Fix the bug that cannot adapt to the available model name.

🐛 Bug: Fix the bug where the timeout was not converted to a float.

Add traffic middleware

Fix the bug that does not adapt to the new API for obtaining the model list.

Add feature: support OpenAI dall-e-3 image generation

Fix the bug where the provider lookup is inaccurate.

revert: try_all_providers method in ModelRequestHandler

refactor: revise round-robin and auto-retry logic in API request handling

fix: Improve round-robin provider selection and add Claude max_tokens auto-fill

Add feature: support vertex claude API using tool use functionality.

✨ Feature: Add feature: Support vertex ai API and vertex tool use invocation.

Fix the bug related to asyncio.CancelledError error

fix bug

🐛 Bug: 1. Fix the bug of httpx reading streamed output timeout.

🐛 Bug: Fix the bug of the model provider matching order error.

Add feature: automatic URL redirection

Fix the issue where Gemini cannot be used.

fix log display error

Optimize log display, showing the model requested by the user.

Fix the bug in the matching model algorithm.

Support downloading configuration files from external URLs.

Support downloading configuration files from external URLs.

Support downloading configuration files from external URLs.

Change log display

Do not display log information of level info

Uvicorn as an ASGI server, disable WebSocket support on startup

Fix a possible bug that occurs when attempting to encode a dictionary (dict) object as a string in a FastAPI application.

Fix a possible bug that occurs when attempting to encode a dictionary (dict) object as a string in a FastAPI application.

Fix a possible bug that occurs when attempting to encode a dictionary (dict) object as a string in a FastAPI application.

Optimize log display

Fix the bug that prevents automatic polling.

Fix the bug that prevents automatic polling.

Fix the bug in the model matching rules.

Optimize log display

Optimize log display

Increase the initial character read timeout.

Add get models endpoint.

Fix the error of name not defined

Fix the issue where the original model name cannot be requested.

Fix the issue where the original model name cannot be requested.

Refactor code

Add GPT format test module

Do not output response stream

Modify the stream read response timeout to 5 seconds.

Fix the bug where the end of the GPT format response does not have a newline

Fix polling algorithm error

Fix the bug where an error is reported when loading the configuration file without api.yaml.

Support setting whether to poll for each API key separately.

🐛 Bug: Fix the bug in the Claude API URL determination algorithm.

Automatically determine which engine to use.