feat(chat): Enforce a hard conversation spend cap - #1068
Open
sentry-junior[bot] wants to merge 5 commits into
Open
feat(chat): Enforce a hard conversation spend cap#1068sentry-junior[bot] wants to merge 5 commits into
sentry-junior[bot] wants to merge 5 commits into
Conversation
Co-Authored-By: David Cramer <david@sentry.io>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
![sentry-warden[bot]](https://avatars.githubusercontent.com/in/2755838?s=60&v=4){kind=small}
Co-Authored-By: David Cramer <david@sentry.io>
Co-Authored-By: David Cramer <david@sentry.io>
dcramer
marked this pull request as ready for review
July 27, 2026 18:24
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
Validate each new provider usage record before combining it with prior spend. Preserve the capped turn's messages and usage so completion persistence blocks later billable calls.
Derive a total for component-only usage before aggregating slices. This keeps cumulative spend accurate when providers report different cost shapes.
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes and found 1 potential issue.
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit 0b3f74a. Configure here.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add a configurable
MAX_SPENDUSD cap that terminates conversation work once provider-reported model cost reaches the threshold. Over-budget turns end with a deterministic user-visible response instead of model output or a generic failure.Core loop enforcement
The agent checks cumulative conversation and in-flight turn usage before the first model call, before tool execution, before each subsequent model turn, and before final assistant delivery. Reaching the cap stops further agent work and delivers the static spend-limit response.
Fail-closed cost reporting
When a cap is configured and a provider reports usage without cost data, the turn stops with the same static response rather than silently treating the call as free. Integration coverage exercises both the threshold and missing-cost paths through the real agent loop.
Configuration
MAX_SPENDaccepts a positive USD amount. It is disabled when unset and fails startup validation for zero, negative, or non-numeric values.Requested by David Cramer via Junior.
--
View Junior Session