style: fix formatting and sync docs

- Fix Black formatting for is_text/is_binary checks
- Update llm.md to reflect binary file support in Claude Code block

autogpt_platform/backend/backend/blocks/claude_code.py

@@ -187,9 +187,11 @@ class ClaudeCodeBlock(Block):
         )
         files: list[SandboxFileOutput] = SchemaField(
             description=(
-                "List of text files created/modified by Claude Code during this execution. "
+                "List of files created/modified by Claude Code during this execution. "
+                "Includes text files and binary files (images, PDFs, etc.). "
                 "Each file has 'path', 'relative_path', 'name', 'content', and 'workspace_ref' fields. "
-                "workspace_ref contains a workspace:// URI if the file was stored to workspace."
+                "workspace_ref contains a workspace:// URI for workspace storage. "
+                "For binary files, content contains a placeholder; use workspace_ref to access the file."
             )
         )
         conversation_history: str = SchemaField(
@@ -453,12 +455,14 @@ class ClaudeCodeBlock(Block):
                     new_conversation_history = turn_entry
 
             # Extract files created/modified during this run and store to workspace
+            # Include binary files (images, PDFs, etc.) - they'll be stored via
+            # store_media_file which handles virus scanning and workspace storage
             sandbox_files = await extract_and_store_sandbox_files(
                 sandbox=sandbox,
                 working_directory=working_directory,
                 execution_context=execution_context,
                 since_timestamp=start_timestamp,
-                text_only=True,
+                text_only=False,  # Extract both text and binary files
             )
 
             return (

autogpt_platform/backend/backend/util/sandbox_files.py

@@ -74,8 +74,51 @@ TEXT_EXTENSIONS = {
     ".tex",
     ".csv",
     ".log",
+    ".svg",  # SVG is XML-based text
 }
 
+# Binary file extensions we explicitly support extracting
+# These are common output formats that users expect to retrieve
+BINARY_EXTENSIONS = {
+    # Images
+    ".png",
+    ".jpg",
+    ".jpeg",
+    ".gif",
+    ".webp",
+    ".ico",
+    ".bmp",
+    ".tiff",
+    ".tif",
+    # Documents
+    ".pdf",
+    # Archives
+    ".zip",
+    ".tar",
+    ".gz",
+    ".7z",
+    # Audio
+    ".mp3",
+    ".wav",
+    ".ogg",
+    ".flac",
+    # Video
+    ".mp4",
+    ".webm",
+    ".mov",
+    ".avi",
+    # Fonts
+    ".woff",
+    ".woff2",
+    ".ttf",
+    ".otf",
+    ".eot",
+}
+
+# Maximum file size for binary extraction (50MB)
+# Prevents OOM from accidentally extracting huge files
+MAX_BINARY_FILE_SIZE = 50 * 1024 * 1024
+
 
 class SandboxFileOutput(BaseModel):
     """A file extracted from a sandbox and optionally stored in workspace."""
@@ -120,7 +163,8 @@ async def extract_sandbox_files(
         sandbox: The E2B sandbox instance
         working_directory: Directory to search for files
         since_timestamp: ISO timestamp - only return files modified after this time
-        text_only: If True, only extract text files (default). If False, extract all files.
+        text_only: If True, only extract text files. If False, also extract
+                   supported binary files (images, PDFs, etc.).
 
     Returns:
         List of ExtractedFile objects with path, content, and metadata
@@ -149,14 +193,45 @@ async def extract_sandbox_files(
             if not file_path:
                 continue
 
-            # Check if it's a text file
-            is_text = any(file_path.endswith(ext) for ext in TEXT_EXTENSIONS)
+            # Check file type (case-insensitive for extensions)
+            file_path_lower = file_path.lower()
+            is_text = any(
+                file_path_lower.endswith(ext.lower()) for ext in TEXT_EXTENSIONS
+            )
+            is_binary = any(
+                file_path_lower.endswith(ext.lower()) for ext in BINARY_EXTENSIONS
+            )
 
-            # Skip non-text files if text_only mode
-            if text_only and not is_text:
-                continue
+            # Determine if we should extract this file
+            if text_only:
+                # Only extract text files
+                if not is_text:
+                    continue
+            else:
+                # Extract text files and supported binary files
+                if not is_text and not is_binary:
+                    continue
 
             try:
+                # For binary files, check size before reading to prevent OOM
+                if is_binary:
+                    stat_result = await sandbox.commands.run(
+                        f"stat -c %s {shlex.quote(file_path)} 2>/dev/null"
+                    )
+                    if stat_result.exit_code != 0 or not stat_result.stdout:
+                        logger.debug(
+                            f"Skipping {file_path}: could not determine file size"
+                        )
+                        continue
+
+                    file_size = int(stat_result.stdout.strip())
+                    if file_size > MAX_BINARY_FILE_SIZE:
+                        logger.info(
+                            f"Skipping {file_path}: size {file_size} bytes "
+                            f"exceeds limit {MAX_BINARY_FILE_SIZE}"
+                        )
+                        continue
+
                 # Read file content as bytes
                 content = await sandbox.files.read(file_path, format="bytes")
                 if isinstance(content, str):

docs/integrations/block-integrations/claude_code.md

@@ -16,7 +16,7 @@ When activated, the block:
    - Install dependencies (npm, pip, etc.)
    - Run terminal commands
    - Build and test applications
-5. Extracts all text files created/modified during execution
+5. Extracts all files created/modified during execution (text files and binary files like images, PDFs, etc.)
 6. Returns the response and files, optionally keeping the sandbox alive for follow-up tasks
 
 The block supports conversation continuation through three mechanisms:
@@ -42,7 +42,7 @@ The block supports conversation continuation through three mechanisms:
 | Output | Description |
 |--------|-------------|
 | Response | The output/response from Claude Code execution |
-| Files | List of text files created/modified during execution. Each file includes path, relative_path, name, and content fields |
+| Files | List of files (text and binary) created/modified during execution. Includes images, PDFs, and other supported formats. Each file has path, relative_path, name, content, and workspace_ref fields. Binary files are stored in workspace and accessible via workspace_ref |
 | Conversation History | Full conversation history including this turn. Use to restore context on a fresh sandbox |
 | Session ID | Session ID for this conversation. Pass back with sandbox_id to continue the conversation |
 | Sandbox ID | ID of the sandbox instance (null if disposed). Pass back with session_id to continue the conversation |

docs/integrations/block-integrations/llm.md

@@ -535,7 +535,7 @@ When activated, the block:
 2. Installs the latest version of Claude Code in the sandbox
 3. Optionally runs setup commands to prepare the environment
 4. Executes your prompt using Claude Code, which can create/edit files, install dependencies, run terminal commands, and build applications
-5. Extracts all text files created/modified during execution
+5. Extracts all files created/modified during execution (text files and binary files like images, PDFs, etc.)
 6. Returns the response and files, optionally keeping the sandbox alive for follow-up tasks
 
 The block supports conversation continuation through three mechanisms:
@@ -563,7 +563,7 @@ The block supports conversation continuation through three mechanisms:
 |--------|-------------|------|
 | error | Error message if execution failed | str |
 | response | The output/response from Claude Code execution | str |
-| files | List of text files created/modified by Claude Code during this execution. Each file has 'path', 'relative_path', 'name', 'content', and 'workspace_ref' fields. workspace_ref contains a workspace:// URI if the file was stored to workspace. | List[SandboxFileOutput] |
+| files | List of files created/modified by Claude Code during this execution. Includes text files and binary files (images, PDFs, etc.). Each file has 'path', 'relative_path', 'name', 'content', and 'workspace_ref' fields. workspace_ref contains a workspace:// URI for workspace storage. For binary files, content contains a placeholder; use workspace_ref to access the file. | List[SandboxFileOutput] |
 | conversation_history | Full conversation history including this turn. Pass this to conversation_history input to continue on a fresh sandbox if the previous sandbox timed out. | str |
 | session_id | Session ID for this conversation. Pass this back along with sandbox_id to continue the conversation. | str |
 | sandbox_id | ID of the sandbox instance. Pass this back along with session_id to continue the conversation. This is None if dispose_sandbox was True (sandbox was disposed). | str |