maestro-flow 0.4.10 → 0.4.12

package/.agy/skills/maestro-ralph/SKILL.md

@@ -19,12 +19,12 @@ Entry points:
 - **`/maestro-ralph continue`** — Resume via maestro-ralph-execute
 - **`/maestro-ralph status`** — Display session progress
 
-Initial decomposition (S_DECOMPOSE): broad intents (重构/全面/迁移/重写) are boundary-clarified via ≤3 questions, producing 执行准则 + 子目标清单 written into status.json, plus a `goal-checklist.md` and a copy-paste `/goal` prompt for the user to bind.
+Initial decomposition (S_DECOMPOSE): boundary-clarified via ≤3 questions for broad intents (重构/全面/迁移/重写). 写入 status.json 的 `boundary_contract` / `execution_criteria` / `task_decomposition`，附 `/goal` prompt。
 
-Three node types:
-- **internal**: `Skill()` call (synchronous, lightweight)
-- **external**: `maestro delegate --to claude` (context-isolated, heavy computation)
-- **decision**: Hand back to ralph for re-evaluation (adaptive branching)
+Node types:
+- **internal** (default): ralph-execute `view_file({command_path})` 命令 .md，按内容内联执行
+- **decision**: 回 ralph 评估
+- **external**: 仅在显式声明时使用（`maestro delegate --to claude`）
 
 Key difference from maestro coordinator:
 - maestro: static chain → one-time selection → runs all steps
@@ -32,6 +32,20 @@ Key difference from maestro coordinator:
 
 Session: `.workflow/.maestro/ralph-{YYYYMMDD-HHmmss}/status.json`
 Mutual invocation with `/maestro-ralph-execute` forms a self-perpetuating work loop.
+
+### Execution Flow
+
+```
+ /maestro-ralph "intent" ─▶ ralph        infer → decompose → build chain
+                              │           resolves command_path per step
+                              │           writes status.json
+                              │           emits /goal prompt
+                              ▼
+                       ralph-execute  ◀─┐ internal → view_file(command_path) inline
+                              │         │ decision → Skill("maestro-ralph")
+                              └─────────┘ writes step.completion_confirmed
+                       loop until all completion_confirmed | paused
+```
 </purpose>
 
 <context>
@@ -54,10 +68,13 @@ Remaining     → intent
 1. **Ralph never executes steps** — only creates sessions and evaluates decisions
 2. **Handoff via Skill("maestro-ralph-execute")** — at session creation and after decision evaluation
 3. **Decision delegates read-only** — `maestro delegate --role analyze --mode analysis`
-4. **External ≠ CLI call** — external spawns full Claude Code session executing the skill command
-5. **Delegate sessions non-interactive** — all external skills MUST append `-y` to args inside the prompt
-6. **Decomposition is outcome-oriented** — sub-goals are deliverables/done-criteria, NEVER lifecycle-stage duplicates (analyze/plan/...). `/goal` binding is user-driven; ralph only emits the prompt
-7. **task_decomposition drives DYNAMIC step growth, not a frozen plan** — sub-goals are the convergence spec; `status.json.steps[]` remains the living chain. The `post-goal-audit` decision node re-checks the checklist and **dynamically inserts scoped execution steps** for every unmet sub-goal (same insert+reindex+retry mechanism as fix-loops). Decomposition never replaces ralph's adaptive branching — it feeds it. New fields are also additive/optional (absent → decomposition off, old behavior); never remove/rename existing fields
+4. **Default type = internal** — `external` 仅显式标注时出现，build 不默认生成
+5. **status.json 是唯一真源** — 不生成 markdown 清单或侧文件
+6. **每个 step 必须 `completion_confirmed: true`** — 基于 `--- COMPLETION STATUS ---` 的 `STATUS: DONE`；缺失则视为未完成
+7. **command_path 在 A_BUILD_STEPS 解析** — 全局优先 `~/.claude/commands/{name}.md`，fallback 项目 `.claude/commands/{name}.md`，写入 status.json
+8. **Decomposition is outcome-oriented** — sub-goals 为可观测交付，禁止 lifecycle 复刻；`/goal` 用户绑定，ralph 只发提示词
+9. **planning_mode governs arg granularity** — `unified` → skill args 无 `{phase}`；`independent` → 含 `{phase}`
+10. **task_decomposition 驱动 steps[] 动态生长** — `post-goal-audit` 按 unmet 子目标插入 scoped mini-loop；字段可选/累加，既有字段不删不改
 </invariants>
 
 <state_machine>
@@ -66,8 +83,11 @@ Remaining     → intent
 S_PARSE_ROUTE     — 解析参数、路由入口                  PERSIST: —
 S_STATUS          — 显示 session 进度                   PERSIST: —
 S_CONTINUE        — 恢复执行                            PERSIST: —
-S_INFER           — 读 state.json、推断生命周期位置      PERSIST: session.lifecycle_position
-S_RESOLVE_PHASE   — 解析目标 phase                      PERSIST: session.phase
+S_RESOLVE_PHASE   — 解析 phase + phase_is_new + D-007 milestone PERSIST: session.phase, session.phase_is_new, session.milestone
+S_INFER           — 基于已解析 phase 推断 lifecycle_position PERSIST: session.lifecycle_position
+S_RESOLVE_SCOPE   — 读 macro analyze conclusions.scope_verdict PERSIST: session.scope_verdict, session.analyze_macro_id
+S_QUALITY_MODE    — 决定质量管线模式                     PERSIST: session.quality_mode
+S_PLANNING_MODE   — 决定统一/独立规划模式               PERSIST: session.planning_mode
 S_DECOMPOSE       — 边界澄清、写执行准则+子目标清单       PERSIST: session.boundary_contract, .execution_criteria, .task_decomposition
 S_BUILD_CHAIN     — 构建步骤链                           PERSIST: session.steps[]
 S_CREATE_SESSION  — 写 status.json                      PERSIST: session (全量)
@@ -84,7 +104,7 @@ S_PARSE_ROUTE:
   → S_STATUS        WHEN: intent == "status"
   → S_CONTINUE      WHEN: intent == "continue"
   → S_DECISION_EVAL WHEN: running session with decision step in "running" status
-  → S_INFER         WHEN: intent is non-empty
+  → S_RESOLVE_PHASE WHEN: intent is non-empty                  ← phase 必须先于 position
   → S_FALLBACK      WHEN: no intent AND no running session
 
 S_STATUS:
@@ -94,20 +114,31 @@ S_CONTINUE:
   → S_DISPATCH      WHEN: running session found
   → S_FALLBACK      WHEN: no running session               DO: display "无运行中的 ralph 会话"
 
