Merge branch 'main' into feature/url-content-extraction

app/api/chat/route.ts

@@ -18,6 +18,11 @@ import {
     supportsPromptCaching,
 } from "@/lib/ai-providers"
 import { findCachedResponse } from "@/lib/cached-responses"
+import {
+    isMinimalDiagram,
+    replaceHistoricalToolInputs,
+    validateFileParts,
+} from "@/lib/chat-helpers"
 import {
     checkAndIncrementRequest,
     isQuotaEnabled,
@@ -34,93 +39,6 @@ import { getUserIdFromRequest } from "@/lib/user-id"
 
 export const maxDuration = 120
 
-// File upload limits (must match client-side)
-const MAX_FILE_SIZE = 2 * 1024 * 1024 // 2MB
-const MAX_FILES = 5
-
-// Helper function to validate file parts in messages
-function validateFileParts(messages: any[]): {
-    valid: boolean
-    error?: string
-} {
-    const lastMessage = messages[messages.length - 1]
-    const fileParts =
-        lastMessage?.parts?.filter((p: any) => p.type === "file") || []
-
-    if (fileParts.length > MAX_FILES) {
-        return {
-            valid: false,
-            error: `Too many files. Maximum ${MAX_FILES} allowed.`,
-        }
-    }
-
-    for (const filePart of fileParts) {
-        // Data URLs format: data:image/png;base64,<data>
-        // Base64 increases size by ~33%, so we check the decoded size
-        if (filePart.url?.startsWith("data:")) {
-            const base64Data = filePart.url.split(",")[1]
-            if (base64Data) {
-                const sizeInBytes = Math.ceil((base64Data.length * 3) / 4)
-                if (sizeInBytes > MAX_FILE_SIZE) {
-                    return {
-                        valid: false,
-                        error: `File exceeds ${MAX_FILE_SIZE / 1024 / 1024}MB limit.`,
-                    }
-                }
-            }
-        }
-    }
-
-    return { valid: true }
-}
-
-// Helper function to check if diagram is minimal/empty
-function isMinimalDiagram(xml: string): boolean {
-    const stripped = xml.replace(/\s/g, "")
-    return !stripped.includes('id="2"')
-}
-
-// Helper function to replace historical tool call XML with placeholders
-// This reduces token usage and forces LLM to rely on the current diagram XML (source of truth)
-// Also fixes invalid/undefined inputs from interrupted streaming
-function replaceHistoricalToolInputs(messages: any[]): any[] {
-    return messages.map((msg) => {
-        if (msg.role !== "assistant" || !Array.isArray(msg.content)) {
-            return msg
-        }
-        const replacedContent = msg.content
-            .map((part: any) => {
-                if (part.type === "tool-call") {
-                    const toolName = part.toolName
-                    // Fix invalid/undefined inputs from interrupted streaming
-                    if (
-                        !part.input ||
-                        typeof part.input !== "object" ||
-                        Object.keys(part.input).length === 0
-                    ) {
-                        // Skip tool calls with invalid inputs entirely
-                        return null
-                    }
-                    if (
-                        toolName === "display_diagram" ||
-                        toolName === "edit_diagram"
-                    ) {
-                        return {
-                            ...part,
-                            input: {
-                                placeholder:
-                                    "[XML content replaced - see current diagram XML in system context]",
-                            },
-                        }
-                    }
-                }
-                return part
-            })
-            .filter(Boolean) // Remove null entries (invalid tool calls)
-        return { ...msg, content: replacedContent }
-    })
-}
-
 // Helper function to create cached stream response
 function createCachedStreamResponse(xml: string): Response {
     const toolCallId = `cached-${Date.now()}`

app/api/parse-url/route.ts

@@ -93,7 +93,7 @@ export async function POST(req: Request) {
 
         let article
         try {
-            article = await extract(url, {
+            article = await extract(url, undefined, {
                 headers: {
                     "User-Agent": "Mozilla/5.0 (compatible; NextAIDrawio/1.0)",
                 },

app/api/validate-model/route.ts

@@ -251,13 +251,26 @@ export async function POST(req: Request) {
             }
 
             case "doubao": {
-                // ByteDance Doubao uses DeepSeek-compatible API
-                const doubao = createDeepSeek({
-                    apiKey,
-                    baseURL:
-                        baseUrl || "https://ark.cn-beijing.volces.com/api/v3",
-                })
-                model = doubao(modelId)
+                // ByteDance Doubao: use DeepSeek for DeepSeek/Kimi models, OpenAI for others
+                const doubaoBaseUrl =
+                    baseUrl || "https://ark.cn-beijing.volces.com/api/v3"
+                const lowerModelId = modelId.toLowerCase()
+                if (
+                    lowerModelId.includes("deepseek") ||
+                    lowerModelId.includes("kimi")
+                ) {
+                    const doubao = createDeepSeek({
+                        apiKey,
+                        baseURL: doubaoBaseUrl,
+                    })
+                    model = doubao(modelId)
+                } else {
+                    const doubao = createOpenAI({
+                        apiKey,
+                        baseURL: doubaoBaseUrl,
+                    })
+                    model = doubao.chat(modelId)
+                }
                 break
             }