diff --git a/agent/conversation_loop.py b/agent/conversation_loop.py
index e34631377e4..1361d6ed6e6 100644
--- a/agent/conversation_loop.py
+++ b/agent/conversation_loop.py
@@ -484,7 +484,8 @@ def run_conversation(
             tools=agent.tools or None,
         )
 
-        if _preflight_tokens >= agent.context_compressor.threshold_tokens:
+        if _preflight_tokens >= agent.context_compressor.threshold_tokens \
+           and agent.context_compressor.should_compress(_preflight_tokens):
             logger.info(
                 "Preflight compression: ~%s tokens >= %s threshold (model %s, ctx %s)",
                 f"{_preflight_tokens:,}",
@@ -4180,6 +4181,7 @@ def run_conversation(
         "estimated_cost_usd": agent.session_estimated_cost_usd,
         "cost_status": agent.session_cost_status,
         "cost_source": agent.session_cost_source,
+        "session_id": agent.session_id,
     }
     if agent._tool_guardrail_halt_decision is not None:
         result["guardrail"] = agent._tool_guardrail_halt_decision.to_metadata()
diff --git a/gateway/run.py b/gateway/run.py
index cb8b60e556d..675774022e3 100644
--- a/gateway/run.py
+++ b/gateway/run.py
@@ -8692,6 +8692,7 @@ class GatewayRunner:
             # session_entry so transcript writes below go to the right session.
             if agent_result.get("session_id") and agent_result["session_id"] != session_entry.session_id:
                 session_entry.session_id = agent_result["session_id"]
+                self.session_store._save()
 
             # Prepend reasoning/thinking if display is enabled (per-platform)
             try: