maestro-flow 0.4.14 → 0.4.16

package/.agents/skills/maestro/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: maestro
 description: Auto-route intent to optimal command chain
-argument-hint: "<intent> [-y] [-c] [--dry-run] [--exec auto|cli|internal] [--tool <name>] [--super]"
+argument-hint: "<intent> [-y] [-c] [--dry-run] [--super]"
 allowed-tools:
   - read_file
   - write_file
@@ -42,22 +42,20 @@ $ARGUMENTS — user intent text, or special keywords.
 - `-y` / `--yes` — Auto mode: skip clarification, skip confirmation, auto-skip on errors
 - `-c` / `--continue` — Resume previous session
 - `--dry-run` — Show chain without executing
-- `--exec <mode>` — `auto` (default), `cli`, `internal`
-- `--tool <name>` — CLI tool for delegates (default: claude)
 - `--super` — Read and follow `maestro-super.md`
 </context>
 
 <invariants>
 1. **All chains dispatch via maestro-ralph-execute** — maestro never executes steps directly
 2. **Session before execution** — status.json created before any step runs
-3. **Auto flags only to supporting commands** — unlisted commands execute as-is
+3. **Auto flag pass-through** — 仅当用户传入 `-y` 时透传 `-y` 到 skill args
 4. **Decomposition contract shared with maestro-ralph** — broad/lifecycle intents run S_DECOMPOSE producing the SAME additive block (`boundary_contract`, `execution_criteria`, `task_decomposition`)。Reference maestro-ralph `A_DECOMPOSE_TASKS`
 5. **status.json 唯一真源** — 不生成 `goal-checklist.md` 或外部清单
-6. **Default step type = internal** — chain 内每个 step 解析 `command_scope`/`command_path`（全局优先 `~/.claude/commands/{name}.md`，fallback 项目）
-7. **Topology awareness** — chain catalog 含 brainstorm / blueprint / analyze-macro(text) / analyze(numeric phase) / roadmap / plan(三路径) / execute / verify / ...；scope_verdict 路由由 ralph 在 `post-analyze-scope` 决定
-8. **D-007 milestone 反查** — 数字 phase 步骤的 `milestone_id` 由 `state.json.milestones[].phase_slugs` 反查得出
-9. **每个 step 必须 `completion_confirmed: true`** — 基于 `--- COMPLETION STATUS ---` 的 `STATUS: DONE`
-10. **schema 向后兼容** — 新增字段全部可选；既有字段名不删不改
+6. **执行步骤统一通过 `maestro ralph next` 加载** — `command_scope`/`command_path` 由 `maestro ralph skills --json --quiet` 预校验（project 覆盖 global）；decision 节点不走 CLI，走 `invoke_skill("maestro-ralph")` handoff
+7. **Topology awareness** — chain catalog 含 brainstorm / blueprint / analyze-macro / analyze / roadmap / plan(三路径) / execute / verify / ...；scope_verdict 由 ralph 在 `post-analyze-scope` 决定
+8. **D-007 milestone 反查** — 数字 phase 的 `milestone_id` 由 `state.json.milestones[].phase_slugs` 反查
+9. **每个 step 必须 `completion_confirmed: true`** — 由 `maestro ralph complete N --status DONE|DONE_WITH_CONCERNS` 写入
+10. **schema** — `ralph_protocol_version: "1"` 标记 CLI-driven session；新增字段全部可选
 </invariants>
 
 <state_machine>
@@ -143,7 +141,7 @@ S_FALLBACK:
    - 数字 phase 上下文 → `analyze {phase}` → `plan {phase}` → `execute {phase}` → `verify {phase}` → quality pipeline
    - 已有 analyze artifact 想直达执行 → `plan --from analyze:{ANL_ID}` → execute → verify
    - 已有 blueprint artifact → `plan --from blueprint:{BLP_ID}` → execute → verify
-4. 每个 step 默认 `type: "internal"`；解析 `command_scope` + `command_path`（全局优先 fallback 项目）；写入 `step.stage` / `step.scope` / `step.source_artifact_ref`（如 `--from` 注入时）
+4. 执行 step：`shell("maestro ralph skills --json --quiet")` 预校验 skill 名，命中写绝对路径到 `command_path`，未命中标 `missing`；同时写 `step.stage` / `step.scope` / `step.source_artifact_ref`。decision 节点不解析 command_path
 
