Code

History

Commits on diff-aware-buffer-plan to crates/open_ai/src35+
  1. Remove deprecated GPT-4o, GPT-4.1, GPT-4.1-mini, and o4-mini (#49082)Richard Feldman committed 9 months ago0b8424a
  2. ep: Use rejected_output for DPO training + OpenAI support (#47697)Oleksiy Syvokon committed 9 months ago757ee05
  3. open_ai: Support reasoning content (#43662)Aero committed 9 months ago7bd3075
  4. Add BYOK GPT-5.2-codex support (#47025)Richard Feldman committed 10 months agoe5706f2
  5. open_ai: Use proper type for Responses API `input` (#46526)Marshall Bowers committed 10 months agoc6a38f2
  6. open_ai: Move `responses` module to its own file (#46450)Marshall Bowers committed 10 months ago30f776e
  7. Add OpenAI Responses API support with chat_completions capability flag (#39989)Matt Stallone committed 10 months ago84017bc
  8. Add GPT-5.2 support (#44656)Richard Feldman committed 11 months agob5a0a33
  9. Add experimental mercury edit prediction provider (#44256)Agus Zubiaga committed 11 months agof08fd73
  10. Add GPT 5.1 to Zed BYOK (#43492)Mikayla Maki committed 11 months ago53eb35f
  11. Add retry support for OpenAI-compatible LLM providers (#37891)Tim McLean committed 1 year agofb90b12
  12. zeta2: Build edit prediction prompt and process model output in client (#41870)Max Brunsfeld committed 1 year ago784fdca
  13. open_ai: Make the deltas optional (#39142)Techy committed 1 year ago27a1884
  14. Settings refactor (#38367)Conrad Irwin committed 1 year agofcdab16
  15. open_ai: Trim newline before "data:" prefix and account for the possibility of no space after ":" (#37644)ZhangJun committed 1 year ago7091c70
  16. language_models: Fix tool_choice null issue for other providers (#34554)Umesh Yadav committed 1 year ago9f74988
  17. Trim API key when submitting requests to LLM providers (#37082)Antonio Scandurra committed 1 year ago39d86ee
  18. open_ai: Remove `model` field from ResponseStreamEvent (#36902)Michael Sloan committed 1 year ago0470bac
  19. Fix a bunch of other low-hanging style lints (#36498)Piotr Osiewicz committed 1 year ago05fc0c4
  20. open_ai: Fix error response parsing (#36390)Oleksiy Syvokon committed 1 year ago42ffa89
  21. openai: Don't send prompt_cache_key for OpenAI-compatible models (#36231)Oleksiy Syvokon committed 1 year ago2a57b16
  22. openai: Don't send reasoning_effort if it's not set (#36228)Oleksiy Syvokon committed 1 year agoa3dcc76
  23. language_models: Add reasoning_effort for custom models (#35929)Cretezy committed 1 year ago8ff2e3e
  24. open_ai: Send `prompt_cache_key` to improve caching (#36065)Oleksiy Syvokon committed 1 year ago7167f19
  25. open_ai: Log inputs that caused parsing errors (#36063)Oleksiy Syvokon committed 1 year ago7ff0f15
  26. Add GPT-5 support through OpenAI API (#35822)Richard Feldman committed 1 year ago7d4d8b8
  27. open_ai: Make OpenAI error message generic (#33383)Umesh Yadav committed 1 year ago3f4098e
  28. language_models: Emit UsageUpdate events for token usage in DeepSeek and OpenAI (#33242)Umesh Yadav committed 1 year ago1081624
  29. open_ai: Fix issues with OpenAI compatible APIs (#32982)Bennet Bo Fenner committed 1 year agoc34b24b
  30. Standardize on u64 for token counts (#32869)Richard Feldman committed 1 year ago5405c2c
  31. OpenAI cleanups (#32597)Ben Brandt committed 1 year ago2d4e427
  32. open_ai: Remove redundant serde aliases and add model limits (#32572)Ben Brandt committed 1 year ago8cc5b04
  33. open_ai: Fix parallel tools issue (#30467)Adrian Furo committed 1 year agoe6f5196
  34. open_ai: Make Assistant message content optional (#31418)Ben Brandt committed 1 year agoef0e1cb
  35. Use `anyhow` more idiomatically (#31052)Kirill Bulatov committed 1 year ago16366cf