fix: normalize prompt_tokens to include cache tokens across all Anthropic providers#1602
Open
Yanhu007 wants to merge 1 commit intoPortkey-AI:mainfrom
Open
fix: normalize prompt_tokens to include cache tokens across all Anthropic providers#1602Yanhu007 wants to merge 1 commit intoPortkey-AI:mainfrom
Yanhu007 wants to merge 1 commit intoPortkey-AI:mainfrom
Conversation
…opic providers Anthropic direct and Vertex AI set prompt_tokens = input_tokens (excluding cache), while Bedrock includes cache tokens. This inconsistency means the same model with the same prompt reports different prompt_tokens depending on which provider is used. Per OpenAI convention, prompt_tokens should include cached tokens, with the breakdown available in prompt_tokens_details.cached_tokens. Add cache_creation_input_tokens and cache_read_input_tokens to prompt_tokens in both non-streaming and streaming paths for: - Anthropic direct (chatComplete.ts) - Google Vertex AI (chatComplete.ts) This makes them consistent with Bedrock's existing behavior. Fixes Portkey-AI#1564
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Fixes #1564
prompt_tokensnormalization is inconsistent across Anthropic access paths:prompt_tokensincludes cache?input_tokensonly)input_tokensonly)inputTokens + cache*)Per OpenAI convention,
prompt_tokensshould include cached tokens, with breakdown inprompt_tokens_details.cached_tokens.Changes
Updated 4 code paths (non-streaming + streaming × 2 providers):
Anthropic direct (
src/providers/anthropic/chatComplete.ts):Vertex AI (
src/providers/google-vertex-ai/chatComplete.ts): same change.Both non-streaming and streaming paths updated.
total_tokenswas already correct.