From d535ab47495057785aa9449f028b3a62334fac4f Mon Sep 17 00:00:00 2001 From: catlog22 Date: Sat, 14 Feb 2026 21:35:55 +0800 Subject: [PATCH] feat: Implement workflow phases for test generation and execution - Added Phase 1: Session Start to detect input mode and create test workflow session. - Added Phase 2: Test Context Gather to gather test context via coverage analysis or codebase scan. - Added Phase 3: Test Concept Enhanced to analyze test requirements using Gemini and generate multi-layered test requirements. - Added Phase 4: Test Task Generate to create test-specific tasks based on analysis results. - Added Phase 5: Test Cycle Execute to manage iterative test execution and fix cycles with adaptive strategies. - Introduced BottomPanel component for terminal dashboard with Queue and Inspector tabs. --- .claude/commands/workflow/tdd-plan.md | 631 ------------------ .../commands/workflow/test-cycle-execute.md | 504 -------------- .claude/commands/workflow/test-fix-gen.md | 477 ------------- .claude/skills/workflow-tdd/SKILL.md | 459 +++++++++++++ .../phases/01-session-discovery.md | 57 ++ .../phases/02-context-gathering.md | 53 ++ .../phases/03-test-coverage-analysis.md | 78 +++ .../phases/04-conflict-resolution.md | 95 +++ .../phases/05-tdd-task-generation.md | 105 +++ .../phases/06-tdd-structure-validation.md | 179 +++++ .../workflow-tdd/phases/07-tdd-verify.md} | 334 +++------ .claude/skills/workflow-test-fix/SKILL.md | 241 ++++--- .../phases/01-session-start.md | 60 ++ .../phases/01-test-fix-gen.md | 309 --------- .../phases/02-test-context-gather.md | 66 ++ .../phases/03-test-concept-enhanced.md | 51 ++ .../phases/04-test-task-generate.md | 46 ++ ...le-execute.md => 05-test-cycle-execute.md} | 4 +- .../src/components/shared/Flowchart.tsx | 1 + .../src/components/shared/TaskDrawer.tsx | 32 +- .../terminal-dashboard/BottomInspector.tsx | 88 ++- .../terminal-dashboard/BottomPanel.tsx | 136 ++++ .../terminal-dashboard/QueuePanel.tsx | 75 ++- ccw/frontend/src/lib/api.ts | 28 +- .../src/pages/TerminalDashboardPage.tsx | 79 ++- ccw/src/core/lite-scanner-complete.ts | 87 ++- ccw/src/core/lite-scanner.ts | 92 ++- 27 files changed, 2004 insertions(+), 2363 deletions(-) delete mode 100644 .claude/commands/workflow/tdd-plan.md delete mode 100644 .claude/commands/workflow/test-cycle-execute.md delete mode 100644 .claude/commands/workflow/test-fix-gen.md create mode 100644 .claude/skills/workflow-tdd/SKILL.md create mode 100644 .claude/skills/workflow-tdd/phases/01-session-discovery.md create mode 100644 .claude/skills/workflow-tdd/phases/02-context-gathering.md create mode 100644 .claude/skills/workflow-tdd/phases/03-test-coverage-analysis.md create mode 100644 .claude/skills/workflow-tdd/phases/04-conflict-resolution.md create mode 100644 .claude/skills/workflow-tdd/phases/05-tdd-task-generation.md create mode 100644 .claude/skills/workflow-tdd/phases/06-tdd-structure-validation.md rename .claude/{commands/workflow/tdd-verify.md => skills/workflow-tdd/phases/07-tdd-verify.md} (60%) create mode 100644 .claude/skills/workflow-test-fix/phases/01-session-start.md delete mode 100644 .claude/skills/workflow-test-fix/phases/01-test-fix-gen.md create mode 100644 .claude/skills/workflow-test-fix/phases/02-test-context-gather.md create mode 100644 .claude/skills/workflow-test-fix/phases/03-test-concept-enhanced.md create mode 100644 .claude/skills/workflow-test-fix/phases/04-test-task-generate.md rename .claude/skills/workflow-test-fix/phases/{02-test-cycle-execute.md => 05-test-cycle-execute.md} (99%) create mode 100644 ccw/frontend/src/components/terminal-dashboard/BottomPanel.tsx diff --git a/.claude/commands/workflow/tdd-plan.md b/.claude/commands/workflow/tdd-plan.md deleted file mode 100644 index 2c5e0ac0..00000000 --- a/.claude/commands/workflow/tdd-plan.md +++ /dev/null @@ -1,631 +0,0 @@ ---- -name: tdd-plan -description: TDD workflow planning with Red-Green-Refactor task chain generation, test-first development structure, and cycle tracking -argument-hint: "\"feature description\"|file.md" -allowed-tools: Skill(*), TodoWrite(*), Read(*), Bash(*) ---- - -# TDD Workflow Plan Command (/workflow:tdd-plan) - -## Coordinator Role - -**This command is a pure orchestrator**: Executes 6 slash commands in sequence, parse outputs, pass context, and ensure complete TDD workflow creation with Red-Green-Refactor task generation. - -**CLI Tool Selection**: CLI tool usage is determined semantically from user's task description. Include "use Codex/Gemini/Qwen" in your request for CLI execution. - -**Task Attachment Model**: -- Skill execute **expands workflow** by attaching sub-tasks to current TodoWrite -- When executing a sub-command (e.g., `/workflow:tools:test-context-gather`), its internal tasks are attached to the orchestrator's TodoWrite -- Orchestrator **executes these attached tasks** sequentially -- After completion, attached tasks are **collapsed** back to high-level phase summary -- This is **task expansion**, not external delegation - -**Auto-Continue Mechanism**: -- TodoList tracks current phase status and dynamically manages task attachment/collapse -- When each phase finishes executing, automatically execute next pending phase -- All phases run autonomously without user interaction -- **⚠️ CONTINUOUS EXECUTION** - Do not stop until all phases complete - -## Core Rules - -1. **Start Immediately**: First action is TodoWrite initialization, second action is execute Phase 1 -2. **No Preliminary Analysis**: Do not read files before Phase 1 -3. **Parse Every Output**: Extract required data for next phase -4. **Auto-Continue via TodoList**: Check TodoList status to execute next pending phase automatically -5. **Track Progress**: Update TodoWrite dynamically with task attachment/collapse pattern -6. **TDD Context**: All descriptions include "TDD:" prefix -7. **Task Attachment Model**: Skill execute **attaches** sub-tasks to current workflow. Orchestrator **executes** these attached tasks itself, then **collapses** them after completion -8. **⚠️ CRITICAL: DO NOT STOP**: Continuous multi-phase workflow. After executing all attached tasks, immediately collapse them and execute next phase - -## TDD Compliance Requirements - -### The Iron Law - -``` -NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST -``` - -**Enforcement Method**: -- Phase 5: `implementation` includes test-first steps (Red → Green → Refactor) -- Green phase: Includes test-fix-cycle configuration (max 3 iterations) -- Auto-revert: Triggered when max iterations reached without passing tests - -**Verification**: Phase 6 validates Red-Green-Refactor structure in all generated tasks - -### TDD Compliance Checkpoint - -| Checkpoint | Validation Phase | Evidence Required | -|------------|------------------|-------------------| -| Test-first structure | Phase 5 | `implementation` has 3 steps | -| Red phase exists | Phase 6 | Step 1: `tdd_phase: "red"` | -| Green phase with test-fix | Phase 6 | Step 2: `tdd_phase: "green"` + test-fix-cycle | -| Refactor phase exists | Phase 6 | Step 3: `tdd_phase: "refactor"` | - -### Core TDD Principles (from ref skills) - -**Red Flags - STOP and Reassess**: -- Code written before test -- Test passes immediately (no Red phase witnessed) -- Cannot explain why test should fail -- "Just this once" rationalization -- "Tests after achieve same goals" thinking - -**Why Order Matters**: -- Tests written after code pass immediately → proves nothing -- Test-first forces edge case discovery before implementation -- Tests-after verify what was built, not what's required - -## 6-Phase Execution (with Conflict Resolution) - -### Phase 1: Session Discovery - -**Step 1.1: Execute** - Session discovery and initialization - -```javascript -Skill(skill="workflow:session:start", args="--type tdd --auto \"TDD: [structured-description]\"") -``` - -**TDD Structured Format**: -``` -TDD: [Feature Name] -GOAL: [Objective] -SCOPE: [Included/excluded] -CONTEXT: [Background] -TEST_FOCUS: [Test scenarios] -``` - -**Parse**: Extract sessionId - -**TodoWrite**: Mark phase 1 completed, phase 2 in_progress - -**After Phase 1**: Return to user showing Phase 1 results, then auto-continue to Phase 2 - ---- - -### Phase 2: Context Gathering - -**Step 2.1: Execute** - Context gathering and analysis - -```javascript -Skill(skill="workflow:tools:context-gather", args="--session [sessionId] \"TDD: [structured-description]\"") -``` - -**Use Same Structured Description**: Pass the same structured format from Phase 1 - -**Input**: `sessionId` from Phase 1 - -**Parse Output**: -- Extract: context-package.json path (store as `contextPath`) -- Typical pattern: `.workflow/active/[sessionId]/.process/context-package.json` - -**Validation**: -- Context package path extracted -- File exists and is valid JSON - -**TodoWrite**: Mark phase 2 completed, phase 3 in_progress - -**After Phase 2**: Return to user showing Phase 2 results, then auto-continue to Phase 3 - ---- - -### Phase 3: Test Coverage Analysis - -**Step 3.1: Execute** - Test coverage analysis and framework detection - -```javascript -Skill(skill="workflow:tools:test-context-gather", args="--session [sessionId]") -``` - -**Purpose**: Analyze existing codebase for: -- Existing test patterns and conventions -- Current test coverage -- Related components and integration points -- Test framework detection - -**Parse**: Extract testContextPath (`.workflow/active/[sessionId]/.process/test-context-package.json`) - - - - - -**TodoWrite Update (Phase 3 Skill executed - tasks attached)**: -```json -[ - {"content": "Phase 1: Session Discovery", "status": "completed", "activeForm": "Executing session discovery"}, - {"content": "Phase 2: Context Gathering", "status": "completed", "activeForm": "Executing context gathering"}, - {"content": "Phase 3: Test Coverage Analysis", "status": "in_progress", "activeForm": "Executing test coverage analysis"}, - {"content": " → Detect test framework and conventions", "status": "in_progress", "activeForm": "Detecting test framework"}, - {"content": " → Analyze existing test coverage", "status": "pending", "activeForm": "Analyzing test coverage"}, - {"content": " → Identify coverage gaps", "status": "pending", "activeForm": "Identifying coverage gaps"}, - {"content": "Phase 5: TDD Task Generation", "status": "pending", "activeForm": "Executing TDD task generation"}, - {"content": "Phase 6: TDD Structure Validation", "status": "pending", "activeForm": "Validating TDD structure"} -] -``` - -**Note**: Skill execute **attaches** test-context-gather's 3 tasks. Orchestrator **executes** these tasks. - -**Next Action**: Tasks attached → **Execute Phase 3.1-3.3** sequentially - - - -**TodoWrite Update (Phase 3 completed - tasks collapsed)**: -```json -[ - {"content": "Phase 1: Session Discovery", "status": "completed", "activeForm": "Executing session discovery"}, - {"content": "Phase 2: Context Gathering", "status": "completed", "activeForm": "Executing context gathering"}, - {"content": "Phase 3: Test Coverage Analysis", "status": "completed", "activeForm": "Executing test coverage analysis"}, - {"content": "Phase 5: TDD Task Generation", "status": "pending", "activeForm": "Executing TDD task generation"}, - {"content": "Phase 6: TDD Structure Validation", "status": "pending", "activeForm": "Validating TDD structure"} -] -``` - -**Note**: Phase 3 tasks completed and collapsed to summary. - -**After Phase 3**: Return to user showing test coverage results, then auto-continue to Phase 4/5 (depending on conflict_risk) - ---- - -### Phase 4: Conflict Resolution (Optional - auto-triggered by conflict risk) - -**Trigger**: Only execute when context-package.json indicates conflict_risk is "medium" or "high" - -**Step 4.1: Execute** - Conflict detection and resolution - -```javascript -Skill(skill="workflow:tools:conflict-resolution", args="--session [sessionId] --context [contextPath]") -``` - -**Input**: -- sessionId from Phase 1 -- contextPath from Phase 2 -- conflict_risk from context-package.json - -**Parse Output**: -- Extract: Execution status (success/skipped/failed) -- Verify: conflict-resolution.json file path (if executed) - -**Validation**: -- File `.workflow/active/[sessionId]/.process/conflict-resolution.json` exists (if executed) - -**Skip Behavior**: -- If conflict_risk is "none" or "low", skip directly to Phase 5 -- Display: "No significant conflicts detected, proceeding to TDD task generation" - - - -**TodoWrite Update (Phase 4 Skill executed - tasks attached, if conflict_risk ≥ medium)**: -```json -[ - {"content": "Phase 1: Session Discovery", "status": "completed", "activeForm": "Executing session discovery"}, - {"content": "Phase 2: Context Gathering", "status": "completed", "activeForm": "Executing context gathering"}, - {"content": "Phase 3: Test Coverage Analysis", "status": "completed", "activeForm": "Executing test coverage analysis"}, - {"content": "Phase 4: Conflict Resolution", "status": "in_progress", "activeForm": "Executing conflict resolution"}, - {"content": " → Detect conflicts with CLI analysis", "status": "in_progress", "activeForm": "Detecting conflicts"}, - {"content": " → Log and analyze detected conflicts", "status": "pending", "activeForm": "Analyzing conflicts"}, - {"content": " → Apply resolution strategies", "status": "pending", "activeForm": "Applying resolution strategies"}, - {"content": "Phase 5: TDD Task Generation", "status": "pending", "activeForm": "Executing TDD task generation"}, - {"content": "Phase 6: TDD Structure Validation", "status": "pending", "activeForm": "Validating TDD structure"} -] -``` - -**Note**: Skill execute **attaches** conflict-resolution's 3 tasks. Orchestrator **executes** these tasks. - -**Next Action**: Tasks attached → **Execute Phase 4.1-4.3** sequentially - - - -**TodoWrite Update (Phase 4 completed - tasks collapsed)**: -```json -[ - {"content": "Phase 1: Session Discovery", "status": "completed", "activeForm": "Executing session discovery"}, - {"content": "Phase 2: Context Gathering", "status": "completed", "activeForm": "Executing context gathering"}, - {"content": "Phase 3: Test Coverage Analysis", "status": "completed", "activeForm": "Executing test coverage analysis"}, - {"content": "Phase 4: Conflict Resolution", "status": "completed", "activeForm": "Executing conflict resolution"}, - {"content": "Phase 5: TDD Task Generation", "status": "pending", "activeForm": "Executing TDD task generation"}, - {"content": "Phase 6: TDD Structure Validation", "status": "pending", "activeForm": "Validating TDD structure"} -] -``` - -**Note**: Phase 4 tasks completed and collapsed to summary. - -**After Phase 4**: Return to user showing conflict resolution results (if executed) and selected strategies, then auto-continue to Phase 5 - -**Memory State Check**: -- Evaluate current context window usage and memory state -- If memory usage is high (>110K tokens or approaching context limits): - - **Step 4.5: Execute** - Memory compaction - - ```javascript - Skill(skill="compact") - ``` - - - This optimizes memory before proceeding to Phase 5 -- Memory compaction is particularly important after analysis phase which may generate extensive documentation -- Ensures optimal performance and prevents context overflow - ---- - -### Phase 5: TDD Task Generation - -**Step 5.1: Execute** - TDD task generation via action-planning-agent with Phase 0 user configuration - -```javascript -Skill(skill="workflow:tools:task-generate-tdd", args="--session [sessionId]") -``` - -**Note**: Phase 0 now includes: -- Supplementary materials collection (file paths or inline content) -- Execution method preference (Agent/Hybrid/CLI) -- CLI tool preference (Codex/Gemini/Qwen/Auto) -- These preferences are passed to agent for task generation - -**Parse**: Extract feature count, task count (not chain count - tasks now contain internal TDD cycles), CLI execution IDs assigned - -**Validate**: -- plan.json exists (structured plan overview with `_metadata.plan_type: "tdd"`) -- IMPL_PLAN.md exists (unified plan with TDD Implementation Tasks section) -- IMPL-*.json files exist (one per feature, or container + subtasks for complex features) -- TODO_LIST.md exists with internal TDD phase indicators -- Each IMPL task includes: - - `meta.tdd_workflow: true` - - `cli_execution.id: {session_id}-{task_id}` - - `cli_execution: { "strategy": "new|resume|fork|merge_fork", ... }` - - `implementation` with exactly 3 steps (red/green/refactor) - - Green phase includes test-fix-cycle configuration - - `focus_paths`: absolute or clear relative paths (enhanced with exploration critical_files) - - `pre_analysis`: includes exploration integration_points analysis -- IMPL_PLAN.md contains workflow_type: "tdd" in frontmatter -- User configuration applied: - - If executionMethod == "cli" or "hybrid": command field added to steps - - CLI tool preference reflected in execution guidance -- Task count ≤18 (compliance with hard limit) - -**Red Flag Detection** (Non-Blocking Warnings): -- Task count >18: `⚠️ Task count exceeds hard limit - request re-scope` -- Missing cli_execution.id: `⚠️ Task lacks CLI execution ID for resume support` -- Missing test-fix-cycle: `⚠️ Green phase lacks auto-revert configuration` -- Generic task names: `⚠️ Vague task names suggest unclear TDD cycles` -- Missing focus_paths: `⚠️ Task lacks clear file scope for implementation` - -**Action**: Log warnings to `.workflow/active/[sessionId]/.process/tdd-warnings.log` (non-blocking) - - - -**TodoWrite Update (Phase 5 Skill executed - tasks attached)**: -```json -[ - {"content": "Phase 1: Session Discovery", "status": "completed", "activeForm": "Executing session discovery"}, - {"content": "Phase 2: Context Gathering", "status": "completed", "activeForm": "Executing context gathering"}, - {"content": "Phase 3: Test Coverage Analysis", "status": "completed", "activeForm": "Executing test coverage analysis"}, - {"content": "Phase 5: TDD Task Generation", "status": "in_progress", "activeForm": "Executing TDD task generation"}, - {"content": " → Discovery - analyze TDD requirements", "status": "in_progress", "activeForm": "Analyzing TDD requirements"}, - {"content": " → Planning - design Red-Green-Refactor cycles", "status": "pending", "activeForm": "Designing TDD cycles"}, - {"content": " → Output - generate IMPL tasks with internal TDD phases", "status": "pending", "activeForm": "Generating TDD tasks"}, - {"content": "Phase 6: TDD Structure Validation", "status": "pending", "activeForm": "Validating TDD structure"} -] -``` - -**Note**: Skill execute **attaches** task-generate-tdd's 3 tasks. Orchestrator **executes** these tasks. Each generated IMPL task will contain internal Red-Green-Refactor cycle. - -**Next Action**: Tasks attached → **Execute Phase 5.1-5.3** sequentially - - - -**TodoWrite Update (Phase 5 completed - tasks collapsed)**: -```json -[ - {"content": "Phase 1: Session Discovery", "status": "completed", "activeForm": "Executing session discovery"}, - {"content": "Phase 2: Context Gathering", "status": "completed", "activeForm": "Executing context gathering"}, - {"content": "Phase 3: Test Coverage Analysis", "status": "completed", "activeForm": "Executing test coverage analysis"}, - {"content": "Phase 5: TDD Task Generation", "status": "completed", "activeForm": "Executing TDD task generation"}, - {"content": "Phase 6: TDD Structure Validation", "status": "in_progress", "activeForm": "Validating TDD structure"} -] -``` - -**Note**: Phase 5 tasks completed and collapsed to summary. Each generated IMPL task contains complete Red-Green-Refactor cycle internally. - -### Phase 6: TDD Structure Validation & Action Plan Verification (RECOMMENDED) -**Internal validation first, then recommend external verification** - -**Internal Validation**: -1. Each task contains complete TDD workflow (Red-Green-Refactor internally) -2. Task structure validation: - - `meta.tdd_workflow: true` in all IMPL tasks - - `cli_execution.id` present (format: {session_id}-{task_id}) - - `cli_execution` strategy assigned (new/resume/fork/merge_fork) - - `implementation` has exactly 3 steps - - Each step has correct `tdd_phase`: "red", "green", "refactor" - - `focus_paths` are absolute or clear relative paths - - `pre_analysis` includes exploration integration analysis -3. Dependency validation: - - Sequential features: IMPL-N depends_on ["IMPL-(N-1)"] if needed - - Complex features: IMPL-N.M depends_on ["IMPL-N.(M-1)"] for subtasks - - CLI execution strategies correctly assigned based on dependency graph -4. Agent assignment: All IMPL tasks use @code-developer -5. Test-fix cycle: Green phase step includes test-fix-cycle logic with max_iterations -6. Task count: Total tasks ≤18 (simple + subtasks hard limit) -7. User configuration: - - Execution method choice reflected in task structure - - CLI tool preference documented in implementation guidance (if CLI selected) - -**Red Flag Checklist** (from TDD best practices): -- [ ] No tasks skip Red phase (`tdd_phase: "red"` exists in step 1) -- [ ] Test files referenced in Red phase (explicit paths, not placeholders) -- [ ] Green phase has test-fix-cycle with `max_iterations` configured -- [ ] Refactor phase has clear completion criteria - -**Non-Compliance Warning Format**: -``` -⚠️ TDD Red Flag: [issue description] - Task: [IMPL-N] - Recommendation: [action to fix] -``` - -**Evidence Gathering** (Before Completion Claims): - -```bash -# Verify session artifacts exist -ls -la .workflow/active/[sessionId]/{IMPL_PLAN.md,TODO_LIST.md} -ls -la .workflow/active/[sessionId]/.task/IMPL-*.json - -# Count generated artifacts -echo "IMPL tasks: $(ls .workflow/active/[sessionId]/.task/IMPL-*.json 2>/dev/null | wc -l)" - -# Sample task structure verification (first task) -jq '{id, tdd: .meta.tdd_workflow, cli_id: .cli_execution.id, phases: [.implementation[].tdd_phase]}' \ - "$(ls .workflow/active/[sessionId]/.task/IMPL-*.json | head -1)" -``` - -**Evidence Required Before Summary**: -| Evidence Type | Verification Method | Pass Criteria | -|---------------|---------------------|---------------| -| File existence | `ls -la` artifacts | All files present | -| Task count | Count IMPL-*.json | Count matches claims (≤18) | -| TDD structure | jq sample extraction | Shows red/green/refactor + cli_execution.id | -| CLI execution IDs | jq extraction | All tasks have cli_execution.id assigned | -| Warning log | Check tdd-warnings.log | Logged (may be empty) | - -**Return Summary**: -``` -TDD Planning complete for session: [sessionId] - -Features analyzed: [N] -Total tasks: [M] (1 task per simple feature + subtasks for complex features) - -Task breakdown: -- Simple features: [K] tasks (IMPL-1 to IMPL-K) -- Complex features: [L] features with [P] subtasks -- Total task count: [M] (within 18-task hard limit) - -Structure: -- IMPL-1: {Feature 1 Name} (Internal: Red → Green → Refactor) -- IMPL-2: {Feature 2 Name} (Internal: Red → Green → Refactor) -- IMPL-3: {Complex Feature} (Container) - - IMPL-3.1: {Sub-feature A} (Internal: Red → Green → Refactor) - - IMPL-3.2: {Sub-feature B} (Internal: Red → Green → Refactor) -[...] - -Plans generated: -- Unified Implementation Plan: .workflow/active/[sessionId]/IMPL_PLAN.md - (includes TDD Implementation Tasks section with workflow_type: "tdd") -- Task List: .workflow/active/[sessionId]/TODO_LIST.md - (with internal TDD phase indicators and CLI execution strategies) -- Task JSONs: .workflow/active/[sessionId]/.task/IMPL-*.json - (with cli_execution.id and execution strategies for resume support) - -TDD Configuration: -- Each task contains complete Red-Green-Refactor cycle -- Green phase includes test-fix cycle (max 3 iterations) -- Auto-revert on max iterations reached -- CLI execution strategies: new/resume/fork/merge_fork based on dependency graph - -User Configuration Applied: -- Execution Method: [agent|hybrid|cli] -- CLI Tool Preference: [codex|gemini|qwen|auto] -- Supplementary Materials: [included|none] -- Task generation follows cli-tools-usage.md guidelines - -⚠️ ACTION REQUIRED: Before execution, ensure you understand WHY each Red phase test is expected to fail. - This is crucial for valid TDD - if you don't know why the test fails, you can't verify it tests the right thing. - -Recommended Next Steps: -1. /workflow:plan-verify --session [sessionId] # Verify TDD plan quality and dependencies -2. /workflow:execute --session [sessionId] # Start TDD execution with CLI strategies -3. /workflow:tdd-verify [sessionId] # Post-execution TDD compliance check - -Quality Gate: Consider running /workflow:plan-verify to validate TDD task structure, dependencies, and CLI execution strategies -``` - -## TodoWrite Pattern - -**Core Concept**: Dynamic task attachment and collapse for TDD workflow with test coverage analysis and Red-Green-Refactor cycle generation. - -### Key Principles - -1. **Task Attachment** (when Skill executed): - - Sub-command's internal tasks are **attached** to orchestrator's TodoWrite - - Example: `/workflow:tools:test-context-gather` attaches 3 sub-tasks (Phase 3.1, 3.2, 3.3) - - First attached task marked as `in_progress`, others as `pending` - - Orchestrator **executes** these attached tasks sequentially - -2. **Task Collapse** (after sub-tasks complete): - - Remove detailed sub-tasks from TodoWrite - - **Collapse** to high-level phase summary - - Example: Phase 3.1-3.3 collapse to "Execute test coverage analysis: completed" - - Maintains clean orchestrator-level view - -3. **Continuous Execution**: - - After collapse, automatically proceed to next pending phase - - No user intervention required between phases - - TodoWrite dynamically reflects current execution state - -**Lifecycle Summary**: Initial pending tasks → Phase executed (tasks ATTACHED) → Sub-tasks executed sequentially → Phase completed (tasks COLLAPSED to summary) → Next phase begins (conditional Phase 4 if conflict_risk ≥ medium) → Repeat until all phases complete. - -### TDD-Specific Features - -- **Phase 3**: Test coverage analysis detects existing patterns and gaps -- **Phase 5**: Generated IMPL tasks contain internal Red-Green-Refactor cycles -- **Conditional Phase 4**: Conflict resolution only if conflict_risk ≥ medium - - - -**Note**: See individual Phase descriptions (Phase 3, 4, 5) for detailed TodoWrite Update examples with full JSON structures. - -## Execution Flow Diagram - -``` -TDD Workflow Orchestrator -│ -├─ Phase 1: Session Discovery -│ └─ /workflow:session:start --auto -│ └─ Returns: sessionId -│ -├─ Phase 2: Context Gathering -│ └─ /workflow:tools:context-gather -│ └─ Returns: context-package.json path -│ -├─ Phase 3: Test Coverage Analysis ← ATTACHED (3 tasks) -│ └─ /workflow:tools:test-context-gather -│ ├─ Phase 3.1: Detect test framework -│ ├─ Phase 3.2: Analyze existing test coverage -│ └─ Phase 3.3: Identify coverage gaps -│ └─ Returns: test-context-package.json ← COLLAPSED -│ -├─ Phase 4: Conflict Resolution (conditional) -│ IF conflict_risk ≥ medium: -│ └─ /workflow:tools:conflict-resolution ← ATTACHED (3 tasks) -│ ├─ Phase 4.1: Detect conflicts with CLI -│ ├─ Phase 4.2: Log and analyze detected conflicts -│ └─ Phase 4.3: Apply resolution strategies -│ └─ Returns: conflict-resolution.json ← COLLAPSED -│ ELSE: -│ └─ Skip to Phase 5 -│ -├─ Phase 5: TDD Task Generation ← ATTACHED (3 tasks) -│ └─ /workflow:tools:task-generate-tdd -│ ├─ Phase 5.1: Discovery - analyze TDD requirements -│ ├─ Phase 5.2: Planning - design Red-Green-Refactor cycles -│ └─ Phase 5.3: Output - generate IMPL tasks with internal TDD phases -│ └─ Returns: IMPL-*.json, IMPL_PLAN.md ← COLLAPSED -│ (Each IMPL task contains internal Red-Green-Refactor cycle) -│ -└─ Phase 6: TDD Structure Validation - └─ Internal validation + summary returned - └─ Recommend: /workflow:plan-verify - -Key Points: -• ← ATTACHED: Skill attaches sub-tasks to orchestrator TodoWrite -• ← COLLAPSED: Sub-tasks executed and collapsed to phase summary -• TDD-specific: Each generated IMPL task contains complete Red-Green-Refactor cycle -``` - -## Input Processing - -Convert user input to TDD-structured format: - -**Simple text** → Add TDD context -**Detailed text** → Extract components with TEST_FOCUS -**File/Issue** → Read and structure with TDD - -## Error Handling - -- **Parsing failure**: Retry once, then report -- **Validation failure**: Report missing/invalid data -- **Command failure**: Keep phase in_progress, report error -- **TDD validation failure**: Report incomplete chains or wrong dependencies - -### TDD Warning Patterns - -| Pattern | Warning Message | Recommended Action | -|---------|----------------|-------------------| -| Task count >10 | High task count detected | Consider splitting into multiple sessions | -| Missing test-fix-cycle | Green phase lacks auto-revert | Add `max_iterations: 3` to task config | -| Red phase missing test path | Test file path not specified | Add explicit test file paths | -| Generic task names | Vague names like "Add feature" | Use specific behavior descriptions | -| No refactor criteria | Refactor phase lacks completion criteria | Define clear refactor scope | - -### Non-Blocking Warning Policy - -**All warnings are advisory** - they do not halt execution: -1. Warnings logged to `.process/tdd-warnings.log` -2. Summary displayed in Phase 6 output -3. User decides whether to address before `/workflow:execute` - -### Error Handling Quick Reference - -| Error Type | Detection | Recovery Action | -|------------|-----------|-----------------| -| Parsing failure | Empty/malformed output | Retry once, then report | -| Missing context-package | File read error | Re-run `/workflow:tools:context-gather` | -| Invalid task JSON | jq parse error | Report malformed file path | -| Task count exceeds 18 | Count validation ≥19 | Request re-scope, split into multiple sessions | -| Missing cli_execution.id | All tasks lack ID | Regenerate tasks with phase 0 user config | -| Test-context missing | File not found | Re-run `/workflow:tools:test-context-gather` | -| Phase timeout | No response | Retry phase, check CLI connectivity | -| CLI tool not available | Tool not in cli-tools.json | Fall back to alternative preferred tool | - -## Related Commands - -**Prerequisite Commands**: -- None - TDD planning is self-contained (can optionally run brainstorm commands before) - -**Called by This Command** (6 phases): -- `/workflow:session:start` - Phase 1: Create or discover TDD workflow session -- `/workflow:tools:context-gather` - Phase 2: Gather project context and analyze codebase -- `/workflow:tools:test-context-gather` - Phase 3: Analyze existing test patterns and coverage -- `/workflow:tools:conflict-resolution` - Phase 4: Detect and resolve conflicts (auto-triggered if conflict_risk ≥ medium) -- `/compact` - Phase 4: Memory optimization (if context approaching limits) -- `/workflow:tools:task-generate-tdd` - Phase 5: Generate TDD tasks (CLI tool usage determined semantically) - -**Follow-up Commands**: -- `/workflow:plan-verify` - Recommended: Verify TDD plan quality and structure before execution -- `/workflow:status` - Review TDD task breakdown -- `/workflow:execute` - Begin TDD implementation -- `/workflow:tdd-verify` - Post-execution: Verify TDD compliance and generate quality report - -## Next Steps Decision Table - -| Situation | Recommended Command | Purpose | -|-----------|---------------------|---------| -| First time planning | `/workflow:plan-verify` | Validate task structure before execution | -| Warnings in tdd-warnings.log | Review log, refine tasks | Address Red Flags before proceeding | -| High task count warning | Consider `/workflow:session:start` | Split into focused sub-sessions | -| Ready to implement | `/workflow:execute` | Begin TDD Red-Green-Refactor cycles | -| After implementation | `/workflow:tdd-verify` | Generate TDD compliance report | -| Need to review tasks | `/workflow:status --session [id]` | Inspect current task breakdown | -| Plan needs changes | `/task:replan` | Update task JSON with new requirements | - -### TDD Workflow State Transitions - -``` -/workflow:tdd-plan - ↓ -[Planning Complete] ──→ /workflow:plan-verify (recommended) - ↓ -[Verified/Ready] ─────→ /workflow:execute - ↓ -[Implementation] ─────→ /workflow:tdd-verify (post-execution) - ↓ -[Quality Report] ─────→ Done or iterate -``` diff --git a/.claude/commands/workflow/test-cycle-execute.md b/.claude/commands/workflow/test-cycle-execute.md deleted file mode 100644 index 22ce48b0..00000000 --- a/.claude/commands/workflow/test-cycle-execute.md +++ /dev/null @@ -1,504 +0,0 @@ ---- -name: test-cycle-execute -description: Execute test-fix workflow with dynamic task generation and iterative fix cycles until test pass rate >= 95% or max iterations reached. Uses @cli-planning-agent for failure analysis and task generation. -argument-hint: "[--resume-session=\"session-id\"] [--max-iterations=N]" -allowed-tools: Skill(*), TodoWrite(*), Read(*), Bash(*), Task(*) ---- - -# Workflow Test-Cycle-Execute Command - -## Quick Start - -```bash -# Execute test-fix workflow (auto-discovers active session) -/workflow:test-cycle-execute - -# Resume interrupted session -/workflow:test-cycle-execute --resume-session="WFS-test-user-auth" - -# Custom iteration limit (default: 10) -/workflow:test-cycle-execute --max-iterations=15 -``` - -**Quality Gate**: Test pass rate >= 95% (criticality-aware) or 100% -**Max Iterations**: 10 (default, adjustable) -**CLI Tools**: Gemini → Qwen → Codex (fallback chain) - -## What & Why - -### Core Concept -Dynamic test-fix orchestrator with **adaptive task generation** based on runtime analysis. - -**vs Standard Execute**: -- **Standard**: Pre-defined tasks → Execute sequentially → Done -- **Test-Cycle**: Initial tasks → **Test → Analyze failures → Generate fix tasks → Fix → Re-test** → Repeat until pass - -### Value Proposition -1. **Automatic Problem Solving**: No manual intervention needed until 95% pass rate -2. **Intelligent Adaptation**: Strategy adjusts based on progress (conservative → aggressive → surgical) -3. **Fast Feedback**: Progressive testing runs only affected tests (70-90% faster) - -### Orchestrator Boundary (CRITICAL) -- **ONLY command** handling test failures - always delegate here -- Manages: iteration loop, strategy selection, pass rate validation -- Delegates: CLI analysis to @cli-planning-agent, execution to @test-fix-agent - -## How It Works - -### Execution Flow - -``` -1. Discovery - └─ Load session, tasks, iteration state - -2. Main Loop (for each task): - ├─ Execute → Test → Calculate pass_rate - ├─ Decision: - │ ├─ 100% → SUCCESS: Next task - │ ├─ 95-99% + low criticality → PARTIAL SUCCESS: Approve with note - │ └─ <95% or critical failures → Fix Loop ↓ - └─ Fix Loop: - ├─ Detect: stuck tests, regression, progress trend - ├─ Select strategy: conservative/aggressive/surgical - ├─ Generate fix task via @cli-planning-agent (IMPL-fix-N.json) - ├─ Execute fix via @test-fix-agent - └─ Re-test → Back to step 2 - -3. Completion - └─ Final validation → Generate summary → Auto-complete session -``` - -### Agent Roles - -| Agent | Responsibility | -|-------|---------------| -| **Orchestrator** | Loop control, strategy selection, pass rate calculation, threshold decisions | -| **@cli-planning-agent** | CLI analysis (Gemini/Qwen/Codex), root cause extraction, task generation, affected test detection | -| **@test-fix-agent** | Test execution, code fixes, criticality assignment, result reporting | - -## Enhanced Features - -### 1. Intelligent Strategy Engine - -**Auto-selects optimal strategy based on iteration context:** - -| Strategy | Trigger | Behavior | -|----------|---------|----------| -| **Conservative** | Iteration 1-2 (default) | Single targeted fix, full validation | -| **Aggressive** | Pass rate >80% + similar failures | Batch fix related issues | -| **Surgical** | Regression detected (pass rate drops >10%) | Minimal changes, rollback focus | - -**Selection Logic** (in orchestrator): -```javascript -if (iteration <= 2) return "conservative"; -if (passRate > 80 && failurePattern.similarity > 0.7) return "aggressive"; -if (regressionDetected) return "surgical"; -return "conservative"; -``` - -**Integration**: Strategy passed to @cli-planning-agent in prompt for tailored analysis. - -### 2. Progressive Testing - -**Runs affected tests during iterations, full suite only for final validation.** - -**How It Works**: -1. @cli-planning-agent analyzes fix_strategy.modification_points -2. Maps modified files to test files (via imports + integration patterns) -3. Returns `affected_tests[]` in task JSON -4. @test-fix-agent runs: `npm test -- ${affected_tests.join(' ')}` -5. Final validation: `npm test` (full suite) - - -**Benefits**: 70-90% iteration speed improvement, instant feedback on fix effectiveness. - -## Core Responsibilities - -### Orchestrator -- Session discovery, task queue management -- Pass rate calculation: `(passed / total) * 100` from test-results.json -- Criticality assessment (high/medium/low) -- Strategy selection based on context -- **Runtime Calculations** (from iteration-state.json): - - Current iteration: `iterations.length + 1` - - Stuck tests: Tests appearing in `failed_tests` for 3+ consecutive iterations - - Regression: Compare consecutive `pass_rate` values (>10% drop) - - Max iterations: Read from `task.meta.max_iterations` -- Iteration control (max 10, default) -- CLI tool fallback chain: Gemini → Qwen → Codex -- TodoWrite progress tracking -- Session auto-complete (pass rate >= 95%) - -### @cli-planning-agent -- Execute CLI analysis with bug diagnosis template -- Parse output for root causes and fix strategy -- Generate IMPL-fix-N.json task definition -- Detect affected tests for progressive testing -- Save: analysis.md, cli-output.txt - -### @test-fix-agent -- Execute tests, save results to test-results.json -- Apply fixes from task.context.fix_strategy -- Assign criticality to failures -- Update task status - -## Reference - -### CLI Tool Configuration - -**Fallback Chain**: Gemini → Qwen → Codex -**Template**: `~/.ccw/workflows/cli-templates/prompts/analysis/01-diagnose-bug-root-cause.txt` -**Timeout**: 40min (2400000ms) - -**Tool Details**: -1. **Gemini** (primary): `gemini-2.5-pro` -2. **Qwen** (fallback): `coder-model` -3. **Codex** (fallback): `gpt-5.1-codex` - -**When to Fallback**: HTTP 429, timeout, analysis quality degraded - -### Session File Structure - -``` -.workflow/active/WFS-test-{session}/ -├── workflow-session.json # Session metadata -├── IMPL_PLAN.md, TODO_LIST.md -├── .task/ -│ ├── IMPL-{001,002}.json # Initial tasks -│ └── IMPL-fix-{N}.json # Generated fix tasks -├── .process/ -│ ├── iteration-state.json # Current iteration + strategy + stuck tests -│ ├── test-results.json # Latest results (pass_rate, criticality) -│ ├── test-output.log # Full test output -│ ├── fix-history.json # All fix attempts -│ ├── iteration-{N}-analysis.md # CLI analysis report -│ └── iteration-{N}-cli-output.txt -└── .summaries/iteration-summaries/ -``` - -### Iteration State JSON - -**Purpose**: Persisted state machine for iteration loop - enables Resume and historical analysis. - -```json -{ - "current_task": "IMPL-002", - "selected_strategy": "aggressive", - "next_action": "execute_fix_task", - "iterations": [ - { - "iteration": 1, - "pass_rate": 70, - "strategy": "conservative", - "failed_tests": ["test_auth_flow", "test_user_permissions"] - }, - { - "iteration": 2, - "pass_rate": 82, - "strategy": "conservative", - "failed_tests": ["test_user_permissions", "test_token_expiry"] - }, - { - "iteration": 3, - "pass_rate": 89, - "strategy": "aggressive", - "failed_tests": ["test_auth_edge_case"] - } - ] -} -``` - -**Field Descriptions**: -- `current_task`: Pointer to active task (essential for Resume) -- `selected_strategy`: Current iteration strategy (runtime state) -- `next_action`: State machine next step (`execute_fix_task` | `retest` | `complete`) -- `iterations[]`: Historical log of all iterations (source of truth for trends) - - -### Agent Invocation Template - -**@cli-planning-agent** (failure analysis): -```javascript -Task( - subagent_type="cli-planning-agent", - run_in_background=false, - description=`Analyze test failures (iteration ${N}) - ${strategy} strategy`, - prompt=` - ## Task Objective - Analyze test failures and generate fix task JSON for iteration ${N} - - ## Strategy - ${selectedStrategy} - ${strategyDescription} - - ## MANDATORY FIRST STEPS - 1. Read test results: ${session.test_results_path} - 2. Read test output: ${session.test_output_path} - 3. Read iteration state: ${session.iteration_state_path} - - ## Context Metadata (Orchestrator-Calculated) - - Session ID: ${sessionId} (from file path) - - Current Iteration: ${N} (= iterations.length + 1) - - Max Iterations: ${maxIterations} (from task.meta.max_iterations) - - Current Pass Rate: ${passRate}% - - Selected Strategy: ${selectedStrategy} (from iteration-state.json) - - Stuck Tests: ${stuckTests} (calculated from iterations[].failed_tests history) - - ## CLI Configuration - - Tool Priority: gemini & codex - - Template: 01-diagnose-bug-root-cause.txt - - Timeout: 2400000ms - - ## Expected Deliverables - 1. Task JSON: ${session.task_dir}/IMPL-fix-${N}.json - - Must include: fix_strategy.test_execution.affected_tests[] - - Must include: fix_strategy.confidence_score - 2. Analysis report: ${session.process_dir}/iteration-${N}-analysis.md - 3. CLI output: ${session.process_dir}/iteration-${N}-cli-output.txt - - ## Strategy-Specific Requirements - - Conservative: Single targeted fix, high confidence required - - Aggressive: Batch fix similar failures, pattern-based approach - - Surgical: Minimal changes, focus on rollback safety - - ## Success Criteria - - Concrete fix strategy with modification points (file:function:lines) - - Affected tests list for progressive testing - - Root cause analysis (not just symptoms) - ` -) -``` - -**@test-fix-agent** (execution): -```javascript -Task( - subagent_type="test-fix-agent", - run_in_background=false, - description=`Execute ${task.meta.type}: ${task.title}`, - prompt=` - ## Task Objective - ${taskTypeObjective[task.meta.type]} - - ## MANDATORY FIRST STEPS - 1. Read task JSON: ${session.task_json_path} - 2. Read iteration state: ${session.iteration_state_path} - 3. ${taskTypeSpecificReads[task.meta.type]} - - ## CRITICAL: Syntax Check Priority - **Before any code modification or test execution:** - - Run project syntax checker (TypeScript: tsc --noEmit, ESLint, etc.) - - Verify zero syntax errors before proceeding - - If syntax errors found: Fix immediately before other work - - Syntax validation is MANDATORY gate - no exceptions - - ## Session Paths - - Workflow Dir: ${session.workflow_dir} - - Task JSON: ${session.task_json_path} - - Test Results Output: ${session.test_results_path} - - Test Output Log: ${session.test_output_path} - - Iteration State: ${session.iteration_state_path} - - ## Task Type: ${task.meta.type} - ${taskTypeGuidance[task.meta.type]} - - ## Expected Deliverables - ${taskTypeDeliverables[task.meta.type]} - - ## Success Criteria - - ${taskTypeSuccessCriteria[task.meta.type]} - - Update task status in task JSON - - Save all outputs to specified paths - - Report completion to orchestrator - ` -) - -// Task Type Configurations -const taskTypeObjective = { - "test-gen": "Generate comprehensive tests based on requirements", - "test-fix": "Execute test suite and report results with criticality assessment", - "test-fix-iteration": "Apply fixes from strategy and validate with tests" -}; - -const taskTypeSpecificReads = { - "test-gen": "Read test context: ${session.test_context_path}", - "test-fix": "Read previous results (if exists): ${session.test_results_path}", - "test-fix-iteration": "Read fix strategy: ${session.analysis_path}, fix history: ${session.fix_history_path}" -}; - -const taskTypeGuidance = { - "test-gen": ` - - Review task.context.requirements for test scenarios - - Analyze codebase to understand implementation - - Generate tests covering: happy paths, edge cases, error handling - - Follow existing test patterns and framework conventions - `, - "test-fix": ` - - Run test command from task.context or project config - - Capture: pass/fail counts, error messages, stack traces - - Assess criticality for each failure: - * high: core functionality broken, security issues - * medium: feature degradation, data integrity issues - * low: edge cases, flaky tests, env-specific issues - - Save structured results to test-results.json - `, - "test-fix-iteration": ` - - Load fix_strategy from task.context.fix_strategy - - Identify modification_points: ${task.context.fix_strategy.modification_points} - - Apply surgical fixes (minimal changes) - - Test execution mode: ${task.context.fix_strategy.test_execution.mode} - * affected_only: Run ${task.context.fix_strategy.test_execution.affected_tests} - * full_suite: Run complete test suite - - If failures persist: Document in test-results.json, DO NOT analyze (orchestrator handles) - ` -}; - -const taskTypeDeliverables = { - "test-gen": "- Test files in target directories\n - Test coverage report\n - Summary in .summaries/", - "test-fix": "- test-results.json (pass_rate, criticality, failures)\n - test-output.log (full test output)\n - Summary in .summaries/", - "test-fix-iteration": "- Modified source files\n - test-results.json (updated pass_rate)\n - test-output.log\n - Summary in .summaries/" -}; - -const taskTypeSuccessCriteria = { - "test-gen": "All test files created, executable without errors, coverage documented", - "test-fix": "Test results saved with accurate pass_rate and criticality, all failures documented", - "test-fix-iteration": "Fixes applied per strategy, tests executed, results reported (pass/fail to orchestrator)" -}; -``` - -### Completion Conditions - -**Full Success**: -- All tasks completed -- Pass rate === 100% -- Action: Auto-complete session - -**Partial Success**: -- All tasks completed -- Pass rate >= 95% and < 100% -- All failures are "low" criticality -- Action: Auto-approve with review note - -**Failure**: -- Max iterations (10) reached without 95% pass rate -- Pass rate < 95% after max iterations -- Action: Generate failure report, mark blocked, return to user - -### Error Handling - -| Scenario | Action | -|----------|--------| -| Test execution error | Log, retry with error context | -| CLI analysis failure | Fallback: Gemini → Qwen → Codex → manual | -| Agent execution error | Save state, retry with simplified context | -| Max iterations reached | Generate failure report, mark blocked | -| Regression detected | Rollback last fix, switch to surgical strategy | -| Stuck tests detected | Continue with alternative strategy, document in failure report | - -**CLI Fallback Triggers** (Gemini → Qwen → Codex → manual): - -Fallback is triggered when any of these conditions occur: - -1. **Invalid Output**: - - CLI tool fails to generate valid `IMPL-fix-N.json` (JSON parse error) - - Missing required fields: `fix_strategy.modification_points` or `fix_strategy.affected_tests` - -2. **Low Confidence**: - - `fix_strategy.confidence_score < 0.4` (indicates uncertain analysis) - -3. **Technical Failures**: - - HTTP 429 (rate limit) or 5xx errors - - Timeout (exceeds 2400000ms / 40min) - - Connection errors - -4. **Quality Degradation**: - - Analysis report < 100 words (too brief, likely incomplete) - - No concrete modification points provided (only general suggestions) - - Same root cause identified 3+ consecutive times (stuck analysis) - -**Fallback Sequence**: -- Try primary tool (Gemini) -- If trigger detected → Try fallback (Qwen) -- If trigger detected again → Try final fallback (Codex) -- If all fail → Mark as degraded, use basic pattern matching from fix-history.json, notify user - -### TodoWrite Structure - -```javascript -TodoWrite({ - todos: [ - { - content: "Execute IMPL-001: Generate tests [code-developer]", - status: "completed", - activeForm: "Executing test generation" - }, - { - content: "Execute IMPL-002: Test & Fix Cycle [ITERATION]", - status: "in_progress", - activeForm: "Running test-fix iteration cycle" - }, - { - content: " → Iteration 1: Initial test (pass: 70%, conservative)", - status: "completed", - activeForm: "Running initial tests" - }, - { - content: " → Iteration 2: Fix validation (pass: 82%, conservative)", - status: "completed", - activeForm: "Fixing validation issues" - }, - { - content: " → Iteration 3: Batch fix auth (pass: 89%, aggressive)", - status: "in_progress", - activeForm: "Fixing authentication issues" - } - ] -}); -``` - -**Update Rules**: -- Add iteration item with: strategy, pass rate -- Mark completed after each iteration -- Update parent task when all complete - -## Commit Strategy - -**Automatic Commits** (orchestrator-managed): - -The orchestrator automatically creates git commits at key checkpoints to enable safe rollback: - -1. **After Successful Iteration** (pass rate increased): - ```bash - git add . - git commit -m "test-cycle: iteration ${N} - ${strategy} strategy (pass: ${oldRate}% → ${newRate}%)" - ``` - -2. **Before Rollback** (regression detected): - ```bash - # Current state preserved, then: - git revert HEAD - git commit -m "test-cycle: rollback iteration ${N} - regression detected (pass: ${newRate}% < ${oldRate}%)" - ``` - -**Commit Content**: -- Modified source files from fix application -- Updated test-results.json, iteration-state.json -- Excludes: temporary files, logs - -**Benefits**: -- **Rollback Safety**: Each iteration is a revert point -- **Progress Tracking**: Git history shows iteration evolution -- **Audit Trail**: Clear record of which strategy/iteration caused issues -- **Resume Capability**: Can resume from any checkpoint - -**Note**: Final session completion creates additional commit with full summary. - -## Post-Completion Expansion - -完成后询问用户是否扩展为issue(test/enhance/refactor/doc)，选中项调用 `/issue:new "{summary} - {dimension}"` - -## Best Practices - -1. **Default Settings Work**: 10 iterations sufficient for most cases -2. **Automatic Commits**: Orchestrator commits after each successful iteration - no manual intervention needed -3. **Trust Strategy Engine**: Auto-selection based on proven heuristics -4. **Monitor Logs**: Check `.process/iteration-N-analysis.md` for CLI analysis insights -5. **Progressive Testing**: Saves 70-90% iteration time automatically diff --git a/.claude/commands/workflow/test-fix-gen.md b/.claude/commands/workflow/test-fix-gen.md deleted file mode 100644 index fd058a5a..00000000 --- a/.claude/commands/workflow/test-fix-gen.md +++ /dev/null @@ -1,477 +0,0 @@ ---- -name: test-fix-gen -description: Create test-fix workflow session with progressive test layers (L0-L3), AI code validation, and test task generation -argument-hint: "(source-session-id | \"feature description\" | /path/to/file.md)" -allowed-tools: Skill(*), TodoWrite(*), Read(*), Bash(*) -group: workflow ---- - -# Workflow Test-Fix Generation Command (/workflow:test-fix-gen) - -## Coordinator Role - -**This command is a pure orchestrator**: Execute 5 slash commands in sequence, parse their outputs, pass context between them, and ensure complete execution through **automatic continuation**. - -**Execution Model - Auto-Continue Workflow**: - -This workflow runs **fully autonomously** once triggered. Phase 3 (test analysis) and Phase 4 (task generation) are delegated to specialized agents. - -1. **User triggers**: `/workflow:test-fix-gen "task"` or `/workflow:test-fix-gen WFS-source-session` -2. **Phase 1 executes** → Test session created → Auto-continues -3. **Phase 2 executes** → Context gathering → Auto-continues -4. **Phase 3 executes** → Test generation analysis (Gemini) → Auto-continues -5. **Phase 4 executes** → Task generation (test-task-generate) → Reports final summary - -**Task Attachment Model**: -- Skill execute **expands workflow** by attaching sub-tasks to current TodoWrite -- When a sub-command is executed, its internal tasks are attached to the orchestrator's TodoWrite -- Orchestrator **executes these attached tasks** sequentially -- After completion, attached tasks are **collapsed** back to high-level phase summary -- This is **task expansion**, not external delegation - -**Auto-Continue Mechanism**: -- TodoList tracks current phase status and dynamically manages task attachment/collapse -- When each phase finishes executing, automatically execute next pending phase -- All phases run autonomously without user interaction -- **⚠️ CONTINUOUS EXECUTION** - Do not stop until all phases complete - -## Core Rules - -1. **Start Immediately**: First action is TodoWrite initialization, second action is Phase 1 command execution -2. **No Preliminary Analysis**: Do not read files, analyze structure, or gather context before Phase 1 -3. **Parse Every Output**: Extract required data from each command output for next phase -4. **Auto-Continue via TodoList**: Check TodoList status to execute next pending phase automatically -5. **Track Progress**: Update TodoWrite dynamically with task attachment/collapse pattern -6. **Task Attachment Model**: Skill execute **attaches** sub-tasks to current workflow. Orchestrator **executes** these attached tasks itself, then **collapses** them after completion -7. **⚠️ CRITICAL: DO NOT STOP**: Continuous multi-phase workflow. After executing all attached tasks, immediately collapse them and execute next phase - ---- - -## Test Strategy Overview - -This workflow generates tests using **Progressive Test Layers (L0-L3)**: - -| Layer | Name | Focus | -|-------|------|-------| -| **L0** | Static Analysis | Compilation, imports, types, AI code issues | -| **L1** | Unit Tests | Function/class behavior (happy/negative/edge cases) | -| **L2** | Integration Tests | Component interactions, API contracts, failure modes | -| **L3** | E2E Tests | User journeys, critical paths (optional) | - -**Key Features**: -- **AI Code Issue Detection** - Validates against common AI-generated code problems (hallucinated imports, placeholder code, mock leakage, etc.) -- **Project Type Detection** - Applies appropriate test templates (React, Node API, CLI, Library, etc.) -- **Quality Gates** - IMPL-001.3 (code validation) and IMPL-001.5 (test quality) ensure high standards - -**Detailed specifications**: See `/workflow:tools:test-task-generate` for complete L0-L3 requirements and quality thresholds. - ---- - -## Execution Process - -``` -Input Parsing: - ├─ Detect input type: Session ID (WFS-*) | Description | File path - └─ Set MODE: session | prompt - -Phase 1: Create Test Session - └─ /workflow:session:start --type test --new "structured-description" - └─ Output: testSessionId (WFS-test-xxx) - -Phase 2: Gather Test Context - ├─ MODE=session → /workflow:tools:test-context-gather --session testSessionId - └─ MODE=prompt → /workflow:tools:context-gather --session testSessionId "description" - └─ Output: contextPath (context-package.json) - -Phase 3: Test Generation Analysis - └─ /workflow:tools:test-concept-enhanced --session testSessionId --context contextPath - └─ Output: TEST_ANALYSIS_RESULTS.md (L0-L3 requirements) - -Phase 4: Generate Test Tasks - └─ /workflow:tools:test-task-generate --session testSessionId - └─ Output: IMPL_PLAN.md, IMPL-*.json (4+ tasks), TODO_LIST.md - -Phase 5: Return Summary - └─ Summary with next steps → /workflow:test-cycle-execute -``` - ---- - -## 5-Phase Execution - -### Phase 1: Create Test Session - -**Step 1.0: Detect Input Mode** - -``` -// Automatic mode detection based on input pattern -if (input.startsWith("WFS-")) { - MODE = "session" - // Load source session to preserve original task description - Read(".workflow/active/[sourceSessionId]/workflow-session.json") -} else { - MODE = "prompt" -} -``` - -**Step 1.1: Execute** - Create test workflow session - -``` -// Session Mode - preserve original task description -Skill(skill="workflow:session:start", args="--type test --new \"Test validation for [sourceSessionId]: [originalTaskDescription]\"") - -// Prompt Mode - use user's description directly -Skill(skill="workflow:session:start", args="--type test --new \"Test generation for: [description]\"") -``` - -**Parse Output**: -- Extract: `SESSION_ID: WFS-test-[slug]` (store as `testSessionId`) - -**Validation**: -- Session Mode: Source session `.workflow/active/[sourceSessionId]/` exists with completed IMPL tasks -- Both Modes: New test session directory created with metadata - -**TodoWrite**: Mark phase 1 completed, phase 2 in_progress - ---- - -### Phase 2: Gather Test Context - -**Step 2.1: Execute** - Gather context based on mode - -``` -// Session Mode - gather from source session -Skill(skill="workflow:tools:test-context-gather", args="--session [testSessionId]") - -// Prompt Mode - gather from codebase -Skill(skill="workflow:tools:context-gather", args="--session [testSessionId] \"[task_description]\"") -``` - -**Input**: `testSessionId` from Phase 1 - -**Parse Output**: -- Extract: context package path (store as `contextPath`) -- Pattern: `.workflow/active/[testSessionId]/.process/[test-]context-package.json` - -**Validation**: -- Context package file exists and is valid JSON -- Contains coverage analysis (session mode) or codebase analysis (prompt mode) -- Test framework detected - -**TodoWrite Update (tasks attached)**: -```json -[ - {"content": "Phase 1: Create Test Session", "status": "completed"}, - {"content": "Phase 2: Gather Test Context", "status": "in_progress"}, - {"content": " → Load source/codebase context", "status": "in_progress"}, - {"content": " → Analyze test coverage", "status": "pending"}, - {"content": " → Generate context package", "status": "pending"}, - {"content": "Phase 3: Test Generation Analysis", "status": "pending"}, - {"content": "Phase 4: Generate Test Tasks", "status": "pending"}, - {"content": "Phase 5: Return Summary", "status": "pending"} -] -``` - -**TodoWrite Update (tasks collapsed)**: -```json -[ - {"content": "Phase 1: Create Test Session", "status": "completed"}, - {"content": "Phase 2: Gather Test Context", "status": "completed"}, - {"content": "Phase 3: Test Generation Analysis", "status": "pending"}, - {"content": "Phase 4: Generate Test Tasks", "status": "pending"}, - {"content": "Phase 5: Return Summary", "status": "pending"} -] -``` - ---- - -### Phase 3: Test Generation Analysis - -**Step 3.1: Execute** - Analyze test requirements with Gemini - -``` -Skill(skill="workflow:tools:test-concept-enhanced", args="--session [testSessionId] --context [contextPath]") -``` - -**Input**: -- `testSessionId` from Phase 1 -- `contextPath` from Phase 2 - -**Expected Behavior**: -- Use Gemini to analyze coverage gaps -- Detect project type and apply appropriate test templates -- Generate **multi-layered test requirements** (L0-L3) -- Scan for AI code issues -- Generate `TEST_ANALYSIS_RESULTS.md` - -**Output**: `.workflow/[testSessionId]/.process/TEST_ANALYSIS_RESULTS.md` - -**Validation** - TEST_ANALYSIS_RESULTS.md must include: -- Project Type Detection (with confidence) -- Coverage Assessment (current vs target) -- Test Framework & Conventions -- Multi-Layered Test Plan (L0-L3) -- AI Issue Scan Results -- Test Requirements by File (with layer annotations) -- Quality Assurance Criteria -- Success Criteria - -**Note**: Detailed specifications for project types, L0-L3 layers, and AI issue detection are defined in `/workflow:tools:test-concept-enhanced`. - ---- - -### Phase 4: Generate Test Tasks - -**Step 4.1: Execute** - Generate test planning documents - -``` -Skill(skill="workflow:tools:test-task-generate", args="--session [testSessionId]") -``` - -**Input**: `testSessionId` from Phase 1 - -**Note**: test-task-generate invokes action-planning-agent to generate test-specific IMPL_PLAN.md and task JSONs based on TEST_ANALYSIS_RESULTS.md. - -**Expected Output** (minimum 4 tasks): - -| Task | Type | Agent | Purpose | -|------|------|-------|---------| -| IMPL-001 | test-gen | @code-developer | Test understanding & generation (L1-L3) | -| IMPL-001.3 | code-validation | @test-fix-agent | Code validation gate (L0 + AI issues) | -| IMPL-001.5 | test-quality-review | @test-fix-agent | Test quality gate | -| IMPL-002 | test-fix | @test-fix-agent | Test execution & fix cycle | - -**Validation**: -- `.workflow/active/[testSessionId]/.task/IMPL-001.json` exists -- `.workflow/active/[testSessionId]/.task/IMPL-001.3-validation.json` exists -- `.workflow/active/[testSessionId]/.task/IMPL-001.5-review.json` exists -- `.workflow/active/[testSessionId]/.task/IMPL-002.json` exists -- `.workflow/active/[testSessionId]/IMPL_PLAN.md` exists -- `.workflow/active/[testSessionId]/TODO_LIST.md` exists - -**TodoWrite Update (agent task attached)**: -```json -[ - {"content": "Phase 1: Create Test Session", "status": "completed"}, - {"content": "Phase 2: Gather Test Context", "status": "completed"}, - {"content": "Phase 3: Test Generation Analysis", "status": "completed"}, - {"content": "Phase 4: Generate Test Tasks", "status": "in_progress"}, - {"content": "Phase 5: Return Summary", "status": "pending"} -] -``` - ---- - -### Phase 5: Return Summary - -**Return to User**: -``` -Test-fix workflow created successfully! - -Input: [original input] -Mode: [Session|Prompt] -Test Session: [testSessionId] - -Tasks Created: -- IMPL-001: Test Understanding & Generation (@code-developer) -- IMPL-001.3: Code Validation Gate - AI Error Detection (@test-fix-agent) -- IMPL-001.5: Test Quality Gate - Static Analysis & Coverage (@test-fix-agent) -- IMPL-002: Test Execution & Fix Cycle (@test-fix-agent) - -Quality Thresholds: -- Code Validation: Zero CRITICAL issues, zero compilation errors -- Minimum Coverage: 80% line, 70% branch -- Static Analysis: Zero critical anti-patterns -- Max Fix Iterations: 5 - -Review artifacts: -- Test plan: .workflow/[testSessionId]/IMPL_PLAN.md -- Task list: .workflow/[testSessionId]/TODO_LIST.md -- Analysis: .workflow/[testSessionId]/.process/TEST_ANALYSIS_RESULTS.md - -CRITICAL - Next Step: - /workflow:test-cycle-execute --session [testSessionId] -``` - ---- - -## Data Flow - -``` -User Input (session ID | description | file path) - ↓ -[Detect Mode: session | prompt] - ↓ -Phase 1: session:start --type test --new "description" - ↓ Output: testSessionId - ↓ -Phase 2: test-context-gather | context-gather - ↓ Input: testSessionId - ↓ Output: contextPath (context-package.json) - ↓ -Phase 3: test-concept-enhanced - ↓ Input: testSessionId + contextPath - ↓ Output: TEST_ANALYSIS_RESULTS.md (L0-L3 requirements + AI issues) - ↓ -Phase 4: test-task-generate - ↓ Input: testSessionId + TEST_ANALYSIS_RESULTS.md - ↓ Output: IMPL_PLAN.md, IMPL-*.json (4+), TODO_LIST.md - ↓ -Phase 5: Return summary to user - ↓ -Next: /workflow:test-cycle-execute -``` - ---- - -## Execution Flow Diagram - -``` -User triggers: /workflow:test-fix-gen "Test user authentication" - ↓ -[Input Detection] → MODE: prompt - ↓ -[TodoWrite Init] 5 orchestrator-level tasks - ↓ -Phase 1: Create Test Session - → /workflow:session:start --type test - → testSessionId extracted (WFS-test-user-auth) - ↓ -Phase 2: Gather Test Context (Skill executed) - → ATTACH 3 sub-tasks: ← ATTACHED - - → Load codebase context - - → Analyze test coverage - - → Generate context package - → Execute sub-tasks sequentially - → COLLAPSE tasks ← COLLAPSED - → contextPath extracted - ↓ -Phase 3: Test Generation Analysis (Skill executed) - → ATTACH 3 sub-tasks: ← ATTACHED - - → Analyze coverage gaps with Gemini - - → Detect AI code issues (L0.5) - - → Generate L0-L3 test requirements - → Execute sub-tasks sequentially - → COLLAPSE tasks ← COLLAPSED - → TEST_ANALYSIS_RESULTS.md created - ↓ -Phase 4: Generate Test Tasks (Skill executed) - → Single agent task (test-task-generate → action-planning-agent) - → Agent autonomously generates: - - IMPL-001.json (test generation) - - IMPL-001.3-validation.json (code validation) - - IMPL-001.5-review.json (test quality) - - IMPL-002.json (test execution) - - IMPL_PLAN.md - - TODO_LIST.md - ↓ -Phase 5: Return Summary - → Display summary with next steps - → Command ends - -Task Pipeline (for execution): -┌──────────────┐ ┌─────────────────┐ ┌─────────────────┐ ┌──────────────┐ -│ IMPL-001 │───→│ IMPL-001.3 │───→│ IMPL-001.5 │───→│ IMPL-002 │ -│ Test Gen │ │ Code Validate │ │ Quality Gate │ │ Test & Fix │ -│ L1-L3 │ │ L0 + AI Issues │ │ Coverage 80%+ │ │ Max 5 iter │ -│@code-developer│ │ @test-fix-agent │ │ @test-fix-agent │ │@test-fix-agent│ -└──────────────┘ └─────────────────┘ └─────────────────┘ └──────────────┘ -``` - ---- - -## Output Artifacts - -### Directory Structure - -``` -.workflow/active/WFS-test-[session]/ -├── workflow-session.json # Session metadata -├── IMPL_PLAN.md # Test generation and execution strategy -├── TODO_LIST.md # Task checklist -├── .task/ -│ ├── IMPL-001.json # Test understanding & generation -│ ├── IMPL-001.3-validation.json # Code validation gate -│ ├── IMPL-001.5-review.json # Test quality gate -│ ├── IMPL-002.json # Test execution & fix cycle -│ └── IMPL-*.json # Additional tasks (if applicable) -└── .process/ - ├── [test-]context-package.json # Context and coverage analysis - └── TEST_ANALYSIS_RESULTS.md # Test requirements and strategy (L0-L3) -``` - -### Session Metadata - -**File**: `workflow-session.json` - -| Mode | Fields | -|------|--------| -| **Session** | `type: "test"`, `source_session_id: "[sourceId]"` | -| **Prompt** | `type: "test"` (no source_session_id) | - ---- - -## Error Handling - -| Phase | Error Condition | Action | -|-------|----------------|--------| -| 1 | Source session not found (session mode) | Return error with session ID | -| 1 | No completed IMPL tasks (session mode) | Return error, source incomplete | -| 2 | Context gathering failed | Return error, check source artifacts | -| 3 | Gemini analysis failed | Return error, check context package | -| 4 | Task generation failed | Retry once, then return error | - ---- - -## Coordinator Checklist - -- Detect input type (session ID / description / file path) -- Initialize TodoWrite before any command -- Execute Phase 1 immediately with structured description -- Parse test session ID from Phase 1 output, store in memory -- Execute Phase 2 with appropriate context-gather command based on mode -- Parse context path from Phase 2 output, store in memory -- Execute Phase 3 test-concept-enhanced with session and context -- Verify TEST_ANALYSIS_RESULTS.md created with L0-L3 requirements -- Execute Phase 4 test-task-generate with session ID -- Verify all Phase 4 outputs (4 task JSONs, IMPL_PLAN.md, TODO_LIST.md) -- Return summary with next step: `/workflow:test-cycle-execute` -- Update TodoWrite after each phase - ---- - -## Usage Examples - -```bash -# Session Mode - test validation for completed implementation -/workflow:test-fix-gen WFS-user-auth-v2 - -# Prompt Mode - text description -/workflow:test-fix-gen "Test the user authentication API endpoints in src/auth/api.ts" - -# Prompt Mode - file reference -/workflow:test-fix-gen ./docs/api-requirements.md - -# With CLI tool preference (semantic detection) -/workflow:test-fix-gen "Test user registration, use Codex for automated fixes" -``` - ---- - -## Related Commands - -**Prerequisite Commands**: -- `/workflow:plan` or `/workflow:execute` - Complete implementation (Session Mode) -- None for Prompt Mode - -**Called by This Command** (5 phases): -- `/workflow:session:start` - Phase 1: Create test workflow session -- `/workflow:tools:test-context-gather` - Phase 2 (Session Mode): Analyze test coverage -- `/workflow:tools:context-gather` - Phase 2 (Prompt Mode): Analyze codebase -- `/workflow:tools:test-concept-enhanced` - Phase 3: Generate test requirements with Gemini -- `/workflow:tools:test-task-generate` - Phase 4: Generate test task JSONs via action-planning-agent - -**Follow-up Commands**: -- `/workflow:status` - Review generated tasks -- `/workflow:test-cycle-execute` - Execute test workflow (REQUIRED next step) -- `/workflow:execute` - Alternative: Standard task execution diff --git a/.claude/skills/workflow-tdd/SKILL.md b/.claude/skills/workflow-tdd/SKILL.md new file mode 100644 index 00000000..9a3552c2 --- /dev/null +++ b/.claude/skills/workflow-tdd/SKILL.md @@ -0,0 +1,459 @@ +--- +name: workflow-tdd +description: Unified TDD workflow skill combining 6-phase TDD planning with Red-Green-Refactor task chain generation, and 4-phase TDD verification with compliance reporting. Triggers on "workflow:tdd-plan", "workflow:tdd-verify". +allowed-tools: Skill, Task, AskUserQuestion, TaskCreate, TaskUpdate, TaskList, Read, Write, Edit, Bash, Glob, Grep +--- + +# Workflow TDD + +Unified TDD workflow skill combining TDD planning (Red-Green-Refactor task chain generation with test-first development structure) and TDD verification (compliance validation with quality gate reporting). Produces IMPL_PLAN.md, task JSONs with internal TDD cycles, and TDD_COMPLIANCE_REPORT.md. + +## Architecture Overview + +``` +┌──────────────────────────────────────────────────────────────────┐ +│ Workflow TDD Orchestrator (SKILL.md) │ +│ → Route by mode: plan | verify │ +│ → Pure coordinator: Execute phases, parse outputs, pass context │ +└──────────────────────────────┬───────────────────────────────────┘ + │ + ┌───────────────────────┴───────────────────────┐ + ↓ ↓ + ┌─────────────┐ ┌───────────┐ + │ Plan Mode │ │ Verify │ + │ (default) │ │ Mode │ + │ Phase 1-6 │ │ Phase 7 │ + └──────┬──────┘ └───────────┘ + │ + ┌─────┼─────┬─────┬─────┬─────┐ + ↓ ↓ ↓ ↓ ↓ ↓ + ┌───┐ ┌───┐ ┌───┐ ┌───┐ ┌───┐ ┌───┐ + │ 1 │ │ 2 │ │ 3 │ │ 4 │ │ 5 │ │ 6 │ + │Ses│ │Ctx│ │Tst│ │Con│ │Gen│ │Val│ + └───┘ └───┘ └───┘ └───┘ └─┬─┘ └───┘ + ↓ + ┌───────────┐ + │ Confirm │─── Verify ──→ Phase 7 + │ (choice) │─── Execute ─→ Skill("workflow-execute") + └───────────┘─── Review ──→ /workflow:status +``` + +## Key Design Principles + +1. **Pure Orchestrator**: SKILL.md routes and coordinates only; execution detail lives in phase files +2. **Progressive Phase Loading**: Read phase docs ONLY when that phase is about to execute +3. **Multi-Mode Routing**: Single skill handles plan/verify via mode detection +4. **Task Attachment Model**: Sub-command tasks are ATTACHED, executed sequentially, then COLLAPSED +5. **Auto-Continue**: After each phase completes, automatically execute next pending phase +6. **TDD Iron Law**: NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST - enforced in task structure + +## Auto Mode + +When `--yes` or `-y`: Auto-continue all phases (skip confirmations), use recommended conflict resolutions, auto-select "Verify Plan Quality" after plan completion. + +## Mode Detection + +```javascript +const args = $ARGUMENTS +const mode = detectMode(args) + +function detectMode(args) { + // Skill trigger determines mode + if (skillName === 'workflow:tdd-verify') return 'verify' + return 'plan' // default: workflow:tdd-plan +} +``` + +## Execution Flow + +### Plan Mode (default) + +``` +Input Parsing: + └─ Convert user input to TDD structured format (GOAL/SCOPE/CONTEXT/TEST_FOCUS) + +Phase 1: Session Discovery + └─ Ref: phases/01-session-discovery.md + └─ Output: sessionId (WFS-xxx) + +Phase 2: Context Gathering + └─ Ref: phases/02-context-gathering.md + ├─ Tasks attached: Analyze structure → Identify integration → Generate package + └─ Output: contextPath + conflictRisk + +Phase 3: Test Coverage Analysis + └─ Ref: phases/03-test-coverage-analysis.md + ├─ Tasks attached: Detect framework → Analyze coverage → Identify gaps + └─ Output: testContextPath + +Phase 4: Conflict Resolution (conditional: conflictRisk ≥ medium) + └─ Decision (conflictRisk check): + ├─ conflictRisk ≥ medium → Ref: phases/04-conflict-resolution.md + │ ├─ Tasks attached: Detect conflicts → Log analysis → Apply strategies + │ └─ Output: conflict-resolution.json + └─ conflictRisk < medium → Skip to Phase 5 + +Phase 5: TDD Task Generation + └─ Ref: phases/05-tdd-task-generation.md + ├─ Tasks attached: Discovery → Planning → Output + └─ Output: IMPL_PLAN.md, IMPL-*.json, TODO_LIST.md + +Phase 6: TDD Structure Validation + └─ Ref: phases/06-tdd-structure-validation.md + └─ Output: Validation report + Plan Confirmation Gate + +Plan Confirmation (User Decision Gate): + └─ Decision (user choice): + ├─ "Verify TDD Compliance" (Recommended) → Route to Phase 7 (tdd-verify) + ├─ "Start Execution" → Skill(skill="workflow-execute") + └─ "Review Status Only" → Route to /workflow:status +``` + +### Verify Mode + +``` +Phase 7: TDD Verification + └─ Ref: phases/07-tdd-verify.md + └─ Output: TDD_COMPLIANCE_REPORT.md with quality gate recommendation +``` + +**Phase Reference Documents** (read on-demand when phase executes): + +| Phase | Document | Purpose | Mode | +|-------|----------|---------|------| +| 1 | [phases/01-session-discovery.md](phases/01-session-discovery.md) | Create or discover TDD workflow session | plan | +| 2 | [phases/02-context-gathering.md](phases/02-context-gathering.md) | Gather project context and analyze codebase | plan | +| 3 | [phases/03-test-coverage-analysis.md](phases/03-test-coverage-analysis.md) | Analyze test coverage and framework detection | plan | +| 4 | [phases/04-conflict-resolution.md](phases/04-conflict-resolution.md) | Detect and resolve conflicts (conditional) | plan | +| 5 | [phases/05-tdd-task-generation.md](phases/05-tdd-task-generation.md) | Generate TDD tasks with Red-Green-Refactor cycles | plan | +| 6 | [phases/06-tdd-structure-validation.md](phases/06-tdd-structure-validation.md) | Validate TDD structure and present confirmation gate | plan | +| 7 | [phases/07-tdd-verify.md](phases/07-tdd-verify.md) | Full TDD compliance verification with quality gate | verify | + +## Core Rules + +1. **Start Immediately**: First action is mode detection + TaskCreate initialization, second action is phase execution +2. **No Preliminary Analysis**: Do not read files, analyze structure, or gather context before Phase 1 +3. **Parse Every Output**: Extract required data from each phase output for next phase +4. **Auto-Continue via TaskList**: Check TaskList status to execute next pending phase automatically +5. **Track Progress**: Update TaskCreate/TaskUpdate dynamically with task attachment/collapse pattern +6. **Task Attachment Model**: Skill execute **attaches** sub-tasks to current workflow. Orchestrator **executes** these attached tasks itself, then **collapses** them after completion +7. **Progressive Phase Loading**: Read phase docs ONLY when that phase is about to execute +8. **DO NOT STOP**: Continuous multi-phase workflow. After executing all attached tasks, immediately collapse them and execute next phase +9. **TDD Context**: All descriptions include "TDD:" prefix + +## TDD Compliance Requirements + +### The Iron Law + +``` +NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST +``` + +**Enforcement Method**: +- Phase 5: `implementation` includes test-first steps (Red → Green → Refactor) +- Green phase: Includes test-fix-cycle configuration (max 3 iterations) +- Auto-revert: Triggered when max iterations reached without passing tests + +**Verification**: Phase 6 validates Red-Green-Refactor structure in all generated tasks + +### TDD Compliance Checkpoint + +| Checkpoint | Validation Phase | Evidence Required | +|------------|------------------|-------------------| +| Test-first structure | Phase 5 | `implementation` has 3 steps | +| Red phase exists | Phase 6 | Step 1: `tdd_phase: "red"` | +| Green phase with test-fix | Phase 6 | Step 2: `tdd_phase: "green"` + test-fix-cycle | +| Refactor phase exists | Phase 6 | Step 3: `tdd_phase: "refactor"` | + +### Core TDD Principles + +**Red Flags - STOP and Reassess**: +- Code written before test +- Test passes immediately (no Red phase witnessed) +- Cannot explain why test should fail +- "Just this once" rationalization +- "Tests after achieve same goals" thinking + +**Why Order Matters**: +- Tests written after code pass immediately → proves nothing +- Test-first forces edge case discovery before implementation +- Tests-after verify what was built, not what's required + +## Input Processing + +**Convert User Input to TDD Structured Format**: + +1. **Simple text** → Add TDD context: + ``` + User: "Build authentication system" + + Structured: + TDD: Authentication System + GOAL: Build authentication system + SCOPE: Core authentication features + CONTEXT: New implementation + TEST_FOCUS: Authentication scenarios + ``` + +2. **Detailed text** → Extract components with TEST_FOCUS: + ``` + User: "Add JWT authentication with email/password login and token refresh" + + Structured: + TDD: JWT Authentication + GOAL: Implement JWT-based authentication + SCOPE: Email/password login, token generation, token refresh endpoints + CONTEXT: JWT token-based security, refresh token rotation + TEST_FOCUS: Login flow, token validation, refresh rotation, error cases + ``` + +3. **File/Issue** → Read and structure with TDD + +## Data Flow + +### Plan Mode + +``` +User Input (task description) + ↓ +[Convert to TDD Structured Format] + ↓ Structured Description: + ↓ TDD: [Feature Name] + ↓ GOAL: [objective] + ↓ SCOPE: [boundaries] + ↓ CONTEXT: [background] + ↓ TEST_FOCUS: [test scenarios] + ↓ +Phase 1: session:start --auto "TDD: structured-description" + ↓ Output: sessionId + ↓ +Phase 2: context-gather --session sessionId "structured-description" + ↓ Input: sessionId + structured description + ↓ Output: contextPath (context-package.json) + conflictRisk + ↓ +Phase 3: test-context-gather --session sessionId + ↓ Input: sessionId + ↓ Output: testContextPath (test-context-package.json) + ↓ +Phase 4: conflict-resolution [conditional: conflictRisk ≥ medium] + ↓ Input: sessionId + contextPath + conflictRisk + ↓ Output: conflict-resolution.json + ↓ Skip if conflictRisk is none/low → proceed directly to Phase 5 + ↓ +Phase 5: task-generate-tdd --session sessionId + ↓ Input: sessionId + all accumulated context + ↓ Output: IMPL_PLAN.md, IMPL-*.json, TODO_LIST.md + ↓ +Phase 6: TDD Structure Validation (internal) + ↓ Validate Red-Green-Refactor structure + ↓ Present Plan Confirmation Gate + ↓ +Plan Confirmation (User Decision Gate): + ├─ "Verify TDD Compliance" (Recommended) → Route to Phase 7 + ├─ "Start Execution" → Skill(skill="workflow-execute") + └─ "Review Status Only" → Route to /workflow:status +``` + +### Verify Mode + +``` +Input: --session sessionId (or auto-detect) + ↓ +Phase 7: Session discovery → Chain validation → Coverage analysis → Report + ↓ Output: TDD_COMPLIANCE_REPORT.md with quality gate +``` + +**Session Memory Flow**: Each phase receives session ID, which provides access to: +- Previous task summaries +- Existing context and analysis +- Session-specific configuration + +## TodoWrite Pattern + +**Core Concept**: Dynamic task attachment and collapse for real-time visibility into TDD workflow execution. + +> **Implementation Note**: Phase files use `TodoWrite` syntax to describe the conceptual tracking pattern. At runtime, these are implemented via `TaskCreate/TaskUpdate/TaskList` tools. Map as follows: +> - Initial list creation → `TaskCreate` for each item +> - Status changes → `TaskUpdate({ taskId, status })` +> - Sub-task attachment → `TaskCreate` + `TaskUpdate({ addBlockedBy })` +> - Sub-task collapse → `TaskUpdate({ status: "completed" })` + `TaskUpdate({ status: "deleted" })` for collapsed sub-items + +### Key Principles + +1. **Task Attachment** (when phase executed): + - Sub-tasks are **attached** to orchestrator's TodoWrite + - **Phase 3, 4, 5**: Multiple sub-tasks attached + - **Phase 1, 2, 6**: Single task (atomic) + - First attached task marked as `in_progress`, others as `pending` + - Orchestrator **executes** these attached tasks sequentially + +2. **Task Collapse** (after sub-tasks complete): + - **Applies to Phase 3, 4, 5**: Remove detailed sub-tasks from TodoWrite + - **Collapse** to high-level phase summary + - **Phase 1, 2, 6**: No collapse needed (single task, just mark completed) + - Maintains clean orchestrator-level view + +3. **Continuous Execution**: After completion, automatically proceed to next pending phase + +**Lifecycle**: Initial pending → Phase executed (tasks ATTACHED) → Sub-tasks executed sequentially → Phase completed (tasks COLLAPSED for 3/4/5, marked completed for 1/2/6) → Next phase → Repeat + +### Initial State (Plan Mode): +```json +[ + {"content": "Phase 1: Session Discovery", "status": "in_progress", "activeForm": "Executing session discovery"}, + {"content": "Phase 2: Context Gathering", "status": "pending", "activeForm": "Executing context gathering"}, + {"content": "Phase 3: Test Coverage Analysis", "status": "pending", "activeForm": "Executing test coverage analysis"}, + {"content": "Phase 5: TDD Task Generation", "status": "pending", "activeForm": "Executing TDD task generation"}, + {"content": "Phase 6: TDD Structure Validation", "status": "pending", "activeForm": "Validating TDD structure"} +] +``` + +**Note**: Phase 4 (Conflict Resolution) is added dynamically after Phase 2 if conflictRisk ≥ medium. + +### Phase 3 (Tasks Attached): +```json +[ + {"content": "Phase 1: Session Discovery", "status": "completed"}, + {"content": "Phase 2: Context Gathering", "status": "completed"}, + {"content": "Phase 3: Test Coverage Analysis", "status": "in_progress"}, + {"content": " → Detect test framework and conventions", "status": "in_progress"}, + {"content": " → Analyze existing test coverage", "status": "pending"}, + {"content": " → Identify coverage gaps", "status": "pending"}, + {"content": "Phase 5: TDD Task Generation", "status": "pending"}, + {"content": "Phase 6: TDD Structure Validation", "status": "pending"} +] +``` + +### Phase 3 (Collapsed): +```json +[ + {"content": "Phase 1: Session Discovery", "status": "completed"}, + {"content": "Phase 2: Context Gathering", "status": "completed"}, + {"content": "Phase 3: Test Coverage Analysis", "status": "completed"}, + {"content": "Phase 5: TDD Task Generation", "status": "pending"}, + {"content": "Phase 6: TDD Structure Validation", "status": "pending"} +] +``` + +### Phase 5 (Tasks Attached): +```json +[ + {"content": "Phase 1: Session Discovery", "status": "completed"}, + {"content": "Phase 2: Context Gathering", "status": "completed"}, + {"content": "Phase 3: Test Coverage Analysis", "status": "completed"}, + {"content": "Phase 5: TDD Task Generation", "status": "in_progress"}, + {"content": " → Discovery - analyze TDD requirements", "status": "in_progress"}, + {"content": " → Planning - design Red-Green-Refactor cycles", "status": "pending"}, + {"content": " → Output - generate IMPL tasks with internal TDD phases", "status": "pending"}, + {"content": "Phase 6: TDD Structure Validation", "status": "pending"} +] +``` + +**Note**: See individual Phase descriptions for detailed TodoWrite Update examples. + +## Post-Phase Updates + +### Memory State Check + +After heavy phases (Phase 2-3), evaluate context window usage: +- If memory usage is high (>110K tokens or approaching context limits): + ```javascript + Skill(skill="compact") + ``` +- Memory compaction is particularly important after analysis phases + +### Planning Notes (Optional) + +Similar to workflow-plan, a `planning-notes.md` can accumulate context across phases if needed. See Phase 1 for initialization. + +## Error Handling + +- **Parsing Failure**: If output parsing fails, retry command once, then report error +- **Validation Failure**: Report which file/data is missing or invalid +- **Command Failure**: Keep phase `in_progress`, report error to user, do not proceed +- **TDD Validation Failure**: Report incomplete chains or wrong dependencies +- **Session Not Found** (verify mode): Report error with available sessions list + +### Error Handling Quick Reference + +| Error Type | Detection | Recovery Action | +|------------|-----------|-----------------| +| Parsing failure | Empty/malformed output | Retry once, then report | +| Missing context-package | File read error | Re-run `/workflow:tools:context-gather` | +| Invalid task JSON | jq parse error | Report malformed file path | +| Task count exceeds 18 | Count validation ≥19 | Request re-scope, split into multiple sessions | +| Missing cli_execution.id | All tasks lack ID | Regenerate tasks with phase 0 user config | +| Test-context missing | File not found | Re-run `/workflow:tools:test-context-gather` | +| Phase timeout | No response | Retry phase, check CLI connectivity | +| CLI tool not available | Tool not in cli-tools.json | Fall back to alternative preferred tool | + +### TDD Warning Patterns + +| Pattern | Warning Message | Recommended Action | +|---------|----------------|-------------------| +| Task count >10 | High task count detected | Consider splitting into multiple sessions | +| Missing test-fix-cycle | Green phase lacks auto-revert | Add `max_iterations: 3` to task config | +| Red phase missing test path | Test file path not specified | Add explicit test file paths | +| Generic task names | Vague names like "Add feature" | Use specific behavior descriptions | +| No refactor criteria | Refactor phase lacks completion criteria | Define clear refactor scope | + +### Non-Blocking Warning Policy + +**All warnings are advisory** - they do not halt execution: +1. Warnings logged to `.process/tdd-warnings.log` +2. Summary displayed in Phase 6 output +3. User decides whether to address before `/workflow:execute` + +## Coordinator Checklist + +### Plan Mode +- **Pre-Phase**: Convert user input to TDD structured format (TDD/GOAL/SCOPE/CONTEXT/TEST_FOCUS) +- Initialize TaskCreate before any command (Phase 4 added dynamically after Phase 2) +- Execute Phase 1 immediately with structured description +- Parse session ID from Phase 1 output, store in memory +- Pass session ID and structured description to Phase 2 command +- Parse context path from Phase 2 output, store in memory +- **Extract conflictRisk from context-package.json**: Determine Phase 4 execution +- Execute Phase 3 (test coverage analysis) with sessionId +- Parse testContextPath from Phase 3 output, store in memory +- **If conflictRisk ≥ medium**: Launch Phase 4 conflict-resolution with sessionId and contextPath +- Wait for Phase 4 to finish executing (if executed), verify conflict-resolution.json created +- **If conflictRisk is none/low**: Skip Phase 4, proceed directly to Phase 5 +- Pass session ID to Phase 5 command (TDD task generation) +- Verify all Phase 5 outputs (IMPL_PLAN.md, IMPL-*.json, TODO_LIST.md) +- Execute Phase 6 (internal TDD structure validation) +- **Plan Confirmation Gate**: Present user with choice (Verify → Phase 7 / Execute / Review Status) +- **If user selects Verify**: Read phases/07-tdd-verify.md, execute Phase 7 in-process +- **If user selects Execute**: Skill(skill="workflow-execute") +- **If user selects Review**: Route to /workflow:status +- **Auto mode (--yes)**: Auto-select "Verify TDD Compliance", then auto-continue to execute if APPROVED +- Update TaskCreate/TaskUpdate after each phase +- After each phase, automatically continue to next phase based on TaskList status + +### Verify Mode +- Detect/validate session (from --session flag or auto-detect) +- Initialize TaskCreate with verification tasks +- Execute Phase 7 through all sub-phases (session validation → chain validation → coverage analysis → report generation) +- Present quality gate result and next step options + +## Related Skills + +**Prerequisite Skills**: +- None - TDD planning is self-contained (can optionally run brainstorm commands before) + +**Called by Plan Mode** (6 phases): +- `/workflow:session:start` - Phase 1: Create or discover TDD workflow session +- `/workflow:tools:context-gather` - Phase 2: Gather project context and analyze codebase +- `/workflow:tools:test-context-gather` - Phase 3: Analyze existing test patterns and coverage +- `/workflow:tools:conflict-resolution` - Phase 4: Detect and resolve conflicts (conditional) +- `/compact` - Phase 4: Memory optimization (if context approaching limits) +- `/workflow:tools:task-generate-tdd` - Phase 5: Generate TDD tasks with Red-Green-Refactor cycles + +**Called by Verify Mode**: +- `/workflow:tools:tdd-coverage-analysis` - Phase 7: Test coverage and cycle analysis + +**Follow-up Skills**: +- `/workflow:tdd-verify` - Verify TDD compliance (can also invoke via verify mode) +- `/workflow:plan-verify` - Verify plan quality and dependencies +- `/workflow:status` - Review TDD task breakdown +- `Skill(skill="workflow-execute")` - Begin TDD implementation diff --git a/.claude/skills/workflow-tdd/phases/01-session-discovery.md b/.claude/skills/workflow-tdd/phases/01-session-discovery.md new file mode 100644 index 00000000..45bb9c33 --- /dev/null +++ b/.claude/skills/workflow-tdd/phases/01-session-discovery.md @@ -0,0 +1,57 @@ +# Phase 1: Session Discovery + +Create or discover TDD workflow session and extract session ID. + +## Objective + +- Create a new TDD workflow session via `/workflow:session:start` +- Extract session ID for subsequent phases + +## Execution + +### Step 1.1: Execute Session Start + +```javascript +Skill(skill="workflow:session:start", args="--type tdd --auto \"TDD: [structured-description]\"") +``` + +**TDD Structured Format**: +``` +TDD: [Feature Name] +GOAL: [Objective] +SCOPE: [Included/excluded] +CONTEXT: [Background] +TEST_FOCUS: [Test scenarios] +``` + +**Example**: +``` +TDD: JWT Authentication +GOAL: Implement JWT-based authentication +SCOPE: Email/password login, token generation, token refresh endpoints +CONTEXT: Existing user database schema, REST API +TEST_FOCUS: Login flow, token validation, refresh rotation, error cases +``` + +### Step 1.2: Parse Output + +- Extract: `SESSION_ID: WFS-[id]` (store as `sessionId`) + +**Validation**: +- Session ID successfully extracted +- Session directory `.workflow/active/[sessionId]/` exists + +**Note**: Session directory contains `workflow-session.json` (metadata). Do NOT look for `manifest.json` here - it only exists in `.workflow/archives/` for archived sessions. + +**TodoWrite**: Mark phase 1 completed, phase 2 in_progress + +**After Phase 1**: Return to user showing Phase 1 results, then auto-continue to Phase 2 + +## Output + +- **Variable**: `sessionId` (WFS-xxx) +- **TodoWrite**: Mark Phase 1 completed, Phase 2 in_progress + +## Next Phase + +Return to orchestrator, then auto-continue to [Phase 2: Context Gathering](02-context-gathering.md). diff --git a/.claude/skills/workflow-tdd/phases/02-context-gathering.md b/.claude/skills/workflow-tdd/phases/02-context-gathering.md new file mode 100644 index 00000000..23d2b4df --- /dev/null +++ b/.claude/skills/workflow-tdd/phases/02-context-gathering.md @@ -0,0 +1,53 @@ +# Phase 2: Context Gathering + +Gather project context and analyze codebase for TDD planning. + +## Objective + +- Gather project context via context-search agents +- Generate context-package.json with codebase analysis +- Extract conflictRisk to determine Phase 4 execution + +## Execution + +### Step 2.1: Execute Context Gathering + +```javascript +Skill(skill="workflow:tools:context-gather", args="--session [sessionId] \"TDD: [structured-description]\"") +``` + +**Use Same Structured Description**: Pass the same structured format from Phase 1. + +**Input**: `sessionId` from Phase 1 + +### Step 2.2: Parse Output + +- Extract: context-package.json path (store as `contextPath`) +- Typical pattern: `.workflow/active/[sessionId]/.process/context-package.json` + +**Validation**: +- Context package path extracted +- File exists and is valid JSON + +### Step 2.3: Extract conflictRisk + +```javascript +const contextPackage = Read(contextPath) +const conflictRisk = contextPackage.conflict_risk // "none" | "low" | "medium" | "high" +``` + +**Note**: conflictRisk determines whether Phase 4 (Conflict Resolution) will execute. + +**TodoWrite**: Mark phase 2 completed, phase 3 in_progress + +**After Phase 2**: Return to user showing Phase 2 results, then auto-continue to Phase 3 + +## Output + +- **Variable**: `contextPath` (path to context-package.json) +- **Variable**: `conflictRisk` ("none" | "low" | "medium" | "high") +- **TodoWrite**: Mark Phase 2 completed, Phase 3 in_progress + +## Next Phase + +Return to orchestrator, then auto-continue to [Phase 3: Test Coverage Analysis](03-test-coverage-analysis.md). diff --git a/.claude/skills/workflow-tdd/phases/03-test-coverage-analysis.md b/.claude/skills/workflow-tdd/phases/03-test-coverage-analysis.md new file mode 100644 index 00000000..1fb799cd --- /dev/null +++ b/.claude/skills/workflow-tdd/phases/03-test-coverage-analysis.md @@ -0,0 +1,78 @@ +# Phase 3: Test Coverage Analysis + +Analyze existing test coverage, detect test framework, and identify coverage gaps. + +## Objective + +- Analyze existing codebase for test patterns and conventions +- Detect current test coverage and framework +- Identify related components and integration points +- Generate test-context-package.json + +## Execution + +### Step 3.1: Execute Test Context Gathering + +```javascript +Skill(skill="workflow:tools:test-context-gather", args="--session [sessionId]") +``` + +**Purpose**: Analyze existing codebase for: +- Existing test patterns and conventions +- Current test coverage +- Related components and integration points +- Test framework detection + +### Step 3.2: Parse Output + +- Extract: testContextPath (`.workflow/active/[sessionId]/.process/test-context-package.json`) + +**Validation**: +- test-context-package.json exists and is valid JSON +- Contains framework detection results + +### TodoWrite Update (Phase 3 Skill executed - tasks attached) + +```json +[ + {"content": "Phase 1: Session Discovery", "status": "completed", "activeForm": "Executing session discovery"}, + {"content": "Phase 2: Context Gathering", "status": "completed", "activeForm": "Executing context gathering"}, + {"content": "Phase 3: Test Coverage Analysis", "status": "in_progress", "activeForm": "Executing test coverage analysis"}, + {"content": " → Detect test framework and conventions", "status": "in_progress", "activeForm": "Detecting test framework"}, + {"content": " → Analyze existing test coverage", "status": "pending", "activeForm": "Analyzing test coverage"}, + {"content": " → Identify coverage gaps", "status": "pending", "activeForm": "Identifying coverage gaps"}, + {"content": "Phase 5: TDD Task Generation", "status": "pending", "activeForm": "Executing TDD task generation"}, + {"content": "Phase 6: TDD Structure Validation", "status": "pending", "activeForm": "Validating TDD structure"} +] +``` + +**Note**: Skill execute **attaches** test-context-gather's 3 tasks. Orchestrator **executes** these tasks. + +**Next Action**: Tasks attached → **Execute Phase 3.1-3.3** sequentially + +### TodoWrite Update (Phase 3 completed - tasks collapsed) + +```json +[ + {"content": "Phase 1: Session Discovery", "status": "completed", "activeForm": "Executing session discovery"}, + {"content": "Phase 2: Context Gathering", "status": "completed", "activeForm": "Executing context gathering"}, + {"content": "Phase 3: Test Coverage Analysis", "status": "completed", "activeForm": "Executing test coverage analysis"}, + {"content": "Phase 5: TDD Task Generation", "status": "pending", "activeForm": "Executing TDD task generation"}, + {"content": "Phase 6: TDD Structure Validation", "status": "pending", "activeForm": "Validating TDD structure"} +] +``` + +**Note**: Phase 3 tasks completed and collapsed to summary. + +**After Phase 3**: Return to user showing test coverage results, then auto-continue to Phase 4/5 (depending on conflict_risk) + +## Output + +- **Variable**: `testContextPath` (path to test-context-package.json) +- **TodoWrite**: Mark Phase 3 completed + +## Next Phase + +Based on `conflictRisk` from Phase 2: +- If conflictRisk ≥ medium → [Phase 4: Conflict Resolution](04-conflict-resolution.md) +- If conflictRisk < medium → Skip to [Phase 5: TDD Task Generation](05-tdd-task-generation.md) diff --git a/.claude/skills/workflow-tdd/phases/04-conflict-resolution.md b/.claude/skills/workflow-tdd/phases/04-conflict-resolution.md new file mode 100644 index 00000000..e15ef286 --- /dev/null +++ b/.claude/skills/workflow-tdd/phases/04-conflict-resolution.md @@ -0,0 +1,95 @@ +# Phase 4: Conflict Resolution (Conditional) + +Detect and resolve conflicts when conflict risk is medium or high. + +## Objective + +- Execute conflict detection and resolution only when conflictRisk ≥ medium +- Generate conflict-resolution.json with resolution strategies +- Skip directly to Phase 5 if conflictRisk is none/low + +## Trigger Condition + +**Only execute when**: `context-package.json` indicates `conflict_risk` is "medium" or "high" + +**Skip Behavior**: If conflict_risk is "none" or "low", skip directly to Phase 5. Display: "No significant conflicts detected, proceeding to TDD task generation" + +## Execution + +### Step 4.1: Execute Conflict Resolution + +```javascript +Skill(skill="workflow:tools:conflict-resolution", args="--session [sessionId] --context [contextPath]") +``` + +**Input**: +- sessionId from Phase 1 +- contextPath from Phase 2 +- conflict_risk from context-package.json + +### Step 4.2: Parse Output + +- Extract: Execution status (success/skipped/failed) +- Verify: conflict-resolution.json file path (if executed) + +**Validation**: +- File `.workflow/active/[sessionId]/.process/conflict-resolution.json` exists (if executed) + +### TodoWrite Update (Phase 4 Skill executed - tasks attached, if conflict_risk ≥ medium) + +```json +[ + {"content": "Phase 1: Session Discovery", "status": "completed", "activeForm": "Executing session discovery"}, + {"content": "Phase 2: Context Gathering", "status": "completed", "activeForm": "Executing context gathering"}, + {"content": "Phase 3: Test Coverage Analysis", "status": "completed", "activeForm": "Executing test coverage analysis"}, + {"content": "Phase 4: Conflict Resolution", "status": "in_progress", "activeForm": "Executing conflict resolution"}, + {"content": " → Detect conflicts with CLI analysis", "status": "in_progress", "activeForm": "Detecting conflicts"}, + {"content": " → Log and analyze detected conflicts", "status": "pending", "activeForm": "Analyzing conflicts"}, + {"content": " → Apply resolution strategies", "status": "pending", "activeForm": "Applying resolution strategies"}, + {"content": "Phase 5: TDD Task Generation", "status": "pending", "activeForm": "Executing TDD task generation"}, + {"content": "Phase 6: TDD Structure Validation", "status": "pending", "activeForm": "Validating TDD structure"} +] +``` + +**Note**: Skill execute **attaches** conflict-resolution's 3 tasks. Orchestrator **executes** these tasks. + +**Next Action**: Tasks attached → **Execute Phase 4.1-4.3** sequentially + +### TodoWrite Update (Phase 4 completed - tasks collapsed) + +```json +[ + {"content": "Phase 1: Session Discovery", "status": "completed", "activeForm": "Executing session discovery"}, + {"content": "Phase 2: Context Gathering", "status": "completed", "activeForm": "Executing context gathering"}, + {"content": "Phase 3: Test Coverage Analysis", "status": "completed", "activeForm": "Executing test coverage analysis"}, + {"content": "Phase 4: Conflict Resolution", "status": "completed", "activeForm": "Executing conflict resolution"}, + {"content": "Phase 5: TDD Task Generation", "status": "pending", "activeForm": "Executing TDD task generation"}, + {"content": "Phase 6: TDD Structure Validation", "status": "pending", "activeForm": "Validating TDD structure"} +] +``` + +**Note**: Phase 4 tasks completed and collapsed to summary. + +**After Phase 4**: Return to user showing conflict resolution results and selected strategies, then auto-continue to Phase 5 + +### Memory State Check + +After Phase 4, evaluate current context window usage and memory state: +- If memory usage is high (>110K tokens or approaching context limits): + + ```javascript + Skill(skill="compact") + ``` + + - This optimizes memory before proceeding to Phase 5 +- Memory compaction is particularly important after analysis phase which may generate extensive documentation +- Ensures optimal performance and prevents context overflow + +## Output + +- **File**: `.workflow/active/[sessionId]/.process/conflict-resolution.json` (if executed) +- **TodoWrite**: Mark Phase 4 completed, Phase 5 in_progress + +## Next Phase + +Return to orchestrator, then auto-continue to [Phase 5: TDD Task Generation](05-tdd-task-generation.md). diff --git a/.claude/skills/workflow-tdd/phases/05-tdd-task-generation.md b/.claude/skills/workflow-tdd/phases/05-tdd-task-generation.md new file mode 100644 index 00000000..23526a13 --- /dev/null +++ b/.claude/skills/workflow-tdd/phases/05-tdd-task-generation.md @@ -0,0 +1,105 @@ +# Phase 5: TDD Task Generation + +Generate TDD tasks with Red-Green-Refactor cycles via action-planning-agent. + +## Objective + +- Generate IMPL_PLAN.md, task JSONs, and TODO_LIST.md with TDD structure +- Each task contains internal Red-Green-Refactor cycle +- Include Phase 0 user configuration (execution method, CLI tool preference) + +## Execution + +### Step 5.1: Execute TDD Task Generation + +```javascript +Skill(skill="workflow:tools:task-generate-tdd", args="--session [sessionId]") +``` + +**Note**: Phase 0 now includes: +- Supplementary materials collection (file paths or inline content) +- Execution method preference (Agent/Hybrid/CLI) +- CLI tool preference (Codex/Gemini/Qwen/Auto) +- These preferences are passed to agent for task generation + +**CLI Tool Selection**: CLI tool usage is determined semantically from user's task description. Include "use Codex/Gemini/Qwen" in your request for CLI execution. + +### Step 5.2: Parse Output + +Extract: feature count, task count, CLI execution IDs assigned + +### Step 5.3: Validate Outputs + +- `plan.json` exists (structured plan overview with `_metadata.plan_type: "tdd"`) +- `IMPL_PLAN.md` exists (unified plan with TDD Implementation Tasks section) +- `IMPL-*.json` files exist (one per feature, or container + subtasks for complex features) +- `TODO_LIST.md` exists with internal TDD phase indicators +- Each IMPL task includes: + - `meta.tdd_workflow: true` + - `cli_execution.id: {session_id}-{task_id}` + - `cli_execution: { "strategy": "new|resume|fork|merge_fork", ... }` + - `implementation` with exactly 3 steps (red/green/refactor) + - Green phase includes test-fix-cycle configuration + - `focus_paths`: absolute or clear relative paths (enhanced with exploration critical_files) + - `pre_analysis`: includes exploration integration_points analysis +- `IMPL_PLAN.md` contains `workflow_type: "tdd"` in frontmatter +- User configuration applied: + - If executionMethod == "cli" or "hybrid": command field added to steps + - CLI tool preference reflected in execution guidance +- Task count ≤18 (compliance with hard limit) + +### Red Flag Detection (Non-Blocking Warnings) + +- Task count >18: `⚠️ Task count exceeds hard limit - request re-scope` +- Missing cli_execution.id: `⚠️ Task lacks CLI execution ID for resume support` +- Missing test-fix-cycle: `⚠️ Green phase lacks auto-revert configuration` +- Generic task names: `⚠️ Vague task names suggest unclear TDD cycles` +- Missing focus_paths: `⚠️ Task lacks clear file scope for implementation` + +**Action**: Log warnings to `.workflow/active/[sessionId]/.process/tdd-warnings.log` (non-blocking) + +### TodoWrite Update (Phase 5 Skill executed - tasks attached) + +```json +[ + {"content": "Phase 1: Session Discovery", "status": "completed", "activeForm": "Executing session discovery"}, + {"content": "Phase 2: Context Gathering", "status": "completed", "activeForm": "Executing context gathering"}, + {"content": "Phase 3: Test Coverage Analysis", "status": "completed", "activeForm": "Executing test coverage analysis"}, + {"content": "Phase 5: TDD Task Generation", "status": "in_progress", "activeForm": "Executing TDD task generation"}, + {"content": " → Discovery - analyze TDD requirements", "status": "in_progress", "activeForm": "Analyzing TDD requirements"}, + {"content": " → Planning - design Red-Green-Refactor cycles", "status": "pending", "activeForm": "Designing TDD cycles"}, + {"content": " → Output - generate IMPL tasks with internal TDD phases", "status": "pending", "activeForm": "Generating TDD tasks"}, + {"content": "Phase 6: TDD Structure Validation", "status": "pending", "activeForm": "Validating TDD structure"} +] +``` + +**Note**: Skill execute **attaches** task-generate-tdd's 3 tasks. Orchestrator **executes** these tasks. Each generated IMPL task will contain internal Red-Green-Refactor cycle. + +**Next Action**: Tasks attached → **Execute Phase 5.1-5.3** sequentially + +### TodoWrite Update (Phase 5 completed - tasks collapsed) + +```json +[ + {"content": "Phase 1: Session Discovery", "status": "completed", "activeForm": "Executing session discovery"}, + {"content": "Phase 2: Context Gathering", "status": "completed", "activeForm": "Executing context gathering"}, + {"content": "Phase 3: Test Coverage Analysis", "status": "completed", "activeForm": "Executing test coverage analysis"}, + {"content": "Phase 5: TDD Task Generation", "status": "completed", "activeForm": "Executing TDD task generation"}, + {"content": "Phase 6: TDD Structure Validation", "status": "in_progress", "activeForm": "Validating TDD structure"} +] +``` + +**Note**: Phase 5 tasks completed and collapsed to summary. Each generated IMPL task contains complete Red-Green-Refactor cycle internally. + +## Output + +- **File**: `plan.json` (structured plan overview) +- **File**: `IMPL_PLAN.md` (unified plan with TDD Implementation Tasks section) +- **File**: `IMPL-*.json` (task JSONs with internal TDD cycles) +- **File**: `TODO_LIST.md` (task list with TDD phase indicators) +- **File**: `.process/tdd-warnings.log` (non-blocking warnings) +- **TodoWrite**: Mark Phase 5 completed, Phase 6 in_progress + +## Next Phase + +Return to orchestrator, then auto-continue to [Phase 6: TDD Structure Validation](06-tdd-structure-validation.md). diff --git a/.claude/skills/workflow-tdd/phases/06-tdd-structure-validation.md b/.claude/skills/workflow-tdd/phases/06-tdd-structure-validation.md new file mode 100644 index 00000000..7b661934 --- /dev/null +++ b/.claude/skills/workflow-tdd/phases/06-tdd-structure-validation.md @@ -0,0 +1,179 @@ +# Phase 6: TDD Structure Validation & Plan Confirmation + +Internal validation of TDD task structure and user decision gate for next steps. + +## Objective + +- Validate Red-Green-Refactor structure in all generated tasks +- Verify TDD compliance checkpoints +- Gather evidence before claiming completion +- Present Plan Confirmation Gate to user + +## Execution + +### Step 6.1: Internal Validation + +Validate each generated task contains complete TDD workflow: + +1. **Task structure validation**: + - `meta.tdd_workflow: true` in all IMPL tasks + - `cli_execution.id` present (format: {session_id}-{task_id}) + - `cli_execution` strategy assigned (new/resume/fork/merge_fork) + - `implementation` has exactly 3 steps + - Each step has correct `tdd_phase`: "red", "green", "refactor" + - `focus_paths` are absolute or clear relative paths + - `pre_analysis` includes exploration integration analysis + +2. **Dependency validation**: + - Sequential features: IMPL-N depends_on ["IMPL-(N-1)"] if needed + - Complex features: IMPL-N.M depends_on ["IMPL-N.(M-1)"] for subtasks + - CLI execution strategies correctly assigned based on dependency graph + +3. **Agent assignment**: All IMPL tasks use @code-developer + +4. **Test-fix cycle**: Green phase step includes test-fix-cycle logic with max_iterations + +5. **Task count**: Total tasks ≤18 (simple + subtasks hard limit) + +6. **User configuration**: + - Execution method choice reflected in task structure + - CLI tool preference documented in implementation guidance (if CLI selected) + +### Step 6.2: Red Flag Checklist + +From TDD best practices: +- [ ] No tasks skip Red phase (`tdd_phase: "red"` exists in step 1) +- [ ] Test files referenced in Red phase (explicit paths, not placeholders) +- [ ] Green phase has test-fix-cycle with `max_iterations` configured +- [ ] Refactor phase has clear completion criteria + +**Non-Compliance Warning Format**: +``` +⚠️ TDD Red Flag: [issue description] + Task: [IMPL-N] + Recommendation: [action to fix] +``` + +### Step 6.3: Evidence Gathering + +Before claiming completion, verify artifacts exist: + +```bash +# Verify session artifacts exist +ls -la .workflow/active/[sessionId]/{IMPL_PLAN.md,TODO_LIST.md} +ls -la .workflow/active/[sessionId]/.task/IMPL-*.json + +# Count generated artifacts +echo "IMPL tasks: $(ls .workflow/active/[sessionId]/.task/IMPL-*.json 2>/dev/null | wc -l)" + +# Sample task structure verification (first task) +jq '{id, tdd: .meta.tdd_workflow, cli_id: .cli_execution.id, phases: [.implementation[].tdd_phase]}' \ + "$(ls .workflow/active/[sessionId]/.task/IMPL-*.json | head -1)" +``` + +**Evidence Required Before Summary**: + +| Evidence Type | Verification Method | Pass Criteria | +|---------------|---------------------|---------------| +| File existence | `ls -la` artifacts | All files present | +| Task count | Count IMPL-*.json | Count matches claims (≤18) | +| TDD structure | jq sample extraction | Shows red/green/refactor + cli_execution.id | +| CLI execution IDs | jq extraction | All tasks have cli_execution.id assigned | +| Warning log | Check tdd-warnings.log | Logged (may be empty) | + +### Step 6.4: Plan Confirmation Gate + +Present user with action choices: + +```javascript +console.log(` +TDD Planning complete for session: ${sessionId} + +Features analyzed: [N] +Total tasks: [M] (1 task per simple feature + subtasks for complex features) + +Task breakdown: +- Simple features: [K] tasks (IMPL-1 to IMPL-K) +- Complex features: [L] features with [P] subtasks +- Total task count: [M] (within 18-task hard limit) + +Structure: +- IMPL-1: {Feature 1 Name} (Internal: Red → Green → Refactor) +- IMPL-2: {Feature 2 Name} (Internal: Red → Green → Refactor) +- IMPL-3: {Complex Feature} (Container) + - IMPL-3.1: {Sub-feature A} (Internal: Red → Green → Refactor) + - IMPL-3.2: {Sub-feature B} (Internal: Red → Green → Refactor) +[...] + +Plans generated: +- Unified Implementation Plan: .workflow/active/[sessionId]/IMPL_PLAN.md + (includes TDD Implementation Tasks section with workflow_type: "tdd") +- Task List: .workflow/active/[sessionId]/TODO_LIST.md + (with internal TDD phase indicators and CLI execution strategies) +- Task JSONs: .workflow/active/[sessionId]/.task/IMPL-*.json + (with cli_execution.id and execution strategies for resume support) + +TDD Configuration: +- Each task contains complete Red-Green-Refactor cycle +- Green phase includes test-fix cycle (max 3 iterations) +- Auto-revert on max iterations reached +- CLI execution strategies: new/resume/fork/merge_fork based on dependency graph + +User Configuration Applied: +- Execution Method: [agent|hybrid|cli] +- CLI Tool Preference: [codex|gemini|qwen|auto] +- Supplementary Materials: [included|none] +- Task generation follows cli-tools-usage.md guidelines + +⚠️ ACTION REQUIRED: Before execution, ensure you understand WHY each Red phase test is expected to fail. + This is crucial for valid TDD - if you don't know why the test fails, you can't verify it tests the right thing. +`); + +// Ask user for next action +const userChoice = AskUserQuestion({ + questions: [{ + question: "TDD Planning complete. What would you like to do next?", + header: "Next Action", + multiSelect: false, + options: [ + { + label: "Verify TDD Compliance (Recommended)", + description: "Run full TDD compliance verification to check task chain structure, coverage, and Red-Green-Refactor cycle quality." + }, + { + label: "Start Execution", + description: "Begin implementing TDD tasks immediately with Red-Green-Refactor cycles." + }, + { + label: "Review Status Only", + description: "View TDD task breakdown and session status without taking further action." + } + ] + }] +}); + +// Execute based on user choice +if (userChoice === "Verify TDD Compliance (Recommended)") { + // Route to Phase 7 (tdd-verify) within this skill + // Orchestrator reads phases/07-tdd-verify.md and executes +} else if (userChoice === "Start Execution") { + Skill(skill="workflow-execute", args="--session " + sessionId); +} else if (userChoice === "Review Status Only") { + Skill(skill="workflow:status", args="--session " + sessionId); +} +``` + +**Auto Mode (--yes)**: Auto-select "Verify TDD Compliance", then auto-continue to execute if quality gate is APPROVED. + +## Output + +- **Validation**: TDD structure verified +- **User Decision**: Route to Phase 7 / Execute / Review +- **TodoWrite**: Mark Phase 6 completed + +## Next Phase (Conditional) + +Based on user's plan confirmation choice: +- If "Verify" → [Phase 7: TDD Verification](07-tdd-verify.md) +- If "Execute" → Skill(skill="workflow-execute") +- If "Review" → External: /workflow:status diff --git a/.claude/commands/workflow/tdd-verify.md b/.claude/skills/workflow-tdd/phases/07-tdd-verify.md similarity index 60% rename from .claude/commands/workflow/tdd-verify.md rename to .claude/skills/workflow-tdd/phases/07-tdd-verify.md index 0acb8c9f..084db1c8 100644 --- a/.claude/commands/workflow/tdd-verify.md +++ b/.claude/skills/workflow-tdd/phases/07-tdd-verify.md @@ -1,82 +1,28 @@ ---- -name: tdd-verify -description: Verify TDD workflow compliance against Red-Green-Refactor cycles. Generates quality report with coverage analysis and quality gate recommendation. Orchestrates sub-commands for comprehensive validation. -argument-hint: "[optional: --session WFS-session-id]" -allowed-tools: Skill(*), TodoWrite(*), Read(*), Write(*), Bash(*), Glob(*) ---- +# Phase 7: TDD Verification -# TDD Verification Command (/workflow:tdd-verify) +Full TDD compliance verification with quality gate reporting. Generates comprehensive TDD_COMPLIANCE_REPORT.md. -## Goal +## Objective -Verify TDD workflow execution quality by validating Red-Green-Refactor cycle compliance, test coverage completeness, and task chain structure integrity. This command orchestrates multiple analysis phases and generates a comprehensive compliance report with quality gate recommendation. - -**Output**: A structured Markdown report saved to `.workflow/active/WFS-{session}/TDD_COMPLIANCE_REPORT.md` containing: -- Executive summary with compliance score and quality gate recommendation -- Task chain validation (TEST → IMPL → REFACTOR structure) -- Test coverage metrics (line, branch, function) -- Red-Green-Refactor cycle verification -- Best practices adherence assessment -- Actionable improvement recommendations +- Verify TDD task chain structure (TEST → IMPL → REFACTOR or internal Red-Green-Refactor) +- Analyze test coverage metrics +- Validate TDD cycle execution quality +- Generate compliance report with quality gate recommendation ## Operating Constraints **ORCHESTRATOR MODE**: -- This command coordinates multiple sub-commands (`/workflow:tools:tdd-coverage-analysis`, `ccw cli`) +- This phase coordinates sub-steps and `/workflow:tools:tdd-coverage-analysis` - MAY write output files: TDD_COMPLIANCE_REPORT.md (primary report), .process/*.json (intermediate artifacts) - MUST NOT modify source task files