ln-1000-pipeline-orchestrator

**路径：**文件路径（references/、../ln-*）相对于此技能目录。

**类型：**L1 编排器 **类别：**1000 流水线

流水线编排器

通过在单一上下文中以 Skill() 调用协调器，并根据协调器阶段产物推进流程，驱动所选 Story 完成整个流水线（任务规划 -> 验证 -> 执行 -> 质量门禁）。

目的与范围

• 解析看板并显示可供用户选择的 Story
• 在执行前一次性提出业务问题；自主做出技术决策
• 驱动所选 Story 完成 4 个阶段：ln-300 -> ln-310 -> ln-400 -> ln-500
• 每个阶段结束后编写阶段说明和检查点，以便报告和恢复
• 处理失败、重试、返工循环，并在需要时升级给用户
• 生成包含分支名称、Git 统计信息和 Agent 审查信息的流水线报告

层级

L0: ln-1000-pipeline-orchestrator (sequential Skill calls, single context)
  +-- Skill("ln-300") — task decomposition (internally manages stateful task-plan workers)
  +-- Skill("ln-310") — validation (internally launches configured external review agents when available)
  +-- Skill("ln-400") — execution (internally dispatches stateful task workers)
  +-- Skill("ln-500") — quality gate (internally runs artifact-first ln-510/ln-520, verdict, finalization)

**核心原则：**ln-1000 通过 Skill 工具调用协调器。每个协调器负责管理自己的内部工作者调度，并生成阶段产物。ln-1000 不会修改现有技能——它会像人工操作员一样调用这些技能，并将协调器产物视为主要完成信号。

任务存储模式

**必须阅读：**加载 references/environment_state_contract.md 和 references/storage_mode_detection.md

提取：task_provider = Task Management -> Provider（linear | file）。

适用场景

• 有一个可处理的 Story——由用户选择
• 需要端到端自动化：任务规划 -> 验证 -> 执行 -> 质量门禁
• 希望通过流水线报告对 Story 进行受控处理

流水线：4 阶段状态机

**必须阅读：**加载 references/pipeline_states.md，了解状态转换规则和守卫条件。 **必须阅读：**加载 references/loop_health_contract.md

Backlog       --> Stage 0 (ln-300) --> Backlog      --> Stage 1 (ln-310) --> Todo
(no tasks)        create tasks         (tasks exist)      validate            |
                                                          | NO-GO             |
                                                          v                   v
                                                       [retry/ask]    Stage 2 (ln-400)
                                                                             |
                                                                             v
                                                                      To Review
                                                                             |
                                                                             v
                                                                      Stage 3 (ln-500)
                                                                       |          |
                                                                      PASS       FAIL
                                                                       |          v
                                                                      Done    To Rework -> Stage 2
                                                               (branch pushed)  (max 2 cycles)

阶段	技能	输入状态	输出状态
0	ln-300-task-coordinator	Backlog（无任务）	Backlog（已创建任务）
1	ln-310-multi-agent-validator	Backlog（存在任务）	Todo
2	ln-400-story-executor	Todo / To Rework	To Review
3	ln-500-story-quality-gate	To Review	Done / To Rework

工作流

阶段 0：恢复检查

PIPELINE="{skill_repo}/ln-1000-pipeline-orchestrator/scripts/cli.mjs"
recovery = Bash: node $PIPELINE status

IF recovery.active == true:
  # Previous run interrupted — resume from CLI state
  1. Extract: story_id, stage, resume_action from recovery JSON
  2. Read already-written stage artifacts and runtime state
  3. Re-read kanban board -> secondary verification only
  4. IF recovery.state.worktree_dir exists: cd {recovery.state.worktree_dir}
  5. Jump to Phase 4, starting from resume_action

IF recovery.active == false:
  # Fresh start — proceed to Phase 1

阶段 1：发现、解析看板并选择 Story

**必须阅读：**加载 references/kanban_parser.md，了解解析模式。

1. 自动发现 docs/tasks/kanban_board.md（或通过存储模式操作调用 Linear API）
2. 从目标项目的 CLAUDE.md 提取项目概要（不是技能仓库）：

   project_brief = {
     name: <from H1 or first line>,
     tech: <from Development Commands / tech references>,
     type: <inferred: "CLI", "API", "web app", "library">,
     key_rules: <2-3 critical rules>
   }
   IF not found: project_brief = { name: basename(project_root), tech: "unknown" }
   

