Refactor tests for speed and reliability, add mock providers for TTS/STT, and fix native mode node spawning.

Add more MCP tools, tests, and skip failing tests requiring Gemini API

feat: add missing integration tests and fix multiple bugs discovered during testing

Mark all slow tests with @pytest.mark.slow

refactor done

Fix Windows PyWinPTY terminal boundary string drops via bat spool execution and full Windows deployment support

Fix token counting, model resolution, and stabilize agent metrics integration tests. Update docker-compose and test runner with improved API key and model config.

Optimize agent drilldown by parallelizing co-worker rubric generation with main agent execution. Added integration test to verify parallel flow.

Fix: Implement cumulative metrics tracking in agent loop, fix metrics reset endpoint, and restore full metrics dashboard UI

feat: Add Dual-Mode (Sync/Async) Webhook Support

test: Add webhook trigger integration test

Fix integration tests for agents, file sync, and audio. Restore 2026 model versions.

feat(agents): full implementation of harness engineering and file sync fixes ...

- Implemented Area 1: Backend scaffolding, CRUD, schemas, and session locking
- Implemented Area 2: Agent execution loop, RAG integration, and Circuit Breaker
- Updated UI: Configure CRON triggers, Target Mesh nodes, and display system prompt in Agent Drilldown
- Fixed LLM fallback resolving vertex_ai_beta
- Fixed File System Sync pseudo-nodes (hub, local) raising 'Offline'
- Fixed FileSystemNavigator initialPath bug causing synced files not to render in UI Mesh Workspace

test: Ensure agent executes periodically and verify response natively in session history

test: Implement comprehensive integration test for Agent lifecycle endpoints