maestro-flow 0.3.38 → 0.3.40

package/.claude/commands/maestro-quick.md

@@ -1,56 +1,56 @@
----
-name: maestro-quick
-description: Execute a quick task with workflow guarantees but skip optional agents
-argument-hint: "[description] [--full] [--discuss]"
-allowed-tools:
-  - Read
-  - Write
-  - Edit
-  - Bash
-  - Glob
-  - Grep
-  - Task
-  - AskUserQuestion
----
-<purpose>
-Execute small, ad-hoc tasks with workflow guarantees (atomic commits, state tracking) using a shortened pipeline. Invoked for tasks that are well-understood and do not require full phase-level planning. Produces scratch task directory with plan, execution results, and optional verification. Flags --discuss and --full enable additional pipeline stages.
-</purpose>
-
-<required_reading>
-@~/.maestro/workflows/quick.md
-</required_reading>
-
-<context>
-$ARGUMENTS
-
-Parse for:
-- `--full` flag -- Enables plan-checking (max 2 iterations) and post-execution verification
-- `--discuss` flag -- Decision extraction before planning (gray areas, Locked/Free/Deferred classification)
-- Remaining text as task description
-</context>
-
-<execution>
-Follow '~/.maestro/workflows/quick.md' completely.
-
-**Next-step routing on completion:**
-- Task done, --full verification passed → /manage-status
-- Task done, verification found gaps → /quality-debug {issue}
-- Task done, want to sync docs → /quality-sync
-- Need a full phase workflow instead → /maestro-plan {phase}
-</execution>
-
-<error_codes>
-| Code | Severity | Condition | Recovery |
-|------|----------|-----------|----------|
-| E001 | error | Task description required (no text provided) | Check arguments format, re-run with correct input |
-| E002 | error | Scratch directory creation failed | Check disk space and .workflow/ permissions |
-| W001 | warning | Verification found minor gaps | Review gaps and determine if they need fixing |
-</error_codes>
-
-<success_criteria>
-- [ ] Scratch task directory created under .workflow/scratch/
-- [ ] plan.json written with task definitions
-- [ ] All tasks executed with summaries written
-- [ ] state.json updated with scratch task entry
-- [ ] Commit created with task changes
-</success_criteria>
+---
+name: maestro-quick
+description: Quick task execution, skip optional agents
+argument-hint: "[description] [--full] [--discuss]"
+allowed-tools:
+  - Read
+  - Write
+  - Edit
+  - Bash
+  - Glob
+  - Grep
+  - Task
+  - AskUserQuestion
+---
+<purpose>
+Execute small, ad-hoc tasks with workflow guarantees (atomic commits, state tracking) using a shortened pipeline. Invoked for tasks that are well-understood and do not require full phase-level planning. Produces scratch task directory with plan, execution results, and optional verification. Flags --discuss and --full enable additional pipeline stages.
+</purpose>
+
+<required_reading>
+@~/.maestro/workflows/quick.md
+</required_reading>
+
+<context>
+$ARGUMENTS
+
+Parse for:
+- `--full` flag -- Enables plan-checking (max 2 iterations) and post-execution verification
+- `--discuss` flag -- Decision extraction before planning (gray areas, Locked/Free/Deferred classification)
+- Remaining text as task description
+</context>
+
+<execution>
+Follow '~/.maestro/workflows/quick.md' completely.
+
+**Next-step routing on completion:**
+- Task done, --full verification passed → /manage-status
+- Task done, verification found gaps → /quality-debug {issue}
+- Task done, want to sync docs → /quality-sync
+- Need a full phase workflow instead → /maestro-plan {phase}
+</execution>
+
+<error_codes>
+| Code | Severity | Condition | Recovery |
+|------|----------|-----------|----------|
+| E001 | error | Task description required (no text provided) | Check arguments format, re-run with correct input |
+| E002 | error | Scratch directory creation failed | Check disk space and .workflow/ permissions |
+| W001 | warning | Verification found minor gaps | Review gaps and determine if they need fixing |
+</error_codes>
+
+<success_criteria>
+- [ ] Scratch task directory created under .workflow/scratch/
+- [ ] plan.json written with task definitions
+- [ ] All tasks executed with summaries written
+- [ ] state.json updated with scratch task entry
+- [ ] Commit created with task changes
+</success_criteria>

package/.claude/commands/maestro-ralph-execute.md

@@ -1,6 +1,6 @@
 ---
 name: maestro-ralph-execute
-description: Single-step executor — find next pending step in session, execute by type (decision/internal/external), hand off to next iteration
+description: Execute next pending step in ralph session
 argument-hint: "[-y] [session-id]"
 allowed-tools:
   - Read
@@ -130,11 +130,6 @@ Display step banner:
 
 If decision node: also show `Retry: {retry_count}/{max_retries}` from parsed args.
 
-Context weight hint (non-auto only, after 4+ completed steps):
-```
-⚡ 已执行 {completed_count} 步，上下文较重。可 /maestro-ralph continue 在新上下文恢复。
-```
-
 ## Step 5: Execute by Type
 
 ### 5a. decision node (ralph-only)
@@ -189,13 +184,8 @@ HARD RULE: external nodes ALWAYS delegate to `claude` — only Claude Code can e
 
 ```
 Bash({
-  command: `maestro delegate "Execute: /${next.skill} ${next.args}
-
-You are a delegate session within a ralph/maestro pipeline.
-Your task: invoke the slash command /${next.skill} with args: ${next.args}
-Use Skill({ skill: \"${next.skill}\", args: \"${next.args}\" }) to execute it.
-Do NOT reimplement the skill logic manually — invoke the actual command.
-All artifact outputs follow the skill's own conventions." --to claude --mode write`,
+  command: `maestro delegate "Execute: Skill({ skill: \"${next.skill}\", args: \"${next.args}\" })
+Do NOT reimplement — invoke the skill command directly." --to claude --mode write`,
   run_in_background: true,
   timeout: 600000
 })
@@ -245,10 +235,10 @@ If not next.retried:
   next.retried = true, next.status = "pending", next.error = null
   Write status.json → Skill("maestro-ralph-execute")  // retry once
 Else:
-  next.status = "skipped"
+  status.status = "paused"
   Write status.json
-  Display: [{next.index}/{total}] ⏭ {next.skill} auto-skipped after retry
-  → Skill("maestro-ralph-execute")  // continue
+  Display: [{next.index}/{total}] ✗ {next.skill} 重试后仍失败，会话已暂停。请检查后 /maestro-ralph continue 恢复。
+  End.
 ```
 
 **Interactive mode (non-auto):**
@@ -302,7 +292,6 @@ Type badges: `◆` decision, `⚡` external, (none) internal.
 | E002 | error | Session status.json corrupt | Show path, suggest manual check |
 | E003 | error | CLI delegate failed + user abort | Mark paused, suggest resume |
 | W001 | warning | Step completed with warnings | Log and continue |
-| W002 | warning | Context heavy (step >= 4) | Hint: /maestro-ralph continue |
 </error_codes>
 
 <success_criteria>
@@ -316,7 +305,7 @@ Type badges: `◆` decision, `⚡` external, (none) internal.
 - [ ] external nodes use maestro delegate --to claude with run_in_background + STOP pattern
 - [ ] Context propagation: output signals update status.json.context
 - [ ] status.json updated after every status change (resume-safe)
-- [ ] Auto mode: retry once then skip; interactive: AskUserQuestion retry/skip/abort
+- [ ] Auto mode: retry once then pause; interactive: AskUserQuestion retry/skip/abort
 - [ ] Completion report shows all steps with status icons and type badges
 - [ ] Self-invocation chain continues until all steps complete or session paused
 </success_criteria>

package/.claude/commands/maestro-ralph.md

@@ -1,6 +1,6 @@
 ---
 name: maestro-ralph
-description: Closed-loop lifecycle decision engine — read project state, infer position, build adaptive command chain with decision/internal/external nodes
+description: Adaptive lifecycle engine — infer state, build command chain
 argument-hint: "[-y] \"intent\" | status | continue"
 allowed-tools:
   - Read
@@ -112,6 +112,12 @@ Also check: `.workflow/roadmap.md` existence, `.workflow/scratch/` for result fi
 
 ### 2.2: Infer lifecycle position
 
+**Phase 0 — Intent-based override:**
+
+If intent matches brainstorm pattern (contains "brainstorm", "头脑风暴", "探索", "ideate", or "设计思路"), position = `brainstorm` regardless of project state.
+
+Chain for existing project: `brainstorm → roadmap → analyze → ...` (skip init if `.workflow/state.json` exists).
+
 **Phase 1 — Bootstrap detection:**
 
 | Condition | Position | Chain starts at |
@@ -164,7 +170,7 @@ Generate steps from `lifecycle_position` to target (default: `milestone-complete
 
 | Stage | Skill command | Type | Decision after |
 |-------|--------------|------|----------------|
-| brainstorm | `maestro-brainstorm "{intent}"` | external | — (0→1 only) |
+| brainstorm | `maestro-brainstorm "{intent}"` | external | — |
 | init | `maestro-init` | internal | — |
 | roadmap | `maestro-roadmap "{intent}"` | internal | — |
 | analyze | `maestro-analyze {phase}` | external | — |
@@ -316,14 +322,32 @@ For quality-gate decisions (post-verify, post-business-test, post-review, post-t
 | Decision type | Files to include |
 |---------------|-----------------|
 | post-verify | `{artifact_dir}/verification.json` |
-| post-business-test | `{artifact_dir}/business-test-results.json` |
+| post-business-test | `{artifact_dir}/.tests/auto-test/report.json` |
 | post-review | `{artifact_dir}/review.json` |
 | post-test | `{artifact_dir}/uat.md`, `{artifact_dir}/.tests/test-results.json` |
 
+**Confidence-aware evaluation**:
+
+Before delegating, check if artifact contains a confidence section (added by downstream commands):
+- `verification.json` → `confidence.overall` (from maestro-verify)
+- `report.json` → `confidence.overall` (from quality-auto-test)
+- `review.json` → may contain dimension confidence (from quality-review)
+- `uat.md` → confidence summary section (from quality-test)
+
+If confidence data found, include in delegate prompt as additional signal:
+```
+已有置信度评估: 整体 {overall}%, 最弱维度: {weakest} ({score}%)
+```
+
+**Confidence-based verdict bias**: When artifact confidence is available:
+- confidence < 60% → bias toward "fix" even if surface status looks clean (hidden quality gaps)
+- confidence 60-95% → use delegate verdict as-is
+- confidence > 95% → bias toward "proceed" (strong evidence of quality)
+
 ```
 Bash({
   command: `maestro delegate "PURPOSE: 评估 ${meta.decision} 质量门结果，判断是否通过
-TASK: 读取结果文件 | 分析通过/失败状态 | 评估问题严重性 | 给出下一步建议
+TASK: 读取结果文件 | 分析通过/失败状态 | 评估问题严重性 | 检查置信度评分 | 给出下一步建议
 MODE: analysis
 CONTEXT: @${result_files}
 EXPECTED: 严格按以下格式输出:
@@ -332,8 +356,10 @@ STATUS: proceed | fix | escalate
 REASON: 一句话解释
 GAP_SUMMARY: 具体问题描述（仅 fix/escalate 时填写，用于传递给 quality-debug）
 CONFIDENCE: high | medium | low
+CONFIDENCE_SCORE: 0-100（从结果文件中读取置信度分数，无则估算）
+WEAKEST_DIMENSION: 最弱维度名称
 ---END---
-CONSTRAINTS: 只评估不修改 | STATUS 三选一 | 如果 retry ${meta.retry_count}/${meta.max_retries} 已达上限且仍有问题则必须 escalate" --role analyze --mode analysis`,
+CONSTRAINTS: 只评估不修改 | STATUS 三选一 | 置信度 < 60% 倾向 fix | 如果 retry ${meta.retry_count}/${meta.max_retries} 已达上限且仍有问题则必须 escalate" --role analyze --mode analysis`,
   run_in_background: true
 })
 STOP — wait for callback.
@@ -346,12 +372,20 @@ STOP — wait for callback.
 Parse structured response:
 ```
 Extract between ---VERDICT--- and ---END---:
-  verdict.status   = "proceed" | "fix" | "escalate"
-  verdict.reason   = string
-  verdict.gap_summary = string (context for quality-debug)
-  verdict.confidence = "high" | "medium" | "low"
+  verdict.status           = "proceed" | "fix" | "escalate"
+  verdict.reason           = string
+  verdict.gap_summary      = string (context for quality-debug)
+  verdict.confidence       = "high" | "medium" | "low"
+  verdict.confidence_score = 0-100 (numeric, from artifact or estimated)
+  verdict.weakest_dimension = string (weakest confidence dimension)
 
 If parse fails → fallback: treat as "fix" with generic gap_summary
+
+Confidence-based verdict adjustment (after parse, before apply):
+  If verdict.confidence_score < 60 AND verdict.status == "proceed":
+    → Override to "fix", reason += " (置信度不足: {score}%，{weakest_dimension} 需加强)"
+  If verdict.confidence_score > 95 AND verdict.status == "fix" AND retry_count > 0:
+    → Suggest "proceed" override, reason += " (置信度充分: {score}%，建议通过)"
 ```
 
 **Apply verdict:**
@@ -497,9 +531,11 @@ End.
 - [ ] Full quality pipeline generated: verify → business-test → review → test-gen → test
 - [ ] Decision nodes inserted after: post-verify, post-business-test, post-review, post-test, post-milestone
 - [ ] Quality-gate decisions delegated via `maestro delegate --role analyze --mode analysis`
-- [ ] Delegate verdict parsed: STATUS / REASON / GAP_SUMMARY / CONFIDENCE
-- [ ] `-y` mode: auto-follow delegate verdict without user confirmation
-- [ ] Interactive mode: display recommendation + AskUserQuestion with override options
+- [ ] Delegate verdict parsed: STATUS / REASON / GAP_SUMMARY / CONFIDENCE / CONFIDENCE_SCORE / WEAKEST_DIMENSION
+- [ ] Confidence-based verdict adjustment applied (< 60% bias fix, > 95% bias proceed)
+- [ ] Artifact confidence sections read when available (verification.json, report.json, uat.md)
+- [ ] `-y` mode: auto-follow adjusted verdict without user confirmation
+- [ ] Interactive mode: display recommendation with confidence score + AskUserQuestion with override options
 - [ ] Delegate failure fallback: treat as "fix" verdict
 - [ ] gap_summary from delegate passed to quality-debug as context
 - [ ] Fix-loop templates applied per decision type with retry_count increment

package/.claude/commands/maestro-roadmap.md

@@ -1,6 +1,6 @@
 ---
 name: maestro-roadmap
-description: Roadmap generation with dual mode — light (requirement→roadmap) or full (requirement→spec package→roadmap)
+description: Generate roadmap from requirements (light or full mode)
 argument-hint: "<requirement> [--mode light|full] [-y] [-c] [-m progressive|direct|auto] [--from-brainstorm SESSION-ID] [--revise [instructions]] [--review]"
 allowed-tools:
   - Read

package/.claude/commands/maestro-ui-design.md

@@ -1,93 +1,93 @@
----
-name: maestro-ui-design
-description: Generate UI design prototypes with multiple styles via ui-ux-pro-max, user selects winner, solidify as code reference
-argument-hint: "<phase|topic> [--styles N] [--stack <stack>] [--targets <pages>] [--layouts N] [--refine] [--persist] [--full] [-y]"
-allowed-tools:
-  - Read
-  - Write
-  - Edit
-  - Bash
-  - Glob
-  - Grep
-  - Agent
-  - AskUserQuestion
----
-<purpose>
-Generate UI design prototypes for a phase or topic. Two workflow paths, auto-selected by skill availability:
-
-1. **Primary (ui-style.md):** Delegates design to ui-ux-pro-max skill. Generates multiple style variants via `--design-system`, user selects, solidifies as code reference. Lightweight and fast.
-2. **Fallback (ui-design.md):** Self-contained 4-layer pipeline (style → animation → layout → assembly) with 6D attribute space, OKLCH tokens, layout templates, and full prototype matrix. Used when ui-ux-pro-max is unavailable or `--full` is requested.
-
-Both paths produce the same output contract: MASTER.md + design-tokens.json + animation-tokens.json + selection.json for downstream plan/execute consumption.
-
-Position in pipeline: analyze -> **ui-design** -> plan -> execute -> verify
-</purpose>
-
-<deferred_reading>
-- [ui-style.md](~/.maestro/workflows/ui-style.md) — read when SKILL_PATH found (primary path)
-- [ui-design.md](~/.maestro/workflows/ui-design.md) — read when SKILL_PATH empty or --full (fallback path)
-- [index.json](~/.maestro/templates/index.json) — read when updating phase metadata
-- [scratch-index.json](~/.maestro/templates/scratch-index.json) — read when operating in scratch mode
-</deferred_reading>
-
-<context>
