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/assistant-tools.ts

@@ -1020,7 +1020,7 @@ export const TOOL_DEFINITIONS: ToolDef[] = [
     type: "function",
     function: {
       name: "generate_project_cover",
-      description: "Generate an AI cover art image for a project using DALL-E. The image will be stored as the project's cover. Requires manageProjects permission and DALL-E to be configured.",
+      description: "Generate an AI cover art image for a project. Uses the configured image provider (DALL-E or Google Gemini). The image will be stored as the project's cover. Requires manageProjects permission.",
       parameters: {
         type: "object",
         properties: {