mirror of
https://github.com/qodo-ai/pr-agent.git
synced 2025-07-04 12:50:38 +08:00
Compare commits
1 Commits
test-almog
...
ofir-frd-p
| Author | SHA1 | Date | |
|---|---|---|---|
| 661a4571f9 |
19
README.md
19
README.md
@ -4,8 +4,8 @@
|
||||
|
||||
|
||||
<picture>
|
||||
<source media="(prefers-color-scheme: dark)" srcset="https://www.qodo.ai/wp-content/uploads/2025/02/PR-Agent-Purple-2.png">
|
||||
<source media="(prefers-color-scheme: light)" srcset="https://www.qodo.ai/wp-content/uploads/2025/02/PR-Agent-Purple-2.png">
|
||||
<source media="(prefers-color-scheme: dark)" srcset="https://codium.ai/images/pr_agent/logo-dark.png" width="330">
|
||||
<source media="(prefers-color-scheme: light)" srcset="https://codium.ai/images/pr_agent/logo-light.png" width="330">
|
||||
<img src="https://codium.ai/images/pr_agent/logo-light.png" alt="logo" width="330">
|
||||
|
||||
</picture>
|
||||
@ -74,7 +74,7 @@ to
|
||||
|
||||
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://www.qodo.ai/images/pr_agent/implement1.png?v=2" width="512"></kbd>
|
||||
<kbd><img src="https://www.qodo.ai/images/pr_agent/implement1.png" width="512"></kbd>
|
||||
|
||||
|
||||
### Jan 1, 2025
|
||||
@ -92,7 +92,7 @@ Following feedback from the community, we have addressed two vulnerabilities ide
|
||||
Supported commands per platform:
|
||||
|
||||
| | | 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/) | ✅ | ✅ | ✅ | ✅ |
|
||||
@ -111,7 +111,6 @@ Supported commands per platform:
|
||||
| | [Custom Prompt](https://qodo-merge-docs.qodo.ai/tools/custom_prompt/) 💎 | ✅ | ✅ | ✅ | |
|
||||
| | [Test](https://qodo-merge-docs.qodo.ai/tools/test/) 💎 | ✅ | ✅ | | |
|
||||
| | [Implement](https://qodo-merge-docs.qodo.ai/tools/implement/) 💎 | ✅ | ✅ | ✅ | |
|
||||
| | [Auto-Approve](https://qodo-merge-docs.qodo.ai/tools/improve/?h=auto#auto-approval) 💎 | ✅ | ✅ | ✅ | |
|
||||
| | | | | | |
|
||||
| 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) | ✅ | ✅ | ✅ | ✅ |
|
||||
@ -124,7 +123,7 @@ Supported commands per platform:
|
||||
| | [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/) 💎 | ✅ | ✅ | | |
|
||||
| | [Static code analysis](https://qodo-merge-docs.qodo.ai/core-abilities/static_code_analysis/) 💎 | ✅ | ✅ | ✅ | |
|
||||
| | [Global and wiki configurations](https://qodo-merge-docs.qodo.ai/usage-guide/configuration_options/) 💎 | ✅ | ✅ | ✅ | |
|
||||
| | [PR interactive actions](https://www.qodo.ai/images/pr_agent/pr-actions.mp4) 💎 | ✅ | ✅ | | |
|
||||
| | [Impact Evaluation](https://qodo-merge-docs.qodo.ai/core-abilities/impact_evaluation/) 💎 | ✅ | ✅ | | |
|
||||
@ -214,6 +213,12 @@ Note that this is a promotional bot, suitable only for initial experimentation.
|
||||
It does not have 'edit' access to your repo, for example, so it cannot update the PR description or add labels (`@CodiumAI-Agent /describe` will publish PR description as a comment). In addition, the bot cannot be used on private repositories, as it does not have access to the files there.
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
To set up your own PR-Agent, see the [Installation](https://qodo-merge-docs.qodo.ai/installation/) section below.
|
||||
Note that when you set your own PR-Agent or use Qodo hosted PR-Agent, there is no need to mention `@CodiumAI-Agent ...`. Instead, directly start with the command, e.g., `/ask ...`.
|
||||
|
||||
---
|
||||
|
||||
|
||||
@ -268,6 +273,8 @@ https://openai.com/enterprise-privacy
|
||||
|
||||
## Links
|
||||
|
||||
[](https://discord.gg/kG35uSHDBc)
|
||||
|
||||
- Discord community: https://discord.gg/kG35uSHDBc
|
||||
- Qodo site: https://www.qodo.ai/
|
||||
- Blog: https://www.qodo.ai/blog/
|
||||
|
||||
@ -1,315 +0,0 @@
|
||||
<div class="search-section">
|
||||
<h1>AI Docs Search</h1>
|
||||
<p class="search-description">
|
||||
Search through our documentation using AI-powered natural language queries.
|
||||
</p>
|
||||
<div class="search-container">
|
||||
<input
|
||||
type="text"
|
||||
id="searchInput"
|
||||
class="search-input"
|
||||
placeholder="Enter your search term..."
|
||||
>
|
||||
<button id="searchButton" class="search-button">Search</button>
|
||||
</div>
|
||||
<div id="spinner" class="spinner-container" style="display: none;">
|
||||
<div class="spinner"></div>
|
||||
</div>
|
||||
<div id="results" class="results-container"></div>
|
||||
</div>
|
||||
|
||||
<style>
|
||||
Untitled
|
||||
.search-section {
|
||||
max-width: 800px;
|
||||
margin: 0 auto;
|
||||
padding: 0 1rem 2rem;
|
||||
}
|
||||
|
||||
h1 {
|
||||
color: #666;
|
||||
font-size: 2.125rem;
|
||||
font-weight: normal;
|
||||
margin-bottom: 1rem;
|
||||
}
|
||||
|
||||
.search-description {
|
||||
color: #666;
|
||||
font-size: 1rem;
|
||||
line-height: 1.5;
|
||||
margin-bottom: 2rem;
|
||||
max-width: 800px;
|
||||
}
|
||||
|
||||
.search-container {
|
||||
display: flex;
|
||||
gap: 1rem;
|
||||
max-width: 800px;
|
||||
margin: 0; /* Changed from auto to 0 to align left */
|
||||
}
|
||||
|
||||
.search-input {
|
||||
flex: 1;
|
||||
padding: 0 0.875rem;
|
||||
border: 1px solid #ddd;
|
||||
border-radius: 4px;
|
||||
font-size: 0.9375rem;
|
||||
outline: none;
|
||||
height: 40px; /* Explicit height */
|
||||
}
|
||||
|
||||
.search-input:focus {
|
||||
border-color: #6c63ff;
|
||||
}
|
||||
|
||||
.search-button {
|
||||
padding: 0 1.25rem;
|
||||
background-color: #2196F3;
|
||||
color: white;
|
||||
border: none;
|
||||
border-radius: 4px;
|
||||
cursor: pointer;
|
||||
font-size: 0.875rem;
|
||||
transition: background-color 0.2s;
|
||||
height: 40px; /* Match the height of search input */
|
||||
display: flex;
|
||||
align-items: center;
|
||||
justify-content: center;
|
||||
}
|
||||
|
||||
.search-button:hover {
|
||||
background-color: #1976D2;
|
||||
}
|
||||
|
||||
.spinner-container {
|
||||
display: flex;
|
||||
justify-content: center;
|
||||
margin-top: 2rem;
|
||||
}
|
||||
|
||||
.spinner {
|
||||
width: 40px;
|
||||
height: 40px;
|
||||
border: 4px solid #f3f3f3;
|
||||
border-top: 4px solid #2196F3;
|
||||
border-radius: 50%;
|
||||
animation: spin 1s linear infinite;
|
||||
}
|
||||
|
||||
@keyframes spin {
|
||||
0% { transform: rotate(0deg); }
|
||||
100% { transform: rotate(360deg); }
|
||||
}
|
||||
|
||||
.results-container {
|
||||
margin-top: 2rem;
|
||||
max-width: 800px;
|
||||
}
|
||||
|
||||
.result-item {
|
||||
padding: 1rem;
|
||||
border: 1px solid #ddd;
|
||||
border-radius: 4px;
|
||||
margin-bottom: 1rem;
|
||||
}
|
||||
|
||||
.result-title {
|
||||
font-size: 1.2rem;
|
||||
color: #2196F3;
|
||||
margin-bottom: 0.5rem;
|
||||
}
|
||||
|
||||
.result-description {
|
||||
color: #666;
|
||||
}
|
||||
|
||||
.error-message {
|
||||
color: #dc3545;
|
||||
padding: 1rem;
|
||||
border: 1px solid #dc3545;
|
||||
border-radius: 4px;
|
||||
margin-top: 1rem;
|
||||
}
|
||||
|
||||
.markdown-content {
|
||||
line-height: 1.6;
|
||||
color: var(--md-typeset-color);
|
||||
background: var(--md-default-bg-color);
|
||||
border: 1px solid var(--md-default-fg-color--lightest);
|
||||
border-radius: 12px;
|
||||
padding: 1.5rem;
|
||||
box-shadow: 0 2px 4px rgba(0,0,0,0.05);
|
||||
position: relative;
|
||||
margin-top: 2rem;
|
||||
}
|
||||
|
||||
.markdown-content::before {
|
||||
content: '';
|
||||
position: absolute;
|
||||
top: -8px;
|
||||
left: 24px;
|
||||
width: 16px;
|
||||
height: 16px;
|
||||
background: var(--md-default-bg-color);
|
||||
border-left: 1px solid var(--md-default-fg-color--lightest);
|
||||
border-top: 1px solid var(--md-default-fg-color--lightest);
|
||||
transform: rotate(45deg);
|
||||
}
|
||||
|
||||
.markdown-content > *:first-child {
|
||||
margin-top: 0;
|
||||
padding-top: 0;
|
||||
}
|
||||
|
||||
.markdown-content p {
|
||||
margin-bottom: 1rem;
|
||||
}
|
||||
|
||||
.markdown-content p:last-child {
|
||||
margin-bottom: 0;
|
||||
}
|
||||
|
||||
.markdown-content code {
|
||||
background: var(--md-code-bg-color);
|
||||
color: var(--md-code-fg-color);
|
||||
padding: 0.2em 0.4em;
|
||||
border-radius: 3px;
|
||||
font-size: 0.9em;
|
||||
font-family: ui-monospace, SFMono-Regular, SF Mono, Menlo, Consolas, Liberation Mono, monospace;
|
||||
}
|
||||
|
||||
.markdown-content pre {
|
||||
background: var(--md-code-bg-color);
|
||||
padding: 1rem;
|
||||
border-radius: 6px;
|
||||
overflow-x: auto;
|
||||
margin: 1rem 0;
|
||||
}
|
||||
|
||||
.markdown-content pre code {
|
||||
background: none;
|
||||
padding: 0;
|
||||
font-size: 0.9em;
|
||||
}
|
||||
|
||||
[data-md-color-scheme="slate"] .markdown-content {
|
||||
box-shadow: 0 2px 4px rgba(0,0,0,0.1);
|
||||
}
|
||||
|
||||
</style>
|
||||
|
||||
<script src="https://cdnjs.cloudflare.com/ajax/libs/marked/9.1.6/marked.min.js"></script>
|
||||
|
||||
<script>
|
||||
window.addEventListener('load', function() {
|
||||
function displayResults(responseText) {
|
||||
const resultsContainer = document.getElementById('results');
|
||||
const spinner = document.getElementById('spinner');
|
||||
const searchContainer = document.querySelector('.search-container');
|
||||
|
||||
// Hide spinner
|
||||
spinner.style.display = 'none';
|
||||
|
||||
// Scroll to search bar
|
||||
searchContainer.scrollIntoView({ behavior: 'smooth', block: 'start' });
|
||||
|
||||
try {
|
||||
const results = JSON.parse(responseText);
|
||||
|
||||
marked.setOptions({
|
||||
breaks: true,
|
||||
gfm: true,
|
||||
headerIds: false,
|
||||
sanitize: false
|
||||
});
|
||||
|
||||
const htmlContent = marked.parse(results.message);
|
||||
|
||||
resultsContainer.className = 'markdown-content';
|
||||
resultsContainer.innerHTML = htmlContent;
|
||||
|
||||
// Scroll after content is rendered
|
||||
setTimeout(() => {
|
||||
const searchContainer = document.querySelector('.search-container');
|
||||
const offset = 55; // Offset from top in pixels
|
||||
const elementPosition = searchContainer.getBoundingClientRect().top;
|
||||
const offsetPosition = elementPosition + window.pageYOffset - offset;
|
||||
|
||||
window.scrollTo({
|
||||
top: offsetPosition,
|
||||
behavior: 'smooth'
|
||||
});
|
||||
}, 100);
|
||||
} catch (error) {
|
||||
console.error('Error parsing results:', error);
|
||||
resultsContainer.innerHTML = '<div class="error-message">Error processing results</div>';
|
||||
}
|
||||
}
|
||||
|
||||
async function performSearch() {
|
||||
const searchInput = document.getElementById('searchInput');
|
||||
const resultsContainer = document.getElementById('results');
|
||||
const spinner = document.getElementById('spinner');
|
||||
const searchTerm = searchInput.value.trim();
|
||||
|
||||
if (!searchTerm) {
|
||||
resultsContainer.innerHTML = '<div class="error-message">Please enter a search term</div>';
|
||||
return;
|
||||
}
|
||||
|
||||
// Show spinner, clear results
|
||||
spinner.style.display = 'flex';
|
||||
resultsContainer.innerHTML = '';
|
||||
|
||||
try {
|
||||
const data = {
|
||||
"query": searchTerm
|
||||
};
|
||||
|
||||
const options = {
|
||||
method: 'POST',
|
||||
headers: {
|
||||
'accept': 'text/plain',
|
||||
'content-type': 'application/json',
|
||||
},
|
||||
body: JSON.stringify(data)
|
||||
};
|
||||
|
||||
// const API_ENDPOINT = 'http://0.0.0.0:3000/api/v1/docs_help';
|
||||
const API_ENDPOINT = 'https://help.merge.qodo.ai/api/v1/docs_help';
|
||||
|
||||
const response = await fetch(API_ENDPOINT, options);
|
||||
|
||||
if (!response.ok) {
|
||||
throw new Error(`HTTP error! status: ${response.status}`);
|
||||
}
|
||||
|
||||
const responseText = await response.text();
|
||||
displayResults(responseText);
|
||||
} catch (error) {
|
||||
spinner.style.display = 'none';
|
||||
resultsContainer.innerHTML = `
|
||||
<div class="error-message">
|
||||
An error occurred while searching. Please try again later.
