Add function that generates a prompt asking the LLM to output a
WorkflowProposal JSON structure instead of a full workflow.
Key differences from buildQuickstartPrompt:
- Outputs reviewable proposal, not internal workflow state
- Focus on explaining purpose of each node
- Human-readable connection descriptions
- Simpler schema without positions or runtime data
- Includes complexity estimate and warnings
The prompt guides the LLM to create proposals that users can
review and modify before building the actual workflow.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Update API routes to fetch from nodebananapro.com
- Remove local workflow JSON files (now hosted on R2)
- Remove LFS tracking (.gitattributes)
- Remove local communityWorkflows.ts metadata (now on server)
- Add COMMUNITY_WORKFLOWS_API_URL env variable option
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
## Template Explorer Enhancements
- Add rich metadata and thumbnails for community workflows
- Create communityWorkflows.ts config for workflow metadata
- Reuse TemplateCard for community workflows with tag filtering
- Search now includes workflow descriptions
## Comment Navigation System
- Add comment navigation icon in header with unviewed count badge
- Navigate between nodes with comments using prev/next controls
- Tooltips show comment preview on hover
## Output Node Improvements
- Add custom filename and createDirectory options for output saves
- Remove default React Flow styling from output nodes
- Fix video output node connections
- Preserve node height on resize
## Image Handling Fixes
- Resolve image history race condition and duplicate images on save
- Preserve image history IDs when saving to new directory
- Verify outputImageRef matches selected history index on save
- Persist useExternalImageStorage setting in workflow config
- Paste images directly into selected imageInput nodes
## Model & Generation Fixes
- Use selectedModel.modelId for Gemini generation
- Return 200 with notFound flag instead of 404 for missing files
## Other
- Add git-lfs tracking for large workflow files
- Remove deprecated example workflows
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Change categories from product/style/composition to simple/advanced
- Add provider filter to sidebar (currently shows Gemini)
- Display provider tags on template cards
- Update tests for new category structure
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Replace model image with new model.png for the Model + Product template,
update the Style Transfer prompt to watercolor children's book style.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add template thumbnails to public/template-thumbnails/
- Add hover images for model-product and style-transfer templates
- Update TemplateCard to support hover image with opacity transition
- Replace street-scene.jpg with new-bg-model-product.png in model-product
- Replace house-lake.jpg with style-transfer-reference.png in style-transfer
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- 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
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>
- Changed DEFAULT_TTL from 10 minutes to 60 minutes
- Reduces API calls to provider model listing endpoints
- Models don't change frequently, longer TTL is appropriate
- Add isLoadingCarouselVideo state for loading indicator
- Add generationsPath from store for video loading
- Add loadVideoById callback to fetch videos from API
- Add carousel navigation handlers (handleCarouselPrevious/Next)
- Add hasCarouselVideos check for conditional display
- Add carousel UI with prev/next buttons and position indicator
- Add loading overlay during carousel navigation
- Update validation.ts with videoHistory fields
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Render dynamic input handles from model schema (GenerateImage/VideoNode)
- Update connection validation with getHandleType() helper
- Add dynamicInputs to getConnectedInputs() return value
- Pass dynamicInputs through generation pipeline (workflowStore -> API)
- Update generateWithFal/Replicate to use dynamic inputs
- Process large images in dynamicInputs to URLs for external providers
- Support prompt from dynamicInputs when top-level prompt is empty
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add ModelInput type for connectable inputs (image/text handles)
- Update model schema API to return both parameters and inputs
- Categorize properties: image inputs, text inputs, and parameters
- Sort inputs by required status and type
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Create /api/models/[modelId] endpoint for fetching model parameter schemas
- Add ModelParameter interface to lib/providers/types.ts
- Support both Replicate and fal.ai providers
- Filter out internal params, prioritize user-relevant ones
- 10-minute cache TTL for schema responses
Add GenerateVideoNode for video generation using Replicate and fal.ai:
- Add GenerateVideoNodeData interface with video output field
- Add generateVideo to NodeType union
- Create GenerateVideoNode component with provider/model selection
- Register in WorkflowCanvas with purple minimap color (#9333ea)
- Add default dimensions and node data creation in store
- Update validation.ts for new node type
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implement generation via fal.ai's fal.run API:
- POST to https://fal.run/{modelId} with prompt and parameters
- Use "Key {apiKey}" auth header (works without key but rate limited)
- Extract image URL from response (handles images array, image object, or output string)
- Fetch image and convert to base64 data URL
- Return GenerationOutput with type: "image"
Note: Image inputs skipped for now (Phase 5 adds URL server)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implement generation via Replicate's prediction API:
- POST to /predictions with model version and prompt
- Poll /predictions/{id} until succeeded/failed/canceled
- Fetch output image URL and convert to base64 data URL
- Return GenerationOutput with type: "image"
Note: Image inputs skipped for now (Phase 5 adds URL server)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Export cache utilities from provider index and add listAllModels/
searchAllModels helper functions for multi-provider operations.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add in-memory cache for provider model lists with 10-minute TTL.
