[Bugfix] make test_openai_schema.py pass

by filtering out test cases to `POST /tokenize` endpoint
that are known to fail with a reply of HTTP 501 Not Implemented.

Enable the test in CI.

FIX #18162

Signed-off-by: David Xia <[email protected]>

Author: davidxia

.buildkite/test-pipeline.yaml

@@ -125,7 +125,7 @@ steps:
   - pytest -v -s entrypoints/llm/test_generate.py # it needs a clean process
   - pytest -v -s entrypoints/llm/test_generate_multiple_loras.py # it needs a clean process
   - VLLM_USE_V1=0 pytest -v -s entrypoints/llm/test_guided_generate.py # it needs a clean process
-  - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/test_oot_registration.py  --ignore=entrypoints/openai/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/test_openai_schema.py
+  - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/test_oot_registration.py  --ignore=entrypoints/openai/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/correctness/
   - pytest -v -s entrypoints/test_chat_utils.py
   - VLLM_USE_V1=0 pytest -v -s entrypoints/offline_mode # Needs to avoid interference with other tests
 

tests/entrypoints/openai/test_openai_schema.py

@@ -42,6 +42,51 @@ def get_schema(server):
 schema = schemathesis.from_pytest_fixture("get_schema")
 
 
+@schemathesis.hook
+def before_generate_case(context: schemathesis.hooks.HookContext, strategy):
+    op = context.operation
+    assert op is not None
+
+    def no_file_type(case: schemathesis.models.Case):
+        """
+        This filter skips test cases for the `POST /tokenize` endpoint where the
+        HTTP request body uses `"type": "file"` in any message's content.
+        We expect these cases to fail because that type isn't implemented here
+        https://github.com/vllm-project/vllm/blob/0b34593017953051b3225b1483ce0f4670e3eb0e/vllm/entrypoints/chat_utils.py#L1038-L1095
+
+        Example test cases that are skipped:
+        curl -X POST -H 'Content-Type: application/json' \
+            -d '{"messages": [{"role": "assistant"}, {"content": [{"file": {}, "type": "file"}], "role": "user"}]}' \
+            http://localhost:8000/tokenize
+
+        curl -X POST -H 'Content-Type: application/json' \
+            -d '{"messages": [{"content": [{"file": {}, "type": "file"}], "role": "user"}]}' \
+            http://localhost:8000/tokenize
+        """  # noqa: E501
+        if op.method.lower() != "post" or op.path != "/tokenize":
+            return True
+
+        if case.body and isinstance(case.body, dict):
+            if "messages" not in case.body:
+                return True
+
+            messages = case.body.get("messages", [])
+            if not isinstance(messages, list) or len(messages) == 0:
+                return True
+
+            for message in messages:
+                if not isinstance(message, dict):
+                    continue
+                content = message.get("content", [])
+                if not isinstance(content, list) or len(content) == 0:
+                    continue
+                if any(item.get("type") == "file" for item in content):
+                    return False
+        return True
+
+    return strategy.filter(no_file_type)
+
+
 @schema.parametrize()
 @schema.override(headers={"Content-Type": "application/json"})
 def test_openapi_stateless(case: schemathesis.Case):