fix(compression): 3-line fix for infinite compression loop (#29335)

Three compounding root causes:

A) run_conversation() result dict missing session_id — gateway's
   dead-code guard at gateway/run.py:8700 never triggers
B) preflight compression bypasses should_compress() anti-thrashing —
   re-triggers every turn when tool schemas dominate token budget
C) gateway updates session_entry.session_id in memory but doesn't
   persist via session_store._save()

Fixes: #29335

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()