From 513ec16357c10967dfea4523ac47548b2c758e36 Mon Sep 17 00:00:00 2001
From: Otto <otto@agpt.co>
Date: Thu, 5 Feb 2026 20:00:02 +0000
Subject: [PATCH] fix: Handle RFC 2045 line-wrapped base64 in embedded
 detection

Sentry correctly identified that the regex and decode would fail on
line-wrapped base64. Fixed by:
- Updated regex to allow whitespace in base64 chunks
- Strip whitespace before decoding with validate=True
- Added test for line-wrapped base64
---
 .../features/chat/tools/binary_output_processor.py   | 10 +++++++---
 .../chat/tools/test_binary_output_processor.py       | 12 ++++++++++++
 2 files changed, 19 insertions(+), 3 deletions(-)

diff --git a/autogpt_platform/backend/backend/api/features/chat/tools/binary_output_processor.py b/autogpt_platform/backend/backend/api/features/chat/tools/binary_output_processor.py
index 00c6617d5e..fce98bf17c 100644
--- a/autogpt_platform/backend/backend/api/features/chat/tools/binary_output_processor.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/binary_output_processor.py
@@ -28,8 +28,9 @@ logger = logging.getLogger(__name__)
 MIN_DECODED_SIZE = 1024  # 1KB
 
 # Pattern to find base64 chunks in text (at least 100 chars to be worth checking)
-# Matches continuous base64 characters, optionally ending with = padding
-EMBEDDED_BASE64_PATTERN = re.compile(r"[A-Za-z0-9+/]{100,}={0,2}")
+# Matches continuous base64 characters (with optional whitespace for line wrapping),
+# optionally ending with = padding
+EMBEDDED_BASE64_PATTERN = re.compile(r"[A-Za-z0-9+/\s]{100,}={0,2}")
 
 # Magic numbers for binary file detection
 MAGIC_SIGNATURES = [
@@ -141,8 +142,11 @@ def _decode_and_validate(b64_str: str) -> Optional[tuple[bytes, str]]:
 
     Returns (content, extension) if valid binary, None otherwise.
     """
+    # Strip whitespace for RFC 2045 line-wrapped base64
+    normalized = re.sub(r"\s+", "", b64_str)
+
     try:
-        content = base64.b64decode(b64_str, validate=True)
+        content = base64.b64decode(normalized, validate=True)
     except (ValueError, binascii.Error):
         return None
 
diff --git a/autogpt_platform/backend/backend/api/features/chat/tools/test_binary_output_processor.py b/autogpt_platform/backend/backend/api/features/chat/tools/test_binary_output_processor.py
index 6018d64789..5a26261842 100644
--- a/autogpt_platform/backend/backend/api/features/chat/tools/test_binary_output_processor.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/test_binary_output_processor.py
@@ -116,6 +116,18 @@ class TestDecodeAndValidate:
         result = _decode_and_validate(wav_b64)
         assert result is None
 
+    def test_handles_line_wrapped_base64(self):
+        """Should handle RFC 2045 line-wrapped base64."""
+        pdf_content = b"%PDF-1.4 " + b"x" * 2000
+        pdf_b64 = base64.b64encode(pdf_content).decode()
+        # Simulate line wrapping at 76 chars
+        wrapped = "\n".join(pdf_b64[i : i + 76] for i in range(0, len(pdf_b64), 76))
+        result = _decode_and_validate(wrapped)
+        assert result is not None
+        content, ext = result
+        assert ext == "pdf"
+        assert content == pdf_content
+
 
 # =============================================================================
 # Marker Expansion Tests