Meter supervisor spend by provider credits delta#106
Merged
Conversation
Cache-replayed responses carry their original recorded cost, so summing the per-scenario CSVs double-counts money spent in earlier runs — the supervisor's first production outing reported $7.74 spent after a minute of free replays and would have tripped the budget governor on phantom spend. With an OpenRouter key the /credits delta from run start is authoritative (polled at most every 20s); the disk sum remains the fallback for providers without a balance endpoint. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Cache replays carry their original recorded cost; summing scenario CSVs double-counts prior runs' spend (observed: $7.74 'spent' in one minute of free replays, which would have tripped the budget governor on phantom spend). Prefer the OpenRouter /credits delta from run start when a key is present; keep the disk sum as fallback. Two new tests.
🤖 Generated with Claude Code