mirror of
https://github.com/DayuanJiang/next-ai-draw-io.git
synced 2026-09-01 17:10:24 +08:00
Add VLM-based diagram validation (#602)
* [Feature] Add VLM-based diagram validation Add automatic VLM (Vision Language Model) validation after display_diagram tool execution. The system captures a screenshot of the rendered diagram, sends it to a VLM for visual analysis, and uses feedback to improve diagram quality through the existing retry mechanism. Changes: - Add /api/validate-diagram endpoint for VLM validation - Add diagram-validator.ts for client-side validation orchestration - Add validation-prompts.ts for VLM system prompts - Add ValidationCard component to display validation status in chat - Add PNG capture functionality to diagram context - Integrate validation into tool handlers with retry support (max 3) - Add "Improve with Suggestions" button for manual regeneration - Add settings toggle to enable/disable VLM validation - Add getValidationModel() helper in ai-providers.ts * refactor(validation): use AI SDK structured outputs and address review feedback - Replace generateText + manual JSON parsing with generateObject and Zod schema for type-safe structured validation output - Use AbortSignal.timeout() instead of Promise.race for cleaner timeout handling - Add timeout validation with minimum 1000ms to handle malformed env values - Remove unused xml parameter from validateRenderedDiagram API - Remove parseValidationResponse function (now handled by schema) - Clear validationStates on session switch and new chat to prevent memory leak - Update 100ms render delay comment to clarify best-effort heuristic - Remove unused useEffect import from ValidationCard - Fix optional chaining lint warning in ValidationCard - Add unit tests for formatValidationFeedback function * refactor(validation): use AI SDK experimental_useObject hook instead of raw fetch - Change API endpoint from generateObject to streamObject for useObject compatibility - Create useValidateDiagram hook using AI SDK's experimental_useObject for reactive validation - Update useDiagramToolHandlers to accept validation function as parameter - Update chat-panel to use new useValidateDiagram hook - Remove validateRenderedDiagram function from lib/diagram-validator.ts (now in hook) - Export ValidationResultSchema from API route for client-side use * fix(validation): extract schema to shared file for client/server compatibility Move ValidationResultSchema to lib/validation-schema.ts to avoid importing server-side modules (ai-providers) into client-side code. This fixes the Turbopack build error caused by the hook importing from the API route. * fix(validation): use 'Valid' instead of 'Complete' for validation success Change ValidationCard success label from 'Complete' to 'Valid' to avoid conflicting with ToolCallCard's 'Complete' badge in E2E tests. This fixes the diagram-generation E2E test that expects a specific count of 'Complete' badges. * fix(validation): add aria-hidden to icons to prevent duplicate ID warning * fix: improve VLM validation with bug fixes and i18n - Fix race condition in pendingValidationRef (reject previous pending validation) - Fix response format consistency (use streaming for all responses) - Remove dead code (unused lastRequestRef and ValidationRequest interface) - Consolidate duplicate types (re-export from validation-schema.ts) - Add 'success_with_warnings' status for valid diagrams with warnings - Fix tool card auto-collapse (only collapse once, respect user toggle) - Set VLM validation default to disabled - Add i18n support for diagram validation settings (en/zh/ja) - Mark feature as experimental in settings UI * fix: resolve TypeScript errors in electron-standalone - Add forwardRef support to ChatInput component with ChatInputRef type - Copy electron.d.ts to electron-standalone/electron folder - Exclude electron-standalone from root tsconfig type checking * fix: return empty string for valid result with no issues in formatValidationFeedback * feat(i18n): add validation strings for ValidationCard component - Add validation section to en.json, zh.json, ja.json dictionaries - Update ValidationCard to use useDictionary hook - Replace all hardcoded English strings with i18n keys --------- Co-authored-by: dayuan.jiang <jdy.toh@gmail.com>
This commit is contained in:
@@ -31,6 +31,7 @@ interface DiagramContextType {
|
||||
successMessage?: string,
|
||||
) => void
|
||||
getThumbnailSvg: () => Promise<string | null>
|
||||
captureValidationPng: () => Promise<string | null>
|
||||
isDrawioReady: boolean
|
||||
onDrawioLoad: () => void
|
||||
resetDrawioReady: () => void
|
||||
@@ -51,6 +52,8 @@ export function DiagramProvider({ children }: { children: React.ReactNode }) {
|
||||
const hasCalledOnLoadRef = useRef(false)
|
||||
const drawioRef = useRef<DrawIoEmbedRef | null>(null)
|
||||
const resolverRef = useRef<((value: string) => void) | null>(null)
|
||||
// Resolver for PNG export (used for VLM validation)
|
||||
const pngResolverRef = useRef<((value: string) => void) | null>(null)
|
||||
// Track if we're expecting an export for history (user-initiated)
|
||||
const expectHistoryExportRef = useRef<boolean>(false)
|
||||
// Track if diagram has been restored after DrawIO remount (e.g., theme change)
|
||||
@@ -147,6 +150,37 @@ export function DiagramProvider({ children }: { children: React.ReactNode }) {
|
||||
}
|
||||
}
|
||||
|
||||
// Capture current diagram as PNG for VLM validation
|
||||
const captureValidationPng = async (): Promise<string | null> => {
|
||||
if (!drawioRef.current) return null
|
||||
// Don't export if diagram is empty
|
||||
if (!isRealDiagram(chartXML)) return null
|
||||
|
||||
try {
|
||||
const pngData = await Promise.race([
|
||||
new Promise<string>((resolve) => {
|
||||
pngResolverRef.current = resolve
|
||||
drawioRef.current?.exportDiagram({ format: "png" })
|
||||
}),
|
||||
new Promise<string>((_, reject) =>
|
||||
setTimeout(
|
||||
() => reject(new Error("PNG export timeout")),
|
||||
5000,
|
||||
),
|
||||
),
|
||||
])
|
||||
|
||||
// PNG data should be a base64 data URL
|
||||
if (pngData?.startsWith("data:image/png")) {
|
||||
return pngData
|
||||
}
|
||||
return null
|
||||
} catch {
|
||||
// Timeout is expected occasionally - don't log as error
|
||||
return null
|
||||
}
|
||||
}
|
||||
|
||||
const loadDiagram = (
|
||||
chart: string,
|
||||
skipValidation?: boolean,
|
||||
@@ -186,6 +220,13 @@ export function DiagramProvider({ children }: { children: React.ReactNode }) {
|
||||
}
|
||||
|
||||
const handleDiagramExport = (data: any) => {
|
||||
// Handle PNG export for VLM validation
|
||||
if (pngResolverRef.current && data.data?.startsWith("data:image/png")) {
|
||||
pngResolverRef.current(data.data)
|
||||
pngResolverRef.current = null
|
||||
return
|
||||
}
|
||||
|
||||
// Handle save to file if requested (process raw data before extraction)
|
||||
if (saveResolverRef.current.resolver) {
|
||||
const format = saveResolverRef.current.format
|
||||
@@ -353,6 +394,7 @@ export function DiagramProvider({ children }: { children: React.ReactNode }) {
|
||||
clearDiagram,
|
||||
saveDiagramToFile,
|
||||
getThumbnailSvg,
|
||||
captureValidationPng,
|
||||
isDrawioReady,
|
||||
onDrawioLoad,
|
||||
resetDrawioReady,
|
||||
|
||||
Reference in New Issue
Block a user