mirror of
https://github.com/dtzp555-max/ocp.git
synced 2026-07-27 07:55:07 +00:00
taodengandClaude Opus 5
79656b485f
Reverting my own half of this PR. The reviewer proved the alignment.yml change was theatre, and my issue #198 was filed on a wrong premise. What I verified myself before reverting: - the alignment job BODY references models.json zero times; only the paths filter I added mentioned it - test.yml is `pull_request:` with NO paths filter, so it already runs on every PR, models.json-only ones included - on a deliberately corrupted models.json (contextWindow 1000000, a typo'd openclawName), `npm test` catches it: 455 passed, 2 failed So the real guard on models.json already existed and always ran. Adding the path would only have made a job execute that inspects nothing about models.json, and then reported a green "Alignment Guardrail" — implying a check that did not happen. That is strictly worse than the job not running, which is precisely the reviewer's point. #198's premise was also wrong. The blacklist greps server.mjs for known hallucinated tokens. A models.json-only PR cannot introduce a token into server.mjs, so CLAUDE.md hard-requirement #2 is INAPPLICABLE on such a PR, not vacuous. I read "the guardrail didn't run" as "coverage gap" without checking what the guardrail actually inspects. The release.yml half is unaffected and stays: that one is a real, reproduced failure (the no-CHANGELOG branch never wrote the file the create step consumes). Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017gbqUZ8HfBZpjjbzQ85oH8