fix schedule xfail ut case (#443)

## Summary

<!--
Include a short paragraph of the changes introduced in this PR.
If this PR requires additional context or rationale, explain why
the changes are necessary.
-->

## Details

<!--
Provide a detailed list of all changes introduced in this pull request.
-->
- [ ]

## Test Plan

<!--
List the steps needed to test this PR.
-->
-

tox -e test -- --runxfail tests/unit/scheduler/test_scheduler.py
tox -e test -- --runxfail tests/integration/scheduler/test_scheduler.py
tox -e test -- --runxfail tests/unit/test_main.py

## Related Issues

<!--
Link any relevant issues that this PR addresses.
-->
- Resolves #

---

- [ ] "I certify that all code in this PR is my own, except as noted
below."

## Use of AI

- [ ] Includes AI-assisted code completion
- [ ] Includes code generated by an AI application
- [ ] Includes AI-generated tests (NOTE: AI written tests should have a
docstring that includes `## WRITTEN BY AI ##`)

Author: sjmonson

tests/integration/scheduler/test_scheduler.py

@@ -91,7 +91,6 @@ async def resolve(self, request: MockRequest, request_info, request_history):
         yield f"response_for_{request.payload}", request_info
 
 
-@pytest.mark.xfail(reason="old and broken", run=False)
 @pytest.mark.smoke
 @pytest.mark.asyncio
 @async_timeout(10.0)
@@ -122,7 +121,7 @@ async def test_scheduler_run_integration(
     received_updates = defaultdict(list)
     received_responses = []
     last_state = None
-    num_requests = 50
+    num_requests = 100
 
     async for resp, req, info, state in scheduler.run(
         requests=[MockRequest(payload=f"req_{ind}") for ind in range(num_requests)],
@@ -177,4 +176,5 @@ def _request_indices():
         assert statuses in (
             ["queued", "in_progress", "completed"],
             ["queued", "in_progress", "errored"],
+            ["queued", "pending", "in_progress"],
         )

tests/unit/scheduler/test_scheduler.py

@@ -137,7 +137,6 @@ def test_initialization(self, valid_instances):
         assert id(instance1) == id(instance2)
         assert hasattr(instance1, "thread_lock")
 
-    @pytest.mark.xfail(reason="old and broken", run=False)
     @pytest.mark.smoke
     @pytest.mark.asyncio
     @async_timeout(10.0)
@@ -164,6 +163,7 @@ async def test_run_basic_functionality(
             requests=requests,
             backend=backend,
             strategy=strategy,
+            startup_duration=0.1,
             env=env,
             **constraint_args,
         ):
@@ -174,7 +174,6 @@ async def test_run_basic_functionality(
         assert all(isinstance(r[2], RequestInfo) for r in results)
         assert all(isinstance(r[3], SchedulerState) for r in results)
 
-    @pytest.mark.xfail(reason="old and broken", run=False)
     @pytest.mark.smoke
     @pytest.mark.asyncio
     @async_timeout(10.0)
@@ -219,7 +218,6 @@ async def test_run_invalid_parameters(self, valid_instances):
             ):
                 pass
 
-    @pytest.mark.xfail(reason="old and broken", run=False)
     @pytest.mark.smoke
     @pytest.mark.asyncio
     @async_timeout(10.0)

tests/unit/test_main.py

@@ -77,7 +77,7 @@ def test_cli_backend_args_header_removal(mock_benchmark_func, tmp_path: Path):
     # Assert that benchmark_with_scenario was called with the correct scenario
     mock_benchmark_func.assert_called_once()
     call_args = mock_benchmark_func.call_args[1]
-    scenario = call_args["scenario"]
+    scenario = call_args["args"]
 
     # Verify the backend_args were merged correctly
     backend_args = scenario.backend_kwargs