fix: correct Gemini model names + add model dropdown

Corrected model names (per Google AI docs):
- gemini-2.5-flash-image (was gemini-2.0-flash-preview-image-generation)
- gemini-3-pro-image-preview (Nano Banana Pro)
- gemini-3.1-flash-image-preview (Nano Banana 2)

UI: replaced text input with dropdown selector showing all 3 models
with human-readable descriptions.

Default changed to gemini-2.5-flash-image (fast, high-volume).

AI Assistant: generate_project_cover tool description updated to be
provider-agnostic (works with both DALL-E and Gemini).

Co-Authored-By: claude-flow <ruv@ruv.net>

packages/api/src/router/settings.ts

@@ -57,7 +57,7 @@ export const settingsRouter = createTRPCRouter({
       azureDalleEndpoint: settings?.azureDalleEndpoint ?? null,
       hasDalleApiKey: !!settings?.azureDalleApiKey,
       // Gemini
-      geminiModel: settings?.geminiModel ?? "gemini-2.0-flash-preview-image-generation",
+      geminiModel: settings?.geminiModel ?? "gemini-2.5-flash-image",
       hasGeminiApiKey: !!settings?.geminiApiKey,
       // Image provider
       imageProvider: settings?.imageProvider ?? "dalle",
@@ -331,7 +331,7 @@ export const settingsRouter = createTRPCRouter({
 
     try {
       const { generateGeminiImage } = await import("../gemini-client.js");
-      const model = settings.geminiModel ?? "gemini-2.0-flash-preview-image-generation";
+      const model = settings.geminiModel ?? "gemini-2.5-flash-image";
 
       // Generate a tiny test image with a simple prompt
       const dataUrl = await generateGeminiImage(