24 Commits

Author SHA1 Message Date
Rui d2c92dfb0a refactor(eve): unify background workflow execution (#3413)
Signed-off-by: Rui Conti <ruiconti@gmail.com>
2026-09-19 00:52:28 -04:00
Andrew Barba 8e011906e0 feat(eve): evals - use evaluation models for judges (#3531)
Signed-off-by: Andrew Barba <barba@hey.com>
2026-09-18 22:13:55 +00:00
Andrew Barba 6ddfa9bfbe feat(eve): sessions - prewarm and stream continuously (#3417)
Signed-off-by: Andrew Barba <barba@hey.com>
2026-09-17 14:28:45 -04:00
Andrew Barba 8b32e31bf9 chore(eve): evals - use gpt-5.6-luna judge (#3464)
Signed-off-by: Andrew Barba <barba@hey.com>
2026-09-17 10:45:05 -04:00
Casey Gowrie ee02527b12 feat(eve): log eval workflow run IDs (#3177)
Signed-off-by: Casey Gowrie <ctgowrie@gmail.com>
2026-09-09 11:14:38 -04:00
mehulsonowal d74fdb46c4 feat(evals): add a Datadog Experiments reporter (#2860) 2026-09-08 18:50:52 -04:00
Andrew Barba 9cb98b9862 fix(eve): resolve ten session, tool, and integration failures (#3082)
Signed-off-by: Andrew Barba <barba@hey.com>
Signed-off-by: Andrew Barba <1316152+AndrewBarba@users.noreply.github.com>
2026-09-05 21:08:24 +00:00
Casey Gowrie a3b23c0357 feat(eve): expose eval session transcripts (#2672)
Signed-off-by: Casey Gowrie <ctgowrie@gmail.com>
2026-08-27 16:47:48 -04:00
Andrew Barba 77eb8194d0 feat(eve): eval reporters - add trace-aware lifecycle callbacks (#1980)
Signed-off-by: Andrew Barba <barba@hey.com>
2026-08-13 01:49:34 +00:00
Colton Padden 09aa810829 docs: reorganize navigation and consolidate guides (#1916)
Signed-off-by: Colton Padden <colton.padden@vercel.com>
2026-08-12 21:49:04 -04:00
Casey Gowrie 40b09e60d9 feat(eve)!: unify public session operation APIs (#1597)
Signed-off-by: Casey Gowrie <ctgowrie@gmail.com>
2026-08-05 17:40:45 -04:00
Casey Gowrie 01791118f9 feat(eve): improve eval assertion diagnostics (#1418)
Signed-off-by: Casey Gowrie <ctgowrie@gmail.com>
2026-07-30 19:52:06 +00:00
Andrew Barba 01ed80d3c0 test(e2e): split model and world suites (#1387)
Signed-off-by: Andrew Barba <barba@hey.com>
2026-07-30 18:54:18 +00:00
Andrew Barba 25683870ff feat(eve): cancellation - cascade to descendant turns (#832)
Signed-off-by: Andrew Barba <barba@hey.com>
2026-07-16 00:49:48 +00:00
Andrew Barba 20cd9a1f26 feat(eve): cancellation layer 2 - HTTP cancel-turn trigger route (+ channel-ops research) (#817)
Signed-off-by: Andrew Barba <barba@hey.com>
2026-07-15 14:45:30 -04:00
Andrew Barba 89cd2d6345 feat(eve): eval assertions - support count predicates (#647)
Signed-off-by: Andrew Barba <barba@hey.com>
Signed-off-by: 墨綠BG <s5460703@gmail.com>
Co-authored-by: 墨綠BG <s5460703@gmail.com>
2026-07-09 13:41:22 -04:00
Andrew Barba 5b3162752a feat(eve): evals - add deterministic mock models (#342)
Signed-off-by: Andrew Barba <barba@hey.com>
2026-06-26 13:49:54 -04:00
Andrew Barba 194a8bb7bd feat(eve): evals - add scoped assertion API (#314)
Signed-off-by: Andrew Barba <barba@hey.com>
2026-06-25 20:18:02 -04:00
Rui c084232e16 fix(eve): verify remote Vercel credentials (#109)
Signed-off-by: Rui Conti <ruiconti@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Andrew Barba <barba@hey.com>
2026-06-22 10:45:17 -04:00
Casey Gowrie 2197c14b13 fix(skills): qualify single-entry dynamic skill maps as slug__key (#143)
Signed-off-by: Casey Gowrie <ctgowrie@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-20 17:54:53 -04:00
Rui 1e2e8effda fix(eve): use lowercase product name consistently (#32) 2026-06-17 15:55:27 +01:00
Allen Zhou 624cfb88d5 docs: add legal safety guidance (#10) 2026-06-16 23:25:07 +01:00
John Phamous 13b0c1ebf9 docs: content and concision fixes + docs:check guardrails (#4)
Co-authored-by: Andrew Barba <barba@hey.com>
2026-06-16 18:56:25 +00:00
Andrew Barba f44e16a3e5 Hello Eve (#1)
Co-authored-by: Casey Gowrie <ctgowrie@gmail.com>
Co-authored-by: Allen Zhou <46854522+allenzhou101@users.noreply.github.com>
Co-authored-by: Rui Conti <ruiconti@gmail.com>
Co-authored-by: JJ Kasper <jj@jjsweb.site>
Co-authored-by: Timo Lins <1440854+timolins@users.noreply.github.com>
Co-authored-by: Felix Arntz <3531426+felixarntz@users.noreply.github.com>
Co-authored-by: Shar Dara <2982650+darafsheh@users.noreply.github.com>
Co-authored-by: John Phamous <johnphammail@gmail.com>
2026-06-16 18:10:54 +01:00