Prompt nodes now accept TXT, Markdown, and DOCX uploads while preserving the node contract as plain prompt text. The canvas preview shows imported Markdown as a lightweight document card, and DOCX extraction stays local to body text so generation inputs remain deterministic.
Constraint: Text-class nodes must still output plain text into existing workflow edges.
Rejected: Add a full document editor/parser layer | too broad for the requested node-level upload and preview behavior.
Confidence: high
Scope-risk: moderate
Directive: Keep uploaded document data normalized to prompt text unless downstream nodes explicitly gain rich document inputs.
Tested: npm run test:run -- src/components/__tests__/PromptNode.test.tsx src/components/modals/__tests__/MarkdownEditorModal.test.tsx src/utils/__tests__/textDocumentImport.test.ts --reporter=dot
Tested: npm run build
Tested: git diff --check
Not-tested: npm run lint still fails because Next 16 treats the existing next lint script as a /lint project path.
The accumulated fixes move the test build toward the current product shape: Popi models are the default provider surface, remote community workflow APIs are removed from the local template flow, media nodes expose accurate preview/preview-modal behavior, and Generate Video owns first-class duration, resolution, and sound defaults instead of burying those values in provider schemas.
The test suite was brought back in line with the product mode split: Popi provider mode is the default runtime, while multi-provider model search remains covered explicitly under multi mode.
Constraint: Product direction is canvas-owned workflow structure with Popi Models as the tested default provider path.
Rejected: Keep legacy community workflow API surface | user requested removing remote data paths and retaining local templates.
Rejected: Treat video duration/resolution/sound as hidden provider params | these are user-facing Generate Video controls.
Confidence: high
Scope-risk: broad
Directive: Do not reintroduce remote community template loading without a product decision on hosted templates and i18n ownership.
Tested: npm test -- --run src/store/utils/__tests__/nodeDefaults.test.ts src/store/execution/__tests__/generateVideoExecutor.test.ts src/components/__tests__/GenerateVideoNode.test.tsx src/components/__tests__/GenerationComposer.test.tsx
Tested: npm run build
Tested: npm test -- --run src/components/__tests__/ModelSearchDialog.test.tsx src/store/utils/__tests__/localStorage.test.ts
Tested: npm run test:run
Not-tested: Live provider generation calls against paid external APIs.
P0 regressions showed several workflow paths needed to stay visible and deterministic: language switching had a hardcoded composer label, Video Trim hid controls before media loaded, and media handoffs to LLM needed real canvas edges rather than implicit conversion. P1 fixes keep canvas-owned structure by adding explicit image/video LLM handles, audio composer validation, 3D output/file routing, and Chat proposal cards that require user apply before mutating nodes.
Constraint: User asked to stop new feature work and only repair P0/P1 product-fit gaps.
Rejected: Auto-convert image or video directly into text for LLM | hides workflow structure and violates the visible-node product model.
Rejected: Let Chat tool calls silently add or edit nodes | canvas structure must be previewed and explicitly applied.
Confidence: high
Scope-risk: moderate
Directive: Keep media transformations represented by visible handles, nodes, and edges; do not add silent Chat or media mutation paths without product review.
Tested: Browser automation for language switch, video input to Generate Video, prompt to Generate Video, LLM default model, Video Trim controls, and video media to LLM input.
Tested: npm run test:run -- src/components/__tests__/ConnectionDropMenu.test.tsx src/components/__tests__/GenerationComposer.test.tsx src/components/__tests__/VideoTrimNode.test.tsx src/components/__tests__/LLMGenerateNode.test.tsx src/store/execution/__tests__/llmGenerateExecutor.test.ts src/app/api/llm/__tests__/route.test.ts src/store/execution/__tests__/generateAudioExecutor.test.ts src/store/execution/__tests__/generate3dExecutor.test.ts src/store/execution/__tests__/simpleNodeExecutors.test.ts src/components/__tests__/OutputNode.test.tsx src/components/__tests__/Generate3DNode.test.tsx src/components/__tests__/ChatPanel.test.tsx src/lib/chat/tools.test.ts src/lib/chat/editOperations.test.ts src/lib/__tests__/llmModels.test.ts src/store/utils/__tests__/nodeDefaults.test.ts
Tested: npm run build
Tested: git diff --cached --check
Not-tested: npm run lint, because the existing script calls removed Next.js lint command and exits with invalid project directory /lint.
Not-tested: Live paid provider calls for LLM, audio, and 3D generation.
P0/P1 reports clustered around unavailable LLM defaults, video media connections, and missing controls on the generation surface. This routes the default NewApiWG LLM away from the unavailable Doubao channel, makes video a first-class schema and canvas connection type, carries request ids into node errors, and fills the composer, trim, audio, and 3D gaps without changing the canvas workflow model.
Constraint: NewApiWG Doubao channels are not reliably routed in the default gateway
Constraint: Video model schemas expose video fields that must not flow through image handles
Rejected: Continue accepting video through image handles | hides incorrect graph types and loses schema-specific dynamic inputs
Confidence: high
Scope-risk: moderate
Directive: Keep media handle types explicit; add schema mapping when adding a new connectable media type
Tested: npm run test:run -- src/store/execution/__tests__/generateVideoExecutor.test.ts src/store/utils/__tests__/connectedInputs.test.ts src/store/execution/__tests__/generateAudioExecutor.test.ts src/store/execution/__tests__/llmGenerateExecutor.test.ts src/store/__tests__/workflowStore.integration.test.ts src/lib/__tests__/llmModels.test.ts src/store/utils/__tests__/nodeDefaults.test.ts src/components/__tests__/GenerationComposer.test.tsx src/app/api/chat/__tests__/route.test.ts src/app/api/llm/__tests__/route.test.ts src/app/api/models/[modelId]/__tests__/route.test.ts src/app/api/generate/providers/__tests__/newapiwg.test.ts
Tested: npm run build
Tested: git diff --check
Not-tested: npm run lint | package script calls removed Next 16 next lint command
Not-tested: npx tsc --noEmit | existing test type errors remain; changed runtime files filtered clean
Browser-local projects cannot load node carousel history through the server-side generations API. Each new image history entry now keeps the generated data URL for immediate in-session switching, while server-backed projects can still fall back to loading by generation id. Browser-local generation paths also skip /api/save-generation because that endpoint can only write server filesystem paths.
Constraint: Project storage can be browser-local and therefore unavailable to server filesystem APIs.
Rejected: Force carousel switching through /api/load-generation | browserfs paths cannot be resolved by the server and cause switching failures.
Confidence: high
Scope-risk: narrow
Directive: Keep carousel history able to switch without server round-trips when images were generated in the current session.
Tested: npm test -- --run src/components/__tests__/GenerateImageNode.test.tsx src/store/execution/__tests__/nanoBananaExecutor.test.ts
Tested: npx tsc --noEmit --pretty false filtered to changed production files
Provider video URLs can expire before users finish composing, and the bottom composer was too visually dominant for canvas work. This change keeps remote videos playable while background-localizing them, teaches video previews to use the media proxy, makes audio nodes first-class in the composer and executor, and adds a compact composer state for canvas visibility.
Constraint: Provider media URLs may be remote, signed, or CORS-restricted during playback and thumbnail extraction
Constraint: Audio generation nodes need to work from their internal prompt as well as connected text
Rejected: Store only provider URLs | remote URLs can expire and break later playback
Rejected: Treat audio nodes as unsupported composer nodes | it falls back to the image model and corrupts user intent
Confidence: high
Scope-risk: moderate
Reversibility: clean
Directive: Keep provider media playable through the resolver/proxy path and preserve local refs as the durable source when available
Tested: npm run test:run
Tested: npm run test:run -- src/components/__tests__/GenerationComposer.test.tsx src/store/execution/__tests__/generateAudioExecutor.test.ts src/store/execution/__tests__/generateVideoExecutor.test.ts src/components/__tests__/VideoStitchNode.test.tsx src/components/__tests__/GenerateVideoNode.test.tsx
Tested: npm run build
Not-tested: npm run lint currently fails because next lint is not supported by this Next.js setup
Not-tested: npx tsc --noEmit still reports pre-existing test typing errors outside this change
The bottom composer now edits and reruns the current generation node while canvas-visible actions own downstream node creation. NewApiWG media normalization, video frame extraction, and node quick-add keep generated media flows explicit and connected rather than hidden behind the prompt box.
