From 00229ec6e479448f41fa3563833d7e3d1ec7411b Mon Sep 17 00:00:00 2001
From: Sebastian <19554889+sebslight@users.noreply.github.com>
Date: Sun, 15 Feb 2026 21:45:55 -0500
Subject: [PATCH] docs(changelog): note browser tool retry-loop fix

---
 CHANGELOG.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index b1b07e3adeb..128709c0021 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -38,6 +38,7 @@ Docs: https://docs.openclaw.ai
 - Web Fetch/Security: cap downloaded response body size before HTML parsing to prevent memory exhaustion from oversized or deeply nested pages. Thanks @xuemian168.
 - Skills/Security: restrict `download` installer `targetDir` to the per-skill tools directory to prevent arbitrary file writes. Thanks @Adam55A-code.
 - Agents: return an explicit timeout error reply when an embedded run times out before producing any payloads, preventing silent dropped turns during slow cache-refresh transitions. (#16659) Thanks @liaosvcaf and @vignesh07.
+- Browser/Agents: when browser control service is unavailable, return explicit non-retry guidance (instead of "try again") so models do not loop on repeated browser tool calls until timeout. (#17673) Thanks @tag-assistant.
 - Agents/OpenAI: force `store=true` for direct OpenAI Responses/Codex runs to preserve multi-turn server-side conversation state, while leaving proxy/non-OpenAI endpoints unchanged. (#16803) Thanks @mark9232 and @vignesh07.
 - Agents/Security: sanitize workspace paths before embedding into LLM prompts (strip Unicode control/format chars) to prevent instruction injection via malicious directory names. Thanks @aether-ai-agent.
 - Agents/Context: apply configured model `contextWindow` overrides after provider discovery so `lookupContextTokens()` honors operator config values (including discovery-failure paths). (#17404) Thanks @michaelbship and @vignesh07.