@fitlab-ai/agent-infra 0.8.4 → 0.9.0

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

@@ -3,6 +3,7 @@ name: review-analysis
 description: >
   Review the requirement analysis artifact.
   Use when a requirements analysis needs an independent review before planning.
+  Only invoke this skill automatically when the conversation includes a resolvable task reference.
 ---
 
 # Requirement Analysis Review
@@ -23,24 +24,18 @@ After loading workflow / skill / rules instructions, and before any task-state j
 Run these commands and paste the raw output into both the user-facing reply and this round's `## State Check` section:
 
 ```bash
-git status -s
-ls -la .agents/workspace/active/{task-id}/
-tail .agents/workspace/active/{task-id}/task.md
+agent-infra-internal task-snapshot {task-id} --format text
 ```
 
-## Task id short ref
+## Task Context Resolution
 
-> If `{task-id}` matches `^[#]?[0-9]+$` (bare numeric or `#`-prefixed), follow the "SKILL parameter resolver" section of `.agents/rules/task-short-id.md`; treat `{task-id}` as the resolved full `TASK-YYYYMMDD-HHMMSS` form for every downstream command.
+> The entry point may omit the task ref and also accepts a legacy positional ref or `--task <ref>` / `-t <ref>`. Separate task scope from the full arguments while preserving every business operand, then call `agent-infra-internal task-context resolve {task-scope}` where `{task-scope}` is empty, one positional ref, or one task flag. Read only `taskId` from the structured result and bind `{task-id}` to that full `TASK-YYYYMMDD-HHMMSS` for downstream commands. Pass through resolution failures without scanning tasks locally.
 
-## Step Start: Write the started Marker
+> Resolve the task reference, then confirm that the task is in a state or directory supported by this skill and that `task.md` exists; if it cannot be located, handle it as a missing task and stop.
 
-After prerequisites pass and before this round's first artifact action, append a started marker to task.md `## Activity Log` (same base action as this round's done entry plus a ` [started]` suffix, note `started`):
+## Step Start: Declare the started Event
 
-```
-- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Review Analysis (Round {N}) [started]** by {agent} — started
-```
-
-`ai task log` pairs it with the done entry written when the review completes onto one row (in progress → done). Format and pairing rules: see the "Activity Log started / done dual-marker convention" in `.agents/rules/task-management.md`.
+After resolving the artifact context and before this round's first artifact action, run `agent-infra-internal task-event {task-id} review-analysis.started --agent {agent}`.
 
 ## Steps
 
@@ -48,9 +43,9 @@ After prerequisites pass and before this round's first artifact action, append a
 
 Require `task.md` and at least one analysis artifact: `analysis.md` or `analysis-r{N}.md`.
 
-### 2. Determine Review Round
+### 2. Resolve Review Context
 
-Record `{analysis-artifact}`, `{review-round}`, and `{review-artifact}` (`review-analysis.md` or `review-analysis-r{N}.md`).
+Run `agent-infra-internal task-artifact {task-id} inspect --family review-analysis`. Continue only for `ready`; take `{analysis-artifact}` from `inputs` and `{review-round}` / `{review-artifact}` from `next.round` / `next.name`. Do not scan rounds or construct names in the skill.
 
 ### 3. Read Analysis Context
 
@@ -70,27 +65,20 @@ Create `.agents/workspace/active/{task-id}/{review-artifact}`.
 
 ### 6. Update Task Status
 
-Get the current time:
-
-```bash
-date "+%Y-%m-%d %H:%M:%S%z" | sed 's/\([+-][0-9][0-9]\)\([0-9][0-9]\)$/\1:\2/'
-```
-
-Set `current_step` to `requirement-analysis-review`, refresh task metadata, and append:
-`- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Review Analysis (Round {N})** by {agent} — Verdict: {Approved/Changes Requested/Rejected}, blockers: {n}, major: {n}, minor: {n}, Manual-validation: {n} → {review-artifact}`
+After the report, submit each new finding with `agent-infra-internal task-ledger {task-id} finding-upsert --stage analysis --review-artifact {review-artifact} --ordinal {n} --severity {blocker|major|minor} --evidence {review-artifact}#{anchor}`; submit prior-response dispositions with `finding-review --id {ledger-id} --status {confirmed|closed|open|needs-human-decision} --evidence {evidence}`. Do not scan ids or edit ledger rows. After all ledger writes, call `agent-infra-internal task-ledger {task-id} stage-status --stage analysis` exactly once. Derive the verdict and next-step branch from `stageStatus.canAdvance`, and blocker/major/minor event counts from `unresolvedFindingCounts`: only `canAdvance=true` permits `approved`; otherwise use `changes-requested` or `rejected`. Then run `agent-infra-internal task-event {task-id} review-analysis.completed --agent {agent} --artifact {review-artifact} --verdict {approved|changes-requested|rejected} --blockers {n} --major {n} --minor {n} --manual-validation {n}`.
 
