Miscellaneous fixes (0.18 beta) (#23725)

frigate/test/test_birdseye.py

@@ -1,8 +1,10 @@
 """Test camera user and password cleanup."""
 
+import multiprocessing as mp
 import unittest
 
-from frigate.output.birdseye import get_canvas_shape
+from frigate.config import FrigateConfig
+from frigate.output.birdseye import BirdsEyeFrameManager, get_canvas_shape
 
 
 class TestBirdseye(unittest.TestCase):
@@ -45,3 +47,70 @@ class TestBirdseye(unittest.TestCase):
         canvas_width, canvas_height = get_canvas_shape(width, height)
         assert canvas_width == width  # width will be the same
         assert canvas_height != height
+
+
+class TestBirdseyeCameraOrder(unittest.TestCase):
+    """Test that birdseye reacts to camera order changes without a restart."""
+
+    def setUp(self):
+        config = {
+            "mqtt": {"enabled": False},
+            "birdseye": {"enabled": True, "mode": "continuous"},
+            "cameras": {
+                camera: {
+                    "ffmpeg": {
+                        "inputs": [
+                            {"path": "rtsp://10.0.0.1:554/video", "roles": ["detect"]}
+                        ]
+                    },
+                    "detect": {"height": 1080, "width": 1920, "fps": 5},
+                }
+                for camera in ("back", "front", "side")
+            },
+        }
+        self.config = FrigateConfig(**config)
+        self.manager = BirdsEyeFrameManager(self.config, mp.Event())
+
+        # mark every camera as continuously active with no frame to draw, which
+        # exercises the layout without needing real yuv frames
+        for camera_data in self.manager.cameras.values():
+            camera_data["current_frame"] = None
+            camera_data["current_frame_time"] = 1.0
+            camera_data["last_active_frame"] = 1.0
+
+    def layout_order(self) -> list[str]:
+        """Return the cameras in the order the current layout renders them."""
+        return [position[0] for row in self.manager.camera_layout for position in row]
+
+    def test_layout_uses_configured_order(self):
+        """Test the layout is sorted by order, then by name when tied."""
+        self.config.cameras["side"].birdseye.order = 0
+        self.config.cameras["back"].birdseye.order = 10
+        self.config.cameras["front"].birdseye.order = 20
+
+        self.manager.update_frame()
+
+        assert self.layout_order() == ["side", "back", "front"]
+
+    def test_order_change_rebuilds_layout(self):
+        """Test a reorder relayouts even though the active cameras are unchanged."""
+        self.manager.update_frame()
+        assert self.layout_order() == ["back", "front", "side"]
+
+        # a stable active set means only an order change can reset the layout,
+        # which is what a settings reorder publishes to this process
+        self.config.cameras["side"].birdseye.order = -10
+
+        _, layout_changed = self.manager.update_frame()
+
+        assert layout_changed
+        assert self.layout_order() == ["side", "back", "front"]
+
+    def test_unchanged_order_keeps_layout(self):
+        """Test a repeat update with no order change doesn't reset the layout."""
+        self.manager.update_frame()
+
+        _, layout_changed = self.manager.update_frame()
+
+        assert not layout_changed
+        assert self.layout_order() == ["back", "front", "side"]

frigate/test/test_gpu_stats.py

@@ -21,8 +21,12 @@ class TestGpuStats(unittest.TestCase):
     @patch("frigate.util.services.time.sleep")
     @patch("frigate.util.services.time.monotonic")
     @patch("frigate.util.services._read_intel_drm_fdinfo")
-    def test_intel_gpu_stats_fdinfo(self, read_fdinfo, monotonic, sleep, get_names):
+    @patch("frigate.util.services._enumerate_drm_devices")
+    def test_intel_gpu_stats_fdinfo(
+        self, drm_devices, read_fdinfo, monotonic, sleep, get_names
+    ):
         # 1 second of wall clock between snapshots
+        drm_devices.return_value = {"0000:00:02.0": "i915"}
         monotonic.side_effect = [0.0, 1.0]
         get_names.return_value = {"0000:00:02.0": "Intel Graphics"}
 
@@ -96,13 +100,15 @@ class TestGpuStats(unittest.TestCase):
     @patch("frigate.util.services.time.sleep")
     @patch("frigate.util.services.time.monotonic")
     @patch("frigate.util.services._read_intel_drm_fdinfo")
+    @patch("frigate.util.services._enumerate_drm_devices")
     def test_intel_gpu_stats_xe_capacity(
-        self, read_fdinfo, monotonic, sleep, get_names
+        self, drm_devices, read_fdinfo, monotonic, sleep, get_names
     ):
         # Xe engines report cumulative cycles paired with total cycles, plus a
         # per-class capacity. drm-cycles-* is summed across every instance of a
         # class, so on Battlemage (capacity 2 for vcs/vecs) busy/total must be
         # divided by capacity to land in 0-100%.
+        drm_devices.return_value = {"0000:03:00.0": "xe"}
         monotonic.side_effect = [0.0, 1.0]
         get_names.return_value = {"0000:03:00.0": "Intel Arc"}
 
@@ -150,7 +156,145 @@ class TestGpuStats(unittest.TestCase):
             },
         }
 
+    @patch("frigate.stats.intel_gpu_info.intel_gpu_name_resolver.get_names")
+    @patch("frigate.util.services.time.sleep")
     @patch("frigate.util.services._read_intel_drm_fdinfo")
-    def test_intel_gpu_stats_no_clients(self, read_fdinfo):
+    @patch("frigate.util.services._enumerate_drm_devices")
+    def test_intel_gpu_stats_no_clients_reports_idle(
+        self, drm_devices, read_fdinfo, sleep, get_names
+    ):
+        # The device exists but nothing holds it open, e.g. while camera
+        # processes are restarting. This is an idle state, not an error:
+        # returning None here would latch the hwaccel error cooldown and
+        # blank GPU stats for an hour over a momentary gap.
+        drm_devices.return_value = {"0000:00:02.0": "i915"}
         read_fdinfo.return_value = {}
+        get_names.return_value = {"0000:00:02.0": "Intel Graphics"}
+
+        assert get_intel_gpu_stats(None) == {
+            "0000:00:02.0": {
+                "name": "Intel Graphics",
+                "vendor": "intel",
+                "gpu": "0.0%",
+                "mem": "-%",
+                "compute": "0.0%",
+                "dec": "0.0%",
+            },
+        }
+        # Idle short-circuits before spending the sample window
+        sleep.assert_not_called()
+        read_fdinfo.assert_called_once()
+
+    @patch("frigate.util.services.time.sleep")
+    @patch("frigate.util.services._read_intel_drm_fdinfo")
+    @patch("frigate.util.services._enumerate_drm_devices")
+    def test_intel_gpu_stats_clients_without_engine_counters(
+        self, drm_devices, read_fdinfo, sleep
+    ):
+        # i915 publishes drm-driver/drm-pdev/drm-client-id but no drm-engine-*
+        # lines while GuC submission is active on kernels older than 6.5, so
+        # clients are found with nothing to sample. Reporting idle here would
+        # be a lie, and sampling a second time cannot help.
+        drm_devices.return_value = {"0000:00:02.0": "i915"}
+        read_fdinfo.return_value = {
+            ("0000:00:02.0", "48", "1109"): {
+                "driver": "i915",
+                "pid": "1109",
+                "engines": {},
+            },
+            ("0000:00:02.0", "51", "1258"): {
+                "driver": "i915",
+                "pid": "1258",
+                "engines": {},
+            },
+        }
+
         assert get_intel_gpu_stats(None) is None
+        sleep.assert_not_called()
+        read_fdinfo.assert_called_once()
+
+    @patch("frigate.util.services._read_intel_drm_fdinfo")
+    @patch("frigate.util.services._enumerate_drm_devices")
+    def test_intel_gpu_stats_no_intel_device(self, drm_devices, read_fdinfo):
+        # Only a non-Intel GPU is visible in sysfs; /proc is never scanned
+        drm_devices.return_value = {"0000:01:00.0": "nvidia"}
+
+        assert get_intel_gpu_stats(None) is None
+        read_fdinfo.assert_not_called()
+
+    @patch("frigate.util.services._read_intel_drm_fdinfo")
+    @patch("frigate.util.services._enumerate_drm_devices")
