Code

History

Commits on v5.0.435+
  1. **Fix model switch logic when quota is exceeded**Luis Pater committed 1 year ago34855bc
  2. **Handle `data:` without trailing space in streaming responses**Luis Pater committed 1 year ago56c8297
  3. Update PassthroughGeminiResponseStream to handle `[DONE]` markerLuis Pater committed 1 year agobdac24b
  4. Update Management API CN docs for authentication requirementsLuis Pater committed 1 year ago6d30faf
  5. Add Gemini-to-Gemini request normalization and passthrough supportLuis Pater committed 1 year agoc0eaa41
  6. Reorganize and reintroduce Management API section in README filesLuis Pater committed 1 year ago8a2285e
  7. Add management API handlers for config and auth file managementLuis Pater committed 1 year agodb43930
  8. Enhance client reload process with new OpenAI compatibility supportLuis Pater committed 1 year agob125410
  9. Add support for new GPT-5 model variantsLuis Pater committed 1 year ago9c9ea99
  10. Merge pull request #16 from hkfires/mainLuis Pater committed 1 year agoba4c114
  11. Add token refresh handling for 401 responses across clientsLuis Pater committed 1 year ago0331660
  12. Set the default Docker timezone to Asia/Shanghaihkfires committed 1 year ago3f78401
  13. Add token refresh handling for 401 responses across clientsLuis Pater committed 1 year ago512c8b6
  14. Update issue templatesLuis Pater committed 1 year ago1aad033
  15. Update README documentation to clarify `auth-dir` configuration for Windows usersLuis Pater committed 1 year agof1d9364
  16. Update README documentation to clarify `auth-dir` configuration for Windows usersLuis Pater committed 1 year agoc2b2c9e
  17. Unlock mutex before returning error in `handlers.go` to prevent deadlocksLuis Pater committed 1 year ago09b9d3b
  18. Fix some bugs.Luis Pater committed 1 year agoe9e0016
  19. Add nil-check for `GetRequestMutex` across handlers to prevent potential panicsLuis Pater committed 1 year ago3704dae
  20. Add `/v1/completions` endpoint with OpenAI compatibilityLuis Pater committed 1 year agobea5f97
  21. Suppress debug logs for model routing and ignore empty tools arraysLuis Pater committed 1 year ago7a6adfa
  22. Add support for localhost unauthenticated requestsLuis Pater committed 1 year ago1c4183d
  23. Improved the `/v1/models` endpointLuis Pater committed 1 year agodff31a7
  24. Add OpenAI compatibility support and improve resource cleanupLuis Pater committed 1 year agoed8873f
  25. Refactor API handlers to implement retry mechanism with configurable limits and improved error handlingLuis Pater committed 1 year ago9102ff0
  26. Refactor codebaseLuis Pater committed 1 year ago8c555c4
  27. Update README to reflect usage of Qwen models instead of Claude modelsLuis Pater committed 1 year ago2b1762b
  28. Add Qwen supportLuis Pater committed 1 year agoaa2f37d
  29. Add claude code supportLuis Pater committed 1 year agod58cc55
  30. Refactor error handling and variable declarations in browser and logging modulesLuis Pater committed 1 year agoc5cc238
  31. Refactor Gemini API handlers to standardize response field names and improve model descriptionsLuis Pater committed 1 year ago6bbdf67
  32. Add request logging capabilities to API handlers and update .gitignoreLuis Pater committed 1 year agofcadf08
  33. Add support for Codex model in provider logic and update documentation for claude codeLuis Pater committed 1 year ago4155805
  34. Add openai codex supportLuis Pater committed 1 year agode7b850
  35. Update `.goreleaser.yml` to specify archive formats for different OS targetsLuis Pater committed 1 year agod2394b0