Allow setting context size for openai compatible endpoints

docker/main/rootfs/usr/local/go2rtc/create_config.py

@@ -23,8 +23,28 @@ sys.path.remove("/opt/frigate")
 yaml = YAML()
 
 # Check if arbitrary exec sources are allowed (defaults to False for security)
-ALLOW_ARBITRARY_EXEC = os.environ.get(
+allow_arbitrary_exec = None
-    "GO2RTC_ALLOW_ARBITRARY_EXEC", "false"
+if "GO2RTC_ALLOW_ARBITRARY_EXEC" in os.environ:
+    allow_arbitrary_exec = os.environ.get("GO2RTC_ALLOW_ARBITRARY_EXEC")
+elif (
+    os.path.isdir("/run/secrets")
+    and os.access("/run/secrets", os.R_OK)
+    and "GO2RTC_ALLOW_ARBITRARY_EXEC" in os.listdir("/run/secrets")
+):
+    allow_arbitrary_exec = (
+        Path(os.path.join("/run/secrets", "GO2RTC_ALLOW_ARBITRARY_EXEC"))
+        .read_text()
+        .strip()
+    )
+# check for the add-on options file
+elif os.path.isfile("/data/options.json"):
+    with open("/data/options.json") as f:
+        raw_options = f.read()
+    options = json.loads(raw_options)
+    allow_arbitrary_exec = options.get("go2rtc_allow_arbitrary_exec")
+
+ALLOW_ARBITRARY_EXEC = allow_arbitrary_exec is not None and str(
+    allow_arbitrary_exec
 ).lower() in ("true", "1", "yes")
 
 FRIGATE_ENV_VARS = {k: v for k, v in os.environ.items() if k.startswith("FRIGATE_")}

docs/docs/configuration/genai/config.md

@@ -41,12 +41,12 @@ If you are trying to use a single model for Frigate and HomeAssistant, it will n
 
 The following models are recommended:
 
-| Model             | Notes                                                                |
+| Model         | Notes                                                                |
-| ----------------- | -------------------------------------------------------------------- |
+| ------------- | -------------------------------------------------------------------- |
-| `qwen3-vl`        | Strong visual and situational understanding, higher vram requirement |
+| `qwen3-vl`    | Strong visual and situational understanding, higher vram requirement |
-| `Intern3.5VL`     | Relatively fast with good vision comprehension                       |
+| `Intern3.5VL` | Relatively fast with good vision comprehension                       |
-| `gemma3`          | Strong frame-to-frame understanding, slower inference times          |
+| `gemma3`      | Strong frame-to-frame understanding, slower inference times          |
-| `qwen2.5-vl`      | Fast but capable model with good vision comprehension                |
+| `qwen2.5-vl`  | Fast but capable model with good vision comprehension                |
 
 :::note
 
@@ -61,10 +61,10 @@ genai:
   provider: ollama
   base_url: http://localhost:11434
   model: minicpm-v:8b
-  provider_options:  # other Ollama client options can be defined
+  provider_options: # other Ollama client options can be defined
     keep_alive: -1
     options:
-        num_ctx: 8192  # make sure the context matches other services that are using ollama
+      num_ctx: 8192 # make sure the context matches other services that are using ollama
 ```
 
 ## Google Gemini
@@ -120,6 +120,23 @@ To use a different OpenAI-compatible API endpoint, set the `OPENAI_BASE_URL` env
 
 :::
 
+:::tip
+
+For OpenAI-compatible servers (such as llama.cpp) that don't expose the configured context size in the API response, you can manually specify the context size in `provider_options`:
+
+```yaml
+genai:
+  provider: openai
+  base_url: http://your-llama-server
+  model: your-model-name
+  provider_options:
+    context_size: 8192 # Specify the configured context size
+```
+
+This ensures Frigate uses the correct context window size when generating prompts.
+
+:::
+
 ## Azure OpenAI
 
 Microsoft offers several vision models through Azure OpenAI. A subscription is required.

frigate/api/defs/query/review_query_parameters.py

@@ -10,7 +10,7 @@ class ReviewQueryParams(BaseModel):
     cameras: str = "all"
     labels: str = "all"
     zones: str = "all"
-    reviewed: int = 0
+    reviewed: Union[int, SkipJsonSchema[None]] = None
     limit: Union[int, SkipJsonSchema[None]] = None
     severity: Union[SeverityEnum, SkipJsonSchema[None]] = None
     before: Union[float, SkipJsonSchema[None]] = None

frigate/genai/openai.py

@@ -22,9 +22,14 @@ class OpenAIClient(GenAIClient):
 
     def _init_provider(self):
         """Initialize the client."""
-        return OpenAI(
+        # Extract context_size from provider_options as it's not a valid OpenAI client parameter
-            api_key=self.genai_config.api_key, **self.genai_config.provider_options
+        # It will be used in get_context_size() instead
-        )
+        provider_opts = {
+            k: v
+            for k, v in self.genai_config.provider_options.items()
+            if k != "context_size"
+        }
+        return OpenAI(api_key=self.genai_config.api_key, **provider_opts)
 
     def _send(self, prompt: str, images: list[bytes]) -> Optional[str]:
         """Submit a request to OpenAI."""
@@ -73,6 +78,16 @@ class OpenAIClient(GenAIClient):
         if self.context_size is not None:
             return self.context_size
 
+        # First check provider_options for manually specified context size
+        # This is necessary for llama.cpp and other OpenAI-compatible servers
+        # that don't expose the configured runtime context size in the API response
+        if "context_size" in self.genai_config.provider_options:
+            self.context_size = self.genai_config.provider_options["context_size"]
+            logger.debug(
+                f"Using context size {self.context_size} from provider_options for model {self.genai_config.model}"
+            )
+            return self.context_size
+
         try:
             models = self.provider.models.list()
             for model in models.data:

frigate/util/classification.py

@@ -43,6 +43,7 @@ def write_training_metadata(model_name: str, image_count: int) -> None:
         model_name: Name of the classification model
         image_count: Number of images used in training
     """
+    model_name = model_name.strip()
     clips_model_dir = os.path.join(CLIPS_DIR, model_name)
     os.makedirs(clips_model_dir, exist_ok=True)
 
@@ -70,6 +71,7 @@ def read_training_metadata(model_name: str) -> dict[str, any] | None:
     Returns:
         Dictionary with last_training_date and last_training_image_count, or None if not found
     """
+    model_name = model_name.strip()
     clips_model_dir = os.path.join(CLIPS_DIR, model_name)
     metadata_path = os.path.join(clips_model_dir, TRAINING_METADATA_FILE)
 
@@ -95,6 +97,7 @@ def get_dataset_image_count(model_name: str) -> int:
     Returns:
         Total count of images across all categories
     """
+    model_name = model_name.strip()
     dataset_dir = os.path.join(CLIPS_DIR, model_name, "dataset")
 
     if not os.path.exists(dataset_dir):
@@ -126,6 +129,7 @@ class ClassificationTrainingProcess(FrigateProcess):
             "TF_KERAS_MOBILENET_V2_WEIGHTS_URL",
             "",
         )
+        model_name = model_name.strip()
         super().__init__(
             stop_event=None,
             priority=PROCESS_PRIORITY_LOW,
@@ -292,6 +296,7 @@ class ClassificationTrainingProcess(FrigateProcess):
 def kickoff_model_training(
     embeddingRequestor: EmbeddingsRequestor, model_name: str
 ) -> None:
+    model_name = model_name.strip()
     requestor = InterProcessRequestor()
     requestor.send_data(
         UPDATE_MODEL_STATE,
@@ -359,6 +364,7 @@ def collect_state_classification_examples(
         model_name: Name of the classification model
         cameras: Dict mapping camera names to normalized crop coordinates [x1, y1, x2, y2] (0-1)
     """
+    model_name = model_name.strip()
     dataset_dir = os.path.join(CLIPS_DIR, model_name, "dataset")
 
     # Step 1: Get review items for the cameras
@@ -714,6 +720,7 @@ def collect_object_classification_examples(
         model_name: Name of the classification model
         label: Object label to collect (e.g., "person", "car")
     """
+    model_name = model_name.strip()
     dataset_dir = os.path.join(CLIPS_DIR, model_name, "dataset")
     temp_dir = os.path.join(dataset_dir, "temp")
     os.makedirs(temp_dir, exist_ok=True)

web/src/pages/Events.tsx

@@ -205,7 +205,7 @@ export default function Events() {
       cameras: reviewSearchParams["cameras"],
       labels: reviewSearchParams["labels"],
       zones: reviewSearchParams["zones"],
-      reviewed: 1,
+      reviewed: null, // We want both reviewed and unreviewed items as we filter in the UI
       before: reviewSearchParams["before"] || last24Hours.before,
       after: reviewSearchParams["after"] || last24Hours.after,
     };

web/src/views/live/LiveDashboardView.tsx

@@ -114,6 +114,7 @@ export default function LiveDashboardView({
     {
       limit: 10,
       severity: "alert",
+      reviewed: 0,
       cameras: alertCameras,
     },
   ]);