+    @patch("frigate.util.services._resolve_intel_gpu_pdev")
+    def test_intel_gpu_stats_unresolvable_device_hint(
+        self, resolve_pdev, drm_devices, read_fdinfo
+    ):
+        # A configured intel_gpu_device that cannot be resolved is a config
+        # error, not a reason to silently fall back to reporting all GPUs
+        resolve_pdev.return_value = None
+
+        assert get_intel_gpu_stats("/dev/dri/renderD999") is None
+        drm_devices.assert_not_called()
+        read_fdinfo.assert_not_called()
+
+    @patch("frigate.util.services._read_intel_drm_fdinfo")
+    @patch("frigate.util.services._enumerate_drm_devices")
+    @patch("frigate.util.services._resolve_intel_gpu_pdev")
+    def test_intel_gpu_stats_hint_resolves_to_non_intel_gpu(
+        self, resolve_pdev, drm_devices, read_fdinfo
+    ):
+        # card numbering can reorder across reboots on multi-GPU hosts, so a
+        # configured hint may point at another vendor's card; call it out
+        # instead of reporting nothing
+        resolve_pdev.return_value = "0000:01:00.0"
+        drm_devices.return_value = {
+            "0000:00:02.0": "i915",
+            "0000:01:00.0": "nvidia",
+        }
+
+        assert get_intel_gpu_stats("/dev/dri/card0") is None
+        read_fdinfo.assert_not_called()
+
+    @patch("frigate.util.services._read_intel_drm_fdinfo")
+    @patch("frigate.util.services._enumerate_drm_devices")
+    def test_intel_gpu_stats_unreadable_proc(self, drm_devices, read_fdinfo):
+        # A scan failure (None) is a different condition than a scan that
+        # finds no clients ({}) and must not report idle
+        drm_devices.return_value = {"0000:00:02.0": "i915"}
+        read_fdinfo.return_value = None
+
+        assert get_intel_gpu_stats(None) is None
+
+    @patch("frigate.stats.intel_gpu_info.intel_gpu_name_resolver.get_names")
+    @patch("frigate.util.services.time.sleep")
+    @patch("frigate.util.services.time.monotonic")
+    @patch("frigate.util.services._read_intel_drm_fdinfo")
+    @patch("frigate.util.services._enumerate_drm_devices")
+    def test_intel_gpu_stats_clients_lost_between_samples(
+        self, drm_devices, read_fdinfo, monotonic, sleep, get_names
+    ):
+        # Clients disappearing during the sample window is transient process
+        # churn, so report idle rather than latching an error
+        drm_devices.return_value = {"0000:00:02.0": "i915"}
+        monotonic.side_effect = [0.0, 1.0]
+        get_names.return_value = {"0000:00:02.0": "Intel Graphics"}
+        read_fdinfo.side_effect = [
+            {
+                ("0000:00:02.0", "1", "100"): {
+                    "driver": "i915",
+                    "pid": "100",
+                    "engines": {"video": (5_000_000_000, 0, 1)},
+                },
+            },
+            {},
+        ]
+
+        assert get_intel_gpu_stats(None) == {
+            "0000:00:02.0": {
+                "name": "Intel Graphics",
+                "vendor": "intel",
+                "gpu": "0.0%",
+                "mem": "-%",
+                "compute": "0.0%",
+                "dec": "0.0%",
+            },
+        }