3. 解析所有状态分区：Backlog、Todo、In Progress、To Review、To Rework
4. 提取 Story 列表，包含：ID、标题、状态、Epic 名称、是否存在任务
5. 筛选：跳过状态为 Done、Postponed、Canceled 的 Story
6. 检测每个 Story 是否存在任务：
   • 存在 _(tasks not created yet)_ -> 无任务 -> 阶段 0
   • 存在任务行（缩进 4 个空格）-> 存在任务 -> 阶段 1+
7. 确定每个 Story 的目标阶段（参见 references/pipeline_states.md 中的阶段到状态映射）
8. 显示可选 Story 并让用户选择一个：

   Project: {project_brief.name} ({project_brief.tech})
   
   Available Stories:
   | # | Story | Status | Stage | Skill | Epic |
   |---|-------|--------|-------|-------|------|
   | 1 | PROJ-42: Auth endpoint | To Review | 3 | ln-500 | Epic: Auth |
   | 2 | PROJ-55: CRUD users | Backlog (no tasks) | 0 | ln-300 | Epic: Users |
   | 3 | PROJ-60: Dashboard | Todo | 2 | ln-400 | Epic: UI |
   
   AskUserQuestion: "Which story to process? Enter # or Story ID."
   

9. 保存所选 Story。仅提取所选 Story 的概要：

   description = tracker getStory(selected_story.id).body  // provider-specific transport per tracker_provider_contract.md
   story_briefs[id] = parse  markers
   IF no markers: story_briefs[id] = { tech: project_brief.tech, keyFiles: "unknown" }
   

阶段 2：执行前提问（一次性）

1. 加载所选 Story 的描述（仅元数据）
2. 检查业务歧义——以下问题：
   • 无法在代码库、文档或标准中找到答案
   • 需要业务/产品决策（支付服务商、身份验证流程、UI 偏好）
3. 将所有业务问题汇总到单个 AskUserQuestion 中
4. 技术问题——使用 project_brief 解决：
   • 库版本：MCP Ref / Context7（针对 project_brief.tech 生态）
   • 架构模式：project_brief.key_rules
   • 标准合规性：由 ln-310 阶段 2 处理

**如果未发现业务问题，则跳过阶段 2。**直接进入阶段 3。

阶段 3：流水线设置

3.0 Linear 状态缓存（仅限 Linear 模式）

IF storage_mode == "linear":
  statuses = list_issue_statuses(teamId=team_id)
  status_cache = {status.name: status.id FOR status IN statuses}

  REQUIRED = ["Backlog", "Todo", "In Progress", "To Review", "To Rework", "Done"]
  missing = [s for s in REQUIRED if s not in status_cache]
  IF missing: ABORT "Missing Linear statuses: {missing}. Configure workflow."

3.1 前置检查：设置验证

验证目标项目中的 .claude/settings.local.json：

• defaultMode = "bypassPermissions"（协调器生成的 Agent 工作线程必须使用此设置）

3.2 工作树隔离

必须阅读： 加载 references/git_worktree_fallback.md

branch_check = git branch --show-current
IF branch_check matches feature/* / optimize/* / upgrade/* / modernize/*:
  worktree_dir = CWD
  project_root = CWD
  branch = branch_check
ELSE:
  story_slug = slugify(selected_story.title)
  branch = "feature/{selected_story.id}-{story_slug}"
  worktree_dir = ".hex-skills/worktrees/story-{selected_story.id}"
  project_root = CWD

  changes = git diff HEAD
  IF changes not empty:
    git diff HEAD > .hex-skills/pipeline/carry-changes.patch

  git fetch origin
  base_branch = detect per references/git_scope_detection.md §Base Branch Detection
  git worktree add -b {branch} {worktree_dir} origin/{base_branch}

