feat: add fine-grained cache token tracking across 5 LLM providers#139
Merged
Conversation
added 2 commits
May 28, 2026 22:56
Replace the monolithic `cached_tokens` field with separate `cached_input_tokens` (cache read hits) and `cache_creation_input_tokens` (cache writes) for precise cost allocation, since providers price cached and non-cached tokens differently. Provider-specific cache field mapping: - OpenAI / Doubao: prompt_tokens_details.cached_tokens - Anthropic: cache_read_input_tokens + cache_creation_input_tokens - DeepSeek: prompt_cache_hit_tokens - Gemini (native): cachedContentTokenCount Also fix total_tokens to use the API-provided value directly (e.g. Gemini includes thinking tokens in total, OpenAI includes reasoning in completion), with input+output as fallback when not available.
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Replace the monolithic
cached_tokensfield with separatecached_input_tokens(cache read hits) andcache_creation_input_tokens(cache writes) for precise costallocation, since providers price cached and non-cached tokens differently.Provider-specific cache field mapping:
Also fix total_tokens to use the API-provided value directly (e.g. Gemini includes thinking tokens in total, OpenAI includes reasoning in completion), with input+output as fallback when not available.