diff --git a/gateway/run.py b/gateway/run.py
index 9a34a066659..ca746bb7837 100644
--- a/gateway/run.py
+++ b/gateway/run.py
@@ -18206,6 +18206,22 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
                     except Exception:
                         pass
 
+                # Re-baseline the cached agent's message_count snapshot before
+                # recursing into the in-band queued (/queue) follow-up turn.
+                # The first turn has completed and flushed its own user +
+                # assistant rows to the SessionDB, so the cross-process
+                # coherence guard (#45966) — which this recursive _run_agent
+                # call re-enters — would otherwise see the grown on-disk count
+                # against the stale build-time snapshot and rebuild the agent
+                # on THIS process's OWN writes, destroying the prompt-cache
+                # prefix #46237 was merged to preserve.  The existing
+                # re-baseline in _handle_message_with_agent only runs after the
+                # whole _run_agent chain unwinds — too late for the in-band
+                # follow-up.  Use the same (session_key, session_id) the
+                # recursive call runs under so the snapshot matches exactly
+                # what the follow-up's guard will consult.  Fail-safe in helper.
+                self._refresh_agent_cache_message_count(session_key, session_id)
+
                 followup_result = await self._run_agent(
                     message=next_message,
                     context_prompt=context_prompt,