langgraph

mirror of https://github.com/langchain-ai/langgraph.git synced 2026-09-30 21:45:08 +02:00

Files

T

Elior Nataf Lackritz a8e732c879 fix(langgraph): give each bulk_update_state update its own task id

An update whose node has no pending task to reuse was stored under
uuid5(checkpoint_id, INTERRUPT), so every such update in one superstep
shared a task id. Savers keep one write per (task_id, idx), so all but the
first update's writes were dropped. Plain channels were unaffected, since
their value is stored in the new checkpoint, but a DeltaChannel replays
those writes and lost every update after the first.

The ith update now gets uuid5(checkpoint_id, f"{INTERRUPT}:{i}"). The first
keeps the old id, so a single update stores exactly what it did before.

2026-09-30 12:47:55 -04:00

checkpoint

chore(deps): bump anyio from 4.12.1 to 4.14.2 in /libs/checkpoint (#8995 )

2026-09-18 15:24:38 -07:00

checkpoint-conformance

chore(deps): bump anyio from 4.13.0 to 4.14.2 in /libs/checkpoint-conformance (#8996 )

2026-09-18 15:36:37 -07:00

checkpoint-postgres

fix(checkpoint-postgres): derive the delta walk cursor once the target loads (#8556 )

2026-09-30 12:16:55 -04:00

checkpoint-sqlite

fix(checkpoint-sqlite): walk delta ancestors by parent pointer (#8557 )