- 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.
- Updated the system prompt to provide clearer guidance on the use of deck memory and tools, emphasizing the distinction between historical context and current slide data.
- Enhanced tool descriptions in the ChatTools class to clarify their intended use cases, focusing on live slide data and the importance of using tools for current content.
- Improved instructions on handling slide indices and the retrieval of slide information, ensuring users understand the differences between memory and live data.
- Updated the LiteParse runner to support two output formats: raw text and JSON, improving compatibility and flexibility.
- Introduced error handling for missing file arguments and file existence checks, enhancing robustness.
- Added functions to clean and extract text from LiteParse JSON outputs, handling malformed JSON gracefully.
- Updated the DocumentsLoader to utilize the new text cleaning functionality, ensuring cleaner document outputs.
- Implemented tests for the new text extraction and cleaning features, ensuring reliability and correctness.
- Introduced a new `ChatHistoryMessageModel` to persist chat messages in the database.
- Implemented a migration script to create the `chat_history_messages` table.
- Enhanced chat services to support storing and retrieving chat history.
- Added functionality for generating multiple media assets in a single API call.
- Updated the chat UI to display assistant activities and tool usage more effectively.
- Refactored API calls to use absolute URLs for better reliability.
- Replaced `get_container_db_async_session` with `async_session_maker` for improved session handling in background tasks.
- Refactored chat memory services to utilize a shared `mem0` client for better memory management.
- Introduced new methods for retrieving and storing chat history, integrating with SQL and memory layers.
- Enhanced error handling and response management in chat-related services.
- Cleaned up unused code and improved overall structure for maintainability.
- Added a new endpoint for streaming chat messages in FastAPI, allowing real-time interaction.
- Enhanced the `PresentationChatService` to support streaming replies with event types for chunked responses, status updates, and tool tracing.
- Updated the chat UI to handle and display assistant activities, including loading states and tool usage.
- Introduced new models for SSE responses and integrated them into the chat service.
- Improved error handling and response management in the chat API.
- Added new middleware to handle session authentication for presentation retrieval.
- Introduced new layout and page components for PDF export, ensuring no loading state is shown during headless rendering.
- Enhanced ConfigurationInitializer to manage loading state based on route.
- Updated DashboardApi to include credentials in requests for presentation data.
- Refactored hasValidLLMConfig function for cleaner validation logic.
- Updated `RUNTIME_CONTENT_FIELDS` to retain only necessary fields during validation.
- Enhanced `PresentationChatMemoryLayer` to prioritize live slide data from the database.
- Modified `search` method to clarify that it retrieves snippets from SQL-backed slides.
- Updated `get_slide_at_index` to include an option for full content retrieval.
- Adjusted tool descriptions to emphasize compact outputs and proper index handling.
- Improved handling of slide indices to accommodate user-friendly 1-based references.
- Introduced a new chat endpoint for handling user messages and generating responses.
- Added models for chat message requests and responses.
- Implemented a conversation store to manage chat history.
- Integrated memory layer for retrieving presentation context.
- Created tools for accessing presentation outlines and searching slides.
- Updated dependencies to include jsonschema for validation.
- Enhanced the API router to include the new chat functionality.
- 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.
- Update sync-presentation-export script to read version from package.json instead of export-version.json.
- Change entrypoint from index.js to index.cjs for CommonJS compatibility.
- Implement logic to ensure CommonJS entrypoint is created if missing.
- Modify ExportTaskService to resolve entrypoint path dynamically.
- Remove inline Puppeteer PDF export logic in favor of bundled export package.
- Add runtime availability checks and sync script execution in start.js.
- Introduce helper functions for output path normalization and entrypoint resolution.
- 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>
- Introduced functions to handle legacy database stamping and migration.
- Added a new Alembic migration script for initializing the database schema.
- Enhanced the migration process to check for unversioned databases and apply necessary stamps before upgrades.
- Created new migration files for adding a theme column to presentations.
- 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)
