From bcce700783814c0fc75459735f85082b47204004 Mon Sep 17 00:00:00 2001
From: srojk34 <286497132+srojk34@users.noreply.github.com>
Date: Fri, 17 Jul 2026 07:59:08 -0700
Subject: [PATCH] fix(compression): reset failure cooldown on runtime switch

---
 agent/context_compressor.py            |  4 +++-
 tests/agent/test_context_compressor.py | 25 +++++++++++++++++++++++++
 2 files changed, 28 insertions(+), 1 deletion(-)

diff --git a/agent/context_compressor.py b/agent/context_compressor.py
index e023aecba9bd1..0194c829886db 100644
--- a/agent/context_compressor.py
+++ b/agent/context_compressor.py
@@ -1175,6 +1175,9 @@ class ContextCompressor(ContextEngine):
         if runtime_changed:
             self._fallback_compression_streak = 0
             self._persist_fallback_compression_streak()
+            # Failure cooldowns are scoped to the model/provider that failed.
+            # A switch must give the new runtime an immediate summary attempt.
+            self._clear_compression_failure_cooldown()
         self._verify_compaction_cleared_threshold = False
         self._last_compression_made_progress = False
 
@@ -1260,7 +1263,6 @@ class ContextCompressor(ContextEngine):
             return max(1, min(int(effective_window * ContextCompressor._MIN_CTX_TRIGGER_RATIO),
                               effective_window - 1))
         return floored
-
     def __init__(
         self,
         model: str,
diff --git a/tests/agent/test_context_compressor.py b/tests/agent/test_context_compressor.py
index 08ef6da986ebd..d44f0e97edc65 100644
--- a/tests/agent/test_context_compressor.py
+++ b/tests/agent/test_context_compressor.py
@@ -3039,6 +3039,31 @@ class TestUpdateModelResetsCalibration:
         assert comp.should_defer_preflight_to_real_usage(comp.threshold_tokens + 5_000) is False
 
 
+    def test_summary_failure_cooldown_cleared(self):
+        """Stale summary-failure cooldown from the old model must not block
+        the new model from generating summaries after a switch."""
+        import time
+        comp = self._comp()
+        # Simulate a 600-second cooldown set because the old model had no
+        # provider configured for summarization.
+        comp._summary_failure_cooldown_until = time.monotonic() + 600
+
+        comp.update_model("new-model", context_length=128_000)
+
+        assert comp._summary_failure_cooldown_until == 0.0
+
+    def test_summary_failure_cooldown_survives_same_runtime_refresh(self):
+        """Refreshing metadata for the same runtime must not defeat backoff."""
+        import time
+        comp = self._comp()
+        cooldown_until = time.monotonic() + 600
+        comp._summary_failure_cooldown_until = cooldown_until
+
+        comp.update_model("big-model", context_length=128_000)
+
+        assert comp._summary_failure_cooldown_until == cooldown_until
+
+
 class TestTruncateToolCallArgsJson:
     """Regression tests for #11762.