fix: add explicit ValueError guard for stat output parsing

- 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 +193,53 @@ 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
+
+                    try:
+                        file_size = int(stat_result.stdout.strip())
+                    except ValueError:
+                        logger.debug(
+                            f"Skipping {file_path}: unexpected stat output "
+                            f"{stat_result.stdout.strip()!r}"
+                        )
+                        continue
+
+                    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):

autogpt_platform/backend/poetry.lock

@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 2.2.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 2.1.1 and should not be changed by hand.
 
 [[package]]
 name = "aio-pika"
@@ -374,7 +374,7 @@ description = "LTS Port of Python audioop"
 optional = false
 python-versions = ">=3.13"
 groups = ["main"]
-markers = "python_version == \"3.13\""
+markers = "python_version >= \"3.13\""
 files = [
     {file = "audioop_lts-0.2.2-cp313-abi3-macosx_10_13_universal2.whl", hash = "sha256:fd3d4602dc64914d462924a08c1a9816435a2155d74f325853c1f1ac3b2d9800"},
     {file = "audioop_lts-0.2.2-cp313-abi3-macosx_10_13_x86_64.whl", hash = "sha256:550c114a8df0aafe9a05442a1162dfc8fec37e9af1d625ae6060fed6e756f303"},
@@ -474,7 +474,7 @@ description = "Backport of asyncio.Runner, a context manager that controls event
 optional = false
 python-versions = "<3.11,>=3.8"
 groups = ["main"]
-markers = "python_version == \"3.10\""
+markers = "python_version < \"3.11\""
 files = [
     {file = "backports_asyncio_runner-1.2.0-py3-none-any.whl", hash = "sha256:0da0a936a8aeb554eccb426dc55af3ba63bcdc69fa1a600b5bb305413a4477b5"},
     {file = "backports_asyncio_runner-1.2.0.tar.gz", hash = "sha256:a5aa7b2b7d8f8bfcaa2b57313f70792df84e32a2a746f585213373f900b42162"},
@@ -487,7 +487,7 @@ description = "Backport of CPython tarfile module"
 optional = false
 python-versions = ">=3.8"
 groups = ["main"]
-markers = "python_version < \"3.12\""
+markers = "python_version <= \"3.11\""
 files = [
     {file = "backports.tarfile-1.2.0-py3-none-any.whl", hash = "sha256:77e284d754527b01fb1e6fa8a1afe577858ebe4e9dad8919e34c862cb399bc34"},
     {file = "backports_tarfile-1.2.0.tar.gz", hash = "sha256:d75e02c268746e1b8144c278978b6e98e85de6ad16f8e4b0844a154557eca991"},
@@ -659,6 +659,7 @@ description = "Foreign Function Interface for Python calling C code."
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
+markers = "platform_python_implementation != \"PyPy\" or sys_platform == \"darwin\""
 files = [
     {file = "cffi-2.0.0-cp310-cp310-macosx_10_13_x86_64.whl", hash = "sha256:0cf2d91ecc3fcc0625c2c530fe004f82c110405f101548512cce44322fa8ac44"},
     {file = "cffi-2.0.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:f73b96c41e3b2adedc34a7356e64c8eb96e03a3782b535e043a986276ce12a49"},
@@ -1360,7 +1361,7 @@ description = "Backport of PEP 654 (exception groups)"
 optional = false
 python-versions = ">=3.7"
 groups = ["main", "dev"]
-markers = "python_version == \"3.10\""
+markers = "python_version < \"3.11\""
 files = [
     {file = "exceptiongroup-1.3.1-py3-none-any.whl", hash = "sha256:a7a39a3bd276781e98394987d3a5701d0c4edffb633bb7a5144577f82c773598"},
     {file = "exceptiongroup-1.3.1.tar.gz", hash = "sha256:8b412432c6055b0b7d14c310000ae93352ed6754f70fa8f7c34141f91c4e3219"},
@@ -1389,21 +1390,18 @@ tests = ["coverage", "coveralls", "dill", "mock", "nose"]
 
 [[package]]
 name = "faker"
-version = "40.4.0"
+version = "38.3.0"
 description = "Faker is a Python package that generates fake data for you."
 optional = false
 python-versions = ">=3.10"
 groups = ["dev"]
 files = [
-    {file = "faker-40.4.0-py3-none-any.whl", hash = "sha256:486d43c67ebbb136bc932406418744f9a0bdf2c07f77703ea78b58b77e9aa443"},
-    {file = "faker-40.4.0.tar.gz", hash = "sha256:76f8e74a3df28c3e2ec2caafa956e19e37a132fdc7ea067bc41783affcfee364"},
+    {file = "faker-38.3.0-py3-none-any.whl", hash = "sha256:b5499b6f2d090dec9b90ded8eae6a27daed10fda3e0dba7a182bb2be8a4d4a6b"},
+    {file = "faker-38.3.0.tar.gz", hash = "sha256:4997de214510db9328ed83b9591891c66e91d7e9a903e5744e0255a68f51ac16"},
 ]
 
