maestro-flow 0.3.39 → 0.3.41

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

@@ -108,6 +108,10 @@ Full mode:
 - [ ] analysis.md written with all 6 dimensions scored with evidence
 - [ ] conclusions.json created with recommendations and decision trail
 - [ ] Intent Coverage tracked and verified (no unresolved ❌ items)
+- [ ] Confidence tracking initialized (Step 4.6) and re-scored each round (Step 5.8)
+- [ ] Readiness gate checked before synthesis (Step 5.10)
+- [ ] Pressure pass completed ≥ 1 time before Step 6
+- [ ] Confidence summary with factor decomposition written to analysis.md
 
 Gaps mode:
 - [ ] Issues loaded from issues.jsonl (all open/registered, or single ISS-ID)

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

@@ -91,6 +91,10 @@ Single role mode:
 - [ ] Final Output Gate passed (Step 5.5) or `--yes` bypassed
 - [ ] All user decisions captured with Decision Recording Protocol
 - [ ] Session metadata updated with completion status
+- [ ] Confidence scored per role completion and after cross-role analysis
+- [ ] Readiness gate checked before spec generation
+- [ ] Pressure pass completed on at least 1 feature spec
+- [ ] Confidence summary appended to synthesis-changelog.md
 
 **Single role mode**:
 - [ ] analysis.md written to `{output_dir}/{role}/`

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

@@ -0,0 +1,333 @@
+---
+name: maestro-collab
+description: Multi-CLI collaborative analysis -- fan-out to multiple CLI tools, cross-verify, synthesize
+argument-hint: "\"<requirement>\" [--tools gemini,qwen,claude] [--mode analysis|write] [--rule <template>] [-y]"
+allowed-tools:
+  - Read
+  - Write
+  - Bash
+  - Glob
+  - Grep
+  - Agent
+  - AskUserQuestion
+---
+
+<purpose>
+Multi-CLI collaboration: fan-out the same requirement to multiple CLI tools in parallel, cross-verify outputs for consensus/conflicts, then synthesize into a unified report with standard downstream artifacts (context.md + conclusions.json).
+
+Each CLI tool independently analyzes the requirement. Results are compared and merged via evidence-weighted synthesis.
+</purpose>
+
+<context>
+$ARGUMENTS — requirement text and optional flags.
+
+```bash
+/maestro-collab "analyze the auth module for security vulnerabilities"
+/maestro-collab "design a caching strategy" --tools gemini,qwen,claude
+/maestro-collab -y "review error handling patterns"
+/maestro-collab "refactor user service" --mode write --tools gemini,claude
+```
+
+**Flags**:
+- `--tools <list>`: Comma-separated CLI tools (default: auto-select first 3 enabled)
+- `--mode analysis|write`: Delegate mode (default: analysis)
+- `--rule <template>`: Shared rule template for all delegates
+- `-y` / `--yes`: Skip plan confirmation
+
+**Output**: `.workflow/scratch/{YYYYMMDD}-collab-{slug}/`
+- `collab-report.md` — full collaboration report
+- `context.md` — standard Locked/Free/Deferred decisions (plan/analyze compatible)
+- `conclusions.json` — structured conclusions (plan fast-track compatible)
+- `per-tool/{tool}-output.md` — raw per-tool outputs
+</context>
+
+<execution>
+
+### Step 1: Parse Arguments
+
+Extract from `$ARGUMENTS`:
+- `requirement` — remaining text after flag removal (error if empty)
+- `--tools` → `selectedTools` (comma-split)
+- `--mode` → `delegateMode` (default: `analysis`)
+- `--rule` → `ruleTemplate`
+- `-y` / `--yes` → `autoYes`
+
+### Step 2: Discover Available CLI Tools
+
+```bash
+Bash("maestro tools list --json 2>/dev/null || cat ~/.maestro/cli-tools.json")
+```
+
+Parse tool entries. Build eligible list:
+- `enabled == true`
+- If `--mode write`: exclude `type == "api-endpoint"`
+
+Auto-select (when `--tools` omitted): first 3 eligible in config order.
+Validate: minimum 2 eligible tools (abort if fewer).
+
+### Step 3: Present Collaboration Plan
+
+**(Skip if `-y`)**
+
+Display plan, then ask user:
+
+```
+============================================================
