From 00ad3d3c9c862352334c4348534dce3fed77dd9b Mon Sep 17 00:00:00 2001
From: raymaylee <100820567+raymaylee@users.noreply.github.com>
Date: Wed, 13 May 2026 23:11:37 -0700
Subject: [PATCH] fix: show context compaction status

---
 run_agent.py                            |  3 +++
 tests/run_agent/test_413_compression.py | 26 +++++++++++++++++++++++++
 2 files changed, 29 insertions(+)

diff --git a/run_agent.py b/run_agent.py
index 590742b2da0..3d4f99cbc08 100644
--- a/run_agent.py
+++ b/run_agent.py
@@ -10341,6 +10341,9 @@ class AIAgent:
             f"{approx_tokens:,}" if approx_tokens else "unknown", self.model,
             focus_topic,
         )
+        self._emit_status(
+            "🗜️ Compacting context — summarizing earlier conversation so I can continue..."
+        )
 
         # Notify external memory provider before compression discards context
         if self._memory_manager:
diff --git a/tests/run_agent/test_413_compression.py b/tests/run_agent/test_413_compression.py
index 5410f196e65..3cbd47c0e1b 100644
--- a/tests/run_agent/test_413_compression.py
+++ b/tests/run_agent/test_413_compression.py
@@ -415,6 +415,32 @@ class TestHTTP413Compression:
 class TestPreflightCompression:
     """Preflight compression should compress history before the first API call."""
 
+    def test_compress_context_emits_lifecycle_status_before_work(self, agent):
+        """Direct context compression should tell gateway users why the turn paused."""
+        events = []
+        agent.status_callback = lambda ev, msg: events.append((ev, msg))
+
+        def _fake_compress(messages, current_tokens=None, focus_topic=None):
+            events.append(("compress", "started"))
+            return [{"role": "user", "content": f"{SUMMARY_PREFIX}\nPrevious conversation"}]
+
+        with (
+            patch.object(agent.context_compressor, "compress", side_effect=_fake_compress),
+            patch.object(agent, "_build_system_prompt", return_value="new system prompt"),
+            patch("run_agent.estimate_request_tokens_rough", return_value=42),
+        ):
+            compressed, new_system_prompt = agent._compress_context(
+                [{"role": "user", "content": "hello"}],
+                "system prompt",
+                approx_tokens=1234,
+            )
+
+        assert compressed == [{"role": "user", "content": f"{SUMMARY_PREFIX}\nPrevious conversation"}]
+        assert new_system_prompt == "new system prompt"
+        assert events[0][0] == "lifecycle"
+        assert "Compacting context" in events[0][1]
+        assert events[1] == ("compress", "started")
+
     def test_preflight_compresses_oversized_history(self, agent):
         """When loaded history exceeds the model's context threshold, compress before API call."""
         agent.compression_enabled = True