From bedc42a94d9853248102f0e2ff524687f10d59d7 Mon Sep 17 00:00:00 2001
From: tzhouam <tzhouam@connect.ust.hk>
Date: Sun, 4 Oct 2026 03:19:39 +0800
Subject: [PATCH] [Bugfix] Preserve session IDs when upgrading Omni engine
 requests

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
---
 tests/engine/test_omni_request.py | 25 ++++++++++++++++++++++++-
 vllm_omni/engine/__init__.py      |  1 +
 2 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/tests/engine/test_omni_request.py b/tests/engine/test_omni_request.py
index 521c92b94..23c880242 100644
--- a/tests/engine/test_omni_request.py
+++ b/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
diff --git a/vllm_omni/engine/__init__.py b/vllm_omni/engine/__init__.py
index c36d6d986..7300e1465 100644
--- a/vllm_omni/engine/__init__.py
+++ b/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,