-
-
Notifications
You must be signed in to change notification settings - Fork 28.6k
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
Add Google Generative AI safety settings #117679
Conversation
homeassistant/components/google_generative_ai_conversation/const.py
Outdated
Show resolved
Hide resolved
@coderabbitai review |
WalkthroughThe recent updates to the Changes
Tip New Features and ImprovementsReview SettingsIntroduced new personality profiles for code reviews. Users can now select between "Chill" and "Assertive" review tones to tailor feedback styles according to their preferences. The "Assertive" profile posts more comments and nitpicks the code more aggressively, while the "Chill" profile is more relaxed and posts fewer comments. AST-based InstructionsCodeRabbit offers customizing reviews based on the Abstract Syntax Tree (AST) pattern matching. Read more about AST-based instructions in the documentation. Community-driven AST-based RulesWe are kicking off a community-driven initiative to create and share AST-based rules. Users can now contribute their AST-based rules to detect security vulnerabilities, code smells, and anti-patterns. Please see the ast-grep-essentials repository for more information. New Static Analysis ToolsWe are continually expanding our support for static analysis tools. We have added support for Tone SettingsUsers can now customize CodeRabbit to review code in the style of their favorite characters or personalities. Here are some of our favorite examples:
Revamped Settings PageWe have redesigned the settings page for a more intuitive layout, enabling users to find and adjust settings quickly. This change was long overdue; it not only improves the user experience but also allows our development team to add more settings in the future with ease. Going forward, the changes to Miscellaneous
Recent Review DetailsConfiguration used: CodeRabbit UI Files selected for processing (6)
Additional comments not posted (5)
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? TipsChatThere are 3 ways to chat with CodeRabbit:
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 as PR comments)
Additionally, you can add CodeRabbit Configration File (
|
@coderabbitai review |
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.
Actionable comments posted: 1
'safety_settings': dict({ | ||
'DANGEROUS': 'BLOCK_LOW_AND_ABOVE', | ||
'HARASSMENT': 'BLOCK_LOW_AND_ABOVE', | ||
'HATE': 'BLOCK_LOW_AND_ABOVE', | ||
'SEXUAL': 'BLOCK_LOW_AND_ABOVE', | ||
}), |
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.
Tip
Codebase Verification
The search results indicate that the snapshot tests only use the BLOCK_LOW_AND_ABOVE
threshold. However, there are other thresholds like BLOCK_MEDIUM_AND_ABOVE
defined in the codebase but not utilized in the tests.
- Consider adding more varied test cases to cover different block thresholds for comprehensive testing.
Analysis chain
The safety settings in the snapshot tests are consistent with the new block thresholds.
Also applies to: 66-71, 116-121, 169-174
Scripts Executed
The following scripts were executed for the analysis:
Script:
#!/bin/bash
# Description: Suggest adding more varied test cases for different block thresholds.
# Test: Search for the usage of different block thresholds in tests. Expect: Varied usage for comprehensive testing.
rg --type yaml $'safety_settings'
Length of output: 32
Script:
#!/bin/bash
# Description: Search for the usage of different block thresholds in the codebase to ensure comprehensive testing.
# Test: Search for the term 'BLOCK_LOW_AND_ABOVE' and other potential block thresholds in the codebase.
rg 'BLOCK_LOW_AND_ABOVE|BLOCK_MEDIUM_AND_ABOVE|BLOCK_HIGH_AND_ABOVE'
Length of output: 2480
Breaking change
Proposed change
Support safety settings. Default to the old behavior of blocking most content.
Type of change
Additional information
Checklist
ruff format homeassistant tests
)If user exposed functionality or configuration variables are added/changed:
If the code communicates with devices, web services, or third-party tools:
Updated and included derived files by running:
python3 -m script.hassfest
.requirements_all.txt
.Updated by running
python3 -m script.gen_requirements_all
..coveragerc
.To help with the load of incoming pull requests: