catlog22/Claude-Code-Workflow
1
0
Fork 0
mirror of https://github.com/catlog22/Claude-Code-Workflow.git synced 2026-02-12 02:37:45 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: Optimize TDD workflow with streamlined file structure and test-gen integration

Browse Source 
## TDD Workflow Enhancements

### File Structure Optimization
- **Eliminated**: TDD_PLAN.md (merged into unified IMPL_PLAN.md)
- **Eliminated**: .process/TDD_TASK_BREAKDOWN.md (enhanced ANALYSIS_RESULTS.md instead)
- **Unified**: Single IMPL_PLAN.md with TDD Task Chains section
- **Result**: Reduced 2 files per TDD session (-33% file count)

### Test-Gen Integration
- Added test coverage analysis phase (Phase 3: test-context-gather)
- Integrated iterative test-fix-cycle into Green phase (IMPL tasks)
- Gemini diagnosis with bug-fix template for test failures
- Auto-revert safety mechanism (max_iterations protection)
- Manual fix by default, optional Codex automation (--use-codex flag)

### Workflow Improvements
- 6-phase TDD planning (added test coverage analysis)
- ANALYSIS_RESULTS.md enhanced with TDD breakdown structure
- IMPL tasks include test-fix-cycle configuration
- Unified IMPL_PLAN.md structure: frontmatter + TDD Task Chains + standard sections

### Configuration
- meta.max_iterations: 3 (TDD) vs 5 (test-gen)
- meta.use_codex: false (default manual fixes)
- workflow_type: "tdd" in IMPL_PLAN.md frontmatter

### Benefits
- Eliminated redundancy (2 fewer files, 1 less Gemini call)
- Context-aware TDD (not greenfield-only)
- Faster feedback (test-fix-cycle in Green phase)
- Autonomous recovery (auto-diagnose and fix)
- Backward compatible (no breaking changes)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
catlog22
2025-10-04 20:11:12 +08:00
parent 73bd0b2832
commit 7047cae356
4 changed files with 381 additions and 121 deletions
Download Patch File Download Diff File Expand all files Collapse all files

199
.claude/commands/workflow/tools/task-generate-tdd.md
View File

@@ -20,6 +20,9 @@ Generate TDD-specific task chains from analysis results with enforced Red-Green-
- **Phase-Explicit**: Each task marked with Red/Green/Refactor phase
- **Artifact-Aware**: Integrates brainstorming outputs
- **Memory-First**: Reuse loaded documents from memory
- **Context-Aware**: Analyzes existing codebase and test patterns
- **Iterative Green Phase**: Auto-diagnose and fix test failures with Gemini + optional Codex
- **Safety-First**: Auto-revert on max iterations to prevent broken state
## Core Responsibilities
- Parse analysis results and identify testable features
@@ -47,32 +50,18 @@ Generate TDD-specific task chains from analysis results with enforced Red-Green-
- Else: Scan `.workflow/{session_id}/.brainstorming/` directory
- Detect: synthesis-specification.md, topic-framework.md, role analyses
### Phase 2: TDD Task Analysis
### Phase 2: TDD Task JSON Generation
#### Gemini TDD Breakdown
```bash
cd project-root && ~/.claude/scripts/gemini-wrapper -p "
PURPOSE: Generate TDD task breakdown with Red-Green-Refactor chains
TASK: Analyze ANALYSIS_RESULTS.md and create TDD-structured task breakdown
CONTEXT: @{.workflow/{session_id}/ANALYSIS_RESULTS.md,.workflow/{session_id}/.brainstorming/*}
EXPECTED:
- Feature list with testable requirements (identify 3-8 features)
- Test cases for each feature (Red phase) - specific test scenarios
- Implementation requirements (Green phase) - minimal code to pass
- Refactoring opportunities (Refactor phase) - quality improvements
**Input**: Use `.process/ANALYSIS_RESULTS.md` directly (enhanced with TDD structure from concept-enhanced phase)
**Note**: The ANALYSIS_RESULTS.md now includes TDD-specific breakdown:
- Feature list with testable requirements
- Test cases for Red phase
- Implementation requirements for Green phase
- Refactoring opportunities
- Task dependencies and execution order
- Focus paths for each phase
RULES:
- Each feature must have TEST → IMPL → REFACTOR chain
- Tests must define clear failure conditions
- Implementation must be minimal to pass tests
- Refactoring must maintain green tests
- Output structured markdown for task generation
- Maximum 10 features (30 total tasks)
" > .workflow/{session_id}/.process/TDD_TASK_BREAKDOWN.md
```
### Phase 3: TDD Task JSON Generation
### Phase 3: Enhanced IMPL_PLAN.md Generation
#### Task Chain Structure
For each feature, generate 3 tasks with ID format:
@@ -145,19 +134,23 @@ For each feature, generate 3 tasks with ID format:
"meta": {
"type": "feature",
"agent": "@code-developer",
"tdd_phase": "green"
"tdd_phase": "green",
"max_iterations": 3,
"use_codex": false
},
"context": {
"requirements": [
"Implement minimal AuthService to pass TEST-1.1",
"Handle valid and invalid credentials",
"Return appropriate success/error responses"
"Return appropriate success/error responses",
"If tests fail after implementation, diagnose and fix iteratively"
],
"focus_paths": ["src/auth/AuthService.ts", "tests/auth/login.test.ts"],
"acceptance": [
"All tests in TEST-1.1 pass",
"Implementation is minimal and focused",
"No over-engineering or premature optimization"
"No over-engineering or premature optimization",
"Test failures resolved within iteration limit"
],
"depends_on": ["TEST-1.1"]
},
@@ -172,21 +165,83 @@ For each feature, generate 3 tasks with ID format:
},
{
"step": "verify_tests_failing",
"action": "Confirm tests are currently failing",
"action": "Confirm tests are currently failing (Red phase validation)",
"command": "bash(npm test -- tests/auth/login.test.ts || echo 'Tests failing as expected')",
"output_to": "initial_test_status",
"on_error": "warn"
},
{
"step": "load_test_context",
"action": "Load test patterns and framework info",
"command": "bash(cat .workflow/WFS-xxx/.process/test-context-package.json 2>/dev/null || echo '{}')",
"output_to": "test_context",
"on_error": "skip_optional"
}
],
"implementation_approach": {
"task_description": "Write minimal code to pass tests, then enter iterative fix cycle if they still fail",
"initial_implementation": [
"Write minimal code based on test requirements",
"Execute test suite: bash(npm test -- tests/auth/login.test.ts)",
"If tests pass → Complete task",
"If tests fail → Capture failure logs and proceed to test-fix cycle"
],
"test_fix_cycle": {
"max_iterations": 3,
"cycle_pattern": "gemini_diagnose → manual_fix (or codex if meta.use_codex=true) → retest",
"tools": {
"diagnosis": "gemini-wrapper (MODE: analysis, uses bug-fix template)",
"fix_application": "manual (default) or codex if meta.use_codex=true",
"verification": "bash(npm test -- tests/auth/login.test.ts)"
},
"exit_conditions": {
"success": "all_tests_pass",
"failure": "max_iterations_reached"
},
"steps": [
"ITERATION LOOP (max 3):",
" 1. Gemini Diagnosis:",
" bash(cd .workflow/WFS-xxx/.process && ~/.claude/scripts/gemini-wrapper --all-files -p \"",
