Miscellaneous fixes (0.17 beta) (#21431)

* Add shortSummary field to review summary to be used for notifications

* pull in current config version into default config

* fix crash when dynamically adding cameras

depending on where we are in the update loop, camera configs might not be updated yet and we are receiving detections already

* add no tracked objects and icon to explore summary view

* reset add camera wizard when closing and saving

* don't flash no exports icon while loading

* Improve handling of homekit config

* Increase prompt tokens reservation

* Adjust

* Catch event not found object detection

* Use thread lock for JinaV2 in onnxruntime

* remove incorrect embeddings process from memray docs

* only show transcribe button if audio event has video

* apply aspect ratio and margin constraints to path overlay in detail stream on mobile

improves a specific case where the overlay was not aligned with 4:3 cameras on mobile phones

* show metadata title as tooltip on icon hover in detail stream

---------

Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>

frigate/detectors/detection_runners.py

@@ -139,8 +139,31 @@ class ONNXModelRunner(BaseModelRunner):
             ModelTypeEnum.dfine.value,
         ]
 
-    def __init__(self, ort: ort.InferenceSession):
+    @staticmethod
+    def is_concurrent_model(model_type: str | None) -> bool:
+        """Check if model requires thread locking for concurrent inference.
+
+        Some models (like JinaV2) share one runner between text and vision embeddings
+        called from different threads, requiring thread synchronization.
+        """
+        if not model_type:
+            return False
+
+        # Import here to avoid circular imports
+        from frigate.embeddings.types import EnrichmentModelTypeEnum
+
+        return model_type == EnrichmentModelTypeEnum.jina_v2.value
+
+    def __init__(self, ort: ort.InferenceSession, model_type: str | None = None):
         self.ort = ort
+        self.model_type = model_type
+
+        # Thread lock to prevent concurrent inference (needed for JinaV2 which shares
+        # one runner between text and vision embeddings called from different threads)
+        if self.is_concurrent_model(model_type):
+            self._inference_lock = threading.Lock()
+        else:
+            self._inference_lock = None
 
     def get_input_names(self) -> list[str]:
         return [input.name for input in self.ort.get_inputs()]
@@ -150,6 +173,10 @@ class ONNXModelRunner(BaseModelRunner):
         return self.ort.get_inputs()[0].shape[3]
 
     def run(self, input: dict[str, Any]) -> Any | None:
+        if self._inference_lock:
+            with self._inference_lock:
+                return self.ort.run(None, input)
+
         return self.ort.run(None, input)
 
 
@@ -576,5 +603,6 @@ def get_optimized_runner(
             ),
             providers=providers,
             provider_options=options,
-        )
+        ),
+        model_type=model_type,
     )