 ### A_CLARIFY
 
@@ -159,9 +157,9 @@ S_FALLBACK:
 3. 派生 `execution_criteria` + `task_decomposition`（每个 sub-goal 含 `done_when` + `evidence` + `lifecycle` + `completion_confirmed: false`）
 4. **status.json 唯一真源**：写入 `boundary_contract` / `execution_criteria` / `task_decomposition`；不生成 markdown 清单
 5. 在最后一个 evidence-producing stage（verify/review/test）之后、`milestone-complete` 之前追加 `decision:post-goal-audit`。ralph-execute 在该节点按需动态生长 `steps[]`
-6. **输出 `/goal` 绑定提示词：**
+6. **输出 `/goal` 绑定提示词（不阻塞，用户可在执行过程中随时输入）：**
    ```
-   📋 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：
+   📋 任务分解完成。可随时复制下面一行设定目标（执行过程中输入即可）：
 
    /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。
    ```
@@ -173,29 +171,28 @@ S_FALLBACK:
    ```json
    {
      "session_id", "source": "maestro", "intent", "task_type", "chain_name",
+     "ralph_protocol_version": "1", "active_step_index": null,
      "phase", "phase_is_new": false, "milestone": "",
      "scope_verdict": null, "analyze_macro_id": null, "blueprint_id": null,
-     "auto_mode": false, "exec_mode": "auto", "cli_tool": "claude",
+     "auto_mode": false, "cli_tool": "claude",
      "context": { "scratch_dir": null, "plan_dir": null, "analysis_dir": null,
        "brainstorm_dir": null, "blueprint_dir": null, "issue_id": null },
      "steps": [{
-       "index": 0, "type": "internal|external|decision",
-       "skill": "", "args": "",
-       "stage": "", "scope": null,
-       "command_scope": "global|project|missing|null",
-       "command_path": "~/.claude/commands/{name}.md | .claude/commands/{name}.md | null",
+       "index": 0, "skill": "", "args": "",
+       "stage": "", "scope": null, "decision": null,
+       "command_scope": "global|project|missing|null", "command_path": "<abs> | null",
        "milestone_id": null, "source_artifact_ref": null,
        "status": "pending", "goal_ref": null,
        "completion_confirmed": false, "completion_status": null,
-       "completion_evidence": null, "completed_at": null
+       "completion_evidence": null, "completed_at": null,
+       "deferred_reads": [], "load": null
      }],
      "waves": [], "current_step": 0, "status": "running",
      "boundary_contract": {}, "execution_criteria": [],
      "task_decomposition": [], "task_decomposition_all_done": false
    }
    ```
-   Decomposition 字段仅在 A_DECOMPOSE_TASKS 产出时写入（additive）
-3. Validate: 所有 step 的 `command_scope != "missing"`；否则 raise E005 列出缺失 skill
+3. Validate: 所有 step 的 `command_scope != "missing"`，否则 raise E005 列出缺失 skill
 4. Initialize tracking via `track_tasks`
 5. If `--super`: read `maestro-super.md`, follow it completely
 
@@ -205,25 +202,6 @@ S_FALLBACK:
 
 <appendix>
 
-### Auto-Yes Flag Map
-
-| Command | Auto Flag | Effect |
-|---------|-----------|--------|
-| maestro-init | `-y` | Skip interactive questioning |
-| maestro-analyze | `-y` | Skip scoping, auto-deepen |
-| maestro-brainstorm | `-y` | Skip questions, use defaults |
-| maestro-blueprint | `-y` | Skip interview, use recommended defaults |
-| maestro-roadmap | `-y` | Skip questions (create/revise/review) |
-| maestro-impeccable | `-y` | Auto-select design variant + skip confirmations |
-| maestro-plan | `-y` | Skip confirmations and clarification |
-| maestro-execute | `-y` | Skip confirmations, blocked auto-continue |
-| quality-auto-test | `-y` | Skip plan confirmation |
-| quality-test | `-y --auto-fix` | Auto-trigger gap-fix loop |
-| quality-retrospective | `-y` | Accept all routing recommendations |
-| maestro-milestone-complete | `-y` | Skip knowledge promotion |
-
-Unlisted commands have no auto flags.
-
 ### Error Codes
 
 | Code | Severity | Description | Recovery |
@@ -248,8 +226,10 @@ Unlisted commands have no auto flags.
 - [ ] status.json 唯一真源；无 markdown 清单；post-goal-audit 节点在 decomposed 时追加；/goal 提示词以 status.json 为判据
 - [ ] Chain selected and confirmed (or auto-confirmed)
 - [ ] Session dir created with status.json before execution; decomposition fields additive-only
-- [ ] 每个 step 含 `command_scope` + `command_path` + `completion_confirmed` 字段
-- [ ] Auto flags propagated to supporting commands only
+- [ ] 执行 step 含 `command_scope` + `command_path` + `completion_confirmed`；decision step 由 `step.decision` 标识
+- [ ] `command_scope`/`command_path` 由 `maestro ralph skills --json --quiet` 预校验（project 覆盖 global）
+- [ ] Session schema 含 `ralph_protocol_version: "1"` + `active_step_index: null` + step.load 占位
+- [ ] 用户传入 `-y` 时透传到 skill args
 - [ ] All chains dispatched via maestro-ralph-execute
 - [ ] Low-complexity intents routed to maestro-quick
 - [ ] (super) Requirements validated before roadmap

package/.agents/skills/maestro-plan/SKILL.md

@@ -136,18 +136,19 @@ Next steps:
   /maestro-plan {phase}         -- Re-plan with modifications
 ```
 
-**Completion status:**
+**Completion (when invoked from ralph):**
+End the step by calling the CLI (no `--- COMPLETION STATUS ---` text block):
 ```
---- COMPLETION STATUS ---
-STATUS: DONE|NEEDS_CONTEXT
-CONCERNS: {description if applicable}
-NEXT: /maestro-execute
---- END STATUS ---
+maestro ralph complete <idx> --status DONE [--evidence scratch/{YYYYMMDD}-plan-P{N}-{slug}/plan.json]
 ```
 
-Status mapping:
-- **DONE** — Plan created/revised and confirmed → NEXT: /maestro-execute
-- **NEEDS_CONTEXT** — Ambiguous requirements, insufficient context to produce plan
+STATUS verdicts (CLI-enforced enum):
+- **DONE** — Plan created/revised and confirmed → next step picks up automatically
+- **DONE_WITH_CONCERNS** — Plan produced but with explicit caveats; pass `--concerns "..."`
+- **NEEDS_RETRY** — Plan failed (tooling error, transient issue); ralph will retry
+- **BLOCKED** — External hard blocker (e.g., upstream artifact missing, dependency unavailable); pass `--reason "..."`
+
+> Ambiguous requirements are NOT a completion status — resolve them in-place via `ask_user` during planning (≤3 rounds), then proceed to DONE. `NEEDS_CONTEXT` has been removed; context shortage is handled by the harness's automatic compaction.
 
 ### Mode: Revise / Check
 

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

@@ -19,7 +19,7 @@ Closed-loop decision engine for the maestro workflow lifecycle.
 Reads project state → infers position → builds adaptive chain → delegates execution.
 
 Entry points:
-- **`/maestro-ralph "intent"`** — New session: infer → decompose → build → (decomposition → emit /goal prompt, STOP；否则 dispatch ralph-execute)
+- **`/maestro-ralph "intent"`** — New session: infer → decompose → build → emit /goal prompt（如有 decomposition）→ dispatch ralph-execute
 - **`/maestro-ralph continue`** — Wrapper; dispatches to ralph-execute（首选直接 `/maestro-ralph-execute` 推进 step）
 - **`/maestro-ralph status`** — Display session progress
 
@@ -27,10 +27,9 @@ Entry points:
 
 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。
 
-Node types:
-- **internal** (default): ralph-execute `read_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`）
+Step kinds:
+- **执行 step**: ralph-execute 调 `shell("maestro ralph next")` 加载 command .md + required_reading 全文，按 stdout 内联执行
+- **decision step**: `step.decision` 字段非空；回 ralph 评估（CLI 只读分析）
 
 Key difference from maestro coordinator:
 - maestro: static chain → one-time selection → runs all steps
@@ -47,9 +46,9 @@ Mutual invocation with `/maestro-ralph-execute` forms a self-perpetuating work l
                               │           writes status.json
                               │           emits /goal prompt
                               ▼
-                       ralph-execute  ◀─┐ internal → read_file(command_path) inline
-                              │         │ decision → invoke_skill("maestro-ralph")
-                              └─────────┘ writes step.completion_confirmed
+                       ralph-execute  ◀─┐ 执行 step → `maestro ralph next` + inline + `ralph complete`
+                              │         │ decision step → invoke_skill("maestro-ralph")
+                              └─────────┘ CLI writes step.completion_confirmed
                        loop until all completion_confirmed | paused
 ```
 </purpose>
@@ -72,14 +71,14 @@ Remaining     → intent
 
 <invariants>
 1. **Ralph never executes steps** — only creates sessions and evaluates decisions
-2. **Handoff via invoke_skill("maestro-ralph-execute")** — 仅当 session 无 `task_decomposition` 时在创建后自动 handoff；decomposition 路径 STOP 等用户输入。decision 评估后始终 handoff
+2. **Handoff via invoke_skill("maestro-ralph-execute")** — 创建 session 后始终自动 handoff；decision 评估后始终 handoff
 3. **Decision delegates read-only** — `maestro delegate --role analyze --mode analysis`
-4. **Default type = internal** — `external` 仅显式标注时出现，build 不默认生成
+4. **执行 step 通过 `maestro ralph next` CLI 加载并内联执行**（详见 invariant 8）
 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. **Internal step 加载契约** — ralph-execute 读 `command_path` 后，必须解析并加载该命令 `<required_reading>` 引用的所有文件（"入口 + workflow"形式的核心），并把 `<deferred_reading>` 路径记录到 `step.deferred_reads`；加载完成后输出 `✓ skill {name} 加载完成`。ralph 在 build 阶段只解析路径，不读 .md 内容
-9. **Decomposition is outcome-oriented** — sub-goals 为可观测交付，禁止 lifecycle 复刻；`/goal` 用户绑定，ralph 只发提示词后 STOP，等用户输入
+6. **每个 step 必须 `completion_confirmed: true`** — 由 `maestro ralph complete N --status DONE`（或 DONE_WITH_CONCERNS）写入；CLI 是唯一合法写入路径
+7. **command_path 在 A_BUILD_STEPS 解析** — 通过 `maestro ralph skills --json --quiet` 预校验（project 覆盖 global），命中即写绝对路径到 status.json；未命中标 `command_scope = "missing"`
+8. **执行 step 加载契约** — 由 `maestro ralph next` CLI 在执行期完成：解析 frontmatter + `<required_reading>` + `<deferred_reading>`，自动读取 required 文件全文并拼入 prompt；缺失 required → 退出码 1（E007），pause session。ralph build 阶段只通过 `maestro ralph skills` 校验路径存在性，不读 .md 内容
+9. **Decomposition is outcome-oriented** — sub-goals 为可观测交付，禁止 lifecycle 复刻；`/goal` 用户绑定，ralph 输出提示词后继续 handoff，用户可在执行过程中随时输入 `/goal`
 10. **planning_mode governs arg granularity** — `unified` → skill args 无 `{phase}`；`independent` → 含 `{phase}`
 11. **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>
@@ -151,9 +150,8 @@ S_BUILD_CHAIN:
   → S_CREATE_SESSION DO: A_BUILD_STEPS
 
 S_CREATE_SESSION:
-  → END             WHEN: task_decomposition present        DO: A_CREATE_SESSION (emits Goal Prompt → STOP，等用户输入 /goal 后手动 /maestro-ralph-execute)
-  → S_CONFIRM       WHEN: not auto_confirm AND no decomposition DO: A_CREATE_SESSION
-  → S_DISPATCH      WHEN: auto_confirm AND no decomposition  DO: A_CREATE_SESSION
+  → S_CONFIRM       WHEN: not auto_confirm                   DO: A_CREATE_SESSION
+  → S_DISPATCH      WHEN: auto_confirm                       DO: A_CREATE_SESSION
 
 S_CONFIRM:
   → S_DISPATCH      WHEN: user selects "Proceed"
@@ -163,7 +161,7 @@ S_CONFIRM:
 S_DISPATCH:
   → END             DO: invoke_skill({ skill: "maestro-ralph-execute" })
 
-S_DECISION_EVAL:
+S_DECISION_EVAL: (decision 节点 == `step.decision` 非空，下述 gate 名取自该字段)
   → S_APPLY_VERDICT WHEN: quality-gate (post-verify, post-business-test, post-review, post-test)
                      DO: A_DELEGATE_EVALUATE
   → S_APPLY_VERDICT WHEN: goal-gate (post-goal-audit)
@@ -202,7 +200,7 @@ S_FALLBACK:
 
 1. Find latest ralph session (by created_at)
 2. Display: Session, Status, Position, Progress, Current step
-3. List steps: [✓] completion_confirmed, [▸] current, [ ] pending, [◆] decision；附 `command_scope`(global/project) + `command_path`
+3. List steps: [✓] completion_confirmed, [▸] current, [ ] pending, [◆] decision（`step.decision` 非空）；执行 step 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
@@ -382,24 +380,26 @@ narrow → derive defaults from intent + codebase, skip questions.
 
 Generate steps from `session.lifecycle_position` to `milestone-complete`.
 
-| Stage | invoke_skill(independent) | invoke_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 |
+| Stage | invoke_skill(independent) | invoke_skill(unified) | Decision after | quality_mode |
+|-------|---------------------|-----------------|----------------|--------------|
+| brainstorm | `maestro-brainstorm "{intent}"` | *(same)* | — | all |
+| blueprint | `maestro-blueprint "{intent}"` | *(same)* | — | all |
+| init | `maestro-init` | *(same)* | — | all |
+| analyze-macro | `maestro-analyze "{intent}"` | *(same)* | `post-analyze-scope` | all |
+| roadmap | `maestro-roadmap --from analyze:{analyze_macro_id}` | *(same)* | — | all |
+| analyze | `maestro-analyze {phase}` | `maestro-analyze` | — | 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` | — | all |
+| execute | `maestro-execute {phase}` | `maestro-execute` | — | all |
+| verify | `maestro-verify {phase}` | `maestro-verify` | `post-verify` | all |
+| business-test | `quality-auto-test {phase}` | `quality-auto-test` | `post-business-test` | full only |
+| review | `quality-review {phase}` | `quality-review` | `post-review` | all (quick: append `--tier quick`) |
+| test-gen | `quality-auto-test {phase}` | `quality-auto-test` | — | full / standard if coverage<80% |
+| test | `quality-test {phase}` | `quality-test` | `post-test` | full, standard |
+| milestone-audit | `maestro-milestone-audit` | *(same)* | — | all |
+| goal-audit | *(decision-only)* | *(same)* | `post-goal-audit` | all (only if decomposed) |
+| milestone-complete | `maestro-milestone-complete` | *(same)* | `post-milestone` | all |
+
+> 所有执行 stage 统一通过 `maestro ralph next` CLI 加载 + 内联执行；decision 节点单独作为独立 step 插入（见规则 4）。
 
 **Build rules (按顺序应用):**
 
@@ -407,18 +407,19 @@ Generate steps from `session.lifecycle_position` to `milestone-complete`.
 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 }`
+4. **决策节点**：每个 Decision after 非空的 stage 之后插入 `{ decision: "<gate>", retry_count: 0, max_retries: 2, command_scope: null, command_path: null }`
 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）：
+9. **command_path 解析**（每个执行 step，decision 节点跳过）：
    - 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
-   - **不在 build 阶段读取 .md 内容**；`<required_reading>` / `<deferred_reading>` 解析与加载由 ralph-execute A_EXEC_INTERNAL 负责（保持入口/工作流分离）
-10. **每个 step 初始化** `completion_confirmed: false`, `completion_status: null`, `completion_evidence: null`, `deferred_reads: []`
+   - **预校验通过 `shell("maestro ralph skills --json --quiet")`** 一次性拉取所有可用 commands + skills（global + project，project 覆盖 global），匹配 skill 名得到：
+     - 命中 commands → `command_scope = "global" | "project"`，`command_path = <绝对路径>`
+     - 命中 skills → 同上（type=skill）
+     - 未命中 → `command_scope = "missing"`, `command_path = null`，A_CREATE_SESSION 报错 E006
+   - **不在 build 阶段读取 .md 内容**；`<required_reading>` / `<deferred_reading>` 解析与加载由 `maestro ralph next` CLI 在执行期完成
+10. **每个 step 初始化** `completion_confirmed: false`, `completion_status: null`, `completion_evidence: null`, `deferred_reads: []`, `load: null`（由 `ralph next` 写入）
 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}`）
@@ -436,7 +437,7 @@ Generate steps from `session.lifecycle_position` to `milestone-complete`.
 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 **Goal Prompt block** (Appendix) → STOP，等用户输入 `/goal`（auto_confirm 也不跳过）
+4. If `task_decomposition` present: display **Goal Prompt block** (Appendix)，不阻塞流程，继续 handoff
 
 ### A_DELEGATE_EVALUATE
 
@@ -597,6 +598,8 @@ Runs only when `task_decomposition` present.
 {
   "session_id": "ralph-{YYYYMMDD-HHmmss}",
   "source": "ralph", "status": "running",
+  "ralph_protocol_version": "1",   // CLI-driven; absent/0 → legacy inline ralph-execute
+  "active_step_index": null,       // CLI-managed; only one step held at a time
   "intent": "", "lifecycle_position": "",
   "phase": null, "phase_is_new": false,
   "milestone": "",                // D-007 反查结果，禁止读 current_milestone
@@ -611,13 +614,15 @@ Runs only when `task_decomposition` present.
     "analysis_dir": null, "brainstorm_dir": null, "blueprint_dir": null },
   "steps": [{
     "index": 0,
-    "type": "internal|external|decision",
-    "skill": "",
+    "skill": "",                  // 执行 step 有值；decision 节点为空字符串/null
     "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",
+    "decision": null,             // 非 null → decision 节点（值为 gate 名，如 "post-verify"）；null → 执行 step
+    "retry_count": 0,             // decision 节点专用
+    "max_retries": 2,             // decision 节点专用
+    "command_scope": "global|project|missing|null",  // 执行 step；decision 节点固定 null
+    "command_path": "<absolute path resolved by `maestro ralph skills --json --quiet`> | 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",
@@ -626,7 +631,8 @@ Runs only when `task_decomposition` present.
     "completion_status": null,
     "completion_evidence": null,
     "completed_at": null,
-    "deferred_reads": []          // 由 ralph-execute A_EXEC_INTERNAL 解析 .md 时填充
+    "deferred_reads": [],         // 由 ralph next CLI 解析 .md 时填充
+    "load": null                  // { loaded_at, required_files[], deferred_files[], resolve_version } —— 由 ralph next 写入
   }],
   "waves": [], "current_step": 0,
 
@@ -648,7 +654,7 @@ Runs only when `task_decomposition` present.
 
 ### 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`。
+所有插入的执行 step 按 A_BUILD_STEPS 规则 9 解析 `command_path` + `command_scope`；`decision:*` 条目为 decision 节点（`step.decision` 字段）。
 
 **post-verify:**
 ```
@@ -710,12 +716,12 @@ decision:post-goal-audit {retry+1}
 链路概览后逐字显示（仅当 decomposition 已产出）：
 
 ```
-📋 任务分解完成。复制以下 /goal 设定终止条件，随后运行 /maestro-ralph-execute：
+📋 任务分解完成。可随时复制以下 /goal 设定终止条件（执行过程中输入即可）：
 
 /goal 直到 {session_dir}/status.json 的 task_decomposition[*] 与 steps[*] 全部 completion_confirmed=true 才停。每轮以 status.json 为唯一行动手册，通过 /maestro-ralph-execute 推进 step；decision 节点由其自动 handoff 回 ralph 评估。禁止手动执行 skill 或修改 boundary_contract.out_of_scope。
 ```
 
-`/goal` 由用户输入；ralph 只输出此提示词。判据以 status.json 为权威。
+`/goal` 由用户输入；ralph 输出提示词后继续 handoff，不阻塞。
 
 ### Error Codes
 
@@ -747,8 +753,8 @@ decision:post-goal-audit {retry+1}
 - [ ] 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）
-- [ ] Ralph build 阶段只解析路径，不读 .md 内容；`<required_reading>` 加载由 ralph-execute A_EXEC_INTERNAL 完成
+- [ ] 执行 step 含 `command_scope` + `command_path`（通过 `maestro ralph skills --json --quiet` 预校验，project 覆盖 global）；decision step 通过 `step.decision` 字段标识
+- [ ] Ralph build 阶段只通过 `ralph skills` 校验路径存在性，不读 .md 内容；`<required_reading>` 加载由 `maestro ralph next` CLI 完成
 - [ ] 每个 step 含 `completion_confirmed` + `completion_status` + `completion_evidence` + `deferred_reads`（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