-
Notifications
You must be signed in to change notification settings - Fork 708
fix: handle binary files in read tool (images/PDFs) #1638
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Open
vihaan-kk
wants to merge
2
commits into
anthropics:main
Choose a base branch
from
vihaan-kk:fix/read-tool-unicode-decode-error
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
+23
−1
Open
Changes from all commits
Commits
Show all changes
2 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -36,6 +36,7 @@ | |
| import os | ||
| import re | ||
| import uuid | ||
| import base64 | ||
| import shutil | ||
| import logging | ||
| import subprocess | ||
|
|
@@ -144,6 +145,20 @@ def _fs_error(op: str, file_path: str, e: OSError) -> ToolError: | |
| return ToolError(f"{op}: {file_path}: {reason}") | ||
|
|
||
|
|
||
| _BINARY_MEDIA_TYPES: dict[str, str] = { | ||
| ".jpg": "image/jpeg", | ||
| ".jpeg": "image/jpeg", | ||
| ".png": "image/png", | ||
| ".gif": "image/gif", | ||
| ".webp": "image/webp", | ||
| ".pdf": "application/pdf", | ||
| } | ||
|
|
||
|
|
||
| def _binary_media_type(path: Path) -> str | None: | ||
| return _BINARY_MEDIA_TYPES.get(path.suffix.lower()) | ||
|
|
||
|
|
||
| def _empty_skill_dirs() -> list[Path]: | ||
| return [] | ||
|
|
||
|
|
@@ -494,7 +509,7 @@ async def bash( | |
|
|
||
| def beta_read_tool(ctx: AgentToolContext) -> BetaAsyncFunctionTool[Any]: | ||
| @beta_async_tool(name="read", input_schema=BetaManagedAgentsAgentToolset20260401ReadInput) | ||
| async def read(file_path: str, view_range: Optional[List[int]] = None) -> str: | ||
| async def read(file_path: str, view_range: Optional[List[int]] = None) -> Any: | ||
| """Read a file rooted at the working directory.""" | ||
| try: | ||
| target = resolve_path(ctx, file_path) | ||
|
|
@@ -513,9 +528,16 @@ async def read(file_path: str, view_range: Optional[List[int]] = None) -> str: | |
| f"read: {file_path} is {st.st_size} bytes, exceeds {limit}-byte limit. " | ||
| "Use bash (head/tail/sed) to read a slice." | ||
| ) | ||
| media = _binary_media_type(target) | ||
| if media is not None: | ||
| data = base64.standard_b64encode(target.read_bytes()).decode("ascii") | ||
| kind = "document" if media == "application/pdf" else "image" | ||
| return [{"type": kind, "source": {"type": "base64", "media_type": media, "data": data}}] | ||
|
vihaan-kk marked this conversation as resolved.
Comment on lines
528
to
+535
|
||
| text = target.read_text() | ||
|
Comment on lines
+531
to
536
Author
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Good point, noted this in the PR description as a follow-up. A separate lower size cap for base64 responses makes sense but felt out of scope for this fix. |
||
| except ToolError: | ||
| raise | ||
| except UnicodeDecodeError as e: | ||
| raise ToolError(f"read: {file_path}: file is not valid UTF-8 text; use bash to inspect binary files") from e | ||
| except OSError as e: | ||
| raise _fs_error("read", file_path, e) from e | ||
| if not view_range: | ||
|
|
||
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.