Miscellaneous fixes (0.17 beta) (#21607)

* Strip model name before training

* Handle options file for go2rtc option

* Make reviewed optional and add null to API call

* Send reviewed for dashboard

* Allow setting context size for openai compatible endpoints

* push empty go2rtc config to avoid homekit error in log

* Add option to set runtime options for LLM providers

* Docs

---------

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

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/config/camera/genai.py

@@ -26,3 +26,6 @@ class GenAIConfig(FrigateBaseModel):
     provider_options: dict[str, Any] = Field(
         default={}, title="GenAI Provider extra options."
     )
+    runtime_options: dict[str, Any] = Field(
+        default={}, title="Options to pass during inference calls."
+    )

frigate/genai/azure-openai.py

@@ -64,6 +64,7 @@ class OpenAIClient(GenAIClient):
                     },
                 ],
                 timeout=self.timeout,
+                **self.genai_config.runtime_options,
             )
         except Exception as e:
             logger.warning("Azure OpenAI returned an error: %s", str(e))

frigate/genai/gemini.py

@@ -35,10 +35,14 @@ class GeminiClient(GenAIClient):
             for img in images
         ] + [prompt]
         try:
+            # Merge runtime_options into generation_config if provided
+            generation_config_dict = {"candidate_count": 1}
+            generation_config_dict.update(self.genai_config.runtime_options)
+
             response = self.provider.generate_content(
                 data,
                 generation_config=genai.types.GenerationConfig(
-                    candidate_count=1,
+                    **generation_config_dict
                 ),
                 request_options=genai.types.RequestOptions(
                     timeout=self.timeout,

frigate/genai/ollama.py

@@ -58,11 +58,15 @@ class OllamaClient(GenAIClient):
             )
             return None
         try:
+            ollama_options = {
+                **self.provider_options,
+                **self.genai_config.runtime_options,
+            }
             result = self.provider.generate(
                 self.genai_config.model,
                 prompt,
                 images=images if images else None,
-                **self.provider_options,
+                **ollama_options,
             )
             logger.debug(
                 f"Ollama tokens used: eval_count={result.get('eval_count')}, prompt_eval_count={result.get('prompt_eval_count')}"

frigate/genai/openai.py

@@ -22,9 +22,14 @@ class OpenAIClient(GenAIClient):
 
     def _init_provider(self):
         """Initialize the client."""
-        return OpenAI(
-            api_key=self.genai_config.api_key, **self.genai_config.provider_options
-        )
+        # Extract context_size from provider_options as it's not a valid OpenAI client parameter
+        # 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."""
@@ -56,6 +61,7 @@ class OpenAIClient(GenAIClient):
                     },
                 ],
                 timeout=self.timeout,
+                **self.genai_config.runtime_options,
             )
             if (
                 result is not None
@@ -73,6 +79,16 @@ 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)