Move workflow evaluations to standalone runner

2026-07-29 10:35:45 +08:00
parent 3187713bfe
commit e6437ab332
9 changed files with 311 additions and 171 deletions
--- a/evals/cases/browser_addon/initial.yaml
+++ b/evals/cases/browser_addon/initial.yaml
@@ -0,0 +1,7 @@
+name: browser_addon_initial_stage
+clientMode: browser_addon
+
+steps:
+  - input: hi
+    expect:
+      stageCode: browser_addon.1001