-S_INFER:
-  → S_RESOLVE_PHASE WHEN: position resolved                 DO: A_INFER_POSITION
-  → S_FALLBACK      WHEN: cannot infer
-
 S_RESOLVE_PHASE:
-  → S_DECOMPOSE     WHEN: phase resolved or null            DO: A_RESOLVE_PHASE
+  → S_INFER         WHEN: phase resolved or null            DO: A_RESOLVE_PHASE
   → S_FALLBACK      WHEN: ambiguous
                      GUARD: auto_confirm does NOT skip phase ambiguity
 
+S_INFER:
+  → S_RESOLVE_SCOPE WHEN: position resolved                 DO: A_INFER_POSITION
+  → S_FALLBACK      WHEN: cannot infer
+
+S_RESOLVE_SCOPE:
+  → S_QUALITY_MODE  DO: A_RESOLVE_SCOPE_VERDICT
+                     GUARD: position ∈ {brainstorm, blueprint, init} → skip (scope_verdict = null)
+
+S_QUALITY_MODE:
+  → S_PLANNING_MODE DO: A_DETERMINE_QUALITY_MODE
+
+S_PLANNING_MODE:
+  → S_DECOMPOSE     DO: A_DETERMINE_PLANNING_MODE
+                     GUARD: lifecycle_position ∈ {brainstorm, blueprint, init, analyze-macro, roadmap} → skip (force independent)
+
 S_DECOMPOSE:
   → S_BUILD_CHAIN   DO: A_DECOMPOSE_TASKS
-                     GUARD: broad intent (重构/全面/重写/迁移/overhaul/migrate/rewrite) → MUST clarify boundary even if auto_confirm
-                     GUARD: narrow intent (single file/function/bug) → auto-derive, skip questions
-                     GUARD: position ∈ {brainstorm, init} → skip decomposition (no concrete target yet)
+                     GUARD: broad intent → MUST clarify boundary even if auto_confirm
+                     GUARD: narrow intent → auto-derive, skip questions
+                     GUARD: position ∈ {brainstorm, blueprint, init} → skip decomposition
 
 S_BUILD_CHAIN:
   → S_CREATE_SESSION DO: A_BUILD_STEPS
@@ -129,6 +160,8 @@ S_DECISION_EVAL:
                      DO: A_DELEGATE_EVALUATE
   → S_APPLY_VERDICT WHEN: goal-gate (post-goal-audit)
                      DO: A_GOAL_AUDIT_EVALUATE
+  → S_APPLY_VERDICT WHEN: scope-gate (post-analyze-scope)
+                     DO: A_SCOPE_EVALUATE
   → S_APPLY_VERDICT WHEN: structural (post-milestone, post-debug-escalate)
                      DO: A_STRUCTURAL_EVALUATE
 
@@ -136,10 +169,12 @@ S_APPLY_VERDICT:
   → S_DISPATCH      WHEN: verdict == "proceed"              DO: A_APPLY_PROCEED
   → S_DISPATCH      WHEN: post-goal-audit + unmet sub-goals  DO: A_APPLY_GOAL_FIX
   → S_DISPATCH      WHEN: post-goal-audit + all sub-goals met DO: A_APPLY_GOAL_DONE
+  → S_DISPATCH      WHEN: post-analyze-scope                 DO: A_APPLY_SCOPE_VERDICT
   → S_DISPATCH      WHEN: verdict == "fix"                  DO: A_APPLY_FIX
   → S_DISPATCH      WHEN: verdict == "escalate"             DO: A_APPLY_ESCALATE
-  → S_DISPATCH      WHEN: post-milestone + next milestone   DO: A_ADVANCE_MILESTONE
-  → END             WHEN: post-milestone + no next milestone DO: mark completed
+  → S_DISPATCH      WHEN: post-milestone + standard + next milestone   DO: A_ADVANCE_MILESTONE
+  → END             WHEN: post-milestone + standard + no next milestone DO: mark completed
+  → END             WHEN: post-milestone + adhoc                       DO: mark completed (adhoc self-contained)
   → END             WHEN: post-debug-escalate (always STOP)  DO: A_PAUSE_ESCALATE
   GUARD: retry_count >= max_retries → force escalate
   GUARD: confidence_score < 60 AND proceed → override to fix
@@ -159,12 +194,53 @@ S_FALLBACK:
 
 1. Find latest ralph session (by created_at)
 2. Display: Session, Status, Position, Progress, Current step
-3. List steps: [✓] completed, [▸] current, [ ] pending, [◆] decision
-4. If `task_decomposition` present: show `Sub-goals: {done}/{total}` and any unmet G-ids (graceful skip if field absent — backward compat)
+3. List steps: [✓] completion_confirmed, [▸] current, [ ] pending, [◆] decision；附 `command_scope`(global/project) + `command_path`
+4. If `task_decomposition` present (absent → skip):
+   ```
+   Sub-goals  ({done}/{total})    source: {session_dir}/status.json#/task_decomposition
+   [x] G1 done_when={done_when}   evidence={evidence}   confirmed={completion_confirmed}
+   [ ] G2 done_when={done_when}   evidence={evidence}   confirmed=false ◀ unmet
+   ```
+
+### A_RESOLVE_PHASE
+
+前置于 A_INFER_POSITION。产出 `phase` + `phase_is_new` + `milestone`（D-007 反查）三元组。
+
+**Priority:**
+
+| Step | 行为 | phase_is_new |
+|------|------|--------------|
+| 1 | intent 匹配 `phase\s*(\d+)` → 取 state.json 对应 phase | false |
+| 2 | intent 派生短语 → 在 `state.json.milestones[*].phase_slugs` / `artifacts[*].path` 查找 | false (匹配) / true (无匹配) |
+| 3 | 未派生 → 取最新 in-progress artifact 的 phase | false |
+| 4 | 仍无 → state.json 首个 incomplete phase | false |
+| 5 | position 将是 brainstorm/blueprint/init/roadmap/analyze-macro → phase = null | n/a |
+| 6 | 仍模糊 → `ask_question` | 由用户回答确定 |
+
+**D-007 Phase→Milestone 反查**（数字 phase 已解析时）：
+```
+resolve_milestone(phase_number):
+  for ms in state.json.milestones:
+    if str(phase_number) in ms.phase_slugs: return ms.id
+  return state.json.current_milestone   # fallback
+```
+写入 `session.milestone`；禁止直接使用 `current_milestone` 当做 phase 所属 milestone。
+
+**写入 session**: `phase`, `phase_is_new`, `milestone`。
+
+**新派生 phase 时 milestone 处理**：
+- state.json 当前 milestone 仍 active → 沿用，新增 phase
+- intent 派生新 milestone 名 → 写入 session 仅作标签；`state.json.milestones` 由 `maestro-roadmap` / `maestro-milestone-release` 创建
 
