Unverified50% confidenceFactExact time
v3.0.71 fixed three issues with scheduled runs: queued runs no longer remain permanently in the pending state; runs whose model calls fail are marked as failed with the error message attached; and after recovering from a service outage, only the most recent missed time point is executed, rather than catching up on all missed runs.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/13/2026
First Seen
Valid until: 1/11/2027
Sources
Related Entities
Related Claims
Unverifiedv3.20.0 fixes a hang issue in Live scenarios occurring near the fractional-level transcription grouping cutoff time.73% similarUnverifiedIssue #8234 documents a silent loop problem: durability="sync" does not enforce ordering between put_writes and checkpoint persistence, which can produce inconsistent state during crash recovery.71% similarUnverifiedWhen fixes were applied without Fix Notes, only about 1% of errors were resolved in the first three hours after deployment; after Fix Notes were added, the model stopped making those errors in subsequent calls.68% similarUnverifiedThe update fixes the issue where canceling immediately after sending a message now truly stops the task; previously, a cancellation occurring during the turn initialization phase would be ignored and the task would continue running.67% similarUnverifiedVersion 4.0.109 fixes the issue where replacement completion requests can maintain a loading state and be cancellable when an earlier request has already settled.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1016285API
curl https://kongchang.com/api/v1/knowledge/claims/1016285MCP
get_claim(id=1016285)