@fitlab-ai/agent-infra 0.8.5 → 0.9.0

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

@@ -12,16 +12,16 @@ After `create-pr`, continuously watch the PR's required CI checks: when everythi
 ## Behavior Boundaries / Key Rules
 
 - Only watch + self-heal the current PR's required checks; make no changes unrelated to the failing check.
-- Self-heal modifies code and `git push`es to the PR branch, but **local tests for the affected area must pass before pushing**; fix attempts have a hard cap (default 2); only self-heal locatable code-layer failures (lint / format / test / type / build), and always route non-code failures (network / permission / external service / flaky) to the help exit.
+- Self-heal publishes through Git workflow intents, but **affected tests must pass first**; the attempt cap and code-layer authorization remain unchanged.
 - The help exit is "produce-then-stop": end this round, output the blocker explanation, and wait for the user to trigger the next step — **never** ask mid-flow.
-- Bare numbers / `#NN` / `TASK-id` arguments are always resolved as task short ids (see `.agents/rules/task-short-id.md`); a PR number is passed only via `--pr <number>` / a PR URL / omission (current branch), never reusing the bare-number syntax.
+- Bare numbers / `NN` / `TASK-id` arguments are always resolved as task short ids (see `.agents/rules/task-short-id.md`); a PR number is passed only via `--pr <number>` / a PR URL / omission (current branch), never reusing the bare-number syntax.
 - After running this skill (task-anchored path), you must update task.md.
 
 Version stamp rule: before creating or updating `task.md` frontmatter, read `.agents/rules/version-stamp.md` and write or refresh `agent_infra_version`.
 
-## Task Argument Short-ID Alias
+## Task Context Resolution
 
-> If the `{task-id}` argument matches `^[#]?[0-9]+$` (a bare number or `#`-prefixed), first read the "SKILL argument parsing" section of `.agents/rules/task-short-id.md` to resolve it; subsequent commands treat `{task-id}` as the resolved full `TASK-YYYYMMDD-HHMMSS` form.
+> Keep `--pr <number>` and PR URLs on the existing PR-anchored path. Otherwise, the task path may omit the task ref and also accepts a legacy positional ref or `--task <ref>` / `-t <ref>`. Separate task scope from the full arguments, then call `agent-infra-internal task-context resolve {task-scope}` and bind `{task-id}` to the returned full `taskId`. A PR anchor and task scope are mutually exclusive.
 
 ## Step Start: Write the started Marker
 
@@ -39,22 +39,22 @@ After prerequisites pass and before this round's first artifact action, append a
 
 Resolve the target PR number `{pr#}` and an optional `{task-id}` via these deterministic branches:
 
-- Scenario A (argument omitted): use the current branch's PR number per `.agents/rules/pr-checks-commands.md`; then determine `{task-id}` via "Reverse-lookup task" below.
-- Scenario B (`#NN` / bare number / `TASK-id`, **task-anchored primary path**): when matching `^[#]?[0-9]+$`, resolve to the full `{task-id}` via "Task Argument Short-ID Alias" (on failure pass through the exit code; do not rewrite error handling); a `TASK-id` is used directly. Read `.agents/workspace/active/{task-id}/task.md` for `pr_number` as `{pr#}`; if `pr_number` is empty, follow "Error Handling" to prompt running `create-pr` first, then stop.
+- Scenario A (argument omitted): reverse-lookup the active task from the current branch, then read its `pr_number`.
+- Scenario B (omitted task ref, positional task ref, or `--task/-t`, **task-anchored primary path**): resolve the full `{task-id}` via "Task Context Resolution" and read `.agents/workspace/active/{task-id}/task.md` for `pr_number` as `{pr#}`; if `pr_number` is empty, follow "Error Handling" to prompt running `create-pr` first, then stop.
 - Scenario C (`--pr <number>` or a PR URL): use that PR number directly as `{pr#}`; then determine `{task-id}` via "Reverse-lookup task".
-- Reverse-lookup task (scenarios A / C): search `.agents/workspace/active/*/task.md` for a task whose `pr_number == {pr#}`; on a hit, take that `{task-id}` (task-anchored); on a miss, enter the "watch-only" degraded path (no `{task-id}`, skip steps 5/6).
+- Reverse-lookup task (scenarios A / C): use task context/query capabilities to find the unique active task bound to `{pr#}`. If none exists, stop and request binding first; the typed checks intent does not create a second taskless state machine.
 
 ### 2. Watch Required Checks
 
 Before running this step, read `reference/monitor-and-heal.md` and `.agents/rules/pr-checks-commands.md`.
 
-Using the watch command in `.agents/rules/pr-checks-commands.md`, poll `{pr#}`'s required checks (with an overall time cap, default 30 minutes), and classify the outcome per the "Outcome Classification" of `reference/monitor-and-heal.md` into the "all green" / "failure" / "pending" scenarios, routing to step 7 (green exit), step 3 (self-heal), or step 4 (help exit) respectively.
+Initialize the in-memory list `repairCommits=[]` for this run. Run `agent-infra-internal platform-checks watch {task-id} --interval-seconds 30 --deadline-seconds 1800`, then route its structured `checks.state` to the all-green, failure, or pending path.
 
 ### 3. Failure Self-Heal Loop
 
 Before running this step, read the "Self-Heal Decision Tree" of `reference/monitor-and-heal.md` and "Resolve a Failing Run id and Pull Logs" of `.agents/rules/pr-checks-commands.md`.
 
-For a failing check: first deterministically resolve its failing run and pull the failure logs per the rule, then classify the failure; before making any local fix, read `.agents/rules/debugging-guide.md` and locate the root cause via its four-phase flow, never blindly patching and retrying; only when it is a locatable code-layer failure, make a minimal local fix, run the relevant tests until they pass, then **stage, commit, and push the fix** (`git add` only the related files → `git commit` per `.agents/rules/commit-and-pr.md` → `git push` to the current PR branch, recording the commit SHA), and return to step 2 to re-watch. Count fix attempts; on reaching the hard cap (default 2) or when the run is unlocatable, go to step 4.
+For a locatable code-layer failure, make the minimum fix and run relevant tests. Then call `git-workflow commit` and `git-workflow push`; append only a remotely verified SHA to `repairCommits`.
 
 ### 4. Help Exit (Produce-Then-Stop)
 
@@ -77,7 +77,7 @@ Update `.agents/workspace/active/{task-id}/task.md`:
 - **Do not change** `pr_status` (keep `created`) or `current_step`
 - **Append** to `## Activity Log` (do not overwrite prior entries; `{N}` = number of existing Watch PR entries for this task + 1):
   ```
-  - {YYYY-MM-DD HH:mm:ss±HH:MM} — **Watch PR (Round {N})** by {agent} — {green: all required checks green / blocked: blocked: {summary}}
+  - {YYYY-MM-DD HH:mm:ss±HH:MM} — **Watch PR (Round {N})** by {agent} — {green: all required checks green, repair commits: {k} [{SHA summary}] / blocked: blocked: {summary}}
   ```
 
 ### 6. Verification Gate
@@ -87,7 +87,7 @@ Update `.agents/workspace/active/{task-id}/task.md`:
 Run the verification gate:
 
 ```bash
-node .agents/scripts/validate-artifact.js gate watch-pr .agents/workspace/active/{task-id} --format text
+agent-infra-internal task-verify {task-id} watch-pr.completed --format text
 ```
 
 Handle the result:
@@ -101,10 +101,12 @@ Keep the gate output in your reply as the verification evidence. Without current
 
 > On the task-anchored path, execute this step only after the gate passes.
 
-> **IMPORTANT**: All TUI command formats listed below must be output in full. Do not show only the format for the current AI agent. 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). 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 short id `#NN` (falling back to the full TASK-id when unallocated or released); (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).
+> **IMPORTANT**: All TUI command formats listed below must be output in full. Do not show only the format for the current AI agent. 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). 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 short id `NN` (falling back to the full TASK-id when unallocated or released); (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).
 
 Output per scenario:
-- "All green" + task-anchored: state that all required checks passed and the PR is ready to merge, then render the next step from the template below (`{task-ref}` becomes the short id):
+- "All green" + task-anchored: state that all required checks passed, then render exactly one exit based on whether this run created repair commits (`{task-ref}` becomes the short id):
+
+  `repairCommits.length == 0`:
 
   ```
   Next step - Complete and archive the task:
@@ -113,7 +115,15 @@ Output per scenario:
     - Codex CLI: $complete-task {task-ref}
   ```
 
-- "All green" + watch-only: state the PR is ready to merge; there is no linked task this run, so run `complete-task` against the relevant task (do not force a short-id command block when no `{task-ref}` is available).
+  `repairCommits.length > 0`:
+
+  ```
+  Next step - Re-run code review:
+    - Claude Code / OpenCode: /review-code {task-ref}
+    - Gemini CLI: /{{project}}:review-code {task-ref}
+    - Codex CLI: $review-code {task-ref}
+  ```
+
 - "Blocked": output only the step 4 blocker explanation; do not recommend a next-step command.
 
