From db4d5e4d001c4b92b547d6c00b1817b610683256 Mon Sep 17 00:00:00 2001
From: vakabunga <vakabunga@proton.me>
Date: Sat, 14 Mar 2026 19:59:22 +0300
Subject: [PATCH] fix: yield to event loop after each SSE write to flush socket

The for-await loop over OpenAI stream chunks runs synchronously when
data is buffered, causing res.write() calls to queue without flushing.
Add setImmediate yield after each progress event so the event loop
reaches its I/O phase and pushes data to the network immediately.
---
 backend/src/routes/import.ts           |  8 +-------
 backend/src/services/pdfToStatement.ts | 10 +++++++++-
 2 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/backend/src/routes/import.ts b/backend/src/routes/import.ts
index 4727ea7..cc38c89 100644
--- a/backend/src/routes/import.ts
+++ b/backend/src/routes/import.ts
@@ -28,14 +28,8 @@ function isJsonFile(file: { mimetype: string; originalname: string }): boolean {
   );
 }
 
-const SSE_PAD_TARGET = 4096;
-
 function sseWrite(res: import('express').Response, data: Record<string, unknown>) {
-  const payload = `data: ${JSON.stringify(data)}\n\n`;
-  const pad = Math.max(0, SSE_PAD_TARGET - payload.length);
-  // SSE comment lines (": ...") are ignored by the browser but push
-  // data past proxy buffer thresholds so each event is delivered immediately.
-  res.write(pad > 0 ? `: ${' '.repeat(pad)}\n${payload}` : payload);
+  res.write(`data: ${JSON.stringify(data)}\n\n`);
 }
 
 const router = Router();
diff --git a/backend/src/services/pdfToStatement.ts b/backend/src/services/pdfToStatement.ts
index c7fe5a6..2e66b32 100644
--- a/backend/src/services/pdfToStatement.ts
+++ b/backend/src/services/pdfToStatement.ts
@@ -150,6 +150,10 @@ const LLM_PROGRESS_MAX = 98;
 const LLM_PROGRESS_RANGE = LLM_PROGRESS_MAX - LLM_PROGRESS_MIN;
 const THROTTLE_MS = 300;
 
+function yieldToEventLoop(): Promise<void> {
+  return new Promise(resolve => setImmediate(resolve));
+}
+
 export async function convertPdfToStatementStreaming(
   buffer: Buffer,
   onProgress: OnProgress,
@@ -163,6 +167,7 @@ export async function convertPdfToStatementStreaming(
   }
 
   onProgress('pdf', 2, 'Извлечение текста из PDF...');
+  await yieldToEventLoop();
 
   let text: string;
   try {
@@ -186,6 +191,7 @@ export async function convertPdfToStatementStreaming(
   }
 
   onProgress('pdf', 8, 'Текст извлечён, отправка в LLM...');
+  await yieldToEventLoop();
 
   const openai = new OpenAI({
     apiKey: config.llmApiKey,
@@ -205,7 +211,6 @@ export async function convertPdfToStatementStreaming(
       stream: true,
     });
 
-    // Estimate expected output size as ~2x the input PDF text length, clamped
     const expectedChars = Math.max(2_000, Math.min(text.length * 2, 30_000));
 
     let accumulated = '';
@@ -227,11 +232,14 @@ export async function convertPdfToStatementStreaming(
           );
           onProgress('llm', llmProgress, 'Конвертация через LLM...');
           lastEmitTime = now;
+          // Let the event loop flush socket writes to the network
+          await yieldToEventLoop();
         }
       }
     }
 
     onProgress('llm', LLM_PROGRESS_MAX, 'LLM завершил, обработка результата...');
+    await yieldToEventLoop();
 
     const content = accumulated.trim();
     if (!content) {