fix: align get_shape_library guidance for non-cloud icon libraries

Add Google Material Design Icons as a new shape library using Google's
CDN. Includes top 300 most popular icons by usage, and updates system
prompts to guide the AI to call get_shape_library before using any icon
library.

.github/CONTRIBUTING.md

@@ -47,10 +47,6 @@ To run tests with UI mode:
 npx playwright test --ui
 ```
 
-## Before You Start
-
-For **significant changes** (new features, architecture changes, large refactors, etc.), please **open an issue first** to discuss your proposal before writing code. This helps avoid wasted effort and ensures alignment with the project direction. Small bug fixes and minor improvements can go straight to a PR.
-
 ## Pull Requests
 
 1. Create a feature branch
@@ -61,12 +57,6 @@ For **significant changes** (new features, architecture changes, large refactors
 
 CI will run the full test suite on your PR.
 
-## Code Review
-
-This project uses GitHub Copilot for automated code review. If you receive review comments from Copilot on your PR:
-- **Valid suggestions**: Please address them in your code.
-- **Invalid or irrelevant suggestions**: Feel free to click "Resolve" to dismiss them.
-
 ## Issues
 
 Include steps to reproduce, expected vs actual behavior, and AI provider used.

.github/workflows/ci.yml

@@ -40,3 +40,5 @@ jobs:
       - name: Build
         run: npm run build
 
+      - name: Security audit
+        run: npm audit --audit-level=high --omit=dev

.gitignore

@@ -72,6 +72,3 @@ CLAUDE.md
 .edgeone
 opencode.json
 ai-models.json
-
-# local backups
-*.bak

Dockerfile

@@ -9,7 +9,6 @@ WORKDIR /app
 COPY package.json package-lock.json* ./
 
 # Install dependencies
-ARG ELECTRON_SKIP_BINARY_DOWNLOAD=1
 RUN npm install
 
 # Stage 2: Build application
@@ -35,11 +34,6 @@ ENV NEXT_PUBLIC_SHOW_ABOUT_AND_NOTICE=${NEXT_PUBLIC_SHOW_ABOUT_AND_NOTICE}
 ARG NEXT_PUBLIC_BASE_PATH=""
 ENV NEXT_PUBLIC_BASE_PATH=${NEXT_PUBLIC_BASE_PATH}
 
-# Control sponsorship and self-hosting messaging in quota notifications.
-# Set NEXT_PUBLIC_SELFHOSTED="true" in self-hosted deployments to hide sponsorship/self-host links and related text in quota popups.
-ARG NEXT_PUBLIC_SELFHOSTED=""
-ENV NEXT_PUBLIC_SELFHOSTED="${NEXT_PUBLIC_SELFHOSTED}"
-
 # Build Next.js application (standalone mode)
 RUN npm run build
 

README.md

@@ -19,7 +19,7 @@ English | [中文](./docs/cn/README_CN.md) | [日本語](./docs/ja/README_JA.md)
 
 A Next.js web application that integrates AI capabilities with draw.io diagrams. Create, modify, and enhance diagrams through natural language commands and AI-assisted visualization.
 
-> Note: Thanks to <img src="https://raw.githubusercontent.com/DayuanJiang/next-ai-draw-io/main/public/doubao-color.png" alt="" height="20" /> [ByteDance Doubao](https://www.volcengine.com/activity/codingplan?ac=MMAP8JTTCAQ2&rc=Z9Z3LDTJ&utm_campaign=drawio&utm_content=drawio&utm_medium=devrel&utm_source=OWO&utm_term=drawio) sponsorship, the demo site now uses the powerful glm-4.7 model!
+> Note: Thanks to <img src="https://raw.githubusercontent.com/DayuanJiang/next-ai-draw-io/main/public/doubao-color.png" alt="" height="20" /> [ByteDance Doubao](https://www.volcengine.com/activity/newyear-referral?utm_campaign=doubao&utm_content=aidrawio&utm_medium=github&utm_source=coopensrc&utm_term=project) sponsorship, the demo site now uses the powerful K2-thinking model!
 
 
 https://github.com/user-attachments/assets/9d60a3e8-4a1c-4b5e-acbb-26af2d3eabd1
@@ -202,7 +202,7 @@ See the [Next.js deployment documentation](https://nextjs.org/docs/app/building-
 
 ## Multi-Provider Support
 
--   [ByteDance Doubao](https://www.volcengine.com/activity/codingplan?ac=MMAP8JTTCAQ2&rc=Z9Z3LDTJ&utm_campaign=drawio&utm_content=drawio&utm_medium=devrel&utm_source=OWO&utm_term=drawio)
+-   [ByteDance Doubao](https://www.volcengine.com/activity/newyear-referral?utm_campaign=doubao&utm_content=aidrawio&utm_medium=github&utm_source=coopensrc&utm_term=project)
 -   AWS Bedrock (default)
 -   OpenAI
 -   Anthropic
@@ -244,7 +244,7 @@ Diagrams are represented as XML that can be rendered in draw.io. The AI processe
 
 ## Support & Contact
 
-**Special thanks to [ByteDance Doubao](https://www.volcengine.com/activity/codingplan?ac=MMAP8JTTCAQ2&rc=Z9Z3LDTJ&utm_campaign=drawio&utm_content=drawio&utm_medium=devrel&utm_source=OWO&utm_term=drawio) for sponsoring the API token usage of the demo site!** Register on the ARK platform to get 500K free tokens for all models!
+**Special thanks to [ByteDance Doubao](https://www.volcengine.com/activity/newyear-referral?utm_campaign=doubao&utm_content=aidrawio&utm_medium=github&utm_source=coopensrc&utm_term=project) for sponsoring the API token usage of the demo site!** Register on the ARK platform to get 500K free tokens for all models!
 
 If you find this project useful, please consider [sponsoring](https://github.com/sponsors/DayuanJiang) to help me host the live demo site!
 

app/[lang]/about/cn/page.tsx

@@ -78,7 +78,7 @@ export default function AboutCN() {
                                 <p>
                                     好消息！感谢{" "}
                                     <a
-                                        href="https://www.volcengine.com/activity/codingplan?ac=MMAP8JTTCAQ2&rc=Z9Z3LDTJ&utm_campaign=drawio&utm_content=drawio&utm_medium=devrel&utm_source=OWO&utm_term=drawio"
+                                        href="https://www.volcengine.com/activity/newyear-referral?utm_campaign=doubao&utm_content=aidrawio&utm_medium=github&utm_source=coopensrc&utm_term=project"
                                         target="_blank"
                                         rel="noopener noreferrer"
                                         className="font-semibold text-blue-600 hover:underline"
@@ -87,7 +87,7 @@ export default function AboutCN() {
                                     </a>
                                     的慷慨赞助，演示站点现已接入强大的{" "}
                                     <span className="font-semibold text-amber-700">
-                                        glm-4.7
+                                        K2-thinking
                                     </span>{" "}
                                     模型，图表生成效果更佳！点击链接注册即可领取{" "}
                                     <span className="font-semibold text-amber-700">
@@ -97,23 +97,6 @@ export default function AboutCN() {
                                 </p>
                             </div>
 
-                            {/* Invite Poster */}
-                            <div className="text-center mb-5">
-                                <a
-                                    href="https://www.volcengine.com/activity/codingplan?ac=MMAP8JTTCAQ2&rc=Z9Z3LDTJ&utm_campaign=drawio&utm_content=drawio&utm_medium=devrel&utm_source=OWO&utm_term=drawio"
-                                    target="_blank"
-                                    rel="noopener noreferrer"
-                                >
-                                    <Image
-                                        src="/volcengine-invite.png"
-                                        alt="火山引擎方舟 Coding Plan"
-                                        width={300}
-                                        height={400}
-                                        className="mx-auto rounded-lg"
-                                    />
-                                </a>
-                            </div>
-
                             {/* Bring Your Own Key */}
                             <div className="text-center">
                                 <h4 className="text-base font-bold text-gray-900 mb-2">
@@ -294,7 +277,7 @@ export default function AboutCN() {
                     <ul className="list-disc pl-6 text-gray-700 space-y-1">
                         <li>
                             <a
-                                href="https://www.volcengine.com/activity/codingplan?ac=MMAP8JTTCAQ2&rc=Z9Z3LDTJ&utm_campaign=drawio&utm_content=drawio&utm_medium=devrel&utm_source=OWO&utm_term=drawio"
+                                href="https://www.volcengine.com/activity/newyear-referral?utm_campaign=doubao&utm_content=aidrawio&utm_medium=github&utm_source=coopensrc&utm_term=project"
                                 target="_blank"
                                 rel="noopener noreferrer"
                                 className="text-blue-600 hover:underline"
@@ -329,7 +312,7 @@ export default function AboutCN() {
                     <p className="text-gray-700 mb-4 font-semibold">
                         特别感谢{" "}
                         <a
-                            href="https://www.volcengine.com/activity/codingplan?ac=MMAP8JTTCAQ2&rc=Z9Z3LDTJ&utm_campaign=drawio&utm_content=drawio&utm_medium=devrel&utm_source=OWO&utm_term=drawio"
+                            href="https://www.volcengine.com/activity/newyear-referral?utm_campaign=doubao&utm_content=aidrawio&utm_medium=github&utm_source=coopensrc&utm_term=project"
                             target="_blank"
                             rel="noopener noreferrer"
                             className="text-blue-600 hover:underline"

app/[lang]/about/ja/page.tsx

@@ -86,7 +86,7 @@ export default function AboutJA() {
                                 <p>
                                     朗報です！
                                     <a
-                                        href="https://www.volcengine.com/activity/codingplan?ac=MMAP8JTTCAQ2&rc=Z9Z3LDTJ&utm_campaign=drawio&utm_content=drawio&utm_medium=devrel&utm_source=OWO&utm_term=drawio"
+                                        href="https://www.volcengine.com/activity/newyear-referral?utm_campaign=doubao&utm_content=aidrawio&utm_medium=github&utm_source=coopensrc&utm_term=project"
                                         target="_blank"
                                         rel="noopener noreferrer"
                                         className="font-semibold text-blue-600 hover:underline"
@@ -95,7 +95,7 @@ export default function AboutJA() {
                                     </a>
                                     様のご支援により、デモサイトでは強力な{" "}
                                     <span className="font-semibold text-amber-700">
-                                        glm-4.7
+                                        K2-thinking
                                     </span>{" "}
                                     モデルを利用できるようになり、より高品質なダイアグラム生成が可能になりました。リンクから登録すると、すべてのモデルで使える{" "}
                                     <span className="font-semibold text-amber-700">
@@ -292,7 +292,7 @@ export default function AboutJA() {
                     <ul className="list-disc pl-6 text-gray-700 space-y-1">
                         <li>
                             <a
-                                href="https://www.volcengine.com/activity/codingplan?ac=MMAP8JTTCAQ2&rc=Z9Z3LDTJ&utm_campaign=drawio&utm_content=drawio&utm_medium=devrel&utm_source=OWO&utm_term=drawio"
+                                href="https://www.volcengine.com/activity/newyear-referral?utm_campaign=doubao&utm_content=aidrawio&utm_medium=github&utm_source=coopensrc&utm_term=project"
                                 target="_blank"
                                 rel="noopener noreferrer"
                                 className="text-blue-600 hover:underline"
@@ -327,7 +327,7 @@ export default function AboutJA() {
                     <p className="text-gray-700 mb-4 font-semibold">
                         デモサイトのAPIトークン使用を支援してくださった{" "}
                         <a
-                            href="https://www.volcengine.com/activity/codingplan?ac=MMAP8JTTCAQ2&rc=Z9Z3LDTJ&utm_campaign=drawio&utm_content=drawio&utm_medium=devrel&utm_source=OWO&utm_term=drawio"
+                            href="https://www.volcengine.com/activity/newyear-referral?utm_campaign=doubao&utm_content=aidrawio&utm_medium=github&utm_source=coopensrc&utm_term=project"
                             target="_blank"
                             rel="noopener noreferrer"
                             className="text-blue-600 hover:underline"

app/[lang]/about/page.tsx

@@ -87,7 +87,7 @@ export default function About() {
                                     Great news! Thanks to the generous
                                     sponsorship from{" "}
                                     <a
-                                        href="https://www.volcengine.com/activity/codingplan?ac=MMAP8JTTCAQ2&rc=Z9Z3LDTJ&utm_campaign=drawio&utm_content=drawio&utm_medium=devrel&utm_source=OWO&utm_term=drawio"
+                                        href="https://www.volcengine.com/activity/newyear-referral?utm_campaign=doubao&utm_content=aidrawio&utm_medium=github&utm_source=coopensrc&utm_term=project"
                                         target="_blank"
                                         rel="noopener noreferrer"
                                         className="font-semibold text-blue-600 hover:underline"
@@ -96,7 +96,7 @@ export default function About() {
                                     </a>
                                     , the demo site now uses the powerful{" "}
                                     <span className="font-semibold text-amber-700">
-                                        glm-4.7
+                                        K2-thinking
                                     </span>{" "}
                                     model for better diagram generation! Sign up
                                     via the link to get{" "}
@@ -311,7 +311,7 @@ export default function About() {
                     <ul className="list-disc pl-6 text-gray-700 space-y-1">
                         <li>
                             <a
-                                href="https://www.volcengine.com/activity/codingplan?ac=MMAP8JTTCAQ2&rc=Z9Z3LDTJ&utm_campaign=drawio&utm_content=drawio&utm_medium=devrel&utm_source=OWO&utm_term=drawio"
+                                href="https://www.volcengine.com/activity/newyear-referral?utm_campaign=doubao&utm_content=aidrawio&utm_medium=github&utm_source=coopensrc&utm_term=project"
                                 target="_blank"
                                 rel="noopener noreferrer"
                                 className="text-blue-600 hover:underline"
@@ -348,7 +348,7 @@ export default function About() {
                     <p className="text-gray-700 mb-4 font-semibold">
                         Special thanks to{" "}
                         <a
-                            href="https://www.volcengine.com/activity/codingplan?ac=MMAP8JTTCAQ2&rc=Z9Z3LDTJ&utm_campaign=drawio&utm_content=drawio&utm_medium=devrel&utm_source=OWO&utm_term=drawio"
+                            href="https://www.volcengine.com/activity/newyear-referral?utm_campaign=doubao&utm_content=aidrawio&utm_medium=github&utm_source=coopensrc&utm_term=project"
                             target="_blank"
                             rel="noopener noreferrer"
                             className="text-blue-600 hover:underline"

app/[lang]/page.tsx

@@ -11,16 +11,10 @@ import {
 } from "@/components/ui/resizable"
 import { useDiagram } from "@/contexts/diagram-context"
 import { i18n, type Locale } from "@/lib/i18n/config"
-import { isIndexedDBUsable } from "@/lib/session-storage"
 
 export default function Home() {
-    const {
-        drawioRef,
-        handleDiagramExport,
-        handleDiagramAutoSave,
-        onDrawioLoad,
-        resetDrawioReady,
-    } = useDiagram()
+    const { drawioRef, handleDiagramExport, onDrawioLoad, resetDrawioReady } =
+        useDiagram()
     const router = useRouter()
     const pathname = usePathname()
     // Extract current language from pathname (e.g., "/zh/about" → "zh")
@@ -32,8 +26,6 @@ export default function Home() {
     const [isLoaded, setIsLoaded] = useState(false)
     const [isDrawioReady, setIsDrawioReady] = useState(false)
     const [isElectron, setIsElectron] = useState(false)
-    const [canPersist, setCanPersist] = useState(false)
-    const [canPersistChecked, setCanPersistChecked] = useState(false)
     const [drawioBaseUrl, setDrawioBaseUrl] = useState(
         process.env.NEXT_PUBLIC_DRAWIO_BASE_URL || "https://embed.diagrams.net",
     )
@@ -84,11 +76,6 @@ export default function Home() {
             setDrawioBaseUrl(`${window.location.origin}/drawio/index.html`)
         }
 
-        void (async () => {
-            const usable = await isIndexedDBUsable()
-            setCanPersist(usable)
-            setCanPersistChecked(true)
-        })()
         setIsLoaded(true)
     }, [pathname, router])
 
@@ -97,17 +84,6 @@ export default function Home() {
         onDrawioLoad()
     }, [onDrawioLoad])
 
-    const handleDrawioAutoSave = useCallback(
-        (data: { xml?: string }) => {
-            handleDiagramAutoSave(data)
-            // Only suppress modified state when persistence is available
-            if (canPersist) {
-                drawioRef.current?.status({ message: "", modified: false })
-            }
-        },
-        [canPersist, drawioRef, handleDiagramAutoSave],
-    )
-
     const handleDarkModeChange = () => {
         const newValue = !darkMode
         setDarkMode(newValue)
@@ -191,32 +167,20 @@ export default function Home() {
                         }`}
                     >
                         <div className="h-full rounded-xl overflow-hidden shadow-soft-lg border border-border/30 relative">
-                            {isLoaded && canPersistChecked && (
+                            {isLoaded && (
                                 <div
                                     className={`h-full w-full ${isDrawioReady ? "" : "invisible absolute inset-0"}`}
                                 >
                                     <DrawIoEmbed
                                         key={`${drawioUi}-${darkMode}-${currentLang}-${isElectron}`}
                                         ref={drawioRef}
-                                        autosave
-                                        onAutoSave={handleDrawioAutoSave}
                                         onExport={handleDiagramExport}
                                         onLoad={handleDrawioLoad}
                                         baseUrl={drawioBaseUrl}
-                                        configuration={
-                                            canPersist
-                                                ? { confirmExit: false }
-                                                : undefined
-                                        }
                                         urlParameters={{
                                             ui: drawioUi,
                                             spin: false,
                                             libraries: false,
-                                            // Disable modified tracking only when persistence is available
-                                            ...(canPersist && {
-                                                modified: false,
-                                                keepmodified: false,
-                                            }),
                                             saveAndExit: false,
                                             noSaveBtn: true,
                                             noExitBtn: true,

app/api/chat/route.ts

@@ -14,7 +14,6 @@ import path from "path"
 import { z } from "zod"
 import {
     getAIModel,
-    SINGLE_SYSTEM_PROVIDERS,
     supportsImageInput,
     supportsPromptCaching,
 } from "@/lib/ai-providers"
@@ -90,12 +89,7 @@ async function handleChatRequest(req: Request): Promise<Response> {
         }
     }
 
-    const body = await req.json()
-    const { messages, xml, previousXml, sessionId } = body
-    const customSystemMessage =
-        typeof body.customSystemMessage === "string"
-            ? body.customSystemMessage.slice(0, 5000)
-            : ""
+    const { messages, xml, previousXml, sessionId } = await req.json()
 
     // Get user ID for Langfuse tracking and quota
     const userId = getUserIdFromRequest(req)
@@ -241,13 +235,8 @@ async function handleChatRequest(req: Request): Promise<Response> {
     )
 
     // Get AI model with optional client overrides
-    const {
-        model,
-        providerOptions,
-        headers,
-        modelId,
-        provider: resolvedProvider,
-    } = getAIModel(clientOverrides)
+    const { model, providerOptions, headers, modelId } =
+        getAIModel(clientOverrides)
 
     // Check if model supports prompt caching
     const shouldCache = supportsPromptCaching(modelId)
@@ -257,9 +246,6 @@ async function handleChatRequest(req: Request): Promise<Response> {
 
     // Get the appropriate system prompt based on model (extended for Opus/Haiku 4.5)
     const systemMessage = getSystemPrompt(modelId, minimalStyle)
-    const finalSystemMessage = customSystemMessage
-        ? `${systemMessage}\n\n## Custom Instructions\n${customSystemMessage}`
-        : systemMessage
 
     // Extract file parts (images) from the last user message
     const fileParts =
@@ -432,57 +418,32 @@ ${userInputText}
     }
 
     // System messages with multiple cache breakpoints for optimal caching:
-    // - Breakpoint 1: System instructions + custom instructions - changes when user updates custom system message
+    // - Breakpoint 1: Static instructions (~1500 tokens) - rarely changes
     // - Breakpoint 2: Current XML context - changes per diagram, but constant within a conversation turn
-    // Some providers (e.g. MiniMax) don't support multiple system messages
-    // Merge them into a single system message for compatibility
-    const isSingleSystemProvider = SINGLE_SYSTEM_PROVIDERS.has(resolvedProvider)
-
-    const xmlContext = `${
-        previousXml
-            ? `Previous diagram XML (before user's last message):
-"""xml
-${previousXml}
-"""
-
-`
-            : ""
-    }Current diagram XML (AUTHORITATIVE - the source of truth):
-"""xml
-${xml || ""}
-"""
-
-IMPORTANT: The "Current diagram XML" is the SINGLE SOURCE OF TRUTH for what's on the canvas right now. The user can manually add, delete, or modify shapes directly in draw.io. Always count and describe elements based on the CURRENT XML, not on what you previously generated. If both previous and current XML are shown, compare them to understand what the user changed. When using edit_diagram, COPY search patterns exactly from the CURRENT XML - attribute order matters!`
-
-    const systemMessages = isSingleSystemProvider
-        ? [
-              {
-                  role: "system" as const,
-                  content: `${finalSystemMessage}\n\n${xmlContext}`,
-              },
-          ]
-        : [
-              // Cache breakpoint 1: Instructions (+ optional custom instructions)
-              {
-                  role: "system" as const,
-                  content: finalSystemMessage,
-                  ...(shouldCache && {
-                      providerOptions: {
-                          bedrock: { cachePoint: { type: "default" } },
-                      },
-                  }),
-              },
-              // Cache breakpoint 2: Previous and Current diagram XML context
-              {
-                  role: "system" as const,
-                  content: xmlContext,
-                  ...(shouldCache && {
-                      providerOptions: {
-                          bedrock: { cachePoint: { type: "default" } },
-                      },
-                  }),
-              },
-          ]
+    // This allows: if only user message changes, both system caches are reused
+    //              if XML changes, instruction cache is still reused
+    const systemMessages = [
+        // Cache breakpoint 1: Instructions (rarely change)
+        {
+            role: "system" as const,
+            content: systemMessage,
+            ...(shouldCache && {
+                providerOptions: {
+                    bedrock: { cachePoint: { type: "default" } },
+                },
+            }),
+        },
+        // Cache breakpoint 2: Previous and Current diagram XML context
+        {
+            role: "system" as const,
+            content: `${previousXml ? `Previous diagram XML (before user's last message):\n"""xml\n${previousXml}\n"""\n\n` : ""}Current diagram XML (AUTHORITATIVE - the source of truth):\n"""xml\n${xml || ""}\n"""\n\nIMPORTANT: 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!`,
+            ...(shouldCache && {
+                providerOptions: {
+                    bedrock: { cachePoint: { type: "default" } },
+                },
+            }),
+        },
+    ]
 
     const allMessages = [...systemMessages, ...enhancedMessages]
 

app/api/parse-url/route.ts

@@ -5,7 +5,6 @@ import { allowPrivateUrls, isPrivateUrl } from "@/lib/ssrf-protection"
 
 const MAX_CONTENT_LENGTH = 150000 // Match PDF limit
 const EXTRACT_TIMEOUT_MS = 15000
-const USER_AGENT = "Mozilla/5.0 (compatible; NextAIDrawio/1.0)"
 
 export async function POST(req: Request) {
     try {
@@ -35,31 +34,6 @@ export async function POST(req: Request) {
                 { status: 400 },
             )
         }
-        const headController = new AbortController()
-        const headTimeout = setTimeout(() => headController.abort(), 3000)
-        try {
-            const headResponse = await fetch(url, {
-                method: "HEAD",
-                headers: { "User-Agent": USER_AGENT },
-                signal: headController.signal,
-            })
-            const contentType = headResponse.headers.get("content-type")
-            if (contentType?.includes("application/pdf")) {
-                return NextResponse.json(
-                    {
-                        error: "PDF URLs are not supported. Please download and upload the PDF file directly",
-                    },
-                    { status: 422 },
-                )
-            }
-        } catch (err) {
-            console.warn(
-                "HEAD pre-check failed, proceeding with extraction:",
-                err,
-            )
-        } finally {
-            clearTimeout(headTimeout)
-        }
 
         // Extract article content with timeout to avoid tying up server resources
         const controller = new AbortController()
@@ -70,7 +44,9 @@ export async function POST(req: Request) {
         let article
         try {
             article = await extract(url, undefined, {
-                headers: { "User-Agent": USER_AGENT },
+                headers: {
+                    "User-Agent": "Mozilla/5.0 (compatible; NextAIDrawio/1.0)",
+                },
                 signal: controller.signal,
             })
         } catch (err: any) {

app/api/validate-model/route.ts

@@ -9,9 +9,7 @@ import { createOpenRouter } from "@openrouter/ai-sdk-provider"
 import { generateText } from "ai"
 import { NextResponse } from "next/server"
 import { createOllama } from "ollama-ai-provider-v2"
-import { normalizeMiniMaxBaseURL } from "@/lib/ai-providers"
 import { allowPrivateUrls, isPrivateUrl } from "@/lib/ssrf-protection"
-import { PROVIDER_INFO, type ProviderName } from "@/lib/types/model-config"
 
 export const runtime = "nodejs"
 
@@ -176,21 +174,10 @@ export async function POST(req: Request) {
             }
 
             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}` },
-                    }),
+                const ollama = createOllama({
+                    baseURL: baseUrl || "http://localhost:11434",
                 })
-                model = ollamaProvider(modelId)
+                model = ollama(modelId)
                 break
             }
 
@@ -321,59 +308,6 @@ export async function POST(req: Request) {
                 }
             }
 
-            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 - OpenAI compatible
-            case "glm":
-            case "qwen":
-            case "kimi":
-            case "qiniu":
-            case "novita": {
-                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}` },

biome.json

@@ -1,5 +1,5 @@
 {
-    "$schema": "https://biomejs.dev/schemas/2.4.4/schema.json",
+    "$schema": "https://biomejs.dev/schemas/2.3.10/schema.json",
     "vcs": {
         "enabled": true,
         "clientKind": "git",

components/chat-input.tsx

@@ -5,6 +5,7 @@ import {
     History,
     Image as ImageIcon,
     Link,
+    Loader2,
     Send,
     Square,
 } from "lucide-react"

components/chat-panel.tsx

@@ -138,22 +138,26 @@ export default function ChatPanel({
     const onFetchChart = (saveToHistory = true) => {
         return Promise.race([
             new Promise<string>((resolve) => {
-                resolverRef.current = resolve
+                if (resolverRef && "current" in resolverRef) {
+                    resolverRef.current = resolve
+                }
                 if (saveToHistory) {
                     onExport()
                 } else {
                     handleExportWithoutHistory()
                 }
             }),
-            new Promise<string>((_, reject) => {
-                const currentResolver = resolverRef.current
-                setTimeout(() => {
-                    if (resolverRef.current === currentResolver) {
-                        resolverRef.current = null
-                    }
-                    reject(new Error("Chart export timed out after 10 seconds"))
-                }, 10000)
-            }),
+            new Promise<string>((_, reject) =>
+                setTimeout(
+                    () =>
+                        reject(
+                            new Error(
+                                "Chart export timed out after 10 seconds",
+                            ),
+                        ),
+                    10000,
+                ),
+            ),
         ])
     }
 
@@ -176,7 +180,6 @@ export default function ChatPanel({
     const [tpmLimit, setTpmLimit] = useState(0)
     const [minimalStyle, setMinimalStyle] = useState(false)
     const [vlmValidationEnabled, setVlmValidationEnabled] = useState(false)
-    const [customSystemMessage, setCustomSystemMessage] = useState("")
     const [shouldFocusInput, setShouldFocusInput] = useState(false)
 
     // Restore input from sessionStorage on mount (when ChatPanel remounts due to key change)
@@ -195,14 +198,6 @@ export default function ChatPanel({
         }
     }, [])
 
-    // Load custom system message from localStorage on mount
-    useEffect(() => {
-        const stored = localStorage.getItem(STORAGE_KEYS.customSystemMessage)
-        if (stored !== null) {
-            setCustomSystemMessage(stored)
-        }
-    }, [])
-
     // Check config on mount
     useEffect(() => {
         fetch(getApiEndpoint("/api/config"))
@@ -313,12 +308,6 @@ export default function ChatPanel({
         localStorage.setItem(STORAGE_KEYS.vlmValidationEnabled, String(value))
     }, [])
 
-    // Handler for custom system message change
-    const handleCustomSystemMessageChange = useCallback((value: string) => {
-        setCustomSystemMessage(value)
-        localStorage.setItem(STORAGE_KEYS.customSystemMessage, value)
-    }, [])
-
     // Ref to store the sendMessage function for use in callbacks
     const sendMessageRef = useRef<typeof sendMessage | null>(null)
 
@@ -601,7 +590,7 @@ export default function ChatPanel({
 
         try {
             const currentSession = sessionManager.currentSession
-            if (currentSession) {
+            if (currentSession && currentSession.messages.length > 0) {
                 // Restore from session manager (IndexedDB)
                 justLoadedSessionRef.current = true
                 syncUIWithSession(currentSession)
@@ -638,7 +627,7 @@ export default function ChatPanel({
         lastSyncedSessionIdRef.current = newSessionId
 
         // Sync UI with new session
-        if (newSession) {
+        if (newSession && newSession.messages.length > 0) {
             justLoadedSessionRef.current = true
             syncUIWithSession(newSession)
         } else if (!newSession) {
@@ -693,7 +682,7 @@ export default function ChatPanel({
         // Debounce: save after 1 second of no changes
         localStorageDebounceRef.current = setTimeout(async () => {
             try {
-                if (messages.length > 0 || hasDiagramNow) {
+                if (messages.length > 0) {
                     const sessionData = await buildSessionData({
                         // Only capture thumbnail if there was a diagram AND this isn't a no-diagram session
                         withThumbnail: hasDiagramNow && !isNodiagramSession,
@@ -715,7 +704,6 @@ export default function ChatPanel({
             }
         }
     }, [
-        chartXML,
         messages,
         status,
         sessionIsAvailable,
@@ -746,8 +734,7 @@ export default function ChatPanel({
         const handleVisibilityChange = async () => {
             if (
                 document.visibilityState === "hidden" &&
-                (messagesRef.current.length > 0 ||
-                    isRealDiagram(chartXMLRef.current))
+                messagesRef.current.length > 0
             ) {
                 try {
                     // Attempt to save session - browser may not wait for completion
@@ -1050,7 +1037,7 @@ export default function ChatPanel({
         sendMessage(
             { parts },
             {
-                body: { xml, previousXml, sessionId, customSystemMessage },
+                body: { xml, previousXml, sessionId },
                 headers: {
                     "x-access-code": config.accessCode,
                     ...(config.aiProvider && {
@@ -1428,8 +1415,6 @@ export default function ChatPanel({
                 onMinimalStyleChange={setMinimalStyle}
                 vlmValidationEnabled={vlmValidationEnabled}
                 onVlmValidationChange={handleVlmValidationChange}
-                customSystemMessage={customSystemMessage}
-                onCustomSystemMessageChange={handleCustomSystemMessageChange}
                 onOpenModelConfig={() => setShowModelConfigDialog(true)}
             />
 

components/model-config-dialog.tsx

@@ -54,11 +54,7 @@ import { useDictionary } from "@/hooks/use-dictionary"
 import type { UseModelConfigReturn } from "@/hooks/use-model-config"
 import { formatMessage } from "@/lib/i18n/utils"
 import type { ProviderConfig, ProviderName } from "@/lib/types/model-config"
-import {
-    PROVIDER_INFO,
-    PROVIDER_LOGO_MAP,
-    SUGGESTED_MODELS,
-} from "@/lib/types/model-config"
+import { PROVIDER_INFO, SUGGESTED_MODELS } from "@/lib/types/model-config"
 import { cn } from "@/lib/utils"
 
 interface ModelConfigDialogProps {
@@ -69,6 +65,24 @@ interface ModelConfigDialogProps {
 
 type ValidationStatus = "idle" | "validating" | "success" | "error"
 
+// Map provider names to models.dev logo names
+const PROVIDER_LOGO_MAP: Record<string, string> = {
+    openai: "openai",
+    anthropic: "anthropic",
+    google: "google",
+    azure: "azure",
+    bedrock: "amazon-bedrock",
+    openrouter: "openrouter",
+    deepseek: "deepseek",
+    siliconflow: "siliconflow",
+    sglang: "openai", // SGLang is OpenAI-compatible
+    gateway: "vercel",
+    edgeone: "tencent-cloud",
+    vertexai: "google",
+    doubao: "bytedance",
+    modelscope: "modelscope",
+}
+
 // Provider logo component
 function ProviderLogo({
     provider,
@@ -268,7 +282,6 @@ export function ModelConfigDialog({
         // Check credentials based on provider type
         const isBedrock = selectedProvider.provider === "bedrock"
         const isEdgeOne = selectedProvider.provider === "edgeone"
-        const isOllama = selectedProvider.provider === "ollama"
         const isVertexAI = selectedProvider.provider === "vertexai"
         if (isBedrock) {
             if (
@@ -283,7 +296,7 @@ export function ModelConfigDialog({
             if (!selectedProvider.vertexApiKey) {
                 return
             }
-        } else if (!isEdgeOne && !isOllama && !selectedProvider.apiKey) {
+        } else if (!isEdgeOne && !selectedProvider.apiKey) {
             return
         }
 
@@ -513,7 +526,7 @@ export function ModelConfigDialog({
                     </div>
 
                     {/* Provider Details (Right Panel) */}
-                    <div className="flex-1 min-w-0 flex flex-col overflow-auto scrollbar-thin">
+                    <div className="flex-1 min-w-0 flex flex-col overflow-auto [&::-webkit-scrollbar]:hidden ">
                         {selectedProvider ? (
                             <ScrollArea className="flex-1" ref={scrollRef}>
                                 <div className="p-6 space-y-8">
@@ -1017,7 +1030,9 @@ export function ModelConfigDialog({
                                                     </div>
                                                 </>
                                             ) : selectedProvider.provider ===
-                                              "edgeone" ? (
+                                                  "ollama" ||
+                                              selectedProvider.provider ===
+                                                  "edgeone" ? (
                                                 <div className="space-y-3">
                                                     <div className="flex items-center gap-2">
                                                         <Button
@@ -1085,9 +1100,6 @@ export function ModelConfigDialog({
                                                                 dict.modelConfig
                                                                     .apiKey
                                                             }
-                                                            {selectedProvider.provider ===
-                                                                "ollama" &&
-                                                                ` ${dict.modelConfig.optional}`}
