- Added environment variables for Vertex AI and Azure OpenAI configurations in docker-compose and user configuration models.
- Updated the application logic to handle Vertex and Azure as new LLM providers, including validation and API key management.
- Enhanced the UI components to support model selection and API key input for Vertex and Azure.
- Updated relevant utility functions and constants to accommodate the new providers.
- Ensured proper error handling for configuration requirements specific to Vertex and Azure.
- Updated the llmai dependency from version 0.2.1 to 0.2.2 for improved functionality.
- Revised the system prompt in the chat service to clarify the use of context and tools, emphasizing the importance of accurate responses based on live data.
- Enhanced the chat UI to better reflect tool usage and assistant activities, improving user experience.
- Replaced all instances of the placeholder image path from "/static/images/placeholder.jpg" to "/static/images/replaceable_template_image.png".
- Added a new Nginx location block for serving app data with a long cache expiration.
- Enhanced the image generation service to return the new template image when generation fails.
- Updated various services and endpoints to ensure consistent handling of asset paths, including resolving backend asset URLs.
- Removed Electron-specific checks from several components to streamline API calls and improve compatibility with web deployments.
- Improved error handling and logging in the PDF export process.
- Adjusted Next.js configuration for API routing to ensure proper asset serving in Docker environments.
- Updated LLMClient to include CODEX in web search checks.
- Simplified web search logic in generate_ppt_outline to improve clarity and efficiency.
- Ensured consistent usage of web search settings across methods.
- Updated docker-compose.yml to allow disabling embedded Ollama via environment variable.
- Refactored Dockerfile and Dockerfile.dev for improved dependency management and installation process.
- Enhanced FastAPI migration scripts to handle orphaned Alembic revisions and added new database migration logic.
- Improved error handling in background tasks and Codex authentication endpoints.
- Added support for font file uploads with better validation and extraction of font names.
- Introduced new image search functionality with support for Pexels and Pixabay APIs.
Add native support for Open WebUI's image generation API as a new
image provider option. Open WebUI exposes an OpenAI-like
/v1/images/generations endpoint but with key differences that
require special handling:
- Response is a bare JSON array instead of {"data": [...]}
- Image URLs are relative paths (e.g. /api/v1/files/.../content)
- File downloads require the same Bearer auth token
The implementation uses raw HTTP calls via aiohttp rather than the
OpenAI SDK to handle these differences. No model parameter is sent
since Open WebUI manages the image model in its own admin settings.
Backend changes:
- New OPEN_WEBUI enum value in ImageProvider
- generate_image_open_webui() method in ImageGenerationService
- Environment getters/setters for OPEN_WEBUI_IMAGE_URL and
OPEN_WEBUI_IMAGE_API_KEY
- UserConfig model and config loading/saving pipeline updated
Frontend changes:
- New "Open WebUI" option in image provider dropdown
- Settings UI with URL and optional API key fields
- Validation, field mappings, and config persistence
Docker:
- OPEN_WEBUI_IMAGE_URL and OPEN_WEBUI_IMAGE_API_KEY added to all
docker-compose service definitions
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add configurable pool settings via environment variables:
DB_POOL_SIZE, DB_MAX_OVERFLOW, DB_POOL_TIMEOUT, DB_POOL_RECYCLE,
DB_POOL_PRE_PING (defaults: 5, 10, 30s, 1800s, true)
- Enable pool_pre_ping by default to detect and recycle stale connections
- Add dispose_engines() called during FastAPI lifespan shutdown to
release all connections back to the database
- Skip pool configuration for SQLite (uses file-lock, not connection pools)
- Apply changes to both servers/ and electron/ FastAPI instances
Fixes#453 (stale connections exhausting pool)
Fixes#454 (missing pool configuration)
- Introduced CodexLLMAdapter to handle structured and unstructured LLM calls via the Codex Responses API.
- Implemented methods for converting tool formats and building request bodies for Codex.
- Refactored LLMClient to utilize CodexLLMAdapter, enhancing tool call handling and response processing.
- Updated LLMToolCallsHandler to support Codex as a valid LLM provider.
- Enhanced schema utilities for better JSON schema handling.
- Implemented a new method to create an AsyncOpenAI client specifically for Codex.
- Added functionality to convert Codex event responses into a dictionary format for easier consumption.
- Updated the streaming methods to utilize the new Codex client and handle API errors gracefully.
- Improved logging for debugging purposes during Codex interactions.
- Refactored message handling in the slide content generation function for clarity and efficiency.
- Added Codex authentication endpoints and logic for OAuth flow.
- Updated Docker configuration to expose port 1455 for Codex callback.
- Enhanced user configuration model to include Codex-related fields.
- Integrated Codex selection into the LLM provider UI.
- Implemented token management and refresh logic for Codex.
- Added utility functions for handling Codex OAuth tokens and state management.
