fix: preserve inter-session input provenance (thanks @anbecker)

docs/concepts/session-tool.md

@@ -94,6 +94,7 @@ Behavior:
 - Announce delivery runs after the primary run completes and is best-effort; `status: "ok"` does not guarantee the announce was delivered.
 - Waits via gateway `agent.wait` (server-side) so reconnects don't drop the wait.
 - Agent-to-agent message context is injected for the primary run.
+- Inter-session messages are persisted with `message.provenance.kind = "inter_session"` so transcript readers can distinguish routed agent instructions from external user input.
 - After the primary run completes, OpenClaw runs a **reply-back loop**:
   - Round 2+ alternates between requester and target agents.
   - Reply exactly `REPLY_SKIP` to stop the ping‑pong.

docs/reference/transcript-hygiene.md

@@ -24,6 +24,7 @@ Scope includes:
 - Turn validation / ordering
 - Thought signature cleanup
 - Image payload sanitization
+- User-input provenance tagging (for inter-session routed prompts)
 
 If you need transcript storage details, see:
 
@@ -72,6 +73,23 @@ Implementation:
 
 ---
 
+## Global rule: inter-session input provenance
+
+When an agent sends a prompt into another session via `sessions_send` (including
+agent-to-agent reply/announce steps), OpenClaw persists the created user turn with:
+
+- `message.provenance.kind = "inter_session"`
+
+This metadata is written at transcript append time and does not change role
+(`role: "user"` remains for provider compatibility). Transcript readers can use
+this to avoid treating routed internal prompts as end-user-authored instructions.
+
+During context rebuild, OpenClaw also prepends a short `[Inter-session message]`
+marker to those user turns in-memory so the model can distinguish them from
+external end-user instructions.
+
+---
+
 ## Provider matrix (current behavior)
 
 **OpenAI / OpenAI Codex**