repo_name stringlengths 1 62 | dataset stringclasses 1 value | lang stringclasses 11 values | pr_id int64 1 20.1k | owner stringlengths 2 34 | reviewer stringlengths 2 39 | diff_hunk stringlengths 15 262k | code_review_comment stringlengths 1 99.6k |
|---|---|---|---|---|---|---|---|
ai-pr-reviewer | github_2023 | typescript | 240 | coderabbitai | github-actions[bot] | @@ -89,34 +88,26 @@ ${tag}`
}
getRawSummary(summary: string) {
- const content = this.getContentWithinTags(
+ return this.getContentWithinTags(
summary,
- RAW_SUMMARY_TAG,
- RAW_SUMMARY_TAG_END
+ RAW_SUMMARY_START_TAG,
+ RAW_SUMMARY_END_TAG
)
- // remove the first and last line
- const lines = content.split('\n')
- if (lines.length < 3) {
- return ''
- }
- lines.shift()
- lines.pop()
- return lines.join('\n')
}
| :robot: OpenAI
The `getRawSummary` function has been modified to remove the first and last line of content obtained within tags. Please review this change for correctness.
```suggestion
getRawSummary(summary: string) {
return this.getContentWithinTags(
summary,
RAW_SUMMARY_START_TAG,
RAW_SUMMARY_END_TAG
).split('\n').slice(1, -1).join('\n')
}
getDescription(description: string) {
return this.removeContentWithinTags(
description,
DESCRIPTION_START_TAG,
DESCRIPTION_END_TAG
)
}
getReleaseNotes(description: string) {
const releaseNotes = this.getContentWithinTags(
description,
DESCRIPTION_START_TAG,
DESCRIPTION_END_TAG
)
return releaseNotes.replace(/(^|\n)> .*/g, '')
}
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 240 | coderabbitai | github-actions[bot] | @@ -140,10 +131,10 @@ ${tag}`
const messageClean = this.removeContentWithinTags(
message,
- DESCRIPTION_TAG,
- DESCRIPTION_TAG_END
+ DESCRIPTION_START_TAG,
+ DESCRIPTION_END_TAG
)
- const newDescription = `${description}\n${DESCRIPTION_TAG}\n${messageClean}\n${DESCRIPTION_TAG_END}`
+ const newDescription = `${description}\n${DESCRIPTION_START_TAG}\n${messageClean}\n${DESCRIPTION_END_TAG}` | :robot: OpenAI
In `Commenter`, `DESCRIPTION_TAG` and `DESCRIPTION_TAG_END` have been replaced with `DESCRIPTION_START_TAG` and `DESCRIPTION_END_TAG`. Please review this change for correctness.
```suggestion
async addCommentToPullRequest(
repo: { owner: string; repo: string },
pull_number: number,
message: string
) {
const { data: comments } = await octokit.issues.listComments({
owner: repo.owner,
repo: repo.repo,
issue_number: pull_number,
})
// remove any existing comment by the bot
const existingComment = comments.find((comment) => comment.user?.login === 'github-actions[bot]')
if (existingComment) {
await octokit.issues.deleteComment({
owner: repo.owner,
repo: repo.repo,
comment_id: existingComment.id,
})
}
const description = await this.getDescriptionFromPullRequest(repo, pull_number)
const messageClean = this.removeContentWithinTags(
message,
DESCRIPTION_START_TAG,
DESCRIPTION_END_TAG
)
const newDescription = `${description}\n${DESCRIPTION_START_TAG}\n${messageClean}\n${DESCRIPTION_END_TAG}`
await octokit.pulls.update({
owner: repo.owner,
repo: repo.repo,
pull_number,
body: newDescription,
})
}
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 240 | coderabbitai | github-actions[bot] | @@ -562,12 +553,12 @@ ${chain}
// commit ids are comments between the commit_ids_reviewed_start and commit_ids_reviewed_end markers
// <!-- [commit_id] -->
getReviewedCommitIds(commentBody: string): string[] {
- const start = commentBody.indexOf(COMMIT_ID_TAG)
- const end = commentBody.indexOf(COMMIT_ID_TAG_END)
+ const start = commentBody.indexOf(COMMIT_ID_START_TAG)
+ const end = commentBody.indexOf(COMMIT_ID_END_TAG)
if (start === -1 || end === -1) {
return []
}
- const ids = commentBody.substring(start + COMMIT_ID_TAG.length, end)
+ const ids = commentBody.substring(start + COMMIT_ID_START_TAG.length, end)
// remove the <!-- and --> markers from each id and extract the id and remove empty strings
return ids
.split('<!--') | :robot: OpenAI
In `Commenter`, `COMMIT_ID_TAG` and `COMMIT_ID_TAG_END` have been replaced with `COMMIT_ID_START_TAG` and `COMMIT_ID_END_TAG`. Please review this change for correctness.
