feat(models): add vLLM provider support (#1860)

support for vLLM 0.19.0 OpenAI-compatible chat endpoints and fixes the Qwen reasoning toggle so flash mode can actually disable thinking.

Co-authored-by: NmanQAQ <normangyao@qq.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>

backend/tests/test_model_factory.py

@@ -604,6 +604,63 @@ def test_codex_provider_strips_unsupported_max_tokens(monkeypatch):
     assert "max_tokens" not in FakeChatModel.captured_kwargs
 
 
+def test_thinking_disabled_vllm_chat_template_format(monkeypatch):
+    wte = {"extra_body": {"chat_template_kwargs": {"thinking": True}}}
+    model = _make_model(
+        "vllm-qwen",
+        use="deerflow.models.vllm_provider:VllmChatModel",
+        supports_thinking=True,
+        when_thinking_enabled=wte,
+    )
+    model.extra_body = {"top_k": 20}
+    cfg = _make_app_config([model])
+    _patch_factory(monkeypatch, cfg)
+
+    captured: dict = {}
+
+    class CapturingModel(FakeChatModel):
+        def __init__(self, **kwargs):
+            captured.update(kwargs)
+            BaseChatModel.__init__(self, **kwargs)
+
+    monkeypatch.setattr(factory_module, "resolve_class", lambda path, base: CapturingModel)
+
+    factory_module.create_chat_model(name="vllm-qwen", thinking_enabled=False)
+
+    assert captured.get("extra_body") == {"top_k": 20, "chat_template_kwargs": {"thinking": False}}
+    assert captured.get("reasoning_effort") is None
+
+
+def test_thinking_disabled_vllm_enable_thinking_format(monkeypatch):
+    wte = {"extra_body": {"chat_template_kwargs": {"enable_thinking": True}}}
+    model = _make_model(
+        "vllm-qwen-enable",
+        use="deerflow.models.vllm_provider:VllmChatModel",
+        supports_thinking=True,
+        when_thinking_enabled=wte,
+    )
+    model.extra_body = {"top_k": 20}
+    cfg = _make_app_config([model])
+    _patch_factory(monkeypatch, cfg)
+
+    captured: dict = {}
+
+    class CapturingModel(FakeChatModel):
+        def __init__(self, **kwargs):
+            captured.update(kwargs)
+            BaseChatModel.__init__(self, **kwargs)
+
+    monkeypatch.setattr(factory_module, "resolve_class", lambda path, base: CapturingModel)
+
+    factory_module.create_chat_model(name="vllm-qwen-enable", thinking_enabled=False)
+
+    assert captured.get("extra_body") == {
+        "top_k": 20,
+        "chat_template_kwargs": {"enable_thinking": False},
+    }
+    assert captured.get("reasoning_effort") is None
+
+
 def test_openai_responses_api_settings_are_passed_to_chatopenai(monkeypatch):
     model = ModelConfig(
         name="gpt-5-responses",

backend/tests/test_vllm_provider.py

@@ -0,0 +1,138 @@
+from __future__ import annotations
+
+from langchain_core.messages import AIMessage, AIMessageChunk, HumanMessage
+
+from deerflow.models.vllm_provider import VllmChatModel
+
+
+def _make_model() -> VllmChatModel:
+    return VllmChatModel(
+        model="Qwen/QwQ-32B",
+        api_key="dummy",
+        base_url="http://localhost:8000/v1",
+    )
+
+
+def test_vllm_provider_restores_reasoning_in_request_payload():
+    model = _make_model()
+    payload = model._get_request_payload(
+        [
+            AIMessage(
+                content="",
+                tool_calls=[{"name": "bash", "args": {"cmd": "pwd"}, "id": "tool-1", "type": "tool_call"}],
+                additional_kwargs={"reasoning": "Need to inspect the workspace first."},
+            ),
+            HumanMessage(content="Continue"),
+        ]
+    )
+
+    assistant_message = payload["messages"][0]
+    assert assistant_message["role"] == "assistant"
+    assert assistant_message["reasoning"] == "Need to inspect the workspace first."
+    assert assistant_message["tool_calls"][0]["function"]["name"] == "bash"
+
+
+def test_vllm_provider_normalizes_legacy_thinking_kwarg_to_enable_thinking():
+    model = VllmChatModel(
+        model="qwen3",
+        api_key="dummy",
+        base_url="http://localhost:8000/v1",
+        extra_body={"chat_template_kwargs": {"thinking": True}},
+    )
+
+    payload = model._get_request_payload([HumanMessage(content="Hello")])
+
+    assert payload["extra_body"]["chat_template_kwargs"] == {"enable_thinking": True}
+
+
+def test_vllm_provider_preserves_explicit_enable_thinking_kwarg():
+    model = VllmChatModel(
+        model="qwen3",
+        api_key="dummy",
+        base_url="http://localhost:8000/v1",
+        extra_body={"chat_template_kwargs": {"enable_thinking": False, "foo": "bar"}},
+    )
+
+    payload = model._get_request_payload([HumanMessage(content="Hello")])
+
+    assert payload["extra_body"]["chat_template_kwargs"] == {
+        "enable_thinking": False,
+        "foo": "bar",
+    }
+
+
+def test_vllm_provider_preserves_reasoning_in_chat_result():
+    model = _make_model()
+    result = model._create_chat_result(
+        {
+            "model": "Qwen/QwQ-32B",
+            "choices": [
+                {
+                    "message": {
+                        "role": "assistant",
+                        "content": "42",
+                        "reasoning": "I compared the two numbers directly.",
+                    },
+                    "finish_reason": "stop",
+                }
+            ],
+            "usage": {"prompt_tokens": 1, "completion_tokens": 1, "total_tokens": 2},
+        }
+    )
+
+    message = result.generations[0].message
+    assert message.additional_kwargs["reasoning"] == "I compared the two numbers directly."
+    assert message.additional_kwargs["reasoning_content"] == "I compared the two numbers directly."
+
+
+def test_vllm_provider_preserves_reasoning_in_streaming_chunks():
+    model = _make_model()
+    chunk = model._convert_chunk_to_generation_chunk(
+        {
+            "model": "Qwen/QwQ-32B",
+            "choices": [
+                {
+                    "delta": {
+                        "role": "assistant",
+                        "reasoning": "First, call the weather tool.",
+                        "content": "Calling tool...",
+                    },
+                    "finish_reason": None,
+                }
+            ],
+        },
+        AIMessageChunk,
+        {},
+    )
+
+    assert chunk is not None
+    assert chunk.message.additional_kwargs["reasoning"] == "First, call the weather tool."
+    assert chunk.message.additional_kwargs["reasoning_content"] == "First, call the weather tool."
+    assert chunk.message.content == "Calling tool..."
+
+
+def test_vllm_provider_preserves_empty_reasoning_values_in_streaming_chunks():
+    model = _make_model()
+    chunk = model._convert_chunk_to_generation_chunk(
+        {
+            "model": "Qwen/QwQ-32B",
+            "choices": [
+                {
+                    "delta": {
+                        "role": "assistant",
+                        "reasoning": "",
+                        "content": "Still replying...",
+                    },
+                    "finish_reason": None,
+                }
+            ],
+        },
+        AIMessageChunk,
+        {},
+    )
+
+    assert chunk is not None
+    assert "reasoning" in chunk.message.additional_kwargs
+    assert chunk.message.additional_kwargs["reasoning"] == ""
+    assert "reasoning_content" not in chunk.message.additional_kwargs
+    assert chunk.message.content == "Still replying..."