Implemented record and replay fixtures for LLM calls #467
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
jfeser
requested changes
Dec 27, 2025
kiranandcode
force-pushed
the
kg-record-replay-llm-requests
branch
from
56834ba to
6c45af0
Compare
jfeser
approved these changes
Dec 31, 2025
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Outdated suggestions cannot be applied.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.
This PR modifies
test_handlers_llm.pyto implement record/replay fixtures. By default, when running locallycompletioncalls are dumped to the folderfixtureswith the test id that they are being run in.When running in CI, the script will instead deserialize the fixtures instead of calling the LLM provider endpoint.
This should allow seamless testing of LLM behaviours locally, while making sure CI runs are deterministic.
Closes #458