|
||||
</div>
|
||||
`;
|
||||
}
|
||||
}
|
||||
|
||||
// Add event listeners
|
||||
const searchButton = document.getElementById('searchButton');
|
||||
const searchInput = document.getElementById('searchInput');
|
||||
|
||||
if (searchButton) {
|
||||
searchButton.addEventListener('click', performSearch);
|
||||
}
|
||||
|
||||
if (searchInput) {
|
||||
searchInput.addEventListener('keypress', function(e) {
|
||||
if (e.key === 'Enter') {
|
||||
performSearch();
|
||||
}
|
||||
});
|
||||
}
|
||||
});
|
||||
</script>
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 15 KiB After Width: | Height: | Size: 4.2 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 57 KiB After Width: | Height: | Size: 263 KiB |
File diff suppressed because one or more lines are too long
|
Before Width: | Height: | Size: 24 KiB After Width: | Height: | Size: 1.2 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 17 KiB After Width: | Height: | Size: 8.7 KiB |
@ -1,5 +1,5 @@
|
||||
## Local and global metadata injection with multi-stage analysis
|
||||
1\.
|
||||
(1)
|
||||
Qodo Merge initially retrieves for each PR the following data:
|
||||
|
||||
- PR title and branch name
|
||||
@ -11,7 +11,7 @@ Qodo Merge initially retrieves for each PR the following data:
|
||||
!!! tip "Tip: Organization-level metadata"
|
||||
In addition to the inputs above, Qodo Merge can incorporate supplementary preferences provided by the user, like [`extra_instructions` and `organization best practices`](https://qodo-merge-docs.qodo.ai/tools/improve/#extra-instructions-and-best-practices). This information can be used to enhance the PR analysis.
|
||||
|
||||
2\.
|
||||
(2)
|
||||
By default, the first command that Qodo Merge executes is [`describe`](https://qodo-merge-docs.qodo.ai/tools/describe/), which generates three types of outputs:
|
||||
|
||||
- PR Type (e.g. bug fix, feature, refactor, etc)
|
||||
@ -49,8 +49,8 @@ __old hunk__
|
||||
...
|
||||
```
|
||||
|
||||
3\. The entire PR files that were retrieved are also used to expand and enhance the PR context (see [Dynamic Context](https://qodo-merge-docs.qodo.ai/core-abilities/dynamic_context/)).
|
||||
(3) The entire PR files that were retrieved are also used to expand and enhance the PR context (see [Dynamic Context](https://qodo-merge-docs.qodo.ai/core-abilities/dynamic_context/)).
|
||||
|
||||
|
||||
4\. All the metadata described above represents several level of cumulative analysis - ranging from hunk level, to file level, to PR level, to organization level.
|
||||
(4) All the metadata described above represents several level of cumulative analysis - ranging from hunk level, to file level, to PR level, to organization level.
|
||||
This comprehensive approach enables Qodo Merge AI models to generate more precise and contextually relevant suggestions and feedback.
|
||||
|
||||
@ -35,7 +35,6 @@ Qodo Merge offers extensive pull request functionalities across various git prov
|
||||
| | ⮑ [Inline file summary](https://qodo-merge-docs.qodo.ai/tools/describe/#inline-file-summary){:target="_blank"} 💎 | ✅ | ✅ | | ✅ |
|
||||
| | Improve | ✅ | ✅ | ✅ | ✅ |
|
||||
| | ⮑ Extended | ✅ | ✅ | ✅ | ✅ |
|
||||
| | [Auto-Approve](https://qodo-merge-docs.qodo.ai/tools/improve/#auto-approval) 💎 | ✅ | ✅ | ✅ | |
|
||||
| | [Custom Prompt](./tools/custom_prompt.md){:target="_blank"} 💎 | ✅ | ✅ | ✅ | ✅ |
|
||||
| | Reflect and Review | ✅ | ✅ | ✅ | ✅ |
|
||||
| | Update CHANGELOG.md | ✅ | ✅ | ✅ | ️ |
|
||||
@ -54,7 +53,8 @@ Qodo Merge offers extensive pull request functionalities across various git prov
|
||||
| | Repo language prioritization | ✅ | ✅ | ✅ | ✅ |
|
||||
| | Adaptive and token-aware file patch fitting | ✅ | ✅ | ✅ | ✅ |
|
||||
| | Multiple models support | ✅ | ✅ | ✅ | ✅ |
|
||||
| | [Static code analysis](./core-abilities/static_code_analysis/){:target="_blank"} 💎 | ✅ | ✅ | | |
|
||||
| | 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](https://www.codium.ai/pricing/){:target="_blank"}, and not in the open-source version.
|
||||
|
||||
@ -14,5 +14,6 @@ An example result:
|
||||
|
||||
{width=750}
|
||||
|
||||
!!! note "Language that are currently supported:"
|
||||
Python, Java, C++, JavaScript, TypeScript, C#.
|
||||
**Notes**
|
||||
|
||||
- Language that are currently supported: Python, Java, C++, JavaScript, TypeScript, C#.
|
||||
|
||||
@ -38,20 +38,20 @@ where `https://real_link_to_image` is the direct link to the image.
|
||||
Note that GitHub has a built-in mechanism of pasting images in comments. However, pasted image does not provide a direct link.
|
||||
To get a direct link to an image, we recommend using the following scheme:
|
||||
|
||||
1\. First, post a comment that contains **only** the image:
|
||||
1) First, post a comment that contains **only** the image:
|
||||
|
||||
{width=512}
|
||||
|
||||
2\. Quote reply to that comment:
|
||||
2) Quote reply to that comment:
|
||||
|
||||
{width=512}
|
||||
|
||||
3\. In the screen opened, type the question below the image:
|
||||
3) In the screen opened, type the question below the image:
|
||||
|
||||
{width=512}
|
||||
{width=512}
|
||||
|
||||
4\. Post the comment, and receive the answer:
|
||||
4) Post the comment, and receive the answer:
|
||||
|
||||
{width=512}
|
||||
|
||||
|
||||
@ -51,8 +51,8 @@ Results obtained with the prompt above:
|
||||
|
||||
## Configuration options
|
||||
|
||||
- `prompt`: the prompt for the tool. It should be a multi-line string.
|
||||
`prompt`: the prompt for the tool. It should be a multi-line string.
|
||||
|
||||
- `num_code_suggestions_per_chunk`: number of code suggestions provided by the 'custom_prompt' tool, per chunk. Default is 4.
|
||||
`num_code_suggestions`: number of code suggestions provided by the 'custom_prompt' tool. Default is 4.
|
||||
|
||||
- `enable_help_text`: if set to true, the tool will display a help text in the comment. Default is true.
|
||||
`enable_help_text`: if set to true, the tool will display a help text in the comment. Default is true.
|
||||
|
||||
@ -143,7 +143,7 @@ The marker `pr_agent:type` will be replaced with the PR type, `pr_agent:summary`
|
||||
|
||||
{width=512}
|
||||
|
||||
becomes
|
||||
→
|
||||
|
||||
{width=512}
|
||||
|
||||
|
||||
@ -27,6 +27,7 @@ You can state a name of a specific component in the PR to get documentation only
|
||||
- `docs_style`: The exact style of the documentation (for python docstring). you can choose between: `google`, `numpy`, `sphinx`, `restructuredtext`, `plain`. Default is `sphinx`.
|
||||
- `extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...".
|
||||
|
||||
!!! note "Notes"
|
||||
- The following languages are currently supported: Python, Java, C++, JavaScript, TypeScript, C#.
|
||||
**Notes**
|
||||
|
||||
- Language that are currently fully supported: Python, Java, C++, JavaScript, TypeScript, C#.
|
||||
- This tool can also be triggered interactively by using the [`analyze`](./analyze.md) tool.
|
||||
|
||||
@ -10,9 +10,8 @@ It leverages LLM technology to transform PR comments and review suggestions into
|
||||
|
||||
### For Reviewers
|
||||
|
||||
Reviewers can request code changes by:
|
||||
|
||||
1. Selecting the code block to be modified.
|
||||
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>
|
||||
@ -47,8 +46,7 @@ You can reference and implement changes from any comment by:
|
||||
Note that the implementation will occur within the review discussion thread.
|
||||
|
||||
|
||||
**Configuration options**
|
||||
|
||||
- Use `/implement` to implement code change within and based on the review discussion.
|
||||
- Use `/implement <code-change-description>` inside a review discussion to implement specific instructions.
|
||||
- Use `/implement <link-to-review-comment>` to indirectly call the tool from any comment.
|
||||
**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>
|
||||
|
||||
@ -9,9 +9,8 @@ The tool can be triggered automatically every time a new PR is [opened](../usage
|
||||
|
||||
{width=512}
|
||||
|
||||
!!! note "The following features are available only for Qodo Merge 💎 users:"
|
||||
- The `Apply this suggestion` checkbox, which interactively converts a suggestion into a committable code comment
|
||||
- The `More` checkbox to generate additional suggestions
|
||||
Note that the `Apply this suggestion` checkbox, which interactively converts a suggestion into a commitable code comment, is available only for Qodo Merge💎 users.
|
||||
|
||||
|
||||
## Example usage
|
||||
|
||||
@ -53,10 +52,9 @@ num_code_suggestions_per_chunk = ...
|
||||
- The `pr_commands` lists commands that will be executed automatically when a PR is opened.
|
||||
- The `[pr_code_suggestions]` section contains the configurations for the `improve` tool you want to edit (if any)
|
||||
|
||||
### Assessing Impact
|
||||
>`💎 feature`
|
||||
### Assessing Impact 💎
|
||||
|
||||
Qodo Merge tracks two types of implementations for tracking implemented suggestions:
|
||||
Note that Qodo Merge tracks two types of implementations:
|
||||
|
||||
- Direct implementation - when the user directly applies the suggestion by clicking the `Apply` checkbox.
|
||||
- Indirect implementation - when the user implements the suggestion in their IDE environment. In this case, Qodo Merge will utilize, after each commit, a dedicated logic to identify if a suggestion was implemented, and will mark it as implemented.
|
||||
@ -69,8 +67,8 @@ In post-process, Qodo Merge counts the number of suggestions that were implement
|
||||
|
||||
{width=512}
|
||||
|
||||
## Suggestion tracking
|
||||
>`💎 feature. Platforms supported: GitHub, GitLab`
|
||||
## Suggestion tracking 💎
|
||||
`Platforms supported: GitHub, GitLab`
|
||||
|
||||
Qodo Merge employs a novel detection system to automatically [identify](https://qodo-merge-docs.qodo.ai/core-abilities/impact_evaluation/) AI code suggestions that PR authors have accepted and implemented.
|
||||
|
||||
@ -103,6 +101,8 @@ The `improve` tool can be further customized by providing additional instruction
|
||||
|
||||
### 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.
|
||||
|
||||
@ -118,9 +118,9 @@ extra_instructions="""\
|
||||
```
|
||||
Use triple quotes to write multi-line instructions. Use bullet points or numbers to make the instructions more readable.
|
||||
|
||||
### Best practices
|
||||
### Best practices 💎
|
||||
|
||||
> `💎 feature. Platforms supported: GitHub, GitLab, Bitbucket`
|
||||
>`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.
|
||||
@ -191,11 +191,11 @@ And the label will be: `{organization_name} best practice`.
|
||||
|
||||
{width=512}
|
||||
|
||||
### Auto best practices
|
||||
### Auto best practices 💎
|
||||
|
||||
>`💎 feature. Platforms supported: GitHub.`
|
||||
>`Platforms supported: GitHub`
|
||||
|
||||
`Auto best practices` is a novel Qodo Merge capability that:
|
||||
'Auto best practices' is a novel Qodo Merge capability that:
|
||||
|
||||
1. Identifies recurring patterns from accepted suggestions
|
||||
2. **Automatically** generates [best practices page](https://github.com/qodo-ai/pr-agent/wiki/.pr_agent_auto_best_practices) based on what your team consistently values
|
||||
@ -228,8 +228,7 @@ max_patterns = 5
|
||||
```
|
||||
|
||||
|
||||
### Combining 'extra instructions' and 'best practices'
|
||||
> `💎 feature`
|
||||
### Combining `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", ...)
|
||||
|
||||
@ -268,8 +267,6 @@ dual_publishing_score_threshold = x
|
||||
Where x represents the minimum score threshold (>=) for suggestions to be presented as commitable PR comments in addition to the table. Default is -1 (disabled).
|
||||
|
||||
### Self-review
|
||||
> `💎 feature`
|
||||
|
||||
If you set in a configuration file:
|
||||
```toml
|
||||
[pr_code_suggestions]
|
||||
@ -313,56 +310,21 @@ code_suggestions_self_review_text = "... (your text here) ..."
|
||||
|
||||
To prevent unauthorized approvals, this configuration defaults to false, and cannot be altered through online comments; enabling requires a direct update to the configuration file and a commit to the repository. This ensures that utilizing the feature demands a deliberate documented decision by the repository owner.
|
||||
|
||||
### Auto-approval
|
||||
> `💎 feature. Platforms supported: GitHub, GitLab, Bitbucket`
|
||||
|
||||
Under specific conditions, Qodo Merge can auto-approve a PR when a specific comment is invoked, or when the PR meets certain criteria.
|
||||
|
||||
To ensure safety, the auto-approval feature is disabled by default. To enable auto-approval, you need to actively set, in a pre-defined _configuration file_, the following:
|
||||
```toml
|
||||
[config]
|
||||
enable_auto_approval = true
|
||||
```
|
||||
Note that this specific flag cannot be set with a command line argument, only in the configuration file, committed to the repository.
|
||||
This ensures that enabling auto-approval is a deliberate decision by the repository owner.
|
||||
|
||||
**(1) Auto-approval by commenting**
|
||||
|
||||
After enabling, by commenting on a PR:
|
||||
```
|
||||
/review auto_approve
|
||||
```
|
||||
Qodo Merge will automatically approve the PR, and add a comment with the approval.
|
||||
|
||||
**(2) Auto-approval when the PR meets certain criteria**
|
||||
|
||||
There are two criteria that can be set for auto-approval:
|
||||
|
||||
- **Review effort score**
|
||||
```toml
|
||||
[config]
|
||||
auto_approve_for_low_review_effort = X # X is a number between 1 to 5
|
||||
```
|
||||
When the [review effort score](https://www.qodo.ai/images/pr_agent/review3.png) is lower or equal to X, the PR will be auto-approved.
|
||||
|
||||
___
|
||||
- **No code suggestions**
|
||||
```toml
|
||||
[config]
|
||||
auto_approve_for_no_suggestions = true
|
||||
```
|
||||
When no [code suggestion](https://www.qodo.ai/images/pr_agent/code_suggestions_as_comment_closed.png) were found for the PR, the PR will be auto-approved.
|
||||
|
||||
### How many code suggestions are generated?
|
||||
Qodo Merge uses a dynamic strategy to generate code suggestions based on the size of the pull request (PR). Here's how it works:
|
||||
|
||||
#### 1. Chunking large PRs
|
||||
1) Chunking large PRs:
|
||||
|
||||
- Qodo Merge divides large PRs into 'chunks'.
|
||||
- Each chunk contains up to `pr_code_suggestions.max_context_tokens` tokens (default: 14,000).
|
||||
|
||||
#### 2. Generating suggestions
|
||||
|
||||
2) Generating suggestions:
|
||||
|
||||
- For each chunk, Qodo Merge generates up to `pr_code_suggestions.num_code_suggestions_per_chunk` suggestions (default: 4).
|
||||
|
||||
|
||||
This approach has two main benefits:
|
||||
|
||||
- Scalability: The number of suggestions scales with the PR size, rather than being fixed.
|
||||
@ -404,10 +366,6 @@ Note: Chunking is primarily relevant for large PRs. For most PRs (up to 500 line
|
||||
<td><b>apply_suggestions_checkbox</b></td>
|
||||
<td> Enable the checkbox to create a committable suggestion. Default is true.</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><b>enable_more_suggestions_checkbox</b></td>
|
||||
<td> Enable the checkbox to generate more suggestions. Default is true.</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><b>enable_help_text</b></td>
|
||||
<td>If set to true, the tool will display a help text in the comment. Default is true.</td>
|
||||
|
||||
@ -18,7 +18,7 @@ The tool will generate code suggestions for the selected component (if no compon
|
||||
|
||||
{width=768}
|
||||
|
||||
!!! note "Notes"
|
||||
**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.
|
||||
|
||||
|
||||
@ -114,6 +114,16 @@ You can enable\disable the `review` tool to add specific labels to the PR:
|
||||
</tr>
|
||||
</table>
|
||||
|
||||
!!! example "Auto-approval"
|
||||
|
||||
If enabled, the `review` tool can approve a PR when a specific comment, `/review auto_approve`, is invoked.
|
||||
|
||||
<table>
|
||||
<tr>
|
||||
<td><b>enable_auto_approval</b></td>
|
||||
<td>If set to true, the tool will approve the PR when invoked with the 'auto_approve' command. Default is false. This flag can be changed only from a configuration file.</td>
|
||||
</tr>
|
||||
</table>
|
||||
|
||||
## Usage Tips
|
||||
|
||||
@ -165,6 +175,23 @@ You can enable\disable the `review` tool to add specific labels to the PR:
|
||||
Use triple quotes to write multi-line instructions. Use bullet points to make the instructions more readable.
|
||||
|
||||
|
||||
!!! tip "Auto-approval"
|
||||
|
||||
Qodo Merge can approve a PR when a specific comment is invoked.
|
||||
|
||||
To ensure safety, the auto-approval feature is disabled by default. To enable auto-approval, you need to actively set in a pre-defined configuration file the following:
|
||||
```
|
||||
[pr_reviewer]
|
||||
enable_auto_approval = true
|
||||
```
|
||||
(this specific flag cannot be set with a command line argument, only in the configuration file, committed to the repository)
|
||||
|
||||
|
||||
After enabling, by commenting on a PR:
|
||||
```
|
||||
/review auto_approve
|
||||
```
|
||||
Qodo Merge will automatically approve the PR, and add a comment with the approval.
|
||||
|
||||
|
||||
!!! tip "Code suggestions"
|
||||
|
||||
@ -16,17 +16,14 @@ It can be invoked manually by commenting on any PR:
|
||||
|
||||
Note that to perform retrieval, the `similar_issue` tool indexes all the repo previous issues (once).
|
||||
|
||||
### Selecting a Vector Database
|
||||
Configure your preferred database by changing the `pr_similar_issue` parameter in `configuration.toml` file.
|
||||
|
||||
#### Available Options
|
||||
Choose from the following Vector Databases:
|
||||
**Select VectorDBs** by changing `pr_similar_issue` parameter in `configuration.toml` file
|
||||
|
||||
2 VectorDBs are available to switch in
|
||||
1. LanceDB
|
||||
2. Pinecone
|
||||
|
||||
#### Pinecone Configuration
|
||||
To use Pinecone with the `similar issue` tool, add these credentials to `.secrets.toml` (or set as environment variables):
|
||||
To enable usage of the '**similar issue**' tool for Pinecone, you need to set the following keys in `.secrets.toml` (or in the relevant environment variables):
|
||||
|
||||
```
|
||||
[pinecone]
|
||||
|
||||
@ -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)):
|
||||
|
||||
!!! note "Notes"
|
||||
- The following languages are currently supported: Python, Java, C++, JavaScript, TypeScript, C#.
|
||||
**Notes** <br>
|
||||
- The following languages are currently supported: Python, Java, C++, JavaScript, TypeScript, C#. <br>
|
||||
- This tool can also be triggered interactively by using the [`analyze`](./analyze.md) tool.
|
||||
|
||||
|
||||
|
||||
@ -142,11 +142,13 @@ Qodo Merge allows you to automatically ignore certain PRs based on various crite
|
||||
|
||||
- PRs with specific titles (using regex matching)
|
||||
- PRs between specific branches (using regex matching)
|
||||
- PRs not from specific folders
|
||||
- PRs that don't include changes from specific folders (using regex matching)
|
||||
- PRs containing specific labels
|
||||
- PRs opened by specific users
|
||||
|
||||
### Ignoring PRs with specific titles
|
||||
### Example usage
|
||||
|
||||
#### Ignoring PRs with specific titles
|
||||
|
||||
To ignore PRs with a specific title such as "[Bump]: ...", you can add the following to your `configuration.toml` file:
|
||||
|
||||
@ -157,7 +159,7 @@ 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
|
||||
#### Ignoring PRs between specific branches
|
||||
|
||||
To ignore PRs from specific source or target branches, you can add the following to your `configuration.toml` file:
|
||||
|
||||
@ -170,7 +172,7 @@ 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 not from specific folders
|
||||
#### Ignoring PRs that don't include changes from specific folders
|
||||
|
||||
To allow only specific folders (often needed in large monorepos), set:
|
||||
|
||||
@ -179,9 +181,9 @@ To allow only specific folders (often needed in large monorepos), set:
|
||||
allow_only_specific_folders=['folder1','folder2']
|
||||
```
|
||||
|
||||
For the configuration above, automatic feedback will only be triggered when the PR changes include files where 'folder1' or 'folder2' is in the file path
|
||||
For the configuration above, automatic feedback will only be triggered when the PR changes include files from 'folder1' or 'folder2'
|
||||
|
||||
### Ignoring PRs containing specific labels
|
||||
#### Ignoring PRs containg specific labels
|
||||
|
||||
To ignore PRs containg specific labels, you can add the following to your `configuration.toml` file:
|
||||
|
||||
@ -192,7 +194,7 @@ 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
|
||||
#### Ignoring PRs from specific users
|
||||
|
||||
Qodo Merge automatically identifies and ignores pull requests created by bots using:
|
||||
|
||||
|
||||
@ -14,12 +14,12 @@ Examples of invoking the different tools via the CLI:
|
||||
|
||||
**Notes:**
|
||||
|
||||
1. in addition to editing your local configuration file, you can also change any configuration value by adding it to the command line:
|
||||
(1) in addition to editing your local configuration file, you can also change any configuration value by adding it to the command line:
|
||||
```
|
||||
python -m pr_agent.cli --pr_url=<pr_url> /review --pr_reviewer.extra_instructions="focus on the file: ..."
|
||||
```
|
||||
|
||||
2. You can print results locally, without publishing them, by setting in `configuration.toml`:
|
||||
(2) You can print results locally, without publishing them, by setting in `configuration.toml`:
|
||||
```
|
||||
[config]
|
||||
publish_output=false
|
||||
@ -27,9 +27,14 @@ verbosity_level=2
|
||||
```
|
||||
This is useful for debugging or experimenting with different tools.
|
||||
|
||||
3. **git provider**: The [git_provider](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L5) field in a configuration file determines the GIT provider that will be used by Qodo Merge. Currently, the following providers are supported:
|
||||
`github` **(default)**, `gitlab`, `bitbucket`, `azure`, `codecommit`, `local`, and `gerrit`.
|
||||
(3)
|
||||
|
||||
**git provider**: The [git_provider](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L5) field in a configuration file determines the GIT provider that will be used by Qodo Merge. Currently, the following providers are supported:
|
||||
`
|
||||
"github", "gitlab", "bitbucket", "azure", "codecommit", "local", "gerrit"
|
||||
`
|
||||
|
||||
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:
|
||||
|
||||
@ -30,14 +30,6 @@ model="" # the OpenAI model you've deployed on Azure (e.g. gpt-4o)
|
||||
fallback_models=["..."]
|
||||
```
|
||||
|
||||
Passing custom headers to the underlying LLM Model API can be done by setting extra_headers parameter to litellm.
|
||||
```
|
||||
[litellm]
|
||||
extra_headers='{"projectId": "<authorized projectId >", ...}') #The value of this setting should be a JSON string representing the desired headers, a ValueError is thrown otherwise.
|
||||
```
|
||||
This enables users to pass authorization tokens or API keys, when routing requests through an API management gateway.
|
||||
|
||||
|
||||
### 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)
|
||||
@ -197,27 +189,15 @@ key = ...
|
||||
|
||||
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:
|
||||
|
||||
1. Set the model name in the configuration file:
|
||||
(1) Set the model name in the configuration file:
|
||||
```
|
||||
[config]
|
||||
model="custom_model_name"
|
||||
fallback_models=["custom_model_name"]
|
||||
```
|
||||
2. Set the maximal tokens for the model:
|
||||
(2) Set the maximal tokens for the model:
|
||||
```
|
||||
[config]
|
||||
custom_model_max_tokens= ...
|
||||
```
|
||||
3. Go to [litellm documentation](https://litellm.vercel.app/docs/proxy/quick_start#supported-llms), find the model you want to use, and set the relevant environment variables.
|
||||
|
||||
4. Most reasoning models do not support chat-style inputs (`system` and `user` messages) or temperature settings.
|
||||
To bypass chat templates and temperature controls, set `config.custom_reasoning_model = true` in your configuration file.
|
||||
|
||||
## Dedicated parameters
|
||||
|
||||
### OpenAI models
|
||||
|
||||
[config]
|
||||
reasoning_efffort= = "medium" # "low", "medium", "high"
|
||||
|
||||
With the OpenAI models that support reasoning effort (eg: o3-mini), you can specify its reasoning effort via `config` section. The default value is `medium`. You can change it to `high` or `low` based on your usage.
|
||||
(3) Go to [litellm documentation](https://litellm.vercel.app/docs/proxy/quick_start#supported-llms), find the model you want to use, and set the relevant environment variables.
|
||||
|
||||
@ -8,6 +8,7 @@ The models supported by Qodo Merge are:
|
||||
|
||||
- `claude-3-5-sonnet`
|
||||
- `gpt-4o`
|
||||
- `deepseek-r1`
|
||||
- `o3-mini`
|
||||
|
||||
To restrict Qodo Merge to using only `Claude-3.5-sonnet`, add this setting:
|
||||
@ -23,11 +24,11 @@ To restrict Qodo Merge to using only `GPT-4o`, add this setting:
|
||||
model="gpt-4o"
|
||||
```
|
||||
|
||||
[//]: # (To restrict Qodo Merge to using only `deepseek-r1` us-hosted, add this setting:)
|
||||
[//]: # (```)
|
||||
[//]: # ([config])
|
||||
[//]: # (model="deepseek/r1")
|
||||
[//]: # (```)
|
||||
To restrict Qodo Merge to using only `deepseek-r1`, add this setting:
|
||||
```
|
||||
[config]
|
||||
model="deepseek/r1"
|
||||
```
|
||||
|
||||
To restrict Qodo Merge to using only `o3-mini`, add this setting:
|
||||
```
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
site_name: Qodo Merge (and open-source PR-Agent)
|
||||
repo_url: https://github.com/qodo-ai/pr-agent
|
||||
repo_name: Qodo-ai/pr-agent
|
||||
repo_url: https://github.com/Codium-ai/pr-agent
|
||||
repo_name: Codium-ai/pr-agent
|
||||
|
||||
nav:
|
||||
- Overview:
|
||||
@ -58,7 +58,6 @@ nav:
|
||||
- Data Privacy: 'chrome-extension/data_privacy.md'
|
||||
- FAQ:
|
||||
- FAQ: 'faq/index.md'
|
||||
- AI Docs Search: 'ai_search/index.md'
|
||||
# - Code Fine-tuning Benchmark: 'finetuning_benchmark/index.md'
|
||||
|
||||
theme:
|
||||
@ -154,4 +153,4 @@ markdown_extensions:
|
||||
|
||||
|
||||
copyright: |
|
||||
© 2025 <a href="https://www.codium.ai/" target="_blank" rel="noopener">QodoAI</a>
|
||||
© 2024 <a href="https://www.codium.ai/" target="_blank" rel="noopener">CodiumAI</a>
|
||||
|
||||
@ -82,7 +82,7 @@
|
||||
|
||||
<footer class="wrapper">
|
||||
<div class="container">
|
||||
<p class="footer-text">© 2025 <a href="https://www.qodo.ai/" target="_blank" rel="noopener">Qodo</a></p>
|
||||
<p class="footer-text">© 2024 <a href="https://www.qodo.ai/" target="_blank" rel="noopener">Qodo</a></p>
|
||||
<div class="footer-links">
|
||||
<a href="https://qodo-gen-docs.qodo.ai/">Qodo Gen</a>
|
||||
<p>|</p>
|
||||
|
||||
@ -3,7 +3,6 @@ from functools import partial
|
||||
|
||||
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.cli_args import CliArgs
|
||||
from pr_agent.algo.utils import update_settings_from_args
|
||||
from pr_agent.config_loader import get_settings
|
||||
from pr_agent.git_providers.utils import apply_repo_settings
|
||||
@ -61,15 +60,25 @@ class PRAgent:
|
||||
else:
|
||||
action, *args = request
|
||||
|
||||
# validate args
|
||||
is_valid, arg = CliArgs.validate_user_args(args)
|
||||
if not is_valid:
|
||||
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 '{arg}' is forbidden. Use instead a configuration file."