 ## Completion Checklist

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

@@ -12,16 +12,16 @@ description: >
 ## 行为边界 / 关键规则
 
 - 仅监控 + 自愈当前 PR 的 required checks；不做与失败 check 无关的改动。
-- 自愈会修改业务代码并 `git push` 到 PR 分支，但**推送前必须本地跑通相关测试**；修复尝试有硬上限（默认 2）；仅对可定位的代码层失败（lint / format / test / 类型 / 构建）自愈，非代码层（网络 / 权限 / 外部服务 / flaky）一律转求助出口。
+- 自愈通过 Git workflow intent 发布修复，但**发布前必须本地跑通相关测试**；修复上限与代码层分类授权不变。
 - 求助出口是「产出后停止」语义：停止本轮、输出阻塞说明、等待用户主动触发，**不**中途提问。
-- 裸数字 / `#NN` / `TASK-id` 入参一律按任务短号解析（见 `.agents/rules/task-short-id.md`）；PR 号只走 `--pr <number>` / PR URL / 省略（当前分支），不复用裸数字语法。
+- 裸数字 / `NN` / `TASK-id` 入参一律按任务短号解析（见 `.agents/rules/task-short-id.md`）；PR 号只走 `--pr <number>` / PR URL / 省略（当前分支），不复用裸数字语法。
 - 执行本技能（任务锚定路径）后，必须更新 task.md。
 
 版本戳规则：创建或更新 `task.md` frontmatter 时，先读取 `.agents/rules/version-stamp.md`，并写入或刷新 `agent_infra_version`。
 
-## 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
 
@@ -39,22 +39,22 @@ description: >
 
 按以下确定性分支解析出目标 PR 号 `{pr#}` 与可选 `{task-id}`：
 
-- 场景 A（省略入参）：按 `.agents/rules/pr-checks-commands.md` 取当前分支的 PR 号；随后按下方「反查任务」确定 `{task-id}`。
-- 场景 B（`#NN` / 裸数字 / `TASK-id`，**任务锚定主路径**）：匹配 `^[#]?[0-9]+$` 时按「任务入参短号别名」解析为完整 `{task-id}`（解析失败直接透传退出码，不重写错误处理）；`TASK-id` 直接采用。读 `.agents/workspace/active/{task-id}/task.md` 取 `pr_number` 作为 `{pr#}`；`pr_number` 为空时按「错误处理」提示先 `create-pr`，停止。
+- 场景 A（省略入参）：从当前分支反查 active task；定位后读取其 `pr_number`。
+- 场景 B（省略 task ref、旧位置 task ref 或 `--task/-t`，**任务锚定主路径**）：按「任务上下文解析」取得完整 `{task-id}`。读 `.agents/workspace/active/{task-id}/task.md` 取 `pr_number` 作为 `{pr#}`；`pr_number` 为空时按「错误处理」提示先 `create-pr`，停止。
 - 场景 C（`--pr <number>` 或 PR URL）：直接取该 PR 号为 `{pr#}`；随后按「反查任务」确定 `{task-id}`。
-- 反查任务（场景 A / C）：在 `.agents/workspace/active/*/task.md` 中查找 `pr_number == {pr#}` 的任务；命中则取该 `{task-id}`（任务锚定）；未命中则进入「仅监控」降级路径（无 `{task-id}`，跳过步骤 5/6）。
+- 反查任务（场景 A / C）：通过任务上下文/任务查询取得与 `{pr#}` 唯一绑定的 active task。未命中时停止并提示先绑定 PR；typed checks intent 不建立第二套无任务状态机。
 
 ### 2. 监控 required checks
 
 执行此步骤前，先读取 `reference/monitor-and-heal.md` 与 `.agents/rules/pr-checks-commands.md`。
 
-按 `.agents/rules/pr-checks-commands.md` 的监控命令对 `{pr#}` 的 required checks 轮询（含总时长上限，默认 30 分钟），按 `reference/monitor-and-heal.md` 的「结果分类」分为「全绿」/「失败」/「挂起」三个场景，分别进入步骤 7 全绿出口、步骤 3 自愈、或步骤 4 求助。
+进入本轮时初始化内存列表 `repairCommits=[]`。调用 `agent-infra-internal platform-checks watch {task-id} --interval-seconds 30 --deadline-seconds 1800`，按结构化 `checks.state` 分为「全绿」/「失败」/「挂起」，分别进入步骤 7、步骤 3 或步骤 4。
 
 ### 3. 失败自愈循环
 
 执行此步骤前，先读取 `reference/monitor-and-heal.md` 的「自愈决策树」与 `.agents/rules/pr-checks-commands.md` 的「解析失败 run id 并拉日志」。
 
-对失败 check：先按规则确定性解析其失败 run 并拉取失败日志、判定失败类别；本地修复前先读取 `.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；仅当属可定位的代码层失败时，本地最小化修复、运行对应测试通过后**暂存并提交本次修复再推送**（`git add` 仅相关文件 → 按 `.agents/rules/commit-and-pr.md` `git commit` → `git push` 到当前 PR 分支，并记录 commit SHA），再回到步骤 2 重新监控。修复尝试计数，达硬上限（默认 2）或 run 不可定位 → 转步骤 4。
+只对可定位代码层失败最小修复并测试；通过后依次调用 `git-workflow commit` 与 `git-workflow push`，仅记录远端复核成功的 SHA。达硬上限或 run 不可定位时转步骤 4。
 
 ### 4. 求助出口（产出后停止）
 
@@ -77,7 +77,7 @@ date "+%Y-%m-%d %H:%M:%S%z" | sed 's/\([+-][0-9][0-9]\)\([0-9][0-9]\)$/\1:\2/'
 - **不改** `pr_status`（保持 `created`）与 `current_step`
 - **追加**到 `## 活动日志`（不要覆盖之前的记录；`{N}` = 本任务已有 Watch PR 条目数 + 1）：
   ```
-  - {YYYY-MM-DD HH:mm:ss±HH:MM} — **Watch PR (Round {N})** by {agent} — {全绿：all required checks green / 阻塞：blocked: {简述}}
+  - {YYYY-MM-DD HH:mm:ss±HH:MM} — **Watch PR (Round {N})** by {agent} — {全绿：all required checks green, repair commits: {k} [{sha 摘要}] / 阻塞：blocked: {简述}}
   ```
 
 ### 6. 完成校验
@@ -87,7 +87,7 @@ date "+%Y-%m-%d %H:%M:%S%z" | sed 's/\([+-][0-9][0-9]\)\([0-9][0-9]\)$/\1:\2/'
 运行完成校验：
 
 ```bash
-node .agents/scripts/validate-artifact.js gate watch-pr .agents/workspace/active/{task-id} --format text
+agent-infra-internal task-verify {task-id} watch-pr.completed --format text
 ```
 
 处理结果：
@@ -101,10 +101,12 @@ node .agents/scripts/validate-artifact.js gate watch-pr .agents/workspace/active
 
 > 任务锚定路径仅在校验通过后执行本步骤。
 
-> **重要**：以下「下一步」中列出的所有 TUI 命令格式必须完整输出，不要只展示当前 AI 代理对应的格式。如果 `.agents/.airc.json` 中配置了自定义 TUI（`customTUIs`），读取每个工具的 `name` 和 `invoke`，按同样格式补充对应命令行（`${skillName}` 替换为技能名，`${projectName}` 替换为项目名）。 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」命令把 `{task-ref}` 渲染为短号 `#NN`（未分配/已释放时回退完整 TASK-id）；(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）。
+> **重要**：以下「下一步」中列出的所有 TUI 命令格式必须完整输出，不要只展示当前 AI 代理对应的格式。如果 `.agents/.airc.json` 中配置了自定义 TUI（`customTUIs`），读取每个工具的 `name` 和 `invoke`，按同样格式补充对应命令行（`${skillName}` 替换为技能名，`${projectName}` 替换为项目名）。 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」命令把 `{task-ref}` 渲染为短号 `NN`（未分配/已释放时回退完整 TASK-id）；(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）。
 
 按场景输出：
-- 「全绿」+ 任务锚定：说明所有 required checks 已通过、PR 可合入，并按下方模板渲染下一步（`{task-ref}` 替换为短号）：
+- 「全绿」+ 任务锚定：说明所有 required checks 已通过，并只按本轮是否产生修复 commit 渲染一个出口（`{task-ref}` 替换为短号）：
+
+  `repairCommits.length == 0`：
 
   ```
   下一步 - 完成并归档任务：
@@ -113,7 +115,15 @@ node .agents/scripts/validate-artifact.js gate watch-pr .agents/workspace/active
     - Codex CLI：$complete-task {task-ref}
   ```
 
-- 「全绿」+ 仅监控降级：说明 PR 可合入；本次无关联任务，请对相应任务运行 `complete-task`（无 `{task-ref}` 可渲染时不强行输出短号命令块）。
+  `repairCommits.length > 0`：
+
+  ```
+  下一步 - 重新代码审查：
+    - Claude Code / OpenCode：/review-code {task-ref}
+    - Gemini CLI：/{{project}}:review-code {task-ref}
+    - Codex CLI：$review-code {task-ref}
+  ```
+
 - 「阻塞」：仅输出步骤 4 的阻塞说明，不推荐下一步命令。
 
 ## 完成检查清单
@@ -127,7 +137,7 @@ node .agents/scripts/validate-artifact.js gate watch-pr .agents/workspace/active
 
 ## 停止
 
-完成检查清单后立即停止。全绿出口等待用户运行 `complete-task`；阻塞出口等待用户裁定。
+完成检查清单后立即停止。全绿出口等待用户运行所选的 `complete-task` 或 `review-code`；阻塞出口等待用户裁定。
 
 ## 注意事项
 

package/templates/.agents/skills/watch-pr/config/verify.json

@@ -15,8 +15,7 @@
       ]
     },
     "activity-log": {
-      "expected_action_pattern": "(Watch PR|Watching PR) \\(Round \\d+\\)",
-      "freshness_minutes": 30
+      "expected_action_pattern": "(Watch PR|Watching PR) \\(Round \\d+\\)"
     }
   }
 }

package/templates/.agents/skills/watch-pr/reference/monitor-and-heal.en.md

@@ -30,8 +30,8 @@ For each failing check, decide "self-heal" vs "ask for help" in this order:
    - Before fixing, run `git status -s` to record the working tree and ensure only changes related to this failure are included.
    - Locate and make a minimal fix per the logs (touch only code / tests / config related to that failure).
    - Run the relevant tests: prefer the local command for the failing job; otherwise read the project `test` skill and select its declared core or full validation command. If neither command is known, ask for help. **Do not commit or push before tests pass.**
-   - After tests pass, publish the fix: per `.agents/rules/commit-and-pr.md` stage only the related files (`git add <paths>`, avoid `git add -A` pulling in unrelated changes) → create the fix commit (`git commit`) → `git push` to the current PR branch.
-   - Record the fix commit SHA, increment the fix count, and return to SKILL step 2 to re-watch.
+   - After tests pass, call `git-workflow commit` and `git-workflow push`, then verify the remote SHA.
+   - Append the fix commit SHA to this run's `repairCommits`, increment the fix count, and return to SKILL step 2. When checks turn green, an empty list routes to `complete-task`; a non-empty list routes to `review-code`.
    - Never make unrelated "drive-by" optimizations; never loosen / skip the failing assertion to "make it green".
 
 ## Help Report Template

package/templates/.agents/skills/watch-pr/reference/monitor-and-heal.zh-CN.md

@@ -30,8 +30,8 @@ unknown: help
    - 自愈前先 `git status -s` 记录当前工作树，确保后续只纳入与本次失败相关的改动。
    - 在本地按日志定位并最小化修复（只动与该失败相关的代码 / 测试 / 配置）。
    - 运行对应测试：优先失败 job 对应的本地命令；否则读取项目 `test` skill，选择其中声明的 core 或 full 验证命令。两者均未知时进入求助出口。**测试通过前不得提交或推送。**
-   - 测试通过后发布修复：按 `.agents/rules/commit-and-pr.md` 仅暂存本次相关文件（`git add <相关路径>`，避免 `git add -A` 卷入无关改动）→ 创建修复 commit（`git commit`）→ `git push` 到当前 PR 分支。
-   - 记录本次修复的 commit SHA，修复计数 +1，回到 SKILL 步骤 2 重新监控。
+   - 测试通过后发布修复：把相关路径、message 与 expected HEAD 写入 intent JSON，调用 `git-workflow commit`，再调用 `git-workflow push` 并复核远端 SHA。
+   - 将本次修复的 commit SHA 追加到当前运行的 `repairCommits`，修复计数 +1，回到 SKILL 步骤 2 重新监控；全绿时列表为空走 `complete-task`，非空走 `review-code`。
    - 绝不执行与失败无关的「顺手优化」；不放宽 / 跳过失败的断言来「修绿」。
 
 ## 求助报告模板

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

@@ -62,7 +62,12 @@ pr_status: pending             # PR status: pending (default) | created (PR crea
 
 ## Human Rulings
 
-<!-- Humans record rulings for needs-human-decision decisions here and flip matching HD- rows in the Review Disagreement Ledger to human-decided. -->
+<!-- Use ai decide <task-ref> <ordinal|ledger-id> [--needs-implementation true|false] <decision> for needs-human-decision rulings; code-stage rulings must explicitly declare whether implementation is required. -->
+
+## Implementation Inputs
+
+| id | ledger_id | decision_evidence | stage | needs_implementation | decided_at | status | consumed_by |
+|----|-----------|-------------------|-------|----------------------|------------|--------|-------------|
 
 ## Workflow Warnings
 

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

@@ -62,7 +62,12 @@ pr_status: pending             # PR 状态：pending（默认）| created（已
 
 ## 人工裁决
 
-<!-- 人类在此记录对 needs-human-decision 决策的裁定，并把 ## 审查分歧账本 对应 HD- 行翻为 human-decided。 -->
+<!-- 使用 ai decide <task-ref> <序号|账本ID> [--needs-implementation true|false] <裁决内容> 写入 needs-human-decision 裁定；code 阶段必须显式声明是否需要实现。 -->
+
+## 实现输入
+
+| id | ledger_id | decision_evidence | stage | needs_implementation | decided_at | status | consumed_by |
+|----|-----------|-------------------|-------|----------------------|------------|--------|-------------|
 
 ## 工作流告警
 

package/templates/.claude/commands/analyze-task.en.md

@@ -1,6 +1,6 @@
 ---
 description: "Analyze a task and produce a requirements document"
-usage: "/analyze-task <task-id>"
+usage: "/analyze-task [task-ref | --task <ref>]"
 ---
 
 Read and execute the analyze-task skill from `.agents/skills/analyze-task/SKILL.md`.

package/templates/.claude/commands/analyze-task.zh-CN.md

@@ -1,6 +1,6 @@
 ---
 description: "分析任务并输出需求分析文档"
-usage: "/analyze-task <task-id>"
+usage: "/analyze-task [task-ref | --task <ref>]"
 ---
 
 读取并执行 `.agents/skills/analyze-task/SKILL.md` 中的 analyze-task 技能。

package/templates/.claude/commands/block-task.en.md

@@ -1,6 +1,6 @@
 ---
 description: "Mark a task as blocked and record the reason"
-usage: "/block-task <task-id> [reason]"
+usage: "/block-task [task-ref | --task <ref>] [reason]"
 disable-model-invocation: true
 ---
 

package/templates/.claude/commands/block-task.zh-CN.md

@@ -1,6 +1,6 @@
 ---
 description: "标记任务为阻塞状态并记录原因"
-usage: "/block-task <task-id> [reason]"
+usage: "/block-task [task-ref | --task <ref>] [reason]"
 disable-model-invocation: true
 ---
 

package/templates/.claude/commands/cancel-task.en.md

@@ -1,6 +1,6 @@
 ---
 description: "Cancel a task and archive it"
-usage: "/cancel-task <task-id> <reason>"
+usage: "/cancel-task [task-ref | --task <ref>] <reason>"
 disable-model-invocation: true
 ---
 

package/templates/.claude/commands/cancel-task.zh-CN.md

@@ -1,6 +1,6 @@
 ---
 description: "取消任务并归档"
-usage: "/cancel-task <task-id> <reason>"
+usage: "/cancel-task [task-ref | --task <ref>] <reason>"
 disable-model-invocation: true
 ---
 

package/templates/.claude/commands/check-task.en.md

@@ -1,6 +1,6 @@
 ---
 description: "Check a task's current status and progress"
-usage: "/check-task <task-id>"
+usage: "/check-task [task-ref | --task <ref>]"
 disable-model-invocation: true
 ---
 

package/templates/.claude/commands/check-task.zh-CN.md

@@ -1,6 +1,6 @@
 ---
 description: "查看任务的当前状态和进度"
-usage: "/check-task <task-id>"
+usage: "/check-task [task-ref | --task <ref>]"
 disable-model-invocation: true
 ---
 

package/templates/.claude/commands/code-task.en.md

@@ -1,6 +1,6 @@
 ---
 description: "Code a task from its technical plan and output a report"
-usage: "/code-task <task-id>"
+usage: "/code-task [task-ref | --task <ref>]"
 ---
 
 Read and execute the code-task skill from `.agents/skills/code-task/SKILL.md`.

package/templates/.claude/commands/code-task.zh-CN.md

@@ -1,6 +1,6 @@
 ---
 description: "根据技术方案编码任务并输出报告"
-usage: "/code-task <task-id>"
+usage: "/code-task [task-ref | --task <ref>]"
 ---
 
 读取并执行 `.agents/skills/code-task/SKILL.md` 中的 code-task 技能。

package/templates/.claude/commands/commit.en.md

@@ -1,5 +1,6 @@
 ---
 description: "Commit the current changes to Git"
+usage: "/commit [task-ref | --task <ref>]"
 ---
 
 Read and execute the commit skill from `.agents/skills/commit/SKILL.md`.

package/templates/.claude/commands/commit.zh-CN.md

@@ -1,5 +1,6 @@
 ---
 description: "提交当前变更到 Git"
+usage: "/commit [task-ref | --task <ref>]"
 ---
 
