[Bugfix] Preserve session IDs when upgrading Omni engine requests

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>

tests/engine/test_async_omni_engine_stage_init.py

@@ -268,21 +268,11 @@ def test_stage_engine_core_client_module_reload_keeps_forward_refs_deferred():
     """Regression test for forward references in make_async_mp_client."""
     import vllm_omni.engine.stage_engine_core_client as client_mod
 
-    # Snapshot the module namespace so a reload cannot strand other test
-    # modules that captured the pre-reload class objects (isinstance checks
-    # against the stale class would then fail). ``importlib.reload`` mutates
-    # the module dict in place; restoring it leaves the runtime exactly as it
-    # was before this test ran.
-    saved = dict(client_mod.__dict__)
-    try:
-        importlib.reload(client_mod)
+    importlib.reload(client_mod)
 
-        assert client_mod.StageEngineCoreClientBase.make_async_mp_client.__annotations__["return"] == (
-            "StageEngineCoreClient | DPLBStageEngineCoreClient"
-        )
-    finally:
-        client_mod.__dict__.clear()
-        client_mod.__dict__.update(saved)
+    assert client_mod.StageEngineCoreClientBase.make_async_mp_client.__annotations__["return"] == (
+        "StageEngineCoreClient | DPLBStageEngineCoreClient"
+    )
 
 
 def test_async_omni_engine_initialize_stages_passes_log_stats_and_client_config_to_runtime(monkeypatch):

tests/engine/test_omni_request.py

@@ -13,13 +13,15 @@ substitutable with the base class — including base-style calls that pass
 
 import inspect
 
+import msgspec
 import numpy as np
 import pytest
 import torch
 from vllm.sampling_params import SamplingParams
+from vllm.v1.engine import EngineCoreRequest
 from vllm.v1.request import Request
 
-from vllm_omni.engine import PromptEmbedsPayload
+from vllm_omni.engine import OmniEngineCoreRequest, PromptEmbedsPayload
 from vllm_omni.request import OmniRequest, OmniStreamingUpdate
 
 pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
@@ -111,3 +113,24 @@ def test_model_intermediate_buffer_round_trips_to_streaming_update():
     assert update is not None
     assert request.model_intermediate_buffer is buffer
     assert update.model_intermediate_buffer is buffer
+
+
+@pytest.mark.parametrize("session_id", [None, "session"])
+def test_session_survives_omni_upgrade_wire_transport_and_scheduler_conversion(session_id):
+    core = EngineCoreRequest(
+        request_id="session-request",
+        prompt_token_ids=[1, 2],
+        mm_features=None,
+        sampling_params=SamplingParams(max_tokens=2),
+        pooling_params=None,
+        arrival_time=0.0,
+        lora_request=None,
+        cache_salt=None,
+        data_parallel_rank=None,
+        session_id=session_id,
+    )
+    upgraded = OmniEngineCoreRequest.from_request(core)
+    decoded = msgspec.msgpack.decode(msgspec.msgpack.encode(upgraded), type=OmniEngineCoreRequest)
+    scheduled = OmniRequest.from_engine_core_request(decoded, block_hasher=None)
+    assert decoded.session_id == session_id
+    assert scheduled.session_id == session_id

vllm_omni/engine/__init__.py

@@ -123,6 +123,7 @@ class OmniEngineCoreRequest(EngineCoreRequest):
             trace_headers=request.trace_headers,
             resumable=request.resumable,
             external_req_id=request.external_req_id,
+            session_id=request.session_id,
             reasoning_ended=request.reasoning_ended,
             reasoning_parser_kwargs=request.reasoning_parser_kwargs,
             abort_immediately=request.abort_immediately,