or implementation code - MUST NOT create or delete tasks in the workflow **Quality Gate Authority**: The compliance report provides a binding recommendation (BLOCK_MERGE / REQUIRE_FIXES / PROCEED_WITH_CAVEATS / APPROVED) based on objective compliance criteria. -## Coordinator Role +## 4-Step Execution -**This command is a pure orchestrator**: Execute 4 phases to verify TDD workflow compliance, test coverage, and Red-Green-Refactor cycle execution. +### Step 7.1: Session Discovery & Validation -## Core Responsibilities -- Verify TDD task chain structure (TEST → IMPL → REFACTOR) -- Analyze test coverage metrics -- Validate TDD cycle execution quality -- Generate compliance report with quality gate recommendation - -## Execution Process - -``` -Input Parsing: - └─ Decision (session argument): - ├─ --session provided → Use provided session - └─ No session → Auto-detect active session - -Phase 1: Session Discovery & Validation - ├─ Detect or validate session directory - ├─ Check required artifacts exist (.task/*.json, .summaries/*) - └─ ERROR if invalid or incomplete - -Phase 2: Task Chain Structure Validation - ├─ Load all task JSONs from .task/ - ├─ Validate TDD structure: TEST-N.M → IMPL-N.M → REFACTOR-N.M - ├─ Verify dependencies (depends_on) - ├─ Validate meta fields (tdd_phase, agent) - └─ Extract chain validation data - -Phase 3: Coverage & Cycle Analysis - ├─ Call: /workflow:tools:tdd-coverage-analysis - ├─ Parse: test-results.json, coverage-report.json, tdd-cycle-report.md - └─ Extract coverage metrics and TDD cycle verification - -Phase 4: Compliance Report Generation - ├─ Aggregate findings from Phases 1-3 - ├─ Calculate compliance score (0-100) - ├─ Determine quality gate recommendation - ├─ Generate TDD_COMPLIANCE_REPORT.md - └─ Display summary to user -``` - -## 4-Phase Execution - -### Phase 1: Session Discovery & Validation - -**Step 1.1: Detect Session** ```bash IF --session parameter provided: session_id = provided session @@ -99,7 +45,7 @@ summaries_dir = session_dir/.summaries process_dir = session_dir/.process ``` -**Step 1.2: Validate Required Artifacts** +**Validate Required Artifacts**: ```bash # Check task files exist task_files = Glob(task_dir/*.json) @@ -117,13 +63,11 @@ IF NOT summaries_exist: --- -### Phase 2: Task Chain Structure Validation +### Step 7.2: Task Chain Structure Validation -**Step 2.1: Load and Parse Task JSONs** +**Load and Parse Task JSONs**: ```bash # Single-pass JSON extraction using jq -validation_data = bash(""" -# Load all tasks and extract structured data cd '{session_dir}/.task' # Extract all task IDs @@ -140,16 +84,15 @@ meta_tdd=$(jq -r '.id + ":" + (.meta.tdd_phase // "missing")' *.json 2>/dev/null meta_agent=$(jq -r '.id + ":" + (.meta.agent // "missing")' *.json 2>/dev/null) # Output as JSON -jq -n --arg ids "$task_ids" \\ - --arg impl "$impl_deps" \\ - --arg refactor "$refactor_deps" \\ - --arg tdd "$meta_tdd" \\ - --arg agent "$meta_agent" \\ +jq -n --arg ids "$task_ids" \ + --arg impl "$impl_deps" \ + --arg refactor "$refactor_deps" \ + --arg tdd "$meta_tdd" \ + --arg agent "$meta_agent" \ '{ids: $ids, impl_deps: $impl, refactor_deps: $refactor, tdd: $tdd, agent: $agent}' -""") ``` -**Step 2.2: Validate TDD Chain Structure** +**Validate TDD Chain Structure**: ``` Parse validation_data JSON and validate: @@ -175,14 +118,14 @@ Calculate: --- -### Phase 3: Coverage & Cycle Analysis +### Step 7.3: Coverage & Cycle Analysis -**Step 3.1: Call Coverage Analysis Sub-command** -```bash +**Call Coverage Analysis Sub-command**: +```javascript Skill(skill="workflow:tools:tdd-coverage-analysis", args="--session {session_id}") ``` -**Step 3.2: Parse Output Files** +**Parse Output Files**: ```bash # Check required outputs exist IF NOT EXISTS(process_dir/test-results.json): @@ -204,7 +147,7 @@ ELSE: cycle_data = Read(process_dir/tdd-cycle-report.md) ``` -**Step 3.3: Extract Coverage Metrics** +**Extract Coverage Metrics**: ``` If coverage_data exists: - line_coverage_percent @@ -224,9 +167,9 @@ If cycle_data exists: --- -### Phase 4: Compliance Report Generation +### Step 7.4: Compliance Report Generation -**Step 4.1: Calculate Compliance Score** +**Calculate Compliance Score**: ``` Base Score: 100 points @@ -254,7 +197,7 @@ Coverage Quality: Final Score: Max(0, Base Score - Total Deductions) ``` -**Step 4.2: Determine Quality Gate** +**Determine Quality Gate**: ``` IF score >= 90 AND no_critical_violations: recommendation = "APPROVED" @@ -266,57 +209,7 @@ ELSE: recommendation = "BLOCK_MERGE" ``` -**Step 4.3: Generate Report** -```bash -report_content = Generate markdown report (see structure below) -report_path = "{session_dir}/TDD_COMPLIANCE_REPORT.md" -Write(report_path, report_content) -``` - -**Step 4.4: Display Summary to User** -```bash -echo "=== TDD Verification Complete ===" -echo "Session: {session_id}" -echo "Report: {report_path}" -echo "" -echo "Quality Gate: {recommendation}" -echo "Compliance Score: {score}/100" -echo "" -echo "Chain Validation: {chain_completeness_score}%" -echo "Line Coverage: {line_coverage}%" -echo "Branch Coverage: {branch_coverage}%" -echo "" -echo "Next: Review full report for detailed findings" -``` - -## TodoWrite Pattern (Optional) - -**Note**: As an orchestrator command, TodoWrite tracking is optional and primarily useful for long-running verification processes. For most cases, the 4-phase execution is fast enough that progress tracking adds noise without value. - -```javascript -// Only use TodoWrite for complex multi-session verification -// Skip for single-session verification -``` - -## Validation Logic - -### Chain Validation Algorithm -``` -1. Load all task JSONs from .workflow/active/{sessionId}/.task/ -2. Extract task IDs and group by feature number -3. For each feature: - - Check TEST-N.M exists - - Check IMPL-N.M exists - - Check REFACTOR-N.M exists (optional but recommended) - - Verify IMPL-N.M depends_on TEST-N.M - - Verify REFACTOR-N.M depends_on IMPL-N.M - - Verify meta.tdd_phase values - - Verify meta.agent assignments -4. Calculate chain completeness score -5. Report incomplete or invalid chains -``` - -### Quality Gate Criteria +**Quality Gate Criteria**: | Recommendation | Score Range | Critical Violations | Action | |----------------|-------------|---------------------|--------| @@ -331,62 +224,30 @@ echo "Next: Review full report for detailed findings" - Tests didn't pass after IMPL (Green phase violation) - Tests broke during REFACTOR (Refactor phase violation) -## Output Files -``` -.workflow/active/WFS-{session-id}/ -├── TDD_COMPLIANCE_REPORT.md # Comprehensive compliance report ⭐ -└── .process/ - ├── test-results.json # From tdd-coverage-analysis - ├── coverage-report.json # From tdd-coverage-analysis - └── tdd-cycle-report.md # From tdd-coverage-analysis +**Generate Report**: +```javascript +const report_content = generateComplianceReport(/* see template below */) +const report_path = `${session_dir}/TDD_COMPLIANCE_REPORT.md` +Write(report_path, report_content) ``` -## Error Handling +**Display Summary to User**: +``` +=== TDD Verification Complete === +Session: {session_id} +Report: {report_path} -### Session Discovery Errors -| Error | Cause | Resolution | -|-------|-------|------------| -| No active session | No WFS-* directories | Provide --session explicitly | -| Multiple active sessions | Multiple WFS-* directories | Provide --session explicitly | -| Session not found | Invalid session-id | Check available sessions | +Quality Gate: {recommendation} +Compliance Score: {score}/100 -### Validation Errors -| Error | Cause | Resolution | -|-------|-------|------------| -| Task files missing | Incomplete planning | Run /workflow:tdd-plan first | -| Invalid JSON | Corrupted task files | Regenerate tasks | -| Missing summaries | Tasks not executed | Execute tasks before verify | +Chain Validation: {chain_completeness_score}% +Line Coverage: {line_coverage}% +Branch Coverage: {branch_coverage}% -### Analysis Errors -| Error | Cause | Resolution | -|-------|-------|------------| -| Coverage tool missing | No test framework | Configure testing first | -| Tests fail to run | Code errors | Fix errors before verify | -| Sub-command fails | tdd-coverage-analysis error | Check sub-command logs | - -## Integration & Usage - -### Command Chain -- **Called After**: `/workflow:execute` (when TDD tasks completed) -- **Calls**: `/workflow:tools:tdd-coverage-analysis` -- **Related**: `/workflow:tdd-plan`, `/workflow:status` - -### Basic Usage -```bash -# Auto-detect active session -/workflow:tdd-verify - -# Specify session -/workflow:tdd-verify --session WFS-auth +Next: Review full report for detailed findings ``` -### When to Use -- After completing all TDD tasks in a workflow -- Before merging TDD workflow branch -- For TDD process quality assessment -- To identify missing TDD steps - -## TDD Compliance Report Structure +## TDD Compliance Report Template ```markdown # TDD Compliance Report - {Session ID} @@ -436,20 +297,6 @@ echo "Next: Review full report for detailed findings" | Green | IMPL-1.1 | ✅ Pass | Minimal implementation made test pass | | Refactor | REFACTOR-1.1 | ✅ Pass | Code improved, tests remained green | -### Feature 2: {Feature Name} -**Status**: ⚠️ Incomplete -**Chain**: TEST-2.1 → IMPL-2.1 (Missing REFACTOR-2.1) - -| Phase | Task | Status | Details | -|-------|------|--------|---------| -| Red | TEST-2.1 | ✅ Pass | Test created and failed | -| Green | IMPL-2.1 | ⚠️ Warning | Implementation seems over-engineered | -| Refactor | REFACTOR-2.1 | ❌ Missing | Task not completed | - -**Issues**: -- REFACTOR-2.1 task not completed (-10 points) -- IMPL-2.1 implementation exceeded minimal scope (-10 points) - ### Chain Validation Summary | Metric | Value | @@ -479,8 +326,7 @@ echo "Next: Review full report for detailed findings" | File | Lines | Issue | Priority | |------|-------|-------|----------| -| src/auth/service.ts | 45-52 | Uncovered error handling | HIGH | -| src/utils/parser.ts | 78-85 | Uncovered edge case | MEDIUM | +| {file} | {lines} | {issue} | {priority} | --- @@ -491,39 +337,25 @@ echo "Next: Review full report for detailed findings" - ✅ Compliant features: {list} - ❌ Non-compliant features: {list} -**Violations**: -- Feature 3: No evidence of initial test failure (-10 points) - ### Green Phase (Make Test Pass) - {N}/{total} implementations made tests pass ({percent}%) - ✅ Compliant features: {list} - ❌ Non-compliant features: {list} -**Violations**: -- Feature 2: Implementation over-engineered (-10 points) - ### Refactor Phase (Improve Quality) - {N}/{total} features completed refactoring ({percent}%) - ✅ Compliant features: {list} - ❌ Non-compliant features: {list} -**Violations**: -- Feature 2, 4: Refactoring step skipped (-20 points total) - --- ## Best Practices Assessment ### Strengths -- Clear test descriptions -- Good test coverage -- Consistent naming conventions -- Well-structured code +- {strengths} ### Areas for Improvement -- Some implementations over-engineered in Green phase -- Missing refactoring steps -- Test failure messages could be more descriptive +- {improvements} --- @@ -533,33 +365,26 @@ echo "Next: Review full report for detailed findings" {List of critical issues with impact and remediation} ### High Priority Issues ({count}) -{List of high priority issues with impact and remediation} +{List of high priority issues} ### Medium Priority Issues ({count}) -{List of medium priority issues with impact and remediation} +{List of medium priority issues} ### Low Priority Issues ({count}) -{List of low priority issues with impact and remediation} +{List of low priority issues} --- ## Recommendations ### Required Fixes (Before Merge) -1. Complete missing REFACTOR tasks (Features 2, 4) -2. Verify initial test failures for Feature 3 -3. Fix tests that broke during refactoring +1. {required fixes} ### Recommended Improvements -1. Simplify over-engineered implementations -2. Add edge case tests for Features 1, 3 -3. Improve test failure message clarity -4. Increase branch coverage to >85% +1. {recommended improvements} ### Optional Enhancements -1. Add more descriptive test names -2. Consider parameterized tests for similar scenarios -3. Document TDD process learnings +1. {optional enhancements} --- @@ -583,3 +408,54 @@ echo "Next: Review full report for detailed findings" **Report End** ``` +## Error Handling + +### Session Discovery Errors + +| Error | Cause | Resolution | +|-------|-------|------------| +| No active session | No WFS-* directories | Provide --session explicitly | +| Multiple active sessions | Multiple WFS-* directories | Provide --session explicitly | +| Session not found | Invalid session-id | Check available sessions | + +### Validation Errors + +| Error | Cause | Resolution | +|-------|-------|------------| +| Task files missing | Incomplete planning | Run /workflow:tdd-plan first | +| Invalid JSON | Corrupted task files | Regenerate tasks | +| Missing summaries | Tasks not executed | Execute tasks before verify | + +### Analysis Errors + +| Error | Cause | Resolution | +|-------|-------|------------| +| Coverage tool missing | No test framework | Configure testing first | +| Tests fail to run | Code errors | Fix errors before verify | +| Sub-command fails | tdd-coverage-analysis error | Check sub-command logs | + +## Output + +- **File**: `TDD_COMPLIANCE_REPORT.md` (comprehensive compliance report) +- **Files**: `.process/test-results.json`, `.process/coverage-report.json`, `.process/tdd-cycle-report.md` + +## Output Files Structure + +``` +.workflow/active/WFS-{session-id}/ +├── TDD_COMPLIANCE_REPORT.md # Comprehensive compliance report ⭐ +└── .process/ + ├── test-results.json # From tdd-coverage-analysis + ├── coverage-report.json # From tdd-coverage-analysis + └── tdd-cycle-report.md # From tdd-coverage-analysis +``` + +## Next Steps Decision Table + +| Situation | Recommended Command | Purpose | +|-----------|---------------------|---------| +| APPROVED | `/workflow:execute` | Start TDD implementation | +| PROCEED_WITH_CAVEATS | `/workflow:execute` | Start with noted caveats | +| REQUIRE_FIXES | Review report, refine tasks | Address issues before proceed | +| BLOCK_MERGE | `/workflow:replan` | Significant restructuring needed | +| After implementation | Re-run `/workflow:tdd-verify` | Verify post-execution compliance | diff --git a/.claude/skills/workflow-test-fix/SKILL.md b/.claude/skills/workflow-test-fix/SKILL.md index 01c636db..cf160195 100644 --- a/.claude/skills/workflow-test-fix/SKILL.md +++ b/.claude/skills/workflow-test-fix/SKILL.md @@ -6,7 +6,7 @@ allowed-tools: Skill, Task, AskUserQuestion, TaskCreate, TaskUpdate, TaskList, R # Workflow Test Fix -Unified test-fix orchestrator that combines **test planning generation** (Phase 1) with **iterative test-cycle execution** (Phase 2) into a single end-to-end pipeline. Creates test sessions with progressive L0-L3 test layers, generates test tasks, then executes them with adaptive fix cycles until pass rate >= 95% or max iterations reached. +Unified test-fix orchestrator that combines **test planning generation** (Phase 1-4) with **iterative test-cycle execution** (Phase 5) into a single end-to-end pipeline. Creates test sessions with progressive L0-L3 test layers, generates test tasks, then executes them with adaptive fix cycles until pass rate >= 95% or max iterations reached. ## Architecture Overview @@ -14,27 +14,29 @@ Unified test-fix orchestrator that combines **test planning generation** (Phase ┌───────────────────────────────────────────────────────────────────────────┐ │ Workflow Test Fix Orchestrator (SKILL.md) │ │ → Pure coordinator: Route entry point, track progress, pass context │ -│ → Two phases: Generation (Phase 1) + Execution (Phase 2) │ +│ → Five phases: Session → Context → Analysis → TaskGen → Execution │ └──────────────────────────────────┬────────────────────────────────────────┘ │ - ┌───────────────────────────┼────────────────────────────┐ - ↓ ↓ -┌──────────────────────┐ ┌──────────────────────┐ -│ Phase 1: Test Gen │ │ Phase 2: Test Cycle │ -│ (test-fix-gen) │─── testSessionId ───────→│ (test-cycle-execute)│ -│ │ │ │ -│ 1. Session Create │ │ 1. Discovery │ -│ 2. Context Gather │ │ 2. Initial Execute │ -│ 3. Test Analysis │ │ 3. Fix Loop │ -│ 4. Task Generation │ │ 4. Completion │ -│ 5. Summary │ │ │ -└──────────────────────┘ └──────────────────────┘ - sessionId pass_rate >= 95% - contextPath or max iterations - IMPL_PLAN.md - IMPL-*.json + ┌────────────┬────────────┬──────┴──────┬────────────┬────────────┐ + ↓ ↓ ↓ ↓ ↓ +┌──────────┐┌──────────┐┌──────────┐┌──────────┐ ┌──────────────┐ +│ Phase 1 ││ Phase 2 ││ Phase 3 ││ Phase 4 │ │ Phase 5 │ +│ Session ││ Context ││ Analysis ││ Task Gen │ │ Test Cycle │ +│ Start ││ Gather ││ Enhanced ││ Generate │ │ Execute │ +│ ││ ││ ││ │ │ │ +│ Input ││ Coverage ││ Gemini ││ IMPL_PLAN│ │ 1. Discovery│ +│ Detect + ││ or Code ││ L0-L3 ││ IMPL-* │ │ 2. Execute │ +│ Session ││ Scan ││ AI Issue ││ TODO_LIST│ │ 3. Fix Loop │ +│ Create ││ ││ ││ │ │ 4. Complete │ +└────┬─────┘└────┬─────┘└────┬─────┘└────┬─────┘ └──────────────┘ + │ │ │ │ ↑ + │testSessionId │ │ │ + └──→────────┘contextPath│ │ │ + └──→───────┘AnalysisRes│ │ + └──→──────┘ testSessionId │ + └──→──(Summary)──→┘ -Task Pipeline (generated in Phase 1, executed in Phase 2): +Task Pipeline (generated in Phase 4, executed in Phase 5): ┌──────────────┐ ┌─────────────────┐ ┌─────────────────┐ ┌──────────────┐ │ IMPL-001 │──→│ IMPL-001.3 │──→│ IMPL-001.5 │──→│ IMPL-002 │ │ Test Gen │ │ Code Validate │ │ Quality Gate │ │ Test & Fix │ @@ -47,7 +49,7 @@ Task Pipeline (generated in Phase 1, executed in Phase 2): 1. **Unified Pipeline**: Generation and execution are one continuous workflow - no manual handoff 2. **Pure Orchestrator**: SKILL.md coordinates only - delegates all execution detail to phase files -3. **Auto-Continue**: Phase 1 completes → Phase 2 starts automatically +3. **Auto-Continue**: Phase 1→2→3→4→(Summary)→5 automatically 4. **Task Attachment/Collapse**: Sub-tasks attached during phase execution, collapsed after completion 5. **Progressive Phase Loading**: Phase docs read **only** when that phase executes, not upfront 6. **Adaptive Strategy**: Fix loop auto-selects strategy (conservative/aggressive/surgical) based on iteration context @@ -75,21 +77,35 @@ When `--yes` or `-y`: Auto-select first active session, skip confirmations, auto ``` Entry Point Detection: - ├─ /workflow:test-fix-gen → Full Pipeline (Phase 1 → Phase 2) - └─ /workflow:test-cycle-execute → Execution Only (Phase 2) + ├─ /workflow:test-fix-gen → Full Pipeline (Phase 1→2→3→4→Summary→5) + └─ /workflow:test-cycle-execute → Execution Only (Phase 5) -Phase 1: Test Generation (test-fix-gen) - └─ Ref: phases/01-test-fix-gen.md - ├─ Step 1.1: Detect input mode (session | prompt) - ├─ Step 1.2: Create test session → testSessionId - ├─ Step 1.3: Gather test context → contextPath - ├─ Step 1.4: Test analysis (Gemini) → TEST_ANALYSIS_RESULTS.md - ├─ Step 1.5: Generate test tasks → IMPL_PLAN.md, IMPL-*.json, TODO_LIST.md +Phase 1: Session Start (session-start) + └─ Ref: phases/01-session-start.md + ├─ Step 1.0: Detect input mode (session | prompt) + ├─ Step 1.1: Create test session → testSessionId + └─ Output: testSessionId, MODE + +Phase 2: Test Context Gather (test-context-gather) + └─ Ref: phases/02-test-context-gather.md + ├─ Step 1.2: Gather test context → contextPath + └─ Output: contextPath + +Phase 3: Test Concept Enhanced (test-concept-enhanced) + └─ Ref: phases/03-test-concept-enhanced.md + ├─ Step 1.3: Test analysis (Gemini) → TEST_ANALYSIS_RESULTS.md + └─ Output: TEST_ANALYSIS_RESULTS.md + +Phase 4: Test Task Generate (test-task-generate) + └─ Ref: phases/04-test-task-generate.md + ├─ Step 1.4: Generate test tasks → IMPL_PLAN.md, IMPL-*.json, TODO_LIST.md └─ Output: testSessionId, 4+ task JSONs - → Auto-continue to Phase 2 -Phase 2: Test Cycle Execution (test-cycle-execute) - └─ Ref: phases/02-test-cycle-execute.md +Summary Output (inline after Phase 4): + └─ Display summary, auto-continue to Phase 5 + +Phase 5: Test Cycle Execution (test-cycle-execute) + └─ Ref: phases/05-test-cycle-execute.md ├─ Step 2.1: Discovery (load session, tasks, iteration state) ├─ Step 2.2: Execute initial tasks (IMPL-001 → 001.3 → 001.5 → 002) ├─ Step 2.3: Fix loop (if pass_rate < 95%) @@ -105,20 +121,23 @@ Phase 2: Test Cycle Execution (test-cycle-execute) | Phase | Document | Purpose | |-------|----------|---------| -| 1 | [phases/01-test-fix-gen.md](phases/01-test-fix-gen.md) | Create test session, gather context, analyze, generate tasks | -| 2 | [phases/02-test-cycle-execute.md](phases/02-test-cycle-execute.md) | Execute tasks, iterative fix cycles, completion | +| 1 | [phases/01-session-start.md](phases/01-session-start.md) | Detect input mode, create test session | +| 2 | [phases/02-test-context-gather.md](phases/02-test-context-gather.md) | Gather test context (coverage/codebase) | +| 3 | [phases/03-test-concept-enhanced.md](phases/03-test-concept-enhanced.md) | Gemini analysis, L0-L3 test requirements | +| 4 | [phases/04-test-task-generate.md](phases/04-test-task-generate.md) | Generate task JSONs and IMPL_PLAN.md | +| 5 | [phases/05-test-cycle-execute.md](phases/05-test-cycle-execute.md) | Execute tasks, iterative fix cycles, completion | ## Core Rules -1. **Start Immediately**: First action is TaskCreate initialization, second action is Phase 1 (or Phase 2 for execute-only entry) +1. **Start Immediately**: First action is TaskCreate initialization, second action is Phase 1 (or Phase 5 for execute-only entry) 2. **No Preliminary Analysis**: Do not read files or gather context before starting the phase 3. **Parse Every Output**: Extract required data from each step output for next step -4. **Auto-Continue**: Phase 1 → Phase 2 automatically (for full pipeline entry) +4. **Auto-Continue**: Phase 1→2→3→4→(Summary)→5 automatically (for full pipeline entry) 5. **Track Progress**: Update TaskCreate/TaskUpdate dynamically with task attachment/collapse pattern 6. **Task Attachment Model**: Sub-tasks **attached** during phase, **collapsed** after completion 7. **DO NOT STOP**: Continuous workflow until quality gate met or max iterations reached 8. **Progressive Loading**: Read phase doc ONLY when that phase is about to execute -9. **Entry Point Routing**: `/workflow:test-fix-gen` → Phase 1 + Phase 2; `/workflow:test-cycle-execute` → Phase 2 only +9. **Entry Point Routing**: `/workflow:test-fix-gen` → Phase 1-5; `/workflow:test-cycle-execute` → Phase 5 only ## Input Processing @@ -130,7 +149,7 @@ User input → Detect type: └─ Otherwise → MODE=prompt, description=input ``` -### test-cycle-execute Entry (Phase 2 Only) +### test-cycle-execute Entry (Phase 5 Only) ``` Arguments → Parse flags: ├─ --resume-session="WFS-xxx" → sessionId=WFS-xxx @@ -145,20 +164,60 @@ User Input (session ID | description | file path) ↓ [Detect Mode: session | prompt] ↓ -Phase 1: Test Generation ───────────────────────────────────────── - ↓ 1.1: session:start → testSessionId - ↓ 1.2: test-context-gather/context-gather → contextPath - ↓ 1.3: test-concept-enhanced → TEST_ANALYSIS_RESULTS.md - ↓ 1.4: test-task-generate → IMPL_PLAN.md, IMPL-*.json, TODO_LIST.md - ↓ 1.5: Summary with next step +Phase 1: Session Start ───────────────────────────────────────── + ↓ 1.0+1.1: session:start → testSessionId, MODE ↓ -Phase 2: Test Cycle Execution ──────────────────────────────────── +Phase 2: Test Context Gather ──────────────────────────────────── + ↓ 1.2: test-context-gather/context-gather → contextPath + ↓ +Phase 3: Test Concept Enhanced ────────────────────────────────── + ↓ 1.3: test-concept-enhanced → TEST_ANALYSIS_RESULTS.md + ↓ +Phase 4: Test Task Generate ───────────────────────────────────── + ↓ 1.4: test-task-generate → IMPL_PLAN.md, IMPL-*.json, TODO_LIST.md + ↓ +Summary Output (inline) ───────────────────────────────────────── + ↓ Display summary with next step + ↓ +Phase 5: Test Cycle Execution ─────────────────────────────────── ↓ 2.1: Load session + tasks + iteration state ↓ 2.2: Execute IMPL-001 → 001.3 → 001.5 → 002 ↓ 2.3: Fix loop (analyze → fix → retest) until pass_rate >= 95% ↓ 2.4: Completion → summary → session archive ``` +## Summary Output (after Phase 4) + +After Phase 4 completes, display the following summary before auto-continuing to Phase 5: + +``` +Test-fix workflow created successfully! + +Input: [original input] +Mode: [Session|Prompt] +Test Session: [testSessionId] + +Tasks Created: +- IMPL-001: Test Understanding & Generation (@code-developer) +- IMPL-001.3: Code Validation Gate - AI Error Detection (@test-fix-agent) +- IMPL-001.5: Test Quality Gate - Static Analysis & Coverage (@test-fix-agent) +- IMPL-002: Test Execution & Fix Cycle (@test-fix-agent) + +Quality Thresholds: +- Code Validation: Zero CRITICAL issues, zero compilation errors +- Minimum Coverage: 80% line, 70% branch +- Static Analysis: Zero critical anti-patterns +- Max Fix Iterations: 5 + +Review artifacts: +- Test plan: .workflow/[testSessionId]/IMPL_PLAN.md +- Task list: .workflow/[testSessionId]/TODO_LIST.md +- Analysis: .workflow/[testSessionId]/.process/TEST_ANALYSIS_RESULTS.md +``` + +**CRITICAL - Next Step**: Auto-continue to Phase 5: Test Cycle Execution. +Pass `testSessionId` to Phase 5 for test execution pipeline. Do NOT wait for user confirmation — the unified pipeline continues automatically. + ## Test Strategy Overview Progressive Test Layers (L0-L3): @@ -177,7 +236,7 @@ Progressive Test Layers (L0-L3): - Pass Rate Gate: >= 95% (criticality-aware) or 100% - Max Fix Iterations: 10 (default, adjustable) -## Strategy Engine (Phase 2) +## Strategy Engine (Phase 5) | Strategy | Trigger | Behavior | |----------|---------|----------| @@ -185,16 +244,16 @@ Progressive Test Layers (L0-L3): | **Aggressive** | Pass rate >80% + similar failures | Batch fix related issues | | **Surgical** | Regression detected (pass rate drops >10%) | Minimal changes, rollback focus | -Selection logic and CLI fallback chain (Gemini → Qwen → Codex) are detailed in Phase 2. +Selection logic and CLI fallback chain (Gemini → Qwen → Codex) are detailed in Phase 5. ## Agent Roles | Agent | Used In | Responsibility | |-------|---------|---------------| -| **Orchestrator** | Both phases | Route entry, track progress, pass context | -| **@code-developer** | Phase 2 (IMPL-001) | Test generation (L1-L3) | -| **@test-fix-agent** | Phase 2 | Test execution, code fixes, criticality assignment | -| **@cli-planning-agent** | Phase 2 (fix loop) | CLI analysis, root cause extraction, fix task generation | +| **Orchestrator** | All phases | Route entry, track progress, pass context | +| **@code-developer** | Phase 5 (IMPL-001) | Test generation (L1-L3) | +| **@test-fix-agent** | Phase 5 | Test execution, code fixes, criticality assignment | +| **@cli-planning-agent** | Phase 5 (fix loop) | CLI analysis, root cause extraction, fix task generation | ## TodoWrite Pattern @@ -206,25 +265,27 @@ Selection logic and CLI fallback chain (Gemini → Qwen → Codex) are detailed > - Sub-task attachment → `TaskCreate` + `TaskUpdate({ addBlockedBy })` > - Sub-task collapse → `TaskUpdate({ status: "completed" })` + `TaskUpdate({ status: "deleted" })` for collapsed sub-items -### Full Pipeline (Phase 1 + Phase 2) +### Full Pipeline (Phase 1-5) ```json [ - {"content": "Phase 1: Test Generation", "status": "in_progress"}, - {"content": " → Create test session", "status": "in_progress"}, - {"content": " → Gather test context", "status": "pending"}, - {"content": " → Test analysis (Gemini)", "status": "pending"}, - {"content": " → Generate test tasks", "status": "pending"}, - {"content": "Phase 2: Test Cycle Execution", "status": "pending"} + {"content": "Phase 1: Session Start", "status": "in_progress"}, + {"content": "Phase 2: Test Context Gather", "status": "pending"}, + {"content": "Phase 3: Test Analysis (Gemini)", "status": "pending"}, + {"content": "Phase 4: Test Task Generate", "status": "pending"}, + {"content": "Phase 5: Test Cycle Execution", "status": "pending"} ] ``` -### Phase 1 Collapsed → Phase 2 Active +### Phase 1-4 Collapsed → Phase 5 Active ```json [ - {"content": "Phase 1: Test Generation", "status": "completed"}, - {"content": "Phase 2: Test Cycle Execution", "status": "in_progress"}, + {"content": "Phase 1: Session Start", "status": "completed"}, + {"content": "Phase 2: Test Context Gather", "status": "completed"}, + {"content": "Phase 3: Test Analysis (Gemini)", "status": "completed"}, + {"content": "Phase 4: Test Task Generate", "status": "completed"}, + {"content": "Phase 5: Test Cycle Execution", "status": "in_progress"}, {"content": " → Execute IMPL-001 [code-developer]", "status": "in_progress"}, {"content": " → Execute IMPL-001.3 [test-fix-agent]", "status": "pending"}, {"content": " → Execute IMPL-001.5 [test-fix-agent]", "status": "pending"}, @@ -237,8 +298,8 @@ Selection logic and CLI fallback chain (Gemini → Qwen → Codex) are detailed ```json [ - {"content": "Phase 1: Test Generation", "status": "completed"}, - {"content": "Phase 2: Test Cycle Execution", "status": "in_progress"}, + {"content": "Phase 1-4: Test Generation", "status": "completed"}, + {"content": "Phase 5: Test Cycle Execution", "status": "in_progress"}, {"content": " → Initial tasks", "status": "completed"}, {"content": " → Iteration 1: Initial test (pass: 70%, conservative)", "status": "completed"}, {"content": " → Iteration 2: Fix validation (pass: 82%, conservative)", "status": "completed"}, @@ -258,7 +319,7 @@ Selection logic and CLI fallback chain (Gemini → Qwen → Codex) are detailed │ ├── IMPL-001.3-validation.json # Code validation gate │ ├── IMPL-001.5-review.json # Test quality gate │ ├── IMPL-002.json # Test execution & fix cycle -│ └── IMPL-fix-{N}.json # Generated fix tasks (Phase 2 fix loop) +│ └── IMPL-fix-{N}.json # Generated fix tasks (Phase 5 fix loop) ├── .process/ │ ├── [test-]context-package.json # Context and coverage analysis │ ├── TEST_ANALYSIS_RESULTS.md # Test requirements (L0-L3) @@ -274,17 +335,17 @@ Selection logic and CLI fallback chain (Gemini → Qwen → Codex) are detailed ## Error Handling -### Phase 1 (Generation) +### Phase 1-4 (Generation) -| Step | Error Condition | Action | -|------|----------------|--------| -| Session create | Source session not found (session mode) | Return error with session ID | -| Session create | No completed IMPL tasks (session mode) | Return error, source incomplete | -| Context gather | Context gathering failed | Return error, check source artifacts | -| Analysis | Gemini analysis failed | Return error, check context package | -| Task gen | Task generation failed | Retry once, then return error | +| Phase | Error Condition | Action | +|-------|----------------|--------| +| 1: Session Start | Source session not found (session mode) | Return error with session ID | +| 1: Session Start | No completed IMPL tasks (session mode) | Return error, source incomplete | +| 2: Context Gather | Context gathering failed | Return error, check source artifacts | +| 3: Analysis | Gemini analysis failed | Return error, check context package | +| 4: Task Gen | Task generation failed | Retry once, then return error | -### Phase 2 (Execution) +### Phase 5 (Execution) | Scenario | Action | |----------|--------| @@ -295,7 +356,7 @@ Selection logic and CLI fallback chain (Gemini → Qwen → Codex) are detailed | Regression detected | Rollback last fix, switch to surgical strategy | | Stuck tests detected | Continue with alternative strategy, document | -## Commit Strategy (Phase 2) +## Commit Strategy (Phase 5) Automatic commits at key checkpoints: 1. **After successful iteration** (pass rate increased): `test-cycle: iteration N - strategy (pass: old% → new%)` @@ -315,16 +376,28 @@ After completion, ask user if they want to expand into issues (test/enhance/refa ## Coordinator Checklist -### Phase 1 (test-fix-gen) +### Phase 1 (session-start) - [ ] Detect input type (session ID / description / file path) - [ ] Initialize TaskCreate before any execution -- [ ] Read Phase 1 doc, execute all 5 internal steps +- [ ] Read Phase 1 doc, execute Steps 1.0 + 1.1 - [ ] Parse testSessionId from step output, store in memory -- [ ] Verify all Phase 1 outputs (4 task JSONs, IMPL_PLAN.md, TODO_LIST.md) -- [ ] Collapse Phase 1 tasks, auto-continue to Phase 2 -### Phase 2 (test-cycle-execute) -- [ ] Read Phase 2 doc +### Phase 2 (test-context-gather) +- [ ] Read Phase 2 doc, execute Step 1.2 +- [ ] Parse contextPath from step output, store in memory + +### Phase 3 (test-concept-enhanced) +- [ ] Read Phase 3 doc, execute Step 1.3 +- [ ] Verify TEST_ANALYSIS_RESULTS.md created + +### Phase 4 (test-task-generate) +- [ ] Read Phase 4 doc, execute Step 1.4 +- [ ] Verify all Phase 1-4 outputs (4 task JSONs, IMPL_PLAN.md, TODO_LIST.md) +- [ ] Display Summary output (inline) +- [ ] Collapse Phase 1-4 tasks, auto-continue to Phase 5 + +### Phase 5 (test-cycle-execute) +- [ ] Read Phase 5 doc - [ ] Load session, tasks, iteration state - [ ] Execute initial tasks sequentially - [ ] Calculate pass rate from test-results.json @@ -340,14 +413,6 @@ After completion, ask user if they want to expand into issues (test/enhance/refa - `/workflow:plan` or `/workflow:execute` - Complete implementation (Session Mode source) - None for Prompt Mode -**Called During Execution**: -- `/workflow:session:start` - Phase 1: Create test session -- `/workflow:tools:test-context-gather` - Phase 1 (Session Mode) -- `/workflow:tools:context-gather` - Phase 1 (Prompt Mode) -- `/workflow:tools:test-concept-enhanced` - Phase 1: Gemini analysis -- `/workflow:tools:test-task-generate` - Phase 1: Task generation -- `/workflow:session:complete` - Phase 2: Archive session - **Follow-up Skills**: - `/workflow:status` - Review workflow state - `/workflow:review` - Post-implementation review diff --git a/.claude/skills/workflow-test-fix/phases/01-session-start.md b/.claude/skills/workflow-test-fix/phases/01-session-start.md new file mode 100644 index 00000000..e46dc03f --- /dev/null +++ b/.claude/skills/workflow-test-fix/phases/01-session-start.md @@ -0,0 +1,60 @@ +# Phase 1: Session Start (session-start) + +Detect input mode and create test workflow session. + +## Objective + +- Detect input mode (session ID vs description) +- Create test workflow session with appropriate metadata + +## Execution + +### Step 1.0: Detect Input Mode + +``` +// Automatic mode detection based on input pattern +if (input.startsWith("WFS-")) { + MODE = "session" + // Load source session to preserve original task description + Read(".workflow/active/[sourceSessionId]/workflow-session.json") +} else { + MODE = "prompt" +} +``` + +### Step 1.1: Create Test Session + +``` +// Session Mode - preserve original task description +Skill(skill="workflow:session:start", args="--type test --new \"Test validation for [sourceSessionId]: [originalTaskDescription]\"") + +// Prompt Mode - use user's description directly +Skill(skill="workflow:session:start", args="--type test --new \"Test generation for: [description]\"") +``` + +**Parse Output**: +- Extract: `SESSION_ID: WFS-test-[slug]` (store as `testSessionId`) + +**Validation**: +- Session Mode: Source session `.workflow/active/[sourceSessionId]/` exists with completed IMPL tasks +- Both Modes: New test session directory created with metadata + +**TodoWrite**: Mark step 1.1 completed, step 1.2 in_progress + +### Session Metadata + +**File**: `workflow-session.json` + +| Mode | Fields | +|------|--------| +| **Session** | `type: "test"`, `source_session_id: "[sourceId]"` | +| **Prompt** | `type: "test"` (no source_session_id) | + +## Output + +- **Variable**: `testSessionId` (WFS-test-xxx) +- **Variable**: `MODE` (session | prompt) + +## Next Phase + +Continue to [Phase 2: Test Context Gather](02-test-context-gather.md). diff --git a/.claude/skills/workflow-test-fix/phases/01-test-fix-gen.md b/.claude/skills/workflow-test-fix/phases/01-test-fix-gen.md deleted file mode 100644 index 6621a7c8..00000000 --- a/.claude/skills/workflow-test-fix/phases/01-test-fix-gen.md +++ /dev/null @@ -1,309 +0,0 @@ -# Phase 1: Test Fix Generation (test-fix-gen) - -Create test-fix workflow session with progressive test layers (L0-L3), AI code validation, and test task generation. This phase runs 5 internal steps sequentially, calling existing sub-commands via Skill(). - -## Objective - -- Detect input mode (session ID vs description) -- Create test workflow session -- Gather test context (coverage analysis or codebase scan) -- Analyze test requirements with Gemini (L0-L3 layers) -- Generate test task JSONs via action-planning-agent - -## Test Strategy Overview - -This workflow generates tests using **Progressive Test Layers (L0-L3)**: - -| Layer | Name | Focus | -|-------|------|-------| -| **L0** | Static Analysis | Compilation, imports, types, AI code issues | -| **L1** | Unit Tests | Function/class behavior (happy/negative/edge cases) | -| **L2** | Integration Tests | Component interactions, API contracts, failure modes | -| **L3** | E2E Tests | User journeys, critical paths (optional) | - -**Key Features**: -- **AI Code Issue Detection** - Validates against common AI-generated code problems (hallucinated imports, placeholder code, mock leakage, etc.) -- **Project Type Detection** - Applies appropriate test templates (React, Node API, CLI, Library, etc.) -- **Quality Gates** - IMPL-001.3 (code validation) and IMPL-001.5 (test quality) ensure high standards - -**Detailed specifications**: See `/workflow:tools:test-task-generate` for complete L0-L3 requirements and quality thresholds. - -## Execution - -### Step 1.0: Detect Input Mode - -``` -// Automatic mode detection based on input pattern -if (input.startsWith("WFS-")) { - MODE = "session" - // Load source session to preserve original task description - Read(".workflow/active/[sourceSessionId]/workflow-session.json") -} else { - MODE = "prompt" -} -``` - -### Step 1.1: Create Test Session - -``` -// Session Mode - preserve original task description -Skill(skill="workflow:session:start", args="--type test --new \"Test validation for [sourceSessionId]: [originalTaskDescription]\"") - -// Prompt Mode - use user's description directly -Skill(skill="workflow:session:start", args="--type test --new \"Test generation for: [description]\"") -``` - -**Parse Output**: -- Extract: `SESSION_ID: WFS-test-[slug]` (store as `testSessionId`) - -**Validation**: -- Session Mode: Source session `.workflow/active/[sourceSessionId]/` exists with completed IMPL tasks -- Both Modes: New test session directory created with metadata - -**TodoWrite**: Mark step 1.1 completed, step 1.2 in_progress - -### Step 1.2: Gather Test Context - -``` -// Session Mode - gather from source session -Skill(skill="workflow:tools:test-context-gather", args="--session [testSessionId]") - -// Prompt Mode - gather from codebase -Skill(skill="workflow:tools:context-gather", args="--session [testSessionId] \"[task_description]\"") -``` - -**Input**: `testSessionId` from Step 1.1 - -**Parse Output**: -- Extract: context package path (store as `contextPath`) -- Pattern: `.workflow/active/[testSessionId]/.process/[test-]context-package.json` - -**Validation**: -- Context package file exists and is valid JSON -- Contains coverage analysis (session mode) or codebase analysis (prompt mode) -- Test framework detected - -**TodoWrite Update (tasks attached)**: -```json -[ - {"content": "Phase 1: Test Generation", "status": "in_progress"}, - {"content": " → Create test session", "status": "completed"}, - {"content": " → Gather test context", "status": "in_progress"}, - {"content": " → Load source/codebase context", "status": "in_progress"}, - {"content": " → Analyze test coverage", "status": "pending"}, - {"content": " → Generate context package", "status": "pending"}, - {"content": " → Test analysis (Gemini)", "status": "pending"}, - {"content": " → Generate test tasks", "status": "pending"}, - {"content": "Phase 2: Test Cycle Execution", "status": "pending"} -] -``` - -**TodoWrite Update (tasks collapsed)**: -```json -[ - {"content": "Phase 1: Test Generation", "status": "in_progress"}, - {"content": " → Create test session", "status": "completed"}, - {"content": " → Gather test context", "status": "completed"}, - {"content": " → Test analysis (Gemini)", "status": "pending"}, - {"content": " → Generate test tasks", "status": "pending"}, - {"content": "Phase 2: Test Cycle Execution", "status": "pending"} -] -``` - -### Step 1.3: Test Generation Analysis - -``` -Skill(skill="workflow:tools:test-concept-enhanced", args="--session [testSessionId] --context [contextPath]") -``` - -**Input**: -- `testSessionId` from Step 1.1 -- `contextPath` from Step 1.2 - -**Expected Behavior**: -- Use Gemini to analyze coverage gaps -- Detect project type and apply appropriate test templates -- Generate **multi-layered test requirements** (L0-L3) -- Scan for AI code issues -- Generate `TEST_ANALYSIS_RESULTS.md` - -**Output**: `.workflow/[testSessionId]/.process/TEST_ANALYSIS_RESULTS.md` - -**Validation** - TEST_ANALYSIS_RESULTS.md must include: -- Project Type Detection (with confidence) -- Coverage Assessment (current vs target) -- Test Framework & Conventions -- Multi-Layered Test Plan (L0-L3) -- AI Issue Scan Results -- Test Requirements by File (with layer annotations) -- Quality Assurance Criteria -- Success Criteria - -**Note**: Detailed specifications for project types, L0-L3 layers, and AI issue detection are defined in `/workflow:tools:test-concept-enhanced`. - -### Step 1.4: Generate Test Tasks - -``` -Skill(skill="workflow:tools:test-task-generate", args="--session [testSessionId]") -``` - -**Input**: `testSessionId` from Step 1.1 - -**Note**: test-task-generate invokes action-planning-agent to generate test-specific IMPL_PLAN.md and task JSONs based on TEST_ANALYSIS_RESULTS.md. - -**Expected Output** (minimum 4 tasks): - -| Task | Type | Agent | Purpose | -|------|------|-------|---------| -| IMPL-001 | test-gen | @code-developer | Test understanding & generation (L1-L3) | -| IMPL-001.3 | code-validation | @test-fix-agent | Code validation gate (L0 + AI issues) | -| IMPL-001.5 | test-quality-review | @test-fix-agent | Test quality gate | -| IMPL-002 | test-fix | @test-fix-agent | Test execution & fix cycle | - -**Validation**: -- `.workflow/active/[testSessionId]/.task/IMPL-001.json` exists -- `.workflow/active/[testSessionId]/.task/IMPL-001.3-validation.json` exists -- `.workflow/active/[testSessionId]/.task/IMPL-001.5-review.json` exists -- `.workflow/active/[testSessionId]/.task/IMPL-002.json` exists -- `.workflow/active/[testSessionId]/IMPL_PLAN.md` exists -- `.workflow/active/[testSessionId]/TODO_LIST.md` exists - -### Step 1.5: Return Summary - -**Return to Orchestrator**: -``` -Test-fix workflow created successfully! - -Input: [original input] -Mode: [Session|Prompt] -Test Session: [testSessionId] - -Tasks Created: -- IMPL-001: Test Understanding & Generation (@code-developer) -- IMPL-001.3: Code Validation Gate - AI Error Detection (@test-fix-agent) -- IMPL-001.5: Test Quality Gate - Static Analysis & Coverage (@test-fix-agent) -- IMPL-002: Test Execution & Fix Cycle (@test-fix-agent) - -Quality Thresholds: -- Code Validation: Zero CRITICAL issues, zero compilation errors -- Minimum Coverage: 80% line, 70% branch -- Static Analysis: Zero critical anti-patterns -- Max Fix Iterations: 5 - -Review artifacts: -- Test plan: .workflow/[testSessionId]/IMPL_PLAN.md -- Task list: .workflow/[testSessionId]/TODO_LIST.md -- Analysis: .workflow/[testSessionId]/.process/TEST_ANALYSIS_RESULTS.md -``` - -**CRITICAL - Next Step**: Auto-continue to Phase 2: Test Cycle Execution. -Pass `testSessionId` to Phase 2 for test execution pipeline. Do NOT wait for user confirmation — the unified pipeline continues automatically. - -## Execution Flow Diagram - -``` -User triggers: /workflow:test-fix-gen "Test user authentication" - ↓ -[Input Detection] → MODE: prompt - ↓ -[TodoWrite Init] Phase 1 sub-steps + Phase 2 - ↓ -Step 1.1: Create Test Session - → /workflow:session:start --type test - → testSessionId extracted (WFS-test-user-auth) - ↓ -Step 1.2: Gather Test Context (Skill executed) - → ATTACH 3 sub-tasks: ← ATTACHED - - → Load codebase context - - → Analyze test coverage - - → Generate context package - → Execute sub-tasks sequentially - → COLLAPSE tasks ← COLLAPSED - → contextPath extracted - ↓ -Step 1.3: Test Generation Analysis (Skill executed) - → ATTACH 3 sub-tasks: ← ATTACHED - - → Analyze coverage gaps with Gemini - - → Detect AI code issues (L0.5) - - → Generate L0-L3 test requirements - → Execute sub-tasks sequentially - → COLLAPSE tasks ← COLLAPSED - → TEST_ANALYSIS_RESULTS.md created - ↓ -Step 1.4: Generate Test Tasks (Skill executed) - → Single agent task (test-task-generate → action-planning-agent) - → Agent autonomously generates: - - IMPL-001.json (test generation) - - IMPL-001.3-validation.json (code validation) - - IMPL-001.5-review.json (test quality) - - IMPL-002.json (test execution) - - IMPL_PLAN.md - - TODO_LIST.md - ↓ -Step 1.5: Return Summary - → Display summary - → Phase 1 complete -``` - -## Output Artifacts - -### Directory Structure - -``` -.workflow/active/WFS-test-[session]/ -├── workflow-session.json # Session metadata -├── IMPL_PLAN.md # Test generation and execution strategy -├── TODO_LIST.md # Task checklist -├── .task/ -│ ├── IMPL-001.json # Test understanding & generation -│ ├── IMPL-001.3-validation.json # Code validation gate -│ ├── IMPL-001.5-review.json # Test quality gate -│ ├── IMPL-002.json # Test execution & fix cycle -│ └── IMPL-*.json # Additional tasks (if applicable) -└── .process/ - ├── [test-]context-package.json # Context and coverage analysis - └── TEST_ANALYSIS_RESULTS.md # Test requirements and strategy (L0-L3) -``` - -### Session Metadata - -**File**: `workflow-session.json` - -| Mode | Fields | -|------|--------| -| **Session** | `type: "test"`, `source_session_id: "[sourceId]"` | -| **Prompt** | `type: "test"` (no source_session_id) | - -## Error Handling - -| Step | Error Condition | Action | -|------|----------------|--------| -| 1.1 | Source session not found (session mode) | Return error with session ID | -| 1.1 | No completed IMPL tasks (session mode) | Return error, source incomplete | -| 1.2 | Context gathering failed | Return error, check source artifacts | -| 1.3 | Gemini analysis failed | Return error, check context package | -| 1.4 | Task generation failed | Retry once, then return error | - -## Usage Examples - -```bash -# Session Mode - test validation for completed implementation -/workflow:test-fix-gen WFS-user-auth-v2 - -# Prompt Mode - text description -/workflow:test-fix-gen "Test the user authentication API endpoints in src/auth/api.ts" - -# Prompt Mode - file reference -/workflow:test-fix-gen ./docs/api-requirements.md -``` - -## Output - -- **Variable**: `testSessionId` (WFS-test-xxx) -- **Variable**: `contextPath` (context-package.json path) -- **Files**: IMPL_PLAN.md, IMPL-*.json (4+), TODO_LIST.md, TEST_ANALYSIS_RESULTS.md -- **TodoWrite**: Mark Phase 1 completed, Phase 2 in_progress - -## Next Phase - -Return to orchestrator, then auto-continue to [Phase 2: Test Cycle Execution](02-test-cycle-execute.md). diff --git a/.claude/skills/workflow-test-fix/phases/02-test-context-gather.md b/.claude/skills/workflow-test-fix/phases/02-test-context-gather.md new file mode 100644 index 00000000..7aae42cc --- /dev/null +++ b/.claude/skills/workflow-test-fix/phases/02-test-context-gather.md @@ -0,0 +1,66 @@ +# Phase 2: Test Context Gather (test-context-gather) + +Gather test context via coverage analysis or codebase scan. + +## Objective + +- Gather test context (coverage analysis or codebase scan) +- Generate context package for downstream analysis + +## Execution + +### Step 1.2: Gather Test Context + +``` +// Session Mode - gather from source session +Skill(skill="workflow:tools:test-context-gather", args="--session [testSessionId]") + +// Prompt Mode - gather from codebase +Skill(skill="workflow:tools:context-gather", args="--session [testSessionId] \"[task_description]\"") +``` + +**Input**: `testSessionId` from Phase 1 + +**Parse Output**: +- Extract: context package path (store as `contextPath`) +- Pattern: `.workflow/active/[testSessionId]/.process/[test-]context-package.json` + +**Validation**: +- Context package file exists and is valid JSON +- Contains coverage analysis (session mode) or codebase analysis (prompt mode) +- Test framework detected + +**TodoWrite Update (tasks attached)**: +```json +[ + {"content": "Phase 1: Test Generation", "status": "in_progress"}, + {"content": " → Create test session", "status": "completed"}, + {"content": " → Gather test context", "status": "in_progress"}, + {"content": " → Load source/codebase context", "status": "in_progress"}, + {"content": " → Analyze test coverage", "status": "pending"}, + {"content": " → Generate context package", "status": "pending"}, + {"content": " → Test analysis (Gemini)", "status": "pending"}, + {"content": " → Generate test tasks", "status": "pending"}, + {"content": "Phase 2: Test Cycle Execution", "status": "pending"} +] +``` + +**TodoWrite Update (tasks collapsed)**: +```json +[ + {"content": "Phase 1: Test Generation", "status": "in_progress"}, + {"content": " → Create test session", "status": "completed"}, + {"content": " → Gather test context", "status": "completed"}, + {"content": " → Test analysis (Gemini)", "status": "pending"}, + {"content": " → Generate test tasks", "status": "pending"}, + {"content": "Phase 2: Test Cycle Execution", "status": "pending"} +] +``` + +## Output + +- **Variable**: `contextPath` (context-package.json path) + +## Next Phase + +Continue to [Phase 3: Test Concept Enhanced](03-test-concept-enhanced.md). diff --git a/.claude/skills/workflow-test-fix/phases/03-test-concept-enhanced.md b/.claude/skills/workflow-test-fix/phases/03-test-concept-enhanced.md new file mode 100644 index 00000000..2613bc6c --- /dev/null +++ b/.claude/skills/workflow-test-fix/phases/03-test-concept-enhanced.md @@ -0,0 +1,51 @@ +# Phase 3: Test Concept Enhanced (test-concept-enhanced) + +Analyze test requirements with Gemini using progressive L0-L3 test layers. + +## Objective + +- Use Gemini to analyze coverage gaps +- Detect project type and apply appropriate test templates +- Generate multi-layered test requirements (L0-L3) +- Scan for AI code issues + +## Execution + +### Step 1.3: Test Generation Analysis + +``` +Skill(skill="workflow:tools:test-concept-enhanced", args="--session [testSessionId] --context [contextPath]") +``` + +**Input**: +- `testSessionId` from Phase 1 +- `contextPath` from Phase 2 + +**Expected Behavior**: +- Use Gemini to analyze coverage gaps +- Detect project type and apply appropriate test templates +- Generate **multi-layered test requirements** (L0-L3) +- Scan for AI code issues +- Generate `TEST_ANALYSIS_RESULTS.md` + +**Output**: `.workflow/[testSessionId]/.process/TEST_ANALYSIS_RESULTS.md` + +**Validation** - TEST_ANALYSIS_RESULTS.md must include: +- Project Type Detection (with confidence) +- Coverage Assessment (current vs target) +- Test Framework & Conventions +- Multi-Layered Test Plan (L0-L3) +- AI Issue Scan Results +- Test Requirements by File (with layer annotations) +- Quality Assurance Criteria +- Success Criteria + +**Note**: Detailed specifications for project types, L0-L3 layers, and AI issue detection are defined in `/workflow:tools:test-concept-enhanced`. + +## Output + +- **File**: `.workflow/[testSessionId]/.process/TEST_ANALYSIS_RESULTS.md` + +## Next Phase + +Continue to [Phase 4: Test Task Generate](04-test-task-generate.md). diff --git a/.claude/skills/workflow-test-fix/phases/04-test-task-generate.md b/.claude/skills/workflow-test-fix/phases/04-test-task-generate.md new file mode 100644 index 00000000..76576369 --- /dev/null +++ b/.claude/skills/workflow-test-fix/phases/04-test-task-generate.md @@ -0,0 +1,46 @@ +# Phase 4: Test Task Generate (test-task-generate) + +Generate test task JSONs via action-planning-agent. + +## Objective + +- Generate test-specific IMPL_PLAN.md and task JSONs based on TEST_ANALYSIS_RESULTS.md +- Create minimum 4 tasks covering test generation, code validation, quality review, and test execution + +## Execution + +### Step 1.4: Generate Test Tasks + +``` +Skill(skill="workflow:tools:test-task-generate", args="--session [testSessionId]") +``` + +**Input**: `testSessionId` from Phase 1 + +**Note**: test-task-generate invokes action-planning-agent to generate test-specific IMPL_PLAN.md and task JSONs based on TEST_ANALYSIS_RESULTS.md. + +**Expected Output** (minimum 4 tasks): + +| Task | Type | Agent | Purpose | +|------|------|-------|---------| +| IMPL-001 | test-gen | @code-developer | Test understanding & generation (L1-L3) | +| IMPL-001.3 | code-validation | @test-fix-agent | Code validation gate (L0 + AI issues) | +| IMPL-001.5 | test-quality-review | @test-fix-agent | Test quality gate | +| IMPL-002 | test-fix | @test-fix-agent | Test execution & fix cycle | + +**Validation**: +- `.workflow/active/[testSessionId]/.task/IMPL-001.json` exists +- `.workflow/active/[testSessionId]/.task/IMPL-001.3-validation.json` exists +- `.workflow/active/[testSessionId]/.task/IMPL-001.5-review.json` exists +- `.workflow/active/[testSessionId]/.task/IMPL-002.json` exists +- `.workflow/active/[testSessionId]/IMPL_PLAN.md` exists +- `.workflow/active/[testSessionId]/TODO_LIST.md` exists + +## Output + +- **Files**: IMPL_PLAN.md, IMPL-*.json (4+), TODO_LIST.md +- **TodoWrite**: Mark Phase 1-4 completed, Phase 5 in_progress + +## Next Phase + +Return to orchestrator for summary output, then auto-continue to [Phase 5: Test Cycle Execute](05-test-cycle-execute.md). diff --git a/.claude/skills/workflow-test-fix/phases/02-test-cycle-execute.md b/.claude/skills/workflow-test-fix/phases/05-test-cycle-execute.md similarity index 99% rename from .claude/skills/workflow-test-fix/phases/02-test-cycle-execute.md rename to .claude/skills/workflow-test-fix/phases/05-test-cycle-execute.md index 68cd8dd1..19e84d9d 100644 --- a/.claude/skills/workflow-test-fix/phases/02-test-cycle-execute.md +++ b/.claude/skills/workflow-test-fix/phases/05-test-cycle-execute.md @@ -53,7 +53,7 @@ Load session, tasks, and iteration state. └─ Load session, tasks, iteration state ``` -**For full-pipeline entry (from Phase 1)**: Use `testSessionId` passed from Phase 1. +**For full-pipeline entry (from Phase 1-4)**: Use `testSessionId` passed from Phase 4. **For direct entry (/workflow:test-cycle-execute)**: - `--resume-session="WFS-xxx"` → Use specified session @@ -526,7 +526,7 @@ The orchestrator automatically creates git commits at key checkpoints to enable - **Variable**: `finalPassRate` (percentage) - **File**: `test-results.json` (final results) - **File**: `iteration-state.json` (full iteration history) -- **TodoWrite**: Mark Phase 2 completed +- **TodoWrite**: Mark Phase 5 completed ## Next Phase diff --git a/ccw/frontend/src/components/shared/Flowchart.tsx b/ccw/frontend/src/components/shared/Flowchart.tsx index 0571deea..377b0c27 100644 --- a/ccw/frontend/src/components/shared/Flowchart.tsx +++ b/ccw/frontend/src/components/shared/Flowchart.tsx @@ -31,6 +31,7 @@ interface FlowchartNodeData extends Record { type: 'pre-analysis' | 'implementation' | 'section'; dependsOn?: string[]; status?: 'pending' | 'in_progress' | 'completed' | 'blocked' | 'skipped'; + showStepStatus?: boolean; } // Status icon component diff --git a/ccw/frontend/src/components/shared/TaskDrawer.tsx b/ccw/frontend/src/components/shared/TaskDrawer.tsx index d2d04fd4..21627023 100644 --- a/ccw/frontend/src/components/shared/TaskDrawer.tsx +++ b/ccw/frontend/src/components/shared/TaskDrawer.tsx @@ -11,7 +11,7 @@ import { Badge } from '../ui/Badge'; import { Button } from '../ui/Button'; import { Tabs, TabsList, TabsTrigger, TabsContent } from '../ui/Tabs'; import type { NormalizedTask, LiteTask } from '@/lib/api'; -import { buildFlowControl } from '@/lib/api'; +import { buildFlowControl, normalizeTask } from '@/lib/api'; import type { TaskData } from '@/types/store'; // ========== Types ========== @@ -86,8 +86,11 @@ export function TaskDrawer({ task, isOpen, onClose }: TaskDrawerProps) { return null; } - // Use NormalizedTask fields (works for both old nested and new flat formats) - const nt = task as NormalizedTask; + // Normalize task to unified flat format (handles old nested, new flat, and raw LiteTask/TaskData) + const nt = React.useMemo( + () => normalizeTask(task as unknown as Record), + [task], + ); const taskId = nt.task_id || 'N/A'; const taskTitle = nt.title || 'Untitled Task'; const taskDescription = nt.description; @@ -103,6 +106,13 @@ export function TaskDrawer({ task, isOpen, onClose }: TaskDrawerProps) { const taskFiles = nt.files || flowControl?.target_files || []; const taskScope = nt.scope; + // Detect if task supports status tracking (new format has explicit status/status_history) + const rawData = nt._raw as Record | undefined; + const sourceRaw = (rawData?._raw as Record) || rawData; + const hasStatusTracking = sourceRaw + ? (sourceRaw.status !== undefined || sourceRaw.status_history !== undefined) + : false; + const statusConfig = taskStatusConfig[taskStatus] || taskStatusConfig.pending; const StatusIcon = statusConfig.icon; @@ -135,10 +145,12 @@ export function TaskDrawer({ task, isOpen, onClose }: TaskDrawerProps) {
{taskId} - - - {formatMessage({ id: statusConfig.label })} - + {hasStatusTracking && ( + + + {formatMessage({ id: statusConfig.label })} + + )}

{taskTitle} @@ -352,9 +364,9 @@ export function TaskDrawer({ task, isOpen, onClose }: TaskDrawerProps) { {/* Empty State */} {!taskDescription && - !(task as LiteTask).meta?.scope && - !((task as LiteTask).context?.acceptance?.length) && - !((task as LiteTask).context?.focus_paths?.length) && + !taskScope && + !acceptanceCriteria.length && + !focusPaths.length && !(flowControl?.pre_analysis?.length) && !(flowControl?.implementation_approach?.length) && (
diff --git a/ccw/frontend/src/components/terminal-dashboard/BottomInspector.tsx b/ccw/frontend/src/components/terminal-dashboard/BottomInspector.tsx index a1f90eba..5ef962bd 100644 --- a/ccw/frontend/src/components/terminal-dashboard/BottomInspector.tsx +++ b/ccw/frontend/src/components/terminal-dashboard/BottomInspector.tsx @@ -1,10 +1,9 @@ // ======================================== // BottomInspector Component // ======================================== -// Collapsible bottom panel showing the full association chain -// (Issue -> Queue -> Session) for the currently selected entity. -// Consumes issueQueueIntegrationStore for association chain data -// and useAssociationHighlight context for the highlighted chain. +// Association chain visualization (Issue -> Queue -> Session). +// Exports InspectorContent (pure content) for embedding in BottomPanel, +// and BottomInspector (legacy standalone collapsible wrapper). import { useState, useCallback, useMemo } from 'react'; import { useIntl } from 'react-intl'; @@ -90,7 +89,86 @@ function formatTimestamp(ts: string): string { } } -// ========== Main Component ========== +// ========== InspectorContent (Pure content, no collapsible wrapper) ========== + +export function InspectorContent() { + const { formatMessage } = useIntl(); + const associationChain = useIssueQueueIntegrationStore(selectAssociationChain); + const { chain: highlightedChain } = useAssociationHighlight(); + + const activeChain = highlightedChain ?? associationChain; + + const chainDetails = useMemo(() => { + if (!activeChain) return null; + + const executions = Object.values(useQueueExecutionStore.getState().executions); + const sessions = useCliSessionStore.getState().sessions; + + let queueStatus: string | undefined; + let executionTimestamp: string | undefined; + if (activeChain.queueItemId) { + const exec = executions.find((e) => e.queueItemId === activeChain.queueItemId); + if (exec) { + queueStatus = exec.status; + executionTimestamp = exec.startedAt; + } + } + + let sessionStatus: string | undefined; + let sessionTimestamp: string | undefined; + if (activeChain.sessionId) { + const session = sessions[activeChain.sessionId]; + if (session) { + sessionStatus = 'active'; + sessionTimestamp = session.createdAt; + } + } + + return { queueStatus, executionTimestamp, sessionStatus, sessionTimestamp }; + }, [activeChain]); + + const hasChain = activeChain !== null; + + return ( +
+ {hasChain ? ( +
+

+ {formatMessage({ id: 'terminalDashboard.inspector.associationChain' })} +

+
+ + + +
+
+ ) : ( +

+ {formatMessage({ id: 'terminalDashboard.inspector.noSelection' })} +

+ )} +
+ ); +} + +// ========== Legacy Standalone Component ========== export function BottomInspector() { const { formatMessage } = useIntl(); diff --git a/ccw/frontend/src/components/terminal-dashboard/BottomPanel.tsx b/ccw/frontend/src/components/terminal-dashboard/BottomPanel.tsx new file mode 100644 index 00000000..c4591dd0 --- /dev/null +++ b/ccw/frontend/src/components/terminal-dashboard/BottomPanel.tsx @@ -0,0 +1,136 @@ +// ======================================== +// BottomPanel Component +// ======================================== +// Full-width collapsible bottom panel with Queue + Inspector tabs. +// Replaces the separate BottomInspector + middle-column QueuePanel layout. +// Queue tab shows inline count badge; Inspector tab shows chain indicator. + +import { useState, useCallback, useMemo } from 'react'; +import { useIntl } from 'react-intl'; +import { ListChecks, Info, ChevronDown, ChevronUp } from 'lucide-react'; +import { cn } from '@/lib/utils'; +import { Badge } from '@/components/ui/Badge'; +import { QueuePanel } from './QueuePanel'; +import { InspectorContent } from './BottomInspector'; +import { useIssueQueue } from '@/hooks/useIssues'; +import { + useIssueQueueIntegrationStore, + selectAssociationChain, +} from '@/stores/issueQueueIntegrationStore'; + +// ========== Types ========== + +type TabId = 'queue' | 'inspector'; + +// ========== Component ========== + +export function BottomPanel() { + const { formatMessage } = useIntl(); + const [isOpen, setIsOpen] = useState(false); + const [activeTab, setActiveTab] = useState('queue'); + + const queueQuery = useIssueQueue(); + const associationChain = useIssueQueueIntegrationStore(selectAssociationChain); + + // Count queue items for badge + const queueCount = useMemo(() => { + if (!queueQuery.data) return 0; + const grouped = queueQuery.data.grouped_items ?? {}; + let count = 0; + for (const items of Object.values(grouped)) { + count += items.length; + } + return count; + }, [queueQuery.data]); + + const hasChain = associationChain !== null; + + const toggle = useCallback(() => { + setIsOpen((prev) => !prev); + }, []); + + const handleTabClick = useCallback((tab: TabId) => { + setActiveTab(tab); + setIsOpen(true); + }, []); + + return ( +
+ {/* Tab bar (always visible, ~36px) */} +
+ {/* Queue tab */} + + + {/* Inspector tab */} + + + {/* Collapse/expand toggle at right */} + +
+ + {/* Collapsible content area */} +
+
+ {activeTab === 'queue' ? ( + + ) : ( + + )} +
+
+
+ ); +} diff --git a/ccw/frontend/src/components/terminal-dashboard/QueuePanel.tsx b/ccw/frontend/src/components/terminal-dashboard/QueuePanel.tsx index f261d9ef..1b84733d 100644 --- a/ccw/frontend/src/components/terminal-dashboard/QueuePanel.tsx +++ b/ccw/frontend/src/components/terminal-dashboard/QueuePanel.tsx @@ -131,12 +131,23 @@ function QueueItemRow({ // ========== Empty State ========== -function QueueEmptyState() { +function QueueEmptyState({ compact = false }: { compact?: boolean }) { const { formatMessage } = useIntl(); + + if (compact) { + return ( +
+ + {formatMessage({ id: 'terminalDashboard.queuePanel.noItems' })} + {formatMessage({ id: 'terminalDashboard.queuePanel.noItemsDesc' })} +
+ ); + } + return (
- +

{formatMessage({ id: 'terminalDashboard.queuePanel.noItems' })}

{formatMessage({ id: 'terminalDashboard.queuePanel.noItemsDesc' })} @@ -163,7 +174,7 @@ function QueueErrorState({ error }: { error: Error }) { // ========== Main Component ========== -export function QueuePanel() { +export function QueuePanel({ embedded = false }: { embedded?: boolean }) { const { formatMessage } = useIntl(); const queueQuery = useIssueQueue(); const associationChain = useIssueQueueIntegrationStore(selectAssociationChain); @@ -200,12 +211,14 @@ export function QueuePanel() { if (queueQuery.isLoading) { return (

-
-

- - {formatMessage({ id: 'terminalDashboard.queuePanel.title' })} -

-
+ {!embedded && ( +
+

+ + {formatMessage({ id: 'terminalDashboard.queuePanel.title' })} +

+
+ )}
@@ -217,12 +230,14 @@ export function QueuePanel() { if (queueQuery.error) { return (
-
-

- - {formatMessage({ id: 'terminalDashboard.queuePanel.title' })} -

-
+ {!embedded && ( +
+

+ + {formatMessage({ id: 'terminalDashboard.queuePanel.title' })} +

+
+ )}
); @@ -230,23 +245,25 @@ export function QueuePanel() { return (
- {/* Header with flow indicator */} -
-

- - - {formatMessage({ id: 'terminalDashboard.queuePanel.title' })} -

- {activeCount > 0 && ( - - {activeCount} - - )} -
+ {/* Header with flow indicator (hidden when embedded) */} + {!embedded && ( +
+

+ + + {formatMessage({ id: 'terminalDashboard.queuePanel.title' })} +

+ {activeCount > 0 && ( + + {activeCount} + + )} +
+ )} {/* Queue Item List */} {allItems.length === 0 ? ( - + ) : (
{allItems.map((item) => ( diff --git a/ccw/frontend/src/lib/api.ts b/ccw/frontend/src/lib/api.ts index 4bafd1a6..73d9e914 100644 --- a/ccw/frontend/src/lib/api.ts +++ b/ccw/frontend/src/lib/api.ts @@ -2062,6 +2062,7 @@ export function normalizeTask(raw: Record): NormalizedTask { const rawFlowControl = raw.flow_control as FlowControl | undefined; const rawMeta = raw.meta as LiteTask['meta'] | undefined; const rawConvergence = raw.convergence as NormalizedTask['convergence'] | undefined; + const rawModPoints = raw.modification_points as Array<{ file?: string; target?: string; change?: string }> | undefined; // Description: new flat field first, then join old context.requirements, then old details/scope const rawRequirements = rawContext?.requirements; @@ -2075,6 +2076,25 @@ export function normalizeTask(raw: Record): NormalizedTask { : undefined) || (raw.scope as string | undefined); + // Normalize files: new flat files > flow_control.target_files > modification_points + const normalizedFiles = normalizeFilesField(raw.files) + || rawFlowControl?.target_files + || (rawModPoints?.length + ? rawModPoints.filter(m => m.file).map(m => ({ path: m.file!, name: m.target, change: m.change })) + : undefined); + + // Normalize focus_paths: top-level > context > files paths + const focusPaths = (raw.focus_paths as string[]) + || rawContext?.focus_paths + || (normalizedFiles?.length ? normalizedFiles.map(f => f.path).filter(Boolean) : undefined) + || []; + + // Normalize acceptance: convergence > context.acceptance > top-level acceptance + const rawAcceptance = raw.acceptance as string[] | undefined; + const convergence = rawConvergence + || (rawContext?.acceptance?.length ? { criteria: rawContext.acceptance } : undefined) + || (rawAcceptance?.length ? { criteria: rawAcceptance } : undefined); + return { // Identity task_id: (raw.task_id as string) || (raw.id as string) || 'N/A', @@ -2089,15 +2109,13 @@ export function normalizeTask(raw: Record): NormalizedTask { // Promoted from context (new first, old fallback) depends_on: (raw.depends_on as string[]) || rawContext?.depends_on || [], - focus_paths: (raw.focus_paths as string[]) || rawContext?.focus_paths || [], - convergence: rawConvergence || (rawContext?.acceptance?.length - ? { criteria: rawContext.acceptance } - : undefined), + focus_paths: focusPaths, + convergence, // Promoted from flow_control (new first, old fallback) pre_analysis: (raw.pre_analysis as PreAnalysisStep[]) || rawFlowControl?.pre_analysis, implementation: (raw.implementation as (ImplementationStep | string)[]) || rawFlowControl?.implementation_approach, - files: normalizeFilesField(raw.files) || rawFlowControl?.target_files, + files: normalizedFiles, // Promoted from meta (new first, old fallback) type: (raw.type as string) || rawMeta?.type, diff --git a/ccw/frontend/src/pages/TerminalDashboardPage.tsx b/ccw/frontend/src/pages/TerminalDashboardPage.tsx index 990977a4..35a17fb7 100644 --- a/ccw/frontend/src/pages/TerminalDashboardPage.tsx +++ b/ccw/frontend/src/pages/TerminalDashboardPage.tsx @@ -2,49 +2,73 @@ // Terminal Dashboard Page // ======================================== // Three-column Allotment layout for terminal execution management. -// Left: session groups + agent list -// Middle: issue + queue workflow panels -// Right: terminal workbench -// Top: GlobalKpiBar (real component) -// Bottom: BottomInspector (collapsible, real component) +// Left: session groups + agent list (with active session count badge) +// Middle: full-height IssuePanel +// Right: terminal workbench (or issue detail preview) +// Bottom: collapsible BottomPanel (Queue + Inspector tabs) // Cross-cutting: AssociationHighlightProvider wraps the layout +import { useMemo } from 'react'; import { useIntl } from 'react-intl'; import { Allotment } from 'allotment'; import 'allotment/dist/style.css'; -import { FolderTree } from 'lucide-react'; +import { FolderTree, Activity } from 'lucide-react'; import { SessionGroupTree } from '@/components/terminal-dashboard/SessionGroupTree'; import { AgentList } from '@/components/terminal-dashboard/AgentList'; import { IssuePanel } from '@/components/terminal-dashboard/IssuePanel'; -import { QueuePanel } from '@/components/terminal-dashboard/QueuePanel'; import { TerminalWorkbench } from '@/components/terminal-dashboard/TerminalWorkbench'; -import { GlobalKpiBar } from '@/components/terminal-dashboard/GlobalKpiBar'; -import { BottomInspector } from '@/components/terminal-dashboard/BottomInspector'; +import { BottomPanel } from '@/components/terminal-dashboard/BottomPanel'; import { AssociationHighlightProvider } from '@/components/terminal-dashboard/AssociationHighlight'; +import { Badge } from '@/components/ui/Badge'; +import { + useSessionManagerStore, + selectGroups, + selectTerminalMetas, +} from '@/stores/sessionManagerStore'; +import type { TerminalStatus } from '@/types/terminal-dashboard'; // ========== Main Page Component ========== export function TerminalDashboardPage() { const { formatMessage } = useIntl(); + const groups = useSessionManagerStore(selectGroups); + const terminalMetas = useSessionManagerStore(selectTerminalMetas); + + // Active session count for left column header badge + const sessionCount = useMemo(() => { + const allSessionIds = groups.flatMap((g) => g.sessionIds); + let activeCount = 0; + for (const sid of allSessionIds) { + const meta = terminalMetas[sid]; + const status: TerminalStatus = meta?.status ?? 'idle'; + if (status === 'active') { + activeCount++; + } + } + return activeCount > 0 ? activeCount : allSessionIds.length; + }, [groups, terminalMetas]); return (
- {/* GlobalKpiBar at top (flex-shrink-0) */} - - - {/* AssociationHighlightProvider wraps the three-column layout + bottom inspector */} + {/* AssociationHighlightProvider wraps the three-column layout + bottom panel */} {/* Three-column Allotment layout (flex-1) */}
- {/* Left column: Sessions */} - + {/* Left column: Sessions + Agents */} +
-
+

{formatMessage({ id: 'terminalDashboard.columns.sessions' })}

+ {sessionCount > 0 && ( + + + {sessionCount} + + )}
{/* SessionGroupTree takes remaining space */}
@@ -57,23 +81,10 @@ export function TerminalDashboardPage() {
- {/* Middle column: Workflow (IssuePanel + QueuePanel vertical split) */} - + {/* Middle column: Full-height IssuePanel */} +
- - {/* Top: IssuePanel */} - -
- -
- - {/* Bottom: QueuePanel */} - -
- -
- - +
@@ -86,8 +97,8 @@ export function TerminalDashboardPage() {
- {/* BottomInspector at bottom (flex-shrink-0) */} - + {/* BottomPanel: collapsible Queue + Inspector tabs (full-width) */} +
); diff --git a/ccw/src/core/lite-scanner-complete.ts b/ccw/src/core/lite-scanner-complete.ts index 6ffdf7c8..2c67964a 100644 --- a/ccw/src/core/lite-scanner-complete.ts +++ b/ccw/src/core/lite-scanner-complete.ts @@ -16,10 +16,9 @@ interface TaskContext { } interface TaskFlowControl { - implementation_approach: Array<{ - step: string; - action: string; - }>; + implementation_approach: Array>; + pre_analysis?: Array>; + target_files?: Array<{ path: string; [key: string]: unknown }>; } interface NormalizedTask { @@ -29,6 +28,13 @@ interface NormalizedTask { meta: TaskMeta; context: TaskContext; flow_control: TaskFlowControl; + // New flat format pass-through fields (consumed by frontend normalizer) + description?: string; + convergence?: { criteria?: string[]; verification?: string; definition_of_done?: string }; + focus_paths?: string[]; + pre_analysis?: Array>; + implementation?: unknown[]; + files?: Array<{ path: string; [key: string]: unknown }>; _raw: unknown; } @@ -282,16 +288,59 @@ function normalizeTask(task: unknown): NormalizedTask | null { const context = taskObj.context as Record | undefined; const flowControl = taskObj.flow_control as Record | undefined; const implementation = taskObj.implementation as unknown[] | undefined; + const preAnalysis = taskObj.pre_analysis as Array> | undefined; + const convergence = taskObj.convergence as NormalizedTask['convergence'] | undefined; const modificationPoints = taskObj.modification_points as Array<{ file?: string }> | undefined; // Ensure id is always a string (handle numeric IDs from JSON) const rawId = taskObj.id ?? taskObj.task_id; const stringId = rawId != null ? String(rawId) : 'unknown'; + // Normalize files: support both string[] and {path, action, change}[] formats + const rawFiles = taskObj.files as unknown[] | undefined; + const normalizedFiles: Array<{ path: string; [key: string]: unknown }> | undefined = + Array.isArray(rawFiles) && rawFiles.length > 0 + ? rawFiles.map(f => typeof f === 'string' ? { path: f } : f as { path: string }) + : undefined; + + // Extract focus_paths: top-level > context > files paths > modification_points + const focusPaths: string[] = + (taskObj.focus_paths as string[]) + || (context?.focus_paths as string[]) + || normalizedFiles?.map(f => f.path).filter(Boolean) + || modificationPoints?.map(m => m.file).filter((f): f is string => !!f) + || []; + + // Build implementation_approach: preserve rich objects, handle strings + let implApproach: Array> = []; + if (flowControl?.implementation_approach) { + implApproach = flowControl.implementation_approach as Array>; + } else if (implementation) { + implApproach = implementation.map((step, i) => { + if (typeof step === 'object' && step !== null) { + return step as Record; + } + return { step: i + 1, title: `Step ${i + 1}`, action: String(step) }; + }); + } + + // Build pre_analysis: top-level > flow_control + const preAnalysisSteps = preAnalysis + || (flowControl?.pre_analysis as Array>) + || undefined; + + // Build acceptance criteria: convergence.criteria > context.acceptance + const acceptance: string[] = + convergence?.criteria + || (context?.acceptance as string[]) + || (taskObj.acceptance as string[]) + || []; + return { id: stringId, title: (taskObj.title as string) || (taskObj.name as string) || (taskObj.summary as string) || 'Untitled Task', status: (status as string).toLowerCase(), + description: taskObj.description as string | undefined, // Preserve original fields for flexible rendering meta: meta ? { type: (meta.type as string) || (taskObj.type as string) || (taskObj.action as string) || 'task', @@ -306,23 +355,29 @@ function normalizeTask(task: unknown): NormalizedTask | null { }, context: context ? { requirements: (context.requirements as string[]) || [], - focus_paths: (context.focus_paths as string[]) || [], - acceptance: (context.acceptance as string[]) || [], + focus_paths: focusPaths, + acceptance, depends_on: (context.depends_on as string[]) || [] } : { - requirements: (taskObj.requirements as string[]) || (taskObj.description ? [taskObj.description as string] : []), - focus_paths: (taskObj.focus_paths as string[]) || modificationPoints?.map(m => m.file).filter((f): f is string => !!f) || [], - acceptance: (taskObj.acceptance as string[]) || [], + requirements: (taskObj.requirements as string[]) + || (taskObj.details as string[]) + || (taskObj.description ? [taskObj.description as string] : taskObj.scope ? [taskObj.scope as string] : []), + focus_paths: focusPaths, + acceptance, depends_on: (taskObj.depends_on as string[]) || [] }, - flow_control: flowControl ? { - implementation_approach: (flowControl.implementation_approach as Array<{ step: string; action: string }>) || [] - } : { - implementation_approach: implementation?.map((step, i) => ({ - step: `Step ${i + 1}`, - action: step as string - })) || [] + flow_control: { + implementation_approach: implApproach, + pre_analysis: preAnalysisSteps, + target_files: normalizedFiles + || (flowControl?.target_files as Array<{ path: string }>) || undefined, }, + // New flat format pass-through: let frontend normalizer consume these directly + convergence, + focus_paths: focusPaths, + pre_analysis: preAnalysisSteps, + implementation: implementation, + files: normalizedFiles, // Keep all original fields for raw JSON view _raw: task }; diff --git a/ccw/src/core/lite-scanner.ts b/ccw/src/core/lite-scanner.ts index 79788934..fff457f8 100644 --- a/ccw/src/core/lite-scanner.ts +++ b/ccw/src/core/lite-scanner.ts @@ -16,11 +16,9 @@ interface TaskContext { } interface TaskFlowControl { - implementation_approach: Array<{ - step: string; - action: string; - }>; - target_files?: Array<{ path: string }>; + implementation_approach: Array>; + pre_analysis?: Array>; + target_files?: Array<{ path: string; [key: string]: unknown }>; } interface NormalizedTask { @@ -30,6 +28,13 @@ interface NormalizedTask { meta: TaskMeta; context: TaskContext; flow_control: TaskFlowControl; + // New flat format pass-through fields (consumed by frontend normalizer) + description?: string; + convergence?: { criteria?: string[]; verification?: string; definition_of_done?: string }; + focus_paths?: string[]; + pre_analysis?: Array>; + implementation?: unknown[]; + files?: Array<{ path: string; [key: string]: unknown }>; _raw: unknown; } @@ -750,16 +755,59 @@ function normalizeTask(task: unknown): NormalizedTask | null { const context = taskObj.context as Record | undefined; const flowControl = taskObj.flow_control as Record | undefined; const implementation = taskObj.implementation as unknown[] | undefined; + const preAnalysis = taskObj.pre_analysis as Array> | undefined; + const convergence = taskObj.convergence as NormalizedTask['convergence'] | undefined; const modificationPoints = taskObj.modification_points as Array<{ file?: string }> | undefined; // Ensure id is always a string (handle numeric IDs from JSON) const rawId = taskObj.id ?? taskObj.task_id; const stringId = rawId != null ? String(rawId) : 'unknown'; + // Normalize files: support both string[] and {path, action, change}[] formats + const rawFiles = taskObj.files as unknown[] | undefined; + const normalizedFiles: Array<{ path: string; [key: string]: unknown }> | undefined = + Array.isArray(rawFiles) && rawFiles.length > 0 + ? rawFiles.map(f => typeof f === 'string' ? { path: f } : f as { path: string }) + : undefined; + + // Extract focus_paths: top-level > context > files paths > modification_points + const focusPaths: string[] = + (taskObj.focus_paths as string[]) + || (context?.focus_paths as string[]) + || normalizedFiles?.map(f => f.path).filter(Boolean) + || modificationPoints?.map(m => m.file).filter((f): f is string => !!f) + || []; + + // Build implementation_approach: preserve rich objects, handle strings + let implApproach: Array> = []; + if (flowControl?.implementation_approach) { + implApproach = flowControl.implementation_approach as Array>; + } else if (implementation) { + implApproach = implementation.map((step, i) => { + if (typeof step === 'object' && step !== null) { + return step as Record; + } + return { step: i + 1, title: `Step ${i + 1}`, action: String(step) }; + }); + } + + // Build pre_analysis: top-level > flow_control + const preAnalysisSteps = preAnalysis + || (flowControl?.pre_analysis as Array>) + || undefined; + + // Build acceptance criteria: convergence.criteria > context.acceptance + const acceptance: string[] = + convergence?.criteria + || (context?.acceptance as string[]) + || (taskObj.acceptance as string[]) + || []; + return { id: stringId, title: (taskObj.title as string) || (taskObj.name as string) || (taskObj.summary as string) || 'Untitled Task', status: (status as string).toLowerCase(), + description: taskObj.description as string | undefined, // Preserve original fields for flexible rendering meta: meta ? { type: (meta.type as string) || (taskObj.type as string) || (taskObj.action as string) || 'task', @@ -774,33 +822,29 @@ function normalizeTask(task: unknown): NormalizedTask | null { }, context: context ? { requirements: (context.requirements as string[]) || [], - focus_paths: (context.focus_paths as string[]) || [], - acceptance: (context.acceptance as string[]) || [], + focus_paths: focusPaths, + acceptance, depends_on: (context.depends_on as string[]) || [] } : { requirements: (taskObj.requirements as string[]) || (taskObj.details as string[]) || (taskObj.description ? [taskObj.description as string] : taskObj.scope ? [taskObj.scope as string] : []), - focus_paths: (taskObj.focus_paths as string[]) - || (Array.isArray(taskObj.files) && taskObj.files.length > 0 && typeof taskObj.files[0] === 'string' - ? taskObj.files as string[] : undefined) - || modificationPoints?.map(m => m.file).filter((f): f is string => !!f) - || [], - acceptance: (taskObj.acceptance as string[]) || [], + focus_paths: focusPaths, + acceptance, depends_on: (taskObj.depends_on as string[]) || [] }, - flow_control: flowControl ? { - implementation_approach: (flowControl.implementation_approach as Array<{ step: string; action: string }>) || [], - target_files: (flowControl.target_files as Array<{ path: string }>) || undefined - } : { - implementation_approach: implementation?.map((step, i) => ({ - step: `Step ${i + 1}`, - action: step as string - })) || [], - target_files: Array.isArray(taskObj.files) && taskObj.files.length > 0 && typeof taskObj.files[0] === 'string' - ? (taskObj.files as string[]).map(f => ({ path: f })) - : undefined + flow_control: { + implementation_approach: implApproach, + pre_analysis: preAnalysisSteps, + target_files: normalizedFiles + || (flowControl?.target_files as Array<{ path: string }>) || undefined, }, + // New flat format pass-through: let frontend normalizer consume these directly + convergence, + focus_paths: focusPaths, + pre_analysis: preAnalysisSteps, + implementation: implementation, + files: normalizedFiles, // Keep all original fields for raw JSON view _raw: task };