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:
yujinze
2026-01-20 20:52:04 +09:00
committed by GitHub
parent b386dc45e6
commit afddba364b
20 changed files with 1741 additions and 399 deletions

View File

@@ -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,