Compare commits

..

8 Commits

Author SHA1 Message Date
dayuan.jiang
9ea48a8426 fix: improve create_new_diagram tool description to prevent misuse and bump to v0.2.0 2026-04-10 17:11:10 +09:00
Dayuan Jiang
0cd1260172 fix: show all enabled panels on chat lobby instead of only templates (#802) 2026-04-10 14:33:56 +09:00
Khanh Thanh
49bfb51b10 feat: Update some tool demos in english about page (#598)
* feat: update about page examples with new diagrams

Replace old cloud architecture and cat examples with ResNet50, RAG,
Authentication, Agile Scrum, and Open Innovation diagrams.
Update all three language versions (EN, CN, JA) for consistency.

* fix: correct ResNet50 prompt text and keep prompts in English

Update the ResNet50 example prompt to match the actual diagram.
Keep all prompt texts in English across CN and JA about pages
since prompts are what users type into the AI.

* docs: update README examples to match about page

Replace GCP, AWS, Azure examples with ResNet50, RAG, Auth,
Agile Scrum, and Open Innovation. Keep Animated Transformer
and Cat Sketch. Keep prompts in English across all versions.

* docs: remove ResNet50 and Agile Scrum examples from READMEs

---------

Co-authored-by: dayuan.jiang <jdy.toh@gmail.com>
2026-04-10 13:11:34 +09:00
Dayuan Jiang
ccd9c1f48e fix: reduce CPU usage during large XML streaming (#801)
* fix: reduce CPU usage during large XML streaming

Skip Prism syntax highlighting while tool call is streaming — use plain
<pre> during streaming and only run Prism once at completion. Also throttle
scrollIntoView to once per 150ms to avoid layout thrashing.

Profiled with Playwright + CDP: for 200-cell diagrams the longest
browser task dropped from 6.7s to ~450ms and total long-task time
fell from ~10.9s to ~1.1s.

* fix: add trailing edge to scroll throttle

Ensures the chat scrolls to the bottom after streaming ends, even if
the last messages update arrives during the 150ms throttle window.
2026-04-10 11:12:50 +09:00
Octopus
622aa8683d fix: remove redundant status(modified:false) call to restore undo/redo (fixes #779) (#780) 2026-04-10 10:30:05 +09:00
Octopus
43ddb7a999 fix: allow Qwen3.5 models to use image input (fixes #799) (#800)
Qwen3.5 models deployed via vLLM natively support image input, but the
supportsImageInput() check was incorrectly blocking them. The function
only exempted qwen3.5-plus and qwen3.5-flash variants, missing the base
qwen3.5 model name.

Simplify the exception to cover all qwen3.5 variants with a single
substring check on "qwen3.5", since it is a common prefix of all three.

Co-authored-by: octo-patch <octo-patch@github.com>
2026-04-10 10:23:39 +09:00
Dayuan Jiang
b9fdf9538c chore: remove MCP preview labels (#790)
MCP server is no longer in preview. Remove "(Preview)" headings from
READMEs, the purple PREVIEW badge from the UI, and the preview i18n keys.
2026-04-06 10:17:38 +09:00
Dayuan Jiang
1f31692701 chore: always bundle latest draw.io version in Electron builds (#792)
Remove pinned v29.3.5 tag so the build always clones the latest draw.io.
This adds the Animated GIF export and other new features to the Electron app.

Closes #770
2026-04-06 10:14:50 +09:00
26 changed files with 322 additions and 261 deletions

View File

@@ -31,7 +31,7 @@ https://github.com/user-attachments/assets/9d60a3e8-4a1c-4b5e-acbb-26af2d3eabd1
- [Table of Contents](#table-of-contents) - [Table of Contents](#table-of-contents)
- [Examples](#examples) - [Examples](#examples)
- [Features](#features) - [Features](#features)
- [MCP Server (Preview)](#mcp-server-preview) - [MCP Server](#mcp-server)
- [Claude Code CLI](#claude-code-cli) - [Claude Code CLI](#claude-code-cli)
- [Getting Started](#getting-started) - [Getting Started](#getting-started)
- [Try it Online](#try-it-online) - [Try it Online](#try-it-online)
@@ -63,24 +63,24 @@ Here are some example prompts and their generated diagrams:
</tr> </tr>
<tr> <tr>
<td width="50%" valign="top"> <td width="50%" valign="top">
<strong>GCP architecture diagram</strong><br /> <strong>RAG Technique Diagram</strong><br />
<p><strong>Prompt:</strong> Generate a GCP architecture diagram with **GCP icons**. In this diagram, users connect to a frontend hosted on an instance.</p> <p><strong>Prompt:</strong> Generate a RAG architecture diagram for **chat application**. Use connected diagram for data ingestion</p>
<img src="./public/gcp_demo.svg" alt="GCP Architecture Diagram" width="480" /> <img src="./public/rag_prod.svg" alt="RAG Architecture Diagram" width="480" />
</td> </td>
<td width="50%" valign="top"> <td width="50%" valign="top">
<strong>AWS architecture diagram</strong><br /> <strong>Authentication using React and AWS</strong><br />
<p><strong>Prompt:</strong> Generate a AWS architecture diagram with **AWS icons**. In this diagram, users connect to a frontend hosted on an instance.</p> <p><strong>Prompt:</strong> Generate authentication process using React with **AWS**. Use Serverless architecture.</p>
<img src="./public/aws_demo.svg" alt="AWS Architecture Diagram" width="480" /> <img src="./public/auth.svg" alt="Authentication Architecture Diagram" width="480" />
</td> </td>
</tr> </tr>
<tr> <tr>
<td width="50%" valign="top"> <td width="50%" valign="top">
<strong>Azure architecture diagram</strong><br /> <strong>Open Innovation</strong><br />
<p><strong>Prompt:</strong> Generate a Azure architecture diagram with **Azure icons**. In this diagram, users connect to a frontend hosted on an instance.</p> <p><strong>Prompt:</strong> Create visualization of Henry Chesbrough's Open Innovation model.</p>
<img src="./public/azure_demo.svg" alt="Azure Architecture Diagram" width="480" /> <img src="./public/inno.svg" alt="Open Innovation Diagram" width="480" />
</td> </td>
<td width="50%" valign="top"> <td width="50%" valign="top">
<strong>Cat sketch prompt</strong><br /> <strong>Cat sketch</strong><br />
<p><strong>Prompt:</strong> Draw a cute cat for me.</p> <p><strong>Prompt:</strong> Draw a cute cat for me.</p>
<img src="./public/cat_demo.svg" alt="Cat Drawing" width="240" /> <img src="./public/cat_demo.svg" alt="Cat Drawing" width="240" />
</td> </td>
@@ -99,9 +99,7 @@ Here are some example prompts and their generated diagrams:
- **Cloud Architecture Diagram Support**: Specialized support for generating cloud architecture diagrams (AWS, GCP, Azure) - **Cloud Architecture Diagram Support**: Specialized support for generating cloud architecture diagrams (AWS, GCP, Azure)
- **Animated Connectors**: Create dynamic and animated connectors between diagram elements for better visualization - **Animated Connectors**: Create dynamic and animated connectors between diagram elements for better visualization
## MCP Server (Preview) ## MCP Server
> **Preview Feature**: This feature is experimental and may not be stable.
Use Next AI Draw.io with AI agents like Claude Desktop, Cursor, and VS Code via MCP (Model Context Protocol). Use Next AI Draw.io with AI agents like Claude Desktop, Cursor, and VS Code via MCP (Model Context Protocol).

View File

@@ -175,92 +175,106 @@ export default function AboutCN() {
</p> </p>
<div className="space-y-8"> <div className="space-y-8">
{/* Animated Transformer */} {/* ResNet50 Architecture */}
<div className="text-center"> <div className="text-center">
<h3 className="text-lg font-semibold text-gray-900 mb-2"> <h3 className="text-lg font-semibold text-gray-900 mb-2">
Transformer连接器 ResNet50模型架构动画
</h3> </h3>
<p className="text-gray-600 mb-4"> <p className="text-gray-600 mb-4">
<strong></strong> <strong>Prompt:</strong> Give me an{" "}
<strong></strong>Transformer架构图 <strong>animated</strong> architecture diagram
of the ResNet50 model.
</p> </p>
<Image <div className="bg-neutral-950 rounded-lg p-4 inline-block">
src="/animated_connectors.svg" <Image
alt="带动画连接器的Transformer架构" src="/resnet50.svg"
width={480} alt="ResNet50模型架构图"
height={360} width={480}
className="mx-auto" height={360}
/> className="mx-auto"
/>
</div>
</div> </div>
{/* Cloud Architecture Grid */} {/* Diagram Grid */}
<div className="grid md:grid-cols-2 gap-6"> <div className="grid md:grid-cols-2 gap-6">
<div className="text-center"> <div className="text-center">
<h3 className="text-lg font-semibold text-gray-900 mb-2"> <h3 className="text-lg font-semibold text-gray-900 mb-2">
GCP架构 RAG技术
</h3> </h3>
<p className="text-gray-600 text-sm mb-4"> <p className="text-gray-600 text-sm mb-4">
<strong></strong> 使 <strong>Prompt:</strong> Generate a RAG
<strong>GCP图标</strong> architecture diagram for{" "}
GCP架构图 <strong>chat application</strong>. Use
connected diagram for data ingestion
</p> </p>
<Image <div className="bg-neutral-950 rounded-lg p-4 flex items-center justify-center w-full h-[400px]">
src="/gcp_demo.svg" <Image
alt="GCP架构图" src="/rag_prod.svg"
width={400} alt="RAG架构图"
height={300} width={480}
className="mx-auto" height={360}
/> className="max-w-full max-h-full object-contain"
/>
</div>
</div> </div>
<div className="text-center"> <div className="text-center">
<h3 className="text-lg font-semibold text-gray-900 mb-2"> <h3 className="text-lg font-semibold text-gray-900 mb-2">
AWS架构图 React和AWS认证流程
</h3> </h3>
<p className="text-gray-600 text-sm mb-4"> <p className="text-gray-600 text-sm mb-4">
<strong></strong> 使 <strong>Prompt:</strong> Generate
<strong>AWS图标</strong> authentication process using React with{" "}
AWS架构图 <strong>AWS</strong>. Use Serverless
architecture.
</p> </p>
<Image <div className="bg-neutral-950 rounded-lg p-4 flex items-center justify-center w-full h-[400px]">
src="/aws_demo.svg" <Image
alt="AWS架构图" src="/auth.svg"
width={400} alt="认证架构图"
height={300} width={480}
className="mx-auto" height={360}
/> className="max-w-full max-h-full object-contain"
/>
</div>
</div> </div>
<div className="text-center"> <div className="text-center">
<h3 className="text-lg font-semibold text-gray-900 mb-2"> <h3 className="text-lg font-semibold text-gray-900 mb-2">
Azure架构图 Scrum流程
</h3> </h3>
<p className="text-gray-600 text-sm mb-4"> <p className="text-gray-600 text-sm mb-4">
<strong></strong> 使 <strong>Prompt:</strong> Generate agile
<strong>Azure图标</strong> scrum workflow diagram for software
Azure架构图 development team.
</p> </p>
<Image <div className="bg-neutral-950 rounded-lg p-4 flex items-center justify-center w-full h-[400px]">
src="/azure_demo.svg" <Image
alt="Azure架构图" src="/agile_scrum.svg"
width={400} alt="敏捷Scrum流程图"
height={300} width={480}
className="mx-auto" height={360}
/> className="max-w-full max-h-full object-contain"
/>
</div>
</div> </div>
<div className="text-center"> <div className="text-center">
<h3 className="text-lg font-semibold text-gray-900 mb-2"> <h3 className="text-lg font-semibold text-gray-900 mb-2">
</h3> </h3>
<p className="text-gray-600 text-sm mb-4"> <p className="text-gray-600 text-sm mb-4">
<strong></strong>{" "} <strong>Prompt:</strong> Create
visualization of Henry Chesbrough&apos;s
Open Innovation model.
</p> </p>
<Image <div className="bg-neutral-950 rounded-lg p-4 flex items-center justify-center w-full h-[400px]">
src="/cat_demo.svg" <Image
alt="猫咪绘图" src="/inno.svg"
width={240} alt="开放式创新图"
height={240} width={480}
className="mx-auto" height={360}
/> className="max-w-full max-h-full object-contain"
/>
</div>
</div> </div>
</div> </div>
</div> </div>

View File

@@ -168,93 +168,106 @@ export default function AboutJA() {
</p> </p>
<div className="space-y-8"> <div className="space-y-8">
{/* Animated Transformer */} {/* ResNet50 Architecture */}
<div className="text-center"> <div className="text-center">
<h3 className="text-lg font-semibold text-gray-900 mb-2"> <h3 className="text-lg font-semibold text-gray-900 mb-2">
Transformerコネクタ ResNet50モデルアーキテクチャアニメーション
</h3> </h3>
<p className="text-gray-600 mb-4"> <p className="text-gray-600 mb-4">
<strong></strong>{" "} <strong>Prompt:</strong> Give me an{" "}
<strong></strong> <strong>animated</strong> architecture diagram
Transformerアーキテクチャ図を作成してください of the ResNet50 model.
</p> </p>
<Image <div className="bg-neutral-950 rounded-lg p-4 inline-block">
src="/animated_connectors.svg" <Image
alt="アニメーションコネクタ付きTransformerアーキテクチャ" src="/resnet50.svg"
width={480} alt="ResNet50モデルアーキテクチャ図"
height={360} width={480}
className="mx-auto" height={360}
/> className="mx-auto"
/>
</div>
</div> </div>
{/* Cloud Architecture Grid */} {/* Diagram Grid */}
<div className="grid md:grid-cols-2 gap-6"> <div className="grid md:grid-cols-2 gap-6">
<div className="text-center"> <div className="text-center">
<h3 className="text-lg font-semibold text-gray-900 mb-2"> <h3 className="text-lg font-semibold text-gray-900 mb-2">
GCPアーキテクチャ図 RAG技術ダイアグラム
</h3> </h3>
<p className="text-gray-600 text-sm mb-4"> <p className="text-gray-600 text-sm mb-4">
<strong></strong>{" "} <strong>Prompt:</strong> Generate a RAG
<strong>GCPアイコン</strong> architecture diagram for{" "}
使GCPアーキテクチャ図を生成してください <strong>chat application</strong>. Use
connected diagram for data ingestion
</p> </p>
<Image <div className="bg-neutral-950 rounded-lg p-4 flex items-center justify-center w-full h-[400px]">
src="/gcp_demo.svg" <Image
alt="GCPアーキテクチャ図" src="/rag_prod.svg"
width={400} alt="RAGアーキテクチャ図"
height={300} width={480}
className="mx-auto" height={360}
/> className="max-w-full max-h-full object-contain"
/>
</div>
</div> </div>
<div className="text-center"> <div className="text-center">
<h3 className="text-lg font-semibold text-gray-900 mb-2"> <h3 className="text-lg font-semibold text-gray-900 mb-2">
AWSアーキテクチャ図 ReactとAWSによる認証
</h3> </h3>
<p className="text-gray-600 text-sm mb-4"> <p className="text-gray-600 text-sm mb-4">
<strong></strong>{" "} <strong>Prompt:</strong> Generate
<strong>AWSアイコン</strong> authentication process using React with{" "}
使AWSアーキテクチャ図を生成してください <strong>AWS</strong>. Use Serverless
architecture.
</p> </p>
<Image <div className="bg-neutral-950 rounded-lg p-4 flex items-center justify-center w-full h-[400px]">
src="/aws_demo.svg" <Image
alt="AWSアーキテクチャ図" src="/auth.svg"
width={400} alt="認証アーキテクチャ図"
height={300} width={480}
className="mx-auto" height={360}
/> className="max-w-full max-h-full object-contain"
/>
</div>
</div> </div>
<div className="text-center"> <div className="text-center">
<h3 className="text-lg font-semibold text-gray-900 mb-2"> <h3 className="text-lg font-semibold text-gray-900 mb-2">
Azureアーキテクチャ図
</h3> </h3>
<p className="text-gray-600 text-sm mb-4"> <p className="text-gray-600 text-sm mb-4">
<strong></strong>{" "} <strong>Prompt:</strong> Generate agile
<strong>Azureアイコン</strong> scrum workflow diagram for software
使Azureアーキテクチャ図を生成してください development team.
</p> </p>
<Image <div className="bg-neutral-950 rounded-lg p-4 flex items-center justify-center w-full h-[400px]">
src="/azure_demo.svg" <Image
alt="Azureアーキテクチャ図" src="/agile_scrum.svg"
width={400} alt="アジャイルスクラム図"
height={300} width={480}
className="mx-auto" height={360}
/> className="max-w-full max-h-full object-contain"
/>
</div>
</div> </div>
<div className="text-center"> <div className="text-center">
<h3 className="text-lg font-semibold text-gray-900 mb-2"> <h3 className="text-lg font-semibold text-gray-900 mb-2">
</h3> </h3>
<p className="text-gray-600 text-sm mb-4"> <p className="text-gray-600 text-sm mb-4">
<strong></strong>{" "} <strong>Prompt:</strong> Create
visualization of Henry Chesbrough&apos;s
Open Innovation model.
</p> </p>
<Image <div className="bg-neutral-950 rounded-lg p-4 flex items-center justify-center w-full h-[400px]">
src="/cat_demo.svg" <Image
alt="猫の絵" src="/inno.svg"
width={240} alt="オープンイノベーション図"
height={240} width={480}
className="mx-auto" height={360}
/> className="max-w-full max-h-full object-contain"
/>
</div>
</div> </div>
</div> </div>
</div> </div>

