- Mount kb_router and calendar_auth_router on gateway (Phase 10 agent capabilities)
- Update calendar_lookup tool schema with action/event_summary/event_start/event_end params
- Add tool result formatting instruction to build_system_prompt when tools assigned (CAP-06)
- Add kb_router and calendar_auth_router to shared/api/__init__.py exports
- Confirm CAP-04 (http_request) and CAP-07 (audit logging) already working
- Add calendar_auth.py: OAuth install/callback/status endpoints with HMAC-signed state
- Replace calendar_lookup.py service account stub with per-tenant OAuth token lookup
- Support list, check_availability, and create actions with natural language responses
- Token auto-refresh: write updated credentials back to channel_connections on refresh
- Add migration 013: add google_calendar to channel_type CHECK constraint
- Add unit tests: 16 tests covering all actions, not-connected path, token refresh write-back
- Service worker push/notificationclick handlers with conversation deep-link
- PushPermission component for opt-in UI in More sheet
- InstallPrompt component (second-visit, Android + iOS)
- IndexedDB message-queue for offline message persistence
- use-chat-socket.ts: drain queue on reconnect, enqueue when offline
SMBs don't need separate Financial Manager, Controller, and Accountant.
Merged into one versatile role that handles invoicing, AP/AR, expenses,
budgets, reporting, and cash flow. Full en/es/pt translations.
Templates: 8 → 6 (Customer Support Rep, Sales Assistant, Marketing
Manager, Office Manager, Project Coordinator, Finance & Accounting Manager)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
New AI employee template: Marketing & Growth Manager (category: marketing).
Creative and data-driven, handles campaign strategy, content briefs,
metrics analysis, social media calendars, and lead gen coordination.
Escalates brand-sensitive decisions and high-budget approvals.
Full translations for Spanish and Portuguese with native business
terminology.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Streaming httpx client uses 300s read timeout (cloud LLMs can take
30-60s for first token). Was using 120s general timeout.
- Guard all WebSocket sends with try/except for client disconnect.
Prevents "Cannot send once close message has been sent" crash.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Celery workers use NullPool to avoid "Future attached to a different
loop" errors from stale pooled async connections across asyncio.run()
calls. FastAPI keeps regular pool (single event loop, safe to reuse).
- Skip pgvector similarity search when no conversation history exists
(first message) — saves ~3s embedding + query overhead.
- Wrap pgvector retrieval in try/except to prevent DB errors from
blocking the LLM response.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Pub-sub loop now handles 'chunk' and 'done' message types (not just 'response')
- 'chunk' messages are forwarded immediately via websocket.send_json
- 'done' message breaks the loop and triggers DB persistence of full response
- Sends final 'done' JSON to browser to signal stream completion
- Legacy 'response' type no longer emitted from orchestrator (now unified as 'done')
- _stream_agent_response_to_redis() publishes chunk/done messages to Redis pub-sub
- _process_message() uses streaming path for web channel with no tools registered
- Non-web channels (Slack, WhatsApp) and tool-enabled agents use non-streaming run_agent()
- streaming_delivered flag prevents double-publish when streaming path is active
- _send_response() web branch changed from 'response' to 'done' message type for consistency
