Document target normalization V0 experiment

tests/gold/target_normalization_v0/cases.json

@@ -0,0 +1,9 @@
+{
+  "schema_version":"experimental-target-normalization-v0",
+  "cases":[
+    {"case_id":"TN-01","observations":[{"observation_id":"obs_1","evidence_id":"e1","content":"Martin: Mit Dr. Schlummer arbeiten wir nicht weiter.","speaker":"Martin","named_person":"Dr. Schlummer","addressee":null}],"fixed_linkage":{"candidate_observation_id":"obs_1","target_observation_id":"obs_1"},"expected":{"normalized_target_text":"Zusammenarbeit mit Dr. Schlummer fortsetzen","action_concepts":[["Zusammenarbeit","arbeiten"],["Schlummer"],["fortsetzen","weiter"]],"material_concepts":[],"forbidden_concepts":["nicht","beenden"],"german_markers":["Zusammenarbeit","arbeiten","fortsetzen"]}},
+    {"case_id":"TN-02","observations":[{"observation_id":"obs_1","evidence_id":"e1","content":"Martin: Eine Möglichkeit wäre, die externe Lösung weiterzuverfolgen.","speaker":"Martin","named_person":null,"addressee":null},{"observation_id":"obs_2","evidence_id":"e2","content":"Martin: Das verfolgen wir nicht weiter.","speaker":"Martin","named_person":null,"addressee":null}],"fixed_linkage":{"candidate_observation_id":"obs_2","target_observation_id":"obs_1"},"expected":{"normalized_target_text":"externe Lösung weiterverfolgen","action_concepts":[["externe Lösung"],["weiterverfolgen","weiter verfolgen"]],"material_concepts":[],"forbidden_concepts":["nicht"],"german_markers":["Lösung","verfolgen"]}},
+    {"case_id":"TN-03","observations":[{"observation_id":"obs_1","evidence_id":"e1","content":"Martin: Für den Druckversuch steht die reale Anlage zur Diskussion.","speaker":"Martin","named_person":null,"addressee":null},{"observation_id":"obs_2","evidence_id":"e2","content":"Martin: Die reale Anlage nutzen wir dafür nicht.","speaker":"Martin","named_person":null,"addressee":null}],"fixed_linkage":{"candidate_observation_id":"obs_2","target_observation_id":"obs_1"},"expected":{"normalized_target_text":"reale Anlage für den Druckversuch nutzen","action_concepts":[["Anlage"],["nutzen"]],"material_concepts":[["real"],["Druckversuch"]],"forbidden_concepts":["nicht","zur Diskussion"],"german_markers":["Anlage","Druckversuch","nutzen"]}},
+    {"case_id":"TN-04","observations":[{"observation_id":"obs_1","evidence_id":"e1","content":"Martin: Wir könnten den Versuch in der realen Anlage durchführen.","speaker":"Martin","named_person":null,"addressee":null},{"observation_id":"obs_2","evidence_id":"e2","content":"Martin: Das machen wir nicht; wir testen stattdessen im Technikum.","speaker":"Martin","named_person":null,"addressee":null}],"fixed_linkage":{"candidate_observation_id":"obs_2","target_observation_id":"obs_1"},"expected":{"normalized_target_text":"Versuch in der realen Anlage durchführen","action_concepts":[["Versuch"],["durchführen"]],"material_concepts":[["real"],["Anlage"]],"forbidden_concepts":["nicht","Technikum","stattdessen"],"german_markers":["Versuch","Anlage","durchführen"]}}
+  ]
+}

tests/test_target_normalization_experiment.py

@@ -0,0 +1,51 @@
+import argparse,copy,json,tempfile,unittest
+from pathlib import Path
+from unittest.mock import Mock
+import src.meeting_lab.controlled_semantic_derivation.experiment_target_normalization as module
+from src.meeting_lab.controlled_semantic_derivation.experiment_h import DerivationValidationError
+
+CASES=module.load_cases(Path("tests/gold/target_normalization_v0/cases.json")); BY={c["case_id"]:c for c in CASES}
+def output(case,text=None):
+ link=case["fixed_linkage"]; return {"candidate_observation_id":link["candidate_observation_id"],"target_observation_id":link["target_observation_id"],"normalized_target_text":text or case["expected"]["normalized_target_text"]}
+
+class TargetNormalizationTests(unittest.TestCase):
+ def test_exact_id_copying_accepted(self):
+  for case in CASES: self.assertEqual(module.validate_output(output(case),case),output(case))
+ def test_changed_candidate_rejected(self):
+  case=BY["TN-02"]; data=output(case); data["candidate_observation_id"]="obs_1"
+  with self.assertRaises(DerivationValidationError): module.validate_output(data,case)
+ def test_changed_target_rejected(self):
+  case=BY["TN-02"]; data=output(case); data["target_observation_id"]="obs_2"
+  with self.assertRaises(DerivationValidationError): module.validate_output(data,case)
+ def test_empty_and_null_text_rejected(self):
+  case=BY["TN-01"]
+  for value in ("",None):
+   data=output(case); data["normalized_target_text"]=value
+   with self.assertRaises(DerivationValidationError): module.validate_output(data,case)
+ def test_unknown_and_forbidden_fields_rejected(self):
+  case=BY["TN-01"]
+  for extra in ({"extra":1},{"status":"x"},{"nested":{"decision":True}}):
+   data=output(case); data.update(extra)
+   with self.assertRaises(DerivationValidationError): module.validate_output(data,case)
+ def test_true_schema_fixes_both_ids_and_disallows_null(self):
+  case=BY["TN-02"]; schema=module.output_schema(case); self.assertEqual(schema["properties"]["candidate_observation_id"]["const"],"obs_2"); self.assertEqual(schema["properties"]["target_observation_id"]["const"],"obs_1"); self.assertEqual(schema["properties"]["normalized_target_text"]["type"],"string"); self.assertFalse(schema["additionalProperties"])
+ def test_payload_uses_schema_object(self):
+  schema=module.output_schema(BY["TN-01"]); payload=module.build_payload("qwen3.5:9B","p",schema,16384,1024); self.assertIs(payload["format"],schema); self.assertIsInstance(payload["format"],dict)
+ def test_duplicate_ids_and_evidence_rejected(self):
+  for field in ("observation_id","evidence_id"):
+   case=copy.deepcopy(BY["TN-02"]); case["observations"][1][field]=case["observations"][0][field]
+   with self.assertRaises(DerivationValidationError): module.validate_linkage(case)
+ def test_prompt_is_fixed_normalization_only(self):
+  first=module.build_prompt(BY["TN-01"]); second=module.build_prompt(BY["TN-02"]); self.assertIn("do not perform target selection",first); self.assertIn("concrete POSITIVE action",first); self.assertEqual(first.split("Fixed candidate_observation_id:")[0],second.split("Fixed candidate_observation_id:")[0])
+ def test_no_target_selection_or_rejection_derivation_exists(self):
+  self.assertFalse(hasattr(module,"select_target")); self.assertFalse(hasattr(module,"derive")); self.assertNotIn("explicitly_rejected",module.OUTPUT_KEYS); self.assertNotIn("status",module.OUTPUT_KEYS)
+ def test_artifacts_preserve_fixed_linkage(self):
+  case=BY["TN-01"]; fixture={"schema_version":module.SCHEMA_VERSION,"cases":[case]}; caller=Mock(return_value=(json.dumps(output(case)),{"model":"qwen3.5:9B"}))
+  with tempfile.TemporaryDirectory() as tmp:
+   root=Path(tmp); path=root/"cases.json"; path.write_text(json.dumps(fixture)); out=root/"out"; args=argparse.Namespace(cases=path,output=out,endpoint="x",model="qwen3.5:9B",timeout=1,num_ctx=16384,num_predict=1024); summary=module.run(args,caller); self.assertEqual(summary["llm_call_count"],1); self.assertEqual(json.loads((out/"tn-01"/"fixed_linkage.json").read_text()),case["fixed_linkage"]); self.assertTrue((out/"tn-01"/"normalized_target_result.json").exists())
+ def test_negative_polarity_fails_evaluation(self):
+  case=BY["TN-01"]; self.assertEqual(module.evaluate(case,output(case,"Mit Dr. Schlummer arbeiten wir nicht weiter"))["classification"],"FAIL")
+ def test_material_scope_and_alternative_contract(self):
+  self.assertEqual(module.evaluate(BY["TN-03"],output(BY["TN-03"]))["classification"],"PASS"); self.assertEqual(module.evaluate(BY["TN-04"],output(BY["TN-04"]))["classification"],"PASS")
+
+if __name__=="__main__": unittest.main()