frigate/test/test_ptz_autotrack.py

@@ -0,0 +1,130 @@
+"""Tests for autotracker state that must survive runtime config changes.
+
+Regression coverage for a family of bugs where per-camera autotracker state was
+built once at startup and never revisited. A camera that is added or enabled
+after startup, or has autotracking enabled from the UI, would either raise a
+KeyError on the autotracker thread or silently keep the wrong state:
+
+- autotracker_init only got an entry for cameras enabled when PtzAutoTracker was
+  constructed, so runtime-enabled cameras raised KeyError on lookup.
+- ptz_metrics autotracker_enabled is what the camera processes read, but nothing
+  updated it when autotracking was enabled through a config save, so it stayed
+  False and the tracker never built a motion estimator.
+"""
+
+import unittest
+from unittest.mock import MagicMock
+
+from frigate.camera import PTZMetrics
+from frigate.config import FrigateConfig
+from frigate.ptz.autotrack import PtzAutoTracker
+
+CAMERA = "ptz_cam"
+
+
+def _config(autotracking_enabled: bool) -> FrigateConfig:
+    return FrigateConfig(
+        **{
+            "mqtt": {"enabled": False},
+            "cameras": {
+                CAMERA: {
+                    "ffmpeg": {
+                        "inputs": [
+                            {"path": "rtsp://10.0.0.1:554/video", "roles": ["detect"]}
+                        ]
+                    },
+                    "detect": {"width": 1920, "height": 1080},
+                    "zones": {"zone": {"coordinates": "0,0,1,0,1,1,0,1"}},
+                    "onvif": {
+                        "host": "10.0.0.1",
+                        "autotracking": {
+                            "enabled": autotracking_enabled,
+                            "required_zones": ["zone"],
+                        },
+                    },
+                }
+            },
+        }
+    )
+
+
+def _make_tracker(autotracking_enabled: bool = True) -> PtzAutoTracker:
+    """Build a PtzAutoTracker without invoking __init__, which would try to set up
+    onvif over the network. Only the config/metrics state is relevant here."""
+    tracker = PtzAutoTracker.__new__(PtzAutoTracker)
+    tracker.config = _config(autotracking_enabled)
+    tracker.ptz_metrics = {CAMERA: PTZMetrics(autotracker_enabled=False)}
+    tracker.onvif = MagicMock()
+    tracker.config_subscriber = MagicMock()
+    tracker.autotracker_init = {}
+    tracker.calibrating = {}
+    tracker.tracked_object = {}
+    return tracker
+
+
+class TestAutotrackerInitGuards(unittest.IsolatedAsyncioTestCase):
+    async def test_camera_maintenance_returns_early_when_not_initialized(self) -> None:
+        # a camera enabled at runtime has no autotracker_init entry, which used to
+        # raise KeyError and kill the autotracker thread for every camera
+        tracker = _make_tracker()
+        self.assertNotIn(CAMERA, tracker.autotracker_init)
+
+        await tracker.camera_maintenance(CAMERA)
+
+        tracker.onvif.get_camera_status.assert_not_called()
+
+    async def test_camera_maintenance_returns_early_when_init_incomplete(self) -> None:
+        # autotracker_init is seeded False for enabled cameras before setup runs
+        tracker = _make_tracker()
+        tracker.autotracker_init[CAMERA] = False
+
+        await tracker.camera_maintenance(CAMERA)
+
+        tracker.onvif.get_camera_status.assert_not_called()
+
+
+class TestAutotrackerMetricSync(unittest.TestCase):
+    def test_metric_follows_config_when_enabled_by_update(self) -> None:
+        # autotracking enabled via a config save: the metric was seeded False when
+        # the camera was added and nothing else updates it
+        tracker = _make_tracker(autotracking_enabled=True)
+        metrics = tracker.ptz_metrics[CAMERA]
+        self.assertFalse(metrics.autotracker_enabled.value)
+
+        tracker.config_subscriber.check_for_updates.return_value = {"onvif": [CAMERA]}
+        tracker.check_for_updates()
+
+        self.assertTrue(metrics.autotracker_enabled.value)
+
+    def test_metric_follows_config_when_disabled_by_update(self) -> None:
+        tracker = _make_tracker(autotracking_enabled=False)
+        metrics = tracker.ptz_metrics[CAMERA]
+        metrics.autotracker_enabled.value = True
+
+        tracker.config_subscriber.check_for_updates.return_value = {
+            "autotracking": [CAMERA]
+        }
+        tracker.check_for_updates()
+
+        self.assertFalse(metrics.autotracker_enabled.value)
+
+    def test_metric_sync_skips_camera_without_metrics(self) -> None:
+        # `add` reaches the maintainer and the autotracker on separate threads with
+        # no ordering guarantee, so the metrics may not exist yet
+        tracker = _make_tracker()
+        tracker.ptz_metrics = {}
+        tracker.config_subscriber.check_for_updates.return_value = {"add": [CAMERA]}
+
+        tracker.check_for_updates()
+
+    def test_metric_sync_skips_unknown_camera(self) -> None:
+        tracker = _make_tracker()
+        tracker.config_subscriber.check_for_updates.return_value = {
+            "add": ["not_in_config"]
+        }
+
+        tracker.check_for_updates()
+
+
+if __name__ == "__main__":
+    unittest.main()