 ### A_INFER_POSITION
 
-**Intent-based override:** brainstorm/头脑风暴/探索/ideate/设计思路 → position = `brainstorm`
+**Intent-based overrides** (按顺序匹配，先命中先用):
+
+| Pattern | Position |
+|---------|----------|
+| brainstorm / 头脑风暴 / 探索 / ideate / 设计思路 | `brainstorm` |
+| blueprint / 规格 / 正式文档 / spec-generate / 7-phase | `blueprint` |
+| broad/medium intent 无数字 phase (重构/全面/重写/迁移/新功能 X) | `analyze-macro` |
 
 **Bootstrap detection:**
 
@@ -173,18 +249,38 @@ S_FALLBACK:
 | No `.workflow/` + no source files | `brainstorm` |
 | No `.workflow/` + has source files | `init` |
 | Has `.workflow/` but no state.json | `init` |
-| Has state.json | → artifact-based inference |
+| Has state.json | → phase-aware artifact inference |
 
-**Artifact-based inference:** Filter by current_milestone + target phase:
+**Phase-aware artifact inference** (使用 A_RESOLVE_PHASE 已写入的 `session.phase` + `session.phase_is_new`)：
 
-| Latest artifact type | Position |
-|---------------------|----------|
-| no milestones or no roadmap.md | `roadmap` |
-| none for phase | `analyze` |
-| analyze | `plan` |
-| plan | `execute` |
-| execute | `verify` |
-| verify | → refine from result files |
+| Condition | Position |
+|-----------|----------|
+| `phase_is_new == true` (新 phase) | `analyze` |
+| no milestones AND no roadmap.md AND has analyze macro artifact | `roadmap` |
+| no milestones AND no roadmap.md AND no analyze artifact | `analyze-macro` |
+| `phase == null` (brainstorm/blueprint/init/roadmap/analyze-macro override 已定) | n/a |
+| phase 已存在 + 无任何 artifact | `analyze` |
+| phase 已存在 + 最新 artifact = analyze | `plan` |
+| phase 已存在 + 最新 artifact = plan | `execute` |
+| phase 已存在 + 最新 artifact = execute | `verify` |
+| phase 已存在 + 最新 artifact = verify | → refine from result files |
+
+**关键不变量**：artifact 过滤按 `session.phase`，不读 `state.json.current_phase`。`phase_is_new` → 直接 `analyze`。
+
+### A_RESOLVE_SCOPE_VERDICT
+
+仅当 `lifecycle_position ∈ {analyze-macro, roadmap, plan}` 且存在最新 analyze artifact 时执行。
+
+1. 定位最新 macro analyze artifact（`type=="analyze"` 且 `scope=="macro"`，按 created_at DESC）→ 记 `session.analyze_macro_id = ANL-xxx`
+2. 读 `{artifact_path}/conclusions.json` 的 `scope_verdict` 字段（`large | medium | small`）
+3. 写入 `session.scope_verdict`；缺失时设 `unknown`
+4. 路由建议（A_BUILD_STEPS 据此决定是否插入 roadmap、plan 是否走 `--from`）：
+
+| scope_verdict | 链路 |
+|---------------|------|
+| `large` | analyze-macro → roadmap → analyze → plan → execute → ... |
+| `medium` / `small` | analyze-macro → plan --from analyze:{ANL_ID} → execute → ...（跳过 roadmap + analyze-phase） |
+| `unknown` | 默认走 large 路径，post-analyze-scope 决策节点再纠正 |
 
 **Refine from verify results:**
 
@@ -197,13 +293,49 @@ S_FALLBACK:
 | uat.md: all passed | `milestone-audit` |
 | uat.md: has failures | `test-failed` |
 
-### A_RESOLVE_PHASE
+### A_DETERMINE_QUALITY_MODE
+
+决定下游质量管线长度。读 `session.quality_mode_override`（CLI 标志 `--quality`），无则按规则推断：
 
-Priority: 1) regex from intent 2) latest artifact's phase 3) first incomplete phase 4) null if brainstorm/init/roadmap 5) ask_question if ambiguous
+| Condition | Mode | Pipeline (verify 之后) |
+|-----------|------|-------------------------|
+| Has `specs/REQ-*.md` + 当前 phase 业务范围明确 | `full` | business-test → review → test-gen → test |
+| Default | `standard` | review → test-gen (当 coverage<80%) → test |
+| `--quality quick` | `quick` | review --tier quick |
+
+写入 `session.quality_mode`。A_BUILD_STEPS 据此过滤 stage（见下）。
+
+### A_DETERMINE_PLANNING_MODE
+
+决定里程碑的规划粒度：一次性规划整个里程碑（统一）还是逐 phase 走完整生命周期（独立）。
+
+**Auto-resolve rules (按优先级):**
+
+| Condition | Mode | Reason |
+|-----------|------|--------|
+| lifecycle_position ∈ {brainstorm, init, roadmap} | `independent` | 前期阶段不涉及多 phase 规划 |
+| `phase_is_new == true` | `independent` | 新 phase 尚无里程碑上下文 |
+| intent 显式指定 phase 编号（如 "phase 2"、"P3"） | `independent` | 用户明确针对单个 phase |
+| milestone 仅含 1 个 phase（读 state.json） | `independent` | 统一无意义 |
+| milestone 含多个 phase + `auto_confirm` | `unified` | 自动模式倾向高效 |
+| milestone 含多个 phase + 非 `auto_confirm` | → ask_question | 征询用户选择 |
+
+**ask_question** (仅当 milestone 含 ≥2 phase 且非 auto_confirm):
+
+```
+question: "当前里程碑含 {N} 个 phase，选择规划模式？"
+options:
+  - label: "统一规划 (Recommended)"
+    description: "一次性分析+规划整个里程碑所有 phase，analyze/plan 走里程碑级，适合 phase 间关联紧密"
+  - label: "独立规划"
+    description: "逐个 phase 走完整生命周期（analyze→plan→execute→verify→...），适合 phase 间独立性高"
+```
+
+写入 `session.planning_mode`（`"unified"` 或 `"independent"`）。`A_BUILD_STEPS` 据此决定 skill args 是否携带 `{phase}` 占位符。
 
 ### A_DECOMPOSE_TASKS
 
-Build the boundary contract + outcome sub-goal checklist that `/goal` will track. Runs once at session creation, before chain build. All output is **additive** to status.json.
+Runs once before chain build; additive to status.json.
 
 **1. Classify intent breadth:**
 
@@ -223,7 +355,7 @@ Build the boundary contract + outcome sub-goal checklist that `/goal` will track
 
 narrow → derive defaults from intent + codebase, skip questions.
 
-**3. Derive `execution_criteria`** (执行准则 — 3-6 short imperative rules every step obeys): backward-compat stance, scope-freeze ("只改请求范围"), test/coverage bar, fix-don't-hide, incremental commit. Each verify/review/test gate later checks against these.
+**3. Derive `execution_criteria`**: backward-compat、scope-freeze、test/coverage bar、fix-don't-hide、incremental commit。
 
 **4. Derive `task_decomposition`** (子目标清单 — outcome-oriented, NOT lifecycle stages). Each entry:
 ```json
@@ -232,45 +364,70 @@ narrow → derive defaults from intent + codebase, skip questions.
   "evidence": "verification.json|review.json|uat.md|<test path>",
   "lifecycle": ["analyze","execute","verify"], "status": "pending" }
 ```
-**Cleverness rule**: `done_when` MUST be objectively verifiable and SHOULD reference an artifact ralph already produces, so the `/goal` Stop hook can re-verify after context compaction. Map each sub-goal to the lifecycle phase(s) that will produce its evidence — this is how the checklist "adapts to ralph": the existing pipeline becomes the machinery that satisfies the goals.
+`done_when` 必须客观可验证，且引用 ralph 已产出的 artifact；`lifecycle` 字段映射到产出 evidence 的生命周期 stage。
 
-**5. Persist** (additive) into session for A_CREATE_SESSION to write: `boundary_contract`, `execution_criteria`, `task_decomposition`. Absent feature (skipped) → write none; downstream treats as "decomposition off".
+**5. Persist** (additive): `boundary_contract`, `execution_criteria`, `task_decomposition`。每个 sub-goal 含 `status: "pending"` + `completion_confirmed: false`。
 
-**6. Stage** the Goal Checklist + Goal Prompt (Appendix) for A_CREATE_SESSION to emit.
+**6. Stage** the Goal Prompt (Appendix) for A_CREATE_SESSION to emit.
 
 ### A_BUILD_STEPS
 
-Generate steps from lifecycle_position to milestone-complete:
-
-| Stage | Skill | Type | Decision after |
-|-------|-------|------|----------------|
-| brainstorm | `maestro-brainstorm "{intent}"` | external | — |
-| init | `maestro-init` | internal | — |
-| roadmap | `maestro-roadmap "{intent}"` | internal | — |
-| analyze | `maestro-analyze {phase}` | external | — |
-| plan | `maestro-plan {phase}` | internal | — |
-| execute | `maestro-execute {phase}` | external | — |
-| verify | `maestro-verify {phase}` | internal | `post-verify` |
-| business-test | `quality-auto-test {phase}` | internal | `post-business-test` |
-| review | `quality-review {phase}` | internal | `post-review` |
-| test-gen | `quality-auto-test {phase}` | internal | — |
-| test | `quality-test {phase}` | internal | `post-test` |
-| milestone-audit | `maestro-milestone-audit` | internal | — |
-| goal-audit | *(decision-only, no skill)* | decision | `post-goal-audit` |
-| milestone-complete | `maestro-milestone-complete` | internal | `post-milestone` |
-
-`goal-audit` row is inserted **only when `task_decomposition` present**, immediately before `milestone-complete`. It is a pure decision node (no skill step) — its job is to re-check the goal-checklist and **dynamically grow `steps[]`** for unmet sub-goals.
-
-Type rationale: `internal` = Skill(), lightweight/interactive; `external` = delegate --to claude, context-isolated heavy computation
-
-Build rules: start from position, skip completed, insert decision nodes with `{ retry_count: 0, max_retries: 2 }`, args use placeholders resolved at execution time by ralph-execute. Steps dynamically inserted by `post-goal-audit` carry optional `goal_ref: "G{n}"` tracing which sub-goal they serve.
+Generate steps from `session.lifecycle_position` to `milestone-complete`.
+
+| Stage | Skill (independent) | Skill (unified) | Type | Decision after | quality_mode |
+|-------|---------------------|-----------------|------|----------------|--------------|
+| brainstorm | `maestro-brainstorm "{intent}"` | *(same)* | internal | — | all |
+| blueprint | `maestro-blueprint "{intent}"` | *(same)* | internal | — | all |
+| init | `maestro-init` | *(same)* | internal | — | all |
+| analyze-macro | `maestro-analyze "{intent}"` | *(same)* | internal | `post-analyze-scope` | all |
+| roadmap | `maestro-roadmap --from analyze:{analyze_macro_id}` | *(same)* | internal | — | all |
+| analyze | `maestro-analyze {phase}` | `maestro-analyze` | internal | — | all |
+| plan | `maestro-plan {phase}` *(scope=phase)* / `maestro-plan --from analyze:{analyze_macro_id}` *(scope=standalone)* / `maestro-plan --from blueprint:{blueprint_id}` *(scope=standalone)* | `maestro-plan` | internal | — | all |
+| execute | `maestro-execute {phase}` | `maestro-execute` | internal | — | all |
+| verify | `maestro-verify {phase}` | `maestro-verify` | internal | `post-verify` | all |
+| business-test | `quality-auto-test {phase}` | `quality-auto-test` | internal | `post-business-test` | full only |
+| review | `quality-review {phase}` | `quality-review` | internal | `post-review` | all (quick: append `--tier quick`) |
+| test-gen | `quality-auto-test {phase}` | `quality-auto-test` | internal | — | full / standard if coverage<80% |
+| test | `quality-test {phase}` | `quality-test` | internal | `post-test` | full, standard |
+| milestone-audit | `maestro-milestone-audit` | *(same)* | internal | — | all |
+| goal-audit | *(decision-only)* | *(same)* | decision | `post-goal-audit` | all (only if decomposed) |
+| milestone-complete | `maestro-milestone-complete` | *(same)* | internal | `post-milestone` | all |
+
+**Build rules (按顺序应用):**
+
+0. **planning_mode 选列**：`unified` → Skill (unified) 列；`independent` → Skill (independent) 列
+1. **起点**：从 `session.lifecycle_position` 开始
+2. **跳过已完成**：跳过当前 milestone+phase 下已有 completed artifact 的 stage（按 `session.phase` 过滤）；unified 按 milestone 过滤
+3. **quality_mode 过滤**：按 `session.quality_mode` 排除不匹配 stage
+4. **决策节点**：每个 Decision after 非空的 stage 之后插入 `{ type: "decision", decision: "<gate>", retry_count: 0, max_retries: 2 }`
+5. **goal-audit 插入**：`task_decomposition` 存在时，在最后一个 evidence-producing stage（verify/review/test）之后、`milestone-complete` 之前插入 `decision:post-goal-audit`
+6. **终点硬约束**：chain 以 `milestone-complete` 结尾
+7. **goal_ref 传播**：`task_decomposition` 存在时，每个 step 按 `step.stage ∈ g.lifecycle` 匹配 `step.goal_ref = g.id`（多匹配取字典序最小）；decision 节点不打 goal_ref
+8. **占位符**：independent 保留 `{phase}` `{intent}`；unified 不带 `{phase}`
+9. **command_path 解析**（每个非 decision step）：
+   - 取 skill 名（args 前的第一个 token）
+   - 全局优先：`~/.claude/commands/{name}.md` 存在 → `command_scope = "global"`
+   - Fallback：`.claude/commands/{name}.md` 存在 → `command_scope = "project"`
+   - 两者都缺 → `command_scope = "missing"`, `command_path = null`，A_CREATE_SESSION 报错 E006
+10. **每个 step 初始化** `completion_confirmed: false`, `completion_status: null`, `completion_evidence: null`
+11. **scope_verdict gating**（仅当 chain 起点 = `analyze-macro`）：
+    - `scope_verdict ∈ {medium, small}` → 跳过 `roadmap` + `analyze` 两 stage；`plan` 选 standalone 列（`--from analyze:{analyze_macro_id}`），不带 `{phase}`
+    - `scope_verdict == large` → 保留 `roadmap` + `analyze`；`plan` 选 phase 列（`{phase}`）
+    - `scope_verdict == unknown` → 默认 large 路径；由 `post-analyze-scope` 决策节点在 macro analyze 完成后纠正（A_APPLY_SCOPE_VERDICT）
+12. **--from 自动注入**：
+    - `analyze_macro_id` 存在且当前 step 是 `roadmap` → args 改为 `--from analyze:{analyze_macro_id}`
+    - `analyze_macro_id` 存在且 `scope_verdict ∈ {medium, small}` 且当前 step 是 `plan` → args 改为 `--from analyze:{analyze_macro_id}`
+    - `blueprint_id` 存在 → 当前 step 是 `plan` → args 改为 `--from blueprint:{blueprint_id}`（优先级低于 phase 数字参数）
+    - 写入 `step.source_artifact_ref` 以便审计
+13. **D-007 Milestone-ref 标注**：每个含 `{phase}` 占位符的 step → `step.milestone_id = session.milestone`（由 A_RESOLVE_PHASE 反查得出），禁止读 `current_milestone`
+14. **动态插入步骤**（A_APPLY_*）同样应用规则 7-13
 
