Compare commits

...

2 Commits

Author SHA1 Message Date
renovate[bot]
34896aa7f2 fix(deps): update dependency zod to v4 2025-12-31 08:24:25 +00:00
Dayuan Jiang
03ac9a79de fix: detect models that don't support image input and return clear error (#474)
Some models (Kimi K2, DeepSeek, Qwen text models) don't support image/vision
input. The AI SDK silently drops unsupported image parts, causing confusing
responses where the model acts as if no image was uploaded.

Added supportsImageInput() function to detect unsupported models by name,
and return a 400 error with clear guidance when users try to upload images
to these models.

Closes #469
2025-12-31 12:20:09 +09:00
4 changed files with 54 additions and 8 deletions

View File

@@ -12,7 +12,11 @@ import fs from "fs/promises"
import { jsonrepair } from "jsonrepair"
import path from "path"
import { z } from "zod"
import { getAIModel, supportsPromptCaching } from "@/lib/ai-providers"
import {
getAIModel,
supportsImageInput,
supportsPromptCaching,
} from "@/lib/ai-providers"
import { findCachedResponse } from "@/lib/cached-responses"
import {
checkAndIncrementRequest,
@@ -295,6 +299,17 @@ async function handleChatRequest(req: Request): Promise<Response> {
lastUserMessage?.parts?.filter((part: any) => part.type === "file") ||
[]
// Check if user is sending images to a model that doesn't support them
// AI SDK silently drops unsupported parts, so we need to catch this early
if (fileParts.length > 0 && !supportsImageInput(modelId)) {
return Response.json(
{
error: `The model "${modelId}" does not support image input. Please use a vision-capable model (e.g., GPT-4o, Claude, Gemini) or remove the image.`,
},
{ status: 400 },
)
}
// User input only - XML is now in a separate cached system message
const formattedUserInput = `User input:
"""md

View File

@@ -906,3 +906,34 @@ export function supportsPromptCaching(modelId: string): boolean {
modelId.startsWith("eu.anthropic")
)
}
/**
* Check if a model supports image/vision input.
* Some models silently drop image parts without error (AI SDK warning only).
*/
export function supportsImageInput(modelId: string): boolean {
const lowerModelId = modelId.toLowerCase()
// Helper to check if model has vision capability indicator
const hasVisionIndicator =
lowerModelId.includes("vision") || lowerModelId.includes("vl")
// Models that DON'T support image/vision input (unless vision variant)
// Kimi K2 models don't support images
if (lowerModelId.includes("kimi") && !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)
if (lowerModelId.includes("qwen") && !hasVisionIndicator) {
return false
}
// Default: assume model supports images
return true
}

View File

@@ -1,18 +1,18 @@
{
"name": "@next-ai-drawio/mcp-server",
"version": "0.1.6",
"version": "0.1.10",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "@next-ai-drawio/mcp-server",
"version": "0.1.6",
"version": "0.1.10",
"license": "Apache-2.0",
"dependencies": {
"@modelcontextprotocol/sdk": "^1.0.4",
"linkedom": "^0.18.0",
"open": "^11.0.0",
"zod": "^3.24.0"
"zod": "^4.0.0"
},
"bin": {
"next-ai-drawio-mcp": "dist/index.js"
@@ -2051,9 +2051,9 @@
}
},
"node_modules/zod": {
"version": "3.25.76",
"resolved": "https://registry.npmjs.org/zod/-/zod-3.25.76.tgz",
"integrity": "sha512-gzUt/qt81nXsFGKIFcC3YnfEAx5NkunCfnDlvuBSSFS02bcXu4Lmea0AFIUwbLWxWPx3d9p8S5QoaujKcNQxcQ==",
"version": "4.3.2",
"resolved": "https://registry.npmjs.org/zod/-/zod-4.3.2.tgz",
"integrity": "sha512-b8L8yn4rIVfiXyHAmnr52/ZEpDumlT0bmxiq3Ws1ybrinhflGpt12Hvv54kYnEsGPRs6o/Ka3/ppA2OWY21IVg==",
"license": "MIT",
"peer": true,
"funding": {

View File

@@ -39,7 +39,7 @@
"@modelcontextprotocol/sdk": "^1.0.4",
"linkedom": "^0.18.0",
"open": "^11.0.0",
"zod": "^3.24.0"
"zod": "^4.0.0"
},
"devDependencies": {
"@types/node": "^24.0.0",