refactor(rlm): enhance code fence parsing and REPL entry formatting - #9309
Merged
Conversation
…rove error handling for invalid code structures
Collaborator
Author
|
@codex review |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 7d218582c4
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
…ine code formatting in REPLEntry
isaacbmiller
marked this pull request as ready for review
February 20, 2026 00:36
Collaborator
Author
|
Discussed offline |
5 tasks
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The RLM module has the LLM write Python in markdown code fences (
python ...), which must be stripped before execution. Previously, _strip_code_fences used a permissive regex that silently passed through anything it couldn't parse — unlabeled fences, multiple blocks, or prose mixed with code would reach the interpreter and fail in confusing ways.This PR rewrites _strip_code_fences as a strict parser that raises SyntaxError on malformed input rlm.py:69-103. Because it can now raise, a new _execute_action_code method rlm.py:534-550 wraps both fence stripping and interpreter execution with proper error handling, replacing duplicated try/except blocks in the sync and async iteration paths.