|
||||
f"CLI argument for param '{forbidden_arg}' is forbidden. Use instead a configuration file."
|
||||
)
|
||||
return False
|
||||
|
||||
# Update settings from args
|
||||
args = update_settings_from_args(args)
|
||||
|
||||
action = action.lstrip("/").lower()
|
||||
|
||||
@ -43,14 +43,13 @@ MAX_TOKENS = {
|
||||
'vertex_ai/claude-3-opus@20240229': 100000,
|
||||
'vertex_ai/claude-3-5-sonnet@20240620': 100000,
|
||||
'vertex_ai/claude-3-5-sonnet-v2@20241022': 100000,
|
||||
'vertex_ai/claude-3-7-sonnet@20250219': 200000,
|
||||
'vertex_ai/gemini-1.5-pro': 1048576,
|
||||
'vertex_ai/gemini-1.5-flash': 1048576,
|
||||
'vertex_ai/gemini-2.0-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': 1048576,
|
||||
'gemini/gemini-2.0-flash-exp': 1048576,
|
||||
'codechat-bison': 6144,
|
||||
'codechat-bison-32k': 32000,
|
||||
'anthropic.claude-instant-v1': 100000,
|
||||
@ -59,7 +58,6 @@ MAX_TOKENS = {
|
||||
'anthropic/claude-3-opus-20240229': 100000,
|
||||
'anthropic/claude-3-5-sonnet-20240620': 100000,
|
||||
'anthropic/claude-3-5-sonnet-20241022': 100000,
|
||||
'anthropic/claude-3-7-sonnet-20250219': 200000,
|
||||
'anthropic/claude-3-5-haiku-20241022': 100000,
|
||||
'bedrock/anthropic.claude-instant-v1': 100000,
|
||||
'bedrock/anthropic.claude-v2': 100000,
|
||||
@ -69,7 +67,6 @@ 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/anthropic.claude-3-7-sonnet-20250219-v1:0': 200000,
|
||||
"bedrock/us.anthropic.claude-3-5-sonnet-20241022-v2:0": 100000,
|
||||
'claude-3-5-sonnet': 100000,
|
||||
'groq/llama3-8b-8192': 8192,
|
||||
@ -104,8 +101,3 @@ NO_SUPPORT_TEMPERATURE_MODELS = [
|
||||
"o3-mini-2025-01-31",
|
||||
"o1-preview"
|
||||
]
|
||||
|
||||
SUPPORT_REASONING_EFFORT_MODELS = [
|
||||
"o3-mini",
|
||||
"o3-mini-2025-01-31"
|
||||
]
|
||||
|
||||
@ -6,12 +6,11 @@ import requests
|
||||
from litellm import acompletion
|
||||
from tenacity import retry, retry_if_exception_type, stop_after_attempt
|
||||
|
||||
from pr_agent.algo import NO_SUPPORT_TEMPERATURE_MODELS, SUPPORT_REASONING_EFFORT_MODELS, USER_MESSAGE_ONLY_MODELS
|
||||
from pr_agent.algo import NO_SUPPORT_TEMPERATURE_MODELS, USER_MESSAGE_ONLY_MODELS
|
||||
from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
|
||||
from pr_agent.algo.utils import ReasoningEffort, get_version
|
||||
from pr_agent.algo.utils import get_version
|
||||
from pr_agent.config_loader import get_settings
|
||||
from pr_agent.log import get_logger
|
||||
import json
|
||||
|
||||
OPENAI_RETRIES = 5
|
||||
|
||||
@ -102,9 +101,6 @@ class LiteLLMAIHandler(BaseAiHandler):
|
||||
# Model that doesn't support temperature argument
|
||||
self.no_support_temperature_models = NO_SUPPORT_TEMPERATURE_MODELS
|
||||
|
||||
# Models that support reasoning effort
|
||||
self.support_reasoning_models = SUPPORT_REASONING_EFFORT_MODELS
|
||||
|
||||
def prepare_logs(self, response, system, user, resp, finish_reason):
|
||||
response_log = response.dict().copy()
|
||||
response_log['system'] = system
|
||||
@ -209,7 +205,7 @@ class LiteLLMAIHandler(BaseAiHandler):
|
||||
{"type": "image_url", "image_url": {"url": img_path}}]
|
||||
|
||||
# Currently, some models do not support a separate system and user prompts
|
||||
if model in self.user_message_only_models or get_settings().config.custom_reasoning_model:
|
||||
if model in self.user_message_only_models:
|
||||
user = f"{system}\n\n\n{user}"
|
||||
system = ""
|
||||
get_logger().info(f"Using model {model}, combining system and user prompts")
|
||||
@ -231,17 +227,9 @@ class LiteLLMAIHandler(BaseAiHandler):
|
||||
}
|
||||
|
||||
# Add temperature only if model supports it
|
||||
if model not in self.no_support_temperature_models and not get_settings().config.custom_reasoning_model:
|
||||
get_logger().info(f"Adding temperature with value {temperature} to model {model}.")
|
||||
if model not in self.no_support_temperature_models:
|
||||
kwargs["temperature"] = temperature
|
||||
|
||||
# Add reasoning_effort if model supports it
|
||||
if (model in self.support_reasoning_models):
|
||||
supported_reasoning_efforts = [ReasoningEffort.HIGH.value, ReasoningEffort.MEDIUM.value, ReasoningEffort.LOW.value]
|
||||
reasoning_effort = get_settings().config.reasoning_effort if (get_settings().config.reasoning_effort in supported_reasoning_efforts) else ReasoningEffort.MEDIUM.value
|
||||
get_logger().info(f"Adding reasoning_effort with value {reasoning_effort} to model {model}.")
|
||||
kwargs["reasoning_effort"] = reasoning_effort
|
||||
|
||||
if get_settings().litellm.get("enable_callbacks", False):
|
||||
kwargs = self.add_litellm_callbacks(kwargs)
|
||||
|
||||
@ -255,16 +243,6 @@ class LiteLLMAIHandler(BaseAiHandler):
|
||||
if self.repetition_penalty:
|
||||
kwargs["repetition_penalty"] = self.repetition_penalty
|
||||
|
||||
#Added support for extra_headers while using litellm to call underlying model, via a api management gateway, would allow for passing custom headers for security and authorization
|
||||
if get_settings().get("LITELLM.EXTRA_HEADERS", None):
|
||||
try:
|
||||
litellm_extra_headers = json.loads(get_settings().litellm.extra_headers)
|
||||
if not isinstance(litellm_extra_headers, dict):
|
||||
raise ValueError("LITELLM.EXTRA_HEADERS must be a JSON object")
|
||||
except json.JSONDecodeError as e:
|
||||
raise ValueError(f"LITELLM.EXTRA_HEADERS contains invalid JSON: {str(e)}")
|
||||
kwargs["extra_headers"] = litellm_extra_headers
|
||||
|
||||
get_logger().debug("Prompts", artifact={"system": system, "user": user})
|
||||
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
|
||||
@ -1,34 +0,0 @@
|
||||
from base64 import b64decode
|
||||
import hashlib
|
||||
|
||||
class CliArgs:
|
||||
@staticmethod
|
||||
def validate_user_args(args: list) -> (bool, str):
|
||||
try:
|
||||
if not args:
|
||||
return True, ""
|
||||
|
||||
# decode forbidden args
|
||||
_encoded_args = 'ZW5hYmxlX2F1dG9fYXBwcm92YWw=:YXBwcm92ZV9wcl9vbl9zZWxmX3Jldmlldw==:YmFzZV91cmw=:dXJs:YXBwX25hbWU=:c2VjcmV0X3Byb3ZpZGVy:Z2l0X3Byb3ZpZGVy:c2tpcF9rZXlz:b3BlbmFpLmtleQ==:QU5BTFlUSUNTX0ZPTERFUg==:dXJp:YXBwX2lk:d2ViaG9va19zZWNyZXQ=:YmVhcmVyX3Rva2Vu:UEVSU09OQUxfQUNDRVNTX1RPS0VO:b3ZlcnJpZGVfZGVwbG95bWVudF90eXBl:cHJpdmF0ZV9rZXk=:bG9jYWxfY2FjaGVfcGF0aA==:ZW5hYmxlX2xvY2FsX2NhY2hl:amlyYV9iYXNlX3VybA==:YXBpX2Jhc2U=:YXBpX3R5cGU=:YXBpX3ZlcnNpb24=:c2tpcF9rZXlz'
|
||||
forbidden_cli_args = []
|
||||
for e in _encoded_args.split(':'):
|
||||
forbidden_cli_args.append(b64decode(e).decode())
|
||||
|
||||
# lowercase all forbidden args
|
||||
for i, _ in enumerate(forbidden_cli_args):
|
||||
forbidden_cli_args[i] = forbidden_cli_args[i].lower()
|
||||
if '.' not in forbidden_cli_args[i]:
|
||||
forbidden_cli_args[i] = '.' + forbidden_cli_args[i]
|
||||
|
||||
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_word in forbidden_cli_args:
|
||||
if forbidden_arg_word in arg_word:
|
||||
return False, forbidden_arg_word
|
||||
return True, ""
|
||||
except Exception as e:
|
||||
return False, str(e)
|
||||
|
||||
|
||||
@ -9,12 +9,11 @@ from pr_agent.log import get_logger
|
||||
|
||||
|
||||
def extend_patch(original_file_str, patch_str, patch_extra_lines_before=0,
|
||||
patch_extra_lines_after=0, filename: str = "", new_file_str="") -> str:
|
||||
patch_extra_lines_after=0, filename: str = "") -> str:
|
||||
if not patch_str or (patch_extra_lines_before == 0 and patch_extra_lines_after == 0) or not original_file_str:
|
||||
return patch_str
|
||||
|
||||
original_file_str = decode_if_bytes(original_file_str)
|
||||
new_file_str = decode_if_bytes(new_file_str)
|
||||
if not original_file_str:
|
||||
return patch_str
|
||||
|
||||
@ -23,7 +22,7 @@ def extend_patch(original_file_str, patch_str, patch_extra_lines_before=0,
|
||||
|
||||
try:
|
||||
extended_patch_str = process_patch_lines(patch_str, original_file_str,
|
||||
patch_extra_lines_before, patch_extra_lines_after, new_file_str)
|
||||
patch_extra_lines_before, patch_extra_lines_after)
|
||||
except Exception as e:
|
||||
get_logger().warning(f"Failed to extend patch: {e}", artifact={"traceback": traceback.format_exc()})
|
||||
return patch_str
|
||||
@ -53,13 +52,12 @@ def should_skip_patch(filename):
|
||||
return False
|
||||
|
||||
|
||||
def process_patch_lines(patch_str, original_file_str, patch_extra_lines_before, patch_extra_lines_after, new_file_str=""):
|
||||
def process_patch_lines(patch_str, original_file_str, patch_extra_lines_before, patch_extra_lines_after):
|
||||
allow_dynamic_context = get_settings().config.allow_dynamic_context
|
||||
patch_extra_lines_before_dynamic = get_settings().config.max_extra_lines_before_dynamic_context
|
||||
|
||||
file_original_lines = original_file_str.splitlines()
|
||||
file_new_lines = new_file_str.splitlines() if new_file_str else []
|
||||
len_original_lines = len(file_original_lines)
|
||||
original_lines = original_file_str.splitlines()
|
||||
len_original_lines = len(original_lines)
|
||||
patch_lines = patch_str.splitlines()
|
||||
extended_patch_lines = []
|
||||
|
||||
@ -75,12 +73,12 @@ def process_patch_lines(patch_str, original_file_str, patch_extra_lines_before,
|
||||
if match:
|
||||
# finish processing previous hunk
|
||||
if is_valid_hunk and (start1 != -1 and patch_extra_lines_after > 0):
|
||||
delta_lines_original = [f' {line}' for line in file_original_lines[start1 + size1 - 1:start1 + size1 - 1 + patch_extra_lines_after]]
|
||||
extended_patch_lines.extend(delta_lines_original)
|
||||
delta_lines = [f' {line}' for line in original_lines[start1 + size1 - 1:start1 + size1 - 1 + patch_extra_lines_after]]
|
||||
extended_patch_lines.extend(delta_lines)
|
||||
|
||||
section_header, size1, size2, start1, start2 = extract_hunk_headers(match)
|
||||
|
||||
is_valid_hunk = check_if_hunk_lines_matches_to_file(i, file_original_lines, patch_lines, start1)
|
||||
is_valid_hunk = check_if_hunk_lines_matches_to_file(i, original_lines, patch_lines, start1)
|
||||
|
||||
if is_valid_hunk and (patch_extra_lines_before > 0 or patch_extra_lines_after > 0):
|
||||
def _calc_context_limits(patch_lines_before):
|
||||
@ -95,15 +93,12 @@ def process_patch_lines(patch_str, original_file_str, patch_extra_lines_before,
|
||||
extended_size2 = max(extended_size2 - delta_cap, size2)
|
||||
return extended_start1, extended_size1, extended_start2, extended_size2
|
||||
|
||||
if allow_dynamic_context and file_new_lines:
|
||||
if allow_dynamic_context:
|
||||
extended_start1, extended_size1, extended_start2, extended_size2 = \
|
||||
_calc_context_limits(patch_extra_lines_before_dynamic)
|
||||
|
||||
lines_before_original = file_original_lines[extended_start1 - 1:start1 - 1]
|
||||
lines_before_new = file_new_lines[extended_start2 - 1:start2 - 1]
