Merge ce0197cc8f into 6f80bcd19f

docs/docs/configuration/genai/config.md

@@ -78,7 +78,7 @@ All llama.cpp native options can be passed through `provider_options`, including
    - Set **Provider** to `llamacpp`
    - Set **Base URL** to your llama.cpp server address (e.g., `http://localhost:8080`)
    - Set **Model** to the name of your model
-   - Optionally, under **Provider Options**, set `context_size` to override the context size Frigate detects from the server
+   - Under **Provider Options**, set `context_size` to tell Frigate your context size so it can send the appropriate amount of information
 
 </TabItem>
 <TabItem value="yaml">
@@ -89,14 +89,12 @@ genai:
   base_url: http://localhost:8080
   model: your-model-name
   provider_options:
-    context_size: 16000 # Optional, overrides the context size reported by the server.
+    context_size: 16000 # Tell Frigate your context size so it can send the appropriate amount of information.
 ```
 
 </TabItem>
 </ConfigTabs>
 
-Frigate queries the llama.cpp server for the model's context size at startup and logs it along with the other detected capabilities. If `context_size` is set in `provider_options`, that value is always used instead, even when the server reports its own.
-
 ### Ollama
 
 [Ollama](https://ollama.com/) allows you to self-host large language models and keep everything running locally. It is highly recommended to host this server on a machine with an Nvidia graphics card, or on a Apple silicon Mac for best performance.

frigate/genai/plugins/llama_cpp.py

@@ -192,7 +192,7 @@ class LlamaCppClient(GenAIClient):
         logger.info(
             "llama.cpp model '%s' initialized — context: %s, vision: %s, audio: %s, tools: %s, reasoning: %s",
             configured_model,
-            self.get_context_size(),
+            self._context_size or "unknown",
             self._supports_vision,
             self._supports_audio,
             self._supports_tools,

frigate/test/test_genai_providers.py

@@ -491,34 +491,6 @@ class TestLlamaCppProvider(unittest.TestCase):
         final = _final_message(self._run_with_lines(client, lines, MULTIMODAL_MESSAGES))
         self.assertEqual(final["content"], "ok")
 
-    def _validated_client(self, server_context_size, provider_options=None):
-        """Build a client as if the server reported the given context size."""
-        cfg = GenAIConfig(
-            provider="llamacpp",
-            model="m",
-            base_url="http://localhost:9999",
-            provider_options=provider_options or {},
-        )
-        info = {
-            "context_size": server_context_size,
-            "supports_vision": False,
-            "supports_audio": False,
-            "supports_tools": False,
-            "supports_reasoning": False,
-            "media_marker": "<__media__>",
-        }
-        cls = PROVIDERS[GenAIProviderEnum.llamacpp]
-        with patch.object(cls, "_get_model_info", return_value=info):
-            return cls(cfg, timeout=5)
-
-    def test_server_context_size_used_without_override(self):
-        client = self._validated_client(4096)
-        self.assertEqual(client.get_context_size(), 4096)
-
-    def test_provider_options_context_size_overrides_server(self):
-        client = self._validated_client(4096, {"context_size": 32768})
-        self.assertEqual(client.get_context_size(), 32768)
-
 
 if __name__ == "__main__":
     unittest.main()