feat(gemini): update Gemini model types and implement rate limiting for free tier

- Changed Gemini model types to 'gemini-2.5-flash-lite', 'gemini-2.5-flash', and 'gemini-3-flash'.
- Introduced RPM limits for free tier models with a maximum of 10 RPM for 'gemini-2.5-flash-lite' and 5 RPM for the others.
- Added rate limiting enforcement in the GeminiAgent class, which waits based on the model's RPM limit.
- Updated getGeminiConfig to include billingEnabled setting, allowing users to skip rate limiting if billing is enabled.
- Modified ContextSettingsModal to reflect new model options and added a toggle for enabling billing.
- Updated default settings to use the new model and billing configuration.

src/shared/SettingsDefaultsManager.ts

@@ -20,7 +20,8 @@ export interface SettingsDefaults {
   // AI Provider Configuration
   CLAUDE_MEM_PROVIDER: string;  // 'claude' | 'gemini'
   CLAUDE_MEM_GEMINI_API_KEY: string;
-  CLAUDE_MEM_GEMINI_MODEL: string;  // 'gemini-2.0-flash-exp' | 'gemini-1.5-flash' | 'gemini-1.5-pro'
+  CLAUDE_MEM_GEMINI_MODEL: string;  // 'gemini-2.5-flash-lite' | 'gemini-2.5-flash' | 'gemini-3-flash'
+  CLAUDE_MEM_GEMINI_BILLING_ENABLED: string;  // 'true' | 'false' - skip rate limiting if billing enabled
   // System Configuration
   CLAUDE_MEM_DATA_DIR: string;
   CLAUDE_MEM_LOG_LEVEL: string;
@@ -57,7 +58,8 @@ export class SettingsDefaultsManager {
     // AI Provider Configuration
     CLAUDE_MEM_PROVIDER: 'claude',  // Default to Claude
     CLAUDE_MEM_GEMINI_API_KEY: '',  // Empty by default, can be set via UI or env
-    CLAUDE_MEM_GEMINI_MODEL: 'gemini-2.0-flash-exp',  // Default Gemini model
+    CLAUDE_MEM_GEMINI_MODEL: 'gemini-2.5-flash-lite',  // Default Gemini model (highest free tier RPM)
+    CLAUDE_MEM_GEMINI_BILLING_ENABLED: 'false',  // Rate limiting enabled by default for no-billing users
     // System Configuration
     CLAUDE_MEM_DATA_DIR: join(homedir(), '.claude-mem'),
     CLAUDE_MEM_LOG_LEVEL: 'INFO',