- Mark NanoBananaNode alias as deprecated with migration guidance
- Mark saveNanoBananaDefaults as deprecated with alternative
- ModelSearchDialog already has video capability badges and filtering
- Add inline validation for number/integer parameters with min/max bounds
- Show red border and error text for out-of-range values
- Clear parameters when switching provider or model (schemas differ)
- Validation shows specific constraints (Min/Max values, integer requirement)
- Add modelsFetchError state with retry button in GenerateImage/VideoNode
- Show clear errors when model list fails to load (API key issues, connection)
- Improve API route error messages to include model name
- Add rate limit handling (429) with user-friendly messages
- Parse provider-specific error responses for better detail
- Improve timeout message for video generation
- Include parameters in requestPayload for nanoBanana and generateVideo nodes
- Add logging for custom parameters in Replicate and fal.ai provider functions
- Parameters already spread via ...input.parameters in existing provider code
- Create ModelParameters component with collapsible UI
- Fetches schema from /api/models/{modelId} endpoint
- Renders appropriate inputs based on parameter type (string, number, boolean, enum)
- Add parameters field to NanoBananaNodeData and GenerateVideoNodeData
- Integrate into GenerateImageNode and GenerateVideoNode
- 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
Tasks completed: 3/3
- Update OutputNode for video detection and playback
- Connect generateVideo output to workflow pipeline
- Bug fix: create generateVideo node for video models in browser
SUMMARY: .planning/phases/06-video-and-polish/06-02-SUMMARY.md
- Check model capabilities when selecting from model browser
- Create generateVideo node for text-to-video or image-to-video models
- Create nanoBanana node for image generation models
- Pass selectedModel with provider, modelId, displayName to node
- Add generateVideo case to getConnectedInputs for downstream nodes
- Update output node execution to detect video content type
- Set video and contentType fields when receiving video content
- Enable Prompt -> GenerateVideo -> Output workflow pipeline
- Add video and contentType fields to OutputNodeData
- Detect video content from data URL prefix or contentType hint
- Render video element with controls, loop, muted autoplay
- Support both base64 data URLs and HTTP URLs for video
- Update lightbox to show video player in fullscreen
- Update placeholder text to 'Waiting for image or video'
- Added to TEXT_TARGET_OPTIONS for text-to-video
- Added to IMAGE_TARGET_OPTIONS for image-to-video
- Fixes UAT-001: node now accessible via connection menu
Extend /api/generate to support video output from Replicate and fal.ai:
- Detect video content type in Replicate response
- Handle fal.ai video.url field for video model responses
- Return video/videoUrl fields with contentType for videos
- Add generateVideo case to executeWorkflow and regenerateNode
- Handle large videos (>20MB) by returning URL directly
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
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>
Phase 06: Video & Polish
- 4 plans created (06-01 through 06-04)
- 11 total tasks defined
- Addresses ISS-001 (model parameter adaptation)
Plans:
- 06-01: GenerateVideo node with video model selector
- 06-02: Video playback in output node
- 06-03: Custom model parameters from provider schemas
- 06-04: Edge case handling and final polish
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Import uploadImageForUrl, shouldUseImageUrl, deleteImages from @/lib/images
- Process images for Replicate/fal providers before generation
- Small images (<256KB) use data URIs directly
- Large images converted to temporary URLs via /api/images/[id]
- Cleanup uploaded images in finally block (success or failure)
- Gemini path unchanged (handles base64 directly)
- Add image parameter to predictionInput when images array provided
- Log image input presence for debugging
- Uses 'image' param name (most common for img2img models)
Phase 05: Image URL Server
- 2 plans created
- 6 total tasks defined
- Request-scoped cleanup (no TTL) to prevent memory accumulation
- Ready for execution
- Extract last segment from model ID (e.g., "effects" from "kling-video/v1.6/pro/effects")
- Append as suffix if not already in name: "Kling 1.6 - effects"
- Helps differentiate model variants with same display name
- Show all capability badges (txt→img, img→img, txt→vid, img→vid)
- Display model ID below name to differentiate similar models
- Larger cover images (20x20 instead of 16x16)
- Taller cards with 3-line description (was 2)
- Better visual differentiation for fal.ai model variants
- Replicate's search API endpoint unreliable, use client-side filtering
- Always cache full model list for Replicate (not per-search-query)
- Apply search filter on cached models for faster subsequent searches
- Remove unused ReplicateSearchResponse and ReplicateSearchResult types
- Add ModelSearchDialog with search, provider filter, and capability filter
- Integrate with /api/models endpoint using API key headers
- Display model grid with cover images, provider badges, and descriptions
- Update addNode to accept optional initialData for pre-configured nodes
- Replace placeholder in FloatingActionBar with actual dialog
- Dialog opens when provider icon is clicked with provider filter in state
- Placeholder UI shows "Coming in 04-02" message
- Close button properly resets modelSearchOpen state
- Ready for 04-02 to implement full search functionality
- Add modelSearchOpen/modelSearchProvider state to workflowStore
- Add setModelSearchOpen action to toggle dialog with provider filter
- Add ProviderIconButton component with Replicate (R) and fal.ai (lightning) icons
- Replicate icon only visible when API key is configured
- fal.ai icon always visible (works without key but rate limited)
- Add useEffect to migrate legacy nodes without selectedModel on mount
- Derive selectedModel from model field for legacy workflows
- Ensures UI reflects correct provider/model for migrated nodes
- Add API key headers (X-Replicate-API-Key, X-Fal-API-Key) for external providers
- Include selectedModel in request payload for provider routing
- Update logging to show provider-specific info
- Apply same changes to regenerateNode for consistency
- Migrate nanoBanana nodes without selectedModel on workflow load
- Derive selectedModel from legacy model field (nano-banana, nano-banana-pro)
- Set provider to gemini and appropriate displayName for migrated nodes
Refactor generate API route to support multiple providers:
- Accept both legacy format and new format with selectedModel
- Route requests to Replicate, fal.ai, or Gemini based on provider
- Extract Gemini logic into generateWithGemini() helper function
- Add generateWithReplicate() and generateWithFal() server-side helpers
- Get provider API keys from request headers (X-Replicate-API-Key, X-Fal-API-Key)
- Preserve backward compatibility for existing Gemini-based workflows
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>
Video models were getting text-to-image capability by default.
Now properly detects video models (by keywords like video, animate,
motion, luma, kling, minimax) and only assigns video capabilities.
Both APIs return paginated results but we were only fetching page 1.
Now fetches up to 5 pages from Replicate (~125 models) and 10 pages
from fal.ai to get more complete model lists.
shrimbly