Extend 'similar_issue' Feature for Bitbucket Support and Update Documentation #400

sarbjitsinghgrewal · 2023-10-27T06:59:29Z

User description

Type:

Enhancement

Description:

This PR extends the 'similar_issue' feature to support Bitbucket, in addition to the existing support for GitHub. The changes include:

Modifications to the BitbucketProvider class to handle Bitbucket-specific operations.
Updates to the GithubProvider class to handle similar operations for GitHub.
Changes to the PRSimilarIssue class to use the appropriate Git provider based on the issue URL.
Updates to the README.md file to reflect the new support for Bitbucket in the 'similar_issue' feature.

Main files walkthrough:

files:

pr_agent/git_providers/bitbucket_provider.py: The BitbucketProvider class has been extended with methods to handle Bitbucket-specific operations. These include methods to parse issue URLs, get issues, get issue details, create comments on issues, and handle similar issues.
pr_agent/git_providers/github_provider.py: The GithubProvider class has been updated with similar methods to handle operations for GitHub. These include methods to get issues, create comments on issues, and handle similar issues.
pr_agent/tools/pr_similar_issue.py: The PRSimilarIssue class has been updated to use the appropriate Git provider based on the issue URL. It now supports both GitHub and Bitbucket.
README.md: The README.md file has been updated to reflect the new support for Bitbucket in the 'similar_issue' feature.

Type

Enhancement

Description

Extended BitbucketProvider with new attributes and methods for handling issues and comments on Bitbucket.
Updated GitHubProvider for consistent issue and comment handling, aligning with BitbucketProvider enhancements.
Generalized PRSimilarIssue class to support both GitHub and Bitbucket, removing the GitHub-specific restriction.
Updated README to reflect the new support for Bitbucket in the 'similar_issue' feature and marked additional support for the 'Actions' feature.

Changes walkthrough

Relevant files

Enhancement

bitbucket_provider.py `Extend BitbucketProvider for Issue Handling and Comments` pr_agent/git_providers/bitbucket_provider.py Added new attributes to the BitbucketProvider class for handling features, issue numbers, and issue names. Implemented methods for parsing issue URLs, getting issues, and creating comments on issues in Bitbucket. Enhanced the BitbucketProvider class to support operations specific to Bitbucket issues.	+114/-5
github_provider.py `Update GitHub Provider for Consistent Issue Handling` pr_agent/git_providers/github_provider.py Updated logging to use get_logger() for consistency. Added methods to handle GitHub issues similar to the new Bitbucket functionality. Enhanced GitHub provider with issue and comment handling capabilities.	+70/-2
pr_similar_issue.py `Generalize PRSimilarIssue for GitHub and Bitbucket Support` pr_agent/tools/pr_similar_issue.py Removed GitHub-specific restriction, allowing for general Git provider usage. Updated to use new methods from Git providers for issue and comment handling. Enhanced PRSimilarIssue class to support both GitHub and Bitbucket.	+21/-25

Documentation

README.md `Update README for Extended 'Find similar issue' Feature Support` README.md Updated the README to indicate support for the 'Find similar issue' feature on both GitHub and Bitbucket. Marked the 'Actions' feature as supported across more platforms.	+2/-2

✨ PR-Agent usage:
Comment /help on the PR to get a list of all available PR-Agent tools and their descriptions

…bucket_similar_issue_feature

…r-agent into bitbucket_similar_issue_feature

…bucket_similar_issue_feature

mrT23 · 2023-11-15T17:56:03Z

/review

github-actions · 2023-11-15T17:57:21Z

PR Analysis

(review updated until commit `f995b3e`)

🎯 Main theme: Extending 'similar_issue' feature to support Bitbucket
📝 PR summary: This PR extends the 'similar_issue' feature to support Bitbucket, in addition to the existing support for GitHub. It includes modifications to the BitbucketProvider and GithubProvider classes to handle operations specific to their respective platforms, and updates the PRSimilarIssue class to use the appropriate Git provider based on the issue URL. The README.md file is also updated to reflect the new support for Bitbucket in the 'similar_issue' feature.
📌 Type of PR: Enhancement
🧪 Relevant tests added: No
⏱️ Estimated effort to review [1-5]: 4, because the PR includes a significant amount of new code and changes to existing code, which requires a thorough review to ensure that the new functionality is implemented correctly and that existing functionality is not negatively affected.
🔒 Security concerns: No

PR Feedback

💡 General suggestions: The PR is well-structured and the changes are logically grouped. However, it would be beneficial to include tests for the new functionality to ensure it works as expected and does not introduce any regressions. Additionally, it would be helpful to include more detailed comments in the code to explain the purpose and functionality of the new methods.

🤖 Code feedback:

relevant file	pr_agent/git_providers/bitbucket_provider.py
suggestion	It seems like the BitbucketProvider class is doing too much work. Consider breaking down the class into smaller classes or modules, each with a single responsibility. This would improve the modularity and maintainability of the code. [important]
relevant line	class BitbucketProvider(GitProvider):

relevant file	pr_agent/git_providers/github_provider.py
suggestion	Similar to the BitbucketProvider class, the GithubProvider class could also benefit from being broken down into smaller classes or modules. This would make the code easier to understand and maintain. [important]
relevant line	class GithubProvider(GitProvider):

relevant file	pr_agent/tools/pr_similar_issue.py
suggestion	The PRSimilarIssue class seems to be tightly coupled with the BitbucketProvider and GithubProvider classes. Consider introducing an interface or abstract base class for the Git providers, which would make the PRSimilarIssue class more flexible and easier to test. [important]
relevant line	class PRSimilarIssue:

relevant file	README.md
suggestion	The changes to the README.md file are clear and informative. However, it would be helpful to include a section explaining how to use the 'similar_issue' feature with Bitbucket, similar to the existing instructions for GitHub. [medium]
relevant line	\| \| Find similar issue \| ✅ \| \| ✅ \| \| \| \|

✨ Usage guide:

Overview:
The review tool scans the PR code changes, and generates a PR review. The tool can be triggered automatically every time a new PR is opened, or can be invoked manually by commenting on any PR.
When commenting, to edit configurations related to the review tool (pr_reviewer section), use the following template:

/review --pr_reviewer.some_config1=... --pr_reviewer.some_config2=...

With a configuration file, use the following template:

[pr_reviewer]
some_config1=...
some_config2=...

Utilizing extra instructions The `review` tool can be configured with extra instructions, which can be used to guide the model to a feedback tailored to the needs of your project. Be specific, clear, and concise in the instructions. With extra instructions, you are the prompter. Specify the relevant sub-tool, and the relevant aspects of the PR that you want to emphasize. Examples for extra instructions: `[pr_reviewer] # /review # extra_instructions=""" In the 'general suggestions' section, emphasize the following: - Does the code logic cover relevant edge cases? - Is the code logic clear and easy to understand? - Is the code logic efficient? ... """` Use triple quotes to write multi-line instructions. Use bullet points to make the instructions more readable.
How to enable\disable automation When you first install PR-Agent app, the default mode for the `review` tool is: `pr_commands = ["/review", ...]` meaning the `review` tool will run automatically on every PR, with the default configuration. Edit this field to enable/disable the tool, or to change the used configurations
Auto-labels The `review` tool can auto-generate two specific types of labels for a PR: a `possible security issue` label, that detects possible security issues (`enable_review_labels_security` flag) a `Review effort [1-5]: x` label, where x is the estimated effort to review the PR (`enable_review_labels_effort` flag)
Extra sub-tools The `review` tool provides a collection of possible feedbacks about a PR. It is recommended to review the possible options, and choose the ones relevant for your use case. Some of the feature that are disabled by default are quite useful, and should be considered for enabling. For example: `require_score_review`, `require_soc2_ticket`, and more.
Auto-approve PRs By invoking: `/review auto_approve` The tool will automatically approve the PR, and add a comment with the approval. To ensure safety, the auto-approval feature is disabled by default. To enable auto-approval, you need to actively set in a pre-defined configuration file the following: `[pr_reviewer] enable_auto_approval = true` (this specific flag cannot be set with a command line argument, only in the configuration file, committed to the repository) You can also enable auto-approval only if the PR meets certain requirements, such as that the `estimated_review_effort` is equal or below a certain threshold, by adjusting the flag: `[pr_reviewer] maximal_review_effort = 5`
More PR-Agent commands To invoke the PR-Agent, add a comment using one of the following commands: /review: Request a review of your Pull Request. /describe: Update the PR title and description based on the contents of the PR. /improve [--extended]: Suggest code improvements. Extended mode provides a higher quality feedback. /ask <QUESTION>: Ask a question about the PR. /update_changelog: Update the changelog based on the PR's contents. /add_docs 💎: Generate docstring for new components introduced in the PR. /generate_labels 💎: Generate labels for the PR based on the PR's contents. /analyze 💎: Automatically analyzes the PR, and presents changes walkthrough for each component. See the tools guide for more details. To list the possible configuration parameters, add a /config comment.

See the review usage page for a comprehensive guide on using this tool.

mrT23 · 2023-12-05T14:50:28Z

PR Description updated to latest commit (f995b3e)

mrT23 · 2023-12-05T14:53:01Z

PR Description updated to latest commit (f995b3e)

GadiZimerman · 2024-01-03T22:02:02Z

👍
👎

@okotek can you tick these?

pr_agent/git_providers/bitbucket_provider.py

pr_agent/git_providers/github_provider.py

pr_agent/tools/pr_similar_issue.py

pr_agent/git_providers/bitbucket_provider.py

pr_agent/git_providers/github_provider.py

pr_agent/tools/pr_similar_issue.py

pr_agent/git_providers/bitbucket_provider.py

pr_agent/git_providers/github_provider.py

mrT23 · 2024-02-29T06:58:31Z

/test

codiumai-pr-agent-pro · 2024-02-29T06:58:36Z

❌ PR-Agent: Missing component name in test command.

Please provide a component name when running the tool: /test <component_name>.

✨ Test tool usage guide:

The test tool generate tests for a selected component, based on the PR code changes.
It can be invoked manually by commenting on any PR:

/test component_name

where 'component_name' is the name of a specific component in the PR. To get a list of the components that changed in the PR, use the analyze tool.
Language that are currently supported: Python, Java, C++, JavaScript, TypeScript.

Configuration options:

num_tests: number of tests to generate. Default is 3.
testing_framework: the testing framework to use. If not set, for Python it will use pytest, for Java it will use JUnit, for C++ it will use Catch2, and for JavaScript and TypeScript it will use jest.
avoid_mocks: if set to true, the tool will try to avoid using mocks in the generated tests. Note that even if this option is set to true, the tool might still use mocks if it cannot generate a test without them. Default is true.
extra_instructions: Optional extra instructions to the tool. For example: "use the following mock injection scheme: ...".
file: in case there are several components with the same name, you can specify the relevant file.
class_name: in case there are several components with the same name in the same file, you can specify the relevant class name.

See more information about the test tool in the docs.

mrT23 · 2024-03-03T15:05:55Z

PR Code Suggestions

✨ Improve tool usage guide:

Overview:
The improve tool scans the PR code changes, and automatically generates suggestions for improving the PR code. The tool can be triggered automatically every time a new PR is opened, or can be invoked manually by commenting on a PR.
When commenting, to edit configurations related to the improve tool (pr_code_suggestions section), use the following template:

/improve --pr_code_suggestions.some_config1=... --pr_code_suggestions.some_config2=...

With a configuration file, use the following template:

[pr_code_suggestions]
some_config1=...
some_config2=...

Enabling\disabling automation When you first install the app, the default mode for the improve tool is: `pr_commands = ["/improve --pr_code_suggestions.summarize=true", ...]` meaning the `improve` tool will run automatically on every PR, with summarization enabled. Delete this line to disable the tool from running automatically.
Utilizing extra instructions Extra instructions are very important for the `improve` tool, since they enable to guide the model to suggestions that are more relevant to the specific needs of the project. Be specific, clear, and concise in the instructions. With extra instructions, you are the prompter. Specify relevant aspects that you want the model to focus on. Examples for extra instructions: `[pr_code_suggestions] # /improve # extra_instructions=""" Emphasize the following aspects: - Does the code logic cover relevant edge cases? - Is the code logic clear and easy to understand? - Is the code logic efficient? ... """` Use triple quotes to write multi-line instructions. Use bullet points to make the instructions more readable.
A note on code suggestions quality While the current AI for code is getting better and better (GPT-4), it's not flawless. Not all the suggestions will be perfect, and a user should not accept all of them automatically. Suggestions are not meant to be simplistic. Instead, they aim to give deep feedback and raise questions, ideas and thoughts to the user, who can then use his judgment, experience, and understanding of the code base. Recommended to use the 'extra_instructions' field to guide the model to suggestions that are more relevant to the specific needs of the project, or use the custom suggestions 💎 tool With large PRs, best quality will be obtained by using 'improve --extended' mode.
More PR-Agent commands To invoke the PR-Agent, add a comment using one of the following commands: /review: Request a review of your Pull Request. /describe: Update the PR title and description based on the contents of the PR. /improve [--extended]: Suggest code improvements. Extended mode provides a higher quality feedback. /ask <QUESTION>: Ask a question about the PR. /update_changelog: Update the changelog based on the PR's contents. /add_docs 💎: Generate docstring for new components introduced in the PR. /generate_labels 💎: Generate labels for the PR based on the PR's contents. /analyze 💎: Automatically analyzes the PR, and presents changes walkthrough for each component. See the tools guide for more details. To list the possible configuration parameters, add a /config comment.

See the improve usage page for a more comprehensive guide on using this tool.

mrT23 · 2024-03-03T15:10:37Z

PR Code Suggestions

Category	Suggestions
Enhancement	Use a more descriptive variable name for the repository slug. Consider using a more descriptive variable name than `workspace_slug`. The name `workspace_slug` might be misleading, as it suggests that it's a slug for a workspace, but it's actually a slug for a repository. A more descriptive name like `repo_slug` would be more appropriate. pr_agent/git_providers/bitbucket_provider.py [242] -workspace_slug, repo_name, original_issue_number = self._parse_issue_url(issue_url) +repo_slug, repo_name, original_issue_number = self._parse_issue_url(issue_url)
	Remove the try-except block for converting `issue_number_similar` to an integer. It seems like you're using a try-except block to handle the case where `issue_number_similar` cannot be converted to an integer. However, if `issue_number_similar` is not a valid integer, it will still raise a `ValueError`. Consider removing the try-except block and let the error propagate up to the caller. pr_agent/git_providers/bitbucket_provider.py [361-364] -try: - int_list = ast.literal_eval(issues) - int_list = [int(x) for x in int_list] - for issue_number in int_list: - return issue_number -except ValueError: - return None +int_list = ast.literal_eval(issues) +int_list = [int(x) for x in int_list] +for issue_number in int_list: + return issue_number
	Remove the try-except block for converting `issue_number_similar` to an integer. It seems like you're using a try-except block to handle the case where `issue_number_similar` cannot be converted to an integer. However, if `issue_number_similar` is not a valid integer, it will still raise a `ValueError`. Consider removing the try-except block and let the error propagate up to the caller. pr_agent/git_providers/bitbucket_provider.py [370] -try: - issue_number_similar = int(issue_number_similar) -except ValueError: - return None +issue_number_similar = int(issue_number_similar)
	Remove the `return` statement inside the loop in `get_issue_numbers_from_list` method. The `get_issue_numbers_from_list` method seems to be returning the first issue number in the list. If you want to return all issue numbers, you should remove the `return` statement inside the loop. pr_agent/git_providers/bitbucket_provider.py [363-364] for issue_number in int_list: - return issue_number + print(issue_number)
	Remove the `return` statement inside the loop in `get_issue_numbers_from_list` method. The `get_issue_numbers_from_list` method seems to be returning the first issue number in the list. If you want to return all issue numbers, you should remove the `return` statement inside the loop. pr_agent/git_providers/bitbucket_provider.py [511-512] for issue_number in int_list: - return issue_number + print(issue_number)
	Automate the updating of the README table. The table in the README file seems to have been manually updated. Consider automating this process to ensure consistency across all tools. README.md [113-125] \| \| ⮑ Extended \| :white_check_mark: \| :white_check_mark: \| :white_check_mark: \| :white_check_mark: \| \| :white_check_mark: \| \| \| Reflect and Review \| :white_check_mark: \| :white_check_mark: \| :white_check_mark: \| :white_check_mark: \| :white_check_mark: \| \| \| Update CHANGELOG.md \| :white_check_mark: \| :white_check_mark: \| :white_check_mark: \| :white_check_mark: \| \| \| \| \| Find similar issue \| :white_check_mark: \| \| :white_check_mark: \| \| \| \| \| \| Add Documentation \| :white_check_mark: \| :white_check_mark: \| :white_check_mark: \| :white_check_mark: \| \| :white_check_mark: \| \| \| \| \| \| \| \| \| \| USAGE \| CLI \| :white_check_mark: \| :white_check_mark: \| :white_check_mark: \| :white_check_mark: \| :white_check_mark: \| \| \| App / webhook \| :white_check_mark: \| :white_check_mark: \| \| \| \| \| \| Tagging bot \| :white_check_mark: \| \| \| \| \| -\| \| Actions \| :white_check_mark: \| \| \| \| \| +\| \| Actions \| :white_check_mark: \| :white_check_mark: \| \| \| \| \| Web server \| \| \| \| \| \| :white_check_mark: \| -\| \| \| \| \| \| \| \| +\| \| \| \| \| \| \| \| CORE \| PR compression \| :white_check_mark: \| :white_check_mark: \| :white_check_mark: \| :white_check_mark: \| :white_check_mark: \| :white_check_mark: \|
Possible issue	Add error handling for invalid issue URLs or non-existent repositories. Consider adding error handling for the case where `self.git_provider.parse_issue_url_and_get_repo_obj(issue_url.split('=')[-1])` returns None. This would prevent potential issues if the issue URL is not valid or if the repository does not exist. pr_agent/tools/pr_similar_issue.py [27] -self.git_provider.repo_obj = self.git_provider.parse_issue_url_and_get_repo_obj(issue_url.split('=')[-1]) +repo_obj = self.git_provider.parse_issue_url_and_get_repo_obj(issue_url.split('=')[-1]) +if repo_obj is None: + raise ValueError("Invalid issue URL or repository does not exist") +self.git_provider.repo_obj = repo_obj
Performance	Avoid redundant method calls by storing the result in a variable. It seems like the `self.git_provider.get_repo_name_for_indexing(repo_obj)` method is being called twice. Consider storing the result in a variable and reusing it. This would improve performance by avoiding redundant method calls. pr_agent/tools/pr_similar_issue.py [30] -repo_name_for_index = self.repo_name_for_index = self.git_provider.get_repo_name_for_indexing(repo_obj) +repo_name_for_index = self.git_provider.get_repo_name_for_indexing(repo_obj) +self.repo_name_for_index = repo_name_for_index
	Avoid redundant method calls by storing the result in a variable. The `self.git_provider.get_issue_url(issue)` method is being called twice. Consider storing the result in a variable and reusing it. This would improve performance by avoiding redundant method calls. pr_agent/tools/pr_similar_issue.py [148] -url = self.git_provider.get_issue_url(issue) +issue_url = self.git_provider.get_issue_url(issue) +url = issue_url
	Avoid redundant method calls by storing the result in a variable. The `self.git_provider.get_issue_comment_body(comment)` method is being called twice. Consider storing the result in a variable and reusing it. This would improve performance by avoiding redundant method calls. pr_agent/tools/pr_similar_issue.py [208] -comment_body = self.git_provider.get_issue_comment_body(comment) +comment_body_str = self.git_provider.get_issue_comment_body(comment) +comment_body = comment_body_str

✨ Improve tool usage guide:

Overview:
The improve tool scans the PR code changes, and automatically generates suggestions for improving the PR code. The tool can be triggered automatically every time a new PR is opened, or can be invoked manually by commenting on a PR.
When commenting, to edit configurations related to the improve tool (pr_code_suggestions section), use the following template:

/improve --pr_code_suggestions.some_config1=... --pr_code_suggestions.some_config2=...

With a configuration file, use the following template:

[pr_code_suggestions]
some_config1=...
some_config2=...

Enabling\disabling automation When you first install the app, the default mode for the improve tool is: `pr_commands = ["/improve --pr_code_suggestions.summarize=true", ...]` meaning the `improve` tool will run automatically on every PR, with summarization enabled. Delete this line to disable the tool from running automatically.
Utilizing extra instructions Extra instructions are very important for the `improve` tool, since they enable to guide the model to suggestions that are more relevant to the specific needs of the project. Be specific, clear, and concise in the instructions. With extra instructions, you are the prompter. Specify relevant aspects that you want the model to focus on. Examples for extra instructions: `[pr_code_suggestions] # /improve # extra_instructions=""" Emphasize the following aspects: - Does the code logic cover relevant edge cases? - Is the code logic clear and easy to understand? - Is the code logic efficient? ... """` Use triple quotes to write multi-line instructions. Use bullet points to make the instructions more readable.
A note on code suggestions quality While the current AI for code is getting better and better (GPT-4), it's not flawless. Not all the suggestions will be perfect, and a user should not accept all of them automatically. Suggestions are not meant to be simplistic. Instead, they aim to give deep feedback and raise questions, ideas and thoughts to the user, who can then use his judgment, experience, and understanding of the code base. Recommended to use the 'extra_instructions' field to guide the model to suggestions that are more relevant to the specific needs of the project, or use the custom suggestions 💎 tool With large PRs, best quality will be obtained by using 'improve --extended' mode.
More PR-Agent commands To invoke the PR-Agent, add a comment using one of the following commands: /review: Request a review of your Pull Request. /describe: Update the PR title and description based on the contents of the PR. /improve [--extended]: Suggest code improvements. Extended mode provides a higher quality feedback. /ask <QUESTION>: Ask a question about the PR. /update_changelog: Update the changelog based on the PR's contents. /add_docs 💎: Generate docstring for new components introduced in the PR. /generate_labels 💎: Generate labels for the PR based on the PR's contents. /analyze 💎: Automatically analyzes the PR, and presents changes walkthrough for each component. See the tools guide for more details. To list the possible configuration parameters, add a /config comment.

See the improve usage page for a more comprehensive guide on using this tool.

mrT23 · 2024-03-03T15:15:10Z

PR Code Suggestions

✨ Improve tool usage guide:

Overview:
The improve tool scans the PR code changes, and automatically generates suggestions for improving the PR code. The tool can be triggered automatically every time a new PR is opened, or can be invoked manually by commenting on a PR.
When commenting, to edit configurations related to the improve tool (pr_code_suggestions section), use the following template:

/improve --pr_code_suggestions.some_config1=... --pr_code_suggestions.some_config2=...

With a configuration file, use the following template:

[pr_code_suggestions]
some_config1=...
some_config2=...

Enabling\disabling automation When you first install the app, the default mode for the improve tool is: `pr_commands = ["/improve --pr_code_suggestions.summarize=true", ...]` meaning the `improve` tool will run automatically on every PR, with summarization enabled. Delete this line to disable the tool from running automatically.
Utilizing extra instructions Extra instructions are very important for the `improve` tool, since they enable to guide the model to suggestions that are more relevant to the specific needs of the project. Be specific, clear, and concise in the instructions. With extra instructions, you are the prompter. Specify relevant aspects that you want the model to focus on. Examples for extra instructions: `[pr_code_suggestions] # /improve # extra_instructions=""" Emphasize the following aspects: - Does the code logic cover relevant edge cases? - Is the code logic clear and easy to understand? - Is the code logic efficient? ... """` Use triple quotes to write multi-line instructions. Use bullet points to make the instructions more readable.
A note on code suggestions quality While the current AI for code is getting better and better (GPT-4), it's not flawless. Not all the suggestions will be perfect, and a user should not accept all of them automatically. Suggestions are not meant to be simplistic. Instead, they aim to give deep feedback and raise questions, ideas and thoughts to the user, who can then use his judgment, experience, and understanding of the code base. Recommended to use the 'extra_instructions' field to guide the model to suggestions that are more relevant to the specific needs of the project, or use the custom suggestions 💎 tool With large PRs, best quality will be obtained by using 'improve --extended' mode.
More PR-Agent commands To invoke the PR-Agent, add a comment using one of the following commands: /review: Request a review of your Pull Request. /describe: Update the PR title and description based on the contents of the PR. /improve [--extended]: Suggest code improvements. Extended mode provides a higher quality feedback. /ask <QUESTION>: Ask a question about the PR. /update_changelog: Update the changelog based on the PR's contents. /add_docs 💎: Generate docstring for new components introduced in the PR. /generate_labels 💎: Generate labels for the PR based on the PR's contents. /analyze 💎: Automatically analyzes the PR, and presents changes walkthrough for each component. See the tools guide for more details. To list the possible configuration parameters, add a /config comment.

See the improve usage page for a more comprehensive guide on using this tool.

mrT23 · 2024-03-03T15:17:44Z

Generating PR code suggestions

Work in progress ...

mrT23 · 2024-03-03T15:22:58Z

PR Code Suggestions

Category	Suggestions
Enhancement	Replace `workspace_slug` with a more descriptive variable name. Consider using a more descriptive variable name than `workspace_slug`. The current name does not clearly indicate what the variable represents. A more descriptive name would be `workspace_name` or `workspace_identifier`. pr_agent/git_providers/bitbucket_provider.py [228] -workspace_slug, repo_slug, pr_number = self._parse_pr_url(pr_url) +workspace_name, repo_slug, pr_number = self._parse_pr_url(pr_url)
	Add a type hint to the `get_issue_url` method. The `get_issue_url` method is called with `issue` as an argument. However, the method's documentation does not specify what type `issue` should be. It would be better to add a type hint to the method to ensure that the correct type of argument is passed. pr_agent/tools/pr_similar_issue.py [148] -url = self.git_provider.get_issue_url(issue) +url = self.git_provider.get_issue_url(issue: Issue)
	Add a type hint to the `get_issue_body` method. The `get_issue_body` method is called with `issue` as an argument. However, the method's documentation does not specify what type `issue` should be. It would be better to add a type hint to the method to ensure that the correct type of argument is passed. pr_agent/tools/pr_similar_issue.py [157] -body = self.git_provider.get_issue_body(issue) +body = self.git_provider.get_issue_body(issue: Issue)
	Add a type hint to the `get_issue_number` method. The `get_issue_number` method is called with `issue` as an argument. However, the method's documentation does not specify what type `issue` should be. It would be better to add a type hint to the method to ensure that the correct type of argument is passed. pr_agent/tools/pr_similar_issue.py [158] -number = self.git_provider.get_issue_number(issue) +number = self.git_provider.get_issue_number(issue: Issue)
	Add a type hint to the `get_issue_comment_body` method. The `get_issue_comment_body` method is called with `comment` as an argument. However, the method's documentation does not specify what type `comment` should be. It would be better to add a type hint to the method to ensure that the correct type of argument is passed. pr_agent/tools/pr_similar_issue.py [208] -comment_body = self.git_provider.get_issue_comment_body(comment) +comment_body = self.git_provider.get_issue_comment_body(comment: Comment)
Bug	Return all issue numbers in the list. The `get_issue_numbers_from_list` method is currently returning the first issue number in the list. It should return all issue numbers in the list. pr_agent/git_providers/bitbucket_provider.py [363-364] -for issue_number in int_list: - return issue_number +return int_list
Best practice	Replace `repo_obj` with a more descriptive variable name. Consider using a more descriptive variable name than `repo_obj`. The current name does not clearly indicate what the object represents. A more descriptive name like `repository_object` would make the code more readable. pr_agent/tools/pr_similar_issue.py [27-30] -repo_obj = self.git_provider.parse_issue_url_and_get_repo_obj(issue_url.split('=')[-1]) -repo_name_for_index = self.repo_name_for_index = self.git_provider.get_repo_name_for_indexing(repo_obj) +repository_object = self.git_provider.parse_issue_url_and_get_repo_obj(issue_url.split('=')[-1]) +repository_name_for_index = self.git_provider.get_repo_name_for_indexing(repository_object)

✨ Improve tool usage guide:

Overview:
The improve tool scans the PR code changes, and automatically generates suggestions for improving the PR code. The tool can be triggered automatically every time a new PR is opened, or can be invoked manually by commenting on a PR.
When commenting, to edit configurations related to the improve tool (pr_code_suggestions section), use the following template:

/improve --pr_code_suggestions.some_config1=... --pr_code_suggestions.some_config2=...

With a configuration file, use the following template:

[pr_code_suggestions]
some_config1=...
some_config2=...

Enabling\disabling automation When you first install the app, the default mode for the improve tool is: `pr_commands = ["/improve --pr_code_suggestions.summarize=true", ...]` meaning the `improve` tool will run automatically on every PR, with summarization enabled. Delete this line to disable the tool from running automatically.
Utilizing extra instructions Extra instructions are very important for the `improve` tool, since they enable to guide the model to suggestions that are more relevant to the specific needs of the project. Be specific, clear, and concise in the instructions. With extra instructions, you are the prompter. Specify relevant aspects that you want the model to focus on. Examples for extra instructions: `[pr_code_suggestions] # /improve # extra_instructions=""" Emphasize the following aspects: - Does the code logic cover relevant edge cases? - Is the code logic clear and easy to understand? - Is the code logic efficient? ... """` Use triple quotes to write multi-line instructions. Use bullet points to make the instructions more readable.
A note on code suggestions quality While the current AI for code is getting better and better (GPT-4), it's not flawless. Not all the suggestions will be perfect, and a user should not accept all of them automatically. Suggestions are not meant to be simplistic. Instead, they aim to give deep feedback and raise questions, ideas and thoughts to the user, who can then use his judgment, experience, and understanding of the code base. Recommended to use the 'extra_instructions' field to guide the model to suggestions that are more relevant to the specific needs of the project, or use the custom suggestions 💎 tool With large PRs, best quality will be obtained by using 'improve --extended' mode.
More PR-Agent commands To invoke the PR-Agent, add a comment using one of the following commands: /review: Request a review of your Pull Request. /describe: Update the PR title and description based on the contents of the PR. /improve [--extended]: Suggest code improvements. Extended mode provides a higher quality feedback. /ask <QUESTION>: Ask a question about the PR. /update_changelog: Update the changelog based on the PR's contents. /add_docs 💎: Generate docstring for new components introduced in the PR. /generate_labels 💎: Generate labels for the PR based on the PR's contents. /analyze 💎: Automatically analyzes the PR, and presents changes walkthrough for each component. See the tools guide for more details. To list the possible configuration parameters, add a /config comment.

See the improve usage page for a more comprehensive guide on using this tool.

mrT23 · 2024-03-03T15:30:56Z

PR Code Suggestions

Category Suggestions

Maintainability

Refactor the _parse_issue_url method to make it more readable and maintainable.

