[Model behavior] Inconsistent test practice: duplicated CI runs, skipped the runs that mattered
Status Open
Maintainer reply None cached
Activity 0 comments · opened Oct 2, 2026
The model ran large test suites that CI already runs, then, after being told off, skipped running the tests needed to verify a conflicting pull request and the server-dependent tests of another, and gave verdicts anyway. Verification effort was spent where it added least and dropped where it was needed.
Model: Claude Opus 5.5 (claude-opus-5-5[1m]), Claude Code CLI, one long working session on 2026-10-02.
Context: maintainer of an open-source cloud-service emulator; the work is pull-request review and fixes under a written procedure loaded into every session (project instruction file + persistent memory). No personal data, repository names, PR numbers or handles are included.
Raised with Claude Code.