Includes get/set/invalidate functions and cache key generation.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add defensive null checks before calling .map() on data.results
in both the API route and provider implementation. Returns empty
array with success:true when results is undefined, preventing
"Cannot read properties of undefined (reading 'map')" crash.
Fixes: UAT-001 from 02-01-ISSUES.md
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
fal.ai API only accepts a single category parameter, but we were
sending multiple categories. Now we fetch all active models and
filter client-side using the existing isRelevantModel() function.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implement ProviderInterface for fal.ai model marketplace:
- Model discovery via REST API (listModels, searchModels, getModel)
- Filter to relevant categories (text-to-image, image-to-image, text-to-video, image-to-video)
- Optional API key auth (works without key but with rate limits)
- Self-registration in provider registry on import
- Stub generate() for Phase 3 implementation
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Implement ProviderInterface for Replicate.com
- listModels() fetches from /v1/models endpoint
- searchModels() uses /v1/search endpoint
- getModel() retrieves single model by owner/name
- inferCapabilities() from model name/description
- Self-registers via registerProvider() on import
- API key read from localStorage provider settings
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add provider registry in src/lib/providers/index.ts:
- Export all types from types.ts
- providerRegistry for storing provider implementations
- registerProvider() for providers to self-register
- getProvider() to retrieve provider by type
- getConfiguredProviders() to get providers with API keys
- getAllProviders() to get all registered providers
Registry will be populated when provider modules are imported
in Phase 2 (Replicate and fal.ai implementations).
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add provider abstraction layer in src/lib/providers/types.ts:
- ProviderModel interface for normalized model metadata
- ModelCapability union type for model capabilities
- GenerationInput/GenerationOutput interfaces for unified I/O
- ProviderInterface contract for provider implementations
This establishes the interface contract that all providers
(Gemini, Replicate, fal.ai) will implement in Phase 2.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
New templates focused on practical image transformation workflows:
- Product Shot: Product + scene/environment
- Model + Product: Combine model, product, and scene
- Color Variations: Generate product color variants
- Background Swap: Place subject in new background
- Style Transfer: Apply style from one image to another
- Scene Composite: Combine elements from multiple scenes
Sample images added to public/sample-images/ including:
- Products: watches, shoes, cosmetics, sunglasses
- Models: 7 model photos for fashion workflows
- Scenes: street scenes, desert, architecture, nature
- Colors/Textures: paint, pastel, wall textures
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Empty level: all prompts empty, no images
- Minimal level: instructional prompts explaining each step
- Full level: complete example prompts with Unsplash sample images
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add welcome screen that appears on empty canvas with 6 preset templates
- Implement AI-powered workflow generation via Gemini LLM
- Create /api/quickstart endpoint for template and AI generation
- Add content level selector (empty/minimal/full)
- Add Quickstart button in Header for re-access when canvas has nodes
- Include JSON validation and repair utilities for LLM output
- Update CLAUDE.md with improved documentation
🤖 Generated with [Claude Code](https://claude.ai/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
shrimbly