Conversation
- Incremented version of PraisonAI from 0.0.99 to 0.0.101 in pyproject.toml and uv.lock. - Added 'litellm' dependency to memory requirements for enhanced functionality. - Updated .gitignore to include 'CopilotKit*' for better file management. - Optimised TaskOutput instantiation in agent.py for clarity. - Refined memory handling in memory.py to utilise LiteLLM for consistency. - Improved model extraction logic in task.py for better fallback handling.
- Incremented the version of PraisonAI from 2.2.28 to 2.2.29 in Dockerfiles (Dockerfile, Dockerfile.chat, Dockerfile.dev, Dockerfile.ui). - Updated the version in the README.md and pyproject.toml files to reflect the new version. - Adjusted the deploy.py script to install the updated version of PraisonAI. - Ensured consistency across all relevant files for seamless integration.
|
Caution Review failedThe pull request is closed. WalkthroughThis update increments the PraisonAI and PraisonAIAgents package versions across Dockerfiles, deployment scripts, and project metadata. It introduces new example and test scripts for agent workflows and guardrail validation. Additionally, it transitions quality metric evaluation from OpenAI to LiteLLM, adjusts agent output construction, and updates dependency management. Changes
Sequence Diagram(s)sequenceDiagram
participant User
participant GuardrailAgentExample.py
participant Agent
participant Guardrail (validate_content)
User->>GuardrailAgentExample.py: Start script with prompt
GuardrailAgentExample.py->>Agent: Create agent with guardrail and retry limit
GuardrailAgentExample.py->>Agent: Start agent with prompt
Agent->>Guardrail: Validate generated content
alt Content fails guardrail
Guardrail-->>Agent: Validation failed
Agent->>Guardrail: Retry validation (up to 1 time)
end
Guardrail-->>Agent: Validation passed or retries exhausted
Agent-->>GuardrailAgentExample.py: Return result
sequenceDiagram
participant Memory
participant LiteLLM
Memory->>LiteLLM: Request completion for quality metrics (model: gpt-4o-mini)
LiteLLM-->>Memory: Return JSON with quality metrics
Memory-->>Memory: Parse and use metrics
Possibly related PRs
Suggested labels
Poem
📜 Recent review detailsConfiguration used: CodeRabbit UI ⛔ Files ignored due to path filters (2)
📒 Files selected for processing (15)
✨ 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 (
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Hello @MervinPraison, 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!
Summary of Changes
Hello team, gemini-code-assist here with a summary of this pull request. This PR primarily focuses on updating the core PraisonAI and praisonaiagents package versions across the project. It also includes specific enhancements within the praisonaiagents package, such as integrating LiteLLM for memory operations, refining the handling of guardrail outputs, and improving how custom LLMs are managed in task callbacks. Additionally, new example files demonstrating guardrail usage and basic agent setup have been added. Various configuration and documentation files have been updated to reflect these changes.
Highlights
- Version Updates: The
PraisonAIpackage is updated to version2.2.29and thepraisonaiagentspackage is updated to0.0.101. These updates are reflected inpyproject.toml,uv.lock, Dockerfiles, the Docker README, and the Homebrew formula. - LiteLLM Integration in Agents Memory: The
praisonaiagentsmemory module (memory.py) now uses LiteLLM for calculating quality metrics, replacing a direct OpenAI client import. This likely provides more flexibility in choosing LLM providers for memory operations. - Guardrail Output Handling Refinement: The
_apply_guardrail_with_retrymethod inpraisonaiagents/agent.pyhas been updated to simplify theTaskOutputobject created during guardrail processing, removing some fields and adding the agent name. - Improved Custom LLM Handling: The
execute_callbackmethod inpraisonaiagents/task.pynow includes logic to correctly extract the model name from custom LLM instances (like Ollama) and provides a default fallback model (gpt-4o-mini). - New Examples/Tests: Two new files,
guardrail_agent_example.pyandtest.py, have been added tosrc/praisonai-agents/to provide examples of using agents with guardrails and a basic agent/task setup with memory.
Changelog
Click here to see the changelog
- .gitignore
- Added
CopilotKit*to ignore files/directories related to CopilotKit.
- Added
- docker/Dockerfile
- Updated
praisonaidependency version to>=2.2.29.
- Updated
- docker/Dockerfile.chat
- Updated
praisonaidependency version to>=2.2.29.
- Updated
- docker/Dockerfile.dev
- Updated
praisonaidependency version to>=2.2.29.
- Updated
- docker/Dockerfile.ui
- Updated
praisonaidependency version to>=2.2.29.
- Updated
- docker/README.md
- Updated PraisonAI version mention in 'Package Versions' to
>=2.2.29. - Updated PraisonAI version in the 'Version Pinning' example to
==2.2.29.
- Updated PraisonAI version mention in 'Package Versions' to
- src/praisonai-agents/guardrail_agent_example.py
- Added a new example file demonstrating agent guardrail functionality.
- src/praisonai-agents/praisonaiagents/agent/agent.py
- Refactored
TaskOutputcreation within the guardrail retry logic (_apply_guardrail_with_retry) to simplify fields and add the agent name.
- Refactored
- src/praisonai-agents/praisonaiagents/memory/memory.py
- Switched from using an internal OpenAI client to LiteLLM for
calculate_quality_metrics. - Changed the default model for quality metrics to
gpt-4o-mini.
- Switched from using an internal OpenAI client to LiteLLM for
- src/praisonai-agents/praisonaiagents/task/task.py
- Added logic to extract the model name from custom LLM instances in
execute_callback. - Added a default fallback model (
gpt-4o-mini) when the model name cannot be determined from a custom LLM instance.
- Added logic to extract the model name from custom LLM instances in
- src/praisonai-agents/pyproject.toml
- Updated
praisonaiagentsversion to0.0.101. - Added
litellm>=1.50.0to thememoryextra dependency. - Updated setuptools package finding configuration.
- Updated
- src/praisonai-agents/test.py
- Added a new basic test/example file for
PraisonAIAgents.
- Added a new basic test/example file for
- src/praisonai-agents/uv.lock
- Updated lock file to reflect
praisonaiagentsversion0.0.101. - Added
litellmdependency for thememoryextra.
- Updated lock file to reflect
- src/praisonai/praisonai.rb
- Updated Homebrew formula URL and SHA256 hash for version
v2.2.29.
- Updated Homebrew formula URL and SHA256 hash for version
- src/praisonai/praisonai/deploy.py
- Updated the hardcoded
praisonaiversion in the generated Dockerfile snippet to2.2.29.
- Updated the hardcoded
- src/praisonai/pyproject.toml
- Updated
PraisonAIversion to2.2.29. - Updated
praisonaiagentsdependency version to>=0.0.101.
- Updated
- src/praisonai/uv.lock
- Updated lock file to reflect
praisonaiversion2.2.29. - Updated lock file to reflect
praisonaiagentsdependency version0.0.101.
- Updated lock file to reflect
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.
Versions bump and climb,
Dependencies align,
Code evolves with time.
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. ↩
PR Reviewer Guide 🔍Here are some key observations to aid the review process:
|
PR Code Suggestions ✨Explore these optional code suggestions:
|
|||||||||||||
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
There was a problem hiding this comment.
Bug: Guardrail Conflict in Example Code
The example src/praisonai-agents/guardrail_agent_example.py contains a logical inconsistency. The agent is instructed to write a 5-word message, but the configured guardrail requires content to be at least 50 characters long. This incompatibility causes the guardrail validation to consistently fail, making the example non-functional.
src/praisonai-agents/guardrail_agent_example.py#L2-L14
PraisonAI/src/praisonai-agents/guardrail_agent_example.py
Lines 2 to 14 in ee85a63
BugBot free trial expires on June 9, 2025
You have used $0.00 of your $50.00 spend limit so far. Manage your spend limit in the Cursor dashboard.
Was this report helpful? Give feedback by reacting with 👍 or 👎
There was a problem hiding this comment.
Code Review
The pull request updates the PraisonAI version, enhances agent and memory modules, adds new examples and tests, and updates dependencies. Overall, the changes seem well-structured and address the described objectives. Here are some specific comments and suggestions.
Summary of Findings
- TaskOutput instantiation: The
TaskOutputinstantiation is being modified, with several fields being removed. Verify that this change does not negatively impact any existing functionality. - Default LLM model: The default LLM model
gpt-4o-miniis hardcoded in multiple places. Consider making it configurable and adding more descriptive comments. - Unused llm_config: The
llm_configdictionary intest.pyis defined but not used. Consider removing it or using it in the test.
Merge Readiness
The pull request is almost ready for merging. Addressing the comments related to the TaskOutput instantiation and the default LLM model would improve the code quality and maintainability. I am unable to directly approve this pull request, and recommend that others review and approve this code before merging. In particular, I would recommend that the author address the medium severity issues before merging.
1 participant
PR Type
enhancement, bug_fix, tests
Description
Bump PraisonAI version to 2.2.29 across all relevant files
Enhance agent and memory modules for improved LLM/model handling
Add new example and test scripts for PraisonAI Agents
Update dependencies and packaging configuration
Changes walkthrough 📝
11 files
Add example for agent guardrail validationOptimize TaskOutput instantiation in guardrail logicUse LiteLLM for quality metrics calculationBump version, add litellm, update setuptools configBump PraisonAI and praisonaiagents versionsUpdate Dockerfile generation to use new versionUpdate Ruby formula for new PraisonAI versionBump PraisonAI version to 2.2.29Bump PraisonAI version to 2.2.29Bump PraisonAI version to 2.2.29Bump PraisonAI version to 2.2.291 files
Refine model extraction for quality metrics1 files
Add test script for agent/task execution1 files
Update PraisonAI version references in docsSummary by CodeRabbit