Added validation-specific LLM configuration options

tests/test_llm_validators.py

@@ -40,6 +40,7 @@ class FakeStructuredLLMClient:
                 "stage_name": stage_name,
                 "messages": list(messages),
                 "response_model": response_model,
+                "config": config,
             }
         )
         if not self._responses:
@@ -62,6 +63,7 @@ class CoordinatedStructuredLLMClient:
                     "stage_name": stage_name,
                     "messages": list(messages),
                     "response_model": response_model,
+                    "config": config,
                 }
             )
             if not self._responses:
@@ -97,15 +99,20 @@ def _context(
     tmp_path,
     replacement_policy="require_unique",
     llm_concurrency=1,
+    validation_llm_concurrency=None,
 ):
+    config = AuditaConfig.from_sources(
+        env={"OPENROUTER_API_KEY": "test-key"},
+        overrides=ConfigOverrides(
+            llm_concurrency=llm_concurrency,
+            validation_llm_concurrency=validation_llm_concurrency,
+        ),
+    )
     return ValidationContext(
         proposals=proposals,
         transcript=transcript,
         glossary=_glossary(),
-        config=AuditaConfig.from_sources(
-            env={"OPENROUTER_API_KEY": "test-key"},
-            overrides=ConfigOverrides(llm_concurrency=llm_concurrency),
-        ),
+        config=config.validation_llm_config(),
         run_spec=ModuleRunSpec(
             instance_name="homophones",
             module_key="homophones",
@@ -1190,3 +1197,157 @@ def test_llm_validators_process_batches_concurrently_and_preserve_proposal_order
         (1, True),
     ]
     assert len(client.calls) == 2
+
+
+def test_validator_uses_validation_llm_config(tmp_path):
+    transcript = parse_transcript_json(
+        """
+        [
+          {"id": 1, "speaker": "A", "start": 0.0, "end": 1.0, "text": "There were gestures at the temple."}
+        ]
+        """
+    )
+    proposals = [
+        CorrectionProposal(
+            proposal_index=0,
+            module_instance="homophones",
+            module_key="homophones",
+            id=1,
+            original_text="gestures",
+            corrected_text="Jesters",
+            confidence=0.95,
+        )
+    ]
+    client = FakeStructuredLLMClient(
+        [
+            {
+                "validations": [
+                    {
+                        "correction_index": 0,
+                        "approved": True,
+                        "confidence": 0.97,
+                        "reason": "ok",
+                    }
+                ]
+            }
+        ]
+    )
+    config = AuditaConfig.from_sources(
+        env={"OPENROUTER_API_KEY": "primary-key"},
+        overrides=ConfigOverrides(
+            model="primary-model",
+            base_url="http://localhost:8000/v1",
+            max_retries=7,
+            llm_timeout_seconds=120,
+            validation_llm_api_key="validation-key",
+            validation_model="validation-model",
+            validation_base_url="http://localhost:9000/v1",
+            validation_max_retries=2,
+            validation_llm_timeout_seconds=240,
+            validation_llm_concurrency=3,
+        ),
+    )
+    context = ValidationContext(
+        proposals=proposals,
+        transcript=transcript,
+        glossary=_glossary(),
+        config=config.validation_llm_config(),
+        run_spec=ModuleRunSpec(
+            instance_name="homophones",
+            module_key="homophones",
+            module=_Module("require_unique"),
+        ),
+        run_dir=tmp_path,
+        llm_client=client,
+    )
+
+    SpokenFormPlausibilityValidator("spoken_form_plausibility_review").validate(context)
+
+    validation_config = client.calls[0]["config"]
+    assert validation_config.api_key == "validation-key"
+    assert validation_config.model == "validation-model"
+    assert validation_config.base_url == "http://localhost:9000/v1"
+    assert validation_config.max_retries == 2
+    assert validation_config.llm_timeout_seconds == 240
+    assert validation_config.llm_concurrency == 3
+
+
+def test_validator_uses_validation_llm_concurrency_override(tmp_path, monkeypatch):
+    transcript = parse_transcript_json(
+        """
+        [
+          {"id": 1, "speaker": "A", "start": 0.0, "end": 1.0, "text": "There were gestures at the temple."},
+          {"id": 2, "speaker": "A", "start": 1.0, "end": 2.0, "text": "ChatGPT still can't do that with a dam."}
+        ]
+        """
+    )
+    proposals = [
+        CorrectionProposal(
+            proposal_index=0,
+            module_instance="homophones",
+            module_key="homophones",
+            id=1,
+            original_text="gestures",
+            corrected_text="Jesters",
+            confidence=0.95,
+        ),
+        CorrectionProposal(
+            proposal_index=1,
+            module_instance="homophones",
+            module_key="homophones",
+            id=2,
+            original_text="dam",
+            corrected_text="damn",
+            confidence=0.95,
+        ),
+    ]
+    client = CoordinatedStructuredLLMClient(
+        [
+            lambda **kwargs: {
+                "validations": [
+                    {
+                        "correction_index": 0 if '"correction_index": 0' in kwargs["messages"][1]["content"] else 1,
+                        "approved": True,
+                        "confidence": 0.97,
+                        "reason": "ok",
+                    }
+                ]
+            },
+            lambda **kwargs: {
+                "validations": [
+                    {
+                        "correction_index": 0 if '"correction_index": 0' in kwargs["messages"][1]["content"] else 1,
+                        "approved": True,
+                        "confidence": 0.94,
+                        "reason": "ok",
+                    }
+                ]
+            },
+        ],
+        threading.Barrier(2, timeout=1.0),
+    )
+
+    def fake_chunk_payload_items(items, max_tokens, payload_fn, empty_error_message):
+        return [
+            TokenBatch(batch_index=0, items=list(items[:1]), token_count=1),
+            TokenBatch(batch_index=1, items=list(items[1:]), token_count=1),
+        ]
+
+    monkeypatch.setattr(llm_module, "chunk_payload_items", fake_chunk_payload_items)
+
+    result = SpokenFormPlausibilityValidator("spoken_form_plausibility_review").validate(
+        _context(
+            proposals=proposals,
+            transcript=transcript,
+            llm_client=client,
+            tmp_path=tmp_path,
+            llm_concurrency=1,
+            validation_llm_concurrency=2,
+        )
+    )
+
+    assert [(decision.proposal_index, decision.approved) for decision in result.decisions] == [
+        (0, True),
+        (1, True),
+    ]
+    assert len(client.calls) == 2