+  COLLABORATION PLAN
+============================================================
+  Requirement: {requirement}
+  Mode:        {delegateMode}
+  Rule:        {ruleTemplate || "none"}
+
+  Available CLI Tools (from cli-tools.json):
+    [✓] gemini    — gemini-3.1-pro-preview     [fullstack, frontend]
+    [✓] claude    — claude-sonnet-4-6           [fullstack]
+    [✓] codex     — gpt-5.5                    [fullstack, backend]
+    [ ] opencode  — (no model)                  [fullstack]
+
+  Selected: gemini, claude, codex (3 tools)
+
+  Pipeline:
+    1. Fan-out → parallel delegate to each tool
+    2. Cross-verification → consensus/conflict analysis
+    3. Synthesis → context.md + conclusions.json
+============================================================
+```
+
+Use `AskUserQuestion` with options:
+- **执行** — proceed with selected tools
+- **修改工具选择** — let user specify different tool combination
+- **取消** — abort
+
+If **修改工具选择**: ask user which tools to use (show eligible list), validate ≥ 2, re-display plan.
+
+### Step 4: Setup Session
+
+```
+slug = requirement kebab-cased, max 40 chars
+outputDir = .workflow/scratch/{YYYYMMDD}-collab-{slug}/
+```
+
+Create `outputDir` + `outputDir/per-tool/`.
+
+### Step 5: Build Delegate Prompt
+
+Shared prompt for all tools:
+
+```
+PURPOSE: {requirement}; success = actionable findings with evidence
+TASK: {auto-decomposed into 3-5 specific verbs}
+MODE: {delegateMode}
+CONTEXT: @**/*
+EXPECTED: Structured findings with file:line references, confidence score (0-100), prioritized recommendations. Sections: ## Findings, ## Recommendations, ## Confidence
+CONSTRAINTS: {extracted from requirement}
+```
+
+### Step 6: Parallel Fan-Out
+
+Launch ALL delegate calls simultaneously using multiple `Bash(run_in_background: true)` in a **single message**:
+
+```
+// Launch all in ONE message — do NOT wait between calls
+Bash({
+  command: `maestro delegate "${prompt}" --to gemini --mode ${mode} ${rule}`,
+  run_in_background: true
+})
+Bash({
+  command: `maestro delegate "${prompt}" --to claude --mode ${mode} ${rule}`,
+  run_in_background: true
+})
+Bash({
+  command: `maestro delegate "${prompt}" --to codex --mode ${mode} ${rule}`,
+  run_in_background: true
+})
+```
+
+**After launching all calls → STOP immediately. Do not output anything. Wait for background completion callbacks.**
+
+### Step 7: Collect Results
+
+As each background callback arrives:
+1. Extract exec ID from output (`[MAESTRO_EXEC_ID=...]`)
+2. Run `maestro delegate output <id>` to get full result
+3. Write raw output to `per-tool/{tool}-output.md`
+
+**Wait until ALL callbacks have arrived before proceeding.**
+
+### Step 8: Cross-Verify
+
+Read all `per-tool/{tool}-output.md` files. Compare findings across tools:
+
+For each finding, classify:
+- **[CONSENSUS]**: 2+ tools agree on same finding/recommendation
+- **[CONFLICT]**: Tools disagree on approach or assessment
+- **[UNIQUE]**: Finding from only one tool
+
+Compute `consensus_level = (consensus_count / total_findings) * 100`.
+
+### Step 9: Synthesize Outputs
+
+Resolve conflicts via evidence-weighted voting:
+- Higher confidence tool's position wins
+- More specific evidence (file:line refs) wins over general statements
+- If tied: mark as `[SUGGESTED]`
+
+Generate three output files:
+
+#### collab-report.md
+
+```markdown
+# Multi-CLI Collaboration Report — {requirement}
+
+## Summary
+- Tools: {tool_list}
+- Consensus level: {N}%
+- Key finding: {top finding}
+
+## Consensus Findings
+{findings agreed by 2+ tools}
+
+## Resolved Conflicts
+{conflicts resolved with rationale and winning tool}
+
+## Unresolved Items
+{items requiring human judgment}
+
+## Unique Insights
+{valuable unique findings with source tool attribution}
+
+## Recommendations
+{prioritized, merged recommendations}
+
+## Per-Tool Confidence
+| Tool | Confidence | Key Strength |