 ### A_CREATE_SESSION
 
-1. Write `.workflow/.maestro/ralph-{YYYYMMDD-HHmmss}/status.json` (see Appendix: Session Schema) — include decomposition fields only if produced (additive)
-2. If `task_decomposition` present: write `{session_dir}/goal-checklist.md` (see Appendix: Goal Checklist Template) — stable within session, referenced verbatim by `/goal`
-3. Display chain overview with step list
-4. If `task_decomposition` present: display the **Goal Prompt block** (Appendix: Goal Prompt Template) — the copy-paste `/goal …` line binding the checklist as a Stop-hook target
+1. Validate: 所有 step 的 `command_scope != "missing"`；否则 raise E006 + 列出缺失 skill
+2. Write `.workflow/.maestro/ralph-{YYYYMMDD-HHmmss}/status.json` (Appendix: Session Schema)
+3. Display chain overview：每步显示 `{index}. {skill} [{type}] [{command_scope}]`
+4. If `task_decomposition` present: display the **Goal Prompt block** (Appendix: Goal Prompt Template)
 
 ### A_DELEGATE_EVALUATE
 
@@ -304,28 +461,64 @@ Build rules: start from position, skip completed, insert decision nodes with `{
 
 ### A_STRUCTURAL_EVALUATE
 
-**post-milestone:** Read state.json → next milestone? → insert lifecycle steps / complete
+**post-milestone:**
+1. Read state.json → resolve completed milestone object
+2. Determine milestone type: `milestone_obj.type` (default `"standard"` if missing)
+3. **Standard milestone** (`type != "adhoc"`): next milestone exists? → insert lifecycle steps / complete
+4. **Adhoc milestone** (`type == "adhoc"`): always END — adhoc milestones are self-contained, no successor to advance to. Set `current_milestone = null`.
+
 **post-debug-escalate:** Always STOP → set paused, display "请人工介入"
 
+### A_SCOPE_EVALUATE
+
+仅由 `post-analyze-scope` 决策节点触发；macro analyze 完成后读 `conclusions.json.scope_verdict` 决定下游链路。
+
+1. 定位刚完成的 macro analyze artifact → `analyze_macro_id`, `conclusions_path = {artifact_path}/conclusions.json`
+2. 读取 `conclusions.scope_verdict`（`large | medium | small`），缺失 → `unknown`
+3. 写入 `session.scope_verdict` + `session.analyze_macro_id`
+4. Append `{session_dir}/decisions.ndjson`:
+   ```json
+   { "id": "DEC-{timestamp}", "type": "scope-gate",
+     "source": "ralph", "node_id": "post-analyze-scope",
+     "verdict": "{scope_verdict}", "analyze_macro_id": "{ANL_ID}" }
+   ```
+5. → A_APPLY_SCOPE_VERDICT
+
 ### A_GOAL_AUDIT_EVALUATE
 
-Re-checks the goal-checklist and decides whether `steps[]` must dynamically grow. Only runs when `task_decomposition` present.
+Runs only when `task_decomposition` present.
 
