- Use multipart/form-data for file upload with 'file' and 'uploadPath' fields
- Extract download URL from data.downloadUrl in upload response
- Wrap parameters in 'input' object for standard models
- Use flat structure with camelCase for Veo models
- Extract results from resultJson.resultUrls in poll response
Co-Authored-By: Claude <noreply@anthropic.com>
- Add Kie.ai section in provider settings with API key input
- Add kie to env-status API for .env detection
Co-Authored-By: Claude <noreply@anthropic.com>
Add Kie.ai as a new provider for image and video generation:
Image models (8):
- z-image, seedream/4.5-text-to-image, seedream/4.5-edit
- nano-banana-pro, gpt-image/1.5-text-to-image, gpt-image/1.5-image-to-image
- google/nano-banana, google/nano-banana-edit
Video models (11):
- sora-2-text-to-video, sora-2-image-to-video
- sora-2-pro-text-to-video, sora-2-pro-image-to-video
- veo3_fast, veo3, bytedance/seedance-1.5-pro
- kling-2.6/text-to-video, kling-2.6/image-to-video
- wan/2-6-text-to-video, wan/2-6-image-to-video
Key changes:
- Add "kie" to ProviderType union
- Add generateWithKie() with image upload and task polling
- Add hardcoded model list and schemas (no discovery API)
- Update workflow store for API key handling
- Update UI components with Kie provider badge
Co-Authored-By: Claude <noreply@anthropic.com>
Rewrite chat system prompt to be concise — bullet points over
paragraphs, 2-4 sentences per response. Make chat panel stretch
from top-16 to bottom-[220px] for near-full canvas height.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Import convertToModelMessages and UIMessage from ai
- Convert incoming messages for useChat hook compatibility
- Return toUIMessageStreamResponse() instead of toTextStreamResponse()
- POST /api/chat with Vercel AI SDK streamText
- Node Banana domain expertise in system prompt
- Conversational workflow planning assistant
- Uses createGoogleGenerativeAI with GEMINI_API_KEY
Add POST endpoint that generates WorkflowProposal JSON from a description:
- Validates description (min 3 chars)
- Calls Gemini with buildProposalPrompt
- Parses JSON with repair logic from validation.ts
- Validates response matches WorkflowProposal structure
- Returns { success: true, proposal } or { success: false, error }
Uses same patterns as /api/quickstart:
- maxDuration = 60
- Temperature 0.3 for consistent output
- Request ID logging
- Rate limit (429) handling
- gemini-3-flash-preview model
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Remove configurable COMMUNITY_WORKFLOWS_API_URL env var that caused
errors when users copied the placeholder from .env.example.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Validate presigned URLs before fetching by checking:
- Protocol is https
- Hostname ends with .r2.cloudflarestorage.com
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Update the community workflow API to fetch presigned URLs from
node-banana-pro, then download workflows directly from R2. This
avoids timeouts when fetching large workflow files (275MB+).
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>
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>
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
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>
- 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.
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>
- 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)
Add tests verifying the parameters field (UI settings) is passed to
provider APIs:
- Replicate: parameters passed to prediction input
- Replicate: dynamicInputs take precedence when merging
- fal.ai: parameters passed to request body
- fal.ai: dynamicInputs take precedence when merging
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add comprehensive tests for /api/models route covering:
- Basic functionality: fal.ai without key, both providers with keys
- Provider filtering by query param
- Capabilities filtering
- Search query param (client-side for Replicate, server-side for fal.ai)
- Caching behavior: cache hits, cache misses, refresh bypass
- Error handling: partial provider failures, all providers failing
- Pagination for both Replicate and fal.ai (max 15 pages)
- Capability inference for Replicate models (video keywords, i2v keywords)
- fal.ai category mapping to ModelCapability
- Model sorting by provider then name
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add comprehensive tests for /api/generate fal.ai path:
- Image generation success (images array response)
- Video generation success (video object response)
- Works without API key (unauthenticated allowed)
- Rate limit (429) handling with and without key
- Various response formats (image, images, video, output)
- Large video (>20MB) returns URL instead of base64
- Empty dynamicInputs values are filtered
- Dynamic inputs passed to fal.ai request
- Environment variable API key fallback
- Error response formats (error.message, detail array)
- No media URL in response handling
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add comprehensive tests for /api/generate Replicate path:
- Image generation success with API key header
- Video generation success
- 401 when API key missing
- Rate limit (429) handling
- Prediction failure handling
- Prediction timeout (5 min max)
- Polling for prediction completion
- Large video (>20MB) returns URL instead of base64
- Dynamic inputs passed to prediction
- Environment variable API key fallback
