Commit Graph

3 Commits

Author SHA1 Message Date
iven
1900abe152 test(intelligence): update tests to use intelligenceClient
- Rewrite context-compactor.test.ts to use intelligenceClient
- Rewrite heartbeat-reflection.test.ts to use intelligenceClient
- Rewrite swarm-skills.test.ts to use intelligenceClient
- Update CLAUDE.md architecture section for unified intelligence layer

All tests now mock Tauri backend calls for unit testing.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-21 15:26:35 +08:00
iven
1cf3f585d3 refactor(store): split gatewayStore into specialized domain stores
Major restructuring:
- Split monolithic gatewayStore into 5 focused stores:
  - connectionStore: WebSocket connection and gateway lifecycle
  - configStore: quickConfig, workspaceInfo, MCP services
  - agentStore: clones, usage stats, agent management
  - handStore: hands, approvals, triggers, hand runs
  - workflowStore: workflows, workflow runs, execution

- Update all components to use new stores with selector pattern
- Remove
2026-03-20 22:14:13 +08:00
iven
137f1a32fa feat: implement Phase 4 - Multi-Agent Swarm + Skill Discovery
Phase 4a: Agent Swarm Collaboration Framework (agent-swarm.ts)
- AgentSwarm class with configurable coordinator + specialist agents
- Three collaboration modes: Sequential (chain), Parallel (concurrent), Debate (multi-round)
- Auto task decomposition based on specialist capabilities
- Debate consensus detection with keyword similarity heuristic
- Rule-based result aggregation with structured markdown output
- Specialist management (add/update/remove) and config updates
- History persistence to localStorage (last 25 tasks)
- Memory integration: saves task completion as lesson memories

Phase 4b: Skill Discovery Engine (skill-discovery.ts)
- SkillDiscoveryEngine with 12 built-in skill definitions from skills/ directory
- Multi-signal search: name, description, triggers, capabilities, category matching
- Conversation-based skill recommendation via topic extraction (CN + EN patterns)
- Memory-augmented confidence scoring for suggestions
- Skill registration, install status toggle, category filtering
- localStorage persistence for skill index and suggestion cache

Phase 4c: chatStore Integration
- dispatchSwarmTask(description, style): creates and executes swarm task, adds result as message
- searchSkills(query): exposes skill search to UI layer

Tests: 317 passing across 13 test files (43 new for swarm + skills)
- AgentSwarm: createTask, sequential/parallel/debate execution, history, specialist mgmt
- SkillDiscovery: search, suggest, register, persist, categories

Refs: ZCLAW_AGENT_INTELLIGENCE_EVOLUTION.md updated - all 4 phases complete
2026-03-15 22:44:18 +08:00