Restructure cli-lite-planning-agent.md and cli-planning-agent.md following action-planning-agent.md's clear hierarchical pattern. Merge duplicate content, consolidate sections, and improve readability while preserving all original information.
Major changes:
- Add cli-lite-planning-agent.md for generating structured task objects
- Upgrade planObject.tasks from string[] to structured objects with 7 fields:
- title, file, action, description (what to do)
- implementation (3-7 steps on how to do it)
- reference (pattern, files, examples to follow)
- acceptance (verification criteria)
- Update lite-execute.md to format structured tasks for Agent/Codex execution
- Clean up agent files: remove "how to call me" sections (cli-planning-agent, cli-explore-agent)
- Update lite-plan.md to use cli-lite-planning-agent for Medium/High complexity tasks
Benefits:
- Execution agents receive complete "how to do" guidance instead of vague descriptions
- Each task includes specific file paths, implementation steps, and verification criteria
- Clear separation of concerns: agents only describe what they do, not how they are called
- Architecture validated by Gemini: 100% consistency, no responsibility leakage
Breaking changes: None (backward compatible via task.title || task fallback in lite-execute)
Introduce comprehensive test quality assurance framework to prevent "hollow tests"
from masking real issues. Optimize JSON data structures following minimal-but-sufficient principle.
Major Changes:
- Multi-layered test strategy (L0: Static, L1: Unit, L2: Integration, L3: E2E)
- New quality gate task (IMPL-001.5-review) validates tests before fix cycle
- Layer-aware failure diagnosis with test_type field support
- JSON simplification: removed redundant failure_context (~44% size reduction)
File Changes:
- new: cli-planning-agent.md - CLI analysis executor with layer-specific guidance
- mod: test-fix-gen.md - multi-layered test planning and quality gate generation
- mod: test-fix-agent.md - layer-aware test execution and failure classification
- mod: test-cycle-execute.md - 95% pass rate threshold with criticality assessment
Technical Details:
- test_type field tracks test layer (static/unit/integration/e2e)
- IMPL-fix-N.json simplified: removed 350 lines of redundant data
- Single source of truth: iteration-N-analysis.md contains full context
- Quality config: ~/.claude/workflows/test-quality-config.json (not in repo)
Benefits:
- Prevents symptom-level fixes through layer-specific diagnosis
- Ensures test quality with static analysis and coverage validation
- Reduces JSON file size by 44% while maintaining information completeness
- Enforces comprehensive test coverage (happy path + negative + edge cases)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Remove general-purpose agent in favor of universal-executor
- Enhance workflow session completion with better state management
- Improve context-gather with advanced filtering and validation
- Archive legacy prompt templates for reference
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Updated synthesis tool to enhance user interaction with multi-select options and improved question presentation in Chinese.
- Revised conflict resolution tool to allow batch processing of conflicts, increasing the limit from 4 to 10 per round and changing user interaction from AskUserQuestion to text output.
- Added context_package_path to task generation tools for better context management.
- Improved task generation schema to include context_package_path for enhanced context delivery.
- Updated CLI templates to reflect changes in task JSON schema, ensuring context_package_path is included.
- Updated references in various workflow commands to utilize role analysis documents instead of synthesis-specification.md.
- Modified CLI templates and command references to reflect the new architecture and document structure.
- Introduced conflict-resolution command to analyze and resolve conflicts between implementation plans and existing codebase.
- Deprecated synthesis role template and provided migration guidance for transitioning to the new role analysis approach.
- Updated implementation_approach in task-generate-tdd.md to use an array format with detailed steps for minimal code implementation and iterative testing.
- Enhanced task-generate.md to support CLI execution mode with Codex, including examples for task execution and session management.
- Modified test-task-generate.md to incorporate CLI execution mode, allowing Codex to autonomously generate tests and execute iterative test-fix cycles.
- Revised task-core.md and workflow-architecture.md to adopt a step-based implementation approach, improving clarity and dependency management in task execution.
- Improved documentation in workflow-architecture.md to clarify flow control structure and variable referencing.
- Remove Code Index MCP integration (focus on design trends only)
- Replace mcp__exa__get_code_context_exa with mcp__exa__web_search_exa for design trend research
- Add detailed shell script integration documentation:
- convert_tokens_to_css.sh: Token JSON to CSS conversion with usage patterns and error handling
- ui-instantiate-prototypes.sh: Template instantiation with auto-detection and mode options
- Update MCP use cases to focus on design trends, color/typography, and accessibility patterns
- Clarify that agent uses web search for current design trends, not code implementation
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Removed the generation of a unified consolidation report in the consolidate.md file, streamlining the output structure.
- Updated the extract.md file to prioritize the --base-path argument for session management and improved error handling for style variant detection.
- Enhanced generate.md to enforce critical requirements for layout templates, ensuring independence from other targets.
- Added a comprehensive analysis report for the ui-instantiate-prototypes.sh script, detailing issues with style variant mismatches and proposing solutions for validation and prevention.
Consolidate separate page/component modes into a unified target system to
reduce code duplication and simplify the workflow parameter model.
Changes:
- Merge --pages and --components into unified --targets parameter
- Add --target-type (auto|page|component) with intelligent detection
- Remove Phase 0d from explore-auto.md (131 lines of duplicate logic)
- Implement detect_target_type() helper for automatic classification
- Update generate.md to support adaptive wrapper generation
- Full HTML structure for pages
- Minimal wrapper for isolated components
- Update imitate-auto.md and update.md for parameter consistency
- Enhance ui-design-agent.md with adaptive design capabilities
- Maintain full backward compatibility with legacy syntax
Benefits:
- Code reduction: -35% in target inference logic (255 → 165 lines)
- Maintenance: Single unified logic path vs dual implementations
- Extensibility: Foundation for future mixed-mode support
- UX: Simpler parameter model with automatic type detection
Technical Details:
- explore-auto.md: 605 lines changed (unified Phase 0c)
- generate.md: 353 lines changed (targets + adaptive wrapper)
- Net change: +685 insertions, -504 deletions across 5 files
All existing workflows remain compatible via legacy parameter support.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
