feat: add model costs, TUI improvements, and usage normalization#6
Merged
Merged
Conversation
- Add optional cost tracking per model with input/output/cache pricing - Subtract cached tokens from uncached input to avoid double-counting - Add recent_requests config option to control TUI request list size - Redesign TUI with resizable tables, logo, and better column layout - Only count /v1/chat/completions as model requests in metrics - Strip User-Agent header on forwarded requests unless set by caller - Add sequence numbers to recent requests for stable ordering - Show per-request, per-model, and total cost in TUI, plain, and JSONL modes
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
costconfig per model (input/output/cache per million tokens). Costs are shown per-request, per-model, and as a total in TUI, plain text, and JSONL modes.recent_requestscount (default 10, max 100, set to 0 to hide)./v1/chat/completionsrequests count as model requests. Each recent request gets a monotonic sequence number.User-Agentheader on forwarded requests unless explicitly set by the caller.