 读取并执行 `.agents/skills/commit/SKILL.md` 中的 commit 技能。

package/templates/.claude/commands/complete-manual-validation.en.md

@@ -1,6 +1,6 @@
 ---
 description: "Mark PR manual validation as completed and update the summary comment"
-usage: "/complete-manual-validation <task-id> [pr-ref] <verification-summary>"
+usage: "/complete-manual-validation [task-ref | --task <ref>] [pr-ref] <verification-summary>"
 disable-model-invocation: true
 ---
 

package/templates/.claude/commands/complete-manual-validation.zh-CN.md

@@ -1,6 +1,6 @@
 ---
 description: "标记 PR 人工验证已完成并更新摘要评论"
-usage: "/complete-manual-validation <task-id> [pr-ref] <verification-summary>"
+usage: "/complete-manual-validation [task-ref | --task <ref>] [pr-ref] <verification-summary>"
 disable-model-invocation: true
 ---
 

package/templates/.claude/commands/complete-task.en.md

@@ -1,6 +1,6 @@
 ---
 description: "Mark a task as completed and archive it"
-usage: "/complete-task <task-id>"
+usage: "/complete-task [task-ref | --task <ref>]"
 ---
 
 Read and execute the complete-task skill from `.agents/skills/complete-task/SKILL.md`.

package/templates/.claude/commands/complete-task.zh-CN.md

@@ -1,6 +1,6 @@
 ---
 description: "标记任务完成并归档"
-usage: "/complete-task <task-id>"
+usage: "/complete-task [task-ref | --task <ref>]"
 ---
 
 读取并执行 `.agents/skills/complete-task/SKILL.md` 中的 complete-task 技能。

package/templates/.claude/commands/create-pr.en.md

@@ -1,6 +1,6 @@
 ---
 description: "Create a Pull Request to a target branch"
-usage: "/create-pr [task-id] [target-branch]"
+usage: "/create-pr [task-ref | --task <ref>] [target-branch]"
 ---
 
 Read and execute the create-pr skill from `.agents/skills/create-pr/SKILL.md`.

package/templates/.claude/commands/create-pr.zh-CN.md

@@ -1,6 +1,6 @@
 ---
 description: "创建 Pull Request 到目标分支"
-usage: "/create-pr [task-id] [target-branch]"
+usage: "/create-pr [task-ref | --task <ref>] [target-branch]"
 ---
 
 读取并执行 `.agents/skills/create-pr/SKILL.md` 中的 create-pr 技能。

package/templates/.claude/commands/plan-task.en.md

@@ -1,6 +1,6 @@
 ---
 description: "Design a technical plan for a task"
-usage: "/plan-task <task-id>"
+usage: "/plan-task [task-ref | --task <ref>]"
 ---
 
 Read and execute the plan-task skill from `.agents/skills/plan-task/SKILL.md`.

package/templates/.claude/commands/plan-task.zh-CN.md

@@ -1,6 +1,6 @@
 ---
 description: "为任务设计技术方案和实施计划"
-usage: "/plan-task <task-id>"
+usage: "/plan-task [task-ref | --task <ref>]"
 ---
 
 读取并执行 `.agents/skills/plan-task/SKILL.md` 中的 plan-task 技能。

package/templates/.claude/commands/review-analysis.en.md

@@ -1,6 +1,6 @@
 ---
 description: "Review a requirement analysis report"
-usage: "/review-analysis <task-id>"
+usage: "/review-analysis [task-ref | --task <ref>]"
 ---
 
 Read and execute the review-analysis skill from `.agents/skills/review-analysis/SKILL.md`.

package/templates/.claude/commands/review-analysis.zh-CN.md

@@ -1,6 +1,6 @@
 ---
 description: "审查需求分析报告"
-usage: "/review-analysis <task-id>"
+usage: "/review-analysis [task-ref | --task <ref>]"
 ---
 
 读取并执行 `.agents/skills/review-analysis/SKILL.md` 中的 review-analysis 技能。

package/templates/.claude/commands/review-code.en.md

@@ -1,6 +1,6 @@
 ---
 description: "Review code implementation and output a code review report"
-usage: "/review-code <task-id>"
+usage: "/review-code [task-ref | --task <ref>]"
 ---
 
 Read and execute the review-code skill from `.agents/skills/review-code/SKILL.md`.

package/templates/.claude/commands/review-code.zh-CN.md

@@ -1,6 +1,6 @@
 ---
 description: "审查代码实现并输出代码审查报告"
-usage: "/review-code <task-id>"
+usage: "/review-code [task-ref | --task <ref>]"
 ---
 