|
||||
lines_before = original_lines[extended_start1 - 1:start1 - 1]
|
||||
found_header = False
|
||||
if lines_before_original == lines_before_new: # Making sure no changes from a previous hunk
|
||||
for i, line, in enumerate(lines_before_original):
|
||||
for i, line, in enumerate(lines_before):
|
||||
if section_header in line:
|
||||
found_header = True
|
||||
# Update start and size in one line each
|
||||
@ -112,11 +107,6 @@ def process_patch_lines(patch_str, original_file_str, patch_extra_lines_before,
|
||||
# get_logger().debug(f"Found section header in line {i} before the hunk")
|
||||
section_header = ''
|
||||
break
|
||||
else:
|
||||
get_logger().debug(f"Extra lines before hunk are different in original and new file - dynamic context",
|
||||
artifact={"lines_before_original": lines_before_original,
|
||||
"lines_before_new": lines_before_new})
|
||||
|
||||
if not found_header:
|
||||
# get_logger().debug(f"Section header not found in the extra lines before the hunk")
|
||||
extended_start1, extended_size1, extended_start2, extended_size2 = \
|
||||
@ -125,23 +115,11 @@ def process_patch_lines(patch_str, original_file_str, patch_extra_lines_before,
|
||||
extended_start1, extended_size1, extended_start2, extended_size2 = \
|
||||
_calc_context_limits(patch_extra_lines_before)
|
||||
|
||||
# check if extra lines before hunk are different in original and new file
|
||||
delta_lines_original = [f' {line}' for line in file_original_lines[extended_start1 - 1:start1 - 1]]
|
||||
if file_new_lines:
|
||||
delta_lines_new = [f' {line}' for line in file_new_lines[extended_start2 - 1:start2 - 1]]
|
||||
if delta_lines_original != delta_lines_new:
|
||||
get_logger().debug(f"Extra lines before hunk are different in original and new file",
|
||||
artifact={"delta_lines_original": delta_lines_original,
|
||||
"delta_lines_new": delta_lines_new})
|
||||
extended_start1 = start1
|
||||
extended_size1 = size1
|
||||
extended_start2 = start2
|
||||
extended_size2 = size2
|
||||
delta_lines_original = []
|
||||
delta_lines = [f' {line}' for line in original_lines[extended_start1 - 1:start1 - 1]]
|
||||
|
||||
# logic to remove section header if its in the extra delta lines (in dynamic context, this is also done)
|
||||
if section_header and not allow_dynamic_context:
|
||||
for line in delta_lines_original:
|
||||
for line in delta_lines:
|
||||
if section_header in line:
|
||||
section_header = '' # remove section header if it is in the extra delta lines
|
||||
break
|
||||
@ -150,12 +128,12 @@ def process_patch_lines(patch_str, original_file_str, patch_extra_lines_before,
|
||||
extended_size1 = size1
|
||||
extended_start2 = start2
|
||||
extended_size2 = size2
|
||||
delta_lines_original = []
|
||||
delta_lines = []
|
||||
extended_patch_lines.append('')
|
||||
extended_patch_lines.append(
|
||||
f'@@ -{extended_start1},{extended_size1} '
|
||||
f'+{extended_start2},{extended_size2} @@ {section_header}')
|
||||
extended_patch_lines.extend(delta_lines_original) # one to zero based
|
||||
extended_patch_lines.extend(delta_lines) # one to zero based
|
||||
continue
|
||||
extended_patch_lines.append(line)
|
||||
except Exception as e:
|
||||
@ -164,14 +142,15 @@ def process_patch_lines(patch_str, original_file_str, patch_extra_lines_before,
|
||||
|
||||
# finish processing last hunk
|
||||
if start1 != -1 and patch_extra_lines_after > 0 and is_valid_hunk:
|
||||
delta_lines_original = file_original_lines[start1 + size1 - 1:start1 + size1 - 1 + patch_extra_lines_after]
|
||||
delta_lines = original_lines[start1 + size1 - 1:start1 + size1 - 1 + patch_extra_lines_after]
|
||||
# add space at the beginning of each extra line
|
||||
delta_lines_original = [f' {line}' for line in delta_lines_original]
|
||||
extended_patch_lines.extend(delta_lines_original)
|
||||
delta_lines = [f' {line}' for line in delta_lines]
|
||||
extended_patch_lines.extend(delta_lines)
|
||||
|
||||
extended_patch_str = '\n'.join(extended_patch_lines)
|
||||
return extended_patch_str
|
||||
|
||||
|
||||
def check_if_hunk_lines_matches_to_file(i, original_lines, patch_lines, start1):
|
||||
"""
|
||||
Check if the hunk lines match the original file content. We saw cases where the hunk header line doesn't match the original file content, and then
|
||||
@ -181,18 +160,8 @@ def check_if_hunk_lines_matches_to_file(i, original_lines, patch_lines, start1):
|
||||
try:
|
||||
if i + 1 < len(patch_lines) and patch_lines[i + 1][0] == ' ': # an existing line in the file
|
||||
if patch_lines[i + 1].strip() != original_lines[start1 - 1].strip():
|
||||
# check if different encoding is needed
|
||||
original_line = original_lines[start1 - 1].strip()
|
||||
for encoding in ['iso-8859-1', 'latin-1', 'ascii', 'utf-16']:
|
||||
try:
|
||||
if original_line.encode(encoding).decode().strip() == patch_lines[i + 1].strip():
|
||||
get_logger().info(f"Detected different encoding in hunk header line {start1}, needed encoding: {encoding}")
|
||||
return False # we still want to avoid extending the hunk. But we don't want to log an error
|
||||
except:
|
||||
pass
|
||||
|
||||
is_valid_hunk = False
|
||||
get_logger().info(
|
||||
get_logger().error(
|
||||
f"Invalid hunk in PR, line {start1} in hunk header doesn't match the original file content")
|
||||
except:
|
||||
pass
|
||||
@ -319,7 +288,7 @@ __old hunk__
|
||||
"""
|
||||
# if the file was deleted, return a message indicating that the file was deleted
|
||||
if hasattr(file, 'edit_type') and file.edit_type == EDIT_TYPE.DELETED:
|
||||
return f"\n\n## File '{file.filename.strip()}' was deleted\n"
|
||||
return f"\n\n## file '{file.filename.strip()}' was deleted\n"
|
||||
|
||||
patch_with_lines_str = f"\n\n## File: '{file.filename.strip()}'\n"
|
||||
patch_lines = patch.splitlines()
|
||||
@ -394,7 +363,7 @@ __old hunk__
|
||||
return patch_with_lines_str.rstrip()
|
||||
|
||||
|
||||
def extract_hunk_lines_from_patch(patch: str, file_name, line_start, line_end, side, remove_trailing_chars: bool = True) -> tuple[str, str]:
|
||||
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 = ""
|
||||
@ -442,8 +411,4 @@ def extract_hunk_lines_from_patch(patch: str, file_name, line_start, line_end, s
|
||||
get_logger().error(f"Failed to extract hunk lines from patch: {e}", artifact={"traceback": traceback.format_exc()})
|
||||
return "", ""
|
||||
|
||||
if remove_trailing_chars:
|
||||
patch_with_lines_str = patch_with_lines_str.rstrip()
|
||||
selected_lines = selected_lines.rstrip()
|
||||
|
||||
return patch_with_lines_str, selected_lines
|
||||
return patch_with_lines_str.rstrip(), selected_lines.rstrip()
|
||||
|
||||
@ -195,15 +195,13 @@ def pr_generate_extended_diff(pr_languages: list,
|
||||
for lang in pr_languages:
|
||||
for file in lang['files']:
|
||||
original_file_content_str = file.base_file
|
||||
new_file_content_str = file.head_file
|
||||
patch = file.patch
|
||||
if not patch:
|
||||
continue
|
||||
|
||||
# extend each patch with extra lines of context
|
||||
extended_patch = extend_patch(original_file_content_str, patch,
|
||||
patch_extra_lines_before, patch_extra_lines_after, file.filename,
|
||||
new_file_str=new_file_content_str)
|
||||
patch_extra_lines_before, patch_extra_lines_after, file.filename)
|
||||
if not extended_patch:
|
||||
get_logger().warning(f"Failed to extend patch for file: {file.filename}")
|
||||
continue
|
||||
@ -386,8 +384,7 @@ def _get_all_deployments(all_models: List[str]) -> List[str]:
|
||||
def get_pr_multi_diffs(git_provider: GitProvider,
|
||||
token_handler: TokenHandler,
|
||||
model: str,
|
||||
max_calls: int = 5,
|
||||
add_line_numbers: bool = True) -> List[str]:
|
||||
max_calls: int = 5) -> List[str]:
|
||||
"""
|
||||
Retrieves the diff files from a Git provider, sorts them by main language, and generates patches for each file.
|
||||
The patches are split into multiple groups based on the maximum number of tokens allowed for the given model.
|
||||
@ -428,8 +425,7 @@ def get_pr_multi_diffs(git_provider: GitProvider,
|
||||
|
||||
# try first a single run with standard diff string, with patch extension, and no deletions
|
||||
patches_extended, total_tokens, patches_extended_tokens = pr_generate_extended_diff(
|
||||
pr_languages, token_handler,
|
||||
add_line_numbers_to_hunks=add_line_numbers,
|
||||
pr_languages, token_handler, add_line_numbers_to_hunks=True,
|
||||
patch_extra_lines_before=PATCH_EXTRA_LINES_BEFORE,
|
||||
patch_extra_lines_after=PATCH_EXTRA_LINES_AFTER)
|
||||
|
||||
@ -458,12 +454,7 @@ def get_pr_multi_diffs(git_provider: GitProvider,
|
||||
if patch is None:
|
||||
continue
|
||||
|
||||
# Add line numbers and metadata to the patch
|
||||
if add_line_numbers:
|
||||
patch = convert_to_hunks_with_lines_numbers(patch, file)
|
||||
else:
|
||||
patch = f"\n\n## File: '{file.filename.strip()}'\n\n{patch.strip()}\n"
|
||||
|
||||
# add AI-summary metadata to the patch
|
||||
if file.ai_file_summary and get_settings().get("config.enable_ai_metadata", False):
|
||||
patch = add_ai_summary_top_patch(file, patch)
|
||||
|
||||
@ -50,11 +50,6 @@ class PRReviewHeader(str, Enum):
|
||||
REGULAR = "## PR Reviewer Guide"
|
||||
INCREMENTAL = "## Incremental PR Reviewer Guide"
|
||||
|
||||
class ReasoningEffort(str, Enum):
|
||||
HIGH = "high"
|
||||
MEDIUM = "medium"
|
||||
LOW = "low"
|
||||
|
||||
|
||||
class PRDescriptionHeader(str, Enum):
|
||||
CHANGES_WALKTHROUGH = "### **Changes walkthrough** 📝"
|
||||
@ -787,7 +782,6 @@ def try_fix_yaml(response_text: str,
|
||||
# fifth fallback - try to remove leading '+' (sometimes added by AI for 'existing code' and 'improved code')
|
||||
response_text_lines_copy = response_text_lines.copy()
|
||||
for i in range(0, len(response_text_lines_copy)):
|
||||
if response_text_lines_copy[i].startswith('+'):
|
||||
response_text_lines_copy[i] = ' ' + response_text_lines_copy[i][1:]
|
||||
try:
|
||||
data = yaml.safe_load('\n'.join(response_text_lines_copy))
|
||||
|
||||
@ -34,7 +34,7 @@ global_settings = Dynaconf(
|
||||
)
|
||||
|
||||
|
||||
def get_settings(use_context=False):
|
||||
def get_settings():
|
||||
"""
|
||||
Retrieves the current settings.
|
||||
|
||||
|
||||
@ -5,7 +5,6 @@ import itertools
|
||||
import re
|
||||
import time
|
||||
import traceback
|
||||
import json
|
||||
from datetime import datetime
|
||||
from typing import Optional, Tuple
|
||||
from urllib.parse import urlparse
|
||||
@ -888,84 +887,6 @@ class GithubProvider(GitProvider):
|
||||
except:
|
||||
return ""
|
||||
|
||||
def fetch_sub_issues(self, issue_url):
|
||||
"""
|
||||
Fetch sub-issues linked to the given GitHub issue URL using GraphQL via PyGitHub.
