Skip to content

Release v0.3.11#265

Merged
placerda merged 1 commit into
mainfrom
release/v0.3.11
Jun 8, 2026
Merged

Release v0.3.11#265
placerda merged 1 commit into
mainfrom
release/v0.3.11

Conversation

@placerda

@placerda placerda commented Jun 8, 2026

Copy link
Copy Markdown
Contributor

Summary

  • Fix local AI-assisted evaluators with reasoning-model graders (gpt-5*, o1*, o3*, o4*) by enabling Azure AI Evaluation reasoning-model parameter handling.
  • Run azd eval commands with --no-prompt and closed stdin so hidden prompts fail visibly instead of appearing to hang.
  • Update Doctor token-limit guidance to accept max_completion_tokens for reasoning models.

Validation

  • python -m pytest tests/ -x -q -> 885 passed, 1 skipped
  • git diff --check

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
@placerda placerda merged commit 2b46ef9 into main Jun 8, 2026
16 of 21 checks passed
@placerda placerda deleted the release/v0.3.11 branch June 8, 2026 20:12
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.

1 participant