@@ -21,7 +21,9 @@ Docs: https://docs.openclaw.ai
2121- CLI: format `openclaw acp client` failures through the shared error formatter so object-shaped errors stay readable instead of printing `[object Object]`. Fixes #83904. (#84080)
2222- Providers/Ollama: default unknown-capabilities models to tool-capable so discovered native Ollama models can use tools when `/api/show` omits capabilities. (#84055) Thanks @dutifulbob.
2323- Installer/Windows: launch `install.ps1` onboarding as an attached child process so fresh native Windows installs do not freeze visibly at `Starting setup...` or corrupt the wizard's terminal rendering.
24+- CLI/update: keep restart health checks working across one-version CLI/Gateway protocol skew and use the managed Gateway service Node for all follow-up commands even when the package root is unchanged, so `openclaw update` no longer silently switches the gateway to a different Node binary when multiple Node installations are present. Thanks @amknight.
2425- Memory/search: close local embedding providers when active-memory searches time out so pending local model loads and embedding contexts are aborted and released. (#83858) Thanks @brokemac79.
26+2527- Agents: include bounded trajectory queued-writer diagnostics in `pi-trajectory-flush` timeout warnings so flush stalls show pending writes, queued bytes, and append state. Fixes #82961. (#82962) Thanks @galiniliev.
2628- Agents/subagents: recover stale completion announces by retrying unsupported transcript-wait wakes without transcript waiting and forcing a message-tool handoff when the requester run is already stale. Fixes #83699. (#83700) Thanks @galiniliev.
2729- Agents: honor explicit `models.providers.<id>.timeoutSeconds` values above the default idle watchdog for cloud and self-hosted providers, so long first-token waits no longer fall back at ~120s when the provider timeout is higher. (#83979) Thanks @yujiawei.
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。