- Renamed Feedback class to follow PascalCase convention
- Fixed candidate enumeration start index from 0 to 1
- Simplified candidate content access by removing .message.content
- Updated CONFIG_PATH environment variable name to CONFIG_PATH_ARG
- Bumped version from 0.5 to 0.6
- Removed unnecessary return statement and trailing newline
Added in-flight request tracking mechanism to prevent cache stampede when multiple concurrent requests arrive for the same endpoint. This introduces new dictionaries to track ongoing requests and a lock to coordinate access. The available_models method was refactored to use an internal helper function and includes request coalescing logic to ensure only one HTTP request is made per endpoint when cache entries expire. The loaded_models method was also updated to use the new caching and coalescing pattern.
Create atomic snapshots by deep copying usage data structures to prevent race conditions.
Protect concurrent reads of usage counts with explicit locking in endpoint selection.
Replace README screenshot with a video link.
Add logic to only append ":latest" suffix to models without existing version suffixes, preventing duplicate version tags and ensuring correct endpoint selection for models following Ollama naming conventions.
Simplify the logic for handling model versions in `openai_chat_completions_proxy` and `openai_completions_proxy` by removing redundant conditions and initializing `local_model` earlier. This makes the code more readable and maintains the same functionality.
- Refactored token aggregation query in db.py to use a single SQL query with SUM() instead of iterating through rows, improving performance
- Combined import statements in db.py and router.py to reduce lines of code
- Enhanced chat proxy in router.py to handle "moe-" prefixed models with multiple query execution and critique generation
- Added last_user_content() helper function to extract user content from messages
- Improved code readability and maintainability through these structural changes
- Introduce a lazily initialized, shared aiosqlite connection stored in self._db and two asyncio locks (_db_lock, _operation_lock) for safe concurrent access
- Ensure the database directory exists before connecting and enable WAL journaling and foreign keys on first connect
- Add close method to gracefully close the persistent connection
- Guard initialization and write operations with _operation_lock to ensure single-threaded schema setup
- Switch to ON CONFLICT UPSERT for token_counts updates and initialize token_time_series table
- Add typing for _db (Optional[aiosqlite.Connection]) and adjust imports accordingly
addition: Frontend button with total stats aggregation task and feedback span element to keep user informed and a small database footprint