-$ARGUMENTS — phase number for phase mode, topic text for scratch mode, with optional flags.
-
-Flags, workflow routing, scope modes, and output artifacts defined in the routed workflow (ui-style.md or ui-design.md).
-
-**Phase mode** (number): resolves phase directory, reads context.md/brainstorm for requirements.
-**Scratch mode** (text): creates `.workflow/scratch/{YYYYMMDD}-ui-design-{slug}/` for standalone exploration.
-</context>
-
-<execution>
-## Workflow Routing
-
-Detect ui-ux-pro-max skill availability and route to the appropriate workflow:
-
-- **`--full` flag present** → Follow '~/.maestro/workflows/ui-design.md' completely (forced full pipeline)
-- **ui-ux-pro-max found** → Follow '~/.maestro/workflows/ui-style.md' completely (lightweight delegation)
-- **ui-ux-pro-max not found** → Follow '~/.maestro/workflows/ui-design.md' completely (self-contained fallback)
-
-Skill detection logic, report format, and complete pipeline steps defined in the routed workflow file.
-
-**Next-step routing on completion:**
-- Plan with design reference → /maestro-plan {phase}
-- Refine selected design → /maestro-ui-design {phase} --refine
-- Analyze before planning → /maestro-analyze {phase}
-</execution>
-
-<error_codes>
-| Code | Severity | Description | Stage |
-|------|----------|-------------|-------|
-| E001 | error | Phase or topic argument required | parse_input |
-| E002 | error | Phase directory not found | parse_input |
-| E003 | error | Python not available (both paths need Python for ui-ux-pro-max or agent fallback) | setup |
-| E004 | error | --refine requires existing design-ref/ | parse_input |
-| W001 | warning | Design system generation returned partial results | generate |
-| W002 | warning | Prototype rendering failed for one variant | render |
-| W003 | warning | No context.md found, using phase goal only | context |
-| W004 | warning | ui-ux-pro-max not found, falling back to full pipeline | routing |
-</error_codes>
-
-<success_criteria>
-**Both paths (common):**
-- [ ] Requirements extracted from phase context (context.md, brainstorm, spec, or user input)
-- [ ] N style variants generated with contrasting design directions
-- [ ] User selected preferred variant (or auto-selected in -y mode)
-- [ ] MASTER.md written with complete design system specification
-- [ ] design-tokens.json written with production-ready tokens (OKLCH colors, component_styles)
-- [ ] animation-tokens.json written (duration, easing, transitions, keyframes)
-- [ ] selection.json recorded with choice metadata
-- [ ] index.json updated with design_ref status
-
-**ui-style.md path (primary):**
-- [ ] ui-ux-pro-max --design-system called with product/industry/style keywords
-- [ ] Tokens extracted from ui-ux-pro-max output into structured JSON
-
-**ui-design.md path (--full or fallback):**
-- [ ] 6D attribute space used for maximum contrast between variants
-- [ ] Layout templates generated per target (dom_structure + css_layout_rules)
-- [ ] HTML prototypes assembled: styles x layouts x targets
-- [ ] compare.html generated as interactive matrix viewer
-</success_criteria>
-</output>
+---
+name: maestro-ui-design
+description: Generate UI design prototypes, select and solidify as code
+argument-hint: "<phase|topic> [--styles N] [--stack <stack>] [--targets <pages>] [--layouts N] [--refine] [--persist] [--full] [-y]"
+allowed-tools:
+  - Read
+  - Write
+  - Edit
+  - Bash
+  - Glob
+  - Grep
+  - Agent
+  - AskUserQuestion
+---
+<purpose>
+Generate UI design prototypes for a phase or topic. Two workflow paths, auto-selected by skill availability:
+
+1. **Primary (ui-style.md):** Delegates design to ui-ux-pro-max skill. Generates multiple style variants via `--design-system`, user selects, solidifies as code reference. Lightweight and fast.
+2. **Fallback (ui-design.md):** Self-contained 4-layer pipeline (style → animation → layout → assembly) with 6D attribute space, OKLCH tokens, layout templates, and full prototype matrix. Used when ui-ux-pro-max is unavailable or `--full` is requested.
