From d2b9d918af8a12f53bc66705e151e7119c40fefe Mon Sep 17 00:00:00 2001 From: Peter Steinberger Date: Fri, 10 Apr 2026 13:53:11 +0100 Subject: [PATCH] docs(changelog): thank @hanamizuki for #64172 --- CHANGELOG.md | 1 + 1 file changed, 1 insertion(+) diff --git a/CHANGELOG.md b/CHANGELOG.md index 70fc9c6700b..44a11901269 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -95,6 +95,7 @@ Docs: https://docs.openclaw.ai - Agents/Bedrock: let `/btw` side questions use `auth: "aws-sdk"` without a static API key so Bedrock IAM and instance-role sessions stop failing before the side question runs. (#64218) Thanks @SnowSky1. - Agents/failover: detect llama.cpp slot context overflows as context-overflow errors so compaction can retry self-hosted OpenAI-compatible runs instead of surfacing the raw upstream 400. (#64196) Thanks @alexander-applyinnovations. - Claude CLI/skills: pass eligible OpenClaw skills into CLI runs, including native Claude Code skill resolution via a temporary plugin plus per-run skill env/API key injection. (#62686, #62723) Thanks @zomars. +- Discord: keep generated auto-thread names working with reasoning models by giving title generation enough output budget for thinking plus visible title text. (#64172) Thanks @hanamizuki. - Heartbeat: ignore doc-only Markdown fence markers in the default `HEARTBEAT.md` template so comment-only heartbeat scaffolds skip API calls again. (#63434) Thanks @ravyg. - Control UI/BTW: render `/btw` side results as dismissible ephemeral cards in the browser, send `/btw` immediately during active runs, and clear stale BTW cards on reset flows so webchat matches the intended detached side-question behavior. (#64290) Thanks @ngutman. - Reply/skills: keep resolved skill and memory secret config stable through embedded reply runs so raw SecretRefs in secondary skill settings no longer crash replies when the gateway already has the live env. (#64249) Thanks @mbelinky.