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

lib/diagram-validator.ts

@@ -3,17 +3,10 @@
  * The actual validation is performed via useValidateDiagram hook using AI SDK's useObject.
  */
 
-export interface ValidationIssue {
-    type: "overlap" | "edge_routing" | "text" | "layout" | "rendering"
-    severity: "critical" | "warning"
-    description: string
-}
+// Re-export types from the schema file (single source of truth)
+export type { ValidationIssue, ValidationResult } from "./validation-schema"
 
-export interface ValidationResult {
-    valid: boolean
-    issues: ValidationIssue[]
-    suggestions: string[]
-}
+import type { ValidationResult } from "./validation-schema"
 
 /**
  * Format validation feedback for display to the AI model.

lib/i18n/dictionaries/en.json

@@ -115,7 +115,11 @@
         "httpProxy": "HTTP Proxy",
         "httpsProxy": "HTTPS Proxy",
         "applyProxy": "Apply",
-        "proxyApplied": "Proxy settings applied"
+        "proxyApplied": "Proxy settings applied",
+        "diagramValidation": "Diagram Validation (Experimental)",
+        "diagramValidationDescription": "Use a vision language model to validate generated diagrams. Requires a VLM like GPT-5.2 or Sonnet-4.5.",
+        "enabled": "Enabled",
+        "disabled": "Disabled"
     },
     "save": {
         "title": "Save Diagram",

lib/i18n/dictionaries/ja.json

@@ -115,7 +115,11 @@
         "httpProxy": "HTTP プロキシ",
         "httpsProxy": "HTTPS プロキシ",
         "applyProxy": "適用",
-        "proxyApplied": "プロキシ設定が適用されました"
+        "proxyApplied": "プロキシ設定が適用されました",
+        "diagramValidation": "ダイアグラム検証（実験的）",
+        "diagramValidationDescription": "視覚言語モデルを使用して生成されたダイアグラムを検証します。GPT-5.2 や Sonnet-4.5 などの VLM が必要です。",
+        "enabled": "有効",
+        "disabled": "無効"
     },
     "save": {
         "title": "ダイアグラムを保存",

lib/i18n/dictionaries/zh.json

@@ -115,7 +115,11 @@
         "httpProxy": "HTTP 代理",
         "httpsProxy": "HTTPS 代理",
         "applyProxy": "应用",
-        "proxyApplied": "代理设置已应用"
+        "proxyApplied": "代理设置已应用",
+        "diagramValidation": "图表验证（实验性）",
+        "diagramValidationDescription": "使用视觉语言模型验证生成的图表。需要支持视觉的模型，如 GPT-5.2 或 Sonnet-4.5。",
+        "enabled": "已启用",
+        "disabled": "已禁用"
     },
     "save": {
         "title": "保存图表",

lib/validation-schema.ts

@@ -35,3 +35,4 @@ export const ValidationResultSchema = z.object({
 })
 
 export type ValidationResult = z.infer<typeof ValidationResultSchema>
+export type ValidationIssue = ValidationResult["issues"][number]