From 78c4730196e154b1acae7742a293ffcab347723b Mon Sep 17 00:00:00 2001
From: vakabunga <vakabunga@proton.me>
Date: Sat, 14 Mar 2026 16:41:12 +0300
Subject: [PATCH] fix: adaptive LLM progress estimation and emit 85% on stream
 end

Hardcoded EXPECTED_CHARS (15k) caused progress to stall at ~20-25% for
short statements. Now expected size is derived from input text length.
Also emit an explicit 85% event when the LLM stream finishes, and
throttle SSE events to 300ms to reduce browser overhead.
---
 backend/src/services/pdfToStatement.ts | 27 ++++++++++++++++++++------
 1 file changed, 21 insertions(+), 6 deletions(-)

diff --git a/backend/src/services/pdfToStatement.ts b/backend/src/services/pdfToStatement.ts
index d351ae7..6bc8401 100644
--- a/backend/src/services/pdfToStatement.ts
+++ b/backend/src/services/pdfToStatement.ts
@@ -145,7 +145,10 @@ export async function convertPdfToStatement(
 export type ProgressStage = 'pdf' | 'llm' | 'import';
 export type OnProgress = (stage: ProgressStage, progress: number, message: string) => void;
 
-const EXPECTED_CHARS = 15_000;
+const LLM_PROGRESS_MIN = 10;
+const LLM_PROGRESS_MAX = 85;
+const LLM_PROGRESS_RANGE = LLM_PROGRESS_MAX - LLM_PROGRESS_MIN;
+const THROTTLE_MS = 300;
 
 export async function convertPdfToStatementStreaming(
   buffer: Buffer,
@@ -202,22 +205,34 @@ 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 = '';
     let charsReceived = 0;
+    let lastEmitTime = 0;
 
     for await (const chunk of stream) {
       const delta = chunk.choices[0]?.delta?.content;
       if (delta) {
         accumulated += delta;
         charsReceived += delta.length;
-        const llmProgress = Math.min(
-          85,
-          Math.round((charsReceived / EXPECTED_CHARS) * 75 + 10),
-        );
-        onProgress('llm', llmProgress, 'Конвертация через LLM...');
+
+        const now = Date.now();
+        if (now - lastEmitTime >= THROTTLE_MS) {
+          const ratio = Math.min(1, charsReceived / expectedChars);
+          const llmProgress = Math.min(
+            LLM_PROGRESS_MAX,
+            Math.round(ratio * LLM_PROGRESS_RANGE + LLM_PROGRESS_MIN),
+          );
+          onProgress('llm', llmProgress, 'Конвертация через LLM...');
+          lastEmitTime = now;
+        }
       }
     }
 
+    onProgress('llm', LLM_PROGRESS_MAX, 'LLM завершил, обработка результата...');
+
     const content = accumulated.trim();
     if (!content) {
       return {