Constraint: Composer must not call providers directly or create hidden downstream branches when a node is selected
Constraint: NewApiWG video families use inconsistent media schemas, so common media aliases are normalized in the provider adapter
Rejected: Let the bottom composer create next-step nodes from selected outputs | hides graph mutation and conflicts with the PRD source-of-truth rules
Rejected: Put NewApiWG model-family payload rules in the composer | provider-specific schemas would leak into UI state
Confidence: high
Scope-risk: moderate
Directive: Keep provider payload normalization in provider/executor layers; do not move it into GenerationComposer
Tested: npm run test:run -- src/components/__tests__/GenerationComposer.test.tsx
Tested: npm run test:run -- src/components/__tests__/WorkflowCanvas.test.tsx
Tested: npm run test:run -- src/components/__tests__/GenerateVideoNode.test.tsx
Tested: npm run test:run -- src/app/api/generate/providers/__tests__/newapiwg.test.ts src/app/api/generate/__tests__/route.test.ts
Tested: npm run test:run -- src/store/execution/__tests__/videoProcessingExecutors.test.ts
Tested: npm run build
Not-tested: npm run lint fails because next lint is incompatible with the current Next 16 script configuration
NewApiWG image and video models need to work against the PopiArt test gateway, with generated remote media visible in the canvas and UI text localized for Chinese users. This wires the gateway-specific image/video paths, model fallback display, remote media proxying, and related i18n cleanup into one releaseable change.
Constraint: Test gateway exposes image and video models through mixed OpenAI-compatible and Gemini-native response shapes
Constraint: Browser video playback can fail when loading signed third-party media URLs directly
Rejected: Keep remote video URLs as direct <video> sources | CORS and range handling made successful generations appear unloaded
Confidence: high
Scope-risk: moderate
Directive: Do not remove the media proxy without validating remote video playback, trimming, and stitching against signed CDN URLs
Tested: npm run build
Tested: npx vitest run src/components/__tests__/OutputNode.test.tsx src/components/__tests__/GenerateVideoNode.test.tsx src/components/__tests__/VideoStitchNode.test.tsx
Tested: npx vitest run src/components/__tests__/WorkflowCanvas.test.tsx src/store/execution/__tests__/generateVideoExecutor.test.ts
Tested: npx vitest run src/app/api/generate/providers/__tests__/newapiwg.test.ts
Not-tested: Live browser replay after pushing to remote deployment
Resolve conflicts in 4 executor files by combining develop's
runWithFallback structure with feature branch's client-side polling.
Both capabilities are now integrated: executors use runWithFallback
for model redundancy, and pollGenerateTask for long-running Kie tasks.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Restore FTUX production logic (remove testing override)
- Fix generate3dExecutor clearOutput field and add modelId validation
- Remap startLevel index after loop partitioning in executeWorkflow
- Add missing mockTutorialExecution dep in FloatingActionBar
- Reset settingsTab to "primary" when fallbackModel is removed
- Clear orphaned fallbackParameters when removing fallback model
- Fix OutputGalleryNode removeMedia to splice single item, not all duplicates
- Add data-tutorial="save-button" to untitled save button in Header
- Move data-tutorial to layout-producing element in BaseNode
- Hydrate FTUXApiKeysStep localKeys from providerSettings
- Remove broken docs URL from ftuxStore tutorial steps
- Add error handling in loadTutorialSampleImage
- Fix mediaStorage ref array misalignment in outputGallery hydration
- Make OutputGalleryNodeData.videos optional to match usage
- Remove unused fitView destructuring from WorkflowCanvas
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Adds SettingsTabBar to LLMGenerateNode with temperature and max tokens
controls for the fallback model. Updates llmGenerateExecutor to use
fallbackParameters override when running the fallback model.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Adds fallbackParameters?: Record<string, unknown> to NanoBananaNodeData,
GenerateVideoNodeData, Generate3DNodeData, and GenerateAudioNodeData so
fallback models can have their own parameter configurations.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Introduces a shared runWithFallback helper that wraps primary model
attempts with an optional fallback. On primary failure (non-abort),
the fallback runs once and metadata is stamped on the node so the UI
can render a "Fallback used" badge. Fallback is skipped when primary
and fallback resolve to the same provider/model to avoid double-billing.
Wired through all generation executors (nanoBanana, generateVideo,
generateAudio, generate3d, llmGenerate) with accompanying tests.
JSON-compatible with Node Banana Pro: fallbackModel and __-prefixed
metadata fields match NBP's shape for clean config round-trips.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
The video stitch node was only copying video tracks from source clips,
silently discarding any embedded audio. Now extracts and concatenates
audio from source videos when no external audio node is connected.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
When batch mode is enabled on an array node, all parsed items are sent
through a single connection to a downstream generate node, which loops
through them sequentially. This eliminates the need to create separate
downstream nodes for each array item.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Add "audio-to-video" to ModelCapability union, extend ModelInput.type
and ModelInputDef.type with "audio", and include "audio-to-video" in
fal.ai RELEVANT_CATEGORIES for model discovery.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds a new videoInput node type that allows users to drag-and-drop or
browse for video files (MP4, WebM, QuickTime), preview them inline with
native video controls, and feed them into downstream video processing
nodes. Includes full media externalization/hydration support, Shift+Y
keyboard shortcut, and ConnectionDropMenu integration.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add audioFileRef, imageARef, imageBRef, and capturedImageRef fields
to AudioInputNodeData, ImageCompareNodeData, and GLBViewerNodeData
to support external media storage optimization.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Add `isOptional?: boolean` to ImageInputNodeData, AudioInputNodeData,
and PromptNodeData. Add "skipped" to NodeStatus union type to support
skip propagation in the execution engine.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Store measured settings panel height in node data (_settingsPanelHeight).
On workflow load, subtract it from persisted height so BaseNode's expand
effect re-adds the real panel height from a clean baseline instead of
double-counting.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add parametersExpanded field to 5 generation node data types (NanoBanana, GenerateVideo, Generate3D, GenerateAudio, LLMGenerate)
- Create useInlineParameters hook for localStorage-backed global setting (default: false)
- Create InlineParameterPanel component with collapsible UI and chevron toggle
- All TypeScript compiles without new errors
Adds an evaluationPaused flag that lets users reset evaluation state
and un-dim all downstream paths. The flag auto-resets on workflow
execution or manual rule edits.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Nano Banana 2 (gemini-3.1-flash-image) supports a new searchTypes API
that allows enabling web search and image search independently. This adds
a useImageSearch toggle visible only for Nano Banana 2, while keeping the
existing Google Search toggle using the legacy format for Nano Banana Pro.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add MatchMode type (exact, contains, starts-with, ends-with)
- Add ConditionalSwitchRule interface with id, value, mode, label, isMatched
- Add ConditionalSwitchNodeData interface with incomingText and rules array
- Add conditionalSwitch to NodeType union (after switch)
- Add ConditionalSwitchNodeData to WorkflowNodeData union
- Add default data with single rule (mode: contains, empty value)
- Add default dimensions (260x180, wider than Switch for mode dropdown)
- Add executeConditionalSwitch passthrough executor
- Add conditionalSwitch to VALID_NODE_TYPES in validation
- Export ConditionalSwitchNode from components index (component created in next task)
- Add "switch" to NodeType union in types/nodes.ts
- Create SwitchNodeData interface with inputType and switches array
- Add SwitchNodeData to WorkflowNodeData union
- Register switch dimensions (220x120) in nodeDefaults.ts and validation.ts
- Add createDefaultNodeData case with single default switch
- Implement executeSwitch passthrough executor in simpleNodeExecutors.ts
- Add SwitchNode export to components/nodes/index.ts
- Add switch dimensions to WorkflowCanvas.tsx default dimensions map
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add 'router' to NodeType union in types/nodes.ts
- Add RouterNodeData interface (extends BaseNodeData, no internal state)
- Add RouterNodeData to WorkflowNodeData union
- Add router dimensions (200x80) to nodeDefaults.ts and validation.ts
- Add router default data (empty object) to both files
- Add executeRouter pure passthrough function to simpleNodeExecutors.ts
- Add RouterNode export to components/nodes/index.ts
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add 'videoFrameGrab' to NodeType union and VideoFrameGrabNodeData interface
- Register default dimensions (320x320) and default data in nodeDefaults
- Wire getSourceOutput to return image type from videoFrameGrab.outputImage
- Add videoFrameGrab dimensions to local Record types in WorkflowCanvas and validation
- Add 'videoTrim' to NodeType union and VideoTrimNodeData interface in nodes.ts
- Add VideoTrimNodeData to WorkflowNodeData union
- Add default dimensions (360x360) and default data to nodeDefaults.ts
- Create useTrimVideo.ts hook with MediaBunny frame-by-frame trim + audio preservation
- Add getSourceOutput case for videoTrim in connectedInputs.ts
- Add executeVideoTrim executor to videoProcessingExecutors.ts
- Wire 'videoTrim' case into executeNode.ts dispatcher
- Fix duplicate Record<NodeType> dimensions in WorkflowCanvas.tsx and validation.ts
Add audio support to the Output node so GenerateAudio can pipe audio
through for playback and download. Adds audio input handle, <audio>
player, audio→output connection validation, and executeOutput audio
handling.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
TianYun
huangmin
宋向航