Files
ARTEX/db
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
..
2026-08-28 07:37:24 +08:00
2026-07-26 04:27:45 -04:00
2026-07-26 04:27:45 -04:00
2026-10-08 23:14:34 +02:00
2026-08-28 12:56:29 +08:00
2026-08-28 12:56:29 +08:00
2026-08-25 12:05:26 +08:00
2026-08-28 12:56:29 +08:00
2026-10-08 23:14:34 +02:00