chore(provider): add Google AI Studio support

crates/forge_domain/src/provider.rs

@@ -72,6 +72,7 @@ impl ProviderId {
     pub const OPENCODE_ZEN: ProviderId = ProviderId(Cow::Borrowed("opencode_zen"));
     pub const FIREWORKS_AI: ProviderId = ProviderId(Cow::Borrowed("fireworks-ai"));
     pub const NOVITA: ProviderId = ProviderId(Cow::Borrowed("novita"));
+    pub const GOOGLE_AI_STUDIO: ProviderId = ProviderId(Cow::Borrowed("google_ai_studio"));
 
     /// Returns all built-in provider IDs
     ///
@@ -104,6 +105,7 @@ impl ProviderId {
             ProviderId::OPENCODE_ZEN,
             ProviderId::FIREWORKS_AI,
             ProviderId::NOVITA,
+            ProviderId::GOOGLE_AI_STUDIO,
         ]
     }
 
@@ -129,6 +131,7 @@ impl ProviderId {
             "codex" => "Codex".to_string(),
             "fireworks-ai" => "FireworksAI".to_string(),
             "novita" => "Novita".to_string(),
+            "google_ai_studio" => "GoogleAIStudio".to_string(),
             _ => {
                 // For other providers, use UpperCamelCase conversion
                 use convert_case::{Case, Casing};
@@ -173,6 +176,7 @@ impl std::str::FromStr for ProviderId {
             "codex" => ProviderId::CODEX,
             "fireworks-ai" => ProviderId::FIREWORKS_AI,
             "novita" => ProviderId::NOVITA,
+            "google_ai_studio" => ProviderId::GOOGLE_AI_STUDIO,
             // For custom providers, use Cow::Owned to avoid memory leaks
             custom => ProviderId(Cow::Owned(custom.to_string())),
         };
@@ -544,6 +548,7 @@ mod tests {
         assert_eq!(ProviderId::IO_INTELLIGENCE.to_string(), "IOIntelligence");
         assert_eq!(ProviderId::CODEX.to_string(), "Codex");
         assert_eq!(ProviderId::FIREWORKS_AI.to_string(), "FireworksAI");
+        assert_eq!(ProviderId::GOOGLE_AI_STUDIO.to_string(), "GoogleAIStudio");
     }
 
     #[test]
@@ -566,6 +571,14 @@ mod tests {
         assert!(built_in.contains(&ProviderId::CODEX));
         assert!(built_in.contains(&ProviderId::OPENAI_RESPONSES_COMPATIBLE));
         assert!(built_in.contains(&ProviderId::FIREWORKS_AI));
+        assert!(built_in.contains(&ProviderId::GOOGLE_AI_STUDIO));
+    }
+
+    #[test]
+    fn test_google_ai_studio_from_str() {
+        let actual = ProviderId::from_str("google_ai_studio").unwrap();
+        let expected = ProviderId::GOOGLE_AI_STUDIO;
+        assert_eq!(actual, expected);
     }
 
     #[test]

crates/forge_repo/src/provider/provider.json

@@ -1888,6 +1888,86 @@
     ],
     "auth_methods": ["google_adc"]
   },
+  {
+    "id": "google_ai_studio",
+    "api_key_vars": "GEMINI_API_KEY",
+    "url_param_vars": [],
+    "response_type": "Google",
+    "url": "https://generativelanguage.googleapis.com/v1beta",
+    "models": [
+      {
+        "id": "gemini-3.1-pro-preview",
+        "name": "Gemini 3.1 Pro Preview",
+        "description": "Most capable Gemini model with advanced reasoning",
+        "context_length": 1000000,
+        "tools_supported": true,
+        "supports_parallel_tool_calls": true,
+        "supports_reasoning": true,
+        "input_modalities": ["text", "image"]
+      },
+      {
+        "id": "gemini-3.1-flash-lite-preview",
+        "name": "Gemini 3.1 Flash Lite Preview",
+        "description": "Cost-efficient Gemini model optimized for high-volume, low latency use cases",
+        "context_length": 1000000,
+        "tools_supported": true,
+        "supports_parallel_tool_calls": true,
+        "supports_reasoning": true,
+        "input_modalities": ["text", "image"]
+      },
+      {
+        "id": "gemini-3-pro-preview",
+        "name": "Gemini 3 Pro Preview",
+        "description": "Advanced Gemini model with strong reasoning capabilities",
+        "context_length": 1000000,
+        "tools_supported": true,
+        "supports_parallel_tool_calls": true,
+        "supports_reasoning": true,
+        "input_modalities": ["text", "image"]
+      },
+      {
+        "id": "gemini-3-flash-preview",
+        "name": "Gemini 3 Flash Preview",
+        "description": "Fast Gemini model with thinking support",
+        "context_length": 1000000,
+        "tools_supported": true,
+        "supports_parallel_tool_calls": true,
+        "supports_reasoning": true,
+        "input_modalities": ["text", "image"]
+      },
+      {
+        "id": "gemini-2.5-pro",
+        "name": "Gemini 2.5 Pro",
+        "description": "Powerful Gemini model for complex tasks with thinking",
+        "context_length": 1000000,
+        "tools_supported": true,
+        "supports_parallel_tool_calls": true,
+        "supports_reasoning": true,
+        "input_modalities": ["text", "image"]
+      },
+      {
+        "id": "gemini-2.5-flash",
+        "name": "Gemini 2.5 Flash",
+        "description": "Fast and efficient Gemini model with thinking",
+        "context_length": 1000000,
+        "tools_supported": true,
+        "supports_parallel_tool_calls": true,
+        "supports_reasoning": true,
+        "input_modalities": ["text", "image"]
+      },
+      {
+        "id": "gemini-2.0-flash",
+        "name": "Gemini 2.0 Flash",
+        "description": "Fast and versatile Gemini model",
+        "context_length": 1000000,
+        "tools_supported": true,
+        "supports_parallel_tool_calls": true,
+        "supports_reasoning": false,
+        "input_modalities": ["text", "image"]
+      }
+    ],
+    "auth_methods": ["api_key"]
+  },
   {
     "id": "minimax",
     "api_key_vars": "MINIMAX_API_KEY",