From 761a431c55ee4e1c2f41203f5456895858f9a1a7 Mon Sep 17 00:00:00 2001
From: Nicolas Mowen <nickmowen213@gmail.com>
Date: Sun, 19 Jul 2026 17:22:33 -0600
Subject: [PATCH] Use manual context size if set

---
 frigate/genai/plugins/llama_cpp.py   |  2 +-
 frigate/test/test_genai_providers.py | 28 ++++++++++++++++++++++++++++
 2 files changed, 29 insertions(+), 1 deletion(-)

diff --git a/frigate/genai/plugins/llama_cpp.py b/frigate/genai/plugins/llama_cpp.py
index af3ecc9b18..a217e0d898 100644
--- a/frigate/genai/plugins/llama_cpp.py
+++ b/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._context_size or "unknown",
+            self.get_context_size(),
             self._supports_vision,
             self._supports_audio,
             self._supports_tools,
diff --git a/frigate/test/test_genai_providers.py b/frigate/test/test_genai_providers.py
index d73d632f0a..5352a81e25 100644
--- a/frigate/test/test_genai_providers.py
+++ b/frigate/test/test_genai_providers.py
@@ -491,6 +491,34 @@ 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()