fix(deps): update major dependencies

.github/workflows/auto-format.yml

@@ -12,20 +12,20 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           ref: ${{ github.event.pull_request.head.sha }}
           token: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Setup Node.js
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v7
         with:
           node-version: '24'
 
       - name: Run Biome format
         # Pin to the version in package.json so CI matches local/pre-commit
         # (npx @latest drifts — e.g. 2.5.0 broke this job on unrelated PRs).
-        run: npx @biomejs/biome@2.5.7 check --write --no-errors-on-unmatched .
+        run: npx @biomejs/biome@2.4.13 check --write --no-errors-on-unmatched .
 
       - name: Check for changes
         id: changes

.github/workflows/ci.yml

@@ -20,10 +20,10 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
 
       - name: Setup Node.js
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v7
         with:
           node-version: '24'
           cache: 'npm'

.github/workflows/docker-build.yml

@@ -26,14 +26,14 @@ jobs:
       
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
+        uses: docker/setup-buildx-action@v4
 
       - name: Log in to GitHub Container Registry
         if: github.event_name != 'pull_request'
-        uses: docker/login-action@v3
+        uses: docker/login-action@v4
         with:
           registry: ${{ env.REGISTRY }}
           username: ${{ github.actor }}
@@ -41,7 +41,7 @@ jobs:
 
       - name: Extract metadata (tags, labels)
         id: meta
-        uses: docker/metadata-action@v5
+        uses: docker/metadata-action@v6
         with:
           images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
           tags: |
@@ -54,7 +54,7 @@ jobs:
             type=raw,value=latest,enable={{is_default_branch}}
 
       - name: Build and push Docker image
-        uses: docker/build-push-action@v6
+        uses: docker/build-push-action@v7
         with:
           context: .
           push: ${{ github.event_name != 'pull_request' }}
@@ -71,7 +71,7 @@ jobs:
       # Push to AWS ECR for App Runner auto-deploy
       - name: Configure AWS credentials
         if: github.event_name != 'pull_request' && github.ref == 'refs/heads/main'
-        uses: aws-actions/configure-aws-credentials@v5
+        uses: aws-actions/configure-aws-credentials@v6
         with:
           aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
           aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}

.github/workflows/electron-release.yml

@@ -26,10 +26,10 @@ jobs:
     runs-on: ${{ matrix.os }}
     steps:
       - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
 
       - name: Setup Node.js
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v7
         with:
           node-version: 24
           cache: "npm"
@@ -58,10 +58,10 @@ jobs:
     runs-on: windows-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
 
       - name: Setup Node.js
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v7
         with:
           node-version: 24
           cache: "npm"
@@ -86,7 +86,7 @@ jobs:
           GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Upload unsigned artifacts for signing
-        uses: actions/upload-artifact@v6
+        uses: actions/upload-artifact@v7
         id: upload-unsigned
         with:
           name: windows-unsigned
@@ -94,7 +94,7 @@ jobs:
           retention-days: 1
 
       - name: Sign with SignPath
-        uses: signpath/github-action-submit-signing-request@v2
+        uses: signpath/github-action-submit-signing-request@v3
         with:
           api-token: ${{ secrets.SIGNPATH_API_TOKEN }}
           organization-id: '880a211d-2cd3-4e7b-8d04-3d1f8eb39df5'
@@ -106,7 +106,7 @@ jobs:
           output-artifact-directory: release-signed
 
       - name: Upload signed artifacts to release
-        uses: softprops/action-gh-release@v2
+        uses: softprops/action-gh-release@v3
         with:
           files: release-signed/*.exe
         env:

.github/workflows/publish-mcp.yml

@@ -28,10 +28,10 @@ jobs:
         working-directory: packages/mcp-server
     steps:
       - name: Checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
 
       - name: Setup Node.js
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v7
         with:
           node-version: 24
           cache: "npm"
@@ -62,10 +62,6 @@ jobs:
         if: steps.version.outputs.publish == 'true'
         run: npm test
 
-      - name: Build and check package contents
-        if: steps.version.outputs.publish == 'true'
-        run: npm run build && npm run check-package
-
       - name: Publish to npm
         if: steps.version.outputs.publish == 'true'
         run: npm publish

.github/workflows/test.yml

@@ -11,12 +11,12 @@ jobs:
     name: Lint & Unit Tests
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v7
 
       - name: Setup Node.js
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v7
         with:
-          node-version: "20"
+          node-version: "24"
           cache: "npm"
 
       - name: Install dependencies
@@ -38,27 +38,23 @@ jobs:
       - name: Run MCP server unit tests
         run: npm --prefix packages/mcp-server test
 
-      # Tests run from src/, so check the built npm package separately
-      - name: Build MCP server and check package contents
-        run: npm --prefix packages/mcp-server run build && npm --prefix packages/mcp-server run check-package
-
   e2e:
     name: E2E Tests
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v7
 
       - name: Setup Node.js
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v7
         with:
-          node-version: "20"
+          node-version: "24"
           cache: "npm"
 
       - name: Install dependencies
         run: npm ci
 
       - name: Cache Playwright browsers
-        uses: actions/cache@v5
+        uses: actions/cache@v6
         id: playwright-cache
         with:
           path: ~/.cache/ms-playwright
@@ -81,7 +77,7 @@ jobs:
           CI: true
 
       - name: Upload test results
-        uses: actions/upload-artifact@v6
+        uses: actions/upload-artifact@v7
         if: always()
         with:
           name: playwright-report

README.md

@@ -138,13 +138,6 @@ Then ask Claude to create diagrams:
 
 The diagram appears in your browser in real-time!
 
-The MCP server includes most of the web app's drawing features:
-
--   The same drawing rules and shape libraries (AWS, Azure, GCP, Kubernetes and more)
--   A screenshot tool, so the AI can check the rendered diagram and fix it
--   Version history, multi-page diagrams, and download as `.drawio`, `.png`, `.svg`, or `.drawio.svg`
--   Auto-save to `~/.next-ai-drawio/`, so you can continue a diagram after a restart
-
 See the [MCP Server README](./packages/mcp-server/README.md) for VS Code, Cursor, and other client configurations.
 
 ## Getting Started

app/[lang]/admin/models-section.tsx

@@ -35,7 +35,6 @@ import { useDictionary } from "@/hooks/use-dictionary"
 import { formatMessage } from "@/lib/i18n/utils"
 import {
     FIXED_CRED_PROVIDERS,
-    generateId,
     PROVIDER_INFO,
     type ProviderName,
     SUGGESTED_MODELS,
@@ -226,7 +225,6 @@ function ProviderDetail({
                         </Button>
                         {suggestions.length > 0 && (
                             <Select
-                                value=""
                                 disabled={disabled}
                                 onValueChange={(v) => addModel(v)}
                             >
@@ -392,14 +390,12 @@ function ProviderDetail({
 export function ModelsSection({
     providers,
     envProviders,
-    envHasDefaultModel,
     disabled,
     password,
     onChange,
 }: {
     providers: AdminProvider[]
     envProviders: EnvProvider[]
-    envHasDefaultModel: boolean
     disabled: boolean
     password: string
     onChange: (providers: AdminProvider[]) => void
@@ -413,16 +409,10 @@ export function ModelsSection({
 
     const addProvider = (provider: ProviderName) => {
         const newProvider: AdminProvider = {
-            // generateId works over plain HTTP; crypto.randomUUID needs HTTPS
-            id: generateId(),
+            id: crypto.randomUUID(),
             provider,
             models: [],
-            // Only the very first provider becomes the default, and only when
-            // the env config has no default that it would replace on save
-            isDefault:
-                providers.length === 0 &&
-                !envProviders.some((p) => p.isDefault) &&
-                !envHasDefaultModel,
+            isDefault: providers.length === 0,
         }
         onChange([...providers, newProvider])
         setSelectedId(newProvider.id)
@@ -506,9 +496,7 @@ export function ModelsSection({
                     ))}
                 </div>
                 <div className="border-t p-2">
-                    {/* Always empty so picking the same type again still fires */}
                     <Select
-                        value=""
                         disabled={disabled}
                         onValueChange={(v) => addProvider(v as ProviderName)}
                     >

app/[lang]/admin/page.tsx

@@ -37,19 +37,6 @@ import { SettingField } from "./setting-field"
 
 const NAV_GROUP_IDS = ["models", ...SETTING_GROUPS.map((g) => g.id)]
 
-// For each toggleable group, whether any of its settings has a value (from
-// the settings file or the environment)
-function groupsWithValues(map: SettingsMap): Record<string, boolean> {
-    const result: Record<string, boolean> = {}
-    for (const group of SETTING_GROUPS) {
-        if (!group.toggleable) continue
-        result[group.id] = !!SETTINGS_BY_GROUP.get(group.id)?.some(
-            (d) => map[d.key]?.source !== "default",
-        )
-    }
-    return result
-}
-
 export default function AdminPage() {
     const dict = useDictionary()
     // Localized group title/description, keyed by group id
@@ -75,8 +62,6 @@ export default function AdminPage() {
     // Models section state
     const [providers, setProviders] = useState<AdminProvider[]>([])
     const [envProviders, setEnvProviders] = useState<EnvProvider[]>([])
-    // Whether .env itself sets AI_MODEL (a default the panel would override)
-    const [envHasDefaultModel, setEnvHasDefaultModel] = useState(false)
     const [savedProviders, setSavedProviders] = useState<string>("[]")
     const providersDirty = JSON.stringify(providers) !== savedProviders
 
@@ -103,13 +88,15 @@ export default function AdminPage() {
             const map: SettingsMap = {}
             for (const s of data.settings) map[s.key] = s
             setSettings(map)
-            // A group stays on while it still has values (e.g. from env vars
-            // that saving can't remove); a user's explicit "on" for a group
-            // with no values yet is kept across saves
+            // Seed each toggle once from whether the group has configured
+            // values; don't stomp a user's explicit toggle on later saves
             setEnabledGroups((prev) => {
-                const next = groupsWithValues(map)
-                for (const id of Object.keys(next)) {
-                    next[id] = next[id] || !!prev[id]
+                const next = { ...prev }
+                for (const group of SETTING_GROUPS) {
+                    if (!group.toggleable || group.id in next) continue
+                    next[group.id] = !!SETTINGS_BY_GROUP.get(group.id)?.some(
+                        (d) => map[d.key]?.source !== "default",
+                    )
                 }
                 return next
             })
@@ -121,12 +108,10 @@ export default function AdminPage() {
         (data: {
             providers: AdminProvider[]
             envProviders?: EnvProvider[]
-            envHasDefaultModel?: boolean
         }) => {
             setProviders(data.providers)
             setSavedProviders(JSON.stringify(data.providers))
             setEnvProviders(data.envProviders ?? [])
-            setEnvHasDefaultModel(!!data.envHasDefaultModel)
         },
         [],
     )
@@ -196,9 +181,8 @@ export default function AdminPage() {
         return () => observer.disconnect()
     }, [authedPassword])
 
-    // value undefined drops the pending change (back to the saved value)
     const handleChange = useCallback(
-        (key: string, value: string | null | undefined) => {
+        (key: string, value: string | null) => {
             setSaveMessage(null)
             setErrors((prev) => {
                 if (!(key in prev)) return prev
@@ -217,7 +201,7 @@ export default function AdminPage() {
                     value === "" &&
                     (!state || state.source !== "file") &&
                     !isSecretValue(state?.value)
-                if (value === undefined || isRevert || isNoop) {
+                if (isRevert || isNoop) {
                     const next = { ...prev }
                     delete next[key]
                     return next
@@ -241,10 +225,9 @@ export default function AdminPage() {
                 const next = { ...prev }
                 for (const key of keys) {
                     if (!enabled) {
-                        // Stage deletion of saved values; drop unsaved input
-                        if (settings[key]?.source === "default")
-                            delete next[key]
-                        else next[key] = null
+                        // Stage deletion only for values currently set
+                        if (settings[key]?.source !== "default")
+                            next[key] = null
                     } else if (next[key] === null) {
                         delete next[key]
                     }
@@ -464,7 +447,6 @@ export default function AdminPage() {
                             <ModelsSection
                                 providers={providers}
                                 envProviders={envProviders}
-                                envHasDefaultModel={envHasDefaultModel}
                                 disabled={!writable || saving}
                                 password={authedPassword}
                                 onChange={(next) => {
@@ -480,11 +462,6 @@ export default function AdminPage() {
                         const defs = SETTINGS_BY_GROUP.get(group.id) ?? []
                         const groupOff =
                             group.toggleable && !enabledGroups[group.id]
-                        // Values from env vars can't be removed here, so the
-                        // group can't be turned off from the panel
-                        const envLocked = defs.some(
-                            (d) => settings[d.key]?.source === "env",
-                        )
                         const fieldsDisabled = !writable || saving || !!groupOff
                         const gt = groupText(group.id)
                         const title = gt?.title ?? group.title
@@ -503,11 +480,6 @@ export default function AdminPage() {
                                     </h2>
                                     {group.toggleable && (
                                         <label
-                                            title={
-                                                envLocked
-                                                    ? dict.admin.sourceEnvTitle
-                                                    : undefined
-                                            }
                                             className={cn(
                                                 "flex cursor-pointer items-center gap-2 rounded-full border px-3 py-1.5 text-xs font-medium transition-colors motion-reduce:transition-none",
                                                 enabledGroups[group.id]
@@ -522,11 +494,7 @@ export default function AdminPage() {
                                                 checked={
                                                     !!enabledGroups[group.id]
                                                 }
-                                                disabled={
-                                                    !writable ||
-                                                    saving ||
-                                                    envLocked
-                                                }
+                                                disabled={!writable || saving}
                                                 aria-label={formatMessage(
                                                     dict.admin.enableGroup,
                                                     { group: title },
@@ -611,9 +579,6 @@ export default function AdminPage() {
                                         setPending({})
                                         setErrors({})
                                         setProviders(JSON.parse(savedProviders))
-                                        setEnabledGroups(
-                                            groupsWithValues(settings),
-                                        )
                                     }}
                                 >
                                     {dict.admin.discard}

app/[lang]/admin/setting-field.tsx

@@ -73,10 +73,8 @@ export function SecretInput({
 }) {
     const dict = useDictionary()
     const [show, setShow] = useState(false)
-    // The stored marker to revert to on empty. Refreshed whenever the parent
-    // passes server state (a marker or nothing), e.g. after a save.
-    const [original, setOriginal] = useState(value)
-    if (typeof value !== "string" && value !== original) setOriginal(value)
+    // The stored marker as it was at mount, to revert to on empty
+    const [original] = useState(value)
     const hadStored = isSecretValue(original)
     const text = typeof value === "string" ? value : ""
     const placeholder = isSecretValue(value)
@@ -148,8 +146,7 @@ export function SettingField({
     pendingValue: string | null | undefined
     error?: string
     disabled: boolean
-    // undefined drops the pending change (back to the saved value)
-    onChange: (value: string | null | undefined) => void
+    onChange: (value: string | null) => void
 }) {
     const dict = useDictionary()
     const isDirty = pendingValue !== undefined
@@ -229,18 +226,16 @@ export function SettingField({
         case "secret":
             control = (
                 <div className="w-full max-w-md">
-                    {/* Clearing a saved secret reverts to it; the X button deletes */}
                     <SecretInput
                         id={inputId}
-                        keepOnEmpty={source === "file"}
                         value={
                             isDirty
                                 ? (pendingValue ?? "")
-                                : (secretState ?? undefined)
+                                : (secretState ?? currentValue)
                         }
                         disabled={disabled}
                         onChange={(v) =>
-                            onChange(typeof v === "string" ? v : undefined)
+                            onChange(typeof v === "string" ? v : "")
                         }
                     />
                 </div>

app/[lang]/page.tsx

@@ -37,6 +37,7 @@ export default function Home() {
     )
 
     const chatPanelRef = useRef<ImperativePanelHandle>(null)
+    const isMobileRef = useRef(false)
 
     // Load preferences from localStorage after mount
     useEffect(() => {
@@ -47,9 +48,7 @@ export default function Home() {
             const currentLocale = pathParts[0]
             if (currentLocale !== savedLocale) {
                 pathParts[0] = savedLocale
-                // Keep the query (e.g. ?session=) and hash
-                const { search, hash } = window.location
-                router.replace(`/${pathParts.join("/")}${search}${hash}`)
+                router.replace(`/${pathParts.join("/")}`)
                 return // Wait for redirect
             }
         }
@@ -107,17 +106,27 @@ export default function Home() {
         resetDrawioReady()
     }
 
-    // Check mobile. The draw.io iframe is not remounted when crossing the
-    // breakpoint (only the chat panel is), so its ready state stays as is.
+    // Check mobile - reset draw.io before crossing breakpoint
+    const isInitialRenderRef = useRef(true)
     useEffect(() => {
         const checkMobile = () => {
-            setIsMobile(window.innerWidth < 768)
+            const newIsMobile = window.innerWidth < 768
+            if (
+                !isInitialRenderRef.current &&
+                newIsMobile !== isMobileRef.current
+            ) {
+                setIsDrawioReady(false)
+                resetDrawioReady()
+            }
+            isMobileRef.current = newIsMobile
+            isInitialRenderRef.current = false
+            setIsMobile(newIsMobile)
         }
 
         checkMobile()
         window.addEventListener("resize", checkMobile)
         return () => window.removeEventListener("resize", checkMobile)
-    }, [])
+    }, [resetDrawioReady])
 
     const toggleChatPanel = () => {
         const panel = chatPanelRef.current
@@ -184,11 +193,7 @@ export default function Home() {
                                             noExitBtn: true,
                                             dark:
                                                 darkMode || drawioUi === "dark",
-                                            // draw.io names Traditional Chinese "zh-tw"
-                                            lang:
-                                                currentLang === "zh-Hant"
-                                                    ? "zh-tw"
-                                                    : currentLang,
+                                            lang: currentLang,
                                             // Enable offline mode in Electron to disable external service calls
                                             ...(isElectron && {
                                                 offline: true,

app/api/admin/providers/route.ts

@@ -7,11 +7,7 @@ import {
     mergeSecrets,
     validateAdminProviders,
 } from "@/lib/admin/providers"
-import {
-    getEnvFallback,
-    isSettingsWritable,
-    saveSettings,
-} from "@/lib/admin/settings"
+import { isSettingsWritable, saveSettings } from "@/lib/admin/settings"
 import { loadEnvServerModelsConfig } from "@/lib/server-model-config"
 
 export const runtime = "nodejs"
@@ -37,9 +33,6 @@ async function payload() {
                 models: p.models,
                 isDefault: !!p.default && !adminHasDefault,
             })) ?? [],
-        // Whether .env sets a default model. getEnvFallback skips the value
-        // the panel overlays onto process.env, so a panel default doesn't count.
-        envHasDefaultModel: !!getEnvFallback("AI_MODEL"),
     }
 }
 

app/api/aihubmix-models/route.ts

@@ -0,0 +1,61 @@
+import { NextResponse } from "next/server"
+import {
+    AIHUBMIX_MODELS_ENDPOINT,
+    extractAihubmixModelIds,
+} from "@/lib/aihubmix-models"
+import { SUGGESTED_MODELS } from "@/lib/types/model-config"
+
+const SUCCESS_CACHE_CONTROL =
+    "public, max-age=300, s-maxage=3600, stale-while-revalidate=86400"
+
+function fallbackResponse() {
+    return NextResponse.json(
+        {
+            models: SUGGESTED_MODELS.aihubmix || [],
+            source: "fallback",
+        },
+        {
+            headers: {
+                "Cache-Control": "no-store",
+            },
+        },
+    )
+}
+
+export async function GET() {
+    try {
+        const response = await fetch(AIHUBMIX_MODELS_ENDPOINT, {
+            next: { revalidate: 3600 },
+        })
+
+        if (!response.ok) {
+            console.warn(
+                `[aihubmix-models] Failed to fetch models: ${response.status}`,
+            )
+            return fallbackResponse()
+        }
+
+        const payload = await response.json()
+        const models = extractAihubmixModelIds(payload)
+
+        if (models.length === 0) {
+            console.warn("[aihubmix-models] Model list response was empty")
+            return fallbackResponse()
+        }
+
+        return NextResponse.json(
+            {
+                models,
+                source: "aihubmix",
+            },
+            {
+                headers: {
+                    "Cache-Control": SUCCESS_CACHE_CONTROL,
+                },
+            },
+        )
+    } catch (error) {
+        console.warn("[aihubmix-models] Failed to load models:", error)
+        return fallbackResponse()
+    }
+}

app/api/chat/route.ts

@@ -4,58 +4,43 @@ import {
     createUIMessageStream,
     createUIMessageStreamResponse,
     InvalidToolInputError,
+    LoadAPIKeyError,
     stepCountIs,
     streamText,
 } from "ai"
+import fs from "fs/promises"
 import { jsonrepair } from "jsonrepair"
 import path from "path"
 import { z } from "zod"
-import { checkAccessCode } from "@/lib/access-code"
 import {
-    CACHE_POINT,
     getAIModel,
     SINGLE_SYSTEM_PROVIDERS,
     supportsPromptCaching,
-    usesServerCredentials,
 } from "@/lib/ai-providers"
 import { findCachedResponse } from "@/lib/cached-responses"
 import {
-    dropInvalidToolCalls,
-    fixToolInputJson,
+    isMinimalDiagram,
     replaceHistoricalToolInputs,
     validateFileParts,
 } from "@/lib/chat-helpers"
-import { withDeprecatedParamsFallback } from "@/lib/deprecated-params"
 import {
     checkAndIncrementRequest,
     isQuotaEnabled,
     recordTokenUsage,
 } from "@/lib/dynamo-quota-manager"
 import {
-    endTrace,
     getTelemetryConfig,
     setTraceInput,
     setTraceOutput,
     wrapWithObserve,
 } from "@/lib/langfuse"
-import { classifyLLMError, streamErrorText } from "@/lib/llm-errors"
 import {
     resolveMaxOutputTokens,
     withOutputTokenLimitFallback,
 } from "@/lib/output-token-limit"
-import {
-    type FlattenedServerModel,
-    findServerModelById,
-} from "@/lib/server-model-config"
-import { allowPrivateUrls, isPrivateUrl } from "@/lib/ssrf-protection"
+import { findServerModelById } from "@/lib/server-model-config"
 import { getSystemPrompt } from "@/lib/system-prompts"
 import { getUserIdFromRequest } from "@/lib/user-id"
-import { hasCells } from "@/packages/mcp-server/src/pages.ts"
-import {
-    getShapeLibrary,
-    SHAPE_LIBRARY_LIST,
-} from "@/packages/mcp-server/src/shape-library.ts"
-import { SWIMLANE_EXAMPLE } from "@/packages/mcp-server/src/xml-examples.ts"
 
 // No explicit cap: a reasoning model can spend minutes planning before it emits
 // the tool call, so take whatever the host allows. Vercel's own default is 300s,
@@ -91,16 +76,24 @@ function createCachedStreamResponse(xml: string): Response {
     return createUIMessageStreamResponse({ stream })
 }
 
-// Responses streamed from the model, whose trace streamText's callbacks end
-const modelStreamResponses = new WeakSet<Response>()
-
 // Inner handler function
-const DEBUG_LLM_PAYLOAD = process.env.DEBUG_LLM_PAYLOAD === "true"
-
 async function handleChatRequest(req: Request): Promise<Response> {
     // Check for access code
-    const accessDenied = checkAccessCode(req)
-    if (accessDenied) return accessDenied
+    const accessCodes =
+        process.env.ACCESS_CODE_LIST?.split(",")
+            .map((code) => code.trim())
+            .filter(Boolean) || []
+    if (accessCodes.length > 0) {
+        const accessCodeHeader = req.headers.get("x-access-code")
+        if (!accessCodeHeader || !accessCodes.includes(accessCodeHeader)) {
+            return Response.json(
+                {
+                    error: "Invalid or missing access code. Please configure it in Settings.",
+                },
+                { status: 401 },
+            )
+        }
+    }
 
     const body = await req.json()
     const { messages, xml, previousXml, sessionId } = body
@@ -133,6 +126,36 @@ async function handleChatRequest(req: Request): Promise<Response> {
         userId: userId,
     })
 
+    // === SERVER-SIDE QUOTA CHECK START ===
+    // Quota is opt-in: only enabled when DYNAMODB_QUOTA_TABLE env var is set
+    const hasOwnApiKey = !!(
+        req.headers.get("x-ai-provider") &&
+        (req.headers.get("x-ai-api-key") ||
+            req.headers.get("x-aws-access-key-id") ||
+            req.headers.get("x-vertex-api-key"))
+    )
+
+    // Skip quota check if: quota disabled, user has own API key, or is anonymous
+    if (isQuotaEnabled() && !hasOwnApiKey && userId !== "anonymous") {
+        const quotaCheck = await checkAndIncrementRequest(userId, {
+            requests: Number(process.env.DAILY_REQUEST_LIMIT) || 10,
+            tokens: Number(process.env.DAILY_TOKEN_LIMIT) || 200000,
+            tpm: Number(process.env.TPM_LIMIT) || 20000,
+        })
+        if (!quotaCheck.allowed) {
+            return Response.json(
+                {
+                    error: quotaCheck.error,
+                    type: quotaCheck.type,
+                    used: quotaCheck.used,
+                    limit: quotaCheck.limit,
+                },
+                { status: 429 },
+            )
+        }
+    }
+    // === SERVER-SIDE QUOTA CHECK END ===
+
     // === FILE VALIDATION START ===
     const fileValidation = validateFileParts(messages)
     if (!fileValidation.valid) {
@@ -142,7 +165,7 @@ async function handleChatRequest(req: Request): Promise<Response> {
 
     // === CACHE CHECK START ===
     const isFirstMessage = messages.length === 1
-    const isEmptyDiagram = !xml || !hasCells(xml)
+    const isEmptyDiagram = !xml || xml.trim() === "" || isMinimalDiagram(xml)
 
     if (isFirstMessage && isEmptyDiagram) {
         const lastMessage = messages[0]
@@ -169,15 +192,6 @@ async function handleChatRequest(req: Request): Promise<Response> {
         baseUrl = `${origin}/api/edgeai`
     }
 
-    // Same rule as validate-model: with ALLOW_PRIVATE_URLS=false a request may
-    // not point the server at a private or internal address
-    if (baseUrl && !allowPrivateUrls() && (await isPrivateUrl(baseUrl))) {
-        return Response.json(
-            { error: "Private or internal base URLs are not allowed." },
-            { status: 400 },
-        )
-    }
-
     // Get cookie header for EdgeOne authentication (eo_token, eo_time)
     const cookieHeader = req.headers.get("cookie")
 
@@ -187,9 +201,8 @@ async function handleChatRequest(req: Request): Promise<Response> {
         baseUrlEnv?: string
         provider?: string
     } = {}
-    let serverModel: FlattenedServerModel | null = null
     if (selectedModelId?.startsWith("server:")) {
-        serverModel = await findServerModelById(selectedModelId)
+        const serverModel = await findServerModelById(selectedModelId)
         console.log(
             `[Server Model Lookup] ID: ${selectedModelId}, Found: ${!!serverModel}, Provider: ${serverModel?.provider}`,
         )
@@ -208,8 +221,7 @@ async function handleChatRequest(req: Request): Promise<Response> {
         provider: serverModelConfig.provider || provider,
         baseUrl,
         apiKey: req.headers.get("x-ai-api-key"),
-        // A server model runs the model it was configured with, whatever the header says
-        modelId: serverModel?.modelId || req.headers.get("x-ai-model"),
+        modelId: req.headers.get("x-ai-model"),
         // AWS Bedrock credentials
         awsAccessKeyId: req.headers.get("x-aws-access-key-id"),
         awsSecretAccessKey: req.headers.get("x-aws-secret-access-key"),
@@ -219,14 +231,11 @@ async function handleChatRequest(req: Request): Promise<Response> {
         ...serverModelConfig,
         // Vertex AI credentials (Express Mode)
         vertexApiKey: req.headers.get("x-vertex-api-key"),
-        // Pass cookies for EdgeOne Pages authentication, and the access code,
-        // which the EdgeOne function checks too
-        ...(provider === "edgeone" && {
-            headers: {
-                ...(cookieHeader && { cookie: cookieHeader }),
-                "x-access-code": req.headers.get("x-access-code") || "",
-            },
-        }),
+        // Pass cookies for EdgeOne Pages authentication
+        ...(provider === "edgeone" &&
+            cookieHeader && {
+                headers: { cookie: cookieHeader },
+            }),
     }
 
     // Read minimal style preference from header
@@ -240,66 +249,17 @@ async function handleChatRequest(req: Request): Promise<Response> {
     const {
         model: baseModel,
         providerOptions,
+        headers,
         modelId,
         provider: resolvedProvider,
     } = getAIModel(clientOverrides)
 
-    // On the server's own keys, only run models the server offers: a server
-    // model picked by id (its model name is fixed above) or one in AI_MODEL.
-    // With their own key, users can run any model.
-    const onServerCredentials = usesServerCredentials(
-        resolvedProvider,
-        clientOverrides,
-    )
-    const envModels =
-        process.env.AI_MODEL?.split(",").map((m) => m.trim()) || []
-    if (onServerCredentials && !serverModel && !envModels.includes(modelId)) {
-        return Response.json(
-            {
-                error: `Model "${modelId}" is not available on this server. Add your own API key in Settings to use it.`,
-            },
-            { status: 400 },
-        )
-    }
+    // Retry with a smaller budget if the provider rejects the requested one
+    const model = withOutputTokenLimitFallback(baseModel)
 
-    // === SERVER-SIDE QUOTA CHECK START ===
-    // Quota is opt-in (DYNAMODB_QUOTA_TABLE) and counts what runs on the
-    // server's keys. Decided by the key actually used: a key header the
-    // provider never reads must not skip it.
-    const countsQuota =
-        isQuotaEnabled() && onServerCredentials && userId !== "anonymous"
-    if (countsQuota) {
-        const quotaCheck = await checkAndIncrementRequest(userId, {
-            requests: Number(process.env.DAILY_REQUEST_LIMIT) || 10,
-            tokens: Number(process.env.DAILY_TOKEN_LIMIT) || 200000,
-            tpm: Number(process.env.TPM_LIMIT) || 20000,
-        })
-        if (!quotaCheck.allowed) {
-            return Response.json(
-                {
-                    error: quotaCheck.error,
-                    type: quotaCheck.type,
-                    used: quotaCheck.used,
-                    limit: quotaCheck.limit,
-                },
-                { status: 429 },
-            )
-        }
-    }
-    // === SERVER-SIDE QUOTA CHECK END ===
-
-    // Retry once if the provider rejects the requested budget, or (newer
-    // Claude models) the sampling or thinking settings
-    const model = withOutputTokenLimitFallback(
-        withDeprecatedParamsFallback(baseModel),
-    )
-
-    // The user setting can raise the budget only on their own key (in the
-    // desktop app every key is the user's); on the server's keys it can only
-    // lower it
+    // User setting wins over server env, so desktop users can raise it themselves
     const maxOutputTokens = resolveMaxOutputTokens(
         req.headers.get("x-max-output-tokens"),
-        onServerCredentials,
     )
     console.log(`[maxOutputTokens] ${maxOutputTokens}`)
 
@@ -334,37 +294,35 @@ ${userInputText}
     // Convert UIMessages to ModelMessages and add system message
     const modelMessages = await convertToModelMessages(messages)
 
-    // DEBUG_LLM_PAYLOAD=true logs the incoming message structure
-    if (DEBUG_LLM_PAYLOAD) {
-        console.log("[route.ts] Incoming messages count:", messages.length)
-        messages.forEach((msg: any, idx: number) => {
-            console.log(
-                `[route.ts] Message ${idx} role:`,
-                msg.role,
-                "parts count:",
-                msg.parts?.length,
-            )
-            if (msg.parts) {
-                msg.parts.forEach((part: any, partIdx: number) => {
-                    if (
-                        part.type === "tool-invocation" ||
-                        part.type === "tool-result"
-                    ) {
-                        console.log(`[route.ts]   Part ${partIdx}:`, {
-                            type: part.type,
-                            toolName: part.toolName,
-                            hasInput: !!part.input,
-                            inputType: typeof part.input,
-                            inputKeys:
-                                part.input && typeof part.input === "object"
-                                    ? Object.keys(part.input)
-                                    : null,
-                        })
-                    }
-                })
-            }
-        })
-    }
+    // DEBUG: Log incoming messages structure
+    console.log("[route.ts] Incoming messages count:", messages.length)
+    messages.forEach((msg: any, idx: number) => {
+        console.log(
+            `[route.ts] Message ${idx} role:`,
+            msg.role,
+            "parts count:",
+            msg.parts?.length,
+        )
+        if (msg.parts) {
+            msg.parts.forEach((part: any, partIdx: number) => {
+                if (
+                    part.type === "tool-invocation" ||
+                    part.type === "tool-result"
+                ) {
+                    console.log(`[route.ts]   Part ${partIdx}:`, {
+                        type: part.type,
+                        toolName: part.toolName,
+                        hasInput: !!part.input,
+                        inputType: typeof part.input,
+                        inputKeys:
+                            part.input && typeof part.input === "object"
+                                ? Object.keys(part.input)
+                                : null,
+                    })
+                }
+            })
+        }
+    })
 
     // Replace historical tool call XML with placeholders to reduce tokens
     // Disabled by default - some models (e.g. minimax) copy placeholders instead of generating XML
@@ -382,43 +340,61 @@ ${userInputText}
     )
 
     // Filter out tool-calls with invalid inputs (from failed repair or interrupted streaming)
-    // and their results. Bedrock API rejects messages where toolUse.input is not a valid
-    // JSON object, and every provider rejects a tool result whose call is gone.
-    enhancedMessages = dropInvalidToolCalls(enhancedMessages)
-
-    // DEBUG_LLM_PAYLOAD=true logs what is sent to the model
-    if (DEBUG_LLM_PAYLOAD) {
-        console.log("[route.ts] Model messages count:", enhancedMessages.length)
-        enhancedMessages.forEach((msg: any, idx: number) => {
-            console.log(
-                `[route.ts] ModelMsg ${idx} role:`,
-                msg.role,
-                "content count:",
-                msg.content?.length,
-            )
-            if (msg.content) {
-                msg.content.forEach((part: any, partIdx: number) => {
-                    if (
-                        part.type === "tool-call" ||
-                        part.type === "tool-result"
-                    ) {
-                        console.log(`[route.ts]   Content ${partIdx}:`, {
-                            type: part.type,
-                            toolName: part.toolName,
-                            hasInput: !!part.input,
-                            inputType: typeof part.input,
-                            inputValue:
-                                part.input === undefined
-                                    ? "undefined"
-                                    : part.input === null
-                                      ? "null"
-                                      : "object",
-                        })
-                    }
-                })
+    // Bedrock API rejects messages where toolUse.input is not a valid JSON object
+    enhancedMessages = enhancedMessages
+        .map((msg: any) => {
+            if (msg.role !== "assistant" || !Array.isArray(msg.content)) {
+                return msg
             }
+            const filteredContent = msg.content.filter((part: any) => {
+                if (part.type === "tool-call") {
+                    // Check if input is a valid object (not null, undefined, or empty)
+                    if (
+                        !part.input ||
+                        typeof part.input !== "object" ||
+                        Object.keys(part.input).length === 0
+                    ) {
+                        console.warn(
+                            `[route.ts] Filtering out tool-call with invalid input:`,
+                            { toolName: part.toolName, input: part.input },
+                        )
+                        return false
+                    }
+                }
+                return true
+            })
+            return { ...msg, content: filteredContent }
         })
-    }
+        .filter((msg: any) => msg.content && msg.content.length > 0)
+
+    // DEBUG: Log modelMessages structure (what's being sent to AI)
+    console.log("[route.ts] Model messages count:", enhancedMessages.length)
+    enhancedMessages.forEach((msg: any, idx: number) => {
+        console.log(
+            `[route.ts] ModelMsg ${idx} role:`,
+            msg.role,
+            "content count:",
+            msg.content?.length,
+        )
+        if (msg.content) {
+            msg.content.forEach((part: any, partIdx: number) => {
+                if (part.type === "tool-call" || part.type === "tool-result") {
+                    console.log(`[route.ts]   Content ${partIdx}:`, {
+                        type: part.type,
+                        toolName: part.toolName,
+                        hasInput: !!part.input,
+                        inputType: typeof part.input,
+                        inputValue:
+                            part.input === undefined
+                                ? "undefined"
+                                : part.input === null
+                                  ? "null"
+                                  : "object",
+                    })
+                }
+            })
+        }
+    })
 
     // Update the last message with user input only (XML moved to separate cached system message)
     if (enhancedMessages.length >= 1) {
@@ -434,7 +410,7 @@ ${userInputText}
                 contentParts.push({
                     type: "image",
                     image: filePart.url,
-                    mediaType: filePart.mediaType,
+                    mimeType: filePart.mediaType,
                 })
             }
 
@@ -454,7 +430,9 @@ ${userInputText}
             if (enhancedMessages[i].role === "assistant") {
                 enhancedMessages[i] = {
                     ...enhancedMessages[i],
-                    providerOptions: CACHE_POINT,
+                    providerOptions: {
+                        bedrock: { cachePoint: { type: "default" } },
+                    },
                 }
                 break // Only cache the last assistant message
             }
@@ -493,7 +471,7 @@ ${previousXml}
 ${xml || ""}
 """
 
-IMPORTANT: The "Current diagram XML" is the SINGLE SOURCE OF TRUTH for what's on the canvas right now. The user can manually add, delete, or modify shapes directly in draw.io. Always count and describe elements based on the CURRENT XML, not on what you previously generated. If both previous and current XML are shown, compare them to understand what the user changed.`
+IMPORTANT: The "Current diagram XML" is the SINGLE SOURCE OF TRUTH for what's on the canvas right now. The user can manually add, delete, or modify shapes directly in draw.io. Always count and describe elements based on the CURRENT XML, not on what you previously generated. If both previous and current XML are shown, compare them to understand what the user changed. When using edit_diagram, COPY search patterns exactly from the CURRENT XML - attribute order matters!`
 
     const systemMessages = isSingleSystemProvider
         ? [
@@ -507,13 +485,21 @@ IMPORTANT: The "Current diagram XML" is the SINGLE SOURCE OF TRUTH for what's on
               {
                   role: "system" as const,
                   content: finalSystemMessage,
-                  ...(shouldCache && { providerOptions: CACHE_POINT }),
+                  ...(shouldCache && {
+                      providerOptions: {
+                          bedrock: { cachePoint: { type: "default" } },
+                      },
+                  }),
               },
               // Cache breakpoint 2: Previous and Current diagram XML context
               {
                   role: "system" as const,
                   content: xmlContext,
-                  ...(shouldCache && { providerOptions: CACHE_POINT }),
+                  ...(shouldCache && {
+                      providerOptions: {
+                          bedrock: { cachePoint: { type: "default" } },
+                      },
+                  }),
               },
           ]
 
@@ -521,10 +507,6 @@ IMPORTANT: The "Current diagram XML" is the SINGLE SOURCE OF TRUTH for what's on
 
     const result = streamText({
         model,
-        // The system messages carry cache points, so they go in messages.
-        // A client's own system messages have string content and were
-        // dropped by the empty-content filter above.
-        allowSystemInMessages: true,
         abortSignal: req.signal,
         // Must be sent: unset means the provider's own default, and Bedrock's is
         // 4096, enough for a small diagram, so larger ones were cut off mid-attribute.
@@ -546,11 +528,23 @@ IMPORTANT: The "Current diagram XML" is the SINGLE SOURCE OF TRUTH for what's on
                 error.name === "AI_InvalidToolInputError"
             ) {
                 try {
-                    // Pre-process to fix common LLM JSON errors that jsonrepair can't handle,
-                    // then use jsonrepair to fix truncated JSON
-                    const repairedInput = jsonrepair(
-                        fixToolInputJson(toolCall.input),
-                    )
+                    // Pre-process to fix common LLM JSON errors that jsonrepair can't handle
+                    let inputToRepair = toolCall.input
+                    if (typeof inputToRepair === "string") {
+                        // Fix `:=` instead of `: ` (LLM sometimes generates this)
+                        inputToRepair = inputToRepair.replace(/:=/g, ": ")
+                        // Fix `= "` instead of `: "`
+                        inputToRepair = inputToRepair.replace(/=\s*"/g, ': "')
+                        // Fix inconsistent quote escaping in XML attributes within JSON strings
+                        // Pattern: attribute="value\" where opening quote is unescaped but closing is escaped
+                        // Example: y="-20\" should be y=\"-20\"
+                        inputToRepair = inputToRepair.replace(
+                            /(\w+)="([^"]*?)\\"/g,
+                            '$1=\\"$2\\"',
+                        )
+                    }
+                    // Use jsonrepair to fix truncated JSON
+                    const repairedInput = jsonrepair(inputToRepair)
                     console.log(
                         `[repairToolCall] Repaired truncated JSON for tool: ${toolCall.toolName}`,
                     )
@@ -560,8 +554,26 @@ IMPORTANT: The "Current diagram XML" is the SINGLE SOURCE OF TRUTH for what's on
                         `[repairToolCall] Failed to repair JSON for tool: ${toolCall.toolName}`,
                         repairError,
                     )
-                    // Keep the original error, so the model and the client see why
-                    // the input was rejected and the model can retry the call
+                    // Return a placeholder input to avoid API errors in multi-step
+                    // The tool will fail gracefully on client side
+                    if (toolCall.toolName === "edit_diagram") {
+                        return {
+                            ...toolCall,
+                            input: {
+                                operations: [],
+                                _error: "JSON repair failed - no operations to apply",
+                            },
+                        }
+                    }
+                    if (toolCall.toolName === "display_diagram") {
+                        return {
+                            ...toolCall,
+                            input: {
+                                xml: "",
+                                _error: "JSON repair failed - empty diagram",
+                            },
+                        }
+                    }
                     return null
                 }
             }
@@ -570,6 +582,7 @@ IMPORTANT: The "Current diagram XML" is the SINGLE SOURCE OF TRUTH for what's on
         },
         messages: allMessages,
         ...(providerOptions && { providerOptions }), // This now includes all reasoning configs
+        ...(headers && { headers }),
         // Langfuse telemetry config (returns undefined if not configured)
         ...(getTelemetryConfig({ sessionId: validSessionId, userId }) && {
             experimental_telemetry: getTelemetryConfig({
@@ -583,20 +596,21 @@ IMPORTANT: The "Current diagram XML" is the SINGLE SOURCE OF TRUTH for what's on
 
             // Record token usage for server-side quota tracking (if enabled)
             // Use totalUsage (cumulative across all steps) instead of usage (final step only)
-            // inputTokens already includes cache reads and writes in AI SDK 6
-            if (countsQuota && totalUsage) {
+            // Include all 4 token types: input, output, cache read, cache write
+            if (
+                isQuotaEnabled() &&
+                !hasOwnApiKey &&
+                userId !== "anonymous" &&
+                totalUsage
+            ) {
                 const totalTokens =
                     (totalUsage.inputTokens || 0) +
-                    (totalUsage.outputTokens || 0)
+                    (totalUsage.outputTokens || 0) +
+                    (totalUsage.cachedInputTokens || 0) +
+                    (totalUsage.inputTokenDetails?.cacheWriteTokens || 0)
                 recordTokenUsage(userId, totalTokens)
             }
         },
-        // onFinish is skipped when the stream fails or is aborted, so end the trace here
-        onError: ({ error }) => {
-            console.error(error) // what AI SDK does without an onError
-            endTrace()
-        },
-        onAbort: () => endTrace(),
         tools: {
             // Client-side tool that will be executed on the client
             display_diagram: {
@@ -611,7 +625,21 @@ VALIDATION RULES (XML will be rejected if violated):
 6. Escape special chars in values: &lt; &gt; &amp; &quot;
 
 Example (generate ONLY this - no wrapper tags):
-${SWIMLANE_EXAMPLE}
+<mxCell id="lane1" value="Frontend" style="swimlane;" vertex="1" parent="1">
+  <mxGeometry x="40" y="40" width="200" height="200" as="geometry"/>
+</mxCell>
+<mxCell id="step1" value="Step 1" style="rounded=1;" vertex="1" parent="lane1">
+  <mxGeometry x="20" y="60" width="160" height="40" as="geometry"/>
+</mxCell>
+<mxCell id="lane2" value="Backend" style="swimlane;" vertex="1" parent="1">
+  <mxGeometry x="280" y="40" width="200" height="200" as="geometry"/>
+</mxCell>
+<mxCell id="step2" value="Step 2" style="rounded=1;" vertex="1" parent="lane2">
+  <mxGeometry x="20" y="60" width="160" height="40" as="geometry"/>
+</mxCell>
+<mxCell id="edge1" style="edgeStyle=orthogonalEdgeStyle;endArrow=classic;" edge="1" parent="1" source="step1" target="step2">
+  <mxGeometry relative="1" as="geometry"/>
+</mxCell>
 
 Notes:
 - For AWS diagrams, use **AWS 2025 icons**.
@@ -689,7 +717,14 @@ Example: If previous output ended with '<mxCell id="x" style="rounded=1', contin
                 description: `Get draw.io shape/icon library documentation with style syntax and shape names.
 
