feat: replace request_type with service + operation in inference log inserts#1207
Merged
Conversation
…inserts - InferenceLogEntry: requestType → service + operation fields - Add cacheReadTokens, cacheWriteTokens, rawUsage fields - Update logInferenceUsage SQL to match new inference_log schema - Update llm-api.ts logInference function + both callers - Embedding calls: service='embedding', operation='create' - Chat calls: service='llm', operation='chat' Coordinates with constructive-db PR #1281 (merged).
Contributor
🤖 Devin AI EngineerI'll be helping with this pull request! Here's what you should know: ✅ I will automatically:
Note: I can only respond to comments from users who have write access to this repository. ⚙️ Control Options:
|
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Coordinates with constructive-db PR #1281 (merged) which added
serviceandoperationfields toinference_log_modulereplacing the oldrequest_typefield.Changes in
graphile-llm/src/metering.ts:InferenceLogEntryinterface:requestType→service+operationfieldscacheReadTokens,cacheWriteTokens(for Anthropic/OpenAI cache billing)rawUsage(jsonb for raw provider response audit)logInferenceUsage()SQL updated to INSERT all new columns (20 params)service: 'embedding', operation: 'create'service: 'llm', operation: 'chat'Changes in
graphql/server/src/middleware/llm-api.ts:logInference()function:requestType→service+operationReview & Testing Checklist for Human
usage_log_inferenceshasservice='llm', operation='chat'service='embedding', operation='create'Notes
The
servicefield uses a fixed vocabulary of ~8 values:llm,embedding,tts,stt,ocr,image_gen,search,compute. Theoperationfield is higher cardinality and service-specific.cacheReadTokens,cacheWriteTokens, andrawUsageare passed asnullfor now — they'll be populated when Anthropic/OpenAI provider support is added.Link to Devin session: https://app.devin.ai/sessions/2b5a29d83d3f478e8d3d972653b4879c
Requested by: @pyramation