fix: swap input/output tokens for Google GenAI#223
Merged
samuelrince merged 3 commits intomainfrom Apr 2, 2026
Merged
Conversation
Use prompt_token_count and candidates_token_count directly instead of deriving via subtraction, fixing the swapped input/output token counts reported in issue #222.
Gemini thinking models report thoughts_token_count separately from candidates_token_count. Since reasoning tokens are generated by the model, they should be counted as output tokens for energy estimation.
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Fix issue #222: input and output token counts were swapped in the Google GenAI tracer. The code was incorrectly assigning
candidates_token_count(generated/output tokens) toinput_tokensand deriving input via subtraction from total.Changes
Use the API fields directly instead of deriving via subtraction:
output_tokens = response.usage_metadata.candidates_token_count(generated tokens)input_tokens = response.usage_metadata.prompt_token_count(prompt tokens)This fixes all 4 code paths (sync, stream, async, async stream) and is more robust than subtraction-based derivation.
Testing
All 6 active Google GenAI tests pass. Verified with mock response that token values are now assigned correctly.