Vidu rejects generic video reference payloads, while the canvas preview also needs to keep long prompt text inside the prompt node bounds. This keeps provider-specific video reference fields for Vidu and constrains long prompt previews without changing the Seedance media field mapping.
Constraint: Vidu/NewApiWG expects reference_video_urls for video-reference generation.
Rejected: Change all video providers to reference_* fields | Seedance has existing coverage and logs using generic images/videos/audios.
Confidence: high
Scope-risk: narrow
Directive: Do not collapse Vidu video references back to videos without validating against the gateway schema.
Tested: npm run test:run -- src/app/api/generate/providers/__tests__/newapiwg.test.ts src/components/__tests__/PromptNode.test.tsx
Tested: git diff --check
Tested: npm run build
Not-tested: Real Vidu generation, to avoid consuming account points.
Local reference images were reaching the gateway as localhost URLs, and selected image/video nodes still exposed duplicate inline settings while the composer is the active control surface. This keeps gateway media inputs self-contained, maps GPT Image 2 sizes from the actual aspect ratio controls, and keeps node bodies focused on preview/output state.
Constraint: NewApiWG upstream cannot fetch browser-local /api/images URLs.
Constraint: Selected-node composer owns image and video generation controls.
Rejected: Keep localhost reference URLs | remote gateway requests cannot dereference local browser routes.
Rejected: Keep duplicate inline settings | it creates conflicting controls with the composer.
Confidence: high
Scope-risk: moderate
Directive: Do not send /api/images temporary URLs to NewApiWG upstream; resolve them to data URLs before provider calls.
Tested: npm run test:run -- src/app/api/generate/providers/__tests__/newapiwg.test.ts src/app/api/generate/__tests__/route.test.ts src/components/__tests__/GenerateImageNode.test.tsx src/components/__tests__/GenerateVideoNode.test.tsx src/components/__tests__/PromptNode.test.tsx src/lib/__tests__/llmModels.test.ts src/store/__tests__/workflowStore.integration.test.ts
Tested: npm run build
Tested: git diff --check
Not-tested: npm run lint still fails because next lint resolves to a nonexistent lint directory under Next 16.
The image-count pricing regression was passing an override into a helper that ignored it, so the test exercised the one-image default while expecting the four-image total. This makes the fixture accept the same node data overrides as the lower-level image node factory without touching production pricing logic.
Constraint: Remote master already contains the UI change that hides unimplemented image toolbar actions.
Rejected: Change GenerationComposer point calculation | the failing evidence showed draft.imageCount was never set by the fixture.
Confidence: high
Scope-risk: narrow
Tested: npm run test:run -- src/components/__tests__/ImageInputNode.test.tsx src/app/api/generate/providers/__tests__/newapiwg.test.ts src/app/api/points/estimate/__tests__/route.test.ts src/components/__tests__/GenerationComposer.test.tsx src/store/execution/__tests__/generateVideoExecutor.test.ts
Tested: npm run build
Tested: git diff --check
Popi/NewAPIWG is now the primary gateway, so the UI and request paths need to avoid legacy provider assumptions while keeping local reference media usable for upstream calls. This change aligns model defaults, point display, inline node controls, and temporary reference image handling around that gateway boundary.
Constraint: Upstream providers cannot fetch localhost reference URLs, but large base64 payloads previously caused request/body reliability issues.
Constraint: Seedance point estimates depend on authenticated NewAPIWG /api/points/estimate responses rather than static catalog prices.
Rejected: Send all reference images directly as large data URLs | would reintroduce oversized JSON/request failures.
Rejected: Restore legacy per-provider key controls by default | current product direction is a single Popi/NewAPI gateway.
Confidence: high
Scope-risk: moderate
Directive: Do not pass /api/images localhost URLs to upstream generation APIs; resolve them server-side or fail before the upstream call.
