Added Requesty as a provider

Requesty is an OpenAI compatible AI gateway. The provider mirrors OpenRouter: chat completions over https://router.requesty.ai/v1/, the same project headers, and a model list read from both the managed policies (models/managed) and the full catalog (models), including the context window.

app/Tests/Models/Corpus/CapabilitySnapshot.txt

@@ -189,6 +189,8 @@ PERPLEXITY | sonar-deep-research | ALWAYS_REASONING, CHAT_COMPLETION_API, MULTIP
 PERPLEXITY | sonar-pro | CHAT_COMPLETION_API, MULTIPLE_IMAGE_INPUT, TEXT_INPUT, TEXT_OUTPUT, WEB_SEARCH | CHAT | (unknown) | (unknown) | (unknown)
 PERPLEXITY | sonar-reasoning | ALWAYS_REASONING, CHAT_COMPLETION_API, MULTIPLE_IMAGE_INPUT, TEXT_INPUT, TEXT_OUTPUT, WEB_SEARCH | CHAT | (unknown) | (unknown) | (unknown)
 PERPLEXITY | sonar-reasoning-pro | ALWAYS_REASONING, CHAT_COMPLETION_API, MULTIPLE_IMAGE_INPUT, TEXT_INPUT, TEXT_OUTPUT, WEB_SEARCH | CHAT | (unknown) | (unknown) | (unknown)
+REQUESTY | anthropic/claude-opus-5 | CHAT_COMPLETION_API, FUNCTION_CALLING, MULTIPLE_IMAGE_INPUT, REASONING_BY_DEFAULT, TEXT_INPUT, TEXT_OUTPUT | CHAT | 1000000 | 600 per request | PROVIDER_API /v1/messages/count_tokens
+REQUESTY | google/gemma-4-31b-it | CHAT_COMPLETION_API, FUNCTION_CALLING, MULTIPLE_IMAGE_INPUT, OPTIONAL_REASONING, TEXT_INPUT, TEXT_OUTPUT | CHAT | (unknown) | (unknown) | (unknown)
 SELF_HOSTED |     | (nothing) | CHAT | (unknown) | (unknown) | (unknown)
 SELF_HOSTED | --- | CHAT_COMPLETION_API, FUNCTION_CALLING, TEXT_INPUT, TEXT_OUTPUT | CHAT | (unknown) | (unknown) | (unknown)
 SELF_HOSTED | 01-ai/yi-large | CHAT_COMPLETION_API, TEXT_INPUT, TEXT_OUTPUT | CHAT | (unknown) | (unknown) | (unknown)

app/Tests/Models/Corpus/ModelCorpus.cs

@@ -237,6 +237,8 @@ public static class ModelCorpus
         new(LITE_LLM, "azure/gpt-5.6", QUOTED_AS_A_NAME_SHAPE),
         new(LITE_LLM, "bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0", NAMED_BY_NO_RULE),
         new(LITE_LLM, "the-fast-one", NAMED_BY_NO_RULE),
+        new(REQUESTY, "anthropic/claude-opus-5", QUOTED_AS_A_NAME_SHAPE),
+        new(REQUESTY, "google/gemma-4-31b-it", NAMED_BY_A_RULE),
     ];
 
     /// <summary>

app/Tests/Provider/ModelListMetadataTests.cs

@@ -2,6 +2,7 @@ using System.Text.Json;
 
 using AIStudio.Provider.Groq;
 using AIStudio.Provider.OpenRouter;
+using AIStudio.Provider.Requesty;
 
 using MistralModelsResponse = AIStudio.Provider.Mistral.ModelsResponse;
 using SelfHostedModelsResponse = AIStudio.Provider.SelfHosted.ModelsResponse;
@@ -105,6 +106,19 @@ public sealed class ModelListMetadataTests
         Assert.That(response.Data[0].ContextWindowTokens, Is.EqualTo(131_072));
     }
 
+    [Test]
+    public void RequestyStatesTheWindowAsTheContextWindow()
+    {
+        var response = JsonSerializer.Deserialize<RequestyModelsResponse>("""
+                                                                         {
+                                                                             "object": "list",
+                                                                             "data": [ { "id": "openai/gpt-4o-mini", "object": "model", "api": "chat", "context_window": 128000, "max_output_tokens": 16384 } ]
+                                                                         }
+                                                                         """, AS_THE_PROVIDERS_READ_IT);
+
+        Assert.That(response.Data[0].ContextWindowTokens, Is.EqualTo(128_000));
+    }
+
     [Test]
     public void MistralStatesTheWindowAsAMaximumLength()
     {