Skip to content
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

Re-add typeerror handling to format message #5704

Closed
wants to merge 1 commit into from

Conversation

mdegat01
Copy link
Contributor

@mdegat01 mdegat01 commented Mar 1, 2025

Proposed change

TypeError handling in format message should not have been removed, required to keep UI from becoming unresponsive as per #2052 . Adjusted to reduce coroutines as per discussion.

Type of change

  • Dependency upgrade
  • Bugfix (non-breaking change which fixes an issue)
  • New feature (which adds functionality to the supervisor)
  • Breaking change (fix/feature causing existing functionality to break)
  • Code quality improvements to existing code or addition of tests

Additional information

  • This PR fixes or closes issue: fixes #
  • This PR is related to issue:
  • Link to documentation pull request:
  • Link to cli pull request:
  • Link to client library pull request:

Checklist

  • The code change is tested and works locally.
  • Local tests pass. Your PR cannot be merged unless tests pass
  • There is no commented out code in this PR.
  • I have followed the development checklist
  • The code has been formatted using Ruff (ruff format supervisor tests)
  • Tests have been added to verify that the new code works.

If API endpoints or add-on configuration are added/changed:

Summary by CodeRabbit

  • Refactor
    • Upgraded error reporting to use an asynchronous approach for smoother and more reliable handling.
  • Tests
    • Updated validations to ensure the robustness of the new asynchronous error processing.

@mdegat01 mdegat01 added the bugfix A bug fix label Mar 1, 2025
@mdegat01 mdegat01 requested a review from agners March 1, 2025 15:54
Copy link
Contributor

coderabbitai bot commented Mar 1, 2025

📝 Walkthrough

Walkthrough

This pull request converts synchronous error message formatting to an asynchronous approach. In the API utility, the format_message call is replaced with async_format_message for handling DockerAPI errors. In the logging utility, the synchronous format_message function is removed and replaced by a new asynchronous version that includes error handling and exception capturing. The tests are updated accordingly to import and call the asynchronous function and to verify its exception handling behavior.

Changes

File(s) Change Summary
supervisor/api/utils.py
tests/utils/test_log_format.py
Replaced the use and import of format_message with async_format_message, updating the error handling flow in API responses and corresponding tests.
supervisor/utils/log_format.py Removed the synchronous format_message and introduced async_format_message with asynchronous error handling and exception capturing using _LOGGER and async_capture_exception.

Sequence Diagram(s)

sequenceDiagram
    participant Client as Client
    participant API as api_return_error
    participant Logger as async_format_message
    participant Sentry as async_capture_exception

    Client->>API: Trigger error (DockerAPIError)
    API->>Logger: Call async_format_message(message)
    Logger->>Logger: Try formatting message
    alt Formatting error (TypeError)
        Logger->>Sentry: Capture exception asynchronously
    end
    Logger-->>API: Return formatted/error message
    API-->>Client: Return error response
Loading
✨ Finishing Touches
  • 📝 Generate Docstrings

Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?

❤️ Share
🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>, please review it.
    • Generate unit testing code for this file.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai generate unit testing code for this file.
    • @coderabbitai modularize this function.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read src/utils.ts and generate unit testing code.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai generate docstrings to generate docstrings for this PR.
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai or @coderabbitai title anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

  • You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
  • Please see the configuration documentation for more information.
  • If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

Copy link
Contributor

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 3

🧹 Nitpick comments (1)
tests/utils/test_log_format.py (1)

24-27: Typo in test function name.

There is a typo in the function name: test_exeption should be test_exception.

-async def test_exeption():
+async def test_exception():

Also note that unlike the other test functions, this one is correctly declared as async since it calls an async function.

📜 Review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 5b18fb6 and 0786e06.

📒 Files selected for processing (3)
  • supervisor/api/utils.py (2 hunks)
  • supervisor/utils/log_format.py (1 hunks)
  • tests/utils/test_log_format.py (2 hunks)
⏰ Context from checks skipped due to timeout of 90000ms (4)
  • GitHub Check: Build armv7 supervisor
  • GitHub Check: Build armhf supervisor
  • GitHub Check: Build aarch64 supervisor
  • GitHub Check: Run tests Python 3.13.2
🔇 Additional comments (3)
tests/utils/test_log_format.py (1)

3-3: Import statement updated correctly.

The import has been correctly updated to use the new async_format_message function instead of the removed format_message.

supervisor/api/utils.py (1)

28-28: Import statement updated correctly.

The import has been correctly updated to use the new async_format_message function.

supervisor/utils/log_format.py (1)

3-3: Added necessary imports for async functionality.

Correctly added imports for asyncio and async_capture_exception from Sentry to support the new error handling functionality.

Also applies to: 7-8



def test_format_message_port():
"""Tests for message formater."""
message = '500 Server Error: Internal Server Error: Bind for 0.0.0.0:80 failed: port is already allocated")'
assert (
format_message(message)
async_format_message(message)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Verification agent

❓ Verification inconclusive

Function calls updated but missing await.

The test is calling the new async_format_message function but isn't awaiting it. According to the implementation docstring, this function "Must be called from event loop" but these test functions aren't async.

