deer-flow

mirror of https://github.com/bytedance/deer-flow.git synced 2026-10-27 05:30:39 +00:00

History

fix(gateway): read subagent batch exports in small pages (#6706 )

* fix(gateway): read subagent batch exports in small pages

The results.jsonl export loaded 500 full rows per page before streaming
them. A row can hold max_result_chars of report plus as much evidence
JSON (result_artifact), so with the default limit one request peaked
around 280 MB and decoding a page's JSON columns stalled the event loop
for about half a second; at the 1,000,000 ceiling a page was roughly
1.7 GB.

Read 10 rows per page instead. Output and ordering are unchanged; a
full export of 1,000 default-sized rows now peaks at 6 MB with a 46 ms
worst stall and takes the same time.

* docs(changelog): reference #6706

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>

2026-10-12 17:38:24 +08:00

channels

feat(channels): Feishu interactive clarification cards (#6670 )

2026-10-11 23:58:54 +08:00

gateway

fix(gateway): read subagent batch exports in small pages (#6706 )

2026-10-12 17:38:24 +08:00

mcp_tasks

feat(mcp): filter background tasks by status (#6527 )

2026-10-10 08:53:51 +08:00

scheduler

fix(scheduler): keep a one-time task's scheduled run after an early trial (#6512 )