{
 "flight": {
  "id": 882211,
  "agent": "cursor",
  "state": "closed",
  "title": "Optimize dataset storage with pyarrow",
  "number": 380,
  "source": "aidev",
  "commits": 12,
  "debrief": null,
  "outcome": "abandoned",
  "signals": [
   "aidev:Cursor"
  ],
  "index_ok": false,
  "additions": 3458,
  "closed_at": "2025-07-07T19:32:05+00:00",
  "deletions": 2457,
  "merged_at": null,
  "opened_at": "2025-07-04T20:45:02+00:00",
  "task_type": "feat",
  "body_chars": 682,
  "confidence": "dataset",
  "updated_at": "2026-11-03T17:53:33.703657+00:00",
  "enriched_at": null,
  "body_excerpt": "Implement PyArrow-based incremental checkpoint storage with deduplication to reduce disk usage and enhance debugging capabilities.\n\nCloses #221 \n\nPreviously, DocETL stored complete intermediate datasets as separate JSON files for each operation, leading to significant storage redundancy and ineffici",
  "review_count": 0,
  "files_changed": 11,
  "hours_to_merge": null,
  "metrics_source": "aidev_commit_sum",
  "change_requests": 0,
  "og_generated_at": null,
  "reviewer_excerpt": null,
  "review_comment_count": 0,
  "reviewer_excerpt_url": null
 },
 "repo": {
  "name": "docetl",
  "owner": "ucbepic",
  "stars": 4218,
  "license": "MIT",
  "full_name": "ucbepic/docetl",
  "primary_language": "Python"
 },
 "author": {
  "login": "shreyashankar",
  "name": "Shreya Shankar",
  "github_profile": "https://github.com/shreyashankar",
  "page": "https://agentriders.com/logs/author/shreyashankar/"
 },
 "claim": null,
 "events": [
  {
   "at": null,
   "url": null,
   "kind": "committed",
   "actor_login": "Cursor Agent"
  },
  {
   "at": null,
   "url": null,
   "kind": "committed",
   "actor_login": "Cursor Agent"
  },
  {
   "at": null,
   "url": null,
   "kind": "committed",
   "actor_login": "Cursor Agent"
  },
  {
   "at": null,
   "url": null,
   "kind": "committed",
   "actor_login": "Cursor Agent"
  },
  {
   "at": null,
   "url": null,
   "kind": "committed",
   "actor_login": "Cursor Agent"
  },
  {
   "at": null,
   "url": null,
   "kind": "committed",
   "actor_login": "Cursor Agent"
  },
  {
   "at": null,
   "url": null,
   "kind": "committed",
   "actor_login": "Cursor Agent"
  },
  {
   "at": null,
   "url": null,
   "kind": "committed",
   "actor_login": "Cursor Agent"
  },
  {
   "at": null,
   "url": null,
   "kind": "committed",
   "actor_login": "Cursor Agent"
  },
  {
   "at": null,
   "url": null,
   "kind": "committed",
   "actor_login": "Cursor Agent"
  },
  {
   "at": null,
   "url": null,
   "kind": "committed",
   "actor_login": "Shreya Shankar"
  },
  {
   "at": null,
   "url": null,
   "kind": "committed",
   "actor_login": "Shreya Shankar"
  },
  {
   "at": "2025-07-07T19:32:05+00:00",
   "url": null,
   "kind": "closed",
   "actor_login": "shreyashankar"
  }
 ],
 "related": [
  {
   "agent": "cursor",
   "state": "merged",
   "title": "Fix github issue 384",
   "number": 387,
   "outcome": "merged_clean",
   "index_ok": true,
   "additions": 113,
   "deletions": 370,
   "merged_at": "2025-07-15T03:08:15+00:00",
   "opened_at": "2025-07-15T01:32:27+00:00",
   "task_type": "fix",
   "files_changed": 2,
   "hours_to_merge": 1.6
  },
  {
   "agent": "cursor",
   "state": "merged",
   "title": "Add operators to pandas API",
   "number": 379,
   "outcome": "merged_clean",
   "index_ok": true,
   "additions": 893,
   "deletions": 14,
   "merged_at": "2025-07-04T18:59:24+00:00",
   "opened_at": "2025-07-04T17:47:19+00:00",
   "task_type": "feat",
   "files_changed": 6,
   "hours_to_merge": 1.2
  },
  {
   "agent": "cursor",
   "state": "merged",
   "title": "Refactor api.py for structured output",
   "number": 378,
   "outcome": "merged_clean",
   "index_ok": true,
   "additions": 3120,
   "deletions": 2470,
   "merged_at": "2025-07-04T17:58:16+00:00",
   "opened_at": "2025-07-04T05:31:42+00:00",
   "task_type": "refactor",
   "files_changed": 8,
   "hours_to_merge": 12.44
  }
 ],
 "pr_url": "https://github.com/ucbepic/docetl/pull/380",
 "page": "https://agentriders.com/logs/ucbepic/docetl/380/"
}