                                                         </Label>
                                                         <div className="flex gap-2">
                                                             <div className="relative flex-1">
@@ -1151,9 +1163,7 @@ export function ModelConfigDialog({
                                                                     handleValidate
                                                                 }
                                                                 disabled={
-                                                                    (selectedProvider.provider !==
-                                                                        "ollama" &&
-                                                                        !selectedProvider.apiKey) ||
+                                                                    !selectedProvider.apiKey ||
                                                                     validationStatus ===
                                                                         "validating"
                                                                 }
@@ -1241,16 +1251,6 @@ export function ModelConfigDialog({
                                                             }
                                                             className="h-9 rounded-xl font-mono text-xs"
                                                         />
-                                                        {selectedProvider.provider ===
-                                                            "minimax" && (
-                                                            <p className="text-xs text-muted-foreground">
-                                                                {
-                                                                    dict
-                                                                        .modelConfig
-                                                                        .minimaxBaseUrlHint
-                                                                }
-                                                            </p>
-                                                        )}
                                                     </div>
                                                 </>
                                             )}

components/model-selector.tsx

@@ -27,10 +27,7 @@ import {
 } from "@/components/ai-elements/model-selector"
 import { ButtonWithTooltip } from "@/components/button-with-tooltip"
 import { useDictionary } from "@/hooks/use-dictionary"
-import {
-    type FlattenedModel,
-    PROVIDER_LOGO_MAP,
-} from "@/lib/types/model-config"
+import type { FlattenedModel } from "@/lib/types/model-config"
 import { cn } from "@/lib/utils"
 
 interface ModelSelectorProps {
@@ -42,6 +39,24 @@ interface ModelSelectorProps {
     showUnvalidatedModels?: boolean
 }
 
+// Map our provider names to models.dev logo names
+const PROVIDER_LOGO_MAP: Record<string, string> = {
+    openai: "openai",
+    anthropic: "anthropic",
+    google: "google",
+    azure: "azure",
+    bedrock: "amazon-bedrock",
+    openrouter: "openrouter",
+    deepseek: "deepseek",
+    siliconflow: "siliconflow",
+    sglang: "openai", // SGLang is OpenAI-compatible, use OpenAI logo
+    gateway: "vercel",
+    edgeone: "tencent-cloud",
+    vertexai: "google",
+    doubao: "bytedance",
+    modelscope: "modelscope",
+}
+
 // Group models by providerLabel (handles duplicate providers)
 function groupModelsByProvider(
     models: FlattenedModel[],
@@ -199,7 +214,7 @@ export function ModelSelector({
                     />
                     <div className="flex flex-1 flex-col min-h-0 overflow-hidden">
                         <div className="flex-1 min-h-0 overflow-hidden">
-                            <ModelSelectorList className="overflow-y-auto scrollbar-thin">
+                            <ModelSelectorList className="[&::-webkit-scrollbar]:hidden [-ms-overflow-style:none] [scrollbar-width:none]">
                                 <ModelSelectorEmpty>
                                     {displayModels.length === 0 &&
                                     models.length > 0

components/quota-limit-toast.tsx

@@ -23,22 +23,9 @@ export function QuotaLimitToast({
 }: QuotaLimitToastProps) {
     const dict = useDictionary()
     const isTokenLimit = type === "token"
-    const isSelfHosted = process.env.NEXT_PUBLIC_SELFHOSTED === "true"
     const formatNumber = (n: number) =>
         n >= 1000 ? `${(n / 1000).toFixed(1)}k` : n.toString()
 
-    const quotaMessage = isTokenLimit
-        ? isSelfHosted
-            ? (dict.quota.messageTokenSelfHosted ?? dict.quota.messageToken)
-            : dict.quota.messageToken
-        : isSelfHosted
-          ? (dict.quota.messageApiSelfHosted ?? dict.quota.messageApi)
-          : dict.quota.messageApi
-
-    const tipHtml = isSelfHosted
-        ? (dict.quota.tipSelfHosted ?? dict.quota.tip)
-        : dict.quota.tip
-
     const handleKeyDown = (e: React.KeyboardEvent) => {
         if (e.key === "Escape") {
             e.preventDefault()
@@ -84,24 +71,19 @@ export function QuotaLimitToast({
             </div>
             {/* Message */}
             <div className="text-sm text-muted-foreground leading-relaxed mb-4 space-y-2">
-                <p>{quotaMessage}</p>
-                {!isSelfHosted && (
-                    <p
-                        dangerouslySetInnerHTML={{
-                            __html: formatMessage(
-                                dict.quota.doubaoSponsorship,
-                                {
-                                    link: "https://www.volcengine.com/activity/codingplan?ac=MMAP8JTTCAQ2&rc=Z9Z3LDTJ&utm_campaign=drawio&utm_content=drawio&utm_medium=devrel&utm_source=OWO&utm_term=drawio",
-                                },
-                            ),
-                        }}
-                    />
-                )}
+                <p>
+                    {isTokenLimit
+                        ? dict.quota.messageToken
+                        : dict.quota.messageApi}
+                </p>
                 <p
                     dangerouslySetInnerHTML={{
-                        __html: tipHtml,
+                        __html: formatMessage(dict.quota.doubaoSponsorship, {
+                            link: "https://www.volcengine.com/activity/newyear-referral?utm_campaign=doubao&utm_content=aidrawio&utm_medium=github&utm_source=coopensrc&utm_term=project",
+                        }),
                     }}
                 />
+                <p dangerouslySetInnerHTML={{ __html: dict.quota.tip }} />
                 <p>{dict.quota.reset}</p>
             </div>{" "}
             {/* Action buttons */}
@@ -119,28 +101,24 @@ export function QuotaLimitToast({
                         {dict.quota.configModel}
                     </button>
                 )}
-                {!isSelfHosted && (
-                    <>
-                        <a
-                            href="https://github.com/DayuanJiang/next-ai-draw-io"
-                            target="_blank"
-                            rel="noopener noreferrer"
-                            className="inline-flex items-center gap-1.5 px-3 py-1.5 text-xs font-medium rounded-lg border border-border text-foreground hover:bg-muted transition-colors"
-                        >
-                            <FaGithub className="w-3.5 h-3.5" />
-                            {dict.quota.selfHost}
-                        </a>
-                        <a
-                            href="https://github.com/sponsors/DayuanJiang"
-                            target="_blank"
-                            rel="noopener noreferrer"
-                            className="inline-flex items-center gap-1.5 px-3 py-1.5 text-xs font-medium rounded-lg border border-border text-foreground hover:bg-muted transition-colors"
-                        >
-                            <Coffee className="w-3.5 h-3.5" />
-                            {dict.quota.sponsor}
-                        </a>
-                    </>
-                )}
+                <a
+                    href="https://github.com/DayuanJiang/next-ai-draw-io"
+                    target="_blank"
+                    rel="noopener noreferrer"
+                    className="inline-flex items-center gap-1.5 px-3 py-1.5 text-xs font-medium rounded-lg border border-border text-foreground hover:bg-muted transition-colors"
+                >
+                    <FaGithub className="w-3.5 h-3.5" />
+                    {dict.quota.selfHost}
+                </a>
+                <a
+                    href="https://github.com/sponsors/DayuanJiang"
+                    target="_blank"
+                    rel="noopener noreferrer"
+                    className="inline-flex items-center gap-1.5 px-3 py-1.5 text-xs font-medium rounded-lg border border-border text-foreground hover:bg-muted transition-colors"
+                >
+                    <Coffee className="w-3.5 h-3.5" />
+                    {dict.quota.sponsor}
+                </a>
             </div>
         </div>
     )

components/settings-dialog.tsx

@@ -22,7 +22,6 @@ import {
     SelectValue,
 } from "@/components/ui/select"
 import { Switch } from "@/components/ui/switch"
-import { Textarea } from "@/components/ui/textarea"
 import { useDictionary } from "@/hooks/use-dictionary"
 import { getApiEndpoint } from "@/lib/base-path"
 import { i18n, type Locale } from "@/lib/i18n/config"
@@ -72,8 +71,6 @@ interface SettingsDialogProps {
     vlmValidationEnabled?: boolean
     onVlmValidationChange?: (value: boolean) => void
     onOpenModelConfig?: () => void
-    customSystemMessage?: string
-    onCustomSystemMessageChange?: (value: string) => void
 }
 
 export const STORAGE_ACCESS_CODE_KEY = "next-ai-draw-io-access-code"
@@ -98,8 +95,6 @@ function SettingsContent({
     vlmValidationEnabled = false,
     onVlmValidationChange = () => {},
     onOpenModelConfig,
-    customSystemMessage = "",
-    onCustomSystemMessageChange = () => {},
 }: SettingsDialogProps) {
     const dict = useDictionary()
     const router = useRouter()
@@ -279,7 +274,7 @@ function SettingsContent({
     }
 
     return (
-        <DialogContent className="sm:max-w-lg p-0 gap-0 max-h-[90vh] flex flex-col overflow-hidden">
+        <DialogContent className="sm:max-w-lg p-0 gap-0">
             {/* Header */}
             <DialogHeader className="px-6 pt-6 pb-4">
                 <DialogTitle>{dict.settings.title}</DialogTitle>
@@ -289,7 +284,7 @@ function SettingsContent({
             </DialogHeader>
 
             {/* Content */}
-            <div className="px-6 pb-6 overflow-y-auto flex-1 scrollbar-thin">
+            <div className="px-6 pb-6">
                 <div className="divide-y divide-border-subtle">
                     {/* API Keys & Models */}
                     {onOpenModelConfig && (
@@ -462,33 +457,6 @@ function SettingsContent({
                         </div>
                     </SettingItem>
 
-                    {/* Custom System Message */}
-                    <div className="py-4 space-y-3">
-                        <div className="space-y-0.5">
-                            <Label
-                                htmlFor="custom-system-message"
-                                className="text-sm font-medium"
-                            >
-                                {dict.settings.customSystemMessage}
-                            </Label>
-                            <p className="text-xs text-muted-foreground">
-                                {dict.settings.customSystemMessageDescription}
-                            </p>
-                        </div>
-                        <Textarea
-                            id="custom-system-message"
-                            value={customSystemMessage}
-                            onChange={(e) =>
-                                onCustomSystemMessageChange(e.target.value)
-                            }
-                            placeholder={
-                                dict.settings.customSystemMessagePlaceholder
-                            }
-                            className="min-h-[80px] max-h-[160px] text-sm"
-                            maxLength={5000}
-                        />
-                    </div>
-
                     {/* Send Shortcut */}
                     <SettingItem
                         label={dict.settings.sendShortcut}

contexts/diagram-context.tsx

@@ -20,10 +20,9 @@ interface DiagramContextType {
     loadDiagram: (chart: string, skipValidation?: boolean) => string | null
     handleExport: () => void
     handleExportWithoutHistory: () => void
-    resolverRef: React.MutableRefObject<((value: string) => void) | null>
-    drawioRef: React.MutableRefObject<DrawIoEmbedRef | null>
+    resolverRef: React.Ref<((value: string) => void) | null>
+    drawioRef: React.Ref<DrawIoEmbedRef | null>
     handleDiagramExport: (data: any) => void
-    handleDiagramAutoSave: (data: { xml?: string }) => void
     clearDiagram: () => void
     saveDiagramToFile: (
         filename: string,
@@ -57,6 +56,8 @@ export function DiagramProvider({ children }: { children: React.ReactNode }) {
     const pngResolverRef = useRef<((value: string) => void) | null>(null)
     // Track if we're expecting an export for history (user-initiated)
     const expectHistoryExportRef = useRef<boolean>(false)
+    // Track if diagram has been restored after DrawIO remount (e.g., theme change)
+    const hasDiagramRestoredRef = useRef<boolean>(false)
     // Track latest chartXML for restoration after remount
     const chartXMLRef = useRef<string>("")
 
@@ -78,22 +79,22 @@ export function DiagramProvider({ children }: { children: React.ReactNode }) {
     }, [chartXML])
 
     // Restore diagram when DrawIO becomes ready after remount (e.g., theme/UI change)
-    // Also restore when chartXML changes while DrawIO is ready (e.g., session loaded after iframe ready)
-    const lastRestoredXmlRef = useRef<string>("")
     useEffect(() => {
-        if (!isDrawioReady || !drawioRef.current) return
-        // Only load if we have a real diagram and it's different from what we already loaded
-        if (
-            isRealDiagram(chartXML) &&
-            chartXML !== lastRestoredXmlRef.current
-        ) {
-            lastRestoredXmlRef.current = chartXML
-            drawioRef.current.load({ xml: chartXML })
-        } else if (!isRealDiagram(chartXML)) {
-            // Reset when diagram is cleared so a future restore can re-load the same XML.
-            lastRestoredXmlRef.current = ""
+        // Reset restore flag when DrawIO is not ready (preparing for next restore cycle)
+        if (!isDrawioReady) {
+            hasDiagramRestoredRef.current = false
+            return
         }
-    }, [isDrawioReady, chartXML])
+        // Only restore once per ready cycle
+        if (hasDiagramRestoredRef.current) return
+        hasDiagramRestoredRef.current = true
+
+        // Restore diagram from ref if we have one
+        const xmlToRestore = chartXMLRef.current
+        if (isRealDiagram(xmlToRestore) && drawioRef.current) {
+            drawioRef.current.load({ xml: xmlToRestore })
+        }
+    }, [isDrawioReady])
 
     // Track if we're expecting an export for file save (stores raw export data)
     const saveResolverRef = useRef<{
@@ -266,16 +267,6 @@ export function DiagramProvider({ children }: { children: React.ReactNode }) {
         }
     }
 
-    const handleDiagramAutoSave = (data: { xml?: string }) => {
-        if (!data?.xml) return
-        // 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
-        }
-        setChartXML(data.xml)
-    }
-
     const clearDiagram = () => {
         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)
@@ -400,7 +391,6 @@ export function DiagramProvider({ children }: { children: React.ReactNode }) {
                 resolverRef,
                 drawioRef,
                 handleDiagramExport,
-                handleDiagramAutoSave,
                 clearDiagram,
                 saveDiagramToFile,
                 getThumbnailSvg,

docs/cn/README_CN.md

@@ -19,9 +19,7 @@
 
 一个集成了AI功能的Next.js网页应用，与draw.io图表无缝结合。通过自然语言命令和AI辅助可视化来创建、修改和增强图表。
 
-> 注：感谢 <img src="https://raw.githubusercontent.com/DayuanJiang/next-ai-draw-io/main/public/doubao-color.png" alt="" height="20" /> [字节跳动豆包](https://www.volcengine.com/activity/codingplan?ac=MMAP8JTTCAQ2&rc=Z9Z3LDTJ&utm_campaign=drawio&utm_content=drawio&utm_medium=devrel&utm_source=OWO&utm_term=drawio) 的赞助支持，本项目的 Demo 现已接入强大的 glm-4.7 模型！
-
-<a href="https://www.volcengine.com/activity/codingplan?ac=MMAP8JTTCAQ2&rc=Z9Z3LDTJ&utm_campaign=drawio&utm_content=drawio&utm_medium=devrel&utm_source=OWO&utm_term=drawio" target="_blank"><img src="../../public/volcengine-invite.png" alt="火山引擎方舟 Coding Plan" width="300" /></a>
+> 注：感谢 <img src="https://raw.githubusercontent.com/DayuanJiang/next-ai-draw-io/main/public/doubao-color.png" alt="" height="20" /> [字节跳动豆包](https://www.volcengine.com/activity/newyear-referral?utm_campaign=doubao&utm_content=aidrawio&utm_medium=github&utm_source=coopensrc&utm_term=project) 的赞助支持，本项目的 Demo 现已接入强大的 K2-thinking 模型！
 
 https://github.com/user-attachments/assets/b2eef5f3-b335-4e71-a755-dc2e80931979
 
@@ -197,7 +195,7 @@ npm run dev
 
 ## 多提供商支持
 
--   [字节跳动豆包](https://www.volcengine.com/activity/codingplan?ac=MMAP8JTTCAQ2&rc=Z9Z3LDTJ&utm_campaign=drawio&utm_content=drawio&utm_medium=devrel&utm_source=OWO&utm_term=drawio)
+-   [字节跳动豆包](https://www.volcengine.com/activity/newyear-referral?utm_campaign=doubao&utm_content=aidrawio&utm_medium=github&utm_source=coopensrc&utm_term=project)
 -   AWS Bedrock（默认）
 -   OpenAI
 -   Anthropic
@@ -238,7 +236,7 @@ npm run dev
 
 ## 支持与联系
 
-**特别感谢[字节跳动豆包](https://www.volcengine.com/activity/codingplan?ac=MMAP8JTTCAQ2&rc=Z9Z3LDTJ&utm_campaign=drawio&utm_content=drawio&utm_medium=devrel&utm_source=OWO&utm_term=drawio)赞助演示站点的 API Token 使用！** 注册火山引擎 ARK 平台即可获得50万免费Token！
+**特别感谢[字节跳动豆包](https://www.volcengine.com/activity/newyear-referral?utm_campaign=doubao&utm_content=aidrawio&utm_medium=github&utm_source=coopensrc&utm_term=project)赞助演示站点的 API Token 使用！** 注册火山引擎 ARK 平台即可获得50万免费Token！
 
 如果您觉得这个项目有用，请考虑[赞助](https://github.com/sponsors/DayuanJiang)来帮助我托管在线演示站点！
 

docs/cn/ai-providers.md

@@ -13,7 +13,7 @@
 
 ### 豆包 (字节跳动火山引擎)
 
-> **免费 Token**：在 [火山引擎 ARK 平台](https://www.volcengine.com/activity/codingplan?ac=MMAP8JTTCAQ2&rc=Z9Z3LDTJ&utm_campaign=drawio&utm_content=drawio&utm_medium=devrel&utm_source=OWO&utm_term=drawio) 注册，即可获得所有模型 50 万免费 Token！
+> **免费 Token**：在 [火山引擎 ARK 平台](https://www.volcengine.com/activity/newyear-referral?utm_campaign=doubao&utm_content=aidrawio&utm_medium=github&utm_source=coopensrc&utm_term=project) 注册，即可获得所有模型 50 万免费 Token！
 
 ```bash
 DOUBAO_API_KEY=your_api_key
@@ -207,85 +207,6 @@ AI_MODEL=openai/gpt-4o
 
 从 [Vercel AI Gateway 仪表板](https://vercel.com/ai-gateway) 获取您的 API 密钥。
 
-### MiniMax
-
-MiniMax 支持两种 API 格式：
-- **Anthropic 兼容**（`/anthropic` 端点）— 推荐，支持 interleaved thinking
-- **OpenAI 兼容**（`/v1` 端点）— 标准 OpenAI 聊天补全格式
-
-```bash
-MINIMAX_API_KEY=your_api_key
-AI_MODEL=MiniMax-M2.7
-```
-
-可选配置：
-
-```bash
-# 中国大陆版，Anthropic 兼容（默认）
-MINIMAX_BASE_URL=https://api.minimaxi.com/anthropic
-
-# 中国大陆版，OpenAI 兼容
-MINIMAX_BASE_URL=https://api.minimaxi.com/v1
-
-# 国际版，Anthropic 兼容
-MINIMAX_BASE_URL=https://api.minimax.io/anthropic
-
-# 国际版，OpenAI 兼容
-MINIMAX_BASE_URL=https://api.minimax.io/v1
-```
-
-### GLM (智谱 AI)
-
-```bash
-GLM_API_KEY=your_api_key
-AI_MODEL=glm-4
-```
-
-可选的自定义端点：
-
-```bash
-GLM_BASE_URL=https://your-custom-endpoint
-```
-
-### Qwen (阿里云通义千问)
-
-```bash
-QWEN_API_KEY=your_api_key
-AI_MODEL=qwen-turbo
-```
-
-可选的自定义端点：
-
-```bash
-QWEN_BASE_URL=https://your-custom-endpoint
-```
-
-### Kimi (月之暗面 Moonshot AI)
-
-```bash
-KIMI_API_KEY=your_api_key
-AI_MODEL=kimi-latest
-```
-
-可选的自定义端点：
-
-```bash
-KIMI_BASE_URL=https://your-custom-endpoint
-```
-
-### Qiniu (七牛云)
-
-```bash
-QINIU_API_KEY=your_api_key
-AI_MODEL=your_model_id
-```
-
-可选的自定义端点：
-
-```bash
-QINIU_BASE_URL=https://your-custom-endpoint
-```
-
 ## 自动检测
 
 如果您只配置了**一个**提供商的 API 密钥，系统将自动检测并使用该提供商。无需设置 `AI_PROVIDER`。
@@ -293,7 +214,7 @@ QINIU_BASE_URL=https://your-custom-endpoint
 如果您配置了**多个** API 密钥，则必须显式设置 `AI_PROVIDER`：
 
 ```bash
-AI_PROVIDER=google  # 或：openai, anthropic, deepseek, siliconflow, doubao, azure, bedrock, openrouter, ollama, gateway, sglang, modelscope, minimax, glm, qwen, kimi, qiniu
+AI_PROVIDER=google  # 或：openai, anthropic, deepseek, siliconflow, doubao, azure, bedrock, openrouter, ollama, gateway, sglang
 ```
 
 ## 服务端多模型配置

docs/en/ai-providers.md

@@ -13,7 +13,7 @@ This guide explains how to configure different AI model providers for next-ai-dr
 
 ### Doubao (ByteDance Volcengine)
 
-> **Free tokens**: Register on the [Volcengine ARK platform](https://www.volcengine.com/activity/codingplan?ac=MMAP8JTTCAQ2&rc=Z9Z3LDTJ&utm_campaign=drawio&utm_content=drawio&utm_medium=devrel&utm_source=OWO&utm_term=drawio) to get 500K free tokens for all models!
+> **Free tokens**: Register on the [Volcengine ARK platform](https://www.volcengine.com/activity/newyear-referral?utm_campaign=doubao&utm_content=aidrawio&utm_medium=github&utm_source=coopensrc&utm_term=project) to get 500K free tokens for all models!
 
 ```bash
 DOUBAO_API_KEY=your_api_key
@@ -222,85 +222,6 @@ Model format uses `provider/model` syntax:
 
 Get your API key from the [Vercel AI Gateway dashboard](https://vercel.com/ai-gateway).
 
-### MiniMax
-
-MiniMax supports two API formats:
-- **Anthropic-compatible** (`/anthropic` endpoint) — recommended, supports interleaved thinking
-- **OpenAI-compatible** (`/v1` endpoint) — standard OpenAI chat completions format
-
-```bash
-MINIMAX_API_KEY=your_api_key
-AI_MODEL=MiniMax-M2.7
-```
-
-Optional configuration:
-
-```bash
-# China mainland, Anthropic-compatible (default)
-MINIMAX_BASE_URL=https://api.minimaxi.com/anthropic
-
-# China mainland, OpenAI-compatible
-MINIMAX_BASE_URL=https://api.minimaxi.com/v1
-
-# International, Anthropic-compatible
-MINIMAX_BASE_URL=https://api.minimax.io/anthropic
-
-# International, OpenAI-compatible
-MINIMAX_BASE_URL=https://api.minimax.io/v1
-```
-
-### GLM (Zhipu AI)
-
-```bash
-GLM_API_KEY=your_api_key
-AI_MODEL=glm-4
-```
-
-Optional custom endpoint:
-
-```bash
-GLM_BASE_URL=https://your-custom-endpoint
-```
-
-### Qwen (Alibaba Cloud)
-
-```bash
-QWEN_API_KEY=your_api_key
-AI_MODEL=qwen-turbo
-```
-
-Optional custom endpoint:
-
-```bash
-QWEN_BASE_URL=https://your-custom-endpoint
-```
-
-### Kimi (Moonshot AI)
-
-```bash
-KIMI_API_KEY=your_api_key
-AI_MODEL=kimi-latest
-```
-
-Optional custom endpoint:
-
-```bash
-KIMI_BASE_URL=https://your-custom-endpoint
-```
-
-### Qiniu (Qiniu Cloud)
-
-```bash
-QINIU_API_KEY=your_api_key
-AI_MODEL=your_model_id
-```
-
-Optional custom endpoint:
-
-```bash
-QINIU_BASE_URL=https://your-custom-endpoint
-```
-
 ## Auto-Detection
 
 If you only configure **one** provider's API key, the system will automatically detect and use that provider. No need to set `AI_PROVIDER`.
@@ -308,7 +229,7 @@ If you only configure **one** provider's API key, the system will automatically
 If you configure **multiple** API keys, you must explicitly set `AI_PROVIDER`:
 
 ```bash
-AI_PROVIDER=google  # or: openai, anthropic, deepseek, siliconflow, doubao, azure, bedrock, openrouter, ollama, gateway, sglang, modelscope, minimax, glm, qwen, kimi, qiniu
+AI_PROVIDER=google  # or: openai, anthropic, deepseek, siliconflow, doubao, azure, bedrock, openrouter, ollama, gateway, sglang, modelscope
 ```
 
 ## Server-Side Multi-Model Configuration

docs/ja/README_JA.md

@@ -19,7 +19,7 @@
 
 AI機能とdraw.ioダイアグラムを統合したNext.jsウェブアプリケーションです。自然言語コマンドとAI支援の可視化により、ダイアグラムを作成、修正、強化できます。
 
-> 注：<img src="https://raw.githubusercontent.com/DayuanJiang/next-ai-draw-io/main/public/doubao-color.png" alt="" height="20" /> [ByteDance Doubao](https://www.volcengine.com/activity/codingplan?ac=MMAP8JTTCAQ2&rc=Z9Z3LDTJ&utm_campaign=drawio&utm_content=drawio&utm_medium=devrel&utm_source=OWO&utm_term=drawio) のご支援により、デモサイトに強力な glm-4.7 モデルを導入しました！
+> 注：<img src="https://raw.githubusercontent.com/DayuanJiang/next-ai-draw-io/main/public/doubao-color.png" alt="" height="20" /> [ByteDance Doubao](https://www.volcengine.com/activity/newyear-referral?utm_campaign=doubao&utm_content=aidrawio&utm_medium=github&utm_source=coopensrc&utm_term=project) のご支援により、デモサイトに強力な K2-thinking モデルを導入しました！
 
 https://github.com/user-attachments/assets/b2eef5f3-b335-4e71-a755-dc2e80931979
 
@@ -196,7 +196,7 @@ Next.jsアプリをデプロイする最も簡単な方法は、Next.jsの作成
 
 ## マルチプロバイダーサポート
 
--   [ByteDance Doubao](https://www.volcengine.com/activity/codingplan?ac=MMAP8JTTCAQ2&rc=Z9Z3LDTJ&utm_campaign=drawio&utm_content=drawio&utm_medium=devrel&utm_source=OWO&utm_term=drawio)
+-   [ByteDance Doubao](https://www.volcengine.com/activity/newyear-referral?utm_campaign=doubao&utm_content=aidrawio&utm_medium=github&utm_source=coopensrc&utm_term=project)
 -   AWS Bedrock（デフォルト）
 -   OpenAI
 -   Anthropic
@@ -237,7 +237,7 @@ AWS BedrockとOpenRouter以外のすべてのプロバイダーはカスタム
 
 ## サポート＆お問い合わせ
 
-**デモサイトのAPIトークン使用を支援してくださった[ByteDance Doubao](https://www.volcengine.com/activity/codingplan?ac=MMAP8JTTCAQ2&rc=Z9Z3LDTJ&utm_campaign=drawio&utm_content=drawio&utm_medium=devrel&utm_source=OWO&utm_term=drawio)に特別な感謝を申し上げます！** ARKプラットフォームに登録すると、50万トークンが無料でもらえます！
+**デモサイトのAPIトークン使用を支援してくださった[ByteDance Doubao](https://www.volcengine.com/activity/newyear-referral?utm_campaign=doubao&utm_content=aidrawio&utm_medium=github&utm_source=coopensrc&utm_term=project)に特別な感謝を申し上げます！** ARKプラットフォームに登録すると、50万トークンが無料でもらえます！
 
 このプロジェクトが役に立ったら、ライブデモサイトのホスティングを支援するために[スポンサー](https://github.com/sponsors/DayuanJiang)をご検討ください！
 

docs/ja/ai-providers.md

@@ -13,7 +13,7 @@
 
 ### Doubao (ByteDance Volcengine)
 
-> **無料トークン**: [Volcengine ARK プラットフォーム](https://www.volcengine.com/activity/codingplan?ac=MMAP8JTTCAQ2&rc=Z9Z3LDTJ&utm_campaign=drawio&utm_content=drawio&utm_medium=devrel&utm_source=OWO&utm_term=drawio)に登録すると、すべてのモデルで使える50万トークンが無料で入手できます！
+> **無料トークン**: [Volcengine ARK プラットフォーム](https://www.volcengine.com/activity/newyear-referral?utm_campaign=doubao&utm_content=aidrawio&utm_medium=github&utm_source=coopensrc&utm_term=project)に登録すると、すべてのモデルで使える50万トークンが無料で入手できます！
 
 ```bash
 DOUBAO_API_KEY=your_api_key
@@ -207,85 +207,6 @@ AI_MODEL=openai/gpt-4o
 
 [Vercel AI Gateway ダッシュボード](https://vercel.com/ai-gateway)から API キーを取得してください。
 
-### MiniMax
-
-MiniMax は 2 つの API 形式をサポートしています：
-- **Anthropic 互換**（`/anthropic` エンドポイント）— 推奨、インターリーブ思考をサポート
-- **OpenAI 互換**（`/v1` エンドポイント）— 標準 OpenAI チャット補完形式
-
-```bash
-MINIMAX_API_KEY=your_api_key
-AI_MODEL=MiniMax-M2.7
-```
-
-オプション設定：
-
-```bash
-# 中国大陸版、Anthropic 互換（デフォルト）
-MINIMAX_BASE_URL=https://api.minimaxi.com/anthropic
-
-# 中国大陸版、OpenAI 互換
-MINIMAX_BASE_URL=https://api.minimaxi.com/v1
-
-# 国際版、Anthropic 互換
-MINIMAX_BASE_URL=https://api.minimax.io/anthropic
-
-# 国際版、OpenAI 互換
-MINIMAX_BASE_URL=https://api.minimax.io/v1
-```
-
-### GLM (Zhipu AI)
-
-```bash
-GLM_API_KEY=your_api_key
-AI_MODEL=glm-4
-```
-
-オプションのカスタムエンドポイント：
-
-```bash
-GLM_BASE_URL=https://your-custom-endpoint
-```
-
-### Qwen (Alibaba Cloud)
-
-```bash
-QWEN_API_KEY=your_api_key
-AI_MODEL=qwen-turbo
-```
-
-オプションのカスタムエンドポイント：
-
-```bash
-QWEN_BASE_URL=https://your-custom-endpoint
-```
-
-### Kimi (Moonshot AI)
-
-```bash
-KIMI_API_KEY=your_api_key
-AI_MODEL=kimi-latest
-```
-
-オプションのカスタムエンドポイント：
-
-```bash
-KIMI_BASE_URL=https://your-custom-endpoint
-```
-
-### Qiniu (Qiniu Cloud)
-
-```bash
-QINIU_API_KEY=your_api_key
-AI_MODEL=your_model_id
-```
-
-オプションのカスタムエンドポイント：
-
-```bash
-QINIU_BASE_URL=https://your-custom-endpoint
-```
-
 ## 自動検出
 