+|------|-----------|--------------|
+```
+
+#### context.md (standard downstream format)
+
+```markdown
+# Context: {requirement}
+
+**Date**: {date}
+**Mode**: collab ({tool_list})
+**Consensus Level**: {N}%
+
+## Decisions
+
+### Decision N: {TITLE}
+- **Context**: {what and why}
+- **Options**: 1. {opt1} 2. {opt2}
+- **Chosen**: {selected}
+- **Reason**: {rationale — which tools agreed/disagreed}
+
+## Constraints
+
+### Locked
+{[CONSENSUS] items — treat as confirmed decisions}
+
+### Free
+{[UNIQUE] items with strong evidence — implementer discretion}
+
+### Deferred
+{[UNRESOLVED] conflicts — require human judgment}
+
+## Code Context
+{file:line references from per-tool findings}
+```
+
+#### conclusions.json
+
+```json
+{
+  "session_id": "{sessionId}",
+  "subject": "{requirement}",
+  "mode": "collab",
+  "tools": ["gemini", "claude", "codex"],
+  "consensus_level": 85,
+  "recommendation": "Go|No-Go|Conditional",
+  "confidence": "high|medium|low",
+  "dimensions": [
+    { "name": "gemini", "score": 80, "findings": "...", "recommendations": "..." }
+  ],
+  "decisions": [
+    { "title": "...", "classification": "locked|free|deferred", "source_tools": [], "rationale": "..." }
+  ],
+  "timestamp": "<ISO>"
+}
+```
+
+### Step 10: Register Artifact
+
+Append to `.workflow/state.json`:
+
+```json
+{
+  "id": "CLB-{next_id}",
+  "type": "collab",
+  "milestone": "{current_milestone}",
+  "phase": null,
+  "scope": "adhoc",
+  "path": "scratch/{YYYYMMDD}-collab-{slug}",
+  "status": "completed",
+  "depends_on": null,
+  "harvested": false,
+  "created_at": "<ISO>",
+  "completed_at": "<ISO>"
+}
+```
+
+### Step 11: Display Summary
+
+```
+============================================================
+  MULTI-CLI COLLABORATION COMPLETE
+============================================================
+  Requirement:     {requirement}
+  Tools:           {tool_list}
+  Consensus Level: {N}%
+
+  Per-Tool:
+    gemini:  completed (confidence: {N}%)
+    claude:  completed (confidence: {N}%)
+    codex:   completed (confidence: {N}%)
+
+  Artifact: CLB-{id}
+  Output:   {outputDir}/
+
+  Next steps:
+    /maestro-analyze "{topic}"            — Deep feasibility analysis
+    /maestro-plan "{phase} --dir {dir}"   — Plan from collab conclusions
+    /maestro-brainstorm "{topic}"         — Expand with multi-role brainstorm
+============================================================
+```
+
+</execution>
+
+<error_codes>
+
+| Code | Severity | Condition | Recovery |
+|------|----------|-----------|----------|
+| E001 | error | Requirement argument missing | Prompt for requirement |
+| E002 | error | Fewer than 2 CLI tools eligible | Check cli-tools.json, enable more tools |
+| E003 | error | Specified tool not found/enabled | Show available tools |
+| E004 | error | All delegates failed | Abort with per-tool error details |
+| W001 | warning | One tool failed | Continue with remaining tools |
+| W002 | warning | >50% conflicts in cross-verify | Highlight in report, recommend manual review |
+| W003 | warning | Low consensus level (<40%) | Flag in summary |
+
+</error_codes>
+
+<success_criteria>
+- [ ] Available tools discovered from cli-tools.json with eligibility filtering
+- [ ] Plan presented via AskUserQuestion with tool modification option (unless -y)
+- [ ] All delegates launched in parallel via Bash(run_in_background: true)
+- [ ] Execution stopped after launch — waited for all callbacks
+- [ ] Per-tool outputs written to per-tool/{tool}-output.md
+- [ ] Cross-verification: consensus/conflict/unique classification complete
+- [ ] collab-report.md produced with merged findings
+- [ ] context.md produced in Locked/Free/Deferred format (downstream compatible)
+- [ ] conclusions.json produced (plan fast-track compatible)
+- [ ] CLB artifact registered in state.json
+- [ ] Partial degradation: continued if 1+ tools succeeded
+</success_criteria>

