mirror of
https://github.com/DayuanJiang/next-ai-draw-io.git
synced 2026-10-09 03:07:46 +08:00
Chats: - New Chat right after an answer saves that chat once. Saves run one at a time and read the chat on screen when their turn comes; a save scheduled for a chat that is no longer on screen is dropped. A chat whose id was still on its way to the URL no longer comes back after New Chat (the next answer went into it). - Crossing the 768 px breakpoint keeps the chat panel: a streaming answer, unsaved messages and attachments stay. The panel gets the sizes of each side, and a panel collapsed on desktop opens on mobile. - The chat's export waits for its own reply: an edit's history export still on its way no longer answers it with the older diagram, and two file saves at once no longer swap results. - A second edit in one answer is previewed on the first edit's result. - Stop also ends a running screenshot check; a chat that cannot be saved (storage full) can be left with "Continue without saving". - Small diagrams with shapes count as diagrams; the tool card no longer crashes on malformed operations. Quota and providers: - Requests that reach the server's own endpoints count toward the quota: EdgeOne (always its own endpoint now), a private base URL whatever key header is sent, keyless Ollama without a URL. With the quota on, a redirect is followed only to a public address. The output cap applies to these requests too. - Stop records the tokens of the steps that finished; the screenshot check counts its tokens without counting a request. - EdgeOne configured only by AI_PROVIDER works, also in the admin Test, which forwards the access code. Azure set up only in the admin panel works in chat. The Test sends a Bedrock session token. - The admin panel's Test of an entry without a URL uses the server's URL as the server does (no private address check for it); the admin panel no longer writes an Ollama URL. MCP server: - Write tools and start_session run one at a time, so two at once never drop each other's change; a cancelled call waiting its turn is skipped. get_diagram and export_diagram keep the session they started with. - Export to .drawio first gets the user's latest edits from the browser. - History thumbnails: one that arrives after the next AI write is dropped; a sync reply keeps the image; a version that changed only page settings is its own entry. - A diagram over the 10 MB limit is saved without its image, or the user is told to download it (the server now answers 413 instead of cutting the connection). - Labels holding text like id='1' or parent='1' are no longer read as attributes (a layer or a parent was deleted). A broken bare <mxGraphModel> file is refused. - After a sync reply the tab no longer sends its autosave copy again. Desktop and files: - A newer switch of the same preset is not rolled back by an older one that failed. .env values with escaped quotes are read whole. - MCP saved files: a file that could not be read stays protected while a folder without permission hides it, and is saved again once deleted. - The desktop app reports "no chats" only when the count was read and no model settings are stored.
185 lines
6.2 KiB
TypeScript
185 lines
6.2 KiB
TypeScript
/**
|
|
* API endpoint for VLM-based diagram validation.
|
|
* Accepts a PNG image and streams validation results using useObject-compatible format.
|
|
*/
|
|
|
|
import { Output, streamText } from "ai"
|
|
import { checkAccessCode, rejectCrossSite } from "@/lib/access-code"
|
|
import { getValidationModel } from "@/lib/ai-providers"
|
|
import {
|
|
checkAndIncrementRequest,
|
|
isQuotaEnabled,
|
|
recordTokenUsage,
|
|
} from "@/lib/dynamo-quota-manager"
|
|
import { getUserIdFromRequest } from "@/lib/user-id"
|
|
import { VALIDATION_SYSTEM_PROMPT } from "@/lib/validation-prompts"
|
|
import {
|
|
type ValidationResult,
|
|
ValidationResultSchema,
|
|
} from "@/lib/validation-schema"
|
|
|
|
export const maxDuration = 30
|
|
|
|
// Data URL length cap (~3.75 MB of PNG), well above a normal diagram capture
|
|
const MAX_IMAGE_DATA_LENGTH = 5 * 1024 * 1024
|
|
|
|
interface ValidateDiagramRequest {
|
|
imageData: string // Base64 PNG data URL
|
|
sessionId?: string
|
|
}
|
|
|
|
// Default valid result for disabled/error cases
|
|
const DEFAULT_VALID_RESULT: ValidationResult = {
|
|
valid: true,
|
|
issues: [],
|
|
suggestions: [],
|
|
}
|
|
|
|
/** A fixed result in the text format useObject reads */
|
|
function createStreamingResponse(result: ValidationResult): Response {
|
|
return new Response(JSON.stringify(result), {
|
|
headers: { "Content-Type": "text/plain; charset=utf-8" },
|
|
})
|
|
}
|
|
|
|
export async function POST(req: Request): Promise<Response> {
|
|
const crossSite = rejectCrossSite(req)
|
|
if (crossSite) return crossSite
|
|
// Uses the server's model credentials, so require the access code
|
|
const accessError = checkAccessCode(req)
|
|
if (accessError) return accessError
|
|
|
|
try {
|
|
// Check if VLM validation is enabled (default: true)
|
|
const enableValidation = process.env.ENABLE_VLM_VALIDATION !== "false"
|
|
if (!enableValidation) {
|
|
return createStreamingResponse(DEFAULT_VALID_RESULT)
|
|
}
|
|
|
|
const body: ValidateDiagramRequest = await req.json()
|
|
const { imageData, sessionId } = body
|
|
|
|
if (!imageData) {
|
|
return Response.json(
|
|
{ error: "Missing imageData" },
|
|
{ status: 400 },
|
|
)
|
|
}
|
|
|
|
// Validate image data format
|
|
if (
|
|
!imageData.startsWith("data:image/png;base64,") &&
|
|
!imageData.startsWith("data:image/")
|
|
) {
|
|
return Response.json(
|
|
{ error: "Invalid image data format" },
|
|
{ status: 400 },
|
|
)
|
|
}
|
|
|
|
if (imageData.length > MAX_IMAGE_DATA_LENGTH) {
|
|
return Response.json(
|
|
{ error: "Image data too large" },
|
|
{ status: 413 },
|
|
)
|
|
}
|
|
|
|
// It runs the server's vision model: with the quota on, the daily
|
|
// and per-minute token limits apply, and its tokens are counted. Not
|
|
// the request limit, which is for chats: the day's last chat still
|
|
// gets its check, and a check does not count as a chat.
|
|
const userId = getUserIdFromRequest(req)
|
|
const countsQuota = isQuotaEnabled() && userId !== "anonymous"
|
|
if (countsQuota) {
|
|
const quotaCheck = await checkAndIncrementRequest(
|
|
userId,
|
|
{
|
|
requests: 0,
|
|
tokens: Number(process.env.DAILY_TOKEN_LIMIT) || 200000,
|
|
tpm: Number(process.env.TPM_LIMIT) || 20000,
|
|
},
|
|
0,
|
|
)
|
|
if (!quotaCheck.allowed) {
|
|
return Response.json(
|
|
{
|
|
error: quotaCheck.error,
|
|
type: quotaCheck.type,
|
|
used: quotaCheck.used,
|
|
limit: quotaCheck.limit,
|
|
},
|
|
{ status: 429 },
|
|
)
|
|
}
|
|
}
|
|
|
|
// Get the validation model
|
|
let model
|
|
try {
|
|
model = getValidationModel()
|
|
} catch (error) {
|
|
console.warn(
|
|
"[validate-diagram] Validation model not available:",
|
|
error,
|
|
)
|
|
// Return valid if no vision model is configured
|
|
return createStreamingResponse(DEFAULT_VALID_RESULT)
|
|
}
|
|
|
|
// Parse timeout with validation (minimum 1000ms, default 10000ms)
|
|
const timeout =
|
|
Math.max(
|
|
1000,
|
|
parseInt(process.env.VALIDATION_TIMEOUT || "10000", 10),
|
|
) || 10000
|
|
|
|
// Stream the VLM response for useObject consumption
|
|
const result = streamText({
|
|
model,
|
|
output: Output.object({ schema: ValidationResultSchema }),
|
|
system: VALIDATION_SYSTEM_PROMPT,
|
|
messages: [
|
|
{
|
|
role: "user",
|
|
content: [
|
|
{
|
|
type: "image",
|
|
image: imageData,
|
|
},
|
|
{
|
|
type: "text",
|
|
text: "Please analyze this diagram for visual quality issues.",
|
|
},
|
|
],
|
|
},
|
|
],
|
|
maxOutputTokens: 1024,
|
|
abortSignal: AbortSignal.timeout(timeout),
|
|
onFinish: ({ output, totalUsage }) => {
|
|
if (countsQuota && totalUsage) {
|
|
recordTokenUsage(
|
|
userId,
|
|
(totalUsage.inputTokens || 0) +
|
|
(totalUsage.outputTokens || 0),
|
|
)
|
|
}
|
|
if (sessionId && output) {
|
|
console.log(
|
|
`[validate-diagram] Session ${sessionId}: valid=${output.valid}, issues=${output.issues?.length ?? 0}`,
|
|
)
|
|
}
|
|
},
|
|
})
|
|
|
|
return result.toTextStreamResponse()
|
|
} catch (error) {
|
|
// Log with session context if available
|
|
const errorMessage =
|
|
error instanceof Error ? error.message : String(error)
|
|
console.error("[validate-diagram] Error:", errorMessage)
|
|
|
|
// On error, return valid to not block the user
|
|
return createStreamingResponse(DEFAULT_VALID_RESULT)
|
|
}
|
|
}
|