 **1つ**のプロバイダーの API キーのみを設定した場合、システムはそのプロバイダーを自動的に検出して使用します。`AI_PROVIDER` を設定する必要はありません。
@@ -293,7 +214,7 @@ QINIU_BASE_URL=https://your-custom-endpoint
 **複数**の API キーを設定する場合は、`AI_PROVIDER` を明示的に設定する必要があります:
 
 ```bash
-AI_PROVIDER=google  # または: openai, anthropic, deepseek, siliconflow, doubao, azure, bedrock, openrouter, ollama, gateway, sglang, modelscope, minimax, glm, qwen, kimi, qiniu
+AI_PROVIDER=google  # または: openai, anthropic, deepseek, siliconflow, doubao, azure, bedrock, openrouter, ollama, gateway, sglang
 ```
 
 ## サーバーサイドマルチモデル設定

electron/electron-builder.yml

@@ -10,13 +10,8 @@ directories:
 afterPack: ./scripts/afterPack.cjs
 
 files:
-  - from: dist-electron
-    to: dist-electron
-    filter:
-      - "**/*"
-  - from: .
-    filter:
-      - package.json
+  - dist-electron/**/*
+  - "!node_modules"
 
 asarUnpack:
   - "**/*.node"

electron/main/config-manager.ts

@@ -359,9 +359,9 @@ const PROVIDER_ENV_MAP: Record<string, { apiKey: string; baseUrl: string }> = {
         baseUrl: "MODELSCOPE_BASE_URL",
     },
     gateway: { apiKey: "AI_GATEWAY_API_KEY", baseUrl: "AI_GATEWAY_BASE_URL" },
-    // bedrock doesn't use API keys in the same way
+    // bedrock and ollama don't use API keys in the same way
     bedrock: { apiKey: "", baseUrl: "" },
-    ollama: { apiKey: "OLLAMA_API_KEY", baseUrl: "OLLAMA_BASE_URL" },
+    ollama: { apiKey: "", baseUrl: "OLLAMA_BASE_URL" },
 }
 
 /**

electron/main/index.ts

@@ -94,8 +94,7 @@ if (!gotTheLock) {
             if (
                 url.includes("diagrams.net") ||
                 url.includes("draw.io") ||
-                url.startsWith("http://localhost") ||
-                url.startsWith("http://127.0.0.1")
+                url.startsWith("http://localhost")
             ) {
                 return { action: "allow" }
             }

electron/main/next-server.ts

@@ -68,7 +68,7 @@ export async function startNextServer(): Promise<string> {
     const env: Record<string, string> = {
         NODE_ENV: "production",
         PORT: String(port),
-        HOSTNAME: "127.0.0.1",
+        HOSTNAME: "localhost",
         // Enable Node.js built-in proxy support for fetch (Node.js 24+)
         NODE_USE_ENV_PROXY: "1",
     }

electron/main/port-manager.ts

@@ -9,11 +9,9 @@ import { app } from "electron"
 const PORT_CONFIG = {
     // Development mode uses fixed port for hot reload compatibility
     development: 6002,
-    // Legacy production port — tried first to preserve localStorage for existing users
-    legacyProduction: 61337,
-    // New production port below the ephemeral range (49152-65535)
-    // to avoid conflicts with Windows Hyper-V / ephemeral port reservations
-    production: 13370,
+    // Production mode uses fixed port (61337) to preserve localStorage
+    // Falls back to sequential ports if unavailable
+    production: 61337,
     // Maximum attempts to find an available port (fallback)
     maxAttempts: 100,
 }
@@ -29,10 +27,7 @@ let allocatedPort: number | null = null
 export function isPortAvailable(port: number): Promise<boolean> {
     return new Promise((resolve) => {
         const server = net.createServer()
-        server.once("error", (err: NodeJS.ErrnoException) => {
-            console.warn(`Port ${port} unavailable: ${err.code}`)
-            resolve(false)
-        })
+        server.once("error", () => resolve(false))
         server.once("listening", () => {
             server.close()
             resolve(true)
@@ -44,12 +39,12 @@ export function isPortAvailable(port: number): Promise<boolean> {
 /**
  * Find an available port
  * - In development: uses fixed port (6002)
- * - In production: uses fixed port (13370) to preserve localStorage
+ * - In production: uses fixed port (61337) to preserve localStorage
  * - Falls back to sequential ports if preferred port is unavailable
- * - Last resort: lets the OS assign a port (port 0)
  *
  * @param reuseExisting If true, try to reuse the previously allocated port
  * @returns Promise<number> The available port
+ * @throws Error if no available port found after max attempts
  */
 export async function findAvailablePort(reuseExisting = true): Promise<number> {
     const isDev = !app.isPackaged
@@ -69,16 +64,7 @@ export async function findAvailablePort(reuseExisting = true): Promise<number> {
         allocatedPort = null
     }
 
-    // In production, try legacy port first to preserve existing users' localStorage
-    if (!isDev) {
-        const legacyPort = PORT_CONFIG.legacyProduction
-        if (await isPortAvailable(legacyPort)) {
-            allocatedPort = legacyPort
-            return legacyPort
-        }
-    }
-
-    // Try preferred port
+    // Try preferred port first
     if (await isPortAvailable(preferredPort)) {
         allocatedPort = preferredPort
         return preferredPort
@@ -98,23 +84,9 @@ export async function findAvailablePort(reuseExisting = true): Promise<number> {
         }
     }
 
-    // Last resort: let the OS pick an available port
-    console.warn(
-        "All sequential ports failed. Requesting OS-assigned port (localStorage may not persist across restarts).",
+    throw new Error(
+        `Failed to find available port after ${PORT_CONFIG.maxAttempts} attempts`,
     )
-    const osPort = await new Promise<number>((resolve, reject) => {
-        const server = net.createServer()
-        server.once("error", reject)
-        server.once("listening", () => {
-            const addr = server.address()
-            const port = (addr as net.AddressInfo).port
-            server.close(() => resolve(port))
-        })
-        server.listen(0, "127.0.0.1")
-    })
-    allocatedPort = osPort
-    console.log(`OS assigned port: ${osPort}`)
-    return osPort
 }
 
 /**
@@ -141,5 +113,5 @@ export function getServerUrl(): string {
             "No port allocated yet. Call findAvailablePort() first.",
         )
     }
-    return `http://127.0.0.1:${allocatedPort}`
+    return `http://localhost:${allocatedPort}`
 }

electron/main/window-manager.ts

@@ -66,11 +66,7 @@ export function createWindow(serverUrl: string): BrowserWindow {
 
     // Handle page title updates
     mainWindow.webContents.on("page-title-updated", (event, title) => {
-        if (
-            title &&
-            !title.includes("localhost") &&
-            !title.includes("127.0.0.1")
-        ) {
+        if (title && !title.includes("localhost")) {
             mainWindow?.setTitle(title)
         } else {
             event.preventDefault()

env.example

@@ -1,6 +1,6 @@
 # AI Provider Configuration
 # AI_PROVIDER: Which provider to use
-# Options: bedrock, openai, anthropic, google, vertexai, azure, ollama, openrouter, deepseek, siliconflow, gateway, novita
+# Options: bedrock, openai, anthropic, google, vertexai, azure, ollama, openrouter, deepseek, siliconflow, gateway
 # Default: bedrock
 AI_PROVIDER=bedrock
 
@@ -59,9 +59,8 @@ AI_MODEL=global.anthropic.claude-sonnet-4-5-20250929-v1:0
 # AZURE_REASONING_EFFORT=low                 # Optional: Azure reasoning effort (low, medium, high)
 # AZURE_REASONING_SUMMARY=detailed
 
-# Ollama Configuration (Local or Cloud)
-# OLLAMA_BASE_URL=https://ollama.com/api  # Optional, defaults to Ollama Cloud
-# OLLAMA_API_KEY=your-ollama-cloud-api-key    # Optional: For Ollama Cloud or authenticated remote instances
+# Ollama (Local) Configuration
+# OLLAMA_BASE_URL=http://localhost:11434/api  # Optional, defaults to localhost
 # OLLAMA_ENABLE_THINKING=true                 # Optional: Enable thinking for models that support it (e.g., qwen3)
 
 # OpenRouter Configuration
@@ -135,40 +134,3 @@ AI_MODEL=global.anthropic.claude-sonnet-4-5-20250929-v1:0
 # Allow private/internal URLs for reverse proxy setups (default: true)
 # Set to "false" to block private IPs, localhost, and internal hostnames
 # ALLOW_PRIVATE_URLS=false
-
-# Self-hosted deployment (Optional)
-# Self-hosted users may implement custom quota-management solutions,
-# which triggers the client UI to display messages suggesting self-hosting or sponsorship.
-# This switch allows self-hosted users to provide custom messages in response to a 429 code,
-# in messageTokenSelfHosted, messageApiSelfHosted, and tipSelfHosted translation strings.
-# NEXT_PUBLIC_SELFHOSTED=true
-
-# Minimax Configuration (Optional)
-# Get your API key from: https://platform.minimaxi.com/docs/guides/models-intro
-# MINIMAX_API_KEY=your_minimax_api_key
-# MINIMAX_BASE_URL=https://api.minimaxi.com/anthropic  # Optional, default (China mainland)
-
-# GLM Configuration (Optional)
-# Get your API key from: https://open.bigmodel.cn/dev/api
-# GLM_API_KEY=your_glm_api_key
-# GLM_BASE_URL=https://open.bigmodel.cn/api/paas/v4  # Optional, default
-
-# Qwen Configuration (Optional)
-# Get your API key from: https://www.aliyun.com/product/bailian
-# QWEN_API_KEY=your_qwen_api_key
-# QWEN_BASE_URL=https://dashscope.aliyuncs.com/compatible-mode/v1  # Optional, default
-
-# Kimi Configuration (Optional)
-# Get your API key from: https://platform.moonshot.cn/
-# KIMI_API_KEY=your_kimi_api_key
-# KIMI_BASE_URL=https://api.moonshot.cn/v1  # Optional, default
-
-# Qiniu Configuration (Optional)
-# Get your API key from: https://www.qiniu.com/ai/models
-# QINIU_API_KEY=your_qiniu_api_key
-# QINIU_BASE_URL=https://api.qnaigc.com/v1  # Optional, default
-
-# Novita AI Configuration (Optional)
-# Get your API key from: https://novita.ai/dashboard/key
-# NOVITA_API_KEY=your_novita_api_key
-# NOVITA_BASE_URL=https://api.novita.ai/openai  # Optional, default

lib/ai-providers.ts

@@ -9,7 +9,7 @@ import { createOpenAI, openai } from "@ai-sdk/openai"
 import { fromNodeProviderChain } from "@aws-sdk/credential-providers"
 import { createOpenRouter } from "@openrouter/ai-sdk-provider"
 import { createOllama, ollama } from "ollama-ai-provider-v2"
-import { PROVIDER_INFO, type ProviderName } from "@/lib/types/model-config"
+import type { ProviderName } from "@/lib/types/model-config"
 
 export type { ProviderName }
 
@@ -18,43 +18,6 @@ interface ModelConfig {
     providerOptions?: any
     headers?: Record<string, string>
     modelId: string
-    provider: ProviderName
-}
-
-// Providers that only support a single system message
-export const SINGLE_SYSTEM_PROVIDERS = new Set<ProviderName>([
-    "minimax",
-    "glm",
-    "qwen",
-    "kimi",
-    "qiniu",
-    "novita",
-])
-
-/**
- * Normalize MiniMax base URL for AI SDK compatibility.
- * MiniMax supports Anthropic-compatible and OpenAI-compatible endpoints.
- */
-export function normalizeMiniMaxBaseURL(rawUrl: string): {
-    baseURL: string
-    isAnthropicCompatible: boolean
-} {
-    const isAnthropicCompatible = rawUrl.includes("/anthropic")
-    let baseURL = rawUrl.replace(/\/$/, "")
-    if (isAnthropicCompatible) {
-        if (!baseURL.endsWith("/anthropic/v1")) {
-            if (baseURL.endsWith("/anthropic")) {
-                baseURL = `${baseURL}/v1`
-            } else {
-                baseURL = `${baseURL}/anthropic/v1`
-            }
-        }
-    } else {
-        if (!baseURL.endsWith("/v1")) {
-            baseURL = `${baseURL}/v1`
-        }
-    }
-    return { baseURL, isAnthropicCompatible }
 }
 
 export interface ClientOverrides {
@@ -94,12 +57,6 @@ const ALLOWED_CLIENT_PROVIDERS: ProviderName[] = [
     "ollama",
     "doubao",
     "modelscope",
-    "glm",
-    "qwen",
-    "qiniu",
-    "kimi",
-    "minimax",
-    "novita",
 ]
 
 // Bedrock provider options for Anthropic beta features
@@ -517,13 +474,7 @@ function buildProviderOptions(
         case "sglang":
         case "gateway":
         case "modelscope":
-        case "doubao":
-        case "minimax":
-        case "glm":
-        case "qwen":
-        case "kimi":
-        case "qiniu":
-        case "novita": {
+        case "doubao": {
             // These providers don't have reasoning configs in AI SDK yet
             // Gateway passes through to underlying providers which handle their own configs
             break
@@ -553,12 +504,6 @@ const PROVIDER_ENV_VARS: Record<ProviderName, string | null> = {
     edgeone: null, // No credentials needed - uses EdgeOne Edge AI
     doubao: "DOUBAO_API_KEY",
     modelscope: "MODELSCOPE_API_KEY",
-    glm: "GLM_API_KEY",
-    qwen: "QWEN_API_KEY",
-    qiniu: "QINIU_API_KEY",
-    kimi: "KIMI_API_KEY",
-    minimax: "MINIMAX_API_KEY",
-    novita: "NOVITA_API_KEY",
 }
 
 /**
@@ -651,7 +596,7 @@ function validateProviderCredentials(
  * - GOOGLE_GENERATIVE_AI_API_KEY: Google API key
  * - AZURE_RESOURCE_NAME, AZURE_API_KEY: Azure OpenAI credentials
  * - AWS_REGION, AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY: AWS Bedrock credentials
- * - OLLAMA_BASE_URL: Ollama server URL (optional, defaults to https://ollama.com/api)
+ * - OLLAMA_BASE_URL: Ollama server URL (optional, defaults to http://localhost:11434)
  * - OPENROUTER_API_KEY: OpenRouter API key
  * - DEEPSEEK_API_KEY: DeepSeek API key
  * - DEEPSEEK_BASE_URL: DeepSeek endpoint (optional)
@@ -666,15 +611,13 @@ export function getAIModel(overrides?: ClientOverrides): ModelConfig {
     // SECURITY: Prevent SSRF attacks (GHSA-9qf7-mprq-9qgm)
     // If a custom baseUrl is provided, an API key MUST also be provided.
     // This prevents attackers from redirecting server API keys to malicious endpoints.
-    // Exception: EdgeOne doesn't require API keys.
-    // Ollama is exempt only when no server OLLAMA_API_KEY is configured;
-    // when it IS configured, the outer guard also enforces client apiKey for custom baseUrls.
+    // Exception: EdgeOne and Ollama providers don't require API keys
     if (
         overrides?.baseUrl &&
         !overrides?.apiKey &&
         !(overrides?.provider === "vertexai" && overrides?.vertexApiKey) &&
         overrides?.provider !== "edgeone" &&
-        !(overrides?.provider === "ollama" && !process.env.OLLAMA_API_KEY)
+        overrides?.provider !== "ollama"
     ) {
         throw new Error(
             `API key is required when using a custom base URL. ` +
@@ -935,19 +878,8 @@ export function getAIModel(overrides?: ClientOverrides): ModelConfig {
 
         case "ollama": {
             const baseURL = overrides?.baseUrl || process.env.OLLAMA_BASE_URL
-            // SECURITY: When client provides a custom base URL, only use
-            // client-provided API key. Never fall back to server OLLAMA_API_KEY
-            // to prevent leaking server credentials to user-controlled endpoints.
-            const apiKey = overrides?.baseUrl
-                ? overrides?.apiKey || undefined
-                : resolveApiKey(overrides, "OLLAMA_API_KEY")
-            if (baseURL || apiKey) {
-                const customOllama = createOllama({
-                    ...(baseURL && { baseURL }),
-                    ...(apiKey && {
-                        headers: { Authorization: `Bearer ${apiKey}` },
-                    }),
-                })
+            if (baseURL) {
+                const customOllama = createOllama({ baseURL })
                 model = customOllama(modelId)
             } else {
                 model = ollama(modelId)
@@ -1227,70 +1159,9 @@ export function getAIModel(overrides?: ClientOverrides): ModelConfig {
             break
         }
 
