From b8e2268628b25e0294da8fae411ca3f218d98860 Mon Sep 17 00:00:00 2001
From: 595650661 <15205536+595650661@users.noreply.github.com>
Date: Wed, 3 Jun 2026 11:23:20 +0800
Subject: [PATCH] fix(agent): add MiniMax 'new_sensitive' to
 content_policy_blocked patterns

The MiniMax output-layer safety filter surfaces the error verbatim as
`output new_sensitive (1027)` (sometimes with additional provider
wrapping like 'Stream stalled mid tool-call: output new_sensitive (1027)').
When the model emits a large tool-call argument block, the upstream
filter trips and the SSE stream is truncated mid-flight, producing
'stream stalled mid tool-call' errors. Until now this case was
misclassified and retried 3x on the same provider, reproducing the same
refusal and burning paid attempts.

Adding `new_sensitive` to `_CONTENT_POLICY_BLOCKED_PATTERNS` routes
it through the existing is_client_error path: skip 3x retry, activate
configured fallback model immediately, surface a clear provider-safety
message to the user.

Refs #32421
---
 agent/error_classifier.py                     |  8 +++++++
 .../test_18028_content_policy_blocked.py      | 21 +++++++++++++++++++
 2 files changed, 29 insertions(+)

diff --git a/agent/error_classifier.py b/agent/error_classifier.py
index 2d43806bc07..a64683ba41e 100644
--- a/agent/error_classifier.py
+++ b/agent/error_classifier.py
@@ -355,6 +355,14 @@ _CONTENT_POLICY_BLOCKED_PATTERNS = [
     # echo back; the underscore form is provider-specific enough.
     "content_filter",
     "responsibleaipolicyviolation",
+    # MiniMax output-layer safety filter. The error string is surfaced
+    # verbatim by MiniMax SDK / OpenAI-compatible endpoints, usually in the
+    # form "output new_sensitive (1027)" when the model's *output* (often a
+    # large tool-call argument block) trips the upstream safety filter and
+    # the SSE stream is truncated mid-flight. ``new_sensitive`` is the
+    # filter name and is narrow enough that billing / format / auth error
+    # strings will not collide. See #32421.
+    "new_sensitive",
 ]
 
 # Auth patterns (non-status-code signals)
diff --git a/tests/run_agent/test_18028_content_policy_blocked.py b/tests/run_agent/test_18028_content_policy_blocked.py
index 1edf16b87ca..5b0ca093494 100644
--- a/tests/run_agent/test_18028_content_policy_blocked.py
+++ b/tests/run_agent/test_18028_content_policy_blocked.py
@@ -41,6 +41,27 @@ class TestContentPolicyBlockedClassification:
         assert result.should_compress is False
         assert result.should_rotate_credential is False
 
+    def test_minimax_output_safety_filter(self):
+        """#32421 — MiniMax output-layer safety filter (e.g. ``output
+        new_sensitive (1027)``) trips mid-stream when the model emits a
+        large tool-call argument block. Must classify as
+        ``content_policy_blocked`` so the loop aborts the 3x retry burn and
+        routes to a configured fallback model.
+        """
+        from agent.error_classifier import classify_api_error, FailoverReason
+
+        e = Exception(
+            "Stream stalled mid tool-call: output new_sensitive (1027) "
+            "[MiniMax-M2.7] — request was rejected by upstream safety "
+            "filter, see provider response for details."
+        )
+        result = classify_api_error(e, provider="MiniMax", model="MiniMax-M2.7")
+        assert result.reason == FailoverReason.content_policy_blocked
+        assert result.retryable is False
+        assert result.should_fallback is True
+        assert result.should_compress is False
+        assert result.should_rotate_credential is False
+
 
 class TestContentPolicyTriggersClientErrorAbort:
     """Mirror the ``is_client_error`` predicate in