+
+Both paths produce the same output contract: MASTER.md + design-tokens.json + animation-tokens.json + selection.json for downstream plan/execute consumption.
+
+Position in pipeline: analyze -> **ui-design** -> plan -> execute -> verify
+</purpose>
+
+<deferred_reading>
+- [ui-style.md](~/.maestro/workflows/ui-style.md) — read when SKILL_PATH found (primary path)
+- [ui-design.md](~/.maestro/workflows/ui-design.md) — read when SKILL_PATH empty or --full (fallback path)
+- [index.json](~/.maestro/templates/index.json) — read when updating phase metadata
+- [scratch-index.json](~/.maestro/templates/scratch-index.json) — read when operating in scratch mode
+</deferred_reading>
+
+<context>
+$ARGUMENTS — phase number for phase mode, topic text for scratch mode, with optional flags.
+
+Flags, workflow routing, scope modes, and output artifacts defined in the routed workflow (ui-style.md or ui-design.md).
+
+**Phase mode** (number): resolves phase directory, reads context.md/brainstorm for requirements.
+**Scratch mode** (text): creates `.workflow/scratch/{YYYYMMDD}-ui-design-{slug}/` for standalone exploration.
+</context>
+
+<execution>
+## Workflow Routing
+
+Detect ui-ux-pro-max skill availability and route to the appropriate workflow:
+
+- **`--full` flag present** → Follow '~/.maestro/workflows/ui-design.md' completely (forced full pipeline)
+- **ui-ux-pro-max found** → Follow '~/.maestro/workflows/ui-style.md' completely (lightweight delegation)
+- **ui-ux-pro-max not found** → Follow '~/.maestro/workflows/ui-design.md' completely (self-contained fallback)
+
+Skill detection logic, report format, and complete pipeline steps defined in the routed workflow file.
+
+**Next-step routing on completion:**
+- Plan with design reference → /maestro-plan {phase}
+- Refine selected design → /maestro-ui-design {phase} --refine
+- Analyze before planning → /maestro-analyze {phase}
+</execution>
+
+<error_codes>
+| Code | Severity | Description | Stage |
+|------|----------|-------------|-------|
+| E001 | error | Phase or topic argument required | parse_input |
+| E002 | error | Phase directory not found | parse_input |
+| E003 | error | Python not available (both paths need Python for ui-ux-pro-max or agent fallback) | setup |
+| E004 | error | --refine requires existing design-ref/ | parse_input |
+| W001 | warning | Design system generation returned partial results | generate |
+| W002 | warning | Prototype rendering failed for one variant | render |
+| W003 | warning | No context.md found, using phase goal only | context |
+| W004 | warning | ui-ux-pro-max not found, falling back to full pipeline | routing |
+</error_codes>
+
+<success_criteria>
+**Both paths (common):**
+- [ ] Requirements extracted from phase context (context.md, brainstorm, spec, or user input)
+- [ ] N style variants generated with contrasting design directions
+- [ ] User selected preferred variant (or auto-selected in -y mode)
+- [ ] MASTER.md written with complete design system specification
+- [ ] design-tokens.json written with production-ready tokens (OKLCH colors, component_styles)
+- [ ] animation-tokens.json written (duration, easing, transitions, keyframes)
+- [ ] selection.json recorded with choice metadata
+- [ ] index.json updated with design_ref status
+
+**ui-style.md path (primary):**
+- [ ] ui-ux-pro-max --design-system called with product/industry/style keywords
+- [ ] Tokens extracted from ui-ux-pro-max output into structured JSON
+
+**ui-design.md path (--full or fallback):**
+- [ ] 6D attribute space used for maximum contrast between variants
+- [ ] Layout templates generated per target (dom_structure + css_layout_rules)
+- [ ] HTML prototypes assembled: styles x layouts x targets
+- [ ] compare.html generated as interactive matrix viewer
+</success_criteria>
+</output>