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

Conversation

@shatfield4
Copy link
Collaborator

Pull Request Type

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

Relevant Issues

resolves #4486

What is in this change?

  • Add max tokens param to KoboldCPP agent provider to fix bug where maximum response tokens is always 512

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

@timothycarambat timothycarambat merged commit 6270a0a into master Oct 9, 2025
1 check passed
@timothycarambat timothycarambat deleted the 4486-bug-when-using-koboldcpp-and-agent-the-max-response-length-is-always-512-regardless-of-context-size branch October 9, 2025 22:28
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[BUG]: When using KoboldCPP And @agent, the max response length is always 512, regardless of context size

3 participants