Fix test_basic_deployment in CI

[Dreamsorcerer]

No description provided.

[greptile-apps]

Greptile Summary

This PR adjusts test_basic_deployment so it can run more reliably in the intended CI lane. The main changes are:

• Moves the test onto the self_hosted pytest marker.
• Replaces the fixed sleep with a bounded polling loop.
• Waits for movement, odometry, and lidar message counts before asserting.

Confidence Score: 5/5

This looks safe to merge.

• No blocking issues found in the changed code.

Important Files Changed

Filename	Overview
dimos/core/test_core.py	Updates test_basic_deployment marker selection and replaces a fixed wait with count-based polling.

_{Reviews (3): Last reviewed commit: "Update test_core.py" | Re-trigger Greptile}

[codecov]

❌ 2 Tests Failed:

Tests completed	Failed	Passed	Skipped
2689	2	2687	70

View the full list of 2 ❄️ flaky test(s)

dimos.e2e_tests.test_dimsim_walk_forward::test_walk_forward

Flake rate in main: 23.85% (Passed 83 times, Failed 26 times)

Stack Traces | 206s run time

lcm_spy = <dimos.e2e_tests.lcm_spy.LcmSpy object at 0x7a7a3da720f0>
start_blueprint = <function start_blueprint.<locals>.set_name_and_start at 0x7a7a3a5ef060>
human_input = <function human_input.<locals>.send_human_input at 0x7a7a3a5ee980>
dim_sim = <dimos.e2e_tests.dim_sim_client.DimSimClient object at 0x7a7a3c559040>

    @pytest.mark.self_hosted_large
    def test_walk_forward(lcm_spy, start_blueprint, human_input, dim_sim) -> None:
        start_blueprint(
            "run",
            "--disable",
            "spatial-memory",
            "--disable",
            "security-module",
            "unitree-go2-agentic",
            simulator="dimsim",
        )
        lcm_spy.save_topic(".../McpClient/on_system_modules/res")
        lcm_spy.wait_for_saved_topic(".../McpClient/on_system_modules/res", timeout=1200.0)
    
        origin_x, origin_y = 1, 2
        dim_sim.set_agent_position(origin_x, origin_y)
    
        human_input("move forward 3 meter")
    
>       lcm_spy.wait_until_odom_position(origin_x + 3, origin_y, threshold=0.4, timeout=120)

dim_sim    = <dimos.e2e_tests.dim_sim_client.DimSimClient object at 0x7a7a3c559040>
human_input = <function human_input.<locals>.send_human_input at 0x7a7a3a5ee980>
lcm_spy    = <dimos.e2e_tests.lcm_spy.LcmSpy object at 0x7a7a3da720f0>
origin_x   = 1
origin_y   = 2
start_blueprint = <function start_blueprint.<locals>.set_name_and_start at 0x7a7a3a5ef060>

dimos/e2e_tests/test_dimsim_walk_forward.py:37: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
dimos/e2e_tests/lcm_spy.py:167: in wait_until_odom_position
    self.wait_for_message_result(
        predicate  = <function LcmSpy.wait_until_odom_position.<locals>.predicate at 0x7a7a3a5ecfe0>
        self       = <dimos.e2e_tests.lcm_spy.LcmSpy object at 0x7a7a3da720f0>
        threshold  = 0.4
        timeout    = 120
        x          = 4
        y          = 2
dimos/e2e_tests/lcm_spy.py:153: in wait_for_message_result
    wait_until(
        event      = <threading.Event at 0x7a7a3c5593a0: unset>
        fail_message = 'Failed to get to position x=4, y=2'
        listener   = <function LcmSpy.wait_for_message_result.<locals>.listener at 0x7a7a3a5ef6a0>
        predicate  = <function LcmSpy.wait_until_odom_position.<locals>.predicate at 0x7a7a3a5ecfe0>
        self       = <dimos.e2e_tests.lcm_spy.LcmSpy object at 0x7a7a3da720f0>
        timeout    = 120
        topic      = '/odom#geometry_msgs.PoseStamped'
        type       = <class 'dimos.msgs.geometry_msgs.PoseStamped.PoseStamped'>
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

predicate = <bound method Event.is_set of <threading.Event at 0x7a7a3c5593a0: unset>>

    def wait_until(
        predicate: Callable[[], bool],
        *,
        timeout: float,
        interval: float = 0.1,
        message: str | None = None,
    ) -> None:
        """Poll ``predicate`` until it returns truthy or ``timeout`` elapses."""
        deadline = time.monotonic() + timeout
        while time.monotonic() < deadline:
            if predicate():
                return
            time.sleep(interval)
>       raise TimeoutError(message or f"Timed out after {timeout}s waiting for condition")
E       TimeoutError: Failed to get to position x=4, y=2

deadline   = 3535953.085535148
interval   = 0.1
message    = 'Failed to get to position x=4, y=2'
predicate  = <bound method Event.is_set of <threading.Event at 0x7a7a3c5593a0: unset>>
timeout    = 120