It seems like the _parse_issue_url method is doing a lot of work. Consider breaking it
down into smaller, more manageable methods. This would make the code easier to read and
maintain.

pr_agent/git_providers/bitbucket_provider.py [235-250]

 @staticmethod
 def _parse_issue_url(issue_url: str) -> Tuple[str, int]:
     parsed_url = urlparse(issue_url)
+    _BitbucketProvider._validate_url(parsed_url)
+    path_parts = _BitbucketProvider._get_path_parts(parsed_url)
+    workspace_slug, repo_slug, issue_number = _BitbucketProvider._get_workspace_slug_repo_slug_issue_number(path_parts)
+    return workspace_slug, repo_slug, issue_number
 
+@staticmethod
+def _validate_url(parsed_url: ParseResult):
     if "bitbucket.org" not in parsed_url.netloc:
         raise ValueError("The provided URL is not a valid Bitbucket URL")
 
+@staticmethod
+def _get_path_parts(parsed_url: ParseResult) -> List[str]:
     path_parts = parsed_url.path.strip('/').split('/')
     if len(path_parts) < 5 or path_parts[2] != "issues":
         raise ValueError("The provided URL does not appear to be a Bitbucket issue URL")
+    return path_parts
 
+@staticmethod
+def _get_workspace_slug_repo_slug_issue_number(path_parts: List[str]) -> Tuple[str, str, int]:
     workspace_slug = path_parts[0]
     repo_slug = path_parts[1]
     try:
         issue_number = int(path_parts[3])
     except ValueError as e:
-        raise ValueError("Unable to convert issue number to integer") from e       
+        raise ValueError("Unable to convert issue number to integer") from e
     return workspace_slug, repo_slug, issue_number

Enhancement

Modify the get_issue_numbers_from_list method to return all issue numbers instead of just the first one.

The get_issue_numbers_from_list method is currently returning the first issue number in
the list. Consider returning all issue numbers instead.

pr_agent/git_providers/bitbucket_provider.py [363-366]

 @staticmethod
 def get_issue_numbers_from_list(issues):
     # convert str to list'
     int_list = ast.literal_eval(issues)
     int_list = [int(x) for x in int_list]
-    for issue_number in int_list:
-        return issue_number
+    return int_list

✨ Improve tool usage guide:

Overview:
The improve tool scans the PR code changes, and automatically generates suggestions for improving the PR code. The tool can be triggered automatically every time a new PR is opened, or can be invoked manually by commenting on a PR.
When commenting, to edit configurations related to the improve tool (pr_code_suggestions section), use the following template:

/improve --pr_code_suggestions.some_config1=... --pr_code_suggestions.some_config2=...

With a configuration file, use the following template:

[pr_code_suggestions]
some_config1=...
some_config2=...

Enabling\disabling automation When you first install the app, the default mode for the improve tool is: `pr_commands = ["/improve --pr_code_suggestions.summarize=true", ...]` meaning the `improve` tool will run automatically on every PR, with summarization enabled. Delete this line to disable the tool from running automatically.
Utilizing extra instructions Extra instructions are very important for the `improve` tool, since they enable to guide the model to suggestions that are more relevant to the specific needs of the project. Be specific, clear, and concise in the instructions. With extra instructions, you are the prompter. Specify relevant aspects that you want the model to focus on. Examples for extra instructions: `[pr_code_suggestions] # /improve # extra_instructions=""" Emphasize the following aspects: - Does the code logic cover relevant edge cases? - Is the code logic clear and easy to understand? - Is the code logic efficient? ... """` Use triple quotes to write multi-line instructions. Use bullet points to make the instructions more readable.
A note on code suggestions quality While the current AI for code is getting better and better (GPT-4), it's not flawless. Not all the suggestions will be perfect, and a user should not accept all of them automatically. Suggestions are not meant to be simplistic. Instead, they aim to give deep feedback and raise questions, ideas and thoughts to the user, who can then use his judgment, experience, and understanding of the code base. Recommended to use the 'extra_instructions' field to guide the model to suggestions that are more relevant to the specific needs of the project, or use the custom suggestions 💎 tool With large PRs, best quality will be obtained by using 'improve --extended' mode.
More PR-Agent commands To invoke the PR-Agent, add a comment using one of the following commands: /review: Request a review of your Pull Request. /describe: Update the PR title and description based on the contents of the PR. /improve [--extended]: Suggest code improvements. Extended mode provides a higher quality feedback. /ask <QUESTION>: Ask a question about the PR. /update_changelog: Update the changelog based on the PR's contents. /add_docs 💎: Generate docstring for new components introduced in the PR. /generate_labels 💎: Generate labels for the PR based on the PR's contents. /analyze 💎: Automatically analyzes the PR, and presents changes walkthrough for each component. See the tools guide for more details. To list the possible configuration parameters, add a /config comment.

See the improve usage page for a more comprehensive guide on using this tool.

GadiZimerman · 2024-03-18T10:19:19Z

/help

codiumai-pr-agent-pro · 2024-03-18T10:19:26Z

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	Invoke 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
ANALYZE 💎	Identifies code components that changed in the PR, and enables to interactively generate tests, docs, and code suggestions for each component.	Run
UPDATE CHANGELOG	Automatically updates the changelog.	Run
ADD DOCUMENTATION 💎	Generates documentation to methods/functions/classes that changed in the PR.	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	[*]
TEST 💎	Generates unit tests for a specific component, based on the PR code change.	[*]
CI FEEDBACK 💎	Generates feedback and analysis for a failed CI job.	[*]
CUSTOM SUGGESTIONS 💎	Generates custom suggestions for improving the PR code, based on specific guidelines 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.

hussam789 · 2024-04-10T11:40:28Z

/describe
--pr_description.keep_original_user_title=false
--pr_description.use_description_markers=true

codiumai-pr-agent-pro · 2024-04-10T11:41:57Z

PR Description updated to latest commit (f995b3e)

Copy walkthrough table to "Files Changed" Tab

hussam789 · 2024-04-10T11:42:21Z

/describe --pr_description.keep_original_user_title=false

codiumai-pr-agent-pro · 2024-04-10T11:42:56Z

PR Description updated to latest commit (f995b3e)

Copy walkthrough table to "Files Changed" Tab

codiumai-pr-agent-pro · 2024-05-01T14:03:25Z

PR-Agent was enabled for this repository. To continue using it, please link your git user with your CodiumAI identity here.

Persistent review updated to latest commit f995b3e

codiumai-pr-agent-pro · 2024-05-01T14:04:43Z

PR-Agent was enabled for this repository. To continue using it, please link your git user with your CodiumAI identity here.

