[Bugfix][Frontend] Apply the JSON schema in Cohere Chat v2 response_format (#60586)

Signed-off-by: mottopanikeiku <176798723+mottopanikeiku@users.noreply.github.com>
Co-authored-by: mottopanikeiku <176798723+mottopanikeiku@users.noreply.github.com>

tests/entrypoints/cohere/test_serving_conversion.py

@@ -770,6 +770,17 @@ class TestResponseFormat:
         dumped = result.response_format.json_schema.model_dump(exclude_none=True)
         assert dumped["json_schema"] == schema
 
+    def test_json_schema_reaches_sampling_params(self):
+        schema = {"type": "object", "properties": {"a": {"type": "string"}}}
+        request = _make_request(
+            response_format={"type": "json_object", "json_schema": schema}
+        )
+
+        params = _convert(request).to_sampling_params(16, {})
+
+        assert params.structured_outputs is not None
+        assert params.structured_outputs.json == schema
+
 
 # ======================================================================
 # Tools / tool_choice

vllm/entrypoints/cohere/serving.py

@@ -601,7 +601,7 @@ class CohereServingChatV2(OpenAIServingChat):
             json_schema=(
                 JsonSchemaResponseFormat(
                     name="cohere_v2_json_schema",
-                    json_schema=rf.json_schema,
+                    schema=rf.json_schema,
                 )
                 if rf.json_schema
                 else None