Pass instruction depth config to llm-connect

tests/test_llm_client.py

@@ -0,0 +1,52 @@
+from __future__ import annotations
+
+import httpx
+
+from activity_core.llm_client import LLMConnectClient
+
+
+def test_llm_connect_client_forwards_run_config(monkeypatch) -> None:
+    captured: dict = {}
+
+    class Response:
+        def raise_for_status(self) -> None:
+            pass
+
+        def json(self) -> dict:
+            return {"content": '{"summary":"ok","recommendations":[]}'}
+
+    def fake_post(url: str, json: dict, timeout: float) -> Response:
+        captured["url"] = url
+        captured["json"] = json
+        captured["timeout"] = timeout
+        return Response()
+
+    monkeypatch.setattr(httpx, "post", fake_post)
+
+    client = LLMConnectClient("http://llm-connect.local/", timeout_seconds=42)
+    result = client.complete(
+        "Prompt",
+        model="fallback-model",
+        config={
+            "model_name": "custodian-triage-balanced",
+            "temperature": 0.2,
+            "max_tokens": 1200,
+            "max_depth": 2,
+            "model_params": {"reasoning_effort": "medium"},
+        },
+    )
+
+    assert result == '{"summary":"ok","recommendations":[]}'
+    assert captured["url"] == "http://llm-connect.local/execute"
+    assert captured["timeout"] == 42
+    assert captured["json"] == {
+        "prompt": "Prompt",
+        "config": {
+            "model_name": "custodian-triage-balanced",
+            "temperature": 0.2,
+            "max_tokens": 1200,
+            "max_depth": 2,
+            "model_params": {"reasoning_effort": "medium"},
+            "timeout_seconds": 42,
+        },
+    }