  IF .hex-skills/pipeline/carry-changes.patch exists:
    git -C {worktree_dir} apply .hex-skills/pipeline/carry-changes.patch && rm .hex-skills/pipeline/carry-changes.patch
    IF apply fails: WARN user "Patch conflicts -- continuing without uncommitted changes"

  cd {worktree_dir}    # All subsequent Skill calls inherit this CWD

协调器启动时会自行检测 feature/* -> 跳过创建自己的工作树（ln-400 阶段 1 步骤 5）。

3.3 初始化流水线状态

Bash: node $PIPELINE start \
  --story {selected_story.id} \
  --title "{selected_story.title}" \
  --storage {storage_mode} \
  --project-brief '{JSON.stringify(project_brief)}' \
  --story-briefs '{JSON.stringify(story_briefs)}' \
  --business-answers '{JSON.stringify(business_answers)}' \
  --status-cache '{JSON.stringify(status_cache)}' \
  --skill-repo-path "{skill_repo}" \
  --worktree-dir "{worktree_dir}" \
  --branch-name "{branch}"

IF result.recovery == true:
  # Active run found — resume instead of fresh start
  Jump to Phase 4 using result.state

3.4 防止休眠（仅限 Windows）

IF platform == "win32":
  Bash: cp {skill_repo}/ln-1000-pipeline-orchestrator/references/scripts/hooks/prevent-sleep.ps1 .hex-skills/pipeline/prevent-sleep.ps1
  Bash: powershell -ExecutionPolicy Bypass -WindowStyle Hidden -File .hex-skills/pipeline/prevent-sleep.ps1 &
  sleep_prevention_pid = $!

阶段 4：流水线执行

必须阅读： 加载 references/phases/phase4_flow.md，了解 ASSERT 防护、阶段说明、上下文恢复和错误处理。 必须阅读： 加载 references/checkpoint_format.md，了解检查点架构。

# --- INITIALIZATION ---
id = selected_story.id
target_stage = determine_stage(selected_story)    # pipeline_states.md / guards.mjs

# --- PROGRESS TRACKER (survives compaction) ---
TodoWrite([
  {content: "Stage 0: Task Decomposition (ln-300)", status: "pending", activeForm: "Decomposing tasks"},
  {content: "Stage 1: Validation (ln-310)", status: "pending", activeForm: "Validating story"},
  {content: "Stage 2: Execution (ln-400)", status: "pending", activeForm: "Executing tasks"},
  {content: "Stage 3: Quality Gate (ln-500)", status: "pending", activeForm: "Running quality gate"},
  {content: "Pipeline Report + Cleanup", status: "pending", activeForm: "Generating report"}
])

# --- STAGE 0: Task Decomposition ---
IF target_stage <= 0:
  Bash: node $PIPELINE advance --story {id} --to STAGE_0
  Skill(skill: "ln-300-task-coordinator", args: "{id}")
  Read Stage 0 coordinator artifact -> Bash: node $PIPELINE record-stage-summary --story {id} --payload '{...}'
  ASSERT Stage 0 artifact: status=completed, stage=0
  IF ASSERT fails: Bash: node $PIPELINE record-loop-health --story {id} --stage 0 --payload '{"error":"Stage 0 ASSERT failed","progress_detected":false}'
  Re-read kanban only as secondary assertion
  IF ASSERT fails: Bash: node $PIPELINE pause --story {id} --reason "Stage 0 artifact missing or invalid"; ESCALATE
  Write stage notes: .hex-skills/pipeline/stage_0_notes_{id}.md (Key Decisions, Artifacts)
  Bash: node $PIPELINE checkpoint --story {id} --stage 0 --plan-score {score} --tasks-remaining '{JSON tasks}' --last-action "Tasks created"

# --- STAGE 1: Validation ---
IF target_stage <= 1:
  Bash: node $PIPELINE advance --story {id} --to STAGE_1
  IF advance fails (guard rejection): handle per error.recovery
  Skill(skill: "ln-310-multi-agent-validator", args: "{id}")
  Read Stage 1 coordinator artifact -> Bash: node $PIPELINE record-stage-summary --story {id} --payload '{...}'
  ASSERT artifact verdict = GO and readiness_score >= 5
  IF NO-GO:
    Bash: node $PIPELINE advance --story {id} --to STAGE_1    # retry (guard auto-increments validation_retries)
    IF advance fails: Bash: node $PIPELINE pause --story {id} --reason "Validation retry exhausted"; ESCALATE
    Skill(skill: "ln-310-multi-agent-validator", args: "{id}")    # retry
    Read retry Stage 1 artifact -> Bash: node $PIPELINE record-stage-summary --story {id} --payload '{...}'
  IF same ASSERT failure repeats without new Stage 1 artifact/checkpoint/status evidence:
    Bash: node $PIPELINE record-loop-health --story {id} --stage 1 --payload '{"error":"Stage 1 ASSERT failed","progress_detected":false}'
    IF result.pause.pause == true: ESCALATE using result.state.paused_reason
  Re-read kanban only as secondary assertion
  IF still NOT Todo: Bash: node $PIPELINE pause --story {id} --reason "Validation artifact or status invalid"; ESCALATE
  Extract agents_info from Stage 1 artifact metadata or review runtime state
  Write stage notes: .hex-skills/pipeline/stage_1_notes_{id}.md (Verdict, Agent Review, Key Decisions)
  Bash: node $PIPELINE checkpoint --story {id} --stage 1 --verdict {verdict} --readiness {score} --agents-info "{agents}" --last-action "Validated"

