[3/5][core]refactor communication layer: PR 3 of 5, all other models in non async mode (#3719)

Signed-off-by: natureofnature <wzliu@connect.hku.hk>

tests/core/sched/test_omni_scheduler_mixin_timeouts.py

@@ -0,0 +1,104 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+"""Unit coverage for _process_pending_input_timeouts.
+
+Verifies that the mixin correctly *delegates* timed-out requests to the
+base scheduler's ``finish_requests`` API with ``RequestStatus.FINISHED_ERROR``.
+The end-to-end effect (queue removal + status set + per-request cleanup +
+client-facing FINISHED_ERROR emission) is the responsibility of upstream
+vLLM's ``finish_requests`` implementation and is covered by upstream tests;
+this file only asserts the wiring from the mixin to that API.
+"""
+
+from __future__ import annotations
+
+from types import SimpleNamespace
+
+import pytest
+
+from vllm_omni.core.sched.omni_scheduler_mixin import OmniSchedulerMixin
+
+
+class _FakeCoordinator:
+    def __init__(self, timed_out_ids):
+        self._timed_out_ids = set(timed_out_ids)
+        self.calls = []
+
+    def collect_timed_out_request_ids(self, timeout_s):
+        self.calls.append(timeout_s)
+        return set(self._timed_out_ids)
+
+
+class _FakeScheduler(OmniSchedulerMixin):
+    def __init__(self, requests, coordinator):
+        self.requests = requests
+        self.input_coordinator = coordinator
+        self.finish_calls = []
+
+    def finish_requests(self, req_ids, status):
+        self.finish_calls.append((set(req_ids), status))
+
+
+def test_process_pending_input_timeouts_delegates_to_finish_requests():
+    """Timed-out request present in self.requests is forwarded to finish_requests."""
+    req_id = "stuck-req"
+    requests = {req_id: SimpleNamespace(request_id=req_id)}
+    coord = _FakeCoordinator(timed_out_ids={req_id})
+    scheduler = _FakeScheduler(requests, coord)
+
+    scheduler._process_pending_input_timeouts()
+
+    assert len(coord.calls) == 1, "coordinator should be polled once"
+    assert coord.calls[0] > 0, "timeout must be positive when enabled"
+
+    assert len(scheduler.finish_calls) == 1
+    finished_ids, status = scheduler.finish_calls[0]
+    assert finished_ids == {req_id}
+    # RequestStatus is the upstream enum; the mixin imports it as
+    # RequestStatus.FINISHED_ERROR.  Check by name to avoid hard import here.
+    assert getattr(status, "name", str(status)).endswith("FINISHED_ERROR")
+
+
+def test_process_pending_input_timeouts_skips_already_freed_request():
+    """Timed-out id no longer in self.requests must not be forwarded."""
+    coord = _FakeCoordinator(timed_out_ids={"already-freed"})
+    scheduler = _FakeScheduler(requests={}, coordinator=coord)
+
+    scheduler._process_pending_input_timeouts()
+
+    assert coord.calls == [coord.calls[0]] and coord.calls[0] > 0
+    assert scheduler.finish_calls == []
+
+
+def test_process_pending_input_timeouts_noop_without_coordinator():
+    """No coordinator => no finish_requests call, no crash."""
+
+    class _NoCoord(OmniSchedulerMixin):
+        def __init__(self):
+            self.requests = {}
+            self.input_coordinator = None
+            self.finish_calls = []
+
+        def finish_requests(self, req_ids, status):
+            self.finish_calls.append((set(req_ids), status))
+
+    scheduler = _NoCoord()
+    scheduler._process_pending_input_timeouts()
+    assert scheduler.finish_calls == []
+
+
+def test_process_pending_input_timeouts_disabled_when_timeout_zero(monkeypatch):
+    """Setting DEFAULT_INPUT_WAIT_TIMEOUT_S <= 0 disables the safety net."""
+    from vllm_omni.core.sched import omni_scheduler_mixin
+
+    monkeypatch.setattr(omni_scheduler_mixin, "DEFAULT_INPUT_WAIT_TIMEOUT_S", 0.0)
+
+    coord = _FakeCoordinator(timed_out_ids={"r1"})
+    scheduler = _FakeScheduler(requests={"r1": SimpleNamespace(request_id="r1")}, coordinator=coord)
+    scheduler._process_pending_input_timeouts()
+    assert coord.calls == [], "coordinator must not be polled when timeout is disabled"
+    assert scheduler.finish_calls == []
+
+
+if __name__ == "__main__":
+    pytest.main([__file__, "-v"])

tests/core/sched/test_omni_scheduling_coordinator.py

@@ -16,7 +16,7 @@ import torch
 import vllm_omni.core.sched.omni_scheduling_coordinator as coord_mod
 from vllm_omni.core.sched.omni_scheduling_coordinator import (
     OmniSchedulingCoordinator,
-    uses_qwen3_omni_full_payload_input_coordinator,
+    uses_full_payload_input_coordinator,
 )
 
