fix(llm): route all DashScope models through native provider (#7234)

DashScope's OpenAI-compatible endpoint serves DeepSeek/Kimi/GLM/etc.,
not only Qwen. Stop restricting the native match to the qwen* prefix so
DASHSCOPE_BASE_URL applies consistently. Fixes #7233.

Co-authored-by: Alphaxiaoteng <230277249+Alphaxiaoteng@users.noreply.github.com>
Co-authored-by: Vidit Ostwal <110953813+Vidit-Ostwal@users.noreply.github.com>

lib/crewai/src/crewai/llm.py

@@ -573,7 +573,8 @@ class LLM(BaseLLM):
             return True
 
         if provider == "dashscope":
-            return model_lower.startswith("qwen")
+            # DashScope's OpenAI-compatible endpoint serves Qwen plus DeepSeek/Kimi/GLM/etc.
+            return True
 
         if provider == "openrouter":
             # OpenRouter uses org/model format but accepts anything

lib/crewai/tests/llms/openai_compatible/test_openai_compatible.py

@@ -298,6 +298,20 @@ class TestLLMIntegration:
             assert isinstance(llm, OpenAICompatibleCompletion)
             assert llm.provider == "dashscope"
 
+    def test_llm_creates_openai_compatible_for_dashscope_non_qwen(self):
+        """Non-Qwen DashScope models must still use the native OpenAI-compatible path."""
+        with patch.dict(
+            os.environ,
+            {
+                "DASHSCOPE_API_KEY": "test-key",
+                "DASHSCOPE_BASE_URL": "https://my-dashscope.example.com/v1",
+            },
+        ):
+            llm = LLM(model="dashscope/deepseek-v3")
+            assert isinstance(llm, OpenAICompatibleCompletion)
+            assert llm.provider == "dashscope"
+            assert llm.base_url == "https://my-dashscope.example.com/v1"
+
     def test_llm_with_explicit_provider(self):
         """Test LLM with explicit provider parameter."""
         with patch.dict(os.environ, {"DEEPSEEK_API_KEY": "test-key"}):