" PURPOSE: Diagnose TDD Green phase test failure iteration [N]",
" TASK: Systematic bug analysis and fix recommendations",
" MODE: analysis",
" CONTEXT: @{CLAUDE.md,**/*CLAUDE.md}",
" Test output: [test_failures]",
" Test requirements: [test_requirements]",
" Implementation: [focus_paths]",
" EXPECTED: Root cause analysis, code path tracing, targeted fixes",
" RULES: $(cat ~/.claude/prompt-templates/bug-fix.md) | Bug: [test_failure_description]",
" Minimal surgical fixes only - stay in Green phase",
" \" > green-fix-iteration-[N]-diagnosis.md)",
" 2. Apply Fix (check meta.use_codex):",
" IF meta.use_codex=false (default): Present diagnosis to user for manual fix",
" IF meta.use_codex=true: Codex applies fix automatically",
" 3. Retest: bash(npm test -- tests/auth/login.test.ts)",
" 4. If pass → Exit loop, complete task",
" If fail → Continue to next iteration",
"IF max_iterations reached: Revert changes, report failure"
]
}
},
"post_completion": [
{
"step": "verify_tests_passing",
"action": "Confirm all tests now pass",
"action": "Confirm all tests now pass (Green phase achieved)",
"command": "bash(npm test -- tests/auth/login.test.ts)",
"output_to": "final_test_status",
"on_error": "fail"
}
]
],
"error_handling": {
"max_iterations_reached": {
"action": "revert_all_changes",
"commands": [
"bash(git reset --hard HEAD)",
"bash(echo 'TDD Green phase failed: Unable to pass tests within 3 iterations' > .workflow/WFS-xxx/.process/green-phase-failure.md)"
],
"report": "Generate failure report in .summaries/IMPL-1.1-failure-report.md"
}
}
}
}
```
@@ -248,19 +303,31 @@ For each feature, generate 3 tasks with ID format:
}
```
### Phase 4: TDD_PLAN.md Generation
### Phase 4: Unified IMPL_PLAN.md Generation
Generate TDD-specific plan with:
- Feature breakdown
- Red-Green-Refactor chains
- Execution order
- TDD compliance checkpoints
Generate single comprehensive IMPL_PLAN.md with:
### Phase 5: Enhanced IMPL_PLAN.md Generation
**Frontmatter**:
```yaml
---
identifier: WFS-{session-id}
workflow_type: "tdd"
feature_count: N
task_count: 3N
tdd_chains: N
---
```
Generate standard IMPL_PLAN.md with TDD context reference.
**Structure**:
1. **Summary**: Project overview
2. **TDD Task Chains** (TDD-specific section):
- Visual representation of TEST → IMPL → REFACTOR chains
- Feature-by-feature breakdown with phase indicators
3. **Task Breakdown**: Standard task listing
4. **Implementation Strategy**: Execution approach
5. **Success Criteria**: Acceptance conditions
### Phase 6: TODO_LIST.md Generation
### Phase 5: TODO_LIST.md Generation
Generate task list with TDD phase indicators:
```markdown
@@ -270,7 +337,7 @@ Generate task list with TDD phase indicators:
- [ ] **REFACTOR-1.1**: Refactor implementation (🔵 REFACTOR) [depends: IMPL-1.1] → [📋](./.task/REFACTOR-1.1.json)
```
### Phase 7: Session State Update
### Phase 6: Session State Update
Update workflow-session.json with TDD metadata:
```json
@@ -285,18 +352,18 @@ Update workflow-session.json with TDD metadata:
## Output Files Structure
```
.workflow/{session-id}/
├── IMPL_PLAN.md # Standard implementation plan
├── TDD_PLAN.md # TDD-specific plan ⭐ NEW
├── IMPL_PLAN.md # Unified plan with TDD Task Chains section
├── TODO_LIST.md # Progress tracking with TDD phases
├── .task/
│ ├── TEST-1.1.json # Red phase task
│ ├── IMPL-1.1.json # Green phase task
│ ├── IMPL-1.1.json # Green phase task (with test-fix-cycle)
│ ├── REFACTOR-1.1.json # Refactor phase task
│ └── ...