Tested: npm run test:run -- src/app/api/generate/providers/__tests__/newapiwg.test.ts src/app/api/points/estimate/__tests__/route.test.ts src/lib/images/store.test.ts src/components/__tests__/GenerationComposer.test.tsx src/components/__tests__/ImageInputNode.test.tsx src/components/__tests__/PromptNode.test.tsx src/components/__tests__/ProjectSetupModal.test.tsx src/store/execution/__tests__/generateVideoExecutor.test.ts src/store/execution/__tests__/nanoBananaExecutor.test.ts src/store/utils/__tests__/nodeDefaults.test.ts
Tested: npm run build
Tested: git diff --check
Not-tested: npm run lint fails because next lint is parsed as a missing /lint project directory under Next 16.
The welcome screen now matches the Popi.TV brand and gives unauthenticated users two explicit paths: jump to the main-site login page or provide a Popi/NewAPI gateway key directly. The manually provided key is persisted in the local user store and forwarded through the NewAPI-backed generation, model, LLM, and chat routes without requiring a login token.
Constraint: Users need a usable local path when they are not logged into the main site.\nRejected: Keep the startup login modal for missing tokens | it blocked the in-welcome login/key choices.\nRejected: Rename internal workflow prompts and storage keys | those are compatibility/internal identifiers, not the visible brand surface.\nConfidence: high\nScope-risk: moderate\nDirective: Keep manual gateway-key access scoped to NewAPI-backed paths; non-NewAPI providers should continue requiring a login token.\nTested: npm run test:run -- src/app/api/models/__tests__/route.test.ts src/app/api/models/[modelId]/__tests__/route.test.ts src/app/api/llm/__tests__/route.test.ts src/app/api/chat/__tests__/route.test.ts src/app/api/generate/__tests__/route.test.ts\nTested: npm run test:run -- src/components/__tests__/QuickstartInitialView.test.tsx src/components/__tests__/WelcomeModal.test.tsx\nTested: npm run build\nTested: Browser verification for Popi.TV welcome title and two unauthenticated entry paths\nTested: git diff --cached --check\nNot-tested: Full test suite\nNot-tested: npm run lint still fails because the existing Next 16 next lint script resolves /lint as a project directory
The welcome screen now matches the Popi.TV brand and gives unauthenticated users two explicit paths: jump to the main-site login page or provide a Popi/NewAPI gateway key directly. The manually provided key is persisted in the local user store and forwarded through the NewAPI-backed generation, model, LLM, and chat routes without requiring a login token.
Constraint: Users need a usable local path when they are not logged into the main site.\nRejected: Keep the startup login modal for missing tokens | it blocked the in-welcome login/key choices.\nRejected: Rename internal workflow prompts and storage keys | those are compatibility/internal identifiers, not the visible brand surface.\nConfidence: high\nScope-risk: moderate\nDirective: Keep manual gateway-key access scoped to NewAPI-backed paths; non-NewAPI providers should continue requiring a login token.\nTested: npm run test:run -- src/app/api/models/__tests__/route.test.ts src/app/api/models/[modelId]/__tests__/route.test.ts src/app/api/llm/__tests__/route.test.ts src/app/api/chat/__tests__/route.test.ts src/app/api/generate/__tests__/route.test.ts\nTested: npm run test:run -- src/components/__tests__/QuickstartInitialView.test.tsx src/components/__tests__/WelcomeModal.test.tsx\nTested: npm run build\nTested: Browser verification for Popi.TV welcome title and two unauthenticated entry paths\nTested: git diff --cached --check\nNot-tested: Full test suite\nNot-tested: npm run lint still fails because the existing Next 16 next lint script resolves /lint as a project directory
Browser directory picking can be intercepted by embedded automation environments, which raises before the user can choose a folder. The project setup browse flow now treats that specific interception as a signal to use the existing server browse-directory fallback, while preserving normal browser picker behavior and cancellation semantics.
