-
Notifications
You must be signed in to change notification settings - Fork 2
Fix bloat suite to test with correct flags #31
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
Conversation
Reviewer's GuideThis PR updates the bloat analysis suite to pass the correct feature flags by extending the configuration tuples and modifying the command builder to disable default features when custom features are specified. Flow diagram for updated bloat analysis command constructionflowchart TD
A[Start bloat analysis] --> B[Iterate over bloat_configs]
B --> C{extra_features present?}
C -- No --> D[Build command without --no-default-features or --features]
C -- Yes --> E[Add --no-default-features to command]
E --> F[Add --features and join extra_features]
F --> G[Build command with features]
D --> H[Run cargo bloat command]
G --> H
H --> I[Collect results]
I --> J[End]
File-Level Changes
Tips and commandsInteracting with Sourcery
Customizing Your ExperienceAccess your dashboard to:
Getting Help
|
Warning Rate limit exceeded@kaidokert has exceeded the limit for the number of commits or files that can be reviewed per hour. Please wait 11 minutes and 22 seconds before requesting another review. ⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. 📒 Files selected for processing (1)
✨ Finishing Touches
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. 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)
Other keywords and placeholders
CodeRabbit Configuration File (
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Summary of Changes
Hello @kaidokert, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!
This pull request refines the avr_demo
bloat analysis suite to ensure that size measurements are performed with the correct and intended feature flags. The changes specifically configure the cargo bloat
command to use designated features and disable default ones, leading to more accurate and representative bloat metrics for specific configurations.
Highlights
- Bloat Test Configuration: I've updated the
bloat_configs
inavr_demo/run_suite.py
to include specific features (int8
forserde
andpico-tiny,int8
forpicojson
) when running bloat analysis. This ensures that the size measurements reflect the impact of these particular feature sets. - Cargo Bloat Command Flags: I've added the
--no-default-features
flag to thecargo bloat
command whenextra_features
are specified. This is crucial for accurate bloat analysis, as it prevents default features from being compiled alongside the explicitly requested ones, providing a clearer picture of the size impact of the chosen features.
Using Gemini Code Assist
The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.
Invoking Gemini
You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command>
or @gemini-code-assist <command>
. Below is a summary of the supported commands.
Feature | Command | Description |
---|---|---|
Code Review | /gemini review |
Performs a code review for the current pull request in its current state. |
Pull Request Summary | /gemini summary |
Provides a summary of the current pull request in its current state. |
Comment | @gemini-code-assist | Responds in comments when explicitly tagged, both in issue comments and review comments. |
Help | /gemini help |
Displays a list of available commands. |
Customization
To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/
folder in the base of the repository. Detailed instructions can be found here.
Limitations & Feedback
Gemini Code Assist is currently in preview and may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments to provide feedback.
You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.
Footnotes
-
Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Hey @kaidokert - I've reviewed your changes and they look great!
Prompt for AI Agents
Please address the comments from this code review:
## Individual Comments
### Comment 1
<location> `avr_demo/run_suite.py:103` </location>
<code_context>
bloat_configs = [
- ("serde", "test_serde", []),
- ("picojson", "test_picojson", []),
+ ("serde", "test_serde", ["int8"]),
+ ("picojson", "test_picojson", ["pico-tiny,int8"]),
]
</code_context>
<issue_to_address>
Feature lists are inconsistent in format between configs.
'picojson' should use ["pico-tiny", "int8"] if both features are intended, to match the format used for 'serde' and avoid passing a single combined feature string.
</issue_to_address>
Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Code Review
This pull request fixes the bloat analysis suite by ensuring the correct cargo flags are used. It adds the --no-default-features
flag when custom features are specified, which prevents default features from being included and provides a more accurate size measurement for the selected configurations. It also defines the specific features to be tested for the serde
and picojson
bloat analysis configurations.
Summary by Sourcery
Fix the AVR demo bloat analysis script to use the correct feature flags when running cargo bloat
Bug Fixes: