Tr/help fixes

[mrT23]

PR Type

Enhancement, Documentation

---

Description

• Improved the PR Help tool functionality:
  • Fixed snippet indexing to start from 1 for better user experience
  • Enhanced logging for clearer answer output display
• Updated Doc-helper AI instructions in pr_help_prompts.toml:
  • Added more detailed guidelines for generating concise answers
  • Clarified priority of main PR-Agent tools (describe, review, improve)
  • Improved Pydantic model definition and naming
• These changes aim to enhance the overall user experience and clarity of the PR Help feature

---

Changes walkthrough 📝

	Relevant files
Enhancement	pr_help_message.py Improve snippet indexing and logging in PR Help tool          pr_agent/tools/pr_help_message.py Fixed indexing in snippet display, now starting from 1 instead of 0 Updated logging to improve readability of the answer output +2/-2
Documentation	pr_help_prompts.toml Enhance Doc-helper AI instructions and model definition    pr_agent/settings/pr_help_prompts.toml Added more detailed instructions for the Doc-helper AI Clarified the priority of main PR-Agent tools Updated the Pydantic model name from 'doc_help' to 'DocHelper' +9/-4

---

💡 PR-Agent usage: Comment /help "your question" on any pull request to receive relevant information

[codiumai-pr-agent-pro]

PR Reviewer Guide 🔍

⏱️ Estimated effort to review: 2 🔵🔵⚪⚪⚪

🏅 Score: 95

🧪 No relevant tests

🔒 No security concerns identified

🔀 Multiple PR themes Sub-PR theme: Improve PR Help tool functionality Relevant files: pr_agent/tools/pr_help_message.py Sub-PR theme: Update Doc-helper AI instructions Relevant files: pr_agent/settings/pr_help_prompts.toml

⚡ No key issues to review

[mrT23]

/help "My team often creates pull requests (PRs) from a combined branch that has already reviewed branches for production deployment. In these cases, executing auto-triggered tasks on such PRs is often unnecessary, as they may involve extensive code changes and place significant load on the pr-agent service.
So, I suggest adding an option to selectively disable auto-triggered tasks on specific pull requests. This feature would allow teams to optimize their workflow and reduce unnecessary processing load. I have implemented and utilized this feature in our pr-agent codebase.

For example, this can be implemented by adding a flag to the PR title or at the end of the PR description. When this flag is present, pr-agent will not automatically perform a review. However, if needed, users can still trigger a review manually by entering a command in a comment after the PR is created.
"

[codiumai-pr-agent-pro]

Question:

My team often creates pull requests (PRs) from a combined branch that has already reviewed branches for production deployment. In these cases, executing auto-triggered tasks on such PRs is often unnecessary, as they may involve extensive code changes and place significant load on the pr-agent service.
So, I suggest adding an option to selectively disable auto-triggered tasks on specific pull requests. This feature would allow teams to optimize their workflow and reduce unnecessary processing load. I have implemented and utilized this feature in our pr-agent codebase.

For example, this can be implemented by adding a flag to the PR title or at the end of the PR description. When this flag is present, pr-agent will not automatically perform a review. However, if needed, users can still trigger a review manually by entering a command in a comment after the PR is created.

Answer:

Thank you for your suggestion. While PR-Agent doesn't currently have a built-in feature to selectively disable auto-triggered tasks on specific pull requests, there are some existing configuration options that might help address your needs:

1. The GitHub app has a configuration toggle handle_push_trigger that can be used to enable or disable automatic tool execution when new code is pushed to an open PR. You can set this to false if you don't want any automatic actions on push events.

2. The push_commands parameter in the GitHub app configuration defines which tools run automatically when new code is pushed. You can customize this list to include only the tools you want to run automatically, or leave it empty to disable all automatic actions on push.

3. For PRs opened from specific branches or with certain characteristics, you could potentially use GitHub Actions in combination with PR-Agent to create more granular control over when the automatic reviews are triggered.

While these options don't provide the exact functionality you're suggesting, they do offer some level of control over automatic actions. Your suggestion for a flag in the PR title or description to disable automatic reviews is an interesting idea that could potentially be considered for future updates to PR-Agent.

In the meantime, even if automatic reviews are triggered, users can always use the manual commands in PR comments to run specific tools when needed, regardless of the automatic settings.

Relevant Sources:

• https://pr-agent-docs.codium.ai/usage-guide/automations_and_usage#github-app
• https://pr-agent-docs.codium.ai/tools/review#usage-tips

[mrT23]

/help
"add a flag to the PR title or at the end of the PR description. When this flag is present, pr-agent will not run automatically"

[codiumai-pr-agent-pro]

Question:

add a flag to the PR title or at the end of the PR description. When this flag is present, pr-agent will not run automatically

Answer:

Unfortunately, PR-Agent does not have a built-in feature to add a flag in the PR title or description to prevent automatic execution. However, there are alternative ways to achieve similar results:

1. Ignore specific PR titles: You can configure PR-Agent to ignore PRs with specific titles by adding patterns to the ignore_pr_title list in your configuration.toml file. For example:

   [config]
   ignore_pr_title = ["\\[Bump\\]", "\\[Skip PR-Agent\\]"]

   This would ignore PRs with titles containing "[Bump]" or "[Skip PR-Agent]".

2. Ignore specific branches: You can also configure PR-Agent to ignore PRs from or to specific branches using ignore_pr_source_branches and ignore_pr_target_branches in the configuration file.

These methods allow you to control when PR-Agent runs automatically, but they require modifying the configuration file rather than adding a flag to individual PRs.

Relevant Sources:

• https://pr-agent-docs.codium.ai/usage-guide/additional_configurations#ignoring-automatic-commands-in-prs

[mrT23]

/improve

[codiumai-pr-agent-pro]

PR Code Suggestions ✨

Latest suggestions up to 3979632

Category	Suggestion	Score
Enhancement	Add a brief explanation of RAG in the system prompt for better context Consider adding a brief explanation of what RAG (Retrieval-Augmented Generation) is in the system prompt. This would provide more context for users who might not be familiar with the term. pr_agent/settings/pr_help_prompts.toml [3] -You will recieve a question, and a list of snippets that were collected for a documentation site using RAG as the retrieval method. +You will receive a question, and a list of snippets that were collected for a documentation site using RAG (Retrieval-Augmented Generation) as the retrieval method. RAG combines a knowledge base lookup with a language model to provide more accurate and contextual responses. Apply this suggestion Suggestion importance[1-10]: 8 Why: This suggestion enhances the documentation by providing clearer context about RAG, which can be beneficial for users unfamiliar with the term.	8
	Upgrade to a more recent embedding model for potentially improved performance Consider using a more recent OpenAI embedding model, such as "text-embedding-3-large", which might provide better performance for similarity search. However, ensure this change aligns with your project's requirements and budget constraints. pr_agent/tools/pr_help_message.py [161-162] -embeddings = OpenAIEmbeddings(model="text-embedding-3-small", +embeddings = OpenAIEmbeddings(model="text-embedding-3-large", api_key=get_settings().openai.key) Apply this suggestion Suggestion importance[1-10]: 4 Why: While using a newer model could potentially improve performance, it may also increase costs. The suggestion lacks consideration of the project's specific requirements and constraints.	4
Organization best practice	Simplify loop iteration using enumerate with a start index Use enumerate() with a start index of 1 to simplify the loop and eliminate manual index manipulation. This adheres to Python's best practices for iterating over sequences. pr_agent/tools/pr_help_message.py [327-328] -for i, s in enumerate(relevant_snippets_full): - relevant_snippets_str += f"Snippet {i+1}:\n\n{s}\n\n" +for i, s in enumerate(relevant_snippets_full, start=1): + relevant_snippets_str += f"Snippet {i}:\n\n{s}\n\n" Apply this suggestion Suggestion importance[1-10]: 7 Why: This suggestion improves code readability and follows Python best practices, eliminating the need for manual index manipulation.	7
	Rephrase comment to avoid implying individual imports of tools Consider rephrasing the comment about PR-Agent's main tools to avoid implying individual imports. Instead, mention them as part of the project's functionality to align with best practices of importing entire modules. pr_agent/settings/pr_help_prompts.toml [9] -- The main tools of pr-agent are 'describe', 'review', 'improve'. If there is ambiguity to which tool the user is referring to, prioritize snippets of these tools over others. +- PR-Agent's main functionalities include 'describe', 'review', and 'improve'. When addressing user queries, prioritize information related to these core features if there's any ambiguity. Apply this suggestion Suggestion importance[1-10]: 6 Why: The suggestion improves clarity in the documentation, but the original text didn't necessarily imply individual imports. It's a minor improvement in communication.	6
	Ensure thread-safe logging by creating a formatted string before logging Use a thread-safe logging approach by creating a formatted string before logging. This ensures atomicity and prevents potential race conditions in multi-threaded environments. pr_agent/tools/pr_help_message.py [210] -get_logger().info(f"Answer:\n{answer_str}") +log_message = f"Answer:\n{answer_str}" +get_logger().info(log_message) Apply this suggestion Suggestion importance[1-10]: 5 Why: The suggestion improves thread safety, but the impact is minimal in this context as the logging operation is likely not in a highly concurrent environment.	5

---

Previous suggestions

Suggestions up to commit 20d8e76

Category	Suggestion	Score
Organization best practice	Remove invalid character from class name to follow Python naming conventions Remove the $ symbol from the class name $DocHelper as it's not valid Python syntax. Use DocHelper instead to follow Python naming conventions. pr_agent/settings/pr_help_prompts.toml [14] -class $DocHelper(BaseModel): +class DocHelper(BaseModel): Suggestion importance[1-10]: 9 Why: This suggestion corrects an invalid Python syntax in the class name, which is crucial for proper code execution and adherence to Python naming conventions.	9
	Use enumerate() with a start index for more pythonic and error-resistant code Use enumerate() with a start index of 1 instead of manually incrementing the index. This improves readability and reduces the chance of off-by-one errors. pr_agent/tools/pr_help_message.py [327-328] -for i, s in enumerate(relevant_snippets_full): - relevant_snippets_str += f"Snippet {i+1}:\n\n{s}\n\n" +for i, s in enumerate(relevant_snippets_full, start=1): + relevant_snippets_str += f"Snippet {i}:\n\n{s}\n\n" Suggestion importance[1-10]: 7 Why: This suggestion improves code readability and reduces the chance of off-by-one errors, which aligns with Python best practices.	7
Enhancement	Use f-string with newline for improved log readability Use an f-string with a newline character to improve readability of the logged answer, instead of concatenating the newline character. pr_agent/tools/pr_help_message.py [210] +get_logger().info(f"Answer:\n{answer_str}") - Suggestion importance[1-10]: 5 Why: The suggestion slightly improves log readability, but the change is minor and the existing code is already using an f-string.	5

[mrT23]

/help

[codiumai-pr-agent-pro]

PR Agent Walkthrough 🤖

Welcome to the PR Agent, an AI-powered tool for automated pull request analysis, feedback, suggestions and more.

Here is a list of tools you can use to interact with the PR Agent:

Tool	Description	Trigger Interactively 💎
DESCRIBE	Generates PR description - title, type, summary, code walkthrough and labels	Run
REVIEW	Adjustable feedback about the PR, possible issues, security concerns, review effort and more	Run
IMPROVE	Code suggestions for improving the PR	Run
UPDATE CHANGELOG	Automatically updates the changelog	Run
ADD DOCS 💎	Generates documentation to methods/functions/classes that changed in the PR	Run
TEST 💎	Generates unit tests for a specific component, based on the PR code change	Run
IMPROVE COMPONENT 💎	Code suggestions for a specific component that changed in the PR	Run
ANALYZE 💎	Identifies code components that changed in the PR, and enables to interactively generate tests, docs, and code suggestions for each component	Run
ASK	Answering free-text questions about the PR	[*]
GENERATE CUSTOM LABELS 💎	Generates custom labels for the PR, based on specific guidelines defined by the user	[*]
CI FEEDBACK 💎	Generates feedback and analysis for a failed CI job	[*]
CUSTOM PROMPT 💎	Generates custom suggestions for improving the PR code, derived only from a specific guidelines prompt defined by the user	[*]
SIMILAR ISSUE	Automatically retrieves and presents similar issues	[*]

(1) Note that each tool be triggered automatically when a new PR is opened, or called manually by commenting on a PR.

(2) Tools marked with [*] require additional parameters to be passed. For example, to invoke the /ask tool, you need to comment on a PR: /ask "<question content>". See the relevant documentation for each tool for more details.