-        case "minimax": {
-            const apiKey = resolveApiKey(overrides, "MINIMAX_API_KEY")
-            const serverBaseUrl = resolveBaseUrlEnv(
-                overrides,
-                "MINIMAX_BASE_URL",
-            )
-            const rawBaseURL = resolveBaseURL(
-                overrides?.apiKey,
-                overrides?.baseUrl,
-                serverBaseUrl,
-                PROVIDER_INFO.minimax.defaultBaseUrl,
-            )
-
-            if (!rawBaseURL) {
-                throw new Error(
-                    "MiniMax base URL could not be resolved. Set MINIMAX_BASE_URL or configure a base URL in settings.",
-                )
-            }
-
-            const { baseURL, isAnthropicCompatible } =
-                normalizeMiniMaxBaseURL(rawBaseURL)
-
-            if (isAnthropicCompatible) {
-                const minimax = createAnthropic({ apiKey, baseURL })
-                model = minimax.chat(modelId)
-            } else {
-                const minimax = createOpenAI({ apiKey, baseURL })
-                model = minimax.chat(modelId)
-            }
-            break
-        }
-
-        case "glm":
-        case "qwen":
-        case "qiniu":
-        case "kimi":
-        case "novita": {
-            const envVar = PROVIDER_ENV_VARS[provider]
-            if (!envVar) {
-                throw new Error(
-                    `API key environment variable not defined for provider: ${provider}`,
-                )
-            }
-            const apiKey = resolveApiKey(overrides, envVar)
-            const baseURL = resolveBaseURL(
-                overrides?.apiKey,
-                overrides?.baseUrl,
-                resolveBaseUrlEnv(
-                    overrides,
-                    `${provider.toUpperCase()}_BASE_URL`,
-                ),
-                PROVIDER_INFO[provider]?.defaultBaseUrl,
-            )
-            const customProvider = createOpenAI({
-                apiKey,
-                baseURL,
-            })
-            model = customProvider.chat(modelId)
-            break
-        }
-
         default:
             throw new Error(
-                `Unknown AI provider: ${provider}. Supported providers: bedrock, openai, anthropic, google, azure, ollama, openrouter, deepseek, siliconflow, sglang, gateway, edgeone, doubao, modelscope, glm, qwen, qiniu, kimi, minimax, novita`,
+                `Unknown AI provider: ${provider}. Supported providers: bedrock, openai, anthropic, google, azure, ollama, openrouter, deepseek, siliconflow, sglang, gateway, edgeone, doubao, modelscope`,
             )
     }
 
@@ -1299,7 +1170,7 @@ export function getAIModel(overrides?: ClientOverrides): ModelConfig {
         providerOptions = customProviderOptions
     }
 
-    return { model, providerOptions, headers, modelId, provider }
+    return { model, providerOptions, headers, modelId }
 }
 
 /**
@@ -1340,40 +1211,16 @@ export function supportsImageInput(modelId: string): boolean {
         return false
     }
 
-    // Moonshot text models (moonshot-v1 series are text-only)
-    if (lowerModelId.includes("moonshot-v1") && !hasVisionIndicator) {
-        return false
-    }
-
-    // MiniMax text models (MiniMax-M2.x series are text-only)
-    if (lowerModelId.includes("minimax") && !hasVisionIndicator) {
-        return false
-    }
-
     // DeepSeek text models (not vision variants)
     if (lowerModelId.includes("deepseek") && !hasVisionIndicator) {
         return false
     }
 
     // Qwen text models (not vision variants like qwen-vl)
-    // qwen3.5-plus is a vision model
-    if (
-        lowerModelId.includes("qwen") &&
-        !hasVisionIndicator &&
-        !lowerModelId.includes("qwen3.5-plus") &&
-        !lowerModelId.includes("qwen3.5-flash")
-    ) {
+    if (lowerModelId.includes("qwen") && !hasVisionIndicator) {
         return false
     }
 
-    // GLM text models (not vision variants)
-    // GLM vision models: glm-4v, glm-4v-9b, glm-4.1v-9b-thinking
-    if (lowerModelId.includes("glm") && !hasVisionIndicator) {
-        if (!/[\d.]v/.test(lowerModelId)) {
-            return false
-        }
-    }
-
     // Default: assume model supports images
     return true
 }

lib/i18n/dictionaries/en.json

@@ -29,12 +29,7 @@
         "openrouter": "OpenRouter",
         "deepseek": "DeepSeek",
         "siliconflow": "SiliconFlow",
-        "modelscope": "ModelScope",
-        "minimax": "MiniMax",
-        "glm": "GLM",
-        "qwen": "Qwen",
-        "kimi": "Kimi",
-        "qiniu": "Qiniu"
+        "modelscope": "ModelScope"
     },
     "chat": {
         "placeholder": "Describe your diagram or upload a file...",
@@ -126,10 +121,7 @@
         "diagramValidation": "Diagram Validation (Experimental)",
         "diagramValidationDescription": "Use a vision language model to validate generated diagrams. Requires a VLM like GPT-5.2 or Sonnet-4.5.",
         "enabled": "Enabled",
-        "disabled": "Disabled",
-        "customSystemMessage": "Custom System Message",
-        "customSystemMessageDescription": "Add custom instructions appended to the AI's system prompt.",
-        "customSystemMessagePlaceholder": "e.g., Always use blue color scheme for diagrams..."
+        "disabled": "Disabled"
     },
     "save": {
         "title": "Save Diagram",
@@ -187,11 +179,8 @@
         "tpmMessage": "Too many requests. Please wait a moment.",
         "tpmMessageDetailed": "Rate limit reached ({limit} tokens/min). Please wait {seconds} seconds before sending another request.",
         "messageApi": "Looks like you've reached today's demo limit. We're thrilled you're enjoying it, and while ByteDance Doubao generously sponsors this demo, we've had to set a few boundaries to keep things fair for everyone.",
-        "messageApiSelfHosted": null,
         "messageToken": "Looks like you've reached today's token limit. We're thrilled you're enjoying it, and while ByteDance Doubao generously sponsors this demo, we've had to set a few boundaries to keep things fair for everyone.",
-        "messageTokenSelfHosted": null,
         "tip": "<strong>Tip:</strong> You can use your own API key (click the Settings icon) or self-host the project to bypass these limits.",
-        "tipSelfHosted": "<strong>Tip:</strong> You can configure your own API key in the settings to continue using the service.",
         "reset": "Your limit resets tomorrow. Thanks for understanding.",
         "doubaoSponsorship": "<a href=\"{link}\" target=\"_blank\" rel=\"noopener noreferrer\" class=\"underline hover:text-foreground\">Register here</a> to get 500K free tokens per model (including Doubao, DeepSeek and Kimi), then configure your API key in model settings.",
         "configModel": "Use Your API Key",
@@ -317,7 +306,6 @@
         "optional": "(optional)",
         "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",
         "models": "Models",
         "customModelId": "Custom model ID...",
         "allAdded": "All added",

lib/i18n/dictionaries/ja.json

@@ -29,12 +29,7 @@
         "openrouter": "OpenRouter",
         "deepseek": "DeepSeek",
         "siliconflow": "SiliconFlow",
-        "modelscope": "ModelScope",
-        "minimax": "MiniMax",
-        "glm": "GLM",
-        "qwen": "Qwen",
-        "kimi": "Kimi",
-        "qiniu": "Qiniu"
+        "modelscope": "ModelScope"
     },
     "chat": {
         "placeholder": "ダイアグラムを説明するか、ファイルをアップロード...",
@@ -126,10 +121,7 @@
         "diagramValidation": "ダイアグラム検証（実験的）",
         "diagramValidationDescription": "視覚言語モデルを使用して生成されたダイアグラムを検証します。GPT-5.2 や Sonnet-4.5 などの VLM が必要です。",
         "enabled": "有効",
-        "disabled": "無効",
-        "customSystemMessage": "カスタムシステムメッセージ",
-        "customSystemMessageDescription": "AIのシステムプロンプトに追加されるカスタム指示を入力します。",
-        "customSystemMessagePlaceholder": "例：ダイアグラムには常に青色のカラースキームを使用..."
+        "disabled": "無効"
     },
     "save": {
         "title": "ダイアグラムを保存",
@@ -187,11 +179,8 @@
         "tpmMessage": "リクエストが多すぎます。しばらくお待ちください。",
         "tpmMessageDetailed": "レート制限に達しました（{limit}トークン/分）。{seconds}秒待ってからもう一度リクエストしてください。",
         "messageApi": "今日のデモ利用上限に達してしまったようです。楽しんでいただけて本当に嬉しいです。このデモはByteDance Doubaoのご厚意により提供されていますが、皆様に公平にご利用いただくため、少し制限を設けさせていただいております。",
-        "messageApiSelfHosted": null,
         "messageToken": "今日のトークン利用上限に達してしまったようです。楽しんでいただけて本当に嬉しいです。このデモはByteDance Doubaoのご厚意により提供されていますが、皆様に公平にご利用いただくため、少し制限を設けさせていただいております。",
-        "messageTokenSelfHosted": null,
         "tip": "<strong>ヒント：</strong>独自の API キーを使用する（設定アイコンをクリック）か、プロジェクトをセルフホストしてこれらの制限を回避できます。",
-        "tipSelfHosted": "<strong>ヒント：</strong>設定で独自の API キーを設定することで、引き続きサービスをご利用いただけます。",
         "reset": "制限は明日リセットされます。ご理解ありがとうございます。",
         "doubaoSponsorship": "<a href=\"{link}\" target=\"_blank\" rel=\"noopener noreferrer\" class=\"underline hover:text-foreground\">こちらから登録</a>すると、各モデル（Doubao、DeepSeek、Kimi含む）で50万トークンを無料で取得できます。モデル設定でAPIキーを設定してください。",
         "configModel": "APIキーを使用",
@@ -317,7 +306,6 @@
         "optional": "（オプション）",
         "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",
         "models": "モデル",
         "customModelId": "カスタムモデル ID...",
         "allAdded": "すべて追加済み",

lib/i18n/dictionaries/zh-Hant.json

@@ -29,12 +29,7 @@
         "openrouter": "OpenRouter",
         "deepseek": "DeepSeek",
         "siliconflow": "SiliconFlow",
-        "modelscope": "ModelScope",
-        "minimax": "MiniMax",
-        "glm": "GLM",
-        "qwen": "Qwen",
-        "kimi": "Kimi",
-        "qiniu": "Qiniu"
+        "modelscope": "ModelScope"
     },
     "chat": {
         "placeholder": "描述您的圖表或上傳檔案...",
@@ -126,10 +121,7 @@
         "diagramValidation": "圖表驗證（實驗性）",
         "diagramValidationDescription": "使用視覺語言模型驗證產生的圖表。需要支援視覺的模型，如 GPT-5.2 或 Sonnet-4.5。",
         "enabled": "已啟用",
-        "disabled": "已停用",
-        "customSystemMessage": "自訂系統訊息",
-        "customSystemMessageDescription": "新增自訂指示，將附加到 AI 的系統提示末尾。",
-        "customSystemMessagePlaceholder": "例如：圖表始終使用藍色配色方案..."
+        "disabled": "已停用"
     },
     "save": {
         "title": "儲存圖表",
@@ -187,11 +179,8 @@
         "tpmMessage": "請求過多。請稍等片刻。",
         "tpmMessageDetailed": "達到速率限制（{limit} 令牌/分鐘）。請等待 {seconds} 秒後再傳送請求。",
         "messageApi": "看來您今天的體驗次數已達上限。非常高興您玩得開心，雖然本專案由字節跳動豆包慷慨贊助，但為了確保大家都能公平使用，我們不得不對使用量做一點小小的限制。",
-        "messageApiSelfHosted": null,
         "messageToken": "看來您今天的 Token 用量已達上限。非常高興您玩得開心，雖然本專案由字節跳動豆包慷慨贊助，但為了確保大家都能公平使用，我們不得不對使用量做一點小小的限制。",
-        "messageTokenSelfHosted": null,
         "tip": "<strong>提示：</strong>您可以使用自己的 API 金鑰（點擊設定圖示）或自行託管專案來繞過這些限制。",
-        "tipSelfHosted": "<strong>提示：</strong>您可以在設定中配置自己的 API 金鑰以繼續使用服務。",
         "reset": "您的限制將在明天重設。感謝您的理解。",
         "doubaoSponsorship": "<a href=\"{link}\" target=\"_blank\" rel=\"noopener noreferrer\" class=\"underline hover:text-foreground\">點此註冊</a>可獲得每個模型 50 萬免費 Token（包括豆包、DeepSeek 和 Kimi），然後在模型設定中配置您的 API Key。",
         "configModel": "使用您的金鑰",
@@ -317,7 +306,6 @@
         "optional": "（可選）",
         "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",
         "models": "模型",
         "customModelId": "自訂模型 ID...",
         "allAdded": "已全部新增",

lib/i18n/dictionaries/zh.json

@@ -29,12 +29,7 @@
         "openrouter": "OpenRouter",
         "deepseek": "DeepSeek",
         "siliconflow": "SiliconFlow",
-        "modelscope": "ModelScope",
-        "minimax": "MiniMax",
-        "glm": "GLM",
-        "qwen": "Qwen",
-        "kimi": "Kimi",
-        "qiniu": "Qiniu"
+        "modelscope": "ModelScope"
     },
     "chat": {
         "placeholder": "描述您的图表或上传文件...",
@@ -126,10 +121,7 @@
         "diagramValidation": "图表验证（实验性）",
         "diagramValidationDescription": "使用视觉语言模型验证生成的图表。需要支持视觉的模型，如 GPT-5.2 或 Sonnet-4.5。",
         "enabled": "已启用",
-        "disabled": "已禁用",
-        "customSystemMessage": "自定义系统消息",
-        "customSystemMessageDescription": "添加自定义指令，将附加到 AI 的系统提示末尾。",
-        "customSystemMessagePlaceholder": "例如：图表始终使用蓝色配色方案..."
+        "disabled": "已禁用"
     },
     "save": {
         "title": "保存图表",
@@ -187,11 +179,8 @@
         "tpmMessage": "请求过多。请稍等片刻。",
         "tpmMessageDetailed": "达到速率限制（{limit} 令牌/分钟）。请等待 {seconds} 秒后再发送请求。",
         "messageApi": "看来您今天的体验次数已达上限。非常高兴您玩得开心，虽然本项目由字节跳动豆包慷慨赞助，但为了确保大家都能公平使用，我们不得不对使用量做一点小小的限制。",
-        "messageApiSelfHosted": null,
         "messageToken": "看来您今天的 Token 用量已达上限。非常高兴您玩得开心，虽然本项目由字节跳动豆包慷慨赞助，但为了确保大家都能公平使用，我们不得不对使用量做一点小小的限制。",
-        "messageTokenSelfHosted": null,
         "tip": "<strong>提示：</strong>您可以使用自己的 API 密钥（点击设置图标）或自托管项目来绕过这些限制。",
-        "tipSelfHosted": "<strong>提示：</strong>您可以在设置中配置自己的 API 密钥以继续使用服务。",
         "reset": "您的限制将在明天重置。感谢您的理解。",
         "doubaoSponsorship": "<a href=\"{link}\" target=\"_blank\" rel=\"noopener noreferrer\" class=\"underline hover:text-foreground\">点击此处注册</a>可获得每个模型 50 万免费 Token（包括豆包、DeepSeek 和 Kimi），然后在模型设置中配置您的 API Key。",
         "configModel": "使用您的密钥",
@@ -317,7 +306,6 @@
         "optional": "（可选）",
         "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",
         "models": "模型",
         "customModelId": "自定义模型 ID...",
         "allAdded": "已全部添加",

lib/session-storage.ts

@@ -47,33 +47,6 @@ interface ChatSessionDB extends DBSchema {
 
 // Database singleton
 let dbPromise: Promise<IDBPDatabase<ChatSessionDB>> | null = null
-const resetDBPromise = () => {
-    dbPromise = null
-}
-
-const isClosingError = (error: unknown): boolean => {
-    return (
-        error instanceof DOMException &&
-        error.name === "InvalidStateError" &&
-        /closing/i.test(error.message)
-    )
-}
-
-const withDB = async <T>(
-    action: (db: IDBPDatabase<ChatSessionDB>) => Promise<T>,
-): Promise<T> => {
-    try {
-        const db = await getDB()
-        return await action(db)
-    } catch (error) {
-        if (isClosingError(error)) {
-            resetDBPromise()
-            const db = await getDB()
-            return await action(db)
-        }
-        throw error
-    }
-}
 
 async function getDB(): Promise<IDBPDatabase<ChatSessionDB>> {
     if (!dbPromise) {
@@ -87,23 +60,7 @@ async function getDB(): Promise<IDBPDatabase<ChatSessionDB>> {
                 }
                 // Future migrations: if (oldVersion < 2) { ... }
             },
-            terminated() {
-                resetDBPromise()
-            },
         })
-        dbPromise
-            .then((db) => {
-                db.onversionchange = () => {
-                    db.close()
-                    resetDBPromise()
-                }
-                db.onclose = () => {
-                    resetDBPromise()
-                }
-            })
-            .catch(() => {
-                resetDBPromise()
-            })
     }
     return dbPromise
 }
@@ -118,46 +75,31 @@ export function isIndexedDBAvailable(): boolean {
     }
 }
 
-// Check if IndexedDB is actually usable (not just present).
-// Note: Do NOT close the db here - getDB() returns a shared singleton connection
-// that other code depends on.
-export async function isIndexedDBUsable(): Promise<boolean> {
-    if (!isIndexedDBAvailable()) return false
-    try {
-        await getDB()
-        return true
-    } catch {
-        return false
-    }
-}
-
 // CRUD Operations
 export async function getAllSessionMetadata(): Promise<SessionMetadata[]> {
     if (!isIndexedDBAvailable()) return []
     try {
-        return await withDB(async (db) => {
-            const tx = db.transaction(STORE_NAME, "readonly")
-            const index = tx.store.index("by-updated")
-            const metadata: SessionMetadata[] = []
+        const db = await getDB()
+        const tx = db.transaction(STORE_NAME, "readonly")
+        const index = tx.store.index("by-updated")
+        const metadata: SessionMetadata[] = []
 
-            // Use cursor to read only metadata fields (avoids loading full messages/XML)
-            let cursor = await index.openCursor(null, "prev") // newest first
-            while (cursor) {
-                const s = cursor.value
-                metadata.push({
-                    id: s.id,
-                    title: s.title,
-                    createdAt: s.createdAt,
-                    updatedAt: s.updatedAt,
-                    messageCount: s.messages.length,
-                    hasDiagram:
-                        !!s.diagramXml && s.diagramXml.trim().length > 0,
-                    thumbnailDataUrl: s.thumbnailDataUrl,
-                })
-                cursor = await cursor.continue()
-            }
-            return metadata
-        })
+        // Use cursor to read only metadata fields (avoids loading full messages/XML)
+        let cursor = await index.openCursor(null, "prev") // newest first
+        while (cursor) {
+            const s = cursor.value
+            metadata.push({
+                id: s.id,
+                title: s.title,
+                createdAt: s.createdAt,
+                updatedAt: s.updatedAt,
+                messageCount: s.messages.length,
+                hasDiagram: !!s.diagramXml && s.diagramXml.trim().length > 0,
+                thumbnailDataUrl: s.thumbnailDataUrl,
+            })
+            cursor = await cursor.continue()
+        }
+        return metadata
     } catch (error) {
         console.error("Failed to get session metadata:", error)
         return []
@@ -167,9 +109,8 @@ export async function getAllSessionMetadata(): Promise<SessionMetadata[]> {
 export async function getSession(id: string): Promise<ChatSession | null> {
     if (!isIndexedDBAvailable()) return null
     try {
-        return await withDB(async (db) => {
-            return (await db.get(STORE_NAME, id)) || null
-        })
+        const db = await getDB()
+        return (await db.get(STORE_NAME, id)) || null
     } catch (error) {
         console.error("Failed to get session:", error)
         return null
@@ -179,9 +120,8 @@ export async function getSession(id: string): Promise<ChatSession | null> {
 export async function saveSession(session: ChatSession): Promise<boolean> {
     if (!isIndexedDBAvailable()) return false
     try {
-        await withDB(async (db) => {
-            await db.put(STORE_NAME, session)
-        })
+        const db = await getDB()
+        await db.put(STORE_NAME, session)
         return true
     } catch (error) {
         // Handle quota exceeded
@@ -193,9 +133,8 @@ export async function saveSession(session: ChatSession): Promise<boolean> {
             await deleteOldestSession()
             // Retry once
             try {
-                await withDB(async (db) => {
-                    await db.put(STORE_NAME, session)
-                })
+                const db = await getDB()
+                await db.put(STORE_NAME, session)
                 return true
             } catch (retryError) {
                 console.error(
@@ -214,9 +153,8 @@ export async function saveSession(session: ChatSession): Promise<boolean> {
 export async function deleteSession(id: string): Promise<void> {
     if (!isIndexedDBAvailable()) return
     try {
-        await withDB(async (db) => {
-            await db.delete(STORE_NAME, id)
-        })
+        const db = await getDB()
+        await db.delete(STORE_NAME, id)
     } catch (error) {
         console.error("Failed to delete session:", error)
     }
@@ -225,9 +163,8 @@ export async function deleteSession(id: string): Promise<void> {
 export async function getSessionCount(): Promise<number> {
     if (!isIndexedDBAvailable()) return 0
     try {
-        return await withDB(async (db) => {
-            return await db.count(STORE_NAME)
-        })
+        const db = await getDB()
+        return await db.count(STORE_NAME)
     } catch (error) {
         console.error("Failed to get session count:", error)
         return 0
@@ -237,15 +174,14 @@ export async function getSessionCount(): Promise<number> {
 export async function deleteOldestSession(): Promise<void> {
     if (!isIndexedDBAvailable()) return
     try {
-        await withDB(async (db) => {
-            const tx = db.transaction(STORE_NAME, "readwrite")
-            const index = tx.store.index("by-updated")
-            const cursor = await index.openCursor()
-            if (cursor) {
-                await cursor.delete()
-            }
-            await tx.done
-        })
+        const db = await getDB()
+        const tx = db.transaction(STORE_NAME, "readwrite")
+        const index = tx.store.index("by-updated")
+        const cursor = await index.openCursor()
+        if (cursor) {
+            await cursor.delete()
+        }
+        await tx.done
     } catch (error) {
         console.error("Failed to delete oldest session:", error)
     }

lib/storage.ts

@@ -27,7 +27,4 @@ export const STORAGE_KEYS = {
 
     // Diagram validation
     vlmValidationEnabled: "next-ai-draw-io-vlm-validation-enabled",
-
-    // Custom system message
-    customSystemMessage: "next-ai-draw-io-custom-system-message",
 } as const

lib/types/model-config.ts

@@ -16,12 +16,6 @@ export type ProviderName =
     | "edgeone"
     | "doubao"
     | "modelscope"
-    | "glm"
-    | "qwen"
-    | "qiniu"
-    | "kimi"
-    | "minimax"
-    | "novita"
 
 // Individual model configuration
 export interface ModelConfig {
@@ -85,26 +79,6 @@ export interface FlattenedModel {
     baseUrlEnv?: string
 }
 
-// Map provider names to models.dev logo names
-export const PROVIDER_LOGO_MAP: Record<string, string> = {
-    openai: "openai",
-    anthropic: "anthropic",
-    google: "google",
-    azure: "azure",
-    bedrock: "amazon-bedrock",
-    openrouter: "openrouter",
-    deepseek: "deepseek",
-    siliconflow: "siliconflow",
-    sglang: "openai", // SGLang is OpenAI-compatible
-    gateway: "vercel",
-    edgeone: "tencent-cloud",
-    vertexai: "google",
-    doubao: "bytedance",
-    modelscope: "modelscope",
-    minimax: "minimax",
-    novita: "novita",
-}
-
 // Provider metadata
 export const PROVIDER_INFO: Record<
     ProviderName,
@@ -130,7 +104,7 @@ export const PROVIDER_INFO: Record<
     bedrock: { label: "Amazon Bedrock" },
     ollama: {
         label: "Ollama",
-        defaultBaseUrl: "https://ollama.com/api",
+        defaultBaseUrl: "http://localhost:11434",
     },
     openrouter: {
         label: "OpenRouter",
@@ -161,30 +135,6 @@ export const PROVIDER_INFO: Record<
         label: "ModelScope",
         defaultBaseUrl: "https://api-inference.modelscope.cn/v1",
     },
-    glm: {
-        label: "GLM (Zhipu)",
-        defaultBaseUrl: "https://open.bigmodel.cn/api/paas/v4",
-    },
-    qwen: {
-        label: "Qwen (Alibaba)",
-        defaultBaseUrl: "https://dashscope.aliyuncs.com/compatible-mode/v1",
-    },
-    qiniu: {
-        label: "Qiniu",
-        defaultBaseUrl: "https://api.qnaigc.com/v1",
-    },
-    kimi: {
-        label: "Kimi (Moonshot)",
-        defaultBaseUrl: "https://api.moonshot.cn/v1",
-    },
-    minimax: {
-        label: "MiniMax",
-        defaultBaseUrl: "https://api.minimaxi.com/anthropic",
-    },
-    novita: {
-        label: "Novita AI",
-        defaultBaseUrl: "https://api.novita.ai/openai",
-    },
 }
 
 // Suggested models per provider for quick add
@@ -314,7 +264,6 @@ export const SUGGESTED_MODELS: Partial<Record<ProviderName, string[]>> = {
         "Qwen/Qwen2.5-Coder-32B-Instruct",
         "Qwen/Qwen2.5-7B-Instruct",
         "Qwen/Qwen2-VL-72B-Instruct",
-        "qwen3.5-plus",
     ],
     sglang: [
         // SGLang is OpenAI-compatible, models depend on deployment
@@ -344,24 +293,10 @@ export const SUGGESTED_MODELS: Partial<Record<ProviderName, string[]>> = {
         "Qwen/Qwen3-235B-A22B-Instruct-2507",
         "Qwen/Qwen3-VL-235B-A22B-Instruct",
         "Qwen/Qwen3-32B",
-        "qwen3.5-plus",
         // DeepSeek
         "deepseek-ai/DeepSeek-R1-0528",
         "deepseek-ai/DeepSeek-V3.2",
     ],
-    minimax: [
-        // MiniMax models (Anthropic-compatible API)
-        "MiniMax-M2.7",
-        "MiniMax-M2.7-highspeed",
-        "MiniMax-M2.5",
-        "MiniMax-M2.5-highspeed",
-    ],
-    novita: [
-        // Novita AI models (OpenAI-compatible API)
-        "moonshotai/kimi-k2.5",
-        "zai-org/glm-5",
-        "minimax/minimax-m2.5",
-    ],
 }
 
 // Helper to generate UUID

package.json

@@ -1,6 +1,6 @@
 {
     "name": "next-ai-draw-io",
-    "version": "0.4.14",
+    "version": "0.4.12",
     "license": "Apache-2.0",
     "private": true,
     "main": "dist-electron/main/index.js",
@@ -43,15 +43,15 @@
         "@aws-sdk/client-dynamodb": "^3.957.0",
         "@aws-sdk/credential-providers": "^3.943.0",
         "@extractus/article-extractor": "^8.0.18",
-        "@formatjs/intl-localematcher": "^0.8.0",
+        "@formatjs/intl-localematcher": "^0.7.2",
         "@langfuse/client": "^4.4.9",
         "@langfuse/otel": "^4.4.4",
         "@langfuse/tracing": "^4.4.9",
         "@next/third-parties": "^16.0.6",
-        "@opennextjs/cloudflare": "^1.17.1",
+        "@opennextjs/cloudflare": "1.16.1",
         "@openrouter/ai-sdk-provider": "^1.5.4",
         "@opentelemetry/api": "^1.9.0",
-        "@opentelemetry/exporter-trace-otlp-http": "^0.212.0",
+        "@opentelemetry/exporter-trace-otlp-http": "^0.209.0",
         "@opentelemetry/sdk-trace-node": "^2.2.0",
         "@radix-ui/react-alert-dialog": "^1.1.15",
         "@radix-ui/react-collapsible": "^1.1.12",
@@ -72,7 +72,7 @@
         "cmdk": "^1.1.1",
         "idb": "^8.0.3",
         "jsonrepair": "^3.13.1",
-        "lucide-react": "^0.575.0",
+        "lucide-react": "^0.562.0",
         "motion": "^12.23.25",
         "nanoid": "^5.0.0",
         "negotiator": "^1.0.0",
@@ -108,7 +108,7 @@
     },
     "devDependencies": {
         "@anthropic-ai/tokenizer": "^0.0.4",
-        "@biomejs/biome": "2.4.4",
+        "@biomejs/biome": "^2.3.10",
         "@playwright/test": "^1.57.0",
         "@tailwindcss/postcss": "^4",
         "@tailwindcss/typography": "^0.5.19",
@@ -128,7 +128,7 @@
         "electron": "^39.2.7",
         "electron-builder": "^26.0.12",
         "esbuild": "^0.27.2",
-        "eslint": "9.39.3",
+        "eslint": "9.39.2",
         "eslint-config-next": "16.1.6",
         "husky": "^9.1.7",
         "jsdom": "^27.4.0",