# --- COMPACTION RECOVERY (replaces old COMPACTION GUARD) ---
# If context compacted and vars lost: Bash: node $PIPELINE status --story {id}
# Extract resume_action from JSON -> continue from there. No manual JSON reads needed.

# --- STAGE 2+3 LOOP (rework cycle, managed by CLI guards) ---
WHILE true:

  # STAGE 2: Execution
  IF target_stage <= 2 OR (status shows rework cycle):
    Bash: node $PIPELINE advance --story {id} --to STAGE_2
    IF advance fails: Bash: node $PIPELINE pause --story {id} --reason "{error}"; ESCALATE; BREAK
    Skill(skill: "ln-400-story-executor", args: "{id}")
    Read Stage 2 coordinator artifact -> Bash: node $PIPELINE record-stage-summary --story {id} --payload '{...}'
    ASSERT artifact story_status = To Review
    IF ASSERT fails: Bash: node $PIPELINE record-loop-health --story {id} --stage 2 --payload '{"error":"Stage 2 ASSERT failed","progress_detected":false}'
    Re-read kanban only as secondary assertion
    IF ASSERT fails: Bash: node $PIPELINE pause --story {id} --reason "Stage 2 artifact missing or invalid"; ESCALATE; BREAK
    git_stats = parse `git diff --stat origin/{base_branch}..HEAD`
    Write stage notes: .hex-skills/pipeline/stage_2_notes_{id}.md (Key Decisions, Git commits)
    Bash: node $PIPELINE checkpoint --story {id} --stage 2 --tasks-completed '{JSON done}' --git-stats '{JSON stats}' --last-action "Implementation complete"

  # STAGE 3: Quality Gate (IMPOSSIBLE TO SKIP — next line after Stage 2)
  Bash: node $PIPELINE advance --story {id} --to STAGE_3
  Skill(skill: "ln-500-story-quality-gate", args: "{id}")
  Read Stage 3 coordinator artifact -> Bash: node $PIPELINE record-stage-summary --story {id} --payload '{...}'
  IF repeated identical quality FAIL has no new artifact/task/code delta:
    Bash: node $PIPELINE record-loop-health --story {id} --stage 3 --payload '{"error":"Stage 3 repeated quality FAIL","progress_detected":false}'
    IF result.pause.pause == true: ESCALATE using result.state.paused_reason
  Extract quality verdict, score, agents_info from Stage 3 artifact
  Re-read kanban only as secondary assertion
  Write stage notes: .hex-skills/pipeline/stage_3_notes_{id}.md (Verdict, Score, Agent Review, Branch)
  Bash: node $PIPELINE checkpoint --story {id} --stage 3 --verdict {verdict} --quality-score {score} --agents-info "{agents}" --last-action "Quality gate: {verdict}"

  IF Story status = Done:
    Bash: node $PIPELINE advance --story {id} --to DONE
    BREAK

  IF Story status = To Rework:
    Read Stage 3 artifact `metadata.rework_hint` for blocking_categories and suggested_focus
    Bash: node $PIPELINE advance --story {id} --to STAGE_2    # guard auto-increments quality_cycles
    IF advance fails (quality_cycles >= 2):
      Bash: node $PIPELINE pause --story {id} --reason "Quality gate failed 2 times"
      ESCALATE: "Quality gate failed after max cycles. Manual review needed."
      BREAK
    # Pass rework focus to ln-400:
    Skill(skill: "ln-400-story-executor", args: "{id} --rework-focus {blocking_categories}")
    CONTINUE

