RomanNum3ral
/
paperclip
mirror of https://github.com/paperclipai/paperclip.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

test(runner): retry proven breadth plan variance

This commit is contained in:
Dotta 2026-09-03 09:26:03 -05:00
parent 2311f08422
commit e0ad6d356f
1 changed files with 7 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
tests/runner-e2e/runner.spec.ts
View File

@ -1446,17 +1446,19 @@ for (const execution of executions) {
}
if (
execution.suite.id === "openrouter-model-breadth" &&
execution.task.id === "question-resume-complete" &&
(execution.task.id === "question-resume-complete" ||
execution.task.id === "plan-approve-complete") &&
exactMessageMatcher?.kind === "message_exact" &&
selectedRuns.every((candidate) => candidate.status === "succeeded") &&
issue.status === "done" &&
finalRunMessage !== exactMessageMatcher.expected &&
record(finalRun.resultJson).summary === exactMessageMatcher.expected
) {
// A breadth model can occasionally satisfy the durable terminal
// contract while paraphrasing the visible final response. Preserve
// the exact persisted-message and DOM assertions, but classify this
// narrowly proven provider variance for one fresh-harness retry.
// An interactive breadth model can occasionally satisfy the durable
// terminal contract while paraphrasing the visible final response.
// Preserve the exact persisted-message and DOM assertions, but
// classify this narrowly proven provider variance for one
// fresh-harness retry.
failureClassOverride = "provider_variance";
}
const observedEnvironmentId =