fix(webchat): keep runtime context out of visible transcripts

Keep WebChat runtime context available to the model while persisting only the transcript-facing user prompt across gateway, CLI, queued follow-up, and embedded Pi paths.

Adds regression coverage for history sanitization, CLI transcript persistence, media-only auto-reply prompts, and embedded Pi prompt rewrite against a real SessionManager file.

Co-authored-by: 91wan <91wan@users.noreply.github.com>

docs/reference/transcript-hygiene.md

@@ -16,6 +16,7 @@ file is backed up alongside the session file.
 
 Scope includes:
 
+- Runtime-only prompt context staying out of user-visible transcript turns
 - Tool call id sanitization
 - Tool call input validation
 - Tool result pairing repair
@@ -30,6 +31,20 @@ If you need transcript storage details, see:
 
 ---
 
+## Global rule: runtime context is not user transcript
+
+Runtime/system context can be added to the model prompt for a turn, but it is
+not end-user-authored content. OpenClaw keeps a separate transcript-facing
+prompt body for Gateway replies, queued followups, ACP, CLI, and embedded Pi
+runs. Stored visible user turns use that transcript body instead of the
+runtime-enriched prompt.
+
+For legacy sessions that already persisted runtime wrappers, Gateway history
+surfaces apply a display projection before returning messages to WebChat,
+TUI, REST, or SSE clients.
+
+---
+
 ## Where this runs
 
 All transcript hygiene is centralized in the embedded runner: