BaaRai
cf369dec4f
feat(server): per-task outcome card for RSI baselines
...
Adds GET /api/tasks/{id}/outcome: finding disposition and severity,
retest verdicts, result-row token totals, tool calls, skill misses, and
wall time in one row. This is the measurement layer an RSI loop needs
before claiming a change helped; it alters no agent behavior.
Metric selection follows harness2 (Google Research, Apache-2.0,
arXiv 2610.14224) and the task-gain / retained-gain / improver-gain
taxonomy in the awesome-rsi list.
2026-10-19 00:28:27 +02:00
..
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-08-28 15:25:20 +08:00
2026-08-28 07:37:24 +08:00
2026-10-08 23:14:34 +02:00
2026-08-24 19:29:14 +08:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-08-31 12:20:31 -04:00
2026-10-08 23:14:34 +02:00
2026-10-12 08:20:37 +02:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-08-24 19:29:38 +08:00
2026-08-25 14:56:15 +08:00
2026-07-26 04:27:45 -04:00
2026-08-28 15:25:20 +08:00
2026-10-12 18:43:29 +02:00
2026-09-09 11:52:15 -04:00
2026-08-24 19:29:00 +08:00
2026-08-28 14:03:07 +08:00
2026-10-08 23:14:34 +02:00
2026-09-11 08:47:57 +08:00
2026-10-12 18:36:44 +02:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-09-10 13:03:20 +08:00
2026-09-10 13:03:20 +08:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-08-24 19:29:00 +08:00
2026-08-24 19:29:00 +08:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-09-15 20:08:12 +08:00
2026-09-15 23:51:37 +08:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-09-12 03:00:28 -04:00
2026-08-25 09:40:05 -04:00
2026-10-12 08:53:20 +02:00
2026-08-24 19:28:18 +08:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-07-26 04:27:45 -04:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-10-12 21:13:28 +02:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-09-11 00:41:01 +08:00
2026-10-08 23:14:34 +02:00
2026-08-24 19:30:14 +08:00
2026-08-28 12:56:29 +08:00
2026-08-28 12:56:29 +08:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-08-24 09:16:44 -04:00
2026-08-24 09:16:44 -04:00
2026-08-24 19:29:00 +08:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00
2026-10-09 14:28:08 +02:00
2026-08-24 19:29:00 +08:00
2026-10-08 23:14:34 +02:00
2026-08-28 08:00:36 +08:00
2026-08-25 14:56:15 +08:00
2026-10-19 00:28:27 +02:00
2026-08-24 19:29:00 +08:00
2026-08-09 09:09:59 -04:00
2026-10-08 23:14:34 +02:00
2026-08-24 19:29:00 +08:00
2026-08-24 19:29:46 +08:00
2026-09-19 09:27:03 -04:00
2026-10-08 23:14:34 +02:00
2026-10-12 21:13:28 +02:00
2026-10-12 18:43:29 +02:00
2026-08-25 12:05:26 +08:00
2026-08-28 12:56:29 +08:00
2026-10-08 23:14:34 +02:00
2026-10-08 23:14:34 +02:00