cost: log the gateway's pricing headers per call, warn on an unpriced model at startup - #205
Merged
Merged
Conversation
… model at startup An unpriced run left no trace: the None sentinel was swallowed, the Review complete line omitted the cost, the ping discarded the header and the key total was hidden behind the run cost. A gateway worker that never loaded its catalog priced every review at nothing and noergler showed nothing, in the log or on the summary, that said so. Every call now logs the raw x-litellm-response-cost and x-litellm-key-spend values plus the gateway's call id (a warning listing the x-litellm-* headers seen when unpriced), the Review complete and Mention Q&A lines carry the cost, and the startup ping warns once when the model is not priced. The key total stays on the summary when a single run is unpriced.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
An unpriced run left no trace: the None sentinel was swallowed, the Review complete line omitted the cost, the ping discarded the header and the key total was hidden behind the run cost. A gateway worker that never loaded its catalog priced every review at nothing and noergler showed nothing, in the log or on the summary, that said so.
Every call now logs the raw x-litellm-response-cost and x-litellm-key-spend values plus the gateway's call id (a warning listing the x-litellm-* headers seen when unpriced), the Review complete and Mention Q&A lines carry the cost, and the startup ping warns once when the model is not priced. The key total stays on the summary when a single run is unpriced.