[Feature Request] Add ability to resume/continue stalled deep-research workflow runs

Resolved 💬 1 comment Opened Jun 5, 2026 by powell-clark Closed Jul 12, 2026

Bug Description
deep-research/workflows - add ability to resume/continue a stalled run so as to not lose good progress. deep-research
Deep research harness — fan-out web searches, fetch sources, …105/105 agents · 2m46s · done

╭ Phases ──────────┬ Synthesize · 0 agents ───────────────────────────────────────────────╮
│ ✔ Scope 1/1 │ Not started yet │
│ ✔ Search 5/5 │ │
│ ✔ Fetch 24/24 │ │
│ ✔ Verify 75/75 │ │
│ ❯ 5 Synthesize │ │
│ │ │
│ │ │
│ │ │
│ │ │
│ │ │
│ │ │
│ │ │
│ │ │
│ │ │
│ │ │
│ │ │
│ │ │
│ │ │
│ │ │
│ │ │
│ …
Note: Content was truncated.

This workflow failed at the synthesis step. When I go into workflows, I cannot continue the workflow and finish it, so I've lost a lot of good tokens and data and research, which is very frustrating.

View original on GitHub ↗

This issue has 1 comment on GitHub. Read the full discussion on GitHub ↗