3 Commits

Author	SHA1	Message	Date
Teknium	b8905c7d62	simplify(compat): livetest scripts spy normalize_usage where the loop calls it (agent.turn_usage), not the old facade	2026-09-03 17:01:56 -07:00
alt-glitch	a667ab60d9	fix(livetest): render multi-query bridge calls	2026-08-25 16:39:12 -07:00
teknium1	2643ea17fb	bench: discovery-bound suite — paraphrase/absence/survey tasks isolate the listing's structural advantage ... Bridge vs listing only (Opus 4.8, 830 real UE schemas, 3 reps/cell). Excluding one both-modes mock artifact: listing 24/24 vs bridge 20/24, searches/task 0.2 vs 4.0. Bridge failures: core-tool substitution at frontier tier (ran the host test suite via terminal instead of discovering RunTests, 2/3 reps), up to 8 searches to prove a negative, and search-vocabulary misses on paraphrase. Listing asserts absence in zero searches and answers a 5-way capability survey in 1 API call.	2026-07-26 08:26:09 -07:00