From 68c0a37cab71206d0e8697ef65420e023eee0c6e Mon Sep 17 00:00:00 2001
From: chriscrosstalk <49691103+chriscrosstalk@users.noreply.github.com>
Date: Fri, 15 May 2026 23:01:45 -0700
Subject: [PATCH] fix(RAG): anchor continuation-batch initial progress to
 overall-file frame (#889)

Each continuation batch of a multi-batch ZIM embed runs as a fresh
BullMQ job, so handle() ran the hardcoded `safeUpdateProgress(job, 5)`
even when the file was already 100k articles into a 600k-article ZIM.
The UI gauge briefly dropped to 5% before the per-batch onProgress
callback caught up to the true overall percentage, reading as a
backward jump every time a new batch started.

Compute initialPercent from batchOffset / totalArticles when available,
falling back to 5 for single-batch files (uploaded PDFs, txts) where
totalArticles isn't set. Capped at 99 to leave headroom for the 100%
final-batch marker.

Follow-up to PR #880 (which fixed the 0-100% scaling during a batch
but still had the initial-frame regression).
---
 admin/app/jobs/embed_file_job.ts | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/admin/app/jobs/embed_file_job.ts b/admin/app/jobs/embed_file_job.ts
index 4607a9a..844af7d 100644
--- a/admin/app/jobs/embed_file_job.ts
+++ b/admin/app/jobs/embed_file_job.ts
@@ -85,8 +85,16 @@ export class EmbedFileJob {
 
       logger.info(`[EmbedFileJob] Services ready. Processing file: ${fileName}`)
 
-      // Update progress starting
-      await this.safeUpdateProgress(job, 5)
+      // Anchor initial progress to where we are in the overall file. For a
+      // continuation batch midway through a multi-batch ZIM (e.g. offset 100k of
+      // 600k), the hardcoded 5 used to make the gauge briefly flash 0→5→real,
+      // which read as a backward jump. Fall back to 5 for single-batch files
+      // where totalArticles isn't set.
+      const initialPercent =
+        totalArticles && totalArticles > 0
+          ? Math.min(99, Math.round(((batchOffset || 0) / totalArticles) * 100))
+          : 5
+      await this.safeUpdateProgress(job, initialPercent)
       await job.updateData({
         ...job.data,
         status: 'processing',