📖 Bump version to 0.0.89

🐛 Bug: Fix the bug where the 201 status code is mistakenly considered an error.

📖 Docs: Update documentation

📖 Bump version to 0.0.88

✨ Feature: Add feature: Support setting model timeout at the channel level

📖 Bump version to 0.0.87

✨ Feature: Add feature: support setting API key random load balancing

📖 Bump version to 0.0.86

🐛 Bug: Fix the bug of undefined review content.

📖 Bump version to 0.0.85

💻 Code: Optimize log display: add error provider name display.

📖 Bump version to 0.0.84

🐛 Bug: Fix the bug where the embedding model cannot receive arrays.

📖 Bump version to 0.0.83

✨ Feature: Add feature: Support that as long as the prefix of the API key exists in the configuration file, the API key is valid.

📖 Bump version to 0.0.82

🐛 Bug: Fix the bug where the embedding URL for GLM and GitHub models is incorrect.

📖 Bump version to 0.0.81

🐛 Bug: The bug where the provider's name, which is purely numeric, was not converted to a string has been fixed.

📖 Bump version to 0.0.80

🐛 Bug: Fix the bug where the response body error returned by the error report incorrectly uses raise.

📖 Bump version to 0.0.79

🐛 Bug: Fix the bug of ZeroDivisionError when the API key does not exist.

📖 Docs: Update documentation

📖 Bump version to 0.0.78

🐛 Bug: Fix the bug where GitHub models cannot retrieve the model when the model field is not set.

📖 Bump version to 0.0.77

🐛 Bug: Fix the issue where an error is returned directly when Authorization is empty.

📖 Bump version to 0.0.76

🐛 Bug: Fix the bug where API initialization throws an error when no API key is present.

📖 Docs: Update documentation

📖 Bump version to 0.0.75

✨ Feature: Add feature: support setting rate limit for each model individually

📖 Docs: Update documentation

💻 Code: Remove the maxDuration field from the vercel configuration file.

🐛 Bug: Fix the bug where the maxDuration in the Vercel configuration file does not take effect.

📖 Bump version to 0.0.74

💻 Code: Add log display for model not found.

📖 Bump version to 0.0.73

🐛 Bug: Fix the bug where the os module was not imported.

🐛 Bug: Fix the bug where functions and builds properties cannot be used simultaneously in Vercel configuration.

💻 Code: Increase the maximum runtime to 60 seconds when deploying with Vercel.

📖 Bump version to 0.0.72

💻 Code: Optimize to reduce unnecessary log output.

📖 Bump version to 0.0.71

💻 Code: Modify the default behavior of API key cooldown, change it to default off for API key cooldown. When there is only one API key in the channel, it will not cooldown under any circumstances. When API_KEY_COOLDOWN_PERIOD is 0, it will not cooldown. After enabling cooldown, any error with the API key will trigger a cooldown.

📖 Bump version to 0.0.70

🐛 Bug: Fix the bug where the return data type of frequency limit is incorrect.

📖 Bump version to 0.0.69

🐛 Bug: Fix the bug of incorrect function parameters entering the cooldown state.