 Available libraries:
-${SHAPE_LIBRARY_LIST}
+- Cloud: aws4, azure2, gcp2, alibaba_cloud, openstack, salesforce
+- Networking: cisco19, network, kubernetes, vvd, rack
+- Business: bpmn, lean_mapping
+- General: flowchart, basic, arrows2, infographic, sitemap
+- UI/Mockups: android, material_design
+- Enterprise: citrix, sap, mscae, atlassian
+- Engineering: fluidpower, electrical, pid, cabinets, floorplan
+- Icons: webicons
 
 Call this tool to get shape names and usage syntax for a specific library.`,
                 inputSchema: z.object({
@@ -700,12 +735,45 @@ Call this tool to get shape names and usage syntax for a specific library.`,
                         ),
                 }),
                 execute: async ({ library }) => {
-                    // Only known library names reach the file system
-                    const result = await getShapeLibrary(
-                        library,
-                        path.join(process.cwd(), "docs/shape-libraries"),
+                    // Sanitize input - prevent path traversal attacks
+                    const sanitizedLibrary = library
+                        .toLowerCase()
+                        .replace(/[^a-z0-9_-]/g, "")
+
+                    if (sanitizedLibrary !== library.toLowerCase()) {
+                        return `Invalid library name "${library}". Use only letters, numbers, underscores, and hyphens.`
+                    }
+
+                    const baseDir = path.join(
+                        process.cwd(),
+                        "docs/shape-libraries",
                     )
-                    return result.ok ? result.text : result.error
+                    const filePath = path.join(
+                        baseDir,
+                        `${sanitizedLibrary}.md`,
+                    )
+
+                    // Verify path stays within expected directory
+                    const resolvedPath = path.resolve(filePath)
+                    if (!resolvedPath.startsWith(path.resolve(baseDir))) {
+                        return `Invalid library path.`
+                    }
+
+                    try {
+                        const content = await fs.readFile(filePath, "utf-8")
+                        return content
+                    } catch (error) {
+                        if (
+                            (error as NodeJS.ErrnoException).code === "ENOENT"
+                        ) {
+                            return `Library "${library}" not found. Available: aws4, azure2, gcp2, alibaba_cloud, cisco19, kubernetes, network, bpmn, flowchart, basic, arrows2, vvd, salesforce, citrix, sap, mscae, atlassian, fluidpower, electrical, pid, cabinets, floorplan, webicons, infographic, sitemap, android, material_design, lean_mapping, openstack, rack`
+                        }
+                        console.error(
+                            `[get_shape_library] Error loading "${library}":`,
+                            error,
+                        )
+                        return `Error loading library "${library}". Please try again.`
+                    }
                 },
             },
         },
@@ -714,9 +782,8 @@ Call this tool to get shape names and usage syntax for a specific library.`,
         }),
     })
 
-    const response = result.toUIMessageStreamResponse({
+    return result.toUIMessageStreamResponse({
         sendReasoning: true,
-        onError: (error) => streamErrorText(error, onServerCredentials),
         messageMetadata: ({ part }) => {
             if (part.type === "finish") {
                 const usage = (part as any).totalUsage
@@ -729,28 +796,63 @@ Call this tool to get shape names and usage syntax for a specific library.`,
             return undefined
         },
     })
-    modelStreamResponses.add(response)
-    return response
 }
 
-// Errors before the stream starts, as JSON the chat panel reads
+// Helper to categorize errors and return appropriate response
 function handleError(error: unknown): Response {
     console.error("Error in chat route:", error)
 
     const isDev = process.env.NODE_ENV === "development"
-    const classified = classifyLLMError(error)
-    const status =
-        (error as { statusCode?: number })?.statusCode ||
-        (error as { status?: number })?.status ||
-        (classified.code === "invalid_api_key" ? 401 : 500)
+
+    // Check for specific AI SDK error types
+    if (APICallError.isInstance(error)) {
+        return Response.json(
+            {
+                error: error.message,
+                ...(isDev && {
+                    details: error.responseBody,
+                    stack: error.stack,
+                }),
+            },
+            { status: error.statusCode || 500 },
+        )
+    }
+
+    if (LoadAPIKeyError.isInstance(error)) {
+        return Response.json(
+            {
+                error: "Authentication failed. Please check your API key.",
+                ...(isDev && {
+                    stack: error.stack,
+                }),
+            },
+            { status: 401 },
+        )
+    }
+
+    // Fallback for other errors with safety filter
+    const message =
+        error instanceof Error ? error.message : "An unexpected error occurred"
+    const status = (error as any)?.statusCode || (error as any)?.status || 500
+
+    // Prevent leaking API keys, tokens, or other sensitive data
+    const lowerMessage = message.toLowerCase()
+    const safeMessage =
+        lowerMessage.includes("key") ||
+        lowerMessage.includes("token") ||
+        lowerMessage.includes("sig") ||
+        lowerMessage.includes("signature") ||
+        lowerMessage.includes("secret") ||
+        lowerMessage.includes("password") ||
+        lowerMessage.includes("credential")
+            ? "Authentication failed. Please check your credentials."
+            : message
 
     return Response.json(
         {
-            ...classified,
+            error: safeMessage,
             ...(isDev && {
-                details: APICallError.isInstance(error)
-                    ? error.responseBody
-                    : undefined,
+                details: message,
                 stack: error instanceof Error ? error.stack : undefined,
             }),
         },
@@ -760,16 +862,11 @@ function handleError(error: unknown): Response {
 
 // Wrap handler with error handling
 async function safeHandler(req: Request): Promise<Response> {
-    let response: Response
     try {
-        response = await handleChatRequest(req)
+        return await handleChatRequest(req)
     } catch (error) {
-        response = handleError(error)
+        return handleError(error)
     }
-    // Early returns, cache hits and errors never reach streamText's callbacks,
-    // so their Langfuse trace has to be ended here
-    if (!modelStreamResponses.has(response)) endTrace()
-    return response
 }
 
 // Wrap with Langfuse observe (if configured)

app/api/log-save/route.ts

@@ -4,7 +4,7 @@ import { getLangfuseClient } from "@/lib/langfuse"
 
 const saveSchema = z.object({
     filename: z.string().min(1).max(255),
-    format: z.enum(["drawio", "png", "svg", "xmlsvg"]),
+    format: z.enum(["drawio", "png", "svg"]),
     sessionId: z.string().min(1).max(200).optional(),
 })
 

app/api/parse-url/route.ts

@@ -1,11 +1,9 @@
 import { extractFromHtml } from "@extractus/article-extractor"
 import { NextResponse } from "next/server"
 import TurndownService from "turndown"
-import { checkAccessCode } from "@/lib/access-code"
 import { isPrivateUrl } from "@/lib/ssrf-protection"
 
 const MAX_CONTENT_LENGTH = 150000 // Match PDF limit
-const MAX_RESPONSE_BYTES = 5 * 1024 * 1024
 const EXTRACT_TIMEOUT_MS = 15000
 const USER_AGENT = "Mozilla/5.0 (compatible; NextAIDrawio/1.0)"
 
@@ -34,36 +32,7 @@ function detectCharset(
     }
 }
 
-// Read the response body, giving up once it passes MAX_RESPONSE_BYTES so a
-// huge download can't exhaust server memory. Returns null when too large.
-async function readLimitedBody(
-    response: Response,
-): Promise<ArrayBuffer | null> {
-    if (Number(response.headers.get("content-length")) > MAX_RESPONSE_BYTES) {
-        return null
-    }
-    if (!response.body) return new ArrayBuffer(0)
-
-    const reader = response.body.getReader()
-    const chunks: Uint8Array[] = []
-    let total = 0
-    while (true) {
-        const { done, value } = await reader.read()
-        if (done) break
-        total += value.byteLength
-        if (total > MAX_RESPONSE_BYTES) {
-            await reader.cancel()
-            return null
-        }
-        chunks.push(value)
-    }
-    return new Blob(chunks as BlobPart[]).arrayBuffer()
-}
-
 export async function POST(req: Request) {
-    const accessError = checkAccessCode(req)
-    if (accessError) return accessError
-
     try {
         const { url } = await req.json()
 
@@ -128,15 +97,7 @@ export async function POST(req: Request) {
                 )
             }
 
-            const buffer = await readLimitedBody(response)
-            if (!buffer) {
-                return NextResponse.json(
-                    {
-                        error: `Page exceeds the ${MAX_RESPONSE_BYTES / 1024 / 1024} MB download limit`,
-                    },
-                    { status: 413 },
-                )
-            }
+            const buffer = await response.arrayBuffer()
             const charset = detectCharset(contentType, buffer)
             html = new TextDecoder(charset).decode(buffer)
         } catch (err: any) {

app/api/provider-models/route.ts

@@ -1,62 +0,0 @@
-import { NextResponse } from "next/server"
-import { checkAccessCode } from "@/lib/access-code"
-import { classifyLLMError } from "@/lib/llm-errors"
-import { canListModels, listProviderModels } from "@/lib/provider-models"
-import {
-    allowPrivateUrls,
-    isPrivateUrl,
-    redirectGuardedFetch,
-} from "@/lib/ssrf-protection"
-import type { ProviderName } from "@/lib/types/model-config"
-
-export const runtime = "nodejs"
-
-// Public lists need no key
-const NO_KEY_NEEDED = new Set<ProviderName>([
-    "ollama",
-    "openrouter",
-    "aihubmix",
-])
-
-/**
- * The models a provider offers, for the "Fetch models" button in model
- * settings. Answers { models: null } for providers that cannot list them,
- * so the dialog keeps its suggested models.
- */
-export async function POST(req: Request) {
-    // Sends requests to a URL the client chose, so require the access code
-    const accessError = checkAccessCode(req)
-    if (accessError) return accessError
-
-    const { provider, apiKey, baseUrl } = (await req.json()) as {
-        provider: ProviderName
-        apiKey?: string
-        baseUrl?: string
-    }
-    if (!canListModels(provider)) {
-        return NextResponse.json({ models: null })
-    }
-    // SECURITY: Block SSRF attacks via custom baseUrl
-    if (baseUrl && !allowPrivateUrls() && (await isPrivateUrl(baseUrl))) {
-        return NextResponse.json({ error: "Invalid base URL" }, { status: 400 })
-    }
-    if (!apiKey && !NO_KEY_NEEDED.has(provider)) {
-        return NextResponse.json(
-            { error: "API key is required" },
-            { status: 400 },
-        )
-    }
-
-    try {
-        const models = await listProviderModels(
-            provider,
-            { apiKey, baseUrl },
-            (baseUrl && redirectGuardedFetch()) || fetch,
-        )
-        return NextResponse.json({ models })
-    } catch (error) {
-        console.warn("[provider-models] Listing failed:", error)
-        const { code, message } = classifyLLMError(error)
-        return NextResponse.json({ code, error: message })
-    }
-}

app/api/validate-diagram/route.ts

@@ -3,8 +3,7 @@
  * Accepts a PNG image and streams validation results using useObject-compatible format.
  */
 
-import { Output, streamText } from "ai"
-import { checkAccessCode } from "@/lib/access-code"
+import { streamObject } from "ai"
 import { getValidationModel } from "@/lib/ai-providers"
 import { VALIDATION_SYSTEM_PROMPT } from "@/lib/validation-prompts"
 import {
@@ -14,9 +13,6 @@ import {
 
 export const maxDuration = 30
 
-// Data URL length cap (~3.75 MB of PNG), well above a normal diagram capture
-const MAX_IMAGE_DATA_LENGTH = 5 * 1024 * 1024
-
 interface ValidateDiagramRequest {
     imageData: string // Base64 PNG data URL
     sessionId?: string
@@ -29,18 +25,25 @@ const DEFAULT_VALID_RESULT: ValidationResult = {
     suggestions: [],
 }
 
-/** A fixed result in the text format useObject reads */
+/**
+ * Create a streaming response for useObject compatibility.
+ * useObject expects text stream format, not plain JSON.
+ */
 function createStreamingResponse(result: ValidationResult): Response {
-    return new Response(JSON.stringify(result), {
+    const encoder = new TextEncoder()
+    const stream = new ReadableStream({
+        start(controller) {
+            // Stream the JSON as text (useObject parses this)
+            controller.enqueue(encoder.encode(JSON.stringify(result)))
+            controller.close()
+        },
+    })
+    return new Response(stream, {
         headers: { "Content-Type": "text/plain; charset=utf-8" },
     })
 }
 
 export async function POST(req: Request): Promise<Response> {
-    // Uses the server's model credentials, so require the access code
-    const accessError = checkAccessCode(req)
-    if (accessError) return accessError
-
     try {
         // Check if VLM validation is enabled (default: true)
         const enableValidation = process.env.ENABLE_VLM_VALIDATION !== "false"
@@ -69,13 +72,6 @@ export async function POST(req: Request): Promise<Response> {
             )
         }
 
-        if (imageData.length > MAX_IMAGE_DATA_LENGTH) {
-            return Response.json(
-                { error: "Image data too large" },
-                { status: 413 },
-            )
-        }
-
         // Get the validation model
         let model
         try {
@@ -97,9 +93,9 @@ export async function POST(req: Request): Promise<Response> {
             ) || 10000
 
         // Stream the VLM response for useObject consumption
-        const result = streamText({
+        const result = streamObject({
             model,
-            output: Output.object({ schema: ValidationResultSchema }),
+            schema: ValidationResultSchema,
             system: VALIDATION_SYSTEM_PROMPT,
             messages: [
                 {
@@ -118,10 +114,10 @@ export async function POST(req: Request): Promise<Response> {
             ],
             maxOutputTokens: 1024,
             abortSignal: AbortSignal.timeout(timeout),
-            onFinish: ({ output }) => {
-                if (sessionId && output) {
+            onFinish: ({ object }) => {
+                if (sessionId && object) {
                     console.log(
-                        `[validate-diagram] Session ${sessionId}: valid=${output.valid}, issues=${output.issues?.length ?? 0}`,
+                        `[validate-diagram] Session ${sessionId}: valid=${object.valid}, issues=${object.issues?.length ?? 0}`,
                     )
                 }
             },

app/api/validate-model/route.ts

@@ -1,16 +1,27 @@
-import { streamText, tool } from "ai"
+import { createAmazonBedrock } from "@ai-sdk/amazon-bedrock"
+import { createAnthropic } from "@ai-sdk/anthropic"
+import { createDeepSeek, deepseek } from "@ai-sdk/deepseek"
+import { createGateway } from "@ai-sdk/gateway"
+import { createGoogleGenerativeAI } from "@ai-sdk/google"
+import { createVertex } from "@ai-sdk/google-vertex"
+import { createOpenAI } from "@ai-sdk/openai"
+import { createAihubmix } from "@aihubmix/ai-sdk-provider"
+import { createOpenRouter } from "@openrouter/ai-sdk-provider"
+import { generateText } from "ai"
 import { NextResponse } from "next/server"
-import { z } from "zod"
-import { checkAccessCode } from "@/lib/access-code"
-import { getAIModel, usesServerCredentials } from "@/lib/ai-providers"
-import { classifyLLMError } from "@/lib/llm-errors"
+import { createOllama } from "ollama-ai-provider-v2"
+import {
+    AIHUBMIX_APP_CODE,
+    isAihubmixStandardBaseURL,
+    normalizeMiniMaxBaseURL,
+} from "@/lib/ai-providers"
 import { allowPrivateUrls, isPrivateUrl } from "@/lib/ssrf-protection"
-import type { ProviderName } from "@/lib/types/model-config"
+import { PROVIDER_INFO, type ProviderName } from "@/lib/types/model-config"
 
 export const runtime = "nodejs"
 
 interface ValidateRequest {
-    provider: ProviderName
+    provider: string
     apiKey: string
     baseUrl?: string
     modelId: string
@@ -22,22 +33,7 @@ interface ValidateRequest {
     vertexApiKey?: string // Express Mode API key
 }
 
-const TEST_TIMEOUT_MS = 15_000
-
-// Drawing works through tool calls, so the test asks for one
-const PING_TOOL = tool({
-    description: "Report that the connection works.",
-    inputSchema: z.object({}),
-})
-
-const NO_TOOL_CALL_WARNING =
-    "Connected, but the model answered without calling a tool. It may not support tool calls, which drawing needs."
-
 export async function POST(req: Request) {
-    // Lets the server send requests to arbitrary URLs, so require the access code
-    const accessError = checkAccessCode(req)
-    if (accessError) return accessError
-
     try {
         const body: ValidateRequest = await req.json()
         const {
@@ -94,87 +90,369 @@ export async function POST(req: Request) {
                 { status: 400 },
             )
         }
-        // The Test button checks the user's own provider. On the server's
-        // keys (Ollama Cloud without a key or URL) anyone could run any model.
-        if (
-            usesServerCredentials(provider, {
-                apiKey,
-                baseUrl,
-                awsAccessKeyId,
-                awsSecretAccessKey,
-                vertexApiKey,
-            })
-        ) {
-            return NextResponse.json(
-                { valid: false, error: "API key is required" },
-                { status: 400 },
-            )
-        }
 
-        // The same model the chat would use. A client base URL makes it
-        // refuse redirects to internal hosts.
-        const { model } = getAIModel({
-            provider,
-            modelId,
-            apiKey,
-            baseUrl,
-            awsAccessKeyId,
-            awsSecretAccessKey,
-            awsRegion,
-            vertexApiKey,
-            // EdgeOne checks the Pages cookies and the access code
-            ...(provider === "edgeone" && {
-                headers: {
-                    cookie: req.headers.get("cookie") || "",
-                    "x-access-code": req.headers.get("x-access-code") || "",
-                },
-            }),
-        })
+        let model: any
 
-        // Streaming, like the chat (some models only stream). Stop at the
-        // first tool call; a reasoning model that runs out of tokens first
-        // proves the connection but not tool support.
-        const startTime = Date.now()
-        const result = streamText({
-            model,
-            prompt: "Call the ping tool.",
-            tools: { ping: PING_TOOL },
-            maxOutputTokens: 1024,
-            maxRetries: 0,
-            abortSignal: AbortSignal.timeout(TEST_TIMEOUT_MS),
-        })
-        let calledTool = false
-        let finishReason: string | undefined
-        for await (const part of result.fullStream) {
-            if (part.type === "error") throw part.error
-            // The timeout ends the stream with an abort part, not an error
-            if (part.type === "abort") {
-                const timeout = new Error(
-                    `The model did not answer within ${TEST_TIMEOUT_MS / 1000} s.`,
-                )
-                timeout.name = "TimeoutError"
-                throw timeout
-            }
-            if (part.type === "tool-call") {
-                calledTool = true
+        switch (provider) {
+            case "openai": {
+                const openai = createOpenAI({
+                    apiKey,
+                    ...(baseUrl && { baseURL: baseUrl }),
+                })
+                model = openai.chat(modelId)
                 break
             }
-            if (part.type === "finish") finishReason = part.finishReason
+
+            case "anthropic": {
+                const anthropic = createAnthropic({
+                    apiKey,
+                    baseURL: baseUrl || "https://api.anthropic.com/v1",
+                })
+                model = anthropic(modelId)
+                break
+            }
+
+            case "google": {
+                const google = createGoogleGenerativeAI({
+                    apiKey,
+                    ...(baseUrl && { baseURL: baseUrl }),
+                })
+                model = google(modelId)
+                break
+            }
+
+            case "vertexai": {
+                const vertex = createVertex({
+                    apiKey: vertexApiKey,
+                    ...(baseUrl && { baseURL: baseUrl }),
+                })
+                model = vertex(modelId)
+                break
+            }
+
+            case "azure": {
+                const azure = createOpenAI({
+                    apiKey,
+                    baseURL: baseUrl,
+                })
+                model = azure.chat(modelId)
+                break
+            }
+
+            case "bedrock": {
+                const bedrock = createAmazonBedrock({
+                    accessKeyId: awsAccessKeyId,
+                    secretAccessKey: awsSecretAccessKey,
+                    region: awsRegion,
+                })
+                model = bedrock(modelId)
+                break
+            }
+
+            case "openrouter": {
+                const openrouter = createOpenRouter({
+                    apiKey,
+                    ...(baseUrl && { baseURL: baseUrl }),
+                })
+                model = openrouter(modelId)
+                break
+            }
+
+            case "aihubmix": {
+                const defaultBaseURL = PROVIDER_INFO.aihubmix.defaultBaseUrl
+
+                if (
+                    isAihubmixStandardBaseURL(baseUrl) ||
+                    baseUrl === defaultBaseURL
+                ) {
+                    const aihubmix = createAihubmix({
+                        apiKey,
+                        appCode: AIHUBMIX_APP_CODE,
+                    })
+                    model = aihubmix(modelId)
+                } else {
+                    const aihubmixCompatible = createOpenAI({
+                        apiKey,
+                        baseURL: baseUrl,
+                    })
+                    model = aihubmixCompatible.chat(modelId)
+                }
+                break
+            }
+
+            case "deepseek": {
+                if (baseUrl || apiKey) {
+                    const ds = createDeepSeek({
+                        apiKey,
+                        ...(baseUrl && { baseURL: baseUrl }),
+                    })
+                    model = ds(modelId)
+                } else {
+                    model = deepseek(modelId)
+                }
+                break
+            }
+
+            case "siliconflow": {
+                const sf = createOpenAI({
+                    apiKey,
+                    baseURL: baseUrl || "https://api.siliconflow.cn/v1",
+                })
+                model = sf.chat(modelId)
+                break
+            }
+
+            case "ollama": {
+                // SECURITY: Mirror ai-providers.ts guard — only use server
+                // OLLAMA_API_KEY when the URL is also from server config.
+                const ollamaApiKey = baseUrl
+                    ? apiKey || undefined
+                    : apiKey || process.env.OLLAMA_API_KEY || undefined
+                const ollamaProvider = createOllama({
+                    baseURL:
+                        baseUrl ||
+                        process.env.OLLAMA_BASE_URL ||
+                        "https://ollama.com/api",
+                    ...(ollamaApiKey && {
+                        headers: { Authorization: `Bearer ${ollamaApiKey}` },
+                    }),
+                })
+                model = ollamaProvider(modelId)
+                break
+            }
+
+            case "gateway": {
+                const gw = createGateway({
+                    apiKey,
+                    ...(baseUrl && { baseURL: baseUrl }),
+                })
+                model = gw(modelId)
+                break
+            }
+
+            case "edgeone": {
+                // EdgeOne uses OpenAI-compatible API via Edge Functions
+                // Need to pass cookies for EdgeOne Pages authentication
+                const cookieHeader = req.headers.get("cookie") || ""
+                const edgeone = createOpenAI({
+                    apiKey: "edgeone", // EdgeOne doesn't require API key
+                    baseURL: baseUrl || "/api/edgeai",
+                    headers: {
+                        cookie: cookieHeader,
+                    },
+                })
+                model = edgeone.chat(modelId)
+                break
+            }
+
+            case "sglang": {
+                // SGLang is OpenAI-compatible
+                const sglang = createOpenAI({
+                    apiKey: apiKey || "not-needed",
+                    baseURL: baseUrl || "http://127.0.0.1:8000/v1",
+                })
+                model = sglang.chat(modelId)
+                break
+            }
+
+            case "doubao": {
+                // ByteDance Doubao: use DeepSeek for DeepSeek/Kimi models, OpenAI for others
+                const doubaoBaseUrl =
+                    baseUrl || "https://ark.cn-beijing.volces.com/api/v3"
+                const lowerModelId = modelId.toLowerCase()
+                if (
+                    lowerModelId.includes("deepseek") ||
+                    lowerModelId.includes("kimi")
+                ) {
+                    const doubao = createDeepSeek({
+                        apiKey,
+                        baseURL: doubaoBaseUrl,
+                    })
+                    model = doubao(modelId)
+                } else {
+                    const doubao = createOpenAI({
+                        apiKey,
+                        baseURL: doubaoBaseUrl,
+                    })
+                    model = doubao.chat(modelId)
+                }
+                break
+            }
+
+            case "modelscope": {
+                const baseURL =
+                    baseUrl || "https://api-inference.modelscope.cn/v1"
+                const startTime = Date.now()
+
+                try {
+                    // Initiate a streaming request (required for QwQ-32B and certain Qwen3 models)
+                    const response = await fetch(
+                        `${baseURL}/chat/completions`,
+                        {
+                            method: "POST",
+                            headers: {
+                                "Content-Type": "application/json",
+                                Authorization: `Bearer ${apiKey}`,
+                            },
+                            body: JSON.stringify({
+                                model: modelId,
+                                messages: [
+                                    { role: "user", content: "Say 'OK'" },
+                                ],
+                                max_tokens: 20,
+                                stream: true,
+                                enable_thinking: false,
+                            }),
+                        },
+                    )
+
+                    if (!response.ok) {
+                        const errorText = await response.text()
+                        throw new Error(
+                            `ModelScope API error (${response.status}): ${errorText}`,
+                        )
+                    }
+
+                    const contentType =
+                        response.headers.get("content-type") || ""
+                    const isValidStreamingResponse =
+                        response.status === 200 &&
+                        (contentType.includes("text/event-stream") ||
+                            contentType.includes("application/json"))
+
+                    if (!isValidStreamingResponse) {
+                        throw new Error(
+                            `Unexpected response format: ${contentType}`,
+                        )
+                    }
+
+                    const responseTime = Date.now() - startTime
+
+                    if (response.body) {
+                        response.body.cancel().catch(() => {
+                            /* Ignore cancellation errors */
+                        })
+                    }
+
+                    return NextResponse.json({
+                        valid: true,
+                        responseTime,
+                        note: "ModelScope model validated (using streaming API)",
+                    })
+                } catch (error) {
+                    console.error(
+                        "[validate-model] ModelScope validation failed:",
+                        error,
+                    )
+                    throw error
+                }
+            }
+
+            case "minimax": {
+                const rawUrl =
+                    baseUrl ||
+                    PROVIDER_INFO.minimax?.defaultBaseUrl ||
+                    "https://api.minimaxi.com/anthropic"
+                const { baseURL: minimaxBaseUrl, isAnthropicCompatible } =
+                    normalizeMiniMaxBaseURL(rawUrl)
+
+                if (isAnthropicCompatible) {
+                    const minimax = createAnthropic({
+                        apiKey,
+                        baseURL: minimaxBaseUrl,
+                    })
+                    model = minimax.chat(modelId)
+                } else {
+                    const minimax = createOpenAI({
+                        apiKey,
+                        baseURL: minimaxBaseUrl,
+                    })
+                    model = minimax.chat(modelId)
+                }
+                break
+            }
+
+            // GLM, Qwen, Kimi, Qiniu, Novita, MiMo, Atlas Cloud - OpenAI compatible
+            case "glm":
+            case "qwen":
+            case "kimi":
+            case "qiniu":
+            case "novita":
+            case "atlascloud":
+            case "mimo": {
+                const baseURL =
+                    baseUrl ||
+                    PROVIDER_INFO[provider as ProviderName]?.defaultBaseUrl ||
+                    ""
+
+                if (!baseURL) {
+                    return NextResponse.json(
+                        {
+                            valid: false,
+                            error: `No base URL configured for provider: ${provider}`,
+                        },
+                        { status: 400 },
+                    )
+                }
+
+                const openai = createOpenAI({
+                    apiKey,
+                    baseURL,
+                })
+                model = openai.chat(modelId)
+                break
+            }
+
+            default:
+                return NextResponse.json(
+                    { valid: false, error: `Unknown provider: ${provider}` },
+                    { status: 400 },
+                )
         }
+
+        // Make a minimal test request
+        const startTime = Date.now()
+        await generateText({
+            model,
+            prompt: "Say 'OK'",
+            maxOutputTokens: 20,
+        })
         const responseTime = Date.now() - startTime
 
         return NextResponse.json({
             valid: true,
             responseTime,
-            ...(!calledTool &&
-                finishReason !== "length" && { warning: NO_TOOL_CALL_WARNING }),
         })
     } catch (error) {
         console.error("[validate-model] Error:", error)
 
-        const { code, message } = classifyLLMError(error)
+        let errorMessage = "Validation failed"
+        if (error instanceof Error) {
+            // Extract meaningful error message
+            if (
+                error.message.includes("401") ||
+                error.message.includes("Unauthorized")
+            ) {
+                errorMessage = "Invalid API key"
+            } else if (
+                error.message.includes("404") ||
+                error.message.includes("not found")
+            ) {
+                errorMessage = "Model not found"
+            } else if (
+                error.message.includes("429") ||
+                error.message.includes("rate limit")
+            ) {
+                errorMessage = "Rate limited - try again later"
+            } else if (error.message.includes("ECONNREFUSED")) {
+                errorMessage = "Cannot connect to server"
+            } else {
+                errorMessage = error.message.slice(0, 100)
+            }
+        }
+
         return NextResponse.json(
-            { valid: false, code, error: message },
+            { valid: false, error: errorMessage },
             { status: 200 }, // Return 200 so client can read error message
         )
     }

app/api/verify-access-code/route.ts

@@ -1,9 +1,29 @@
-import { checkAccessCode } from "@/lib/access-code"
-
 export async function POST(req: Request) {
-    if (checkAccessCode(req)) {
+    const accessCodes =
+        process.env.ACCESS_CODE_LIST?.split(",")
+            .map((code) => code.trim())
+            .filter(Boolean) || []
+
+    // If no access codes configured, verification always passes
+    if (accessCodes.length === 0) {
+        return Response.json({
+            valid: true,
+            message: "No access code required",
+        })
+    }
+
+    const accessCodeHeader = req.headers.get("x-access-code")
+
+    if (!accessCodeHeader) {
         return Response.json(
-            { valid: false, message: "Invalid or missing access code" },
+            { valid: false, message: "Access code is required" },
+            { status: 401 },
+        )
+    }
+
+    if (!accessCodes.includes(accessCodeHeader)) {
+        return Response.json(
+            { valid: false, message: "Invalid access code" },
             { status: 401 },
         )
     }

biome.json

@@ -7,12 +7,7 @@
     },
     "files": {
         "ignoreUnknown": false,
-        "includes": [
-            "**",
-            "!public",
-            "!packages/mcp-server/src/preview",
-            "!lib/model-catalog.json"
-        ]
+        "includes": ["**", "!public"]
     },
     "formatter": {
         "enabled": true,

components/chat-input.tsx

@@ -11,9 +11,7 @@ import {
 } from "lucide-react"
 import type React from "react"
 import {
-    type Dispatch,
     forwardRef,
-    type SetStateAction,
     useCallback,
     useEffect,
     useImperativeHandle,
@@ -43,20 +41,9 @@ import { FilePreviewList } from "./file-preview-list"
 
 const MAX_IMAGE_SIZE = 2 * 1024 * 1024 // 2MB
 const MAX_FILES = 5
-// Image formats every supported model provider accepts (SVG is read as text)
-const SUPPORTED_IMAGE_TYPES = [
-    "image/png",
-    "image/jpeg",
-    "image/gif",
-    "image/webp",
-]
 
 function isValidFileType(file: File): boolean {
-    return (
-        SUPPORTED_IMAGE_TYPES.includes(file.type) ||
-        isPdfFile(file) ||
-        isTextFile(file)
-    )
+    return file.type.startsWith("image/") || isPdfFile(file) || isTextFile(file)
 }
 
 function formatFileSize(bytes: number): string {
@@ -177,7 +164,7 @@ interface ChatInputProps {
         { text: string; charCount: number; isExtracting: boolean }
     >
     urlData?: Map<string, UrlData>
-    onUrlChange?: Dispatch<SetStateAction<Map<string, UrlData>>>
+    onUrlChange?: (data: Map<string, UrlData>) => void
 
     sessionId?: string
     error?: Error | null
@@ -257,11 +244,6 @@ export const ChatInput = forwardRef<ChatInputRef, ChatInputProps>(
         // Allow retry when there's an error (even if status is still "streaming" or "submitted")
         const isDisabled =
             (status === "streaming" || status === "submitted") && !error
-        // Block sending until attached files and URLs have their text, otherwise
-        // their content would be silently dropped
-        const isExtractingAttachments =
-            files.some((file) => pdfData.get(file)?.isExtracting) ||
-            Array.from(urlData?.values() ?? []).some((d) => d.isExtracting)
 
         const adjustTextareaHeight = useCallback(() => {
             const textarea = textareaRef.current
@@ -299,9 +281,6 @@ export const ChatInput = forwardRef<ChatInputRef, ChatInputProps>(
         }
 
         const handleKeyDown = (e: React.KeyboardEvent) => {
-            // Enter that confirms an IME candidate must not send the message
-            if (e.nativeEvent.isComposing || e.keyCode === 229) return
-
             const shouldSend =
                 sendShortcut === "enter"
                     ? e.key === "Enter" &&
@@ -313,12 +292,7 @@ export const ChatInput = forwardRef<ChatInputRef, ChatInputProps>(
             if (shouldSend) {
                 e.preventDefault()
                 const form = e.currentTarget.closest("form")
-                if (
-                    form &&
-                    input.trim() &&
-                    !isDisabled &&
-                    !isExtractingAttachments
-                ) {
+                if (form && input.trim() && !isDisabled) {
                     form.requestSubmit()
                 }
             }
@@ -406,9 +380,13 @@ export const ChatInput = forwardRef<ChatInputRef, ChatInputProps>(
 
             if (isDisabled) return
 
-            // Let validateFiles show a toast for unsupported types
+            const droppedFiles = e.dataTransfer.files
+            const supportedFiles = Array.from(droppedFiles).filter((file) =>
+                isValidFileType(file),
+            )
+
             const { validFiles, errors } = validateFiles(
-                Array.from(e.dataTransfer.files),
+                supportedFiles,
                 files.length,
                 dict,
             )
@@ -423,34 +401,33 @@ export const ChatInput = forwardRef<ChatInputRef, ChatInputProps>(
 
             setIsExtractingUrl(true)
 
-            // Use functional updates so a removal or send made while extracting
-            // is not overwritten when the request finishes
             try {
-                onUrlChange((prev) =>
-                    new Map(prev).set(url, {
-                        url,
-                        title: url,
-                        content: "",
-                        charCount: 0,
-                        isExtracting: true,
-                    }),
-                )
+                const existing = urlData
+                    ? new Map(urlData)
+                    : new Map<string, UrlData>()
+                existing.set(url, {
+                    url,
+                    title: url,
+                    content: "",
+                    charCount: 0,
+                    isExtracting: true,
+                })
+                onUrlChange(existing)
 
                 const data = await extractUrlContent(url)
 
-                // Skip if the URL was removed while extracting
-                onUrlChange((prev) =>
-                    prev.has(url) ? new Map(prev).set(url, data) : prev,
-                )
+                const newUrlData = new Map(existing)
+                newUrlData.set(url, data)
+                onUrlChange(newUrlData)
 
                 setShowUrlDialog(false)
             } catch (error) {
                 // Remove the URL from the data map on error
-                onUrlChange((prev) => {
-                    const next = new Map(prev)
-                    next.delete(url)
-                    return next
-                })
+                const newUrlData = urlData
+                    ? new Map(urlData)
+                    : new Map<string, UrlData>()
+                newUrlData.delete(url)
+                onUrlChange(newUrlData)
                 showErrorToast(
                     <span className="text-muted-foreground">
                         {error instanceof Error
@@ -486,12 +463,11 @@ export const ChatInput = forwardRef<ChatInputRef, ChatInputProps>(
                             urlData={urlData}
                             onRemoveUrl={
                                 onUrlChange
-                                    ? (url) =>
-                                          onUrlChange((prev) => {
-                                              const next = new Map(prev)
-                                              next.delete(url)
-                                              return next
-                                          })
+                                    ? (url) => {
+                                          const next = new Map(urlData)
+                                          next.delete(url)
+                                          onUrlChange(next)
+                                      }
                                     : undefined
                             }
                         />
@@ -583,7 +559,7 @@ export const ChatInput = forwardRef<ChatInputRef, ChatInputProps>(
                                 ref={fileInputRef}
                                 className="hidden"
                                 onChange={handleFileChange}
-                                accept="image/png,image/jpeg,image/gif,image/webp,.svg,.pdf,application/pdf,text/*,.md,.markdown,.json,.csv,.xml,.yaml,.yml,.toml"
+                                accept="image/*,.pdf,application/pdf,text/*,.md,.markdown,.json,.csv,.xml,.yaml,.yml,.toml"
                                 multiple
                                 disabled={isDisabled}
                             />
@@ -612,11 +588,7 @@ export const ChatInput = forwardRef<ChatInputRef, ChatInputProps>(
                         ) : (
                             <Button
                                 type="submit"
-                                disabled={
-                                    isDisabled ||
-                                    isExtractingAttachments ||
-                                    !input.trim()
-                                }
+                                disabled={isDisabled || !input.trim()}
                                 size="sm"
                                 className="h-8 px-4 rounded-xl font-medium shadow-sm"
                                 aria-label={dict.chat.send}
@@ -642,8 +614,9 @@ export const ChatInput = forwardRef<ChatInputRef, ChatInputProps>(
                             dict.save.savedSuccessfully,
                         )
                     }
-                    // Local date as YYYY-MM-DD (toISOString would give UTC)
-                    defaultFilename={`diagram-${new Date().toLocaleDateString("sv-SE")}`}
+                    defaultFilename={`diagram-${new Date()
+                        .toISOString()
+                        .slice(0, 10)}`}
                 />
                 {onUrlChange && (
                     <UrlInputDialog
@@ -656,11 +629,7 @@ export const ChatInput = forwardRef<ChatInputRef, ChatInputProps>(
                 <TemplateCreateDialog
                     open={showSaveAsTemplate}
                     onOpenChange={setShowSaveAsTemplate}
-                    onSuccess={() => {
-                        setShowSaveAsTemplate(false)
-                        // Let the template list in the lobby reload
-                        window.dispatchEvent(new Event("templatesChanged"))
-                    }}
+                    onSuccess={() => setShowSaveAsTemplate(false)}
                     initialPrompt={input.trim()}
                 />
             </form>

components/chat-message-display.tsx

@@ -26,7 +26,6 @@ import {
     ReasoningContent,
     ReasoningTrigger,
 } from "@/components/ai-elements/reasoning"
-import { Shimmer } from "@/components/ai-elements/shimmer"
 import { ChatLobby } from "@/components/chat/ChatLobby"
 import { TemplateCreateDialog } from "@/components/chat/TemplateCreateDialog"
 import { ToolCallCard } from "@/components/chat/ToolCallCard"
@@ -38,12 +37,12 @@ import { ScrollArea } from "@/components/ui/scroll-area"
 import { useDictionary } from "@/hooks/use-dictionary"
 import { getApiEndpoint } from "@/lib/base-path"
 import {
+    applyDiagramOperations,
     convertToLegalXml,
     extractCompleteMxCells,
     replaceNodes,
+    validateAndFixXml,
 } from "@/lib/utils"
-import { applyDiagramOperations } from "@/packages/mcp-server/src/diagram-operations.ts"
-import { BLANK_MXFILE } from "@/packages/mcp-server/src/pages.ts"
 
 // Helper to extract complete operations from streaming input
 function getCompleteOperations(
@@ -130,14 +129,12 @@ const getMessageTextContent = (message: UIMessage): string => {
         .join("\n")
 }
 
-// Matches the [PDF: ...], [File: ...] and [URL: ...] sections appended to the user's text
-export const APPENDED_FILE_SECTIONS_PATTERN =
-    /\n\n\[(PDF|File|URL):\s*[^\]]+\]\n[\s\S]*$/
-
 // Get only the user's original text, excluding appended file content
 const getUserOriginalText = (message: UIMessage): string => {
     const fullText = getMessageTextContent(message)
-    return fullText.replace(APPENDED_FILE_SECTIONS_PATTERN, "").trim()
+    // Strip out [PDF: ...], [File: ...], and [URL: ...] sections that were appended
+    const filePattern = /\n\n\[(PDF|File|URL):\s*[^\]]+\]\n[\s\S]*$/
+    return fullText.replace(filePattern, "").trim()
 }
 
 interface SessionMetadata {
@@ -149,8 +146,6 @@ interface SessionMetadata {
 
 interface ChatMessageDisplayProps {
     messages: UIMessage[]
-    // Shown on an error that a model setting can fix (bad key, unknown model)
-    onOpenModelConfig?: () => void
     setInput: (input: string) => void
     setFiles: (files: File[]) => void
     processedToolCallsRef: MutableRefObject<Set<string>>
@@ -174,7 +169,6 @@ interface ChatMessageDisplayProps {
 
 export function ChatMessageDisplay({
     messages,
-    onOpenModelConfig,
     setInput,
     setFiles,
     processedToolCallsRef,
@@ -194,23 +188,6 @@ export function ChatMessageDisplay({
     currentInput = "",
 }: ChatMessageDisplayProps) {
     const dict = useDictionary()
-    // The thinking header in the page language
-    const thinkingMessage = (isStreaming: boolean, duration?: number) => {
-        if (isStreaming || duration === 0) {
-            return <Shimmer duration={1}>{dict.reasoning.thinking}</Shimmer>
-        }
-        if (duration === undefined) return <p>{dict.reasoning.thoughtBrief}</p>
-        return (
-            <p>
-                {duration === 1
-                    ? dict.reasoning.thoughtForOne
-                    : dict.reasoning.thoughtFor.replace(
-                          "{duration}",
-                          String(duration),
-                      )}
-            </p>
-        )
-    }
     const { chartXML, loadDiagram: onDisplayChart } = useDiagram()
     const messagesEndRef = useRef<HTMLDivElement>(null)
     const scrollTopRef = useRef<HTMLDivElement>(null)
@@ -231,6 +208,20 @@ export function ChatMessageDisplay({
             scrollTopRef.current?.scrollIntoView({ behavior: "instant" })
         }
     }, [messages.length, processedToolCalls])
+    // Debounce streaming diagram updates - store pending XML and timeout
+    const pendingXmlRef = useRef<string | null>(null)
+    const debounceTimeoutRef = useRef<ReturnType<typeof setTimeout> | null>(
+        null,
+    )
+    const STREAMING_DEBOUNCE_MS = 150 // Only update diagram every 150ms during streaming
+    // Refs for edit_diagram streaming
+    const pendingEditRef = useRef<{
+        operations: DiagramOperation[]
+        toolCallId: string
+    } | null>(null)
+    const editDebounceTimeoutRef = useRef<ReturnType<typeof setTimeout> | null>(
+        null,
+    )
     const [expandedTools, setExpandedTools] = useState<Record<string, boolean>>(
         {},
     )
@@ -352,30 +343,73 @@ export function ChatMessageDisplay({
         }
     }
 
-    // Streaming preview of display_diagram: draw the complete cells written
-    // so far. The tool handler validates and loads the final diagram.
     const handleDisplayChart = useCallback(
-        (xml: string) => {
-            const completeCells = extractCompleteMxCells(xml || "")
-            if (!completeCells) return
-            const convertedXml = convertToLegalXml(completeCells)
-            if (convertedXml === previousXML.current) return
+        (xml: string, showToast = false) => {
+            let currentXml = xml || ""
 
-            // Skip this update while the cells written so far don't parse
-            const testDoc = new DOMParser().parseFromString(
-                `<root>${convertedXml}</root>`,
-                "text/xml",
-            )
-            if (testDoc.querySelector("parsererror")) return
+            // During streaming (showToast=false), extract only complete mxCell elements
+            // This allows progressive rendering even with partial/incomplete trailing XML
+            if (!showToast) {
+                const completeCells = extractCompleteMxCells(currentXml)
+                if (!completeCells) {
+                    return
+                }
+                currentXml = completeCells
+            }
 
-            try {
-                // An empty canvas gets a default mxfile to put the cells in
-                const baseXML = chartXML || BLANK_MXFILE
-                const replacedXML = replaceNodes(baseXML, convertedXml)
-                previousXML.current = convertedXml
-                onDisplayChart(replacedXML, true)
-            } catch (error) {
-                console.error("Error processing XML:", error)
+            const convertedXml = convertToLegalXml(currentXml)
+            if (convertedXml !== previousXML.current) {
+                // Parse and validate XML BEFORE calling replaceNodes
+                const parser = new DOMParser()
+                // Wrap in root element for parsing multiple mxCell elements
+                const testDoc = parser.parseFromString(
+                    `<root>${convertedXml}</root>`,
+                    "text/xml",
+                )
+                const parseError = testDoc.querySelector("parsererror")
+
+                if (parseError) {
+                    // Only show toast if this is the final XML (not during streaming)
+                    if (showToast) {
+                        toast.error(dict.errors.malformedXml)
+                    }
+                    return // Skip this update
+                }
+
+                try {
+                    // If chartXML is empty, create a default mxfile structure to use with replaceNodes
+                    // This ensures the XML is properly wrapped in mxfile/diagram/mxGraphModel format
+                    const baseXML =
+                        chartXML ||
+                        `<mxfile><diagram name="Page-1" id="page-1"><mxGraphModel><root><mxCell id="0"/><mxCell id="1" parent="0"/></root></mxGraphModel></diagram></mxfile>`
+                    const replacedXML = replaceNodes(baseXML, convertedXml)
+
+                    // During streaming (showToast=false), skip heavy validation for lower latency
+                    // The quick DOM parse check above catches malformed XML
+                    // Full validation runs on final output (showToast=true)
+                    if (!showToast) {
+                        previousXML.current = convertedXml
+                        onDisplayChart(replacedXML, true)
+                        return
+                    }
+
+                    // Final output: run full validation and auto-fix
+                    const validation = validateAndFixXml(replacedXML)
+                    if (validation.valid) {
+                        previousXML.current = convertedXml
+                        // Use fixed XML if available, otherwise use original
+                        const xmlToLoad = validation.fixed || replacedXML
+                        onDisplayChart(xmlToLoad, true)
+                    } else {
+                        toast.error(dict.errors.validationFailed)
+                    }
+                } catch (error) {
+                    console.error("Error processing XML:", error)
+                    // Only show toast if this is the final XML (not during streaming)
+                    if (showToast) {
+                        toast.error(dict.errors.failedToProcess)
+                    }
+                }
             }
         },
         [chartXML, onDisplayChart],
@@ -422,17 +456,8 @@ export function ChatMessageDisplay({
         // Previous messages are already processed and won't change
         const messagesToProcess =
             messages.length > 0 ? [messages[messages.length - 1]] : []
-        // The diagram without streamed previews. Undoing a failed edit's
-        // preview below changes it before chartXML catches up, and an edit
-        // streaming right after must start from the undone diagram.
-        let baseXml = chartXML
 
         messagesToProcess.forEach((message) => {
-            // Messages restored from a saved session were applied before it was
-            // saved; the saved diagram is authoritative, so don't replay them
-            const isRestoredMessage =
-                loadedMessageIdsRef?.current.has(message.id) ?? false
-
             if (message.parts) {
                 message.parts.forEach((part) => {
                     if (part.type?.startsWith("tool-")) {
@@ -450,8 +475,6 @@ export function ChatMessageDisplay({
                             })
                         }
 
-                        if (isRestoredMessage) return
-
                         if (
                             part.type === "tool-display_diagram" &&
                             input?.xml
@@ -465,62 +488,63 @@ export function ChatMessageDisplay({
                                 return // Skip redundant processing
                             }
 
-                            // Messages update at most every 150 ms while
-                            // streaming (useChat throttle in chat-panel)
-                            if (state === "input-streaming") {
-                                handleDisplayChart(xml)
-                                lastProcessedXmlRef.current.set(toolCallId, xml)
+                            if (
+                                state === "input-streaming" ||
+                                state === "input-available"
+                            ) {
+                                // Debounce streaming updates - queue the XML and process after delay
+                                pendingXmlRef.current = xml
+
+                                if (!debounceTimeoutRef.current) {
+                                    // No pending timeout - set one up
+                                    debounceTimeoutRef.current = setTimeout(
+                                        () => {
+                                            const pendingXml =
+                                                pendingXmlRef.current
+                                            debounceTimeoutRef.current = null
+                                            pendingXmlRef.current = null
+                                            if (pendingXml) {
+                                                handleDisplayChart(
+                                                    pendingXml,
+                                                    false,
+                                                )
+                                                lastProcessedXmlRef.current.set(
+                                                    toolCallId,
+                                                    pendingXml,
+                                                )
+                                            }
+                                        },
+                                        STREAMING_DEBOUNCE_MS,
+                                    )
+                                }
                             } else if (
+                                state === "output-available" &&
                                 !processedToolCalls.current.has(toolCallId)
                             ) {
-                                // Input complete: the tool handler loads the
-                                // validated diagram
+                                // Final output - process immediately (clear any pending debounce)
+                                if (debounceTimeoutRef.current) {
+                                    clearTimeout(debounceTimeoutRef.current)
+                                    debounceTimeoutRef.current = null
+                                    pendingXmlRef.current = null
+                                }
+                                // Show toast only if final XML is malformed
+                                handleDisplayChart(xml, true)
                                 processedToolCalls.current.add(toolCallId)
+                                // Clean up the ref entry - tool is complete, no longer needed
                                 lastProcessedXmlRef.current.delete(toolCallId)
                             }
                         }
 
                         // Handle edit_diagram streaming - apply operations incrementally for preview
                         // Uses shared editDiagramOriginalXmlRef to coordinate with tool handler
-                        if (part.type === "tool-edit_diagram") {
-                            // Failed or stopped: if the original XML is still
-                            // stored, the tool handler never ran (invalid
-                            // JSON, or the user pressed stop), so undo the
-                            // streamed preview here. Invalid JSON leaves no
-                            // operations in the input, so check this first.
-                            if (state === "output-error") {
-                                const originalXml =
-                                    editDiagramOriginalXmlRef.current.get(
-                                        toolCallId,
-                                    )
-                                if (originalXml) {
-                                    editDiagramOriginalXmlRef.current.delete(
-                                        toolCallId,
-                                    )
-                                    onDisplayChart(originalXml, true)
-                                    baseXml = originalXml
-                                }
-                                return
-                            }
-                            if (!input?.operations) return
-
-                            if (state !== "input-streaming") {
-                                // Input complete: the tool handler applies the
-                                // checked edit (it reads the original XML too)
-                                if (
-                                    !processedToolCalls.current.has(toolCallId)
-                                ) {
-                                    lastProcessedXmlRef.current.delete(
-                                        toolCallId + "-opCount",
-                                    )
-                                    processedToolCalls.current.add(toolCallId)
-                                }
-                                return
-                            }
-
+                        if (
+                            part.type === "tool-edit_diagram" &&
+                            input?.operations
+                        ) {
                             const completeOps = getCompleteOperations(
                                 input.operations as DiagramOperation[],
                             )
+
                             if (completeOps.length === 0) return
 
                             // Capture original XML when streaming starts (store in shared ref)
@@ -529,7 +553,7 @@ export function ChatMessageDisplay({
                                     toolCallId,
                                 )
                             ) {
-                                if (!baseXml) {
+                                if (!chartXML) {
                                     console.warn(
                                         "[edit_diagram streaming] No chart XML available",
                                     )
@@ -537,9 +561,10 @@ export function ChatMessageDisplay({
                                 }
                                 editDiagramOriginalXmlRef.current.set(
                                     toolCallId,
-                                    baseXml,
+                                    chartXML,
                                 )
                             }
+
                             const originalXml =
                                 editDiagramOriginalXmlRef.current.get(
                                     toolCallId,
@@ -547,36 +572,94 @@ export function ChatMessageDisplay({
                             if (!originalXml) return
 
                             // Skip if no change from last processed state
-                            const countKey = `${toolCallId}-opCount`
-                            const opCount = String(completeOps.length)
+                            const lastCount = lastProcessedXmlRef.current.get(
+                                toolCallId + "-opCount",
+                            )
+                            if (lastCount === String(completeOps.length)) return
+
                             if (
-                                lastProcessedXmlRef.current.get(countKey) ===
-                                opCount
+                                state === "input-streaming" ||
+                                state === "input-available"
                             ) {
-                                return
-                            }
-                            try {
-                                const { result } = applyDiagramOperations(
-                                    originalXml,
-                                    completeOps,
-                                )
-                                // Load the full document so other pages stay intact
-                                onDisplayChart(result, true)
-                                lastProcessedXmlRef.current.set(
-                                    countKey,
-                                    opCount,
-                                )
-                            } catch (e) {
-                                console.warn(
-                                    "[edit_diagram streaming] Operation failed:",
-                                    e instanceof Error ? e.message : e,
+                                // Queue the operations for debounced processing
+                                pendingEditRef.current = {
+                                    operations: completeOps,
+                                    toolCallId,
+                                }
+
+                                if (!editDebounceTimeoutRef.current) {
+                                    editDebounceTimeoutRef.current = setTimeout(
+                                        () => {
+                                            const pending =
+                                                pendingEditRef.current
+                                            editDebounceTimeoutRef.current =
+                                                null
+                                            pendingEditRef.current = null
+
+                                            if (pending) {
+                                                const origXml =
+                                                    editDiagramOriginalXmlRef.current.get(
+                                                        pending.toolCallId,
+                                                    )
+                                                if (!origXml) return
+
+                                                try {
+                                                    const {
+                                                        result: editedXml,
+                                                    } = applyDiagramOperations(
+                                                        origXml,
+                                                        pending.operations,
+                                                    )
+                                                    handleDisplayChart(
+                                                        editedXml,
+                                                        false,
+                                                    )
+                                                    lastProcessedXmlRef.current.set(
+                                                        pending.toolCallId +
+                                                            "-opCount",
+                                                        String(
+                                                            pending.operations
+                                                                .length,
+                                                        ),
+                                                    )
+                                                } catch (e) {
+                                                    console.warn(
+                                                        `[edit_diagram streaming] Operation failed:`,
+                                                        e instanceof Error
+                                                            ? e.message
+                                                            : e,
+                                                    )
+                                                }
+                                            }
+                                        },
+                                        STREAMING_DEBOUNCE_MS,
+                                    )
+                                }
+                            } else if (
+                                state === "output-available" &&
+                                !processedToolCalls.current.has(toolCallId)
+                            ) {
+                                // Final state - cleanup streaming refs (tool handler does final application)
+                                if (editDebounceTimeoutRef.current) {
+                                    clearTimeout(editDebounceTimeoutRef.current)
+                                    editDebounceTimeoutRef.current = null
+                                }
+                                lastProcessedXmlRef.current.delete(
+                                    toolCallId + "-opCount",
                                 )
+                                processedToolCalls.current.add(toolCallId)
+                                // Note: Don't delete editDiagramOriginalXmlRef here - tool handler needs it
                             }
                         }
                     }
                 })
             }
         })
+
+        // NOTE: Don't cleanup debounce timeouts here!
+        // The cleanup runs on every re-render (when messages changes),
+        // which would cancel the timeout before it fires.
+        // Let the timeouts complete naturally - they're harmless if component unmounts.
     }, [messages, handleDisplayChart, chartXML])
 
     return (
@@ -762,11 +845,7 @@ export function ChatMessageDisplay({
                                                                 !isRestoredMessage
                                                             }
                                                         >
-                                                            <ReasoningTrigger
-                                                                getThinkingMessage={
-                                                                    thinkingMessage
-                                                                }
-                                                            />
+                                                            <ReasoningTrigger />
                                                             <ReasoningContent>
                                                                 {
                                                                     reasoningPart.text
@@ -872,12 +951,8 @@ export function ChatMessageDisplay({
                                                     part.type?.startsWith(
                                                         "tool-",
                                                     )
-                                                // Blank text (some models send
-                                                // a lone space) gets no bubble
                                                 const isContentPart =
-                                                    (part.type === "text" &&
-                                                        part.text.trim() !==
-                                                            "") ||
+                                                    part.type === "text" ||
                                                     part.type === "file"
 
                                                 if (isToolPart) {
@@ -1227,32 +1302,6 @@ export function ChatMessageDisplay({
                                                                     return null
                                                                 },
                                                             )}
-                                                            {message.role ===
-                                                                "system" &&
-                                                                (
-                                                                    message.metadata as
-                                                                        | {
-                                                                              openModelConfig?: boolean
-                                                                          }
-                                                                        | undefined
-                                                                )
-                                                                    ?.openModelConfig &&
-                                                                onOpenModelConfig && (
-                                                                    <button
-                                                                        type="button"
-                                                                        onClick={
-                                                                            onOpenModelConfig
-                                                                        }
-                                                                        className="mt-2 text-xs font-medium underline underline-offset-2 hover:opacity-80"
-                                                                    >
-                                                                        {
-                                                                            dict
-                                                                                .errors
-                                                                                .llm
-                                                                                .openModelSettings
-                                                                        }
-                                                                    </button>
-                                                                )}
                                                         </div>
                                                     )
                                                 },

components/chat-panel.tsx

@@ -1,7 +1,7 @@
 "use client"
 
 import { useChat } from "@ai-sdk/react"
-import { DefaultChatTransport, isToolUIPart, type UIMessage } from "ai"
+import { DefaultChatTransport } from "ai"
 import {
     MessageSquarePlus,
     PanelRightClose,
@@ -41,13 +41,8 @@ import type { UrlData } from "@/lib/url-utils"
 import { type FileData, useFileProcessor } from "@/lib/use-file-processor"
 import { useQuotaManager } from "@/lib/use-quota-manager"
 import { cn, formatXML, isRealDiagram } from "@/lib/utils"
-import { prepareNewDiagram } from "@/packages/mcp-server/src/new-diagram.ts"
-import { BLANK_MXFILE, hasCells } from "@/packages/mcp-server/src/pages.ts"
 import type { ValidationState } from "./chat/ValidationCard"
-import {
-    APPENDED_FILE_SECTIONS_PATTERN,
-    ChatMessageDisplay,
-} from "./chat-message-display"
+import { ChatMessageDisplay } from "./chat-message-display"
 import { DevXmlSimulator } from "./dev-xml-simulator"
 
 // localStorage keys for persistence
@@ -56,6 +51,21 @@ const STORAGE_SESSION_ID_KEY = "next-ai-draw-io-session-id"
 // sessionStorage keys
 const SESSION_STORAGE_INPUT_KEY = "next-ai-draw-io-input"
 
+// Type for message parts (tool calls and their states)
+interface MessagePart {
+    type: string
+    state?: string
+    toolName?: string
+    input?: { xml?: string; [key: string]: unknown }
+    [key: string]: unknown
+}
+
+interface ChatMessage {
+    role: string
+    parts?: MessagePart[]
+    [key: string]: unknown
+}
+
 interface ChatPanelProps {
     isVisible: boolean
     onToggleVisibility: () => void
@@ -78,23 +88,23 @@ const MAX_CONTINUATION_RETRY_COUNT = 2 // Limit for truncation continuation retr
  * Check if auto-resubmit should happen based on tool errors.
  * Only checks the LAST tool part (most recent tool call), not all tool parts.
  */
-function hasToolErrors(messages: UIMessage[]): boolean {
+function hasToolErrors(messages: ChatMessage[]): boolean {
     const lastMessage = messages[messages.length - 1]
-    if (lastMessage?.role !== "assistant") return false
-    const lastToolPart = lastMessage.parts.filter(isToolUIPart).at(-1)
-    return lastToolPart?.state === TOOL_ERROR_STATE
-}
+    if (!lastMessage || lastMessage.role !== "assistant") {
+        return false
+    }
 
-/**
- * Snapshots keep the full multi-page document, but the model only sees and
- * edits the first page, so give it the first page's mxGraphModel.
- * Older snapshots already hold a single mxGraphModel and are returned as is.
- */
-function getFirstPageXml(xml: string): string {
-    if (!xml.includes("<mxfile")) return xml
-    const doc = new DOMParser().parseFromString(xml, "text/xml")
-    const model = doc.querySelector("diagram")?.querySelector("mxGraphModel")
-    return model ? formatXML(new XMLSerializer().serializeToString(model)) : xml
+    const toolParts =
+        (lastMessage.parts as MessagePart[] | undefined)?.filter((part) =>
+            part.type?.startsWith("tool-"),
+        ) || []
+
+    if (toolParts.length === 0) {
+        return false
+    }
+
+    const lastToolPart = toolParts[toolParts.length - 1]
+    return lastToolPart?.state === TOOL_ERROR_STATE
 }
 
 export default function ChatPanel({
@@ -326,8 +336,19 @@ export default function ChatPanel({
         localStorage.setItem(STORAGE_KEYS.maxOutputTokens, digitsOnly)
     }, [])
 
-    // Failed VLM validations in the current user turn (reset on user action)
-    const validationRetryCountRef = useRef(0)
+    // Ref to store the sendMessage function for use in callbacks
+    const sendMessageRef = useRef<typeof sendMessage | null>(null)
+
+    // Callback to improve diagram with validation suggestions
+    const handleImproveWithSuggestions = useCallback((feedback: string) => {
+        if (sendMessageRef.current) {
+            // Send the feedback as a new user message to trigger regeneration
+            sendMessageRef.current({
+                role: "user",
+                parts: [{ type: "text", text: feedback }],
+            })
+        }
+    }, [])
 
     // VLM validation hook using AI SDK's useObject
     const { validateWithFallback } = useValidateDiagram()
@@ -336,7 +357,6 @@ export default function ChatPanel({
     const { handleToolCall } = useDiagramToolHandlers({
         partialXmlRef,
         editDiagramOriginalXmlRef,
-        validationRetryCountRef,
         chartXMLRef,
         onDisplayChart,
         onFetchChart,
@@ -364,87 +384,95 @@ export default function ChatPanel({
             await handleToolCall({ toolCall }, addToolOutput)
         },
         onError: (error) => {
-            // An edit still streaming when the request failed never reaches
-            // the tool handler: undo its preview. The first stored original
-            // is the diagram before any of them.
-            const [originalXml] = editDiagramOriginalXmlRef.current.values()
-            if (originalXml) onDisplayChart(originalXml, true)
-            editDiagramOriginalXmlRef.current.clear()
-
-            // Server errors are JSON: a quota limit ({type: request, token or
-            // tpm}), a provider error ({type: "provider", code, message}) or
-            // {error}. The SDK puts the response body in error.message.
-            let data: any = null
+            // Handle server-side quota limit (429 response)
+            // AI SDK puts the full response body in error.message for non-OK responses
             try {
-                data = JSON.parse(error.message)
+                const data = JSON.parse(error.message)
+                if (data.type === "request") {
+                    quotaManager.showQuotaLimitToast(data.used, data.limit)
+                    return
+                }
+                if (data.type === "token") {
+                    quotaManager.showTokenLimitToast(data.used, data.limit)
+                    return
+                }
+                if (data.type === "tpm") {
+                    quotaManager.showTPMLimitToast(data.limit)
+                    return
+                }
             } catch {
-                // Plain text, e.g. a network failure in the browser
+                // Not JSON, fall through to string matching for backwards compatibility
             }
-            if (data?.type === "request") {
-                quotaManager.showQuotaLimitToast(data.used, data.limit)
+
+            // Fallback to string matching
+            if (error.message.includes("Daily request limit")) {
+                quotaManager.showQuotaLimitToast()
                 return
             }
-            if (data?.type === "token") {
-                quotaManager.showTokenLimitToast(data.used, data.limit)
+            if (error.message.includes("Daily token limit")) {
+                quotaManager.showTokenLimitToast()
                 return
             }
-            if (data?.type === "tpm") {
-                quotaManager.showTPMLimitToast(data.limit)
+            if (
+                error.message.includes("Rate limit exceeded") ||
+                error.message.includes("tokens per minute")
+            ) {
+                quotaManager.showTPMLimitToast()
                 return
             }
 
-            const isAccessCodeError = String(
-                data?.error ?? error.message,
-            ).includes("Invalid or missing access code")
             // Silence access code error in console since it's handled by UI
-            if (!isAccessCodeError) console.error("Chat error:", error)
+            if (!error.message.includes("Invalid or missing access code")) {
+                console.error("Chat error:", error)
+            }
 
-            // A hint the user can act on, then the provider's own words
-            let text: string = error.message
-            let openModelConfig = false
-            if (data?.type === "provider") {
-                const hints = dict.errors.llm as Record<string, string>
-                text = hints[data.code]
-                    ? `${hints[data.code]}\n\n${data.message}`
-                    : data.message
-                openModelConfig = [
-                    "invalid_api_key",
-                    "forbidden",
-                    "model_not_found",
-                ].includes(data.code)
-            } else if (typeof data?.error === "string") {
-                text = data.error
-            } else if (error.message === "Failed to fetch") {
-                text = dict.errors.networkError
+            // Translate technical errors into user-friendly messages
+            // The server now handles detailed error messages, so we can display them directly.
+            // But we still handle connection/network errors that happen before reaching the server.
+            let friendlyMessage = error.message
+
+            // Simple check for network errors if message is generic
+            if (friendlyMessage === "Failed to fetch") {
+                friendlyMessage = "Network error. Please check your connection."
+            }
+
+            // Truncated tool input error (model output limit too low)
+            if (friendlyMessage.includes("toolUse.input is invalid")) {
+                friendlyMessage =
+                    "Output was truncated before the diagram could be generated. Try a simpler request or increase the maxOutputLength."
+            }
+
+            // Translate image not supported error
+            if (
+                friendlyMessage.includes("image content block") ||
+                friendlyMessage.toLowerCase().includes("image_url")
+            ) {
+                friendlyMessage = "This model doesn't support image input."
             }
 
             // Add system message for error so it can be cleared
-            setMessages((currentMessages) => [
-                ...currentMessages,
-                {
+            setMessages((currentMessages) => {
+                const errorMessage = {
                     id: `error-${Date.now()}`,
                     role: "system" as const,
-                    content: text,
-                    parts: [{ type: "text" as const, text }],
-                    // The message shows a button that opens model settings
-                    ...(openModelConfig && {
-                        metadata: { openModelConfig: true },
-                    }),
-                },
-            ])
+                    content: friendlyMessage,
+                    parts: [{ type: "text" as const, text: friendlyMessage }],
+                }
+                return [...currentMessages, errorMessage]
+            })
 
-            if (isAccessCodeError) {
+            if (error.message.includes("Invalid or missing access code")) {
                 // Show settings dialog to help user fix it
                 setShowSettingsDialog(true)
             }
         },
-        // Re-render streamed messages at most every 150 ms. The streaming
-        // diagram preview draws on each update, so this also limits redraws
-        experimental_throttle: 150,
+        onFinish: () => {},
         sendAutomaticallyWhen: ({ messages }) => {
             const isInContinuationMode = partialXmlRef.current.length > 0
 
-            const shouldRetry = hasToolErrors(messages)
+            const shouldRetry = hasToolErrors(
+                messages as unknown as ChatMessage[],
+            )
 
             if (!shouldRetry) {
                 // No error, reset retry count and clear state
@@ -490,6 +518,11 @@ export default function ChatPanel({
         },
     })
 
+    // Store sendMessage in ref for use in callbacks (like handleImproveWithSuggestions)
+    useEffect(() => {
+        sendMessageRef.current = sendMessage
+    }, [sendMessage])
+
     // Ref to track latest messages for unload persistence
     const messagesRef = useRef(messages)
     useEffect(() => {
@@ -498,9 +531,6 @@ export default function ChatPanel({
 
     // Track last synced session ID to detect external changes (e.g., URL back/forward)
     const lastSyncedSessionIdRef = useRef<string | null>(null)
-    // Messages array from our latest save. A session holding this exact array was
-    // created by our own save, so it must not be treated as an external switch.
-    const lastSavedMessagesRef = useRef<unknown[] | null>(null)
 
     // Helper: Sync UI state with session data (eliminates duplication)
     // Track message IDs that are being loaded from session (to skip animations/scroll)
@@ -567,10 +597,8 @@ export default function ChatPanel({
                     thumbnailDataUrl = latestSvgRef.current
                 }
             }
-            const messages = sanitizeMessages(messagesRef.current)
-            lastSavedMessagesRef.current = messages
             return {
-                messages,
+                messages: sanitizeMessages(messagesRef.current),
                 xmlSnapshots: Array.from(xmlSnapshotsRef.current.entries()),
                 diagramXml: currentDiagramXml,
                 thumbnailDataUrl,
@@ -623,13 +651,8 @@ export default function ChatPanel({
         // Skip if session ID hasn't changed (our own saves don't change the ID)
         if (newSessionId === lastSyncedSessionIdRef.current) return
 
-        // Our own save created this session; the UI already shows its content
-        const isOwnNewSession =
-            newSession?.messages === lastSavedMessagesRef.current
-
         // Update last synced ID
         lastSyncedSessionIdRef.current = newSessionId
-        if (isOwnNewSession) return
 
         // Sync UI with new session
         if (newSession) {
@@ -770,25 +793,16 @@ export default function ChatPanel({
     const onFormSubmit = async (e: React.FormEvent<HTMLFormElement>) => {
         e.preventDefault()
         const isProcessing = status === "streaming" || status === "submitted"
-        // Attachments still extracting have no text yet. Template sends call
-        // requestSubmit() and skip the disabled send button, so check here too.
-        const isExtracting =
-            files.some((f) => pdfData.get(f)?.isExtracting) ||
-            Array.from(urlData.values()).some((d) => d.isExtracting)
-        if (input.trim() && !isProcessing && !isExtracting) {
-            // Check if input matches a cached example (only when no messages
-            // yet and the canvas is empty, same rule as the server)
-            if (messages.length === 0 && !hasCells(chartXMLRef.current || "")) {
-                // Pass the file name so a user's own file never matches an example
+        if (input.trim() && !isProcessing) {
+            // Check if input matches a cached example (only when no messages yet)
+            if (messages.length === 0) {
                 const cached = findCachedResponse(
                     input.trim(),
                     files.length > 0,
-                    files.length === 1 ? files[0].name : undefined,
                 )
                 if (cached) {
-                    // Add the user message and a finished display_diagram
-                    // answer, and load its diagram here: these messages never
-                    // reach the tool handler
+                    // Add user message and fake assistant response to messages
+                    // The chat-message-display useEffect will handle displaying the diagram
                     const toolCallId = `cached-${Date.now()}`
 
                     // Build user message text including any file content
@@ -820,16 +834,6 @@ export default function ChatPanel({
                             ],
                         },
                     ] as any)
-                    // Snapshot the canvas before the example so editing this message works
-                    xmlSnapshotsRef.current.set(
-                        0,
-                        chartXMLRef.current || BLANK_MXFILE,
-                    )
-                    const prepared = prepareNewDiagram(cached.xml, {
-                        pageId: "page-1",
-                        pageName: "Page-1",
-                    })
-                    if (prepared.ok) onDisplayChart(prepared.xml, true)
                     setInput("")
                     sessionStorage.removeItem(SESSION_STORAGE_INPUT_KEY)
                     setFiles([])
@@ -839,6 +843,9 @@ export default function ChatPanel({
             }
 
             try {
+                let chartXml = await onFetchChart()
+                chartXml = formatXML(chartXml)
+
                 // Build user text by concatenating input with pre-extracted text
                 // (Backend only reads first text part, so we must combine them)
                 const parts: any[] = []
@@ -853,45 +860,32 @@ export default function ChatPanel({
                 // Add the combined text as the first part
                 parts.unshift({ type: "text", text: userText })
 
-                await sendWithCurrentDiagram(parts)
+                // Get previous XML from the last snapshot (before this message)
+                const snapshotKeys = Array.from(
+                    xmlSnapshotsRef.current.keys(),
+                ).sort((a, b) => b - a)
+                const previousXml =
+                    snapshotKeys.length > 0
+                        ? xmlSnapshotsRef.current.get(snapshotKeys[0]) || ""
+                        : ""
 
+                // Save XML snapshot for this message (will be at index = current messages.length)
+                const messageIndex = messages.length
+                xmlSnapshotsRef.current.set(messageIndex, chartXml)
+
+                sendChatMessage(parts, chartXml, previousXml, sessionId)
+
+                // Token count is tracked in onFinish with actual server usage
                 setInput("")
                 sessionStorage.removeItem(SESSION_STORAGE_INPUT_KEY)
                 setFiles([])
                 setUrlData(new Map())
             } catch (error) {
                 console.error("Error fetching chart data:", error)
-                toast.error(dict.errors.failedToExport)
             }
         }
     }
 
-    // Export the current diagram, snapshot it for this message, and send
-    const sendWithCurrentDiagram = async (parts: any[]) => {
-        const chartXml = formatXML(await onFetchChart())
-        const previousXml = getPreviousXml(messages.length)
-
-        // Snapshot the full multi-page document (kept fresh by autosave) so
-        // regenerate/edit can restore every page; the model gets page 1 only
-        xmlSnapshotsRef.current.set(
-            messages.length,
-            chartXMLRef.current || chartXml,
-        )
-
-        sendChatMessage(parts, chartXml, previousXml, sessionId)
-    }
-
-    // Send VLM validation feedback as a new user message through the normal send path
-    const handleImproveWithSuggestions = async (feedback: string) => {
-        if (status === "streaming" || status === "submitted") return
-        try {
-            await sendWithCurrentDiagram([{ type: "text", text: feedback }])
-        } catch (error) {
-            console.error("Error fetching chart data:", error)
-            toast.error(dict.errors.failedToExport)
-        }
-    }
-
     // Handle session switching from history dropdown
     const handleSelectSession = useCallback(
         async (sessionId: string) => {
@@ -995,9 +989,10 @@ export default function ChatPanel({
     // Handle sending a template directly (called from TemplatePanel)
     const handleSendTemplate = useCallback(
         async (template: { prompt: string }) => {
-            // Keep attachments: they are sent along with the template prompt
             flushSync(() => {
                 setInput(template.prompt)
+                setFiles([])
+                setUrlData(new Map())
             })
 
             const formElement = document.getElementById(
@@ -1007,7 +1002,7 @@ export default function ChatPanel({
                 formElement.requestSubmit()
             }
         },
-        [setInput],
+        [setInput, setFiles, setUrlData],
     )
 
     const handleInputChange = (
@@ -1022,15 +1017,13 @@ export default function ChatPanel({
     }
 
     // Helper functions for message actions (regenerate/edit)
-    // Extract previous XML snapshot (first page, as sent to the model) before a given message index
+    // Extract previous XML snapshot before a given message index
     const getPreviousXml = (beforeIndex: number): string => {
         const snapshotKeys = Array.from(xmlSnapshotsRef.current.keys())
             .filter((k) => k < beforeIndex)
             .sort((a, b) => b - a)
         return snapshotKeys.length > 0
-            ? getFirstPageXml(
-                  xmlSnapshotsRef.current.get(snapshotKeys[0]) || "",
-              )
+            ? xmlSnapshotsRef.current.get(snapshotKeys[0]) || ""
             : ""
     }
 
@@ -1082,7 +1075,6 @@ export default function ChatPanel({
         // Reset all retry/continuation state on user-initiated message
         autoRetryCountRef.current = 0
         continuationRetryCountRef.current = 0
-        validationRetryCountRef.current = 0
         partialXmlRef.current = ""
 
         const config = getSelectedAIConfig()
@@ -1231,12 +1223,7 @@ export default function ChatPanel({
         })
 
         // Now send the message after state is guaranteed to be updated
-        sendChatMessage(
-            userParts,
-            getFirstPageXml(savedXml),
-            previousXml,
-            sessionId,
-        )
+        sendChatMessage(userParts, savedXml, previousXml, sessionId)
     }
 
     const handleEditMessage = async (messageIndex: number, newText: string) => {
@@ -1263,13 +1250,10 @@ export default function ChatPanel({
         // Clean up snapshots for messages after the user message (they will be removed)
         cleanupSnapshotsAfter(messageIndex)
 
-        // Create new parts with updated text. The edit box only shows the typed
-        // text, so keep the appended PDF/file/URL content
+        // Create new parts with updated text
         const newParts = message.parts?.map((part: any) => {
             if (part.type === "text") {
-                const appended =
-                    part.text.match(APPENDED_FILE_SECTIONS_PATTERN)?.[0] ?? ""
-                return { ...part, text: newText + appended }
+                return { ...part, text: newText }
             }
             return part
         }) || [{ type: "text", text: newText }]
@@ -1282,12 +1266,7 @@ export default function ChatPanel({
         })
 
         // Now send the edited message after state is guaranteed to be updated
-        sendChatMessage(
-            newParts,
-            getFirstPageXml(savedXml),
-            previousXml,
-            sessionId,
-        )
+        sendChatMessage(newParts, savedXml, previousXml, sessionId)
     }
 
     // Collapsed view (desktop only)
@@ -1416,7 +1395,6 @@ export default function ChatPanel({
             {/* Messages */}
             <main className="flex-1 w-full overflow-hidden">
                 <ChatMessageDisplay
-                    onOpenModelConfig={() => setShowModelConfigDialog(true)}
                     messages={messages}
                     setInput={setInput}
                     setFiles={handleFileChange}

components/chat/ChatLobby.tsx

@@ -194,8 +194,6 @@ export function ChatLobby({
                                     className="group w-full flex items-center gap-3 p-3 rounded-xl border border-border/60 bg-card hover:bg-accent/50 hover:border-primary/30 transition-all duration-200 cursor-pointer text-left"
                                     onClick={() => onSelectSession(session.id)}
                                     onKeyDown={(e) => {
-                                        // Ignore keys bubbling up from the delete button
-                                        if (e.target !== e.currentTarget) return
                                         if (
                                             e.key === "Enter" ||
                                             e.key === " "

components/chat/TemplateCreateDialog.tsx

@@ -55,9 +55,6 @@ export function TemplateCreateDialog({
 
     const handleSubmit = async (e: React.FormEvent) => {
         e.preventDefault()
-        // React submit events bubble through the portal; keep them away from
-        // the chat form this dialog may be rendered in
-        e.stopPropagation()
 
         const trimmedPrompt = prompt.trim()
         if (!trimmedPrompt) {

components/chat/TemplateEditDialog.tsx

@@ -39,16 +39,16 @@ export function TemplateEditDialog({
     const [isSubmitting, setIsSubmitting] = useState(false)
     const [error, setError] = useState<string | null>(null)
 
-    // Populate form each time the dialog opens, dropping any cancelled edits
+    // Populate form when template changes
     useEffect(() => {
-        if (open && template) {
+        if (template) {
             setTitle(template.title || "")
             setDescription(template.description || "")
             setPrompt(template.prompt || "")
             setPinned(template.pinned || false)
             setError(null)
         }
-    }, [open, template])
+    }, [template])
 
     const handleOpenChange = (newOpen: boolean) => {
         if (!newOpen) {
@@ -59,9 +59,6 @@ export function TemplateEditDialog({
 
     const handleSubmit = async (e: React.FormEvent) => {
         e.preventDefault()
-        // React submit events bubble through the portal; keep them away from
-        // any form this dialog may be rendered in
-        e.stopPropagation()
 
         if (!template) return
 

components/chat/TemplatePanel.tsx

@@ -110,10 +110,6 @@ export function TemplatePanel({
 
     useEffect(() => {
         loadTemplates()
-        // Reload when a template is saved elsewhere, e.g. from the chat input
-        window.addEventListener("templatesChanged", loadTemplates)
-        return () =>
-            window.removeEventListener("templatesChanged", loadTemplates)
     }, [loadTemplates])
 
     const handleCreateSuccess = () => {
@@ -224,8 +220,7 @@ export function TemplatePanel({
             const url = URL.createObjectURL(blob)
             const a = document.createElement("a")
             a.href = url
-            // Local date as YYYY-MM-DD (toISOString would give UTC)
-            a.download = `templates-${new Date().toLocaleDateString("sv-SE")}.json`
+            a.download = `templates-${new Date().toISOString().split("T")[0]}.json`
             document.body.appendChild(a)
             a.click()
             document.body.removeChild(a)
@@ -307,28 +302,6 @@ export function TemplatePanel({
         }
     }
 
-    // Shared by the empty state and the list, so import works in both
-    const importInput = (
-        <input
-            ref={fileInputRef}
-            type="file"
-            accept="application/json,.json"
-            onChange={handleImport}
-            className="hidden"
-        />
-    )
-    const importMessageBox = importMessage && (
-        <div
-            className={`text-xs px-3 py-2 rounded-lg ${
-                importMessage.type === "success"
-                    ? "bg-green-100 text-green-800 dark:bg-green-900/30 dark:text-green-400"
-                    : "bg-red-100 text-red-800 dark:bg-red-900/30 dark:text-red-400"
-            }`}
-        >
-            {importMessage.text}
-        </div>
-    )
-
     // Empty state: no templates at all
     if (!loading && templates.length === 0) {
         return (
@@ -359,18 +332,6 @@ export function TemplatePanel({
                         <Plus className="w-4 h-4" />
                         {dict.templates.createFirst}
                     </button>
-                    <button
-                        type="button"
-                        onClick={() => fileInputRef.current?.click()}
-                        className="mt-2 inline-flex items-center gap-1.5 px-3 py-1.5 rounded-md text-xs font-medium text-muted-foreground hover:text-foreground hover:bg-muted transition-colors"
-                    >
-                        <Upload className="w-3.5 h-3.5" />
-                        {dict.templates.importTemplates}
-                    </button>
-                    {importInput}
-                    {importMessageBox && (
-                        <div className="mt-3">{importMessageBox}</div>
-                    )}
 
                     <TemplateCreateDialog
                         open={createDialogOpen}
@@ -428,11 +389,27 @@ export function TemplatePanel({
                         <Upload className="w-3.5 h-3.5" />
                         {dict.templates.importTemplates}
                     </button>
-                    {importInput}
+                    <input
+                        ref={fileInputRef}
+                        type="file"
+                        accept="application/json,.json"
+                        onChange={handleImport}
+                        className="hidden"
+                    />
                 </div>
 
                 {/* Import message */}
-                {importMessageBox}
+                {importMessage && (
+                    <div
+                        className={`text-xs px-3 py-2 rounded-lg ${
+                            importMessage.type === "success"
+                                ? "bg-green-100 text-green-800 dark:bg-green-900/30 dark:text-green-400"
+                                : "bg-red-100 text-red-800 dark:bg-red-900/30 dark:text-red-400"
+                        }`}
+                    >
+                        {importMessage.text}
+                    </div>
+                )}
 
                 <div className="space-y-2">
                     {loading
@@ -470,8 +447,6 @@ export function TemplatePanel({
                                         handleTemplateClick(template)
                                     }
                                     onKeyDown={(e) => {
-                                        // Ignore keys bubbling up from the action buttons
-                                        if (e.target !== e.currentTarget) return
                                         if (
                                             e.key === "Enter" ||
                                             e.key === " "

components/chat/ToolCallCard.tsx

@@ -66,7 +66,7 @@ export function ToolCallCard({
     dict,
 }: ToolCallCardProps) {
     const callId = part.toolCallId
-    const { state, input, output, errorText } = part
+    const { state, input, output } = part
     // Default to expanded for all states (user can manually collapse if needed)
     const isExpanded = expandedTools[callId] ?? true
     const toolName = part.type?.replace("tool-", "")
@@ -92,14 +92,6 @@ export function ToolCallCard({
         }
     }
 
-    // Incomplete XML means the output hit the length limit, unless the user
-    // stopped the generation themselves
-    const isTruncated =
-        state === "output-error" &&
-        errorText !== "Stopped by user" &&
-        (toolName === "display_diagram" || toolName === "append_diagram") &&
-        !isMxCellXmlComplete(input?.xml)
-
     const handleCopy = () => {
         let textToCopy = ""
 
@@ -169,15 +161,22 @@ export function ToolCallCard({
                         </>
                     )}
                     {state === "output-error" &&
-                        (isTruncated ? (
-                            <span className="text-xs font-medium text-yellow-600 bg-yellow-50 px-2 py-0.5 rounded-full">
-                                Truncated
-                            </span>
-                        ) : (
-                            <span className="text-xs font-medium text-red-600 bg-red-50 px-2 py-0.5 rounded-full">
-                                Error
-                            </span>
-                        ))}
+                        (() => {
+                            // Check if this is a truncation (incomplete XML) vs real error
+                            const isTruncated =
+                                (toolName === "display_diagram" ||
+                                    toolName === "append_diagram") &&
+                                !isMxCellXmlComplete(input?.xml)
+                            return isTruncated ? (
+                                <span className="text-xs font-medium text-yellow-600 bg-yellow-50 px-2 py-0.5 rounded-full">
+                                    Truncated
+                                </span>
+                            ) : (
+                                <span className="text-xs font-medium text-red-600 bg-red-50 px-2 py-0.5 rounded-full">
+                                    Error
+                                </span>
+                            )
+                        })()}
                     {input && Object.keys(input).length > 0 && (
                         <button
                             type="button"
@@ -225,16 +224,23 @@ export function ToolCallCard({
                     ) : null}
                 </div>
             )}
-            {/* AI SDK stores tool errors in errorText */}
-            {state === "output-error" && (errorText || output) && (
-                <div
-                    className={`px-4 py-3 border-t border-border/40 text-sm whitespace-pre-wrap break-words ${isTruncated ? "text-yellow-600" : "text-red-600"}`}
-                >
-                    {isTruncated
-                        ? "Output truncated due to length limits. Try a simpler request or increase Max Output Tokens in Settings."
-                        : (errorText ?? output)}
-                </div>
-            )}
+            {output &&
+                state === "output-error" &&
+                (() => {
+                    const isTruncated =
+                        (toolName === "display_diagram" ||
+                            toolName === "append_diagram") &&
+                        !isMxCellXmlComplete(input?.xml)
+                    return (
+                        <div
+                            className={`px-4 py-3 border-t border-border/40 text-sm ${isTruncated ? "text-yellow-600" : "text-red-600"}`}
+                        >
+                            {isTruncated
+                                ? "Output truncated due to length limits. Try a simpler request or increase the maxOutputLength."
+                                : output}
+                        </div>
+                    )
+                })()}
             {/* Show get_shape_library output on success */}
             {output &&
                 toolName === "get_shape_library" &&

components/chat/types.ts

@@ -1,6 +1,8 @@
-import type { DiagramOperation } from "@/packages/mcp-server/src/diagram-operations.ts"
-
-export type { DiagramOperation }
+export interface DiagramOperation {
+    operation: "update" | "add" | "delete"
+    cell_id: string
+    new_xml?: string
+}
 
 export interface ToolPartLike {
     type: string
@@ -11,5 +13,4 @@ export interface ToolPartLike {
         operations?: DiagramOperation[]
     } & Record<string, unknown>
     output?: string
-    errorText?: string
 }

components/dev-xml-simulator.tsx

@@ -2,7 +2,7 @@
 
 import { useEffect, useRef, useState } from "react"
 import { useDictionary } from "@/hooks/use-dictionary"
-import { prepareNewDiagram } from "@/packages/mcp-server/src/new-diagram.ts"
+import { wrapWithMxFile } from "@/lib/utils"
 
 // Dev XML presets for streaming simulator
 const DEV_XML_PRESETS: Record<string, string> = {
@@ -237,8 +237,8 @@ export function DevXmlSimulator({
         })
 
         // Display the final diagram
-        const prepared = prepareNewDiagram(xml)
-        if (prepared.ok) onDisplayChart(prepared.xml)
+        const fullXml = wrapWithMxFile(xml)
+        onDisplayChart(fullXml)
 
         setIsSimulating(false)
     }

components/model-config-dialog.tsx

@@ -4,12 +4,12 @@ import {
     AlertCircle,
     Check,
     ChevronRight,
+    Clock,
     Eye,
     EyeOff,
     Key,
     Loader2,
     Plus,
-    RefreshCw,
     Server,
     Settings2,
     Sparkles,
@@ -34,13 +34,6 @@ import {
     AlertDialogTitle,
 } from "@/components/ui/alert-dialog"
 import { Button } from "@/components/ui/button"
-import {
-    Command,
-    CommandEmpty,
-    CommandInput,
-    CommandItem,
-    CommandList,
-} from "@/components/ui/command"
 import {
     Dialog,
     DialogContent,
@@ -50,11 +43,6 @@ import {
 } from "@/components/ui/dialog"
 import { Input } from "@/components/ui/input"
 import { Label } from "@/components/ui/label"
-import {
-    Popover,
-    PopoverContent,
-    PopoverTrigger,
-} from "@/components/ui/popover"
 import { ScrollArea } from "@/components/ui/scroll-area"
 import {
     Select,
@@ -68,13 +56,7 @@ import { useDictionary } from "@/hooks/use-dictionary"
 import type { UseModelConfigReturn } from "@/hooks/use-model-config"
 import { getApiEndpoint } from "@/lib/base-path"
 import { formatMessage } from "@/lib/i18n/utils"
-import type { ListedModel } from "@/lib/provider-models"
-import { STORAGE_KEYS } from "@/lib/storage"
-import type {
-    ModelConfig,
-    ProviderConfig,
-    ProviderName,
-} from "@/lib/types/model-config"
+import type { ProviderConfig, ProviderName } from "@/lib/types/model-config"
 import { PROVIDER_INFO, SUGGESTED_MODELS } from "@/lib/types/model-config"
 import { cn } from "@/lib/utils"
 
@@ -143,34 +125,22 @@ export function ModelConfigDialog({
     > | null>(null)
     const [deleteConfirmOpen, setDeleteConfirmOpen] = useState(false)
     const [deleteConfirmText, setDeleteConfirmText] = useState("")
-    // Models whose test is running (they are all tested at once)
-    const [validatingModelIds, setValidatingModelIds] = useState<Set<string>>(
-        () => new Set(),
-    )
+    const [validatingModelIndex, setValidatingModelIndex] = useState<
+        number | null
+    >(null)
     const [duplicateError, setDuplicateError] = useState<string>("")
     const [editError, setEditError] = useState<{
         modelId: string
         message: string
     } | null>(null)
-    // Model ID being typed; written to the config only when valid on blur
-    const [modelIdDraft, setModelIdDraft] = useState<{
-        id: string
-        value: string
-    } | null>(null)
-    // Bumped on every credential edit so a running test can tell that its
-    // results belong to the old credentials
-    const credentialsVersionRef = useRef(0)
-    // Models fetched from the provider, per provider config
-    const [fetchedModels, setFetchedModels] = useState<
-        Record<string, ListedModel[]>
+    const [dynamicSuggestedModels, setDynamicSuggestedModels] = useState<
+        Partial<Record<ProviderName, string[]>>
     >({})
-    const [fetchingModels, setFetchingModels] = useState(false)
-    const [fetchModelsError, setFetchModelsError] = useState("")
-    const [modelPickerOpen, setModelPickerOpen] = useState(false)
-    // models.dev data for hints, loaded with the dialog (it is ~180 KB)
-    const [getModelInfo, setGetModelInfo] = useState<
-        typeof import("@/lib/model-catalog").getModelInfo | null
-    >(null)
+    const [loadedSuggestedProviders, setLoadedSuggestedProviders] = useState<
+        Partial<Record<ProviderName, boolean>>
+    >({})
+    const [loadingSuggestedProvider, setLoadingSuggestedProvider] =
+        useState<ProviderName | null>(null)
 
     const {
         config,
@@ -187,11 +157,6 @@ export function ModelConfigDialog({
         (p) => p.id === selectedProviderId,
     )
 
-    // Discard an unfinished model ID edit when the dialog closes
-    useEffect(() => {
-        if (!open) setModelIdDraft(null)
-    }, [open])
-
     // Cleanup validation reset timeout on unmount
     useEffect(() => {
         return () => {
@@ -202,74 +167,73 @@ export function ModelConfigDialog({
     }, [])
 
     useEffect(() => {
-        if (!open || getModelInfo) return
-        import("@/lib/model-catalog").then((catalog) =>
-            setGetModelInfo(() => catalog.getModelInfo),
-        )
-    }, [open, getModelInfo])
-
-    const handleFetchModels = async () => {
-        if (!selectedProvider) return
-        const providerId = selectedProvider.id
-        setFetchingModels(true)
-        setFetchModelsError("")
-        try {
-            const response = await fetch(
-                getApiEndpoint("/api/provider-models"),
-                {
-                    method: "POST",
-                    headers: {
-                        "Content-Type": "application/json",
-                        "x-access-code":
-                            localStorage.getItem(STORAGE_KEYS.accessCode) || "",
-                    },
-                    body: JSON.stringify({
-                        provider: selectedProvider.provider,
-                        apiKey: selectedProvider.apiKey,
-                        baseUrl: selectedProvider.baseUrl,
-                    }),
-                },
-            )
-            const data = await response.json().catch(() => ({}))
-            if (Array.isArray(data.models)) {
-                setFetchedModels((current) => ({
-                    ...current,
-                    [providerId]: data.models,
-                }))
-                setModelPickerOpen(true)
-            } else {
-                const hints = dict.errors.llm as Record<string, string>
-                setFetchModelsError(
-                    [hints[data.code], data.error].filter(Boolean).join(" ") ||
-                        `Request failed (${response.status})`,
-                )
-            }
-        } catch {
-            setFetchModelsError(dict.errors.networkError)
-        } finally {
-            setFetchingModels(false)
+        if (
+            !open ||
+            selectedProvider?.provider !== "aihubmix" ||
+            loadedSuggestedProviders.aihubmix
+        ) {
+            return
         }
-    }
 
-    // The provider's own list once fetched, else the suggested models
-    const suggestedModels: ListedModel[] = selectedProvider
-        ? fetchedModels[selectedProvider.id] ||
-          (SUGGESTED_MODELS[selectedProvider.provider] || []).map((id) => ({
-              id,
-          }))
+        let cancelled = false
+        setLoadingSuggestedProvider("aihubmix")
+
+        fetch(getApiEndpoint("/api/aihubmix-models"))
+            .then((response) => {
+                if (!response.ok) {
+                    throw new Error(`Failed to load models: ${response.status}`)
+                }
+                return response.json()
+            })
+            .then((data: { models?: unknown }) => {
+                if (cancelled || !Array.isArray(data.models)) {
+                    return
+                }
+
+                const models = data.models.filter(
+                    (model): model is string => typeof model === "string",
+                )
+                if (models.length > 0) {
+                    setDynamicSuggestedModels((current) => ({
+                        ...current,
+                        aihubmix: models,
+                    }))
+                }
+            })
+            .catch((error) => {
+                console.warn("Failed to load AIHubMix models:", error)
+            })
+            .finally(() => {
+                if (cancelled) {
+                    return
+                }
+
+                setLoadedSuggestedProviders((current) => ({
+                    ...current,
+                    aihubmix: true,
+                }))
+                setLoadingSuggestedProvider(null)
+            })
+
+        return () => {
+            cancelled = true
+        }
+    }, [open, selectedProvider?.provider, loadedSuggestedProviders.aihubmix])
+
+    // Get suggested models for current provider
+    const suggestedModels = selectedProvider
+        ? dynamicSuggestedModels[selectedProvider.provider] ||
+          SUGGESTED_MODELS[selectedProvider.provider] ||
+          []
         : []
-    // Tool calls are what drawing needs: false when known to be missing
-    const supportsTools = (model: ListedModel) =>
-        selectedProvider
-            ? (model.tools ??
-              getModelInfo?.(selectedProvider.provider, model.id)?.tools)
-            : undefined
+    const isLoadingSuggestedModels =
+        selectedProvider?.provider === loadingSuggestedProvider
 
     // Filter out already-added models from suggestions
     const existingModelIds =
         selectedProvider?.models.map((m) => m.modelId) || []
     const availableSuggestions = suggestedModels.filter(
-        (model) => !existingModelIds.includes(model.id),
+        (modelId) => !existingModelIds.includes(modelId),
     )
     const emptyStateSuggestions = selectedProvider
         ? (SUGGESTED_MODELS[selectedProvider.provider] || [])
@@ -282,8 +246,6 @@ export function ModelConfigDialog({
         const newProvider = addProvider(providerType)
         setSelectedProviderId(newProvider.id)
         setValidationStatus("idle")
-        setFetchModelsError("")
-        setModelPickerOpen(false)
     }
 
     // Handle provider field updates
@@ -291,9 +253,9 @@ export function ModelConfigDialog({
         field: keyof ProviderConfig,
         value: string | boolean,
     ) => {
-        if (!selectedProviderId || !selectedProvider) return
-        const updates: Partial<ProviderConfig> = { [field]: value }
-        // Reset validation of the provider and its models when credentials change
+        if (!selectedProviderId) return
+        updateProvider(selectedProviderId, { [field]: value })
+        // Reset validation when credentials change
         const credentialFields = [
             "apiKey",
             "baseUrl",
@@ -303,21 +265,9 @@ export function ModelConfigDialog({
             "vertexApiKey",
         ]
         if (credentialFields.includes(field)) {
-            credentialsVersionRef.current++
             setValidationStatus("idle")
-            setValidatingModelIds(new Set())
-            setFetchedModels(({ [selectedProviderId]: _, ...rest }) => rest)
-            setFetchModelsError("")
-            updates.validated = false
-            updates.models = selectedProvider.models.map((m) => ({
-                ...m,
-                validated: undefined,
-                validationError: undefined,
-                validationWarning: undefined,
-                responseTime: undefined,
-            }))
+            updateProvider(selectedProviderId, { validated: false })
         }
-        updateProvider(selectedProviderId, updates)
     }
 
     // Handle adding a model to current provider
@@ -387,96 +337,60 @@ export function ModelConfigDialog({
 
         let allValid = true
         let errorCount = 0
-        const credentialsVersion = credentialsVersionRef.current
 
-        // For EdgeOne, construct baseUrl from current origin
-        const baseUrl = isEdgeOne
-            ? `${window.location.origin}${getApiEndpoint("/api/edgeai")}`
-            : selectedProvider.baseUrl
+        // Validate each model
+        for (let i = 0; i < selectedProvider.models.length; i++) {
+            const model = selectedProvider.models[i]
+            setValidatingModelIndex(i)
 
-        // Test every model at once; each row updates when its answer arrives
-        setValidatingModelIds(new Set(selectedProvider.models.map((m) => m.id)))
-        await Promise.all(
-            selectedProvider.models.map(async (model) => {
-                let update: Partial<ModelConfig>
-                try {
-                    const response = await fetch(
-                        getApiEndpoint("/api/validate-model"),
-                        {
-                            method: "POST",
-                            headers: {
-                                "Content-Type": "application/json",
-                                "x-access-code":
-                                    localStorage.getItem(
-                                        STORAGE_KEYS.accessCode,
-                                    ) || "",
-                            },
-                            body: JSON.stringify({
-                                provider: selectedProvider.provider,
-                                apiKey: selectedProvider.apiKey,
-                                baseUrl,
-                                modelId: model.modelId,
-                                // AWS Bedrock credentials
-                                awsAccessKeyId: selectedProvider.awsAccessKeyId,
-                                awsSecretAccessKey:
-                                    selectedProvider.awsSecretAccessKey,
-                                awsRegion: selectedProvider.awsRegion,
-                                // Vertex AI credentials (Express Mode)
-                                vertexApiKey: selectedProvider.vertexApiKey,
-                            }),
-                        },
-                    )
-                    const data = await response.json().catch(() => ({}))
-                    update = data.valid
-                        ? {
-                              validated: true,
-                              validationError: undefined,
-                              validationWarning: data.warning,
-                              responseTime: data.responseTime,
-                          }
-                        : {
-                              validated: false,
-                              // The hint for the error's kind, then the
-                              // provider's own message
-                              validationError:
-                                  [
-                                      (
-                                          dict.errors.llm as Record<
-                                              string,
-                                              string
-                                          >
-                                      )[data.code],
-                                      data.error,
-                                  ]
-                                      .filter(Boolean)
-                                      .join(" ") ||
-                                  (response.ok
-                                      ? "Validation failed"
-                                      : `Request failed (${response.status})`),
-                              validationWarning: undefined,
-                          }
-                } catch {
-                    update = {
-                        validated: false,
-                        validationError: "Network error",
-                        validationWarning: undefined,
-                    }
-                }
-                // Credentials changed during the test: drop the result
-                if (credentialsVersionRef.current !== credentialsVersion) return
-                if (update.validated === false) {
+            try {
+                // For EdgeOne, construct baseUrl from current origin
+                const baseUrl = isEdgeOne
+                    ? `${window.location.origin}/api/edgeai`
+                    : selectedProvider.baseUrl
+
+                const response = await fetch("/api/validate-model", {
+                    method: "POST",
+                    headers: { "Content-Type": "application/json" },
+                    body: JSON.stringify({
+                        provider: selectedProvider.provider,
+                        apiKey: selectedProvider.apiKey,
+                        baseUrl,
+                        modelId: model.modelId,
+                        // AWS Bedrock credentials
+                        awsAccessKeyId: selectedProvider.awsAccessKeyId,
+                        awsSecretAccessKey: selectedProvider.awsSecretAccessKey,
+                        awsRegion: selectedProvider.awsRegion,
+                        // Vertex AI credentials (Express Mode)
+                        vertexApiKey: selectedProvider.vertexApiKey,
+                    }),
+                })
+                const data = await response.json()
+
+                if (data.valid) {
+                    updateModel(selectedProviderId, model.id, {
+                        validated: true,
+                        validationError: undefined,
+                    })
+                } else {
                     allValid = false
                     errorCount++
+                    updateModel(selectedProviderId, model.id, {
+                        validated: false,
+                        validationError: data.error || "Validation failed",
+                    })
                 }
-                updateModel(selectedProviderId, model.id, update)
-                setValidatingModelIds((prev) => {
-                    const next = new Set(prev)
-                    next.delete(model.id)
-                    return next
+            } catch {
+                allValid = false
+                errorCount++
+                updateModel(selectedProviderId, model.id, {
+                    validated: false,
+                    validationError: "Network error",
                 })
-            }),
-        )
-        if (credentialsVersionRef.current !== credentialsVersion) return
+            }
+        }
+
+        setValidatingModelIndex(null)
 
         if (allValid) {
             setValidationStatus("success")
@@ -493,13 +407,7 @@ export function ModelConfigDialog({
             setValidationStatus("error")
             setValidationError(`${errorCount} model(s) failed validation`)
         }
-    }, [
-        selectedProvider,
-        selectedProviderId,
-        updateProvider,
-        updateModel,
-        dict,
-    ])
+    }, [selectedProvider, selectedProviderId, updateProvider, updateModel])
 
     // Get all available provider types
     const availableProviders = Object.keys(PROVIDER_INFO) as ProviderName[]
@@ -655,10 +563,6 @@ export function ModelConfigDialog({
                                                 )
                                                 setValidationStatus("idle")
                                                 setShowApiKey(false)
-                                                // These belong to the
-                                                // provider shown before
-                                                setFetchModelsError("")
-                                                setModelPickerOpen(false)
                                             }}
                                             className={cn(
                                                 "group flex items-center gap-3 px-3 py-2.5 rounded-xl w-full",
@@ -711,9 +615,7 @@ export function ModelConfigDialog({
 
                         {/* Add Provider */}
                         <div className="p-3 border-t border-border-subtle">
-                            {/* Always empty so picking the same type again still fires */}
                             <Select
-                                value=""
                                 onValueChange={(v) =>
                                     handleAddProvider(v as ProviderName)
                                 }
@@ -934,136 +836,57 @@ export function ModelConfigDialog({
                                                 >
                                                     <Plus className="h-3.5 w-3.5" />
                                                 </Button>
-                                                {PROVIDER_INFO[
-                                                    selectedProvider.provider
-                                                ].modelList && (
-                                                    <Button
-                                                        variant="outline"
-                                                        size="sm"
-                                                        className="h-8 rounded-lg"
-                                                        onClick={
-                                                            handleFetchModels
+                                                <Select
+                                                    onValueChange={(value) => {
+                                                        if (value) {
+                                                            handleAddModel(
+                                                                value,
+                                                            )
                                                         }
-                                                        disabled={
-                                                            fetchingModels
-                                                        }
-                                                        title={
-                                                            dict.modelConfig
-                                                                .fetchModels
-                                                        }
-                                                        aria-label={
-                                                            dict.modelConfig
-                                                                .fetchModels
-                                                        }
-                                                    >
-                                                        {fetchingModels ? (
-                                                            <Loader2 className="h-3.5 w-3.5 animate-spin" />
-                                                        ) : (
-                                                            <RefreshCw className="h-3.5 w-3.5" />
-                                                        )}
-                                                    </Button>
-                                                )}
-                                                {/* modal: the dialog blocks the
-                                                wheel outside itself, and the
-                                                list is rendered outside it */}
-                                                <Popover
-                                                    modal
-                                                    open={modelPickerOpen}
-                                                    onOpenChange={
-                                                        setModelPickerOpen
+                                                    }}
+                                                    disabled={
+                                                        isLoadingSuggestedModels ||
+                                                        availableSuggestions.length ===
+                                                            0
                                                     }
                                                 >
-                                                    <PopoverTrigger asChild>
-                                                        <Button
-                                                            variant="outline"
-                                                            size="sm"
-                                                            className="w-28 h-8 rounded-lg text-xs"
-                                                            disabled={
-                                                                availableSuggestions.length ===
+                                                    <SelectTrigger className="w-28 h-8 rounded-lg hover:bg-interactive-hover">
+                                                        {isLoadingSuggestedModels ? (
+                                                            <Loader2 className="h-3.5 w-3.5 animate-spin" />
+                                                        ) : (
+                                                            <span className="text-xs">
+                                                                {availableSuggestions.length ===
                                                                 0
-                                                            }
-                                                        >
-                                                            {availableSuggestions.length ===
-                                                            0
-                                                                ? dict
-                                                                      .modelConfig
-                                                                      .allAdded
-                                                                : dict
-                                                                      .modelConfig
-                                                                      .suggested}
-                                                        </Button>
-                                                    </PopoverTrigger>
-                                                    <PopoverContent
-                                                        className="w-80 p-0"
-                                                        align="end"
-                                                    >
-                                                        <Command>
-                                                            <CommandInput
-                                                                placeholder={
-                                                                    dict
-                                                                        .modelConfig
-                                                                        .searchModels
-                                                                }
-                                                            />
-                                                            <CommandList className="max-h-72">
-                                                                <CommandEmpty>
-                                                                    {
-                                                                        dict
-                                                                            .modelConfig
-                                                                            .noModelsFound
+                                                                    ? dict
+                                                                          .modelConfig
+                                                                          .allAdded
+                                                                    : dict
+                                                                          .modelConfig
+                                                                          .suggested}
+                                                            </span>
+                                                        )}
+                                                    </SelectTrigger>
+                                                    <SelectContent className="max-h-72">
+                                                        {availableSuggestions.map(
+                                                            (modelId) => (
+                                                                <SelectItem
+                                                                    key={
+                                                                        modelId
                                                                     }
-                                                                </CommandEmpty>
-                                                                {availableSuggestions.map(
-                                                                    (model) => (
-                                                                        <CommandItem
-                                                                            key={
-                                                                                model.id
-                                                                            }
-                                                                            value={
-                                                                                model.id
-                                                                            }
-                                                                            onSelect={() => {
-                                                                                handleAddModel(
-                                                                                    model.id,
-                                                                                )
-                                                                                setModelPickerOpen(
-                                                                                    false,
-                                                                                )
-                                                                            }}
-                                                                            className="font-mono text-xs"
-                                                                        >
-                                                                            <span className="truncate">
-                                                                                {
-                                                                                    model.id
-                                                                                }
-                                                                            </span>
-                                                                            {supportsTools(
-                                                                                model,
-                                                                            ) ===
-                                                                                false && (
-                                                                                <span className="ml-auto shrink-0 font-sans text-[10px] text-amber-600 dark:text-amber-400">
-                                                                                    {
-                                                                                        dict
-                                                                                            .modelConfig
-                                                                                            .noTools
-                                                                                    }
-                                                                                </span>
-                                                                            )}
-                                                                        </CommandItem>
-                                                                    ),
-                                                                )}
-                                                            </CommandList>
-                                                        </Command>
-                                                    </PopoverContent>
-                                                </Popover>
+                                                                    value={
+                                                                        modelId
+                                                                    }
+                                                                    className="font-mono text-xs"
+                                                                >
+                                                                    {modelId}
+                                                                </SelectItem>
+                                                            ),
+                                                        )}
+                                                    </SelectContent>
+                                                </Select>
                                             </div>
                                         }
                                     >
-                                        {fetchModelsError && (
-                                            <p className="mb-2 text-xs text-destructive">
-                                                {fetchModelsError}
-                                            </p>
-                                        )}
                                         {/* Model List */}
                                         <div className="rounded-2xl border border-border-subtle bg-surface-2/30 overflow-hidden min-h-[120px]">
                                             {selectedProvider.models.length ===
@@ -1117,7 +940,7 @@ export function ModelConfigDialog({
                                             ) : (
                                                 <div className="divide-y divide-border-subtle">
                                                     {selectedProvider.models.map(
-                                                        (model) => (
+                                                        (model, index) => (
                                                             <div
                                                                 key={model.id}
                                                                 className={cn(
@@ -1127,24 +950,28 @@ export function ModelConfigDialog({
                                                                 <div className="flex items-center gap-3 p-3 min-w-0">
                                                                     {/* Status icon */}
                                                                     <div className="flex items-center justify-center w-8 h-8 rounded-lg flex-shrink-0">
-                                                                        {validatingModelIds.has(
-                                                                            model.id,
-                                                                        ) ? (
+                                                                        {validatingModelIndex !==
+                                                                            null &&
+                                                                        index ===
+                                                                            validatingModelIndex ? (
                                                                             // Currently validating
                                                                             <div className="w-full h-full rounded-lg bg-blue-500/10 flex items-center justify-center">
                                                                                 <Loader2 className="h-4 w-4 text-blue-500 animate-spin" />
                                                                             </div>
+                                                                        ) : validatingModelIndex !==
+                                                                              null &&
+                                                                          index >
+                                                                              validatingModelIndex &&
+                                                                          model.validated ===
+                                                                              undefined ? (
+                                                                            // Queued
+                                                                            <div className="w-full h-full rounded-lg bg-muted flex items-center justify-center">
+                                                                                <Clock className="h-4 w-4 text-muted-foreground" />
+                                                                            </div>
                                                                         ) : model.validated ===
                                                                           true ? (
-                                                                            // Valid, with the time the test took
-                                                                            <div
-                                                                                className="w-full h-full rounded-lg bg-success-muted flex items-center justify-center"
-                                                                                title={
-                                                                                    model.responseTime
-                                                                                        ? `${(model.responseTime / 1000).toFixed(1)} s`
-                                                                                        : undefined
-                                                                                }
-                                                                            >
+                                                                            // Valid
+                                                                            <div className="w-full h-full rounded-lg bg-success-muted flex items-center justify-center">
                                                                                 <Check className="h-4 w-4 text-success" />
                                                                             </div>
                                                                         ) : model.validated ===
@@ -1162,10 +989,7 @@ export function ModelConfigDialog({
                                                                     </div>
                                                                     <Input
                                                                         value={
-                                                                            modelIdDraft?.id ===
-                                                                            model.id
-                                                                                ? modelIdDraft.value
-                                                                                : model.modelId
+                                                                            model.modelId
                                                                         }
                                                                         title={
                                                                             model.modelId
@@ -1183,14 +1007,24 @@ export function ModelConfigDialog({
                                                                                     null,
                                                                                 )
                                                                             }
-                                                                            setModelIdDraft(
-                                                                                {
-                                                                                    id: model.id,
-                                                                                    value: e
-                                                                                        .target
-                                                                                        .value,
-                                                                                },
-                                                                            )
+                                                                            if (
+                                                                                selectedProviderId
+                                                                            ) {
+                                                                                updateModel(
+                                                                                    selectedProviderId,
+                                                                                    model.id,
+                                                                                    {
+                                                                                        modelId:
+                                                                                            e
+                                                                                                .target
+                                                                                                .value,
+                                                                                        validated:
+                                                                                            undefined,
+                                                                                        validationError:
+                                                                                            undefined,
+                                                                                    },
+                                                                                )
+                                                                            }
                                                                         }}
                                                                         onKeyDown={(
                                                                             e,
@@ -1207,10 +1041,6 @@ export function ModelConfigDialog({
                                                                         ) => {
                                                                             const newModelId =
                                                                                 e.target.value.trim()
-                                                                            // Drop the draft; an invalid ID falls back to the saved one
-                                                                            setModelIdDraft(
-                                                                                null,
-                                                                            )
 
                                                                             // Helper to show error with shake
                                                                             const showError =
@@ -1305,28 +1135,6 @@ export function ModelConfigDialog({
                                                                             setEditError(
                                                                                 null,
                                                                             )
-                                                                            if (
-                                                                                selectedProviderId &&
-                                                                                newModelId !==
-                                                                                    model.modelId
-                                                                            ) {
-                                                                                updateModel(
-                                                                                    selectedProviderId,
-                                                                                    model.id,
-                                                                                    {
-                                                                                        modelId:
-                                                                                            newModelId,
-                                                                                        validated:
-                                                                                            undefined,
-                                                                                        validationError:
-                                                                                            undefined,
-                                                                                        validationWarning:
-                                                                                            undefined,
-                                                                                        responseTime:
-                                                                                            undefined,
-                                                                                    },
-                                                                                )
-                                                                            }
                                                                         }}
                                                                         className="flex-1 min-w-0 font-mono text-sm h-8 border-0 bg-transparent focus-visible:bg-background focus-visible:ring-1"
                                                                     />
@@ -1354,28 +1162,6 @@ export function ModelConfigDialog({
                                                                             }
                                                                         </p>
                                                                     )}
-                                                                {!model.validationWarning &&
-                                                                    getModelInfo?.(
-                                                                        selectedProvider.provider,
-                                                                        model.modelId,
-                                                                    )?.tools ===
-                                                                        false && (
-                                                                        <p className="text-[11px] text-amber-600 dark:text-amber-400 px-3 pb-2 pl-14">
-                                                                            {
-                                                                                dict
-                                                                                    .modelConfig
-                                                                                    .mayNotDraw
-                                                                            }
-                                                                        </p>
-                                                                    )}
-                                                                {model.validated &&
-                                                                    model.validationWarning && (
-                                                                        <p className="text-[11px] text-amber-600 dark:text-amber-400 px-3 pb-2 pl-14">
-                                                                            {
-                                                                                model.validationWarning
-                                                                            }
-                                                                        </p>
-                                                                    )}
                                                                 {/* Show edit error inline */}
                                                                 {editError?.modelId ===
                                                                     model.id && (

components/model-selector.tsx

@@ -264,13 +264,9 @@ export function ModelSelector({
                                                         (model) => (
                                                             <ModelSelectorItem
                                                                 key={model.id}
-                                                                // Unique value so same-named models highlight
-                                                                // separately; keywords keep search by name
-                                                                value={model.id}
-                                                                keywords={[
-                                                                    model.modelId,
-                                                                    providerLabel,
-                                                                ]}
+                                                                value={
+                                                                    model.modelId
+                                                                }
                                                                 onSelect={() =>
                                                                     handleSelect(
                                                                         model.id,
@@ -355,11 +351,9 @@ export function ModelSelector({
                                                         (model) => (
                                                             <ModelSelectorItem
                                                                 key={model.id}
-                                                                value={model.id}
-                                                                keywords={[
-                                                                    model.modelId,
-                                                                    providerLabel,
-                                                                ]}
+                                                                value={
+                                                                    model.modelId
+                                                                }
                                                                 onSelect={() =>
                                                                     handleSelect(
                                                                         model.id,

components/provider-credentials-fields.tsx

@@ -13,12 +13,7 @@ import {
 } from "@/components/ui/select"
 import { useDictionary } from "@/hooks/use-dictionary"
 import { formatMessage } from "@/lib/i18n/utils"
-import {
-    chatRequestUrl,
-    normalizeBaseUrl,
-    PROVIDER_INFO,
-    type ProviderName,
-} from "@/lib/types/model-config"
+import { PROVIDER_INFO, type ProviderName } from "@/lib/types/model-config"
 
 // Logical secret field. The caller owns the actual input — plaintext for the
 // user dialog, write-only masked for the admin panel — supplied via
@@ -82,7 +77,6 @@ export function ProviderCredentialsFields({
     const baseUrlLabel = formatMessage(dict.modelConfig.baseUrlWithExample, {
         example: info.defaultBaseUrl || "https://api.example.com/v1",
     })
-    const requestUrl = baseUrl ? chatRequestUrl(provider, baseUrl) : null
 
     // EdgeOne needs no credentials — the caller supplies just a test button
     if (provider === "edgeone") {
@@ -214,29 +208,17 @@ export function ProviderCredentialsFields({
                 </>
             ) : (
                 <>
-                    {/* API Key, with a link to where the provider issues keys */}
+                    {/* API Key */}
                     <div className="space-y-2">
-                        <div className="flex items-center justify-between">
-                            <Label
-                                htmlFor="api-key"
-                                className="text-xs font-medium flex items-center gap-1.5"
-                            >
-                                <Key className="h-3.5 w-3.5 text-muted-foreground" />
-                                {dict.modelConfig.apiKey}
-                                {provider === "ollama" &&
-                                    ` ${dict.modelConfig.optional}`}
-                            </Label>
-                            {info.apiKeyUrl && (
-                                <a
-                                    href={info.apiKeyUrl}
-                                    target="_blank"
-                                    rel="noopener noreferrer"
-                                    className="text-xs text-primary hover:underline"
-                                >
-                                    {dict.modelConfig.getApiKey}
-                                </a>
-                            )}
-                        </div>
+                        <Label
+                            htmlFor="api-key"
+                            className="text-xs font-medium flex items-center gap-1.5"
+                        >
+                            <Key className="h-3.5 w-3.5 text-muted-foreground" />
+                            {dict.modelConfig.apiKey}
+                            {provider === "ollama" &&
+                                ` ${dict.modelConfig.optional}`}
+                        </Label>
                         {renderSecret({ field: "apiKey", id: "api-key" })}
                     </div>
 
@@ -256,28 +238,12 @@ export function ProviderCredentialsFields({
                             onChange={(e) =>
                                 onChange("baseUrl", e.target.value)
                             }
-                            // Drop a pasted endpoint path such as /chat/completions
-                            onBlur={(e) => {
-                                const normalized = normalizeBaseUrl(
-                                    e.target.value,
-                                )
-                                if (normalized !== e.target.value) {
-                                    onChange("baseUrl", normalized)
-                                }
-                            }}
                             placeholder={
                                 info.defaultBaseUrl ||
                                 dict.modelConfig.customEndpoint
                             }
                             className="h-9 rounded-xl font-mono text-xs"
                         />
-                        {requestUrl && (
-                            <p className="text-xs text-muted-foreground font-mono break-all">
-                                {formatMessage(dict.modelConfig.requestUrl, {
-                                    url: requestUrl,
-                                })}
-                            </p>
-                        )}
                         {provider === "minimax" && (
                             <p className="text-xs text-muted-foreground">
                                 {dict.modelConfig.minimaxBaseUrlHint}

contexts/diagram-context.tsx

@@ -1,17 +1,16 @@
 "use client"
 
 import type React from "react"
-import { createContext, useContext, useRef, useState } from "react"
+import { createContext, useContext, useEffect, useRef, useState } from "react"
 import type { DrawIoEmbedRef, EventExport } from "react-drawio"
 import { toast } from "sonner"
 import type { ExportFormat } from "@/components/save-dialog"
 import { getApiEndpoint } from "@/lib/base-path"
 import {
-    BLANK_MXFILE,
-    normalizeToMxfile,
-} from "@/packages/mcp-server/src/pages.ts"
-import { validateAndFixXml } from "@/packages/mcp-server/src/xml-validation.ts"
-import { extractDiagramXML, isRealDiagram } from "../lib/utils"
+    extractDiagramXML,
+    isRealDiagram,
+    validateAndFixXml,
+} from "../lib/utils"
 
 interface DiagramContextType {
     chartXML: string
@@ -43,12 +42,6 @@ interface DiagramContextType {
 
 const DiagramContext = createContext<DiagramContextType | undefined>(undefined)
 
-// Exports for thumbnails, validation PNGs and file saves carry a tag in the
-// request's `message` field. draw.io echoes the request back in the export
-// event, so each result reaches its own caller; untagged exports (chat-panel's
-// onFetchChart) resolve resolverRef.
-type ExportTag = "thumbnail" | "validation"
-
 export function DiagramProvider({ children }: { children: React.ReactNode }) {
     const [chartXML, setChartXML] = useState<string>("")
     const [latestSvg, setLatestSvg] = useState<string>("")
@@ -60,10 +53,8 @@ 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)
-    // Pending thumbnail and validation PNG exports, keyed by their export tag
-    const taggedResolversRef = useRef<
-        Partial<Record<ExportTag, (value: string) => void>>
-    >({})
+    // 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 latest chartXML for restoration after remount
@@ -85,12 +76,10 @@ export function DiagramProvider({ children }: { children: React.ReactNode }) {
         setIsDrawioReady(false)
     }
 
-    // Update chartXML and its ref together, so callbacks that read the ref
-    // (export handler, autosave) see the new value right away
-    const updateChartXML = (xml: string) => {
-        chartXMLRef.current = xml
-        setChartXML(xml)
-    }
+    // Keep chartXMLRef in sync with state for restoration after remount
+    useEffect(() => {
+        chartXMLRef.current = chartXML
+    }, [chartXML])
 
     // Track if we're expecting an export for file save (stores raw export data)
     const saveResolverRef = useRef<{
@@ -117,52 +106,64 @@ export function DiagramProvider({ children }: { children: React.ReactNode }) {
         }
     }
 
-    // Export with a tag in `message` (draw.io echoes it back in the export
-    // event) and wait for that result. Resolves to null on timeout, which is
-    // expected occasionally.
-    const requestTaggedExport = (
-        tag: ExportTag,
-        format: "xmlsvg" | "png",
-        timeoutMs: number,
-    ) =>
-        new Promise<string | null>((resolve) => {
-            const finish = (value: string | null) => {
-                clearTimeout(timer)
-                if (taggedResolversRef.current[tag] === finish) {
-                    delete taggedResolversRef.current[tag]
-                }
-                resolve(value)
-            }
-            const timer = setTimeout(() => finish(null), timeoutMs)
-            taggedResolversRef.current[tag] = finish
-            drawioRef.current?.exportDiagram({ format, message: tag })
-        })
-
     // Get current diagram as SVG for thumbnail (used by session storage)
     const getThumbnailSvg = async (): Promise<string | null> => {
         if (!drawioRef.current) return null
         // Don't export if diagram is empty
-        if (!isRealDiagram(chartXMLRef.current)) return null
+        if (!isRealDiagram(chartXML)) return null
+
+        try {
+            const svgData = await Promise.race([
+                new Promise<string>((resolve) => {
+                    resolverRef.current = resolve
+                    drawioRef.current?.exportDiagram({ format: "xmlsvg" })
+                }),
+                new Promise<string>((_, reject) =>
+                    setTimeout(() => reject(new Error("Export timeout")), 3000),
+                ),
+            ])
 
-        // xmlsvg exports return an SVG data URL
-        const svgData = await requestTaggedExport("thumbnail", "xmlsvg", 3000)
-        if (svgData?.startsWith("data:image/svg")) {
             // Update latestSvg so it's available for future saves
-            setLatestSvg(svgData)
-            return svgData
+            if (svgData?.includes("<svg")) {
+                setLatestSvg(svgData)
+                return svgData
+            }
+            return null
+        } catch {
+            // Timeout is expected occasionally - don't log as error
+            return null
         }
-        return null
     }
 
     // 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(chartXMLRef.current)) return null
+        if (!isRealDiagram(chartXML)) return null
 
-        const pngData = await requestTaggedExport("validation", "png", 5000)
-        // PNG data should be a base64 data URL
-        return pngData?.startsWith("data:image/png") ? pngData : 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 = (
@@ -171,11 +172,9 @@ export function DiagramProvider({ children }: { children: React.ReactNode }) {
     ): string | null => {
         let xmlToLoad = chart
 
-        // Validate XML structure before loading (unless skipped for internal
-        // use). Not strict: the XML may hold the user's own diagram, and the
-        // tool handlers check model XML strictly before it gets here.
+        // Validate XML structure before loading (unless skipped for internal use)
         if (!skipValidation) {
-            const validation = validateAndFixXml(chart, { strict: false })
+            const validation = validateAndFixXml(chart)
             if (!validation.valid) {
                 console.warn(
                     "[loadDiagram] Validation error:",
@@ -194,7 +193,7 @@ export function DiagramProvider({ children }: { children: React.ReactNode }) {
         }
 
         // Keep chartXML in sync even when diagrams are injected (e.g., display_diagram tool)
-        updateChartXML(xmlToLoad)
+        setChartXML(xmlToLoad)
 
         if (drawioRef.current) {
             drawioRef.current.load({
@@ -206,17 +205,24 @@ export function DiagramProvider({ children }: { children: React.ReactNode }) {
     }
 
     const handleDiagramExport = (data: EventExport) => {
-        // Tagged exports (thumbnail, validation PNG, file save) go only to
-        // their own caller, so they never take the result meant for resolverRef
-        const tag = data.message?.message
-        if (tag === "thumbnail" || tag === "validation") {
-            taggedResolversRef.current[tag]?.(data.data)
+        // Handle PNG export for VLM validation
+        if (pngResolverRef.current && data.data?.startsWith("data:image/png")) {
+            pngResolverRef.current(data.data)
+            pngResolverRef.current = null
             return
         }
-        if (tag === "save") {
-            saveResolverRef.current.resolver?.(data.data, data.xml)
+
+        // Handle save to file if requested (process raw data before extraction)
+        if (saveResolverRef.current.resolver) {
+            const format = saveResolverRef.current.format
+            saveResolverRef.current.resolver(data.data, data.xml)
             saveResolverRef.current = { resolver: null, format: null }
-            return
+            // For non-xmlsvg formats, skip XML extraction as it will fail
+            // Only drawio (which uses xmlsvg internally) has the content attribute
+            // xmlsvg is saved directly as SVG file, no need for extraction
+            if (format === "png" || format === "svg" || format === "xmlsvg") {
+                return
+            }
         }
 
         // Don't write chartXML here: exports don't change the diagram, and
@@ -230,15 +236,12 @@ export function DiagramProvider({ children }: { children: React.ReactNode }) {
         // Limit to 20 entries to prevent memory leaks during long sessions
         const MAX_HISTORY_SIZE = 20
         if (expectHistoryExportRef.current) {
-            // Store the full multi-page document (extractedXML is only the
-            // first page), so restoring a version keeps every page
-            const historyXml = chartXMLRef.current || extractedXML
             setDiagramHistory((prev) => {
                 const newHistory = [
                     ...prev,
                     {
                         svg: data.data,
-                        xml: historyXml,
+                        xml: extractedXML,
                     },
                 ]
                 // Keep only the last MAX_HISTORY_SIZE entries (circular buffer)
@@ -253,20 +256,18 @@ export function DiagramProvider({ children }: { children: React.ReactNode }) {
         }
     }
 
-    // react-drawio registers this callback once per iframe mount, so it must
-    // read refs: state captured in its closure would stay stale after a remount
     const handleDiagramAutoSave = (data: { xml?: string }) => {
         if (!data?.xml) return
-        // Don't overwrite a pending restore - if we have a real diagram but
-        // DrawIO hasn't loaded yet, it means we're waiting to restore
-        if (!hasCalledOnLoadRef.current && isRealDiagram(chartXMLRef.current)) {
+        // Don't overwrite a pending restore - if we have a real diagram in state
+        // but DrawIO isn't ready yet, it means we're waiting to restore
+        if (!isDrawioReady && isRealDiagram(chartXML)) {
             return
         }
-        updateChartXML(data.xml)
+        setChartXML(data.xml)
     }
 
     const clearDiagram = () => {
-        const emptyDiagram = BLANK_MXFILE
+        const emptyDiagram = `<mxfile><diagram name="Page-1" id="page-1"><mxGraphModel><root><mxCell id="0"/><mxCell id="1" parent="0"/></root></mxGraphModel></diagram></mxfile>`
         // Skip validation for trusted internal template (loadDiagram also sets chartXML)
         loadDiagram(emptyDiagram, true)
         setLatestSvg("")
@@ -300,11 +301,11 @@ export function DiagramProvider({ children }: { children: React.ReactNode }) {
                     const xml = fullDiagramXML?.trim()
                         ? fullDiagramXML
                         : extractDiagramXML(exportData)
-                    fileContent =
-                        normalizeToMxfile(xml, {
-                            pageId: "page-1",
-                            pageName: "Page-1",
-                        }) ?? xml
+                    let xmlContent = xml
+                    if (!xml.includes("<mxfile")) {
+                        xmlContent = `<mxfile><diagram name="Page-1" id="page-1">${xml}</diagram></mxfile>`
+                    }
+                    fileContent = xmlContent
                     mimeType = "application/xml"
                     extension = ".drawio"
                 } else if (format === "png") {
@@ -364,10 +365,7 @@ export function DiagramProvider({ children }: { children: React.ReactNode }) {
         }
 
         // Export diagram - callback will be handled in handleDiagramExport
-        drawioRef.current.exportDiagram({
-            format: drawioFormat,
-            message: "save",
-        })
+        drawioRef.current.exportDiagram({ format: drawioFormat })
     }
 
     // Log save event to Langfuse (just flags the trace, doesn't send content)

docs/cn/README_CN.md

@@ -124,13 +124,6 @@ claude mcp add drawio -- npx @next-ai-drawio/mcp-server@latest
 
 图表会实时显示在浏览器中！
 
-MCP服务器包含网页版的大部分画图功能：
-
--   与网页版相同的画图规则和形状库（AWS、Azure、GCP、Kubernetes等）
--   截图工具，AI可以查看画好的图并自行修正
--   版本历史、多页图表，以及下载为`.drawio`、`.png`、`.svg`或`.drawio.svg`格式
--   自动保存到`~/.next-ai-drawio/`，重启后可以接着画
-
 详情请参阅[MCP服务器README](../../packages/mcp-server/README.md)，了解VS Code、Cursor等客户端配置。
 
 ## 快速开始

docs/cn/ai-providers.md

@@ -149,11 +149,9 @@ AZURE_REASONING_SUMMARY=detailed  # 可选：none, brief, detailed
 AWS_REGION=us-west-2
 AWS_ACCESS_KEY_ID=your_access_key_id
 AWS_SECRET_ACCESS_KEY=your_secret_access_key
-AI_MODEL=global.anthropic.claude-sonnet-5-5
+AI_MODEL=anthropic.claude-sonnet-4-5-20250514-v1:0
 ```
 
-较新的 Claude 模型只能通过推理配置文件（inference profile）的 ID 调用，这种 ID 以地区前缀开头，例如 `global.` 或 `us.`。直接用 `anthropic.claude-sonnet-5-5` 这样的 ID 会报错 “on-demand throughput isn't supported”。
-
 注意：在 AWS 环境（Lambda、带有 IAM 角色的 EC2）中，凭证会自动从 IAM 角色获取。
 
 ### OpenRouter

docs/en/ai-providers.md

@@ -164,11 +164,9 @@ AZURE_REASONING_SUMMARY=detailed  # Optional: none, brief, detailed
 AWS_REGION=us-west-2
 AWS_ACCESS_KEY_ID=your_access_key_id
 AWS_SECRET_ACCESS_KEY=your_secret_access_key
-AI_MODEL=global.anthropic.claude-sonnet-5-5
+AI_MODEL=anthropic.claude-sonnet-4-5-20250514-v1:0
 ```
 
-Recent Claude models answer only through an inference profile id, which starts with a region prefix such as `global.` or `us.`. The plain id (`anthropic.claude-sonnet-5-5`) fails with "on-demand throughput isn't supported".
-
 Note: On AWS (Lambda, EC2 with IAM role), credentials are automatically obtained from the IAM role.
 
 ### OpenRouter

docs/ja/README_JA.md

@@ -122,13 +122,6 @@ Claudeにダイアグラムの作成を依頼：
 
 ダイアグラムがリアルタイムでブラウザに表示されます！
 
-MCPサーバーには、Webアプリの主な作図機能が含まれています：
-
--   Webアプリと同じ作図ルールとシェイプライブラリ（AWS、Azure、GCP、Kubernetesなど）
--   スクリーンショットツール：AIが描画結果を確認して修正できます
--   バージョン履歴、複数ページのダイアグラム、`.drawio`・`.png`・`.svg`・`.drawio.svg`形式でのダウンロード
--   `~/.next-ai-drawio/`への自動保存：再起動後も続きから編集できます
-
 詳細は[MCPサーバーREADME](../../packages/mcp-server/README.md)をご覧ください（VS Code、Cursorなどのクライアント設定も含む）。
 
