🐛 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.

📖 Bump version to 0.0.68

🐛 Bug: Fix the bug where GitHub Action cannot run.

🐛 Bug: 1. Fix the bug where the closed client cannot be found when closing the request client.

📖 Bump version to 0.0.67

📖 Docs: Update documentation

📖 Bump version to 0.0.66

💻 Code: When there is only one optional provider, cooling will not take effect.

📖 Bump version to 0.0.65

🐛 Bug: Fixed the bug with limited concurrency and removed unnecessary asynchronous mutex locks.

📖 Bump version to 0.0.64

🐛 Bug: Fix the bug where Vercel fails to start successfully.

📖 Bump version to 0.0.63

🐛 Bug: Fix the bug where Vercel fails to start successfully.

📖 Bump version to 0.0.62

🐛 Bug: Fix the bug where Vercel fails to start successfully.

📖 Bump version to 0.0.61

🐛 Bug: Fix the bug of incorrect weight allocation

📖 Bump version to 0.0.60

✨ Feature: Add feature: Support model-level cooling. When a model under a channel reports an error, it does not affect other models under the same channel, only the model that reported the error is cooled.

📖 Bump version to 0.0.59

📖 Bump version to 0.0.58

💻 Code: GitHub Action Docker image build adds support for manual trigger

📖 Bump version to 0.0.57

🐛 Bug: Fix the bug in the chart display.

📖 Bump version to 0.0.56

🐛 Bug: Fixed the bug where the cooling model could not take effect in this request.

📖 Bump version to 0.0.55

✨ Feature: Add feature: Support channel cooldown. When an API channel response fails, the channel will automatically be excluded and cooled down for a period of time, during which no requests will be made to that channel. After the cooldown period ends, the model will automatically be restored until it fails again, triggering another cooldown.

📖 Bump version to 0.0.54

🪞 Frontend: Fixed the bug where the chart size was displayed incorrectly when there was no data.

📖 Bump version to 0.0.53

🐛 Bug: Fix the bug in the moral check database update error.

📖 Bump version to 0.0.52

🪞 Frontend: Add request model statistics bar chart

📖 Bump version to 0.0.51

💰 Sponsors: Thanks to @PowerHunter for the CNY 200 sponsorship, sponsorship information has been added to the README.

📖 Bump version to 0.0.50

🐛 Bug: Fix the bug where the model cannot be found.

📖 Bump version to 0.0.49