From 3007174a61cbad9145794f24c9d7f9251fdf1d39 Mon Sep 17 00:00:00 2001
From: Teknium <127238744+teknium1@users.noreply.github.com>
Date: Thu, 9 Apr 2026 11:11:34 -0700
Subject: [PATCH] fix: prevent 400 format errors from triggering compression
 loop on Codex Responses API (#6751)

The error classifier's generic-400 heuristic only extracted err_body_msg from
the nested body structure (body['error']['message']), missing the flat body
format used by OpenAI's Responses API (body['message']). This caused
descriptive 400 errors like 'Invalid input[index].name: string does not match
pattern' to appear generic when the session was large, misclassifying them as
context overflow and triggering an infinite compression loop.

Added flat-body fallback in _classify_400() consistent with the parent
classify_api_error() function's existing handling at line 297-298.
---
 agent/error_classifier.py            |  3 +++
 tests/agent/test_error_classifier.py | 32 ++++++++++++++++++++++++++++
 2 files changed, 35 insertions(+)

diff --git a/agent/error_classifier.py b/agent/error_classifier.py
index b227932ad..0f1450113 100644
--- a/agent/error_classifier.py
+++ b/agent/error_classifier.py
@@ -596,6 +596,9 @@ def _classify_400(
         err_obj = body.get("error", {})
         if isinstance(err_obj, dict):
             err_body_msg = (err_obj.get("message") or "").strip().lower()
+        # Responses API (and some providers) use flat body: {"message": "..."}
+        if not err_body_msg:
+            err_body_msg = (body.get("message") or "").strip().lower()
     is_generic = len(err_body_msg) < 30 or err_body_msg in ("error", "")
     is_large = approx_tokens > context_length * 0.4 or approx_tokens > 80000 or num_messages > 80
 
diff --git a/tests/agent/test_error_classifier.py b/tests/agent/test_error_classifier.py
index da248f821..c59735589 100644
--- a/tests/agent/test_error_classifier.py
+++ b/tests/agent/test_error_classifier.py
@@ -507,6 +507,38 @@ class TestClassifyApiError:
         assert result.reason == FailoverReason.format_error
         assert result.retryable is False
 
+    def test_400_flat_body_descriptive_not_context_overflow(self):
+        """Responses API flat body with descriptive error + large session → format error.
+
+        The Codex Responses API returns errors in flat body format:
+        {"message": "...", "type": "..."} without an "error" wrapper.
+        A descriptive 400 must NOT be misclassified as context overflow
+        just because the session is large.
+        """
+        e = MockAPIError(
+            "Invalid 'input[index].name': string does not match pattern.",
+            status_code=400,
+            body={"message": "Invalid 'input[index].name': string does not match pattern.",
+                  "type": "invalid_request_error"},
+        )
+        result = classify_api_error(e, approx_tokens=200000, context_length=400000, num_messages=500)
+        assert result.reason == FailoverReason.format_error
+        assert result.retryable is False
+
+    def test_400_flat_body_generic_large_session_still_context_overflow(self):
+        """Flat body with generic 'Error' message + large session → context overflow.
+
+        Regression: the flat-body fallback must not break the existing heuristic
+        for genuinely generic errors from providers that use flat bodies.
+        """
+        e = MockAPIError(
+            "Error",
+            status_code=400,
+            body={"message": "Error"},
+        )
+        result = classify_api_error(e, approx_tokens=100000, context_length=200000)
+        assert result.reason == FailoverReason.context_overflow
+
     # ── Peer closed + large session ──
 
     def test_peer_closed_large_session(self):