Constraint: In-app browser automation may install Page.setInterceptFileChooserDialog and break showDirectoryPicker
Constraint: Browser File System Access selection should still be preferred when it works
Rejected: Always fall back after any browser picker error | permission and unsupported errors should remain visible instead of silently choosing a server path
Confidence: high
Scope-risk: narrow
Directive: Do not broaden fallback errors without checking browser local-project semantics
Tested: npm run test:run -- src/components/__tests__/ProjectSetupModal.test.tsx --testNamePattern "fall back to browse-directory API"
Tested: npm run test:run -- src/components/__tests__/ProjectSetupModal.test.tsx --testNamePattern "Browse Button"
Tested: npm run test:run -- src/components/__tests__/ProjectSetupModal.test.tsx --testNamePattern "fall back to browse-directory API|should call browse-directory API|should keep selected parent path|should handle cancelled browse dialog"
Tested: npm run build
Not-tested: npm run lint | existing Next 16 next lint script resolves to nonexistent /lint directory
Not-tested: Full ProjectSetupModal test file | existing Provider tab assertions expect API key inputs hidden by current Popi mode
The canvas now treats the visible plus affordance as part of the output handle hit zone, so users can click or drag from the same right-side target. Empty image input nodes also handle double-click locally before the canvas node double-click centering logic sees the event.
Constraint: The plus affordance must not block React Flow handle drag events
Rejected: Keep the plus as the primary pointer target | it prevented drag-to-connect from the same visual area
Confidence: high
Scope-risk: moderate
Directive: Keep quick-add visuals non-interactive unless handle dragging is reworked at the React Flow layer
Tested: npm run test:run -- src/components/__tests__/ImageInputNode.test.tsx src/components/__tests__/WorkflowCanvas.test.tsx
Tested: npm run build
Not-tested: npm run lint | existing Next 16 next lint script resolves to nonexistent /lint directory
This keeps the testing branch aligned with the current Popi.TV interaction direction: generation is controlled from the selected node context, model/provider selection is simplified around the NewAPI gateway path, Popiai embedding can hydrate workflow state, and media nodes expose names plus dimensions in the canvas header.
Constraint: Testing branch needs the full current source state, not runtime logs or local browser artifacts
Rejected: Commit logs, browserfs state, and handoff bundles | they are local runtime artifacts rather than application source
Confidence: high
Scope-risk: moderate
Reversibility: clean
Directive: Keep model selection consolidated around the NewAPI gateway unless supplier-specific behavior is intentionally reintroduced
Tested: npm run test:run -- src/components/__tests__/FloatingNodeHeader.test.tsx src/components/__tests__/nodeHeaderMedia.test.ts src/components/__tests__/WorkflowCanvas.test.tsx
Tested: npm run test:run -- src/components/__tests__/ImageInputNode.test.tsx src/components/__tests__/GenerateVideoNode.test.tsx src/components/__tests__/GenerateImageNode.test.tsx
Tested: npm run build
Tested: git diff --check -- src
Not-tested: npm run lint | existing script uses next lint and resolves to nonexistent ./lint directory
The app header still exposed the internal popiart-node label while the requested product brand is Popi.TV. This keeps the existing icon asset but makes it decorative so the visible header label is the accessible brand signal.
Constraint: Keep the change scoped to the top-left header logo area.
Rejected: Rename all popiart-node strings globally | the request only targeted the top-left Logo.
Confidence: high
Scope-risk: narrow
Directive: Do not broaden this into a product-wide rename without checking welcome and onboarding copy.
Tested: npm run test:run -- src/components/__tests__/Header.test.tsx
The app header still exposed the internal popiart-node label while the requested product brand is Popi.TV. This keeps the existing icon asset but makes it decorative so the visible header label is the accessible brand signal.
Constraint: Keep the change scoped to the top-left header logo area.
Rejected: Rename all popiart-node strings globally | the request only targeted the top-left Logo.
Confidence: high
Scope-risk: narrow
Directive: Do not broaden this into a product-wide rename without checking welcome and onboarding copy.