 # ------------------------------------------------------------------ #
@@ -92,47 +92,96 @@ class MockQueue:
 
 
 class TestFullPayloadCoordinatorSelection(unittest.TestCase):
-    def test_qwen3_omni_talker_and_code2wav_use_full_payload_input_coordinator(self):
-        for model_stage in ("talker", "code2wav"):
+    """Tests for the (model_arch, model_stage) whitelist gate.
+
+    The init_omni_connectors arch allowlist is keyed by ``model_arch`` and
+    is a superset of the stages registered here -- consumer-wait stages
+    must be registered explicitly in ``_FULL_PAYLOAD_INPUT_STAGES``, while
+    the init allowlist covers both producer- and consumer-side runners.
+    These tests pin which ``(arch, stage)`` pairs the gate fires for today.
+    """
+
+    # Expected whitelist (model_arch, model_stage).  Hardcoded to avoid the
+    # tautology of importing _FULL_PAYLOAD_INPUT_STAGES and asserting it
+    # against itself; any drift between this matrix and the whitelist will
+    # fail loudly here.
+    EXPECTED_FULL_PAYLOAD_INPUT_STAGES: frozenset[tuple[str, str]] = frozenset(
+        {
+            ("Qwen3OmniMoeForConditionalGeneration", "talker"),
+            ("Qwen3OmniMoeForConditionalGeneration", "code2wav"),
+            ("Qwen2_5OmniForConditionalGeneration", "talker"),
+            ("Qwen2_5OmniForConditionalGeneration", "code2wav"),
+            ("CovoAudioForConditionalGeneration", "code2wav"),
+            ("MiMoAudioModel", "code2wav"),
+            ("Qwen3TTSCode2Wav", "code2wav"),
+            ("CosyVoice3Model", "cosyvoice3_code2wav"),
+            ("DyninOmniForConditionalGeneration", "token2image"),
+            ("DyninOmniForConditionalGeneration", "token2audio"),
+        }
+    )
+
+    def test_whitelist_matches_expected_matrix(self):
+        """_FULL_PAYLOAD_INPUT_STAGES must equal the hardcoded expected matrix.
+
+        Catches both accidental additions (which would silently enable the
+        consumer-wait gate for a new arch) and accidental removals (which
+        would silently disable an enabled arch).
+        """
+        from vllm_omni.core.sched.omni_scheduling_coordinator import _FULL_PAYLOAD_INPUT_STAGES
+
+        self.assertEqual(
+            frozenset(_FULL_PAYLOAD_INPUT_STAGES),
+            self.EXPECTED_FULL_PAYLOAD_INPUT_STAGES,
+            msg="_FULL_PAYLOAD_INPUT_STAGES drifted from the expected matrix; "
+            "update EXPECTED_FULL_PAYLOAD_INPUT_STAGES if intentional.",
+        )
+
+    def test_all_whitelisted_arch_stage_pairs_fire_gate(self):
+        """Every (arch, stage) pair in the expected matrix must fire
+        the gate when stage_id > 0 and async_chunk=False.
+        """
+        for arch, stage in self.EXPECTED_FULL_PAYLOAD_INPUT_STAGES:
             model_config = SimpleNamespace(
                 stage_id=1,
                 async_chunk=False,
-                model_arch="Qwen3OmniMoeForConditionalGeneration",
-                model_stage=model_stage,
+                model_arch=arch,
+                model_stage=stage,
+            )
+            self.assertTrue(
+                uses_full_payload_input_coordinator(model_config),
+                msg=f"expected gate to fire for {arch}/{stage}",
             )
 
-            self.assertTrue(uses_qwen3_omni_full_payload_input_coordinator(model_config))
-
-    def test_async_chunk_and_non_qwen3_omni_do_not_use_full_payload_input_coordinator(self):
+    def test_other_arch_or_stage_or_mode_does_not_fire(self):
         cases = [
             SimpleNamespace(
-                stage_id=1,
-                async_chunk=True,
-                model_arch="Qwen3OmniMoeForConditionalGeneration",
-                model_stage="talker",
+                stage_id=1, async_chunk=True, model_arch="Qwen3OmniMoeForConditionalGeneration", model_stage="talker"
+            ),
+            SimpleNamespace(
+                stage_id=0, async_chunk=False, model_arch="Qwen3OmniMoeForConditionalGeneration", model_stage="thinker"
             ),
             SimpleNamespace(
                 stage_id=1,
                 async_chunk=False,
-                model_arch="Qwen3TTSForConditionalGeneration",
-                model_stage="code2wav",
-            ),
-            SimpleNamespace(
-                stage_id=1,
-                async_chunk=False,
-                model_arch="Qwen2_5OmniForConditionalGeneration",
-                model_stage="talker",
-            ),
-            SimpleNamespace(
-                stage_id=0,
-                async_chunk=False,
                 model_arch="Qwen3OmniMoeForConditionalGeneration",
-                model_stage="thinker",
+                model_stage="some_future_stage",
+            ),
+            SimpleNamespace(
+                stage_id=1, async_chunk=False, model_arch="Qwen3TTSForConditionalGeneration", model_stage="code2wav"
+            ),
+            SimpleNamespace(
+                stage_id=1, async_chunk=False, model_arch="MingFlashOmniForConditionalGeneration", model_stage="talker"
+            ),
+            SimpleNamespace(stage_id=1, async_chunk=False, model_arch=None, model_stage="talker"),
+            SimpleNamespace(
+                stage_id=1, async_chunk=False, model_arch="Qwen3OmniMoeForConditionalGeneration", model_stage=None
             ),
         ]
-
         for model_config in cases:
-            self.assertFalse(uses_qwen3_omni_full_payload_input_coordinator(model_config))
+            self.assertFalse(
+                uses_full_payload_input_coordinator(model_config),
+                msg=f"expected gate OFF for {model_config}",
+            )
 
 
 class TestChunkCoordinatorStateTransition(unittest.TestCase):