Skip to content

Conversation

xfalcox
Copy link
Member

@xfalcox xfalcox commented Aug 8, 2025

  • Add 'minimal' as a supported reasoning effort value in LlmModel configuration
  • Update OpenAI endpoint validation to accept 'minimal' effort level
  • Implement dual payload format support:
    • Responses API: { reasoning: { effort: "value" } }
    • Standard API: { reasoning_effort: "value" }
  • Add comprehensive tests for reasoning effort payload formats
  • Update GPT-5 model configurations with max_output_tokens and pricing fixes

- Add 'minimal' as a supported reasoning effort value in LlmModel configuration
- Update OpenAI endpoint validation to accept 'minimal' effort level
- Implement dual payload format support:
  * Responses API: `{ reasoning: { effort: "value" } }`
  * Standard API: `{ reasoning_effort: "value" }`
- Add comprehensive tests for reasoning effort payload formats
- Update GPT-5 model configurations with max_output_tokens and pricing fixes
@xfalcox xfalcox merged commit 730598e into main Aug 8, 2025
17 checks passed
@xfalcox xfalcox deleted the gpt-5-followup branch August 8, 2025 17:47
pento pushed a commit that referenced this pull request Aug 11, 2025
…34179)

- Add 'minimal' as a supported reasoning effort value in LlmModel
configuration
- Update OpenAI endpoint validation to accept 'minimal' effort level
- Implement dual payload format support:
  * Responses API: `{ reasoning: { effort: "value" } }`
  * Standard API: `{ reasoning_effort: "value" }`
- Add comprehensive tests for reasoning effort payload formats
- Update GPT-5 model configurations with max_output_tokens and pricing
fixes
yuriyaran pushed a commit that referenced this pull request Aug 21, 2025
…34179)

- Add 'minimal' as a supported reasoning effort value in LlmModel
configuration
- Update OpenAI endpoint validation to accept 'minimal' effort level
- Implement dual payload format support:
  * Responses API: `{ reasoning: { effort: "value" } }`
  * Standard API: `{ reasoning_effort: "value" }`
- Add comprehensive tests for reasoning effort payload formats
- Update GPT-5 model configurations with max_output_tokens and pricing
fixes
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Development

Successfully merging this pull request may close these issues.

2 participants