Tested: npm run test:run -- src/components/__tests__/Header.test.tsx
Output nodes were collapsing multiple connected media inputs into one visible result, which made image/video/audio/3D connections look ignored. The node now preserves each connected media kind and presents explicit result switching with current/all download actions.
Constraint: Output node remains a result endpoint and does not transform media or create hidden downstream behavior
Rejected: Auto-merge media into one combined preview | would hide workflow structure and violate the endpoint-only product model
Confidence: high
Scope-risk: moderate
Directive: Keep output node behavior as explicit result display; route further processing through visible downstream nodes
Tested: npm test -- --run src/components/__tests__/OutputNode.test.tsx src/store/execution/__tests__/simpleNodeExecutors.test.ts
Tested: npm run build
Tested: npm run test:run
Tested: Playwright localhost smoke with no page or console errors
The bottom composer and right-side node settings both expose video duration, resolution, and sound. Selected video nodes now receive quick-control changes immediately, so both surfaces read the same node data instead of diverging until blur or generate.
Constraint: Bottom composer remains the primary quick control while existing node settings continue to read workflow store data
Rejected: Remove the node settings panel | broader product change outside this fix
Rejected: Convert all composer draft fields to immediate store writes | higher risk and unnecessary for the reported video parameter mismatch
Confidence: high
Scope-risk: narrow
Directive: Keep shared video parameters on GenerateVideoNodeData; do not introduce a second parameter source for quick controls
Tested: npm run test:run -- src/components/__tests__/GenerationComposer.test.tsx
Tested: npm run test:run -- src/components/__tests__/GenerateVideoNode.test.tsx
Tested: git diff --check
Not-tested: full lint/typecheck still blocked by existing repo script/type issues from prior verification
Vidu-style video models can load parameter schemas that change the Generate Video node height and trigger React Flow dimension updates. The fix keeps schema-driven resize notifications stable, skips no-op node height writes, and ignores duplicate React Flow node changes before they enter the workflow store.
It also preserves completed media outputs when a stopped or reloaded workflow still has transient loading/skipped state, so existing video results do not appear stuck after recovery.
Constraint: The crash was reported from a browser state where choosing Vidu hit React's maximum update depth in onNodesChange.
Rejected: Clear browser storage as the fix | it would hide persisted workflow loops without fixing the update path.
Rejected: Remove dynamic video handles | visible media/text inputs are product behavior and required for model-specific workflows.
Confidence: high
Scope-risk: moderate
Directive: Keep React Flow dimension and schema resize writes idempotent; new node resize paths should no-op when dimensions are already applied.
Tested: npm test -- --run src/components/__tests__/GenerateVideoNode.test.tsx -t 'should not resize repeatedly'
Tested: npm test -- --run src/components/__tests__/GenerateVideoNode.test.tsx src/components/__tests__/ModelParameters.test.tsx src/store/__tests__/workflowStore.integration.test.ts src/store/__tests__/skipPropagation.test.ts src/store/execution/__tests__/generateVideoExecutor.test.ts
Tested: npm run build
Tested: npm run test:run
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.
The bottom composer is the canonical image-generation control surface now. The legacy right-side control panel was still rendering schema defaults for selected image nodes, which made aspect and size controls disagree on the same operation.
Constraint: Image generation controls must stay consistent with the Popi composer UX
Rejected: Synchronize both panels | duplicating controls preserves the confusing two-source UI
Confidence: high
Scope-risk: narrow
Directive: Do not re-enable the right-side image panel unless it reads from the same composer-owned state
Tested: npm run test:run -- src/components/__tests__/ControlPanel.test.tsx
Tested: npm run test:run -- src/components/__tests__/GenerationComposer.test.tsx src/components/__tests__/ControlPanel.test.tsx
Tested: PROVIDER_MODE=popi NEXT_PUBLIC_PROVIDER_MODE=popi npm run build
Tested: Playwright localhost check for composer visible and legacy image settings absent
The composer top row no longer shows the placeholder Style, Mark, and Focus chips. Reference image upload remains available while those future controls are deferred.
