- 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
- 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
- run_agent_streaming() calls POST /complete/stream and yields token strings
- Reads NDJSON lines from the streaming response, yields on 'chunk' events
- On 'error' or connection failure, yields the fallback response string
- Tool calls are not supported in the streaming path
- Existing run_agent() (non-streaming, tool-call loop) is unchanged
- complete_stream() in router.py yields token strings via acompletion(stream=True)
- POST /complete/stream returns NDJSON: chunk lines then a done line
- Streaming path does not support tool calls (plain text only)
- Non-streaming POST /complete endpoint unchanged
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>
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)
- Add require_platform_admin guard to GET/POST /tenants, PUT/DELETE /tenants/{id}
- Add require_tenant_member to GET /tenants/{id}, GET agents, GET agent/{id}
- Add require_tenant_admin to POST agents, PUT/DELETE agents
- Add require_tenant_admin to billing checkout and portal endpoints
- Add require_tenant_admin to channels slack/install and whatsapp/connect
- Add require_tenant_member to channels /{tid}/test
- Add require_tenant_admin to all llm_keys endpoints
- Add require_tenant_member to all usage GET endpoints
- Add POST /tenants/{tid}/agents/{aid}/test (require_tenant_member for operators)
- Add GET /tenants/{tid}/users with pending invitations (require_tenant_admin)
- Add GET /admin/users with tenant filter/role filter (require_platform_admin)
- Add POST /admin/impersonate with AuditEvent logging (require_platform_admin)
- Add POST /admin/stop-impersonation with AuditEvent logging (require_platform_admin)
- Slack callback: check data.ok (not data.success) to match backend response
- SlackInstallResponse: use url + state fields (not authorize_url)
- connect-channel.tsx: update all authorize_url refs to url
- BudgetAlert: use current_usd (not current_cost_usd) to match backend Pydantic model
- usage page: update alert.current_cost_usd to alert.current_usd
- Slack OAuth callback route handler (/api/slack/callback)
- Onboarding wizard: 3-step stepper (connect channel -> configure agent -> test message)
- Connect Channel: Slack OAuth button + WhatsApp manual credentials form
- Configure Agent: links to Agent Designer, Next enabled only with active agent
- Test Message: per-channel test buttons, required step, no separate Go Live button
- BYO API key management settings page at /settings/api-keys
- API Keys nav link in sidebar
- recharts installed (was missing, blocked portal build)
- Create llm_keys.py: GET list (redacted, key_hint only), POST (encrypt + store), DELETE (204 or 404)
- LlmKeyResponse never exposes encrypted_key or raw api_key
- 409 returned on duplicate (tenant_id, provider) key
- Cross-tenant deletion prevented by tenant_id verification in DELETE query
- Update api/__init__.py to export llm_keys_router
- All 5 LLM key CRUD tests passing (32 total unit tests green)
- Add stripe and cryptography to shared pyproject.toml
- Add recharts, @stripe/stripe-js, stripe to portal package.json (submodule)
- Add billing fields to Tenant model (stripe_customer_id, subscription_status, agent_quota, trial_ends_at)
- Add budget_limit_usd to Agent model
- Create TenantLlmKey and StripeEvent models in billing.py (AuditBase and Base respectively)
- Create KeyEncryptionService (MultiFernet encrypt/decrypt/rotate) in crypto.py
- Create compute_budget_status helper in usage.py (threshold logic: ok/warning/exceeded)
- Add platform_encryption_key, stripe_, slack_oauth settings to config.py
- Create Alembic migration 005 with all schema changes, RLS, grants, and composite index
- All 12 tests passing (key encryption roundtrip, rotation, budget thresholds)
- Move key imports to module level in tasks.py for testability and clarity
- Pop WhatsApp extras (phone_number_id, bot_token) in handle_message before model_validate
- Build unified extras dict and extract wa_id from sender.user_id
- Change _process_message signature to accept extras dict
- Add _build_response_extras() helper for channel-aware extras assembly
- Replace all _update_slack_placeholder calls in _process_message with _send_response()
- Add escalation pre-check: skip LLM when Redis escalation_status_key == 'escalated'
- Add escalation post-check: check_escalation_rules after run_agent; call escalate_to_human
when rule matches and agent.escalation_assignee is set
- Add _build_conversation_metadata() helper (billing keyword v1 detection)
- Add channel parameter to build_system_prompt(), build_messages_with_memory(),
build_messages_with_media() for WhatsApp tier-2 business-function scoping
- WhatsApp scoping appends 'You only handle: {topics}' when tool_assignments non-empty
- Pass msg.channel to build_messages_with_memory() in _process_message
- All 26 new tests pass; all existing escalation/WhatsApp tests pass (no regressions)
