9 Commits

Author	SHA1	Message	Date
Sehoon Shon	5f4fa08b38	Remove previewFeatures and default to Gemini 3 (#18414)	2026-02-06 18:02:57 +00:00
Yuna Seol	d281782e69	feat: expand verify-release to macOS and Windows (#18145) ... Co-authored-by: Yuna Seol <yunaseol@google.com>	2026-02-05 21:21:55 +00:00
Alisa	21aa049734	Improving memory tool instructions and eval testing (#18091)	2026-02-05 18:07:47 +00:00
Gal Zahavi	7e1668997f	fix(cli): allow restricted .env loading in untrusted sandboxed folders (#17806)	2026-02-04 01:08:10 +00:00
Coco Sheng	18c9bb1fc8	fix(test): improve test isolation and enable subagent evaluations (#18138)	2026-02-03 19:05:26 +00:00
Vedant Mahajan	61c64931d6	test: add integration test to verify stdout/stderr routing (#17280) ... Co-authored-by: Allen Hutchison <adh@google.com>	2026-01-29 00:01:57 +00:00
Jerop Kipruto	54e03635d9	feat(plan): refactor TestRig and eval helper to support configurable approval modes (#17171)	2026-01-21 15:43:48 +00:00
Christian Gunderman	b4a786e42f	Stabilize the git evals (#16989)	2026-01-19 06:18:06 +00:00
Christian Gunderman	b82c66b2d8	Behavioral evals framework. (#16047)	2026-01-14 04:49:17 +00:00