Restructure lite-plan.md (844→668 lines, -176) and lite-execute.md (597→569 lines, -28) following agent document patterns. Move Data Structures sections to end as reference, simplify repeated content, improve hierarchical organization. All original content preserved.
Key changes:
- Data Structures moved to end (from beginning)
- Simplified Execution Process to avoid duplication
- Improved section hierarchy and flow
- Consistent structure across both documents
Issue found by Gemini analysis:
- executionContext.planObject.tasks was incorrectly documented as string[]
- Actual runtime structure is array of structured task objects (7 fields)
- This caused documentation mismatch between lite-plan and lite-execute
Fix:
- Update executionContext definition to show full task object structure
- Add comment clarifying it's an array of structured objects (7 fields each)
- Aligns with actual implementation and lite-execute consumption logic
Impact: Documentation only (no code changes, runtime behavior was already correct)
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)
Changes:
1. Initialize previousExecutionResults array in Step 5.1
2. Add id field to executionCalls objects (format: [Method-Index])
3. Add execution loop structure in Step 5.2 showing sequential processing
4. Clarify executionId comes from executionCalls[currentIndex].id
5. Add comments explaining ID storage for result collection
Benefits:
- Clear definition of where executionId comes from
- Explicit initialization of tracking variables
- Better understanding of execution flow and result collection
- Proper context continuity across multiple execution calls
Improvements:
1. Add plan summary in confirmation question for quick review
2. Add previousExecutionResults tracking for multi-execution flows
3. Include execution result collection mechanism after each call
4. Update both Agent and Codex execution prompts with context continuity
Benefits:
- Subsequent executions can see what previous calls completed
- Avoid duplicate work across multiple execution calls
- Better dependency management and task flow
- Clear context propagation: executionId, status, tasks, outputs, notes
Change Phase 4 confirmation flow from single-step to two-step process:
- Step 4.1: Display complete plan as readable text output
- Step 4.2: Collect three-dimensional input via AskUserQuestion
Benefits:
- Clearer plan presentation (not embedded in question)
- Simpler question interface focused on user decisions
- Better user experience with logical separation
- Deleted the `list` command for design runs.
- Removed the `update` command and its associated documentation.
- Introduced `design-sync` command to synchronize finalized design system references to brainstorming artifacts.
- Updated command references in `COMMAND_REFERENCE.md`, `GETTING_STARTED.md`, and `GETTING_STARTED_CN.md` to reflect the new command structure.
- Ensured all related documentation and output styles are consistent with the new command naming and functionality.
- Implemented the '/workflow:ui-design:list' command to list all available design runs with metadata including session, created time, and prototype count.
- Developed the '/workflow:ui-design:reference-page-generator' command to generate multi-component reference pages and documentation from design run extraction, including setup, validation, and preview generation phases.
- Added detailed error handling and usage examples for both commands to enhance user experience and clarity.
- Updated auto-parallel.md to clarify the task attachment model, emphasizing the orchestration of tasks through attachment rather than delegation. Improved descriptions of phases and execution flow.
- Revised plan.md, tdd-plan.md, test-fix-gen.md, and test-gen.md to simplify lifecycle patterns, replacing detailed patterns with concise lifecycle summaries.
- Modified reference-page-generator.md to streamline the component extraction process, focusing on layout templates and removing unnecessary complexity in the operations.
- Enhanced error handling and output messages across various workflows to improve clarity and user guidance.
- Introduced Task Attachment Model to clarify how SlashCommand invocations expand workflows by attaching sub-tasks to the current TodoWrite.
- Added Auto-Continue Mechanism details to explain dynamic task management and continuous execution across phases.
- Updated TodoWrite examples to reflect task attachment and collapsing behavior during workflow execution.
- Improved execution flow diagrams for both test-fix-gen and test-gen workflows to illustrate task attachment and phase completion.
- Emphasized critical aspects of continuous execution and task management in the documentation.
- fix(discover-design-files.sh): Fix script errors and expand framework support
* Fix variable quoting and conditional checks
* Remove keyword restrictions for JS file discovery
* Add support for .mjs, .cjs, .vue, .svelte files
* Now correctly discovers all JS/TS framework files recursively
- feat(import-from-code): Add optional gemini/qwen CLI analysis for agents
* Add CLI-Assisted Analysis step to Style/Animation/Layout agents
* Optional usage for large codebases (>20 files) or complex frameworks
* All CLI calls use analysis mode (READ-ONLY)
* Agent can use CLI output to guide file reading and token extraction
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