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

@@ -143,8 +143,12 @@ Follow workflow plan.md § "Revise Mode" and § "Check Mode" respectively. These
 - [ ] Every task has `read_first[]` with at least the file being modified + source of truth files
 - [ ] Every task has `convergence.criteria[]` with grep-verifiable conditions (no subjective language)
 - [ ] Every task `action` and `implementation` contain concrete values (no "align X with Y")
+- [ ] Plan confidence scored in P4 with 5-dimension factor model
+- [ ] Plan readiness gate checked before P4.5 collision detection
+- [ ] Pressure pass completed on highest-complexity task
+- [ ] plan.json includes confidence section (overall, dimensions, pressure_pass)
 - [ ] Collision detection executed against same-milestone plans (non-blocking)
 - [ ] Plan-checker passed (or minor issues acknowledged)
-- [ ] User confirmation captured (execute/modify/cancel)
+- [ ] User confirmation captured (execute/modify/cancel) with confidence displayed
 - [ ] Artifact registered in state.json with correct scope/milestone/phase/depends_on
 </success_criteria>

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

@@ -326,10 +326,28 @@ For quality-gate decisions (post-verify, post-business-test, post-review, post-t
 | 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:
@@ -338,8 +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.
@@ -352,12 +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:**
@@ -503,9 +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/quality-auto-test.md

@@ -116,6 +116,10 @@ Append to state.json.artifacts[]:
 - [ ] Tests executed progressively (L0→L3) with fail-fast on critical
 - [ ] Iteration engine ran (inner: test_defect fix, outer: strategy adjust)
 - [ ] state.json, report.json, reflection-log.md written
+- [ ] Test confidence scored per iteration (Step 7.5) with 5-dimension factor model
+- [ ] Convergence check includes confidence >= 60% alongside pass_rate threshold
+- [ ] Pressure pass completed on highest-pass-rate layer before completion
+- [ ] report.json includes confidence section
 - [ ] index.json updated with auto_test section
 - [ ] If spec source: traceability matrix built, traceability.md written
 - [ ] If failures: issues auto-created in issues.jsonl

package/.claude/commands/quality-debug.md

@@ -115,7 +115,11 @@ If user confirms, invoke `Skill({ skill: "spec-add", args: "<category> <content>
 - [ ] evidence.ndjson written with structured NDJSON entries
 - [ ] understanding.md tracks evolving understanding per cluster
 - [ ] Root causes collected with fix_direction and affected_files
+- [ ] Multi-factor confidence scored per gap (Step 7.0) replacing simple high/medium/low
+- [ ] Readiness gate checked before ROOT CAUSE declaration
+- [ ] Pressure pass completed on confirmed hypothesis
+- [ ] Confidence table appended to understanding.md
 - [ ] If --from-uat: uat.md gaps updated with diagnosis artifacts
-- [ ] Results unified into diagnosis summary
+- [ ] Results unified into diagnosis summary with confidence section
 - [ ] Next step routed (plan --gaps + execute if fix needed, verify if fix applied, resume if inconclusive)
 </success_criteria>

package/.claude/commands/quality-test.md

@@ -95,6 +95,10 @@ Append to state.json.artifacts[]:
 - [ ] Severity inferred from natural language (never asked)
 - [ ] Batched writes: on issue, every 5 passes, or completion
 - [ ] test-results.json and coverage-report.json written
+- [ ] UAT confidence scored with 4-dimension factor model
+- [ ] Readiness gate checked before final report
+- [ ] Pressure pass completed if > 80% pass rate
+- [ ] Confidence summary appended to uat.md
 - [ ] index.json uat fields updated
 - [ ] If issues: parallel debug agents spawned per gap cluster
 - [ ] Gaps updated with root_cause, fix_direction, affected_files

package/.codex/skills/maestro/SKILL.md

@@ -139,9 +139,15 @@ After each barrier skill completes, read its artifacts and update `state.context
 }
 ```
 
-7. **Initialize plan tracking** (dual-track: status.json + update_plan):
+7. **Initialize tracking** (goal constraint → plan sub-items):
 
 ```
+// Goal = outer constraint — ensures entire chain completes
+functions.create_goal({
+  objective: `Maestro ${chain_name}: ${steps.length} steps [${steps.map(s => s.skill).join(' → ')}]`
+})
+
+// Plan = inner tracking — sub-step progress
 functions.update_plan({
   plan: steps.map((step, i) => ({
     id: `step-${i}`,
@@ -233,9 +239,12 @@ Object with all fields required: `status` ("completed"|"failed"), `skill_call` (
 