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add tests for input validation and edge cases:
- Reject requests with no prompt, images, or dynamic inputs
- Accept image-to-image (images only, no prompt)
- Accept dynamicInputs with prompt, image frames, and image_url
- Handle multiple images in request
Add provider routing tests:
- Route to Gemini when no selectedModel provided
- Route to Gemini when selectedModel.provider is gemini
- Return 401 for Replicate without API key
Add response handling tests:
- Verify proper response structure
- Handle default MIME type fallback
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add comprehensive tests for /api/generate route covering Gemini path:
- Success with prompt only and with images
- Config options (aspectRatio, resolution, googleSearch)
- Model mapping (nano-banana, nano-banana-pro)
- API key handling (env var vs header)
- Error cases (missing key, rate limits, no candidates, text-only response)
- MIME type extraction from data URLs
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Tests Google/Gemini provider path covering success, validation, rate limits,
and API error handling. Uses vi.hoisted for proper mock class constructor.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Always render image/text handles with placeholders for unused inputs
- Placeholder handles (dimmed 30%) preserve connections for models that
don't use that input type (e.g., text-to-image models)
- Normalize dynamic handle IDs to standard values (image, text, image-0)
- Update findCompatibleHandle to return normalized IDs
- Map normalized handles to schema names in getConnectedInputs
- Exclude image_size from image input detection
- Switch save-generation to hash suffix format for better readability
Co-Authored-By: Claude <noreply@anthropic.com>
- Add MD5 hashing of buffer content for deduplication
- Check for existing file by hash prefix before saving
- Use hash-prefixed filenames: {hash}_{prompt}.{ext}
- Add isDuplicate field to response JSON
- Log deduplication events for observability
- Fix isImageInput() to use word-boundary checks instead of substring
matching, preventing num_images from being misclassified as image input
- Fix stale node data in workflow execution by getting fresh data from
store instead of using captured array references
- Add missing parameters to regenerateNode request bodies for both
nanoBanana and generateVideo nodes
- Update fal.ai schema fetch to use Model Search API endpoint
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Group file operations (save, open folder) together with subtle separator
- Separate settings button with visual spacing
- Add hover background states to icon buttons for better interactivity
- Improve unsaved indicator with ring outline for better visibility
- Use consistent padding (p-1.5) and rounded corners
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add support for multiple file extensions (png, jpg, jpeg, webp, gif, mp4, webm, mov)
- Search for file by ID with any supported extension
- Return appropriate MIME type based on actual file extension
- Return video field for video files, image field for image files
- Include contentType field in response to indicate type
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Updated .env.example to include new API keys for OpenAI, Replicate, and fal.ai.
- Modified API routes to prioritize user-provided API keys over environment variables for Gemini and OpenAI.
- Improved error messages for missing API keys to guide users on configuration.
- Enhanced ProjectSetupModal to support OpenAI provider and manage API key overrides.
- Updated workflow store to handle new provider settings and API key integration for OpenAI.
- Added functionality to auto-save generated images and videos to the specified directory.
- Introduced a model search dialog for selecting external models in GenerateImageNode and GenerateVideoNode.
- Updated node titles to reflect selected models dynamically.
- Improved parameter handling by expanding the ModelParameters component to notify parent nodes on schema load.
- Adjusted handle positions and styles for better alignment and visual consistency.
- Enhanced input validation and processing for dynamic inputs across the workflow.
- Handle colors: cyan (#22d3ee) for image, magenta (#d946ef) for text
- Labels positioned outside node boundary (left of inputs, right of outputs)
- Label text color matches handle color
- Inputs sorted: image handles at top, text handles at bottom
- Visual gap between image and text input groups
- Added CSS variables for handle colors (used by label styling)
- Output handles also have colored labels (Video/Image)
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>
- Use 'models' array instead of 'data' array
- Iterate paths to find POST endpoint (not always at '/')
- Resolve $ref schema references from components.schemas
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The previous /api endpoint returned 404 for all models. Now using
the correct Model Search API with OpenAPI expansion:
GET https://api.fal.ai/v1/models?endpoint_id={modelId}&expand=openapi-3.0
Also added fallback path traversal for alternate OpenAPI structures.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Many fal.ai models don't expose OpenAPI schemas at /api endpoint.
Return empty parameters instead of error so generation still works
and UI doesn't show error message.
- 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
lapoaiscalers