└── .process/
├── ANALYSIS_RESULTS.md # Input from concept-enhanced
├── TDD_TASK_BREAKDOWN.md # Gemini TDD breakdown ⭐ NEW
└── context-package.json # Input from context-gather
├── ANALYSIS_RESULTS.md # Enhanced with TDD breakdown from concept-enhanced
├── test-context-package.json # Test coverage analysis
├── context-package.json # Input from context-gather
└── green-fix-iteration-*.md # Fix logs from Green phase
```
## Validation Rules
@@ -356,13 +423,49 @@ Structure:
- Feature 2: TEST-2.1 → IMPL-2.1 → REFACTOR-2.1
Plans generated:
- TDD Plan: .workflow/WFS-auth/TDD_PLAN.md
- Implementation Plan: .workflow/WFS-auth/IMPL_PLAN.md
- Unified Plan: .workflow/WFS-auth/IMPL_PLAN.md (includes TDD Task Chains section)
Next: /workflow:execute or /workflow:tdd-verify
```
## Test Coverage Analysis Integration
The TDD workflow includes test coverage analysis (via `/workflow:tools:test-context-gather`) to:
- Detect existing test patterns and conventions
- Identify current test coverage gaps
- Discover test framework and configuration
- Enable integration with existing tests
This makes TDD workflow context-aware instead of assuming greenfield scenarios.
## Iterative Green Phase with Test-Fix Cycle
IMPL (Green phase) tasks include automatic test-fix cycle:
**Process Flow**:
1. **Initial Implementation**: Write minimal code to pass tests
2. **Test Execution**: Run test suite
3. **Success Path**: Tests pass → Complete task
4. **Failure Path**: Tests fail → Enter iterative fix cycle:
- **Gemini Diagnosis**: Analyze failures with bug-fix template
- **Fix Application**: Manual (default) or Codex (if meta.use_codex=true)
- **Retest**: Verify fix resolves failures
- **Repeat**: Up to max_iterations (default: 3)
5. **Safety Net**: Auto-revert all changes if max iterations reached
**Key Benefits**:
- ✅ Faster feedback loop within Green phase
- ✅ Autonomous recovery from initial implementation errors
- ✅ Systematic debugging with Gemini's bug-fix template
- ✅ Safe rollback prevents broken TDD state
## Configuration Options
- **meta.max_iterations**: Number of fix attempts (default: 3 for TDD, 5 for test-gen)
- **meta.use_codex**: Enable Codex automated fixes (default: false, manual)
## Related Commands
- `/workflow:tdd-plan` - Orchestrates TDD workflow planning
- `/workflow:tdd-plan` - Orchestrates TDD workflow planning (6 phases)
- `/workflow:tools:test-context-gather` - Analyzes test coverage
- `/workflow:execute` - Executes TDD tasks in order
- `/workflow:tdd-verify` - Verifies TDD compliance
- `/workflow:test-gen` - Post-implementation test generation

125
.claude/commands/workflow/tools/test-task-generate.md
View File

@@ -1,24 +1,25 @@
---
name: test-task-generate
description: Generate test-fix task JSON with iterative test-fix-retest cycle specification
usage: /workflow:tools:test-task-generate --session <test-session-id>
argument-hint: "--session WFS-test-session-id"
usage: /workflow:tools:test-task-generate [--use-codex] --session <test-session-id>
argument-hint: "[--use-codex] --session WFS-test-session-id"
examples:
- /workflow:tools:test-task-generate --session WFS-test-auth
- /workflow:tools:test-task-generate --use-codex --session WFS-test-auth
---
# Test Task Generation Command
## Overview
Generate specialized test-fix task JSON with comprehensive test-fix-retest cycle specification, including Gemini diagnosis and Codex resume mechanism for intelligent failure resolution.
Generate specialized test-fix task JSON with comprehensive test-fix-retest cycle specification, including Gemini diagnosis (using bug-fix template) and manual fix workflow (Codex automation only when explicitly requested).