|
||||
"""
|
||||
sub_issues = set()
|
||||
|
||||
# Extract owner, repo, and issue number from URL
|
||||
parts = issue_url.rstrip("/").split("/")
|
||||
owner, repo, issue_number = parts[-4], parts[-3], parts[-1]
|
||||
|
||||
try:
|
||||
# Gets Issue ID from Issue Number
|
||||
query = f"""
|
||||
query {{
|
||||
repository(owner: "{owner}", name: "{repo}") {{
|
||||
issue(number: {issue_number}) {{
|
||||
id
|
||||
}}
|
||||
}}
|
||||
}}
|
||||
"""
|
||||
response_tuple = self.github_client._Github__requester.requestJson("POST", "/graphql",
|
||||
input={"query": query})
|
||||
|
||||
# Extract the JSON response from the tuple and parses it
|
||||
if isinstance(response_tuple, tuple) and len(response_tuple) == 3:
|
||||
response_json = json.loads(response_tuple[2])
|
||||
else:
|
||||
get_logger().error(f"Unexpected response format: {response_tuple}")
|
||||
return sub_issues
|
||||
|
||||
|
||||
issue_id = response_json.get("data", {}).get("repository", {}).get("issue", {}).get("id")
|
||||
|
||||
if not issue_id:
|
||||
get_logger().warning(f"Issue ID not found for {issue_url}")
|
||||
return sub_issues
|
||||
|
||||
# Fetch Sub-Issues
|
||||
sub_issues_query = f"""
|
||||
query {{
|
||||
node(id: "{issue_id}") {{
|
||||
... on Issue {{
|
||||
subIssues(first: 10) {{
|
||||
nodes {{
|
||||
url
|
||||
}}
|
||||
}}
|
||||
}}
|
||||
}}
|
||||
}}
|
||||
"""
|
||||
sub_issues_response_tuple = self.github_client._Github__requester.requestJson("POST", "/graphql", input={
|
||||
"query": sub_issues_query})
|
||||
|
||||
# Extract the JSON response from the tuple and parses it
|
||||
if isinstance(sub_issues_response_tuple, tuple) and len(sub_issues_response_tuple) == 3:
|
||||
sub_issues_response_json = json.loads(sub_issues_response_tuple[2])
|
||||
else:
|
||||
get_logger().error("Unexpected sub-issues response format", artifact={"response": sub_issues_response_tuple})
|
||||
return sub_issues
|
||||
|
||||
if not sub_issues_response_json.get("data", {}).get("node", {}).get("subIssues"):
|
||||
get_logger().error("Invalid sub-issues response structure")
|
||||
return sub_issues
|
||||
|
||||
nodes = sub_issues_response_json.get("data", {}).get("node", {}).get("subIssues", {}).get("nodes", [])
|
||||
get_logger().info(f"Github Sub-issues fetched: {len(nodes)}", artifact={"nodes": nodes})
|
||||
|
||||
for sub_issue in nodes:
|
||||
if "url" in sub_issue:
|
||||
sub_issues.add(sub_issue["url"])
|
||||
|
||||
except Exception as e:
|
||||
get_logger().exception(f"Failed to fetch sub-issues. Error: {e}")
|
||||
|
||||
return sub_issues
|
||||
|
||||
def auto_approve(self) -> bool:
|
||||
try:
|
||||
res = self.pr.create_review(event="APPROVE")
|
||||
|
||||
@ -25,6 +25,29 @@ router = APIRouter()
|
||||
secret_provider = get_secret_provider() if get_settings().get("CONFIG.SECRET_PROVIDER") else None
|
||||
|
||||
|
||||
async def get_mr_url_from_commit_sha(commit_sha, gitlab_token, project_id):
|
||||
try:
|
||||
import requests
|
||||
headers = {
|
||||
'Private-Token': f'{gitlab_token}'
|
||||
}
|
||||
# API endpoint to find MRs containing the commit
|
||||
gitlab_url = get_settings().get("GITLAB.URL", 'https://gitlab.com')
|
||||
response = requests.get(
|
||||
f'{gitlab_url}/api/v4/projects/{project_id}/repository/commits/{commit_sha}/merge_requests',
|
||||
headers=headers
|
||||
)
|
||||
merge_requests = response.json()
|
||||
if merge_requests and response.status_code == 200:
|
||||
pr_url = merge_requests[0]['web_url']
|
||||
return pr_url
|
||||
else:
|
||||
get_logger().info(f"No merge requests found for commit: {commit_sha}")
|
||||
return None
|
||||
except Exception as e:
|
||||
get_logger().error(f"Failed to get MR url from commit sha: {e}")
|
||||
return None
|
||||
|
||||
async def handle_request(api_url: str, body: str, log_context: dict, sender_id: str):
|
||||
log_context["action"] = body
|
||||
log_context["event"] = "pull_request" if body == "/review" else "comment"
|
||||
@ -167,14 +190,14 @@ async def gitlab_webhook(background_tasks: BackgroundTasks, request: Request):
|
||||
# ignore bot users
|
||||
if is_bot_user(data):
|
||||
return JSONResponse(status_code=status.HTTP_200_OK, content=jsonable_encoder({"message": "success"}))
|
||||
|
||||
log_context["sender"] = sender
|
||||
if data.get('object_kind') == 'merge_request':
|
||||
if data.get('event_type') != 'note': # not a comment
|
||||
# ignore MRs based on title, labels, source and target branches
|
||||
if not should_process_pr_logic(data):
|
||||
return JSONResponse(status_code=status.HTTP_200_OK, content=jsonable_encoder({"message": "success"}))
|
||||
|
||||
if data['object_attributes'].get('action') in ['open', 'reopen']:
|
||||
log_context["sender"] = sender
|
||||
if data.get('object_kind') == 'merge_request' and data['object_attributes'].get('action') in ['open', 'reopen']:
|
||||
title = data['object_attributes'].get('title')
|
||||
url = data['object_attributes'].get('url')
|
||||
draft = data['object_attributes'].get('draft')
|
||||
get_logger().info(f"New merge request: {url}")
|
||||
@ -183,26 +206,6 @@ async def gitlab_webhook(background_tasks: BackgroundTasks, request: Request):
|
||||
return JSONResponse(status_code=status.HTTP_200_OK, content=jsonable_encoder({"message": "success"}))
|
||||
|
||||
await _perform_commands_gitlab("pr_commands", PRAgent(), url, log_context, data)
|
||||
|
||||
# for push event triggered merge requests
|
||||
elif data['object_attributes'].get('action') == 'update' and data['object_attributes'].get('oldrev'):
|
||||
url = data['object_attributes'].get('url')
|
||||
draft = data['object_attributes'].get('draft')
|
||||
get_logger().info(f"New merge request: {url}")
|
||||
if draft:
|
||||
get_logger().info(f"Skipping draft MR: {url}")
|
||||
return JSONResponse(status_code=status.HTTP_200_OK, content=jsonable_encoder({"message": "success"}))
|
||||
|
||||
commands_on_push = get_settings().get(f"gitlab.push_commands", {})
|
||||
handle_push_trigger = get_settings().get(f"gitlab.handle_push_trigger", False)
|
||||
if not commands_on_push or not handle_push_trigger:
|
||||
get_logger().info("Push event, but no push commands found or push trigger is disabled")
|
||||
return JSONResponse(status_code=status.HTTP_200_OK,
|
||||
content=jsonable_encoder({"message": "success"}))
|
||||
|
||||
get_logger().debug(f'A push event has been received: {url}')
|
||||
await _perform_commands_gitlab("push_commands", PRAgent(), url, log_context, data)
|
||||
|
||||
elif data.get('object_kind') == 'note' and data.get('event_type') == 'note': # comment on MR
|
||||
if 'merge_request' in data:
|
||||
mr = data['merge_request']
|
||||
@ -214,6 +217,29 @@ async def gitlab_webhook(background_tasks: BackgroundTasks, request: Request):
|
||||
body = handle_ask_line(body, data)
|
||||
|
||||
await handle_request(url, body, log_context, sender_id)
|
||||
elif data.get('object_kind') == 'push' and data.get('event_name') == 'push':
|
||||
try:
|
||||
project_id = data['project_id']
|
||||
commit_sha = data['checkout_sha']
|
||||
url = await get_mr_url_from_commit_sha(commit_sha, gitlab_token, project_id)
|
||||
if not url:
|
||||
get_logger().info(f"No MR found for commit: {commit_sha}")
|
||||
return JSONResponse(status_code=status.HTTP_200_OK,
|
||||
content=jsonable_encoder({"message": "success"}))
|
||||
|
||||
# we need first to apply_repo_settings
|
||||
apply_repo_settings(url)
|
||||
commands_on_push = get_settings().get(f"gitlab.push_commands", {})
|
||||
handle_push_trigger = get_settings().get(f"gitlab.handle_push_trigger", False)
|
||||
if not commands_on_push or not handle_push_trigger:
|
||||
get_logger().info("Push event, but no push commands found or push trigger is disabled")
|
||||
return JSONResponse(status_code=status.HTTP_200_OK,
|
||||
content=jsonable_encoder({"message": "success"}))
|
||||
|
||||
get_logger().debug(f'A push event has been received: {url}')
|
||||
await _perform_commands_gitlab("push_commands", PRAgent(), url, log_context, data)
|
||||
except Exception as e:
|
||||
get_logger().error(f"Failed to handle push event: {e}")
|
||||
|
||||
background_tasks.add_task(inner, request_json)
|
||||
end_time = datetime.now()
|
||||
|
||||
@ -17,7 +17,6 @@ use_global_settings_file=true
|
||||
disable_auto_feedback = false
|
||||
ai_timeout=120 # 2minutes
|
||||
skip_keys = []
|
||||
custom_reasoning_model = false # when true, disables system messages and temperature controls for models that don't support chat-style inputs
|
||||
# token limits
|
||||
max_description_tokens = 500
|
||||
max_commits_tokens = 500
|
||||
@ -48,12 +47,6 @@ 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
|
||||
reasoning_effort = "medium" # "low", "medium", "high"
|
||||
# auto approval 💎
|
||||
enable_auto_approval=false # Set to true to enable auto-approval of PRs under certain conditions
|
||||
auto_approve_for_low_review_effort=-1 # -1 to disable, [1-5] to set the threshold for auto-approval
|
||||
auto_approve_for_no_suggestions=false # If true, the PR will be auto-approved if there are no suggestions
|
||||
|
||||
|
||||
[pr_reviewer] # /review #
|
||||
# enable/disable features
|
||||
@ -76,6 +69,9 @@ minimal_commits_for_incremental_review=0
|
||||
minimal_minutes_for_incremental_review=0
|
||||
enable_intro_text=true
|
||||
enable_help_text=false # Determines whether to include help text in the PR review. Enabled by default.
