mirror of
https://github.com/garrytan/gstack.git
synced 2026-10-02 17:40:02 +02:00
test(qa-bugs): keep claude-opus-4-7 after qa-b6-static stalled on the default model
qa-b6-static timed out on claude-fable-5-1 in census 36597762183 and in one of two targeted reruns. Both times the stream stopped mid-message with no pending tool, right after the model found the disabled submit button, and stayed silent until the 300 s deadline. Per the B8 fallback, re-pin with a TODOS entry; budgets and retries are unchanged. A rerun on opus-4-7 passed (125 s, 5/5 detected).
This commit is contained in:
1 parent
1c32c7d16a
commit
4c5fc0e2ce
2 files changed
+6
-4
No files matched your search
@@ -1,5 +1,4 @@
|
||||
import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
|
||||
import { resolveEvalModel } from '../lib/eval-model';
|
||||
import { CAPTURE_MS, CAPTURE_LONG_MS } from './helpers/eval-budgets';
|
||||
import { runSkillTest } from './helpers/session-runner';
|
||||
import { outcomeJudge } from './helpers/llm-judge';
|
||||
@@ -109,7 +108,7 @@ CRITICAL RULES:
|
||||
timeout: CAPTURE_MS,
|
||||
testName: `qa-${label}`,
|
||||
runId,
|
||||
model: resolveEvalModel('capture'),
|
||||
model: 'claude-opus-4-7',
|
||||
});
|
||||
|
||||
logCost(`/qa ${label}`, result);
|
||||
|
||||
Reference in new issue
Block a user