Constraint: User asked to hide the highlighted area temporarily, not remove reference upload
Rejected: Disabling the buttons visually | hidden controls better avoid confusing unfinished affordances
Confidence: high
Scope-risk: narrow
Directive: Reintroduce these chips only with implemented behavior behind them
Tested: npm run test:run -- src/components/__tests__/GenerationComposer.test.tsx
Tested: PROVIDER_MODE=popi NEXT_PUBLIC_PROVIDER_MODE=popi npm run build
The bottom generation composer now treats reference thumbnails as previewable assets: clicking a thumbnail opens a portal lightbox with the full image, backdrop/click-close behavior, and Escape close support. The remove button stops propagation so deletion remains distinct from preview opening.
Constraint: Keep the interaction inside the existing composer surface without introducing a shared modal dependency
Rejected: Reusing output-node lightbox directly | it is coupled to node media state and download/video behavior
Confidence: high
Scope-risk: narrow
Directive: Keep thumbnail click and remove click separated; do not nest buttons
Tested: npm run test:run -- src/components/__tests__/GenerationComposer.test.tsx
Tested: PROVIDER_MODE=popi NEXT_PUBLIC_PROVIDER_MODE=popi npm run build
Tested: Playwright uploaded a reference image, opened the preview dialog, and closed it with Escape
New users now land on Popi gateway defaults that match the tested production-style path: APIYI Nano Banana 2 for images, Doubao Seedance for video, and Doubao Seed 2.0 Lite for LLM chat/tool use. Settings and FTUX screens render these effective defaults instead of empty placeholders, while existing local node defaults keep taking precedence.
The same pass keeps provider-overload errors user-facing by formatting the model name that the node currently displays, so fallback and switched-model failures are easier to understand across media nodes.
Constraint: Popi mode should hide internal NewApiWG naming and default to models available through the Popi gateway.
Rejected: Persist default values into localStorage for every new user | would make future system default changes harder and could overwrite explicit user preferences.
Confidence: high
Scope-risk: moderate
Directive: Do not change these defaults without checking the Popi gateway model ids and www.popi.art login/model-routing assumptions.
Tested: npm run test:run -- src/lib/__tests__/llmModels.test.ts src/store/utils/__tests__/nodeDefaults.test.ts src/store/execution/__tests__/generateVideoExecutor.test.ts src/components/__tests__/ProjectSetupModal.test.tsx src/components/__tests__/GenerationComposer.test.tsx src/app/api/chat/__tests__/route.test.ts src/components/__tests__/LLMGenerateNode.test.tsx src/utils/__tests__/userFacingErrors.test.ts
Tested: PROVIDER_MODE=popi NEXT_PUBLIC_PROVIDER_MODE=popi npm run build
Tested: git diff --check
Not-tested: npm run lint currently fails because next lint is no longer a valid project command in this Next.js setup
The right-side assistant now uses the existing chat/tooling path as a docked canvas surface instead of a hidden floating experiment. It can prepare workflow edits, prepare run actions, and keep all mutations behind an explicit preview/apply step.
A shared chat node schema keeps the model prompt and local edit validator aligned with real node types, while the context builder strips broader media payloads before chat requests.
Constraint: Keep the deployed master/TEST-s version stable while this work proceeds on a feature branch
Constraint: No new dependencies and no broad canvas rewrite
Rejected: Directly applying model-suggested edits | local validation and preview remain the safety boundary
Rejected: Full multimodal image upload in the first pass | current implementation only exposes media metadata and failure state
Confidence: high
Scope-risk: moderate
Reversibility: clean
Directive: Add new AI-editable node fields through src/lib/chat/nodeSchema.ts before exposing them in prompts
Tested: npm run test:run -- src/lib/chat/contextBuilder.test.ts src/lib/chat/tools.test.ts src/lib/chat/editOperations.test.ts src/components/__tests__/ChatPanel.test.tsx src/components/__tests__/WorkflowCanvas.test.tsx src/app/api/chat/__tests__/route.test.ts
Tested: PROVIDER_MODE=popi NEXT_PUBLIC_PROVIDER_MODE=popi npm run build
Tested: Browser smoke on http://localhost:3000 verified docked assistant, close/reopen, selected-node focus, and run controls
Not-tested: Live LLM tool-call execution against the gateway
Default provider mode now exposes only Popi Models while preserving the existing multi-provider implementation behind an explicit multi mode. The model browser, project settings, onboarding, node badges, and model API all share the same provider-mode decision so the test deployment matches the www.popi.art login-aligned direction.
