diff --git a/CHANGELOG.md b/CHANGELOG.md
index e3bdbdba86f..452af59a71d 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -16,6 +16,7 @@ Docs: https://docs.openclaw.ai
 
 ### Fixes
 
+- Chat/UI: strip inline reply/audio directive tags (`[[reply_to_current]]`, `[[reply_to:<id>]]`, `[[audio_as_voice]]`) from displayed chat history, live chat event output, and session preview snippets so control tags no longer leak into user-visible surfaces.
 - Security/Shell env: validate login-shell executable paths for shell-env fallback (`/etc/shells` + trusted prefixes) and block `SHELL` in dangerous env override policy paths so untrusted shell-path injection falls back safely to `/bin/sh`. Thanks @athuljayaram for reporting.
 - Security/Config: make parsed chat allowlist checks fail closed when `allowFrom` is empty, restoring expected DM/pairing gating.
 - Security/Exec: in non-default setups that manually add `sort` to `tools.exec.safeBins`, block `sort --compress-program` so allowlist-mode safe-bin checks cannot bypass approval. Thanks @tdjackey for reporting.
@@ -23,7 +24,7 @@ Docs: https://docs.openclaw.ai
 - Security/Archive: block zip symlink escapes during archive extraction.
 - Security/Discord: add `openclaw security audit` warnings for name/tag-based Discord allowlist entries (DM allowlists, guild/channel `users`, and pairing-store entries), highlighting slug-collision risk while keeping name-based matching supported, and canonicalize resolved Discord allowlist names to IDs at runtime without rewriting config files. Thanks @tdjackey for reporting.
 - Security/Gateway: block node-role connections when device identity metadata is missing.
-- Security/OpenClawKit/UI: strip synthetic inbound metadata wrappers from displayed conversation history so internal untrusted context does not leak into user-visible chat logs.
+- Chat/Usage/TUI: strip synthetic inbound metadata blocks (including `Conversation info` and trailing `Untrusted context` channel metadata wrappers) from displayed conversation history so internal prompt context no longer leaks into user-visible logs.
 - Security/Browser relay: harden extension relay auth token handling for `/extension` and `/cdp` pathways.
 - Cron: persist `delivered` state in cron job records so delivery failures remain visible in status and logs. (#19174) Thanks @simonemacario.
 - Config/Doctor: only repair the OAuth credentials directory when affected channels are configured, avoiding fresh-install noise.
@@ -61,11 +62,6 @@ Docs: https://docs.openclaw.ai
 
 ### Fixes
 
-- Chat/UI: strip inline reply/audio directive tags (`[[reply_to_current]]`, `[[reply_to:<id>]]`, `[[audio_as_voice]]`) from displayed chat history, live chat event output, and session preview snippets so control tags no longer leak into user-visible surfaces.
-- Chat/Usage/TUI: strip synthetic inbound metadata blocks (including `Conversation info` and trailing `Untrusted context` channel metadata wrappers) from displayed conversation history so internal prompt context no longer leaks into user-visible logs.
-- Security/Exec: in non-default setups that manually add `sort` to `tools.exec.safeBins`, block `sort --compress-program` so allowlist-mode safe-bin checks cannot bypass approval. Thanks @tdjackey for reporting.
-- Doctor/State integrity: only require/create the OAuth credentials directory when WhatsApp or pairing-backed channels are configured, and downgrade fresh-install missing-dir noise to an informational warning.
-- Agents/Sanitization: stop rewriting billing-shaped assistant text outside explicit error context so normal replies about billing/credits/payment are preserved across messaging channels. (#17834, fixes #11359)
 - Security/Agents: cap embedded Pi runner outer retry loop with a higher profile-aware dynamic limit (32-160 attempts) and return an explicit `retry_limit` error payload when retries never converge, preventing unbounded internal retry cycles (`GHSA-76m6-pj3w-v7mf`).
 - Telegram: detect duplicate bot-token ownership across Telegram accounts at startup/status time, mark secondary accounts as not configured with an explicit fix message, and block duplicate account startup before polling to avoid endless `getUpdates` conflict loops.
 - Agents/Tool images: include source filenames in `agents/tool-images` resize logs so compression events can be traced back to specific files.