-1. Read `session.task_decomposition` + `goal_checklist_path`
-2. For each sub-goal `status != "done"`: resolve its `evidence` artifact (verification.json / review.json / uat.md / test path) under the current phase scratch dir
+1. Read `session.task_decomposition` from status.json
+2. For each sub-goal `status != "done"`: resolve `evidence` artifact under current phase scratch dir
 3. Delegate read-only audit (run_in_background, STOP, wait):
    ```
-   maestro delegate "PURPOSE: 审计子目标达成情况，决定是否需要补充执行步骤
-   TASK: 逐个读取每个未完成子目标的 evidence 产物 | 对照 done_when 判定 met/unmet | 给出每个 unmet 子目标的差距
-   CONTEXT: @{goal_checklist_path} @{evidence artifacts} | 执行准则: {execution_criteria} | 边界: {boundary_contract}
-   EXPECTED: ---VERDICT--- STATUS(all_met|has_unmet) / UNMET=[{id:G2,gap:'...',target_phase:execute}] / CONFIDENCE_SCORE(0-100) ---END---
-   CONSTRAINTS: 只评估不修改 | 严格按 done_when 判定 | 不得超出 boundary_contract"
+   maestro delegate "PURPOSE: 审计未完成子目标，判定 met / unmet
+   TASK:
+     1. 读取 status.json.task_decomposition 中 status!=done 的子目标
+     2. 打开 evidence 产物，对照 done_when 严格判定
+     3. 输出 met / unmet，unmet 给出 gap + target_phase
+   CONTEXT:
+     status.json   = {session_dir}/status.json
+     evidence      = {evidence artifacts}
+     execution_criteria = {execution_criteria}
+     boundary_contract  = {boundary_contract}
+   EXPECTED:
+     ---VERDICT---
+     STATUS=all_met|has_unmet
+     UNMET=[{id:G2,gap:'...',target_phase:execute}, ...]
+     CONFIDENCE_SCORE=0-100
+     ---END---
+   CONSTRAINTS:
+     - 只评估，不修改文件
+     - 严格按 done_when 判定；evidence 缺失 → unmet
+     - 不得建议超出 boundary_contract 的修改
+   "
    --role analyze --mode analysis
    ```
-4. On callback: parse UNMET list. For each met sub-goal → set `task_decomposition[i].status="done"` + flip `[ ]→[x]` in goal-checklist.md
-5. **Decision log**: append to `{session_dir}/decisions.ndjson` with `"type": "goal-gate"`, `unmet_count`, `unmet_ids`
+4. On callback: 对每个 met 子目标，set `task_decomposition[i].status="done"` + `completion_confirmed=true` + `completed_at=now`
+5. Append `{session_dir}/decisions.ndjson` with `"type": "goal-gate"`, `unmet_count`, `unmet_ids`
 6. Verdict: `all_met` → A_APPLY_GOAL_DONE; `has_unmet` → A_APPLY_GOAL_FIX
-   GUARD: retry_count >= max_retries AND still unmet → A_APPLY_ESCALATE (insert quality-debug, hand to human)
+   GUARD: retry_count >= max_retries AND still unmet → A_APPLY_ESCALATE
 
 ### A_APPLY_PROCEED
 
@@ -343,22 +536,33 @@ Re-checks the goal-checklist and decides whether `steps[]` must dynamically grow
 1. Insert `[quality-debug "{gap_summary}", decision:post-debug-escalate]`
 2. Increment retry_count, reindex, write status.json
 
-### A_APPLY_GOAL_FIX
+### A_APPLY_SCOPE_VERDICT
 
-**This is the dynamic step-growth core.** For every unmet sub-goal, inject scoped execution steps so `steps[]` grows toward convergence:
+由 `post-analyze-scope` 触发，依据 `session.scope_verdict` 重塑下游链路。
 
-1. For each `unmet` sub-goal `G{n}` (grouped by `target_phase` to avoid duplicate runs):
-   insert before the `goal-audit` node a scoped mini-loop (see Appendix: Fix-Loop Templates → post-goal-audit), each inserted step tagged `goal_ref: "G{n}"`
-2. Re-append a fresh `decision:post-goal-audit {retry+1}` after the inserted steps (re-loops until all met or max retries)
-3. Reindex steps, increment retry_count, write status.json (steps[] now larger — the JSON "grew")
-4. Display: ◆ Goal audit: {k} sub-goals unmet → +{N} steps inserted (G{ids}), retry {r}/{max}
+1. 读 `session.scope_verdict`
+2. 路径 A（`large`）：保持当前链；为后续 `roadmap` step 注入 `--from analyze:{analyze_macro_id}`；为后续 `plan` step 选 phase 列；继续推进
+3. 路径 B（`medium` / `small`）：
+   - 删除 `goal-audit` 之前所有未完成的 `roadmap` + `analyze` (phase) step
+   - 把下一个未完成的 `plan` step 改为 `maestro-plan --from analyze:{analyze_macro_id}`，去掉 `{phase}`，`source_artifact_ref = analyze:{analyze_macro_id}`
+   - 后续 `execute` / `verify` 等沿用同一 standalone scope（不带 `{phase}`，由 plan 写出的 task 列表驱动）
+4. 路径 C（`unknown`）：
+   - 非 auto_confirm → ask_question 二选一（large / medium-small）；auto_confirm → 默认 large
+5. Reindex steps，标 decision completed，write status.json
+6. Display: ◆ Scope verdict: {verdict} → {kept|collapsed to standalone via analyze:{ANL_ID}}
+
+### A_APPLY_GOAL_FIX
+
+1. 对每个 unmet 子目标 `G{n}`（按 `target_phase` 分组去重）：在 `goal-audit` 节点前插入 scoped mini-loop（见 Appendix: Fix-Loop Templates → post-goal-audit），每条插入 step `goal_ref: "G{n}"`，按 A_BUILD_STEPS 规则 9 解析 `command_path`
+2. 重新追加 `decision:post-goal-audit {retry+1}`
+3. Reindex steps, increment retry_count, write status.json
+4. Display: ◆ Goal audit: {k} unmet → +{N} steps inserted (G{ids}), retry {r}/{max}
 
 ### A_APPLY_GOAL_DONE
 
-1. Set all `task_decomposition[*].status="done"`, write status.json
-2. Append `ALL_GOALS_DONE` sentinel line to goal-checklist.md (satisfies the user's `/goal` Stop hook)
-3. Mark goal-audit decision completed; proceed to `milestone-complete`
-4. Display: ◆ Goal audit: 全部子目标达成 ✓ — checklist 已写入 ALL_GOALS_DONE
+1. status.json: set 每个 `task_decomposition[*].status="done"`, `completion_confirmed=true`, `completed_at=now`，顶层 `task_decomposition_all_done=true`
+2. Mark goal-audit decision completed；proceed to `milestone-complete`
+3. Display: ◆ Goal audit: all met ✓
 
