Compare commits

..

1 Commits

Author SHA1 Message Date
Tal
401dc29dee Update setup.py 2024-12-08 08:47:13 +02:00
67 changed files with 1114 additions and 1671 deletions

2
.gitignore vendored
View File

@ -1,7 +1,6 @@
.idea/
.lsp/
.vscode/
.env
venv/
pr_agent/settings/.secrets.toml
__pycache__
@ -10,4 +9,3 @@ dist/
build/
.DS_Store
docs/.cache/
.qodo

122
README.md
View File

@ -41,25 +41,6 @@ Qode Merge PR-Agent aims to help efficiently review and handle pull requests, by
## News and Updates
### Jan 2, 2025
New tool [/Implement](https://qodo-merge-docs.qodo.ai/tools/implement/) (💎), which converts human code review discussions and feedback into ready-to-commit code changes.
<kbd><img src="https://codium.ai/images/pr_agent/implement1.png" width="512"></kbd>
### Jan 1, 2025
Update logic and [documentation](https://qodo-merge-docs.qodo.ai/usage-guide/changing_a_model/#ollama) for running local models via Ollama.
### December 30, 2024
Following [feedback](https://research.kudelskisecurity.com/2024/08/29/careful-where-you-code-multiple-vulnerabilities-in-ai-powered-pr-agent/) from the community, we have addressed two vulnerabilities identified in the open-source PR-Agent project. The fixes are now included in the newly released version (v0.26), available as of today.
### December 25, 2024
The `review` tool previously included a legacy feature for providing code suggestions (controlled by '--pr_reviewer.num_code_suggestion'). This functionality has been deprecated. Use instead the [`improve`](https://qodo-merge-docs.qodo.ai/tools/improve/) tool, which offers higher quality and more actionable code suggestions.
### December 2, 2024
Open-source repositories can now freely use Qodo Merge Pro, and enjoy easy one-click installation using a marketplace [app](https://github.com/apps/qodo-merge-pro-for-open-source).
@ -90,47 +71,50 @@ Focused mode
<kbd><img src="https://qodo.ai/images/pr_agent/code_suggestions_focused_mode.png" width="512"></kbd>
### November 4, 2024
Qodo Merge PR Agent will now leverage context from Jira or GitHub tickets to enhance the PR Feedback. Read more about this feature
[here](https://qodo-merge-docs.qodo.ai/core-abilities/fetching_ticket_context/)
## Overview
<div style="text-align:left;">
Supported commands per platform:
| | | GitHub | GitLab | Bitbucket | Azure DevOps |
| | | GitHub | Gitlab | Bitbucket | Azure DevOps |
|-------|---------------------------------------------------------------------------------------------------------|:--------------------:|:--------------------:|:--------------------:|:------------:|
| TOOLS | [Review](https://qodo-merge-docs.qodo.ai/tools/review/) | ✅ | ✅ | ✅ | ✅ |
| | [Describe](https://qodo-merge-docs.qodo.ai/tools/describe/) | ✅ | ✅ | ✅ | |
| | [Improve](https://qodo-merge-docs.qodo.ai/tools/improve/) | ✅ | ✅ | ✅ | ✅ |
| | [Ask](https://qodo-merge-docs.qodo.ai/tools/ask/) | ✅ | ✅ | ✅ | ✅ |
| TOOLS | Review | ✅ | ✅ | ✅ | ✅ |
| | ⮑ Incremental | ✅ | | | |
| | Describe | ✅ | ✅ | ✅ | ✅ |
| | ⮑ [Inline File Summary](https://pr-agent-docs.codium.ai/tools/describe#inline-file-summary) 💎 | ✅ | | | |
| | Improve | ✅ | ✅ | ✅ | ✅ |
| | ⮑ Extended | ✅ | ✅ | ✅ | ✅ |
| | Ask | ✅ | ✅ | ✅ | ✅ |
| | ⮑ [Ask on code lines](https://pr-agent-docs.codium.ai/tools/ask#ask-lines) | ✅ | ✅ | | |
| | [Update CHANGELOG](https://qodo-merge-docs.qodo.ai/tools/update_changelog/) | ✅ | ✅ | ✅ | ✅ |
| | [Ticket Context](https://qodo-merge-docs.qodo.ai/core-abilities/fetching_ticket_context/) 💎 | ✅ | ✅ | ✅ | |
| | [Utilizing Best Practices](https://qodo-merge-docs.qodo.ai/tools/improve/#best-practices) 💎 | ✅ | ✅ | ✅ | |
| | [PR Chat](https://qodo-merge-docs.qodo.ai/chrome-extension/features/#pr-chat) 💎 | ✅ | | | |
| | [Suggestion Tracking](https://qodo-merge-docs.qodo.ai/tools/improve/#suggestion-tracking) 💎 | ✅ | ✅ | | |
| | [CI Feedback](https://pr-agent-docs.codium.ai/tools/ci_feedback/) 💎 | ✅ | | | |
| | [PR Documentation](https://pr-agent-docs.codium.ai/tools/documentation/) 💎 | ✅ | ✅ | | |
| | [Custom Labels](https://pr-agent-docs.codium.ai/tools/custom_labels/) 💎 | ✅ | ✅ | | |
| | [Analyze](https://pr-agent-docs.codium.ai/tools/analyze/) 💎 | ✅ | ✅ | | |
| | [Similar Code](https://pr-agent-docs.codium.ai/tools/similar_code/) 💎 | ✅ | | | |
| | [Custom Prompt](https://pr-agent-docs.codium.ai/tools/custom_prompt/) 💎 | ✅ | ✅ | ✅ | |
| | [Test](https://pr-agent-docs.codium.ai/tools/test/) 💎 | ✅ | ✅ | | |
| | [Implement](https://pr-agent-docs.codium.ai/tools/implement/) 💎 | ✅ | ✅ | ✅ | |
| | Reflect and Review | ✅ | ✅ | ✅ | ✅ |
| | Update CHANGELOG.md | ✅ | ✅ | ✅ | ✅ |
| | Find Similar Issue | ✅ | | | |
| | [Add PR Documentation](https://pr-agent-docs.codium.ai/tools/documentation/) 💎 | ✅ | ✅ | | |
| | [Custom Labels](https://pr-agent-docs.codium.ai/tools/custom_labels/) 💎 | ✅ | ✅ | | |
| | [Analyze](https://pr-agent-docs.codium.ai/tools/analyze/) 💎 | ✅ | ✅ | | |
| | [CI Feedback](https://pr-agent-docs.codium.ai/tools/ci_feedback/) 💎 | ✅ | | | |
| | [Similar Code](https://pr-agent-docs.codium.ai/tools/similar_code/) 💎 | ✅ | | | |
| | | | | | |
| USAGE | [CLI](https://qodo-merge-docs.qodo.ai/usage-guide/automations_and_usage/#local-repo-cli) | ✅ | ✅ | ✅ | ✅ |
| | [App / webhook](https://qodo-merge-docs.qodo.ai/usage-guide/automations_and_usage/#github-app) | ✅ | ✅ | ✅ | ✅ |
| | [Tagging bot](https://github.com/Codium-ai/pr-agent#try-it-now) | ✅ | | | |
| | [Actions](https://qodo-merge-docs.qodo.ai/installation/github/#run-as-a-github-action) | ✅ |✅| ✅ |✅|
| USAGE | CLI | ✅ | ✅ | ✅ | ✅ |
| | App / webhook | ✅ | ✅ | ✅ | ✅ |
| | Tagging bot | ✅ | | | |
| | Actions | ✅ |✅| ✅ |✅|
| | | | | | |
| CORE | [PR compression](https://qodo-merge-docs.qodo.ai/core-abilities/compression_strategy/) | ✅ | ✅ | ✅ | ✅ |
| CORE | PR compression | ✅ | ✅ | ✅ | ✅ |
| | Repo language prioritization | ✅ | ✅ | ✅ | ✅ |
| | Adaptive and token-aware file patch fitting | ✅ | ✅ | ✅ | ✅ |
| | [Multiple models support](https://qodo-merge-docs.qodo.ai/usage-guide/changing_a_model/) | ✅ | ✅ | ✅ | ✅ |
| | [Local and global metadata](https://qodo-merge-docs.qodo.ai/core-abilities/metadata/) | ✅ | ✅ | ✅ | |
| | [Dynamic context](https://qodo-merge-docs.qodo.ai/core-abilities/dynamic_context/) | ✅ | ✅ | ✅ | ✅ |
| | [Self reflection](https://qodo-merge-docs.qodo.ai/core-abilities/self_reflection/) | ✅ | ✅ | ✅ | ✅ |
| | [Static code analysis](https://qodo-merge-docs.qodo.ai/core-abilities/static_code_analysis/) 💎 | ✅ | ✅ | ✅ | |
| | Multiple models support | ✅ | ✅ | ✅ | ✅ |
| | [Static code analysis](https://pr-agent-docs.codium.ai/core-abilities/#static-code-analysis) 💎 | ✅ | ✅ | ✅ | |
| | [Global and wiki configurations](https://pr-agent-docs.codium.ai/usage-guide/configuration_options/) 💎 | ✅ | ✅ | ✅ | |
| | [PR interactive actions](https://www.codium.ai/images/pr_agent/pr-actions.mp4) 💎 | ✅ | ✅ | | |
| | [Impact Evaluation](https://qodo-merge-docs.qodo.ai/core-abilities/impact_evaluation/) 💎 | ✅ | ✅ | | |
- 💎 means this feature is available only in [PR-Agent Pro](https://www.codium.ai/pricing/)
[//]: # (- Support for additional git providers is described in [here]&#40;./docs/Full_environments.md&#41;)
@ -154,8 +138,6 @@ ___
\
**Analyze 💎 ([`/analyze`](https://pr-agent-docs.codium.ai/tools/analyze/))**: Identify code components that changed in the PR, and enables to interactively generate tests, docs, and code suggestions for each component.
\
**Test 💎 ([`/test`](https://pr-agent-docs.codium.ai/tools/test/))**: Generate tests for a selected component, based on the PR code changes.
\
**Custom Prompt 💎 ([`/custom_prompt`](https://pr-agent-docs.codium.ai/tools/custom_prompt/))**: Automatically generates custom suggestions for improving the PR code, based on specific guidelines defined by the user.
\
**Generate Tests 💎 ([`/test component_name`](https://pr-agent-docs.codium.ai/tools/test/))**: Generates unit tests for a selected component, based on the PR code changes.
@ -163,8 +145,6 @@ ___
**CI Feedback 💎 ([`/checks ci_job`](https://pr-agent-docs.codium.ai/tools/ci_feedback/))**: Automatically generates feedback and analysis for a failed CI job.
\
**Similar Code 💎 ([`/find_similar_component`](https://pr-agent-docs.codium.ai/tools/similar_code/))**: Retrieves the most similar code components from inside the organization's codebase, or from open-source code.
\
**Implement 💎 ([`/implement`](https://qodo-merge-docs.qodo.ai/tools/implement/))**: Generates implementation code from review suggestions.
___
## Example results
@ -195,8 +175,50 @@ ___
</kbd>
</p>
</div>
<hr>
<h4><a href="https://github.com/Codium-ai/pr-agent/pull/530">/generate_labels</a></h4>
<div align="center">
<p float="center">
<kbd><img src="https://www.codium.ai/images/pr_agent/geneare_custom_labels_main_short.png" width="300"></kbd>
</p>
</div>
[//]: # (<h4><a href="https://github.com/Codium-ai/pr-agent/pull/78#issuecomment-1639739496">/reflect_and_review:</a></h4>)
[//]: # (<div align="center">)
[//]: # (<p float="center">)
[//]: # (<img src="https://www.codium.ai/images/reflect_and_review.gif" width="800">)
[//]: # (</p>)
[//]: # (</div>)
[//]: # (<h4><a href="https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695020538">/ask:</a></h4>)
[//]: # (<div align="center">)
[//]: # (<p float="center">)
[//]: # (<img src="https://www.codium.ai/images/ask-2.gif" width="800">)
[//]: # (</p>)
[//]: # (</div>)
[//]: # (<h4><a href="https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695024952">/improve:</a></h4>)
[//]: # (<div align="center">)
[//]: # (<p float="center">)
[//]: # (<img src="https://www.codium.ai/images/improve-2.gif" width="800">)
[//]: # (</p>)
[//]: # (</div>)
<div align="left">

View File

@ -1,11 +1,11 @@
[Qodo Merge Chrome extension](https://chromewebstore.google.com/detail/pr-agent-chrome-extension/ephlnjeghhogofkifjloamocljapahnl){:target="_blank"} is a collection of tools that integrates seamlessly with your GitHub environment, aiming to enhance your Git usage experience, and providing AI-powered capabilities to your PRs.
[Qodo Merge Chrome extension](https://chromewebstore.google.com/detail/pr-agent-chrome-extension/ephlnjeghhogofkifjloamocljapahnl) is a collection of tools that integrates seamlessly with your GitHub environment, aiming to enhance your Git usage experience, and providing AI-powered capabilities to your PRs.
With a single-click installation you will gain access to a context-aware chat on your pull requests code, a toolbar extension with multiple AI feedbacks, Qodo Merge filters, and additional abilities.
The extension is powered by top code models like Claude 3.5 Sonnet and GPT4. All the extension's features are free to use on public repositories.
For private repositories, you will need to install [Qodo Merge Pro](https://github.com/apps/qodo-merge-pro){:target="_blank"} in addition to the extension (Quick GitHub app setup with a 14-day free trial. No credit card needed).
For a demonstration of how to install Qodo Merge Pro and use it with the Chrome extension, please refer to the tutorial video at the provided [link](https://codium.ai/images/pr_agent/private_repos.mp4){:target="_blank"}.
For private repositories, you will need to install [Qodo Merge Pro](https://github.com/apps/qodo-merge-pro) in addition to the extension (Quick GitHub app setup with a 14-day free trial. No credit card needed).
For a demonstration of how to install Qodo Merge Pro and use it with the Chrome extension, please refer to the tutorial video at the provided [link](https://codium.ai/images/pr_agent/private_repos.mp4).
<img src="https://codium.ai/images/pr_agent/PR-AgentChat.gif" width="768">

View File

@ -1,29 +1,24 @@
# Fetching Ticket Context for PRs
`Supported Git Platforms: GitHub, GitLab, Bitbucket`
`Supported Git Platforms : GitHub, GitLab, Bitbucket`
## Overview
Qodo Merge PR Agent streamlines code review workflows by seamlessly connecting with multiple ticket management systems.
This integration enriches the review process by automatically surfacing relevant ticket information and context alongside code changes.
## Ticket systems supported
- GitHub
- Jira (💎)
## Affected Tools
Ticket Recognition Requirements:
1. The PR description should contain a link to the ticket or if the branch name starts with the ticket id / number.
2. For Jira tickets, you should follow the instructions in [Jira Integration](https://qodo-merge-docs.qodo.ai/core-abilities/fetching_ticket_context/#jira-integration) in order to authenticate with Jira.
Ticket data fetched:
1. Ticket Title
2. Ticket Description
3. Custom Fields (Acceptance criteria)
4. Subtasks (linked tasks)
5. Labels
6. Attached Images/Screenshots
## Affected Tools
Ticket Recognition Requirements:
- The PR description should contain a link to the ticket or if the branch name starts with the ticket id / number.
- For Jira tickets, you should follow the instructions in [Jira Integration](https://qodo-merge-docs.qodo.ai/core-abilities/fetching_ticket_context/#jira-integration) in order to authenticate with Jira.
6. Attached Images/Screenshots 💎
### Describe tool
Qodo Merge PR Agent will recognize the ticket and use the ticket content (title, description, labels) to provide additional context for the code changes.
@ -120,45 +115,9 @@ jira_api_email = "YOUR_EMAIL"
```
#### Jira Data Center/Server 💎
#### Jira Server/Data Center 💎
##### Local App Authentication (For Qodo Merge On-Premise Customers)
##### 1. Step 1: Set up an application link in Jira Data Center/Server
* Go to Jira Administration > Applications > Application Links > Click on `Create link`
![application links](https://www.qodo.ai/images/pr_agent/jira_app_links.png){width=384}
* Choose `External application` and set the direction to `Incoming` and then click `Continue`
![external application](https://www.qodo.ai/images/pr_agent/jira_create_link.png){width=256}
* In the following screen, enter the following details:
* Name: `Qodo Merge`
* Redirect URL: Enter your Qodo Merge URL followed `https://{QODO_MERGE_ENDPOINT}/register_ticket_provider`
* Permission: Select `Read`
* Click `Save`
![external application details](https://www.qodo.ai/images/pr_agent/jira_fill_app_link.png){width=384}
* Copy the `Client ID` and `Client secret` and set them in your `.secrets` file:
![client id and secret](https://www.qodo.ai/images/pr_agent/jira_app_credentionals.png){width=256}
```toml
[jira]
jira_app_secret = "..."
jira_client_id = "..."
```
##### 2. Step 2: Authenticate with Jira Data Center/Server
* Open this URL in your browser: `https://{QODO_MERGE_ENDPOINT}/jira_auth`
* Click on link
![jira auth success](https://www.qodo.ai/images/pr_agent/jira_auth_page.png){width=384}
* You will be redirected to Jira Data Center/Server, click `Allow`
* You will be redirected back to Qodo Merge PR Agent and you will see a success message.
##### Personal Access Token (PAT) Authentication
We also support Personal Access Token (PAT) Authentication method.
Currently, we only support the Personal Access Token (PAT) Authentication method.
1. Create a [Personal Access Token (PAT)](https://confluence.atlassian.com/enterprise/using-personal-access-tokens-1026032365.html) in your Jira account
2. In your Configuration file/Environment variables/Secrets file, add the following lines:

View File

@ -32,14 +32,14 @@ For example, when generating code suggestions for different files, Qodo Merge ca
@@ ... @@ def func1():
__new hunk__
11 unchanged code line0
12 unchanged code line1
13 +new code line2 added
14 unchanged code line3
11 unchanged code line0 in the PR
12 unchanged code line1 in the PR
13 +new code line2 added in the PR
14 unchanged code line3 in the PR
__old hunk__
unchanged code line0
unchanged code line1
-old code line2 removed
-old code line2 removed in the PR
unchanged code line3
@@ ... @@ def func2():

View File

@ -61,7 +61,7 @@ Or be triggered interactively by using the `analyze` tool.
### Find Similar Code
The [`similar code`](https://qodo-merge-docs.qodo.ai/tools/similar_code/) tool retrieves the most similar code components from inside the organization's codebase or from open-source code, including details about the license associated with each repository.
The [`similar code`](https://qodo-merge-docs.qodo.ai/tools/similar_code/) tool retrieves the most similar code components from inside the organization's codebase, or from open-source code.
For example:

View File

@ -1,6 +1,6 @@
# FAQ
??? note "Q: Can Qodo Merge serve as a substitute for a human reviewer?"
??? note "Question: Can Qodo Merge serve as a substitute for a human reviewer?"
#### Answer:<span style="display:none;">1</span>
Qodo Merge is designed to assist, not replace, human reviewers.
@ -12,7 +12,7 @@
1. Preserves user's original PR header
2. Places user's description above the AI-generated PR description
3. Won't approve PRs; approval remains reviewer's responsibility
3. Cannot approve PRs; approval remains reviewer's responsibility
4. The code suggestions are optional, and aim to:
- Encourage self-review and self-reflection
- Highlight potential bugs or oversights
@ -22,15 +22,15 @@
___
??? note "Q: I received an incorrect or irrelevant suggestion. Why?"
??? note "Question: I received an incorrect or irrelevant suggestion. Why?"
#### Answer:<span style="display:none;">2</span>
- Modern AI models, like Claude 3.5 Sonnet and GPT-4, are improving rapidly but remain imperfect. Users should critically evaluate all suggestions rather than accepting them automatically.
- AI errors are rare, but possible. A main value from reviewing the code suggestions lies in their high probability of catching **mistakes or bugs made by the PR author**. We believe it's worth spending 30-60 seconds reviewing suggestions, even if some aren't relevant, as this practice can enhance code quality and prevent bugs in production.
- AI errors are rare, but possible. A main value from reviewing the code suggestions lies in their high probability of catching **mistakes or bugs made by the PR author**. We believe it's worth spending 30-60 seconds reviewing suggestions, even if some aren't relevant, as this practice can enhances code quality and prevent bugs in production.
- The hierarchical structure of the suggestions is designed to help the user _quickly_ understand them, and to decide which ones are relevant and which are not:
- The hierarchical structure of the suggestions is designed to help the user to _quickly_ understand them, and to decide which ones are relevant and which are not:
- Only if the `Category` header is relevant, the user should move to the summarized suggestion description.
- Only if the summarized suggestion description is relevant, the user should click on the collapsible, to read the full suggestion description with a code preview example.
@ -40,14 +40,14 @@ ___
___
??? note "Q: How can I get more tailored suggestions?"
??? note "Question: How can I get more tailored suggestions?"
#### Answer:<span style="display:none;">3</span>
See [here](https://qodo-merge-docs.qodo.ai/tools/improve/#extra-instructions-and-best-practices) for more information on how to use the `extra_instructions` and `best_practices` configuration options, to guide the model to more tailored suggestions.
___
??? note "Q: Will you store my code? Are you using my code to train models?"
??? note "Question: Will you store my code ? Are you using my code to train models?"
#### Answer:<span style="display:none;">4</span>
No. Qodo Merge strict privacy policy ensures that your code is not stored or used for training purposes.
@ -56,35 +56,12 @@ ___
___
??? note "Q: Can I use my own LLM keys with Qodo Merge?"
??? note "Question: Can I use my own LLM keys with Qodo Merge?"
#### Answer:<span style="display:none;">5</span>
When you self-host the [open-source](https://github.com/Codium-ai/pr-agent) version, you use your own keys.
When you self-host, you use your own keys.
Qodo Merge Pro with SaaS deployment is a hosted version of Qodo Merge, where Qodo manages the infrastructure and the keys.
For enterprise customers, on-prem deployment is also available. [Contact us](https://www.codium.ai/contact/#pricing) for more information.
___
??? note "Q: Can Qodo Merge review draft/offline PRs?"
#### Answer:<span style="display:none;">5</span>
Yes. While Qodo Merge won't automatically review draft PRs, you can still get feedback by manually requesting it through [online commenting](https://qodo-merge-docs.qodo.ai/usage-guide/automations_and_usage/#online-usage).
For active PRs, you can customize the automatic feedback settings [here](https://qodo-merge-docs.qodo.ai/usage-guide/automations_and_usage/#qodo-merge-automatic-feedback) to match your team's workflow.
___
??? note "Q: Can the 'Review effort' feedback be calibrated or customized?"
#### Answer:<span style="display:none;">5</span>
Yes, you can customize review effort estimates using the `extra_instructions` configuration option (see [documentation](https://qodo-merge-docs.qodo.ai/tools/review/#configuration-options)).
Example mapping:
- Effort 1: < 30 minutes review time
- Effort 2: 30-60 minutes review time
- Effort 3: 60-90 minutes review time
- ...
Note: The effort levels (1-5) are primarily meant for _comparative_ purposes, helping teams prioritize reviewing smaller PRs first. The actual review duration may vary, as the focus is on providing consistent relative effort estimates.
___

View File

@ -25,44 +25,36 @@ To search the documentation site using natural language:
Qodo Merge offers extensive pull request functionalities across various git providers.
| | | GitHub | GitLab | Bitbucket | Azure DevOps |
|-------|---------------------------------------------------------------------------------------------------------|:--------------------:|:--------------------:|:--------------------:|:------------:|
| TOOLS | [Review](https://qodo-merge-docs.qodo.ai/tools/review/) | ✅ | ✅ | ✅ | ✅ |
| | [Describe](https://qodo-merge-docs.qodo.ai/tools/describe/) | ✅ | ✅ | ✅ | |
| | [Improve](https://qodo-merge-docs.qodo.ai/tools/improve/) | ✅ | ✅ | ✅ | ✅ |
| | [Ask](https://qodo-merge-docs.qodo.ai/tools/ask/) | ✅ | ✅ | ✅ | ✅ |
| | ⮑ [Ask on code lines](https://pr-agent-docs.codium.ai/tools/ask#ask-lines) | ✅ || | |
| | [Update CHANGELOG](https://qodo-merge-docs.qodo.ai/tools/update_changelog/) | ✅ | ✅ | ✅ | ✅ |
| | [Ticket Context](https://qodo-merge-docs.qodo.ai/core-abilities/fetching_ticket_context/) 💎 | ✅ | ✅ || |
| | [Utilizing Best Practices](https://qodo-merge-docs.qodo.ai/tools/improve/#best-practices) 💎 | ✅ | ✅ || |
| | [PR Chat](https://qodo-merge-docs.qodo.ai/chrome-extension/features/#pr-chat) 💎 | ✅ | | | |
| | [Suggestion Tracking](https://qodo-merge-docs.qodo.ai/tools/improve/#suggestion-tracking) 💎 | ✅ | ✅ | | |
| | [CI Feedback](https://pr-agent-docs.codium.ai/tools/ci_feedback/) 💎 | ✅ | | | |
| | [PR Documentation](https://pr-agent-docs.codium.ai/tools/documentation/) 💎 | ✅ | ✅ | | |
| | [Custom Labels](https://pr-agent-docs.codium.ai/tools/custom_labels/) 💎 | ✅ | ✅ | | |
| | [Analyze](https://pr-agent-docs.codium.ai/tools/analyze/) 💎 | ✅ || | |
| | [Similar Code](https://pr-agent-docs.codium.ai/tools/similar_code/) 💎 | ✅ | | | |
| | [Custom Prompt](https://pr-agent-docs.codium.ai/tools/custom_prompt/) 💎 | ✅ | ✅ | ✅ | |
| | [Test](https://pr-agent-docs.codium.ai/tools/test/) 💎 | ✅ | ✅ | | |
| | [Implement](https://pr-agent-docs.codium.ai/tools/implement/) 💎 | ✅ | ✅ | | |
| | | | | | |
| USAGE | [CLI](https://qodo-merge-docs.qodo.ai/usage-guide/automations_and_usage/#local-repo-cli) | ✅ | ✅ | ✅ | ✅ |
| | [App / webhook](https://qodo-merge-docs.qodo.ai/usage-guide/automations_and_usage/#github-app) | ✅ | ✅ | ✅ | ✅ |
| | [Tagging bot](https://github.com/Codium-ai/pr-agent#try-it-now) | ✅ | | | |
| | [Actions](https://qodo-merge-docs.qodo.ai/installation/github/#run-as-a-github-action) | ✅ |✅| ✅ |✅|
| | | | | | |
| CORE | [PR compression](https://qodo-merge-docs.qodo.ai/core-abilities/compression_strategy/) | ✅ | ✅ | ✅ | |
| | Adaptive and token-aware file patch fitting | ✅ | ✅ | ✅ | ✅ |
| | [Multiple models support](https://qodo-merge-docs.qodo.ai/usage-guide/changing_a_model/) | ✅ | ✅ | ✅ | ✅ |
| | [Local and global metadata](https://qodo-merge-docs.qodo.ai/core-abilities/metadata/) | ✅ | ✅ | ✅ | ✅ |
| | [Dynamic context](https://qodo-merge-docs.qodo.ai/core-abilities/dynamic_context/) | ✅ | ✅ | ✅ | ✅ |
| | [Self reflection](https://qodo-merge-docs.qodo.ai/core-abilities/self_reflection/) | ✅ | ✅ | ✅ | ✅ |
| | [Static code analysis](https://qodo-merge-docs.qodo.ai/core-abilities/static_code_analysis/) 💎 | ✅ | ✅ | ✅ | |
| | [Global and wiki configurations](https://pr-agent-docs.codium.ai/usage-guide/configuration_options/) 💎 | ✅ | ✅ | ✅ | |
| | [PR interactive actions](https://www.codium.ai/images/pr_agent/pr-actions.mp4) 💎 | ✅ | ✅ | | |
| | [Impact Evaluation](https://qodo-merge-docs.qodo.ai/core-abilities/impact_evaluation/) 💎 | ✅ | ✅ | | |
| | | GitHub | Gitlab | Bitbucket | Azure DevOps |
|-------|-----------------------------------------------------------------------------------------------------------------------|:------:|:------:|:---------:|:------------:|
| TOOLS | Review | ✅ | ✅ | ✅ | ✅ |
| | ⮑ Incremental | ✅ | | | |
| | Ask | ✅ | ✅ | ✅ | ✅ |
| | Describe | ✅ | ✅ | ✅ | ✅ |
| | ⮑ [Inline file summary](https://qodo-merge-docs.qodo.ai/tools/describe/#inline-file-summary){:target="_blank"} 💎 | ✅ | | | |
| | Improve | ✅ | ✅ | ✅ | ✅ |
| | ⮑ Extended | ✅ | ✅ | | |
| | [Custom Prompt](./tools/custom_prompt.md){:target="_blank"} 💎 | ✅ | ✅ | | |
| | Reflect and Review | ✅ | ✅ | ✅ | |
| | Update CHANGELOG.md | | ✅ | ✅ | |
| | Find Similar Issue | ✅ | | | |
| | [Add PR Documentation](./tools/documentation.md){:target="_blank"} 💎 | ✅ | | | |
| | [Generate Custom Labels](./tools/describe.md#handle-custom-labels-from-the-repos-labels-page-💎){:target="_blank"} 💎 | ✅ | ✅ | | |
| | [Analyze PR Components](./tools/analyze.md){:target="_blank"} 💎 | | | | |
| | | | | | |
| USAGE | CLI | ✅ | ✅ | ✅ | |
| | App / webhook | ✅ | | | |
| | Actions | ✅ | | | |
| | | | | |
| CORE | PR compression | ✅ | ✅ | ✅ | ✅ |
| | Repo language prioritization | ✅ | ✅ | ✅ | ✅ |
| | Adaptive and token-aware file patch fitting | ✅ | ✅ | ✅ | |
| | Multiple models support | ✅ | ✅ | ✅ | ✅ |
| | Incremental PR review | ✅ | | | |
| | [Static code analysis](./tools/analyze.md/){:target="_blank"} 💎 | ✅ | ✅ | ✅ | |
| | [Multiple configuration options](./usage-guide/configuration_options.md){:target="_blank"} 💎 | | | | |
💎 marks a feature available only in [Qodo Merge Pro](https://www.qodo.ai/pricing/){:target="_blank"}
💎 marks a feature available only in [Qodo Merge Pro](https://www.codium.ai/pricing/){:target="_blank"}
## Example Results

View File

@ -3,8 +3,8 @@
## Self-hosted Qodo Merge
If you choose to host your own Qodo Merge, you first need to acquire two tokens:
1. An OpenAI key from [here](https://platform.openai.com/api-keys){:target="_blank"}, with access to GPT-4 (or a key for other [language models](https://qodo-merge-docs.qodo.ai/usage-guide/changing_a_model/), if you prefer).
2. A GitHub\GitLab\BitBucket personal access token (classic), with the repo scope. [GitHub from [here](https://github.com/settings/tokens){:target="_blank"}]
1. An OpenAI key from [here](https://platform.openai.com/api-keys), with access to GPT-4 (or a key for other [language models](https://qodo-merge-docs.qodo.ai/usage-guide/changing_a_model/), if you prefer).
2. A GitHub\GitLab\BitBucket personal access token (classic), with the repo scope. [GitHub from [here](https://github.com/settings/tokens)]
There are several ways to use self-hosted Qodo Merge:

View File

@ -66,30 +66,7 @@ To invoke a tool (for example `review`), you can run directly from the Docker im
docker run --rm -it -e CONFIG.GIT_PROVIDER=bitbucket -e OPENAI.KEY=$OPENAI_API_KEY -e BITBUCKET.BEARER_TOKEN=$BITBUCKET_BEARER_TOKEN codiumai/pr-agent:latest --pr_url=<pr_url> review
```
For other git providers, update `CONFIG.GIT_PROVIDER` accordingly and check the `pr_agent/settings/.secrets_template.toml` file for environment variables expected names and values.
The `pr_agent` uses [Dynaconf](https://www.dynaconf.com/) to load settings from configuration files.
It is also possible to provide or override the configuration by setting the corresponding environment variables.
You can define the corresponding environment variables by following this convention: `<TABLE>__<KEY>=<VALUE>` or `<TABLE>.<KEY>=<VALUE>`.
The `<TABLE>` refers to a table/section in a configuration file and `<KEY>=<VALUE>` refers to the key/value pair of a setting in the configuration file.
For example, suppose you want to run `pr_agent` that connects to a self-hosted GitLab instance similar to an example above.
You can define the environment variables in a plain text file named `.env` with the following content:
> Warning: Never commit the `.env` file to version control system as it might contains sensitive credentials!
```
CONFIG__GIT_PROVIDER="gitlab"
GITLAB__URL="<your url>"
GITLAB__PERSONAL_ACCESS_TOKEN="<your token>"
OPENAI__KEY="<your key>"
```
Then, you can run `pr_agent` using Docker with the following command:
```shell
docker run --rm -it --env-file .env codiumai/pr-agent:latest <tool> <tool parameter>
```
For other git providers, update CONFIG.GIT_PROVIDER accordingly, and check the `pr_agent/settings/.secrets_template.toml` file for the environment variables expected names and values.
---

View File

@ -3,7 +3,7 @@ See [here](https://qodo-merge-docs.qodo.ai/overview/pr_agent_pro/) for more deta
A complimentary two-week trial is provided to all new users. Following the trial period, user licenses (seats) are required for continued access.
To purchase user licenses, please visit our [pricing page](https://www.qodo.ai/pricing/).
Once subscribed, users can seamlessly deploy the application across any of their code repositories.
Once subscribed, users can seamlessly deploy the application across any of their GitHub repositories.
## Install Qodo Merge Pro for GitHub

View File

@ -41,8 +41,6 @@ Qodo Merge offers extensive pull request functionalities across various git prov
| | [Add PR Documentation](./tools/documentation.md){:target="_blank"} 💎 | ✅ | ✅ | | ✅ |
| | [Generate Custom Labels](./tools/describe.md#handle-custom-labels-from-the-repos-labels-page-💎){:target="_blank"} 💎 | ✅ | ✅ | | ✅ |
| | [Analyze PR Components](./tools/analyze.md){:target="_blank"} 💎 | ✅ | ✅ | | ✅ |
| | [Test](https://pr-agent-docs.codium.ai/tools/test/) 💎 | ✅ | ✅ | | |
| | [Implement](https://pr-agent-docs.codium.ai/tools/implement/) 💎 | ✅ | ✅ | ✅ | |
| | | | | | |
| USAGE | CLI | ✅ | ✅ | ✅ | ✅ |
| | App / webhook | ✅ | ✅ | ✅ | ✅ |
@ -53,8 +51,8 @@ Qodo Merge offers extensive pull request functionalities across various git prov
| | Adaptive and token-aware file patch fitting | ✅ | ✅ | ✅ | ✅ |
| | Multiple models support | ✅ | ✅ | ✅ | ✅ |
| | Incremental PR review | ✅ | | | |
| | [Static code analysis](./tools/analyze.md/){:target="_blank"} 💎 | ✅ | ✅ | ✅ | ✅ |
| | [Multiple configuration options](./usage-guide/configuration_options.md){:target="_blank"} 💎 | ✅ | ✅ | ✅ | ✅ |
| | [Static code analysis](./tools/analyze.md/){:target="_blank"} 💎 | ✅ | ✅ | ✅ | ✅ |
| | [Multiple configuration options](./usage-guide/configuration_options.md){:target="_blank"} 💎 | ✅ | ✅ | ✅ | ✅ |
💎 marks a feature available only in [Qodo Merge Pro](https://www.codium.ai/pricing/){:target="_blank"}

View File

@ -1,6 +1,6 @@
### Overview
[Qodo Merge Pro](https://www.codium.ai/pricing/){:target="_blank"} is a hosted version of open-source [Qodo Merge (PR-Agent)](https://github.com/Codium-ai/pr-agent){:target="_blank"}. A complimentary two-week trial is offered, followed by a monthly subscription fee.
[Qodo Merge Pro](https://www.codium.ai/pricing/) is a hosted version of open-source [Qodo Merge (PR-Agent)](https://github.com/Codium-ai/pr-agent). A complimentary two-week trial is offered, followed by a monthly subscription fee.
Qodo Merge Pro is designed for companies and teams that require additional features and capabilities. It provides the following benefits:
1. **Fully managed** - We take care of everything for you - hosting, models, regular updates, and more. Installation is as simple as signing up and adding the Qodo Merge app to your GitHub\GitLab\BitBucket repo.
@ -33,15 +33,14 @@ Here are some of the additional features and capabilities that Qodo Merge Pro of
Here are additional tools that are available only for Qodo Merge Pro users:
| Feature | Description |
|---------------------------------------------------------------------------------------|-------------|
| Feature | Description |
|---------|-------------|
| [**Custom Prompt Suggestions**](https://qodo-merge-docs.qodo.ai/tools/custom_prompt/) | Generate code suggestions based on custom prompts from the user |
| [**Analyze PR components**](https://qodo-merge-docs.qodo.ai/tools/analyze/) | Identify the components that changed in the PR, and enable to interactively apply different tools to them |
| [**Tests**](https://qodo-merge-docs.qodo.ai/tools/test/) | Generate tests for code components that changed in the PR |
| [**PR documentation**](https://qodo-merge-docs.qodo.ai/tools/documentation/) | Generate docstring for code components that changed in the PR |
| [**Improve Component**](https://qodo-merge-docs.qodo.ai/tools/improve_component/) | Generate code suggestions for code components that changed in the PR |
| [**Similar code search**](https://qodo-merge-docs.qodo.ai/tools/similar_code/) | Search for similar code in the repository, organization, or entire GitHub |
| [**Code implementation**](https://qodo-merge-docs.qodo.ai/tools/implement/) | Generates implementation code from review suggestions |
| [**Analyze PR components**](https://qodo-merge-docs.qodo.ai/tools/analyze/) | Identify the components that changed in the PR, and enable to interactively apply different tools to them |
| [**Tests**](https://qodo-merge-docs.qodo.ai/tools/test/) | Generate tests for code components that changed in the PR |
| [**PR documentation**](https://qodo-merge-docs.qodo.ai/tools/documentation/) | Generate docstring for code components that changed in the PR |
| [**Improve Component**](https://qodo-merge-docs.qodo.ai/tools/improve_component/) | Generate code suggestions for code components that changed in the PR |
| [**Similar code search**](https://qodo-merge-docs.qodo.ai/tools/similar_code/) | Search for similar code in the repository, organization, or entire GitHub |
### Supported languages

View File

@ -1,50 +0,0 @@
## Overview
The `implement` tool converts human code review discussions and feedback into ready-to-commit code changes.
It leverages LLM technology to transform PR comments and review suggestions into concrete implementation code, helping developers quickly turn feedback into working solutions.
## Usage Scenarios
### For Reviewers
Reviewers can request code changes by: <br>
1. Selecting the code block to be modified. <br>
2. Adding a comment with the syntax:
```
/implement <code-change-description>
```
![implement1](https://codium.ai/images/pr_agent/implement1.png){width=640}
### For PR Authors
PR authors can implement suggested changes by replying to a review comment using either: <br>
1. Add specific implementation details as described above
```
/implement <code-change-description>
```
2. Use the original review comment as instructions
```
/implement
```
![implement2](https://codium.ai/images/pr_agent/implement2.png){width=640}
### For Referencing Comments
You can reference and implement changes from any comment by:
```
/implement <link-to-review-comment>
```
![implement3](https://codium.ai/images/pr_agent/implement3.png){width=640}
Note that the implementation will occur within the review discussion thread.
**Configuration options** <br>
- Use `/implement` to implement code change within and based on the review discussion. <br>
- Use `/implement <code-change-description>` inside a review discussion to implement specific instructions. <br>
- Use `/implement <link-to-review-comment>` to indirectly call the tool from any comment. <br>

View File

@ -95,112 +95,6 @@ This feature is controlled by a boolean configuration parameter: `pr_code_sugges
Instead, we leverage a dedicated private page, within your repository wiki, to track suggestions. This approach offers convenient secure suggestion tracking while avoiding pull requests or any noise to the main repository.
## `Extra instructions` and `best practices`
The `improve` tool can be further customized by providing additional instructions and best practices to the AI model.
### Extra instructions
>`Platforms supported: GitHub, GitLab, Bitbucket, Azure DevOps`
You can use the `extra_instructions` configuration option to give the AI model additional instructions for the `improve` tool.
Be specific, clear, and concise in the instructions. With extra instructions, you are the prompter.
Examples for possible instructions:
```toml
[pr_code_suggestions]
extra_instructions="""\
(1) Answer in japanese
(2) Don't suggest to add try-except block
(3) Ignore changes in toml files
...
"""
```
Use triple quotes to write multi-line instructions. Use bullet points or numbers to make the instructions more readable.
### Best practices 💎
>`Platforms supported: GitHub, GitLab, Bitbucket`
Another option to give additional guidance to the AI model is by creating a `best_practices.md` file, either in your repository's root directory or as a [**wiki page**](https://github.com/Codium-ai/pr-agent/wiki) (we recommend the wiki page, as editing and maintaining it over time is easier).
This page can contain a list of best practices, coding standards, and guidelines that are specific to your repo/organization.
The AI model will use this wiki page as a reference, and in case the PR code violates any of the guidelines, it will create additional suggestions, with a dedicated label: `Organization
best practice`.
Example for a python `best_practices.md` content:
```markdown
## Project best practices
- Make sure that I/O operations are encapsulated in a try-except block
- Use the `logging` module for logging instead of `print` statements
- Use `is` and `is not` to compare with `None`
- Use `if __name__ == '__main__':` to run the code only when the script is executed
- Use `with` statement to open files
...
```
Tips for writing an effective `best_practices.md` file:
- Write clearly and concisely
- Include brief code examples when helpful
- Focus on project-specific guidelines, that will result in relevant suggestions you actually want to get
- Keep the file relatively short, under 800 lines, since:
- AI models may not process effectively very long documents
- Long files tend to contain generic guidelines already known to AI
#### Local and global best practices
By default, Qodo Merge will look for a local `best_practices.md` wiki file in the root of the relevant local repo.
If you want to enable also a global `best_practices.md` wiki file, set first in the global configuration file:
```toml
[best_practices]
enable_global_best_practices = true
```
Then, create a `best_practices.md` wiki file in the root of [global](https://qodo-merge-docs.qodo.ai/usage-guide/configuration_options/#global-configuration-file) configuration repository, `pr-agent-settings`.
#### Best practices for multiple languages
For a git organization working with multiple programming languages, you can maintain a centralized global `best_practices.md` file containing language-specific guidelines.
When reviewing pull requests, Qodo Merge automatically identifies the programming language and applies the relevant best practices from this file.
To do this, structure your `best_practices.md` file using the following format:
```
# [Python]
...
# [Java]
...
# [JavaScript]
...
```
#### Dedicated label for best practices suggestions
Best practice suggestions are labeled as `Organization best practice` by default.
To customize this label, modify it in your configuration file:
```toml
[best_practices]
organization_name = "..."
```
And the label will be: `{organization_name} best practice`.
#### Example results
![best_practice](https://codium.ai/images/pr_agent/org_best_practice.png){width=512}
### How to combine `extra instructions` and `best practices`
The `extra instructions` configuration is more related to the `improve` tool prompt. It can be used, for example, to avoid specific suggestions ("Don't suggest to add try-except block", "Ignore changes in toml files", ...) or to emphasize specific aspects or formats ("Answer in Japanese", "Give only short suggestions", ...)
In contrast, the `best_practices.md` file is a general guideline for the way code should be written in the repo.
Using a combination of both can help the AI model to provide relevant and tailored suggestions.
## Usage Tips
### Implementing the proposed code suggestions
@ -297,6 +191,99 @@ This approach has two main benefits:
Note: Chunking is primarily relevant for large PRs. For most PRs (up to 500 lines of code), Qodo Merge will be able to process the entire code in a single call.
### 'Extra instructions' and 'best practices'
#### Extra instructions
>`Platforms supported: GitHub, GitLab, Bitbucket`
You can use the `extra_instructions` configuration option to give the AI model additional instructions for the `improve` tool.
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 possible instructions:
```toml
[pr_code_suggestions]
extra_instructions="""\
(1) Answer in japanese
(2) Don't suggest to add try-excpet block
(3) Ignore changes in toml files
...
"""
```
Use triple quotes to write multi-line instructions. Use bullet points or numbers to make the instructions more readable.
#### Best practices 💎
>`Platforms supported: GitHub, GitLab`
Another option to give additional guidance to the AI model is by creating a dedicated [**wiki page**](https://github.com/Codium-ai/pr-agent/wiki) called `best_practices.md`.
This page can contain a list of best practices, coding standards, and guidelines that are specific to your repo/organization.
The AI model will use this wiki page as a reference, and in case the PR code violates any of the guidelines, it will suggest improvements accordingly, with a dedicated label: `Organization
best practice`.
Example for a `best_practices.md` content can be found [here](https://github.com/Codium-ai/pr-agent/blob/main/docs/docs/usage-guide/EXAMPLE_BEST_PRACTICE.md) (adapted from Google's [pyguide](https://google.github.io/styleguide/pyguide.html)).
This file is only an example. Since it is used as a prompt for an AI model, we want to emphasize the following:
- It should be written in a clear and concise manner
- If needed, it should give short relevant code snippets as examples
- Recommended to limit the text to 800 lines or fewer. Heres why:
1) Extremely long best practices documents may not be fully processed by the AI model.
2) A lengthy file probably represent a more "**generic**" set of guidelines, which the AI model is already familiar with. The objective is to focus on a more targeted set of guidelines tailored to the specific needs of this project.
##### Local and global best practices
By default, Qodo Merge will look for a local `best_practices.md` wiki file in the root of the relevant local repo.
If you want to enable also a global `best_practices.md` wiki file, set first in the global configuration file:
```toml
[best_practices]
enable_global_best_practices = true
```
Then, create a `best_practices.md` wiki file in the root of [global](https://qodo-merge-docs.qodo.ai/usage-guide/configuration_options/#global-configuration-file) configuration repository, `pr-agent-settings`.
##### Best practices for multiple languages
For a git organization working with multiple programming languages, you can maintain a centralized global `best_practices.md` file containing language-specific guidelines.
When reviewing pull requests, Qodo Merge automatically identifies the programming language and applies the relevant best practices from this file.
Structure your `best_practices.md` file using the following format:
```
# [Python]
...
# [Java]
...
# [JavaScript]
...
```
##### Dedicated label for best practices suggestions
Best practice suggestions are labeled as `Organization best practice` by default.
To customize this label, modify it in your configuration file:
```toml
[best_practices]
organization_name = ""
```
And the label will be: `{organization_name} best practice`.
##### Example results
![best_practice](https://codium.ai/images/pr_agent/org_best_practice.png){width=512}
#### How to combine `extra instructions` and `best practices`
The `extra instructions` configuration is more related to the `improve` tool prompt. It can be used, for example, to avoid specific suggestions ("Don't suggest to add try-except block", "Ignore changes in toml files", ...) or to emphasize specific aspects or formats ("Answer in Japanese", "Give only short suggestions", ...)
In contrast, the `best_practices.md` file is a general guideline for the way code should be written in the repo.
Using a combination of both can help the AI model to provide relevant and tailored suggestions.
## Configuration options
??? example "General options"
@ -342,10 +329,6 @@ Note: Chunking is primarily relevant for large PRs. For most PRs (up to 500 line
<td><b>wiki_page_accepted_suggestions</b></td>
<td>If set to true, the tool will automatically track accepted suggestions in a dedicated wiki page called `.pr_agent_accepted_suggestions`. Default is true.</td>
</tr>
<tr>
<td><b>allow_thumbs_up_down</b></td>
<td>If set to true, all code suggestions will have thumbs up and thumbs down buttons, to encourage users to provide feedback on the suggestions. Default is false.</td>
</tr>
</table>
??? example "Params for number of suggestions and AI calls"
@ -363,6 +346,10 @@ Note: Chunking is primarily relevant for large PRs. For most PRs (up to 500 line
<td><b>max_number_of_calls</b></td>
<td>Maximum number of chunks. Default is 3.</td>
</tr>
<tr>
<td><b>rank_extended_suggestions</b></td>
<td>If set to true, the tool will rank the suggestions, based on importance. Default is true.</td>
</tr>
</table>
## A note on code suggestions quality

View File

@ -2,22 +2,21 @@
Here is a list of Qodo Merge tools, each with a dedicated page that explains how to use it:
| Tool | Description |
|------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------|
| **[PR Description (`/describe`](./describe.md))** | Automatically generating PR description - title, type, summary, code walkthrough and labels |
| **[PR Review (`/review`](./review.md))** | Adjustable feedback about the PR, possible issues, security concerns, review effort and more |
| **[Code Suggestions (`/improve`](./improve.md))** | Code suggestions for improving the PR |
| **[Question Answering (`/ask ...`](./ask.md))** | Answering free-text questions about the PR, or on specific code lines |
| **[Update Changelog (`/update_changelog`](./update_changelog.md))** | Automatically updating the CHANGELOG.md file with the PR changes |
| **[Find Similar Issue (`/similar_issue`](./similar_issues.md))** | Automatically retrieves and presents similar issues |
| **[Help (`/help`](./help.md))** | Provides a list of all the available tools. Also enables to trigger them interactively (💎) |
| **💎 [Add Documentation (`/add_docs`](./documentation.md))** | Generates documentation to methods/functions/classes that changed in the PR |
| **💎 [Generate Custom Labels (`/generate_labels`](./custom_labels.md))** | Generates custom labels for the PR, based on specific guidelines defined by the user |
| **💎 [Analyze (`/analyze`](./analyze.md))** | Identify code components that changed in the PR, and enables to interactively generate tests, docs, and code suggestions for each component|
| **💎 [Test (`/test`](./test.md))** | generate tests for a selected component, based on the PR code changes |
| **💎 [Custom Prompt (`/custom_prompt`](./custom_prompt.md))** | Automatically generates custom suggestions for improving the PR code, based on specific guidelines defined by the user |
| **💎 [Generate Tests (`/test component_name`](./test.md))** | Automatically generates unit tests for a selected component, based on the PR code changes |
| **💎 [Improve Component (`/improve_component component_name`](./improve_component.md))** | Generates code suggestions for a specific code component that changed in the PR |
| **💎 [CI Feedback (`/checks ci_job`](./ci_feedback.md))** | Automatically generates feedback and analysis for a failed CI job |
| **💎 [Implement (`/implement`](./implement.md))** | Generates implementation code from review suggestions |
| Tool | Description |
|------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------|
| **[PR Description (`/describe`](./describe.md))** | Automatically generating PR description - title, type, summary, code walkthrough and labels |
| **[PR Review (`/review`](./review.md))** | Adjustable feedback about the PR, possible issues, security concerns, review effort and more |
| **[Code Suggestions (`/improve`](./improve.md))** | Code suggestions for improving the PR |
| **[Question Answering (`/ask ...`](./ask.md))** | Answering free-text questions about the PR, or on specific code lines |
| **[Update Changelog (`/update_changelog`](./update_changelog.md))** | Automatically updating the CHANGELOG.md file with the PR changes |
| **[Find Similar Issue (`/similar_issue`](./similar_issues.md))** | Automatically retrieves and presents similar issues |
| **[Help (`/help`](./help.md))** | Provides a list of all the available tools. Also enables to trigger them interactively (💎) |
| **💎 [Add Documentation (`/add_docs`](./documentation.md))** | Generates documentation to methods/functions/classes that changed in the PR |
| **💎 [Generate Custom Labels (`/generate_labels`](./custom_labels.md))** | Generates custom labels for the PR, based on specific guidelines defined by the user |
| **💎 [Analyze (`/analyze`](./analyze.md))** | Identify code components that changed in the PR, and enables to interactively generate tests, docs, and code suggestions for each component |
| **💎 [Custom Prompt (`/custom_prompt`](./custom_prompt.md))** | Automatically generates custom suggestions for improving the PR code, based on specific guidelines defined by the user |
| **💎 [Generate Tests (`/test component_name`](./test.md))** | Automatically generates unit tests for a selected component, based on the PR code changes |
| **💎 [Improve Component (`/improve_component component_name`](./improve_component.md))** | Generates code suggestions for a specific code component that changed in the PR |
| **💎 [CI Feedback (`/checks ci_job`](./ci_feedback.md))** | Automatically generates feedback and analysis for a failed CI job |
Note that the tools marked with 💎 are available only for Qodo Merge Pro users.

View File

@ -39,13 +39,54 @@ pr_commands = [
]
[pr_reviewer]
extra_instructions = "..."
num_code_suggestions = ...
...
```
- The `pr_commands` lists commands that will be executed automatically when a PR is opened.
- The `[pr_reviewer]` section contains the configurations for the `review` tool you want to edit (if any).
[//]: # ()
[//]: # (### Incremental Mode)
[//]: # (Incremental review only considers changes since the last Qodo Merge review. This can be useful when working on the PR in an iterative manner, and you want to focus on the changes since the last review instead of reviewing the entire PR again.)
[//]: # (For invoking the incremental mode, the following command can be used:)
[//]: # (```)
[//]: # (/review -i)
[//]: # (```)
[//]: # (Note that the incremental mode is only available for GitHub.)
[//]: # ()
[//]: # (![incremental review]&#40;https://codium.ai/images/pr_agent/incremental_review_2.png&#41;{width=512})
[//]: # (### PR Reflection)
[//]: # ()
[//]: # (By invoking:)
[//]: # (```)
[//]: # (/reflect_and_review)
[//]: # (```)
[//]: # (The tool will first ask the author questions about the PR, and will guide the review based on their answers.)
[//]: # ()
[//]: # (![reflection questions]&#40;https://codium.ai/images/pr_agent/reflection_questions.png&#41;{width=512})
[//]: # ()
[//]: # (![reflection answers]&#40;https://codium.ai/images/pr_agent/reflection_answers.png&#41;{width=512})
[//]: # ()
[//]: # (![reflection insights]&#40;https://codium.ai/images/pr_agent/reflection_insights.png&#41;{width=512})
## Configuration options
@ -53,12 +94,16 @@ extra_instructions = "..."
<table>
<tr>
<td><b>persistent_comment</b></td>
<td>If set to true, the review comment will be persistent, meaning that every new review request will edit the previous one. Default is true.</td>
<td><b>num_code_suggestions</b></td>
<td>Number of code suggestions provided by the 'review' tool. Default is 0, meaning no code suggestions will be provided by the `review` tool.</td>
</tr>
<tr>
<td><b>final_update_message</b></td>
<td>When set to true, updating a persistent review comment during online commenting will automatically add a short comment with a link to the updated review in the pull request .Default is true.</td>
<td><b>inline_code_comments</b></td>
<td>If set to true, the tool will publish the code suggestions as comments on the code diff. Default is false. Note that you need to set `num_code_suggestions`>0 to get code suggestions </td>
</tr>
<tr>
<td><b>persistent_comment</b></td>
<td>If set to true, the review comment will be persistent, meaning that every new review request will edit the previous one. Default is true.</td>
</tr>
<tr>
<td><b>extra_instructions</b></td>
@ -144,9 +189,9 @@ If enabled, the `review` tool can approve a PR when a specific comment, `/review
!!! tip "Automation"
When you first install Qodo Merge app, the [default mode](../usage-guide/automations_and_usage.md#github-app-automatic-tools-when-a-new-pr-is-opened) for the `review` tool is:
```
pr_commands = ["/review", ...]
pr_commands = ["/review --pr_reviewer.num_code_suggestions=0", ...]
```
Meaning the `review` tool will run automatically on every PR, without any additional configurations.
Meaning the `review` tool will run automatically on every PR, without providing code suggestions.
Edit this field to enable/disable the tool, or to change the configurations used.
!!! tip "Possible labels from the review tool"
@ -204,8 +249,12 @@ If enabled, the `review` tool can approve a PR when a specific comment, `/review
maximal_review_effort = 5
```
!!! tip "Code suggestions"
[//]: # (!!! tip "Code suggestions")
The `review` tool previously included a legacy feature for providing code suggestions (controlled by `--pr_reviewer.num_code_suggestion`). This functionality has been deprecated and replaced by the [`improve`](./improve.md) tool, which offers higher quality and more actionable code suggestions.
[//]: # ()
[//]: # ( If you set `num_code_suggestions`>0 , the `review` tool will also provide code suggestions.)
[//]: # ( )
[//]: # ( Notice If you are interested **only** in the code suggestions, it is recommended to use the [`improve`]&#40;./improve.md&#41; feature instead, since it is a dedicated only to code suggestions, and usually gives better results.)
[//]: # ( Use the `review` tool if you want to get more comprehensive feedback, which includes code suggestions as well.)

View File

@ -49,10 +49,9 @@ It can be invoked automatically from the analyze table, can be accessed by:
/analyze
```
Choose the components you want to find similar code for, and click on the `similar` checkbox.
![analyze similar](https://codium.ai/images/pr_agent/analyze_similar.png){width=768}
You can search for similar code either within the organization's codebase or globally, which includes open-source repositories. Each result will include the relevant code components along with their associated license details.
If you are looking to search for similar code in the organization's codebase, you can click on the `Organization` checkbox, and it will invoke a new search command just for the organization's codebase.
![similar code global](https://codium.ai/images/pr_agent/similar_code_global.png){width=768}

View File

@ -17,8 +17,8 @@ The tool will generate tests for the selected component (if no component is stat
(Example taken from [here](https://github.com/Codium-ai/pr-agent/pull/598#issuecomment-1913679429)):
**Notes** <br>
- The following languages are currently supported: Python, Java, C++, JavaScript, TypeScript, C#. <br>
**Notes**
- Language that are currently supported by the tool: Python, Java, C++, JavaScript, TypeScript, C#.
- This tool can also be triggered interactively by using the [`analyze`](./analyze.md) tool.

View File

@ -17,4 +17,3 @@ Under the section `pr_update_changelog`, the [configuration file](https://github
- `push_changelog_changes`: whether to push the changes to CHANGELOG.md, or just print them. Default is false (print only).
- `extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...
- `add_pr_link`: whether the model should try to add a link to the PR in the changelog. Default is true.

View File

@ -1,5 +1,5 @@
## Show possible configurations
The possible configurations of Qodo Merge are stored in [here](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml){:target="_blank"}.
The possible configurations of Qodo Merge are stored in [here](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml).
In the [tools](https://qodo-merge-docs.qodo.ai/tools/) page you can find explanations on how to use these configurations for each tool.
To print all the available configurations as a comment on your PR, you can use the following command:
@ -138,17 +138,7 @@ LANGSMITH_BASE_URL=<url>
## Ignoring automatic commands in PRs
Qodo Merge allows you to automatically ignore certain PRs based on various criteria:
- PRs with specific titles (using regex matching)
- PRs between specific branches (using regex matching)
- PRs that don't include changes from specific folders (using regex matching)
- PRs containing specific labels
- PRs opened by specific users
### Example usage
#### Ignoring PRs with specific titles
In some cases, you may want to automatically ignore specific PRs . Qodo Merge enables you to ignore PR with a specific title, or from/to specific branches (regex matching).
To ignore PRs with a specific title such as "[Bump]: ...", you can add the following to your `configuration.toml` file:
@ -159,7 +149,6 @@ ignore_pr_title = ["\\[Bump\\]"]
Where the `ignore_pr_title` is a list of regex patterns to match the PR title you want to ignore. Default is `ignore_pr_title = ["^\\[Auto\\]", "^Auto"]`.
#### Ignoring PRs between specific branches
To ignore PRs from specific source or target branches, you can add the following to your `configuration.toml` file:
@ -172,7 +161,6 @@ ignore_pr_target_branches = ["qa"]
Where the `ignore_pr_source_branches` and `ignore_pr_target_branches` are lists of regex patterns to match the source and target branches you want to ignore.
They are not mutually exclusive, you can use them together or separately.
#### Ignoring PRs that don't include changes from specific folders
To allow only specific folders (often needed in large monorepos), set:
@ -182,35 +170,3 @@ allow_only_specific_folders=['folder1','folder2']
```
For the configuration above, automatic feedback will only be triggered when the PR changes include files from 'folder1' or 'folder2'
#### Ignoring PRs containg specific labels
To ignore PRs containg specific labels, you can add the following to your `configuration.toml` file:
```
[config]
ignore_pr_labels = ["do-not-merge"]
```
Where the `ignore_pr_labels` is a list of labels that when present in the PR, the PR will be ignored.
#### Ignoring PRs from specific users
Qodo Merge automatically identifies and ignores pull requests created by bots using:
- GitHub's native bot detection system
- Name-based pattern matching
While this detection is robust, it may not catch all cases, particularly when:
- Bots are registered as regular user accounts
- Bot names don't match common patterns
To supplement the automatic bot detection, you can manually specify users to ignore. Add the following to your `configuration.toml` file to ignore PRs from specific users:
```
[config]
ignore_pr_authors = ["my-special-bot-user", ...]
```
Where the `ignore_pr_authors` is a list of usernames that you want to ignore.

View File

@ -1,5 +1,4 @@
## Local repo (CLI)
When running from your locally cloned Qodo Merge repo (CLI), your local configuration file will be used.
Examples of invoking the different tools via the CLI:
@ -36,29 +35,9 @@ This is useful for debugging or experimenting with different tools.
Default is "github".
### CLI Health Check
To verify that Qodo Merge has been configured correctly, you can run this health check command from the repository root:
```bash
python -m tests.health_test.main
```
If the health check passes, you will see the following output:
```
========
Health test passed successfully
========
```
At the end of the run.
Before running the health check, ensure you have:
- Configured your [LLM provider](https://qodo-merge-docs.qodo.ai/usage-guide/changing_a_model/)
- Added a valid GitHub token to your configuration file
## Online usage
### Online usage
Online usage means invoking Qodo Merge tools by [comments](https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695021901) on a PR.
Commands for invoking the different tools via comments:
@ -78,11 +57,7 @@ For example, if you want to edit the `review` tool configurations, you can run:
```
Any configuration value in [configuration file](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml) file can be similarly edited. Comment `/config` to see the list of available configurations.
## Qodo Merge Automatic Feedback
### Disabling all automatic feedback
## Disabling automatic feedback
To easily disable all automatic feedback from Qodo Merge (GitHub App, GitLab Webhook, BitBucket App, Azure DevOps Webhook), set in a configuration file:
@ -91,52 +66,46 @@ To easily disable all automatic feedback from Qodo Merge (GitHub App, GitLab Web
disable_auto_feedback = true
```
When this parameter is set to `true`, Qodo Merge will not run any automatic tools (like `describe`, `review`, `improve`) when a new PR is opened, or when new code is pushed to an open PR.
### GitHub App
## GitHub App
!!! note "Configurations for Qodo Merge Pro"
Qodo Merge Pro for GitHub is an App, hosted by CodiumAI. So all the instructions below are relevant also for Qodo Merge Pro users.
Same goes for [GitLab webhook](#gitlab-webhook) and [BitBucket App](#bitbucket-app) sections.
#### GitHub app automatic tools when a new PR is opened
### GitHub app automatic tools when a new PR is opened
The [github_app](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L220) section defines GitHub app specific configurations.
The [github_app](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L108) section defines GitHub app specific configurations.
The configuration parameter `pr_commands` defines the list of tools that will be **run automatically** when a new PR is opened:
The configuration parameter `pr_commands` defines the list of tools that will be **run automatically** when a new PR is opened.
```toml
[github_app]
pr_commands = [
"/describe",
"/review",
"/improve",
"/improve --pr_code_suggestions.suggestions_score_threshold=5",
]
```
This means that when a new PR is opened/reopened or marked as ready for review, Qodo Merge will run the `describe`, `review` and `improve` tools.
For the `improve` tool, for example, the `suggestions_score_threshold` parameter will be set to 5 (suggestions below a score of 5 won't be presented)
You can override the default tool parameters by using one the three options for a [configuration file](https://qodo-merge-docs.qodo.ai/usage-guide/configuration_options/): **wiki**, **local**, or **global**.
For example, if your configuration file contains:
For example, if your local `.pr_agent.toml` file contains:
```toml
[pr_description]
generate_ai_title = true
```
Every time you run the `describe` tool, including automatic runs, the PR title will be generated by the AI.
Every time you run the `describe` tool (including automatic runs) the PR title will be generated by the AI.
You can customize configurations specifically for automated runs by using the `--config_path=<value>` parameter.
For instance, to modify the `review` tool settings only for newly opened PRs, use:
To change which tools will run automatically when a new PR is opened, you can set the `pr_commands` parameter in the configuration file.
```toml
[github_app]
pr_commands = [
"/describe",
"/review --pr_reviewer.extra_instructions='focus on the file: ...'",
"/improve",
]
pr_commands = ["describe", "review"]
```
#### GitHub app automatic tools for push actions (commits to an open PR)
In this case, only the `describe` and `review` tools will run automatically when a new PR is opened.
### GitHub app automatic tools for push actions (commits to an open PR)
In addition to running automatic tools when a PR is opened, the GitHub app can also respond to new code that is pushed to an open PR.
@ -152,7 +121,7 @@ push_commands = [
```
This means that when new code is pushed to the PR, the Qodo Merge will run the `describe` and `review` tools, with the specified parameters.
### GitHub Action
## GitHub Action
`GitHub Action` is a different way to trigger Qodo Merge tools, and uses a different configuration mechanism than `GitHub App`.<br>
You can configure settings for `GitHub Action` by adding environment variables under the env section in `.github/workflows/pr_agent.yml` file.
Specifically, start by setting the following environment variables:
@ -163,7 +132,7 @@ Specifically, start by setting the following environment variables:
github_action_config.auto_review: "true" # enable\disable auto review
github_action_config.auto_describe: "true" # enable\disable auto describe
github_action_config.auto_improve: "true" # enable\disable auto improve
github_action_config.pr_actions: '["opened", "reopened", "ready_for_review", "review_requested"]'
github_action_config.pr_actions: ["opened", "reopened", "ready_for_review", "review_requested"]
```
`github_action_config.auto_review`, `github_action_config.auto_describe` and `github_action_config.auto_improve` are used to enable/disable automatic tools that run when a new PR is opened.
If not set, the default configuration is for all three tools to run automatically when a new PR is opened.
@ -186,7 +155,7 @@ publish_labels = false
to prevent Qodo Merge from publishing labels when running the `describe` tool.
### GitLab Webhook
## GitLab Webhook
After setting up a GitLab webhook, to control which commands will run automatically when a new MR is opened, you can set the `pr_commands` parameter in the configuration file, similar to the GitHub App:
```toml
@ -212,7 +181,7 @@ push_commands = [
Note that to use the 'handle_push_trigger' feature, you need to give the gitlab webhook also the "Push events" scope.
### BitBucket App
## BitBucket App
Similar to GitHub app, when running Qodo Merge from BitBucket App, the default [configuration file](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml) from a pre-built docker will be initially loaded.
By uploading a local `.pr_agent.toml` file to the root of the repo's main branch, you can edit and customize any configuration parameter. Note that you need to upload `.pr_agent.toml` prior to creating a PR, in order for the configuration to take effect.
@ -231,7 +200,7 @@ If you experience a lack of responses from Qodo Merge, you might want to set: `b
This will prevent Qodo Merge from acquiring the full file content, and will only use the diff content. This will reduce the number of requests made to BitBucket, at the cost of small decrease in accuracy, as dynamic context will not be applicable.
#### BitBucket Self-Hosted App automatic tools
### BitBucket Self-Hosted App automatic tools
To control which commands will run automatically when a new PR is opened, you can set the `pr_commands` parameter in the configuration file:
Specifically, set the following values:
@ -256,7 +225,7 @@ push_commands = [
]
```
### Azure DevOps provider
## Azure DevOps provider
To use Azure DevOps provider use the following settings in configuration.toml:
```toml
@ -278,14 +247,14 @@ org = "https://dev.azure.com/YOUR_ORGANIZATION/"
# pat = "YOUR_PAT_TOKEN" needed only if using PAT for authentication
```
#### Azure DevOps Webhook
### Azure DevOps Webhook
To control which commands will run automatically when a new PR is opened, you can set the `pr_commands` parameter in the configuration file, similar to the GitHub App:
```toml
[azure_devops_server]
pr_commands = [
"/describe",
"/review",
"/review --pr_reviewer.num_code_suggestions=0",
"/improve",
]
```

View File

@ -5,6 +5,7 @@ To use a different model than the default (GPT-4), you need to edit in the [conf
```
[config]
model = "..."
model_turbo = "..."
fallback_models = ["..."]
```
@ -26,43 +27,57 @@ deployment_id = "" # The deployment name you chose when you deployed the engine
and set in your configuration file:
```
[config]
model="" # the OpenAI model you've deployed on Azure (e.g. gpt-4o)
fallback_models=["..."]
model="" # the OpenAI model you've deployed on Azure (e.g. gpt-3.5-turbo)
model_turbo="" # the OpenAI model you've deployed on Azure (e.g. gpt-3.5-turbo)
fallback_models=["..."] # the OpenAI model you've deployed on Azure (e.g. gpt-3.5-turbo)
```
### Ollama
You can run models locally through either [VLLM](https://docs.litellm.ai/docs/providers/vllm) or [Ollama](https://docs.litellm.ai/docs/providers/ollama)
E.g. to use a new model locally via Ollama, set in `.secrets.toml` or in a configuration file:
```
[config]
model = "ollama/qwen2.5-coder:32b"
fallback_models=["ollama/qwen2.5-coder:32b"]
custom_model_max_tokens=128000 # set the maximal input tokens for the model
duplicate_examples=true # will duplicate the examples in the prompt, to help the model to generate structured output
[ollama]
api_base = "http://localhost:11434" # or whatever port you're running Ollama on
```
!!! note "Local models vs commercial models"
Qodo Merge is compatible with almost any AI model, but analyzing complex code repositories and pull requests requires a model specifically optimized for code analysis.
Commercial models such as GPT-4, Claude Sonnet, and Gemini have demonstrated robust capabilities in generating structured output for code analysis tasks with large input. In contrast, most open-source models currently available (as of January 2025) face challenges with these complex tasks.
Based on our testing, local open-source models are suitable for experimentation and learning purposes, but they are not suitable for production-level code analysis tasks.
Hence, for production workflows and real-world usage, we recommend using commercial models.
### Hugging Face
**Local**
You can run Hugging Face models locally through either [VLLM](https://docs.litellm.ai/docs/providers/vllm) or [Ollama](https://docs.litellm.ai/docs/providers/ollama)
E.g. to use a new Hugging Face model locally via Ollama, set:
```
[__init__.py]
MAX_TOKENS = {
"model-name-on-ollama": <max_tokens>
}
e.g.
MAX_TOKENS={
...,
"ollama/llama2": 4096
}
[config] # in configuration.toml
model = "ollama/llama2"
model_turbo = "ollama/llama2"
fallback_models=["ollama/llama2"]
[ollama] # in .secrets.toml
api_base = ... # the base url for your Hugging Face inference endpoint
# e.g. if running Ollama locally, you may use:
api_base = "http://localhost:11434/"
```
### Inference Endpoints
To use a new model with Hugging Face Inference Endpoints, for example, set:
```
[__init__.py]
MAX_TOKENS = {
"model-name-on-huggingface": <max_tokens>
}
e.g.
MAX_TOKENS={
...,
"meta-llama/Llama-2-7b-chat-hf": 4096
}
[config] # in configuration.toml
model = "huggingface/meta-llama/Llama-2-7b-chat-hf"
model_turbo = "huggingface/meta-llama/Llama-2-7b-chat-hf"
fallback_models=["huggingface/meta-llama/Llama-2-7b-chat-hf"]
custom_model_max_tokens=... # set the maximal input tokens for the model
[huggingface] # in .secrets.toml
key = ... # your Hugging Face api key
@ -76,6 +91,7 @@ To use Llama2 model with Replicate, for example, set:
```
[config] # in configuration.toml
model = "replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1"
model_turbo = "replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1"
fallback_models=["replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1"]
[replicate] # in .secrets.toml
key = ...
@ -91,6 +107,7 @@ To use Llama3 model with Groq, for example, set:
```
[config] # in configuration.toml
model = "llama3-70b-8192"
model_turbo = "llama3-70b-8192"
fallback_models = ["groq/llama3-70b-8192"]
[groq] # in .secrets.toml
key = ... # your Groq api key
@ -104,6 +121,7 @@ To use Google's Vertex AI platform and its associated models (chat-bison/codecha
```
[config] # in configuration.toml
model = "vertex_ai/codechat-bison"
model_turbo = "vertex_ai/codechat-bison"
fallback_models="vertex_ai/codechat-bison"
[vertexai] # in .secrets.toml
@ -122,6 +140,7 @@ To use [Google AI Studio](https://aistudio.google.com/) models, set the relevant
```toml
[config] # in configuration.toml
model="google_ai_studio/gemini-1.5-flash"
model_turbo="google_ai_studio/gemini-1.5-flash"
fallback_models=["google_ai_studio/gemini-1.5-flash"]
[google_ai_studio] # in .secrets.toml
@ -137,6 +156,7 @@ To use Anthropic models, set the relevant models in the configuration section of
```
[config]
model="anthropic/claude-3-opus-20240229"
model_turbo="anthropic/claude-3-opus-20240229"
fallback_models=["anthropic/claude-3-opus-20240229"]
```
@ -153,6 +173,7 @@ To use Amazon Bedrock and its foundational models, add the below configuration:
```
[config] # in configuration.toml
model="bedrock/anthropic.claude-3-sonnet-20240229-v1:0"
model_turbo="bedrock/anthropic.claude-3-sonnet-20240229-v1:0"
fallback_models=["bedrock/anthropic.claude-v2:1"]
```
@ -166,25 +187,6 @@ drop_params = true
AWS session is automatically authenticated from your environment, but you can also explicitly set `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY` and `AWS_REGION_NAME` environment variables. Please refer to [this document](https://litellm.vercel.app/docs/providers/bedrock) for more details.
### DeepSeek
To use deepseek-chat model with DeepSeek, for example, set:
```toml
[config] # in configuration.toml
model = "deepseek/deepseek-chat"
fallback_models=["deepseek/deepseek-chat"]
```
and fill up your key
```toml
[deepseek] # in .secrets.toml
key = ...
```
(you can obtain a deepseek-chat key from [here](https://platform.deepseek.com))
### Custom models
If the relevant model doesn't appear [here](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/algo/__init__.py), you can still use it as a custom model:
@ -193,6 +195,7 @@ If the relevant model doesn't appear [here](https://github.com/Codium-ai/pr-agen
```
[config]
model="custom_model_name"
model_turbo="custom_model_name"
fallback_models=["custom_model_name"]
```
(2) Set the maximal tokens for the model:

View File

@ -1,24 +0,0 @@
`Supported Git Platforms: GitHub, GitLab, Bitbucket`
For optimal functionality of Qodo Merge, we recommend enabling a wiki for each repository where Qodo Merge is installed. The wiki serves several important purposes:
**Key Wiki Features:**
- Storing a [configuration file](https://qodo-merge-docs.qodo.ai/usage-guide/configuration_options/#wiki-configuration-file)
- Defining a [`best_practices.md`](https://qodo-merge-docs.qodo.ai/tools/improve/#best-practices) file
- Track [accepted suggestions](https://qodo-merge-docs.qodo.ai/tools/improve/#suggestion-tracking)
- Facilitates learning over time by creating an [auto_best_practices.md]() file
**Setup Instructions (GitHub):**
To enable a wiki for your repository:
1. Navigate to your repository's main page on GitHub
2. Select "Settings" from the top navigation bar
3. Locate the "Features" section
4. Enable the "Wikis" option by checking the corresponding box
5. Return to your repository's main page
6. Look for the newly added "Wiki" tab in the top navigation
7. Initialize your wiki by clicking "Create the first page" (this step is important - without creating an initial page, the wiki will not be fully functional)

View File

@ -5,7 +5,6 @@ It includes information on how to adjust Qodo Merge configurations, define which
- [Introduction](./introduction.md)
- [Enabling a Wiki](./enabling_a_wiki)
- [Configuration File](./configuration_options.md)
- [Usage and Automation](./automations_and_usage.md)
- [Local Repo (CLI)](./automations_and_usage.md#local-repo-cli)

View File

@ -2,7 +2,7 @@
After [installation](https://qodo-merge-docs.qodo.ai/installation/), there are three basic ways to invoke Qodo Merge:
1. Locally running a CLI command
2. Online usage - by [commenting](https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695021901){:target="_blank"} on a PR
2. Online usage - by [commenting](https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695021901) on a PR
3. Enabling Qodo Merge tools to run automatically when a new PR is opened

View File

@ -18,7 +18,6 @@ nav:
- Usage Guide:
- 'usage-guide/index.md'
- Introduction: 'usage-guide/introduction.md'
- Enabling a Wiki: 'usage-guide/enabling_a_wiki.md'
- Configuration File: 'usage-guide/configuration_options.md'
- Usage and Automation: 'usage-guide/automations_and_usage.md'
- Managing Mail Notifications: 'usage-guide/mail_notifications.md'
@ -42,7 +41,6 @@ nav:
- 💎 Custom Prompt: 'tools/custom_prompt.md'
- 💎 CI Feedback: 'tools/ci_feedback.md'
- 💎 Similar Code: 'tools/similar_code.md'
- 💎 Implement: 'tools/implement.md'
- Core Abilities:
- 'core-abilities/index.md'
- Fetching ticket context: 'core-abilities/fetching_ticket_context.md'

View File

@ -13,6 +13,7 @@ from pr_agent.tools.pr_config import PRConfig
from pr_agent.tools.pr_description import PRDescription
from pr_agent.tools.pr_generate_labels import PRGenerateLabels
from pr_agent.tools.pr_help_message import PRHelpMessage
from pr_agent.tools.pr_information_from_user import PRInformationFromUser
from pr_agent.tools.pr_line_questions import PR_LineQuestions
from pr_agent.tools.pr_questions import PRQuestions
from pr_agent.tools.pr_reviewer import PRReviewer
@ -24,6 +25,8 @@ command2class = {
"answer": PRReviewer,
"review": PRReviewer,
"review_pr": PRReviewer,
"reflect": PRInformationFromUser,
"reflect_and_review": PRInformationFromUser,
"describe": PRDescription,
"describe_pr": PRDescription,
"improve": PRCodeSuggestions,
@ -46,6 +49,7 @@ commands = list(command2class.keys())
class PRAgent:
def __init__(self, ai_handler: partial[BaseAiHandler,] = LiteLLMAIHandler):
self.ai_handler = ai_handler # will be initialized in run_action
self.forbidden_cli_args = ['enable_auto_approval']
async def handle_request(self, pr_url, request, notify=None) -> bool:
# First, apply repo specific settings if exists
@ -60,33 +64,24 @@ class PRAgent:
else:
action, *args = request
forbidden_cli_args = ['enable_auto_approval', 'approve_pr_on_self_review', 'base_url', 'url', 'app_name', 'secret_provider',
'git_provider', 'skip_keys', 'openai.key', 'ANALYTICS_FOLDER', 'uri', 'app_id', 'webhook_secret',
'bearer_token', 'PERSONAL_ACCESS_TOKEN', 'override_deployment_type', 'private_key',
'local_cache_path', 'enable_local_cache', 'jira_base_url', 'api_base', 'api_type', 'api_version',
'skip_keys']
if args:
for arg in args:
if arg.startswith('--'):
arg_word = arg.lower()
arg_word = arg_word.replace('__', '.') # replace double underscore with dot, e.g. --openai__key -> --openai.key
for forbidden_arg in forbidden_cli_args:
forbidden_arg_word = forbidden_arg.lower()
if '.' not in forbidden_arg_word:
forbidden_arg_word = '.' + forbidden_arg_word
if forbidden_arg_word in arg_word:
get_logger().error(
f"CLI argument for param '{forbidden_arg}' is forbidden. Use instead a configuration file."
)
return False
for forbidden_arg in self.forbidden_cli_args:
for arg in args:
if forbidden_arg in arg:
get_logger().error(
f"CLI argument for param '{forbidden_arg}' is forbidden. Use instead a configuration file."
)
return False
args = update_settings_from_args(args)
action = action.lstrip("/").lower()
if action not in command2class:
get_logger().error(f"Unknown command: {action}")
get_logger().debug(f"Unknown command: {action}")
return False
with get_logger().contextualize(command=action, pr_url=pr_url):
get_logger().info("PR-Agent request handler started", analytics=True)
if action == "reflect_and_review":
get_settings().pr_reviewer.ask_and_reflect = True
if action == "answer":
if notify:
notify()

View File

@ -24,12 +24,9 @@ MAX_TOKENS = {
'o1-mini-2024-09-12': 128000, # 128K, but may be limited by config.max_model_tokens
'o1-preview': 128000, # 128K, but may be limited by config.max_model_tokens
'o1-preview-2024-09-12': 128000, # 128K, but may be limited by config.max_model_tokens
'o1-2024-12-17': 204800, # 200K, but may be limited by config.max_model_tokens
'o1': 204800, # 200K, but may be limited by config.max_model_tokens
'claude-instant-1': 100000,
'claude-2': 100000,
'command-nightly': 4096,
'deepseek/deepseek-chat': 128000, # 128K, but may be limited by config.max_model_tokens
'replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1': 4096,
'meta-llama/Llama-2-7b-chat-hf': 4096,
'vertex_ai/codechat-bison': 6144,
@ -42,11 +39,9 @@ MAX_TOKENS = {
'vertex_ai/claude-3-5-sonnet-v2@20241022': 100000,
'vertex_ai/gemini-1.5-pro': 1048576,
'vertex_ai/gemini-1.5-flash': 1048576,
'vertex_ai/gemini-2.0-flash-exp': 1048576,
'vertex_ai/gemma2': 8200,
'gemini/gemini-1.5-pro': 1048576,
'gemini/gemini-1.5-flash': 1048576,
'gemini/gemini-2.0-flash-exp': 1048576,
'codechat-bison': 6144,
'codechat-bison-32k': 32000,
'anthropic.claude-instant-v1': 100000,
@ -64,14 +59,13 @@ MAX_TOKENS = {
'bedrock/anthropic.claude-3-5-haiku-20241022-v1:0': 100000,
'bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0': 100000,
'bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0': 100000,
"bedrock/us.anthropic.claude-3-5-sonnet-20241022-v2:0": 100000,
'claude-3-5-sonnet': 100000,
'groq/llama3-8b-8192': 8192,
'groq/llama3-70b-8192': 8192,
'groq/llama-3.1-8b-instant': 8192,
'groq/llama-3.3-70b-versatile': 128000,
'groq/mixtral-8x7b-32768': 32768,
'groq/gemma2-9b-it': 8192,
'groq/llama-3.1-8b-instant': 131072,
'groq/llama-3.1-70b-versatile': 131072,
'groq/llama-3.1-405b-reasoning': 131072,
'ollama/llama3': 4096,
'watsonx/meta-llama/llama-3-8b-instruct': 4096,
"watsonx/meta-llama/llama-3-70b-instruct": 4096,

View File

@ -7,7 +7,6 @@ from litellm import acompletion
from tenacity import retry, retry_if_exception_type, stop_after_attempt
from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
from pr_agent.algo.utils import get_version
from pr_agent.config_loader import get_settings
from pr_agent.log import get_logger
@ -90,10 +89,6 @@ class LiteLLMAIHandler(BaseAiHandler):
if get_settings().get("GOOGLE_AI_STUDIO.GEMINI_API_KEY", None):
os.environ["GEMINI_API_KEY"] = get_settings().google_ai_studio.gemini_api_key
# Support deepseek models
if get_settings().get("DEEPSEEK.KEY", None):
os.environ['DEEPSEEK_API_KEY'] = get_settings().get("DEEPSEEK.KEY")
def prepare_logs(self, response, system, user, resp, finish_reason):
response_log = response.dict().copy()
response_log['system'] = system
@ -137,7 +132,7 @@ class LiteLLMAIHandler(BaseAiHandler):
if "langfuse" in callbacks:
metadata.update({
"trace_name": command,
"tags": [git_provider, command, f'version:{get_version()}'],
"tags": [git_provider, command],
"trace_metadata": {
"command": command,
"pr_url": pr_url,
@ -146,7 +141,7 @@ class LiteLLMAIHandler(BaseAiHandler):
if "langsmith" in callbacks:
metadata.update({
"run_name": command,
"tags": [git_provider, command, f'version:{get_version()}'],
"tags": [git_provider, command],
"extra": {
"metadata": {
"command": command,
@ -197,8 +192,8 @@ class LiteLLMAIHandler(BaseAiHandler):
messages[1]["content"] = [{"type": "text", "text": messages[1]["content"]},
{"type": "image_url", "image_url": {"url": img_path}}]
# Currently, model OpenAI o1 series does not support a separate system and user prompts
O1_MODEL_PREFIX = 'o1'
# Currently O1 does not support separate system and user prompts
O1_MODEL_PREFIX = 'o1-'
model_type = model.split('/')[-1] if '/' in model else model
if model_type.startswith(O1_MODEL_PREFIX):
user = f"{system}\n\n\n{user}"

View File

@ -364,51 +364,48 @@ __old hunk__
def extract_hunk_lines_from_patch(patch: str, file_name, line_start, line_end, side) -> tuple[str, str]:
try:
patch_with_lines_str = f"\n\n## File: '{file_name.strip()}'\n\n"
selected_lines = ""
patch_lines = patch.splitlines()
RE_HUNK_HEADER = re.compile(
r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
match = None
start1, size1, start2, size2 = -1, -1, -1, -1
skip_hunk = False
selected_lines_num = 0
for line in patch_lines:
if 'no newline at end of file' in line.lower():
continue
if line.startswith('@@'):
skip_hunk = False
selected_lines_num = 0
header_line = line
patch_with_lines_str = f"\n\n## File: '{file_name.strip()}'\n\n"
selected_lines = ""
patch_lines = patch.splitlines()
RE_HUNK_HEADER = re.compile(
r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
match = None
start1, size1, start2, size2 = -1, -1, -1, -1
skip_hunk = False
selected_lines_num = 0
for line in patch_lines:
if 'no newline at end of file' in line.lower():
continue
match = RE_HUNK_HEADER.match(line)
if line.startswith('@@'):
skip_hunk = False
selected_lines_num = 0
header_line = line
section_header, size1, size2, start1, start2 = extract_hunk_headers(match)
match = RE_HUNK_HEADER.match(line)
section_header, size1, size2, start1, start2 = extract_hunk_headers(match)
# check if line range is in this hunk
if side.lower() == 'left':
# check if line range is in this hunk
if side.lower() == 'left':
# check if line range is in this hunk
if not (start1 <= line_start <= start1 + size1):
skip_hunk = True
continue
elif side.lower() == 'right':
if not (start2 <= line_start <= start2 + size2):
skip_hunk = True
continue
patch_with_lines_str += f'\n{header_line}\n'
if not (start1 <= line_start <= start1 + size1):
skip_hunk = True
continue
elif side.lower() == 'right':
if not (start2 <= line_start <= start2 + size2):
skip_hunk = True
continue
patch_with_lines_str += f'\n{header_line}\n'
elif not skip_hunk:
if side.lower() == 'right' and line_start <= start2 + selected_lines_num <= line_end:
selected_lines += line + '\n'
if side.lower() == 'left' and start1 <= selected_lines_num + start1 <= line_end:
selected_lines += line + '\n'
patch_with_lines_str += line + '\n'
if not line.startswith('-'): # currently we don't support /ask line for deleted lines
selected_lines_num += 1
except Exception as e:
get_logger().error(f"Failed to extract hunk lines from patch: {e}", artifact={"traceback": traceback.format_exc()})
return "", ""
elif not skip_hunk:
if side.lower() == 'right' and line_start <= start2 + selected_lines_num <= line_end:
selected_lines += line + '\n'
if side.lower() == 'left' and start1 <= selected_lines_num + start1 <= line_end:
selected_lines += line + '\n'
patch_with_lines_str += line + '\n'
if not line.startswith('-'): # currently we don't support /ask line for deleted lines
selected_lines_num += 1
return patch_with_lines_str.rstrip(), selected_lines.rstrip()

View File

@ -11,7 +11,7 @@ from pr_agent.algo.git_patch_processing import (
from pr_agent.algo.language_handler import sort_files_by_main_languages
from pr_agent.algo.token_handler import TokenHandler
from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo
from pr_agent.algo.utils import ModelType, clip_tokens, get_max_tokens, get_weak_model
from pr_agent.algo.utils import ModelType, clip_tokens, get_max_tokens
from pr_agent.config_loader import get_settings
from pr_agent.git_providers.git_provider import GitProvider
from pr_agent.log import get_logger
@ -205,11 +205,10 @@ def pr_generate_extended_diff(pr_languages: list,
if not extended_patch:
get_logger().warning(f"Failed to extend patch for file: {file.filename}")
continue
full_extended_patch = f"\n\n## {file.filename}\n{extended_patch.rstrip()}\n"
if add_line_numbers_to_hunks:
full_extended_patch = convert_to_hunks_with_lines_numbers(extended_patch, file)
else:
full_extended_patch = f"\n\n## File: '{file.filename.strip()}'\n{extended_patch.rstrip()}\n"
# add AI-summary metadata to the patch
if file.ai_file_summary and get_settings().get("config.enable_ai_metadata", False):
@ -317,13 +316,13 @@ def generate_full_patch(convert_hunks_to_line_numbers, file_dict, max_tokens_mod
# TODO: Option for alternative logic to remove hunks from the patch to reduce the number of tokens
# until we meet the requirements
if get_settings().config.verbosity_level >= 2:
get_logger().warning(f"Patch too large, skipping it: '{filename}'")
get_logger().warning(f"Patch too large, skipping it, {filename}")
remaining_files_list_new.append(filename)
continue
if patch:
if not convert_hunks_to_line_numbers:
patch_final = f"\n\n## File: '{filename.strip()}'\n\n{patch.strip()}\n"
patch_final = f"\n\n## File: '{filename.strip()}\n\n{patch.strip()}\n'"
else:
patch_final = "\n\n" + patch.strip()
patches.append(patch_final)
@ -355,8 +354,8 @@ async def retry_with_fallback_models(f: Callable, model_type: ModelType = ModelT
def _get_all_models(model_type: ModelType = ModelType.REGULAR) -> List[str]:
if model_type == ModelType.WEAK:
model = get_weak_model()
if model_type == ModelType.TURBO:
model = get_settings().config.model_turbo
else:
model = get_settings().config.model
fallback_models = get_settings().config.fallback_models

View File

@ -1,6 +1,5 @@
from dataclasses import dataclass
from enum import Enum
from typing import Optional
class EDIT_TYPE(Enum):
@ -22,5 +21,4 @@ class FilePatchInfo:
old_filename: str = None
num_plus_lines: int = -1
num_minus_lines: int = -1
language: Optional[str] = None
ai_file_summary: str = None

View File

@ -7,13 +7,11 @@ import html
import json
import os
import re
import sys
import textwrap
import time
import traceback
from datetime import datetime
from enum import Enum
from importlib.metadata import PackageNotFoundError, version
from typing import Any, List, Tuple
import html2text
@ -23,19 +21,12 @@ from pydantic import BaseModel
from starlette_context import context
from pr_agent.algo import MAX_TOKENS
from pr_agent.algo.git_patch_processing import extract_hunk_lines_from_patch
from pr_agent.algo.token_handler import TokenEncoder
from pr_agent.algo.types import FilePatchInfo
from pr_agent.config_loader import get_settings, global_settings
from pr_agent.log import get_logger
def get_weak_model() -> str:
if get_settings().get("config.model_weak"):
return get_settings().config.model_weak
return get_settings().config.model
class Range(BaseModel):
line_start: int # should be 0-indexed
line_end: int
@ -44,7 +35,8 @@ class Range(BaseModel):
class ModelType(str, Enum):
REGULAR = "regular"
WEAK = "weak"
TURBO = "turbo"
class PRReviewHeader(str, Enum):
REGULAR = "## PR Reviewer Guide"
@ -105,8 +97,7 @@ def unique_strings(input_list: List[str]) -> List[str]:
def convert_to_markdown_v2(output_data: dict,
gfm_supported: bool = True,
incremental_review=None,
git_provider=None,
files=None) -> str:
git_provider=None) -> str:
"""
Convert a dictionary of data into markdown format.
Args:
@ -230,13 +221,9 @@ def convert_to_markdown_v2(output_data: dict,
continue
relevant_file = issue.get('relevant_file', '').strip()
issue_header = issue.get('issue_header', '').strip()
if issue_header.lower() == 'possible bug':
issue_header = 'Possible Issue' # Make the header less frightening
issue_content = issue.get('issue_content', '').strip()
start_line = int(str(issue.get('start_line', 0)).strip())
end_line = int(str(issue.get('end_line', 0)).strip())
relevant_lines_str = extract_relevant_lines_str(end_line, files, relevant_file, start_line, dedent=True)
if git_provider:
reference_link = git_provider.get_line_link(relevant_file, start_line, end_line)
else:
@ -244,10 +231,7 @@ def convert_to_markdown_v2(output_data: dict,
if gfm_supported:
if reference_link is not None and len(reference_link) > 0:
if relevant_lines_str:
issue_str = f"<details><summary><a href='{reference_link}'><strong>{issue_header}</strong></a>\n\n{issue_content}</summary>\n\n{relevant_lines_str}\n\n</details>"
else:
issue_str = f"<a href='{reference_link}'><strong>{issue_header}</strong></a><br>{issue_content}"
issue_str = f"<a href='{reference_link}'><strong>{issue_header}</strong></a><br>{issue_content}"
else:
issue_str = f"<strong>{issue_header}</strong><br>{issue_content}"
else:
@ -271,49 +255,25 @@ def convert_to_markdown_v2(output_data: dict,
if gfm_supported:
markdown_text += "</table>\n"
if 'code_feedback' in output_data:
if gfm_supported:
markdown_text += f"\n\n"
markdown_text += f"<details><summary> <strong>Code feedback:</strong></summary>\n\n"
markdown_text += "<hr>"
else:
markdown_text += f"\n\n### Code feedback:\n\n"
for i, value in enumerate(output_data['code_feedback']):
if value is None or value == '' or value == {} or value == []:
continue
markdown_text += parse_code_suggestion(value, i, gfm_supported)+"\n\n"
if markdown_text.endswith('<hr>'):
markdown_text= markdown_text[:-4]
if gfm_supported:
markdown_text += f"</details>"
return markdown_text
def extract_relevant_lines_str(end_line, files, relevant_file, start_line, dedent=False) -> str:
"""
Finds 'relevant_file' in 'files', and extracts the lines from 'start_line' to 'end_line' string from the file content.
"""
try:
relevant_lines_str = ""
if files:
files = set_file_languages(files)
for file in files:
if file.filename.strip() == relevant_file:
if not file.head_file:
# as a fallback, extract relevant lines directly from patch
patch = file.patch
get_logger().info(f"No content found in file: '{file.filename}' for 'extract_relevant_lines_str'. Using patch instead")
_, selected_lines = extract_hunk_lines_from_patch(patch, file.filename, start_line, end_line,side='right')
if not selected_lines:
get_logger().error(f"Failed to extract relevant lines from patch: {file.filename}")
return ""
# filter out '-' lines
relevant_lines_str = ""
for line in selected_lines.splitlines():
if line.startswith('-'):
continue
relevant_lines_str += line[1:] + '\n'
else:
relevant_file_lines = file.head_file.splitlines()
relevant_lines_str = "\n".join(relevant_file_lines[start_line - 1:end_line])
if dedent and relevant_lines_str:
# Remove the longest leading string of spaces and tabs common to all lines.
relevant_lines_str = textwrap.dedent(relevant_lines_str)
relevant_lines_str = f"```{file.language}\n{relevant_lines_str}\n```"
break
return relevant_lines_str
except Exception as e:
get_logger().exception(f"Failed to extract relevant lines: {e}")
return ""
def ticket_markdown_logic(emoji, markdown_text, value, gfm_supported) -> str:
ticket_compliance_str = ""
final_compliance_level = -1
@ -583,22 +543,27 @@ def load_large_diff(filename, new_file_content_str: str, original_file_content_s
"""
Generate a patch for a modified file by comparing the original content of the file with the new content provided as
input.
"""
if not original_file_content_str and not new_file_content_str:
return ""
Args:
new_file_content_str: The new content of the file as a string.
original_file_content_str: The original content of the file as a string.
Returns:
The generated or provided patch string.
Raises:
None.
"""
patch = ""
try:
original_file_content_str = (original_file_content_str or "").rstrip() + "\n"
new_file_content_str = (new_file_content_str or "").rstrip() + "\n"
diff = difflib.unified_diff(original_file_content_str.splitlines(keepends=True),
new_file_content_str.splitlines(keepends=True))
if get_settings().config.verbosity_level >= 2 and show_warning:
get_logger().info(f"File was modified, but no patch was found. Manually creating patch: {filename}.")
get_logger().warning(f"File was modified, but no patch was found. Manually creating patch: {filename}.")
patch = ''.join(diff)
return patch
except Exception as e:
get_logger().exception(f"Failed to generate patch for file: {filename}")
return ""
except Exception:
pass
return patch
def update_settings_from_args(args: List[str]) -> List[str]:
@ -1141,48 +1106,3 @@ def process_description(description_full: str) -> Tuple[str, List]:
get_logger().exception(f"Failed to process description: {e}")
return base_description_str, files
def get_version() -> str:
# First check pyproject.toml if running directly out of repository
if os.path.exists("pyproject.toml"):
if sys.version_info >= (3, 11):
import tomllib
with open("pyproject.toml", "rb") as f:
data = tomllib.load(f)
if "project" in data and "version" in data["project"]:
return data["project"]["version"]
else:
get_logger().warning("Version not found in pyproject.toml")
else:
get_logger().warning("Unable to determine local version from pyproject.toml")
# Otherwise get the installed pip package version
try:
return version('pr-agent')
except PackageNotFoundError:
get_logger().warning("Unable to find package named 'pr-agent'")
return "unknown"
def set_file_languages(diff_files) -> List[FilePatchInfo]:
try:
# if the language is already set, do not change it
if hasattr(diff_files[0], 'language') and diff_files[0].language:
return diff_files
# map file extensions to programming languages
language_extension_map_org = get_settings().language_extension_map_org
extension_to_language = {}
for language, extensions in language_extension_map_org.items():
for ext in extensions:
extension_to_language[ext] = language
for file in diff_files:
extension_s = '.' + file.filename.rsplit('.')[-1]
language_name = "txt"
if extension_s and (extension_s in extension_to_language):
language_name = extension_to_language[extension_s]
file.language = language_name.lower()
except Exception as e:
get_logger().exception(f"Failed to set file languages: {e}")
return diff_files

View File

@ -3,7 +3,6 @@ import asyncio
import os
from pr_agent.agent.pr_agent import PRAgent, commands
from pr_agent.algo.utils import get_version
from pr_agent.config_loader import get_settings
from pr_agent.log import get_logger, setup_logger
@ -46,7 +45,6 @@ def set_parser():
To edit any configuration parameter from 'configuration.toml', just add -config_path=<value>.
For example: 'python cli.py --pr_url=... review --pr_reviewer.extra_instructions="focus on the file: ..."'
""")
parser.add_argument('--version', action='version', version=f'pr-agent {get_version()}')
parser.add_argument('--pr_url', type=str, help='The URL of the PR to review', default=None)
parser.add_argument('--issue_url', type=str, help='The URL of the Issue to review', default=None)
parser.add_argument('command', type=str, help='The', choices=commands, default='review')
@ -77,8 +75,6 @@ def run(inargs=None, args=None):
async def inner():
if args.issue_url:
result = await asyncio.create_task(PRAgent().handle_request(args.issue_url, [command] + args.rest))
elif args.repo_url:
result = await asyncio.create_task(PRAgent().handle_request(args.repo_url, [command] + args.rest))
else:
result = await asyncio.create_task(PRAgent().handle_request(args.pr_url, [command] + args.rest))

View File

@ -12,6 +12,7 @@ global_settings = Dynaconf(
envvar_prefix=False,
merge_enabled=True,
settings_files=[join(current_dir, f) for f in [
"settings/.secrets.toml",
"settings/configuration.toml",
"settings/ignore.toml",
"settings/language_extensions.toml",
@ -28,7 +29,6 @@ global_settings = Dynaconf(
"settings/pr_add_docs.toml",
"settings/custom_labels.toml",
"settings/pr_help_prompts.toml",
"settings/.secrets.toml",
"settings_prod/.secrets.toml",
]]
)

View File

@ -326,13 +326,13 @@ class AzureDevopsProvider(GitProvider):
edit_type = EDIT_TYPE.ADDED
elif diff_types[file] == "delete":
edit_type = EDIT_TYPE.DELETED
elif "rename" in diff_types[file]: # diff_type can be `rename` | `edit, rename`
elif diff_types[file] == "rename":
edit_type = EDIT_TYPE.RENAMED
version = GitVersionDescriptor(
version=base_sha.commit_id, version_type="commit"
)
if edit_type == EDIT_TYPE.ADDED or edit_type == EDIT_TYPE.RENAMED:
if edit_type == EDIT_TYPE.ADDED:
original_file_content_str = ""
else:
try:

View File

@ -402,21 +402,10 @@ class BitbucketServerProvider(GitProvider):
try:
projects_index = path_parts.index("projects")
except ValueError:
projects_index = -1
try:
users_index = path_parts.index("users")
except ValueError:
users_index = -1
if projects_index == -1 and users_index == -1:
except ValueError as e:
raise ValueError(f"The provided URL '{pr_url}' does not appear to be a Bitbucket PR URL")
if projects_index != -1:
path_parts = path_parts[projects_index:]
else:
path_parts = path_parts[users_index:]
path_parts = path_parts[projects_index:]
if len(path_parts) < 6 or path_parts[2] != "repos" or path_parts[4] != "pull-requests":
raise ValueError(
@ -424,8 +413,6 @@ class BitbucketServerProvider(GitProvider):
)
workspace_slug = path_parts[1]
if users_index != -1:
workspace_slug = f"~{workspace_slug}"
repo_slug = path_parts[3]
try:
pr_number = int(path_parts[5])

View File

@ -19,7 +19,7 @@ from ..algo.language_handler import is_valid_file
from ..algo.types import EDIT_TYPE
from ..algo.utils import (PRReviewHeader, Range, clip_tokens,
find_line_number_of_relevant_line_in_file,
load_large_diff, set_file_languages)
load_large_diff)
from ..config_loader import get_settings
from ..log import get_logger
from ..servers.utils import RateLimitExceeded
@ -174,24 +174,6 @@ class GithubProvider(GitProvider):
diff_files = []
invalid_files_names = []
is_close_to_rate_limit = False
# The base.sha will point to the current state of the base branch (including parallel merges), not the original base commit when the PR was created
# We can fix this by finding the merge base commit between the PR head and base branches
# Note that The pr.head.sha is actually correct as is - it points to the latest commit in your PR branch.
# This SHA isn't affected by parallel merges to the base branch since it's specific to your PR's branch.
repo = self.repo_obj
pr = self.pr
try:
compare = repo.compare(pr.base.sha, pr.head.sha) # communication with GitHub
merge_base_commit = compare.merge_base_commit
except Exception as e:
get_logger().error(f"Failed to get merge base commit: {e}")
merge_base_commit = pr.base
if merge_base_commit.sha != pr.base.sha:
get_logger().info(
f"Using merge base commit {merge_base_commit.sha} instead of base commit ")
counter_valid = 0
for file in files:
if not is_valid_file(file.filename):
@ -199,36 +181,48 @@ class GithubProvider(GitProvider):
continue
patch = file.patch
if is_close_to_rate_limit:
# allow only a limited number of files to be fully loaded. We can manage the rest with diffs only
counter_valid += 1
avoid_load = False
if counter_valid >= MAX_FILES_ALLOWED_FULL and patch and not self.incremental.is_incremental:
avoid_load = True
if counter_valid == MAX_FILES_ALLOWED_FULL:
get_logger().info(f"Too many files in PR, will avoid loading full content for rest of files")
if avoid_load:
new_file_content_str = ""
original_file_content_str = ""
else:
# allow only a limited number of files to be fully loaded. We can manage the rest with diffs only
counter_valid += 1
avoid_load = False
if counter_valid >= MAX_FILES_ALLOWED_FULL and patch and not self.incremental.is_incremental:
avoid_load = True
if counter_valid == MAX_FILES_ALLOWED_FULL:
get_logger().info(f"Too many files in PR, will avoid loading full content for rest of files")
new_file_content_str = self._get_pr_file_content(file, self.pr.head.sha) # communication with GitHub
if self.incremental.is_incremental and self.unreviewed_files_set:
original_file_content_str = self._get_pr_file_content(file, self.incremental.last_seen_commit_sha)
patch = load_large_diff(file.filename, new_file_content_str, original_file_content_str)
self.unreviewed_files_set[file.filename] = patch
else:
if avoid_load:
new_file_content_str = ""
original_file_content_str = ""
else:
new_file_content_str = self._get_pr_file_content(file, self.pr.head.sha) # communication with GitHub
# The base.sha will point to the current state of the base branch (including parallel merges), not the original base commit when the PR was created
# We can fix this by finding the merge base commit between the PR head and base branches
# Note that The pr.head.sha is actually correct as is - it points to the latest commit in your PR branch.
# This SHA isn't affected by parallel merges to the base branch since it's specific to your PR's branch.
repo = self.repo_obj
pr = self.pr
try:
compare = repo.compare(pr.base.sha, pr.head.sha)
merge_base_commit = compare.merge_base_commit
except Exception as e:
get_logger().error(f"Failed to get merge base commit: {e}")
merge_base_commit = pr.base
if merge_base_commit.sha != pr.base.sha:
get_logger().info(
f"Using merge base commit {merge_base_commit.sha} instead of base commit "
f"{pr.base.sha} for {file.filename}")
original_file_content_str = self._get_pr_file_content(file, merge_base_commit.sha)
if self.incremental.is_incremental and self.unreviewed_files_set:
original_file_content_str = self._get_pr_file_content(file, self.incremental.last_seen_commit_sha)
if not patch:
patch = load_large_diff(file.filename, new_file_content_str, original_file_content_str)
self.unreviewed_files_set[file.filename] = patch
else:
if avoid_load:
original_file_content_str = ""
else:
original_file_content_str = self._get_pr_file_content(file, merge_base_commit.sha)
# original_file_content_str = self._get_pr_file_content(file, self.pr.base.sha)
if not patch:
patch = load_large_diff(file.filename, new_file_content_str, original_file_content_str)
if file.status == 'added':
edit_type = EDIT_TYPE.ADDED
@ -243,14 +237,9 @@ class GithubProvider(GitProvider):
edit_type = EDIT_TYPE.UNKNOWN
# count number of lines added and removed
if hasattr(file, 'additions') and hasattr(file, 'deletions'):
num_plus_lines = file.additions
num_minus_lines = file.deletions
else:
patch_lines = patch.splitlines(keepends=True)
num_plus_lines = len([line for line in patch_lines if line.startswith('+')])
num_minus_lines = len([line for line in patch_lines if line.startswith('-')])
patch_lines = patch.splitlines(keepends=True)
num_plus_lines = len([line for line in patch_lines if line.startswith('+')])
num_minus_lines = len([line for line in patch_lines if line.startswith('-')])
file_patch_canonical_structure = FilePatchInfo(original_file_content_str, new_file_content_str, patch,
file.filename, edit_type=edit_type,
num_plus_lines=num_plus_lines,
@ -900,7 +889,18 @@ class GithubProvider(GitProvider):
RE_HUNK_HEADER = re.compile(
r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
diff_files = set_file_languages(diff_files)
# map file extensions to programming languages
language_extension_map_org = get_settings().language_extension_map_org
extension_to_language = {}
for language, extensions in language_extension_map_org.items():
for ext in extensions:
extension_to_language[ext] = language
for file in diff_files:
extension_s = '.' + file.filename.rsplit('.')[-1]
language_name = "txt"
if extension_s and (extension_s in extension_to_language):
language_name = extension_to_language[extension_s]
file.language = language_name.lower()
for suggestion in code_suggestions_copy:
try:

View File

@ -141,18 +141,6 @@ class LocalGitProvider(GitProvider):
def remove_comment(self, comment):
pass # Not applicable to the local git provider, but required by the interface
def add_eyes_reaction(self, comment):
pass # Not applicable to the local git provider, but required by the interface
def get_commit_messages(self):
pass # Not applicable to the local git provider, but required by the interface
def get_repo_settings(self):
pass # Not applicable to the local git provider, but required by the interface
def remove_reaction(self, comment):
pass # Not applicable to the local git provider, but required by the interface
def get_languages(self):
"""
Calculate percentage of languages in repository. Used for hunk prioritisation.

View File

@ -99,5 +99,5 @@ def set_claude_model():
"""
model_claude = "bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0"
get_settings().set('config.model', model_claude)
get_settings().set('config.model_weak', model_claude)
get_settings().set('config.model_turbo', model_claude)
get_settings().set('config.fallback_models', [model_claude])

View File

@ -24,6 +24,10 @@ from pr_agent.identity_providers import get_identity_provider
from pr_agent.identity_providers.identity_provider import Eligibility
from pr_agent.log import LoggingFormat, get_logger, setup_logger
from pr_agent.secret_providers import get_secret_provider
from pr_agent.servers.github_action_runner import get_setting_or_env, is_true
from pr_agent.tools.pr_code_suggestions import PRCodeSuggestions
from pr_agent.tools.pr_description import PRDescription
from pr_agent.tools.pr_reviewer import PRReviewer
setup_logger(fmt=LoggingFormat.JSON, level="DEBUG")
router = APIRouter()
@ -71,18 +75,6 @@ async def handle_manifest(request: Request, response: Response):
return JSONResponse(manifest_obj)
def _get_username(data):
actor = data.get("data", {}).get("actor", {})
if actor:
if "username" in actor:
return actor["username"]
elif "display_name" in actor:
return actor["display_name"]
elif "nickname" in actor:
return actor["nickname"]
return ""
async def _perform_commands_bitbucket(commands_conf: str, agent: PRAgent, api_url: str, log_context: dict, data: dict):
apply_repo_settings(api_url)
if commands_conf == "pr_commands" and get_settings().config.disable_auto_feedback: # auto commands for PR, and auto feedback is disabled
@ -126,14 +118,6 @@ def should_process_pr_logic(data) -> bool:
title = pr_data.get("title", "")
source_branch = pr_data.get("source", {}).get("branch", {}).get("name", "")
target_branch = pr_data.get("destination", {}).get("branch", {}).get("name", "")
sender = _get_username(data)
# logic to ignore PRs from specific users
ignore_pr_users = get_settings().get("CONFIG.IGNORE_PR_AUTHORS", [])
if ignore_pr_users and sender:
if sender in ignore_pr_users:
get_logger().info(f"Ignoring PR from user '{sender}' due to 'config.ignore_pr_authors' setting")
return False
# logic to ignore PRs with specific titles
if title:
@ -183,7 +167,16 @@ async def handle_github_webhooks(background_tasks: BackgroundTasks, request: Req
return "OK"
# Get the username of the sender
log_context["sender"] = _get_username(data)
actor = data.get("data", {}).get("actor", {})
if actor:
try:
username = actor["username"]
except KeyError:
try:
username = actor["display_name"]
except KeyError:
username = actor["nickname"]
log_context["sender"] = username
sender_id = data.get("data", {}).get("actor", {}).get("account_id", "")
log_context["sender_id"] = sender_id

View File

@ -257,14 +257,6 @@ def should_process_pr_logic(body) -> bool:
pr_labels = pull_request.get("labels", [])
source_branch = pull_request.get("head", {}).get("ref", "")
target_branch = pull_request.get("base", {}).get("ref", "")
sender = body.get("sender", {}).get("login")
# logic to ignore PRs from specific users
ignore_pr_users = get_settings().get("CONFIG.IGNORE_PR_AUTHORS", [])
if ignore_pr_users and sender:
if sender in ignore_pr_users:
get_logger().info(f"Ignoring PR from user '{sender}' due to 'config.ignore_pr_authors' setting")
return False
# logic to ignore PRs with specific titles
if title:
@ -284,7 +276,6 @@ def should_process_pr_logic(body) -> bool:
get_logger().info(f"Ignoring PR with labels '{labels_str}' due to config.ignore_pr_labels settings")
return False
# logic to ignore PRs with specific source or target branches
ignore_pr_source_branches = get_settings().get("CONFIG.IGNORE_PR_SOURCE_BRANCHES", [])
ignore_pr_target_branches = get_settings().get("CONFIG.IGNORE_PR_TARGET_BRANCHES", [])
if pull_request and (ignore_pr_source_branches or ignore_pr_target_branches):

View File

@ -84,7 +84,6 @@ async def is_valid_notification(notification, headers, handled_ids, session, use
return False, handled_ids
async with session.get(latest_comment, headers=headers) as comment_response:
check_prev_comments = False
user_tag = "@" + user_id
if comment_response.status == 200:
comment = await comment_response.json()
if 'id' in comment:
@ -102,6 +101,7 @@ async def is_valid_notification(notification, headers, handled_ids, session, use
get_logger().debug(f"no comment_body")
check_prev_comments = True
else:
user_tag = "@" + user_id
if user_tag not in comment_body:
get_logger().debug(f"user_tag not in comment_body")
check_prev_comments = True

View File

@ -100,14 +100,6 @@ def should_process_pr_logic(data) -> bool:
if not data.get('object_attributes', {}):
return False
title = data['object_attributes'].get('title')
sender = data.get("user", {}).get("username", "")
# logic to ignore PRs from specific users
ignore_pr_users = get_settings().get("CONFIG.IGNORE_PR_AUTHORS", [])
if ignore_pr_users and sender:
if sender in ignore_pr_users:
get_logger().info(f"Ignoring PR from user '{sender}' due to 'config.ignore_pr_authors' settings")
return False
# logic to ignore MRs for titles, labels and source, target branches.
ignore_mr_title = get_settings().get("CONFIG.IGNORE_PR_TITLE", [])

View File

@ -91,6 +91,3 @@ pat = ""
# Optional, uncomment if you want to use Azure devops webhooks. Value assinged when you create the webhook
# webhook_username = "<basic auth user>"
# webhook_password = "<basic auth password>"
[deepseek]
key = ""

View File

@ -1,8 +1,8 @@
[config]
# models
model="gpt-4o-2024-11-20"
model="gpt-4-turbo-2024-04-09"
model_turbo="gpt-4o-2024-11-20"
fallback_models=["gpt-4o-2024-08-06"]
#model_weak="gpt-4o-mini-2024-07-18" # optional, a weaker model to use for some easier tasks
# CLI
git_provider="github"
publish_output=true
@ -34,7 +34,6 @@ ai_disclaimer_title="" # Pro feature, title for a collapsible disclaimer to AI
ai_disclaimer="" # Pro feature, full text for the AI disclaimer
output_relevant_configurations=false
large_patch_policy = "clip" # "clip", "skip"
duplicate_prompt_examples = false
# seed
seed=-1 # set positive value to fix the seed (and ensure temperature=0)
temperature=0.2
@ -43,7 +42,6 @@ ignore_pr_title = ["^\\[Auto\\]", "^Auto"] # a list of regular expressions to ma
ignore_pr_target_branches = [] # a list of regular expressions of target branches to ignore from PR agent when an PR is created
ignore_pr_source_branches = [] # a list of regular expressions of source branches to ignore from PR agent when an PR is created
ignore_pr_labels = [] # labels to ignore from PR agent when an PR is created
ignore_pr_authors = [] # authors to ignore from PR agent when an PR is created
#
is_auto_command = false # will be auto-set to true if the command is triggered by an automation
enable_ai_metadata = false # will enable adding ai metadata
@ -57,6 +55,10 @@ require_can_be_split_review=false
require_security_review=true
require_ticket_analysis_review=true
# general options
num_code_suggestions=0
inline_code_comments = false
ask_and_reflect=false
#automatic_review=true
persistent_comment=true
extra_instructions = ""
final_update_message = true
@ -90,7 +92,6 @@ publish_description_as_comment_persistent=true
## changes walkthrough section
enable_semantic_files_types=true
collapsible_file_list='adaptive' # true, false, 'adaptive'
collapsible_file_list_threshold=8
inline_file_summary=false # false, true, 'table'
# markers
use_description_markers=false
@ -99,6 +100,7 @@ include_generated_by_header=true
enable_large_pr_handling=true
max_ai_calls=4
async_ai_calls=true
mention_extra_files=true
#custom_labels = ['Bug fix', 'Tests', 'Bug fix with tests', 'Enhancement', 'Documentation', 'Other']
[pr_questions] # /ask #
@ -113,6 +115,7 @@ dual_publishing_score_threshold=-1 # -1 to disable, [0-10] to set the threshold
focus_only_on_problems=true
#
extra_instructions = ""
rank_suggestions = false
enable_help_text=false
enable_chat_text=false
enable_intro_text=true
@ -127,7 +130,7 @@ auto_extended_mode=true
num_code_suggestions_per_chunk=4
max_number_of_calls = 3
parallel_calls = true
rank_extended_suggestions = false
final_clip_factor = 0.8
# self-review checkbox
demand_code_suggestions_self_review=false # add a checkbox for the author to self-review the code suggestions
@ -137,7 +140,6 @@ fold_suggestions_on_self_review=true # Pro feature. if true, the code suggestion
# Suggestion impact 💎
publish_post_process_suggestion_impact=true
wiki_page_accepted_suggestions=true
allow_thumbs_up_down=false
[pr_custom_prompt] # /custom_prompt #
prompt = """\
@ -161,7 +163,6 @@ class_name = "" # in case there are several methods with the same name in
[pr_update_changelog] # /update_changelog #
push_changelog_changes=false
extra_instructions = ""
add_pr_link=true
[pr_analyze] # /analyze #
enable_help_text=true
@ -218,7 +219,7 @@ override_deployment_type = true
handle_pr_actions = ['opened', 'reopened', 'ready_for_review']
pr_commands = [
"/describe --pr_description.final_update_message=false",
"/review",
"/review --pr_reviewer.num_code_suggestions=0",
"/improve",
]
# settings for "pull_request" event with "synchronize" action - used to detect and handle push triggers for new commits
@ -230,27 +231,27 @@ push_trigger_pending_tasks_backlog = true
push_trigger_pending_tasks_ttl = 300
push_commands = [
"/describe",
"/review",
"/review --pr_reviewer.num_code_suggestions=0",
]
[gitlab]
url = "https://gitlab.com"
pr_commands = [
"/describe --pr_description.final_update_message=false",
"/review",
"/review --pr_reviewer.num_code_suggestions=0",
"/improve",
]
handle_push_trigger = false
push_commands = [
"/describe",
"/review",
"/review --pr_reviewer.num_code_suggestions=0",
]
[bitbucket_app]
pr_commands = [
"/describe --pr_description.final_update_message=false",
"/review",
"/improve --pr_code_suggestions.commitable_code_suggestions=true",
"/review --pr_reviewer.num_code_suggestions=0",
"/improve --pr_code_suggestions.commitable_code_suggestions=true --pr_code_suggestions.suggestions_score_threshold=7",
]
avoid_full_files = false
@ -275,8 +276,8 @@ avoid_full_files = false
url = ""
pr_commands = [
"/describe --pr_description.final_update_message=false",
"/review",
"/improve --pr_code_suggestions.commitable_code_suggestions=true",
"/review --pr_reviewer.num_code_suggestions=0",
"/improve --pr_code_suggestions.commitable_code_suggestions=true --pr_code_suggestions.suggestions_score_threshold=7",
]
[litellm]

View File

@ -17,36 +17,30 @@ The PR code diff will be in the following structured format:
@@ ... @@ def func1():
__new hunk__
unchanged code line0
unchanged code line1
+new code line2 added
unchanged code line3
unchanged code line0 in the PR
unchanged code line1 in the PR
+new code line2 added in the PR
unchanged code line3 in the PR
__old hunk__
unchanged code line0
unchanged code line1
-old code line2 removed
-old code line2 removed in the PR
unchanged code line3
@@ ... @@ def func2():
__new hunk__
unchanged code line4
+new code line5 removed
+new code line5 removed in the PR
unchanged code line6
## File: 'src/file2.py'
...
======
Important notes about the structured diff format above:
1. Each PR code chunk is decoupled into separate '__new hunk__' and '__old hunk__' sections:
- The '__new hunk__' section shows the code chunk AFTER the PR changes.
- The '__old hunk__' section shows the code chunk BEFORE the PR changes. If no code was removed from the chunk, the '__old hunk__' section will be omitted.
2. The diff uses line prefixes to show changes:
'+' → new line code added (will appear only in '__new hunk__')
'-' → line code removed (will appear only in '__old hunk__')
' ' → unchanged context lines (will appear in both sections)
- In the format above, the diff is organized into separate '__new hunk__' and '__old hunk__' sections for each code chunk. '__new hunk__' contains the updated code, while '__old hunk__' shows the removed code. If no code was removed in a specific chunk, the __old hunk__ section will be omitted.
- Code lines are prefixed with symbols: '+' for new code added in the PR, '-' for code removed, and ' ' for unchanged code.
{%- if is_ai_metadata %}
3. When available, an AI-generated summary will precede each file's diff, with a high-level overview of the changes. Note that this summary may not be fully accurate or complete.
- When available, an AI-generated summary will precede each file's diff, with a high-level overview of the changes. Note that this summary may not be fully accurate or complete.
{%- endif %}
@ -56,17 +50,16 @@ Specific guidelines for generating code suggestions:
{%- else %}
- Provide up to {{ num_code_suggestions }} distinct and insightful code suggestions. Return less suggestions if no pertinent ones are applicable.
{%- endif %}
- DO NOT suggest implementing changes that are already present in the '+' lines compared to the '-' lines.
- Focus your suggestions ONLY on new code introduced in the PR ('+' lines in '__new hunk__' sections).
- Focus solely on enhancing new code introduced in the PR, identified by '+' prefixes in '__new hunk__' sections.
{%- if not focus_only_on_problems %}
- Prioritize suggestions that address potential issues, critical problems, and bugs in the PR code. Avoid repeating changes already implemented in the PR. If no pertinent suggestions are applicable, return an empty list.
- Don't suggest to add docstring, type hints, or comments, to remove unused imports, or to use more specific exception types.
{%- else %}
- Only give suggestions that address critical problems and bugs in the PR code. If no relevant suggestions are applicable, return an empty list.
- Do not suggest to change packages version, add missing import statement, or declare undefined variable.
{%- endif %}
- When mentioning code elements (variables, names, or files) in your response, surround them with backticks (`). For example: "verify that `user_id` is..."
- Note that you only see changed code segments (diff hunks in a PR), not the entire codebase. Avoid suggestions that might duplicate existing functionality or questioning code elements (like variables declerations or import statements) that may be defined elsewhere in the codebase.
- Don't suggest to add docstring, type hints, or comments, to remove unused imports, or to use more specific exception types.
- When referencing variables or names from the code, enclose them in backticks (`). Example: "ensure that `variable_name` is..."
- Be mindful you are viewing a partial PR code diff, not the full codebase. Avoid suggestions that might conflict with unseen code or alerting variables not declared in the visible scope, as the context is incomplete.
{%- if extra_instructions %}
@ -86,7 +79,7 @@ class CodeSuggestion(BaseModel):
suggestion_content: str = Field(description="An actionable suggestion to enhance, improve or fix the new code introduced in the PR. Don't present here actual code snippets, just the suggestion. Be short and concise")
existing_code: str = Field(description="A short code snippet from a '__new hunk__' section that the suggestion aims to enhance or fix. Include only complete code lines. Use ellipsis (...) for brevity if needed. This snippet should represent the specific PR code targeted for improvement.")
improved_code: str = Field(description="A refined code snippet that replaces the 'existing_code' snippet after implementing the suggestion.")
one_sentence_summary: str = Field(description="A concise, single-sentence overview (up to 6 words) of the suggested improvement. Focus on the 'what'. Be general, and avoid method or variable names.")
one_sentence_summary: str = Field(description="A concise, single-sentence overview of the suggested improvement. Focus on the 'what'. Be general, and avoid method or variable names.")
{%- if not focus_only_on_problems %}
label: str = Field(description="A single, descriptive label that best characterizes the suggestion type. Possible labels include 'security', 'possible bug', 'possible issue', 'performance', 'enhancement', 'best practice', 'maintainability', 'typo'. Other relevant labels are also acceptable.")
{%- else %}
@ -118,6 +111,7 @@ code_suggestions:
...
```
Each YAML output MUST be after a newline, indented, with block scalar indicator ('|').
"""
@ -125,40 +119,12 @@ user="""--PR Info--
Title: '{{title}}'
{%- if date %}
Today's Date: {{date}}
{%- endif %}
The PR Diff:
======
{{ diff_no_line_numbers|trim }}
======
{%- if duplicate_prompt_examples %}
Example output:
```yaml
code_suggestions:
- relevant_file: |
src/file1.py
language: |
python
suggestion_content: |
...
existing_code: |
...
improved_code: |
...
one_sentence_summary: |
...
label: |
...
```
(replace '...' with actual content)
{%- endif %}
Response (should be a valid YAML, and nothing else):
```yaml

View File

@ -49,14 +49,14 @@ The PR code diff will be presented in the following structured format:
@@ ... @@ def func1():
__new hunk__
11 unchanged code line0
12 unchanged code line1
13 +new code line2 added
14 unchanged code line3
11 unchanged code line0 in the PR
12 unchanged code line1 in the PR
13 +new code line2 added in the PR
14 unchanged code line3 in the PR
__old hunk__
unchanged code line0
unchanged code line1
-old code line2 removed
-old code line2 removed in the PR
unchanged code line3
@@ ... @@ def func2():
@ -122,25 +122,6 @@ Below are {{ num_code_suggestions }} AI-generated code suggestions for enhancing
======
{%- if duplicate_prompt_examples %}
Example output:
```yaml
code_suggestions:
- suggestion_summary: |
...
relevant_file: "..."
relevant_lines_start: ...
relevant_lines_end: ...
suggestion_score: ...
why: |
...
- ...
```
(replace '...' with actual content)
{%- endif %}
Response (should be a valid YAML, and nothing else):
```yaml
"""

View File

@ -1,11 +1,15 @@
[pr_description_prompt]
system="""You are PR-Reviewer, a language model designed to review a Git Pull Request (PR).
Your task is to provide a full description for the PR content - type, description, title and files walkthrough.
- Focus on the new PR code (lines starting with '+' in the 'PR Git Diff' section).
{%- if enable_custom_labels %}
Your task is to provide a full description for the PR content - files walkthrough, title, type, description and labels.
{%- else %}
Your task is to provide a full description for the PR content - files walkthrough, title, type, and description.
{%- endif %}
- Focus on the new PR code (lines starting with '+').
- Keep in mind that the 'Previous title', 'Previous description' and 'Commit messages' sections may be partial, simplistic, non-informative or out of date. Hence, compare them to the PR diff code, and use them only as a reference.
- The generated title and description should prioritize the most significant changes.
- If needed, each YAML output should be in block scalar indicator ('|')
- When quoting variables, names or file paths from the code, use backticks (`) instead of single quote (').
- If needed, each YAML output should be in block scalar indicator ('|-')
- When quoting variables or names from the code, use backticks (`) instead of single quote (').
{%- if extra_instructions %}
@ -34,20 +38,22 @@ class PRType(str, Enum):
{%- if enable_semantic_files_types %}
class FileDescription(BaseModel):
filename: str = Field(description="The full file path of the relevant file")
{%- if include_file_summary_changes %}
filename: str = Field(description="The full file path of the relevant file.")
language: str = Field(description="The programming language of the relevant file.")
changes_summary: str = Field(description="concise summary of the changes in the relevant file, in bullet points (1-4 bullet points).")
{%- endif %}
changes_title: str = Field(description="one-line summary (5-10 words) capturing the main theme of changes in the file")
changes_title: str = Field(description="an informative title for the changes in the files, describing its main theme (5-10 words).")
label: str = Field(description="a single semantic label that represents a type of code changes that occurred in the File. Possible values (partial list): 'bug fix', 'tests', 'enhancement', 'documentation', 'error handling', 'configuration changes', 'dependencies', 'formatting', 'miscellaneous', ...")
{%- endif %}
class PRDescription(BaseModel):
type: List[PRType] = Field(description="one or more types that describe the PR content. Return the label member value (e.g. 'Bug fix', not 'bug_fix')")
description: str = Field(description="summarize the PR changes in up to four bullet points, each up to 8 words. For large PRs, add sub-bullets if needed. Order bullets by importance, with each bullet highlighting a key change group.")
title: str = Field(description="a concise and descriptive title that captures the PR's main theme")
{%- if enable_semantic_files_types %}
pr_files: List[FileDescription] = Field(max_items=20, description="a list of all the files that were changed in the PR, and summary of their changes. Each file must be analyzed regardless of change size.")
pr_files: List[FileDescription] = Field(max_items=15, description="a list of the files in the PR, and summary of their changes")
{%- endif %}
description: str = Field(description="an informative and concise description of the PR. Use bullet points. Display first the most significant changes.")
title: str = Field(description="an informative title for the PR, describing its main theme")
{%- if enable_custom_labels %}
labels: List[Label] = Field(min_items=0, description="choose the relevant custom labels that describe the PR content, and return their keys. Use the value field of the Label object to better understand the label meaning.")
{%- endif %}
=====
@ -58,24 +64,31 @@ Example output:
type:
- ...
- ...
description: |
...
title: |
...
{%- if enable_semantic_files_types %}
pr_files:
- filename: |
...
{%- if include_file_summary_changes %}
language: |
...
changes_summary: |
...
{%- endif %}
changes_title: |
...
label: |
label_key_1
...
...
{%- endif %}
description: |
...
title: |
...
{%- if enable_custom_labels %}
labels:
- |
...
- |
...
{%- endif %}
```
Answer should be a valid YAML, and nothing else. Each YAML output MUST be after a newline, with proper indent, and block scalar indicator ('|')
@ -123,44 +136,13 @@ Commit messages:
{%- endif %}
The PR Git Diff:
The PR Diff:
=====
{{ diff|trim }}
=====
Note that lines in the diff body are prefixed with a symbol that represents the type of change: '-' for deletions, '+' for additions, and ' ' (a space) for unchanged lines.
{%- if duplicate_prompt_examples %}
Example output:
```yaml
type:
- Bug fix
- Refactoring
- ...
description: |
...
title: |
...
{%- if enable_semantic_files_types %}
pr_files:
- filename: |
...
{%- if include_file_summary_changes %}
changes_summary: |
...
{%- endif %}
changes_title: |
...
label: |
label_key_1
...
{%- endif %}
```
(replace '...' with the actual values)
{%- endif %}
Response (should be a valid YAML, and nothing else):
```yaml

View File

@ -1,6 +1,10 @@
[pr_review_prompt]
system="""You are PR-Reviewer, a language model designed to review a Git Pull Request (PR).
{%- if num_code_suggestions > 0 %}
Your task is to provide constructive and concise feedback for the PR, and also provide meaningful code suggestions.
{%- else %}
Your task is to provide constructive and concise feedback for the PR.
{%- endif %}
The review should focus on new code added in the PR code diff (lines starting with '+')
@ -16,20 +20,20 @@ The format we will use to present the PR code diff:
@@ ... @@ def func1():
__new hunk__
11 unchanged code line0
12 unchanged code line1
13 +new code line2 added
14 unchanged code line3
11 unchanged code line0 in the PR
12 unchanged code line1 in the PR
13 +new code line2 added in the PR
14 unchanged code line3 in the PR
__old hunk__
unchanged code line0
unchanged code line1
-old code line2 removed
-old code line2 removed in the PR
unchanged code line3
@@ ... @@ def func2():
__new hunk__
unchanged code line4
+new code line5 removed
+new code line5 removed in the PR
unchanged code line6
## File: 'src/file2.py'
@ -43,8 +47,18 @@ __new hunk__
{%- if is_ai_metadata %}
- If available, an AI-generated summary will appear and provide a high-level overview of the file changes. Note that this summary may not be fully accurate or complete.
{%- endif %}
- When quoting variables, names or file paths from the code, use backticks (`) instead of single quote (').
- When quoting variables or names from the code, use backticks (`) instead of single quote (').
{%- if num_code_suggestions > 0 %}
Code suggestions guidelines:
- Provide up to {{ num_code_suggestions }} code suggestions. Try to provide diverse and insightful suggestions.
- Focus on important suggestions like fixing code problems, issues and bugs. As a second priority, provide suggestions for meaningful code improvements, like performance, vulnerability, modularity, and best practices.
- Avoid making suggestions that have already been implemented in the PR code. For example, if you want to add logs, or change a variable to const, or anything else, make sure it isn't already in the PR code.
- Don't suggest to add docstring, type hints, or comments.
- Suggestions should address the new code added in the PR diff (lines starting with '+')
{%- endif %}
{%- if extra_instructions %}
@ -66,8 +80,8 @@ class SubPR(BaseModel):
class KeyIssuesComponentLink(BaseModel):
relevant_file: str = Field(description="The full file path of the relevant file")
issue_header: str = Field(description="One or two word title for the the issue. For example: 'Possible Bug', etc.")
issue_content: str = Field(description="A short and concise summary of what should be further inspected and validated during the PR review process for this issue. Do not reference line numbers in this field.")
issue_header: str = Field(description="One or two word title for the the issue. For example: 'Possible Bug', 'Performance Issue', 'Code Smell', etc.")
issue_content: str = Field(description="A short and concise summary of what should be further inspected and validated during the PR review process for this issue. Don't state line numbers here")
start_line: int = Field(description="The start line that corresponds to this issue in the relevant file")
end_line: int = Field(description="The end line that corresponds to this issue in the relevant file")
@ -97,16 +111,32 @@ class Review(BaseModel):
{%- if question_str %}
insights_from_user_answers: str = Field(description="shortly summarize the insights you gained from the user's answers to the questions")
{%- endif %}
key_issues_to_review: List[KeyIssuesComponentLink] = Field("A short and diverse list (0-3 issues) of high-priority bugs, problems or performance concerns introduced in the PR code, which the PR reviewer should further focus on and validate during the review process.")
key_issues_to_review: List[KeyIssuesComponentLink] = Field("A diverse list of bugs, issue or major performance concerns introduced in this PR, which the PR reviewer should further investigate")
{%- if require_security_review %}
security_concerns: str = Field(description="Does this PR code introduce possible vulnerabilities such as exposure of sensitive information (e.g., API keys, secrets, passwords), or security concerns like SQL injection, XSS, CSRF, and others ? Answer 'No' (without explaining why) if there are no possible issues. If there are security concerns or issues, start your answer with a short header, such as: 'Sensitive information exposure: ...', 'SQL injection: ...' etc. Explain your answer. Be specific and give examples if possible")
{%- endif %}
{%- if require_can_be_split_review %}
can_be_split: List[SubPR] = Field(min_items=0, max_items=3, description="Can this PR, which contains {{ num_pr_files }} changed files in total, be divided into smaller sub-PRs with distinct tasks that can be reviewed and merged independently, regardless of the order ? Make sure that the sub-PRs are indeed independent, with no code dependencies between them, and that each sub-PR represent a meaningful independent task. Output an empty list if the PR code does not need to be split.")
{%- endif %}
{%- if num_code_suggestions > 0 %}
class CodeSuggestion(BaseModel):
relevant_file: str = Field(description="The full file path of the relevant file")
language: str = Field(description="The programming language of the relevant file")
suggestion: str = Field(description="a concrete suggestion for meaningfully improving the new PR code. Also describe how, specifically, the suggestion can be applied to new PR code. Add tags with importance measure that matches each suggestion ('important' or 'medium'). Do not make suggestions for updating or adding docstrings, renaming PR title and description, or linter like.")
relevant_line: str = Field(description="a single code line taken from the relevant file, to which the suggestion applies. The code line should start with a '+'. Make sure to output the line exactly as it appears in the relevant file")
{%- endif %}
{%- if num_code_suggestions > 0 %}
class PRReview(BaseModel):
review: Review
code_feedback: List[CodeSuggestion]
{%- else %}
class PRReview(BaseModel):
review: Review
{%- endif %}
=====
@ -155,6 +185,18 @@ review:
title: ...
- ...
{%- endif %}
{%- if num_code_suggestions > 0 %}
code_feedback:
- relevant_file: |
directory/xxx.py
language: |
python
suggestion: |
xxx [important]
relevant_line: |
xxx
{%- endif %}
```
Answer should be a valid YAML, and nothing else. Each YAML output MUST be after a newline, with proper indent, and block scalar indicator ('|')
@ -221,59 +263,6 @@ The PR code diff:
======
{%- if duplicate_prompt_examples %}
Example output:
```yaml
review:
{%- if related_tickets %}
ticket_compliance_check:
- ticket_url: |
...
ticket_requirements: |
...
fully_compliant_requirements: |
...
not_compliant_requirements: |
...
overall_compliance_level: |
...
{%- endif %}
{%- if require_estimate_effort_to_review %}
estimated_effort_to_review_[1-5]: |
3
{%- endif %}
{%- if require_score %}
score: 89
{%- endif %}
relevant_tests: |
No
key_issues_to_review:
- relevant_file: |
...
issue_header: |
...
issue_content: |
...
start_line: ...
end_line: ...
- ...
security_concerns: |
No
{%- if require_can_be_split_review %}
can_be_split:
- relevant_files:
- ...
- ...
title: ...
- ...
{%- endif %}
```
(replace '...' with the actual values)
{%- endif %}
Response (should be a valid YAML, and nothing else):
```yaml
"""

View File

@ -1,14 +1,9 @@
[pr_update_changelog_prompt]
system="""You are a language model called PR-Changelog-Updater.
Your task is to add a brief summary of this PR's changes to CHANGELOG.md file of the project:
- Follow the file's existing format and style conventions like dates, section titles, etc.
- Only add new changes (don't repeat existing entries)
- Be general, and avoid specific details, files, etc. The output should be minimal, no more than 3-4 short lines.
- Write only the new content to be added to CHANGELOG.md, without any introduction or summary. The content should appear as if it's a natural part of the existing file.
{%- if pr_link %}
- If relevant, convert the changelog main header into a clickable link using the PR URL '{{ pr_link }}'. Format: header [*][pr_link]
{%- endif %}
Your task is to update the CHANGELOG.md file of the project, to shortly summarize important changes introduced in this PR (the '+' lines).
- The output should match the existing CHANGELOG.md format, style and conventions, so it will look like a natural part of the file. For example, if previous changes were summarized in a single line, you should do the same.
- Don't repeat previous changes. Generate only new content, that is not already in the CHANGELOG.md file.
- Be general, and avoid specific details, files, etc. The output should be minimal, no more than 3-4 short lines. Ignore non-relevant subsections.
{%- if extra_instructions %}
@ -52,19 +47,16 @@ The PR Git Diff:
{{ diff|trim }}
======
Current date:
```
{{today}}
```
The current 'CHANGELOG.md' file
The current CHANGELOG.md:
======
{{ changelog_file_str }}
======
Response:
```markdown
"""

View File

@ -4,7 +4,6 @@ import difflib
import re
import textwrap
import traceback
from datetime import datetime
from functools import partial
from typing import Dict, List
@ -22,7 +21,7 @@ from pr_agent.config_loader import get_settings
from pr_agent.git_providers import (AzureDevopsProvider, GithubProvider,
GitLabProvider, get_git_provider,
get_git_provider_with_context)
from pr_agent.git_providers.git_provider import get_main_pr_language, GitProvider
from pr_agent.git_providers.git_provider import get_main_pr_language
from pr_agent.log import get_logger
from pr_agent.servers.help import HelpMessage
from pr_agent.tools.pr_description import insert_br_after_x_chars
@ -82,8 +81,6 @@ class PRCodeSuggestions:
"relevant_best_practices": "",
"is_ai_metadata": get_settings().get("config.enable_ai_metadata", False),
"focus_only_on_problems": get_settings().get("pr_code_suggestions.focus_only_on_problems", False),
"date": datetime.now().strftime('%Y-%m-%d'),
'duplicate_prompt_examples': get_settings().config.get('duplicate_prompt_examples', False),
}
self.pr_code_suggestions_prompt_system = get_settings().pr_code_suggestions_prompt.system
@ -106,8 +103,6 @@ class PRCodeSuggestions:
relevant_configs = {'pr_code_suggestions': dict(get_settings().pr_code_suggestions),
'config': dict(get_settings().config)}
get_logger().debug("Relevant configs", artifacts=relevant_configs)
# publish "Preparing suggestions..." comments
if (get_settings().config.publish_output and get_settings().config.publish_output_progress and
not get_settings().config.get('is_auto_command', False)):
if self.git_provider.is_supported("gfm_markdown"):
@ -115,26 +110,33 @@ class PRCodeSuggestions:
else:
self.git_provider.publish_comment("Preparing suggestions...", is_temporary=True)
# call the model to get the suggestions, and self-reflect on them
if not self.is_extended:
data = await retry_with_fallback_models(self._prepare_prediction, model_type=ModelType.REGULAR)
data = await retry_with_fallback_models(self._prepare_prediction)
else:
data = await retry_with_fallback_models(self._prepare_prediction_extended, model_type=ModelType.REGULAR)
data = await retry_with_fallback_models(self._prepare_prediction_extended)
if not data:
data = {"code_suggestions": []}
self.data = data
# Handle the case where the PR has no suggestions
if (data is None or 'code_suggestions' not in data or not data['code_suggestions']):
await self.publish_no_suggestions()
pr_body = "## PR Code Suggestions ✨\n\nNo code suggestions found for the PR."
get_logger().warning('No code suggestions found for the PR.')
if get_settings().config.publish_output and get_settings().config.publish_output_no_suggestions:
get_logger().debug(f"PR output", artifact=pr_body)
if self.progress_response:
self.git_provider.edit_comment(self.progress_response, body=pr_body)
else:
self.git_provider.publish_comment(pr_body)
else:
get_settings().data = {"artifact": ""}
return
# publish the suggestions
if get_settings().config.publish_output:
# If a temporary comment was published, remove it
self.git_provider.remove_initial_comment()
if (not self.is_extended and get_settings().pr_code_suggestions.rank_suggestions) or \
(self.is_extended and get_settings().pr_code_suggestions.rank_extended_suggestions):
get_logger().info('Ranking Suggestions...')
data['code_suggestions'] = await self.rank_suggestions(data['code_suggestions'])
# Publish table summarized suggestions
if get_settings().config.publish_output:
self.git_provider.remove_initial_comment()
if ((not get_settings().pr_code_suggestions.commitable_code_suggestions) and
self.git_provider.is_supported("gfm_markdown")):
@ -144,7 +146,10 @@ class PRCodeSuggestions:
# require self-review
if get_settings().pr_code_suggestions.demand_code_suggestions_self_review:
pr_body = await self.add_self_review_text(pr_body)
text = get_settings().pr_code_suggestions.code_suggestions_self_review_text
pr_body += f"\n\n- [ ] {text}"
if get_settings().pr_code_suggestions.approve_pr_on_self_review:
pr_body += ' <!-- approve pr self-review -->'
# add usage guide
if (get_settings().pr_code_suggestions.enable_chat_text and get_settings().config.is_auto_command
@ -160,13 +165,13 @@ class PRCodeSuggestions:
pr_body += show_relevant_configurations(relevant_section='pr_code_suggestions')
# publish the PR comment
if get_settings().pr_code_suggestions.persistent_comment: # true by default
self.publish_persistent_comment_with_history(self.git_provider,
pr_body,
if get_settings().pr_code_suggestions.persistent_comment:
final_update_message = False
self.publish_persistent_comment_with_history(pr_body,
initial_header="## PR Code Suggestions ✨",
update_header=True,
name="suggestions",
final_update_message=False,
final_update_message=final_update_message,
max_previous_comments=get_settings().pr_code_suggestions.max_history_len,
progress_response=self.progress_response)
else:
@ -177,15 +182,29 @@ class PRCodeSuggestions:
# dual publishing mode
if int(get_settings().pr_code_suggestions.dual_publishing_score_threshold) > 0:
await self.dual_publishing(data)
data_above_threshold = {'code_suggestions': []}
try:
for suggestion in data['code_suggestions']:
if int(suggestion.get('score', 0)) >= int(get_settings().pr_code_suggestions.dual_publishing_score_threshold) \
and suggestion.get('improved_code'):
data_above_threshold['code_suggestions'].append(suggestion)
if not data_above_threshold['code_suggestions'][-1]['existing_code']:
get_logger().info(f'Identical existing and improved code for dual publishing found')
data_above_threshold['code_suggestions'][-1]['existing_code'] = suggestion[
'improved_code']
if data_above_threshold['code_suggestions']:
get_logger().info(
f"Publishing {len(data_above_threshold['code_suggestions'])} suggestions in dual publishing mode")
self.push_inline_code_suggestions(data_above_threshold)
except Exception as e:
get_logger().error(f"Failed to publish dual publishing suggestions, error: {e}")
else:
await self.push_inline_code_suggestions(data)
self.push_inline_code_suggestions(data)
if self.progress_response:
self.git_provider.remove_comment(self.progress_response)
else:
get_logger().info('Code suggestions generated for PR, but not published since publish_output is False.')
pr_body = self.generate_summarized_suggestions(data)
get_settings().data = {"artifact": pr_body}
get_settings().data = {"artifact": data}
return
except Exception as e:
get_logger().error(f"Failed to generate code suggestions for PR, error: {e}",
@ -198,108 +217,47 @@ class PRCodeSuggestions:
self.git_provider.remove_initial_comment()
self.git_provider.publish_comment(f"Failed to generate code suggestions for PR")
except Exception as e:
get_logger().exception(f"Failed to update persistent review, error: {e}")
pass
async def add_self_review_text(self, pr_body):
text = get_settings().pr_code_suggestions.code_suggestions_self_review_text
pr_body += f"\n\n- [ ] {text}"
approve_pr_on_self_review = get_settings().pr_code_suggestions.approve_pr_on_self_review
fold_suggestions_on_self_review = get_settings().pr_code_suggestions.fold_suggestions_on_self_review
if approve_pr_on_self_review and not fold_suggestions_on_self_review:
pr_body += ' <!-- approve pr self-review -->'
elif fold_suggestions_on_self_review and not approve_pr_on_self_review:
pr_body += ' <!-- fold suggestions self-review -->'
else:
pr_body += ' <!-- approve and fold suggestions self-review -->'
return pr_body
async def publish_no_suggestions(self):
pr_body = "## PR Code Suggestions ✨\n\nNo code suggestions found for the PR."
if get_settings().config.publish_output and get_settings().config.publish_output_no_suggestions:
get_logger().warning('No code suggestions found for the PR.')
get_logger().debug(f"PR output", artifact=pr_body)
if self.progress_response:
self.git_provider.edit_comment(self.progress_response, body=pr_body)
else:
self.git_provider.publish_comment(pr_body)
else:
get_settings().data = {"artifact": ""}
async def dual_publishing(self, data):
data_above_threshold = {'code_suggestions': []}
try:
for suggestion in data['code_suggestions']:
if int(suggestion.get('score', 0)) >= int(
get_settings().pr_code_suggestions.dual_publishing_score_threshold) \
and suggestion.get('improved_code'):
data_above_threshold['code_suggestions'].append(suggestion)
if not data_above_threshold['code_suggestions'][-1]['existing_code']:
get_logger().info(f'Identical existing and improved code for dual publishing found')
data_above_threshold['code_suggestions'][-1]['existing_code'] = suggestion[
'improved_code']
if data_above_threshold['code_suggestions']:
get_logger().info(
f"Publishing {len(data_above_threshold['code_suggestions'])} suggestions in dual publishing mode")
await self.push_inline_code_suggestions(data_above_threshold)
except Exception as e:
get_logger().error(f"Failed to publish dual publishing suggestions, error: {e}")
@staticmethod
def publish_persistent_comment_with_history(git_provider: GitProvider,
pr_comment: str,
def publish_persistent_comment_with_history(self, pr_comment: str,
initial_header: str,
update_header: bool = True,
name='review',
final_update_message=True,
max_previous_comments=4,
progress_response=None,
only_fold=False):
progress_response=None):
def _extract_link(comment_text: str):
r = re.compile(r"<!--.*?-->")
match = r.search(comment_text)
up_to_commit_txt = ""
if match:
up_to_commit_txt = f" up to commit {match.group(0)[4:-3].strip()}"
return up_to_commit_txt
if isinstance(git_provider, AzureDevopsProvider): # get_latest_commit_url is not supported yet
if isinstance(self.git_provider, AzureDevopsProvider): # get_latest_commit_url is not supported yet
if progress_response:
git_provider.edit_comment(progress_response, pr_comment)
new_comment = progress_response
self.git_provider.edit_comment(progress_response, pr_comment)
else:
new_comment = git_provider.publish_comment(pr_comment)
return new_comment
self.git_provider.publish_comment(pr_comment)
return
history_header = f"#### Previous suggestions\n"
last_commit_num = git_provider.get_latest_commit_url().split('/')[-1][:7]
if only_fold: # A user clicked on the 'self-review' checkbox
text = get_settings().pr_code_suggestions.code_suggestions_self_review_text
latest_suggestion_header = f"\n\n- [x] {text}"
else:
latest_suggestion_header = f"Latest suggestions up to {last_commit_num}"
last_commit_num = self.git_provider.get_latest_commit_url().split('/')[-1][:7]
latest_suggestion_header = f"Latest suggestions up to {last_commit_num}"
latest_commit_html_comment = f"<!-- {last_commit_num} -->"
found_comment = None
if max_previous_comments > 0:
try:
prev_comments = list(git_provider.get_issue_comments())
prev_comments = list(self.git_provider.get_issue_comments())
for comment in prev_comments:
if comment.body.startswith(initial_header):
prev_suggestions = comment.body
found_comment = comment
comment_url = git_provider.get_comment_url(comment)
comment_url = self.git_provider.get_comment_url(comment)
if history_header.strip() not in comment.body:
# no history section
# extract everything between <table> and </table> in comment.body including <table> and </table>
table_index = comment.body.find("<table>")
if table_index == -1:
git_provider.edit_comment(comment, pr_comment)
self.git_provider.edit_comment(comment, pr_comment)
continue
# find http link from comment.body[:table_index]
up_to_commit_txt = _extract_link(comment.body[:table_index])
up_to_commit_txt = self.extract_link(comment.body[:table_index])
prev_suggestion_table = comment.body[
table_index:comment.body.rfind("</table>") + len("</table>")]
@ -320,7 +278,7 @@ class PRCodeSuggestions:
# get text after the latest_suggestion_header in comment.body
table_ind = latest_table.find("<table>")
up_to_commit_txt = _extract_link(latest_table[:table_ind])
up_to_commit_txt = self.extract_link(latest_table[:table_ind])
latest_table = latest_table[table_ind:latest_table.rfind("</table>") + len("</table>")]
# enforce max_previous_comments
@ -347,12 +305,11 @@ class PRCodeSuggestions:
get_logger().info(f"Persistent mode - updating comment {comment_url} to latest {name} message")
if progress_response: # publish to 'progress_response' comment, because it refreshes immediately
git_provider.edit_comment(progress_response, pr_comment_updated)
git_provider.remove_comment(comment)
comment = progress_response
self.git_provider.edit_comment(progress_response, pr_comment_updated)
self.git_provider.remove_comment(comment)
else:
git_provider.edit_comment(comment, pr_comment_updated)
return comment
self.git_provider.edit_comment(comment, pr_comment_updated)
return
except Exception as e:
get_logger().exception(f"Failed to update persistent review, error: {e}")
pass
@ -361,12 +318,9 @@ class PRCodeSuggestions:
body = pr_comment.replace(initial_header, "").strip()
pr_comment = f"{initial_header}\n\n{latest_commit_html_comment}\n\n{body}\n\n"
if progress_response:
git_provider.edit_comment(progress_response, pr_comment)
new_comment = progress_response
self.git_provider.edit_comment(progress_response, pr_comment)
else:
new_comment = git_provider.publish_comment(pr_comment)
return new_comment
self.git_provider.publish_comment(pr_comment)
def extract_link(self, s):
r = re.compile(r"<!--.*?-->")
@ -417,7 +371,50 @@ class PRCodeSuggestions:
response_reflect = await self.self_reflect_on_suggestions(data["code_suggestions"],
patches_diff, model=model_reflection)
if response_reflect:
await self.analyze_self_reflection_response(data, response_reflect)
response_reflect_yaml = load_yaml(response_reflect)
code_suggestions_feedback = response_reflect_yaml["code_suggestions"]
if len(code_suggestions_feedback) == len(data["code_suggestions"]):
for i, suggestion in enumerate(data["code_suggestions"]):
try:
suggestion["score"] = code_suggestions_feedback[i]["suggestion_score"]
suggestion["score_why"] = code_suggestions_feedback[i]["why"]
if 'relevant_lines_start' not in suggestion:
relevant_lines_start = code_suggestions_feedback[i].get('relevant_lines_start', -1)
relevant_lines_end = code_suggestions_feedback[i].get('relevant_lines_end', -1)
suggestion['relevant_lines_start'] = relevant_lines_start
suggestion['relevant_lines_end'] = relevant_lines_end
if relevant_lines_start < 0 or relevant_lines_end < 0:
suggestion["score"] = 0
try:
if get_settings().config.publish_output:
suggestion_statistics_dict = {'score': int(suggestion["score"]),
'label': suggestion["label"].lower().strip()}
get_logger().info(f"PR-Agent suggestions statistics",
statistics=suggestion_statistics_dict, analytics=True)
except Exception as e:
get_logger().error(f"Failed to log suggestion statistics, error: {e}")
pass
except Exception as e: #
get_logger().error(f"Error processing suggestion score {i}",
artifact={"suggestion": suggestion,
"code_suggestions_feedback": code_suggestions_feedback[i]})
suggestion["score"] = 7
suggestion["score_why"] = ""
# if the before and after code is the same, clear one of them
try:
if suggestion['existing_code'] == suggestion['improved_code']:
get_logger().debug(
f"edited improved suggestion {i + 1}, because equal to existing code: {suggestion['existing_code']}")
if get_settings().pr_code_suggestions.commitable_code_suggestions:
suggestion['improved_code'] = "" # we need 'existing_code' to locate the code in the PR
else:
suggestion['existing_code'] = ""
except Exception as e:
get_logger().error(f"Error processing suggestion {i + 1}, error: {e}")
else:
# get_logger().error(f"Could not self-reflect on suggestions. using default score 7")
for i, suggestion in enumerate(data["code_suggestions"]):
@ -426,58 +423,6 @@ class PRCodeSuggestions:
return data
async def analyze_self_reflection_response(self, data, response_reflect):
response_reflect_yaml = load_yaml(response_reflect)
code_suggestions_feedback = response_reflect_yaml.get("code_suggestions", [])
if code_suggestions_feedback and len(code_suggestions_feedback) == len(data["code_suggestions"]):
for i, suggestion in enumerate(data["code_suggestions"]):
try:
suggestion["score"] = code_suggestions_feedback[i]["suggestion_score"]
suggestion["score_why"] = code_suggestions_feedback[i]["why"]
if 'relevant_lines_start' not in suggestion:
relevant_lines_start = code_suggestions_feedback[i].get('relevant_lines_start', -1)
relevant_lines_end = code_suggestions_feedback[i].get('relevant_lines_end', -1)
suggestion['relevant_lines_start'] = relevant_lines_start
suggestion['relevant_lines_end'] = relevant_lines_end
if relevant_lines_start < 0 or relevant_lines_end < 0:
suggestion["score"] = 0
try:
if get_settings().config.publish_output:
if not suggestion["score"]:
score = -1
else:
score = int(suggestion["score"])
label = suggestion["label"].lower().strip()
label = label.replace('<br>', ' ')
suggestion_statistics_dict = {'score': score,
'label': label}
get_logger().info(f"PR-Agent suggestions statistics",
statistics=suggestion_statistics_dict, analytics=True)
except Exception as e:
get_logger().error(f"Failed to log suggestion statistics, error: {e}")
pass
except Exception as e: #
get_logger().error(f"Error processing suggestion score {i}",
artifact={"suggestion": suggestion,
"code_suggestions_feedback": code_suggestions_feedback[i]})
suggestion["score"] = 7
suggestion["score_why"] = ""
# if the before and after code is the same, clear one of them
try:
if suggestion['existing_code'] == suggestion['improved_code']:
get_logger().debug(
f"edited improved suggestion {i + 1}, because equal to existing code: {suggestion['existing_code']}")
if get_settings().pr_code_suggestions.commitable_code_suggestions:
suggestion['improved_code'] = "" # we need 'existing_code' to locate the code in the PR
else:
suggestion['existing_code'] = ""
except Exception as e:
get_logger().error(f"Error processing suggestion {i + 1}, error: {e}")
@staticmethod
def _truncate_if_needed(suggestion):
max_code_suggestion_length = get_settings().get("PR_CODE_SUGGESTIONS.MAX_CODE_SUGGESTION_LENGTH", 0)
@ -541,7 +486,7 @@ class PRCodeSuggestions:
return data
async def push_inline_code_suggestions(self, data):
def push_inline_code_suggestions(self, data):
code_suggestions = []
if not data['code_suggestions']:
@ -639,9 +584,7 @@ class PRCodeSuggestions:
patches_diff_lines = patches_diff.splitlines()
for i, line in enumerate(patches_diff_lines):
if line.strip():
if line.isnumeric():
patches_diff_lines[i] = ''
elif line[0].isdigit():
if line[0].isdigit():
# find the first letter in the line that starts with a valid letter
for j, char in enumerate(line):
if not char.isdigit():
@ -699,6 +642,62 @@ class PRCodeSuggestions:
self.data = data = None
return data
async def rank_suggestions(self, data: List) -> List:
"""
Call a model to rank (sort) code suggestions based on their importance order.
Args:
data (List): A list of code suggestions to be ranked.
Returns:
List: The ranked list of code suggestions.
"""
suggestion_list = []
if not data:
return suggestion_list
for suggestion in data:
suggestion_list.append(suggestion)
data_sorted = [[]] * len(suggestion_list)
if len(suggestion_list) == 1:
return suggestion_list
try:
suggestion_str = ""
for i, suggestion in enumerate(suggestion_list):
suggestion_str += f"suggestion {i + 1}: " + str(suggestion) + '\n\n'
variables = {'suggestion_list': suggestion_list, 'suggestion_str': suggestion_str}
model = get_settings().config.model
environment = Environment(undefined=StrictUndefined)
system_prompt = environment.from_string(get_settings().pr_sort_code_suggestions_prompt.system).render(
variables)
user_prompt = environment.from_string(get_settings().pr_sort_code_suggestions_prompt.user).render(variables)
response, finish_reason = await self.ai_handler.chat_completion(model=model, system=system_prompt,
user=user_prompt)
sort_order = load_yaml(response)
for s in sort_order['Sort Order']:
suggestion_number = s['suggestion number']
importance_order = s['importance order']
data_sorted[importance_order - 1] = suggestion_list[suggestion_number - 1]
if get_settings().pr_code_suggestions.final_clip_factor != 1:
max_len = max(
len(data_sorted),
int(get_settings().pr_code_suggestions.num_code_suggestions_per_chunk),
)
new_len = int(0.5 + max_len * get_settings().pr_code_suggestions.final_clip_factor)
if new_len < len(data_sorted):
data_sorted = data_sorted[:new_len]
except Exception as e:
if get_settings().config.verbosity_level >= 1:
get_logger().info(f"Could not sort suggestions, error: {e}")
data_sorted = suggestion_list
return data_sorted
def generate_summarized_suggestions(self, data: Dict) -> str:
try:
pr_body = "## PR Code Suggestions ✨\n\n"
@ -814,12 +813,7 @@ class PRCodeSuggestions:
get_logger().info(f"Failed to publish summarized code suggestions, error: {e}")
return ""
async def self_reflect_on_suggestions(self,
suggestion_list: List,
patches_diff: str,
model: str,
prev_suggestions_str: str = "",
dedicated_prompt: str = "") -> str:
async def self_reflect_on_suggestions(self, suggestion_list: List, patches_diff: str, model: str) -> str:
if not suggestion_list:
return ""
@ -832,22 +826,13 @@ class PRCodeSuggestions:
'suggestion_str': suggestion_str,
"diff": patches_diff,
'num_code_suggestions': len(suggestion_list),
'prev_suggestions_str': prev_suggestions_str,
"is_ai_metadata": get_settings().get("config.enable_ai_metadata", False),
'duplicate_prompt_examples': get_settings().config.get('duplicate_prompt_examples', False)}
"is_ai_metadata": get_settings().get("config.enable_ai_metadata", False)}
environment = Environment(undefined=StrictUndefined)
if dedicated_prompt:
system_prompt_reflect = environment.from_string(
get_settings().get(dedicated_prompt).system).render(variables)
user_prompt_reflect = environment.from_string(
get_settings().get(dedicated_prompt).user).render(variables)
else:
system_prompt_reflect = environment.from_string(
get_settings().pr_code_suggestions_reflect_prompt.system).render(variables)
user_prompt_reflect = environment.from_string(
get_settings().pr_code_suggestions_reflect_prompt.user).render(variables)
system_prompt_reflect = environment.from_string(
get_settings().pr_code_suggestions_reflect_prompt.system).render(
variables)
user_prompt_reflect = environment.from_string(
get_settings().pr_code_suggestions_reflect_prompt.user).render(variables)
with get_logger().contextualize(command="self_reflect_on_suggestions"):
response_reflect, finish_reason_reflect = await self.ai_handler.chat_completion(model=model,
system=system_prompt_reflect,
@ -855,4 +840,4 @@ class PRCodeSuggestions:
except Exception as e:
get_logger().info(f"Could not reflect on suggestions, error: {e}")
return ""
return response_reflect
return response_reflect

View File

@ -38,15 +38,12 @@ class PRConfig:
if (header.lower().startswith("pr_") or header.lower().startswith("config")) and header.lower() in configuration_headers
}
skip_keys = ['ai_disclaimer', 'ai_disclaimer_title', 'ANALYTICS_FOLDER', 'secret_provider', "skip_keys", "app_id", "redirect",
'trial_prefix_message', 'no_eligible_message', 'identity_provider', 'ALLOWED_REPOS',
'APP_NAME', 'PERSONAL_ACCESS_TOKEN', 'shared_secret', 'key', 'AWS_ACCESS_KEY_ID', 'AWS_SECRET_ACCESS_KEY', 'user_token',
'private_key', 'private_key_id', 'client_id', 'client_secret', 'token', 'bearer_token']
skip_keys = ['ai_disclaimer', 'ai_disclaimer_title', 'ANALYTICS_FOLDER', 'secret_provider', "skip_keys",
'trial_prefix_message', 'no_eligible_message', 'identity_provider', 'ALLOWED_REPOS',
'APP_NAME']
extra_skip_keys = get_settings().config.get('config.skip_keys', [])
if extra_skip_keys:
skip_keys.extend(extra_skip_keys)
skip_keys_lower = [key.lower() for key in skip_keys]
markdown_text = "<details> <summary><strong>🛠️ PR-Agent Configurations:</strong></summary> \n\n"
markdown_text += f"\n\n```yaml\n\n"
@ -55,7 +52,7 @@ class PRConfig:
markdown_text += "\n\n"
markdown_text += f"==================== {header} ===================="
for key, value in configs.items():
if key.lower() in skip_keys_lower:
if key in skip_keys:
continue
markdown_text += f"\n{header.lower()}.{key.lower()} = {repr(value) if isinstance(value, str) else value}"
markdown_text += " "

View File

@ -1,7 +1,6 @@
import asyncio
import copy
import re
import traceback
from functools import partial
from typing import List, Tuple
@ -58,7 +57,6 @@ class PRDescription:
self.ai_handler.main_pr_language = self.main_pr_language
# Initialize the variables dictionary
self.COLLAPSIBLE_FILE_LIST_THRESHOLD = get_settings().pr_description.get("collapsible_file_list_threshold", 8)
self.vars = {
"title": self.git_provider.pr.title,
"branch": self.git_provider.get_pr_branch(),
@ -71,8 +69,6 @@ class PRDescription:
"custom_labels_class": "", # will be filled if necessary in 'set_custom_labels' function
"enable_semantic_files_types": get_settings().pr_description.enable_semantic_files_types,
"related_tickets": "",
"include_file_summary_changes": len(self.git_provider.get_diff_files()) <= self.COLLAPSIBLE_FILE_LIST_THRESHOLD,
'duplicate_prompt_examples': get_settings().config.get('duplicate_prompt_examples', False),
}
self.user_description = self.git_provider.get_user_description()
@ -89,6 +85,7 @@ class PRDescription:
self.patches_diff = None
self.prediction = None
self.file_label_dict = None
self.COLLAPSIBLE_FILE_LIST_THRESHOLD = 8
async def run(self):
try:
@ -102,7 +99,7 @@ class PRDescription:
# ticket extraction if exists
await extract_and_cache_pr_tickets(self.git_provider, self.vars)
await retry_with_fallback_models(self._prepare_prediction, ModelType.WEAK)
await retry_with_fallback_models(self._prepare_prediction, ModelType.TURBO)
if self.prediction:
self._prepare_data()
@ -117,8 +114,6 @@ class PRDescription:
pr_labels, pr_file_changes = [], []
if get_settings().pr_description.publish_labels:
pr_labels = self._prepare_labels()
else:
get_logger().debug(f"Publishing labels disabled")
if get_settings().pr_description.use_description_markers:
pr_title, pr_body, changes_walkthrough, pr_file_changes = self._prepare_pr_answer_with_markers()
@ -142,7 +137,6 @@ class PRDescription:
pr_body += show_relevant_configurations(relevant_section='pr_description')
if get_settings().config.publish_output:
# publish labels
if get_settings().pr_description.publish_labels and pr_labels and self.git_provider.is_supported("get_labels"):
original_labels = self.git_provider.get_pr_labels(update=True)
@ -170,49 +164,43 @@ class PRDescription:
self.git_provider.publish_description(pr_title, pr_body)
# publish final update message
if (get_settings().pr_description.final_update_message and not get_settings().config.get('is_auto_command', False)):
if (get_settings().pr_description.final_update_message):
latest_commit_url = self.git_provider.get_latest_commit_url()
if latest_commit_url:
pr_url = self.git_provider.get_pr_url()
update_comment = f"**[PR Description]({pr_url})** updated to latest commit ({latest_commit_url})"
self.git_provider.publish_comment(update_comment)
self.git_provider.remove_initial_comment()
else:
get_logger().info('PR description, but not published since publish_output is False.')
get_settings().data = {"artifact": pr_body}
return
except Exception as e:
get_logger().error(f"Error generating PR description {self.pr_id}: {e}",
artifact={"traceback": traceback.format_exc()})
get_logger().error(f"Error generating PR description {self.pr_id}: {e}")
return ""
async def _prepare_prediction(self, model: str) -> None:
if get_settings().pr_description.use_description_markers and 'pr_agent:' not in self.user_description:
get_logger().info("Markers were enabled, but user description does not contain markers. skipping AI prediction")
get_logger().info(
"Markers were enabled, but user description does not contain markers. skipping AI prediction")
return None
large_pr_handling = get_settings().pr_description.enable_large_pr_handling and "pr_description_only_files_prompts" in get_settings()
output = get_pr_diff(self.git_provider, self.token_handler, model, large_pr_handling=large_pr_handling, return_remaining_files=True)
output = get_pr_diff(self.git_provider, self.token_handler, model, large_pr_handling=large_pr_handling,
return_remaining_files=True)
if isinstance(output, tuple):
patches_diff, remaining_files_list = output
else:
patches_diff = output
remaining_files_list = []
if not large_pr_handling or patches_diff:
self.patches_diff = patches_diff
if patches_diff:
# generate the prediction
get_logger().debug(f"PR diff", artifact=self.patches_diff)
self.prediction = await self._get_prediction(model, patches_diff, prompt="pr_description_prompt")
# extend the prediction with additional files not shown
if get_settings().pr_description.enable_semantic_files_types:
self.prediction = await self.extend_uncovered_files(self.prediction)
if (remaining_files_list and 'pr_files' in self.prediction and 'label:' in self.prediction and
get_settings().pr_description.mention_extra_files):
get_logger().debug(f"Extending additional files, {len(remaining_files_list)} files")
self.prediction = await self.extend_additional_files(remaining_files_list)
else:
get_logger().error(f"Error getting PR diff {self.pr_id}",
artifact={"traceback": traceback.format_exc()})
get_logger().error(f"Error getting PR diff {self.pr_id}")
self.prediction = None
else:
# get the diff in multiple patches, with the token handler only for the files prompt
@ -297,81 +285,43 @@ class PRDescription:
prompt="pr_description_only_description_prompts")
prediction_headers = prediction_headers.strip().removeprefix('```yaml').strip('`').strip()
# extend the tables with the files not shown
files_walkthrough_extended = await self.extend_uncovered_files(files_walkthrough)
# manually add extra files to final prediction
MAX_EXTRA_FILES_TO_OUTPUT = 100
if get_settings().pr_description.mention_extra_files:
for i, file in enumerate(remaining_files_list):
extra_file_yaml = f"""\
- filename: |
{file}
changes_summary: |
...
changes_title: |
...
label: |
additional files (token-limit)
"""
files_walkthrough = files_walkthrough.strip() + "\n" + extra_file_yaml.strip()
if i >= MAX_EXTRA_FILES_TO_OUTPUT:
files_walkthrough += f"""\
extra_file_yaml =
- filename: |
Additional {len(remaining_files_list) - MAX_EXTRA_FILES_TO_OUTPUT} files not shown
changes_summary: |
...
changes_title: |
...
label: |
additional files (token-limit)
"""
break
# final processing
self.prediction = prediction_headers + "\n" + "pr_files:\n" + files_walkthrough_extended
self.prediction = prediction_headers + "\n" + "pr_files:\n" + files_walkthrough
if not load_yaml(self.prediction, keys_fix_yaml=self.keys_fix):
get_logger().error(f"Error getting valid YAML in large PR handling for describe {self.pr_id}")
if load_yaml(prediction_headers, keys_fix_yaml=self.keys_fix):
get_logger().debug(f"Using only headers for describe {self.pr_id}")
self.prediction = prediction_headers
async def extend_uncovered_files(self, original_prediction: str) -> str:
try:
prediction = original_prediction
# get the original prediction filenames
original_prediction_loaded = load_yaml(original_prediction, keys_fix_yaml=self.keys_fix)
if isinstance(original_prediction_loaded, list):
original_prediction_dict = {"pr_files": original_prediction_loaded}
else:
original_prediction_dict = original_prediction_loaded
filenames_predicted = [file['filename'].strip() for file in original_prediction_dict.get('pr_files', [])]
# extend the prediction with additional files not included in the original prediction
pr_files = self.git_provider.get_diff_files()
prediction_extra = "pr_files:"
MAX_EXTRA_FILES_TO_OUTPUT = 100
counter_extra_files = 0
for file in pr_files:
if file.filename in filenames_predicted:
continue
# add up to MAX_EXTRA_FILES_TO_OUTPUT files
counter_extra_files += 1
if counter_extra_files > MAX_EXTRA_FILES_TO_OUTPUT:
extra_file_yaml = f"""\
- filename: |
Additional files not shown
changes_title: |
...
label: |
additional files
"""
prediction_extra = prediction_extra + "\n" + extra_file_yaml.strip()
get_logger().debug(f"Too many remaining files, clipping to {MAX_EXTRA_FILES_TO_OUTPUT}")
break
extra_file_yaml = f"""\
- filename: |
{file.filename}
changes_title: |
...
label: |
additional files
"""
prediction_extra = prediction_extra + "\n" + extra_file_yaml.strip()
# merge the two dictionaries
if counter_extra_files > 0:
get_logger().info(f"Adding {counter_extra_files} unprocessed extra files to table prediction")
prediction_extra_dict = load_yaml(prediction_extra, keys_fix_yaml=self.keys_fix)
if isinstance(original_prediction_dict, dict) and isinstance(prediction_extra_dict, dict):
original_prediction_dict["pr_files"].extend(prediction_extra_dict["pr_files"])
new_yaml = yaml.dump(original_prediction_dict)
if load_yaml(new_yaml, keys_fix_yaml=self.keys_fix):
prediction = new_yaml
if isinstance(original_prediction, list):
prediction = yaml.dump(original_prediction_dict["pr_files"])
return prediction
except Exception as e:
get_logger().error(f"Error extending uncovered files {self.pr_id}: {e}")
return original_prediction
async def extend_additional_files(self, remaining_files_list) -> str:
prediction = self.prediction
try:
@ -443,44 +393,35 @@ class PRDescription:
self.data['pr_files'] = self.data.pop('pr_files')
def _prepare_labels(self) -> List[str]:
pr_labels = []
pr_types = []
# If the 'PR Type' key is present in the dictionary, split its value by comma and assign it to 'pr_types'
if 'labels' in self.data and self.data['labels']:
if 'labels' in self.data:
if type(self.data['labels']) == list:
pr_labels = self.data['labels']
pr_types = self.data['labels']
elif type(self.data['labels']) == str:
pr_labels = self.data['labels'].split(',')
elif 'type' in self.data and self.data['type'] and get_settings().pr_description.publish_labels:
pr_types = self.data['labels'].split(',')
elif 'type' in self.data:
if type(self.data['type']) == list:
pr_labels = self.data['type']
pr_types = self.data['type']
elif type(self.data['type']) == str:
pr_labels = self.data['type'].split(',')
pr_labels = [label.strip() for label in pr_labels]
pr_types = self.data['type'].split(',')
pr_types = [label.strip() for label in pr_types]
# convert lowercase labels to original case
try:
if "labels_minimal_to_labels_dict" in self.variables:
d: dict = self.variables["labels_minimal_to_labels_dict"]
for i, label_i in enumerate(pr_labels):
for i, label_i in enumerate(pr_types):
if label_i in d:
pr_labels[i] = d[label_i]
pr_types[i] = d[label_i]
except Exception as e:
get_logger().error(f"Error converting labels to original case {self.pr_id}: {e}")
return pr_labels
return pr_types
def _prepare_pr_answer_with_markers(self) -> Tuple[str, str, str, List[dict]]:
get_logger().info(f"Using description marker replacements {self.pr_id}")
# Remove the 'PR Title' key from the dictionary
ai_title = self.data.pop('title', self.vars["title"])
if (not get_settings().pr_description.generate_ai_title):
# Assign the original PR title to the 'title' variable
title = self.vars["title"]
else:
# Assign the value of the 'PR Title' key to 'title' variable
title = ai_title
title = self.vars["title"]
body = self.user_description
if get_settings().pr_description.include_generated_by_header:
ai_header = f"### 🤖 Generated by PR Agent at {self.git_provider.last_commit_id.sha}\n\n"
@ -489,11 +430,7 @@ class PRDescription:
ai_type = self.data.get('type')
if ai_type and not re.search(r'<!--\s*pr_agent:type\s*-->', body):
if isinstance(ai_type, list):
pr_types = [f"{ai_header}{t}" for t in ai_type]
pr_type = ','.join(pr_types)
else:
pr_type = f"{ai_header}{ai_type}"
pr_type = f"{ai_header}{ai_type}"
body = body.replace('pr_agent:type', pr_type)
ai_summary = self.data.get('description')
@ -570,11 +507,6 @@ class PRDescription:
elif 'pr_files' in key.lower() and get_settings().pr_description.enable_semantic_files_types:
changes_walkthrough, pr_file_changes = self.process_pr_files_prediction(changes_walkthrough, value)
changes_walkthrough = f"{PRDescriptionHeader.CHANGES_WALKTHROUGH.value}\n{changes_walkthrough}"
elif key.lower().strip() == 'description':
if isinstance(value, list):
value = ', '.join(v.rstrip() for v in value)
value = value.replace('\n-', '\n\n-').strip() # makes the bullet points more readable by adding double space
pr_body += f"{value}\n"
else:
# if the value is a list, join its items by comma
if isinstance(value, list):
@ -592,18 +524,14 @@ class PRDescription:
return file_label_dict
for file in self.data['pr_files']:
try:
required_fields = ['changes_title', 'filename', 'label']
required_fields = ['changes_summary', 'changes_title', 'filename', 'label']
if not all(field in file for field in required_fields):
# can happen for example if a YAML generation was interrupted in the middle (no more tokens)
get_logger().warning(f"Missing required fields in file label dict {self.pr_id}, skipping file",
artifact={"file": file})
continue
if not file.get('changes_title'):
get_logger().warning(f"Empty changes title or summary in file label dict {self.pr_id}, skipping file",
artifact={"file": file})
continue
filename = file['filename'].replace("'", "`").replace('"', '`')
changes_summary = file.get('changes_summary', "").strip()
changes_summary = file['changes_summary']
changes_title = file['changes_title'].strip()
label = file.get('label').strip().lower()
if label not in file_label_dict:
@ -646,14 +574,12 @@ class PRDescription:
for filename, file_changes_title, file_change_description in list_tuples:
filename = filename.replace("'", "`").rstrip()
filename_publish = filename.split("/")[-1]
if file_changes_title and file_changes_title.strip() != "...":
file_changes_title_code = f"<code>{file_changes_title}</code>"
file_changes_title_code_br = insert_br_after_x_chars(file_changes_title_code, x=(delta - 5)).strip()
if len(file_changes_title_code_br) < (delta - 5):
file_changes_title_code_br += "&nbsp; " * ((delta - 5) - len(file_changes_title_code_br))
filename_publish = f"<strong>{filename_publish}</strong><dd>{file_changes_title_code_br}</dd>"
else:
filename_publish = f"<strong>{filename_publish}</strong>"
file_changes_title_code = f"<code>{file_changes_title}</code>"
file_changes_title_code_br = insert_br_after_x_chars(file_changes_title_code, x=(delta - 5)).strip()
if len(file_changes_title_code_br) < (delta - 5):
file_changes_title_code_br += "&nbsp; " * ((delta - 5) - len(file_changes_title_code_br))
filename_publish = f"<strong>{filename_publish}</strong><dd>{file_changes_title_code_br}</dd>"
diff_plus_minus = ""
delta_nbsp = ""
diff_files = self.git_provider.get_diff_files()
@ -662,8 +588,6 @@ class PRDescription:
num_plus_lines = f.num_plus_lines
num_minus_lines = f.num_minus_lines
diff_plus_minus += f"+{num_plus_lines}/-{num_minus_lines}"
if len(diff_plus_minus) > 12 or diff_plus_minus == "+0/-0":
diff_plus_minus = "[link]"
delta_nbsp = "&nbsp; " * max(0, (8 - len(diff_plus_minus)))
break
@ -672,40 +596,9 @@ class PRDescription:
if hasattr(self.git_provider, 'get_line_link'):
filename = filename.strip()
link = self.git_provider.get_line_link(filename, relevant_line_start=-1)
if (not link or not diff_plus_minus) and ('additional files' not in filename.lower()):
get_logger().warning(f"Error getting line link for '{filename}'")
continue
# Add file data to the PR body
file_change_description_br = insert_br_after_x_chars(file_change_description, x=(delta - 5))
pr_body = self.add_file_data(delta_nbsp, diff_plus_minus, file_change_description_br, filename,
filename_publish, link, pr_body)
# Close the collapsible file list
if use_collapsible_file_list:
pr_body += """</table></details></td></tr>"""
else:
pr_body += """</table></td></tr>"""
pr_body += """</tr></tbody></table>"""
except Exception as e:
get_logger().error(f"Error processing pr files to markdown {self.pr_id}: {str(e)}")
pass
return pr_body, pr_comments
def add_file_data(self, delta_nbsp, diff_plus_minus, file_change_description_br, filename, filename_publish, link,
pr_body) -> str:
if not file_change_description_br:
pr_body += f"""
<tr>
<td>{filename_publish}</td>
<td><a href="{link}">{diff_plus_minus}</a>{delta_nbsp}</td>
</tr>
"""
else:
pr_body += f"""
pr_body += f"""
<tr>
<td>
<details>
@ -725,7 +618,17 @@ class PRDescription:
</tr>
"""
return pr_body
if use_collapsible_file_list:
pr_body += """</table></details></td></tr>"""
else:
pr_body += """</table></td></tr>"""
pr_body += """</tr></tbody></table>"""
except Exception as e:
get_logger().error(f"Error processing pr files to markdown {self.pr_id}: {e}")
pass
return pr_body, pr_comments
def count_chars_without_html(string):
if '<' not in string:
@ -734,14 +637,11 @@ def count_chars_without_html(string):
return len(no_html_string)
def insert_br_after_x_chars(text: str, x=70):
def insert_br_after_x_chars(text, x=70):
"""
Insert <br> into a string after a word that increases its length above x characters.
Use proper HTML tags for code and new lines.
"""
if not text:
return ""
if count_chars_without_html(text) < x:
return text

View File

@ -114,7 +114,7 @@ class PRHelpMessage:
self.vars['snippets'] = docs_prompt.strip()
# run the AI model
response = await retry_with_fallback_models(self._prepare_prediction, model_type=ModelType.WEAK)
response = await retry_with_fallback_models(self._prepare_prediction, model_type=ModelType.REGULAR)
response_yaml = load_yaml(response)
response_str = response_yaml.get('response')
relevant_sections = response_yaml.get('relevant_sections')
@ -232,7 +232,7 @@ class PRHelpMessage:
for i in range(len(tool_names)):
pr_comment += f"\n<tr><td align='left'>\n\n<strong>{tool_names[i]}</strong></td>\n<td>{descriptions[i]}</td>\n<td>\n\n{checkbox_list[i]}\n</td></tr>"
pr_comment += "</table>\n\n"
pr_comment += f"""\n\n(1) Note that each tool can be [triggered automatically](https://pr-agent-docs.codium.ai/usage-guide/automations_and_usage/#github-app-automatic-tools-when-a-new-pr-is-opened) when a new PR is opened, or called manually by [commenting on a PR](https://pr-agent-docs.codium.ai/usage-guide/automations_and_usage/#online-usage)."""
pr_comment += f"""\n\n(1) Note that each tool be [triggered automatically](https://pr-agent-docs.codium.ai/usage-guide/automations_and_usage/#github-app-automatic-tools-when-a-new-pr-is-opened) when a new PR is opened, or called manually by [commenting on a PR](https://pr-agent-docs.codium.ai/usage-guide/automations_and_usage/#online-usage)."""
pr_comment += f"""\n\n(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."""
elif isinstance(self.git_provider, BitbucketServerProvider):
# only support basic commands in BBDC
@ -242,7 +242,7 @@ class PRHelpMessage:
for i in range(len(tool_names)):
pr_comment += f"\n<tr><td align='left'>\n\n<strong>{tool_names[i]}</strong></td><td>{commands[i]}</td><td>{descriptions[i]}</td></tr>"
pr_comment += "</table>\n\n"
pr_comment += f"""\n\nNote that each tool can be [invoked automatically](https://pr-agent-docs.codium.ai/usage-guide/automations_and_usage/) when a new PR is opened, or called manually by [commenting on a PR](https://pr-agent-docs.codium.ai/usage-guide/automations_and_usage/#online-usage)."""
pr_comment += f"""\n\nNote that each tool be [invoked automatically](https://pr-agent-docs.codium.ai/usage-guide/automations_and_usage/) when a new PR is opened, or called manually by [commenting on a PR](https://pr-agent-docs.codium.ai/usage-guide/automations_and_usage/#online-usage)."""
if get_settings().config.publish_output:
self.git_provider.publish_comment(pr_comment)

View File

@ -0,0 +1,79 @@
import copy
from functools import partial
from jinja2 import Environment, StrictUndefined
from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
from pr_agent.algo.ai_handlers.litellm_ai_handler import LiteLLMAIHandler
from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
from pr_agent.algo.token_handler import TokenHandler
from pr_agent.config_loader import get_settings
from pr_agent.git_providers import get_git_provider
from pr_agent.git_providers.git_provider import get_main_pr_language
from pr_agent.log import get_logger
class PRInformationFromUser:
def __init__(self, pr_url: str, args: list = None,
ai_handler: partial[BaseAiHandler,] = LiteLLMAIHandler):
self.git_provider = get_git_provider()(pr_url)
self.main_pr_language = get_main_pr_language(
self.git_provider.get_languages(), self.git_provider.get_files()
)
self.ai_handler = ai_handler()
self.ai_handler.main_pr_language = self.main_pr_language
self.vars = {
"title": self.git_provider.pr.title,
"branch": self.git_provider.get_pr_branch(),
"description": self.git_provider.get_pr_description(),
"language": self.main_pr_language,
"diff": "", # empty diff for initial calculation
"commit_messages_str": self.git_provider.get_commit_messages(),
}
self.token_handler = TokenHandler(self.git_provider.pr,
self.vars,
get_settings().pr_information_from_user_prompt.system,
get_settings().pr_information_from_user_prompt.user)
self.patches_diff = None
self.prediction = None
async def run(self):
get_logger().info('Generating question to the user...')
if get_settings().config.publish_output:
self.git_provider.publish_comment("Preparing questions...", is_temporary=True)
await retry_with_fallback_models(self._prepare_prediction)
get_logger().info('Preparing questions...')
pr_comment = self._prepare_pr_answer()
if get_settings().config.publish_output:
get_logger().info('Pushing questions...')
self.git_provider.publish_comment(pr_comment)
self.git_provider.remove_initial_comment()
return ""
async def _prepare_prediction(self, model):
get_logger().info('Getting PR diff...')
self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
get_logger().info('Getting AI prediction...')
self.prediction = await self._get_prediction(model)
async def _get_prediction(self, model: str):
variables = copy.deepcopy(self.vars)
variables["diff"] = self.patches_diff # update diff
environment = Environment(undefined=StrictUndefined)
system_prompt = environment.from_string(get_settings().pr_information_from_user_prompt.system).render(variables)
user_prompt = environment.from_string(get_settings().pr_information_from_user_prompt.user).render(variables)
if get_settings().config.verbosity_level >= 2:
get_logger().info(f"\nSystem prompt:\n{system_prompt}")
get_logger().info(f"\nUser prompt:\n{user_prompt}")
response, finish_reason = await self.ai_handler.chat_completion(
model=model, temperature=get_settings().config.temperature, system=system_prompt, user=user_prompt)
return response
def _prepare_pr_answer(self) -> str:
model_output = self.prediction.strip()
if get_settings().config.verbosity_level >= 2:
get_logger().info(f"answer_str:\n{model_output}")
answer_str = f"{model_output}\n\n Please respond to the questions above in the following format:\n\n" +\
"\n>/answer\n>1) ...\n>2) ...\n>...\n"
return answer_str

View File

@ -79,17 +79,13 @@ class PR_LineQuestions:
line_end=line_end,
side=side)
if self.patch_with_lines:
model_answer = await retry_with_fallback_models(self._get_prediction, model_type=ModelType.WEAK)
# sanitize the answer so that no line will start with "/"
model_answer_sanitized = model_answer.strip().replace("\n/", "\n /")
if model_answer_sanitized.startswith("/"):
model_answer_sanitized = " " + model_answer_sanitized
response = await retry_with_fallback_models(self._get_prediction, model_type=ModelType.TURBO)
get_logger().info('Preparing answer...')
if comment_id:
self.git_provider.reply_to_comment_from_comment_id(comment_id, model_answer_sanitized)
self.git_provider.reply_to_comment_from_comment_id(comment_id, response)
else:
self.git_provider.publish_comment(model_answer_sanitized)
self.git_provider.publish_comment(response)
return ""

View File

@ -63,7 +63,7 @@ class PRQuestions:
if img_path:
get_logger().debug(f"Image path identified", artifact=img_path)
await retry_with_fallback_models(self._prepare_prediction, model_type=ModelType.WEAK)
await retry_with_fallback_models(self._prepare_prediction, model_type=ModelType.TURBO)
pr_comment = self._prepare_pr_answer()
get_logger().debug(f"PR output", artifact=pr_comment)
@ -117,16 +117,6 @@ class PRQuestions:
return response
def _prepare_pr_answer(self) -> str:
model_answer = self.prediction.strip()
# sanitize the answer so that no line will start with "/"
model_answer_sanitized = model_answer.replace("\n/", "\n /")
if model_answer_sanitized.startswith("/"):
model_answer_sanitized = " " + model_answer_sanitized
if model_answer_sanitized != model_answer:
get_logger().debug(f"Sanitized model answer",
artifact={"model_answer": model_answer, "sanitized_answer": model_answer_sanitized})
answer_str = f"### **Ask**❓\n{self.question_str}\n\n"
answer_str += f"### **Answer:**\n{model_answer_sanitized}\n\n"
answer_str += f"### **Answer:**\n{self.prediction.strip()}\n\n"
return answer_str

View File

@ -86,6 +86,7 @@ class PRReviewer:
"require_estimate_effort_to_review": get_settings().pr_reviewer.require_estimate_effort_to_review,
'require_can_be_split_review': get_settings().pr_reviewer.require_can_be_split_review,
'require_security_review': get_settings().pr_reviewer.require_security_review,
'num_code_suggestions': get_settings().pr_reviewer.num_code_suggestions,
'question_str': question_str,
'answer_str': answer_str,
"extra_instructions": get_settings().pr_reviewer.extra_instructions,
@ -94,7 +95,6 @@ class PRReviewer:
"enable_custom_labels": get_settings().config.enable_custom_labels,
"is_ai_metadata": get_settings().get("config.enable_ai_metadata", False),
"related_tickets": get_settings().get('related_tickets', []),
'duplicate_prompt_examples': get_settings().config.get('duplicate_prompt_examples', False),
}
self.token_handler = TokenHandler(
@ -148,7 +148,7 @@ class PRReviewer:
if get_settings().config.publish_output and not get_settings().config.get('is_auto_command', False):
self.git_provider.publish_comment("Preparing review...", is_temporary=True)
await retry_with_fallback_models(self._prepare_prediction, model_type=ModelType.REGULAR)
await retry_with_fallback_models(self._prepare_prediction)
if not self.prediction:
self.git_provider.remove_initial_comment()
return None
@ -168,10 +168,8 @@ class PRReviewer:
self.git_provider.publish_comment(pr_review)
self.git_provider.remove_initial_comment()
else:
get_logger().info("Review output is not published")
get_settings().data = {"artifact": pr_review}
return
if get_settings().pr_reviewer.inline_code_comments:
self._publish_inline_code_comments()
except Exception as e:
get_logger().error(f"Failed to review PR: {e}")
@ -233,6 +231,33 @@ class PRReviewer:
key_issues_to_review = data['review'].pop('key_issues_to_review')
data['review']['key_issues_to_review'] = key_issues_to_review
if 'code_feedback' in data:
code_feedback = data['code_feedback']
# Filter out code suggestions that can be submitted as inline comments
if get_settings().pr_reviewer.inline_code_comments:
del data['code_feedback']
else:
for suggestion in code_feedback:
if ('relevant_file' in suggestion) and (not suggestion['relevant_file'].startswith('``')):
suggestion['relevant_file'] = f"``{suggestion['relevant_file']}``"
if 'relevant_line' not in suggestion:
suggestion['relevant_line'] = ''
relevant_line_str = suggestion['relevant_line'].split('\n')[0]
# removing '+'
suggestion['relevant_line'] = relevant_line_str.lstrip('+').strip()
# try to add line numbers link to code suggestions
if hasattr(self.git_provider, 'generate_link_to_relevant_line_number'):
link = self.git_provider.generate_link_to_relevant_line_number(suggestion)
if link:
suggestion['relevant_line'] = f"[{suggestion['relevant_line']}]({link})"
else:
pass
incremental_review_markdown_text = None
# Add incremental review section
if self.incremental.is_incremental:
@ -241,9 +266,7 @@ class PRReviewer:
incremental_review_markdown_text = f"Starting from commit {last_commit_url}"
markdown_text = convert_to_markdown_v2(data, self.git_provider.is_supported("gfm_markdown"),
incremental_review_markdown_text,
git_provider=self.git_provider,
files=self.git_provider.get_diff_files())
incremental_review_markdown_text, git_provider=self.git_provider)
# Add help text if gfm_markdown is supported
if self.git_provider.is_supported("gfm_markdown") and get_settings().pr_reviewer.enable_help_text:
@ -263,6 +286,38 @@ class PRReviewer:
return markdown_text
def _publish_inline_code_comments(self) -> None:
"""
Publishes inline comments on a pull request with code suggestions generated by the AI model.
"""
if get_settings().pr_reviewer.num_code_suggestions == 0:
return
first_key = 'review'
last_key = 'security_concerns'
data = load_yaml(self.prediction.strip(),
keys_fix_yaml=["ticket_compliance_check", "estimated_effort_to_review_[1-5]:", "security_concerns:", "key_issues_to_review:",
"relevant_file:", "relevant_line:", "suggestion:"],
first_key=first_key, last_key=last_key)
comments: List[str] = []
for suggestion in data.get('code_feedback', []):
relevant_file = suggestion.get('relevant_file', '').strip()
relevant_line_in_file = suggestion.get('relevant_line', '').strip()
content = suggestion.get('suggestion', '')
if not relevant_file or not relevant_line_in_file or not content:
get_logger().info("Skipping inline comment with missing file/line/content")
continue
if self.git_provider.is_supported("create_inline_comment"):
comment = self.git_provider.create_inline_comment(content, relevant_file, relevant_line_in_file)
if comment:
comments.append(comment)
else:
self.git_provider.publish_inline_comment(content, relevant_file, relevant_line_in_file, suggestion)
if comments:
self.git_provider.publish_inline_comments(comments)
def _get_user_answers(self) -> Tuple[str, str]:
"""
Retrieves the question and answer strings from the discussion messages related to a pull request.

View File

@ -41,7 +41,6 @@ class PRUpdateChangelog:
"description": self.git_provider.get_pr_description(),
"language": self.main_language,
"diff": "", # empty diff for initial calculation
"pr_link": "",
"changelog_file_str": self.changelog_file_str,
"today": date.today(),
"extra_instructions": get_settings().pr_update_changelog.extra_instructions,
@ -74,7 +73,7 @@ class PRUpdateChangelog:
if get_settings().config.publish_output:
self.git_provider.publish_comment("Preparing changelog updates...", is_temporary=True)
await retry_with_fallback_models(self._prepare_prediction, model_type=ModelType.WEAK)
await retry_with_fallback_models(self._prepare_prediction, model_type=ModelType.TURBO)
new_file_content, answer = self._prepare_changelog_update()
@ -103,23 +102,12 @@ class PRUpdateChangelog:
async def _get_prediction(self, model: str):
variables = copy.deepcopy(self.vars)
variables["diff"] = self.patches_diff # update diff
if get_settings().pr_update_changelog.add_pr_link:
variables["pr_link"] = self.git_provider.get_pr_url()
environment = Environment(undefined=StrictUndefined)
system_prompt = environment.from_string(get_settings().pr_update_changelog_prompt.system).render(variables)
user_prompt = environment.from_string(get_settings().pr_update_changelog_prompt.user).render(variables)
response, finish_reason = await self.ai_handler.chat_completion(
model=model, system=system_prompt, user=user_prompt, temperature=get_settings().config.temperature)
# post-process the response
response = response.strip()
if not response:
return ""
if response.startswith("```"):
response_lines = response.splitlines()
response_lines = response_lines[1:]
response = "\n".join(response_lines)
response = response.strip("`")
return response
def _prepare_changelog_update(self) -> Tuple[str, str]:

View File

@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
[project]
name = "pr-agent"
version = "0.2.5"
version = "0.2.4"
authors = [{ name = "CodiumAI", email = "tal.r@codium.ai" }]

View File

@ -3,3 +3,4 @@
from setuptools import setup
setup()
print("testing ...")

View File

@ -1,70 +0,0 @@
import argparse
import asyncio
import copy
import os
from pathlib import Path
from starlette_context import request_cycle_context, context
from pr_agent.cli import run_command
from pr_agent.config_loader import get_settings, global_settings
from pr_agent.agent.pr_agent import PRAgent, commands
from pr_agent.log import get_logger, setup_logger
from tests.e2e_tests import e2e_utils
log_level = os.environ.get("LOG_LEVEL", "INFO")
setup_logger(log_level)
async def run_async():
pr_url = os.getenv('TEST_PR_URL', 'https://github.com/Codium-ai/pr-agent/pull/1385')
get_settings().set("config.git_provider", "github")
get_settings().set("config.publish_output", False)
get_settings().set("config.fallback_models", [])
agent = PRAgent()
try:
# Run the 'describe' command
get_logger().info(f"\nSanity check for the 'describe' command...")
original_settings = copy.deepcopy(get_settings())
await agent.handle_request(pr_url, ['describe'])
pr_header_body = dict(get_settings().data)['artifact']
assert pr_header_body.startswith('###') and 'PR Type' in pr_header_body and 'Description' in pr_header_body
context['settings'] = copy.deepcopy(original_settings) # Restore settings state after each test to prevent test interference
get_logger().info("PR description generated successfully\n")
# Run the 'review' command
get_logger().info(f"\nSanity check for the 'review' command...")
original_settings = copy.deepcopy(get_settings())
await agent.handle_request(pr_url, ['review'])
pr_review_body = dict(get_settings().data)['artifact']
assert pr_review_body.startswith('##') and 'PR Reviewer Guide' in pr_review_body
context['settings'] = copy.deepcopy(original_settings) # Restore settings state after each test to prevent test interference
get_logger().info("PR review generated successfully\n")
# Run the 'improve' command
get_logger().info(f"\nSanity check for the 'improve' command...")
original_settings = copy.deepcopy(get_settings())
await agent.handle_request(pr_url, ['improve'])
pr_improve_body = dict(get_settings().data)['artifact']
assert pr_improve_body.startswith('##') and 'PR Code Suggestions' in pr_improve_body
context['settings'] = copy.deepcopy(original_settings) # Restore settings state after each test to prevent test interference
get_logger().info("PR improvements generated successfully\n")
get_logger().info(f"\n\n========\nHealth test passed successfully\n========")
except Exception as e:
get_logger().exception(f"\n\n========\nHealth test failed\n========")
raise e
def run():
with request_cycle_context({}):
context['settings'] = copy.deepcopy(global_settings)
asyncio.run(run_async())
if __name__ == '__main__':
run()

View File

@ -24,13 +24,6 @@ class TestBitbucketServerProvider:
assert repo_slug == "my-repo"
assert pr_number == 1
def test_parse_pr_url_with_users(self):
url = "https://bitbucket.company-server.url/users/username/repos/my-repo/pull-requests/1"
workspace_slug, repo_slug, pr_number = BitbucketServerProvider._parse_pr_url(url)
assert workspace_slug == "~username"
assert repo_slug == "my-repo"
assert pr_number == 1
def mock_get_content_of_file(self, project_key, repository_slug, filename, at=None, markup=None):
content_map = {
'9c1cffdd9f276074bfb6fb3b70fbee62d298b058': 'file\nwith\nsome\nlines\nto\nemulate\na\nreal\nfile\n',
@ -251,7 +244,7 @@ class TestBitbucketServerProvider:
FilePatchInfo(
'file\nwith\nmultiple\nlines\nto\nemulate\na\nreal\nfile',
'readme\nwithout\nsome\nlines\nto\nsimulate\na\nreal\nfile',
'--- \n+++ \n@@ -1,9 +1,9 @@\n-file\n-with\n-multiple\n+readme\n+without\n+some\n lines\n to\n-emulate\n+simulate\n a\n real\n file\n',
'--- \n+++ \n@@ -1,9 +1,9 @@\n-file\n-with\n-multiple\n+readme\n+without\n+some\n lines\n to\n-emulate\n+simulate\n a\n real\n file',
'Readme.md',
edit_type=EDIT_TYPE.MODIFIED,
)
@ -273,7 +266,7 @@ class TestBitbucketServerProvider:
FilePatchInfo(
'file\nwith\nsome\nlines\nto\nemulate\na\nreal\nfile',
'readme\nwithout\nsome\nlines\nto\nsimulate\na\nreal\nfile',
'--- \n+++ \n@@ -1,9 +1,9 @@\n-file\n-with\n+readme\n+without\n some\n lines\n to\n-emulate\n+simulate\n a\n real\n file\n',
'--- \n+++ \n@@ -1,9 +1,9 @@\n-file\n-with\n+readme\n+without\n some\n lines\n to\n-emulate\n+simulate\n a\n real\n file',
'Readme.md',
edit_type=EDIT_TYPE.MODIFIED,
)
@ -295,7 +288,7 @@ class TestBitbucketServerProvider:
FilePatchInfo(
'file\nwith\nsome\nlines\nto\nemulate\na\nreal\nfile',
'readme\nwithout\nsome\nlines\nto\nsimulate\na\nreal\nfile',
'--- \n+++ \n@@ -1,9 +1,9 @@\n-file\n-with\n+readme\n+without\n some\n lines\n to\n-emulate\n+simulate\n a\n real\n file\n',
'--- \n+++ \n@@ -1,9 +1,9 @@\n-file\n-with\n+readme\n+without\n some\n lines\n to\n-emulate\n+simulate\n a\n real\n file',
'Readme.md',
edit_type=EDIT_TYPE.MODIFIED,
)

View File

@ -47,10 +47,13 @@ class TestConvertToMarkdown:
def test_simple_dictionary_input(self):
input_data = {'review': {
'estimated_effort_to_review_[1-5]': '1, because the changes are minimal and straightforward, focusing on a single functionality addition.\n',
'relevant_tests': 'No\n', 'possible_issues': 'No\n', 'security_concerns': 'No\n'}}
'relevant_tests': 'No\n', 'possible_issues': 'No\n', 'security_concerns': 'No\n'}, 'code_feedback': [
{'relevant_file': '``pr_agent/git_providers/git_provider.py\n``', 'language': 'python\n',
'suggestion': "Consider raising an exception or logging a warning when 'pr_url' attribute is not found. This can help in debugging issues related to the absence of 'pr_url' in instances where it's expected. [important]\n",
'relevant_line': '[return ""](https://github.com/Codium-ai/pr-agent-pro/pull/102/files#diff-52d45f12b836f77ed1aef86e972e65404634ea4e2a6083fb71a9b0f9bb9e062fR199)'}]}
expected_output = f'{PRReviewHeader.REGULAR.value} 🔍\n\nHere are some key observations to aid the review process:\n\n<table>\n<tr><td>⏱️&nbsp;<strong>Estimated effort to review</strong>: 1 🔵⚪⚪⚪⚪</td></tr>\n<tr><td>🧪&nbsp;<strong>No relevant tests</strong></td></tr>\n<tr><td>&nbsp;<strong>Possible issues</strong>: No\n</td></tr>\n<tr><td>🔒&nbsp;<strong>No security concerns identified</strong></td></tr>\n</table>'
expected_output = f'{PRReviewHeader.REGULAR.value} 🔍\n\nHere are some key observations to aid the review process:\n\n<table>\n<tr><td>⏱️&nbsp;<strong>Estimated effort to review</strong>: 1 🔵⚪⚪⚪⚪</td></tr>\n<tr><td>🧪&nbsp;<strong>No relevant tests</strong></td></tr>\n<tr><td>&nbsp;<strong>Possible issues</strong>: No\n</td></tr>\n<tr><td>🔒&nbsp;<strong>No security concerns identified</strong></td></tr>\n</table>\n\n\n<details><summary> <strong>Code feedback:</strong></summary>\n\n<hr><table><tr><td>relevant file</td><td>pr_agent/git_providers/git_provider.py\n</td></tr><tr><td>suggestion &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</td><td>\n\n<strong>\n\nConsider raising an exception or logging a warning when \'pr_url\' attribute is not found. This can help in debugging issues related to the absence of \'pr_url\' in instances where it\'s expected. [important]\n\n</strong>\n</td></tr><tr><td>relevant line</td><td><a href=\'https://github.com/Codium-ai/pr-agent-pro/pull/102/files#diff-52d45f12b836f77ed1aef86e972e65404634ea4e2a6083fb71a9b0f9bb9e062fR199\'>return ""</a></td></tr></table><hr>\n\n</details>'
assert convert_to_markdown_v2(input_data).strip() == expected_output.strip()
@ -64,7 +67,7 @@ class TestConvertToMarkdown:
assert convert_to_markdown_v2(input_data).strip() == expected_output.strip()
def test_dictionary_with_empty_dictionaries(self):
input_data = {'review': {}}
input_data = {'review': {}, 'code_feedback': [{}]}
expected_output = ''

View File

@ -3,7 +3,6 @@ import pytest
from pr_agent.algo.git_patch_processing import extend_patch
from pr_agent.algo.pr_processing import pr_generate_extended_diff
from pr_agent.algo.token_handler import TokenHandler
from pr_agent.algo.utils import load_large_diff
from pr_agent.config_loader import get_settings
@ -146,8 +145,8 @@ class TestExtendedPatchMoreLines:
# Check that with no extra lines, the patches are the same as the original patches
p0 = patches_extended_no_extra_lines[0].strip()
p1 = patches_extended_no_extra_lines[1].strip()
assert p0 == "## File: 'file1'\n" + pr_languages[0]['files'][0].patch.strip()
assert p1 == "## File: 'file2'\n" + pr_languages[0]['files'][1].patch.strip()
assert p0 == '## file1\n' + pr_languages[0]['files'][0].patch.strip()
assert p1 == '## file2\n' + pr_languages[0]['files'][1].patch.strip()
patches_extended_with_extra_lines, total_tokens, patches_extended_tokens = pr_generate_extended_diff(
pr_languages, token_handler, add_line_numbers_to_hunks=False,
@ -155,37 +154,5 @@ class TestExtendedPatchMoreLines:
patch_extra_lines_after=1
)
p0_extended = patches_extended_with_extra_lines[0].strip()
assert p0_extended == "## File: 'file1'\n\n@@ -3,8 +3,8 @@ \n line0\n line1\n-original content\n+modified content\n line2\n line3\n line4\n line5\n line6"
class TestLoadLargeDiff:
def test_no_newline(self):
patch = load_large_diff("test.py",
"""\
old content 1
some new content
another line
""",
"""
old content 1
old content 2""")
patch_expected="""\
---
+++
@@ -1,3 +1,3 @@
-
old content 1
- old content 2
+ some new content
+ another line
"""
assert patch == patch_expected
def test_empty_inputs(self):
assert load_large_diff("test.py", "", "") == ""
assert load_large_diff("test.py", None, None) == ""
assert (load_large_diff("test.py", "content\n", "") ==
'--- \n+++ \n@@ -1 +1 @@\n-\n+content\n')
assert p0_extended == '## file1\n\n@@ -3,8 +3,8 @@ \n line0\n line1\n-original content\n+modified content\n line2\n line3\n line4\n line5\n line6'