## Core Philosophy
- **Analysis-Driven Test Generation**: Use TEST_ANALYSIS_RESULTS.md from test-concept-enhanced
- **Agent-Based Test Creation**: Call @code-developer agent for comprehensive test generation
- **Coverage-First**: Generate all missing tests before execution
- **Test Execution**: Execute complete test suite after generation
- **Gemini Diagnosis**: Use Gemini for root cause analysis and fix suggestions
- **Codex Resume**: Apply fixes using `codex exec "..." resume --last` for context continuity
- **Gemini Diagnosis**: Use Gemini for root cause analysis and fix suggestions (references bug-fix template)
- **Manual Fixes First**: Apply fixes manually by default, codex only when explicitly needed
- **Iterative Refinement**: Repeat test-analyze-fix-retest cycle until all tests pass
- **Surgical Fixes**: Minimal code changes, no refactoring during test fixes
- **Auto-Revert**: Rollback all changes if max iterations reached
@@ -26,27 +27,32 @@ Generate specialized test-fix task JSON with comprehensive test-fix-retest cycle
## Core Responsibilities
- Parse TEST_ANALYSIS_RESULTS.md from test-concept-enhanced
- Extract test requirements and generation strategy
- Parse `--use-codex` flag to determine fix mode (manual vs automated)
- Generate test generation subtask calling @code-developer
- Generate test execution and fix cycle task JSON
- Configure Gemini diagnosis and Codex execution workflow
- Generate test execution and fix cycle task JSON with appropriate fix mode
- Configure Gemini diagnosis workflow (bug-fix template) and manual/Codex fix application
- Create test-oriented IMPL_PLAN.md and TODO_LIST.md with test generation phase
## Execution Lifecycle
### Phase 1: Input Validation & Discovery
1. **Test Session Validation**
1. **Parameter Parsing**
- Parse `--use-codex` flag from command arguments
- Store flag value for IMPL-002.json generation
2. **Test Session Validation**
- Load `.workflow/{test-session-id}/workflow-session.json`
- Verify `workflow_type: "test_session"`
- Extract `source_session_id` from metadata
2. **Test Analysis Results Loading**
3. **Test Analysis Results Loading**
- **REQUIRED**: Load `.workflow/{test-session-id}/.process/TEST_ANALYSIS_RESULTS.md`
- Parse test requirements by file
- Extract test generation strategy
- Identify test files to create with specifications
3. **Test Context Package Loading**
4. **Test Context Package Loading**
- Load `.workflow/{test-session-id}/.process/test-context-package.json`
- Extract test framework configuration
- Extract coverage gaps and priorities
@@ -183,13 +189,15 @@ Generate **TWO task JSON files**:
"agent": "@test-fix-agent",
"source_session": "[sourceSessionId]",
"test_framework": "jest|pytest|cargo|detected",
"max_iterations": 5
"max_iterations": 5,
"use_codex": false // Set to true if --use-codex flag present
},
"context": {
"requirements": [
"Execute complete test suite (generated in IMPL-001)",
"Diagnose test failures using Gemini analysis",
"Fix failures using Codex with resume mechanism",
"Diagnose test failures using Gemini analysis with bug-fix template",
"Present fixes to user for manual application (default)",
"Use Codex ONLY if user explicitly requests automation",
"Iterate until all tests pass or max iterations reached",
"Revert changes if unable to fix within iteration limit"
],
@@ -272,14 +280,14 @@ Generate **TWO task JSON files**:
}
],
"implementation_approach": {
"task_description": "Execute iterative test-fix-retest cycle using Gemini diagnosis and Codex execution",
"task_description": "Execute iterative test-fix-retest cycle using Gemini diagnosis (bug-fix template) and manual fixes (Codex only if explicitly needed)",
"test_fix_cycle": {
"max_iterations": 5,
"cycle_pattern": "test → gemini_diagnose → codex_fix_resume → retest",