 ## はじめに

docs/ja/ai-providers.md

@@ -149,11 +149,9 @@ AZURE_REASONING_SUMMARY=detailed  # 任意: none, brief, detailed
 AWS_REGION=us-west-2
 AWS_ACCESS_KEY_ID=your_access_key_id
 AWS_SECRET_ACCESS_KEY=your_secret_access_key
-AI_MODEL=global.anthropic.claude-sonnet-5-5
+AI_MODEL=anthropic.claude-sonnet-4-5-20250514-v1:0
 ```
 
-最近の Claude モデルは、推論プロファイル（inference profile）の ID でのみ呼び出せます。この ID は `global.` や `us.` などのリージョン接頭辞で始まります。`anthropic.claude-sonnet-5-5` のような接頭辞なしの ID では「on-demand throughput isn't supported」というエラーになります。
-
 注: AWS 上（IAM ロールを持つ Lambda や EC2）では、認証情報は IAM ロールから自動的に取得されます。
 
 ### OpenRouter

docs/shape-libraries/README.md

@@ -11,6 +11,7 @@ Reference: `style="shape=mxgraph.<library>.<shape_name>"`
 | gcp2 | 297 | `mxgraph.gcp2` | Google Cloud Platform - Compute Engine, BigQuery, GKE, etc. | [gcp2.md](./gcp2.md) |
 | alibaba_cloud | 273 | `mxgraph.alibaba_cloud` | Alibaba Cloud - ECS, OSS, RDS, SLB, VPC, etc. | [alibaba_cloud.md](./alibaba_cloud.md) |
 | openstack | 18 | `mxgraph.openstack` | OpenStack cloud platform icons | [openstack.md](./openstack.md) |
+| digitalocean | 74 | `mxgraph.digitalocean` | DigitalOcean - Droplets, Spaces, Kubernetes, etc. | [digitalocean.md](./digitalocean.md) |
 | salesforce | 96 | `mxgraph.salesforce` | Salesforce platform icons | [salesforce.md](./salesforce.md) |
 
 ## Networking & Infrastructure
@@ -19,6 +20,7 @@ Reference: `style="shape=mxgraph.<library>.<shape_name>"`
 |---------|--------|--------|-------------|------|
 | cisco19 | 232 | `mxgraph.cisco19` | Cisco network equipment - routers, switches, firewalls | [cisco19.md](./cisco19.md) |
 | network | 58 | `mxgraph.networks` | General network diagram symbols | [network.md](./network.md) |
+| arista | 45 | `mxgraph.arista` | Arista network switches and equipment | [arista.md](./arista.md) |
 | kubernetes | 40 | `mxgraph.kubernetes` | Kubernetes - pods, services, deployments, nodes | [kubernetes.md](./kubernetes.md) |
 | vvd | 93 | `mxgraph.vvd` | VMware Validated Design icons | [vvd.md](./vvd.md) |
 | rack | 11 | `mxgraph.rack` | Server rack and data center equipment | [rack.md](./rack.md) |
@@ -28,6 +30,7 @@ Reference: `style="shape=mxgraph.<library>.<shape_name>"`
 | Library | Shapes | Prefix | Description | File |
 |---------|--------|--------|-------------|------|
 | bpmn | 39 | `mxgraph.bpmn` | Business Process Model and Notation - events, gateways, tasks | [bpmn.md](./bpmn.md) |
+| eip | 36 | `mxgraph.eip` | Enterprise Integration Patterns - messaging, routing | [eip.md](./eip.md) |
 | lean_mapping | 13 | `mxgraph.lean_mapping` | Lean/Value Stream Mapping symbols | [lean_mapping.md](./lean_mapping.md) |
 
 ## General Diagrams
@@ -45,7 +48,6 @@ Reference: `style="shape=mxgraph.<library>.<shape_name>"`
 | Library | Shapes | Prefix | Description | File |
 |---------|--------|--------|-------------|------|
 | android | 17 | `mxgraph.android` | Android UI mockup components | [android.md](./android.md) |
-| material_design | 300 | `image=https://fonts.gstatic.com/...` | Google Material Icons (SVG images) | [material_design.md](./material_design.md) |
 
 ## Enterprise Software
 
@@ -71,5 +73,6 @@ Reference: `style="shape=mxgraph.<library>.<shape_name>"`
 | Library | Shapes | Prefix | Description | File |
 |---------|--------|--------|-------------|------|
 | webicons | 176 | `mxgraph.webicons` | Web/social media logos - GitHub, Twitter, AWS, etc. | [webicons.md](./webicons.md) |
+| un-ocha-icons | 242 | `mxgraph.un-ocha-icons` | UN OCHA humanitarian icons | [un-ocha-icons.md](./un-ocha-icons.md) |
 
-**Total: 30 libraries, 4,184 shapes**
+**Total: 33 libraries, 4,281 shapes**

edge-functions/api/edgeai/chat/completions.ts

@@ -67,62 +67,41 @@ const MODEL_ALIASES: Record<string, string> = {
     "deepseek-v3-0324": "@tx/deepseek-ai/deepseek-v3-0324",
 }
 
+const CORS_HEADERS = {
+    "Access-Control-Allow-Origin": "*",
+    "Access-Control-Allow-Methods": "POST, OPTIONS",
+    "Access-Control-Allow-Headers": "Content-Type, Authorization",
+}
+
 /**
- * Create standardized JSON response
+ * Create standardized response with CORS headers
  */
 function createResponse(body: any, status = 200, extraHeaders = {}): Response {
     return new Response(JSON.stringify(body), {
         status,
         headers: {
             "Content-Type": "application/json",
+            ...CORS_HEADERS,
             ...extraHeaders,
         },
     })
 }
 
-// Only the app's own server (/api/chat, /api/validate-model) calls this
-// function, so no CORS headers are sent: other sites' pages can't call it
-// from a browser and spend the deployment's Edge AI quota.
-// Same rule as lib/access-code.ts, but reading the edge function's env.
-// No codes configured (or env unavailable) means no check.
-function hasValidAccessCode(request: Request, env: any): boolean {
-    const accessCodes: string[] =
-        env?.ACCESS_CODE_LIST?.split(",")
-            .map((code: string) => code.trim())
-            .filter(Boolean) || []
-    if (accessCodes.length === 0) return true
-    const accessCode = request.headers.get("x-access-code")
-    return !!accessCode && accessCodes.includes(accessCode)
+/**
+ * Handle OPTIONS request for CORS preflight
+ */
+function handleOptionsRequest(): Response {
+    return new Response(null, {
+        headers: {
+            ...CORS_HEADERS,
+            "Access-Control-Max-Age": "86400",
+        },
+    })
 }
 
-export async function onRequest({ request, env }: any) {
-    // Requiring JSON also makes any cross-site browser request need a CORS
-    // preflight, which fails without CORS headers
-    if (
-        request.method !== "POST" ||
-        !request.headers.get("content-type")?.includes("application/json")
-    ) {
-        return createResponse(
-            {
-                error: {
-                    message: "Expected a POST request with a JSON body",
-                    type: "invalid_request_error",
-                },
-            },
-            400,
-        )
-    }
-
-    if (!hasValidAccessCode(request, env)) {
-        return createResponse(
-            {
-                error: {
-                    message: "Invalid or missing access code",
-                    type: "invalid_request_error",
-                },
-            },
-            401,
-        )
+export async function onRequest({ request, env: _env }: any) {
+    if (request.method === "OPTIONS") {
+        return handleOptionsRequest()
     }
 
     request.headers.delete("accept-encoding")
@@ -174,7 +153,7 @@ export async function onRequest({ request, env }: any) {
                         type: "invalid_request_error",
                     },
                 },
-                400,
+                429,
             )
         }
 
@@ -237,6 +216,7 @@ export async function onRequest({ request, env }: any) {
                     "Cache-Control": "no-cache, no-store, no-transform",
                     "X-Accel-Buffering": "no",
                     Connection: "keep-alive",
+                    ...CORS_HEADERS,
                 },
             })
         } catch (error: any) {

electron/electron.d.ts

@@ -60,6 +60,10 @@ declare global {
             maximize: () => void
             /** Close the window */
             close: () => void
+            /** Open file dialog and return file path */
+            openFile: () => Promise<string | null>
+            /** Save data to file via save dialog */
+            saveFile: (data: string) => Promise<boolean>
             /** Get proxy configuration */
             getProxy: () => Promise<ProxyConfig>
             /** Set proxy configuration (saves and restarts server) */

electron/main/app-menu.ts

@@ -32,55 +32,6 @@ export function rebuildAppMenu(): void {
     buildAppMenu()
 }
 
-/**
- * Apply a preset and restart the server so it takes effect.
- * If the restart fails, go back to the previous preset and restart again,
- * so the running server always matches the saved current preset.
- * Throws an error describing the outcome on failure.
- */
-export async function switchPreset(
-    id: string,
-): Promise<Record<string, string>> {
-    const previousPresetId = getCurrentPresetId()
-    const env = applyPresetToEnv(id)
-    if (!env) {
-        throw new Error("Preset not found")
-    }
-    rebuildAppMenu()
-
-    // In development, scripts/electron-dev.mjs restarts the Next.js dev server
-    if (!app.isPackaged) {
-        return env
-    }
-
-    try {
-        await restartNextServer()
-        return env
-    } catch (error) {
-        console.error("Failed to restart server:", error)
-        const reason = error instanceof Error ? error.message : String(error)
-
-        // Revert to previous preset on failure
-        if (!previousPresetId || !applyPresetToEnv(previousPresetId)) {
-            setCurrentPreset(null)
-        }
-        // Rebuild menu to restore previous checkmark state
-        rebuildAppMenu()
-
-        try {
-            await restartNextServer()
-        } catch (retryError) {
-            console.error("Failed to restart server again:", retryError)
-            throw new Error(
-                `The server could not be restarted.\n\nPlease restart the app.\n\nError: ${reason}`,
-            )
-        }
-        throw new Error(
-            `The server could not be restarted.\n\nThe previous configuration has been restored.\n\nError: ${reason}`,
-        )
-    }
-}
-
 /**
  * Get the menu template with translations
  */
@@ -241,14 +192,32 @@ function buildConfigMenu(
         type: "radio",
         checked: preset.id === currentPresetId,
         click: async () => {
-            try {
-                await switchPreset(preset.id)
-            } catch (error) {
-                // Show error dialog to notify user
-                dialog.showErrorBox(
-                    "Configuration Error",
-                    `Failed to apply preset "${preset.name}". ${error instanceof Error ? error.message : String(error)}`,
-                )
+            const previousPresetId = getCurrentPresetId()
+            const env = applyPresetToEnv(preset.id)
+
+            if (env) {
+                try {
+                    await restartNextServer()
+                    rebuildAppMenu() // Rebuild menu to update checkmarks
+                } catch (error) {
+                    console.error("Failed to restart server:", error)
+
+                    // Revert to previous preset on failure
+                    if (previousPresetId) {
+                        applyPresetToEnv(previousPresetId)
+                    } else {
+                        setCurrentPreset(null)
+                    }
+
+                    // Rebuild menu to restore previous checkmark state
+                    rebuildAppMenu()
+
+                    // Show error dialog to notify user
+                    dialog.showErrorBox(
+                        "Configuration Error",
+                        `Failed to apply preset "${preset.name}". The server could not be restarted.\n\nThe previous configuration has been restored.\n\nError: ${error instanceof Error ? error.message : String(error)}`,
+                    )
+                }
             }
         },
     }))

electron/main/config-manager.ts

@@ -1,11 +1,5 @@
 import { randomUUID } from "node:crypto"
-import {
-    existsSync,
-    mkdirSync,
-    readFileSync,
-    renameSync,
-    writeFileSync,
-} from "node:fs"
+import { existsSync, mkdirSync, readFileSync, writeFileSync } from "node:fs"
 import path from "node:path"
 import { app, safeStorage } from "electron"
 
@@ -36,9 +30,7 @@ let hasWarnedAboutPlaintext = false
  * Warns if encryption is not available (API key stored in plaintext)
  */
 function encryptValue(value: string): string {
-    // Already encrypted (a value that could not be decrypted): keep it as is
-    // instead of wrapping it in a second layer of encryption
-    if (!value || value.startsWith(ENCRYPTED_PREFIX)) {
+    if (!value) {
         return value
     }
 
@@ -69,7 +61,6 @@ function encryptValue(value: string): string {
 /**
  * Decrypt a sensitive value using safeStorage
  * Returns the original value if it's not encrypted or decryption fails
- * (so saving writes the stored ciphertext back unchanged)
  */
 function decryptValue(value: string): string {
     if (!value || !value.startsWith(ENCRYPTED_PREFIX)) {
@@ -188,15 +179,6 @@ export function loadPresets(): ConfigPresetsFile {
         return data
     } catch (error) {
         console.error("Failed to load config presets:", error)
-        // Move the unreadable file aside so the next save can't overwrite
-        // the user's presets with an empty list
-        const backupPath = `${configPath}.corrupt-${Date.now()}`
-        try {
-            renameSync(configPath, backupPath)
-            console.error(`Unreadable config presets moved to ${backupPath}`)
-        } catch (renameError) {
-            console.error("Failed to back up config presets:", renameError)
-        }
         return {
             version: 1,
             currentPresetId: null,
@@ -229,11 +211,7 @@ export function savePresets(data: ConfigPresetsFile): void {
     }
 
     try {
-        // Write a temp file and rename it, so a crash mid-write can't leave
-        // a truncated config file
-        const tempPath = `${configPath}.tmp`
-        writeFileSync(tempPath, JSON.stringify(dataToSave, null, 2), "utf-8")
-        renameSync(tempPath, configPath)
+        writeFileSync(configPath, JSON.stringify(dataToSave, null, 2), "utf-8")
     } catch (error) {
         console.error("Failed to save config presets:", error)
         throw error
@@ -329,10 +307,9 @@ export function deletePreset(id: string): boolean {
 
     data.presets.splice(index, 1)
 
-    // Clear current preset (and its env vars) if it was deleted
+    // Clear current preset if it was deleted
     if (data.currentPresetId === id) {
         data.currentPresetId = null
-        setPresetEnv(null)
     }
 
     savePresets(data)
@@ -345,15 +322,13 @@ export function deletePreset(id: string): boolean {
 export function setCurrentPreset(id: string | null): boolean {
     const data = loadPresets()
 
-    let preset: ConfigPreset | null = null
     if (id !== null) {
-        preset = data.presets.find((p) => p.id === id) || null
+        const preset = data.presets.find((p) => p.id === id)
         if (!preset) {
             return false
         }
     }
 
-    setPresetEnv(preset)
     data.currentPresetId = id
     savePresets(data)
     return true
@@ -390,23 +365,78 @@ const PROVIDER_ENV_MAP: Record<string, { apiKey: string; baseUrl: string }> = {
 }
 
 /**
- * Map a preset's config to environment variables
+ * Apply preset environment variables to the current process
+ * Returns the environment variables that were applied
+ */
+export function applyPresetToEnv(id: string): Record<string, string> | null {
+    const data = loadPresets()
+    const preset = data.presets.find((p) => p.id === id)
+
+    if (!preset) {
+        return null
+    }
+
+    const appliedEnv: Record<string, string> = {}
+    const provider = preset.config.AI_PROVIDER?.toLowerCase()
+
+    for (const [key, value] of Object.entries(preset.config)) {
+        if (value !== undefined && value !== "") {
+            // Map generic AI_API_KEY to provider-specific key
+            if (
+                key === "AI_API_KEY" &&
+                provider &&
+                PROVIDER_ENV_MAP[provider]
+            ) {
+                const providerApiKey = PROVIDER_ENV_MAP[provider].apiKey
+                if (providerApiKey) {
+                    process.env[providerApiKey] = value
+                    appliedEnv[providerApiKey] = value
+                }
+            }
+            // Map generic AI_BASE_URL to provider-specific key
+            else if (
+                key === "AI_BASE_URL" &&
+                provider &&
+                PROVIDER_ENV_MAP[provider]
+            ) {
+                const providerBaseUrl = PROVIDER_ENV_MAP[provider].baseUrl
+                if (providerBaseUrl) {
+                    process.env[providerBaseUrl] = value
+                    appliedEnv[providerBaseUrl] = value
+                }
+            }
+            // Apply other env vars directly
+            else {
+                process.env[key] = value
+                appliedEnv[key] = value
+            }
+        }
+    }
+
+    // Set as current preset
+    data.currentPresetId = id
+    savePresets(data)
+
+    return appliedEnv
+}
+
+/**
+ * Get environment variables from current preset
  * Maps generic AI_API_KEY/AI_BASE_URL to provider-specific keys
  */
-function presetToEnv(preset: ConfigPreset): Record<string, string> {
+export function getCurrentPresetEnv(): Record<string, string> {
+    const preset = getCurrentPreset()
+    if (!preset) {
+        return {}
+    }
+
     const env: Record<string, string> = {}
     const provider = preset.config.AI_PROVIDER?.toLowerCase()
 
     for (const [key, value] of Object.entries(preset.config)) {
         if (value !== undefined && value !== "") {
-            // A key that could not be decrypted is useless to the server
-            if (value.startsWith(ENCRYPTED_PREFIX)) {
-                console.warn(
-                    `Preset "${preset.name}": ${key} could not be decrypted. Please enter it again in Settings.`,
-                )
-            }
             // Map generic AI_API_KEY to provider-specific key
-            else if (
+            if (
                 key === "AI_API_KEY" &&
                 provider &&
                 PROVIDER_ENV_MAP[provider]
@@ -436,90 +466,6 @@ function presetToEnv(preset: ConfigPreset): Record<string, string> {
     return env
 }
 
-/**
- * Values that env vars had before a preset first set them
- * (from the system or .env files), and the keys the active preset set
- */
-const originalEnv: Record<string, string | undefined> = {}
-let presetEnvKeys: string[] = []
-
-/**
- * Replace the env vars of the previous preset with those of the given preset
- * (null leaves no preset applied). Restoring first means switching presets
- * never leaves the previous preset's base URL, model or key behind.
- */
-function setPresetEnv(preset: ConfigPreset | null): Record<string, string> {
-    for (const key of presetEnvKeys) {
-        if (originalEnv[key] === undefined) {
-            delete process.env[key]
-        } else {
-            process.env[key] = originalEnv[key]
-        }
-    }
-
-    const env = preset ? presetToEnv(preset) : {}
-    for (const [key, value] of Object.entries(env)) {
-        if (!(key in originalEnv)) {
-            originalEnv[key] = process.env[key]
-        }
-        process.env[key] = value
-    }
-    presetEnvKeys = Object.keys(env)
-
-    writeDevPresetEnv(env)
-    return env
-}
-
-const DEV_ENV_FILE_NAME = "dev-preset-env.json"
-
-/**
- * Development only: write the active preset's env vars (decrypted and mapped)
- * for scripts/electron-dev.mjs, which restarts the Next.js dev server when
- * this file changes. The dev server can't decrypt the config file itself.
- */
-function writeDevPresetEnv(env: Record<string, string>): void {
-    if (app.isPackaged) {
-        return
-    }
-    try {
-        const filePath = path.join(app.getPath("userData"), DEV_ENV_FILE_NAME)
-        writeFileSync(filePath, JSON.stringify(env, null, 2), {
-            encoding: "utf-8",
-            mode: 0o600,
-        })
-    } catch (error) {
-        console.error("Failed to write dev preset env:", error)
-    }
-}
-
-/**
- * Apply preset environment variables to the current process
- * Returns the environment variables that were applied
- */
-export function applyPresetToEnv(id: string): Record<string, string> | null {
-    const data = loadPresets()
-    const preset = data.presets.find((p) => p.id === id)
-
-    if (!preset) {
-        return null
-    }
-
-    const appliedEnv = setPresetEnv(preset)
-
-    // Set as current preset
-    data.currentPresetId = id
-    savePresets(data)
-
-    return appliedEnv
-}
-
-/**
- * Apply the saved current preset's environment variables (used at startup)
- */
-export function applyCurrentPresetToEnv(): void {
-    setPresetEnv(getCurrentPreset())
-}
-
 /**
  * Get user's preferred locale from config
  * Returns undefined if not set

electron/main/env-loader.ts

@@ -48,16 +48,12 @@ function loadEnvFromFile(filePath: string): void {
             const key = trimmed.slice(0, equalIndex).trim()
             let value = trimmed.slice(equalIndex + 1).trim()
 
-            const quote = value[0]
-            const closingQuote =
-                quote === '"' || quote === "'" ? value.indexOf(quote, 1) : -1
-            if (closingQuote > 0) {
-                // Quoted value: keep what's inside the quotes and drop
-                // anything after them (e.g. a comment)
-                value = value.slice(1, closingQuote)
-            } else {
-                // Unquoted value: drop an inline comment ("value  # comment")
-                value = value.replace(/\s+#.*$/, "")
+            // Remove surrounding quotes
+            if (
+                (value.startsWith('"') && value.endsWith('"')) ||
+                (value.startsWith("'") && value.endsWith("'"))
+            ) {
+                value = value.slice(1, -1)
             }
 
             // Don't override existing environment variables

electron/main/index.ts

@@ -1,17 +1,12 @@
 import { app, BrowserWindow, dialog, shell } from "electron"
 import { buildAppMenu } from "./app-menu"
-import { applyCurrentPresetToEnv } from "./config-manager"
+import { getCurrentPresetEnv } from "./config-manager"
 import { loadEnvFile } from "./env-loader"
 import { registerIpcHandlers } from "./ipc-handlers"
 import { startNextServer, stopNextServer } from "./next-server"
 import { applyProxyToEnv } from "./proxy-manager"
 import { registerSettingsWindowHandlers } from "./settings-window"
-import {
-    createWindow,
-    getAppUrl,
-    getMainWindow,
-    isAppUrl,
-} from "./window-manager"
+import { createWindow, getMainWindow } from "./window-manager"
 
 // Single instance lock
 const gotTheLock = app.requestSingleInstanceLock()
@@ -33,14 +28,16 @@ if (!gotTheLock) {
     // Apply proxy settings from saved config
     applyProxyToEnv()
 
-    const isDev = !app.isPackaged
+    // Apply saved preset environment variables (overrides .env)
+    const presetEnv = getCurrentPresetEnv()
+    for (const [key, value] of Object.entries(presetEnv)) {
+        process.env[key] = value
+    }
+
+    const isDev = process.env.NODE_ENV === "development"
+    let serverUrl: string | null = null
 
     app.whenReady().then(async () => {
-        // Apply saved preset environment variables (overrides .env).
-        // Must run after ready: on Windows and Linux safeStorage can't
-        // decrypt the API key before that.
-        applyCurrentPresetToEnv()
-
         // Register IPC handlers
         registerIpcHandlers()
         registerSettingsWindowHandlers()
@@ -49,7 +46,6 @@ if (!gotTheLock) {
         buildAppMenu()
 
         try {
-            let serverUrl: string
             if (isDev) {
                 // Development: use the dev server URL
                 serverUrl =
@@ -73,9 +69,8 @@ if (!gotTheLock) {
 
         app.on("activate", () => {
             if (BrowserWindow.getAllWindows().length === 0) {
-                const appUrl = getAppUrl()
-                if (appUrl) {
-                    createWindow(appUrl)
+                if (serverUrl) {
+                    createWindow(serverUrl)
                 }
             }
         })
@@ -92,47 +87,24 @@ if (!gotTheLock) {
         stopNextServer()
     })
 
-    // Pages allowed inside app windows: the app server and draw.io
-    const isInAppUrl = (url: string): boolean => {
-        if (isAppUrl(url)) return true
-        try {
-            const { hostname } = new URL(url)
-            return ["diagrams.net", "draw.io"].some(
-                (domain) =>
-                    hostname === domain || hostname.endsWith(`.${domain}`),
-            )
-        } catch {
-            return false
-        }
-    }
-
-    const isWebUrl = (url: string): boolean =>
-        url.startsWith("http://") || url.startsWith("https://")
-
     // Open external links in default browser
     app.on("web-contents-created", (_, contents) => {
         contents.setWindowOpenHandler(({ url }) => {
-            if (isInAppUrl(url)) {
+            // Allow diagrams.net iframe
+            if (
+                url.includes("diagrams.net") ||
+                url.includes("draw.io") ||
+                url.startsWith("http://localhost") ||
+                url.startsWith("http://127.0.0.1")
+            ) {
                 return { action: "allow" }
             }
             // Open other links in external browser
-            if (isWebUrl(url)) {
+            if (url.startsWith("http://") || url.startsWith("https://")) {
                 shell.openExternal(url)
                 return { action: "deny" }
             }
             return { action: "allow" }
         })
-
-        // Clicking a plain link would otherwise replace the app page with
-        // an external site that keeps the preload API
-        contents.on("will-navigate", (event) => {
-            if (isInAppUrl(event.url)) {
-                return
-            }
-            event.preventDefault()
-            if (isWebUrl(event.url)) {
-                shell.openExternal(event.url)
-            }
-        })
     })
 }

electron/main/ipc-handlers.ts

@@ -1,6 +1,7 @@
-import { app, BrowserWindow, type IpcMainInvokeEvent, ipcMain } from "electron"
-import { rebuildAppMenu, switchPreset } from "./app-menu"
+import { app, BrowserWindow, dialog, ipcMain } from "electron"
+import { rebuildAppMenu } from "./app-menu"
 import {
+    applyPresetToEnv,
     type ConfigPreset,
     createPreset,
     deletePreset,
@@ -19,7 +20,6 @@ import {
     type ProxyConfig,
     saveProxyConfig,
 } from "./proxy-manager"
-import { isAppUrl } from "./window-manager"
 
 /**
  * Allowed configuration keys for presets
@@ -48,32 +48,13 @@ function sanitizePresetConfig(
     return sanitized
 }
 
-/**
- * Register an IPC handler that only answers the app's own pages
- * (the main window on the app server, or the local settings page).
- * A main window that somehow ends up on an external site still gets the
- * preload API, so its calls must be rejected here.
- */
-function handle<Args extends unknown[]>(
-    channel: string,
-    listener: (event: IpcMainInvokeEvent, ...args: Args) => unknown,
-): void {
-    ipcMain.handle(channel, (event, ...args) => {
-        const url = event.senderFrame?.url
-        if (!isAppUrl(url) && !url?.startsWith("file://")) {
-            throw new Error(`Blocked "${channel}" from untrusted page: ${url}`)
-        }
-        return listener(event, ...(args as Args))
-    })
-}
-
 /**
  * Register all IPC handlers
  */
 export function registerIpcHandlers(): void {
     // ==================== App Info ====================
 
-    handle("get-version", () => {
+    ipcMain.handle("get-version", () => {
         return app.getVersion()
     })
 
@@ -98,30 +79,84 @@ export function registerIpcHandlers(): void {
         win?.close()
     })
 
+    // ==================== File Dialogs ====================
+
+    ipcMain.handle("dialog-open-file", async (event) => {
+        const win = BrowserWindow.fromWebContents(event.sender)
+        if (!win) return null
+
+        const result = await dialog.showOpenDialog(win, {
+            properties: ["openFile"],
+            filters: [
+                { name: "Draw.io Files", extensions: ["drawio", "xml"] },
+                { name: "All Files", extensions: ["*"] },
+            ],
+        })
+
+        if (result.canceled || result.filePaths.length === 0) {
+            return null
+        }
+
+        // Read the file content
+        const fs = await import("node:fs/promises")
+        try {
+            const content = await fs.readFile(result.filePaths[0], "utf-8")
+            return content
+        } catch (error) {
+            console.error("Failed to read file:", error)
+            return null
+        }
+    })
+
+    ipcMain.handle("dialog-save-file", async (event, data: string) => {
+        const win = BrowserWindow.fromWebContents(event.sender)
+        if (!win) return false
+
+        const result = await dialog.showSaveDialog(win, {
+            filters: [
+                { name: "Draw.io Files", extensions: ["drawio"] },
+                { name: "XML Files", extensions: ["xml"] },
+            ],
+        })
+
+        if (result.canceled || !result.filePath) {
+            return false
+        }
+
+        const fs = await import("node:fs/promises")
+        try {
+            await fs.writeFile(result.filePath, data, "utf-8")
+            return true
+        } catch (error) {
+            console.error("Failed to save file:", error)
+            return false
+        }
+    })
+
     // ==================== Config Presets ====================
 
-    handle("config-presets:get-all", () => {
+    ipcMain.handle("config-presets:get-all", () => {
         return getAllPresets()
     })
 
-    handle("config-presets:get-current", () => {
+    ipcMain.handle("config-presets:get-current", () => {
         return getCurrentPreset()
     })
 
-    handle("config-presets:get-current-id", () => {
+    ipcMain.handle("config-presets:get-current-id", () => {
         return getCurrentPresetId()
     })
 
-    handle(
+    ipcMain.handle(
         "config-presets:save",
-        async (
+        (
             _event,
             preset: Omit<ConfigPreset, "id" | "createdAt" | "updatedAt"> & {
                 id?: string
             },
         ) => {
             // Validate preset name
-            if (typeof preset?.name !== "string" || !preset.name.trim()) {
+            if (typeof preset.name !== "string" || !preset.name.trim()) {
                 throw new Error("Invalid preset name")
             }
 
@@ -130,48 +165,42 @@ export function registerIpcHandlers(): void {
 
             if (preset.id) {
                 // Update existing preset
-                const updated = updatePreset(preset.id, {
+                return updatePreset(preset.id, {
                     name: preset.name.trim(),
                     config: sanitizedConfig,
                 })
-                // Re-apply the active preset so the edit takes effect
-                if (updated && updated.id === getCurrentPresetId()) {
-                    await switchPreset(updated.id)
-                } else {
-                    rebuildAppMenu()
-                }
-                return updated
             }
             // Create new preset
-            const created = createPreset({
+            return createPreset({
                 name: preset.name.trim(),
                 config: sanitizedConfig,
             })
-            rebuildAppMenu()
-            return created
         },
     )
 
-    handle("config-presets:delete", async (_event, id: string) => {
-        const wasCurrent = id === getCurrentPresetId()
-        // Deleting the active preset also clears its env vars
-        const deleted = deletePreset(id)
-        rebuildAppMenu()
-
-        // Restart so the server stops using the deleted preset
-        if (deleted && wasCurrent && app.isPackaged) {
-            await restartNextServer()
-        }
-        return deleted
+    ipcMain.handle("config-presets:delete", (_event, id: string) => {
+        return deletePreset(id)
     })
 
-    handle("config-presets:apply", async (_event, id: string) => {
+    ipcMain.handle("config-presets:apply", async (_event, id: string) => {
+        const env = applyPresetToEnv(id)
+        if (!env) {
+            return { success: false, error: "Preset not found" }
+        }
+
+        const isDev = process.env.NODE_ENV === "development"
+
+        if (isDev) {
+            // In development mode, the config file change will trigger
+            // the file watcher in electron-dev.mjs to restart Next.js
+            // We just need to save the preset (already done in applyPresetToEnv)
+            return { success: true, env, devMode: true }
+        }
+
+        // Production mode: restart the Next.js server to apply new environment variables
         try {
-            const env = await switchPreset(id)
-            // In development mode, electron-dev.mjs restarts Next.js
-            return app.isPackaged
-                ? { success: true, env }
-                : { success: true, env, devMode: true }
+            await restartNextServer()
+            return { success: true, env }
         } catch (error) {
             return {
                 success: false,
@@ -183,39 +212,30 @@ export function registerIpcHandlers(): void {
         }
     })
 
-    handle("config-presets:set-current", (_event, id: string | null) => {
-        return setCurrentPreset(id)
-    })
+    ipcMain.handle(
+        "config-presets:set-current",
+        (_event, id: string | null) => {
+            return setCurrentPreset(id)
+        },
+    )
 
     // ==================== Proxy Settings ====================
 
-    handle("get-proxy", () => {
+    ipcMain.handle("get-proxy", () => {
         return getProxyConfig()
     })
 
-    handle("set-proxy", async (_event, config: ProxyConfig) => {
-        const isOptionalString = (value: unknown) =>
-            value === undefined || typeof value === "string"
-        if (
-            typeof config !== "object" ||
-            config === null ||
-            !isOptionalString(config.httpProxy) ||
-            !isOptionalString(config.httpsProxy)
-        ) {
-            return { success: false, error: "Invalid proxy settings" }
-        }
-
+    ipcMain.handle("set-proxy", async (_event, config: ProxyConfig) => {
         try {
             // Save config to file
-            saveProxyConfig({
-                httpProxy: config.httpProxy,
-                httpsProxy: config.httpsProxy,
-            })
+            saveProxyConfig(config)
 
             // Apply to current process environment
             applyProxyToEnv()
 
-            if (!app.isPackaged) {
+            const isDev = process.env.NODE_ENV === "development"
+
+            if (isDev) {
                 // In development, env vars are already applied
                 // Next.js dev server may need manual restart
                 return { success: true, devMode: true }
@@ -237,11 +257,11 @@ export function registerIpcHandlers(): void {
 
     // ==================== User Locale ====================
 
-    handle("get-user-locale", () => {
+    ipcMain.handle("get-user-locale", () => {
         return getUserLocale()
     })
 
-    handle("set-user-locale", (_event, locale: string) => {
+    ipcMain.handle("set-user-locale", (_event, locale: string) => {
         // Validate locale is one of the supported values
         if (!["en", "zh", "ja", "zh-Hant"].includes(locale)) {
             return { success: false, error: "Invalid locale" }

electron/main/next-server.ts

@@ -6,22 +6,10 @@ import {
     getAllocatedPort,
     getServerUrl,
     isPortAvailable,
-    saveServerPort,
 } from "./port-manager"
-import { setAppUrl } from "./window-manager"
 
 let serverProcess: UtilityProcess | null = null
 
-// Start and restart run one at a time, so overlapping calls (e.g. two quick
-// preset switches) can't leave two servers running
-let serverQueue: Promise<unknown> = Promise.resolve()
-
-function runExclusive<T>(task: () => Promise<T>): Promise<T> {
-    const result = serverQueue.then(task)
-    serverQueue = result.catch(() => {})
-    return result
-}
-
 /**
  * Get the path to the standalone server resources
  * In packaged app: resources/standalone
@@ -57,11 +45,7 @@ async function waitForServer(url: string, timeout = 30000): Promise<void> {
  * Start the Next.js standalone server using Electron's utilityProcess
  * This API is designed for running Node.js code in the background
  */
-export function startNextServer(): Promise<string> {
-    return runExclusive(startServer)
-}
-
-async function startServer(): Promise<string> {
+export async function startNextServer(): Promise<string> {
     const resourcePath = getResourcePath()
     const serverPath = path.join(resourcePath, "server.js")
 
@@ -87,13 +71,6 @@ async function startServer(): Promise<string> {
         HOSTNAME: "127.0.0.1",
         // Enable Node.js built-in proxy support for fetch (Node.js 24+)
         NODE_USE_ENV_PROXY: "1",
-        // The preset keys are the user's own, not a server's
-        NEXT_AI_DRAWIO_DESKTOP: "1",
-    }
-
-    // Keep requests to local model servers (e.g. Ollama) off the proxy
-    if (!process.env.NO_PROXY && !process.env.no_proxy) {
-        env.NO_PROXY = "localhost,127.0.0.1,[::1]"
     }
 
     // Set cache directory to a writable location (user's app data folder)
@@ -119,33 +96,28 @@ async function startServer(): Promise<string> {
 
     // Use Electron's utilityProcess API for running Node.js in background
     // This is the recommended way to run Node.js code in Electron
-    const proc = utilityProcess.fork(serverPath, [], {
+    serverProcess = utilityProcess.fork(serverPath, [], {
         cwd: resourcePath,
         env,
         stdio: "pipe",
     })
-    serverProcess = proc
 
-    proc.stdout?.on("data", (data) => {
+    serverProcess.stdout?.on("data", (data) => {
         console.log(`[Next.js] ${data.toString().trim()}`)
     })
 
-    proc.stderr?.on("data", (data) => {
+    serverProcess.stderr?.on("data", (data) => {
         console.error(`[Next.js Error] ${data.toString().trim()}`)
     })
 
-    proc.on("exit", (code) => {
+    serverProcess.on("exit", (code) => {
         console.log(`Next.js server exited with code ${code}`)
-        // An old server can exit after a new one started; keep the new one
-        if (serverProcess === proc) {
-            serverProcess = null
-        }
+        serverProcess = null
     })
 
     const url = getServerUrl()
     await waitForServer(url)
     console.log(`Next.js server started at ${url}`)
-    saveServerPort(port)
 
     return url
 }
@@ -154,36 +126,39 @@ async function startServer(): Promise<string> {
  * Stop the Next.js server process and wait for it to exit
  */
 export async function stopNextServer(): Promise<void> {
-    const proc = serverProcess
-    if (!proc) {
-        return
-    }
-    console.log("Stopping Next.js server...")
-    serverProcess = null
+    if (serverProcess) {
+        console.log("Stopping Next.js server...")
 
-    // Resolves true when the process exits, false after the timeout
-    const waitForExit = (ms: number) =>
-        new Promise<boolean>((resolve) => {
-            proc.once("exit", () => resolve(true))
-            setTimeout(() => resolve(false), ms)
+        // Create a promise that resolves when the process exits
+        const exitPromise = new Promise<void>((resolve) => {
+            const proc = serverProcess
+            if (!proc) {
+                resolve()
+                return
+            }
+
+            const onExit = () => {
+                resolve()
+            }
+
+            proc.once("exit", onExit)
+
+            // Timeout after 5 seconds
+            setTimeout(() => {
+                proc.removeListener("exit", onExit)
+                resolve()
+            }, 5000)
         })
 
-    proc.kill()
+        serverProcess.kill()
+        serverProcess = null
 
-    // Next.js waits for open requests (e.g. a streaming reply) before it
-    // exits, so force kill it if it is still running after 5 seconds
-    if (!(await waitForExit(5000)) && proc.pid) {
-        console.warn("Next.js server did not exit in time, force killing it")
-        try {
-            process.kill(proc.pid, "SIGKILL")
-        } catch (error) {
-            console.error("Failed to force kill Next.js server:", error)
-        }
-        await waitForExit(2000)
+        // Wait for process to exit
+        await exitPromise
+
+        // Additional wait for OS to release port
+        await new Promise((resolve) => setTimeout(resolve, 500))
     }
-
-    // Additional wait for OS to release port
-    await new Promise((resolve) => setTimeout(resolve, 500))
 }
 
 /**
@@ -209,19 +184,15 @@ async function waitForServerStop(timeout = 5000): Promise<void> {
 /**
  * Restart the Next.js server with new environment variables
  */
-export function restartNextServer(): Promise<string> {
-    return runExclusive(async () => {
-        console.log("Restarting Next.js server...")
+export async function restartNextServer(): Promise<string> {
+    console.log("Restarting Next.js server...")
 
-        // Stop the current server and wait for it to exit
-        await stopNextServer()
+    // Stop the current server and wait for it to exit
+    await stopNextServer()
 
-        // Wait for the port to be released
-        await waitForServerStop()
+    // Wait for the port to be released
+    await waitForServerStop()
 
-        // Start the server again, and follow it if it moved to another port
-        const url = await startServer()
-        setAppUrl(url)
-        return url
-    })
+    // Start the server again
+    return startNextServer()
 }

electron/main/port-manager.ts

@@ -1,6 +1,4 @@
-import { readFileSync, writeFileSync } from "node:fs"
 import net from "node:net"
-import path from "node:path"
 import { app } from "electron"
 
 /**
@@ -25,40 +23,6 @@ const PORT_CONFIG = {
  */
 let allocatedPort: number | null = null
 
-/**
- * File that remembers the production port from the last launch, so the app
- * keeps the same origin (and its localStorage) instead of switching between
- * the legacy and new port depending on which one is free at startup
- */
-function getSavedPortPath(): string {
-    return path.join(app.getPath("userData"), "server-port.json")
-}
-
-function loadSavedPort(): number | null {
-    try {
-        const { port } = JSON.parse(readFileSync(getSavedPortPath(), "utf-8"))
-        return Number.isInteger(port) ? port : null
-    } catch {
-        return null
-    }
-}
-
-/**
- * Remember the port of the first production launch. A later launch that
- * found it taken keeps it remembered: the user's data lives under that
- * origin, and the next launch goes back to it once it is free.
- */
-export function saveServerPort(port: number): void {
-    if (!app.isPackaged || loadSavedPort() !== null) {
-        return
-    }
-    try {
-        writeFileSync(getSavedPortPath(), JSON.stringify({ port }), "utf-8")
-    } catch (error) {
-        console.error("Failed to save server port:", error)
-    }
-}
-
 /**
  * Check if a specific port is available
  */
@@ -80,8 +44,7 @@ export function isPortAvailable(port: number): Promise<boolean> {
 /**
  * Find an available port
  * - In development: uses fixed port (6002)
- * - In production: uses the port from the last launch, then the legacy
- *   port (61337), then 13370, to preserve localStorage
+ * - In production: uses fixed port (13370) to preserve localStorage
  * - Falls back to sequential ports if preferred port is unavailable
  * - Last resort: lets the OS assign a port (port 0)
  *
@@ -106,20 +69,6 @@ export async function findAvailablePort(reuseExisting = true): Promise<number> {
         allocatedPort = null
     }
 
-    // In production, use the port from the last launch first
-    if (!isDev) {
-        const savedPort = loadSavedPort()
-        if (savedPort !== null) {
-            if (await isPortAvailable(savedPort)) {
-                allocatedPort = savedPort
-                return savedPort
-            }
-            console.warn(
-                `Port ${savedPort} from the last launch is unavailable. Data saved under it will not show on the new port.`,
-            )
-        }
-    }
-
     // In production, try legacy port first to preserve existing users' localStorage
     if (!isDev) {
         const legacyPort = PORT_CONFIG.legacyProduction

electron/main/proxy-manager.ts

@@ -13,22 +13,18 @@ function getConfigPath(): string {
 
 /**
  * Load proxy configuration from JSON file
- * Returns null if the user never saved proxy settings (or the file is invalid)
  */
-export function loadProxyConfig(): ProxyConfig | null {
+export function loadProxyConfig(): ProxyConfig {
     try {
         const configPath = getConfigPath()
         if (fs.existsSync(configPath)) {
-            const data = JSON.parse(fs.readFileSync(configPath, "utf-8"))
-            if (data && typeof data === "object" && !Array.isArray(data)) {
-                return data as ProxyConfig
-            }
-            console.error("Ignoring invalid proxy config:", data)
+            const data = fs.readFileSync(configPath, "utf-8")
+            return JSON.parse(data) as ProxyConfig
         }
     } catch (error) {
         console.error("Failed to load proxy config:", error)
     }
-    return null
+    return {}
 }
 
 /**
@@ -37,11 +33,7 @@ export function loadProxyConfig(): ProxyConfig | null {
 export function saveProxyConfig(config: ProxyConfig): void {
     try {
         const configPath = getConfigPath()
-        // Write a temp file and rename it, so a crash mid-write can't leave
-        // a truncated file
-        const tempPath = `${configPath}.tmp`
-        fs.writeFileSync(tempPath, JSON.stringify(config, null, 2), "utf-8")
-        fs.renameSync(tempPath, configPath)
+        fs.writeFileSync(configPath, JSON.stringify(config, null, 2), "utf-8")
     } catch (error) {
         console.error("Failed to save proxy config:", error)
         throw error
@@ -55,11 +47,6 @@ export function saveProxyConfig(config: ProxyConfig): void {
 export function applyProxyToEnv(): void {
     const config = loadProxyConfig()
 
-    // No saved settings: keep proxy vars inherited from the system or .env
-    if (!config) {
-        return
-    }
-
     if (config.httpProxy) {
         process.env.HTTP_PROXY = config.httpProxy
         process.env.http_proxy = config.httpProxy

electron/main/window-manager.ts

@@ -3,9 +3,6 @@ import { app, BrowserWindow, screen } from "electron"
 
 let mainWindow: BrowserWindow | null = null
 
-// URL of the app server the main window loads
-let appUrl: string | null = null
-
 /**
  * Get the icon path based on platform
  * Note: electron-builder converts icon.png during packaging,
@@ -31,7 +28,6 @@ function getIconPath(): string | undefined {
  * Create the main application window
  */
 export function createWindow(serverUrl: string): BrowserWindow {
-    appUrl = serverUrl
     const { width, height } = screen.getPrimaryDisplay().workAreaSize
 
     mainWindow = new BrowserWindow({
@@ -60,7 +56,7 @@ export function createWindow(serverUrl: string): BrowserWindow {
     })
 
     // Open DevTools in development
-    if (!app.isPackaged) {
+    if (process.env.NODE_ENV === "development") {
         mainWindow.webContents.openDevTools()
     }
 
@@ -97,36 +93,3 @@ export function createWindow(serverUrl: string): BrowserWindow {
 export function getMainWindow(): BrowserWindow | null {
     return mainWindow
 }
-
-/**
- * Get the app server URL the main window loads
- */
-export function getAppUrl(): string | null {
-    return appUrl
-}
-
-/**
- * Point the main window at a new app server URL
- * (the restarted server can come up on a different port)
- */
-export function setAppUrl(url: string): void {
-    if (url === appUrl) {
-        return
-    }
-    appUrl = url
-    mainWindow?.loadURL(url)
-}
-
-/**
- * Check if a URL belongs to the app server (same origin)
- */
-export function isAppUrl(url: string | undefined): boolean {
-    if (!url || !appUrl) {
-        return false
-    }
-    try {
-        return new URL(url).origin === new URL(appUrl).origin
-    } catch {
-        return false
-    }
-}

electron/preload/index.ts

@@ -18,6 +18,10 @@ contextBridge.exposeInMainWorld("electronAPI", {
     maximize: () => ipcRenderer.send("window-maximize"),
     close: () => ipcRenderer.send("window-close"),
 
+    // File operations
+    openFile: () => ipcRenderer.invoke("dialog-open-file"),
+    saveFile: (data: string) => ipcRenderer.invoke("dialog-save-file", data),
+
     // Proxy settings
     getProxy: () => ipcRenderer.invoke("get-proxy"),
     setProxy: (config: { httpProxy?: string; httpsProxy?: string }) =>

electron/settings/settings.js

@@ -213,9 +213,6 @@ async function savePreset() {
         }
     })
 
-    // closeModal() clears editingPresetId, so remember it for the toast
-    const isEdit = Boolean(editingPresetId)
-
     try {
         saveBtn.disabled = true
         saveBtn.innerHTML = '<span class="loading"></span>'
@@ -223,7 +220,10 @@ async function savePreset() {
         await window.settingsAPI.savePreset(preset)
         await loadPresets()
         closeModal()
-        showToast(isEdit ? "Preset updated" : "Preset created", "success")
+        showToast(
+            editingPresetId ? "Preset updated" : "Preset created",
+            "success",
+        )
     } catch (error) {
         console.error("Failed to save preset:", error)
         showToast("Failed to save preset", "error")
@@ -265,6 +265,8 @@ async function applyPreset(id) {
 
         const result = await window.settingsAPI.applyPreset(id)
         if (result.success) {
+            currentPresetId = id
+            renderPresets()
             showToast("Preset applied, server restarting...", "success")
         } else {
             showToast(result.error || "Failed to apply preset", "error")
@@ -272,9 +274,6 @@ async function applyPreset(id) {
     } catch (error) {
         console.error("Failed to apply preset:", error)
         showToast("Failed to apply preset", "error")
-    } finally {
-        // Reload to show the active preset and reset the Apply button
-        await loadPresets()
     }
 }
 

env.example

@@ -12,8 +12,7 @@ AI_PROVIDER=bedrock
 AI_MODEL=global.anthropic.claude-sonnet-4-5-20250929-v1:0
 
 # Output limit, all providers (default: 64000). Shared by reasoning and the diagram XML,
-# so a thinking model can spend it all before the tool call. Users can lower it in Settings,
-# and raise it only when they use their own API key, so this also caps cost on server keys.
+# so a thinking model can spend it all before the tool call. Users can override it in Settings.
 # If a model's own ceiling is lower, the request is retried with that ceiling automatically.
 # MAX_OUTPUT_TOKENS=64000
 
@@ -44,6 +43,7 @@ AI_MODEL=global.anthropic.claude-sonnet-4-5-20250929-v1:0
 # Google Generative AI Configuration
 # GOOGLE_GENERATIVE_AI_API_KEY=...
 # GOOGLE_BASE_URL=https://generativelanguage.googleapis.com/v1beta  # Optional: Custom endpoint
+# GOOGLE_CANDIDATE_COUNT=1                   # Optional: Number of candidates to generate
 # GOOGLE_TOP_K=40                            # Optional: Top K sampling parameter
 # GOOGLE_TOP_P=0.95                          # Optional: Nucleus sampling parameter
 # Note: Gemini 2.5/3 models automatically enable reasoning display (includeThoughts: true)
@@ -123,14 +123,9 @@ AI_MODEL=global.anthropic.claude-sonnet-4-5-20250929-v1:0
 
 # Temperature (Optional)
 # Controls randomness in AI responses. Lower = more deterministic.
-# Leave unset for models that don't support temperature (e.g., GPT-5.1 reasoning models).
-# Claude 4.7 and later reject it; the request is then retried without it.
+# Leave unset for models that don't support temperature (e.g., GPT-5.1 reasoning models)
 # TEMPERATURE=0
 
-# Debug Logging (Optional)
-# Log the structure of the messages each chat request sends to the model
-# DEBUG_LLM_PAYLOAD=true
-
 # Access Control (Optional)
 # ACCESS_CODE_LIST=your-secret-code,another-code
 

hooks/use-diagram-tool-handlers.ts

@@ -1,4 +1,5 @@
 import type { MutableRefObject } from "react"
+import { useRef } from "react"
 import type { DiagramOperation } from "@/components/chat/types"
 import type {
     ValidationState,
@@ -6,15 +7,10 @@ import type {
 } from "@/components/chat/ValidationCard"
 import type { ValidationResult } from "@/lib/diagram-validator"
 import { formatValidationFeedback } from "@/lib/diagram-validator"
-import { isMxCellXmlComplete } from "@/lib/utils"
-import { editDiagram } from "@/packages/mcp-server/src/edit-diagram.ts"
-import { prepareNewDiagram } from "@/packages/mcp-server/src/new-diagram.ts"
+import { isMxCellXmlComplete, wrapWithMxFile } from "@/lib/utils"
 
 const DEBUG = process.env.NODE_ENV === "development"
 
-// display_diagram replaces the document with this one page
-const NEW_PAGE = { pageId: "page-1", pageName: "Page-1" }
-
 interface ToolCall {
     toolCallId: string
     toolName: string
@@ -52,8 +48,6 @@ type ValidateDiagramFn = (
 interface UseDiagramToolHandlersParams {
     partialXmlRef: MutableRefObject<string>
     editDiagramOriginalXmlRef: MutableRefObject<Map<string, string>>
-    // Failed VLM validations in the current user turn (reset on each user message)
-    validationRetryCountRef: MutableRefObject<number>
     chartXMLRef: MutableRefObject<string>
     onDisplayChart: (xml: string, skipValidation?: boolean) => string | null
     onFetchChart: (saveToHistory?: boolean) => Promise<string>
@@ -78,7 +72,6 @@ interface UseDiagramToolHandlersParams {
 export function useDiagramToolHandlers({
     partialXmlRef,
     editDiagramOriginalXmlRef,
-    validationRetryCountRef,
     chartXMLRef,
     onDisplayChart,
     onFetchChart,
@@ -89,6 +82,9 @@ export function useDiagramToolHandlers({
     sessionId,
     onValidationStateChange,
 }: UseDiagramToolHandlersParams) {
+    // Track validation retry count per tool call
+    const validationRetryCountRef = useRef<Map<string, number>>(new Map())
+
     // Helper to update validation state
     const updateValidationState = (
         toolCallId: string,
@@ -178,12 +174,11 @@ NEXT STEP: Call append_diagram with the continuation XML.
         const finalXml = xml
         partialXmlRef.current = "" // Reset any partial from previous truncation
 
-        // Wrap, validate and auto-fix the model's XML like the MCP server's
-        // create_new_diagram, then load it
-        const prepared = prepareNewDiagram(finalXml, NEW_PAGE)
-        const validationError = prepared.ok
-            ? onDisplayChart(prepared.xml, true)
-            : prepared.error
+        // Wrap raw XML with full mxfile structure for draw.io
+        const fullXml = wrapWithMxFile(finalXml)
+
+        // loadDiagram validates and returns error if invalid
+        const validationError = onDisplayChart(fullXml)
 
         if (validationError) {
             console.warn("[display_diagram] Validation error:", validationError)
@@ -237,15 +232,17 @@ ${finalXml}
                             )
                         }
 
-                        // Each retry is a new tool call, so count attempts per user turn
-                        const attempt = validationRetryCountRef.current + 1
+                        const retryCount =
+                            validationRetryCountRef.current.get(
+                                toolCall.toolCallId,
+                            ) || 0
 
                         // Notify UI that we're validating (include the image)
                         updateValidationState(
                             toolCall.toolCallId,
                             "validating",
                             {
-                                attempt,
+                                attempt: retryCount + 1,
                                 maxAttempts: MAX_VALIDATION_RETRIES,
                                 imageData: capturedPngData,
                             },
@@ -257,14 +254,17 @@ ${finalXml}
                         )
 
                         if (!result.valid) {
-                            if (attempt < MAX_VALIDATION_RETRIES) {
-                                validationRetryCountRef.current = attempt
+                            if (retryCount < MAX_VALIDATION_RETRIES) {
+                                validationRetryCountRef.current.set(
+                                    toolCall.toolCallId,
+                                    retryCount + 1,
+                                )
 
                                 const feedback =
                                     formatValidationFeedback(result)
                                 if (DEBUG) {
                                     console.log(
-                                        `[display_diagram] Validation failed (attempt ${attempt}/${MAX_VALIDATION_RETRIES}):`,
+                                        `[display_diagram] Validation failed (attempt ${retryCount + 1}/${MAX_VALIDATION_RETRIES}):`,
                                         result.issues,
                                     )
                                 }
@@ -274,7 +274,7 @@ ${finalXml}
                                     toolCall.toolCallId,
                                     "failed",
                                     {
-                                        attempt,
+                                        attempt: retryCount + 1,
                                         maxAttempts: MAX_VALIDATION_RETRIES,
                                         result,
                                         imageData: capturedPngData,
@@ -285,17 +285,19 @@ ${finalXml}
                                     tool: "display_diagram",
                                     toolCallId: toolCall.toolCallId,
                                     state: "output-error",
-                                    errorText: `[Validation attempt ${attempt}/${MAX_VALIDATION_RETRIES}]\n${feedback}`,