This also includes the pending UI and i18n node-label changes already present in the tracked worktree so the committed state matches the verified build.
Constraint: Product entry must align with www.popi.art by exposing Popi Models instead of internal NewApiWG naming
Constraint: Test deployment should match the full tracked working tree that passed build
Rejected: Delete legacy provider code | multi-provider internals remain useful behind PROVIDER_MODE=multi
Rejected: UI-only hiding | API and store layers now enforce Popi mode too
Confidence: high
Scope-risk: broad
Reversibility: clean
Directive: Keep NewApiWG as the internal provider id unless the gateway API/env contract is migrated
Tested: npm run test:run -- src/components/__tests__/ProjectSetupModal.test.tsx src/app/api/models/__tests__/route.test.ts src/lib/__tests__/llmModels.test.ts
Tested: npm run test:run -- src/components/__tests__/GenerateImageNode.test.tsx src/components/__tests__/GenerateVideoNode.test.tsx src/components/__tests__/GenerateAudioNode.test.tsx src/components/__tests__/Generate3DNode.test.tsx src/components/__tests__/LLMGenerateNode.test.tsx
Tested: npm run test:run -- src/lib/chat/tools.test.ts
Tested: PROVIDER_MODE=popi NEXT_PUBLIC_PROVIDER_MODE=popi npm run build
Tested: Browser smoke on http://localhost:3000 verified Project Settings and Model Search only expose Popi Models
Not-tested: Direct npx tsc --noEmit remains blocked by pre-existing test typing errors outside this change
Node plus actions should offer a short continuation menu while handle dragging remains a full exploration surface. This records the product rule in a dedicated PRD and implements a static priority filter inside the existing connection menu instead of introducing a separate ranking layer.
Constraint: Test server flow uses the connection drop menu for both drag-created nodes and node plus quick-add actions
Rejected: Split quick-add into a separate menu component | duplicated option compatibility logic and increased drift risk
Confidence: high
Scope-risk: narrow
Directive: Keep quick-add filtering downstream of compatibility filtering so suggestions never create invalid handle connections
Tested: npm run test:run -- src/components/__tests__/ConnectionDropMenu.test.tsx src/components/__tests__/WorkflowCanvas.test.tsx
Tested: npm run test:run
Tested: npm run build
Not-tested: npm run lint; current next lint script is not supported by the installed Next CLI
The TEST-s line can fast-forward into master, but the verification gate exposed stale test assumptions: video nodes now expose both input and output Video labels, and WorkflowCanvas tests need the ReactFlow setNodes API used by image node resizing.
Constraint: Preserve runtime behavior while making the merge gate reliable
Rejected: Change production node labels | the UI behavior is intentional and already deployed on TEST-s
Confidence: high
Scope-risk: narrow
Tested: npm run test:run -- src/components/__tests__/GenerateVideoNode.test.tsx src/components/__tests__/WorkflowCanvas.test.tsx
Tested: npm run test:run
Tested: npm run build
The collapsed composer should expand from the surrounding summary area, but the model label and generate button are explicit action targets. This keeps model selection and generation isolated while retaining one-click expansion from the remaining collapsed surface.