 ### A_ADVANCE_MILESTONE
 
@@ -385,40 +589,62 @@ Re-checks the goal-checklist and decides whether `steps[]` must dynamically grow
   "session_id": "ralph-{YYYYMMDD-HHmmss}",
   "source": "ralph", "status": "running",
   "intent": "", "lifecycle_position": "",
-  "phase": null, "milestone": "",
-  "auto_mode": false, "quality_mode": "standard",
+  "phase": null, "phase_is_new": false,
+  "milestone": "",                // D-007 反查结果，禁止读 current_milestone
+  "auto_mode": false,
+  "quality_mode": "standard",     // "full" | "standard" | "quick"
+  "planning_mode": "independent", // "unified" | "independent"
+  "scope_verdict": null,          // "large" | "medium" | "small" | "unknown" | null
+  "analyze_macro_id": null,       // "ANL-xxx" 来自最新 macro analyze
+  "blueprint_id": null,           // "BLP-xxx" 若存在
   "cli_tool": "claude", "passed_gates": [],
   "context": { "issue_id": null, "scratch_dir": null, "plan_dir": null,
-    "analysis_dir": null, "brainstorm_dir": null },
-  "steps": [{ "index": 0, "type": "internal|external|decision",
-    "skill": "", "args": "", "status": "pending",
-    "goal_ref": null }],
+    "analysis_dir": null, "brainstorm_dir": null, "blueprint_dir": null },
+  "steps": [{
+    "index": 0,
+    "type": "internal|external|decision",
+    "skill": "",
+    "args": "",
+    "stage": "",                  // brainstorm|blueprint|init|analyze-macro|roadmap|analyze|plan|execute|verify|...
+    "scope": null,                // "phase"|"standalone"|"milestone"|null（plan 等需要）
+    "command_scope": "global|project|missing|null",
+    "command_path": "~/.claude/commands/{name}.md | .claude/commands/{name}.md | null",
+    "milestone_id": null,         // D-007 反查注入；仅含 {phase} 占位符的 step 有
+    "source_artifact_ref": null,  // "analyze:ANL-xxx" | "blueprint:BLP-xxx" | null
+    "status": "pending|running|completed|skipped|failed",
+    "goal_ref": null,
+    "completion_confirmed": false,
+    "completion_status": null,
+    "completion_evidence": null,
+    "completed_at": null
+  }],
   "waves": [], "current_step": 0,
 
-  "_comment": "↓ OPTIONAL additive decomposition block (v0.4.8+). Absent → no decomposition; readers MUST tolerate missing keys. Never remove/rename above fields.",
+  // Optional decomposition block (additive; absent → decomposition off)
   "boundary_contract": {
     "in_scope": [], "out_of_scope": [], "constraints": [], "definition_of_done": ""
   },
   "execution_criteria": [],
   "task_decomposition": [
     { "id": "G1", "goal": "", "boundary": "", "done_when": "",
-      "evidence": "", "lifecycle": [], "status": "pending|done" }
+      "evidence": "", "lifecycle": [], "status": "pending|done",
+      "completion_confirmed": false, "completed_at": null }
   ],
-  "goal_checklist_path": ""
+  "task_decomposition_all_done": false
 }
 ```
 
-> **Extensibility contract (two dimensions)**:
-> 1. **Schema-additive** — decomposition block fields are optional; absence = old behavior.
-> 2. **Step-dynamic** — `steps[]` is a *living array*: `post-goal-audit` (and existing fix/escalate/milestone decisions) **append/reindex steps at runtime** until sub-goals converge. The JSON "extends" primarily by growing `steps[]`, not by freezing a plan. `goal_ref` (optional, default null) traces dynamically-added steps back to the sub-goal that spawned them.
+新增字段可选，缺省=旧行为；既有字段名不删不改。
 
 ### Fix-Loop Templates
 
+所有插入 step 默认 `type: "internal"`，按 A_BUILD_STEPS 规则 9 解析 `command_path` + `command_scope`。
+
 **post-verify:**
 ```
 quality-debug "{gap_summary}"
 maestro-plan --gaps {phase}
-maestro-execute {phase}                [external]
+maestro-execute {phase}
 maestro-verify {phase}
 decision:post-verify {retry+1}
 ```
@@ -427,7 +653,7 @@ decision:post-verify {retry+1}
 ```
 quality-debug --from-business-test "{gap_summary}"
 maestro-plan --gaps {phase}
-maestro-execute {phase}                [external]
+maestro-execute {phase}
 maestro-verify {phase}
 decision:post-verify {retry: 0}
 quality-auto-test {phase}
@@ -438,7 +664,7 @@ decision:post-business-test {retry+1}
 ```
 quality-debug "{gap_summary}"
 maestro-plan --gaps {phase}
-maestro-execute {phase}                [external]
+maestro-execute {phase}
 quality-review {phase}
 decision:post-review {retry+1}
 ```
@@ -447,7 +673,7 @@ decision:post-review {retry+1}
 ```
 quality-debug --from-uat "{gap_summary}"
 maestro-plan --gaps {phase}
-maestro-execute {phase}                [external]
+maestro-execute {phase}
 maestro-verify {phase}
 decision:post-verify {retry: 0}
 quality-auto-test {phase}
@@ -459,59 +685,29 @@ quality-test {phase}
 decision:post-test {retry+1}
 ```
 
-**post-goal-audit:** (per unmet sub-goal group — this is what dynamically grows `steps[]`)
+**post-goal-audit:** (per unmet sub-goal group)
 ```
-# for each unmet sub-goal G{n}, scoped to its target_phase:
+# for each unmet sub-goal G{n}, scoped to target_phase:
 maestro-plan --gaps {target_phase} "G{n}: {gap}"     [goal_ref: G{n}]
-maestro-execute {target_phase}             [external] [goal_ref: G{n}]
-maestro-verify {target_phase}                         [goal_ref: G{n}]
-# after all unmet groups inserted, re-loop the audit:
+maestro-execute {target_phase}                       [goal_ref: G{n}]
+maestro-verify {target_phase}                        [goal_ref: G{n}]
+# after all unmet groups inserted:
 decision:post-goal-audit {retry+1}
 ```
-Notes: only unmet sub-goals' phases are re-run (no full-pipeline replay); inserted steps carry `goal_ref` for traceability; loop exits when audit returns `all_met` (→ A_APPLY_GOAL_DONE) or retry hits max (→ escalate to human). This keeps growth bounded.
-
-### Goal Checklist Template
-
-Written to `{session_dir}/goal-checklist.md`. Stable within the session; never renamed (so the `/goal` condition string stays valid across context compaction).
-
-```markdown
-# Ralph Goal Checklist — {session_id}
-> Intent: {intent}
-
-## 执行准则 / Execution Criteria
-- {criterion 1}
-- {criterion 2}
-
-## 边界契约 / Boundary Contract
-- In scope: {in_scope}
-- Out of scope: {out_of_scope}
-- Constraints: {constraints}
-- Definition of Done: {definition_of_done}
-
-## 子目标 / Sub-goals
-- [ ] G1: {goal} — done when: {done_when} (evidence: {evidence})
-- [ ] G2: {goal} — done when: {done_when} (evidence: {evidence})
-- [ ] G3: ...
-
-<!-- ralph-execute flips [ ]→[x] when a sub-goal's evidence artifact confirms done;
-     appends the line `ALL_GOALS_DONE` once every box is [x]. -->
-```
-
-`maestro-ralph-execute` responsibility (additive, optional): after a step whose `lifecycle` covers a sub-goal, re-check that sub-goal's `evidence` artifact; if satisfied, set `task_decomposition[i].status="done"` in status.json AND flip its checkbox in goal-checklist.md. When all done → append `ALL_GOALS_DONE`. If decomposition fields absent → do nothing (old behavior).
 
 ### Goal Prompt Template
 
-Displayed verbatim after the chain overview (only when decomposition produced):
+链路概览后逐字显示（仅当 decomposition 已产出）：
 
 ```
-📋 任务分解完成。可选(推荐)：复制下面一行设定目标，让会话在所有子目标达成前不停：
+📋 任务分解完成。复制下面一行设定目标，会话在子目标全部达成前不停：
 
-/goal 当 {session_dir}/goal-checklist.md 中所有子目标复选框均为 [x] 且文件含 ALL_GOALS_DONE 哨兵时目标达成；否则依据文件内"执行准则"继续推进未完成子目标，不得超出边界契约范围
+/goal 目标达成条件: {session_dir}/status.json 中 task_decomposition[*].status == "done" 且 task_decomposition[*].completion_confirmed == true 且 steps[*].completion_confirmed == true。未达成时：阅读 {session_dir}/status.json 取得 execution_criteria / boundary_contract / task_decomposition / steps 作为行动手册，调用 /maestro-ralph continue 推进；严禁手动执行 skill 或越界修改 status.json.boundary_contract.out_of_scope。
 
-然后运行 /maestro-ralph continue 开始执行。
+随后运行 /maestro-ralph continue 立即开始执行。
 ```
 
-> `/goal` 是 harness 命令、仅用户可输入 — ralph 只输出此提示词，不能自行注册。这与 status.json 的可扩展约定一致：绑定是用户侧、可选的增量能力。
+`/goal` 由用户输入；ralph 只输出此提示词。判据以 status.json 为权威。
 
 ### Error Codes
 
@@ -522,6 +718,7 @@ Displayed verbatim after the chain overview (only when decomposition produced):
 | E003 | error | Artifact dir not found for decision | Show glob, ask |
 | E004 | error | Delegate verdict parse failed | Fallback: "fix" |
 | E005 | error | Delegate execution failed | Fallback: "fix" |
+| E006 | error | command_scope == "missing" for one or more steps | List missing skills, abort build |
 | W001 | warning | Decision expanded chain | Auto-handled |
 | W002 | warning | Max retries, escalating | Auto-handled |
 | W003 | warning | Multiple running sessions | Use latest, warn |
@@ -529,18 +726,27 @@ Displayed verbatim after the chain overview (only when decomposition produced):
 
 ### Success Criteria
 
-- [ ] State parsed, position inferred from bootstrap + artifacts + result files
-- [ ] Decomposition runs as initial step; broad intent boundary-clarified via ≤3 questions (ignores auto_confirm); narrow auto-derives
-- [ ] status.json enriched additively with boundary_contract + execution_criteria + task_decomposition; absent fields = old behavior preserved
-- [ ] goal-checklist.md generated with verifiable done_when mapped to ralph evidence + ALL_GOALS_DONE sentinel
-- [ ] Goal Prompt emitted for user to bind via /goal
-- [ ] post-goal-audit decision node inserted before milestone-complete (only when decomposed)
-- [ ] Unmet sub-goals DYNAMICALLY grow steps[] via scoped per-goal mini-loops (goal_ref tagged), looping until all_met or max retries → escalate
-- [ ] Quality pipeline generated: verify → business-test → review → test-gen → test
-- [ ] Decision nodes delegate-evaluated via maestro delegate --role analyze
-- [ ] Verdict parsed with confidence adjustment
-- [ ] Fix-loop templates applied with retry tracking
-- [ ] Ralph never executes steps — only creates sessions and evaluates decisions
-- [ ] Handoff to maestro-ralph-execute via Skill() at creation and after decisions
+- [ ] Phase 先于 position 解析；phase_is_new 标记写入 session
+- [ ] D-007 反查：phase 数字 → `session.milestone`，禁止读 current_milestone；写入 step.milestone_id
+- [ ] phase_is_new=true → lifecycle_position 强制 `analyze`
+- [ ] Intent overrides 识别 brainstorm / blueprint / analyze-macro
+- [ ] A_RESOLVE_SCOPE_VERDICT 读 macro analyze conclusions.scope_verdict，写入 session.scope_verdict + analyze_macro_id
+- [ ] 链路起点 = analyze-macro 时：large→roadmap+analyze+plan(phase)；medium/small→直跳 plan --from analyze:{ANL_ID}（跳过 roadmap+analyze）
+- [ ] post-analyze-scope decision 节点在 macro analyze 之后插入；A_SCOPE_EVALUATE/A_APPLY_SCOPE_VERDICT 重塑链路
+- [ ] plan step args 支持三路径：`{phase}` / `--from analyze:{ANL_ID}` / `--from blueprint:{BLP_ID}`，写入 step.source_artifact_ref
+- [ ] roadmap step args 自动注入 `--from analyze:{analyze_macro_id}`（若存在）
+- [ ] artifact 过滤按 session.phase；unified 按 milestone
+- [ ] quality_mode 由 A_DETERMINE_QUALITY_MODE 决定，过滤 build steps
+- [ ] Decomposition: broad intent ≤3 question clarify；narrow auto-derive
+- [ ] status.json 唯一真源：boundary_contract + execution_criteria + task_decomposition；无外部清单
+- [ ] 每个 step 默认 `type: "internal"`，含 `command_scope` + `command_path`（全局优先 fallback 项目）
+- [ ] 每个 step 含 `completion_confirmed` + `completion_status` + `completion_evidence`（初始 false/null）
+- [ ] 每个 sub-goal 含 `completion_confirmed`（初始 false）
+- [ ] post-goal-audit decision 仅在 decomposed 时插入，位于 milestone-complete 之前
+- [ ] Unmet sub-goals 动态 grow steps[]（goal_ref tagged）；max retries → escalate
+- [ ] planning_mode 显式决定；unified=无 `{phase}`, independent=带 `{phase}`
+- [ ] Chain 必须以 `milestone-complete` 结尾
+- [ ] Decision nodes 由 maestro delegate --role analyze 评估
+- [ ] Ralph 不执行 step，只 evaluate；Skill("maestro-ralph-execute") handoff
 
 </appendix>