.../utils/testing/waiting.py:35: TimeoutError

dimos.perception.test_image_embedding.TestImageEmbedding::test_clip_embedding_initialization

Flake rate in main: 30.00% (Passed 7 times, Failed 3 times)

Stack Traces | 27.9s run time

request = <SubRequest 'monitor_threads' for <Function test_clip_embedding_initialization>>

    @pytest.fixture(autouse=True)
    def monitor_threads(request):
        # Capture threads before test runs
        test_name = request.node.nodeid
        with _seen_threads_lock:
            _before_test_threads[test_name] = {
                t.ident for t in threading.enumerate() if t.ident is not None
            }
    
        yield
    
        with _seen_threads_lock:
            before = _before_test_threads.get(test_name, set())
    
        # Threads intentionally left running for the whole process and cleaned up on
        # exit, so they don't count as per-test leaks.
        expected_persistent_thread_prefixes = [
            "Dask-Offload",
            # HuggingFace safetensors conversion thread - no user cleanup API
            # https://github..../transformers/issues/29513
            "Thread-auto_conversion",
        ]
    
        def live_new_threads():
            # Threads created during this test that are still running. A thread that
            # has already stopped is not a leak -- it's done, just not yet reaped
            # from threading's registry -- so we key on is_alive(), not presence.
            result = []
            for t in threading.enumerate():
                if t.ident is None or t.ident in before or t.name == "MainThread":
                    continue
                if any(t.name.startswith(prefix) for prefix in expected_persistent_thread_prefixes):
                    continue
                if t.is_alive():
                    result.append(t)
            return result
    
        # Some C extensions tear their callback threads down asynchronously, so a
        # thread can stay alive briefly after the test cleaned up its owner (notably
        # zenoh's pyo3-closure threads, freed shortly after the session is closed).
        # A single snapshot races that teardown and flags a thread that is about to
        # exit. Give new threads a grace period to drain; only ones that stay alive
        # are real leaks (a genuinely leaked thread never exits).
        deadline = time.monotonic() + 5.0
        leaked = live_new_threads()
        while leaked and time.monotonic() < deadline:
            time.sleep(0.02)
            leaked = live_new_threads()
    
        if not leaked:
            return
    
        with _seen_threads_lock:
            # Report each leaked thread only once across the session.
            truly_new = [t for t in leaked if t.ident not in _seen_threads]
            for t in leaked:
                _seen_threads.add(t.ident)
    
        if not truly_new:
            return
    
        thread_names = [t.name for t in truly_new]
    
>       pytest.fail(
            f"Non-closed threads created during this test. Thread names: {thread_names}. "
            "Please look at the first test that fails and fix that."
        )
E       Failed: Non-closed threads created during this test. Thread names: ['Thread-252']. Please look at the first test that fails and fix that.

before     = {124717805999808, 124717814392512, 124717831177920, 124717839570624, 124717856356032, 124717864748736, ...}
deadline   = 4527038.613525735
expected_persistent_thread_prefixes = ['Dask-Offload', 'Thread-auto_conversion']
leaked     = [<TMonitor(Thread-252, started daemon 124717789214400)>]
live_new_threads = <function monitor_threads.<locals>.live_new_threads at 0x716ee7303d80>
request    = <SubRequest 'monitor_threads' for <Function test_clip_embedding_initialization>>
t          = <TMonitor(Thread-252, started daemon 124717789214400)>
test_name  = 'dimos/perception/test_image_embedding.py::TestImageEmbedding::test_clip_embedding_initialization'
thread_names = ['Thread-252']
truly_new  = [<TMonitor(Thread-252, started daemon 124717789214400)>]

dimos/conftest.py:273: Failed

To view more test analytics, go to the Test Analytics Dashboard
_{📋 Got 3 mins? Take this short survey to help us improve Test Analytics.}