feat: add Requesty as a model provider

Add Requesty (https://requesty.ai), an OpenAI-compatible LLM router, as a
model provider by mirroring the existing OpenRouter integration.

Backend:
- app/services/requesty_model_normalizer.py: normalizes Requesty's /v1/models
  catalogue, mapping its flat capability booleans (supports_tool_calling/
  supports_vision/supports_image_generation) and context_window field onto the
  shared normalized shape (Requesty differs from OpenRouter's architecture +
  supported_parameters + context_length layout)
- provider_registry.py: Requesty ProviderSpec (OpenAI-compatible, base URL
  https://router.requesty.ai/v1, REQUESTY_API_KEY bearer auth)
- model_connection_service.py: key verification + live model discovery
- quality_score.py: Requesty score entry
- unit tests mirroring the OpenRouter normalizer coverage

Frontend:
- Requesty provider icon + registration, metadata entry, and base-url hint

Signed-off-by: Thibault Jaigu <thibault.jaigu@gmail.com>

surfsense_web/components/settings/model-connections/default-connect-form.tsx

@@ -11,7 +11,12 @@ function baseUrlHint(provider: string) {
 	if (provider === "openai_compatible") {
 		return "Enter the full endpoint URL.";
 	}
-	if (provider === "openai" || provider === "anthropic" || provider === "openrouter") {
+	if (
+		provider === "openai" ||
+		provider === "anthropic" ||
+		provider === "openrouter" ||
+		provider === "requesty"
+	) {
 		return "Override only if you route through a proxy or gateway.";
 	}
 	return undefined;

surfsense_web/components/settings/model-connections/provider-metadata.tsx

@@ -7,6 +7,7 @@ export const PROVIDER_ORDER = [
 	"bedrock",
 	"azure",
 	"openrouter",
+	"requesty",
 	"ollama_chat",
 	"lm_studio",
 	"openai_compatible",
@@ -43,6 +44,12 @@ export const PROVIDER_DISPLAY: Record<
 		iconKey: "openrouter",
 		defaultBaseUrl: "https://openrouter.ai/api/v1",
 	},
+	requesty: {
+		name: "Requesty",
+		subtitle: "Requesty",
+		iconKey: "requesty",
+		defaultBaseUrl: "https://router.requesty.ai/v1",
+	},
 	vertex_ai: { name: "Gemini", subtitle: "Google Cloud Vertex AI", iconKey: "vertex_ai" },
 };