The provider branch makes model defaults and Popi metadata resolution more asynchronous, while the local UI keeps duplicate node-body settings hidden. This keeps pricing available when metadata is already complete, avoids refreshing placeholder Popi selections, preserves explicit Popi schema hydration, and fixes strict TypeScript narrowing exposed by the merged media upload route.
Constraint: Preserve hidden node-body settings while keeping Popi provider schema hydration available.
Rejected: Re-enable inline node settings for all external providers | would reintroduce duplicated controls the user asked to hide.
Confidence: high
Scope-risk: moderate
Directive: Do not fetch per-model schemas for hidden non-Popi node settings unless an explicit modelSchemaRequestId requests it.
Tested: npm run test:run -- src/components/__tests__/PromptNode.test.tsx src/components/__tests__/WorkflowCanvas.test.tsx src/components/modals/__tests__/MarkdownEditorModal.test.tsx src/components/__tests__/FloatingNodeHeader.test.tsx src/components/__tests__/LLMGenerateNode.test.tsx src/components/__tests__/GenerateImageNode.test.tsx src/components/__tests__/GenerateVideoNode.test.tsx src/components/__tests__/GenerationComposer.test.tsx src/app/api/generate/providers/__tests__/popiserver.test.ts src/app/api/__tests__/popiserverModels.test.ts --reporter=dot
Tested: npm run build
Tested: git diff --check
Tested: rg -n '^(<<<<<<<|=======|>>>>>>>)' src
Not-tested: npm run lint cannot run because the existing Next 16 script maps next lint to a missing ./lint project directory.
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.
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 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
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 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 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
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.
TianYun
huangmin