packages/mcp-server/package-lock.json

@@ -1,12 +1,12 @@
 {
     "name": "@next-ai-drawio/mcp-server",
-    "version": "0.1.17",
+    "version": "0.1.12",
     "lockfileVersion": 3,
     "requires": true,
     "packages": {
         "": {
             "name": "@next-ai-drawio/mcp-server",
-            "version": "0.1.17",
+            "version": "0.1.12",
             "license": "Apache-2.0",
             "dependencies": {
                 "@modelcontextprotocol/sdk": "^1.0.4",
@@ -469,9 +469,9 @@
             }
         },
         "node_modules/@hono/node-server": {
-            "version": "1.19.9",
-            "resolved": "https://registry.npmjs.org/@hono/node-server/-/node-server-1.19.9.tgz",
-            "integrity": "sha512-vHL6w3ecZsky+8P5MD+eFfaGTyCeOHUIFYMGpQGbrBTSmNNoxv0if69rEZ5giu36weC5saFuznL411gRX7bJDw==",
+            "version": "1.19.7",
+            "resolved": "https://registry.npmjs.org/@hono/node-server/-/node-server-1.19.7.tgz",
+            "integrity": "sha512-vUcD0uauS7EU2caukW8z5lJKtoGMokxNbJtBiwHgpqxEXokaHCBkQUmCHhjFB1VUTWdqj25QoMkMKzgjq+uhrw==",
             "license": "MIT",
             "engines": {
                 "node": ">=18.14.1"
@@ -481,12 +481,12 @@
             }
         },
         "node_modules/@modelcontextprotocol/sdk": {
-            "version": "1.27.1",
-            "resolved": "https://registry.npmjs.org/@modelcontextprotocol/sdk/-/sdk-1.27.1.tgz",
-            "integrity": "sha512-sr6GbP+4edBwFndLbM60gf07z0FQ79gaExpnsjMGePXqFcSSb7t6iscpjk9DhFhwd+mTEQrzNafGP8/iGGFYaA==",
+            "version": "1.25.2",
+            "resolved": "https://registry.npmjs.org/@modelcontextprotocol/sdk/-/sdk-1.25.2.tgz",
+            "integrity": "sha512-LZFeo4F9M5qOhC/Uc1aQSrBHxMrvxett+9KLHt7OhcExtoiRN9DKgbZffMP/nxjutWDQpfMDfP3nkHI4X9ijww==",
             "license": "MIT",
             "dependencies": {
-                "@hono/node-server": "^1.19.9",
+                "@hono/node-server": "^1.19.7",
                 "ajv": "^8.17.1",
                 "ajv-formats": "^3.0.1",
                 "content-type": "^1.0.5",
@@ -494,15 +494,14 @@
                 "cross-spawn": "^7.0.5",
                 "eventsource": "^3.0.2",
                 "eventsource-parser": "^3.0.0",
-                "express": "^5.2.1",
-                "express-rate-limit": "^8.2.1",
-                "hono": "^4.11.4",
-                "jose": "^6.1.3",
+                "express": "^5.0.1",
+                "express-rate-limit": "^7.5.0",
+                "jose": "^6.1.1",
                 "json-schema-typed": "^8.0.2",
                 "pkce-challenge": "^5.0.0",
                 "raw-body": "^3.0.0",
                 "zod": "^3.25 || ^4.0",
-                "zod-to-json-schema": "^3.25.1"
+                "zod-to-json-schema": "^3.25.0"
             },
             "engines": {
                 "node": ">=18"
@@ -521,9 +520,9 @@
             }
         },
         "node_modules/@types/node": {
-            "version": "24.11.0",
-            "resolved": "https://registry.npmjs.org/@types/node/-/node-24.11.0.tgz",
-            "integrity": "sha512-fPxQqz4VTgPI/IQ+lj9r0h+fDR66bzoeMGHp8ASee+32OSGIkeASsoZuJixsQoVef1QJbeubcPBxKk22QVoWdw==",
+            "version": "24.10.6",
+            "resolved": "https://registry.npmjs.org/@types/node/-/node-24.10.6.tgz",
+            "integrity": "sha512-B8h60xgJMR/xmgyX9fncRzEW9gCxoJjdenUhke2v1JGOd/V66KopmWrLPXi5oUI4VuiGK+d+HlXJjDRZMj21EQ==",
             "dev": true,
             "license": "MIT",
             "dependencies": {
@@ -1035,6 +1034,7 @@
             "resolved": "https://registry.npmjs.org/express/-/express-5.2.1.tgz",
             "integrity": "sha512-hIS4idWWai69NezIdRt2xFVofaF4j+6INOpJlVOLDO8zXGpUVEVzIYk12UUi2JzjEzWL3IOAxcTubgz9Po0yXw==",
             "license": "MIT",
+            "peer": true,
             "dependencies": {
                 "accepts": "^2.0.0",
                 "body-parser": "^2.2.1",
@@ -1074,13 +1074,10 @@
             }
         },
         "node_modules/express-rate-limit": {
-            "version": "8.2.1",
-            "resolved": "https://registry.npmjs.org/express-rate-limit/-/express-rate-limit-8.2.1.tgz",
-            "integrity": "sha512-PCZEIEIxqwhzw4KF0n7QF4QqruVTcF73O5kFKUnGOyjbCCgizBBiFaYpd/fnBLUMPw/BWw9OsiN7GgrNYr7j6g==",
+            "version": "7.5.1",
+            "resolved": "https://registry.npmjs.org/express-rate-limit/-/express-rate-limit-7.5.1.tgz",
+            "integrity": "sha512-7iN8iPMDzOMHPUYllBEsQdWVB6fPDMPqwjBaFrgr4Jgr/+okjvzAy+UHlYYL/Vs0OsOrMkwS6PJDkFlJwoxUnw==",
             "license": "MIT",
-            "dependencies": {
-                "ip-address": "10.0.1"
-            },
             "engines": {
                 "node": ">= 16"
             },
@@ -1263,10 +1260,11 @@
             }
         },
         "node_modules/hono": {
-            "version": "4.11.9",
-            "resolved": "https://registry.npmjs.org/hono/-/hono-4.11.9.tgz",
-            "integrity": "sha512-Eaw2YTGM6WOxA6CXbckaEvslr2Ne4NFsKrvc0v97JD5awbmeBLO5w9Ho9L9kmKonrwF9RJlW6BxT1PVv/agBHQ==",
+            "version": "4.11.1",
+            "resolved": "https://registry.npmjs.org/hono/-/hono-4.11.1.tgz",
+            "integrity": "sha512-KsFcH0xxHes0J4zaQgWbYwmz3UPOOskdqZmItstUG93+Wk1ePBLkLGwbP9zlmh1BFUiL8Qp+Xfu9P7feJWpGNg==",
             "license": "MIT",
+            "peer": true,
             "engines": {
                 "node": ">=16.9.0"
             }
@@ -1350,15 +1348,6 @@
             "integrity": "sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ==",
             "license": "ISC"
         },
-        "node_modules/ip-address": {
-            "version": "10.0.1",
-            "resolved": "https://registry.npmjs.org/ip-address/-/ip-address-10.0.1.tgz",
-            "integrity": "sha512-NWv9YLW4PoW2B7xtzaS3NCot75m6nK7Icdv0o3lfMceJVRfSoQwqD4wEH5rLwoKJwUiZ/rfpiVBhnaF0FK4HoA==",
-            "license": "MIT",
-            "engines": {
-                "node": ">= 12"
-            }
-        },
         "node_modules/ipaddr.js": {
             "version": "1.9.1",
             "resolved": "https://registry.npmjs.org/ipaddr.js/-/ipaddr.js-1.9.1.tgz",
@@ -2062,18 +2051,19 @@
             }
         },
         "node_modules/zod": {
-            "version": "4.3.6",
-            "resolved": "https://registry.npmjs.org/zod/-/zod-4.3.6.tgz",
-            "integrity": "sha512-rftlrkhHZOcjDwkGlnUtZZkvaPHCsDATp4pGpuOOMDaTdDDXF91wuVDJoWoPsKX/3YPQ5fHuF3STjcYyKr+Qhg==",
+            "version": "4.3.5",
+            "resolved": "https://registry.npmjs.org/zod/-/zod-4.3.5.tgz",
+            "integrity": "sha512-k7Nwx6vuWx1IJ9Bjuf4Zt1PEllcwe7cls3VNzm4CQ1/hgtFUK2bRNG3rvnpPUhFjmqJKAKtjV576KnUkHocg/g==",
             "license": "MIT",
+            "peer": true,
             "funding": {
                 "url": "https://github.com/sponsors/colinhacks"
             }
         },
         "node_modules/zod-to-json-schema": {
-            "version": "3.25.1",
-            "resolved": "https://registry.npmjs.org/zod-to-json-schema/-/zod-to-json-schema-3.25.1.tgz",
-            "integrity": "sha512-pM/SU9d3YAggzi6MtR4h7ruuQlqKtad8e9S0fmxcMi+ueAK5Korys/aWcV9LIIHTVbj01NdzxcnXSN+O74ZIVA==",
+            "version": "3.25.0",
+            "resolved": "https://registry.npmjs.org/zod-to-json-schema/-/zod-to-json-schema-3.25.0.tgz",
+            "integrity": "sha512-HvWtU2UG41LALjajJrML6uQejQhNJx+JBO9IflpSja4R03iNWfKXrj6W2h7ljuLyc1nKS+9yDyL/9tD1U/yBnQ==",
             "license": "ISC",
             "peerDependencies": {
                 "zod": "^3.25 || ^4"

packages/mcp-server/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@next-ai-drawio/mcp-server",
-    "version": "0.1.17",
+    "version": "0.1.16",
     "description": "MCP server for Next AI Draw.io - AI-powered diagram generation with real-time browser preview",
     "type": "module",
     "main": "dist/index.js",

packages/mcp-server/src/http-server.ts

@@ -198,12 +198,9 @@ function handleRequest(
 ): void {
     const url = new URL(req.url || "/", `http://localhost:${serverPort}`)
 
-    const requestOrigin = req.headers.origin
-    if (requestOrigin === `http://localhost:${serverPort}`) {
-        res.setHeader("Access-Control-Allow-Origin", requestOrigin)
-        res.setHeader("Access-Control-Allow-Methods", "GET, POST, OPTIONS")
-        res.setHeader("Access-Control-Allow-Headers", "Content-Type")
-    }
+    res.setHeader("Access-Control-Allow-Origin", "*")
+    res.setHeader("Access-Control-Allow-Methods", "GET, POST, OPTIONS")
+    res.setHeader("Access-Control-Allow-Headers", "Content-Type")
 
     if (req.method === "OPTIONS") {
         res.writeHead(204)

tests/e2e/history-restore.spec.ts

@@ -1,6 +1,7 @@
 import { SINGLE_BOX_XML } from "./fixtures/diagrams"
 import {
     expect,
+    expectBeforeAndAfterReload,
     getChatInput,
     getIframe,
     getIframeContent,

tests/e2e/iframe-interaction.spec.ts

@@ -1,6 +1,7 @@
 import { TEST_NODE_XML } from "./fixtures/diagrams"
 import {
     expect,
+    getChatInput,
     getIframe,
     getIframeContent,
     sendMessage,

tests/e2e/language.spec.ts

@@ -1,5 +1,6 @@
 import {
     expect,
+    expectBeforeAndAfterReload,
     getChatInput,
     getIframe,
     openSettings,

tests/e2e/multi-turn.spec.ts

@@ -3,6 +3,7 @@ import {
     createMixedMock,
     createMultiTurnMock,
     expect,
+    getChatInput,
     sendMessage,
     test,
     waitForComplete,

tests/e2e/settings.spec.ts

@@ -1,4 +1,10 @@
-import { expect, getIframe, openSettings, test } from "./lib/fixtures"
+import {
+    expect,
+    getIframe,
+    getSettingsButton,
+    openSettings,
+    test,
+} from "./lib/fixtures"
 
 test.describe("Settings", () => {
     test.beforeEach(async ({ page }) => {

tests/unit/ai-providers.test.ts

@@ -1,6 +1,5 @@
-import { afterEach, beforeEach, describe, expect, it, vi } from "vitest"
+import { describe, expect, it } from "vitest"
 import {
-    getAIModel,
     resolveBaseURL,
     supportsImageInput,
     supportsPromptCaching,
@@ -174,19 +173,6 @@ describe("supportsImageInput", () => {
         expect(supportsImageInput("moonshotai/kimi-k2.5")).toBe(true)
     })
 
-    it("returns false for Moonshot v1 text models", () => {
-        expect(supportsImageInput("moonshot-v1-8k")).toBe(false)
-        expect(supportsImageInput("moonshot-v1-32k")).toBe(false)
-        expect(supportsImageInput("moonshot-v1-128k")).toBe(false)
-    })
-
-    it("returns false for MiniMax text models", () => {
-        expect(supportsImageInput("MiniMax-M2.7")).toBe(false)
-        expect(supportsImageInput("MiniMax-M2.5")).toBe(false)
-        expect(supportsImageInput("MiniMax-M2")).toBe(false)
-        expect(supportsImageInput("MiniMax-M2.5-highspeed")).toBe(false)
-    })
-
     it("returns false for DeepSeek text models", () => {
         expect(supportsImageInput("deepseek-chat")).toBe(false)
         expect(supportsImageInput("deepseek-coder")).toBe(false)
@@ -195,30 +181,6 @@ describe("supportsImageInput", () => {
     it("returns false for Qwen text models", () => {
         expect(supportsImageInput("qwen-turbo")).toBe(false)
         expect(supportsImageInput("qwen-plus")).toBe(false)
-        expect(supportsImageInput("qwen3-max")).toBe(false)
-    })
-
-    it("returns true for Qwen vision models", () => {
-        expect(supportsImageInput("qwen-vl")).toBe(true)
-        expect(supportsImageInput("qwen3.5-plus")).toBe(true)
-        expect(supportsImageInput("qwen3.5-flash")).toBe(true)
-        expect(supportsImageInput("qwen3-vl-plus")).toBe(true)
-        expect(supportsImageInput("qwen3-vl-flash")).toBe(true)
-    })
-
-    it("returns false for GLM text models", () => {
-        expect(supportsImageInput("glm-4")).toBe(false)
-        expect(supportsImageInput("glm-4-plus")).toBe(false)
-        expect(supportsImageInput("glm-4-flash")).toBe(false)
-        expect(supportsImageInput("glm-4-long")).toBe(false)
-        expect(supportsImageInput("glm-4.7")).toBe(false)
-        expect(supportsImageInput("glm-5")).toBe(false)
-    })
-
-    it("returns true for GLM vision models", () => {
-        expect(supportsImageInput("glm-4v")).toBe(true)
-        expect(supportsImageInput("glm-4v-9b")).toBe(true)
-        expect(supportsImageInput("glm-4.1v-9b-thinking")).toBe(true)
     })
 
     it("returns true for Claude and GPT models by default", () => {
@@ -227,120 +189,3 @@ describe("supportsImageInput", () => {
         expect(supportsImageInput("gemini-pro")).toBe(true)
     })
 })
-
-vi.mock("ollama-ai-provider-v2", () => {
-    const mockModel = { modelId: "test-model" }
-    const mockProviderFn = vi.fn(() => mockModel)
-    const mockCreateOllama = vi.fn(() => mockProviderFn)
-    const mockOllama = vi.fn(() => mockModel)
-    return { createOllama: mockCreateOllama, ollama: mockOllama }
-})
-
-describe("Ollama API key security", () => {
-    let createOllamaMock: ReturnType<typeof vi.fn>
-    const savedEnv: Record<string, string | undefined> = {}
-
-    beforeEach(async () => {
-        savedEnv.OLLAMA_API_KEY = process.env.OLLAMA_API_KEY
-        savedEnv.OLLAMA_BASE_URL = process.env.OLLAMA_BASE_URL
-        delete process.env.OLLAMA_BASE_URL
-
-        const mod = await import("ollama-ai-provider-v2")
-        createOllamaMock = mod.createOllama as ReturnType<typeof vi.fn>
-        createOllamaMock.mockClear()
-    })
-
-    afterEach(() => {
-        process.env.OLLAMA_API_KEY = savedEnv.OLLAMA_API_KEY
-        process.env.OLLAMA_BASE_URL = savedEnv.OLLAMA_BASE_URL
-    })
-
-    it("applies server OLLAMA_API_KEY when no client baseUrl is provided", () => {
-        process.env.OLLAMA_API_KEY = "server-secret-key"
-
-        getAIModel({ provider: "ollama", modelId: "llama2" })
-
-        expect(createOllamaMock).toHaveBeenCalledWith(
-            expect.objectContaining({
-                headers: { Authorization: "Bearer server-secret-key" },
-            }),
-        )
-    })
-
-    it("does NOT leak server OLLAMA_API_KEY when client provides a custom baseUrl", () => {
-        process.env.OLLAMA_API_KEY = "server-secret-key"
-
-        // When server has OLLAMA_API_KEY, the SSRF guard rejects
-        // client-provided baseUrl without an apiKey outright
-        expect(() =>
-            getAIModel({
-                provider: "ollama",
-                baseUrl: "https://evil-server.com",
-                modelId: "llama2",
-            }),
-        ).toThrow("API key is required")
-    })
-
-    it("uses client API key when client provides both baseUrl and apiKey", () => {
-        process.env.OLLAMA_API_KEY = "server-secret-key"
-
-        getAIModel({
-            provider: "ollama",
-            baseUrl: "https://my-ollama.com",
-            apiKey: "client-key",
-            modelId: "llama2",
-        })
-
-        expect(createOllamaMock).toHaveBeenCalledWith(
-            expect.objectContaining({
-                baseURL: "https://my-ollama.com",
-                headers: { Authorization: "Bearer client-key" },
-            }),
-        )
-    })
-
-    it("applies both server OLLAMA_BASE_URL and OLLAMA_API_KEY when no client overrides", () => {
-        process.env.OLLAMA_BASE_URL = "https://cloud.ollama.com"
-        process.env.OLLAMA_API_KEY = "server-key"
-
-        getAIModel({ provider: "ollama", modelId: "llama2" })
-
-        expect(createOllamaMock).toHaveBeenCalledWith(
-            expect.objectContaining({
-                baseURL: "https://cloud.ollama.com",
-                headers: { Authorization: "Bearer server-key" },
-            }),
-        )
-    })
-
-    it("works when OLLAMA_API_KEY is set but OLLAMA_BASE_URL is not", () => {
-        process.env.OLLAMA_API_KEY = "server-key"
-        delete process.env.OLLAMA_BASE_URL
-
-        getAIModel({ provider: "ollama", modelId: "llama2" })
-
-        expect(createOllamaMock).toHaveBeenCalledTimes(1)
-        const callArgs = createOllamaMock.mock.calls[0][0]
-        expect(callArgs).not.toHaveProperty("baseURL")
-        expect(callArgs).toEqual(
-            expect.objectContaining({
-                headers: { Authorization: "Bearer server-key" },
-            }),
-        )
-    })
-
-    it("allows client custom baseUrl without apiKey when no server OLLAMA_API_KEY", () => {
-        delete process.env.OLLAMA_API_KEY
-
-        getAIModel({
-            provider: "ollama",
-            baseUrl: "https://my-ollama.com",
-            modelId: "llama2",
-        })
-
-        expect(createOllamaMock).toHaveBeenCalledTimes(1)
-        const callArgs = createOllamaMock.mock.calls[0][0]
-        expect(callArgs.baseURL).toBe("https://my-ollama.com")
-        expect(callArgs).not.toHaveProperty("headers")
-    })
-})