+                                    errorText: `[Validation attempt ${retryCount + 1}/${MAX_VALIDATION_RETRIES}]\n${feedback}`,
                                 })
                                 return
                             } else {
-                                // Last attempt - accept the diagram with warning
+                                // Max retries reached - accept the diagram with warning
                                 if (DEBUG) {
                                     console.log(
                                         "[display_diagram] Max validation retries reached, accepting diagram",
                                     )
                                 }
-                                validationRetryCountRef.current = 0
+                                validationRetryCountRef.current.delete(
+                                    toolCall.toolCallId,
+                                )
 
                                 // Notify UI that we're accepting with issues (include the image)
                                 updateValidationState(
@@ -312,8 +314,10 @@ ${finalXml}
                                 return
                             }
                         } else {
-                            // Validation passed - reset retry count
-                            validationRetryCountRef.current = 0
+                            // Validation passed - clean up retry count
+                            validationRetryCountRef.current.delete(
+                                toolCall.toolCallId,
+                            )
                             if (DEBUG) {
                                 console.log(
                                     "[display_diagram] Validation passed!",
@@ -378,17 +382,12 @@ ${finalXml}
         }
 
         let currentXml = ""
-        // Use the original XML captured during streaming (shared with chat-message-display)
-        // This ensures we apply operations to the same base XML that streaming used
-        const originalXml = editDiagramOriginalXmlRef.current.get(
-            toolCall.toolCallId,
-        )
-        // On failure, undo the streaming preview so the canvas matches the XML
-        // reported back to the model
-        const restoreOriginal = () => {
-            if (originalXml) onDisplayChart(originalXml, true)
-        }
         try {
+            // Use the original XML captured during streaming (shared with chat-message-display)
+            // This ensures we apply operations to the same base XML that streaming used
+            const originalXml = editDiagramOriginalXmlRef.current.get(
+                toolCall.toolCallId,
+            )
             if (originalXml) {
                 currentXml = originalXml
             } else {
@@ -402,19 +401,26 @@ ${finalXml}
                 }
             }
 
-            // All or nothing, checked like the MCP server's edit_diagram.
-            // The model sees the first page, so edits target it.
-            const outcome = editDiagram(currentXml, operations, {})
-            if (!outcome.ok) {
-                const reason = outcome.pageError
-                    ? outcome.errors[0]
-                    : `No changes were made because ${outcome.errors.length} operation(s) failed:\n${outcome.errors.map((e) => `- ${e}`).join("\n")}`
-                restoreOriginal()
+            const { applyDiagramOperations } = await import("@/lib/utils")
+            const { result: editedXml, errors } = applyDiagramOperations(
+                currentXml,
+                operations,
+            )
+
+            // Check for operation errors
+            if (errors.length > 0) {
+                const errorMessages = errors
+                    .map(
+                        (e) =>
+                            `- ${e.type} on cell_id="${e.cellId}": ${e.message}`,
+                    )
+                    .join("\n")
+
                 addToolOutput({
                     tool: "edit_diagram",
                     toolCallId: toolCall.toolCallId,
                     state: "output-error",
-                    errorText: `${reason}
+                    errorText: `Some operations failed:\n${errorMessages}
 
 Current diagram XML:
 \`\`\`xml
@@ -428,12 +434,35 @@ Please check the cell IDs and retry.`,
                 return
             }
 
-            onDisplayChart(outcome.xml, true)
+            // loadDiagram validates and returns error if invalid
+            const validationError = onDisplayChart(editedXml)
+            if (validationError) {
+                console.warn(
+                    "[edit_diagram] Validation error:",
+                    validationError,
+                )
+                addToolOutput({
+                    tool: "edit_diagram",
+                    toolCallId: toolCall.toolCallId,
+                    state: "output-error",
+                    errorText: `Edit produced invalid XML: ${validationError}
+
+Current diagram XML:
+\`\`\`xml
+${currentXml}
+\`\`\`
+
+Please fix the operations to avoid structural issues.`,
+                })
+                // Clean up the shared original XML ref
+                editDiagramOriginalXmlRef.current.delete(toolCall.toolCallId)
+                return
+            }
             onExport()
             addToolOutput({
                 tool: "edit_diagram",
                 toolCallId: toolCall.toolCallId,
-                output: `Successfully applied ${outcome.applied} operation(s) to the diagram.`,
+                output: `Successfully applied ${operations.length} operation(s) to the diagram.`,
             })
             // Clean up the shared original XML ref
             editDiagramOriginalXmlRef.current.delete(toolCall.toolCallId)
@@ -443,7 +472,6 @@ Please check the cell IDs and retry.`,
             const errorMessage =
                 error instanceof Error ? error.message : String(error)
 
-            restoreOriginal()
             addToolOutput({
                 tool: "edit_diagram",
                 toolCallId: toolCall.toolCallId,
@@ -468,19 +496,6 @@ Please check cell IDs and retry, or use display_diagram to regenerate.`,
     ) => {
         const { xml } = toolCall.input as { xml: string }
 
-        // Nothing to continue: loading the fragment alone would replace the whole diagram
-        if (!partialXmlRef.current) {
-            addToolOutput({
-                tool: "append_diagram",
-                toolCallId: toolCall.toolCallId,
-                state: "output-error",
-                errorText: `ERROR: There is no truncated diagram to continue, so append_diagram cannot be used now.
-
-Use display_diagram to create the complete diagram, or edit_diagram to change the current one.`,
-            })
-            return
-        }
-
         // Detect if LLM incorrectly started fresh instead of continuing
         // LLM should only output bare mxCells now, so wrapper tags indicate error
         const trimmed = xml.trim()
@@ -519,10 +534,8 @@ Start your continuation with the NEXT character after where it stopped.`,
             const finalXml = partialXmlRef.current
             partialXmlRef.current = "" // Reset
 
-            const prepared = prepareNewDiagram(finalXml, NEW_PAGE)
-            const validationError = prepared.ok
-                ? onDisplayChart(prepared.xml, true)
-                : prepared.error
+            const fullXml = wrapWithMxFile(finalXml)
+            const validationError = onDisplayChart(fullXml)
 
             if (validationError) {
                 addToolOutput({

hooks/use-model-config.ts

@@ -101,15 +101,6 @@ function saveConfig(config: MultiModelConfig): void {
     localStorage.setItem(STORAGE_KEYS.modelConfigs, JSON.stringify(config))
 }
 
-/**
- * Server model to fall back to: the one marked default, else the first one
- */
-function defaultServerModelId(
-    serverModels: FlattenedServerModel[],
-): string | undefined {
-    return (serverModels.find((m) => m.isDefault) ?? serverModels[0])?.id
-}
-
 export interface UseModelConfigReturn {
     // State
     config: MultiModelConfig
@@ -153,16 +144,6 @@ export function useModelConfig(): UseModelConfigReturn {
         setIsLoaded(true)
     }, [])
 
-    // Pick up config changes saved by other tabs, so this tab neither shows a
-    // stale model nor overwrites their changes on its next save
-    useEffect(() => {
-        const handleStorage = (e: StorageEvent) => {
-            if (e.key === STORAGE_KEYS.modelConfigs) setConfig(loadConfig())
-        }
-        window.addEventListener("storage", handleStorage)
-        return () => window.removeEventListener("storage", handleStorage)
-    }, [])
-
     // Load server models on mount (if any)
     useEffect(() => {
         if (typeof window === "undefined") return
@@ -184,18 +165,17 @@ export function useModelConfig(): UseModelConfigReturn {
                 setServerModels(raw)
                 setServerLoaded(true)
 
-                // Auto-select the default server model if no model is selected,
-                // or if the saved server model is gone (renamed or removed)
+                // Auto-select default server model if no model is currently selected
                 setConfig((prev) => {
-                    const id = prev.selectedModelId
-                    const isStale =
-                        id?.startsWith("server:") &&
-                        !raw.some((m) => m.id === id)
-                    if (id && !isStale) return prev
-                    const fallback = defaultServerModelId(raw)
-                    return fallback === id
-                        ? prev
-                        : { ...prev, selectedModelId: fallback }
+                    if (!prev.selectedModelId && raw.length > 0) {
+                        const defaultModel = raw.find((m) => m.isDefault)
+                        if (defaultModel) {
+                            return { ...prev, selectedModelId: defaultModel.id }
+                        }
+                        // If no default marked, use first server model
+                        return { ...prev, selectedModelId: raw[0].id }
+                    }
+                    return prev
                 })
             })
             .catch((error) => {
@@ -280,31 +260,24 @@ export function useModelConfig(): UseModelConfigReturn {
         [],
     )
 
-    const deleteProvider = useCallback(
-        (providerId: string) => {
-            setConfig((prev) => {
-                const provider = prev.providers.find((p) => p.id === providerId)
-                const modelIds = provider?.models.map((m) => m.id) || []
+    const deleteProvider = useCallback((providerId: string) => {
+        setConfig((prev) => {
+            const provider = prev.providers.find((p) => p.id === providerId)
+            const modelIds = provider?.models.map((m) => m.id) || []
 
-                // Fall back to the default server model if the selected model
-                // belongs to the deleted provider
-                const newSelectedId =
-                    prev.selectedModelId &&
-                    modelIds.includes(prev.selectedModelId)
-                        ? defaultServerModelId(serverModels)
-                        : prev.selectedModelId
+            // Clear selected model if it belongs to deleted provider
+            const newSelectedId =
+                prev.selectedModelId && modelIds.includes(prev.selectedModelId)
+                    ? undefined
+                    : prev.selectedModelId
 
-                return {
-                    ...prev,
-                    providers: prev.providers.filter(
-                        (p) => p.id !== providerId,
-                    ),
-                    selectedModelId: newSelectedId,
-                }
-            })
-        },
-        [serverModels],
-    )
+            return {
+                ...prev,
+                providers: prev.providers.filter((p) => p.id !== providerId),
+                selectedModelId: newSelectedId,
+            }
+        })
+    }, [])
 
     const addModel = useCallback(
         (providerId: string, modelId: string): ModelConfig => {
@@ -361,15 +334,14 @@ export function useModelConfig(): UseModelConfigReturn {
                           }
                         : p,
                 ),
-                // Fall back to the default server model if the selected model
-                // was deleted
+                // Clear selected model if it was deleted
                 selectedModelId:
                     prev.selectedModelId === modelConfigId
-                        ? defaultServerModelId(serverModels)
+                        ? undefined
                         : prev.selectedModelId,
             }))
         },
-        [serverModels],
+        [],
     )
 
     const resetConfig = useCallback(() => {

hooks/use-session-manager.ts

@@ -1,8 +1,6 @@
 "use client"
 
 import { useCallback, useEffect, useRef, useState } from "react"
-import { toast } from "sonner"
-import { useDictionary } from "@/hooks/use-dictionary"
 import {
     type ChatSession,
     createEmptySession,
@@ -46,15 +44,6 @@ export interface UseSessionManagerReturn {
     clearCurrentSession: () => void
 }
 
-// Reading the session list loads every stored session in full, and window
-// focus also fires each time the user clicks back from the draw.io iframe
-const FOCUS_REFRESH_INTERVAL_MS = 30_000
-
-function notifySaveFailed(message: string) {
-    // Same id, so repeated failures update one toast instead of stacking
-    toast.error(message, { id: "session-save-failed", duration: 8000 })
-}
-
 interface UseSessionManagerOptions {
     /** Session ID from URL param - if provided, load this session; if null, start blank */
     initialSessionId?: string | null
@@ -64,7 +53,6 @@ export function useSessionManager(
     options: UseSessionManagerOptions = {},
 ): UseSessionManagerReturn {
     const { initialSessionId } = options
-    const dict = useDictionary()
     const [sessions, setSessions] = useState<SessionMetadata[]>([])
     const [currentSessionId, setCurrentSessionId] = useState<string | null>(
         null,
@@ -175,15 +163,9 @@ export function useSessionManager(
         handleSessionIdChange()
     }, [initialSessionId, isAvailable])
 
-    // Refresh sessions on window focus (multi-tab sync), at most once per interval
-    const lastFocusRefreshRef = useRef(0)
+    // Refresh sessions on window focus (multi-tab sync)
     useEffect(() => {
         const handleFocus = () => {
-            const now = Date.now()
-            if (now - lastFocusRefreshRef.current < FOCUS_REFRESH_INTERVAL_MS) {
-                return
-            }
-            lastFocusRefreshRef.current = now
             refreshSessions()
         }
         window.addEventListener("focus", handleFocus)
@@ -256,8 +238,6 @@ export function useSessionManager(
             ) {
                 return
             }
-            // Nothing can be stored without IndexedDB
-            if (!isIndexedDBAvailable()) return
 
             if (!currentSession) {
                 // Create a new session if none exists
@@ -270,12 +250,7 @@ export function useSessionManager(
                     diagramHistory: data.diagramHistory,
                     title: extractTitle(data.messages),
                 }
-                // Without a stored session, keep no session id (it would end
-                // up in the URL and point to nothing after a reload)
-                if (!(await saveSession(newSession))) {
-                    notifySaveFailed(dict.errors.sessionSaveFailed)
-                    return
-                }
+                await saveSession(newSession)
                 await enforceSessionLimit()
                 setCurrentSession(newSession)
                 setCurrentSessionId(newSession.id)
@@ -302,10 +277,7 @@ export function useSessionManager(
                         : currentSession.title,
             }
 
-            if (!(await saveSession(updatedSession))) {
-                notifySaveFailed(dict.errors.sessionSaveFailed)
-                return
-            }
+            await saveSession(updatedSession)
             setCurrentSession(updatedSession)
 
             // Update sessions list metadata
@@ -326,7 +298,7 @@ export function useSessionManager(
                 ),
             )
         },
-        [currentSession, currentSessionId, refreshSessions, dict],
+        [currentSession, currentSessionId, refreshSessions],
     )
 
     // Clear current session state (for starting fresh without loading another session)

hooks/use-validate-diagram.ts

@@ -6,7 +6,6 @@
 
 import { experimental_useObject as useObject } from "@ai-sdk/react"
 import { useCallback, useRef } from "react"
-import { getSelectedAIConfig } from "@/hooks/use-model-config"
 import { getApiEndpoint } from "@/lib/base-path"
 import {
     type ValidationResult,
@@ -40,8 +39,6 @@ export function useValidateDiagram(options: UseValidateDiagramOptions = {}) {
     const { object, submit, isLoading, error, stop } = useObject({
         api: getApiEndpoint("/api/validate-diagram"),
         schema: ValidationResultSchema,
-        // Resolved per request so a changed access code is picked up
-        headers: () => ({ "x-access-code": getSelectedAIConfig().accessCode }),
         onFinish: ({
             object,
             error: finishError,

lib/access-code.ts

@@ -1,22 +0,0 @@
-/**
- * Check the x-access-code header against ACCESS_CODE_LIST.
- * Returns a 401 response to send back when the check fails, or null when the
- * request may continue (including when no access codes are configured).
- */
-export function checkAccessCode(req: Request): Response | null {
-    const accessCodes =
-        process.env.ACCESS_CODE_LIST?.split(",")
-            .map((code) => code.trim())
-            .filter(Boolean) || []
-    if (accessCodes.length === 0) return null
-
-    const accessCodeHeader = req.headers.get("x-access-code")
-    if (accessCodeHeader && accessCodes.includes(accessCodeHeader)) return null
-
-    return Response.json(
-        {
-            error: "Invalid or missing access code. Please configure it in Settings.",
-        },
-        { status: 401 },
-    )
-}

lib/admin/providers.ts

@@ -2,7 +2,6 @@ import { z } from "zod"
 import {
     ProviderNameSchema,
     type ServerModelsConfig,
-    slugify,
 } from "@/lib/server-model-config"
 import {
     FIXED_CRED_PROVIDERS,
@@ -183,15 +182,12 @@ export function validateAdminProviders(
             return `${PROVIDER_INFO[single].label} is already configured in AI_MODELS_CONFIG / ai-models.json and shares global credentials. Manage it via the environment configuration instead.`
         }
     }
-    // Server model ids are built from the slugified name, so names must
-    // stay distinct after slugifying ("OpenAI" and "openai" would collide)
     const names = list.map((p) => displayName(p))
-    const slugs = names.map(slugify)
-    if (new Set(slugs).size !== slugs.length) {
-        return "Provider display names must be unique (ignoring case and punctuation)."
+    if (new Set(names).size !== names.length) {
+        return "Provider display names must be unique."
     }
-    const envSlugs = new Set(envProviders.map((p) => slugify(p.name)))
-    const clash = names.find((_, i) => envSlugs.has(slugs[i]))
+    const envNames = new Set(envProviders.map((p) => p.name))
+    const clash = names.find((n) => envNames.has(n))
     if (clash) {
         return `"${clash}" is already defined in AI_MODELS_CONFIG / ai-models.json. Use a different display name.`
     }
@@ -244,14 +240,10 @@ export function deriveEnvUpdates(
         indexByProvider.set(p.provider, index + 1)
 
         if (p.provider === "bedrock") {
-            // ADMIN_ names keep the standard AWS_* vars untouched, so other
-            // AWS clients (e.g. the DynamoDB quota table) keep their own
-            // credentials instead of picking up the panel's Bedrock keys
-            if (p.awsAccessKeyId)
-                updates.ADMIN_AWS_ACCESS_KEY_ID = p.awsAccessKeyId
+            if (p.awsAccessKeyId) updates.AWS_ACCESS_KEY_ID = p.awsAccessKeyId
             if (p.awsSecretAccessKey)
-                updates.ADMIN_AWS_SECRET_ACCESS_KEY = p.awsSecretAccessKey
-            if (p.awsRegion) updates.ADMIN_AWS_REGION = p.awsRegion
+                updates.AWS_SECRET_ACCESS_KEY = p.awsSecretAccessKey
+            if (p.awsRegion) updates.AWS_REGION = p.awsRegion
         } else if (p.provider === "vertexai") {
             if (p.vertexApiKey) updates.GOOGLE_VERTEX_API_KEY = p.vertexApiKey
             if (p.baseUrl) updates.GOOGLE_VERTEX_BASE_URL = p.baseUrl
@@ -292,10 +284,6 @@ function derivedEnvKeys(list: StoredAdminProvider[]): string[] {
         const index = indexByProvider.get(p.provider) ?? 0
         indexByProvider.set(p.provider, index + 1)
         if (p.provider === "bedrock") {
-            keys.add("ADMIN_AWS_ACCESS_KEY_ID")
-            keys.add("ADMIN_AWS_SECRET_ACCESS_KEY")
-            keys.add("ADMIN_AWS_REGION")
-            // Written by older versions; listed so the next save clears them
             keys.add("AWS_ACCESS_KEY_ID")
             keys.add("AWS_SECRET_ACCESS_KEY")
             keys.add("AWS_REGION")

lib/admin/settings.ts

@@ -10,27 +10,13 @@ interface SettingsFile {
     values: Record<string, string>
 }
 
-interface SettingsState {
-    // Original env values snapshotted before the first overlay, so removing
-    // a key from the settings file restores the env default. null = was unset.
-    originalEnv: Record<string, string | null>
-    // Keys currently overlaid, so we can restore ones removed from the file.
-    overlaidKeys: Set<string>
-    cachedSettings: Record<string, string> | null
-}
+// Original env values snapshotted before the first overlay, so removing a
+// key from the settings file restores the env default. null = was unset.
+const originalEnv: Record<string, string | null> = {}
+// Keys currently overlaid, so we can restore ones removed from the file.
+let overlaidKeys = new Set<string>()
 
-// Kept on globalThis because the build can load this module more than once
-// (instrumentation.ts and the API routes get separate copies); per-module
-// state would make a route forget what instrumentation overlaid at startup.
-const globalState = globalThis as typeof globalThis & {
-    __adminSettingsState?: SettingsState
-}
-globalState.__adminSettingsState ??= {
-    originalEnv: {},
-    overlaidKeys: new Set(),
-    cachedSettings: null,
-}
-const state = globalState.__adminSettingsState
+let cachedSettings: Record<string, string> | null = null
 
 export function getSettingsPath(): string {
     const custom = process.env.SETTINGS_FILE
@@ -39,7 +25,7 @@ export function getSettingsPath(): string {
 }
 
 export function loadSettings(): Record<string, string> {
-    if (state.cachedSettings) return state.cachedSettings
+    if (cachedSettings) return cachedSettings
     try {
         const raw = fs.readFileSync(getSettingsPath(), "utf8")
         const parsed = JSON.parse(raw) as SettingsFile
@@ -57,22 +43,21 @@ export function loadSettings(): Record<string, string> {
         for (const [key, value] of Object.entries(rawValues)) {
             if (typeof value === "string") values[key] = value
         }
-        state.cachedSettings = values
+        cachedSettings = values
     } catch (err: any) {
         if (err?.code !== "ENOENT") {
             console.error("[admin-settings] Failed to read settings file:", err)
         }
-        state.cachedSettings = {}
+        cachedSettings = {}
     }
-    return state.cachedSettings
+    return cachedSettings
 }
 
 export function applyToEnv(): void {
     const values = loadSettings()
-    const { originalEnv } = state
 
     // Restore env for keys that were overlaid before but are now gone
-    for (const key of state.overlaidKeys) {
+    for (const key of overlaidKeys) {
         if (!(key in values)) {
             const original = originalEnv[key]
             if (original === null) delete process.env[key]
@@ -87,12 +72,12 @@ export function applyToEnv(): void {
         process.env[key] = value
     }
 
-    state.overlaidKeys = new Set(Object.keys(values))
+    overlaidKeys = new Set(Object.keys(values))
 }
 
 // The effective env value if the file entry were removed (for fallback display)
 export function getEnvFallback(key: string): string | null {
-    if (state.overlaidKeys.has(key)) return state.originalEnv[key] ?? null
+    if (overlaidKeys.has(key)) return originalEnv[key] ?? null
     return process.env[key] ?? null
 }
 
@@ -116,7 +101,7 @@ export function saveSettings(updates: Record<string, string | null>): void {
     fs.writeFileSync(tmpPath, JSON.stringify(data, null, 2), { mode: 0o600 })
     fs.renameSync(tmpPath, filePath)
 
-    state.cachedSettings = current
+    cachedSettings = current
     applyToEnv()
 }
 
@@ -137,13 +122,13 @@ export function isSettingsWritable(): boolean {
 
 // Test-only: reset module state
 export function _resetForTests(): void {
-    state.cachedSettings = null
+    cachedSettings = null
     writableCache = null
-    for (const key of state.overlaidKeys) {
-        const original = state.originalEnv[key]
+    for (const key of overlaidKeys) {
+        const original = originalEnv[key]
         if (original === null) delete process.env[key]
         else if (original !== undefined) process.env[key] = original
     }
-    state.overlaidKeys = new Set()
-    state.originalEnv = {}
+    overlaidKeys = new Set()
+    for (const key of Object.keys(originalEnv)) delete originalEnv[key]
 }

lib/aihubmix-models.ts

@@ -0,0 +1,79 @@
+export const AIHUBMIX_MODELS_ENDPOINT = "https://aihubmix.com/api/v1/models"
+
+const NON_CHAT_MODEL_TYPES = new Set([
+    "embedding",
+    "image_generation",
+    "rerank",
+    "transcription",
+    "tts",
+    "video",
+])
+
+type AihubmixModelListPayload = {
+    data?: unknown
+}
+
+type AihubmixModelRecord = {
+    model_id?: unknown
+    types?: unknown
+}
+
+function getModelTypes(types: unknown): Set<string> {
+    if (typeof types !== "string") {
+        return new Set()
+    }
+
+    return new Set(
+        types
+            .split(",")
+            .map((type) => type.trim())
+            .filter(Boolean),
+    )
+}
+
+function isChatModel(record: AihubmixModelRecord): record is {
+    model_id: string
+    types: string
+} {
+    if (typeof record.model_id !== "string" || !record.model_id.trim()) {
+        return false
+    }
+
+    const types = getModelTypes(record.types)
+    if (!types.has("llm")) {
+        return false
+    }
+
+    return !Array.from(NON_CHAT_MODEL_TYPES).some((type) => types.has(type))
+}
+
+export function extractAihubmixModelIds(payload: unknown): string[] {
+    const data = (payload as AihubmixModelListPayload)?.data
+    if (!Array.isArray(data)) {
+        return []
+    }
+
+    const seen = new Set<string>()
+    const modelIds: string[] = []
+
+    for (const item of data) {
+        if (!item || typeof item !== "object") {
+            continue
+        }
+
+        const record = item as AihubmixModelRecord
+        if (!isChatModel(record)) {
+            continue
+        }
+
+        const modelId = record.model_id.trim()
+        if (seen.has(modelId)) {
+            continue
+        }
+
+        seen.add(modelId)
+        modelIds.push(modelId)
+    }
+
+    return modelIds
+}

lib/cached-responses.ts

@@ -1,8 +1,6 @@
 export interface CachedResponse {
     promptText: string
     hasImage: boolean
-    // Name of the bundled example file the prompt is sent with
-    fileName?: string
     xml: string
 }
 
@@ -256,7 +254,6 @@ export const CACHED_EXAMPLE_RESPONSES: CachedResponse[] = [
     {
         promptText: "Replicate this in aws style",
         hasImage: true,
-        fileName: "architecture.png",
         xml: `<mxCell id="2" value="AWS" style="sketch=0;outlineConnect=0;gradientColor=none;html=1;whiteSpace=wrap;fontSize=12;fontStyle=0;container=1;pointerEvents=0;collapsible=0;recursiveResize=0;shape=mxgraph.aws4.group;grIcon=mxgraph.aws4.group_aws_cloud;strokeColor=#232F3E;fillColor=none;verticalAlign=top;align=left;spacingLeft=30;fontColor=#232F3E;dashed=0;rounded=1;arcSize=5;" vertex="1" parent="1">
     <mxGeometry x="340" y="40" width="880" height="520" as="geometry"/>
   </mxCell>
@@ -321,7 +318,6 @@ export const CACHED_EXAMPLE_RESPONSES: CachedResponse[] = [
     {
         promptText: "Replicate this flowchart.",
         hasImage: true,
-        fileName: "example.png",
         xml: `<mxCell id="2" value="Lamp doesn't work" style="rounded=1;whiteSpace=wrap;html=1;fillColor=#ffcccc;strokeColor=#000000;strokeWidth=2;fontSize=18;fontStyle=0;" vertex="1" parent="1">
     <mxGeometry x="140" y="40" width="180" height="60" as="geometry"/>
   </mxCell>
@@ -383,7 +379,6 @@ export const CACHED_EXAMPLE_RESPONSES: CachedResponse[] = [
     {
         promptText: "Summarize this paper as a diagram",
         hasImage: true,
-        fileName: "chain-of-thought.txt",
         xml: `<mxCell id="title_bg" parent="1"
                     style="rounded=1;whiteSpace=wrap;html=1;fillColor=#1a237e;strokeColor=none;arcSize=8;"
                     value="" vertex="1">
@@ -884,19 +879,14 @@ export const CACHED_EXAMPLE_RESPONSES: CachedResponse[] = [
     },
 ]
 
-// Examples that come with a file only match when that exact example file is
-// attached, so a user's own file with the same prompt still goes to the model.
-// Callers that can't tell file names (the server) only get text-only examples.
 export function findCachedResponse(
     promptText: string,
     hasImage: boolean,
-    fileName?: string,
 ): CachedResponse | undefined {
     return CACHED_EXAMPLE_RESPONSES.find(
         (c) =>
             c.promptText === promptText &&
             c.hasImage === hasImage &&
-            (!c.fileName || c.fileName === fileName) &&
             c.xml !== "",
     )
 }

lib/chat-helpers.ts

@@ -6,37 +6,25 @@ export const MAX_FILE_SIZE = 2 * 1024 * 1024 // 2MB
 export const MAX_FILES = 5
 
 // Helper function to validate file parts in messages
-// Checks every message, since history is sent to the model too
 export function validateFileParts(messages: any[]): {
     valid: boolean
     error?: string
 } {
-    for (const message of messages) {
-        const fileParts =
-            message?.parts?.filter((p: any) => p.type === "file") || []
+    const lastMessage = messages[messages.length - 1]
+    const fileParts =
+        lastMessage?.parts?.filter((p: any) => p.type === "file") || []
 
-        if (fileParts.length > MAX_FILES) {
-            return {
-                valid: false,
-                error: `Too many files. Maximum ${MAX_FILES} allowed.`,
-            }
+    if (fileParts.length > MAX_FILES) {
+        return {
+            valid: false,
+            error: `Too many files. Maximum ${MAX_FILES} allowed.`,
         }
+    }
 
-        for (const filePart of fileParts) {
-            // The client sends files inline. Any other URL would be downloaded
-            // by the server (AI SDK does that for models without URL support).
-            if (
-                typeof filePart.url !== "string" ||
-                !filePart.url.startsWith("data:")
-            ) {
-                return {
-                    valid: false,
-                    error: "Files must be uploaded inline as data URLs.",
-                }
-            }
-
-            // Data URLs format: data:image/png;base64,<data>
-            // Base64 increases size by ~33%, so we check the decoded size
+    for (const filePart of fileParts) {
+        // Data URLs format: data:image/png;base64,<data>
+        // Base64 increases size by ~33%, so we check the decoded size
+        if (filePart.url?.startsWith("data:")) {
             const base64Data = filePart.url.split(",")[1]
             if (base64Data) {
                 const sizeInBytes = Math.ceil((base64Data.length * 3) / 4)
@@ -53,83 +41,49 @@ export function validateFileParts(messages: any[]): {
     return { valid: true }
 }
 
-// A tool-call input providers accept: a non-empty JSON object
-function isValidToolInput(input: unknown): boolean {
-    return !!input && typeof input === "object" && Object.keys(input).length > 0
+// Helper function to check if diagram is minimal/empty
+export function isMinimalDiagram(xml: string): boolean {
+    const stripped = xml.replace(/\s/g, "")
+    return !stripped.includes('id="2"')
 }
 
 // Helper function to replace historical tool call XML with placeholders
 // This reduces token usage and forces LLM to rely on the current diagram XML (source of truth)
-// Tool calls with invalid inputs are left for dropInvalidToolCalls to remove
+// Also fixes invalid/undefined inputs from interrupted streaming
 export function replaceHistoricalToolInputs(messages: any[]): any[] {
     return messages.map((msg) => {
         if (msg.role !== "assistant" || !Array.isArray(msg.content)) {
             return msg
         }
-        const replacedContent = msg.content.map((part: any) => {
-            if (
-                part.type === "tool-call" &&
-                isValidToolInput(part.input) &&
-                (part.toolName === "display_diagram" ||
-                    part.toolName === "edit_diagram")
-            ) {
-                return {
-                    ...part,
-                    input: {
-                        placeholder:
-                            "[XML content replaced - see current diagram XML in system context]",
-                    },
+        const replacedContent = msg.content
+            .map((part: any) => {
+                if (part.type === "tool-call") {
+                    const toolName = part.toolName
+                    // Fix invalid/undefined inputs from interrupted streaming
+                    if (
+                        !part.input ||
+                        typeof part.input !== "object" ||
+                        Object.keys(part.input).length === 0
+                    ) {
+                        // Skip tool calls with invalid inputs entirely
+                        return null
+                    }
+                    if (
+                        toolName === "display_diagram" ||
+                        toolName === "edit_diagram"
+                    ) {
+                        return {
+                            ...part,
+                            input: {
+                                placeholder:
+                                    "[XML content replaced - see current diagram XML in system context]",
+                            },
+                        }
+                    }
                 }
-            }
-            return part
-        })
+                return part
+            })
+            .filter(Boolean) // Remove null entries (invalid tool calls)
         return { ...msg, content: replacedContent }
     })
 }
-
-// Remove tool-calls with invalid inputs (from failed repair or interrupted streaming),
-// together with their tool-results: providers reject a result whose call is missing.
-// Messages left empty are removed too (Bedrock rejects empty content arrays).
-export function dropInvalidToolCalls(messages: any[]): any[] {
-    const droppedIds = new Set<string>()
-    return messages
-        .map((msg) => {
-            if (!Array.isArray(msg.content)) return msg
-            const content = msg.content.filter((part: any) => {
-                if (
-                    msg.role === "assistant" &&
-                    part.type === "tool-call" &&
-                    !isValidToolInput(part.input)
-                ) {
-                    console.warn(
-                        `[chat-helpers] Dropping tool-call with invalid input:`,
-                        { toolName: part.toolName, input: part.input },
-                    )
-                    droppedIds.add(part.toolCallId)
-                    return false
-                }
-                // Results always come after their call, so the id is known by now
-                return !(
-                    part.type === "tool-result" &&
-                    droppedIds.has(part.toolCallId)
-                )
-            })
-            return { ...msg, content }
-        })
-        .filter((msg) => !Array.isArray(msg.content) || msg.content.length > 0)
-}
-
-// Fix common LLM JSON mistakes in tool-call input before jsonrepair runs
-export function fixToolInputJson(input: string): string {
-    return (
-        input
-            // Inconsistent quote escaping in XML attributes inside JSON strings:
-            // y="-20\" (opening quote unescaped, closing escaped) becomes y=\"-20\".
-            // Must run before the key fix below, which would rewrite the `="`.
-            .replace(/(\w+)="([^"]*?)\\"/g, '$1=\\"$2\\"')
-            // `:=` instead of `: `
-            .replace(/:=/g, ": ")
-            // `"key"= "` instead of `"key": "`, only for JSON keys
-            .replace(/"(\w+)"\s*=\s*"/g, '"$1": "')
-    )
-}

lib/deprecated-params.ts

@@ -1,94 +0,0 @@
-import { wrapLanguageModel } from "ai"
-import { rejectionText } from "@/lib/output-token-limit"
-
-type WrappedModel = ReturnType<typeof wrapLanguageModel>
-
-/**
- * Claude 4.7 and later answer a non-default temperature, top_p or top_k,
- * and the extended thinking budget (thinking type "enabled"), with a 400.
- * TEMPERATURE and the *_THINKING_BUDGET_TOKENS settings send exactly these.
- */
-const DEPRECATED_PARAM =
-    /`?(?:temperature|top_p|top_k)`? is deprecated for this model|"?thinking\.type\.enabled"? is not supported/i
-
-interface CallParams {
-    temperature?: number
-    topP?: number
-    topK?: number
-    providerOptions?: Record<string, Record<string, unknown> | undefined>
-}
-
-// What these models take instead of a budget. Without display "summarized"
-// they think but send no thinking text to show.
-const ADAPTIVE_THINKING = { type: "adaptive", display: "summarized" }
-
-/** Turn a thinking config of type "enabled" stored under key into adaptive */
-function adaptiveThinking(
-    options: Record<string, unknown> | undefined,
-    key: string,
-): Record<string, unknown> | undefined {
-    const config = options?.[key] as { type?: string } | undefined
-    if (config?.type !== "enabled") return options
-    return { ...options, [key]: ADAPTIVE_THINKING }
-}
-
-/**
- * The params without the settings newer Claude models reject, or null when
- * the error is about something else or there is nothing to change. The
- * model then runs with its default sampling, and a thinking budget becomes
- * adaptive thinking.
- */
-export function withoutDeprecatedParams<T extends CallParams>(
-    error: unknown,
-    params: T,
-): T | null {
-    const text = rejectionText(error)
-    if (!text || !DEPRECATED_PARAM.test(text)) return null
-
-    const { temperature, topP, topK, ...rest } = params
-    const options = params.providerOptions
-    const anthropic = adaptiveThinking(options?.anthropic, "thinking")
-    const bedrock = adaptiveThinking(options?.bedrock, "reasoningConfig")
-    const changed =
-        temperature !== undefined ||
-        topP !== undefined ||
-        topK !== undefined ||
-        anthropic !== options?.anthropic ||
-        bedrock !== options?.bedrock
-    if (!changed) return null
-
-    return {
-        ...rest,
-        ...(options && {
-            providerOptions: {
-                ...options,
-                ...(anthropic && { anthropic }),
-                ...(bedrock && { bedrock }),
-            },
-        }),
-    } as T
-}
-
-/** Retry the stream once without the settings newer Claude models reject. */
-export function withDeprecatedParamsFallback(
-    model: WrappedModel,
-): WrappedModel {
-    return wrapLanguageModel({
-        model,
-        middleware: {
-            specificationVersion: "v3",
-            async wrapStream({ doStream, params, model: inner }) {
-                try {
-                    return await doStream()
-                } catch (error) {
-                    const retry = withoutDeprecatedParams(error, params)
-                    if (!retry) throw error
-                    console.warn(
-                        "[model params] Rejected sampling or thinking settings, retrying with default sampling and adaptive thinking",
-                    )
-                    return await inner.doStream(retry)
-                }
-            },
-        },
-    })
-}

lib/i18n/dictionaries/en.json

@@ -178,6 +178,9 @@
         "networkError": "Network error. Please check your connection.",
         "retryLimit": "Auto-retry limit reached ({max}). Please try again manually.",
         "continuationRetryLimit": "Continuation retry limit reached ({max}). The diagram may be too complex.",
+        "validationFailed": "Diagram validation failed. Please try regenerating.",
+        "malformedXml": "AI generated invalid diagram XML. Please try regenerating.",
+        "failedToProcess": "Failed to process diagram. Please try regenerating.",
         "sessionCorrupted": "Session data was corrupted. Starting fresh.",
         "failedToSave": "Failed to save messages to localStorage",
         "failedToRestore": "Failed to restore from localStorage",
@@ -185,23 +188,7 @@
         "failedToExport": "Error fetching chart data",
         "failedToLoadExample": "Error loading example image",
         "failedToRecordFeedback": "Failed to record your feedback. Please try again.",
-        "storageUpdateFailed": "Chat cleared but browser storage could not be updated",
-        "sessionSaveFailed": "Could not save this chat. Browser storage may be full: delete old chats from history and try again.",
-        "llm": {
-            "invalid_api_key": "The provider rejected the API key. Check it in model settings.",
-            "forbidden": "The provider refused the request. The key may not have access to this model or region.",
-            "model_not_found": "The provider does not know this model. Check the model ID in model settings.",
-            "insufficient_quota": "The provider account has no credit or quota left.",
-            "rate_limited": "The provider is limiting requests. Wait a moment and try again.",
-            "context_too_long": "The conversation is too long for this model. Start a new chat or pick a model with a larger context.",
-            "images_unsupported": "This model doesn't support image input.",
-            "tools_unsupported": "This model doesn't support tool calls, which drawing needs. Pick another model.",
-            "output_truncated": "The output was cut off before the diagram was complete. Try a simpler request or raise the output limit in settings.",
-            "provider_unavailable": "The provider is having problems. Try again later.",
-            "cannot_connect": "Could not reach the provider. Check the base URL and your network.",
-            "timeout": "The provider did not answer in time.",
-            "openModelSettings": "Open model settings"
-        }
+        "storageUpdateFailed": "Chat cleared but browser storage could not be updated"
     },
     "quota": {
         "dailyLimit": "Daily Quota Reached",
@@ -248,7 +235,6 @@
     "reasoning": {
         "thinking": "Thinking...",
         "thoughtFor": "Thought for {duration} seconds",
-        "thoughtForOne": "Thought for 1 second",
         "thoughtBrief": "Thought for a few seconds"
     },
     "dev": {
@@ -385,11 +371,6 @@
         "enterSecretKey": "Enter your secret access key",
         "baseUrl": "Base URL",
         "optional": "(optional)",
-        "getApiKey": "Get API key",
-        "fetchModels": "Fetch models from the provider",
-        "noTools": "no tool calls",
-        "mayNotDraw": "models.dev lists no tool call support for this model, so it may not be able to draw.",
-        "requestUrl": "Requests go to {url}",
         "baseUrlWithExample": "Base URL (optional, e.g. {example})",
         "customEndpoint": "Custom endpoint URL",
         "minimaxBaseUrlHint": "Use /anthropic for Anthropic-compatible API (recommended), or /v1 for OpenAI-compatible API",

lib/i18n/dictionaries/ja.json

@@ -178,6 +178,9 @@
         "networkError": "ネットワークエラー。接続を確認してください。",
         "retryLimit": "自動再試行制限に達しました（{max}）。手動で再試行してください。",
         "continuationRetryLimit": "継続再試行制限に達しました（{max}）。ダイアグラムが複雑すぎる可能性があります。",
+        "validationFailed": "ダイアグラムの検証に失敗しました。再生成してみてください。",
+        "malformedXml": "AI が無効なダイアグラム XML を生成しました。再生成してみてください。",
+        "failedToProcess": "ダイアグラムの処理に失敗しました。再生成してみてください。",
         "sessionCorrupted": "セッションデータが破損しました。最初からやり直します。",
         "failedToSave": "localStorage へのメッセージの保存に失敗しました",
         "failedToRestore": "localStorage からの復元に失敗しました",
@@ -185,23 +188,7 @@
         "failedToExport": "チャートデータの取得エラー",
         "failedToLoadExample": "例の画像の読み込みエラー",
         "failedToRecordFeedback": "フィードバックの記録に失敗しました。もう一度お試しください。",
-        "storageUpdateFailed": "チャットはクリアされましたが、ブラウザストレージを更新できませんでした",
-        "sessionSaveFailed": "このチャットを保存できませんでした。ブラウザのストレージがいっぱいの可能性があります。履歴から古いチャットを削除して、もう一度お試しください。",
-        "llm": {
-            "invalid_api_key": "プロバイダーが API キーを拒否しました。モデル設定で確認してください。",
-            "forbidden": "プロバイダーがリクエストを拒否しました。このキーにはこのモデルまたはリージョンの利用権限がない可能性があります。",
-            "model_not_found": "プロバイダーがこのモデルを認識できません。モデル設定でモデル ID を確認してください。",
-            "insufficient_quota": "プロバイダーのアカウントの残高または利用枠がなくなりました。",
-            "rate_limited": "プロバイダーがリクエスト数を制限しています。少し待ってから再試行してください。",
-            "context_too_long": "会話がこのモデルで扱える長さを超えています。新しいチャットを始めるか、より長いコンテキストに対応したモデルを選んでください。",
-            "images_unsupported": "このモデルは画像入力に対応していません。",
-            "tools_unsupported": "このモデルはツール呼び出しに対応していません。作図にはツール呼び出しが必要です。別のモデルを選んでください。",
-            "output_truncated": "ダイアグラムが完成する前に出力が途中で切れました。リクエストを簡単にするか、設定で出力上限を上げてください。",
-            "provider_unavailable": "プロバイダーで問題が発生しています。しばらくしてから再試行してください。",
-            "cannot_connect": "プロバイダーに接続できません。Base URL とネットワークを確認してください。",
-            "timeout": "プロバイダーから時間内に応答がありませんでした。",
-            "openModelSettings": "モデル設定を開く"
-        }
+        "storageUpdateFailed": "チャットはクリアされましたが、ブラウザストレージを更新できませんでした"
     },
     "quota": {
         "dailyLimit": "1日の割当量に達しました",
@@ -248,7 +235,6 @@
     "reasoning": {
         "thinking": "考え中...",
         "thoughtFor": "{duration} 秒考えました",
-        "thoughtForOne": "1 秒考えました",
         "thoughtBrief": "数秒考えました"
     },
     "dev": {
@@ -339,11 +325,6 @@
         "enterSecretKey": "シークレットアクセスキーを入力",
         "baseUrl": "ベース URL",
         "optional": "（オプション）",
-        "getApiKey": "API キーを取得",
-        "fetchModels": "プロバイダーからモデル一覧を取得",
-        "noTools": "ツール呼び出し非対応",
-        "mayNotDraw": "models.dev によると、このモデルはツール呼び出しに対応していないため、作図できない可能性があります。",
-        "requestUrl": "リクエスト先: {url}",
         "baseUrlWithExample": "ベース URL（オプション、例: {example}）",
         "customEndpoint": "カスタムエンドポイント URL",
         "minimaxBaseUrlHint": "/anthropic で Anthropic 互換 API（推奨）、または /v1 で OpenAI 互換 API を使用",

lib/i18n/dictionaries/zh-Hant.json

@@ -178,6 +178,9 @@
         "networkError": "網路錯誤。請檢查您的連線。",
         "retryLimit": "已達自動重試限制（{max}）。請手動重試。",
         "continuationRetryLimit": "已達繼續重試限制（{max}）。圖表可能過於複雜。",
+        "validationFailed": "圖表驗證失敗。請嘗試重新產生。",
+        "malformedXml": "AI 產生的圖表 XML 無效。請嘗試重新產生。",
+        "failedToProcess": "無法處理圖表。請嘗試重新產生。",
         "sessionCorrupted": "工作階段資料已損壞。重新開始。",
         "failedToSave": "無法儲存訊息到 localStorage",
         "failedToRestore": "無法從 localStorage 還原",
@@ -185,23 +188,7 @@
         "failedToExport": "取得圖表資料時出錯",
         "failedToLoadExample": "載入範例圖片時出錯",
         "failedToRecordFeedback": "記錄您的回饋失敗。請重試。",
-        "storageUpdateFailed": "聊天已清除，但無法更新瀏覽器儲存空間",
-        "sessionSaveFailed": "無法儲存這個對話。瀏覽器儲存空間可能已滿，請在歷史紀錄裡刪除舊對話後重試。",
-        "llm": {
-            "invalid_api_key": "服務商拒絕了這個 API Key，請在模型設定中檢查。",
-            "forbidden": "服務商拒絕了這次請求。這個 Key 可能沒有使用該模型或該地區的權限。",
-            "model_not_found": "服務商找不到這個模型，請在模型設定中檢查模型 ID。",
-            "insufficient_quota": "服務商帳戶的餘額或額度已經用完。",
-            "rate_limited": "服務商正在限制請求頻率，請稍候再試。",
-            "context_too_long": "對話內容超過了這個模型能處理的長度。請開啟新的對話，或換一個上下文更長的模型。",
-            "images_unsupported": "這個模型不支援圖片輸入。",
-            "tools_unsupported": "這個模型不支援工具呼叫，而繪圖需要工具呼叫。請換一個模型。",
-            "output_truncated": "輸出在圖表完成之前就被截斷了。請簡化請求，或在設定中調高輸出上限。",
-            "provider_unavailable": "服務商發生問題，請稍後再試。",
-            "cannot_connect": "無法連線到服務商，請檢查 Base URL 和網路。",
-            "timeout": "服務商沒有及時回應。",
-            "openModelSettings": "開啟模型設定"
-        }
+        "storageUpdateFailed": "聊天已清除，但無法更新瀏覽器儲存空間"
     },
     "quota": {
         "dailyLimit": "已達每日配額",
@@ -248,7 +235,6 @@
     "reasoning": {
         "thinking": "思考中...",
         "thoughtFor": "思考了 {duration} 秒",
-        "thoughtForOne": "思考了 1 秒",
         "thoughtBrief": "思考了幾秒鐘"
     },
     "dev": {
@@ -385,11 +371,6 @@
         "enterSecretKey": "輸入您的 Secret Key",
         "baseUrl": "基礎 URL",
         "optional": "（可選）",
-        "getApiKey": "取得 API Key",
-        "fetchModels": "從服務商取得模型清單",
-        "noTools": "不支援工具呼叫",
-        "mayNotDraw": "models.dev 顯示這個模型不支援工具呼叫，可能無法繪圖。",
-        "requestUrl": "請求將傳送至 {url}",
         "baseUrlWithExample": "基礎 URL（可選，例如 {example}）",
         "customEndpoint": "自訂端點 URL",
         "minimaxBaseUrlHint": "使用 /anthropic 端點為 Anthropic 相容 API（推薦），或使用 /v1 端點為 OpenAI 相容 API",

lib/i18n/dictionaries/zh.json

@@ -178,6 +178,9 @@
         "networkError": "网络错误。请检查您的连接。",
         "retryLimit": "已达到自动重试限制（{max}）。请手动重试。",
         "continuationRetryLimit": "已达到继续重试限制（{max}）。图表可能过于复杂。",
+        "validationFailed": "图表验证失败。请尝试重新生成。",
+        "malformedXml": "AI 生成的图表 XML 无效。请尝试重新生成。",
+        "failedToProcess": "无法处理图表。请尝试重新生成。",
         "sessionCorrupted": "会话数据已损坏。重新开始。",
         "failedToSave": "无法保存消息到 localStorage",
         "failedToRestore": "无法从 localStorage 恢复",
@@ -185,23 +188,7 @@
         "failedToExport": "获取图表数据时出错",
         "failedToLoadExample": "加载示例图片时出错",
         "failedToRecordFeedback": "记录您的反馈失败。请重试。",
-        "storageUpdateFailed": "聊天已清除，但无法更新浏览器存储",
-        "sessionSaveFailed": "无法保存这个对话。浏览器存储空间可能已满，请在历史记录里删除旧对话后重试。",
-        "llm": {
-            "invalid_api_key": "服务商拒绝了这个 API Key，请在模型设置里检查。",
-            "forbidden": "服务商拒绝了这次请求。这个 Key 可能没有使用该模型或该地区的权限。",
-            "model_not_found": "服务商找不到这个模型，请在模型设置里检查模型 ID。",
-            "insufficient_quota": "服务商账户的余额或额度已经用完。",
-            "rate_limited": "服务商正在限制请求频率，请稍等片刻再试。",
-            "context_too_long": "对话内容超过了这个模型能处理的长度。请新开一个对话，或换一个上下文更长的模型。",
-            "images_unsupported": "这个模型不支持图片输入。",
-            "tools_unsupported": "这个模型不支持工具调用，而画图需要工具调用。请换一个模型。",
-            "output_truncated": "输出在图画完之前就被截断了。请简化请求，或在设置里调高输出上限。",
-            "provider_unavailable": "服务商出了问题，请稍后再试。",
-            "cannot_connect": "连接不上服务商，请检查 Base URL 和网络。",
-            "timeout": "服务商没有及时响应。",
-            "openModelSettings": "打开模型设置"
-        }
+        "storageUpdateFailed": "聊天已清除，但无法更新浏览器存储"
     },
     "quota": {
         "dailyLimit": "已达每日配额",
@@ -248,7 +235,6 @@
     "reasoning": {
         "thinking": "思考中...",
         "thoughtFor": "思考了 {duration} 秒",
-        "thoughtForOne": "思考了 1 秒",
         "thoughtBrief": "思考了几秒钟"
     },
     "dev": {
@@ -385,11 +371,6 @@
         "enterSecretKey": "输入您的 Secret Key",
         "baseUrl": "基础 URL",
         "optional": "（可选）",
-        "getApiKey": "获取 API Key",
-        "fetchModels": "从服务商获取模型列表",
-        "noTools": "不支持工具调用",
-        "mayNotDraw": "models.dev 显示这个模型不支持工具调用，可能无法画图。",
-        "requestUrl": "请求将发往 {url}",
         "baseUrlWithExample": "基础 URL（可选，例如 {example}）",
         "customEndpoint": "自定义端点 URL",
         "minimaxBaseUrlHint": "使用 /anthropic 端点为 Anthropic 兼容 API（推荐），或使用 /v1 端点为 OpenAI 兼容 API",

lib/langfuse.ts

@@ -51,15 +51,8 @@ export function setTraceOutput(output: string) {
     if (!isLangfuseEnabled()) return
 
     updateActiveTrace({ output })
-    endTrace()
-}
-
-// End the observe() wrapper span (AI SDK creates its own child spans with usage).
-// It uses endOnExit: false, so every request path has to end it, or the trace
-// is never exported: stream finish, stream error/abort, and early returns.
-export function endTrace() {
-    if (!isLangfuseEnabled()) return
 
+    // End the observe() wrapper span (AI SDK creates its own child spans with usage)
     const activeSpan = api.trace.getActiveSpan()
     if (activeSpan) {
         activeSpan.end()

lib/llm-errors.ts

@@ -1,178 +0,0 @@
-import {
-    APICallError,
-    InvalidToolInputError,
-    LoadAPIKeyError,
-    NoSuchToolError,
-    RetryError,
-    ToolCallRepairError,
-} from "ai"
-
-/**
- * What went wrong with a model call, for a hint the user can act on. The
- * provider's own message always goes along, because a guess can be wrong.
- */
-export type LLMErrorCode =
-    | "invalid_api_key"
-    | "forbidden"
-    | "model_not_found"
-    | "insufficient_quota"
-    | "rate_limited"
-    | "context_too_long"
-    | "images_unsupported"
-    | "tools_unsupported"
-    | "output_truncated"
-    | "provider_unavailable"
-    | "cannot_connect"
-    | "timeout"
-    | "unknown"
-
-export interface LLMError {
-    type: "provider"
-    code: LLMErrorCode
-    message: string
-}
-
-// Texts that name the cause more precisely than the status code: a quota
-// error can come as 403 or 429, a context or image error as a plain 400
-const SPECIFIC_TEXTS: Array<[RegExp, LLMErrorCode]> = [
-    [
-        // Not "too many tokens": that is Bedrock's throttling message
-        /context length|context window|maximum context|prompt is too long|input is too long|too many input tokens/i,
-        "context_too_long",
-    ],
-    [
-        /image content block|image_url|does not support image|image input is not supported/i,
-        "images_unsupported",
-    ],
-    [
-        /does not support tools|tool use is not supported|tools? (?:are|is) not supported|function calling is not supported/i,
-        "tools_unsupported",
-    ],
-    // Bedrock, when the output limit cut the tool call's JSON short
-    [/toolUse\.input is invalid/i, "output_truncated"],
-    // Bedrock, for a model id without the inference profile prefix
-    [/on-demand throughput isn.t supported/i, "model_not_found"],
-    [
-        /insufficient[_ ]quota|insufficient balance|exceeded your current quota|credit balance is too low|余额不足/i,
-        "insufficient_quota",
-    ],
-]
-
-const STATUS_CODES: Record<number, LLMErrorCode> = {
-    401: "invalid_api_key",
-    402: "insufficient_quota",
-    // Not "invalid key": a valid key can lack access to a model or region
-    403: "forbidden",
-    404: "model_not_found",
-    408: "timeout",
-    // A retired model
-    410: "model_not_found",
-    413: "context_too_long",
-    429: "rate_limited",
-}
-
-const GENERAL_TEXTS: Array<[RegExp, LLMErrorCode]> = [
-    [
-        /model[_ ]not[_ ]found|model .*does not exist|unknown model|no such model/i,
-        "model_not_found",
-    ],
-    [
-        /invalid[_ ]api[_ ]key|incorrect api key|unauthorized/i,
-        "invalid_api_key",
-    ],
-    [/rate limit|too many requests/i, "rate_limited"],
-    [
-        /Cannot connect to API|ECONNREFUSED|ENOTFOUND|ECONNRESET|ETIMEDOUT|fetch failed/i,
-        "cannot_connect",
-    ],
-]
-
-/** Secrets a provider may echo back: API keys, Bearer tokens, key=value */
-function redact(text: string): string {
-    return text
-        .replace(/\b(sk|pk|rk|ak)-[A-Za-z0-9_-]{8,}/g, "$1-[redacted]")
-        .replace(/\bBearer\s+[A-Za-z0-9._~+/-]+=*/gi, "Bearer [redacted]")
-        .replace(/\bAKIA[0-9A-Z]{16}\b/g, "[redacted]")
-        .replace(
-            /\b(api[_-]?key|access[_-]?key|secret|token|password|signature)(["']?\s*[:=]\s*["']?)[^\s"',&}]+/gi,
-            "$1$2[redacted]",
-        )
-}
-
-function problemDetail(body: string): string | undefined {
-    try {
-        const detail = JSON.parse(body)?.detail
-        return typeof detail === "string" ? detail : undefined
-    } catch {
-        return undefined
-    }
-}
-
-/**
- * The error text for the chat stream: what went wrong with the provider as
- * JSON for the hint, or the text the model must read to fix a tool call.
- * On the server's keys the provider's own text stays in the server log:
- * it can name the server's account, role or internal hosts.
- */
-export function streamErrorText(error: unknown, hideDetails = false): string {
-    // The SDK passes an invalid tool call's error as a plain string
-    if (typeof error === "string") return error
-    if (isToolCallError(error)) return (error as Error).message
-    const classified = classifyLLMError(error)
-    if (hideDetails) {
-        console.error("[chat] Provider error:", error)
-        classified.message = "The provider returned an error."
-    }
-    return JSON.stringify(classified)
-}
-
-/**
- * Model and tool errors the SDK sends back to the model as the tool result,
- * so it can fix its call. Their text has to stay as it is.
- */
-export function isToolCallError(error: unknown): boolean {
-    return (
-        InvalidToolInputError.isInstance(error) ||
-        NoSuchToolError.isInstance(error) ||
-        ToolCallRepairError.isInstance(error)
-    )
-}
-
-export function classifyLLMError(error: unknown): LLMError {
-    // After the SDK's retries, the last attempt says what happened
-    const e = RetryError.isInstance(error) ? error.lastError : error
-    // Errors sent inside the stream can be plain objects like OpenRouter's
-    // { code: 503, message }
-    const plain = e as {
-        message?: unknown
-        code?: unknown
-        statusCode?: number
-    }
-    const raw =
-        e instanceof Error
-            ? e.message
-            : typeof plain?.message === "string"
-              ? plain.message
-              : String(e)
-    const body = APICallError.isInstance(e) ? (e.responseBody ?? "") : ""
-    // A problem+json body names the reason the SDK left out (NVIDIA: "Gone")
-    const detail = problemDetail(body)
-    const message = redact(detail ? `${raw}: ${detail}` : raw).slice(0, 500)
-    const text = `${raw} ${body}`
-    const status = APICallError.isInstance(e)
-        ? e.statusCode
-        : (plain?.statusCode ??
-          (typeof plain?.code === "number" ? plain.code : undefined))
-
-    const find = (rules: Array<[RegExp, LLMErrorCode]>) =>
-        rules.find(([pattern]) => pattern.test(text))?.[1]
-    const code =
-        (e instanceof Error && e.name === "TimeoutError" && "timeout") ||
-        (LoadAPIKeyError.isInstance(e) && "invalid_api_key") ||
-        find(SPECIFIC_TEXTS) ||
-        (status && STATUS_CODES[status]) ||
-        (status && status >= 500 && "provider_unavailable") ||
-        find(GENERAL_TEXTS) ||
-        "unknown"
-    return { type: "provider", code, message }
-}

lib/model-catalog.ts

@@ -1,45 +0,0 @@
-import catalog from "@/lib/model-catalog.json"
-import type { ProviderName } from "@/lib/types/model-config"
-
-/**
- * What models.dev knows about a model (scripts/update-model-catalog.mjs).
- * Only used for hints: requests are sent the same way either way, since
- * the data can be wrong or out of date.
- */
-export interface ModelInfo {
-    tools: boolean
-    images: boolean
-    reasoning: boolean
-    context?: number
-    output?: number
-}
-
-const CATALOG = catalog as Record<string, Record<string, ModelInfo>>
-
-/**
- * The entry for a model: an exact match ignoring case, else the longest id
- * the model id starts with, followed by "-", ":" or ".". So
- * claude-sonnet-4-5-20250929 finds claude-sonnet-4-5, but gpt-4 does not
- * find gpt-4o.
- */
-export function getModelInfo(
-    provider: ProviderName,
-    modelId: string,
-): ModelInfo | undefined {
-    const models = CATALOG[provider]
-    if (!models) return undefined
-    const wanted = modelId.trim().toLowerCase()
-    let best: string | undefined
-    for (const id of Object.keys(models)) {
-        const lower = id.toLowerCase()
-        if (lower === wanted) return models[id]
-        if (
-            wanted.startsWith(lower) &&
-            "-:.".includes(wanted[lower.length]) &&
-            lower.length > (best?.length ?? 0)
-        ) {
-            best = id
-        }
-    }
-    return best ? models[best] : undefined
-}

lib/output-token-limit.ts

@@ -22,12 +22,6 @@ export const MAX_OUTPUT_TOKENS_LIMIT = 200000
  */
 const MIN_USABLE_OUTPUT_TOKENS = 1024
 
-/**
- * Retry budget when a rejection names the budget parameter but no number we can
- * read. It is the default from before 64000, which these providers ran with.
- */
-const FALLBACK_OUTPUT_TOKENS = 16000
-
 /** Status codes that can carry a complaint about the requested budget. */
 const BUDGET_REJECTION_STATUSES = new Set([400, 422])
 
@@ -35,8 +29,24 @@ function usableLimit(value: number): number | null {
     return value >= MIN_USABLE_OUTPUT_TOKENS ? value : null
 }
 
-/** Message and body of an error that may be about the budget, or null. */
-export function rejectionText(error: unknown): string | null {
+/**
+ * A budget this large exceeds what some models accept. Providers reject it with a
+ * 400 that names the real limit, so we parse the number out and retry once
+ * instead of failing the turn.
+ *
+ * Formats seen in the wild:
+ * - Bedrock: "The maximum tokens you requested exceeds the model limit of 4096."
+ * - OpenRouter: "This endpoint's maximum context length is 64000 tokens. However,
+ *   you requested about 64025 tokens (25 of text input, 64000 in the output)."
+ *   Note this one is an input+output ceiling, so the input has to be subtracted.
+ * - Anthropic: "max_tokens: 200000 > 64000, which is the maximum allowed..."
+ * - OpenAI: "This model supports at most 16384 completion tokens"
+ *
+ * Every pattern names tokens explicitly. A generic one (an earlier draft matched
+ * "lower than N") would reinterpret unrelated failures, and retrying on a bogus
+ * number turns a readable error into an empty diagram.
+ */
+export function parseOutputTokenLimit(error: unknown): number | null {
     const err = error as {
         message?: unknown
         responseBody?: unknown
@@ -56,109 +66,24 @@ export function rejectionText(error: unknown): string | null {
         typeof err?.responseBody === "string" ? err.responseBody : "",
     ].join(" ")
 
-    return text.trim() ? text : null
-}
+    if (!text) return null
 
-/**
- * A budget this large exceeds what some models accept. Providers reject it with a
- * 400 that names the real limit, so we parse the number out and retry once
- * instead of failing the turn.
- *
- * Formats seen in the wild:
- * - Bedrock: "The maximum tokens you requested exceeds the model limit of 4096."
- * - OpenRouter: "This endpoint's maximum context length is 64000 tokens. However,
- *   you requested about 64025 tokens (25 of text input, 64000 in the output)."
- *   Note this one is an input+output ceiling, so the input has to be subtracted.
- *   vLLM and SGLang send the same kind of ceiling, with the input written as
- *   "6000 in the messages", "has 6000 input tokens" or "6000 tokens from the input".
- * - Anthropic: "max_tokens: 200000 > 64000, which is the maximum allowed..."
- * - OpenAI: "This model supports at most 16384 completion tokens"
- * - Volcengine Ark: "The parameter `max_tokens` specified in the request are not
- *   valid: integer above maximum value, expected a value <= 32768, but got 64000"
- * - DashScope: "Range of max_tokens should be [1, 8192]"
- *
- * Every pattern names tokens explicitly. A generic one (an earlier draft matched
- * "lower than N") would reinterpret unrelated failures, and retrying on a bogus
- * number turns a readable error into an empty diagram.
- */
-function readCeiling(text: string): number | null {
     // Combined input+output ceiling: subtract the input the provider counted,
     // plus a small margin because its estimate is approximate.
-    const context = text.match(/maximum context length (?:is|of) (\d+)/i)
+    const context = text.match(/maximum context length is (\d+)/i)
     if (context) {
-        const input =
-            text.match(/(\d+) of text input/i) ||
-            text.match(/(\d+) in the messages/i) ||
-            text.match(/(\d+) tokens from the input/i) ||
-            text.match(/(\d+) input tokens/i)
-        return Number(context[1]) - (input ? Number(input[1]) : 0) - 1024
+        const input = text.match(/(\d+) of text input/i)
+        return usableLimit(
+            Number(context[1]) - (input ? Number(input[1]) : 0) - 1024,
+        )
     }
 
     const output =
         text.match(/model limit of (\d+)/i) ||
         text.match(/> (\d+), which is the maximum/i) ||
-        text.match(/at most (\d+) completion tokens/i) ||
-        text.match(/max_\w*tokens.*?expected a value (?:<=|\\u003c=) (\d+)/i) ||
-        text.match(/Range of max_tokens should be \[1,\s*(\d+)\]/i)
+        text.match(/at most (\d+) completion tokens/i)
 
-    return output ? Number(output[1]) : null
-}
-
-/** The usable output ceiling named in a rejection, or null. */
-export function parseOutputTokenLimit(error: unknown): number | null {
-    const text = rejectionText(error)
-    const ceiling = text ? readCeiling(text) : null
-    return ceiling === null ? null : usableLimit(ceiling)
-}
-
-/**
- * Thinking budget the provider adds on top of maxOutputTokens. Bedrock and
- * Anthropic send maxOutputTokens + budgetTokens as max_tokens, so a ceiling in
- * their rejection covers both.
- */
-function thinkingBudget(providerOptions: unknown): number {
-    const options = providerOptions as
-        | {
-              bedrock?: {
-                  reasoningConfig?: { type?: string; budgetTokens?: unknown }
-              }
-              anthropic?: {
-                  thinking?: { type?: string; budgetTokens?: unknown }
-              }
-          }
-        | undefined
-    const config =
-        options?.bedrock?.reasoningConfig ?? options?.anthropic?.thinking
-    return config?.type === "enabled" && typeof config.budgetTokens === "number"
-        ? config.budgetTokens
-        : 0
-}
-
-/**
- * The budget to retry with after a rejection, or null to surface the error.
- */
-export function retryOutputTokens(
-    error: unknown,
-    params: { maxOutputTokens?: number; providerOptions?: unknown },
-): number | null {
-    const requested = params.maxOutputTokens
-    const text = rejectionText(error)
-    if (!requested || !text) return null
-
-    const ceiling = readCeiling(text)
-    if (ceiling !== null) {
-        // The ceiling applies to what was actually sent, thinking included,
-        // so the retry has to leave room for the thinking too.
-        const thinking = thinkingBudget(params.providerOptions)
-        if (ceiling >= requested + thinking) return null
-        return usableLimit(ceiling - thinking)
-    }
-
-    // Names the budget parameter, but in a format we cannot read a number from
-    if (/max_\w*tokens/i.test(text) && requested > FALLBACK_OUTPUT_TOKENS) {
-        return FALLBACK_OUTPUT_TOKENS
-    }
-    return null
+    return output ? usableLimit(Number(output[1])) : null
 }
 
 /**
@@ -178,15 +103,17 @@ export function withOutputTokenLimitFallback(
                 try {
                     return await doStream()
                 } catch (error) {
-                    const retry = retryOutputTokens(error, params)
-                    if (!retry) throw error
+                    const limit = parseOutputTokenLimit(error)
+                    const requested = params.maxOutputTokens
+
+                    if (!limit || !requested || limit >= requested) throw error
 
                     console.warn(
-                        `[maxOutputTokens] ${params.maxOutputTokens} rejected, retrying with ${retry}`,
+                        `[maxOutputTokens] ${requested} rejected, retrying with ${limit}`,
                     )
                     return await inner.doStream({
                         ...params,
-                        maxOutputTokens: retry,
+                        maxOutputTokens: limit,
                     })
                 }
             },
@@ -208,17 +135,11 @@ function validBudget(value: string | null | undefined): number | null {
  * desktop app too), then server env, then the default. Both sources go through
  * the same validation, so a typo in either falls back instead of reaching the
  * provider.
- *
- * On the server's credentials the user setting can only lower the server value,
- * so MAX_OUTPUT_TOKENS keeps capping what the server pays for.
  */
-export function resolveMaxOutputTokens(
-    headerValue: string | null,
-    usesServerCredentials: boolean,
-): number {
-    const header = validBudget(headerValue)
-    const server =
-        validBudget(process.env.MAX_OUTPUT_TOKENS) ?? DEFAULT_MAX_OUTPUT_TOKENS
-    if (header === null) return server
-    return usesServerCredentials ? Math.min(header, server) : header
+export function resolveMaxOutputTokens(headerValue: string | null): number {
+    return (
+        validBudget(headerValue) ??
+        validBudget(process.env.MAX_OUTPUT_TOKENS) ??
+        DEFAULT_MAX_OUTPUT_TOKENS
+    )
 }

lib/pdf-utils.ts

@@ -1,4 +1,4 @@
-import { extractText } from "unpdf"
+import { extractText, getDocumentProxy } from "unpdf"
 
 // Maximum characters allowed for extracted text (configurable via env)
 const DEFAULT_MAX_EXTRACTED_CHARS = 150000 // 150k chars
@@ -14,7 +14,6 @@ const TEXT_EXTENSIONS = [
     ".json",
     ".csv",
     ".xml",
-    ".svg",
     ".html",
     ".css",
     ".js",
@@ -44,10 +43,8 @@ const TEXT_EXTENSIONS = [
  */
 export async function extractPdfText(file: File): Promise<string> {
     const buffer = await file.arrayBuffer()
-    // Pass raw bytes so unpdf destroys the PDF document when it is done
-    const { text } = await extractText(new Uint8Array(buffer), {
-        mergePages: true,
-    })
+    const pdf = await getDocumentProxy(new Uint8Array(buffer))
+    const { text } = await extractText(pdf, { mergePages: true })
     return text as string
 }
 

lib/provider-models.ts

@@ -1,200 +0,0 @@
-import { createGateway } from "ai"
-import { getModelInfo } from "@/lib/model-catalog"
-import {
-    normalizeBaseUrl,
-    PROVIDER_INFO,
-    type ProviderName,
-} from "@/lib/types/model-config"
-
-/** A model a provider offers. tools is false when it cannot call tools. */
-export interface ListedModel {
-    id: string
-    tools?: boolean
-}
-
-export const AIHUBMIX_MODELS_ENDPOINT = "https://aihubmix.com/api/v1/models"
-
-export function canListModels(provider: ProviderName): boolean {
-    return (
-        Object.hasOwn(PROVIDER_INFO, provider) &&
-        !!PROVIDER_INFO[provider].modelList
-    )
-}
-
-// Models in OpenAI-style lists that are not for chat
-const NON_CHAT =
-    /(?:^|[-/_])(?:embed(?:ding)?s?|whisper|tts|transcribe|dall-e|moderation|rerank|realtime|sora)(?:$|[-/_])|gpt-image/i
-
-const NON_CHAT_AIHUBMIX_TYPES = new Set([
-    "embedding",
-    "image_generation",
-    "rerank",
-    "transcription",
-    "tts",
-    "video",
-])
-
-/** Chat model ids from AIHubMix's public model list */
-export function extractAihubmixModelIds(payload: unknown): string[] {
-    const data = (payload as { data?: unknown })?.data
-    if (!Array.isArray(data)) return []
-    const ids = new Set<string>()
-    for (const item of data) {
-        const record = item as { model_id?: unknown; types?: unknown }
-        if (typeof record?.model_id !== "string" || !record.model_id.trim()) {
-            continue
-        }
-        const types = new Set(
-            typeof record.types === "string"
-                ? record.types.split(",").map((t) => t.trim())
-                : [],
-        )
-        if (!types.has("llm")) continue
-        if ([...NON_CHAT_AIHUBMIX_TYPES].some((t) => types.has(t))) continue
-        ids.add(record.model_id.trim())
-    }
-    return [...ids]
-}
-
-/** GET a JSON list; a failed request carries its status for the error hint */
-async function getJson(
-    url: string,
-    headers: Record<string, string>,
-    fetchFn: typeof fetch,
-): Promise<any> {
-    const response = await fetchFn(url, {
-        headers,
-        signal: AbortSignal.timeout(15_000),
-    })
-    if (!response.ok) {
-        throw Object.assign(
-            new Error(`The model list request failed (${response.status})`),
-            { statusCode: response.status },
-        )
-    }
-    return response.json()
-}
-
-/**
- * Where to list from without the user's base URL: where chat goes then. For
- * Ollama that is the server's Ollama, else the SDK's local default; a local
- * default in PROVIDER_INFO (SGLang's) only fills the settings form.
- */
-function listFallbackUrl(provider: ProviderName): string {
-    if (provider === "ollama") {
-        return process.env.OLLAMA_BASE_URL || "http://127.0.0.1:11434/api"
-    }
-    const url = PROVIDER_INFO[provider].defaultBaseUrl
-    return url?.startsWith("https://") ? url : ""
-}
-
-/**
- * The provider's chat models, with tool support from the provider's own
- * data or else models.dev. Only the client's key is used, so the server's
- * keys never go to a URL the client chose.
- */
-export async function listProviderModels(
-    provider: ProviderName,
-    { apiKey, baseUrl }: { apiKey?: string; baseUrl?: string },
-    fetchFn: typeof fetch = fetch,
-): Promise<ListedModel[]> {
-    const base = normalizeBaseUrl(baseUrl || listFallbackUrl(provider))
-    const bearer: Record<string, string> = apiKey
-        ? { Authorization: `Bearer ${apiKey}` }
-        : {}
-    let models: ListedModel[]
-
-    // AIHubMix has a public list, unless the user points to another
-    // endpoint, which is OpenAI-compatible
-    const style =
-        provider === "aihubmix" &&
-        baseUrl &&
-        !/^https:\/\/aihubmix\.com(\/v1)?$/.test(base)
-            ? "openai"
-            : PROVIDER_INFO[provider].modelList
-
-    switch (style) {
-        case "anthropic": {
-            const data = await getJson(
-                `${base}/models?limit=1000`,
-                {
-                    "x-api-key": apiKey ?? "",
-                    "anthropic-version": "2023-06-01",
-                },
-                fetchFn,
-            )
-            models = (data.data ?? []).map((m: { id: string }) => ({
-                id: m.id,
-            }))
-            break
-        }
-        case "google": {
-            // The key goes in a header: in the URL it would end up in logs
-            const data = await getJson(
-                `${base}/models?pageSize=1000`,
-                { "x-goog-api-key": apiKey ?? "" },
-                fetchFn,
-            )
-            models = (data.models ?? [])
-                .filter((m: { supportedGenerationMethods?: string[] }) =>
-                    m.supportedGenerationMethods?.includes("generateContent"),
-                )
-                .map((m: { name: string }) => ({
-                    id: m.name.replace(/^models\//, ""),
-                }))
-            break
-        }
-        case "ollama": {
-            const api = base.endsWith("/api") ? base : `${base}/api`
-            const data = await getJson(`${api}/tags`, bearer, fetchFn)
-            models = (data.models ?? []).map((m: { name: string }) => ({
-                id: m.name,
-            }))
-            break
-        }
-        case "openrouter": {
-            const data = await getJson(`${base}/models`, bearer, fetchFn)
-            models = (data.data ?? []).map(
-                (m: { id: string; supported_parameters?: string[] }) => ({
-                    id: m.id,
-                    ...(m.supported_parameters && {
-                        tools: m.supported_parameters.includes("tools"),
-                    }),
-                }),
-            )
-            break
-        }
-        case "gateway": {
-            const { models: entries } = await createGateway({
-                ...(apiKey && { apiKey }),
-                ...(baseUrl && { baseURL: base }),
-                fetch: fetchFn,
-            }).getAvailableModels()
-            models = entries
-                .filter((m) => !m.modelType || m.modelType === "language")
-                .map((m) => ({ id: m.id }))
-            break
-        }
-        case "aihubmix": {
-            const data = await getJson(AIHUBMIX_MODELS_ENDPOINT, {}, fetchFn)
-            models = extractAihubmixModelIds(data).map((id) => ({ id }))
-            break
-        }
-        default: {
-            if (!base) {
-                throw new Error(
-                    `${PROVIDER_INFO[provider].label} needs a base URL to list its models.`,
-                )
-            }
-            const data = await getJson(`${base}/models`, bearer, fetchFn)
-            models = (data.data ?? [])
-                .map((m: { id: string }) => ({ id: m.id }))
-                .filter((m: ListedModel) => !NON_CHAT.test(m.id))
-        }
-    }
-
-    return models.map((m) => ({
-        ...m,
-        tools: m.tools ?? getModelInfo(provider, m.id)?.tools,
-    }))
-}

lib/server-model-config.ts

@@ -47,14 +47,11 @@ export interface FlattenedServerModel {
 
 /**
  * Convert provider name to URL-safe slug for use in model ID
- * e.g., "OpenAI Production" → "openai-production", "主力" → "4e3b-529b"
- * Non-ASCII characters become their hex code point so CJK names stay
- * distinct; the id is sent in HTTP headers, which must be ASCII.
+ * e.g., "OpenAI Production" → "openai-production"
  */
-export function slugify(name: string): string {
+function slugify(name: string): string {
     return name
         .toLowerCase()
-        .replace(/[^\p{ASCII}]/gu, (c) => `-${c.codePointAt(0)?.toString(16)}-`)
         .replace(/[^a-z0-9]+/g, "-")
         .replace(/^-|-$/g, "")
 }
@@ -192,7 +189,6 @@ export async function loadFlattenedServerModels(): Promise<
     const defaultModelId = process.env.AI_MODEL
 
     const flattened: FlattenedServerModel[] = []
-    const seenIds = new Set<string>()
 
     for (const p of cfg.providers) {
         const providerLabel =
@@ -203,16 +199,6 @@ export async function loadFlattenedServerModels(): Promise<
 
         for (const modelId of p.models) {
             const id = `server:${nameSlug}:${modelId}`
-            // Names that differ only in case or punctuation share a slug.
-            // A repeated id would always resolve to the first provider's
-            // credentials, so drop it instead.
-            if (seenIds.has(id)) {
-                console.warn(
-                    `[server-model-config] Skipping duplicate model id "${id}". Provider names must differ in letters or digits.`,
-                )
-                continue
-            }
-            seenIds.add(id)
 
             // Default model priority:
             // 1. From ai-models.json: first model of provider with default: true

lib/session-storage.ts

@@ -1,6 +1,5 @@
 import { type DBSchema, type IDBPDatabase, openDB } from "idb"
 import { nanoid } from "nanoid"
-import { toast } from "sonner"
 import type { Template } from "./template-storage"
 
 // Constants
@@ -62,7 +61,6 @@ let dbPromise: Promise<IDBPDatabase<ChatSessionDB>> | null = null
 
 async function getDB(): Promise<IDBPDatabase<ChatSessionDB>> {
     if (!dbPromise) {
-        // A failed or lost connection is not cached: the next call reopens it
         dbPromise = openDB<ChatSessionDB>(DB_NAME, DB_VERSION, {
             upgrade(db, oldVersion) {
                 if (oldVersion < 1) {
@@ -90,28 +88,6 @@ async function getDB(): Promise<IDBPDatabase<ChatSessionDB>> {
                     }
                 }
             },
-            blocked() {
-                // An older tab keeps the DB open, so the upgrade has to wait
-                toast.warning(
-                    "Please close other tabs of this app to finish updating chat storage.",
-                    { id: "idb-upgrade-blocked", duration: 10000 },
-                )
-            },
-            blocking(_currentVersion, _blockedVersion, event) {
-                // Another tab needs to upgrade the DB: close our connection so
-                // it is not stuck, and reopen on the next call
-                const db = event.target as IDBDatabase
-                db.close()
-                dbPromise = null
-            },
-            terminated() {
-                // The browser closed the connection (e.g. Safari after a long
-                // time in the background)
-                dbPromise = null
-            },
-        }).catch((error) => {
-            dbPromise = null
-            throw error
         })
     }
     return dbPromise
@@ -169,8 +145,6 @@ export async function getSession(id: string): Promise<ChatSession | null> {
     }
 }
 
-// Returns false on failure (e.g. storage quota exceeded). Other sessions are
-// never deleted automatically; the caller tells the user instead.
 export async function saveSession(session: ChatSession): Promise<boolean> {
     if (!isIndexedDBAvailable()) return false
     try {
@@ -178,11 +152,29 @@ export async function saveSession(session: ChatSession): Promise<boolean> {
         await db.put(STORE_NAME, session)
         return true
     } catch (error) {
-        console.error("Failed to save session:", error)
-        // Reopen the connection next time in case it was lost (Safari reports
-        // "Connection to Indexed Database server lost" without closing it)
-        dbPromise = null
-        return false
+        // Handle quota exceeded
+        if (
+            error instanceof DOMException &&
+            error.name === "QuotaExceededError"
+        ) {
+            console.warn("Storage quota exceeded, deleting oldest session...")
+            await deleteOldestSession()
+            // Retry once
+            try {
+                const db = await getDB()
+                await db.put(STORE_NAME, session)
+                return true
+            } catch (retryError) {
+                console.error(
+                    "Failed to save session after cleanup:",
+                    retryError,
+                )
+                return false
+            }
+        } else {
+            console.error("Failed to save session:", error)
+            return false
+        }
     }
 }
 

lib/ssrf-protection.ts

@@ -115,19 +115,3 @@ export async function isPrivateUrl(urlString: string): Promise<boolean> {
 export function allowPrivateUrls(): boolean {
     return process.env.ALLOW_PRIVATE_URLS !== "false"
 }
-
-/**
- * A fetch for requests to a base URL the client chose. With private URLs
- * blocked, a public URL could still redirect the request to an internal
- * host, so redirects are refused. Undefined when private URLs are allowed.
- */
-export function redirectGuardedFetch(): typeof fetch | undefined {
-    if (allowPrivateUrls()) return undefined
-    return async (input, init) => {
-        const response = await fetch(input, { ...init, redirect: "manual" })
-        if (response.status >= 300 && response.status < 400) {
-            throw new Error("Redirects are not allowed for custom base URLs")
-        }
-        return response
-    }
-}

lib/system-prompts.ts

@@ -1,14 +1,11 @@
 /**
  * System prompts for different AI models
  * Extended prompt is used for models with higher cache token minimums (Opus 4.5, Haiku 4.5)
+ *
+ * Token counting utilities are in a separate file (token-counter.ts) to avoid
+ * WebAssembly issues with Next.js server-side rendering.
  */
 
-import {
-    SWIMLANE_EXAMPLE,
-    TWO_EDGES_EXAMPLE,
-    WAYPOINT_EXAMPLE,
-} from "@/packages/mcp-server/src/xml-examples.ts"
-
 // Default system prompt (~1900 tokens) - works with all models
 export const DEFAULT_SYSTEM_PROMPT = `
 You are an expert diagram creation assistant specializing in draw.io XML generation.
@@ -44,7 +41,7 @@ parameters: {
 tool name: edit_diagram
 description: Edit specific parts of the EXISTING diagram. Use this when making small targeted changes like adding/removing elements, changing labels, or adjusting properties. This is more efficient than regenerating the entire diagram.
 parameters: {
-  operations: Array<{operation: "update" | "add" | "delete", cell_id: string, new_xml?: string}>
+  edits: Array<{search: string, replace: string}>
 }
 ---Tool3---
 tool name: append_diagram
@@ -244,7 +241,21 @@ const EXTENDED_ADDITIONS = `
 
 **Example with swimlanes and edges** (generate ONLY this - no wrapper tags):
 \`\`\`xml
-${SWIMLANE_EXAMPLE}
+<mxCell id="lane1" value="Frontend" style="swimlane;" vertex="1" parent="1">
+  <mxGeometry x="40" y="40" width="200" height="200" as="geometry"/>
+</mxCell>
+<mxCell id="step1" value="Step 1" style="rounded=1;" vertex="1" parent="lane1">
+  <mxGeometry x="20" y="60" width="160" height="40" as="geometry"/>
+</mxCell>
+<mxCell id="lane2" value="Backend" style="swimlane;" vertex="1" parent="1">
+  <mxGeometry x="280" y="40" width="200" height="200" as="geometry"/>
+</mxCell>
+<mxCell id="step2" value="Step 2" style="rounded=1;" vertex="1" parent="lane2">
+  <mxGeometry x="20" y="60" width="160" height="40" as="geometry"/>
+</mxCell>
+<mxCell id="edge1" style="edgeStyle=orthogonalEdgeStyle;endArrow=classic;" edge="1" parent="1" source="step1" target="step2">
+  <mxGeometry relative="1" as="geometry"/>
+</mxCell>
 \`\`\`
 
 ### append_diagram Details
@@ -307,7 +318,12 @@ If cell_id not found, check "Current diagram XML" for correct IDs. Use display_d
 
 ### Two edges between same nodes (CORRECT - no overlap):
 \`\`\`xml
-${TWO_EDGES_EXAMPLE}
+<mxCell id="e1" value="A to B" style="edgeStyle=orthogonalEdgeStyle;exitX=1;exitY=0.3;entryX=0;entryY=0.3;endArrow=classic;" edge="1" parent="1" source="a" target="b">
+  <mxGeometry relative="1" as="geometry"/>
+</mxCell>
+<mxCell id="e2" value="B to A" style="edgeStyle=orthogonalEdgeStyle;exitX=0;exitY=0.7;entryX=1;entryY=0.7;endArrow=classic;" edge="1" parent="1" source="b" target="a">
+  <mxGeometry relative="1" as="geometry"/>
+</mxCell>
 \`\`\`
 
 ### Edge with single waypoint (simple detour):
@@ -326,7 +342,14 @@ ${TWO_EDGES_EXAMPLE}
 **WRONG:** Direct diagonal line crosses over Develop
 **CORRECT:** Route around the OUTSIDE (go right first, then up)
 \`\`\`xml
-${WAYPOINT_EXAMPLE}
+<mxCell id="hotfix_to_main" style="edgeStyle=orthogonalEdgeStyle;exitX=0.5;exitY=0;entryX=1;entryY=0.5;endArrow=classic;" edge="1" parent="1" source="hotfix" target="main">
+  <mxGeometry relative="1" as="geometry">
+    <Array as="points">
+      <mxPoint x="750" y="80"/>
+      <mxPoint x="750" y="150"/>
+    </Array>
+  </mxGeometry>
+</mxCell>
 \`\`\`
 This routes the edge to the RIGHT of all shapes (x=750), then enters Main from the right side.
 

lib/types/model-config.ts

@@ -32,8 +32,6 @@ export interface ModelConfig {
     modelId: string // e.g., "gpt-4o", "claude-sonnet-4-5"
     validated?: boolean // Has this model been validated
     validationError?: string // Error message if validation failed
-    validationWarning?: string // Passed, but e.g. did not call a tool
-    responseTime?: number // Milliseconds the last test took
 }
 
 // Provider configuration
@@ -122,45 +120,22 @@ export const PROVIDER_LOGO_MAP: Record<string, string> = {
     atlascloud: "openai",
 }
 
-/** How a provider lists its models (see lib/provider-models.ts) */
-export type ModelListStyle =
-    | "openai"
-    | "anthropic"
-    | "google"
-    | "ollama"
-    | "openrouter"
-    | "aihubmix"
-    | "gateway"
-
-// Provider metadata. apiKeyUrl is the page where users create a key.
-// modelList is missing where a key alone cannot list the models (Bedrock,
-// Vertex, Azure) or the list is not reliable (Doubao, MiniMax).
+// Provider metadata
 export const PROVIDER_INFO: Record<
     ProviderName,
-    {
-        label: string
-        defaultBaseUrl?: string
-        apiKeyUrl?: string
-        modelList?: ModelListStyle
-    }
+    { label: string; defaultBaseUrl?: string }
 > = {
     openai: {
         label: "OpenAI",
         defaultBaseUrl: "https://api.openai.com/v1",
-        apiKeyUrl: "https://platform.openai.com/api-keys",
-        modelList: "openai",
     },
     anthropic: {
         label: "Anthropic",
         defaultBaseUrl: "https://api.anthropic.com/v1",
-        apiKeyUrl: "https://platform.claude.com/settings/keys",
-        modelList: "anthropic",
     },
     google: {
         label: "Google",
         defaultBaseUrl: "https://generativelanguage.googleapis.com/v1beta",
-        apiKeyUrl: "https://aistudio.google.com/apikey",
-        modelList: "google",
     },
     vertexai: { label: "Google Vertex AI" },
     azure: {
@@ -171,114 +146,77 @@ export const PROVIDER_INFO: Record<
     ollama: {
         label: "Ollama",
         defaultBaseUrl: "https://ollama.com/api",
-        apiKeyUrl: "https://ollama.com/settings/keys",
-        modelList: "ollama",
     },
     openrouter: {
         label: "OpenRouter",
         defaultBaseUrl: "https://openrouter.ai/api/v1",
-        apiKeyUrl: "https://openrouter.ai/keys",
-        modelList: "openrouter",
     },
     aihubmix: {
         label: "AIHubMix",
         defaultBaseUrl: "https://aihubmix.com/v1",
-        apiKeyUrl: "https://aihubmix.com/token",
-        modelList: "aihubmix",
     },
     deepseek: {
         label: "DeepSeek",
         defaultBaseUrl: "https://api.deepseek.com/v1",
-        apiKeyUrl: "https://platform.deepseek.com/api_keys",
-        modelList: "openai",
     },
     siliconflow: {
         label: "SiliconFlow",
         defaultBaseUrl: "https://api.siliconflow.cn/v1",
-        apiKeyUrl: "https://cloud.siliconflow.cn/account/ak",
-        modelList: "openai",
     },
     sglang: {
         label: "SGLang",
         defaultBaseUrl: "http://127.0.0.1:8000/v1",
-        modelList: "openai",
     },
     gateway: {
         label: "AI Gateway",
         defaultBaseUrl: "https://ai-gateway.vercel.sh/v1/ai",
-        apiKeyUrl: "https://vercel.com/ai-gateway",
-        modelList: "gateway",
     },
     edgeone: { label: "EdgeOne Pages" },
     doubao: {
         label: "Doubao (ByteDance)",
         defaultBaseUrl: "https://ark.cn-beijing.volces.com/api/v3",
-        apiKeyUrl:
-            "https://console.volcengine.com/ark/region:ark+cn-beijing/apiKey",
     },
     modelscope: {
         label: "ModelScope",
         defaultBaseUrl: "https://api-inference.modelscope.cn/v1",
-        apiKeyUrl: "https://modelscope.cn/my/myaccesstoken",
-        modelList: "openai",
     },
     glm: {
         label: "GLM (Zhipu)",
         defaultBaseUrl: "https://open.bigmodel.cn/api/paas/v4",
-        apiKeyUrl: "https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys",
-        modelList: "openai",
     },
     qwen: {
         label: "Qwen (Alibaba)",
         defaultBaseUrl: "https://dashscope.aliyuncs.com/compatible-mode/v1",
-        apiKeyUrl: "https://bailian.console.aliyun.com/?tab=model#/api-key",
-        modelList: "openai",
     },
     qiniu: {
         label: "Qiniu",
         defaultBaseUrl: "https://api.qnaigc.com/v1",
-        apiKeyUrl: "https://www.qiniu.com/ai/models",
-        modelList: "openai",
     },
     kimi: {
         label: "Kimi (Moonshot)",
         defaultBaseUrl: "https://api.moonshot.cn/v1",
-        apiKeyUrl: "https://platform.moonshot.cn/console/api-keys",
-        modelList: "openai",
     },
     minimax: {
         label: "MiniMax",
         defaultBaseUrl: "https://api.minimaxi.com/anthropic",
-        apiKeyUrl:
-            "https://platform.minimaxi.com/user-center/basic-information/interface-key",
     },
     novita: {
         label: "Novita AI",
         defaultBaseUrl: "https://api.novita.ai/openai",
-        apiKeyUrl: "https://novita.ai/dashboard/key",
-        modelList: "openai",
     },
     mimo: {
         label: "MiMo (Xiaomi)",
         defaultBaseUrl: "https://api.xiaomimimo.com/v1",
-        apiKeyUrl: "https://platform.xiaomimimo.com/#/console/api-keys",
-        modelList: "openai",
     },
     atlascloud: {
         label: "Atlas Cloud",
         defaultBaseUrl: "https://api.atlascloud.ai/v1",
-        apiKeyUrl: "https://www.atlascloud.ai/console/api-keys",
-        modelList: "openai",
     },
 }
 
 // Suggested models per provider for quick add
 export const SUGGESTED_MODELS: Partial<Record<ProviderName, string[]>> = {
     openai: [
-        "gpt-6.1-sol",
-        "gpt-6-sol",
-        "gpt-6-luna",
-        "gpt-6-astra",
         "gpt-5.5-pro",
         "gpt-5.5",
         "gpt-5.4-pro",
@@ -292,13 +230,7 @@ export const SUGGESTED_MODELS: Partial<Record<ProviderName, string[]>> = {
         "gpt-4o-mini",
     ],
     anthropic: [
-        // Claude 5 series (latest)
-        "claude-opus-5-5",
-        "claude-sonnet-5-5",
-        "claude-fable-5-1",
-        "claude-opus-5",
-        "claude-sonnet-5",
-        // Claude 4.8 / 4.7 / 4.6 series (dateless pinned IDs)
+        // Claude 4.8 / 4.7 / 4.6 series (latest, dateless pinned IDs)
         "claude-opus-4-8",
         "claude-sonnet-4-6",
         "claude-haiku-4-5",
@@ -347,47 +279,39 @@ export const SUGGESTED_MODELS: Partial<Record<ProviderName, string[]>> = {
         "o3",
         "o4-mini",
     ],
-    // Newer models only answer through an inference profile id (the region
-    // prefix). Each id here was called once on 2026-10-04.
     bedrock: [
-        // Anthropic Claude ("global." works from any region)
-        "global.anthropic.claude-opus-5-5",
-        "global.anthropic.claude-sonnet-5-5",
-        "global.anthropic.claude-fable-5-1",
-        "global.anthropic.claude-opus-5",
-        "global.anthropic.claude-sonnet-5",
-        "global.anthropic.claude-opus-4-8",
-        "global.anthropic.claude-opus-4-7",
-        "global.anthropic.claude-sonnet-4-6",
-        "global.anthropic.claude-opus-4-6-v1",
-        "global.anthropic.claude-opus-4-5-20251101-v1:0",
-        "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
-        "global.anthropic.claude-haiku-4-5-20251001-v1:0",
-        "global.anthropic.claude-sonnet-4-20250514-v1:0",
+        // Anthropic Claude
+        "anthropic.claude-opus-4-8",
+        "anthropic.claude-opus-4-7",
+        "anthropic.claude-sonnet-4-6",
+        "anthropic.claude-opus-4-6-v1",
+        "anthropic.claude-opus-4-5-20251101-v1:0",
+        "anthropic.claude-sonnet-4-5-20250929-v1:0",
+        "anthropic.claude-haiku-4-5-20251001-v1:0",
+        "anthropic.claude-opus-4-1-20250805-v1:0",
+        "anthropic.claude-opus-4-20250514-v1:0",
+        "anthropic.claude-sonnet-4-20250514-v1:0",
+        "anthropic.claude-3-5-haiku-20241022-v1:0",
         // Amazon Nova
-        "us.amazon.nova-2-lite-v1:0",
+        "amazon.nova-2-lite-v1:0",
+        "amazon.nova-premier-v1:0",
         "amazon.nova-pro-v1:0",
         "amazon.nova-lite-v1:0",
         "amazon.nova-micro-v1:0",
         // Meta Llama
-        "us.meta.llama4-maverick-17b-instruct-v1:0",
-        "us.meta.llama4-scout-17b-instruct-v1:0",
-        "us.meta.llama3-3-70b-instruct-v1:0",
+        "meta.llama4-maverick-17b-instruct-v1:0",
+        "meta.llama4-scout-17b-instruct-v1:0",
+        "meta.llama3-3-70b-instruct-v1:0",
         // Mistral
         "mistral.mistral-large-3-675b-instruct",
-        "us.mistral.pixtral-large-2502-v1:0",
+        "mistral.pixtral-large-2502-v1:0",
     ],
     openrouter: [
         // Anthropic
-        "anthropic/claude-opus-5.5",
-        "anthropic/claude-sonnet-5.5",
-        "anthropic/claude-fable-5.1",
         "anthropic/claude-opus-4.8",
         "anthropic/claude-sonnet-4.6",
         "anthropic/claude-haiku-4.5",
         // OpenAI
-        "openai/gpt-6.1-sol",
-        "openai/gpt-6-luna",
         "openai/gpt-5.5",
         "openai/gpt-5.4",
         "openai/gpt-5.4-mini",
@@ -476,10 +400,6 @@ export const SUGGESTED_MODELS: Partial<Record<ProviderName, string[]>> = {
         "default",
     ],
     gateway: [
-        "anthropic/claude-opus-5.5",
-        "anthropic/claude-sonnet-5.5",
-        "openai/gpt-6.1-sol",
-        "openai/gpt-6-luna",
         "openai/gpt-5.5",
         "anthropic/claude-opus-4.7",
         "google/gemini-3.1-pro-preview",
@@ -609,38 +529,3 @@ export function findModelById(
 ): FlattenedModel | undefined {
     return flattenModels(config).find((m) => m.id === modelId)
 }
-
-/**
- * A base URL the way the SDKs expect it: no spaces, no trailing slash, and
- * no endpoint path users often paste along (".../v1/chat/completions"),
- * which the SDK would append a second time.
- */
-export function normalizeBaseUrl(url: string): string {
-    return url
-        .trim()
-        .replace(/\/+$/, "")
-        .replace(/\/(?:chat\/completions|completions|messages|responses)$/, "")
-}
-
-/** Where a chat request goes for a base URL, or null when the SDK decides */
-export function chatRequestUrl(
-    provider: ProviderName,
-    baseUrl: string,
-): string | null {
-    const url = normalizeBaseUrl(baseUrl)
-    if (!url) return null
-    if (provider === "anthropic") return `${url}/messages`
-    // These SDKs build their own paths (or, for MiniMax, pick the protocol
-    // from the URL)
-    const ownPaths: ProviderName[] = [
-        "google",
-        "vertexai",
-        "azure",
-        "bedrock",
-        "ollama",
-        "gateway",
-        "minimax",
-        "edgeone",
-    ]
-    return ownPaths.includes(provider) ? null : `${url}/chat/completions`
-}

lib/url-utils.ts

@@ -1,6 +1,5 @@
 import { z } from "zod"
 import { getApiEndpoint } from "@/lib/base-path"
-import { STORAGE_KEYS } from "@/lib/storage"
 
 export interface UrlData {
     url: string
@@ -19,11 +18,7 @@ const UrlResponseSchema = z.object({
 export async function extractUrlContent(url: string): Promise<UrlData> {
     const response = await fetch(getApiEndpoint("/api/parse-url"), {
         method: "POST",
-        headers: {
-            "Content-Type": "application/json",
-            "x-access-code":
-                localStorage.getItem(STORAGE_KEYS.accessCode) || "",
-        },
+        headers: { "Content-Type": "application/json" },
         body: JSON.stringify({ url }),
     })
 

lib/use-file-processor.tsx

@@ -27,72 +27,78 @@ export function useFileProcessor() {
     const handleFileChange = async (newFiles: File[]) => {
         setFiles(newFiles)
 
-        const pending = newFiles.filter(
-            (file) =>
-                (isPdfFile(file) || isTextFile(file)) && !pdfData.has(file),
-        )
+        // Extract text immediately for new PDF/text files
+        for (const file of newFiles) {
+            const needsExtraction =
+                (isPdfFile(file) || isTextFile(file)) && !pdfData.has(file)
+            if (needsExtraction) {
+                // Mark as extracting
+                setPdfData((prev) => {
+                    const next = new Map(prev)
+                    next.set(file, {
+                        text: "",
+                        charCount: 0,
+                        isExtracting: true,
+                    })
+                    return next
+                })
 
-        // Before any await: drop data for removed files and mark every new
-        // file as extracting, so queued files also block sending
-        setPdfData((prev) => {
-            const next = new Map<File, FileData>()
-            for (const file of newFiles) {
-                const existing = prev.get(file)
-                if (existing) next.set(file, existing)
-            }
-            for (const file of pending) {
-                next.set(file, { text: "", charCount: 0, isExtracting: true })
-            }
-            return next
-        })
+                // Extract text asynchronously
+                try {
+                    let text: string
+                    if (isPdfFile(file)) {
+                        text = await extractPdfText(file)
+                    } else {
+                        text = await extractTextFileContent(file)
+                    }
 
-        // Extract one file at a time
-        for (const file of pending) {
-            try {
-                let text: string
-                if (isPdfFile(file)) {
-                    text = await extractPdfText(file)
-                } else {
-                    text = await extractTextFileContent(file)
-                }
+                    // Check character limit
+                    if (text.length > MAX_EXTRACTED_CHARS) {
+                        const limitK = MAX_EXTRACTED_CHARS / 1000
+                        toast.error(
+                            `${file.name}: Content exceeds ${limitK}k character limit (${(text.length / 1000).toFixed(1)}k chars)`,
+                        )
+                        setPdfData((prev) => {
+                            const next = new Map(prev)
+                            next.delete(file)
+                            return next
+                        })
+                        // Remove the file from the list
+                        setFiles((prev) => prev.filter((f) => f !== file))
+                        continue
+                    }
 
-                // Check character limit
-                if (text.length > MAX_EXTRACTED_CHARS) {
-                    const limitK = MAX_EXTRACTED_CHARS / 1000
-                    toast.error(
-                        `${file.name}: Content exceeds ${limitK}k character limit (${(text.length / 1000).toFixed(1)}k chars)`,
-                    )
+                    setPdfData((prev) => {
+                        const next = new Map(prev)
+                        next.set(file, {
+                            text,
+                            charCount: text.length,
+                            isExtracting: false,
+                        })
+                        return next
+                    })
+                } catch (error) {
+                    console.error("Failed to extract text:", error)
+                    toast.error(`Failed to read file: ${file.name}`)
                     setPdfData((prev) => {
                         const next = new Map(prev)
                         next.delete(file)
                         return next
                     })
-                    // Remove the file from the list
-                    setFiles((prev) => prev.filter((f) => f !== file))
-                    continue
                 }
-
-                setPdfData((prev) => {
-                    // The file was removed while extracting
-                    if (!prev.has(file)) return prev
-                    const next = new Map(prev)
-                    next.set(file, {
-                        text,
-                        charCount: text.length,
-                        isExtracting: false,
-                    })
-                    return next
-                })
-            } catch (error) {
-                console.error("Failed to extract text:", error)
-                toast.error(`Failed to read file: ${file.name}`)
-                setPdfData((prev) => {
-                    const next = new Map(prev)
-                    next.delete(file)
-                    return next
-                })
             }
         }
+
+        // Clean up pdfData for removed files
+        setPdfData((prev) => {
+            const next = new Map(prev)
+            for (const key of prev.keys()) {
+                if (!newFiles.includes(key)) {
+                    next.delete(key)
+                }
+            }
+            return next
+        })
     }
 
     return {

next.config.ts

@@ -10,11 +10,9 @@ const nextConfig: NextConfig = {
     env: {
         APP_VERSION: packageJson.version,
     },
-    // Include instrumentation.ts in standalone build for Langfuse telemetry,
-    // and the shape library docs get_shape_library reads at run time
+    // Include instrumentation.ts in standalone build for Langfuse telemetry
     outputFileTracingIncludes: {
         "*": ["./instrumentation.ts"],
-        "/api/chat": ["./docs/shape-libraries/*.md"],
     },
 }
 

package.json

@@ -31,26 +31,26 @@
         "test:e2e": "playwright test"
     },
     "dependencies": {
-        "@ai-sdk/amazon-bedrock": "^4.0.191",
-        "@ai-sdk/anthropic": "^3.0.127",
-        "@ai-sdk/azure": "^3.0.133",
-        "@ai-sdk/deepseek": "^2.0.71",
-        "@ai-sdk/google": "^3.0.130",
-        "@ai-sdk/google-vertex": "^4.0.210",
-        "@ai-sdk/openai": "^3.0.124",
-        "@ai-sdk/openai-compatible": "^2.0.81",
-        "@ai-sdk/react": "^3.0.303",
-        "@aihubmix/ai-sdk-provider": "^2.2.1",
+        "@ai-sdk/amazon-bedrock": "^4.0.1",
+        "@ai-sdk/anthropic": "^3.0.0",
+        "@ai-sdk/azure": "^3.0.0",
+        "@ai-sdk/deepseek": "^2.0.0",
+        "@ai-sdk/gateway": "^3.0.0",
+        "@ai-sdk/google": "^3.0.0",
+        "@ai-sdk/google-vertex": "^4.0.16",
+        "@ai-sdk/openai": "^3.0.0",
+        "@ai-sdk/react": "^3.0.1",
+        "@aihubmix/ai-sdk-provider": "^2.1.0",
         "@aws-sdk/client-dynamodb": "^3.957.0",
         "@aws-sdk/credential-providers": "^3.943.0",
-        "@extractus/article-extractor": "^8.0.18",
+        "@extractus/article-extractor": "^9.0.0",
         "@formatjs/intl-localematcher": "^0.9.0",
-        "@langfuse/client": "^4.4.9",
-        "@langfuse/otel": "^4.4.4",
-        "@langfuse/tracing": "^4.4.9",
+        "@langfuse/client": "^5.0.0",
+        "@langfuse/otel": "^5.0.0",
+        "@langfuse/tracing": "^5.0.0",
         "@next/third-parties": "^16.0.6",
         "@opennextjs/cloudflare": "^1.17.1",
-        "@openrouter/ai-sdk-provider": "^2.10.0",
+        "@openrouter/ai-sdk-provider": "^2.0.0",
         "@opentelemetry/api": "^1.9.0",
         "@opentelemetry/exporter-trace-otlp-http": "^0.222.0",
         "@opentelemetry/sdk-trace-node": "^2.2.0",
@@ -66,29 +66,28 @@
         "@radix-ui/react-tooltip": "^1.1.8",
         "@radix-ui/react-use-controllable-state": "^1.2.2",
         "@xmldom/xmldom": "^0.9.8",
-        "ai": "^6.0.300",
+        "ai": "^6.0.1",
         "base-64": "^1.0.0",
         "class-variance-authority": "^0.7.1",
         "clsx": "^2.1.1",
         "cmdk": "^1.1.1",
         "idb": "^8.0.3",
         "jsonrepair": "^3.13.1",
-        "lucide-react": "^0.577.0",
-        "motion": "^12.23.25",
-        "nanoid": "^5.0.0",
+        "lucide-react": "^1.0.0",
+        "motion": "^14.0.0",
+        "nanoid": "^6.0.0",
         "negotiator": "^1.0.0",
         "next": "^16.0.7",
-        "ollama-ai-provider-v2": "^3.6.0",
-        "pako": "^2.1.0",
+        "ollama-ai-provider-v2": "^3.0.0",
+        "pako": "^3.0.0",
         "prism-react-renderer": "^2.4.1",
         "react": "^19.1.2",
         "react-dom": "^19.1.2",
         "react-drawio": "^1.0.3",
         "react-icons": "^5.5.0",
         "react-markdown": "^10.1.0",
-        "react-resizable-panels": "^3.0.6",
+        "react-resizable-panels": "^4.0.0",
         "remark-gfm": "^4.0.1",
-        "saxes": "^6.0.0",
         "server-only": "^0.0.1",
         "sonner": "^2.0.7",
         "tailwind-merge": "^3.0.2",
@@ -119,27 +118,27 @@
         "@testing-library/user-event": "^14.6.1",
         "@types/negotiator": "^0.6.4",
         "@types/node": "^24.0.0",
-        "@types/pako": "^2.0.3",
+        "@types/pako": "^3.0.0",
         "@types/react": "^19",
         "@types/react-dom": "^19",
         "@types/turndown": "^5.0.6",
-        "@vitejs/plugin-react": "^5.1.2",
-        "@vitest/coverage-v8": "^4.0.16",
-        "concurrently": "^9.2.1",
+        "@vitejs/plugin-react": "^6.0.0",
+        "@vitest/coverage-v8": "^5.0.0",
+        "concurrently": "^10.0.0",
         "cross-env": "^10.1.0",
         "electron": "^39.2.7",
         "electron-builder": "^26.0.12",
         "esbuild": "^0.28.0",
-        "eslint": "9.39.5",
+        "eslint": "10.12.0",
         "eslint-config-next": "16.1.6",
         "husky": "^9.1.7",
-        "jsdom": "^27.4.0",
-        "lint-staged": "^16.2.7",
+        "jsdom": "^30.0.0",
+        "lint-staged": "^17.0.0",
         "shx": "^0.4.0",
         "tailwindcss": "^4",
-        "typescript": "^5",
+        "typescript": "^7.0.0",
         "vite-tsconfig-paths": "^6.0.3",
-        "vitest": "^4.0.16",
+        "vitest": "^5.0.0",
         "wait-on": "^9.0.3",
         "wrangler": "^4.60.0"
     },

packages/claude-plugin/README.md

@@ -25,13 +25,10 @@ claude mcp add drawio -- npx @next-ai-drawio/mcp-server@latest
 ## Features
 
 - **Real-time Preview**: Diagrams appear and update in your browser as Claude creates them
-- **Drawing Rules and Shape Libraries**: Claude gets the web app's layout and style rules and the icon docs for AWS, Azure, GCP, Kubernetes and more
-- **Self-check**: Claude can take a screenshot of the rendered diagram and fix what looks wrong
-- **Version History**: Restore one of the last 20 versions from the **History** button, shown as thumbnails
+- **Version History**: Restore previous diagram versions with visual thumbnails
 - **Natural Language**: Describe diagrams in plain text - flowcharts, architecture diagrams, etc.
-- **Edit Support**: Modify existing diagrams with natural language instructions, including your own edits in the browser
-- **Export**: Save diagrams as `.drawio`, `.png`, `.svg`, or `.drawio.svg` files
-- **Auto-save**: Each diagram is saved to `~/.next-ai-drawio/`, so `claude --resume` can pick it up again
+- **Edit Support**: Modify existing diagrams with natural language instructions
+- **Export**: Save diagrams as `.drawio` files
 - **Self-contained**: Embedded server, no external dependencies required
 
 ## Use Case Examples
@@ -75,16 +72,11 @@ between user, client app, auth server, and resource server
 
 | Tool | Description |
 |------|-------------|
-| `start_session` | Opens browser with real-time diagram preview; the result includes the drawing rules |
-| `get_drawing_guide` | Return the drawing rules again |
-| `get_shape_library` | Return the shapes and icon styles of a library such as `aws4` |
+| `start_session` | Opens browser with real-time diagram preview |
 | `create_new_diagram` | Create a new diagram from XML |
-| `load_diagram` | Load a `.drawio` file from disk |
-| `edit_diagram` | Edit diagram by ID-based operations; all or nothing |
+| `edit_diagram` | Edit diagram by ID-based operations |
 | `get_diagram` | Get the current diagram XML |
-| `screenshot_diagram` | Return a PNG of a page so Claude can check the result |
-| `export_diagram` | Save diagram to a `.drawio`, `.png`, `.svg`, or `.drawio.svg` file |
-| `list_pages`, `add_page`, `rename_page`, `delete_page` | Work with multi-page diagrams |
+| `export_diagram` | Save diagram to a `.drawio` file |
 
 ## How It Works
 
@@ -103,8 +95,6 @@ Claude Code <--stdio--> MCP Server <--http--> Browser (draw.io)
 |----------|---------|-------------|
 | `PORT` | `6002` | Port for the embedded HTTP server |
 | `DRAWIO_BASE_URL` | `https://embed.diagrams.net` | Base URL for draw.io (for self-hosted deployments) |
-| `DRAWIO_DATA_DIR` | `~/.next-ai-drawio` | Folder for auto-saved diagrams; `off` turns auto-save off |
-| `DEBUG` | unset | Set to `true` to log debug messages |
 
 ## Links
 

packages/mcp-server/README.md

@@ -104,41 +104,27 @@ Use the standard MCP configuration with:
 ## Features
 
 - **Real-time Preview**: Diagrams appear and update in your browser as the AI creates them
-- **Drawing Rules**: The AI gets the same layout, edge and style rules as the web app, plus the shape library docs (AWS, Azure, GCP, Kubernetes, Cisco and more), so it uses real icon names instead of guessing
-- **Self-check**: The AI can take a screenshot of the rendered diagram and fix overlapping shapes or edges that cross shapes
-- **Edit Support**: Modify existing diagrams with natural language instructions. If any change in an edit fails, nothing is written and the AI gets the reason and the current page XML
-- **Your Edits Are Kept**: Changes you make in the browser are read before the AI edits again. If the AI overwrites a change you were still making, your version is saved in History
-- **Version History**: Click **History** at the top right of the preview page to restore one of the last 20 versions, shown as thumbnails
-- **Download and Export**: Save as `.drawio`, `.png`, `.svg`, or `.drawio.svg` (an SVG with the diagram embedded, which draw.io can open and edit again), from the **Download** button or through `export_diagram`
-- **Multi-page**: List, add, rename, and delete pages, and edit any page
-- **Auto-save**: Each session's diagram is saved to `~/.next-ai-drawio/<session-id>.drawio`, so it survives a restart of the MCP client
-- **Themes and Dark Mode**: Pick a draw.io theme under **Extras > Theme**; the page follows the system dark mode
+- **Version History**: Restore previous diagram versions with visual thumbnails - click the clock button (bottom-right) to browse and restore earlier states
+- **Natural Language**: Describe diagrams in plain text - flowcharts, architecture diagrams, etc.
+- **Edit Support**: Modify existing diagrams with natural language instructions
+- **Export**: Save diagrams as `.drawio` files
 - **Self-contained**: Embedded server, works offline (except draw.io UI which loads from `embed.diagrams.net` by default, configurable via `DRAWIO_BASE_URL`)
 
 ## Available Tools
 
 | Tool | Description |
 |------|-------------|
-| `start_session` | Opens browser with real-time diagram preview; the result includes the drawing rules |
-| `get_drawing_guide` | Return the drawing rules again, for example after a long conversation was compacted |
-| `get_shape_library` | Return the shapes and icon styles of a library such as `aws4`, `azure2`, or `kubernetes` |
-| `create_new_diagram` | Create a new diagram from XML; a plain list of `mxCell` elements is enough |
+| `start_session` | Opens browser with real-time diagram preview |
+| `create_new_diagram` | Create a new diagram from XML (requires `xml` argument) |
 | `load_diagram` | Load a `.drawio` file from disk into the session (handles compressed files) |
-| `edit_diagram` | Edit diagram by ID-based operations (update/add/delete cells); all or nothing |
-| `get_diagram` | Get the current diagram XML, including your edits in the browser |
-| `screenshot_diagram` | Return a PNG of a page so the AI can check the rendered diagram |
-| `export_diagram` | Save diagram to a `.drawio`, `.png`, `.svg`, or `.drawio.svg` file |
+| `edit_diagram` | Edit diagram by ID-based operations (update/add/delete cells) |
+| `get_diagram` | Get the current diagram XML |
+| `export_diagram` | Save diagram to a `.drawio`, `.png`, or `.svg` file |
 | `list_pages` | List every page (tab) with id, name, index, and cell count |
 | `add_page` | Append a new page without touching existing ones |
 | `rename_page` | Rename a page |
 | `delete_page` | Delete a page (refuses to delete the last one) |
 
-## Continue a Diagram Later
-
-After every change, the diagram is saved as a normal `.drawio` file in `~/.next-ai-drawio/`, and `start_session` tells the AI the file path. When you resume a conversation after restarting your MCP client (for example `claude --resume`), the AI calls `start_session` and then `load_diagram` with that path. You can also open the file in draw.io yourself.
-
-The newest 50 files are kept. Set `DRAWIO_DATA_DIR` to use another folder, or to `off` to turn auto-save off.
-
 ## How It Works
 
 ```
@@ -168,8 +154,6 @@ The newest 50 files are kept. Set `DRAWIO_DATA_DIR` to use another folder, or to
 |----------|---------|-------------|
 | `PORT` | `6002` | Port for the embedded HTTP server |
 | `DRAWIO_BASE_URL` | `https://embed.diagrams.net` | Base URL for the draw.io embed. Set this to use a self-hosted draw.io instance for private deployments. |
-| `DRAWIO_DATA_DIR` | `~/.next-ai-drawio` | Folder for the auto-saved `.drawio` files. Set to `off` to turn auto-save off. |
-| `DEBUG` | unset | Set to `true` to log debug messages to stderr. |
 
 ### Private Deployment (Self-hosted draw.io)
 
@@ -195,7 +179,7 @@ You can deploy your own draw.io instance using the official Docker image:
 docker run -d -p 8080:8080 jgraph/drawio
 ```
 
-Then set `DRAWIO_BASE_URL=http://localhost:8080` (or your server's URL). The preview page loads nothing else from the internet, so with a local draw.io it works fully offline.
+Then set `DRAWIO_BASE_URL=http://localhost:8080` (or your server's URL).
 
 ## Troubleshooting
 
@@ -224,10 +208,6 @@ Call `start_session` first to open the browser window.
 
 Check that the browser URL has the `?mcp=` query parameter. The MCP session ID connects the browser to the server.
 
-### Screenshot or PNG/SVG export times out
-
-PNG and SVG files are rendered by draw.io in the preview tab. Browsers slow down tabs that stay in the background, so the tab may not answer in time. Bring the preview tab to the front and try again.
-
 ## License
 
 Apache-2.0

packages/mcp-server/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@next-ai-drawio/mcp-server",
-    "version": "0.3.0",
+    "version": "0.2.3",
     "description": "MCP server for Next AI Draw.io - AI-powered diagram generation with real-time browser preview",
     "type": "module",
     "main": "dist/index.js",
@@ -8,8 +8,7 @@
         "next-ai-drawio-mcp": "./dist/index.js"
     },
     "scripts": {
-        "build": "tsc && node scripts/copy-assets.mjs",
-        "check-package": "node scripts/check-package.mjs",
+        "build": "tsc",
         "dev": "tsx watch src/index.ts",
         "start": "node dist/index.js",
         "test": "vitest run",
@@ -39,19 +38,16 @@
         "access": "public"
     },
     "dependencies": {
-        "@modelcontextprotocol/sdk": "^1.31.0",
+        "@modelcontextprotocol/sdk": "^1.0.4",
         "linkedom": "^0.18.0",
         "open": "^11.0.0",
-        "pako": "^2.2.0",
-        "saxes": "^6.0.0",
         "zod": "^4.0.0"
     },
     "devDependencies": {
         "@types/node": "^24.0.0",
-        "@types/pako": "^2.0.4",
         "tsx": "^4.19.0",
-        "typescript": "^5",
-        "vitest": "^4.1.8"
+        "typescript": "^7.0.0",
+        "vitest": "^5.0.0"
     },
     "engines": {
         "node": ">=18"

packages/mcp-server/scripts/check-package.mjs

@@ -1,23 +0,0 @@
-// Fail if the npm package would miss files the server reads at runtime.
-// Tests run from src/ (tsx) and cannot notice a broken dist/ copy step.
-// Run after `npm run build`.
-import { execSync } from "node:child_process"
-
-const REQUIRED = [
-    "dist/index.js",
-    "dist/shape-libraries/aws4.md",
-    "dist/preview/index.html",
-    "dist/preview/preview.css",
-    "dist/preview/preview.js",
-]
-
-const [pack] = JSON.parse(
-    execSync("npm pack --dry-run --json", { encoding: "utf8" }),
-)
-const files = new Set(pack.files.map((f) => f.path))
-const missing = REQUIRED.filter((f) => !files.has(f))
-if (missing.length > 0) {
-    console.error(`npm package is missing: ${missing.join(", ")}`)
-    process.exit(1)
-}
-console.log(`npm package OK (${files.size} files)`)

packages/mcp-server/scripts/copy-assets.mjs

@@ -1,22 +0,0 @@
-// Copy non-TypeScript assets into dist/ after tsc, so they ship in the npm
-// package ("files": ["dist"]).
-import { cpSync, mkdirSync, readdirSync } from "node:fs"
-import { dirname, join } from "node:path"
-import { fileURLToPath } from "node:url"
-
-const pkg = join(dirname(fileURLToPath(import.meta.url)), "..")
-
-// Shape library docs live at the repository root, shared with the web app
-const libSrc = join(pkg, "../../docs/shape-libraries")
-const libDest = join(pkg, "dist/shape-libraries")
-mkdirSync(libDest, { recursive: true })
-for (const file of readdirSync(libSrc)) {
-    if (file.endsWith(".md") && file !== "README.md") {
-        cpSync(join(libSrc, file), join(libDest, file))
-    }
-}
-
-// Browser preview page (HTML, CSS and script)
-cpSync(join(pkg, "src/preview"), join(pkg, "dist/preview"), {
-    recursive: true,
-})

packages/mcp-server/src/diagram-operations.ts

@@ -7,10 +7,7 @@
  * first page is targeted (the "active page by convention" — see pages.ts).
  */
 
-import { decompressPageContent } from "./load-diagram.ts"
-import { log } from "./logger.ts"
-import { findPageElement, hasPageSelector, type PageSelector } from "./pages.ts"
-import { getXmlSyntaxError } from "./xml-syntax.ts"
+import { findPageElement, hasPageSelector, type PageSelector } from "./pages.js"
 
 export interface DiagramOperation {
     operation: "update" | "add" | "delete"
@@ -29,56 +26,6 @@ export interface ApplyOperationsResult {
     errors: OperationError[]
 }
 
-// Cells with links, tooltips or custom data are stored as
-// <UserObject id="..."><mxCell .../></UserObject> (or <object>): the id sits
-// on the wrapper, so the wrapper is treated as the cell.
-const CELL_SELECTOR = "mxCell, UserObject, object"
-
-/**
- * Return the <root> of a <diagram> page, creating it when missing. An empty
- * page gets a blank model with the "0" and "1" root cells; a page whose text
- * is draw.io's compressed format is decompressed in place. Returns null if
- * the text is neither empty nor decompressible.
- */
-function ensurePageRoot(doc: Document, page: Element): Element | null {
-    const existing = page.querySelector("root")
-    if (existing) return existing
-
-    let model = page.querySelector("mxGraphModel")
-    if (!model) {
-        const text = page.textContent?.trim() ?? ""
-        if (text) {
-            const xml = decompressPageContent(text)
-            if (!xml || getXmlSyntaxError(xml)) return null
-            const parsed = new DOMParser().parseFromString(xml, "text/xml")
-            if (parsed.documentElement?.tagName !== "mxGraphModel") return null
-            page.textContent = ""
-            model = page.appendChild(
-                doc.importNode(parsed.documentElement, true),
-            ) as Element
-            const decompressedRoot = model.querySelector("root")
-            if (decompressedRoot) return decompressedRoot
-        } else {
-            model = page.appendChild(doc.createElement("mxGraphModel"))
-        }
-    }
-
-    const blank = new DOMParser().parseFromString(
-        `<root><mxCell id="0"/><mxCell id="1" parent="0"/></root>`,
-        "text/xml",
-    )
-    return model.appendChild(
-        doc.importNode(blank.documentElement, true),
-    ) as Element
-}
-
-/** Read parent/source/target, which a wrapped cell keeps on its inner mxCell. */
-function cellAttr(cell: Element, name: string): string | null {
-    const inner =
-        cell.tagName === "mxCell" ? cell : cell.querySelector("mxCell")
-    return inner?.getAttribute(name) ?? null
-}
-
 /**
  * Apply diagram operations (update/add/delete) using ID-based lookup.
  *
@@ -96,8 +43,12 @@ export function applyDiagramOperations(
 ): ApplyOperationsResult {
     const errors: OperationError[] = []
 
-    // Check for syntax errors, then parse the XML
-    const parseError = getXmlSyntaxError(xmlContent)
+    // Parse the XML
+    const parser = new DOMParser()
+    const doc = parser.parseFromString(xmlContent, "text/xml")
+
+    // Check for parse errors
+    const parseError = doc.querySelector("parsererror")
     if (parseError) {
         return {
             result: xmlContent,
@@ -105,13 +56,11 @@ export function applyDiagramOperations(
                 {
                     type: "update",
                     cellId: "",
-                    message: `XML parse error: ${parseError}`,
+                    message: `XML parse error: ${parseError.textContent}`,
                 },
             ],
         }
     }
-    const parser = new DOMParser()
-    const doc = parser.parseFromString(xmlContent, "text/xml")
 
     // Locate the <root> element to operate on.
     //
@@ -137,7 +86,7 @@ export function applyDiagramOperations(
                 ],
             }
         }
-        root = ensurePageRoot(doc as unknown as Document, found.element)
+        root = found.element.querySelector("root")
         if (!root) {
             const pageId =
                 found.element.getAttribute("id") || `(index ${found.index})`
@@ -147,7 +96,7 @@ export function applyDiagramOperations(
                     {
                         type: "update",
                         cellId: "",
-                        message: `Page "${pageId}" has no <root> element and its content could not be decompressed`,
+                        message: `Page "${pageId}" has no <root> element`,
                     },
                 ],
             }
@@ -183,16 +132,10 @@ export function applyDiagramOperations(
 
     // Build a map of cell IDs to elements (scoped to the resolved page).
     const cellMap = new Map<string, Element>()
-    root.querySelectorAll(CELL_SELECTOR).forEach((cell) => {
+    root.querySelectorAll("mxCell").forEach((cell) => {
         const id = cell.getAttribute("id")
-        // A wrapped mxCell may repeat its wrapper's id; the wrapper is the cell
-        const wrapped =
-            cell.tagName === "mxCell" &&
-            /^(UserObject|object)$/.test(cell.parentElement?.tagName ?? "")
-        if (id && !wrapped) cellMap.set(id, cell)
+        if (id) cellMap.set(id, cell)
     })
-    // Ids deleted so far in this batch; deleting one again is a no-op
-    const deletedIds = new Set<string>()
 
     // Process each operation
     for (const op of operations) {
@@ -221,7 +164,7 @@ export function applyDiagramOperations(
                 `<wrapper>${op.new_xml}</wrapper>`,
                 "text/xml",
             )
-            const newCell = newDoc.querySelector(CELL_SELECTOR)
+            const newCell = newDoc.querySelector("mxCell")
             if (!newCell) {
                 errors.push({
                     type: "update",
@@ -273,7 +216,7 @@ export function applyDiagramOperations(
                 `<wrapper>${op.new_xml}</wrapper>`,
                 "text/xml",
             )
-            const newCell = newDoc.querySelector(CELL_SELECTOR)
+            const newCell = newDoc.querySelector("mxCell")
             if (!newCell) {
                 errors.push({
                     type: "add",
@@ -313,15 +256,8 @@ export function applyDiagramOperations(
 
             const existingCell = cellMap.get(op.cell_id)
             if (!existingCell) {
-                // Skip cells already cascade-deleted by a previous operation
-                // (AI may redundantly list children/edges); warn otherwise
-                if (!deletedIds.has(op.cell_id)) {
-                    errors.push({
-                        type: "delete",
-                        cellId: op.cell_id,
-                        message: `Cell with id="${op.cell_id}" not found`,
-                    })
-                }
+                // Cell not found - might have been cascade-deleted by a previous operation
+                // Skip silently instead of erroring (AI may redundantly list children/edges)
                 continue
             }
 
@@ -334,17 +270,17 @@ export function applyDiagramOperations(
                 cellsToDelete.add(cellId)
 
                 // Find children (cells where parent === cellId)
-                // cellMap only holds this page's cells, so other pages' cells
-                // with the same parent id (notably "1") are never touched.
-                for (const [childId, child] of cellMap) {
-                    if (
-                        childId !== "0" &&
-                        childId !== "1" &&
-                        cellAttr(child, "parent") === cellId
-                    ) {
+                // Scoped to `root` so other pages' cells with the same parent id
+                // (notably "1") are never touched.
+                const children = root!.querySelectorAll(
+                    `mxCell[parent="${cellId}"]`,
+                )
+                children.forEach((child) => {
+                    const childId = child.getAttribute("id")
+                    if (childId && childId !== "0" && childId !== "1") {
                         collectDescendants(childId)
                     }
-                }
+                })
             }
 
             // Collect the target cell and all its descendants
@@ -353,23 +289,23 @@ export function applyDiagramOperations(
             // Find edges referencing any of the cells to be deleted
             // Also recursively collect children of those edges (e.g., edge labels)
             for (const cellId of cellsToDelete) {
-                for (const [edgeId, edge] of cellMap) {
+                const referencingEdges = root.querySelectorAll(
+                    `mxCell[source="${cellId}"], mxCell[target="${cellId}"]`,
+                )
+                referencingEdges.forEach((edge) => {
+                    const edgeId = edge.getAttribute("id")
                     // Protect root cells from being added via edge references
-                    if (edgeId === "0" || edgeId === "1") continue
-                    if (
-                        cellAttr(edge, "source") === cellId ||
-                        cellAttr(edge, "target") === cellId
-                    ) {
+                    if (edgeId && edgeId !== "0" && edgeId !== "1") {
                         // Recurse to collect edge's children (like labels)
                         collectDescendants(edgeId)
                     }
-                }
+                })
             }
 
-            // Log what will be deleted (stderr: stdout carries JSON-RPC)
+            // Log what will be deleted
             if (cellsToDelete.size > 1) {
-                log.debug(
-                    `Cascade delete "${op.cell_id}" → deleting ${cellsToDelete.size} cells: ${Array.from(cellsToDelete).join(", ")}`,
+                console.log(
+                    `[applyDiagramOperations] Cascade delete "${op.cell_id}" → deleting ${cellsToDelete.size} cells: ${Array.from(cellsToDelete).join(", ")}`,
                 )
             }
 
@@ -380,7 +316,6 @@ export function applyDiagramOperations(
                     cell.parentNode?.removeChild(cell)
                     cellMap.delete(cellId)
                 }
-                deletedIds.add(cellId)
             }
         }
     }

packages/mcp-server/src/dom.ts

@@ -1,73 +0,0 @@
-/**
- * DOM setup for Node. The XML helpers use the global DOMParser and
- * XMLSerializer, which the browser has and Node gets from here.
- *
- * linkedom gives us a DOM with querySelector, but it is lenient: it never
- * reports syntax errors (no <parsererror>; xml-syntax.ts checks them), and
- * its serializer writes raw newlines inside attribute values, which the
- * browser reads back as spaces. serializeXml writes attribute values safely.
- */
-import { DOMParser } from "linkedom"
-
-const ESCAPES: Record<string, string> = {
-    "&": "&amp;",
-    "<": "&lt;",
-    ">": "&gt;",
-    '"': "&quot;",
-    "\t": "&#9;",
-    "\n": "&#xa;",
-    "\r": "&#xd;",
-}
-const escapeChars = (text: string, chars: RegExp) =>
-    text.replace(chars, (c) => ESCAPES[c])
-
-/**
- * Serialize a linkedom node as XML. Attribute values escape tabs and line
- * breaks too, so multi-line labels (value="a&#xa;b") survive a round trip.
- */
-export function serializeXml(node: Node): string {
-    switch (node.nodeType) {
-        case 9: {
-            // Document
-            const root = (node as Document).documentElement
-            return root ? serializeXml(root) : ""
-        }
-        case 1: {
-            // Element
-            const el = node as Element
-            let out = `<${el.tagName}`
-            for (const attr of Array.from(el.attributes)) {
-                out += ` ${attr.name}="${escapeChars(attr.value, /[&<>"\t\n\r]/g)}"`
-            }
-            if (el.childNodes.length === 0) return `${out}/>`
-            out += ">"
-            for (const child of Array.from(el.childNodes)) {
-                out += serializeXml(child)
-            }
-            return `${out}</${el.tagName}>`
-        }
-        case 3:
-            // Text
-            return escapeChars(node.textContent ?? "", /[&<>]/g)
-        case 4:
-            // CDATA
-            return `<![CDATA[${node.textContent ?? ""}]]>`
-        case 8:
-            // Comment
-            return `<!--${node.textContent ?? ""}-->`
-        default:
-            return ""
-    }
-}
-
-class XMLSerializerPolyfill {
-    serializeToString(node: Node): string {
-        return serializeXml(node)
-    }
-}
-
-/** Install the DOMParser and XMLSerializer globals the XML helpers use. */
-export function installDomPolyfill(): void {
-    ;(globalThis as any).DOMParser = DOMParser
-    ;(globalThis as any).XMLSerializer = XMLSerializerPolyfill
-}

packages/mcp-server/src/drawing-guide.ts

@@ -1,107 +0,0 @@
-/**
- * Drawing guide for the model, returned by start_session, get_drawing_guide
- * and the diagram-workflow prompt.
- *
- * Adapted from the web app's system prompt (lib/system-prompts.ts) and its
- * tool descriptions (app/api/chat/route.ts). When drawing rules change there,
- * update this file too.
- */
-
-import {
-    indent,
-    SWIMLANE_EXAMPLE,
-    TWO_EDGES_EXAMPLE,
-    WAYPOINT_EXAMPLE,
-} from "./xml-examples.ts"
-
-export const DRAWING_GUIDE = `# Draw.io drawing guide
-
-## Workflow
-- create_new_diagram draws a new diagram and REPLACES the whole document. add_page adds another tab. edit_diagram changes cells of an existing page. load_diagram opens a .drawio file (the server reads the file itself). get_diagram returns the current XML, including the user's manual edits. export_diagram saves to a file.
-- Before drawing, describe your layout plan in 2-3 sentences, so shapes do not overlap and edges do not cross shapes.
-- Send XML only through tool calls, never in chat text. Never draw a box just to send the user a message.
-- Before using any icon library (AWS, Azure, GCP, Kubernetes, Cisco, BPMN, Material Design, web icons...), call get_shape_library and use the exact style names it returns. NEVER guess icon style names. For AWS, use the AWS 2025 icons (library aws4).
-- After drawing or heavily editing a complex diagram, call screenshot_diagram once to see the result, and fix overlapping shapes and edges that cross shapes.
-- When replicating a diagram from an image, match its style and layout closely: straight or curved lines, rounded or square shapes.
-- The preview page has History (it saves a snapshot before every AI change and can restore any of the last 20 versions) and Download. You can make changes freely; nothing is lost.
-
-## The XML you send
-Single page (create_new_diagram, add_page): send ONLY the mxCell elements. The server adds <mxfile>, <mxGraphModel>, <root> and the root cells id="0" and id="1".
-
-    <mxCell id="2" value="Label" style="rounded=1;whiteSpace=wrap;html=1;" vertex="1" parent="1">
-      <mxGeometry x="100" y="100" width="120" height="60" as="geometry"/>
-    </mxCell>
-    <mxCell id="3" style="edgeStyle=orthogonalEdgeStyle;exitX=1;exitY=0.5;entryX=0;entryY=0.5;endArrow=classic;html=1;" edge="1" parent="1" source="2" target="4">
-      <mxGeometry relative="1" as="geometry"/>
-    </mxCell>
-
-Several pages at once (create_new_diagram only): send a full <mxfile> with one <diagram id="..." name="..."> per page. Every page's <root> must start with <mxCell id="0"/><mxCell id="1" parent="0"/>.
-
-Rules (XML that breaks them is rejected):
-1. All mxCell elements are siblings. NEVER nest an mxCell inside another mxCell.
-2. Ids are unique within a page and start from "2" ("0" and "1" are the root cells).
-3. parent="1" for top-level shapes, parent="<container id>" for shapes inside a container.
-4. Edge source and target must reference existing cell ids.
-5. Escape special characters in attribute values: &lt; for <, &gt; for >, &amp; for &, &quot; for ".
-6. NEVER include XML comments (<!-- -->). draw.io strips them.
-7. In tool arguments (JSON), every " inside the XML must be escaped as \\".
-
-Containers and swimlanes: children use the container id as parent and coordinates relative to the container.
-
-${indent(SWIMLANE_EXAMPLE)}
-
-## Layout
-- Keep every element of a page within x 0 to 800 and y 0 to 600, so the whole diagram fits one view without a page break.
-- Containers (for example AWS cloud boxes) are at most 700 pixels wide and 550 pixels tall.
-- Start near x=40, y=40 and keep elements grouped closely.
-- For large diagrams, stack vertically or use a grid instead of spreading wide.
-
-## Edge routing rules
-Rule 1: Never let two edges share a path. Two edges between the same nodes exit and enter at different points (exitY=0.3 for the first, exitY=0.7 for the second, not both 0.5).
-Rule 2: For bidirectional connections (A to B and B to A), use opposite sides: A exits right (exitX=1) into the left of B (entryX=0); B exits left (exitX=0) into the right of A (entryX=1).
-Rule 3: Always set exitX, exitY, entryX and entryY in the edge style, e.g. style="edgeStyle=orthogonalEdgeStyle;exitX=1;exitY=0.3;entryX=0;entryY=0.3;endArrow=classic;".
-Rule 4: Route edges AROUND shapes in the way. Before drawing an edge, find every shape between source and target; if one is in the path, add waypoints. Route diagonal connections along the outside of the diagram, not through the middle. Keep 20-30px clearance from shapes. An edge must never cross another shape's box.
-Rule 5: Plan the layout first. Organize shapes into rows or columns following the flow, space them 150-200px apart so edges have room, and prefer one flow direction (left to right or top to bottom).
-Rule 6: Use 2-3 waypoints for L-shaped or U-shaped paths. Each change of direction needs a waypoint, and segments should be horizontal or vertical.
-Rule 7: Use natural connection points. Never connect at corners (both X and Y 0 or 1). Top-to-bottom flow: exitY=1 into entryY=0. Left-to-right flow: exitX=1 into entryX=0. Diagonal: the side closest to the target.
-
-Before sending XML, check:
-1. Does any edge cross a shape that is not its source or target? Add waypoints.
-2. Do two edges share a path? Change their exit or entry points.
-3. Is any connection point at a corner? Use the middle of a side.
-4. Could moving shapes remove edge crossings? Revise the layout.
-
-Two edges between the same nodes:
-
-${indent(TWO_EDGES_EXAMPLE)}
-
-Waypoints go inside <Array as="points"> in the edge geometry. Example: Hotfix (right, bottom) connects to Main (center, top) while Develop (center, middle) is in between, so the edge goes right to x=750 first, then up, and enters Main from the right:
-
-${indent(WAYPOINT_EXAMPLE)}
-
-## Styles
-- Shapes: rounded=1, fillColor=#hex, strokeColor=#hex, whiteSpace=wrap;html=1;
-- Edges: endArrow=classic, block, open or none; startArrow=none or classic; curved=1; edgeStyle=orthogonalEdgeStyle
-- Text: fontSize=14, fontStyle=1 (bold), align=center, left or right
-- Animated connectors: add flowAnimation=1 to the edge style.
-
-## Minimal style
-When the user asks for a minimal, plain, black-and-white or unstyled diagram, use these rules instead of the styles above:
-- No fillColor, strokeColor, rounded, fontSize, fontStyle or hex colors.
-- Shapes use style "whiteSpace=wrap;html=1;", edges use "html=1;endArrow=classic;".
-- Containers that hold other shapes use "whiteSpace=wrap;html=1;fillColor=none;" so they do not cover their children.
-- Keep at least 50px between elements, and follow all edge routing rules strictly.
-
-## Editing with edit_diagram
-- update replaces a cell: send the complete mxCell including mxGeometry, with the same id as cell_id.
-- add inserts a new cell with a new id. One cell per operation.
-- delete removes a cell. Its children and every edge connected to it are deleted too, so give only the container's id.
-- All-or-nothing: if any operation fails, nothing is applied. A rejected call includes the current XML of the page; rebuild your operations on it and retry.
-- If the diagram is large, change it with edit_diagram instead of redrawing it.
-
-    {"operations": [{"operation": "update", "cell_id": "3", "new_xml": "<mxCell id=\\"3\\" value=\\"New Label\\" style=\\"rounded=1;\\" vertex=\\"1\\" parent=\\"1\\"><mxGeometry x=\\"100\\" y=\\"100\\" width=\\"120\\" height=\\"60\\" as=\\"geometry\\"/></mxCell>"}]}
-    {"page_name": "CNN", "operations": [{"operation": "add", "cell_id": "conv-1", "new_xml": "<mxCell id=\\"conv-1\\" value=\\"Conv\\" vertex=\\"1\\" parent=\\"1\\"><mxGeometry x=\\"40\\" y=\\"40\\" width=\\"120\\" height=\\"60\\" as=\\"geometry\\"/></mxCell>"}]}
-    {"page_index": 1, "operations": [{"operation": "delete", "cell_id": "5"}]}
-
-Pages: list_pages shows every page's id, name and index. edit_diagram, get_diagram and export_diagram take an optional page_id, page_name or page_index; without one they use the first page.
-`

packages/mcp-server/src/edit-diagram.ts

@@ -1,109 +0,0 @@
-/**
- * Core of the edit_diagram tool, kept free of session state so it can be
- * unit tested.
- *
- * All-or-nothing, like the web app (hooks/use-diagram-tool-handlers.ts):
- * if any operation fails, nothing is written and every failure is reported,
- * so the model never builds on a half-applied edit.
- */
-
-import {
-    applyDiagramOperations,
-    type DiagramOperation,
-} from "./diagram-operations.ts"
-import { type PageSelector, projectPage } from "./pages.ts"
-import { validateAndFixXml, validateMxCellStructure } from "./xml-validation.ts"
-
-export type EditOutcome =
-    | { ok: true; xml: string; applied: number; fixes: string[] }
-    | { ok: false; errors: string[]; pageError: boolean }
-
-/** Number of top-level elements in an XML fragment. */
-function countTopLevelElements(fragment: string): number {
-    const doc = new DOMParser().parseFromString(
-        `<wrapper>${fragment}</wrapper>`,
-        "text/xml",
-    )
-    // On a syntax error the browser adds a <parsererror> element (Chrome
-    // next to the cells, Firefox as the root); the syntax is checked later
-    const root = doc.documentElement
-    if (!root || root.tagName === "parsererror") return 1
-    return Array.from(root.children).filter(
-        (el) => el.tagName !== "parsererror",
-    ).length
-}
-
-/** The target page as a one-page <mxfile>, or the whole document. */
-export function targetPageXml(xml: string, selector: PageSelector): string {
-    const projection = projectPage(xml, selector)
-    return projection.ok ? projection.xml : xml
-}
-
-export function editDiagram(
-    xml: string,
-    operations: DiagramOperation[],
-    selector: PageSelector,
-): EditOutcome {
-    const errors: string[] = []
-    const fixes: string[] = []
-    const prepared: DiagramOperation[] = []
-
-    for (const op of operations) {
-        if (op.operation === "delete" || !op.new_xml) {
-            prepared.push(op)
-            continue
-        }
-        // Checked before validation: several cells fail the strict parser
-        // with a misleading "only one root" syntax error.
-        if (countTopLevelElements(op.new_xml) > 1) {
-            errors.push(
-                `${op.operation} ${op.cell_id}: new_xml must contain exactly one cell; use one add operation per cell`,
-            )
-            continue
-        }
-        const check = validateAndFixXml(op.new_xml)
-        if (!check.valid) {
-            errors.push(
-                `${op.operation} ${op.cell_id}: invalid new_xml: ${check.error}`,
-            )
-            continue
-        }
-        if (check.fixed) {
-            fixes.push(`${op.cell_id}: ${check.fixes.join(", ")}`)
-        }
-        prepared.push({ ...op, new_xml: check.fixed ?? op.new_xml })
-    }
-    if (errors.length > 0) return { ok: false, errors, pageError: false }
-
-    const { result, errors: opErrors } = applyDiagramOperations(
-        xml,
-        prepared,
-        selector,
-    )
-    // An empty cellId means the page itself could not be edited
-    const pageLevel = opErrors.find((e) => e.cellId === "")
-    if (pageLevel) {
-        return { ok: false, errors: [pageLevel.message], pageError: true }
-    }
-    if (opErrors.length > 0) {
-        return {
-            ok: false,
-            errors: opErrors.map((e) => `${e.type} ${e.cellId}: ${e.message}`),
-            pageError: false,
-        }
-    }
-
-    // Validate only the target page, and reject only errors this edit
-    // introduced: problems already in other pages or in a loaded file must
-    // not block every edit.
-    const after = validateMxCellStructure(targetPageXml(result, selector))
-    if (after && !validateMxCellStructure(targetPageXml(xml, selector))) {
-        return {
-            ok: false,
-            errors: [`the edit would make the page invalid: ${after}`],
-            pageError: false,
-        }
-    }
-
-    return { ok: true, xml: result, applied: operations.length, fixes }
-}

packages/mcp-server/src/edit-gate.ts

@@ -17,7 +17,7 @@
  * change: the set of pages, each page's name, and each page's cell tree
  * (tags + sorted attributes + text). Byte equality is kept as a fast path.
  */
-import { isMxGraphModel, normalizeToMxfile, parseMxfile } from "./pages.ts"
+import { isMxGraphModel, normalizeToMxfile, parseMxfile } from "./pages.js"
 
 export type EditGateResult =
     | { ok: true }