Dipg research #98
Closed
Dipg research #98
+7,190
−0
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
meta-cla
bot
added
the
CLA Signed
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
- Refactored client parser to be more robust and include 'done' flag. - Made unit tests deterministic and self-contained using mocking. - Updated README with correct paths and reliable server polling logic.
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
parsing and state creation within the try-except block
This commit introduces a number of improvements to the dipg_safety_env, focusing on improving test coverage, fixing bugs, and clarifying documentation. The key changes are: - A new test file with unit tests for all reward functions. - A new end-to-end test for the step() function. - The environment tests have been moved to the tests/ directory. - The tests now use a mock dataset, removing the need to download external files for testing. - A bug in the match_format_exactly reward function's regex has been fixed. - A corrupted file that was causing a SyntaxError has been repaired. - The README.md has been updated to reflect these changes and provide clear instructions on how to run the tests.
pankit-eng
approved these changes
Oct 30, 2025
There was a problem hiding this comment.
I'd like for @Darktex to take a look since this environment brings in a couple of relevant abstractions - dataloading & reward pipelines that we have mentioned in RFCs as well.
| @@ -0,0 +1,38 @@ | |||
| # scripts/download_dataset.py | |||
There was a problem hiding this comment.
Where is this script getting used?
| && rm -rf /var/lib/apt/lists/* | ||
|
|
||
| # Install all necessary Python packages for the server, including gunicorn | ||
| RUN pip install --no-cache-dir \ |
There was a problem hiding this comment.
You may want to rebase on top of @Mortimerp9 's recent change to move deps into requirements.txt
|
Hm, so this one is a clone of #97 -- let me just close this and review in the same place in 97... |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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.
No description provided.