  Bash: node $PIPELINE pause --story {id} --reason "Unexpected Stage 3 outcome"
  ESCALATE: "Story ended Stage 3 in unexpected status. Manual review needed."
  BREAK

### Stop Conditions (Quality Cycle)

| Condition | Action |
|-----------|--------|
| All tasks Done + Story = Done | STOP — Story completed successfully |
| `quality_cycles >= 2` | STOP — ESCALATE: "Quality gate failed after max cycles. Manual review needed." |
| Validation retry fails (NO-GO after retry) | STOP — ESCALATE: ask user for direction |
| Stage 2 precondition fails | STOP — ESCALATE: "Stage 2 incomplete, manual intervention needed" |
| Same stage ASSERT failure repeats without new evidence | STOP — runtime `record-loop-health` pauses with actionable reason |

### Phase 5: Cleanup & Report

0. 标记流水线已完成

pre_cleanup_status = Bash: node $PIPELINE status --story {id} IF pre_cleanup_status.state.phase != "DONE": Bash: node $PIPELINE advance --story {id} --to DONE

1. 根据完成定义进行自我验证

status = Bash: node $PIPELINE status --story {id} final_state = status.state.phase OR "DONE" verification = { story_selected: status.state.story_id == id story_processed: final_state IN ("DONE", "PAUSED") } IF ANY verification == false: WARN user with details

2. 阅读阶段说明

stage_notes = {} FOR N IN 0..3: IF .hex-skills/pipeline/stage_{N}notes{id}.md exists: stage_notes[N] = read file content ELSE: stage_notes[N] = "(no notes captured)"

3. 提取分支信息

branch_name = git branch --show-current git_stats_final = git diff --stat origin/{base_branch}..HEAD (if not already captured)

4. 完成流水线报告

durations = {N: stage_timestamps.stage_{N}end - stage_timestamps.stage{N}_start FOR N IN 0..3 IF both timestamps exist}

Write docs/tasks/reports/pipeline-{date}.md:

流水线报告 -- {date}

事项： {id} -- {title} 分支： {branch_name} 最终状态： {final_state} 耗时： {now() - pipeline_start_time}

任务规划（ln-300）

任务数	计划得分	耗时
创建 {N} 项	{score}/4	{durations[0]}

{stage_notes[0]}

验证（ln-310）

判定	就绪度	Agent 评审	耗时
{verdict}	{score}/10	{agents_info}	{durations[1]}

{stage_notes[1]}

实现（ln-400）

状态	文件	行数	耗时
{result}	{files_changed}	+{added}/-{deleted}	{durations[2]}

{stage_notes[2]}

质量门禁（ln-500）

判定	得分	Agent 评审	返工	耗时
{verdict}	{score}/100	{agents_info}	{quality_cycles}	{durations[3]}

{stage_notes[3]}

流水线指标

墙钟时间	返工轮次	验证重试次数
{total_duration}	{quality_cycles}	{validation_retries}

5. 向用户显示流水线摘要

流水线已完成：

事项	分支	规划	验证	实现	质量门禁	状态
{id}	{branch}	{stage0}	{stage1}	{stage2}	{stage3}	{final_state}

报告已保存：docs/tasks/reports/pipeline-{date}.md

6. 清理工作树

cd {project_root} IF final_state == "PAUSED" AND worktree_dir exists AND worktree_dir != project_root: git -C {worktree_dir} add -A git -C {worktree_dir} commit -m "WIP: {id} pipeline paused" --allow-empty git -C {worktree_dir} push -u origin {branch} git worktree remove {worktree_dir} --force Display: "部分工作已保存到分支 {branch}（远程）。工作树已清理。" IF final_state == "DONE" AND worktree_dir exists AND worktree_dir != project_root:

ln-500 在阶段 7 中已提交并推送。仅清理工作树。

git worktree remove {worktree_dir} --force

7. 停止防止睡眠（Windows）

IF sleep_prevention_pid: kill $sleep_prevention_pid 2>/dev/null || true

8. 移除流水线状态文件

删除 .hex-skills/pipeline/ 目录

9. 向用户报告结果位置

## Coordinator Artifacts as Orchestration Truth

- **Read coordinator artifact first** after each stage completion. Never treat prose output as completion truth
- Re-read board after each stage only as a secondary assertion for expected status transitions
- Coordinators (ln-300/310/400/500) update Linear/kanban via their own logic. Lead verifies the artifact first, then checks board consistency
- **Update algorithm:** Follow `references/kanban_update_algorithm.md` for Epic grouping and indentation

## Error Handling

| Situation | Detection | Action |
|-----------|----------|--------|
| ln-300 task creation fails | Skill returns error | Escalate to user: "Cannot create tasks for Story {id}" |
| ln-310 NO-GO (Score <5) | Stage 1 artifact verdict != GO | Retry once. If still NO-GO -> ask user |
| Task in To Rework 3+ times | ln-400 reports rework loop | Escalate: "Task X reworked 3 times, need input" |
| ln-500 FAIL | Stage 3 artifact verdict = FAIL | Fix tasks auto-created by ln-500. Stage 2 re-entry. Max 2 quality cycles |
| Skill call error | Exception from Skill() | `node $PIPELINE status` -> re-invoke same Skill (runtime + artifacts handle resume) |
| Context compression | PostCompact hook or manual detection | `node $PIPELINE status` -> extract resume_action -> continue |

## Worker Invocation (MANDATORY)

**Host Skill Invocation:** `Skill(skill: "...", args: "...")` is mandatory delegation.
- Claude: call the Skill tool exactly as shown.
- Codex: if no Skill tool exists, locate the named skill in available skills, read its `SKILL.md`, treat `args` as `$ARGUMENTS`, execute that skill workflow, then return here with its result/artifact.
- Do not inline worker logic or mark the worker complete without executing the target skill.

| Stage | Skill | Invocation |
|-------|-------|------------|
| 0 | ln-300-task-coordinator | `Skill(skill: "ln-300-task-coordinator", args: "{id}")` |
| 1 | ln-310-multi-agent-validator | `Skill(skill: "ln-310-multi-agent-validator", args: "{id}")` |
| 2 | ln-400-story-executor | `Skill(skill: "ln-400-story-executor", args: "{id}")` |
| 3 | ln-500-story-quality-gate | `Skill(skill: "ln-500-story-quality-gate", args: "{id}")` |

