Fix missing token usage from some external model endpoints #199
+12
−0
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Outdated suggestions cannot be applied.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 will add an extra condition to check for chunks that have token usage information but do not have
choicesordeltaproperties. I opened #198, then was able to trace the cause down to GPT-5 sending a chunk at the end that was not handled by any branch of the if/elif statements since it did not havechunk.choicesorchunk.delta.Here's an example of the last chunk from calling
llm.stream("..."), if you add aprint('Chunk Received:', chunk)statement on line 635 ofchat_models.py