} --in-labels from-diff --base {base-branch} --requirements
 ```
 
+If `--base` is supplied, it must exactly match task.md's `delivery_base_ref`; the core uses that task-bound ref as the only diff evidence and never falls back to `main` or a repository default. The `in:` target is the intersection of the `labels.in` mapping and repository labels, and unrelated labels are preserved.
+
 ## Error Handling
 
 Treat sync failures as warnings only. Do not block an already completed `git commit`.

package/templates/.agents/skills/commit/reference/issue-metadata-sync.zh-CN.md

@@ -14,6 +14,8 @@
 agent-infra-internal platform-issue sync {task-id} --agent {standard-agent-token} --in-labels from-diff --base {base-branch} --requirements
 ```
 
+`--base`（如保留）必须与 task.md 的 `delivery_base_ref` 完全一致；core 以 task-bound base 作为唯一 diff evidence，不回退到 `main` 或仓库默认分支。`in:` target 只来自 `labels.in` 映射与仓库实际 labels 的交集，并保留其他 labels。
+
 ## 错误处理
 
 同步失败只记为警告，不阻塞已完成的 `git commit`。

package/templates/.agents/skills/commit/reference/pr-summary-sync.en.md

@@ -2,8 +2,8 @@
 
 Run only when `{task-id}` is valid and task.md has a `bound/verified` `pr_delivery_fact`.
 
-1. Run `agent-infra-internal platform-pr summary-context {task-id}`.
-2. Generate the plain summary body per `.agents/rules/pr-sync.md` and write it to a temporary file.
-3. Run `agent-infra-internal platform-pr summary-sync {task-id} --agent {standard-agent-token} --body-file {summary-body-file} --result no_op`. The commit path only synchronizes an existing PR summary and neither creates nor reuses a PR, so `no_op` explicitly represents the unchanged PR identity.
+1. Run `agent-infra-internal platform-pr summary-context {task-id}` to obtain canonical inputs and report status; rebuild a stale/missing sidecar through the `change-report` flow for the current head.
+2. Generate the plain summary body per `.agents/rules/pr-sync.md`, with exactly one `<!-- canonical-pr-change-report -->` placeholder, and write it to a temporary file.
+3. Run `agent-infra-internal platform-pr summary-sync {task-id} --agent {standard-agent-token} --body-file {summary-body-file} --change-report-file .agents/workspace/active/{task-id}/pr-change-report.json --result no_op`. The commit path only synchronizes an existing PR summary and neither creates nor reuses a PR, so `no_op` explicitly represents the unchanged PR identity.
 
 Failure records a warning but never blocks or rolls back the completed commit. `no-op` maps to `summary skipped (no diff)`.

package/templates/.agents/skills/commit/reference/pr-summary-sync.zh-CN.md

@@ -2,8 +2,8 @@
 
 仅当 `{task-id}` 有效且 `task.md` 存在 `bound/verified` 的 `pr_delivery_fact` 时执行；否则跳过。
 
-1. 调用 `agent-infra-internal platform-pr summary-context {task-id}` 获取 canonical 聚合输入。
-2. 按 `.agents/rules/pr-sync.md` 生成纯摘要正文并写入临时文件。
-3. 调用 `agent-infra-internal platform-pr summary-sync {task-id} --agent {standard-agent-token} --body-file {summary-body-file} --result no_op`。commit 路径只同步已有 PR 摘要，不创建或复用 PR，因此固定使用 `no_op` 表示 PR 身份未变化。
+1. 调用 `agent-infra-internal platform-pr summary-context {task-id}` 获取 canonical 聚合输入和报告状态；sidecar stale/missing 时先按 `change-report` 流程重建当前 head 报告。
+2. 按 `.agents/rules/pr-sync.md` 生成只含一次 `<!-- canonical-pr-change-report -->` 的纯摘要正文并写入临时文件。
+3. 调用 `agent-infra-internal platform-pr summary-sync {task-id} --agent {standard-agent-token} --body-file {summary-body-file} --change-report-file .agents/workspace/active/{task-id}/pr-change-report.json --result no_op`。commit 路径只同步已有 PR 摘要，不创建或复用 PR，因此固定使用 `no_op` 表示 PR 身份未变化。
 
 同步失败只记录 warning，不阻塞或回滚已经完成的 commit。`no-op` 回传 `summary skipped (no diff)`。

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

@@ -9,9 +9,15 @@ description: >
 # Complete Manual Validation
 > `--agent` values are defined in `.agents/rules/task-management.md` under “Collaborator Token Specification”.
 
+Lifecycle events require explicit trigger data: use `{trigger-initiator}=orchestrator` for orchestration and `model` otherwise; `{request-id}` is a stable single-line identifier for this task and artifact round, and `{reason-code}` is `user-request` or `validation-rerun`. Reuse the same values for started and completed.
+
 
 ## Boundary / Critical Rules
 
+### Persisted Report Evidence
+
+Before generating the validation completion report, read `.agents/rules/evidence-reporting.md`. Record commands, scope, structured results, actual conclusions, and uncovered parts for state checks and synchronization; keep the stricter basename-only and sanitized-result boundaries for manual validation.
+
 - This skill closes the manual-validation status in an existing PR summary comment; it does not create a parallel ordinary validation comment.
 - It must write `manual-validation.md` or `manual-validation-r{N}.md` so later PR summary refreshes can reuse the validation result.
 - If the `sync-pr` summary comment is missing, fail instead of creating a partial fallback summary.
@@ -24,7 +30,7 @@ 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
@@ -38,7 +44,7 @@ agent-infra-internal task-snapshot {task-id} --format text
 
 ## Step Start: Write the started Marker
 
-After resolving the artifact context and before this round's first artifact action, run `agent-infra-internal task-event {task-id} manual-validation.started --agent {standard-agent-token}` and record the returned `artifactContext`.
+After resolving the artifact context and before this round's first artifact action, run `agent-infra-internal task-event {task-id} manual-validation.started --agent {standard-agent-token} --initiator {trigger-initiator} --request-id {request-id} --reason-code {reason-code}` and record the returned `artifactContext`.
 
 ## Steps
 
@@ -86,7 +92,7 @@ Before this step, read `reference/report-template.md`. Create `{manual-validatio
 
 ### 6. Update task.md
 
-Run `agent-infra-internal task-event {task-id} manual-validation.completed --agent {standard-agent-token} --artifact {manual-validation-artifact} --summary-result "{summary-result}"`. The core keeps `current_step` unchanged while atomically recording the implementation-notes link, metadata, and done log.
+Run `agent-infra-internal task-event {task-id} manual-validation.completed --agent {standard-agent-token} --initiator {trigger-initiator} --request-id {request-id} --reason-code {reason-code} --artifact {manual-validation-artifact} --summary-result "{summary-result}"`. The core keeps `current_step` unchanged while atomically recording the implementation-notes link, metadata, and done log.
 
 If the task has a valid `issue_number`, run `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}`, then `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {manual-validation-artifact} --agent {standard-agent-token}`.
 
@@ -109,7 +115,7 @@ Report:
 - Artifact path
 - PR summary sync result
 - Current verification output
-- Suggested next step: enter the final closing flow and run /complete-task {task-ref}
+- Suggested next step: enter the final closing flow and run /complete-task --task {task-ref}
 
 Before rendering the final output, read `.agents/rules/next-step-output.md` and append `Completed at: YYYY-MM-DD HH:mm:ss` as the absolute last line.