|
||||
# auto approval
|
||||
enable_auto_approval=false
|
||||
|
||||
|
||||
[pr_description] # /describe #
|
||||
publish_labels=false
|
||||
|
||||
@ -187,10 +187,6 @@ Ticket Description:
|
||||
|
||||
|
||||
--PR Info--
|
||||
{%- if date %}
|
||||
|
||||
Today's Date: {{date}}
|
||||
{%- endif %}
|
||||
|
||||
Title: '{{title}}'
|
||||
|
||||
|
||||
@ -1,250 +0,0 @@
|
||||
|
||||
import copy
|
||||
import json
|
||||
import re
|
||||
from datetime import datetime
|
||||
|
||||
import uvicorn
|
||||
from fastapi import APIRouter, FastAPI, Request, status
|
||||
from fastapi.encoders import jsonable_encoder
|
||||
from fastapi.responses import JSONResponse
|
||||
from starlette.background import BackgroundTasks
|
||||
from starlette.middleware import Middleware
|
||||
from starlette_context import context
|
||||
from starlette_context.middleware import RawContextMiddleware
|
||||
|
||||
from pr_agent.agent.pr_agent import PRAgent
|
||||
from pr_agent.algo.utils import update_settings_from_args
|
||||
from pr_agent.config_loader import get_settings, global_settings
|
||||
from pr_agent.git_providers.utils import apply_repo_settings
|
||||
from pr_agent.log import LoggingFormat, get_logger, setup_logger
|
||||
from pr_agent.secret_providers import get_secret_provider
|
||||
|
||||
setup_logger(fmt=LoggingFormat.JSON, level="DEBUG")
|
||||
router = APIRouter()
|
||||
|
||||
secret_provider = get_secret_provider() if get_settings().get("CONFIG.SECRET_PROVIDER") else None
|
||||
|
||||
|
||||
async def handle_request(api_url: str, body: str, log_context: dict, sender_id: str):
|
||||
log_context["action"] = body
|
||||
log_context["event"] = "pull_request" if body == "/review" else "comment"
|
||||
log_context["api_url"] = api_url
|
||||
log_context["app_name"] = get_settings().get("CONFIG.APP_NAME", "Unknown")
|
||||
|
||||
with get_logger().contextualize(**log_context):
|
||||
await PRAgent().handle_request(api_url, body)
|
||||
|
||||
|
||||
async def _perform_commands_gitlab(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
|
||||
get_logger().info(f"Auto feedback is disabled, skipping auto commands for PR {api_url=}", **log_context)
|
||||
return
|
||||
if not should_process_pr_logic(data): # Here we already updated the configurations
|
||||
return
|
||||
commands = get_settings().get(f"gitlab.{commands_conf}", {})
|
||||
get_settings().set("config.is_auto_command", True)
|
||||
for command in commands:
|
||||
try:
|
||||
split_command = command.split(" ")
|
||||
command = split_command[0]
|
||||
args = split_command[1:]
|
||||
other_args = update_settings_from_args(args)
|
||||
new_command = ' '.join([command] + other_args)
|
||||
get_logger().info(f"Performing command: {new_command}")
|
||||
with get_logger().contextualize(**log_context):
|
||||
await agent.handle_request(api_url, new_command)
|
||||
except Exception as e:
|
||||
get_logger().error(f"Failed to perform command {command}: {e}")
|
||||
|
||||
|
||||
def is_bot_user(data) -> bool:
|
||||
try:
|
||||
# logic to ignore bot users (unlike Github, no direct flag for bot users in gitlab)
|
||||
sender_name = data.get("user", {}).get("name", "unknown").lower()
|
||||
bot_indicators = ['codium', 'bot_', 'bot-', '_bot', '-bot']
|
||||
if any(indicator in sender_name for indicator in bot_indicators):
|
||||
get_logger().info(f"Skipping GitLab bot user: {sender_name}")
|
||||
return True
|
||||
except Exception as e:
|
||||
get_logger().error(f"Failed 'is_bot_user' logic: {e}")
|
||||
return False
|
||||
|
||||
|
||||
def should_process_pr_logic(data) -> bool:
|
||||
try:
|
||||
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", [])
|
||||
ignore_mr_labels = get_settings().get("CONFIG.IGNORE_PR_LABELS", [])
|
||||
ignore_mr_source_branches = get_settings().get("CONFIG.IGNORE_PR_SOURCE_BRANCHES", [])
|
||||
ignore_mr_target_branches = get_settings().get("CONFIG.IGNORE_PR_TARGET_BRANCHES", [])
|
||||
|
||||
#
|
||||
if ignore_mr_source_branches:
|
||||
source_branch = data['object_attributes'].get('source_branch')
|
||||
if any(re.search(regex, source_branch) for regex in ignore_mr_source_branches):
|
||||
get_logger().info(
|
||||
f"Ignoring MR with source branch '{source_branch}' due to gitlab.ignore_mr_source_branches settings")
|
||||
return False
|
||||
|
||||
if ignore_mr_target_branches:
|
||||
target_branch = data['object_attributes'].get('target_branch')
|
||||
if any(re.search(regex, target_branch) for regex in ignore_mr_target_branches):
|
||||
get_logger().info(
|
||||
f"Ignoring MR with target branch '{target_branch}' due to gitlab.ignore_mr_target_branches settings")
|
||||
return False
|
||||
|
||||
if ignore_mr_labels:
|
||||
labels = [label['title'] for label in data['object_attributes'].get('labels', [])]
|
||||
if any(label in ignore_mr_labels for label in labels):
|
||||
labels_str = ", ".join(labels)
|
||||
get_logger().info(f"Ignoring MR with labels '{labels_str}' due to gitlab.ignore_mr_labels settings")
|
||||
return False
|
||||
|
||||
if ignore_mr_title:
|
||||
if any(re.search(regex, title) for regex in ignore_mr_title):
|
||||
get_logger().info(f"Ignoring MR with title '{title}' due to gitlab.ignore_mr_title settings")
|
||||
return False
|
||||
except Exception as e:
|
||||
get_logger().error(f"Failed 'should_process_pr_logic': {e}")
|
||||
return True
|
||||
|
||||
|
||||
@router.post("/webhook")
|
||||
async def gitlab_webhook(background_tasks: BackgroundTasks, request: Request):
|
||||
start_time = datetime.now()
|
||||
request_json = await request.json()
|
||||
context["settings"] = copy.deepcopy(global_settings)
|
||||
|
||||
async def inner(data: dict):
|
||||
log_context = {"server_type": "gitlab_app"}
|
||||
get_logger().debug("Received a GitLab webhook")
|
||||
if request.headers.get("X-Gitlab-Token") and secret_provider:
|
||||
request_token = request.headers.get("X-Gitlab-Token")
|
||||
secret = secret_provider.get_secret(request_token)
|
||||
if not secret:
|
||||
get_logger().warning(f"Empty secret retrieved, request_token: {request_token}")
|
||||
return JSONResponse(status_code=status.HTTP_401_UNAUTHORIZED,
|
||||
content=jsonable_encoder({"message": "unauthorized"}))
|
||||
try:
|
||||
secret_dict = json.loads(secret)
|
||||
gitlab_token = secret_dict["gitlab_token"]
|
||||
log_context["token_id"] = secret_dict.get("token_name", secret_dict.get("id", "unknown"))
|
||||
context["settings"].gitlab.personal_access_token = gitlab_token
|
||||
except Exception as e:
|
||||
get_logger().error(f"Failed to validate secret {request_token}: {e}")
|
||||
return JSONResponse(status_code=status.HTTP_401_UNAUTHORIZED, content=jsonable_encoder({"message": "unauthorized"}))
|
||||
elif get_settings().get("GITLAB.SHARED_SECRET"):
|
||||
secret = get_settings().get("GITLAB.SHARED_SECRET")
|
||||
if not request.headers.get("X-Gitlab-Token") == secret:
|
||||
get_logger().error("Failed to validate secret")
|
||||
return JSONResponse(status_code=status.HTTP_401_UNAUTHORIZED, content=jsonable_encoder({"message": "unauthorized"}))
|
||||
else:
|
||||
get_logger().error("Failed to validate secret")
|
||||
return JSONResponse(status_code=status.HTTP_401_UNAUTHORIZED, content=jsonable_encoder({"message": "unauthorized"}))
|
||||
gitlab_token = get_settings().get("GITLAB.PERSONAL_ACCESS_TOKEN", None)
|
||||
if not gitlab_token:
|
||||
get_logger().error("No gitlab token found")
|
||||
return JSONResponse(status_code=status.HTTP_401_UNAUTHORIZED, content=jsonable_encoder({"message": "unauthorized"}))
|
||||
|
||||
get_logger().info("GitLab data", artifact=data)
|
||||
sender = data.get("user", {}).get("username", "unknown")
|
||||
sender_id = data.get("user", {}).get("id", "unknown")
|
||||
|
||||
# ignore bot users
|
||||
if is_bot_user(data):
|
||||
return JSONResponse(status_code=status.HTTP_200_OK, content=jsonable_encoder({"message": "success"}))
|
||||
|
||||
log_context["sender"] = sender
|
||||
if data.get('object_kind') == 'merge_request':
|
||||
# ignore MRs based on title, labels, source and target branches
|
||||
if not should_process_pr_logic(data):
|
||||
return JSONResponse(status_code=status.HTTP_200_OK, content=jsonable_encoder({"message": "success"}))
|
||||
|
||||
if data['object_attributes'].get('action') in ['open', 'reopen']:
|
||||
url = data['object_attributes'].get('url')
|
||||
draft = data['object_attributes'].get('draft')
|
||||
get_logger().info(f"New merge request: {url}")
|
||||
if draft:
|
||||
get_logger().info(f"Skipping draft MR: {url}")
|
||||
return JSONResponse(status_code=status.HTTP_200_OK, content=jsonable_encoder({"message": "success"}))
|
||||
|
||||
await _perform_commands_gitlab("pr_commands", PRAgent(), url, log_context, data)
|
||||
|
||||
# Handle the Draft to Ready transition
|
||||
elif data['object_attributes'].get('action') == 'update':
|
||||
url = data['object_attributes'].get('url')
|
||||
old_draft_status = data['changes']['draft']['previous']
|
||||
new_draft_status = data['object_attributes'].get('draft')
|
||||
|
||||
# Check if the merge request transitioned from Draft to Ready
|
||||
if old_draft_status and not new_draft_status:
|
||||
get_logger().info(f"Merge Request transitioned from Draft to Ready: {url}")
|
||||
await _perform_commands_gitlab("pr_draft_ready_commands", PRAgent(), url, log_context, data)
|
||||
|
||||
elif data.get('object_kind') == 'note' and data.get('event_type') == 'note': # comment on MR
|
||||
if 'merge_request' in data:
|
||||
mr = data['merge_request']
|
||||
url = mr.get('url')
|
||||
|
||||
get_logger().info(f"A comment has been added to a merge request: {url}")
|
||||
body = data.get('object_attributes', {}).get('note')
|
||||
if data.get('object_attributes', {}).get('type') == 'DiffNote' and '/ask' in body: # /ask_line
|
||||
body = handle_ask_line(body, data)
|
||||
|
||||
await handle_request(url, body, log_context, sender_id)
|
||||
|
||||
background_tasks.add_task(inner, request_json)
|
||||
end_time = datetime.now()
|
||||
get_logger().info(f"Processing time: {end_time - start_time}", request=request_json)
|
||||
return JSONResponse(status_code=status.HTTP_200_OK, content=jsonable_encoder({"message": "success"}))
|
||||
|
||||
|
||||
def handle_ask_line(body, data):
|
||||
try:
|
||||
line_range_ = data['object_attributes']['position']['line_range']
|
||||
start_line = line_range_['start']['new_line']
|
||||
end_line = line_range_['end']['new_line']
|
||||
question = body.replace('/ask', '').strip()
|
||||
path = data['object_attributes']['position']['new_path']
|
||||
side = 'RIGHT'
|
||||
comment_id = data['object_attributes']["discussion_id"]
|
||||
get_logger().info("Handling line comment")
|
||||
body = f"/ask_line --line_start={start_line} --line_end={end_line} --side={side} --file_name={path} --comment_id={comment_id} {question}"
|
||||
except Exception as e:
|
||||
get_logger().error(f"Failed to handle ask line comment: {e}")
|
||||
return body
|
||||
|
||||
@router.get("/")
|
||||
async def root():
|
||||
return {"status": "ok"}
|
||||
|
||||
gitlab_url = get_settings().get("GITLAB.URL", None)
|
||||
if not gitlab_url:
|
||||
raise ValueError("GITLAB.URL is not set")
|
||||
get_settings().config.git_provider = "gitlab"
|
||||
middleware = [Middleware(RawContextMiddleware)]
|
||||
app = FastAPI(middleware=middleware)
|
||||
app.include_router(router)
|
||||
|
||||
|
||||
def start():
|
||||
uvicorn.run(app, host="0.0.0.0", port=3000)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
start()
|
||||
@ -95,7 +95,6 @@ class PRReviewer:
|
||||
"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),
|
||||
"date": datetime.datetime.now().strftime('%Y-%m-%d'),
|
||||
}
|
||||
|
||||
self.token_handler = TokenHandler(
|
||||
@ -123,10 +122,10 @@ class PRReviewer:
|
||||
if self.incremental.is_incremental and not self._can_run_incremental_review():
|
||||
return None
|
||||
|
||||
# if isinstance(self.args, list) and self.args and self.args[0] == 'auto_approve':
|
||||
# get_logger().info(f'Auto approve flow PR: {self.pr_url} ...')
|
||||
# self.auto_approve_logic()
|
||||
# return None
|
||||
if isinstance(self.args, list) and self.args and self.args[0] == 'auto_approve':
|
||||
get_logger().info(f'Auto approve flow PR: {self.pr_url} ...')
|
||||
self.auto_approve_logic()
|
||||
return None
|
||||
|
||||
get_logger().info(f'Reviewing PR: {self.pr_url} ...')
|
||||
relevant_configs = {'pr_reviewer': dict(get_settings().pr_reviewer),
|
||||
@ -402,7 +401,7 @@ class PRReviewer:
|
||||
"""
|
||||
Auto-approve a pull request if it meets the conditions for auto-approval.
|
||||
"""
|
||||
if get_settings().config.enable_auto_approval:
|
||||
if get_settings().pr_reviewer.enable_auto_approval:
|
||||
is_auto_approved = self.git_provider.auto_approve()
|
||||
if is_auto_approved:
|
||||
get_logger().info("Auto-approved PR")
|
||||
|
||||
@ -70,65 +70,41 @@ async def extract_tickets(git_provider):
|
||||
user_description = git_provider.get_user_description()
|
||||
tickets = extract_ticket_links_from_pr_description(user_description, git_provider.repo, git_provider.base_url_html)
|
||||
tickets_content = []
|
||||
|
||||
if tickets:
|
||||
|
||||
for ticket in tickets:
|
||||
# extract ticket number and repo name
|
||||
repo_name, original_issue_number = git_provider._parse_issue_url(ticket)
|
||||
|
||||
# get the ticket object
|
||||
try:
|
||||
issue_main = git_provider.repo_obj.get_issue(original_issue_number)
|
||||
except Exception as e:
|
||||
get_logger().error(f"Error getting main issue: {e}",
|
||||
get_logger().error(f"Error getting issue_main error= {e}",
|
||||
artifact={"traceback": traceback.format_exc()})
|
||||
continue
|
||||
|
||||
issue_body_str = issue_main.body or ""
|
||||
# clip issue_main.body max length
|
||||
issue_body_str = issue_main.body
|
||||
if not issue_body_str:
|
||||
issue_body_str = ""
|
||||
if len(issue_body_str) > MAX_TICKET_CHARACTERS:
|
||||
issue_body_str = issue_body_str[:MAX_TICKET_CHARACTERS] + "..."
|
||||
|
||||
# Extract sub-issues
|
||||
sub_issues_content = []
|
||||
try:
|
||||
sub_issues = git_provider.fetch_sub_issues(ticket)
|
||||
for sub_issue_url in sub_issues:
|
||||
try:
|
||||
sub_repo, sub_issue_number = git_provider._parse_issue_url(sub_issue_url)
|
||||
sub_issue = git_provider.repo_obj.get_issue(sub_issue_number)
|
||||
|
||||
sub_body = sub_issue.body or ""
|
||||
if len(sub_body) > MAX_TICKET_CHARACTERS:
|
||||
sub_body = sub_body[:MAX_TICKET_CHARACTERS] + "..."