 ### Phase 3: Completion Report
 
-Finalize dual tracking:
+Finalize tracking:
 - status.json: `state.status = 'completed'`
 - update_plan: all steps → `"completed"` (skipped steps also marked completed)
+- **update_goal**: `functions.update_goal({ status: "complete" })` — release goal constraint
+
+**Note**: Abort path (Phase 2 step 7) does NOT call `update_goal` — goal stays running for `--continue` resume.
 
 ```
 === COORDINATE COMPLETE ===

package/.codex/skills/maestro-analyze/SKILL.md

@@ -112,6 +112,7 @@ id,title,description,dimension,analysis_type,deps,context_from,wave,status,findi
 | `findings` | Output | Key findings summary (max 500 chars) |
 | `score` | Output | Dimension score (0-100 for scoring tasks, empty for explore/decide) |
 | `recommendations` | Output | Dimension-specific recommendations |
+| `confidence_score` | Output | Per-dimension confidence score (0-100) from factor-based assessment |
 | `error` | Output | Error message if failed |
 
 ### Per-Wave CSV (Temporary)
@@ -356,6 +357,10 @@ Write wave CSV with `prev_context`, execute `spawn_agents_on_csv` for synthesis
 {prioritized recommendations with rationale}
 ```
 
+3b. **Confidence scoring** (full mode only):
+
+   Factors (weights): findings_depth(.30), evidence_strength(.25), coverage_breadth(.20), user_validation(.15, 0 in CSV mode), consistency(.10). Overall = average of dimension scores. Thresholds: <60% deeper | 60-80% optional | 80-95% converging | >95% converge. Append confidence summary to `analysis.md` and `conclusions.json`.
+
 4. Build `context.md` (both modes):
 
 ```markdown
@@ -479,6 +484,8 @@ echo '{"ts":"<ISO>","worker":"{id}","type":"exploration_finding","data":{"file":
 - [ ] analysis.md + conclusions.json produced (full mode only)
 - [ ] Deferred items auto-created as issues
 - [ ] Artifact registered in state.json
+- [ ] Confidence scored per dimension with factor-based model (full mode only)
+- [ ] Confidence summary appended to analysis.md and conclusions.json
 - [ ] Final outputs copied to scratchDir
 - [ ] discoveries.ndjson append-only throughout
 </success_criteria>

package/.codex/skills/maestro-brainstorm/SKILL.md

@@ -364,9 +364,15 @@ spawn_agents_on_csv({
 - Skill: maestro-roadmap --mode full -- Generate full spec package from brainstorm
 ```
 
-4. Copy artifacts to output `.brainstorming/` directory (phase mode or scratch mode target)
-5. Update phase `index.json` with brainstorm status (if phase mode)
-6. **Next-Step Routing** (skip if AUTO_YES — default to first applicable):
+4. **Brainstorm confidence scoring**:
+
+   Dimensions (5): role_coverage, cross_role_consistency, feature_completeness, spec_quality, design_feasibility. Factors (weights): analysis_depth(.30), evidence_strength(.25), coverage_breadth(.20), user_validation(.15, 0 if --yes), consistency(.10). Append confidence summary to `synthesis-changelog.md`.
+
+   **Conflict-based quality gate**: >3 `[UNRESOLVED]` conflicts → warn before artifact registration.
+
+5. Copy artifacts to output `.brainstorming/` directory (phase mode or scratch mode target)
+6. Update phase `index.json` with brainstorm status (if phase mode)
+7. **Next-Step Routing** (skip if AUTO_YES — default to first applicable):
    - Detect UI features: scan feature-index.json for UI/frontend-related features (keywords: ui, interface, page, component, dashboard, form, layout)
    - `request_user_input` (include UI Design option only when UI features detected):
      ```json
@@ -439,4 +445,7 @@ echo '{"ts":"<ISO>","worker":"{id}","type":"terminology","data":{"term":"CRDT","
 - [ ] context.md produced with full brainstorm report
 - [ ] Artifacts copied to target .brainstorming/ directory
 - [ ] discoveries.ndjson append-only throughout
+- [ ] Confidence scored per role and after cross-role synthesis
+- [ ] Conflict-based quality gate evaluated (> 3 unresolved = warning)
+- [ ] Confidence summary appended to synthesis-changelog.md
 </success_criteria>