Merge 45d3c6389e 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
-   - Under **Provider Options**, set `context_size` to tell Frigate your context size so it can send the appropriate amount of information
+   - Optionally, under **Provider Options**, set `context_size` to override the context size Frigate detects from the server
 
 </TabItem>
 <TabItem value="yaml">
@@ -89,12 +89,14 @@ genai:
   base_url: http://localhost:8080
   model: your-model-name
   provider_options:
-    context_size: 16000 # Tell Frigate your context size so it can send the appropriate amount of information.
+    context_size: 16000 # Optional, overrides the context size reported by the server.
 ```
 
 </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._context_size or "unknown",
+            self.get_context_size(),
             self._supports_vision,
             self._supports_audio,
             self._supports_tools,

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()

web/e2e/specs/settings/semantic-search.spec.ts

@@ -0,0 +1,129 @@
+/**
+ * Semantic Search settings tests -- MEDIUM tier.
+ *
+ * Focuses on the model_size field, which is unused when a GenAI embeddings
+ * provider is selected as the semantic search model. The resolved config always
+ * reports model_size (it has a schema default of "small"), even when the YAML
+ * file has no such key. Clearing model_size for a provider used to run
+ * unconditionally, which falsely marked the section dirty on load and asked the
+ * backend to delete a key that wasn't in the config file (KeyError: 'model_size').
+ */
+
+import { readFileSync } from "node:fs";
+import { resolve, dirname } from "node:path";
+import { fileURLToPath } from "node:url";
+import { test, expect } from "../../fixtures/frigate-test";
+import type { Page } from "@playwright/test";
+import { configFactory } from "../../fixtures/mock-data/config";
+
+const __dirname = dirname(fileURLToPath(import.meta.url));
+const CONFIG_SCHEMA = JSON.parse(
+  readFileSync(
+    resolve(__dirname, "../../fixtures/mock-data/config-schema.json"),
+    "utf-8",
+  ),
+);
+
+const PROVIDER = "llama_cpp";
+const SETTINGS_URL = "/settings?page=integrationSemanticSearch";
+const NOT_APPLICABLE = "Not applicable for GenAI providers";
+const UNSAVED = "You have unsaved changes";
+
+type SemanticSearch = {
+  enabled?: boolean;
+  model?: string;
+  model_size?: string;
+};
+
+async function installRoutes(page: Page, semanticSearch: SemanticSearch) {
+  const config = configFactory({
+    genai: { [PROVIDER]: { provider: PROVIDER, roles: ["embeddings"] } },
+    semantic_search: semanticSearch,
+  });
+
+  let lastSavedConfig: unknown = null;
+
+  await page.route("**/api/config/schema.json", (route) =>
+    route.fulfill({ json: CONFIG_SCHEMA }),
+  );
+  await page.route("**/api/config", (route) => {
+    if (route.request().method() === "GET") {
+      return route.fulfill({ json: config });
+    }
+    return route.fulfill({ json: { success: true } });
+  });
+  await page.route("**/api/config/set", async (route) => {
+    lastSavedConfig = route.request().postDataJSON();
+    await route.fulfill({ json: { success: true, require_restart: false } });
+  });
+  await page.route("**/api/config/raw_paths", (route) =>
+    route.fulfill({ json: { semantic_search: semanticSearch } }),
+  );
+
+  return { capturedConfig: () => lastSavedConfig };
+}
+
+test.describe("semantic search model_size @medium", () => {
+  test("a provider with a defaulted model_size is not dirty on load", async ({
+    frigateApp,
+  }) => {
+    // model_size stays at its schema default ("small"), i.e. it is not present
+    // in the YAML. This mirrors the reported bug: selecting a GenAI provider and
+    // returning to the page.
+    await installRoutes(frigateApp.page, {
+      enabled: true,
+      model: PROVIDER,
+    });
+    await frigateApp.goto(SETTINGS_URL);
+
+    // The provider path is active: model_size shows "Not applicable".
+    await expect(frigateApp.page.getByText(NOT_APPLICABLE)).toBeVisible();
+
+    // Give any clearing effect time to fire, then confirm the section stayed
+    // clean (no phantom unsaved-changes banner, Save disabled).
+    await frigateApp.page.waitForTimeout(1000);
+    await expect(frigateApp.page.getByText(UNSAVED)).toBeHidden();
+    await expect(
+      frigateApp.page.getByRole("button", { name: "Save", exact: true }),
+    ).toBeDisabled();
+  });
+
+  test("switching from a configured non-default model_size clears it", async ({
+    frigateApp,
+  }) => {
+    // A genuinely configured non-default model_size ("large") can only come from
+    // the YAML, so switching to a provider must still remove it.
+    const capture = await installRoutes(frigateApp.page, {
+      enabled: true,
+      model: "jinav2",
+      model_size: "large",
+    });
+    await frigateApp.goto(SETTINGS_URL);
+
+    // Starts clean on a Jina model.
+    await expect(frigateApp.page.getByText(UNSAVED)).toBeHidden();
+
+    // Switch the model to the GenAI provider.
+    await frigateApp.page
+      .getByRole("combobox", { name: /Semantic search model/ })
+      .click();
+    await frigateApp.page.getByRole("option", { name: PROVIDER }).click();
+
+    // The change is now dirty and model_size is no longer applicable.
+    await expect(frigateApp.page.getByText(NOT_APPLICABLE)).toBeVisible();
+    await expect(frigateApp.page.getByText(UNSAVED)).toBeVisible();
+
+    await frigateApp.page
+      .getByRole("button", { name: "Save", exact: true })
+      .click();
+
+    // The saved payload removes model_size (empty string = "remove" key).
+    await expect
+      .poll(() => capture.capturedConfig(), { timeout: 5_000 })
+      .toMatchObject({
+        config_data: {
+          semantic_search: { model: PROVIDER, model_size: "" },
+        },
+      });
+  });
+});

web/src/components/config-form/theme/widgets/SemanticSearchModelSizeWidget.tsx

@@ -24,15 +24,19 @@ export function SemanticSearchModelSizeWidget(props: WidgetProps) {
     model !== "jinav1" &&
     model !== "jinav2";
 
-  // Clear model_size while on a provider (buildOverrides converts to ""
-  // which the backend treats as "remove"). Restore the schema default
-  // when returning to a Jina model so the field isn't left empty.
+  // model_size is unused on a GenAI provider. Only clear it (which the backend
+  // treats as "remove") for a non-default value, which can only come from the
+  // config file. A defaulted value is indistinguishable from unset in the
+  // resolved config, so clearing it would falsely dirty the field and delete a
+  // YAML key that isn't there. Restore the default when returning to a Jina model.
   const { value, onChange, schema } = props;
   const schemaDefault = schema?.default as string | undefined;
   useEffect(() => {
-    if (isProvider && value !== undefined) {
-      onChange(undefined);
-    } else if (!isProvider && value === undefined && schemaDefault) {
+    if (isProvider) {
+      if (value !== undefined && value !== schemaDefault) {
+        onChange(undefined);
+      }
+    } else if (value === undefined && schemaDefault) {
       onChange(schemaDefault);
     }
   }, [isProvider, value, onChange, schemaDefault]);