Either:

  1. The non-async test functions should be updated to be async and use await
  2. The implementation should clarify if it's safe to call without await in some contexts

Also applies to: 19-19


🏁 Script executed:

#!/bin/bash
# Check if async_format_message is being awaited in other places in the codebase
rg "await async_format_message" --type py

Length of output: 43


Await the Async Call in Tests
The tests are invoking async_format_message without awaiting its result, which contradicts its implementation requirement ("Must be called from event loop"). This occurs at both line 10 and line 19 of tests/utils/test_log_format.py. You need to either:

  • Update the test functions to be async and use await async_format_message(message), or
  • Clarify in the function's docstring that it’s safe to call without awaiting in test contexts.

@@ -139,7 +139,7 @@ def api_return_error(
if error and not message:
message = get_message_from_exception_chain(error)
if check_exception_chain(error, DockerAPIError):
message = format_message(message)
message = async_format_message(message)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue

Function call updated but missing await.

The code is calling async_format_message but isn't awaiting it. According to the implementation docstring, this function "Must be called from event loop".

Since api_return_error isn't an async function, you should either:

  1. Make api_return_error async and await the call
  2. Run the function in the event loop using asyncio.run_coroutine_threadsafe or similar

This is especially important for error handling, as any exceptions from TypeError might be lost if not properly awaited.

Comment on lines +16 to 29
def async_format_message(message: str) -> str:
"""Return a formated message if it's known.

Must be called from event loop.
"""
try:
match = RE_BIND_FAILED.match(message)
if match:
return f"Port '{match.group(1)}' is already in use by something else on the host."
except TypeError as err:
_LOGGER.error("The type of message is not a string - %s", err)
asyncio.get_running_loop().create_task(async_capture_exception(err))

return message
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue

Function implementation issue with async pattern.

The implementation has several issues:

  1. The function isn't declared as async even though it creates an async task and requires an event loop
  2. It doesn't await the async_capture_exception task which could lead to lost exceptions
  3. The docstring states it "Must be called from event loop" but doesn't explain how to properly call it

These issues could lead to unexpected behavior when called from various contexts. The current implementation is neither truly synchronous nor properly asynchronous.

Consider one of these options:

# Option 1: Make it truly async and await the exception capture
-def async_format_message(message: str) -> str:
+async def async_format_message(message: str) -> str:
    """Return a formated message if it's known.
    
    Must be called with await.
    """
    try:
        match = RE_BIND_FAILED.match(message)
        if match:
            return f"Port '{match.group(1)}' is already in use by something else on the host."
    except TypeError as err:
        _LOGGER.error("The type of message is not a string - %s", err)
-        asyncio.get_running_loop().create_task(async_capture_exception(err))
+        await async_capture_exception(err)

    return message
# Option 2: Keep it synchronous with better naming and handling
-def async_format_message(message: str) -> str:
+def format_message_with_error_capture(message: str) -> str:
    """Return a formated message if it's known.
    
    This function attempts to run in an event loop context to capture exceptions,
    but will still work if no event loop is available.
    """
    try:
        match = RE_BIND_FAILED.match(message)
        if match:
            return f"Port '{match.group(1)}' is already in use by something else on the host."
    except TypeError as err:
        _LOGGER.error("The type of message is not a string - %s", err)
        try:
            asyncio.get_running_loop().create_task(async_capture_exception(err))
        except RuntimeError:
            # No event loop available, just log the error
            pass

    return message
📝 Committable suggestion

‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.

Suggested change
def async_format_message(message: str) -> str:
"""Return a formated message if it's known.
Must be called from event loop.
"""
try:
match = RE_BIND_FAILED.match(message)
if match:
return f"Port '{match.group(1)}' is already in use by something else on the host."
except TypeError as err:
_LOGGER.error("The type of message is not a string - %s", err)
asyncio.get_running_loop().create_task(async_capture_exception(err))
return message
async def async_format_message(message: str) -> str:
"""Return a formated message if it's known.
Must be called with await.
"""
try:
match = RE_BIND_FAILED.match(message)
if match:
return f"Port '{match.group(1)}' is already in use by something else on the host."
except TypeError as err:
_LOGGER.error("The type of message is not a string - %s", err)
await async_capture_exception(err)
return message

Copy link
Member

@agners agners left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I don't think that is necessary.

I've outlined my reasoning in the PR's commit message, see 670bddd.

@home-assistant home-assistant bot marked this pull request as draft March 1, 2025 16:19
@home-assistant
Copy link

home-assistant bot commented Mar 1, 2025

Please take a look at the requested changes, and use the Ready for review button when you are done, thanks 👍

Learn more about our pull request process.

@agners
Copy link
Member

agners commented Mar 1, 2025

Closing, as discussed separately, there is no code path where the exception can happen today.

FWIW, we should rework format_message. Ideally the message should be captured where it originates, and converted into a Supervisor specific exception.

@agners agners closed this Mar 1, 2025
@github-actions github-actions bot locked and limited conversation to collaborators Mar 3, 2025
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants