Implement llm-connect ADHOC diagnostics

tests/test_structured_output_smoke.py

@@ -0,0 +1,142 @@
+import json
+
+from llm_connect.gemini import GeminiAdapter
+from llm_connect.models import RunConfig
+from llm_connect.openai import OpenAIAdapter
+from llm_connect.openrouter import OpenRouterAdapter
+
+
+STRUCTURED_SCHEMA = {
+    "type": "object",
+    "properties": {
+        "summary": {"type": "string"},
+        "recommendations": {"type": "array", "items": {"type": "string"}},
+    },
+    "required": ["summary", "recommendations"],
+}
+
+
+SMOKE_CONFIG = RunConfig(
+    model_name="gpt-4",
+    temperature=0.1,
+    max_tokens=300,
+    model_params={
+        "reasoning_effort": "medium",
+        "max_depth": 3,
+        "json_schema": STRUCTURED_SCHEMA,
+    },
+)
+
+
+def test_openrouter_structured_output_payload_and_model_routing(monkeypatch):
+    captured: dict[str, object] = {}
+
+    def fake_post_json(url, payload, headers=None, timeout=300):  # noqa: ANN001
+        captured["url"] = url
+        captured["payload"] = payload
+        captured["headers"] = headers
+        captured["timeout"] = timeout
+        return {
+            "id": "or-response",
+            "model": payload["model"],
+            "choices": [
+                {
+                    "message": {
+                        "content": json.dumps(
+                            {"summary": "ok", "recommendations": ["keep payload clean"]}
+                        )
+                    },
+                    "finish_reason": "stop",
+                }
+            ],
+            "usage": {"prompt_tokens": 1, "completion_tokens": 2, "total_tokens": 3},
+        }
+
+    monkeypatch.setattr("llm_connect.openrouter.post_json", fake_post_json)
+    adapter = OpenRouterAdapter(
+        model="anthropic/claude-sonnet-4",
+        api_key="or-test",
+        api_base="https://openrouter.example/api/v1",
+    )
+
+    response = adapter.execute_prompt("Return JSON.", SMOKE_CONFIG)
+    payload = captured["payload"]
+
+    assert response.model == "anthropic/claude-sonnet-4"
+    assert payload["model"] == "anthropic/claude-sonnet-4"
+    assert payload["response_format"]["json_schema"]["schema"] == STRUCTURED_SCHEMA
+    assert payload["response_format"]["json_schema"]["strict"] is False
+    assert "reasoning_effort" not in payload
+    assert "max_depth" not in payload
+    assert "json_schema" not in payload
+
+
+def test_openai_structured_output_payload(monkeypatch):
+    captured: dict[str, object] = {}
+
+    def fake_post_json(url, payload, headers=None, timeout=300):  # noqa: ANN001
+        captured["payload"] = payload
+        return {
+            "id": "oa-response",
+            "model": payload["model"],
+            "choices": [
+                {
+                    "message": {
+                        "content": json.dumps({"summary": "ok", "recommendations": []})
+                    },
+                    "finish_reason": "stop",
+                }
+            ],
+            "usage": {"prompt_tokens": 1, "completion_tokens": 2, "total_tokens": 3},
+        }
+
+    monkeypatch.setattr("llm_connect.openai.post_json", fake_post_json)
+    adapter = OpenAIAdapter(model="gpt-4.1-mini", api_key="sk-test")
+
+    response = adapter.execute_prompt("Return JSON.", SMOKE_CONFIG)
+    payload = captured["payload"]
+
+    assert response.model == "gpt-4.1-mini"
+    assert payload["model"] == "gpt-4.1-mini"
+    assert payload["response_format"]["json_schema"]["schema"] == STRUCTURED_SCHEMA
+    assert "reasoning_effort" not in payload
+    assert "max_depth" not in payload
+    assert "json_schema" not in payload
+
+
+def test_gemini_structured_output_payload(monkeypatch):
+    captured: dict[str, object] = {}
+
+    def fake_post_json(url, payload, headers=None, timeout=300):  # noqa: ANN001
+        captured["url"] = url
+        captured["payload"] = payload
+        return {
+            "candidates": [
+                {
+                    "content": {
+                        "parts": [
+                            {"text": json.dumps({"summary": "ok", "recommendations": []})}
+                        ]
+                    },
+                    "finishReason": "STOP",
+                }
+            ],
+            "usageMetadata": {
+                "promptTokenCount": 1,
+                "candidatesTokenCount": 2,
+                "totalTokenCount": 3,
+            },
+        }
+
+    monkeypatch.setattr("llm_connect.gemini.post_json", fake_post_json)
+    adapter = GeminiAdapter(model="gemini-2.5-flash", api_key="gemini-test")
+
+    response = adapter.execute_prompt("Return JSON.", SMOKE_CONFIG)
+    payload = captured["payload"]
+
+    assert response.model == "gemini-2.5-flash"
+    assert payload["generationConfig"]["responseMimeType"] == "application/json"
+    assert payload["generationConfig"]["responseSchema"] == STRUCTURED_SCHEMA
+    assert "reasoning_effort" not in payload
+    assert "max_depth" not in payload
+    assert "json_schema" not in payload