View File

@@ -182,96 +182,106 @@ export default function About() {
</p> </p>
<div className="space-y-8"> <div className="space-y-8">
{/* Animated Transformer */} {/* ResNet50 Architecture */}
<div className="text-center"> <div className="text-center">
<h3 className="text-lg font-semibold text-gray-900 mb-2"> <h3 className="text-lg font-semibold text-gray-900 mb-2">
Animated Transformer Connectors Animated ResNet50 Model Architecture
</h3> </h3>
<p className="text-gray-600 mb-4"> <p className="text-gray-600 mb-4">
<strong>Prompt:</strong> Give me an{" "} <strong>Prompt:</strong> Give me an{" "}
<strong>animated connector</strong> diagram of <strong>animated</strong> architecture diagram
transformer&apos;s architecture. of the ResNet50 model.
</p> </p>
<Image <div className="bg-neutral-950 rounded-lg p-4 inline-block">
src="/animated_connectors.svg" <Image
alt="Transformer Architecture with Animated Connectors" src="/resnet50.svg"
width={480} alt="Architecture diagram for ResNet50 model"
height={360} width={480}
className="mx-auto" height={360}
/> className="mx-auto"
/>
</div>
</div> </div>
{/* Cloud Architecture Grid */} {/* Diagram Grid */}
<div className="grid md:grid-cols-2 gap-6"> <div className="grid md:grid-cols-2 gap-6">
<div className="text-center"> <div className="text-center">
<h3 className="text-lg font-semibold text-gray-900 mb-2"> <h3 className="text-lg font-semibold text-gray-900 mb-2">
GCP Architecture Diagram RAG Technique Diagram
</h3> </h3>
<p className="text-gray-600 text-sm mb-4"> <p className="text-gray-600 text-sm mb-4">
<strong>Prompt:</strong> Generate a GCP <strong>Prompt:</strong> Generate a RAG
architecture diagram with{" "} architecture diagram for{" "}
<strong>GCP icons</strong>. Users connect to <strong>chat application</strong>. Use
a frontend hosted on an instance. connected diagram for data ingestion
</p> </p>
<Image <div className="bg-neutral-950 rounded-lg p-4 flex items-center justify-center w-full h-[400px]">
src="/gcp_demo.svg" <Image
alt="GCP Architecture Diagram" src="/rag_prod.svg"
width={400} alt="RAG Architecture Diagram"
height={300} width={480}
className="mx-auto" height={360}
/> className="max-w-full max-h-full object-contain"
/>
</div>
</div> </div>
<div className="text-center"> <div className="text-center">
<h3 className="text-lg font-semibold text-gray-900 mb-2"> <h3 className="text-lg font-semibold text-gray-900 mb-2">
AWS Architecture Diagram Authentication using React and AWS
</h3> </h3>
<p className="text-gray-600 text-sm mb-4"> <p className="text-gray-600 text-sm mb-4">
<strong>Prompt:</strong> Generate an AWS <strong>Prompt:</strong> Generate
architecture diagram with{" "} authentication process using React with{" "}
<strong>AWS icons</strong>. Users connect to <strong>AWS</strong>. Use Serverless
a frontend hosted on an instance. architecture.
</p> </p>
<Image <div className="bg-neutral-950 rounded-lg p-4 flex items-center justify-center w-full h-[400px]">
src="/aws_demo.svg" <Image
alt="AWS Architecture Diagram" src="/auth.svg"
width={400} alt="Authentication Architecture Diagram"
height={300} width={480}
className="mx-auto" height={360}
/> className="max-w-full max-h-full object-contain"
/>
</div>
</div> </div>
<div className="text-center"> <div className="text-center">
<h3 className="text-lg font-semibold text-gray-900 mb-2"> <h3 className="text-lg font-semibold text-gray-900 mb-2">
Azure Architecture Diagram Agile Scrum Process
</h3> </h3>
<p className="text-gray-600 text-sm mb-4"> <p className="text-gray-600 text-sm mb-4">
<strong>Prompt:</strong> Generate an Azure <strong>Prompt:</strong> Generate agile
architecture diagram with{" "} scrum workflow diagram for software
<strong>Azure icons</strong>. Users connect development team.
to a frontend hosted on an instance.
</p> </p>
<Image <div className="bg-neutral-950 rounded-lg p-4 flex items-center justify-center w-full h-[400px]">
src="/azure_demo.svg" <Image
alt="Azure Architecture Diagram" src="/agile_scrum.svg"
width={400} alt="Agile Scrum Diagram"
height={300} width={480}
className="mx-auto" height={360}
/> className="max-w-full max-h-full object-contain"
/>
</div>
</div> </div>
<div className="text-center"> <div className="text-center">
<h3 className="text-lg font-semibold text-gray-900 mb-2"> <h3 className="text-lg font-semibold text-gray-900 mb-2">
Cat Sketch Open Innovation
</h3> </h3>
<p className="text-gray-600 text-sm mb-4"> <p className="text-gray-600 text-sm mb-4">
<strong>Prompt:</strong> Draw a cute cat for <strong>Prompt:</strong> Create
me. visualization of Henry Chesbrough&apos;s
Open Innovation model.
</p> </p>
<Image <div className="bg-neutral-950 rounded-lg p-4 flex items-center justify-center w-full h-[400px]">
src="/cat_demo.svg" <Image
alt="Cat Drawing" src="/inno.svg"
width={240} alt="Open Innovation Diagram"
height={240} width={480}
className="mx-auto" height={360}
/> className="max-w-full max-h-full object-contain"
/>
</div>
</div> </div>
</div> </div>
</div> </div>

View File

@@ -100,12 +100,8 @@ export default function Home() {
const handleDrawioAutoSave = useCallback( const handleDrawioAutoSave = useCallback(
(data: { xml?: string }) => { (data: { xml?: string }) => {
handleDiagramAutoSave(data) handleDiagramAutoSave(data)
// Only suppress modified state when persistence is available
if (canPersist) {
drawioRef.current?.status({ message: "", modified: false })
}
}, },
[canPersist, drawioRef, handleDiagramAutoSave], [handleDiagramAutoSave],
) )
const handleDarkModeChange = () => { const handleDarkModeChange = () => {

View File

@@ -141,9 +141,6 @@ export default function ExamplePanel({
<span className="text-sm font-medium text-foreground group-hover:text-purple-500 transition-colors"> <span className="text-sm font-medium text-foreground group-hover:text-purple-500 transition-colors">
{dict.examples.mcpServer} {dict.examples.mcpServer}
</span> </span>
<span className="px-1.5 py-0.5 text-[10px] font-semibold bg-purple-500 text-white rounded">
{dict.examples.preview}
</span>
</div> </div>
<p className="text-xs text-muted-foreground"> <p className="text-xs text-muted-foreground">
{dict.examples.mcpDescription} {dict.examples.mcpDescription}

View File

@@ -417,6 +417,7 @@ export function ChatMessageDisplay({
// Track previous message count to detect bulk loads vs streaming // Track previous message count to detect bulk loads vs streaming
const prevMessageCountRef = useRef(0) const prevMessageCountRef = useRef(0)
const scrollThrottleRef = useRef<ReturnType<typeof setTimeout> | null>(null)
useEffect(() => { useEffect(() => {
if (messagesEndRef.current && messages.length > 0) { if (messagesEndRef.current && messages.length > 0) {
@@ -430,8 +431,17 @@ export function ChatMessageDisplay({
return return
} }
// Single message added - smooth scroll // Throttle scroll during streaming to avoid layout thrashing
messagesEndRef.current.scrollIntoView({ behavior: "smooth" }) // Leading + trailing: scroll immediately, then once more after cooldown
if (!scrollThrottleRef.current) {
messagesEndRef.current.scrollIntoView({ behavior: "smooth" })
scrollThrottleRef.current = setTimeout(() => {
scrollThrottleRef.current = null
messagesEndRef.current?.scrollIntoView({
behavior: "smooth",
})
}, 150)
}
} }
}, [messages]) }, [messages])

View File

@@ -107,8 +107,8 @@ export function ChatLobby({
currentInput = "", currentInput = "",
dict, dict,
}: ChatLobbyProps) { }: ChatLobbyProps) {
const [templatesExpanded, setTemplatesExpanded] = useState(false) const [templatesExpanded, setTemplatesExpanded] = useState(true)
const [examplesExpanded, setExamplesExpanded] = useState(false) const [examplesExpanded, setExamplesExpanded] = useState(true)
const [panelVisibility, setPanelVisibility] = useState(getPanelVisibility) const [panelVisibility, setPanelVisibility] = useState(getPanelVisibility)
const [deleteDialogOpen, setDeleteDialogOpen] = useState(false) const [deleteDialogOpen, setDeleteDialogOpen] = useState(false)
const [sessionToDelete, setSessionToDelete] = useState<string | null>(null) const [sessionToDelete, setSessionToDelete] = useState<string | null>(null)
@@ -125,19 +125,25 @@ export function ChatLobby({
const hasHistory = sessions.length > 0 const hasHistory = sessions.length > 0
if (!hasHistory) { if (!hasHistory) {
if (panelVisibility.myTemplates) { if (!panelVisibility.myTemplates && !panelVisibility.quickExamples) {
return ( return null
<TemplatePanel
setInput={setInput}
onSendTemplate={onSendTemplate}
currentInput={currentInput}
/>
)
} }
if (panelVisibility.quickExamples) { return (
return <ExamplePanel setInput={setInput} setFiles={setFiles} /> <div className="animate-fade-in">
} {panelVisibility.myTemplates && (
return null <TemplatePanel
setInput={setInput}
onSendTemplate={onSendTemplate}
currentInput={currentInput}
/>
)}
{panelVisibility.quickExamples && (
<div className={panelVisibility.myTemplates ? "mt-6" : ""}>
<ExamplePanel setInput={setInput} setFiles={setFiles} />
</div>
)}
</div>
)
} }
// Show history + collapsible examples when there are sessions // Show history + collapsible examples when there are sessions

View File

@@ -195,7 +195,22 @@ export function ToolCallCard({
{input && isExpanded && ( {input && isExpanded && (
<div className="px-4 py-3 border-t border-border/40 bg-muted/20"> <div className="px-4 py-3 border-t border-border/40 bg-muted/20">
{typeof input === "object" && input.xml ? ( {typeof input === "object" && input.xml ? (
<CodeBlock code={input.xml} language="xml" /> state === "input-streaming" ||
state === "input-available" ? (
<pre
className="text-[11px] leading-relaxed overflow-x-auto overflow-y-auto max-h-48 scrollbar-thin break-all whitespace-pre-wrap"
style={{
fontFamily:
"var(--font-mono), ui-monospace, monospace",
margin: 0,
padding: 0,
}}
>
{input.xml}
</pre>
) : (
<CodeBlock code={input.xml} language="xml" />
)
) : typeof input === "object" && ) : typeof input === "object" &&
input.operations && input.operations &&
Array.isArray(input.operations) ? ( Array.isArray(input.operations) ? (

View File

@@ -30,7 +30,7 @@ https://github.com/user-attachments/assets/b2eef5f3-b335-4e71-a755-dc2e80931979
- [目录](#目录) - [目录](#目录)
- [示例](#示例) - [示例](#示例)
- [功能特性](#功能特性) - [功能特性](#功能特性)
- [MCP服务器(预览)](#mcp服务器预览) - [MCP服务器](#mcp服务器)
- [Claude Code CLI](#claude-code-cli) - [Claude Code CLI](#claude-code-cli)
- [快速开始](#快速开始) - [快速开始](#快速开始)
- [在线试用](#在线试用) - [在线试用](#在线试用)
@@ -56,31 +56,31 @@ https://github.com/user-attachments/assets/b2eef5f3-b335-4e71-a755-dc2e80931979
<tr> <tr>
<td colspan="2" valign="top" align="center"> <td colspan="2" valign="top" align="center">
<strong>动画Transformer连接器</strong><br /> <strong>动画Transformer连接器</strong><br />
<p><strong>提示词:</strong> 给我一个带有**动画连接器**的Transformer架构图。</p> <p><strong>Prompt:</strong> Give me a **animated connector** diagram of transformer's architecture.</p>
<img src="../../public/animated_connectors.svg" alt="带动画连接器的Transformer架构" width="480" /> <img src="../../public/animated_connectors.svg" alt="带动画连接器的Transformer架构" width="480" />
</td> </td>
</tr> </tr>
<tr> <tr>
<td width="50%" valign="top"> <td width="50%" valign="top">
<strong>GCP架构图</strong><br /> <strong>RAG技术图</strong><br />
<p><strong>提示词:</strong> 使用**GCP图标**生成一个GCP架构图。在这个图中用户连接到托管在实例上的前端。</p> <p><strong>Prompt:</strong> Generate a RAG architecture diagram for **chat application**. Use connected diagram for data ingestion</p>
<img src="../../public/gcp_demo.svg" alt="GCP架构图" width="480" /> <img src="../../public/rag_prod.svg" alt="RAG架构图" width="480" />
</td> </td>
<td width="50%" valign="top"> <td width="50%" valign="top">
<strong>AWS架构图</strong><br /> <strong>React和AWS认证流程</strong><br />
<p><strong>提示词:</strong> 使用**AWS图标**生成一个AWS架构图。在这个图中用户连接到托管在实例上的前端。</p> <p><strong>Prompt:</strong> Generate authentication process using React with **AWS**. Use Serverless architecture.</p>
<img src="../../public/aws_demo.svg" alt="AWS架构图" width="480" /> <img src="../../public/auth.svg" alt="认证架构图" width="480" />
</td> </td>
</tr> </tr>
<tr> <tr>
<td width="50%" valign="top"> <td width="50%" valign="top">
<strong>Azure架构图</strong><br /> <strong>开放式创新</strong><br />
<p><strong>提示词:</strong> 使用**Azure图标**生成一个Azure架构图。在这个图中用户连接到托管在实例上的前端。</p> <p><strong>Prompt:</strong> Create visualization of Henry Chesbrough's Open Innovation model.</p>
<img src="../../public/azure_demo.svg" alt="Azure架构图" width="480" /> <img src="../../public/inno.svg" alt="开放式创新图" width="480" />
</td> </td>
<td width="50%" valign="top"> <td width="50%" valign="top">
<strong>猫咪素描</strong><br /> <strong>猫咪素描</strong><br />
<p><strong>提示词:</strong> 给我画一只可爱的猫。</p> <p><strong>Prompt:</strong> Draw a cute cat for me.</p>
<img src="../../public/cat_demo.svg" alt="猫咪绘图" width="240" /> <img src="../../public/cat_demo.svg" alt="猫咪绘图" width="240" />
</td> </td>
</tr> </tr>
@@ -98,9 +98,7 @@ https://github.com/user-attachments/assets/b2eef5f3-b335-4e71-a755-dc2e80931979
- **云架构图支持**专门支持生成云架构图AWS、GCP、Azure - **云架构图支持**专门支持生成云架构图AWS、GCP、Azure
- **动画连接器**:在图表元素之间创建动态动画连接器,实现更好的可视化效果 - **动画连接器**:在图表元素之间创建动态动画连接器,实现更好的可视化效果
## MCP服务器(预览) ## MCP服务器
> **预览功能**:此功能为实验性功能,可能不稳定。
通过MCP模型上下文协议在Claude Desktop、Cursor和VS Code等AI代理中使用Next AI Draw.io。 通过MCP模型上下文协议在Claude Desktop、Cursor和VS Code等AI代理中使用Next AI Draw.io。

View File

@@ -28,7 +28,7 @@ https://github.com/user-attachments/assets/b2eef5f3-b335-4e71-a755-dc2e80931979
- [目次](#目次) - [目次](#目次)
- [](#例) - [](#例)
- [機能](#機能) - [機能](#機能)
- [MCPサーバー(プレビュー)](#mcpサーバープレビュー) - [MCPサーバー](#mcpサーバー)
- [Claude Code CLI](#claude-code-cli) - [Claude Code CLI](#claude-code-cli)
- [はじめに](#はじめに) - [はじめに](#はじめに)
- [オンラインで試す](#オンラインで試す) - [オンラインで試す](#オンラインで試す)
@@ -54,31 +54,31 @@ https://github.com/user-attachments/assets/b2eef5f3-b335-4e71-a755-dc2e80931979
<tr> <tr>
<td colspan="2" valign="top" align="center"> <td colspan="2" valign="top" align="center">
<strong>アニメーションTransformerコネクタ</strong><br /> <strong>アニメーションTransformerコネクタ</strong><br />
<p><strong>プロンプト:</strong> **アニメーションコネクタ**付きのTransformerアーキテクチャ図を作成してください。</p> <p><strong>Prompt:</strong> Give me a **animated connector** diagram of transformer's architecture.</p>
<img src="../../public/animated_connectors.svg" alt="アニメーションコネクタ付きTransformerアーキテクチャ" width="480" /> <img src="../../public/animated_connectors.svg" alt="アニメーションコネクタ付きTransformerアーキテクチャ" width="480" />
</td> </td>
</tr> </tr>
<tr> <tr>
<td width="50%" valign="top"> <td width="50%" valign="top">
<strong>GCPアーキテクチャ図</strong><br /> <strong>RAG技術ダイアグラム</strong><br />
<p><strong>プロンプト:</strong> **GCPアイコン**を使用してGCPアーキテクチャ図を生成してください。この図では、ユーザーがインスタンス上でホストされているフロントエンドに接続します。</p> <p><strong>Prompt:</strong> Generate a RAG architecture diagram for **chat application**. Use connected diagram for data ingestion</p>
<img src="../../public/gcp_demo.svg" alt="GCPアーキテクチャ図" width="480" /> <img src="../../public/rag_prod.svg" alt="RAGアーキテクチャ図" width="480" />
</td> </td>
<td width="50%" valign="top"> <td width="50%" valign="top">
<strong>AWSアーキテクチャ図</strong><br /> <strong>ReactとAWSによる認証</strong><br />
<p><strong>プロンプト:</strong> **AWSアイコン**を使用してAWSアーキテクチャ図を生成してください。この図では、ユーザーがインスタンス上でホストされているフロントエンドに接続します。</p> <p><strong>Prompt:</strong> Generate authentication process using React with **AWS**. Use Serverless architecture.</p>
<img src="../../public/aws_demo.svg" alt="AWSアーキテクチャ図" width="480" /> <img src="../../public/auth.svg" alt="認証アーキテクチャ図" width="480" />
</td> </td>
</tr> </tr>
<tr> <tr>
<td width="50%" valign="top"> <td width="50%" valign="top">
<strong>Azureアーキテクチャ図</strong><br /> <strong>オープンイノベーション</strong><br />
<p><strong>プロンプト:</strong> **Azureアイコン**を使用してAzureアーキテクチャ図を生成してください。この図では、ユーザーがインスタンス上でホストされているフロントエンドに接続します。</p> <p><strong>Prompt:</strong> Create visualization of Henry Chesbrough's Open Innovation model.</p>
<img src="../../public/azure_demo.svg" alt="Azureアーキテクチャ図" width="480" /> <img src="../../public/inno.svg" alt="オープンイノベーション図" width="480" />
</td> </td>
<td width="50%" valign="top"> <td width="50%" valign="top">
<strong>猫のスケッチ</strong><br /> <strong>猫のスケッチ</strong><br />
<p><strong>プロンプト:</strong> かわいい猫を描いてください。</p> <p><strong>Prompt:</strong> Draw a cute cat for me.</p>
<img src="../../public/cat_demo.svg" alt="猫の絵" width="240" /> <img src="../../public/cat_demo.svg" alt="猫の絵" width="240" />
</td> </td>
</tr> </tr>
@@ -96,9 +96,7 @@ https://github.com/user-attachments/assets/b2eef5f3-b335-4e71-a755-dc2e80931979
- **クラウドアーキテクチャダイアグラムサポート**クラウドアーキテクチャダイアグラムの生成を専門的にサポートAWS、GCP、Azure - **クラウドアーキテクチャダイアグラムサポート**クラウドアーキテクチャダイアグラムの生成を専門的にサポートAWS、GCP、Azure
- **アニメーションコネクタ**:より良い可視化のためにダイアグラム要素間に動的でアニメーション化されたコネクタを作成 - **アニメーションコネクタ**:より良い可視化のためにダイアグラム要素間に動的でアニメーション化されたコネクタを作成
## MCPサーバー(プレビュー) ## MCPサーバー
> **プレビュー機能**:この機能は実験的であり、安定しない可能性があります。
MCPModel Context Protocolを介して、Claude Desktop、Cursor、VS CodeなどのAIエージェントでNext AI Draw.ioを使用できます。 MCPModel Context Protocolを介して、Claude Desktop、Cursor、VS CodeなどのAIエージェントでNext AI Draw.ioを使用できます。

View File

@@ -1356,12 +1356,11 @@ export function supportsImageInput(modelId: string): boolean {
} }
// Qwen text models (not vision variants like qwen-vl) // Qwen text models (not vision variants like qwen-vl)
// qwen3.5-plus is a vision model // Qwen3.5 series (qwen3.5, qwen3.5-plus, qwen3.5-flash) natively support image input
if ( if (
lowerModelId.includes("qwen") && lowerModelId.includes("qwen") &&
!hasVisionIndicator && !hasVisionIndicator &&
!lowerModelId.includes("qwen3.5-plus") && !lowerModelId.includes("qwen3.5")
!lowerModelId.includes("qwen3.5-flash")
) { ) {
return false return false
} }

View File

@@ -76,8 +76,7 @@
"creativeDescription": "Draw something fun and creative", "creativeDescription": "Draw something fun and creative",
"cachedNote": "Examples are cached for instant response", "cachedNote": "Examples are cached for instant response",
"mcpServer": "MCP Server", "mcpServer": "MCP Server",
"mcpDescription": "Use in Claude Desktop, VS Code & Cursor", "mcpDescription": "Use in Claude Desktop, VS Code & Cursor"
"preview": "PREVIEW"
}, },
"settings": { "settings": {
"title": "Settings", "title": "Settings",

View File

@@ -76,8 +76,7 @@
"creativeDescription": "楽しくてクリエイティブなものを描く", "creativeDescription": "楽しくてクリエイティブなものを描く",
"cachedNote": "例はキャッシュされ、即座に応答します", "cachedNote": "例はキャッシュされ、即座に応答します",
"mcpServer": "MCP サーバー", "mcpServer": "MCP サーバー",
"mcpDescription": "Claude Desktop、VS Code、Cursor で使用", "mcpDescription": "Claude Desktop、VS Code、Cursor で使用"
"preview": "プレビュー"
}, },
"settings": { "settings": {
"title": "設定", "title": "設定",