## TodoWrite format (mandatory)

```text
- Phase 1: Resolve Story and business context (pending)
- Phase 2: Ask targeted business questions only if needed (pending)
- Phase 3: Setup pipeline runtime and worktree state (pending)
- Phase 4: Execute stage 0 -> 3 sequentially with ASSERT guards (pending)
- Phase 5: Write report, clean worktree, and finalize runtime state (pending)
- Phase 6: Run pipeline meta-analysis (pending)

TodoWrite 格式（必填）：

{content: "Stage N: {name} (ln-NNN)", status: "pending", activeForm: "{verb}ing"}

关键规则

1. **单个 Story 处理。**由用户选择要处理的 Story
2. **通过 Skill 调用协调器。**Lead 通过 Skill 工具调用 ln-300/ln-310/ln-400/ln-500。每个协调器负责管理自己的内部 Worker 调度（Agent/Skill）
3. **保持 Skills 原样。**绝不修改或绕过现有 Skill 逻辑
4. **优先验证工件。**每次 Skill 调用后，先读取协调器工件，再重新读取看板作为次要断言。Lead 绝不在聊天状态中缓存阶段状态
5. **质量循环限制。**每个 Story 最多允许 2 次质量 FAIL（原始版本 + 1 次返工）。第 2 次 FAIL 后，升级给用户处理
6. **Worktree 生命周期。**ln-1000 在 Phase 3.4 创建 worktree。ln-500 负责分支最终化（提交、推送）。ln-1000 在 Phase 5 清理 worktree（Lead 位于 worktree 中，因此 ln-500 会跳过清理）
7. **阶段备注。**Lead 在每个阶段后写入 .hex-skills/pipeline/stage_N_notes_{id}.md，用于 Pipeline 报告
8. **检查点。**CLI 脚本在每个阶段后通过 node $PIPELINE checkpoint 将按运行范围划分的运行时状态写入 .hex-skills/pipeline/runtime/runs/{run_id}/

已知问题

症状	可能原因	自行恢复
长时间运行后 Lead 输出泛泛的文本	上下文压缩破坏了状态变量	node $PIPELINE status -> 提取 resume_action -> 从那里继续
ln-400 卡在同一任务上	任务陷入返工循环	ln-400 在内部处理；返工 3 次后升级处理

反模式

• 执行后跳过质量门禁（Stage 3 紧接在 Stage 2 后面，不可能跳过）
• 将看板状态视为主要完成信号，而不是协调器工件
• 直接运行 mypy/ruff/pytest，而不是让协调器处理
• 未经用户选择就处理多个 Story
• 在 Phase 3.4 之外创建 worktree（协调器会自行检测 feature/*）
• 修改协调器的内部调度（ln-400 的 Agent/Skill 模式本身就是正确的）

计划模式支持

在计划模式下调用时，显示可用的 Story，并询问用户要为哪个 Story 制定计划：

1. 解析看板（Phase 1 步骤 1-7）
2. 显示可用的 Story 表格
3. AskUserQuestion：「要为哪个 Story 制定计划？输入 # 或 Story ID。」
4. 如果发现业务歧义，则执行 Phase 2（执行前问题）
5. 解析 skill_repo_path —— skills 仓库根目录的绝对路径
6. 显示所选 Story 的执行计划
7. 按照下方格式将计划写入计划文件，并调用 ExitPlanMode

计划输出格式：

## Pipeline Plan for {date}

> **BEFORE EXECUTING -- MANDATORY READ:** Load `{skill_repo_path}/ln-1000-pipeline-orchestrator/SKILL.md` (full file).
> After reading SKILL.md, start from Phase 3 (Pipeline Setup) using the context below.

**Story:** {ID}: {Title}
**Current Status:** {status}
**Target Stage:** {N} ({skill_name})
**Storage Mode:** {file|linear}
**Project Brief:** {name} ({tech})
**Business Answers:** {answers from Phase 2, or "none"}
**Skill Repo Path:** {skill_repo_path}

### Execution Sequence
1. Read full SKILL.md + references (Phase 3 prerequisites)
2. Setup worktree + initialize CLI-managed pipeline state (Phase 3)
3. Execute stages sequentially via Skill() calls (Phase 4)
4. Generate pipeline report (Phase 5)
5. Cleanup worktree + state files (Phase 5)

完成定义（在 Phase 5 自行验证）

• 用户已选择 Story（已设置 state.story_id）
• 业务问题已解决（已存储或跳过）
• Story 已处理至终态（state.phase IN ("DONE", "PAUSED")）
• 每个阶段的 ASSERT 验证均已通过（优先验证工件，看板为次要依据）
• 每个已完成阶段均已写入阶段备注
• 已生成 Pipeline 报告（文件位于 docs/tasks/reports/）
• 已向用户显示 Pipeline 摘要
• 已清理 worktree（Phase 5 步骤 6）
• 已运行 Meta-Analysis（Phase 6）

Phase 6：Meta-Analysis

**必须阅读：**加载 和 references/phases/phase6_meta_analysis.md

Skill 类型：execution-orchestrator。根据请求，在 Phase 5 之后运行。Pipeline 专属实现（恢复映射、趋势跟踪、假设审计、报告格式）见 phase6_meta_analysis.md。

参考文件

Phase 4-6 流程（渐进式披露）

• Pipeline 流程：references/phases/phase4_flow.md（ASSERT 守卫、阶段备注、上下文恢复、错误处理）
• Meta-analysis：references/phases/phase6_meta_analysis.md（恢复映射、趋势跟踪、报告格式）

Core Infrastructure

• MANDATORY READ: Load references/git_worktree_fallback.md
• MANDATORY READ: Load references/research_tool_fallback.md
• Pipeline states: references/pipeline_states.md
• Checkpoint format: references/checkpoint_format.md
• Kanban parsing: references/kanban_parser.md
• Kanban update algorithm: references/kanban_update_algorithm.md
• Settings template: references/templates/settings_template.json
• Sleep prevention: references/scripts/hooks/prevent-sleep.ps1
• Environment state: references/environment_state_contract.md
• Storage mode operations: references/storage_mode_detection.md
• Auto-discovery patterns: references/auto_discovery_pattern.md

Delegated Skills

• ../ln-300-task-coordinator/SKILL.md
• ../ln-310-multi-agent-validator/SKILL.md
• ../ln-400-story-executor/SKILL.md
• ../ln-500-story-quality-gate/SKILL.md

---

Version: 3.0.0 Last Updated: 2026-03-19