José Braulio González Valido
|
b9b527af9d
|
ci: Run the Instance AI eval PR gate on the pr tier only (no-changelog) (#39315)
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
|
2026-09-22 18:42:31 +00:00 |
|
Michael Drury
|
684b930fa6
|
feat(core): Improve Agent Builder evaluation and intent routing (#38329)
|
2026-09-14 13:13:51 +00:00 |
|
José Braulio González Valido
|
42754a82b3
|
fix(core): Ignore undeclared fields in agent resume payloads (#35607)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-08-06 08:06:04 +00:00 |
|
Charlie Kolb
|
e41aae0fb6
|
ci: Show workflow_dispatch inputs in workflow run names (#35496)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-08-04 09:46:14 +00:00 |
|
José Braulio González Valido
|
4d11639cf1
|
test(ai-builder): Add plan-rejection eval and harden multi-turn eval consistency (no-changelog) (#33433)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-07-06 06:11:22 +00:00 |
|
José Braulio González Valido
|
a8f1b2c1b8
|
ci: Scope Instance AI evals dispatcher to PR gating (no-changelog) (#33499)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-03 07:29:09 +00:00 |
|
José Braulio González Valido
|
c3741ce12a
|
feat(ai-builder): Re-run Instance AI evals against the PR head on demand (no-changelog) (#33148)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-06-29 06:00:43 +00:00 |
|
José Braulio González Valido
|
05c554dad5
|
ci: Align instance AI eval workflow with main CI docker image build (no-changelog) (#32094)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-06-11 07:35:00 +00:00 |
|
José Braulio González Valido
|
46a222a15b
|
ci: Re-enable Instance AI evals on PRs with cost-bounded trigger (no-changelog) (#31430)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-06-05 08:40:23 +00:00 |
|
José Braulio González Valido
|
f25e12de87
|
ci(ai-builder): Add iterations + experiment-name inputs to instance-ai eval dispatch (no-changelog) (#31631)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-06-04 09:57:08 +00:00 |
|
Tomi Turtiainen
|
c5c8983f34
|
ci: Integrate n8n sandbox service into Instance AI evals (no-changelog) (#31051)
|
2026-05-27 08:55:54 +00:00 |
|
José Braulio González Valido
|
da3e6b1635
|
ci: Disable Instance AI eval auto-trigger on PR review (no-changelog) (#30930)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-05-22 07:57:27 +00:00 |
|
José Braulio González Valido
|
be220ab32a
|
ci: Split Instance AI evals to own workflow, fire on approval only (no-changelog) (#30815)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-05-20 13:38:53 +00:00 |
|