fix: include thoughtsTokenCount in completion_tokens for Gemini #1458
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
- Non-streaming and streaming responses now sum candidatesTokenCount + thoughtsTokenCount - Aligns with OpenAI format where completion_tokens includes reasoning tokens - completion_tokens_details.reasoning_tokens provides the breakdown
voodoohop
added a commit
to pollinations/pollinations
that referenced
this pull request
Nov 27, 2025
voodoohop
added a commit
to pollinations/pollinations
that referenced
this pull request
Nov 27, 2025
* feat: add Portkey gateway deployment automation * fix: use pollinations fork with Gemini token counting fix PR: Portkey-AI/gateway#1458 * fix: improve deploy script reliability - Use fetch-based approach to get exact commit (no depth issues) - Add commit verification after checkout - Use npm ci for faster CI builds (fallback to npm install) - Suppress cd - output
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Outdated suggestions cannot be applied.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.
completion_tokensnow includesthoughtsTokenCountfor Gemini thinking modelscompletion_tokensis the total (reasoning + output)completion_tokens_details.reasoning_tokensprovides the breakdownProblem:
candidatesTokenCount(output) andthoughtsTokenCount(reasoning) separatelycompletion_tokensto be the sum of bothcandidatesTokenCountwas usedChanges:
src/providers/google/chatComplete.tssrc/providers/google-vertex-ai/chatComplete.ts