HuggingFace LLM #251
Merged
HuggingFace LLM #251
Conversation
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
MarcCote
reviewed
Oct 15, 2025
MarcCote
reviewed
Oct 15, 2025
* Refactor tokenization methods to accept messages as input * Update README.md Co-authored-by: Marc-Alexandre Côté <marc.cote.19@gmail.com> * Update debug_gym/llms/openai.py Co-authored-by: Marc-Alexandre Côté <marc.cote.19@gmail.com> * Specify base images for mini-nightmare and aider (#255) * specify base image for mini nightmare * switch to debug-gym:aider image * remove default image * passing base image * test workspace * formatting issues * Simplify configs. Fix issue with overwriting entrypoints. --------- Co-authored-by: Marc-Alexandre Côté <marc.cote.19@gmail.com> * Support env variable in pod_spec_kwargs (#248) * Support env variable in pod_spec_kwargs * Ensure kubectl binaries are discoverable Add logic to set environment variables for kubectl discovery * update test_kubernetes * Refactor ShellSession to split shell_command, then add ["-c", command] keeping the command string intact * Pass Kubernetes service environment variables to support in-cluster kubectl access * Add isort and black to development dependencies * black and isort * Terminal env vars (#256) * Refactor terminal classes to allow include_os_env_vars param only for local terminal * Removed include_os_env_vars from kubernetes terminal * Set include_os_env_vars to True by default in LocalTerminal * Initialize env_vars in LocalTerminal constructor to ensure it defaults to an empty dictionary. * Removed redundant environment variable handling for in-cluster Kubernetes access * Simply logic * Set default base image --------- Co-authored-by: Alessandro Sordoni <alessandro.sordoni@gmail.com> Co-authored-by: Xingdi (Eric) Yuan <xingdi-eric-yuan@users.noreply.github.com> Co-authored-by: Matheus Pereira <matpereira@microsoft.com> * Move trim utils to llms * Remove message normalization from HuggingFaceLLM * Adjust message truncation logic and update test assertion for token counts --------- Co-authored-by: Marc-Alexandre Côté <marc.cote.19@gmail.com> Co-authored-by: Chinmay Singh <chsingh@microsoft.com> Co-authored-by: Alessandro Sordoni <alessandro.sordoni@gmail.com> Co-authored-by: Xingdi (Eric) Yuan <xingdi-eric-yuan@users.noreply.github.com>
matheper
approved these changes
Oct 23, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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 is to address #249