 读取并执行 `.agents/skills/review-code/SKILL.md` 中的 review-code 技能。

package/templates/.claude/commands/review-plan.en.md

@@ -1,6 +1,6 @@
 ---
 description: "Review a technical plan"
-usage: "/review-plan <task-id>"
+usage: "/review-plan [task-ref | --task <ref>]"
 ---
 
 Read and execute the review-plan skill from `.agents/skills/review-plan/SKILL.md`.

package/templates/.claude/commands/review-plan.zh-CN.md

@@ -1,6 +1,6 @@
 ---
 description: "审查技术方案"
-usage: "/review-plan <task-id>"
+usage: "/review-plan [task-ref | --task <ref>]"
 ---
 
 读取并执行 `.agents/skills/review-plan/SKILL.md` 中的 review-plan 技能。

package/templates/.claude/commands/watch-pr.en.md

@@ -1,6 +1,6 @@
 ---
 description: "Watch a PR's required checks and self-heal on failure"
-usage: "/watch-pr [task-id | --pr <number>]"
+usage: "/watch-pr [task-ref | --task <ref> | --pr <number>]"
 ---
 
 Read and execute the watch-pr skill from `.agents/skills/watch-pr/SKILL.md`.

package/templates/.claude/commands/watch-pr.zh-CN.md

@@ -1,6 +1,6 @@
 ---
 description: "监控 PR 的 required checks 并在失败时自愈"
-usage: "/watch-pr [task-id | --pr <number>]"
+usage: "/watch-pr [task-ref | --task <ref> | --pr <number>]"
 ---
 
 读取并执行 `.agents/skills/watch-pr/SKILL.md` 中的 watch-pr 技能。

package/templates/.gemini/commands/_project_/analyze-task.en.toml

@@ -2,6 +2,8 @@ description = "Analyze a task and produce a requirements document"
 prompt = """
 Analyze task {{args}}.
 
+Task scope may be omitted or explicitly overridden with `--task <ref>` / `-t <ref>`; dedicated anchors such as `--pr` retain their existing meaning.
+
 Read and execute the analyze-task skill from `.agents/skills/analyze-task/SKILL.md`.
 
 Follow all steps defined in the skill exactly.

package/templates/.gemini/commands/_project_/analyze-task.zh-CN.toml

@@ -2,6 +2,8 @@ description = "分析任务并输出需求分析文档"
 prompt = """
 分析任务 {{args}}。
 
+任务 scope 可省略，或通过 `--task <ref>` / `-t <ref>` 显式覆盖；`--pr` 等专用锚点保持原语义。
+
 读取并执行 `.agents/skills/analyze-task/SKILL.md` 中的 analyze-task 技能。
 
 严格按照技能中定义的所有步骤执行。

package/templates/.gemini/commands/_project_/block-task.en.toml

@@ -2,6 +2,8 @@ description = "Mark a task as blocked and record the reason"
 prompt = """
 Block task: {{args}}
 
+Task scope may be omitted or explicitly overridden with `--task <ref>` / `-t <ref>`; dedicated anchors such as `--pr` retain their existing meaning.
+
 Read and execute the block-task skill from `.agents/skills/block-task/SKILL.md`.
 
 Follow all steps defined in the skill exactly.

package/templates/.gemini/commands/_project_/block-task.zh-CN.toml

@@ -2,6 +2,8 @@ description = "标记任务为阻塞状态并记录原因"
 prompt = """
 阻塞任务：{{args}}
 
+任务 scope 可省略，或通过 `--task <ref>` / `-t <ref>` 显式覆盖；`--pr` 等专用锚点保持原语义。
+
 读取并执行 `.agents/skills/block-task/SKILL.md` 中的 block-task 技能。
 
 严格按照技能中定义的所有步骤执行。

package/templates/.gemini/commands/_project_/cancel-task.en.toml

@@ -2,6 +2,8 @@ description = "Cancel a task and archive it"
 prompt = """
 Cancel task: {{args}}
 
+Task scope may be omitted or explicitly overridden with `--task <ref>` / `-t <ref>`; dedicated anchors such as `--pr` retain their existing meaning.
+
 Read and execute the cancel-task skill from `.agents/skills/cancel-task/SKILL.md`.
 
 Follow all steps defined in the skill exactly.

package/templates/.gemini/commands/_project_/cancel-task.zh-CN.toml

@@ -2,6 +2,8 @@ description = "取消任务并归档"
 prompt = """
 取消任务：{{args}}
 
+任务 scope 可省略，或通过 `--task <ref>` / `-t <ref>` 显式覆盖；`--pr` 等专用锚点保持原语义。
+
 读取并执行 `.agents/skills/cancel-task/SKILL.md` 中的 cancel-task 技能。
 
 严格按照技能中定义的所有步骤执行。