garrytan and capy-ai[bot] 4473f71da4
fix(eval-plan): pilot start keeps the R54 refusal; --tier-question rejects a flag ...
Review pass 1 (full depth) found the frontier refusal could be skipped by
starting a pilot on Haiku or Sonnet arms behind a dry run made on other arms,
or behind a dry-run.json written before the check existed. startPilot now
refuses a pilot whose every arm is Haiku or Sonnet unless its dry run recorded
a tier question. dry-run --tier-question no longer takes the next flag as its
answer. The testing doc now says the frontier re-cost is printed for
comparison with the brief cap, not enforced.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-01 23:50:50 +00:00
2026-11-01 09:35:42 +00:00
2026-06-09 22:29:23 -07:00
2026-10-04 07:58:41 -07:00
2026-10-20 00:24:28 +00:00
2026-10-29 09:58:34 +00:00
2026-10-20 00:24:28 +00:00
2026-10-07 23:29:05 +00:00
2026-09-21 12:27:25 -04:00
2026-10-29 09:58:34 +00:00
2026-10-20 00:24:28 +00:00
2026-10-20 00:24:28 +00:00
2026-10-20 00:24:28 +00:00
2026-10-31 16:31:27 +00:00
2026-10-20 00:24:28 +00:00
2026-10-20 00:24:28 +00:00
2026-10-10 23:26:08 +00:00
2026-10-07 23:29:05 +00:00
2026-10-07 23:29:05 +00:00
2026-11-01 20:15:10 +00:00
2026-10-17 21:17:39 +00:00
2026-10-17 21:17:39 +00:00
2026-10-26 06:41:22 +00:00
2026-04-18 15:05:42 +08:00
2026-10-25 01:00:05 +00:00
2026-11-01 07:41:10 +00:00
2026-10-31 10:23:41 +00:00
2026-10-04 07:58:41 -07:00
2026-10-16 22:00:32 +00:00
2026-10-31 09:54:03 +00:00
2026-10-20 00:24:28 +00:00
2026-10-20 00:24:28 +00:00
2026-10-16 22:00:32 +00:00
2026-10-27 08:16:11 +00:00
2026-10-20 00:24:28 +00:00
2026-10-11 00:32:15 +00:00
2026-10-26 04:32:27 +00:00
2026-10-26 04:32:27 +00:00
2026-10-07 23:29:05 +00:00
2026-10-04 07:58:41 -07:00
2026-11-01 09:52:31 +00:00
2026-10-20 00:24:28 +00:00
2026-10-03 07:54:09 -07:00
2026-10-20 00:24:28 +00:00
2026-10-20 00:24:28 +00:00
2026-10-20 00:24:28 +00:00
2026-10-29 09:58:34 +00:00
2026-10-20 00:24:28 +00:00
2026-10-03 16:13:45 -07:00
2026-10-20 01:06:17 +00:00
2026-10-25 22:31:08 +00:00
2026-10-26 17:35:04 +00:00
2026-10-20 00:24:28 +00:00
2026-08-31 08:55:30 -07:00
2026-10-26 07:08:52 +00:00
2026-10-29 04:55:01 +00:00
2026-10-26 04:32:27 +00:00
2026-10-26 04:32:27 +00:00
2026-11-01 10:13:55 +00:00
2026-10-28 13:05:02 +00:00
2026-10-28 13:05:02 +00:00
2026-11-01 20:45:39 +00:00
2026-10-20 00:24:28 +00:00
2026-10-06 23:42:19 +00:00
2026-10-20 00:24:28 +00:00
2026-10-20 00:24:28 +00:00
2026-11-01 23:50:50 +00:00
2026-10-31 11:15:23 +00:00
2026-03-26 11:15:24 -06:00
2026-10-30 12:16:21 +00:00
2026-11-01 00:29:06 +00:00
2026-06-25 09:42:45 -07:00
2026-10-31 15:33:39 +00:00
2026-10-24 23:55:21 +00:00
2026-10-26 09:33:07 +00:00
2026-10-20 00:24:28 +00:00
2026-10-26 04:32:27 +00:00
2026-05-21 21:21:07 -07:00
2026-10-04 07:58:41 -07:00
2026-10-20 00:24:28 +00:00
2026-10-25 05:06:30 +00:00
