- Update test data to use new multi-provider interface fields
- Add test for unknown pricing indicator
- Remove resolution-specific test that no longer applies
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Card layout with 48x48 icon area
- Template name and 2-line description with line-clamp
- Node count badge and category badge with color coding
- Tag pills display (max 4 shown)
- Loading state with spinner animation
- Disabled state with reduced opacity
- Hover states for interactive feedback
- Update calculatePredictedCost to produce CostBreakdownItem[] format
- Add unknownPricingCount to return value (was missing)
- CostDialog already using modelName property
- Add TemplateMetadata interface with nodeCount, category, tags, previewImage
- Add TemplateCategory type (product, style, composition, community)
- Update PresetTemplate interface with category and tags fields
- Add category and tags to all 6 preset templates
- Add getTemplateMetadata() to extract node count from workflow
- Add getPresetWithMetadata() to get template with full metadata
- Update getAllPresets() to include category and tags in return type
Phase 25: Template Explorer UI
- 2 plans created
- 5 total tasks defined
- Ready for execution
Plan 01: Template types, TemplateCard, grid layout (3 tasks)
Plan 02: Sidebar filters, WelcomeModal integration (2 tasks + checkpoint)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add fetchFalPricing() to batch-fetch pricing from fal.ai API:
- GET /v1/models/pricing?endpoint_id={ids}
- Maps "image" unit -> per-run, others -> per-second
- Best-effort: errors logged but don't fail model fetching
Pricing is merged into ProviderModel after fetching fal.ai models.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add pricing field to GEMINI_IMAGE_MODELS array:
- nano-banana: $0.039 per-run
- nano-banana-pro: $0.134 per-run
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The aspectRatio, resolution, and useGoogleSearch controls were only
shown when isGeminiOnly was true, but that was always false since
fal.ai is always available. Now these controls show based on whether
the currently selected model is a Gemini model.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When connecting to nodes with multiple input handles of the same type,
now finds the first unoccupied handle instead of always targeting the
first one. Returns null if all handles are occupied.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The generateVideo node type was missing from imageStorage.ts, causing
input images to be saved as new files on every workflow save instead
of being deduplicated via refs.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Security & API route fixes:
- Remove API key query param support in fal/models route to prevent credential leakage
- Fix MIME type fallback in save-generation route (now uses prefix-based fallback: image/* -> png, video/* -> mp4, unknown -> bin)
- Add timeout (60s) and size limits (500MB) for remote fetch in save-generation route using AbortController
CSS fix:
- Consolidate duplicate :root blocks in globals.css
- Change handle selector from data-handletype="prompt" to data-handletype="text"
- Update --handle-color-text CSS variable from #a3a3a3 to #3b82f6
Test file global mock isolation:
- Fix useAnnotationStore mock to support Zustand selector pattern
- Use vi.stubGlobal() instead of direct global assignments to prevent test leakage
- Restore global.Image in afterAll hook in AnnotationModal.test.tsx
- Wrap async Done assertion in waitFor() in AnnotationModal.test.tsx
- Use idiomatic fireEvent.dragOver() in AnnotationNode.test.tsx
- Fix global.confirm stub with proper beforeAll/afterAll lifecycle in CostDialog.test.tsx
- Import ReactNode type properly in EdgeToolbar.test.tsx
- Update save-generation route test to expect AbortController signal in fetch call
- Add Multi-Provider Support (Beta) section for Replicate and fal.ai
- Update Tech Stack and Environment Variables with new providers
- Add docs link to welcome modal (https://node-banana-docs.vercel.app/)
- Remove debug console.log statements from gridSplitter and WorkflowCanvas
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Fixes issues with external provider models (e.g., seedream-4.5) where:
- Boolean/integer params with "image" in name were misclassified as image inputs
- Array params without items.type specification were incorrectly rejected
- Handle ID mismatch between node components (image-0) and store (image)
- dynamicInputs not passed to API in node regeneration code path
Changes:
- Update isImageInput() to check schema types, not just names
- Map both indexed (image-0) and legacy (image) handle IDs to schema names
- Add dynamicInputs to nanoBanana regeneration request body
- Add hidden backward-compat handles for edge routing
- Add comprehensive tests for schema classification and handle mapping
- Fix Toast test to use specific selector for close button
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
These planning phase documents are local development artifacts
that don't need to be shared in the repo. They remain in .gitignore.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Create server.js with extended requestTimeout (10 min) for long-running fal.ai video generation
- Update package.json dev script to use custom server
- Add comments explaining why queue API is not used (file size limitations)
- Use WHATWG URL API instead of deprecated url.parse()
- Added support for long-running video generation using a queue system with a 10-minute timeout.
- Updated maxDuration constant to reflect the new timeout for video generation.
- Enhanced API request handling to accommodate video generation, including error handling and polling for completion.
- Updated model retrieval tests to reflect the inclusion of additional models and improved provider filtering.
- Modified component tests to track model usage and reflect changes in the UI for provider selection.
- Image data flow through node chains (imageInput, annotation, nanoBanana)
- Text data flow through node chains (prompt, llmGenerate)
- Dynamic inputs from schema-mapped connections
- State updates during execution (status, outputImage)
- Mixed image and text data flow
The open project button was only visible for unsaved projects. Now it
displays in both states so users can always load a different project.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When providers like fal.ai or Replicate expect array parameters (e.g.,
image_urls), single values from dynamicInputs are now automatically
wrapped in arrays based on the OpenAPI schema's type property.
Changes:
- Add isArray field to ModelInput type for schema detection
- Update getFalInputMapping() to return schemaArrayParams
- Update getInputMappingFromSchema() to return schemaArrayParams
- Apply array wrapping in both fal.ai and Replicate handlers
- Add tests for array wrapping behavior
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Phase 20: Integration Tests
- 2 plans created
- 6 total tasks defined
- Tests cover getConnectedInputs, validateWorkflow, topological sort,
data flow, error handling, and connection validation
- Ready for execution
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add provider icons (Gemini, Replicate, fal.ai) as filter buttons
- Replace dropdown with horizontal icon button group
- Add green badge color for Gemini provider
- Add 'Recently Used' section at top of model list
- Filter recent models by capability (image/video)
- Show max 4 recent models with cover images
- Track model usage via trackModelUsage on selection
- Add getProviderDisplayName helper for consistent naming
Phase 19 complete. All types now organized into 7 domain files:
annotation, nodes, providers, models, workflow, api, quickstart.
index.ts is a pure re-export hub.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add GEMINI_IMAGE_MODELS constant with nano-banana and nano-banana-pro
- Update GET handler to include Gemini models in response
- Support provider=gemini filter (returns only Gemini models)
- Gemini models appear first in 'all providers' results
- No API key needed for Gemini (always available)
Create api.ts with GenerateRequest, GenerateResponse, LLMGenerateRequest,
LLMGenerateResponse. Move RecentModel to providers.ts. Convert index.ts
to pure re-export hub with no type definitions.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
shrimbly