fix: normalize Content-Type parameters in multimodal image processing (#1446)

SWEBenchMultimodalProblemStatement._download_and_convert_image compared the
full lowercased Content-Type header against VALID_IMAGE_MIME_TYPES. When a
server returns a valid image with media type parameters (for example
"Content-Type: image/png; charset=utf-8", which is legal per RFC 9110), the
string "image/png; charset=utf-8" is not in the allowed set, so the image is
logged as an unsupported MIME type and silently dropped from the problem
statement.

Strip the media type parameters (split on ";", strip, lowercase) before the
existing image/jpg -> image/jpeg normalization and the membership check, so the
bare media type is validated and used in the encoded data URI. Behavior for
unsupported types, size limits, empty images, and network failures is
unchanged.

Add a regression test covering a Content-Type header with a charset parameter.

Closes #1441

Signed-off-by: Anas Khan <83116240+anxkhn@users.noreply.github.com>

sweagent/agent/problem_statement.py

@@ -237,7 +237,8 @@ class SWEBenchMultimodalProblemStatement(_BuiltinProblemStatementBase):
             }
             response = requests.get(url, headers=headers, timeout=30, stream=True)
             response.raise_for_status()
-            content_type = response.headers.get("content-type", "").lower()
+            # strip any media type parameters (e.g. "image/png; charset=utf-8") before validation
+            content_type = response.headers.get("content-type", "").split(";")[0].strip().lower()
             if content_type == "image/jpg":
                 content_type = "image/jpeg"
             if content_type not in VALID_IMAGE_MIME_TYPES:

tests/test_problem_statement_multimodal.py

@@ -43,6 +43,23 @@ class TestSWEBenchMultimodalProblemStatement:
         assert "Test problem statement" in result
         assert f"![{self.example_image_url}](data:image/png;base64," in result
 
+    @patch("requests.get")
+    def test_get_problem_statement_with_content_type_parameters(self, mock_get):
+        """Test that a Content-Type header with media type parameters is still accepted."""
+        # servers may append parameters like charset, which is legal per RFC 9110
+        mock_response = Mock()
+        mock_response.raise_for_status.return_value = None
+        mock_response.headers = {"content-type": "image/png; charset=utf-8"}
+        mock_response.iter_content.return_value = [b"fake_image_data"]
+        mock_get.return_value = mock_response
+        problem_statement = SWEBenchMultimodalProblemStatement(
+            text="Test problem statement", issue_images=[self.example_image_url]
+        )
+        result = problem_statement.get_problem_statement()
+        # the parameters should be stripped before validation and encoding
+        assert "Test problem statement" in result
+        assert f"![{self.example_image_url}](data:image/png;base64," in result
+
     @patch("requests.get")
     def test_get_problem_statement_with_network_error(self, mock_get):
         """Test that network errors are handled gracefully with warnings."""