View File

@@ -76,8 +76,7 @@
"creativeDescription": "繪製有趣且富有創意的內容", "creativeDescription": "繪製有趣且富有創意的內容",
"cachedNote": "範例已快取,可即時回應", "cachedNote": "範例已快取,可即時回應",
"mcpServer": "MCP 伺服器", "mcpServer": "MCP 伺服器",
"mcpDescription": "在 Claude Desktop、VS Code 和 Cursor 中使用", "mcpDescription": "在 Claude Desktop、VS Code 和 Cursor 中使用"
"preview": "預覽"
}, },
"settings": { "settings": {
"title": "設定", "title": "設定",

View File

@@ -76,8 +76,7 @@
"creativeDescription": "绘制有趣且富有创意的内容", "creativeDescription": "绘制有趣且富有创意的内容",
"cachedNote": "示例已缓存,可即时响应", "cachedNote": "示例已缓存,可即时响应",
"mcpServer": "MCP 服务器", "mcpServer": "MCP 服务器",
"mcpDescription": "在 Claude Desktop、VS Code 和 Cursor 中使用", "mcpDescription": "在 Claude Desktop、VS Code 和 Cursor 中使用"
"preview": "预览"
}, },
"settings": { "settings": {
"title": "设置", "title": "设置",

View File

@@ -1,12 +1,12 @@
{ {
"name": "@next-ai-drawio/mcp-server", "name": "@next-ai-drawio/mcp-server",
"version": "0.1.17", "version": "0.2.0",
"lockfileVersion": 3, "lockfileVersion": 3,
"requires": true, "requires": true,
"packages": { "packages": {
"": { "": {
"name": "@next-ai-drawio/mcp-server", "name": "@next-ai-drawio/mcp-server",
"version": "0.1.17", "version": "0.2.0",
"license": "Apache-2.0", "license": "Apache-2.0",
"dependencies": { "dependencies": {
"@modelcontextprotocol/sdk": "^1.0.4", "@modelcontextprotocol/sdk": "^1.0.4",

View File

@@ -1,6 +1,6 @@
{ {
"name": "@next-ai-drawio/mcp-server", "name": "@next-ai-drawio/mcp-server",
"version": "0.1.19", "version": "0.2.0",
"description": "MCP server for Next AI Draw.io - AI-powered diagram generation with real-time browser preview", "description": "MCP server for Next AI Draw.io - AI-powered diagram generation with real-time browser preview",
"type": "module", "type": "module",
"main": "dist/index.js", "main": "dist/index.js",

View File

@@ -155,19 +155,22 @@ server.registerTool(
server.registerTool( server.registerTool(
"create_new_diagram", "create_new_diagram",
{ {
description: `Create a NEW diagram from mxGraphModel XML. Use this when creating a diagram from scratch or replacing the current diagram entirely. description: `Create a NEW diagram from mxGraphModel XML. ONLY use this when creating a diagram from scratch.
⚠️ DO NOT use this tool to modify an existing diagram — it will DESTROY all existing content and user changes. Use edit_diagram instead for ANY modifications to an existing diagram.
CRITICAL: You MUST provide the 'xml' argument in EVERY call. Do NOT call this tool without xml. CRITICAL: You MUST provide the 'xml' argument in EVERY call. Do NOT call this tool without xml.
When to use this tool: When to use this tool:
- Creating a new diagram from scratch - Creating a new diagram from scratch (no existing diagram)
- Replacing the current diagram with a completely different one - The user explicitly asks to "start over" or "create a new diagram"
- Major structural changes that require regenerating the diagram
When to use edit_diagram instead: When to use edit_diagram instead (ALWAYS prefer edit_diagram if a diagram already exists):
- Small modifications to existing diagram - ANY modifications to an existing diagram
- Adding/removing individual elements - Adding/removing/moving elements
- Changing labels, colors, or positions - Changing labels, colors, styles, or positions
- Restructuring or reorganizing existing content
- Adding new elements to an existing diagram
XML FORMAT - Full mxGraphModel structure: XML FORMAT - Full mxGraphModel structure:
<mxGraphModel> <mxGraphModel>

View File

@@ -12,7 +12,8 @@
"declaration": true, "declaration": true,
"declarationMap": true, "declarationMap": true,
"sourceMap": true, "sourceMap": true,
"resolveJsonModule": true "resolveJsonModule": true,
"types": ["node"]
}, },
"include": ["src/**/*"], "include": ["src/**/*"],
"exclude": ["node_modules", "dist"] "exclude": ["node_modules", "dist"]

1
public/agile_scrum.svg Normal file

File diff suppressed because one or more lines are too long

After

Width:  |  Height:  |  Size: 30 KiB

1
public/auth.svg Normal file

File diff suppressed because one or more lines are too long

After

Width:  |  Height:  |  Size: 42 KiB

1
public/inno.svg Normal file

File diff suppressed because one or more lines are too long

After

Width:  |  Height:  |  Size: 27 KiB

1
public/rag_prod.svg Normal file

File diff suppressed because one or more lines are too long

After

Width:  |  Height:  |  Size: 35 KiB

1
public/resnet50.svg Normal file

File diff suppressed because one or more lines are too long

After

Width:  |  Height:  |  Size: 39 KiB

View File

@@ -200,6 +200,8 @@ describe("supportsImageInput", () => {
it("returns true for Qwen vision models", () => { it("returns true for Qwen vision models", () => {
expect(supportsImageInput("qwen-vl")).toBe(true) expect(supportsImageInput("qwen-vl")).toBe(true)
expect(supportsImageInput("Qwen3.5")).toBe(true)
expect(supportsImageInput("qwen3.5")).toBe(true)
expect(supportsImageInput("qwen3.5-plus")).toBe(true) expect(supportsImageInput("qwen3.5-plus")).toBe(true)
expect(supportsImageInput("qwen3.5-flash")).toBe(true) expect(supportsImageInput("qwen3.5-flash")).toBe(true)
expect(supportsImageInput("qwen3-vl-plus")).toBe(true) expect(supportsImageInput("qwen3-vl-plus")).toBe(true)