- Added new benchmark result files: compare_2026-02-09_score_fast3.json and compare_2026-02-09_score_fast4.json.
- Implemented KeepAliveLspBridge to maintain a persistent LSP connection across multiple queries, improving performance.
- Created unit tests for staged clustering strategies in test_staged_stage3_fast_strategies.py, ensuring correct behavior of score and dir_rr strategies.
Embed a real-time shared context mechanism (coordination/discoveries.ndjson)
into all 4 agent roles, eliminating redundant codebase exploration. Each agent
reads the board on start, skips covered areas, and appends new findings as
NDJSON entries for other agents to consume.
Key additions per file:
- SKILL.md: Design principle #8, discovery type table with dedup keys and
required data fields, board lifecycle rules
- 02-agent-execution.md: Self-sufficient discovery protocol snippet in each
spawn prompt with write method, required fields, and dedup keys
- 4 role files: Full Shared Discovery Protocol section with board location,
lifecycle, physical write method (Bash echo >>), reads/writes tables with
dedup keys and required data schemas, and embedded Read/Write steps in
execution process
- Added argument parsing and prep package loading in session initialization.
- Implemented validation checks for prep-package.json integrity.
- Integrated prep package data into cycle state, including task refinement and auto-iteration settings.
- Updated agent execution to utilize source references and focus directives from prep package.
- Modified context gathering and test context generation to reference active workflow paths.
- Introduced a new interactive prompt for pre-flight checklist and task quality assessment.
- Created a detailed schema and integration specification for prep-package.json.
- Ensured all relevant phases validate and utilize the prep package effectively.
- Implemented E2E tests for code relationship visualization in Graph Explorer.
- Added tests for archived session management in History, including search, filter, restore, and delete functionalities.
- Created tests for workflow orchestration in Orchestrator, covering node creation, connection, deletion, and workflow management.
- Developed tests for project statistics and timeline visualization in Project, including error handling and internationalization checks.
According to OpenAI Codex skill specification, SKILL.md files must have both
'name' and 'description' fields in YAML frontmatter. Added missing 'name' field
to all three skills:
- CCW Loop
- CCW Loop-B
- Parallel Dev Cycle
Also enhanced ccw-loop description with Chinese trigger keywords for better
multi-language support.
- Introduced a new specification for agent communication optimization focusing on file references instead of content transfer to enhance efficiency and reduce message size.
- Established a coordination protocol detailing communication channels, message formats, and dependency resolution strategies among agents (RA, EP, CD, VAS).
- Created a unified progress format specification for all agents, standardizing documentation structure and versioning practices.
