From 6717e2a59b15b3b36a4b9606918a94d006858c39 Mon Sep 17 00:00:00 2001 From: catlog22 Date: Wed, 26 Nov 2025 10:00:18 +0800 Subject: [PATCH] refactor: Update review-fix command examples and output structure for clarity and consistency --- .claude/commands/workflow/review-fix.md | 20 +++++++--- .claude/commands/workflow/session/complete.md | 37 +++++++++++++++---- 2 files changed, 43 insertions(+), 14 deletions(-) diff --git a/.claude/commands/workflow/review-fix.md b/.claude/commands/workflow/review-fix.md index 77296bf1..09a9adec 100644 --- a/.claude/commands/workflow/review-fix.md +++ b/.claude/commands/workflow/review-fix.md @@ -10,21 +10,21 @@ allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(*), Task(*), Edit(*) ## Quick Start ```bash -# Fix from exported findings file -/workflow:review-fix .workflow/.reviews/session-WFS-123/fix-export-1706184622000.json +# Fix from exported findings file (session-based path) +/workflow:review-fix .workflow/active/WFS-123/.review/fix-export-1706184622000.json # Fix from review directory (auto-discovers latest export) -/workflow:review-fix .workflow/.reviews/session-WFS-123/ +/workflow:review-fix .workflow/active/WFS-123/.review/ # Resume interrupted fix session /workflow:review-fix --resume # Custom max retry attempts per finding -/workflow:review-fix .workflow/.reviews/session-WFS-123/ --max-iterations=5 +/workflow:review-fix .workflow/active/WFS-123/.review/ --max-iterations=5 ``` **Fix Source**: Exported findings from review cycle dashboard -**Output Directory**: `{review-dir}/fixes/{fix-session-id}/` (fixed location) +**Output Directory**: `{review-dir}/fixes/{fix-session-id}/` (within session .review/) **Default Max Iterations**: 3 (per finding, adjustable) **CLI Tools**: @cli-planning-agent (planning), @cli-execute-agent (fixing) @@ -224,12 +224,20 @@ if (result.passRate < 100%) { - TodoWrite completion: Mark all phases done - Output summary to user with dashboard link +**Phase 5: Session Completion (Optional)** +- If all findings fixed successfully (no failures): + - Prompt user: "All fixes complete. Complete workflow session? [Y/n]" + - If confirmed: Execute `/workflow:session:complete` to archive session with lessons learned +- If partial success (some failures): + - Output: "Some findings failed. Review fix-summary.md before completing session." + - Do NOT auto-complete session + ### Output File Structure ``` -.workflow/.reviews/{review-id}/ +.workflow/active/WFS-{session-id}/.review/ ├── fix-export-{timestamp}.json # Exported findings (input) └── fixes/{fix-session-id}/ ├── fix-plan.json # Planning agent output (execution plan) diff --git a/.claude/commands/workflow/session/complete.md b/.claude/commands/workflow/session/complete.md index 8b85ce87..40d803f1 100644 --- a/.claude/commands/workflow/session/complete.md +++ b/.claude/commands/workflow/session/complete.md @@ -87,20 +87,29 @@ Analyze workflow session for archival preparation. Session is STILL in active lo 2. **Count files**: tasks (.task/*.json) and summaries (.summaries/*.md) -3. **Generate lessons**: Use gemini with ~/.claude/workflows/cli-templates/prompts/archive/analysis-simple.txt - - Return: {successes, challenges, watch_patterns} +3. **Extract review data** (if .review/ exists): + - Count dimension results: .review/dimensions/*.json + - Count deep-dive results: .review/iterations/*.json + - Extract findings summary from dimension JSONs (total, critical, high, medium, low) + - Check fix results if .review/fixes/ exists (fixed_count, failed_count) + - Build review_metrics: {dimensions_analyzed, total_findings, severity_distribution, fix_success_rate} -4. **Build archive entry**: +4. **Generate lessons**: Use gemini with ~/.claude/workflows/cli-templates/prompts/archive/analysis-simple.txt + - Return: {successes, challenges, watch_patterns} + - If review data exists, include review-specific lessons (common issue patterns, effective fixes) + +5. **Build archive entry**: - Calculate: duration_hours, success_rate, tags (3-5 keywords) - Construct complete JSON with session_id, description, archived_at, metrics, tags, lessons - Include archive_path: ".workflow/archives/WFS-session-name" (future location) + - If review data exists, include review_metrics in metrics object -5. **Extract feature metadata** (for Phase 4): +6. **Extract feature metadata** (for Phase 4): - Parse IMPL_PLAN.md for title (first # heading) - Extract description (first paragraph, max 200 chars) - Generate feature tags (3-5 keywords from content) -6. **Return result**: Complete metadata package for atomic commit +7. **Return result**: Complete metadata package for atomic commit { "status": "success", "session_id": "WFS-session-name", @@ -109,7 +118,17 @@ Analyze workflow session for archival preparation. Session is STILL in active lo "description": "...", "archived_at": "...", "archive_path": ".workflow/archives/WFS-session-name", - "metrics": {...}, + "metrics": { + "duration_hours": 2.5, + "tasks_completed": 5, + "summaries_generated": 3, + "review_metrics": { // Optional, only if .review/ exists + "dimensions_analyzed": 4, + "total_findings": 15, + "severity_distribution": {"critical": 1, "high": 3, "medium": 8, "low": 3}, + "fix_success_rate": 0.87 // Optional, only if .review/fixes/ exists + } + }, "tags": [...], "lessons": {...} }, @@ -193,6 +212,7 @@ bash(rm .workflow/archives/WFS-session-name/.archiving) Location: .workflow/archives/WFS-session-name/ Lessons: ${archiveEntry.lessons.successes.length} successes, ${archiveEntry.lessons.challenges.length} challenges Manifest: Updated with ${manifest.length} total sessions + ${reviewMetrics ? `Review: ${reviewMetrics.total_findings} findings across ${reviewMetrics.dimensions_analyzed} dimensions, ${Math.round(reviewMetrics.fix_success_rate * 100)}% fixed` : ''} ``` ### Phase 4: Update Project Feature Registry @@ -435,9 +455,10 @@ Session state: PARTIALLY COMPLETE (session archived, manifest needs update) **Phase 2: Agent Analysis** (Read-only data processing) - Extract all session data from active location - Count tasks and summaries -- Generate lessons learned analysis +- Extract review data if .review/ exists (dimension results, findings, fix results) +- Generate lessons learned analysis (including review-specific lessons if applicable) - Extract feature metadata from IMPL_PLAN.md -- Build complete archive + feature metadata package +- Build complete archive + feature metadata package (with review_metrics if applicable) - **No file modifications** - pure analysis - **Total**: 1 agent invocation