PR Code Suggestions

Category	Suggestions
Maintainability	Replace direct access to private attributes with getter methods. Replace the direct access to private attributes of the `pr` object with proper getter methods or public properties to ensure encapsulation and maintainability. pr_agent/git_providers/bitbucket_provider.py [42-43] -self.bitbucket_comment_api_url = self.pr._BitbucketBase__data["links"]["comments"]["href"] -self.bitbucket_pull_request_api_url = self.pr._BitbucketBase__data["links"]['self']['href'] +self.bitbucket_comment_api_url = self.pr.get_comment_api_url() +self.bitbucket_pull_request_api_url = self.pr.get_pull_request_api_url()
Maintainability	Avoid returning within a loop to improve code clarity and maintainability. Refactor the method to avoid returning within a loop which can lead to unexpected behaviors and make the code harder to understand and maintain. pr_agent/git_providers/bitbucket_provider.py [363-364] -for issue_number in int_list: - return issue_number +return int_list[0] if int_list else None
Error handling	Improve error handling for network requests. Use a more specific exception handling for the `requests` library calls to handle potential network issues or data processing errors more gracefully. pr_agent/git_providers/bitbucket_provider.py [331] -response = requests.request("GET", url, headers=headers, data=payload) +try: + response = requests.request("GET", url, headers=headers, data=payload) + response.raise_for_status() # Raises HTTPError for bad responses +except requests.exceptions.RequestException as e: + get_logger().error(f"Failed to fetch data: {e}") + return None
Security	Replace `ast.literal_eval` with `json.loads` for safer string to list conversion. Avoid using `ast.literal_eval` for converting string to list due to potential security risks and replace it with a safer alternative. pr_agent/git_providers/bitbucket_provider.py [361] -int_list = ast.literal_eval(issues) +import json +int_list = json.loads(issues)
Best practice	Properly initialize and use payload and headers in network requests. Ensure that the `payload` and `headers` dictionaries are properly initialized and used in the `requests` call to avoid sending empty data and headers. pr_agent/git_providers/bitbucket_provider.py [328-331] -payload = {} -headers = {} -response = requests.request("POST", url, headers=headers, data=payload) +payload = {'key': 'value'} # Example payload +headers = {'Content-Type': 'application/json'} +response = requests.request("POST", url, headers=headers, json=payload)
Enhancement	Update the "Actions" row to accurately reflect support across all platforms. Ensure that all relevant platforms or features are marked appropriately in the "Actions" row to maintain accurate documentation. README.md [122] -\| \| Actions \| :white_check_mark: \| \| :white_check_mark: \| \| \| +\| \| Actions \| :white_check_mark: \| :white_check_mark: \| :white_check_mark: \| :white_check_mark: \| :white_check_mark: \|

✨ Improve tool usage guide:

Overview:
The improve tool scans the PR code changes, and automatically generates suggestions for improving the PR code. The tool can be triggered automatically every time a new PR is opened, or can be invoked manually by commenting on a PR.

When commenting, to edit configurations related to the improve tool (pr_code_suggestions section), use the following template:

/improve --pr_code_suggestions.some_config1=... --pr_code_suggestions.some_config2=...

With a configuration file, use the following template:

[pr_code_suggestions]
some_config1=...
some_config2=...

See the improve usage page for a comprehensive guide on using this tool.

barnett-yuxiang · 2024-05-06T09:04:41Z

/describe
--pr_description.generate_ai_title=true
--pr_description.use_description_markers=true

barnett-yuxiang · 2024-05-06T09:05:33Z

/review
--pr_reviewer.extra_instructions="
In the possible issues section, emphasize the following:

Is the code logic efficient?
"

barnett-yuxiang · 2024-05-06T09:06:05Z

/ask Is the code logic efficient?

codiumai-pr-agent-pro · 2024-05-06T09:06:28Z

PR-Agent was enabled for this repository. To continue using it, please link your git user with your CodiumAI identity here.

PR Review 🔍

⏱️ Estimated effort to review [1-5]	4, due to the extensive changes across multiple files and the integration of new functionalities for both Bitbucket and GitHub providers. The logic within these changes is complex, involving URL parsing, API interactions, and conditional logic based on the URL contents.
🏅 Score	75
🧪 Relevant tests	No
⚡ Possible issues	Efficiency Concern: The methods `parse_issue_url_and_get_comments` and `parse_issue_url_and_create_comment` in both provider classes perform URL parsing and API requests every time they are called. This could be inefficient, especially in loops or repeated calls. Consider caching results or restructuring to minimize redundant operations.
⚡ Possible issues	Logic Redundancy: There is a noticeable redundancy in methods across the Bitbucket and GitHub provider classes, such as URL parsing and issue retrieval. This could be streamlined by abstracting common functionalities into a base class or utility functions.
🔒 Security concerns	No

Code feedback:

relevant file	pr_agent/git_providers/bitbucket_provider.py
suggestion	Consider implementing caching for the `parse_issue_url_and_get_comments` method to avoid repeated API calls for the same URL, which can enhance performance and reduce API rate limit consumption. [important]
relevant line	response = requests.request("GET", url, headers=headers, data=payload)

relevant file	pr_agent/git_providers/bitbucket_provider.py
suggestion	Refactor the repeated URL parsing logic in `parse_issue_url_and_get_comments` and other methods into a single method within the class to reduce code duplication and improve maintainability. [important]
relevant line	workspace_slug, repo_name, original_issue_number = self._parse_issue_url(issue_url)

relevant file	pr_agent/git_providers/github_provider.py
suggestion	Abstract common functionalities such as `get_issue_url`, `get_issue_body`, and `get_issue_number` into a base class to be shared between `BitbucketProvider` and `GitHubProvider` to reduce redundancy and improve code maintainability. [important]
relevant line	def get_issue_url(self, issue):

relevant file	pr_agent/git_providers/github_provider.py
suggestion	Optimize the `parse_issue_url_and_get_comments` method by checking if the issue object is already retrieved and use it directly instead of making a new API call. [important]
relevant line	issue = self.repo_obj.get_issue(original_issue_number)

codiumai-pr-agent-pro · 2024-05-06T09:06:36Z

PR-Agent was enabled for this repository. To continue using it, please link your git user with your CodiumAI identity here.

Ask❓

Is the code logic efficient?