 `manual-validation` is the data source for the `Manual-validation` count folded into review rows in `ai task log`; do not add a parallel manual-verification field.
 
-If task.md has a valid `issue_number`, read `.agents/rules/issue-sync.md`, sync the task comment, and publish the `{review-artifact}` comment.
+If task.md has a valid `issue_number`, run `agent-infra-internal platform-comment sync {task-id} --kind task --agent {agent}`, then `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {review-artifact} --agent {agent}`.
 
 ### 7. Run Completion Gate
 
 ```bash
-node .agents/scripts/validate-artifact.js gate review-analysis .agents/workspace/active/{task-id} {review-artifact} --format text
+agent-infra-internal task-verify {task-id} review-analysis.completed --artifact {review-artifact} --format text
 ```
 
 ### 8. Tell the User
 
 Use the conclusion branch in `reference/output-templates.md` and show all TUI command formats.
 
-> Before rendering the final output, read `.agents/rules/next-step-output.md` and apply both of its rules: (1) render `{task-ref}` in the "Next steps" commands as the current task's short id `#NN` (see that file for lookup and fallback), while other `{task-id}` placeholders (report titles, paths) keep the full TASK-id form; (2) append the `Completed at` line as the very last line of the user-facing output (this applies to every user-facing output — success, error, and early-return paths alike, not only the success path).
+> Before rendering the final output, read `.agents/rules/next-step-output.md` and apply both of its rules: (1) render `{task-ref}` in the "Next steps" commands as the current task's short id `NN` (see that file for lookup and fallback), while other `{task-id}` placeholders (report titles, paths) keep the full TASK-id form; (2) append the `Completed at` line as the very last line of the user-facing output (this applies to every user-facing output — success, error, and early-return paths alike, not only the success path).

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

@@ -3,6 +3,7 @@ name: review-analysis
 description: >
   审查需求分析报告。
   当需求分析需要在进入方案前接受独立审查时使用。
+  仅当对话包含可解析的任务引用时才可自动调用本技能。
 ---
 
 # 需求分析审查
@@ -23,26 +24,20 @@ description: >
 运行以下命令，并把原文粘贴到回复正文和本轮产物的 `## 状态核对` 段：
 
 ```bash
-git status -s
-ls -la .agents/workspace/active/{task-id}/
-tail .agents/workspace/active/{task-id}/task.md
+agent-infra-internal task-snapshot {task-id} --format text
 ```
 
 状态核对完成前，禁止任何关于外部状态的断言。
 
-## 任务入参短号别名
+## 任务上下文解析
 
-> 如果 `{task-id}` 入参匹配 `^[#]?[0-9]+$`（裸数字或带 `#` 前缀），先读取 `.agents/rules/task-short-id.md` 的「SKILL 入参解析」段执行解析；后续命令视 `{task-id}` 为解析后的全长 `TASK-YYYYMMDD-HHMMSS` 形式。
+> 入口允许省略 task ref，也接受旧位置 task ref 或 `--task <ref>` / `-t <ref>`。先从完整参数中分离 task scope 并原样保留其他业务操作数，再调用 `agent-infra-internal task-context resolve {task-scope}`；`{task-scope}` 为空、位置 ref 或 task flag 之一。只读取结构化结果的 `taskId`，后续把 `{task-id}` 绑定为该完整 `TASK-YYYYMMDD-HHMMSS`。解析失败时透传非零退出码，不自行扫描任务。
 
-## 步骤开始：写入 started 标记
+> 解析任务引用，并确认任务位于本技能支持的状态或目录且存在 `task.md`；无法定位时按未找到任务处理并停止。
 
-确认前置条件后、本轮第一个产出动作之前，向 task.md `## 活动日志` 追加一条 started 标记（与本轮 done 条目同基名 + ` [started]` 后缀，note 用 `started`）：
+## 步骤开始：声明 started 事件
 
-```
-- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Review Analysis (Round {N}) [started]** by {agent} — started
-```
-
-`ai task log` 会把它与审查完成时写入的 done 条目配对成一行（进行中 → 已完成）。格式与配对规则见 `.agents/rules/task-management.md` 的「Activity Log started / done 双标记约定」。
+确认前置条件和产物上下文后、本轮第一个产出动作之前执行 `agent-infra-internal task-event {task-id} review-analysis.started --agent {agent}`。
 
 ## 执行步骤
 ### 1. 验证前置条件
@@ -51,12 +46,9 @@ tail .agents/workspace/active/{task-id}/task.md
 - `.agents/workspace/active/{task-id}/task.md`
 - 至少一个分析产物：`analysis.md` 或 `analysis-r{N}.md`
 
-### 2. 确定审查轮次
+### 2. 解析审查上下文
 
-扫描任务目录并记录：
-- `{analysis-artifact}`：最高轮次的分析产物
-- `{review-round}`
-- `{review-artifact}`：`review-analysis.md` 或 `review-analysis-r{N}.md`
+运行 `agent-infra-internal task-artifact {task-id} inspect --family review-analysis`。仅当结果为 `ready` 时继续；从 `inputs` 取得 `{analysis-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。
 
 ### 3. 阅读分析上下文
 
@@ -76,28 +68,16 @@ tail .agents/workspace/active/{task-id}/task.md
 
 ### 6. 更新任务状态
 
-获取当前时间：
-
-```bash
-date "+%Y-%m-%d %H:%M:%S%z" | sed 's/\([+-][0-9][0-9]\)\([0-9][0-9]\)$/\1:\2/'
-```
-
-更新 task.md：
-- `current_step`：requirement-analysis-review
-- `assigned_to`：{当前代理}
-- `updated_at`：{当前时间}
-- `agent_infra_version`：按 `.agents/rules/version-stamp.md` 取值
-- 追加：
-  `- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Review Analysis (Round {N})** by {agent} — Verdict: {Approved/Changes Requested/Rejected}, blockers: {n}, major: {n}, minor: {n}, Manual-validation: {n} → {review-artifact}`
+报告完成后，新 finding 逐条调用 `agent-infra-internal task-ledger {task-id} finding-upsert --stage analysis --review-artifact {review-artifact} --ordinal {n} --severity {blocker|major|minor} --evidence {review-artifact}#{anchor}`；复核上一轮响应时调用 `finding-review --id {ledger-id} --status {confirmed|closed|open|needs-human-decision} --evidence {相称证据}`。不得扫描编号或手写账本行。全部账本写入完成后只调用一次 `agent-infra-internal task-ledger {task-id} stage-status --stage analysis`，以 `stageStatus.canAdvance` 决定 verdict 和下一步，并以 `unresolvedFindingCounts` 填写 blocker/major/minor：仅 `canAdvance=true` 可用 `approved`，否则必须用 `changes-requested` 或 `rejected`。随后执行 `agent-infra-internal task-event {task-id} review-analysis.completed --agent {agent} --artifact {review-artifact} --verdict {approved|changes-requested|rejected} --blockers {n} --major {n} --minor {n} --manual-validation {n}`。
 
 `manual-validation` 是 `ai task log` 中 review 行「人工校验点」（EN `Manual-validation`）计数的数据源；不要新增并行人工验证字段。
 
-如果 task.md 中存在有效的 `issue_number`，执行前先读取 `.agents/rules/issue-sync.md`，完成 upstream 仓库检测和权限检测，然后同步 task 评论并发布 `{review-artifact}` 评论。
+如果 task.md 中存在有效的 `issue_number`，调用 `agent-infra-internal platform-comment sync {task-id} --kind task --agent {agent}`，再调用 `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {review-artifact} --agent {agent}`；失败按 `.agents/rules/issue-sync.md` 记录 warning。
 
 ### 7. 完成校验
 
 ```bash
-node .agents/scripts/validate-artifact.js gate review-analysis .agents/workspace/active/{task-id} {review-artifact} --format text
+agent-infra-internal task-verify {task-id} review-analysis.completed --artifact {review-artifact} --format text
 ```
 
 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。
@@ -106,7 +86,7 @@ node .agents/scripts/validate-artifact.js gate review-analysis .agents/workspace
 
 按 `reference/output-templates.md` 的结论分支输出，并展示所有 TUI 的下一步命令。
 
-> 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）。
+> 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）。
 
 ## 完成检查清单
 

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

@@ -20,6 +20,7 @@
       "required_sections": [
         "Review Summary",
         "Findings",
+        "Non-blocking Advisories",
         "Manual Validation Items",
         "Conclusion and Recommendations",
         "State Check",
@@ -30,12 +31,10 @@
       "required_patterns": [
         "^### Approval Decision$",
         "^\\$ "
-      ],
-      "freshness_minutes": 30
+      ]
     },
     "activity-log": {
-      "expected_action_pattern": "(Review Analysis|Analysis Review) \\(Round \\d+\\)",
-      "freshness_minutes": 30
+      "expected_action_pattern": "(Review Analysis|Analysis Review) \\(Round \\d+\\)"
     },
     "platform-sync": {
       "when": "issue_number_exists",

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

@@ -20,6 +20,7 @@
       "required_sections": [
         "审查摘要",
         "问题清单",
+        "非阻塞建议",
         "人工校验项",
         "结论与建议",
         "状态核对",
@@ -30,12 +31,10 @@
       "required_patterns": [
         "^### 审查决定$",
         "^\\$ "
-      ],
-      "freshness_minutes": 30
+      ]
     },
     "activity-log": {
-      "expected_action_pattern": "(Review Analysis|Analysis Review) \\(Round \\d+\\)",
-      "freshness_minutes": 30
+      "expected_action_pattern": "(Review Analysis|Analysis Review) \\(Round \\d+\\)"
     },
     "platform-sync": {
       "when": "issue_number_exists",

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

@@ -4,9 +4,9 @@ Read this file before presenting the final review result to the user.
 
