Both issue-devpipeline and team-planex executors now maintain
execution.md (overview + task table + summary) and
execution-events.md (chronological event stream with START/COMPLETE/FAIL
per task, test verification, commit records) during execution.
- Add tags: memory.tags to importMemories upsertMemory call to prevent
tag loss during cross-project import
- Guard buildCompressionMetadata against division by zero when
originalSize is 0
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.
When both prompt and target flags (--uncommitted/--base/--commit) are
provided together for codex review mode, warn user and drop the prompt
to avoid CLI argument conflict error.
Previously, parallel tasks assigned to the same role (e.g., multiple
EXPLORE-* tasks with owner: 'explorer') executed serially because only
one agent instance existed per role name. This adds conditional parallel
agent spawning with instance-specific names (explorer-1, explorer-2) and
--agent-name arg for role task discovery filtering.
Affected skills: team-ultra-analyze, team-quality-assurance,
team-brainstorm, team-issue. Single-task modes preserve backward
compatibility with original agent names.
Only log "Loaded X pending questions" when X > 0 to reduce noise
in CLI output. The message was appearing on every ccw command due to
module import chain, but is only meaningful for ccw view startup.
- Implemented Skill Hub page with tabs for remote, local, and installed skills.
- Added localization support for Chinese in skill-hub.json.
- Created API routes for fetching remote skills, listing local skills, and managing installed skills.
- Developed functionality for installing and uninstalling skills from both remote and local sources.
- Introduced caching mechanism for remote skills and handling updates for installed skills.
1. Race condition fix: Removed frontend direct lockSession call in
useOrchestratorExecution.ts - session locking now handled purely
via backend WebSocket broadcast (CLI_SESSION_LOCKED)
2. WebSocket handlers: Added handleSessionLockedMessage and
handleSessionUnlockedMessage to sessionManagerStore.ts
3. useWebSocket integration: Added case handlers for
CLI_SESSION_LOCKED and CLI_SESSION_UNLOCKED messages
4. API input validation: Added validation for sessionConfig,
stepTimeout, and errorStrategy in execute-in-session endpoint
5. Fixed wsBroadcast reference: Changed to broadcastToClients
from context
- Remove AgentList component from left sidebar
- Integrate orchestration plans display into ExecutionMonitorPanel
- Execution Monitor now shows both workflow executions and orchestration plans
- Cleaner sidebar with only session tree
- Add tag/name input field to CliConfigModal with auto-generation
- Auto-generate format: {tool}-{HHmmss} (e.g., gemini-143052)
- Add regenerate button for quick name changes
- Add i18n keys for new fields (en/zh)
Sessions are now grouped by tag in the sidebar for better organization.
- Replace dropdown menu with direct dialog button
- Remove unused state variables (selectedTool, launchMode, selectedShell)
- Update button icon to Plus and label to "New Session"
- Clean up i18n keys (remove unused tool/mode/shell options)
- Add confirmation dialog when closing pane with active session
- Add explicit "Close Session" button to terminate backend PTY
- Handle "session not found" scenario with user-friendly message
- Add i18n keys for new UI elements (en/zh)
- Remove codex-lens/build/ from version control
- Update .gitignore to exclude build directories
- Add ccw/.tmp-ccw-auth-home/ to gitignore (runtime temp)
- Implement tests for KeywordDetector including keyword detection, sanitization, and priority handling.
- Add tests for SessionStateService covering session validation, loading, saving, and state updates.
- Create tests for UserAbortDetector to validate user abort detection logic and pattern matching.
- Implemented `explorer` role for parallel codebase exploration using `cli-explore-agent`.
- Created `explore.md` command documentation detailing exploration strategy and execution steps.
- Established `synthesizer` role for integrating insights from explorations, analyses, and discussions.
- Developed `synthesize.md` command documentation outlining synthesis strategy and output format.
- Configured team settings in `team-config.json` to support new roles and pipeline modes.
- Added regression test for CodexLens bootstrap fallback to ensure robustness in error handling.
- Added new staged settings in config.py for coarse_k, lsp_depth, stage2_mode, and clustering strategy.
- Updated config-handlers.ts to handle new staged settings and map environment variables.
- Enhanced codexlens.json localization files for English and Chinese to include new staged settings.
- Modified astgrep_js_ts_processor.py to improve import handling for named imports.
- Updated JavaScript and TypeScript patterns to support new import formats.
- Added tests for staged settings loading and performance benchmarks for stage-2 expansion.
- Introduced a comprehensive template for generating epics and stories, including an index and individual epic files.
- Created a product brief template to outline product vision, problem statements, and target users.
- Developed a requirements PRD template to structure functional and non-functional requirements, including traceability and prioritization.
- Implemented ast-grep processors for JavaScript and TypeScript to extract relationships such as imports and inheritance.
- Added corresponding patterns for JavaScript and TypeScript to support relationship extraction.
- Established comparison tests to validate the accuracy of relationship extraction between tree-sitter and ast-grep methods.
- 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 effort level options (low, medium, high) in the CLI tool settings.
- Updated the SettingsPage and CliToolCard components to handle effort level updates.
- Enhanced CLI command options to accept effort level via --effort parameter.
- Modified backend routes to support effort level updates in tool configurations.
- Created a new CliViewerToolbar component for improved CLI viewer interactions.
- Implemented logic to manage and display execution statuses and layouts in the CLI viewer.
- Removed obsolete ccw-test command file.
- Updated ccw command to include new team workflows and collaborative planning features.
- Enhanced review-cycle skill with unified auto mode detection for streamlined user experience.
- Improved team-quality-assurance monitoring command to utilize consistent auto mode detection.
- Standardized auto mode detection across workflow-execute and workflow-multi-cli-plan skills.
- Introduced cycle workflows for integration testing and refactoring with self-iterating capabilities.
- Added detailed usage examples for new team workflows and collaborative planning commands.
- Updated QueueCard tests to use getAllByText for better resilience against multiple occurrences.
- Modified useCodexLens tests to check for error existence instead of specific message.
- Added mock for ResizeObserver in test setup to support components using it.
- Introduced integration tests for appStore and hooks interactions, covering locale and theme flows.
- Created layout-utils tests to validate pane manipulation functions.
- Added queryKeys tests to ensure correct key generation for workspace queries.
- Implemented utils tests for class name merging and memory metadata parsing.
- Remove Phase 5 (parallel role document update agents) - role analyses are now immutable
- Merge Phase 6/6.5 into single Spec Agent that sequentially generates all feature specs, feature-index.json, and synthesis-changelog.md
- Add conditional Review Agent triggered by complexity score (>= 4/8)
- Reduce agent calls from (N_roles + N_features) to 1 Spec + 0~1 Review
- Reduce total context from ~50K+ to ~15-20K words
- Add 4 design principles: immutable role outputs, spec as final artifact, single agent sequential generation, on-demand review
