Move tool execution to a spawned task so synchronous git2 operations
don't block the tokio worker thread, allowing heartbeat chunks to be
sent every 10s during long tool execution.
Also add analysis-first reasoning prompt to system messages.
Add with_embed_service() builder and embed_service() accessor to ToolContext,
wired through ChatService so function-calling tools can access Qdrant vector search.
- process_react now returns (String, i64, i64) tuple with token counts
- Extract token stats from rig Agent FinalResponse usage field
- Both streaming and non-streaming ReAct modes now bill correctly
- Add record_ai_session() helper calling billing::record_ai_usage()
- Replace all Set(None) cost/currency with actual calculated values
- Cost computed from model_pricing via Decimal precision
- Use AgentBuilder for native tool-calling with stream_prompt()
- Add RecordingTool wrapper preserving retry + DB recording
- Fix tool_choice bug in do_completion (same as call_stream_once)
- Add seq field to RoomMessageStreamChunkEvent for strict ordering
- Map streaming events: Text→Answer, Reasoning→Thought, ToolCall→Action
- Only final event has done=true, removed premature stream ending
- Store __chunks__ JSON in thinking_content for ordered replay
- Start SSH rate limiter cleanup task that was missing (prevent memory leak)
- Create single ToolContext outside tool execution loop so max_tool_calls
and max_depth guards actually fire across batch tool calls (was creating
fresh context per call, bypassing all limits)
When a user mentions a repository in room chat, extract the repo name
from @[repo:name:label] brackets, look up the full repo model from the
database, and inject its details (name, description, default branch,
visibility) into the AI message context. Works independently of
embed_service availability.
- StreamChunk/StreamChunkType types for preserving arrival order
- Chunk collection in call_stream_once and process_stream
- Add "error sending request" and "Http client error" to retryable errors
- StreamResult includes chunks vector for ordered replay
- Streaming path: on tool_call execution error, emit an [Observation]
chunk so the model sees the failure and can retry/adapt
- Non-streaming path: inject error as a user message so the loop
continues with error context, not silently stop
- Refactor room-context.tsx with improved WebSocket state management
- Enhance room-ws-client.ts with reconnect logic and message handling
- Update Discord layout components with message editor improvements
- Add WebSocket universal endpoint support in ws_universal.rs
