From 8bdec8088204a321b15dabe7c0df731ad3a66ae1 Mon Sep 17 00:00:00 2001
From: ai-ag2026 <261867348+ai-ag2026@users.noreply.github.com>
Date: Sun, 3 May 2026 16:01:28 +0200
Subject: [PATCH] fix(agent): surface preflight compression status

Preflight compression can run synchronously before the first model call when a loaded session exceeds the active context threshold. Gateway users saw no visible progress while the compression LLM call was in flight, which can look like a dropped message during long compactions.\n\nEmit the existing lifecycle status through _emit_status before starting preflight compression so CLI, gateway, and WebUI status callbacks all get immediate feedback.\n\nAdds a regression assertion for the preflight path.
---
 run_agent.py                            | 10 +++++-----
 tests/run_agent/test_413_compression.py |  6 ++++++
 2 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/run_agent.py b/run_agent.py
index cfcd325eb..2e0baa2a4 100644
--- a/run_agent.py
+++ b/run_agent.py
@@ -10623,11 +10623,11 @@ class AIAgent:
                     self.model,
                     f"{self.context_compressor.context_length:,}",
                 )
-                if not self.quiet_mode:
-                    self._safe_print(
-                        f"📦 Preflight compression: ~{_preflight_tokens:,} tokens "
-                        f">= {self.context_compressor.threshold_tokens:,} threshold"
-                    )
+                self._emit_status(
+                    f"📦 Preflight compression: ~{_preflight_tokens:,} tokens "
+                    f">= {self.context_compressor.threshold_tokens:,} threshold. "
+                    "This may take a moment."
+                )
                 # May need multiple passes for very large sessions with small
                 # context windows (each pass summarises the middle N turns).
                 for _pass in range(3):
diff --git a/tests/run_agent/test_413_compression.py b/tests/run_agent/test_413_compression.py
index 8bd357d3d..5410f196e 100644
--- a/tests/run_agent/test_413_compression.py
+++ b/tests/run_agent/test_413_compression.py
@@ -432,6 +432,8 @@ class TestPreflightCompression:
 
         ok_resp = _mock_response(content="After preflight", finish_reason="stop")
         agent.client.chat.completions.create.side_effect = [ok_resp]
+        status_messages = []
+        agent.status_callback = lambda ev, msg: status_messages.append((ev, msg))
 
         with (
             patch.object(agent, "_compress_context") as mock_compress,
@@ -460,6 +462,10 @@ class TestPreflightCompression:
         )
         assert result["completed"] is True
         assert result["final_response"] == "After preflight"
+        assert any(
+            ev == "lifecycle" and "Preflight compression" in msg
+            for ev, msg in status_messages
+        )
 
     def test_no_preflight_when_under_threshold(self, agent):
         """When history fits within context, no preflight compression needed."""