 ## Select exactly one output scenario
 
-Evaluate in this order (**manual-validation count does not participate in selection**):
-1. If `Blocker = 0`, `Major = 0`, and `Minor = 0`, use Scenario A, regardless of manual-validation count
-2. If `Blocker = 0` and (`Major > 0` or `Minor > 0`), use Scenario B
+Select from `stage-status` (**manual-validation and advisory counts do not participate**):
+1. If `stageStatus.canAdvance=true`, use Scenario A
+2. If `stageStatus.canAdvance=false` and there are no blockers, use Scenario B
 3. If `Blocker > 0` and the issues can be handled by one focused revision, use Scenario C
 4. If the requirement analysis needs broad rewriting or fresh clarification, use Scenario D
 
@@ -16,7 +16,9 @@ Rules:
 - If `Blocker > 0`, never use an approved template
 - Never count manual-validation items as blocker / major / minor or use them to trigger Scenario B/C/D
 - The selected scenario must include all TUI command formats
-- The count line always shows 4 numbers: the first three (Blockers / Major / Minor) must be 0 to proceed; the fourth, `Human-decision` (`{h}`), is the number of rows in task.md `## 审查分歧账本` with `stage=analysis` and `status=needs-human-decision` — a "pending human ruling" item that need not be zero and does not participate in scenario selection. When `{h} > 0`, before the selected scenario's "Next steps" commands you must expand each pending ruling per the "Pending human-decision pre-block" in `.agents/rules/next-step-output.md` and prompt to resolve them first
+- The count line shows 4 numbers. `Human-decision` (`{h}`) counts this stage's `needs-human-decision` rows; because those rows are unresolved, `{h} > 0` means `canAdvance=false`. Expand the "Pending human-decision pre-block" from `.agents/rules/next-step-output.md` and show revision and re-review paths only.
+
+For Scenarios B/C/D, follow the revision commands with re-review commands: `/review-analysis {task-ref}`, `/{{project}}:review-analysis {task-ref}`, and `$review-analysis {task-ref}`.
 
 ### Scenario A: Approved with no findings
 
@@ -34,23 +36,18 @@ Next step - write the technical plan:
 Reminder: manual-validation items belong in the PR description manual verification checklist and should not trigger /analyze-task.
 ```
 
-### Scenario B: Approved with findings
+### Scenario B: Changes requested (major / minor)
 
 ```text
-Task {task-id} requirement analysis review completed. Verdict: approved.
+Task {task-id} requirement analysis review completed. Verdict: changes requested.
 - Blockers: 0 | Major issues: {n} | Minor issues: {n} | Human-decision: {h}
 - Review report: .agents/workspace/active/{task-id}/{review-artifact}
 
-Next step - revise analysis before continuing (recommended):
+Next step - revise requirement analysis:
   - Claude Code / OpenCode: /analyze-task {task-ref}
   - Gemini CLI: /{{project}}:analyze-task {task-ref}
   - Codex CLI: $analyze-task {task-ref}
 
-Or proceed directly to planning:
-  - Claude Code / OpenCode: /plan-task {task-ref}
-  - Gemini CLI: /{{project}}:plan-task {task-ref}
-  - Codex CLI: $plan-task {task-ref}
-
 [When manual-validation > 0, append:]
 Reminder: manual-validation items belong in the PR description manual verification checklist and should not trigger /analyze-task.
 ```

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

@@ -4,9 +4,9 @@
 
 ## 选择唯一输出场景
 
-按以下顺序判断（**注意：manual-validation 数量不参与判断**）：
-1. 如果 `Blocker = 0` 且 `Major = 0` 且 `Minor = 0`，使用场景 A（不管 manual-validation 是否 > 0）
-2. 如果 `Blocker = 0` 且（`Major > 0` 或 `Minor > 0`），使用场景 B
+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. 如果需求分析需要大范围重写或重新澄清，使用场景 D
 
@@ -16,7 +16,9 @@
 - 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
 - 所选场景中必须包含所有 TUI 命令格式
-- 计数行固定显示 4 个数字：前三项（阻塞 / 主要 / 次要）必须为 0 才进下一步；第四项 `人工裁决`（`{h}`）= task.md `## 审查分歧账本` 中 `stage=analysis` 且 `status=needs-human-decision` 的行数，是「待人裁」项、不要求归零，也不参与场景判断。当 `{h} > 0` 时，必须在选定场景的「下一步」命令之前，按 `.agents/rules/next-step-output.md`「人工裁决待办前置块」逐项展开裁决项并提示先完成裁决
+- 计数行固定显示 4 个数字。`人工裁决`（`{h}`）是本阶段 `needs-human-decision` 行数；它属于未闭环账本状态，因此 `{h} > 0` 时 `canAdvance=false`，必须按 `.agents/rules/next-step-output.md` 的「人工裁决待办前置块」展开详情，并只输出修订与复审路径。
+
+场景 B/C/D 在修订命令后继续列出复审命令：`/review-analysis {task-ref}`、`/{{project}}:review-analysis {task-ref}`、`$review-analysis {task-ref}`。
 
 ### 场景 A：通过且无问题
 
@@ -34,23 +36,18 @@
 提醒：manual-validation 项需在 PR description 的「待人工验证」清单中承接，不应触发 /analyze-task。
 ```
 
-### 场景 B：通过但有问题
+### 场景 B：需要修改（major / minor）
 
 ```text
-任务 {task-id} 需求分析审查完成。结论：通过。
+任务 {task-id} 需求分析审查完成。结论：需要修改。
 - 阻塞项：0 | 主要问题：{n} | 次要问题：{n} | 人工裁决：{h}
 - 审查报告：.agents/workspace/active/{task-id}/{review-artifact}
 
-下一步 - 修订分析后继续（推荐）：
+下一步 - 修订需求分析：
   - Claude Code / OpenCode：/analyze-task {task-ref}
   - Gemini CLI：/{{project}}:analyze-task {task-ref}
   - Codex CLI：$analyze-task {task-ref}
 
-或直接进入方案设计：
-  - Claude Code / OpenCode：/plan-task {task-ref}
-  - Gemini CLI：/{{project}}:plan-task {task-ref}
-  - Codex CLI：$plan-task {task-ref}
-
 [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 /analyze-task。
 ```

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

@@ -40,12 +40,18 @@ Use this template when writing `review-analysis.md` or `review-analysis-r{N}.md`
 **Description**: {details}
 **Suggested Fix**: {fix suggestion}
 
-### Minor Issues (optional improvements)
+### Minor Issues (low impact, closure required)
 
 #### 1. {Improvement point}
 **File**: `{file-path}:{line-number}`
 **Suggestion**: {improvement suggestion}
 
+## Non-blocking Advisories
+
+> Record only future optimizations that do not affect the current artifact's completeness, correctness, or acceptance. Advisories do not enter the disagreement ledger, finding counts, or verdict.
+
+- {future optimization}
+
 ## Manual Validation Items
 
 > Items the AI agent cannot close in the current execution environment; they do not participate in the next analysis round. Maintainers carry them in the PR description as a "manual verification required" checklist.
@@ -61,7 +67,8 @@ Use this template when writing `review-analysis.md` or `review-analysis-r{N}.md`
 
 ## Review Disagreement Ledger Writeback
 
-> Upsert each finding this round into the task.md disagreement ledger: append an `open` row for new findings (id prefix `AN-`, stage=analysis); per the hand-back duty set the executor's prior-round responses to `confirmed` / back to `open` / `needs-human-decision`. State machine and evidence rules: `.agents/rules/review-handshake.md`.
+> Record the structured intents to submit: use `task-ledger finding-upsert` for new findings and `finding-review` for prior responses. The core allocates `AN-N` and validates transitions; do not edit task.md table rows.
+> Every finding escalated to `needs-human-decision` must include a self-contained detail block per `.agents/rules/human-decision-context.md`, with evidence pointing to that stable anchor.
 
 ## Evidence
 

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

@@ -40,12 +40,18 @@
 **说明**：{details}
 **修复建议**：{fix suggestion}
 
-### 次要问题（可选改进）
+### 次要问题（低影响但需闭环）
 
 #### 1. {改进点}
 **文件**：`{file-path}:{line-number}`
 **建议**：{improvement suggestion}
 
+## 非阻塞建议
+
+> 仅记录不影响当前产物完整性、正确性和验收的后续优化；不写入审查分歧账本，不计入 blocker / major / minor，也不影响结论。
+
+- {future optimization}
+
 ## 人工校验项
 
 > AI agent 在本执行环境无法闭环的项；不参与下一轮 refine。维护者在 PR description 中以「待人工验证」清单承接。
@@ -61,7 +67,8 @@
 
 ## 审查分歧账本回写
 
-> 把本轮每条 finding upsert 到 task.md `## 审查分歧账本`：新 finding 追加 `open` 行（id 前缀 `AN-`，stage=analysis），对执行方上一轮响应按回交义务改 `confirmed` / 置回 `open` / `needs-human-decision`。状态机与证据规则见 `.agents/rules/review-handshake.md`。
+> 本段记录将提交的结构化意图：新 finding 用 `task-ledger finding-upsert`，上一轮响应复核用 `finding-review`；由核心分配 `AN-N` 并校验状态机，禁止手写 task.md 表格。
+> 凡升级为 `needs-human-decision` 的 finding，必须按 `.agents/rules/human-decision-context.md` 在本报告中提供自足详情块，并让 evidence 指向该稳定锚点。
 
 ## 证据原文
 

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

@@ -14,6 +14,7 @@ Follow the `analysis-review` step in `.agents/workflows/feature-development.yaml
 - [ ] The design stage has enough input to proceed
 - [ ] The analysis matches the original Issue or user request
 - [ ] The reviewer checked whether the executor missed any key design decision that should be upgraded to `[needs-human-decision]`
+- [ ] Every `needs-human-decision` detail produced this round follows the self-contained structure in `.agents/rules/human-decision-context.md`
 - [ ] Every blocker is backed by reproducible grep/sed/nl evidence; conclusions not directly verified are declared under Self-Doubt
 
 **Common anti-examples**:
@@ -29,6 +30,12 @@ Follow the `analysis-review` step in `.agents/workflows/feature-development.yaml
 3. **Actionable**: suggest a concrete fix
 4. **Severity-based**: clearly distinguish blockers, major issues, and minor issues
 
+## Three-category Decision Tree
+
+1. A gap in requirements, constraints, risks, affected scope, or verifiable acceptance criteria is a formal finding. Assign blocker / major / minor by impact; severity does not control closure, so minor findings must also reach a terminal state.
+2. When there is no known defect but validation requires a real environment, permission, or human operation, classify it as manual-validation.
+3. Only a future optimization that does not affect the current analysis's completeness, correctness, or acceptance is an advisory. Put it only in Non-blocking Advisories; do not add it to the ledger, finding counts, or verdict.
+
 ## Manual Validation Classification
 
 Some findings cannot be closed by an AI agent in the current execution environment, for example:

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

@@ -14,6 +14,7 @@
 - [ ] 后续设计阶段是否有足够输入
 - [ ] 与原始 Issue / 用户需求是否一致
 - [ ] 已复核执行方是否漏标应升级为 `[needs-human-decision]` 的关键设计决策
+- [ ] 本轮所有 `needs-human-decision` 详情均符合 `.agents/rules/human-decision-context.md` 的自足结构
 - [ ] 每条 blocker 都配可复现的 grep/sed/nl 证据，未直接验证的结论已在「自我质疑」声明
 
 **常见反例**：
@@ -29,6 +30,12 @@
 3. **可执行**：给出明确可落地的修复建议
 4. **按严重程度分类**：明确区分 blocker、major 和 minor
 
+## 三类审查项决策树
+
+1. 若问题揭示当前需求分析缺少需求、约束、风险、影响范围或可验证验收标准，登记为正式 finding，并按影响赋予 blocker / major / minor；severity 只表示影响大小，minor 也必须闭环。
+2. 若没有已知缺陷，但只能依赖真实环境、权限或人工操作完成验证，归为 manual-validation。
+3. 仅当建议属于未来优化且不影响当前分析的完整性、正确性和验收时，归为 advisory。advisory 只写入「非阻塞建议」，不进入账本、问题计数或 verdict。
+
 ## 人工校验项分类
 
 某些发现项是 AI agent 在本执行环境**无法闭环**的，例如：

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

@@ -3,6 +3,7 @@ name: review-code
 description: >
   Review code implementation and output a code review report.
   Use when a code implementation needs review before merging.
+  Only invoke this skill automatically when the conversation includes a resolvable task reference.
 ---
 
 # Code Review
@@ -32,26 +33,20 @@ After loading workflow / skill / rules instructions, and before any task-state j
 Run these commands and paste the raw output into both the user-facing reply and this round's `## State Check` section:
 
 ```bash
-git status -s
-ls -la .agents/workspace/active/{task-id}/
-tail .agents/workspace/active/{task-id}/task.md
+agent-infra-internal task-snapshot {task-id} --format text
 ```
 
 Before the state check is complete, do not make external-state assertions such as "the code is unchanged", "tests passed", or "there are no other references", including in reasoning. This gate is only a structural floor; evidence pairing and authenticity still require the report template and review discipline.
 
-## Task id short ref
+## Task Context Resolution
 
-> If `{task-id}` matches `^[#]?[0-9]+$` (bare numeric or `#`-prefixed), follow the "SKILL parameter resolver" section of `.agents/rules/task-short-id.md`; treat `{task-id}` as the resolved full `TASK-YYYYMMDD-HHMMSS` form for every downstream command.
+> The entry point may omit the task ref and also accepts a legacy positional ref or `--task <ref>` / `-t <ref>`. Separate task scope from the full arguments while preserving every business operand, then call `agent-infra-internal task-context resolve {task-scope}` where `{task-scope}` is empty, one positional ref, or one task flag. Read only `taskId` from the structured result and bind `{task-id}` to that full `TASK-YYYYMMDD-HHMMSS` for downstream commands. Pass through resolution failures without scanning tasks locally.
 
-## Step Start: Write the started Marker
-
-After prerequisites pass and before this round's first artifact action, append a started marker to task.md `## Activity Log` (same base action as this round's done entry plus a ` [started]` suffix, note `started`):
+> Resolve the task reference, then confirm that the task is in a state or directory supported by this skill and that `task.md` exists; if it cannot be located, handle it as a missing task and stop.
 
-```
-- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Review Code (Round {N}) [started]** by {agent} — started
-```
+## Step Start: Write the started Marker
 
-`ai task log` pairs it with the done entry written when the review completes onto one row (in progress → done). Format and pairing rules: see the "Activity Log started / done dual-marker convention" in `.agents/rules/task-management.md`.
+After resolving the artifact context and before this round's first artifact action, run `agent-infra-internal task-event {task-id} review-code.started --agent {agent}`.
 
 ## Steps
 
@@ -61,11 +56,9 @@ Require:
 - `.agents/workspace/active/{task-id}/task.md`
 - at least one code artifact: `code.md` or `code-r{N}.md`
 
-### 2. Determine Review Round
+### 2. Resolve the Artifact Context
 
-Scan the task directory and record:
-- `{review-round}`
-- `{review-artifact}` as `review-code.md` or `review-code-r{N}.md`
+Run `agent-infra-internal task-artifact {task-id} inspect --family review-code`. Continue only for `ready`; take the latest `{code-artifact}` from `inputs` and `{review-round}` / `{review-artifact}` from `next.round` / `next.name`. Do not scan rounds or construct names in the skill. Then run the started event and verify the returned identity.
 
 ### 3. Read Implementation and Refinement Context
 
@@ -77,7 +70,7 @@ Follow `.agents/workflows/feature-development.yaml` and inspect the full change
 - Capture `R=$(git rev-parse HEAD)` exactly once; reuse that R for this round's report, fingerprint, and task review fact, and do not re-read HEAD later as a substitute
 - `git diff --binary "$R" -- <post-review-globs>` for tracked changes
 - `git ls-files -o --exclude-standard -z -- <post-review-globs>` for untracked new files
-- `node .agents/scripts/review-diff-fingerprint.js worktree "$R"` for the reviewed diff fingerprint; write it into the report
+- Write `mode=worktree` and baseline `R` to a temporary JSON file, then call `agent-infra-internal git-workflow snapshot --input {file}` to generate the reviewed diff fingerprint `F` and reviewed snapshot tree `T` together; write both into the report
 
 > Detailed review criteria, severity rules, and reviewer expectations live in `reference/review-criteria.md`. Read `reference/review-criteria.md` before reviewing.
 > Test review gate: when `git diff` touches test files, read `.agents/rules/testing-discipline.md` first and check it item by item, especially "do not add negative assertions when a positive assertion already covers the behavior".
@@ -90,33 +83,27 @@ Create `.agents/workspace/active/{task-id}/{review-artifact}`.
 
 ### 6. Update Task Status
 
-Get the current time:
-
-```bash
-date "+%Y-%m-%d %H:%M:%S%z" | sed 's/\([+-][0-9][0-9]\)\([0-9][0-9]\)$/\1:\2/'
-```
-
 Update task.md:
-- When this round's `Overall Verdict` / `总体结论` is `Approved` / `通过`, write `last_reviewed_commit: {R}`; the presence of a worktree diff does not affect this write, and repeating the same R is idempotent
-- When this round is not Approved, preserve the existing `last_reviewed_commit`; do not advance or clear it
-- Append:
-`- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Review Code (Round {N})** by {agent} — Verdict: {Approved/Changes Requested/Rejected}, blockers: {n}, major: {n}, minor: {n}, Manual-validation: {n} → {artifact-filename}`
+- After the report, submit each new finding with `agent-infra-internal task-ledger {task-id} finding-upsert --stage code --review-artifact {review-artifact} --ordinal {n} --severity {blocker|major|minor} --evidence {review-artifact}#{anchor}`; submit prior-response dispositions with `finding-review --id {ledger-id} --status {confirmed|closed|open|needs-human-decision} --evidence {evidence}`. Do not scan ids or edit ledger rows
+- After all ledger writes, call `agent-infra-internal task-ledger {task-id} stage-status --stage code` exactly once. Derive the verdict and next-step branch from `stageStatus.canAdvance`, and blocker/major/minor event counts from `unresolvedFindingCounts`; only `canAdvance=true` permits Approved
+- Only when `canAdvance=true`, the verdict is Approved, and `T == R^{tree}`, write `last_reviewed_commit: {R}`. Clear an old value for an Approved snapshot with uncommitted differences; otherwise preserve the existing value and do not advance it
+- For an Approved exit, collect PR and required-checks facts as defined in `reference/output-templates.md`: route uncommitted/unpushed code to `commit`, no PR to `create-pr` (except no-PR flow), non-terminal checks to `watch-pr`, and route to `complete-task` only when `HEAD == last_reviewed_commit == PR head` with checks `passed|no-required`; never route by review round alone
+- After handling `last_reviewed_commit`, run `agent-infra-internal task-event {task-id} review-code.completed --agent {agent} --artifact {review-artifact} --verdict {approved|changes-requested|rejected} --blockers {n} --major {n} --minor {n} --manual-validation {n}`
 