|
||||
|
||||
sub_issues_content.append({
|
||||
'ticket_url': sub_issue_url,
|
||||
'title': sub_issue.title,
|
||||
'body': sub_body
|
||||
})
|
||||
except Exception as e:
|
||||
get_logger().warning(f"Failed to fetch sub-issue content for {sub_issue_url}: {e}")
|
||||
|
||||
except Exception as e:
|
||||
get_logger().warning(f"Failed to fetch sub-issues for {ticket}: {e}")
|
||||
|
||||
# Extract labels
|
||||
# extract labels
|
||||
labels = []
|
||||
try:
|
||||
for label in issue_main.labels:
|
||||
labels.append(label.name if hasattr(label, 'name') else label)
|
||||
if isinstance(label, str):
|
||||
labels.append(label)
|
||||
else:
|
||||
labels.append(label.name)
|
||||
except Exception as e:
|
||||
get_logger().error(f"Error extracting labels error= {e}",
|
||||
artifact={"traceback": traceback.format_exc()})
|
||||
|
||||
tickets_content.append({
|
||||
'ticket_id': issue_main.number,
|
||||
'ticket_url': ticket,
|
||||
'title': issue_main.title,
|
||||
'body': issue_body_str,
|
||||
'labels': ", ".join(labels),
|
||||
'sub_issues': sub_issues_content # Store sub-issues content
|
||||
})
|
||||
|
||||
tickets_content.append(
|
||||
{'ticket_id': issue_main.number,
|
||||
'ticket_url': ticket, 'title': issue_main.title, 'body': issue_body_str,
|
||||
'labels': ", ".join(labels)})
|
||||
return tickets_content
|
||||
|
||||
except Exception as e:
|
||||
@ -139,27 +115,14 @@ async def extract_tickets(git_provider):
|
||||
async def extract_and_cache_pr_tickets(git_provider, vars):
|
||||
if not get_settings().get('pr_reviewer.require_ticket_analysis_review', False):
|
||||
return
|
||||
|
||||
related_tickets = get_settings().get('related_tickets', [])
|
||||
|
||||
if not related_tickets:
|
||||
tickets_content = await extract_tickets(git_provider)
|
||||
|
||||
if tickets_content:
|
||||
# Store sub-issues along with main issues
|
||||
for ticket in tickets_content:
|
||||
if "sub_issues" in ticket and ticket["sub_issues"]:
|
||||
for sub_issue in ticket["sub_issues"]:
|
||||
related_tickets.append(sub_issue) # Add sub-issues content
|
||||
|
||||
related_tickets.append(ticket)
|
||||
|
||||
get_logger().info("Extracted tickets and sub-issues from PR description",
|
||||
artifact={"tickets": related_tickets})
|
||||
|
||||
vars['related_tickets'] = related_tickets
|
||||
get_settings().set('related_tickets', related_tickets)
|
||||
else:
|
||||
get_logger().info("Extracted tickets from PR description", artifact={"tickets": tickets_content})
|
||||
vars['related_tickets'] = tickets_content
|
||||
get_settings().set('related_tickets', tickets_content)
|
||||
else: # if tickets are already cached
|
||||
get_logger().info("Using cached tickets", artifact={"tickets": related_tickets})
|
||||
vars['related_tickets'] = related_tickets
|
||||
|
||||
|
||||
@ -1,5 +1,5 @@
|
||||
aiohttp==3.9.5
|
||||
anthropic[vertex]==0.47.1
|
||||
anthropic[vertex]==0.39.0
|
||||
atlassian-python-api==3.41.4
|
||||
azure-devops==7.1.0b3
|
||||
azure-identity==1.15.0
|
||||
|
||||
@ -5,11 +5,12 @@ 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
|
||||
get_settings().set("CONFIG.CLI_MODE", True)
|
||||
get_settings().config.allow_dynamic_context = False
|
||||
|
||||
|
||||
class TestExtendPatch:
|
||||
def setUp(self):
|
||||
get_settings().config.allow_dynamic_context = False
|
||||
|
||||
# Tests that the function works correctly with valid input
|
||||
def test_happy_path(self):
|
||||
original_file_str = 'line1\nline2\nline3\nline4\nline5'
|
||||
@ -74,46 +75,41 @@ class TestExtendPatch:
|
||||
actual_output = extend_patch(original_file_str, patch_str,
|
||||
patch_extra_lines_before=num_lines, patch_extra_lines_after=num_lines)
|
||||
assert actual_output == expected_output
|
||||
get_settings(use_context=False).config.allow_dynamic_context = original_allow_dynamic_context
|
||||
get_settings().config.allow_dynamic_context = original_allow_dynamic_context
|
||||
|
||||
|
||||
def test_dynamic_context(self):
|
||||
get_settings(use_context=False).config.max_extra_lines_before_dynamic_context = 10
|
||||
get_settings().config.max_extra_lines_before_dynamic_context = 10
|
||||
original_file_str = "def foo():"
|
||||
for i in range(9):
|
||||
original_file_str += f"\n line({i})"
|
||||
patch_str ="@@ -10,1 +10,1 @@ def foo():\n- line(8)\n+ new_line(8)"
|
||||
new_file_str = "\n".join(original_file_str.splitlines()[:-1] + [" new_line(8)"])
|
||||
patch_str ="@@ -11,1 +11,1 @@ def foo():\n- line(9)\n+ new_line(9)"
|
||||
num_lines=1
|
||||
|
||||
get_settings(use_context=False).config.allow_dynamic_context = True
|
||||
get_settings().config.allow_dynamic_context = True
|
||||
actual_output = extend_patch(original_file_str, patch_str,
|
||||
patch_extra_lines_before=num_lines, patch_extra_lines_after=num_lines, new_file_str=new_file_str)
|
||||
expected_output='\n@@ -1,10 +1,10 @@ \n def foo():\n line(0)\n line(1)\n line(2)\n line(3)\n line(4)\n line(5)\n line(6)\n line(7)\n- line(8)\n+ new_line(8)'
|
||||
patch_extra_lines_before=num_lines, patch_extra_lines_after=num_lines)
|
||||
expected_output='\n@@ -1,10 +1,10 @@ \n def foo():\n line(0)\n line(1)\n line(2)\n line(3)\n line(4)\n line(5)\n line(6)\n line(7)\n line(8)\n- line(9)\n+ new_line(9)'
|
||||
assert actual_output == expected_output
|
||||
|
||||
get_settings(use_context=False).config.allow_dynamic_context = False
|
||||
get_settings().config.allow_dynamic_context = False
|
||||
actual_output2 = extend_patch(original_file_str, patch_str,
|
||||
patch_extra_lines_before=1, patch_extra_lines_after=1)
|
||||
expected_output_no_dynamic_context = '\n@@ -9,2 +9,2 @@ def foo():\n line(7)\n- line(8)\n+ new_line(8)'
|
||||
patch_extra_lines_before=num_lines, patch_extra_lines_after=num_lines)
|
||||
expected_output_no_dynamic_context = '\n@@ -10,1 +10,1 @@ def foo():\n line(8)\n- line(9)\n+ new_line(9)'
|
||||
assert actual_output2 == expected_output_no_dynamic_context
|
||||
|
||||
get_settings(use_context=False).config.allow_dynamic_context = False
|
||||
actual_output3 = extend_patch(original_file_str, patch_str,
|
||||
patch_extra_lines_before=3, patch_extra_lines_after=3)
|
||||
expected_output_no_dynamic_context = '\n@@ -7,4 +7,4 @@ def foo():\n line(5)\n line(6)\n line(7)\n- line(8)\n+ new_line(8)'
|
||||
assert actual_output3 == expected_output_no_dynamic_context
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
class TestExtendedPatchMoreLines:
|
||||
def setUp(self):
|
||||
get_settings().config.allow_dynamic_context = False
|
||||
|
||||
class File:
|
||||
def __init__(self, base_file, patch, head_file, filename, ai_file_summary=None):
|
||||
def __init__(self, base_file, patch, filename, ai_file_summary=None):
|
||||
self.base_file = base_file
|
||||
self.patch = patch
|
||||
self.head_file = head_file
|
||||
self.filename = filename
|
||||
self.ai_file_summary = ai_file_summary
|
||||
|
||||
@ -132,11 +128,9 @@ class TestExtendedPatchMoreLines:
|
||||
'files': [
|
||||
self.File(base_file="line000\nline00\nline0\nline1\noriginal content\nline2\nline3\nline4\nline5\nline6\nline7\nline8\nline9\nline10",
|
||||
patch="@@ -5,5 +5,5 @@\n-original content\n+modified content\n line2\n line3\n line4\n line5",
|
||||
head_file="line000\nline00\nline0\nline1\nmodified content\nline2\nline3\nline4\nline5\nline6\nline7\nline8\nline9\nline10",
|
||||
filename="file1"),
|
||||
self.File(base_file="original content\nline2\nline3\nline4\nline5\nline6\nline7\nline8\nline9\nline10",
|
||||
patch="@@ -6,5 +6,5 @@\nline6\nline7\nline8\n-line9\n+modified line9\nline10",
|
||||
head_file="original content\nline2\nline3\nline4\nline5\nline6\nline7\nline8\nmodified line9\nline10",
|
||||
filename="file2")
|
||||
]
|
||||
}
|
||||
@ -161,9 +155,11 @@ 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",
|
||||
|
||||
@ -1,121 +0,0 @@
|
||||
# Currently doing API calls - wrong !
|
||||
|
||||
|
||||
# import unittest
|
||||
# import asyncio
|
||||
# from unittest.mock import AsyncMock, patch
|
||||
# from pr_agent.tools.ticket_pr_compliance_check import extract_tickets, extract_and_cache_pr_tickets
|
||||
# from pr_agent.git_providers.github_provider import GithubProvider
|
||||
#
|
||||
#
|
||||
# class TestTicketCompliance(unittest.TestCase):
|
||||
#
|
||||
# @patch.object(GithubProvider, 'get_user_description', return_value="Fixes #1 and relates to #2")
|
||||
# @patch.object(GithubProvider, '_parse_issue_url', side_effect=lambda url: ("WonOfAKind/KimchiBot", int(url.split('#')[-1])))
|
||||
# @patch.object(GithubProvider, 'repo_obj')
|
||||
# async def test_extract_tickets(self, mock_repo, mock_parse_issue_url, mock_user_desc):
|
||||
# """
|
||||
# Test extract_tickets() to ensure it extracts tickets correctly
|
||||
# and fetches their content.
|
||||
# """
|
||||
# github_provider = GithubProvider()
|
||||
# github_provider.repo = "WonOfAKind/KimchiBot"
|
||||
# github_provider.base_url_html = "https://github.com"
|
||||
#
|
||||
# # Mock issue retrieval
|
||||
# mock_issue = AsyncMock()
|
||||
# mock_issue.number = 1
|
||||
# mock_issue.title = "Sample Issue"
|
||||
# mock_issue.body = "This is a test issue body."
|
||||
# mock_issue.labels = ["bug", "high priority"]
|
||||
#
|
||||
# # Mock repo object
|
||||
# mock_repo.get_issue.return_value = mock_issue
|
||||
#
|
||||
# tickets = await extract_tickets(github_provider)
|
||||
#
|
||||
# # Verify tickets were extracted correctly
|
||||
# self.assertIsInstance(tickets, list)
|
||||
# self.assertGreater(len(tickets), 0, "Expected at least one ticket!")
|
||||
#
|
||||
# # Verify ticket structure
|
||||
# first_ticket = tickets[0]
|
||||
# self.assertIn("ticket_id", first_ticket)
|
||||
# self.assertIn("ticket_url", first_ticket)
|
||||
# self.assertIn("title", first_ticket)
|
||||
# self.assertIn("body", first_ticket)
|
||||
# self.assertIn("labels", first_ticket)
|
||||
#
|
||||
# print("\n Test Passed: extract_tickets() successfully retrieved ticket info!")
|
||||
#
|
||||
# @patch.object(GithubProvider, 'get_user_description', return_value="Fixes #1 and relates to #2")
|
||||
# @patch.object(GithubProvider, '_parse_issue_url', side_effect=lambda url: ("WonOfAKind/KimchiBot", int(url.split('#')[-1])))
|
||||
# @patch.object(GithubProvider, 'repo_obj')
|
||||
# async def test_extract_and_cache_pr_tickets(self, mock_repo, mock_parse_issue_url, mock_user_desc):
|
||||
# """
|
||||
# Test extract_and_cache_pr_tickets() to ensure tickets are extracted and cached correctly.
|
||||
# """
|
||||
# github_provider = GithubProvider()
|
||||
# github_provider.repo = "WonOfAKind/KimchiBot"
|
||||
# github_provider.base_url_html = "https://github.com"
|
||||
#
|
||||
# vars = {} # Simulate the dictionary to store results
|
||||
#
|
||||
# # Mock issue retrieval
|
||||
# mock_issue = AsyncMock()
|
||||
# mock_issue.number = 1
|
||||
# mock_issue.title = "Sample Issue"
|
||||
# mock_issue.body = "This is a test issue body."
|
||||
# mock_issue.labels = ["bug", "high priority"]
|
||||
#
|
||||
# # Mock repo object
|
||||
# mock_repo.get_issue.return_value = mock_issue
|
||||
#
|
||||
# # Run function
|
||||
# await extract_and_cache_pr_tickets(github_provider, vars)
|
||||
#
|
||||
# # Ensure tickets are cached
|
||||
# self.assertIn("related_tickets", vars)
|
||||
# self.assertIsInstance(vars["related_tickets"], list)
|
||||
# self.assertGreater(len(vars["related_tickets"]), 0, "Expected at least one cached ticket!")
|
||||
#
|
||||
# print("\n Test Passed: extract_and_cache_pr_tickets() successfully cached ticket data!")
|
||||
#
|
||||
# def test_fetch_sub_issues(self):
|
||||
# """
|
||||
# Test fetch_sub_issues() to ensure sub-issues are correctly retrieved.
|
||||
# """
|
||||
# github_provider = GithubProvider()
|
||||
# issue_url = "https://github.com/WonOfAKind/KimchiBot/issues/1" # Known issue with sub-issues
|
||||
# result = github_provider.fetch_sub_issues(issue_url)
|
||||
#
|
||||
# print("Fetched sub-issues:", result)
|
||||
#
|
||||
# self.assertIsInstance(result, set) # Ensure result is a set
|
||||
# self.assertGreater(len(result), 0, "Expected at least one sub-issue but found none!")
|
||||
#
|
||||
# print("\n Test Passed: fetch_sub_issues() retrieved sub-issues correctly!")
|
||||
#
|
||||
# def test_fetch_sub_issues_with_no_results(self):
|
||||
# """
|
||||
# Test fetch_sub_issues() to ensure an empty set is returned for an issue with no sub-issues.
|
||||
# """
|
||||
# github_provider = GithubProvider()
|
||||
# issue_url = "https://github.com/qodo-ai/pr-agent/issues/1499" # Likely non-existent issue
|
||||
# result = github_provider.fetch_sub_issues(issue_url)
|
||||
#
|
||||
# print("Fetched sub-issues for non-existent issue:", result)
|
||||
#
|
||||
# self.assertIsInstance(result, set) # Ensure result is a set
|
||||
# self.assertEqual(len(result), 0, "Expected no sub-issues but some were found!")
|
||||
#
|
||||
# print("\n Test Passed: fetch_sub_issues_with_no_results() correctly returned an empty set!")
|
||||
#
|
||||
#
|
||||
# if __name__ == "__main__":
|
||||
# asyncio.run(unittest.main())
|
||||
#
|
||||
#
|
||||
#
|
||||
#
|
||||
#
|
||||
Reference in New Issue
Block a user