1. extractStructuredTasks regex: /### (TASK-\d+|T\d+):/ was too strict,
failing when Gemini outputs fewer #'s or omits colon. Relaxed to
/#{1,3}\s*(TASK-\d+|T\d+):?\s*/ to tolerate format variations.
2. CLI Command Template CONTEXT field: added explicit instruction to use
Prior Analysis from task description as primary planning context when
exploration files are absent.
Revert the Phase 2 skip when no explorations. CLI execution should always
run but use Prior Analysis block from task description as primary context
when exploration files are absent.
Global CLAUDE.md sets `run_in_background: true` as default for CLI calls,
which conflicts with the agent's need for synchronous results. The agent
may have followed the global default, firing CLI in background and getting
no output to parse. Strengthen the instruction to explicitly override the
global default with `run_in_background: false`.
When cli-lite-planning-agent receives empty exploration context (from
analyze-with-file → lite-plan flow), it previously spent all tool budget
on CLI execution (Phase 2) leaving no budget for file writing (Phase 4).
Add explicit "Prior Analysis Fast Path" in Execution Flow: when prompt
contains "No exploration files", skip Phase 2 and generate plan directly
from task description's Prior Analysis block, preserving tool budget for
mandatory file output (plan.json + .task/*.json).
- Introduced `lite-plan` command for intelligent task analysis and planning.
- Implemented dynamic exploration and clarification phases based on task complexity.
- Added support for auto mode and forced exploration flags.
- Defined output artifacts and session structure for planning results.
- Enhanced execution process with context handoff to `lite-execute`.
chore(temp): create temporary memory content and import script
- Added `.temp-memory-content.txt` to store session details and execution plan.
- Implemented `temp-import-memory.cjs` to handle memory import using core-memory command.
- Ensured cleanup of temporary files after execution.
- Introduced SpecCategory and SpecScope types to categorize specs by workflow stage and scope (global/project).
- Updated Spec interface to include category and scope properties.
- Enhanced SpecCard component to display category and scope badges.
- Implemented category and scope filtering in SpecsSettingsPage.
- Updated localization files to support new category and scope labels.
- Modified spec loading commands to utilize category instead of keywords.
- Adjusted spec index builder to handle category and scope during spec parsing.
- Updated seed documents to include category information.
- Updated test cycle execution steps to streamline agent execution.
- Improved HookDialog component with enhanced validation messages and localization.
- Introduced SpecDialog component for better spec management.
- Added new hooks for fetching and updating specs list and frontmatter.
- Implemented API functions for specs list retrieval and index rebuilding.
- Added localization support for new specs settings and hooks.
- Enhanced SpecsSettingsPage to manage project and personal specs effectively.
- Updated CLI commands to support keyword-based spec loading.
- Improved spec index builder to categorize specs by workflow stages.
- Implement SpecDialog for managing spec details including title, read mode, priority, and keywords.
- Add validation and keyword management functionality.
- Integrate SpecDialog into SpecsSettingsPage for editing specs.
feat: create index file for specs components
- Export SpecCard, SpecDialog, and related types from a new index file for better organization.
feat: implement SpecsSettingsPage for managing specs and hooks
- Create main settings page with tabs for Project Specs, Personal Specs, Hooks, Injection, and Settings.
- Integrate SpecDialog and HookDialog for editing specs and hooks.
- Add search functionality and mock data for specs and hooks.
feat: add spec management API routes
- Implement API endpoints for listing specs, getting spec details, updating frontmatter, rebuilding indices, and initializing the spec system.
- Handle errors and responses appropriately for each endpoint.
- Added Phase 5: Plan Quality Check to cli-lite-planning-agent.md, detailing mandatory quality validation after plan generation.
- Introduced quality dimensions: completeness, granularity, dependencies, acceptance criteria, implementation steps, and constraint compliance.
- Specified CLI command format for quality check execution and expected output structure.
- Implemented result parsing and auto-fix strategies for minor issues.
- Updated integration flow to ensure quality check is executed before returning the plan to the orchestrator.
Refactor lite-plan.md to reflect internal quality check execution for medium/high complexity plans.
Create new brainstorm-with-file.md for interactive brainstorming workflow, detailing session setup, execution process, and implementation steps.
- Updated package name from `codexlens` to `codex-lens` in all relevant files to ensure consistency with `pyproject.toml`.
- Enhanced `findLocalPackagePath()` to always search for local paths, even when running from `node_modules`.
- Removed fallback logic for PyPI installation in several functions, providing clearer error messages for local installation failures.
- Added detailed documentation on installation steps and error handling for local development packages.
- Introduced a new summary document outlining the issues and fixes related to CodexLens installation.
- Replace $PROTO/$TMPL environment variable injection with systemRules/roles direct concatenation
- Append rules to END of prompt instead of prepending
- Change prompt field name from RULES to CONSTRAINTS in all prompts
- Default to universal-rigorous-style template when --rule not specified
- Update all .claude documentation, agents, commands, and skills
- Add streaming_content type support for Gemini delta messages
Breaking: Prompts now use CONSTRAINTS field instead of RULES
- Updated command patterns across documentation and templates to reflect the new CLI syntax.
- Enhanced CLI tool implementation to support reading prompts from files and multi-line inputs.
- Modified core components and views to ensure compatibility with the new command structure.
- Adjusted help messages and internationalization strings to align with the updated command format.
- Improved error handling and user notifications in the CLI execution flow.
- Introduced `help-i18n.js` for managing translations in Chinese and English for the help view.
- Created `help.js` to render the help view, including command categories, workflow diagrams, and CodexLens quick-start.
- Implemented search functionality with debounce for command filtering.
- Added workflow diagram rendering with Cytoscape.js integration.
- Developed tests for write-file verification, ensuring proper handling of small and large JSON files.
- Update cli-lite-planning-agent to serve both lite-plan and lite-fix
- Add schema-driven output (plan-json-schema or fix-plan-json-schema)
- Support both explorations (lite-plan) and diagnoses (lite-fix) context
- Remove CLI execution ID planning from lite-plan.md and lite-fix.md
- Delegate CLI execution ID assignment to agent when user selects CLI execution
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
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)
