feat(agent): 增强多模态链路与工具调用能力

backend/tests/unit/services/test_litellm_service.py

@@ -33,11 +33,11 @@ def test_calculate_cost_uses_second_qwen_tier() -> None:
 
 def test_run_completion_extracts_usage_and_cost() -> None:
     service = LiteLLMService()
+    captured: dict[str, object] = {}
 
-    result = service.run_completion_with_cost(
-        model="dashscope/qwen3.5-flash",
-        messages=[{"role": "user", "content": "hello"}],
-        completion_fn=lambda **_: {
+    def _fake_completion(**kwargs: object) -> dict[str, object]:
+        captured.update(kwargs)
+        return {
             "model": "dashscope/qwen3.5-flash",
             "usage": {
                 "prompt_tokens": 2000,
@@ -46,10 +46,17 @@ def test_run_completion_extracts_usage_and_cost() -> None:
                 "prompt_tokens_details": {"cached_tokens": 500},
             },
             "choices": [{"message": {"content": "ok"}}],
-        },
+        }
+
+    result = service.run_completion_with_cost(
+        model="dashscope/qwen3.5-flash",
+        messages=[{"role": "user", "content": "hello"}],
+        response_format={"type": "json_object"},
+        completion_fn=_fake_completion,
     )
 
     assert result.usage.prompt_tokens == 2000
     assert result.usage.completion_tokens == 100
     assert result.usage.total_tokens == 2100
     assert result.usage.cost == pytest.approx(0.00051)
+    assert captured["response_format"] == {"type": "json_object"}