1. Rename factory.py's EvoAgent data class to AgentConfig
- Avoids naming conflict with base/evo_agent.py's EvoAgent
2. Export pipeline_runner functions in backend/core/__init__.py
- Add create_agents, create_long_term_memory, stop_gateway
3. Consolidate PromptLoader to singleton pattern
- Add get_prompt_loader() singleton function
- Update all usages to use singleton
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Remove Docker-based microservices (docker-compose.yml, Makefile, Dockerfiles)
- Update start-dev.sh to use backend.app:app entry point
- Add shared schema and client modules for service communication
- Add team coordination modules (messenger, registry, task_delegator, coordinator)
- Add evaluation hooks and skill adaptation hooks
- Add skill template and gateway server
- Update frontend WebSocket URL configuration
- Add explain components for insider and technical analysis
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add EvaluationHook for post-execution agent evaluation
- Add SkillAdaptationHook for dynamic skill adaptation
- Add team/ directory with team coordination logic
- Add TEAM_PIPELINE.yaml for smoke_fullstack pipeline config
- Update RuntimeView, TraderView and RuntimeSettingsPanel UI
- Add runtimeApi and websocket services
- Add runtime_state.json to smoke_fullstack state
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add initialization of watchlistDraftSymbols when opening settings
- Previously watchlist was empty because initial state was never set
- Now copies from runtimeWatchlistSymbols on panel open
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Gateway now starts automatically when calling POST /runtime/start
- No need to run python backend/main.py separately
- Single service architecture: only FastAPI (port 8000) needed
- Gateway runs in background task and stops with pipeline
- Add error handling and logging for Gateway lifecycle
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add backend/core/pipeline_runner.py with full pipeline execution logic
- Integrate main.py pipeline startup into REST API
- Add comprehensive logging and error handling
- Support mock/live/backtest modes via API
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add POST /runtime/start, /stop, /restart APIs
- Run directories use timestamp format: YYYYMMDD_HHMMSS
- Add force stop support in TradingRuntimeManager
- Frontend: use REST API to start runtime instead of WebSocket
- Remove RuntimeView page from navigation
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add agent core modules (agent_core, factory, registry, skill_loader)
- Add runtime system for agent execution management
- Add REST API for agents, workspaces, and runtime control
- Add process supervisor for agent lifecycle management
- Add workspace template system with agent profiles
- Add frontend RuntimeView and runtime API integration
- Add per-agent skill workspaces for smoke_fullstack run
- Refactor skill system with active/installed separation
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