"cycle_pattern": "test → gemini_diagnose → manual_fix (or codex if needed) → retest",
"tools": {
"test_execution": "bash(test_command)",
"diagnosis": "gemini-wrapper (MODE: analysis)",
"fix_application": "codex exec resume --last (MODE: write)",
"diagnosis": "gemini-wrapper (MODE: analysis, uses bug-fix template)",
"fix_application": "manual (default) or codex exec resume --last (if explicitly needed)",
"verification": "bash(test_command) + regression_check"
},
"exit_conditions": {
@@ -303,30 +311,36 @@ Generate **TWO task JSON files**:
" WHILE (tests failing AND current_iteration < max_iterations):",
" current_iteration++",
" ",
" STEP 2.1: Gemini Diagnosis",
" STEP 2.1: Gemini Diagnosis (using bug-fix template)",
" - Prepare diagnosis context:",
" * Test failure output from previous run",
" * Source files from focus_paths",
" * Implementation summaries from source session",
" - Execute Gemini analysis:",
" bash(cd .workflow/WFS-test-[session]/.process && ~/.claude/scripts/gemini-wrapper -p \"",
" - Execute Gemini analysis with bug-fix template:",
" bash(cd .workflow/WFS-test-[session]/.process && ~/.claude/scripts/gemini-wrapper --all-files -p \"",
" PURPOSE: Diagnose test failure iteration [N] and propose minimal fix",
" TASK: Analyze test output and identify root cause with specific code change",
" TASK: Systematic bug analysis and fix recommendations for test failure",
" MODE: analysis",
" CONTEXT: Test output: [test_failures]",
" CONTEXT: @{CLAUDE.md,**/*CLAUDE.md}",
" Test output: [test_failures]",
" Source files: [focus_paths]",
" Implementation: [implementation_context]",
" EXPECTED: Root cause analysis with fix in format:",
" FILE: path/to/file.ts",
" FUNCTION: functionName",
" LINES: 45-52",
" CHANGE: Specific code modification to apply",
" RULES: Minimal surgical fixes only - no refactoring",
" Focus on test failure, not code quality",
" EXPECTED: Root cause analysis, code path tracing, targeted fixes",
" RULES: $(cat ~/.claude/prompt-templates/bug-fix.md) | Bug: [test_failure_description]",
" Minimal surgical fixes only - no refactoring",
" \" > fix-iteration-[N]-diagnosis.md)",
" - Parse diagnosis → extract fix_suggestion and target_files",
" - Present fix to user for manual application (default)",
" ",
" STEP 2.2: Codex Fix with Resume Mechanism",
" STEP 2.2: Apply Fix (Based on meta.use_codex Flag)",
" ",
" IF meta.use_codex = false (DEFAULT):",
" - Present Gemini diagnosis to user for manual fix",
" - User applies fix based on diagnosis recommendations",
" - Stage changes: bash(git add -A)",
" - Store fix log: .process/fix-iteration-[N]-changes.log",
" ",
" IF meta.use_codex = true (--use-codex flag present):",
" - Stage current changes (if valid git repo): bash(git add -A)",
" - First iteration: Start new Codex session",
" codex -C [project_root] --full-auto exec \"",
@@ -391,8 +405,8 @@ Generate **TWO task JSON files**:
" Analyze existing test files",
" Identify files without tests",
" IF tests missing:",
" Generate tests using Codex",
" Verify test generation successful",
" Report to user (no automatic generation)",
" Wait for user to generate tests or request automation",
" ELSE:",
" Skip to Phase 1",
"PHASE 1: Initial Test Execution",
@@ -401,8 +415,10 @@ Generate **TWO task JSON files**:
" ELSE → Store failures, proceed to Phase 2",
"PHASE 2: Iterative Fix Cycle (max 5 iterations)",
" LOOP (max 5 times):",
" 1. Gemini diagnoses failure → fix suggestion",
" 2. Codex applies fix (resume for continuity)",
" 1. Gemini diagnoses failure with bug-fix template → fix suggestion",
" 2. Check meta.use_codex flag:",
" - IF false (default): Present fix to user for manual application",
" - IF true (--use-codex): Codex applies fix with resume for continuity",
" 3. Retest and check results",
" 4. IF pass → Exit loop to Phase 3",
" 5. ELSE → Continue with updated context",
