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/lib/provider-icons.tsx

@@ -29,6 +29,7 @@ import {
 	QwenIcon,
 	RecraftIcon,
 	ReplicateIcon,
+	RequestyIcon,
 	SambaNovaIcon,
 	TogetherAiIcon,
 	VertexAiIcon,
@@ -117,6 +118,8 @@ export function getProviderIcon(
 			return <RecraftIcon className={cn(className)} />;
 		case "REPLICATE":
 			return <ReplicateIcon className={cn(className)} />;
+		case "REQUESTY":
+			return <RequestyIcon className={cn(className)} />;
 		case "SAMBANOVA":
 			return <SambaNovaIcon className={cn(className)} />;
 		case "TOGETHER_AI":