Add with_embed_service() builder and embed_service() accessor to ToolContext,
wired through ChatService so function-calling tools can access Qdrant vector search.
- chunk_text(): char-boundary-safe text chunking at paragraph/sentence breaks (7000 char limit)
- embed_memories_batch(): groups messages by room, batch-embeds all texts to reduce Qdrant calls
- embed_issue_chunked(): auto-chunks long issue bodies
- embed_skill(): upgraded with auto-chunking via chunk_text
- TagEmbedInput struct for batch tag embedding
- embed_tags_batch() / search_tags() with project isolation
- ensure_collections() now creates embed_repo_tag collection
- ai_react_nonstreaming now passes real input/output tokens to billing
- Was passing hardcoded 0,0 despite destructuring token data
- Also fix unused variable warnings
Critical fixes:
- Wrap balance updates in database transactions with SELECT FOR UPDATE
- Move history insert after balance validation to prevent orphaned records
- Use Decimal throughout to avoid silent conversion failures
- Prevent concurrent requests from causing negative balances
Tasks resolved:
- Task #4: Silent Decimal conversion failures
- Task #5: Missing transaction isolation (race conditions)
- Task #6: History inserted before validation
- 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
- atob() returns Latin-1 binary string, not UTF-8
- Chinese characters decoded incorrectly causing mojibake
- Use TextDecoder("utf-8") with Uint8Array for correct handling
- 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
- Clear activeAiStream, streamingChunks, and timers when room changes
- Add showCursor prop to OrderedStreamChunks — only show cursor
during active streaming, not for saved content
Create changelog page with language tabs (EN/CN/DE/FR),
timeline layout, and MDX rendering. Add generate script
to build changelog data from mdx files.
- issue_triage.rs: use check_project_access instead of nonexistent get_project_member
- email/lib.rs: make EMAIL_REGEX pub to suppress dead_code warning
- tracing_fmt.rs: minor import ordering cleanup and code formatting
- Import room_message_reaction, room_message_edit_history, room_notifications modules
- Fix room_message_edit_history: no Room column, use subquery via messages
- Change publish_project_room_event from Result to () handling
- Add QuerySelect import for limit() method in workers.rs
- Add Offline status to ModelStatus enum
- Sync marks all models offline first, then activates found ones
- Deduplicate by model name (ignoring provider)
- Deactivate orphaned models (offline -> deprecated)
- Add models_offline and models_deactivated to SyncModelsResponse
- Add deduplicate_existing_models() for cleanup
- Rename upsert_model to upsert_model_by_name
- commits.tsx: fix Unix timestamp (time_secs) not multiplied by 1000
- RoomMessageSearch.tsx: add explicit generic type for resp.data
- RoomPinPanel.tsx: make sender_id optional (string | null)
- message-list.tsx: remove unused index variable in map
- repository-context.tsx: use correct RepoInfo field names
- use-audio-recording.ts: use audioStream state instead of undefined var
- universal-ws.ts: rename unused id to _id
- Reject secrets shorter than 32 bytes (fall back to generated key)
- Use SHA-256 hash instead of naive byte cycling to derive the key
(cycling "password" to 64 bytes gave extremely low entropy)
- 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)
- Fix second copy of push_subscription unwrap that was in a
tokio::spawn block with different indentation
- Replace constant UUID parse unwrap with expect()
- SSH rate limiter: wire SshRateLimiter into SSHServer with IP-based
rate limiting on new_client connections
- Room startup: cap initial room load at 1000 via limit() to prevent
resource exhaustion on large instances
- WS token exposure: only include token in URL for cross-origin
connections; same-origin web clients authenticate via secure cookies
- CSRF: confirmed SameSite::Lax + Secure + HttpOnly are all set
(session config defaults)
