feat(ai-providers): add Requesty as an AI provider

CHANGELOG.md

@@ -71,6 +71,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Export from a data file window to every bundled format, for all, filtered or selected rows.
 - **Import into Table** from a data file window, into an open connection's import sheet.
 - **Text Encoding** in a data file's Save As panel.
+- Requesty as an AI provider, an OpenAI-compatible router.
 
 ### Changed
 

TablePro/Core/AI/Registry/AIProviderRegistration.swift

@@ -101,7 +101,7 @@ enum AIProviderRegistration {
             }
         ))
 
-        for type in [AIProviderType.openRouter, .openCode, .ollama, .llamaCpp, .mlx, .custom] {
+        for type in [AIProviderType.openRouter, .requesty, .openCode, .ollama, .llamaCpp, .mlx, .custom] {
             var capabilities: AIProviderCapabilities = [
                 .chat, .models, .reasoning, .images,
                 .endpointConfigurable, .maxOutputTokens, .modelListFetchable

TablePro/Models/AI/AIModels.swift

@@ -15,6 +15,7 @@ enum AIProviderType: String, Codable, CaseIterable, Identifiable, Sendable {
     case claudeAgent
     case openAI
     case openRouter
+    case requesty
     case gemini
     case xai
     case ollama
@@ -34,6 +35,7 @@ enum AIProviderType: String, Codable, CaseIterable, Identifiable, Sendable {
         case .claudeAgent:  return "Claude Agent"
         case .openAI:       return "OpenAI"
         case .openRouter:   return "OpenRouter"
+        case .requesty:     return "Requesty"
         case .gemini:       return "Gemini"
         case .xai:          return "xAI"
         case .ollama:       return "Ollama"
@@ -53,6 +55,7 @@ enum AIProviderType: String, Codable, CaseIterable, Identifiable, Sendable {
         case .claudeAgent:  return ""
         case .openAI:       return "https://api.openai.com"
         case .openRouter:   return "https://openrouter.ai/api"
+        case .requesty:     return "https://router.requesty.ai"
         case .gemini:       return "https://generativelanguage.googleapis.com"
         case .xai:          return "https://api.x.ai"
         case .ollama:       return "http://localhost:11434"
@@ -106,6 +109,7 @@ enum AIProviderType: String, Codable, CaseIterable, Identifiable, Sendable {
         case .claudeAgent:  return "terminal"
         case .openAI:       return "cpu"
         case .openRouter:   return "globe"
+        case .requesty:     return "arrow.triangle.branch"
         case .gemini:       return "wand.and.stars"
         case .xai:          return "x.circle"
         case .ollama:       return "desktopcomputer"

TableProTests/Core/AI/AIEndpointTests.swift

@@ -23,6 +23,7 @@ struct AIEndpointTests {
         #expect(chatURL("https://api.openai.com", .chatCompletions) == "https://api.openai.com/v1/chat/completions")
         #expect(modelsURL("https://api.openai.com", .chatCompletions) == "https://api.openai.com/v1/models")
         #expect(chatURL("https://openrouter.ai/api", .chatCompletions) == "https://openrouter.ai/api/v1/chat/completions")
+        #expect(chatURL("https://router.requesty.ai", .chatCompletions) == "https://router.requesty.ai/v1/chat/completions")
         #expect(chatURL("https://opencode.ai/zen", .chatCompletions) == "https://opencode.ai/zen/v1/chat/completions")
         #expect(chatURL("http://localhost:8080", .chatCompletions) == "http://localhost:8080/v1/chat/completions")
     }

TableProTests/Core/AI/AIProviderCapabilitiesTests.swift

@@ -40,7 +40,7 @@ struct AIProviderCapabilitiesTests {
 
     @Test("HTTP API-key providers accept max output tokens, a configurable endpoint, and model fetch")
     func standardHTTPProviders() {
-        for type in [AIProviderType.openAI, .claude, .gemini, .xai, .openRouter, .ollama] {
+        for type in [AIProviderType.openAI, .claude, .gemini, .xai, .openRouter, .requesty, .ollama] {
             let provider = descriptor(type)
             #expect(provider?.allowsMaxOutputTokens == true, "\(type.rawValue) should accept max output tokens")
             #expect(provider?.allowsEndpointConfiguration == true, "\(type.rawValue) should allow endpoint config")

docs/security/privacy.mdx

@@ -50,7 +50,7 @@ On iPhone and iPad the heartbeat is off until you choose **Share Usage Data**, a
 
 Nothing reaches a model until you add a provider, and a fresh install has none: with none configured, every AI path returns before it builds a request. **Enable AI Features** in **Settings > AI** is on out of the box, but it gates an empty tab.
 
-One provider is marked active and answers inline suggestions and the editor actions; the chat panel's own model picker can send a turn to any other provider you configured. Requests go to that provider's endpoint. The presets are `api.anthropic.com`, `api.openai.com`, `generativelanguage.googleapis.com`, `api.x.ai`, `openrouter.ai`, `api.cursor.com` and `opencode.ai`, plus `http://localhost:11434` for Ollama and `http://localhost:8080` for llama.cpp and MLX, which keeps their traffic on the machine. Every endpoint field is editable, and a custom provider goes wherever you point it.
+One provider is marked active and answers inline suggestions and the editor actions; the chat panel's own model picker can send a turn to any other provider you configured. Requests go to that provider's endpoint. The presets are `api.anthropic.com`, `api.openai.com`, `generativelanguage.googleapis.com`, `api.x.ai`, `openrouter.ai`, `router.requesty.ai`, `api.cursor.com` and `opencode.ai`, plus `http://localhost:11434` for Ollama and `http://localhost:8080` for llama.cpp and MLX, which keeps their traffic on the machine. Every endpoint field is editable, and a custom provider goes wherever you point it.
 
 A chat turn carries: