---
pid: 1532856
cwd: "/home/ubuntu/transcripts"
command: "cd /home/ubuntu/transcripts && source venv/bin/activate && python3 << 'PYEOF'\nimport os, time, boto3\nfrom concurrent.futures import ThreadPoolExecutor, as_completed\nfrom botocore.config import Config\nfrom dotenv import load_dotenv\n\nload_dotenv('.env')\ns3 = boto3.client('s3', endpoint_url=os.environ['R2_ENDPOINT_URL'], aws_access_key_id=os.environ['R2_ACCESS_KEY_ID'], aws_secret_access_key=os.environ['R2_SECRET_ACCESS_KEY'], region_name='auto', config=Config(max_pool_connections=16, multipart_threshold=256*1024*1024, multipart_chunksize=128*1024*1024))\n\nBUCKET = 'metafiles'\nPREFIX = 'transcripts_metadata'\n\n# Verify bucket exists\ntry:\n    s3.head_bucket(Bucket=BUCKET)\n    print(f\"Bucket '{BUCKET}' exists\")\nexcept Exception as e:\n    print(f\"Bucket '{BUCKET}' check failed: {e}\")\n    print(\"Attempting to create bucket...\")\n    try:\n        s3.create_bucket(Bucket=BUCKET)\n        print(f\"Created bucket '{BUCKET}'\")\n    except Exception as e2:\n        print(f\"Create failed: {e2}\")\n        raise\n\nDATA_FILES = [\n    (\"data/transcription_results.parquet\", \"data\"),\n    (\"data/transcription_flags.parquet\", \"data\"),\n    (\"data/recover_v2_consolidated.parquet\", \"data\"),\n    (\"data/recover_manifest.parquet\", \"data\"),\n    (\"data/youtube_video_metadata_all.csv\", \"data\"),\n    (\"data/video_tts_classification_all.csv\", \"data\"),\n    (\"data/video_tts_classification_final.csv\", \"data\"),\n    (\"data/video_tts_dropped_by_channel.csv\", \"data\"),\n    (\"data/golden_segments.csv\", \"data\"),\n    (\"data/redo_segments.csv\", \"data\"),\n    (\"data/dispose_segments.csv\", \"data\"),\n    (\"data/video_summary.csv\", \"data\"),\n]\n\nFINAL_DATA_FILES = [\n    (\"final_data/final_cleaned_segments_with_variants_rerouted_repetition_filtered.parquet\", \"final_data\"),\n    (\"final_data/final_cleaned_segments.parquet\", \"final_data\"),\n    (\"final_data/transcript_variants_clean_rerouted.parquet\", \"final_data\"),\n    (\"final_data/transcript_variants_merged.parquet\", \"final_data\"),\n    (\"final_data/final_cleaned_excluded_videos.csv\", \"final_data\"),\n    (\"final_data/final_cleaned_keep_videos.csv\", \"final_data\"),\n    (\"final_data/final_cleaned_video_rollup.parquet\", \"final_data\"),\n    (\"final_data/repetition_flags.parquet\", \"final_data\"),\n]\n\nALL_FILES = DATA_FILES + FINAL_DATA_FILES\n\ndef upload_one(local_path, r2_key, size_gb):\n    t0 = time.time()\n    print(f\"  UPLOADING {local_path} ({size_gb:.1f}GB) -> s3://{BUCKET}/{r2_key}\")\n    s3.upload_file(local_path, BUCKET, r2_key)\n    elapsed = time.time() - t0\n    print(f\"  DONE      {local_path} in {elapsed:.0f}s\")\n    return local_path, elapsed\n\nt0 = time.time()\ntotal_bytes = 0\nfor local_rel, subfolder in ALL_FILES:\n    local_path = f\"/home/ubuntu/transcripts/{local_rel}\"\n    size = os.path.getsize(local_path)\n    total_bytes += size\n    r2_key = f\"{PREFIX}/{subfolder}/{os.path.basename(local_rel)}\"\n    upload_one(local_path, r2_key, size / (1024**3))\n\nelapsed = time.time() - t0\nprint(f\"\\n=== BACKUP COMPLETE ===\")\nprint(f\"Files: {len(ALL_FILES)}\")\nprint(f\"Total: {total_bytes / (1024**3):.1f} GB\")\nprint(f\"Time:  {elapsed:.0f}s\")\nPYEOF"
started_at: 2026-03-14T01:11:16.522Z
running_for_seconds: 0     
---
Traceback (most recent call last):
  File "<stdin>", line 7, in <module>
  File "/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/botocore/config.py", line 354, in __init__
    self._user_provided_options = self._record_user_provided_options(
  File "/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/botocore/config.py", line 402, in _record_user_provided_options
    raise TypeError(f"Got unexpected keyword argument '{key}'")
TypeError: Got unexpected keyword argument 'multipart_threshold'

---
exit_code: 1
elapsed_ms: 224
ended_at: 2026-03-14T01:11:16.746Z
---