docs: refresh session recall sanitization mirrors

docs/tools/index.md

@@ -130,8 +130,9 @@ Use `group:*` shorthands in allow/deny lists:
 | `group:openclaw`   | All built-in OpenClaw tools (excludes plugin tools)                                                       |
 
 `sessions_history` returns a bounded, safety-filtered recall view. It strips
-thinking tags, downgraded tool-call scaffolding, leaked model control tokens,
-and malformed MiniMax tool-call XML from assistant text, then applies
+thinking tags, `<relevant-memories>` scaffolding, plain-text tool-call XML
+payloads, downgraded tool-call scaffolding, leaked model control tokens, and
+malformed MiniMax tool-call XML from assistant text, then applies
 redaction/truncation and possible oversized-row placeholders instead of acting
 as a raw transcript dump.
 

docs/tools/subagents.md

@@ -265,6 +265,8 @@ Announce payloads include a stats line at the end (even when wrapped):
 
 - assistant recall is normalized first:
   - thinking tags are stripped
+  - `<relevant-memories>` / `<relevant_memories>` scaffolding blocks are stripped
+  - plain-text tool-call XML payload blocks such as `<tool_call>...</tool_call>` / `<function_calls>...</function_calls>` are stripped
   - downgraded tool-call/result scaffolding and historical-context markers are stripped
   - leaked model control tokens such as `<|assistant|>` are stripped
   - malformed MiniMax tool-call XML is stripped