Constraint: Red-marked collapsed controls have dedicated product actions
Rejected: Treat the whole collapsed summary as one expand button | steals the model selector action
Confidence: high
Scope-risk: narrow
Directive: Do not bind collapsed-container expansion over buttons with dedicated actions
Tested: npm run test:run -- src/components/__tests__/GenerationComposer.test.tsx
Tested: npm run build
Not-tested: npm run lint | existing script calls unsupported next lint under Next 16
Not-tested: npx tsc --noEmit | existing unrelated test type errors remain
Users expect a collapsed bottom composer to expand from the visible summary itself, not only the small expand icon. The collapsed summary now acts as the expansion target while preserving the generate button's submit behavior, and a regression test locks the summary-click path.
Constraint: TEST-s deployment branch is used for the test server
Rejected: Keep model summary opening the model dialog while collapsed | conflicts with the requested one-click expand behavior
Confidence: high
Scope-risk: narrow
Directive: Keep collapsed summary clicks focused on expansion; preserve generate button isolation
Tested: npm run test:run -- src/components/__tests__/GenerationComposer.test.tsx
Tested: npm run build
Tested: Local browser check on http://localhost:3000/ collapsed summary click
Not-tested: npm run lint | existing script calls unsupported next lint under Next 16
Not-tested: npx tsc --noEmit | existing unrelated test type errors remain
The canvas needs to respect what users can see: media nodes should reflect the actual image ratio, and the connection menu should dismiss when the user clicks away instead of forcing a node choice. The fix stays inside the affected node/menu components and their regression tests.
Constraint: Windows pointer/canvas interactions can prevent bubble-phase outside-click handlers from seeing the click
Rejected: Add a modal/backdrop around the connection menu | heavier behavior change and unnecessary for a transient menu
Rejected: Add user-facing aspect-ratio controls | the media already exposes dimensions and should not need extra configuration
Confidence: high
Scope-risk: narrow
Directive: Keep connection-menu dismissal as capture-phase pointer handling unless Windows canvas behavior is revalidated
Tested: npm test -- --run src/components/__tests__/ConnectionDropMenu.test.tsx src/components/__tests__/ImageInputNode.test.tsx src/components/__tests__/GenerateImageNode.test.tsx
Tested: npm run build
Not-tested: Manual Windows PC browser run
The LLM selector exposed display-style Doubao model names that the NewApiWG test gateway cannot route. The UI now stores the gateway model ids returned by /models, while the API route maps legacy saved selector values to those ids so existing workflows do not keep failing.
Constraint: Preserve GPT-4.1 Mini as the NewApiWG default and keep old workflow JSON compatible.
Rejected: Remove Doubao from the LLM selector | the gateway exposes working Doubao chat model ids, so the issue is stale ids rather than product support.
Confidence: high
Scope-risk: narrow
Directive: LLM selector values must be callable provider ids; use labels only for display text.
Tested: Live NewApiWG chat completion with doubao-seed-2-0-lite-260428 and doubao-seed-2-0-pro-260215.
Tested: npm run test:run -- src/lib/__tests__/llmModels.test.ts src/app/api/llm/__tests__/route.test.ts src/components/__tests__/LLMGenerateNode.test.tsx src/store/utils/__tests__/nodeDefaults.test.ts
Tested: npm run build
Tested: git diff --check
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.
The TEST-s branch renders the composer generate action with the English aria-label used by nearby tests. Updating the stale assertion keeps the test focused on image-count persistence instead of locale-specific text.
Constraint: TEST-s currently renders the generate button aria-label as Generate in this test setup
Rejected: Change composer runtime label for the test | would alter UI behavior to satisfy a stale assertion
Confidence: high
Scope-risk: narrow
Directive: Prefer stable accessible labels already used in adjacent composer tests
Tested: npm run test:run -- src/components/__tests__/GenerateImageNode.test.tsx src/components/__tests__/GenerationComposer.test.tsx src/app/api/generate/providers/__tests__/newapiwg.test.ts
Tested: git diff --check
Not-tested: Full browser locale sweep
weige
TianYun