feat(prompt): expose cached input token counts in ResponseMetaInfo#1703
Open
mvanhorn wants to merge 1 commit intoJetBrains:developfrom
Open
feat(prompt): expose cached input token counts in ResponseMetaInfo#1703mvanhorn wants to merge 1 commit intoJetBrains:developfrom
mvanhorn wants to merge 1 commit intoJetBrains:developfrom
Conversation
Add cachedInputTokensCount field to ResponseMetaInfo so users can track cached vs uncached token usage for billing and monitoring. Providers now parse cached token data from API responses: - Anthropic: cache_creation_input_tokens + cache_read_input_tokens - OpenAI: prompt_tokens_details.cached_tokens - Bedrock (Anthropic): cache_read_input_tokens + cache_creation_input_tokens - Bedrock (Amazon Nova): cache_read_input_tokens + cache_creation_input_tokens Also updates the Java ResponseMetaInfoBuilder with a cachedInputTokensCount setter. Fixes JetBrains#1275
aozherelyeva
requested review from
EugeneTheDev,
antoniibelyshev and
devcrocod
and removed request for
antoniibelyshev and
devcrocod
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
ResponseMetaInfodoes not include cached input token counts, even though providers return this data. This adds acachedInputTokensCount: Int?field (default null for backward compatibility) and populates it from each provider's response:cache_creation_input_tokensandcache_read_input_tokensfrom the usage objectprompt_tokens_details.cached_tokenscache_read_input_tokensandcache_creation_input_tokensAlso adds a
cachedInputTokensCount()setter to the JavaResponseMetaInfoBuilder.Files changed:
prompt/prompt-model/.../Message.kt- New field onResponseMetaInfoprompt/prompt-model/.../MessageBuilder.kt- Java builder setterprompt/prompt-executor/.../AnthropicLLMClient.kt- Parse cached tokens from Anthropicprompt/prompt-executor/.../OpenAILLMClient.kt- Parse cached tokens from OpenAIprompt/prompt-executor/.../BedrockAnthropicClaudeSerialization.kt- Parse cached tokens from BedrockFixes #1275
This contribution was developed with AI assistance (Claude Code + Codex).