@@ -490,15 +506,17 @@ Diagnose and fix all test failures using iterative Gemini analysis and Codex exe
## Test-Fix-Retest Cycle
- **Max Iterations**: 5
- **Diagnosis Tool**: Gemini (analysis mode)
- **Fix Tool**: Codex (resume mechanism)
- **Diagnosis Tool**: Gemini (analysis mode with bug-fix template from bug-index.md)
- **Fix Tool**: Manual (default, meta.use_codex=false) or Codex (if --use-codex flag, meta.use_codex=true)
- **Verification**: Bash test execution + regression check
### Cycle Workflow
1. **Initial Test**: Execute full suite, capture failures
2. **Iterative Fix Loop** (max 5 times):
- Gemini diagnoses failure → surgical fix suggestion
- Codex applies fix using resume for context continuity
- Gemini diagnoses failure using bug-fix template → surgical fix suggestion
- Check meta.use_codex flag:
- If false (default): Present fix to user for manual application
- If true (--use-codex): Codex applies fix with resume for context continuity
- Retest and verify (check for regressions)
- Continue until all pass or max iterations reached
3. **Final Validation**: Confirm all tests pass, certify code
@@ -596,9 +614,17 @@ Diagnose and fix all test failures using iterative Gemini analysis and Codex exe
### Basic Usage
```bash
# Manual fix mode (default)
/workflow:tools:test-task-generate --session WFS-test-auth
# Automated Codex fix mode
/workflow:tools:test-task-generate --use-codex --session WFS-test-auth
```
### Flag Behavior
- **No flag**: `meta.use_codex=false`, manual fixes presented to user
- **--use-codex**: `meta.use_codex=true`, Codex automatically applies fixes with resume mechanism
## Related Commands
- `/workflow:test-gen` - Creates test session and calls this tool
- `/workflow:tools:context-gather` - Provides cross-session context
@@ -610,15 +636,20 @@ Diagnose and fix all test failures using iterative Gemini analysis and Codex exe
The `@test-fix-agent` will execute the task by following the `flow_control.implementation_approach` specification:
1. **Load task JSON**: Read complete test-fix task from `.task/IMPL-001.json`
2. **Execute pre_analysis**: Load source context, discover framework, analyze tests
3. **Phase 1**: Run initial test suite
4. **Phase 2**: If failures, enter iterative loop:
- Use Gemini for diagnosis (analysis mode)
- Use Codex resume for fixes (maintains context)
1. **Load task JSON**: Read complete test-fix task from `.task/IMPL-002.json`
2. **Check meta.use_codex**: Determine fix mode (manual or automated)
3. **Execute pre_analysis**: Load source context, discover framework, analyze tests
4. **Phase 1**: Run initial test suite
5. **Phase 2**: If failures, enter iterative loop:
- Use Gemini for diagnosis (analysis mode with bug-fix template)
- Check meta.use_codex flag:
- If false (default): Present fix suggestions to user for manual application
- If true (--use-codex): Use Codex resume for automated fixes (maintains context)
- Retest and check for regressions
- Repeat max 5 times
5. **Phase 3**: Generate summary and certify code
6. **Error Recovery**: Revert changes if max iterations reached
6. **Phase 3**: Generate summary and certify code
7. **Error Recovery**: Revert changes if max iterations reached
The agent uses the `codex exec "..." resume --last` pattern to maintain conversation context across multiple fix iterations, ensuring consistency and learning from previous attempts.
**Bug Diagnosis Template**: Uses bug-fix.md template as referenced in bug-index.md for systematic root cause analysis, code path tracing, and targeted fix recommendations.
**Codex Usage**: The agent uses `codex exec "..." resume --last` pattern ONLY when meta.use_codex=true (--use-codex flag present) to maintain conversation context across multiple fix iterations, ensuring consistency and learning from previous attempts.