Spaces:
Runtime error
Runtime error
Commit History
-
Remove binary files from tracking
8085285
-
Add multi-LLM support, settings & migrations
Introduce a multi-LLM architecture and related settings plus DB migrations. Added alembic migrations to add missing columns and new llm config tables; new backend/integrations/llm modules (providers.py, factory.py, registry.py, resolver.py) to replace the global client pattern and enable per-task LLM resolution. Added settings route for LLM provider/task management and wired services (planner, executor, chat, response analyzer) to use get_llm_for_task (including async plan generation and a /plan/stream SSE endpoint). Updated routes and services to use DB session and timezone-aware datetimes, added frontend pages/components (SettingsPage, UsagePage, workflow subcomponents), and updated env.example with AUTH credentials. Misc: small .claude tweaks and other bugfixes related to planning/streaming, token usage logging, and Vite proxy config.1e24842
-
Add Chat Assistant & selection handling
Introduce a persistent, context-aware Chat Assistant and interactive selection flow across backend, frontend, schemas, and docs. Key changes: - Backend: add ChatSession/ChatMessage models, chat_assistant service, and endpoints (/chat, /chat-sessions/*, POST /context/{session_id}) in main.py; save/load last 20 messages and persist assistant actions as structured JSON. Increase httpx timeout and deduplicate query params before execution; make request.body flexible (Any). Add Unicode import for SQLAlchemy types. - Schemas: new ChatRequest/ChatResponse/ChatMessage/ChatSessionSummary and selection option fields in AnalyzeResponse/ContextUpdate. - API executor: stricter rules, body can be array, files and enum handling clarified. - Frontend & docs: add ChatAssistant component, Chat UI/embedded panel, selection modal flow, and update Project/UX/Research docs to describe structured actions, selection detection, and persistence. This enables conversational control (execute_step, modify_reques…6270070