From deb5ed601094a8c7d3c75d4739a62ecfe52aa958 Mon Sep 17 00:00:00 2001
From: Igor Loskutov <igor.loskutoff@gmail.com>
Date: Fri, 23 Jan 2026 16:36:16 -0500
Subject: [PATCH] Fix: Preserve track_index explicitly in PaddedTrackInfo

- Add track_index to PaddedTrackInfo model
- Preserve track_index from PadTrackResult when building padded_tracks list
- Use explicit track_index instead of enumerate in process_transcriptions
- Removes fragile ordering assumption
---
 .../hatchet/workflows/daily_multitrack_pipeline.py       | 9 +++++----
 server/reflector/hatchet/workflows/models.py             | 1 +
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/server/reflector/hatchet/workflows/daily_multitrack_pipeline.py b/server/reflector/hatchet/workflows/daily_multitrack_pipeline.py
index 8fc59a3f..7f0e4198 100644
--- a/server/reflector/hatchet/workflows/daily_multitrack_pipeline.py
+++ b/server/reflector/hatchet/workflows/daily_multitrack_pipeline.py
@@ -434,11 +434,12 @@ async def process_paddings(input: PipelineInput, ctx: Context) -> ProcessPadding
     for result in results:
         pad_result = PadTrackResult(**result[TaskName.PAD_TRACK])
 
-        # Store S3 key info (not presigned URL) - consumer tasks presign on demand
         if pad_result.padded_key:
             padded_tracks.append(
                 PaddedTrackInfo(
-                    key=pad_result.padded_key, bucket_name=pad_result.bucket_name
+                    key=pad_result.padded_key,
+                    bucket_name=pad_result.bucket_name,
+                    track_index=pad_result.track_index,
                 )
             )
 
@@ -482,13 +483,13 @@ async def process_transcriptions(
     bulk_runs = [
         transcription_workflow.create_bulk_run_item(
             input=TranscriptionInput(
-                track_index=i,
+                track_index=padded_track.track_index,
                 padded_key=padded_track.key,
                 bucket_name=padded_track.bucket_name,
                 language=source_language,
             )
         )
-        for i, padded_track in enumerate(padded_tracks)
+        for padded_track in padded_tracks
     ]
 
     results = await transcription_workflow.aio_run_many(bulk_runs)
diff --git a/server/reflector/hatchet/workflows/models.py b/server/reflector/hatchet/workflows/models.py
index b78f6e1a..4ba4a2a4 100644
--- a/server/reflector/hatchet/workflows/models.py
+++ b/server/reflector/hatchet/workflows/models.py
@@ -58,6 +58,7 @@ class PaddedTrackInfo(BaseModel):
 
     key: NonEmptyString
     bucket_name: NonEmptyString | None
+    track_index: int
 
 
 class ProcessPaddingsResult(BaseModel):