changelog: add browser MCP redaction and MEMORY/TTS guidance (#81930) · openclaw/openclaw@c8e12ca
vincentkoc
·
2026-05-17
·
via Recent Commits to openclaw:main
| Original file line number | Diff line number | Diff line change |
|---|
@@ -29,6 +29,8 @@ Docs: https://docs.openclaw.ai
|
29 | 29 | |
30 | 30 | ### Fixes |
31 | 31 | |
| 32 | +- Browser plugin: redact attach-details from Chrome MCP diagnostics and keep raw Chrome launch error output around long enough to surface in user reports without leaking sensitive paths. |
| 33 | +- System prompts: clarify MEMORY guidance over generic TTS hints in the embedded speech-core/system-prompt scaffolding so agents prefer memory-store usage over speech defaults. Fixes #81930. Thanks @giodl73-repo. |
32 | 34 | - Agents/auth: include the checked credential source in missing API key errors, so users can see which env var, profile, or config path to fix. Fixes #82785. Thanks @loeclos. |
33 | 35 | - Providers/GitHub Copilot: hash Responses replay item ids with sha256 instead of a weak 32-bit hash and build same-provider Copilot tool-call ids distinctly, so concurrent tool-call replays no longer collide and reject follow-up turns. |
34 | 36 | - Providers/Anthropic-messages: extract `reasoning_content` from `thinking` blocks during assistant replay so proxy providers that route through the Anthropic-messages transport preserve reasoning context across tool-call follow-up turns. Thanks @Sunnyone2three. |
|
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。
