Skip to content

Conversation

@anakin87
Copy link
Contributor

@anakin87 anakin87 commented Dec 29, 2025

Description

I noticed that the docs are not up to date with the v0.1.8 API (see release notes).

In this PR, I'm updating the docs to reflect the changes (use @vf.stop, follow updated env_response signature, ...)
This also fixes #608.

@willccbb @mikasenghaas

Note that I did not update api_reference.md because it's unclear to me what should be exposed there. I'd prefer if a maintainer could handle this separately.

Type of Change

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • Documentation update
  • Test improvement

Testing

  • All existing tests pass when running uv run pytest locally.
  • New tests have been added to cover the changes

Checklist

  • My code follows the style guidelines of this project as outlined in AGENTS.md
  • I have performed a self-review of my own code
  • I have commented my code, particularly in hard-to-understand areas
  • I have made corresponding changes to the documentation
  • My changes generate no new warnings
  • Any dependent changes have been merged and published

Additional Notes


Note

Updates documentation to align with v0.1.8 protocol and state changes.

  • Switch MultiTurnEnv examples to async env_response(...) -> Messages (no tuple) and use @vf.stop-decorated stop conditions instead of overriding is_completed
  • Document trajectory-based rollout state (state["trajectory"], completion, is_completed, stop_condition, timing) and reference TrajectoryStep structure
  • Revise examples (Wordle, custom protocols, games) to new API; remove turn counters from state where unnecessary
  • Update training/eval snippets: new env.rollout(input=...) usage, Rubric.score_rollout(state, ...), and scoring outputs now under state["reward"]/state["metrics"]; clarify save_every behavior
  • Minor cleanup across README and docs sections to reflect current tool/stateful env patterns and message types

Written by Cursor Bugbot for commit fd3d8d6. This will update automatically on new commits. Configure here.

@anakin87 anakin87 marked this pull request as ready for review December 29, 2025 10:21
@lukalotl
Copy link

lukalotl commented Dec 29, 2025

Finally found this PR after digging around— the docs really tripped me up over the last few hours, would be great to get this in

Copy link
Member

@mikasenghaas mikasenghaas left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

lgtm

@anakin87
Copy link
Contributor Author

@mikasenghaas Feel free to merge...

As a contributor, I cannot do that.

@willccbb
Copy link
Member

willccbb commented Jan 3, 2026

Thanks for the lift here! sorry for delay on reviewing, planning a more exhaustive docs overhaul shortly but will be great to get this in :)

@willccbb willccbb merged commit 7f04c69 into PrimeIntellect-ai:main Jan 3, 2026
3 checks passed
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.

Broken link for examples.

4 participants