LLM responses can take >60s (especially with local models). The
WebSocket listener was timing out before the response arrived,
causing agent replies to appear in logs but not in the chat UI.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Human verification approved for all 6 I18N requirements
- Portal confirmed rendering correctly in EN/ES/PT
- Language switcher, persistence, and AI Employee language response verified
- Phase 7 (multilanguage) marked complete in ROADMAP.md
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Chat API queries on web_conversations need tenant context set before
RLS policies allow the SELECT. Also fixes crypto.randomUUID fallback.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add OLLAMA_MODEL setting to shared config (default: qwen3:32b)
- LLM router reads from settings instead of hardcoded model name
- Create .env file with all configurable settings documented
- docker-compose passes OLLAMA_MODEL to llm-pool container
To change the model: edit OLLAMA_MODEL in .env and restart llm-pool.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Added balanced/economy/local groups alongside fast/quality so all 5
agent model_preference values resolve to real provider groups.
All default to local Ollama qwen3:32b, commercial as fallback.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The gateway never called configure_rls_hook(engine), so SET LOCAL
app.current_tenant was never set for any DB operation through the
portal API endpoints. All tenant-scoped writes (agent creation, etc.)
failed with "new row violates row-level security policy."
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Create gateway/channels/web.py with normalize_web_event() and /chat/ws/{conversation_id}
WebSocket endpoint (auth via first JSON message, typing indicator, Redis pub-sub response)
- Create shared/api/chat.py with GET/POST/DELETE /api/portal/chat/conversations* REST API
with require_tenant_member RBAC enforcement and RLS context var setup
- Add chat_router to shared/api/__init__.py exports
- Mount chat_router and web_chat_router in gateway/main.py (Phase 6 Web Chat routers)
- All 19 unit tests pass; full 313-test suite green
- Add ChannelType.WEB = 'web' to shared/models/message.py
- Add webchat_response_key() to shared/redis_keys.py
- Create WebConversation and WebConversationMessage ORM models (SQLAlchemy 2.0)
- Create migration 008_web_chat.py with RLS, indexes, and channel_type CHECK update
- Pop conversation_id/portal_user_id extras in handle_message before model_validate
- Add web case to _build_response_extras and _send_response (Redis pub-sub publish)
- Import webchat_response_key in orchestrator/tasks.py
- Write 19 unit tests covering CHAT-01 through CHAT-05 (all pass)
- Add AgentTemplate ORM model to tenant.py (global, not tenant-scoped)
- Create migration 007 with agent_templates table and 7 seed templates
- Create shared/prompts/system_prompt_builder.py with build_system_prompt()
- AI transparency clause always present (non-negotiable per Phase 1 decision)
- Unit tests pass (17 tests, all sections verified)
