Agents: note HTTP 499 fallback fix

This commit is contained in:
Altay
2026-03-10 01:49:37 +03:00
parent 686619b2a5
commit 0053bae140

View File

@@ -38,6 +38,7 @@ Docs: https://docs.openclaw.ai
- Protocol/Swift model sync: regenerate pending node work Swift bindings after the landed `node.pending.*` schema additions so generated protocol artifacts are consistent again. (#41477) Thanks @mbelinky.
- Discord/reply chunking: resolve the effective `maxLinesPerMessage` config across live reply paths and preserve `chunkMode` in the fast send path so long Discord replies no longer split unexpectedly at the default 17-line limit. (#40133) thanks @rbutera.
- Logging/probe observations: suppress structured embedded and model-fallback probe warnings on the console without hiding error or fatal output. (#41338) thanks @altaywtf.
- Agents/fallback: treat HTTP 499 responses as transient in both raw-text and structured failover paths so Anthropic-style client-closed overload responses trigger model fallback reliably. (#41468) thanks @zeroasterisk.
## 2026.3.8