frigate/test/test_ptz_onvif.py

@@ -0,0 +1,147 @@
+"""Tests for ONVIF init state that must not depend on the autotracking config.
+
+Regression coverage for a camera that is initialized while autotracking is off and
+has it enabled later, which is the normal wizard flow: set the camera up first,
+configure autotracking afterwards. The autotracking-only request objects used to
+be created only when autotracking was enabled at init time, so the camera was left
+with init=True but no status_request. get_camera_status skips its re-init branch
+when init is True, so it went straight to the missing key and raised KeyError on
+the tracking thread.
+
+The request objects are built from the locally parsed WSDL and cost no network, so
+they are always created and init=True now implies they exist.
+"""
+
+import unittest
+from unittest.mock import AsyncMock, MagicMock
+
+from frigate.config import FrigateConfig
+from frigate.ptz.onvif import OnvifController
+
+CAMERA = "ptz_cam"
+
+
+def _config(autotracking_enabled: bool) -> FrigateConfig:
+    return FrigateConfig(
+        **{
+            "mqtt": {"enabled": False},
+            "cameras": {
+                CAMERA: {
+                    "ffmpeg": {
+                        "inputs": [
+                            {"path": "rtsp://10.0.0.1:554/video", "roles": ["detect"]}
+                        ]
+                    },
+                    "detect": {"width": 1920, "height": 1080},
+                    "zones": {"zone": {"coordinates": "0,0,1,0,1,1,0,1"}},
+                    "onvif": {
+                        "host": "10.0.0.1",
+                        "autotracking": {
+                            "enabled": autotracking_enabled,
+                            "required_zones": ["zone"],
+                        },
+                    },
+                }
+            },
+        }
+    )
+
+
+def _make_profile() -> MagicMock:
+    profile = MagicMock()
+    profile.token = "profile_1"
+    profile.Name = "MainStream"
+    profile.VideoEncoderConfiguration = MagicMock()
+    ptz_config = MagicMock()
+    ptz_config.token = "ptz_config_1"
+    ptz_config.DefaultContinuousPanTiltVelocitySpace = "space"
+    ptz_config.DefaultContinuousZoomVelocitySpace = "space"
+    profile.PTZConfiguration = ptz_config
+    return profile
+
+
+def _make_onvif_camera() -> MagicMock:
+    """A camera that supports PTZ but nothing optional, so init takes the simplest
+    path through the feature detection below."""
+    onvif = MagicMock()
+    onvif.update_xaddrs = AsyncMock()
+
+    video_source = MagicMock()
+    video_source.token = "video_source_1"
+
+    media = MagicMock()
+    media.GetProfiles = AsyncMock(return_value=[_make_profile()])
+    media.GetVideoSources = AsyncMock(return_value=[video_source])
+    onvif.create_media_service = AsyncMock(return_value=media)
+    onvif.get_definition = MagicMock(return_value={"ptz": "definition"})
+
+    ptz = MagicMock()
+    # create_type is a local WSDL lookup, so tag the result to assert on it later
+    ptz.create_type = MagicMock(side_effect=lambda name: MagicMock(request_type=name))
+    ptz.GetConfigurationOptions = AsyncMock(side_effect=Exception("not supported"))
+    onvif.create_ptz_service = AsyncMock(return_value=ptz)
+    onvif.create_imaging_service = AsyncMock(side_effect=Exception("not supported"))
+    return onvif
+
+
+def _make_controller(autotracking_enabled: bool) -> OnvifController:
+    """Build a controller without invoking __init__, which would start an event loop
+    thread and reach out to the camera."""
+    config = _config(autotracking_enabled)
+    controller = OnvifController.__new__(OnvifController)
+    controller.config = config
+    controller.cams = {CAMERA: {"onvif": _make_onvif_camera(), "init": False}}
+    controller.failed_cams = {}
+    controller.camera_configs = {CAMERA: config.cameras[CAMERA]}
+    controller.ptz_metrics = {CAMERA: MagicMock()}
+    return controller
+
+
+class TestOnvifInitRequests(unittest.IsolatedAsyncioTestCase):
+    async def test_status_request_created_when_autotracking_disabled(self) -> None:
+        # the wizard flow: onvif configured first, autotracking enabled later
+        controller = _make_controller(autotracking_enabled=False)
+
+        self.assertTrue(await controller._init_onvif(CAMERA))
+
+        cam = controller.cams[CAMERA]
+        self.assertTrue(cam["init"])
+        self.assertIn("status_request", cam)
+        self.assertIn("service_capabilities_request", cam)
+
+    async def test_status_request_created_when_autotracking_enabled(self) -> None:
+        controller = _make_controller(autotracking_enabled=True)
+
+        self.assertTrue(await controller._init_onvif(CAMERA))
+
+        cam = controller.cams[CAMERA]
+        self.assertIn("status_request", cam)
+        self.assertIn("service_capabilities_request", cam)
+
+    async def test_init_implies_status_request_exists(self) -> None:
+        # the invariant get_camera_status relies on: it skips re-init when init is
+        # True and then reads status_request without guarding
+        for autotracking_enabled in (True, False):
+            with self.subTest(autotracking_enabled=autotracking_enabled):
+                controller = _make_controller(autotracking_enabled)
+
+                await controller._init_onvif(CAMERA)
+
+                cam = controller.cams[CAMERA]
+                if cam["init"]:
+                    self.assertEqual(cam["status_request"].request_type, "GetStatus")
+
+    async def test_requests_built_without_contacting_camera(self) -> None:
+        # create_type is a local WSDL lookup; cameras that do not implement
+        # GetServiceCapabilities must not be asked about it during init
+        controller = _make_controller(autotracking_enabled=False)
+
+        await controller._init_onvif(CAMERA)
+
+        ptz = controller.cams[CAMERA]["ptz"]
+        ptz.GetServiceCapabilities.assert_not_called()
+        ptz.GetStatus.assert_not_called()
+
+
+if __name__ == "__main__":
+    unittest.main()