Users can now attach images in the web chat for Simba to analyze using
Ollama's gemma3 vision model. Images are stored in Garage (S3-compatible)
and displayed in chat history.
Also fixes aerich migration config by extracting TORTOISE_CONFIG into a
standalone config/db.py module, removing the stale aerich_config.py, and
adding missing MODELS_STATE to migration 3.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Move blueprints.email.helpers import from module-level to inside the
endpoint functions that use it, breaking the circular dependency chain.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Users can now receive a unique email address (ask+<token>@domain) and
interact with Simba by sending emails. Inbound emails hit a Mailgun
webhook, are authenticated via HMAC token lookup, processed through the
LangChain agent, and replied to via the Mailgun API.
- Extract shared SIMBA_SYSTEM_PROMPT to blueprints/conversation/prompts.py
- Add email_enabled and email_hmac_token fields to User model
- Create blueprints/email with webhook, signature validation, rate limiting
- Add admin endpoints to enable/disable email per user
- Update AdminPanel with Email column, toggle, and copy-address button
- Add Mailgun env vars to .env.example
- Include database migration for new fields
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add /me, /admin/users, and WhatsApp link/unlink endpoints
- Add AdminPanel component with user management UI
- Add userService methods for admin API calls
- Fix simba mode so cat responses appear in the message list
- Fetch userinfo endpoint for groups on OIDC callback (Authelia compat)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Implemented parse_email_body function for RFC822 email parsing
- Uses stdlib email.message_from_bytes with modern EmailMessage API
- Extracts text and HTML bodies using get_body() method
- Prefers plain text over HTML for "preferred" field
- Converts HTML to text using html2text when text body missing
- Extracts all metadata: subject, from, to, date, message_id
- Uses parsedate_to_datetime for proper date parsing
- Handles UnicodeDecodeError gracefully with partial data return
- Follows async patterns and logging conventions from existing codebase
- Created IMAPService class with async connect/list_folders/close methods
- Uses aioimaplib for async IMAP4_SSL operations
- Implements proper connection cleanup with logout() not close()
- Added aioimaplib and html2text dependencies to pyproject.toml
- Follows async patterns from existing service classes (ynab_service.py, mealie_service.py)
- Includes comprehensive logging with [IMAP] and [IMAP ERROR] prefixes
- Add EncryptedTextField for transparent Fernet encryption
- Create EmailAccount model with encrypted IMAP credentials
- Create EmailSyncStatus model for sync state tracking
- Create Email model with 30-day retention logic
- Follow existing blueprint patterns from users/conversation
- Update llm.py to use OpenAI client with custom base_url for llama-server
- Update agents.py to use ChatOpenAI instead of ChatOllama
- Remove unused ollama imports from main.py, chunker.py, query.py
- Add LLAMA_SERVER_URL and LLAMA_MODEL_NAME env vars
- Remove ollama and langchain-ollama dependencies
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
