[Fix][Generator] Correct chat history length for retoknenize codepath with env.init#214
Merged
CharlieFRuan merged 2 commits intoNovaSky-AI:mainfrom Aug 28, 2025
Merged
Conversation
… with env.init Co-authored-by: Alexander Conway <alex-dr@users.noreply.github.com>
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request addresses a bug in the retokenize_chat_history codepath within SkyRLGymGenerator. The issue arose when env.init() altered the length of the chat_history, as the original length was incorrectly assumed. The fix introduces initial_chat_history_length to correctly capture the length of the chat history after the env.init() call. This new variable is then used to accurately slice the chat history, separating the initial prompt from the generated turns. The change is correct and effectively resolves the bug. The implementation is clean and I have no further suggestions.
tyler-griggs
approved these changes
Aug 28, 2025
dzorlu
referenced
this pull request
in fleet-ai/SkyRL
Feb 4, 2026
… with env.init (#214) This pull request addresses a bug in the `retokenize_chat_history` codepath within SkyRLGymGenerator. The issue arose when env.init() altered the length of the chat_history, as the original length was incorrectly assumed. The fix introduces initial_chat_history_length to correctly capture the length of the chat history after the env.init() call. This new variable is then used to accurately slice the chat history, separating the initial prompt from the generated turns. --------- Co-authored-by: Alexander Conway <alex-dr@users.noreply.github.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This pull request addresses a bug in the
retokenize_chat_historycodepath within SkyRLGymGenerator. The issue arose when env.init() altered the length of the chat_history, as the original length was incorrectly assumed. The fix introduces initial_chat_history_length to correctly capture the length of the chat history after the env.init() call. This new variable is then used to accurately slice the chat history, separating the initial prompt from the generated turns.This PR fixes this issue and closes #213