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>
API: new testGeminiConnection adminProcedure
- Generates a simple test image via Gemini API
- Returns { ok, model } on success, { ok: false, error } on failure
- Audit logged: "Gemini test succeeded/failed"
UI: "Test Gemini" button next to "Save Image Settings"
- Only visible when Gemini provider is selected
- Shows green success or red error result below the buttons
- Displays the model name on success
Model: gemini-2.0-flash-preview-image-generation (correct name)
Co-Authored-By: claude-flow <ruv@ruv.net>
Schema:
- SystemSettings: geminiApiKey, geminiModel, imageProvider fields
- imageProvider: "dalle" (default) or "gemini"
Gemini Client (packages/api/src/gemini-client.ts):
- Direct HTTP call to Gemini REST API with responseModalities: [TEXT, IMAGE]
- Returns base64 data URL
- Error parsing with user-friendly messages
Router (project.ts):
- generateCover: routes to DALL-E or Gemini based on imageProvider setting
- New isImageGenConfigured query returning { configured, provider }
Admin UI (SystemSettingsClient.tsx):
- "Image Generation" section with provider radio buttons (DALL-E / Gemini)
- Conditional fields: DALL-E config or Gemini API key + model
- Separate save button for image settings
Security:
- geminiApiKey sanitized in audit logs (SENSITIVE_FIELDS)
- API key stored server-side only, never sent to client
Co-Authored-By: claude-flow <ruv@ruv.net>
- Add DALL-E cover art generation for projects (Azure OpenAI + standard OpenAI)
- CoverArtSection component with generate/upload/remove/focus-point controls
- Client-side image compression (10MB input → WebP/JPEG, max 1920px)
- DALL-E settings in admin panel (deployment, endpoint, API key)
- MCP assistant tools for cover art (generate_project_cover, remove_project_cover)
- Rename "Planarchy" → "plANARCHY" across all UI-facing text (13 files)
- Fix hardcoded canEdit={true} on project detail page — now checks user role
- Computation graph visualization (2D/3D) for calculation rules
- OG image and OpenGraph metadata
Co-Authored-By: claude-flow <ruv@ruv.net>
Hartmut