Conversation
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
There was a problem hiding this comment.
Your trial has ended. Reactivate Greptile to resume code reviews.
Aggregate the full runs list into a workspace spend report: totals, spend by provider, top endpoints, top runs, and failed-run billing. Supports -j for agents. Claude-Session: https://claude.ai/code/session_01A72LKxMpKrLftv4VrPQgzA
There was a problem hiding this comment.
Your trial has ended. Reactivate Greptile to resume code reviews.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds a
monid spendcommand that summarizes workspace spend by provider and endpoint.What it does
GET /v1/runsand aggregates client-side: total spend with date range, spend per provider, top endpoints, top runs by cost, and failed-run count with the amount billed on failures ($0.00 when billing is healthy).-j/--jsonfor machine-readable output, matching the other commands.formatSpendReportadded alongsideformatBalance.buildSpendReport, in the same style as the existing price/format tests. One deliberate call pinned by a test: BLOCKED runs don't count as failures, since that's a budget guardrail firing as intended.monid spendrow to the skill's command table (version left untouched).Note on scale
Aggregation is client-side, so the command fetches the full run history (one request per 100 runs). For accounts with very large histories a backend summary endpoint would be the better home for this;
buildSpendReportmaps directly onto that shape, and the CLI side would shrink to one call plus the formatter. Happy to adapt the PR in that direction if preferred.