langwatch-scenario 0.7.13__py3-none-any.whl → 0.7.14__py3-none-any.whl

{langwatch_scenario-0.7.13.dist-info → langwatch_scenario-0.7.14.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: langwatch-scenario
-Version: 0.7.13
+Version: 0.7.14
 Summary: The end-to-end agent testing library
 Author-email: LangWatch Team <support@langwatch.ai>
 License: MIT

{langwatch_scenario-0.7.13.dist-info → langwatch_scenario-0.7.14.dist-info}/RECORD

@@ -2,7 +2,7 @@ scenario/__init__.py,sha256=4WO8TjY8Lc0NhYL7b9LvaB1xCBqwUkLuI0uIA6PQP6c,4223
 scenario/_error_messages.py,sha256=QVFSbhzsVNGz2GOBOaoQFW6w6AOyZCWLTt0ySWPfnGw,3882
 scenario/agent_adapter.py,sha256=PoY2KQqYuqzIIb3-nhIU-MPXwHJc1vmwdweMy7ut-hk,4255
 scenario/cache.py,sha256=J6s6Sia_Ce6TrnsInlhfxm6SF8tygo3sH-_cQCRX1WA,6213
-scenario/judge_agent.py,sha256=xIZaS7t7lWLLEj7UKYRpqKtxXtu7vO3ePN90lW8wbFQ,17686
+scenario/judge_agent.py,sha256=RxXYpImLsr6FpFivSRB26vWSnQFJlAd6ocWdyL6EAYM,17752
 scenario/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 scenario/pytest_plugin.py,sha256=wRCuGD9uwrrLt2fY15zK6mnmY9W_dO_m0WalPJYE5II,11491
 scenario/scenario_executor.py,sha256=v41UgSHebosXf95FfYIeVUm6s4IbMP_U58FdGoZ_kZU,35653
@@ -235,8 +235,8 @@ scenario/config/__init__.py,sha256=b2X_bqkIrd7jZY9dRrXk2wOqoPe87Nl_SRGuZhlolxA,1
 scenario/config/langwatch.py,sha256=ijWchFbUsLbQooAZmwyTw4rxfRLQseZ1GoVSiPPbzpw,1677
 scenario/config/model.py,sha256=VQtPkG-O1gVjtMIKbMOrbcnySv8pqODokC_VOaKVS4g,2054
 scenario/config/scenario.py,sha256=tUnzFBtuhPimU4EyaXm9T6KlpfntGtQaH5teW2F9oGk,5426
-langwatch_scenario-0.7.13.dist-info/METADATA,sha256=mitJjq_Y3AjIUtMFK5gpXpOYBdG9tRU-yHqhLWE6tGM,20065
-langwatch_scenario-0.7.13.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-langwatch_scenario-0.7.13.dist-info/entry_points.txt,sha256=WlEnJ_gku0i18bIa3DSuGqXRX-QDQLe_s0YmRzK45TI,45
-langwatch_scenario-0.7.13.dist-info/top_level.txt,sha256=45Mn28aedJsetnBMB5xSmrJ-yo701QLH89Zlz4r1clE,9
-langwatch_scenario-0.7.13.dist-info/RECORD,,
+langwatch_scenario-0.7.14.dist-info/METADATA,sha256=B9rniakNtewXOAzmgYi4AbfMRRRS1_GqtXKZiSRtNYQ,20065
+langwatch_scenario-0.7.14.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+langwatch_scenario-0.7.14.dist-info/entry_points.txt,sha256=WlEnJ_gku0i18bIa3DSuGqXRX-QDQLe_s0YmRzK45TI,45
+langwatch_scenario-0.7.14.dist-info/top_level.txt,sha256=45Mn28aedJsetnBMB5xSmrJ-yo701QLH89Zlz4r1clE,9
+langwatch_scenario-0.7.14.dist-info/RECORD,,

scenario/judge_agent.py

@@ -339,7 +339,8 @@ if you don't have enough information to make a verdict, say inconclusive with ma
                                 "type": "object",
                                 "properties": {
                                     criteria_names[idx]: {
-                                        "enum": [True, False, "inconclusive"],
+                                        "type": "string",
+                                        "enum": ["true", "false", "inconclusive"],
                                         "description": criterion,
                                     }
                                     for idx, criterion in enumerate(self.criteria)
@@ -415,12 +416,12 @@ if you don't have enough information to make a verdict, say inconclusive with ma
                         passed_criteria = [
                             self.criteria[idx]
                             for idx, criterion in enumerate(criteria.values())
-                            if criterion == True
+                            if criterion == "true"
                         ]
                         failed_criteria = [
                             self.criteria[idx]
                             for idx, criterion in enumerate(criteria.values())
-                            if criterion == False or criterion == "inconclusive"
+                            if criterion == "false" or criterion == "inconclusive"
                         ]
 
                         # Return the appropriate ScenarioResult based on the verdict