- Add Post-Completion implementation in analyze-with-file Phase 4: write
handoff-lite-plan.json and call Skill with --from-analysis flag
- Add --from-analysis parsing in SKILL.md router (Step 0) to inject
analysisHandoff into workflowPreferences
- Reconstruct exploration context in lite-plan Phase 1 from upstream
analysis artifacts, skipping redundant exploration and clarification
- Tighten Low complexity criteria to truly trivial changes only
- Expand agent trigger: analysisHandoff or multi-angle exploration
forces cli-lite-planning-agent regardless of complexity
Add a new session sync command that updates both project-guidelines.json
and project-tech.json from session context in one shot. Replace inline
Step 6 (Update Development Index) in lite-execute with sync call, and
add auto-sync to Post-Completion Expansion across 6 execution commands.
Simplify session/complete by replacing Phase 4+5 with single sync call.
Implement 5 interconnected memorycore enhancements:
1. Tags backend: add tags TEXT column to memories table with migration,
JSON array storage, full CRUD support via upsertMemory/getMemory/getMemories
2. LLM auto-tag extraction: extend extraction prompt to produce tags,
parse and validate in pipeline, create CMEM from extraction results
3. Session summary API: expose rollout_summary via new REST endpoints
GET /api/core-memory/sessions/summaries and sessions/:id/summary
4. Hook injection: increase SESSION_START_LIMIT to 1500, add Component 5
(Recent Sessions) to UnifiedContextBuilder with 300-char budget
5. Tag filtering: add getMemoriesByTags() with json_each() for safe
SQL matching, wire through MCP tool, CLI --tags flag, REST ?tags= param
6. Solidify compress mode: add --type compress to solidify.md with
getRecentMemories(), archiveMemories(), buildCompressionMetadata()
Security fixes: safeParseTags() for corrupt DB data, json_each() instead
of LIKE injection, ESCAPE clause for searchSessionsByKeyword, singleton
store in unified-context-builder.
- Implemented CcwLitellmStatus component to display installation status and provide install/uninstall actions.
- Integrated hooks for managing installation and uninstallation processes.
- Added package discovery utility to locate local Python packages with environment variable and configuration support.
- Enhanced diagnostics with detailed search results for package paths.
Issues are stored solely in .workflow/issues/issues.jsonl via ccw issue create.
Wave/dependency info embedded in issue tags (wave-N) and extended_context.notes.
Session directory now only contains roadmap.md, strategy-assessment.json, and
optional exploration-codebase.json. team-planex consumes issues directly by ID.
- Introduced Phase 6: Post-Implementation Review with detailed steps for specialized reviews (quality, security, architecture, action items).
- Updated SKILL.md to reflect new phase and its execution lifecycle.
- Enhanced Flowchart component to conditionally display step statuses based on task tracking.
- Modified TaskDrawer to pass status tracking prop to Flowchart.
- Improved AgentList and other terminal dashboard components for better UI consistency and responsiveness.
- Removed GlobalKpiBar component as part of UI cleanup.
- Added issue detail preview in TerminalWorkbench for better user experience when no terminal is active.
- Updated localization files for new strings related to the terminal dashboard and workbench.
- Enhanced TaskListTab to conditionally render task stats and status dropdown based on task status tracking.
- 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.
- Implement TerminalTabBar for session tab management with status indicators and alert badges.
- Create TerminalWorkbench to combine TerminalTabBar and TerminalInstance for terminal session display.
- Add localization support for terminal dashboard in English and Chinese.
- Develop TerminalDashboardPage for the main layout of the terminal dashboard with a three-column structure.
- Introduce Zustand stores for session management and issue/queue integration, handling session groups, terminal metadata, and alert management.
- Create a monitor web worker for off-main-thread output analysis, detecting errors and stalls in terminal sessions.
- Define TypeScript types for terminal dashboard state management and integration.
- Introduced a new quality standards document outlining assessment criteria for team command .md files, including completeness, pattern compliance, integration, and consistency dimensions.
- Established quality gates and issue classification for errors, warnings, and informational notes.
- Created a comprehensive team command design patterns document detailing infrastructure and collaboration patterns, including message bus integration, YAML front matter requirements, task lifecycle, five-phase execution structure, and error handling.
- Included a pattern selection guide for collaboration scenarios to enhance team interaction models.
Move execute.md from commands/workflow/ to skills/workflow-execute/SKILL.md,
update all references in workflow-plan to use Skill(skill="workflow-execute")
instead of the old /workflow:execute command path.
- Introduced a new schema version (v2) with a global_relationships table.
- Implemented CRUD operations for file relationships, including update and delete functionalities.
- Added query capabilities for relationships by target and symbols.
- Created migration logic from v1 to v2 schema.
- Enhanced tests for global relationships, covering various scenarios including insertion, querying, and deletion.
docs: Add update-single command for generating module documentation
- Created a new command to generate manual-style documentation (CLAUDE.md) for a single module.
- Detailed execution process and implementation phases for the command.
- Included usage examples and error handling guidelines.
feat: Implement team command for CLI interface
- Added a new team command for logging and retrieving messages in a team message bus.
- Supported subcommands for logging, reading, listing, and checking status of messages.
- Included error handling and JSON output options.
test: Add comprehensive tests for global relationships
- Developed extensive tests for the global_relationships table in GlobalSymbolIndex.
- Covered schema creation, migration, CRUD operations, and performance benchmarks.
- Ensured project isolation and validated query functionalities for relationships.
refactor: rename variables for clarity in ReviewSessionPage and SessionsPage
fix: update version check logic in SettingsPage
chore: remove unused imports in TeamPage and session-detail components
fix: enhance error handling in MCP server
fix: apply default mode in edit-file tool handler
chore: remove tsbuildinfo file
docs: add Quick Plan & Execute phase documentation for issue discovery
chore: clean up ping output file
Fix 3 issues found by Gemini full-chain analysis:
1. (High) cross_cutting_specs path format mismatch: feature-index.json
uses relative paths ("role/file.md") but context-package uses full
paths (".workflow/.../role/file.md"). Changed action-planning-agent
to use endsWith() matching and read from context-package objects
instead of raw feature-index strings.
2. (Medium) Add explicit feature_index_path field to context-package
schema in context-search-agent, so task-generate-agent can read it
directly instead of hardcoding paths. Updated both single-module
and multi-module prompt templates with fallback logic.
3. (Medium) Expand synthesis_output in context-search-agent to include
feature_driven sub-object pointing to feature-index.json and
feature-specs/ directory alongside legacy synthesis-specification.md.
Requirements, architecture, and epics now output as directories with
individual files per design point (_index.md + REQ-*.md/ADR-*.md/EPIC-*.md),
linked via relative paths for better referencing and downstream consumption.
Phase 6 handoff bridge simplified to read directly from individual EPIC files.
Phase 6 now creates brainstorm_artifacts-compatible bridge files
(.brainstorming/guidance-specification.md, feature-index.json, feature-specs)
when handing off to workflow:plan or req-plan, enabling context-search-agent
auto-discovery without modifying downstream consumers.
- Created a new JSON file with benchmark results from the run on 2026-02-09.
- Added tests for the StandaloneLspManager to verify path normalization on Windows, including handling of percent-encoded URIs and ensuring plain Windows paths remain unchanged.
- Implemented a new color generation module to create CSS variables based on a single hue value, supporting both light and dark modes.
- Added unit tests for the color generation logic to ensure accuracy and robustness.
- Replaced dropdown location filter with tab navigation in RulesManagerPage and SkillsManagerPage for improved UX.
- Updated app store to manage custom theme hues and states, allowing for dynamic theme adjustments.
- Sanitized notification content before persisting to localStorage to prevent sensitive data exposure.
- Refactored memory retrieval logic to handle archived status more flexibly.
- Improved Tailwind CSS configuration with new gradient utilities and animations.
- Minor adjustments to SettingsPage layout for better visual consistency.
- Implemented Accordion component using Radix UI for collapsible sections.
- Created Zustand store to manage coordinator execution state, command chains, logs, and interactive questions.
- Added validation tests for CLI settings type definitions, ensuring type safety and correct behavior of helper functions.
- Updated code-developer, tdd-developer, and test-fix-agent to streamline execution modes based on task.meta.execution_config.method.
- Removed legacy command handling and introduced CLI handoff for 'cli' execution method.
- Enhanced buildCliHandoffPrompt to include task JSON path and improved context handling.
- Updated task-generate-agent and task-generate-tdd to reflect new execution method mappings and removed command field from implementation_approach.
- Improved CLI settings validation in CliSettingsModal with format and length checks.
- Added localization for new CLI settings messages in English and Chinese.
- Enhanced GPU selector to use localized strings for GPU types.
- Introduced TypeScript LSP setup documentation for better user guidance.
- analyze-with-file: Add dynamic direction generation from dimensions, support up to 4 parallel agent perspectives, enable cli-explore-agent parallelization
- brainstorm-with-file: Add dynamic direction generation from dimensions, add Agent-First guideline for complex tasks
- collaborative-plan-with-file: Add Understanding phase guidelines to prioritize latest documentation and resolve ambiguities with user clarification
Key improvements:
- Dimension-Direction Mapping replaces hard-coded options, enabling task-aware direction recommendations
- Multi-perspective parallel exploration (Analysis Perspectives, up to 4) with synthesis
- cli-explore-agent supports parallel execution per perspective for richer codebase context
- Agent-First principle: delegate complex tasks (code analysis, implementation) to agents/CLI instead of main process analysis
- Understanding phase emphasizes latest documentation discovery and clarification of ambiguities before planning
feat: Implement ConflictTab component to display conflict resolution decisions in session detail
feat: Create ImplPlanTab component to show implementation plan with modal viewer in session detail
feat: Develop ReviewTab component to display review findings by dimension in session detail
test: Add end-to-end tests for CodexLens Manager functionality including navigation, tab switching, and settings validation
- Implemented a utility function `detectJsonInLine` to identify and parse JSON data from different formats including direct JSON, tool calls, tool results, embedded JSON, and code blocks.
- Introduced `JsonDetectionResult` interface to standardize the detection results.
- Added a new test results file to track the status of tests.
Add /workflow:init-guidelines command that interactively fills project-guidelines.json
based on project analysis from project-tech.json. Features:
- 5-round questionnaire covering coding style, naming, file structure, documentation,
architecture, tech stack, performance, security, and quality rules
- Dynamic question generation based on detected language/framework/architecture
- Append/reset mode for existing guidelines
- Multi-select options with "Other" for custom input
Modify /workflow:init to ask user whether to run init-guidelines after initialization
when guidelines are empty (scaffold only).
- Add --with-commit flag to argument-hint and usage examples
- Auto-commit changes based on summary document after each agent task
- Minimal principle: only commit files modified by completed task
- Commit message format: {type}: {task-title} - {summary}
- Type mapping: feature→feat, bugfix→fix, refactor→refactor, etc.
- Created error context snapshots for Firefox, WebKit, and Chromium to capture UI state during API error monitoring.
- Implemented e2e tests for API error detection, including console errors, failed API requests, and proxy errors.
- Added functionality to ignore specific API patterns in monitoring assertions.
- Ensured tests validate the monitoring system's ability to detect and report errors effectively.
Implement two major enhancements to test generation workflow:
1. Gemini Test Enhancement (Phase 1.5)
- Add Gemini CLI analysis for comprehensive test suggestions
- Generate enriched test specifications for L1-L3 test layers
- Focus on API contracts, integration patterns, error scenarios
- Create gemini-enriched-suggestions.md as artifact
2. Planning Notes Mechanism (test-planning-notes.md)
- Similar to plan.md's planning-notes pattern
- Record Test Intent (Phase 1)
- Embed complete Gemini enrichment (Phase 1.5)
- Track consolidated test requirements
- Support N+1 context with decisions and deferred items
Implementation Details:
- Created Gemini prompt template: test-suggestions-enhancement.txt
- Enhanced test-task-generate.md with Phase 1, 1.5, 2 logic
- Gemini content embedded in planning-notes for single source of truth
- test-action-planning-agent reads both TEST_ANALYSIS_RESULTS.md and test-planning-notes.md
- Backward compatible: Phase 1.5 is optional enhancement
Benefits:
- Comprehensive test coverage (API, integration, error scenarios)
- Full traceability of test planning process
- Consolidated context in one file for easy review
- Preserved Gemini output as independent artifact
- Implemented navigation.spec.ts to test language switching and translation of navigation elements.
- Created sessions-page.spec.ts to verify translations on the sessions page, including headers, status badges, and date formatting.
- Developed settings-page.spec.ts to ensure settings page content is translated and persists across sessions.
- Added skills-page.spec.ts to validate translations for skill categories, action buttons, and empty states.
- Add dimensions I (Constraints Compliance) and J (N+1 Context Validation)
- Verify tasks respect Consolidated Constraints from planning-notes.md
- Detect deferred items incorrectly included in current plan
- Check decision contradictions against N+1 Decisions table
