fix(llma): cache cost calculation in the LangChain callback #346
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
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
Radu-Raicea
approved these changes
Oct 31, 2025
Co-authored-by: Radu Raicea <radu@raicea.com>
14 tasks
- Updated version to 6.7.12 - Added changelog entry for 6.7.12
- Kept all new tests from both branches - PR branch: 5 new cache token tests - Master: 1 new LangChain 1.0+ compatibility test
Master has already released 6.7.12 with other fixes, so this PR will be 6.7.13
carlos-marchal-ph
added a commit
that referenced
this pull request
Nov 10, 2025
PR #346 introduced cache token subtraction for all providers, causing double subtraction for OpenAI/OpenRouter and resulting in negative costs. The plugin-server only subtracts cache tokens for Anthropic providers (exact match on provider name or substring match on model name). This fix aligns the Python SDK with that behavior. Changes: - Only subtract cache tokens when provider="anthropic" OR model contains "anthropic" - Passes provider and model metadata to usage parsing functions - Updates tests to reflect correct behavior (no subtraction for OpenAI) - Adds test for Anthropic provider subtraction Fixes negative cost calculations for users on OpenAI/OpenRouter with cached tokens.
carlos-marchal-ph
added a commit
that referenced
this pull request
Nov 10, 2025
PR #346 introduced cache token subtraction for all providers, causing double subtraction for OpenAI/OpenRouter and resulting in negative costs. The plugin-server only subtracts cache tokens for Anthropic providers (exact match on provider name or substring match on model name). This fix aligns the Python SDK with that behavior. Changes: - Only subtract cache tokens when provider="anthropic" OR model contains "anthropic" - Passes provider and model metadata to usage parsing functions - Updates tests to reflect correct behavior (no subtraction for OpenAI) - Adds test for Anthropic provider subtraction Fixes negative cost calculations for users on OpenAI/OpenRouter with cached tokens.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Problem
LangChain passes input tokens as a sum of input and cached tokens, so we incorrectly calculate the total cost.