2026-10-26 04:32:27 +00:00
2026-10-20 00:24:28 +00:00
2026-04-24 01:38:21 -07:00
2026-10-25 16:35:45 +00:00
2026-11-01 08:12:16 +00:00
2026-10-20 00:24:28 +00:00
2026-11-01 09:52:31 +00:00
2026-11-01 09:52:31 +00:00
2026-10-31 10:23:41 +00:00
2026-10-28 13:05:02 +00:00
2026-11-01 09:35:42 +00:00
2026-11-01 09:35:42 +00:00
2026-10-29 02:33:42 +00:00
2026-10-26 04:32:27 +00:00
2026-10-26 04:32:27 +00:00
2026-10-26 04:32:27 +00:00
2026-10-20 00:24:28 +00:00
2026-10-20 00:24:28 +00:00
2026-10-04 07:58:41 -07:00
2026-10-20 00:24:28 +00:00
2026-10-28 13:05:02 +00:00
2026-10-28 02:58:29 +00:00
2026-10-28 02:58:29 +00:00
2026-10-31 10:23:41 +00:00
2026-10-26 04:32:27 +00:00
2026-10-20 00:24:28 +00:00
2026-10-20 00:24:28 +00:00
2026-10-31 05:53:14 +00:00
2026-10-20 00:24:28 +00:00
2026-10-29 04:22:41 +00:00
2026-10-27 03:04:06 +00:00
2026-10-27 03:04:06 +00:00
2026-10-20 00:24:28 +00:00
2026-10-17 00:41:41 +00:00
2026-11-01 06:11:17 +00:00
2026-10-20 00:24:28 +00:00
2026-10-31 00:42:31 +00:00
2026-03-30 22:25:46 -06:00
2026-10-11 16:48:11 +00:00
2026-10-03 07:54:09 -07:00
2026-11-01 06:11:17 +00:00
2026-10-20 00:24:28 +00:00
2026-10-27 17:20:55 +00:00
2026-10-07 23:29:05 +00:00
2026-10-27 15:11:13 +00:00
2026-11-01 20:30:10 +00:00
2026-10-27 10:16:08 +00:00
2026-10-20 00:24:28 +00:00
2026-10-20 00:24:28 +00:00
2026-10-26 04:32:27 +00:00
2026-10-26 04:32:27 +00:00
2026-10-20 00:24:28 +00:00
2026-11-01 01:50:36 +00:00
2026-10-20 00:24:28 +00:00
2026-10-26 04:32:27 +00:00
2026-10-02 11:11:00 -07:00
2026-10-19 23:31:59 +00:00
2026-10-20 00:24:28 +00:00
2026-11-01 05:57:18 +00:00
2026-10-27 01:30:23 +00:00
2026-11-01 13:28:21 +00:00
2026-11-01 13:42:07 +00:00
2026-11-01 05:57:18 +00:00
2026-11-01 01:38:04 +00:00
2026-11-01 05:57:18 +00:00
2026-10-31 07:22:56 +00:00
2026-10-20 00:24:28 +00:00
2026-10-01 13:55:16 -07:00
2026-10-16 22:00:32 +00:00
2026-10-04 07:58:41 -07:00
2026-10-10 23:26:08 +00:00
2026-11-01 00:29:06 +00:00
2026-10-26 04:32:27 +00:00
2026-11-01 13:42:07 +00:00
2026-11-01 13:42:07 +00:00
2026-10-31 06:07:36 +00:00
2026-10-31 01:09:31 +00:00
2026-11-01 05:29:22 +00:00
2026-11-01 21:26:59 +00:00
2026-10-31 01:09:31 +00:00
2026-10-28 02:58:29 +00:00
2026-10-17 03:32:16 +00:00
2026-11-01 01:25:15 +00:00
2026-11-01 05:57:18 +00:00
2026-10-26 04:32:27 +00:00
2026-10-31 05:06:03 +00:00
2026-10-01 11:57:48 -07:00
2026-11-01 06:11:17 +00:00
2026-10-20 00:24:28 +00:00
2026-11-01 09:35:42 +00:00
2026-10-26 04:32:27 +00:00
2026-10-01 11:57:48 -07:00
2026-10-26 04:32:27 +00:00
2026-10-26 04:32:27 +00:00
2026-10-20 00:24:28 +00:00
2026-10-26 23:45:45 +00:00
2026-11-01 09:35:42 +00:00
2026-10-28 09:59:40 +00:00
2026-10-26 07:22:44 +00:00
2026-11-01 00:29:06 +00:00
2026-10-01 11:57:48 -07:00
2026-10-29 05:35:56 +00:00
2026-10-20 00:24:28 +00:00
2026-10-27 06:36:56 +00:00
2026-10-31 13:54:04 +00:00
