Files
oak-gpui/crates
Cretezy 8ff2e3e195 language_models: Add reasoning_effort for custom models (#35929)
Release Notes:

- Added `reasoning_effort` support to custom models

Tested using the following config:
```json5
  "language_models": {
    "openai": {
      "available_models": [
        {
          "name": "gpt-5-mini",
          "display_name": "GPT 5 Mini (custom reasoning)",
          "max_output_tokens": 128000,
          "max_tokens": 272000,
          "reasoning_effort": "high" // Can be minimal, low, medium (default), and high
        }
      ],
      "version": "1"
    }
  }
```

Docs:
https://platform.openai.com/docs/api-reference/chat/create#chat_create-reasoning_effort

This work could be used to split the GPT 5/5-mini/5-nano into each of
it's reasoning effort variant. E.g. `gpt-5`, `gpt-5 low`, `gpt-5
minimal`, `gpt-5 high`, and same for mini/nano.

Release Notes:

* Added a setting to control `reasoning_effort` in OpenAI models
2025-08-13 06:09:16 +00:00
..
2025-08-05 18:16:47 +00:00
2025-08-06 09:01:06 +00:00
2025-07-29 13:24:34 -07:00
2025-08-05 18:16:47 +00:00
2025-07-21 13:44:51 +02:00
2025-06-17 20:26:27 +00:00
2025-07-17 14:25:55 +00:00
2025-07-08 14:34:57 +00:00
2025-08-06 00:02:26 +00:00
2025-08-07 23:07:33 +00:00