 [package.dependencies]
-tzdata = {version = "*", markers = "platform_system == \"Windows\""}
-
-[package.extras]
-tzdata = ["tzdata"]
+tzdata = "*"
 
 [[package]]
 name = "fastapi"
@@ -1845,16 +1843,16 @@ files = [
 google-auth = ">=2.14.1,<3.0.0"
 googleapis-common-protos = ">=1.56.2,<2.0.0"
 grpcio = [
-    {version = ">=1.49.1,<2.0.0", optional = true, markers = "python_version >= \"3.11\" and extra == \"grpc\""},
     {version = ">=1.33.2,<2.0.0", optional = true, markers = "extra == \"grpc\""},
+    {version = ">=1.49.1,<2.0.0", optional = true, markers = "python_version >= \"3.11\" and extra == \"grpc\""},
 ]
 grpcio-status = [
-    {version = ">=1.49.1,<2.0.0", optional = true, markers = "python_version >= \"3.11\" and extra == \"grpc\""},
     {version = ">=1.33.2,<2.0.0", optional = true, markers = "extra == \"grpc\""},
+    {version = ">=1.49.1,<2.0.0", optional = true, markers = "python_version >= \"3.11\" and extra == \"grpc\""},
 ]
 proto-plus = [
-    {version = ">=1.25.0,<2.0.0", markers = "python_version >= \"3.13\""},
     {version = ">=1.22.3,<2.0.0"},
+    {version = ">=1.25.0,<2.0.0", markers = "python_version >= \"3.13\""},
 ]
 protobuf = ">=3.19.5,<3.20.0 || >3.20.0,<3.20.1 || >3.20.1,<4.21.0 || >4.21.0,<4.21.1 || >4.21.1,<4.21.2 || >4.21.2,<4.21.3 || >4.21.3,<4.21.4 || >4.21.4,<4.21.5 || >4.21.5,<7.0.0"
 requests = ">=2.18.0,<3.0.0"
@@ -1965,8 +1963,8 @@ google-api-core = {version = ">=1.34.1,<2.0.dev0 || >=2.11.dev0,<3.0.0", extras
 google-auth = ">=2.14.1,<2.24.0 || >2.24.0,<2.25.0 || >2.25.0,<3.0.0"
 grpcio = ">=1.33.2,<2.0.0"
 proto-plus = [
-    {version = ">=1.25.0,<2.0.0", markers = "python_version >= \"3.13\""},
     {version = ">=1.22.3,<2.0.0"},
+    {version = ">=1.25.0,<2.0.0", markers = "python_version >= \"3.13\""},
 ]
 protobuf = ">=3.20.2,<4.21.0 || >4.21.0,<4.21.1 || >4.21.1,<4.21.2 || >4.21.2,<4.21.3 || >4.21.3,<4.21.4 || >4.21.4,<4.21.5 || >4.21.5,<7.0.0"
 
@@ -2026,9 +2024,9 @@ google-cloud-core = ">=2.0.0,<3.0.0"
 grpc-google-iam-v1 = ">=0.12.4,<1.0.0"
 opentelemetry-api = ">=1.9.0"
 proto-plus = [
+    {version = ">=1.22.0,<2.0.0"},
+    {version = ">=1.22.2,<2.0.0", markers = "python_version >= \"3.11\""},
     {version = ">=1.25.0,<2.0.0", markers = "python_version >= \"3.13\""},
-    {version = ">=1.22.2,<2.0.0", markers = "python_version >= \"3.11\" and python_version < \"3.13\""},
-    {version = ">=1.22.0,<2.0.0", markers = "python_version < \"3.11\""},
 ]
 protobuf = ">=3.20.2,<4.21.0 || >4.21.0,<4.21.1 || >4.21.1,<4.21.2 || >4.21.2,<4.21.3 || >4.21.3,<4.21.4 || >4.21.4,<4.21.5 || >4.21.5,<7.0.0"
 
@@ -3872,7 +3870,7 @@ description = "Fundamental package for array computing in Python"
 optional = false
 python-versions = ">=3.10"
 groups = ["main"]
-markers = "python_version == \"3.10\""
+markers = "python_version < \"3.11\""
 files = [
     {file = "numpy-2.2.6-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:b412caa66f72040e6d268491a59f2c43bf03eb6c96dd8f0307829feb7fa2b6fb"},
     {file = "numpy-2.2.6-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:8e41fd67c52b86603a91c1a505ebaef50b3314de0213461c7a6e99c9a3beff90"},
@@ -4357,9 +4355,9 @@ files = [
 
 [package.dependencies]
 numpy = [
-    {version = ">=1.26.0", markers = "python_version >= \"3.12\""},
-    {version = ">=1.23.2", markers = "python_version == \"3.11\""},
     {version = ">=1.22.4", markers = "python_version < \"3.11\""},
+    {version = ">=1.23.2", markers = "python_version == \"3.11\""},
+    {version = ">=1.26.0", markers = "python_version >= \"3.12\""},
 ]
 python-dateutil = ">=2.8.2"
 pytz = ">=2020.1"
@@ -4602,8 +4600,8 @@ pinecone-plugin-interface = ">=0.0.7,<0.0.8"
 python-dateutil = ">=2.5.3"
 typing-extensions = ">=3.7.4"
 urllib3 = [
-    {version = ">=1.26.5", markers = "python_version >= \"3.12\" and python_version < \"4.0\""},
     {version = ">=1.26.0", markers = "python_version >= \"3.8\" and python_version < \"3.12\""},
+    {version = ">=1.26.5", markers = "python_version >= \"3.12\" and python_version < \"4.0\""},
 ]
 
 [package.extras]
@@ -5431,7 +5429,7 @@ description = "C parser in Python"
 optional = false
 python-versions = ">=3.10"
 groups = ["main"]
-markers = "implementation_name != \"PyPy\""
+markers = "(platform_python_implementation != \"PyPy\" or sys_platform == \"darwin\") and implementation_name != \"PyPy\""
 files = [
     {file = "pycparser-3.0-py3-none-any.whl", hash = "sha256:b727414169a36b7d524c1c3e31839a521725078d7b2ff038656844266160a992"},
     {file = "pycparser-3.0.tar.gz", hash = "sha256:600f49d217304a5902ac3c37e1281c9fe94e4d0489de643a9504c5cdfdfc6b29"},
@@ -6200,10 +6198,10 @@ files = [
 grpcio = ">=1.41.0"
 httpx = {version = ">=0.20.0", extras = ["http2"]}
 numpy = [
-    {version = ">=2.1.0", markers = "python_version == \"3.13\""},
-    {version = ">=1.21", markers = "python_version == \"3.11\""},
-    {version = ">=1.26", markers = "python_version == \"3.12\""},
     {version = ">=1.21,<2.3.0", markers = "python_version == \"3.10\""},
+    {version = ">=1.21", markers = "python_version == \"3.11\""},
+    {version = ">=2.1.0", markers = "python_version == \"3.13\""},
+    {version = ">=1.26", markers = "python_version == \"3.12\""},
 ]
 portalocker = ">=2.7.0,<4.0"
 protobuf = ">=3.20.0"
@@ -7409,7 +7407,7 @@ description = "A lil' TOML parser"
 optional = false
 python-versions = ">=3.8"
 groups = ["main", "dev"]
-markers = "python_version == \"3.10\""
+markers = "python_version < \"3.11\""
 files = [
     {file = "tomli-2.4.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:b5ef256a3fd497d4973c11bf142e9ed78b150d36f5773f1ca6088c230ffc5867"},
     {file = "tomli-2.4.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:5572e41282d5268eb09a697c89a7bee84fae66511f87533a6f88bd2f7b652da9"},
@@ -7585,7 +7583,6 @@ files = [
     {file = "tzdata-2025.3-py2.py3-none-any.whl", hash = "sha256:06a47e5700f3081aab02b2e513160914ff0694bce9947d6b76ebd6bf57cfc5d1"},
     {file = "tzdata-2025.3.tar.gz", hash = "sha256:de39c2ca5dc7b0344f2eba86f49d614019d29f060fc4ebc8a417896a620b56a7"},
 ]
-markers = {dev = "platform_system == \"Windows\""}
 
 [[package]]
 name = "tzlocal"
@@ -8533,4 +8530,4 @@ cffi = ["cffi (>=1.17,<2.0) ; platform_python_implementation != \"PyPy\" and pyt
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.10,<3.14"
-content-hash = "73d5ca72e97dce394fe111708cb5be0c714f9812b016de45ad0b84de85a833bc"
+content-hash = "55e095de555482f0fe47de7695f390fe93e7bcf739b31c391b2e5e3c3d938ae3"

autogpt_platform/backend/pyproject.toml

@@ -93,7 +93,7 @@ posthog = "^7.6.0"
 [tool.poetry.group.dev.dependencies]
 aiohappyeyeballs = "^2.6.1"
 black = "^24.10.0"
-faker = "^40.4.0"
+faker = "^38.2.0"
 httpx = "^0.28.1"
 isort = "^5.13.2"
 poethepoet = "^0.41.0"

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 |