θΏ™ζ˜―indexlocζδΎ›ηš„ζœεŠ‘οΌŒδΈθ¦θΎ“ε…₯任何密码
Skip to content

Conversation

@roman-y-wu
Copy link

Pull Request Type

  • ✨ feat
  • πŸ› fix
  • ♻️ refactor
  • πŸ’„ style
  • πŸ”¨ chore
  • πŸ“ docs

Relevant Issues

resolves #4304

What is in this change?

Properly detects and handles gpt-5 models.

Additional Information

Developer Validations

  • I ran yarn lint from the root of the repo & committed changes
  • Relevant documentation has been updated
  • I have tested my code functionality
  • Docker build succeeds locally

Roman Wu added 4 commits August 11, 2025 16:22
- Introduced max_tokens handling in OpenAiLLM and OpenAIProvider classes.
- Updated system settings to include OpenAiMaxTokens from environment variables.
- Added tests for GPT-5 parameter construction logic.
@Chan9390
Copy link

While executing agent with GPT-5 (with temperature set as 1), I got the error:
image

Does this PR implicitly fix it?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

PR:needs review Needs review by core team

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[BUG]: ChatGPT - gpt-5 model: 400 Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.

3 participants