Harden long-running behavioral evaluations

2026-09-23 00:19:35 +08:00
parent 9f54f8f5a3
commit afcd6c614e
4 changed files with 35 additions and 3 deletions
@@ -22,6 +22,18 @@ class ClientConfigTests(unittest.TestCase):
        self.assertEqual(solver.api_key, "solver-key")
        self.assertEqual(renderer.base_url, "https://renderer.example/v1")
        self.assertEqual(solver.base_url, "https://solver.example/v1")
+        self.assertEqual(renderer.timeout_seconds, 240)
+
+    def test_role_timeout_can_be_overridden(self):
+        values = {
+            "SOLVER_API_KEY": "solver-key",
+            "SOLVER_BASE_URL": "https://solver.example/v1",
+            "SOLVER_MODEL": "solver-model",
+            "SOLVER_TIMEOUT_SECONDS": "360",
+        }
+        with patch.dict(os.environ, values, clear=True):
+            solver = LLMClientConfig.from_env("solver")
+        self.assertEqual(solver.timeout_seconds, 360)

    def test_missing_role_base_url_is_rejected(self):
        values = {