fix(runtime): surface typed harness provider failures - #336
Merged
Merged
Conversation
Contributor
|
Important
This repository does not receive automatic reviews because it has fewer than 10 stars. ⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Advanced Run ID: Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Contributor
There was a problem hiding this comment.
All reported issues were addressed across 9 files
Reply with feedback, questions, or to request a fix.
Re-trigger cubic
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Recognized model-provider failures currently reach agent handlers as ordinary nonzero harness results, so a handler can replace an actionable quota or authentication error with “exit 1.” The shared runtime now rejects these failures with
HarnessProviderErrorbefore returning output to the handler. No agent repository changes are needed.The runtime classifies usage/credit limits, rate limits, authentication failures, context limits, provider request timeouts, and availability errors. Messages use safe templates, with a validated provider-reported reset time when available. Successful runs, OS kills, and unrecognized process failures retain their existing result contract. No automatic retry, credential switching, or paid fallback is introduced.
harness.provider_errorandrunner.handler.errorcarry the structuredproviderFailure; the runner's error text is actionable for existing run-record consumers. Original diagnostics remain accessible on the error as a non-enumerableresult. Cloud customer-notice rendering can consume the structured message without duplicating CLI parsing.Validation: the unchanged-handler regression failed before the fix; all 174 runtime tests and runtime typecheck now pass. Coverage includes Claude/Codex error envelopes, stdout/stderr diagnostics, invalid reset hints, safe serialization, successful/unknown/OS-kill results, no retry, and no task output reaching a success path. No live customer task was rerun.