 Always include the `Manual-validation: {n}` field in the done log, including when it is 0.
 `manual-validation` is the data source for the `Manual-validation` count folded into review rows in `ai task log`; do not add a parallel manual-verification field.
 
 If task.md contains a valid `issue_number`, perform these sync actions (skip and continue on any failure):
-- Read `.agents/rules/issue-sync.md` before syncing, and complete upstream repository detection plus permission detection
-- Set `status: in-progress` by following issue-sync.md
-- Create or update the task comment marker defined in `.agents/rules/issue-sync.md` (follow the task.md comment sync rule in issue-sync.md)
-- Publish the `{review-artifact}` comment
+- Run `agent-infra-internal platform-issue sync {task-id} --agent {agent} --status in-progress`
+- Run `agent-infra-internal platform-comment sync {task-id} --kind task --agent {agent}`
+- Run `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {review-artifact} --agent {agent}`
 
 ### 7. Verification Gate
 
 Run the verification gate to confirm the task artifact and sync state are valid:
 
 ```bash
-node .agents/scripts/validate-artifact.js gate review-code .agents/workspace/active/{task-id} {review-artifact} --format text
+agent-infra-internal task-verify {task-id} review-code.completed --artifact {review-artifact} --format text
 ```
 
 Handle the result as follows:
@@ -133,16 +120,15 @@ Keep the gate output in your reply as fresh evidence. Do not claim completion wi
 > **Important — branch labels are not values for the verdict field**. The four labels below are user-output template categories (scenarios A/B/C/D), **not** values for the `**Overall Verdict**:` field. The field accepts exactly one of the three canonical values (`Approved` / `Changes Requested` / `Rejected`, or zh-CN `通过` / `需要修改` / `拒绝`); combined phrases like `Approved with issues` will be rejected by the verify gate.
 
 Choose exactly one branch based on the findings:
-- no blockers, no major, no minor -> approved with no issues
-- no blockers, but major or minor findings -> approved with issues
-- blockers that can be fixed in a focused pass -> changes requested
+- `stageStatus.canAdvance=true` -> approved
+- `stageStatus.canAdvance=false` and focused fixes are sufficient -> changes requested
 - major redesign or re-implementation needed -> rejected
 
 manual-validation counts do not influence branch selection; they are displayed only as manual validation counts.
 
 > The full four-branch output templates, selection rules, and prohibition clauses live in `reference/output-templates.md`. Read `reference/output-templates.md` before reporting the review result.
 
-> Before rendering the final output, read `.agents/rules/next-step-output.md` and apply both of its rules: (1) render `{task-ref}` in the "Next steps" commands as the current task's short id `#NN` (see that file for lookup and fallback), while other `{task-id}` placeholders (report titles, paths) keep the full TASK-id form; (2) append the `Completed at` line as the very last line of the user-facing output (this applies to every user-facing output — success, error, and early-return paths alike, not only the success path).
+> Before rendering the final output, read `.agents/rules/next-step-output.md` and apply both of its rules: (1) render `{task-ref}` in the "Next steps" commands as the current task's short id `NN` (see that file for lookup and fallback), while other `{task-id}` placeholders (report titles, paths) keep the full TASK-id form; (2) append the `Completed at` line as the very last line of the user-facing output (this applies to every user-facing output — success, error, and early-return paths alike, not only the success path).
 
 Include all TUI command formats in the next-step output. If `.agents/.airc.json` configures custom TUIs (via `customTUIs`), read each tool's `name` and `invoke`, then add the matching command line in the same format (`${skillName}` becomes the skill name and `${projectName}` becomes the project name).