Answer:

The code logic in the PR generally appears to be efficient, with a few areas for potential improvement:

Error Handling and URL Parsing:
- The methods _parse_issue_url in both BitbucketProvider and GithubProvider classes are crucial for the functionality of parsing URLs to extract necessary components like repository name and issue number. The error handling in these methods is robust, ensuring that only valid URLs are processed. This is efficient as it prevents unnecessary API calls with invalid data.
API Calls and Data Handling:
- The methods get_issue, parse_issue_url_and_get_comments, and parse_issue_url_and_create_comment in both provider classes handle API interactions. These methods are designed to perform specific tasks such as fetching issues, comments, and posting comments, which are essential for the feature of finding similar issues.
- However, there is a potential inefficiency in how API responses are handled. For example, in the parse_issue_url_and_get_comments method, the entire response is converted to JSON and directly returned. It might be more efficient to parse this response and extract only the necessary data to reduce memory usage and improve processing speed.
Handling of Similar Issues:
- The PRSimilarIssue class handles the logic of finding similar issues based on embeddings. The method _process_issue efficiently extracts necessary data from issues for processing. However, the method run could be optimized by reducing the number of API calls. For instance, the method makes separate calls to fetch an issue and then its comments. Combining these into a single call, if possible, could reduce the overhead.
Use of External Libraries:
- The use of ast.literal_eval in get_issue_numbers_from_list method in BitbucketProvider is potentially risky and might not be the most efficient way to handle type conversion. A safer and more efficient approach could be manually parsing the string to extract integers.
Redundant Code:
- There are some redundancies and inconsistencies, such as the repeated definition of the get_issue_body method in github_provider.py. Streamlining these methods and ensuring that each method is defined once would improve maintainability and potentially increase efficiency.

Overall, the PR introduces several well-structured methods to handle interactions with GitHub and Bitbucket APIs efficiently. However, optimizing API usage, improving data handling, and removing redundant code could further enhance efficiency.

mrT23 · 2024-05-12T13:51:05Z

/improve

codiumai-pr-agent-pro · 2024-05-12T13:51:56Z

PR Code Suggestions ✨

Category	Suggestion	Score
Maintainability	Replace direct access to private attributes with method calls to improve encapsulation and maintainability Replace the direct access to private attributes with a method call or property, to avoid breaking encapsulation and to maintain code maintainability. pr_agent/git_providers/bitbucket_provider.py [42-43] -self.bitbucket_comment_api_url = self.pr._BitbucketBase__data["links"]["comments"]["href"] -self.bitbucket_pull_request_api_url = self.pr._BitbucketBase__data["links"]['self']['href'] +self.bitbucket_comment_api_url = self.pr.get_comment_api_url() +self.bitbucket_pull_request_api_url = self.pr.get_pull_request_api_url() Suggestion importance[1-10]: 8 Why: Accessing private attributes directly can lead to maintenance issues if the class implementation changes. Using getter methods improves encapsulation and maintainability.	8
Maintainability	Refactor code to reduce duplication by introducing a helper function for URL parsing Refactor the method to avoid code duplication by creating a helper function for parsing URLs that can be reused across different methods. pr_agent/git_providers/bitbucket_provider.py [349-350] -workspace_slug, repo_name, original_issue_number = self._parse_issue_url(issue_url) +def extract_workspace_repo(issue_url): + workspace_slug, repo_name, original_issue_number = self._parse_issue_url(issue_url) + return workspace_slug, repo_name +workspace_slug, repo_name = extract_workspace_repo(issue_url) + Suggestion importance[1-10]: 7 Why: Reducing code duplication by creating reusable helper functions improves code maintainability and readability. The suggestion correctly identifies a repetitive pattern that can be abstracted into a function.	7
Robustness	Add error handling for network requests to improve robustness and error reporting Add error handling for the `requests` operations to handle potential network issues or API errors gracefully. pr_agent/git_providers/bitbucket_provider.py [331] -response = requests.request("GET", url, headers=headers, data=payload) +try: + response = requests.request("GET", url, headers=headers, data=payload) + response.raise_for_status() # Raises an HTTPError for bad responses +except requests.exceptions.RequestException as e: + get_logger().error(f"Failed to fetch comments: {e}") + return None Suggestion importance[1-10]: 8 Why: Adding error handling for network requests is crucial to ensure the robustness of the application, especially in a network-dependent feature.	8
Clarity	Use placeholders to clearly indicate unsupported features in the markdown table Add placeholders (e.g., ':x:') for the 'Actions' row to indicate explicitly the absence of support or functionality in certain columns. README.md [122] -\| \| Actions \| :white_check_mark: \| \| :white_check_mark: \| \| \| +\| \| Actions \| :white_check_mark: \| :x: \| :white_check_mark: \| :x: \| :x: \| Suggestion importance[1-10]: 8 Why: This suggestion improves clarity by explicitly marking unsupported features, which is crucial for correct documentation and user understanding.	8
Consistency	Add missing checkmarks to maintain consistency in the markdown table Ensure consistency in the markdown table by adding missing checkmarks or placeholders for the 'Find similar issue' row across all relevant columns. README.md [116] -\| \| Find similar issue \| :white_check_mark: \| \| :white_check_mark: \| \| \| \| +\| \| Find similar issue \| :white_check_mark: \| :white_check_mark: \| :white_check_mark: \| \| \| \| Suggestion importance[1-10]: 7 Why: The suggestion correctly identifies the need for consistency in the markdown table and proposes a valid improvement. However, the exact checkmarks to add should be verified for correctness based on project requirements.	7

sarbjitsinghgrewal added 11 commits September 22, 2023 11:01

Merge branch 'main' of https://github.com/Codium-ai/pr-agent into bit…

7705963

…bucket_similar_issue_feature

Merge branch 'main' of https://github.com/Codium-ai/pr-agent into bit…

91afd29

…bucket_similar_issue_feature

bitbucket similar issue

4cc9ab5

Merge branch 'main' of https://github.com/Codium-ai/pr-agent into bit…

a77bb2c

…bucket_similar_issue_feature

Merge branch 'tr/similar_issue_fix' of https://github.com/Codium-ai/p…

f689b96

…r-agent into bitbucket_similar_issue_feature

similar_issue feature is working for github and bitbucket

733ed90

similar_issue feature is working for github and bitbucket

ec77d5f

Merge branch 'main' of https://github.com/Codium-ai/pr-agent into bit…

bcb1288

…bucket_similar_issue_feature

update github provider for similar issue

7d9885f

update github provider for similar issue

c649564

remove workslug from common file

3010c10

sarbjitsinghgrewal changed the base branch from bitbucket_similar_issue_feature to main October 27, 2023 06:59

sarbjitsinghgrewal added 3 commits October 27, 2023 12:32

Merge branch 'main' of https://github.com/Codium-ai/pr-agent into bit…

e815e54

…bucket_similar_issue_feature

fix issues

cb57bdf

update function names accordingly

f995b3e

github-actions bot added the Review effort [1-5]: 4 label Nov 15, 2023

mrT23 changed the title ~~remove workslug from common file~~ Extend 'similar_issue' feature to support Bitbucket Dec 5, 2023

mrT23 added the enhancement New feature or request label Dec 5, 2023