test(ai): Remove flaky token count integration expect directives #9401
+29
−88
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Outdated suggestions cannot be applied.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.
Discussion
We had some "ballpark" checks for the number of tokens returned in responses.
However, the number of tokens returned had a high variance based on general AI chaos and the model that was used. This PR replaces somewhat exacting token count checks with simple non-zero checks in order to reduce flake.
Additionally, the change removes
toolUsePromptTokenCountchecks for thegemini-2.0-flashmodel, which doesn't support this field.Testing
This change updates the tests themselves. Tested locally.
API Changes
N/A.