11 Commits

Author	SHA1	Message	Date
Alice Hau	d47ab3e31b	fix: fix allowing multiple selectors in goosebench (#1814)	2025-03-23 22:29:16 -04:00
marcelle	4c03b34058	feat: refactor register eval (#1713)	2025-03-18 15:18:09 -04:00
Zaki Ali	a9fefd0e43	feat: add default metrics for core evals (#1602)	2025-03-14 18:11:31 -07:00
marcelle	c23be1eb19	fix: ensure repeating benches return to initial run-dir (#1617)	2025-03-11 11:44:57 -04:00
Zaki Ali	c0e719eaba	fix: merge error logging in goose bench (#1545)	2025-03-10 15:45:00 -07:00
Alice Hau	bb4feacf03	feat: add additional goosebench evals (#1571) ... Co-authored-by: Alice Hau <alice.a.hau@gmail.com>	2025-03-10 15:11:44 -04:00
marcelle	1354133b18	fix: included files was panicing because dir didnt exist (#1583)	2025-03-09 22:47:46 -04:00
marcelle	00fc3a5de8	Feat: support auto-including dirs in binary/bench-work-dir (#1576)	2025-03-07 17:53:39 -05:00
marcelle	798d657e7e	bugfix: refactor workdirs to be async-safe, and simpler (#1558)	2025-03-06 21:11:35 -05:00
Zaki Ali	ebf7cb1231	feat: split required_extensions in bench to builtin/external (#1547)	2025-03-06 17:12:21 -08:00
marcelle	49dee048e4	feat: goose bench framework for functional and regression testing ... Co-authored-by: Zaki Ali <zaki@squareup.com>	2025-03-05 21:23:00 -05:00