```suggestion
// commit ids are comments between the commit_ids_reviewed_start and commit_ids_reviewed_end markers
// <!-- [commit_id] -->
getReviewedCommitIds(commentBody: string): string[] {
const start = commentBody.indexOf(COMMIT_ID_START_TAG)
const end = commentBody.indexOf(COMMIT_ID_END_TAG)
if (start === -1 || end === -1) {
return []
}
const ids = commentBody.substring(start + COMMIT_ID_START_TAG.length, end)
// remove the <!-- and --> markers from each id and extract the id and remove empty strings
return ids.split('<!--').map((id) => id.replace(/(-->|\n)/g, '').trim()).filter(Boolean)
}
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 232 | coderabbitai | github-actions[bot] | @@ -16,6 +16,7 @@ async function run(): Promise<void> {
getBooleanInput('debug'),
getBooleanInput('summary_only'),
getInput('max_files'),
+ getBooleanInput('review_simple_changes'), | :robot: OpenAI
The new boolean option `review_simple_changes` is not being initialized correctly. It should be initialized as `getBooleanInput('review_simple_changes')`.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 232 | coderabbitai | github-actions[bot] | @@ -58,6 +58,7 @@ jobs:
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
with:
debug: false
+ review_simple_changes: false | :robot: OpenAI
The `review_simple_changes` parameter is not defined in the old hunk and it's unclear what it does. Please provide more information on what this parameter does and how it affects the workflow.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 232 | coderabbitai | github-actions[bot] | @@ -23,8 +23,8 @@ $file_diff
\`\`\`
I would like you to summarize the diff within 50 words.
-
-Below the summary, I would also like you to triage the diff as \`NEEDS_REVIEW\` or
+`
+ triageFileDiff = `Below the summary, I would also like you to triage the diff as \`NEEDS_REVIEW\` or
\`APPROVED\` based on the following criteria:
- If the diff involves any modifications to the logic or functionality, even if they | :robot: OpenAI
The new hunk introduces a new feature to triage the diff as `NEEDS_REVIEW` or `APPROVED` based on certain criteria. However, the implementation is incomplete and contains a syntax error. Please fix the syntax error and complete the implementation of this feature. Additionally, it would be helpful to provide more details on the criteria for triaging the diff in the code comments or documentation.
```suggestion
/**
* Summarizes the file diff and triages it as `NEEDS_REVIEW` or `APPROVED` based on certain criteria.
*
* @param inputs - The inputs object containing the necessary information.
* @param reviewSimpleChanges - A boolean indicating whether to review simple changes or not.
* @returns The summarized file diff with triage information.
*/
renderSummarizeFileDiff(inputs: Inputs, reviewSimpleChanges: boolean): string {
let prompt = `
\`\`\`
${inputs.diffSummary}
\`\`\`
Triage: ${reviewSimpleChanges ? 'APPROVED' : 'NEEDS_REVIEW'}
`;
return inputs.render(prompt);
}
```
---new_hunk---
```
248: this.summarizeReleaseNotes = summarizeReleaseNotes
249: }
250:
251: renderSummarizeFileDiff(
252: inputs: Inputs,
253: reviewSimpleChanges: boolean
254: ): string {
255: let prompt = this.summarizeFileDiff
256: if (reviewSimpleChanges === false) {
257: prompt += this.triageFileDiff
258: }
259: return inputs.render(prompt)
260: }
261:
262: renderSummarizeChangesets(inputs: Inputs): string {
```
---old_hunk---
```
this.summarizeReleaseNotes = summarizeReleaseNotes
}
renderSummarizeFileDiff(inputs: Inputs): string {
return inputs.render(this.summarizeFileDiff)
}
renderSummarizeChangesets(inputs: Inputs): string {
```
---end_change_section---
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 232 | coderabbitai | github-actions[bot] | @@ -248,8 +248,15 @@ $patches
this.summarizeReleaseNotes = summarizeReleaseNotes
}
- renderSummarizeFileDiff(inputs: Inputs): string {
- return inputs.render(this.summarizeFileDiff)
+ renderSummarizeFileDiff(
+ inputs: Inputs,
+ reviewSimpleChanges: boolean
+ ): string {
+ let prompt = this.summarizeFileDiff
+ if (reviewSimpleChanges === false) {
+ prompt += this.triageFileDiff
+ }
+ return inputs.render(prompt) | :robot: OpenAI
The new hunk introduces a new boolean parameter `reviewSimpleChanges` to the `renderSummarizeFileDiff` function. The implementation of this feature is incomplete and contains a syntax error. Please fix the syntax error and complete the implementation of this feature. Additionally, it would be helpful to provide more details on the purpose of this parameter in the code comments or documentation.
```suggestion
/**
* Summarizes the file diff and triages it as `NEEDS_REVIEW` or `APPROVED` based on certain criteria.
*
* @param inputs - The inputs object containing the necessary information.
* @param reviewSimpleChanges - A boolean indicating whether to review simple changes or not.
* @returns The summarized file diff with triage information.
*/
renderSummarizeFileDiff(inputs: Inputs, reviewSimpleChanges: boolean): string {
let prompt = `
\`\`\`
${inputs.diffSummary}
\`\`\`
Triage: ${reviewSimpleChanges ? 'APPROVED' : 'NEEDS_REVIEW'}
`;
if (reviewSimpleChanges === false) {
prompt += this.triageFileDiff;
}
return inputs.render(prompt);
}
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 232 | coderabbitai | github-actions[bot] | @@ -248,8 +248,15 @@ $patches
this.summarizeReleaseNotes = summarizeReleaseNotes
}
- renderSummarizeFileDiff(inputs: Inputs): string {
- return inputs.render(this.summarizeFileDiff)
+ renderSummarizeFileDiff(
+ inputs: Inputs,
+ reviewSimpleChanges: boolean
+ ): string {
+ let prompt = this.summarizeFileDiff
+ if (reviewSimpleChanges === false) {
+ prompt += this.triageFileDiff
+ }
+ return inputs.render(prompt)
}
renderSummarizeChangesets(inputs: Inputs): string { | :robot: OpenAI
> Note: This review was outside of the patch, so it was mapped to the patch with the greatest overlap. Original lines [262-266]
The new hunk introduces a new function `renderSummarizeChangesets`. However, there is no implementation provided for this function. Please provide an implementation for this function or remove it if it is not needed.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 231 | coderabbitai | github-actions[bot] | @@ -23,7 +23,6 @@ NOTES:
[more conservative data usage policy](https://openai.com/policies/api-data-usage-policies)
compared to their ChatGPT offering. | :robot: OpenAI
The link to the data usage policy seems to be broken. Please verify and update if necessary.
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 229 | coderabbitai | github-actions[bot] | @@ -50,7 +50,6 @@ Your task is to de-deduplicate and group together files with
related/similar changes into a single changeset. Respond with the updated
changesets using the same format as the input.
-Changesets:
$raw_summary
`
| :robot: OpenAI
The code seems to be incomplete and doesn't provide enough context to review. Please provide the complete new hunk for review.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 227 | coderabbitai | github-actions[bot] | @@ -22,17 +22,22 @@
"devDependencies": {
"@jest/globals": "^29.5.0",
"@types/node": "^18.15.11",
+ "@typescript-eslint/eslint-plugin": "^5.59.0",
"@typescript-eslint/parser": "^5.59.0",
"@vercel/ncc": "^0.36.1",
"chatgpt": "^5.2.2",
"eslint": "^8.38.0",
+ "eslint-config-standard-with-typescript": "^34.0.1",
"eslint-plugin-github": "^4.6.1",
+ "eslint-plugin-import": "^2.27.5",
"eslint-plugin-jest": "^27.2.1",
+ "eslint-plugin-n": "^15.7.0",
+ "eslint-plugin-promise": "^6.1.1",
"jest": "^27.2.5",
"js-yaml": "^4.1.0",
"prettier": "2.8.7",
"ts-jest": "^27.1.2",
- "typescript": "^4.4.4"
+ "typescript": "^4.9.5" | :robot: OpenAI
The `package-lock.json` file has been updated with new dev dependencies. No issues found.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 227 | coderabbitai | github-actions[bot] | @@ -2197,15 +2202,15 @@
"dev": true
},
"node_modules/@typescript-eslint/eslint-plugin": {
- "version": "5.56.0",
- "resolved": "https://registry.npmjs.org/@typescript-eslint/eslint-plugin/-/eslint-plugin-5.56.0.tgz",
- "integrity": "sha512-ZNW37Ccl3oMZkzxrYDUX4o7cnuPgU+YrcaYXzsRtLB16I1FR5SHMqga3zGsaSliZADCWo2v8qHWqAYIj8nWCCg==",
+ "version": "5.59.0",
+ "resolved": "https://registry.npmjs.org/@typescript-eslint/eslint-plugin/-/eslint-plugin-5.59.0.tgz",
+ "integrity": "sha512-p0QgrEyrxAWBecR56gyn3wkG15TJdI//eetInP3zYRewDh0XS+DhB3VUAd3QqvziFsfaQIoIuZMxZRB7vXYaYw==",
"dev": true,
"dependencies": {
"@eslint-community/regexpp": "^4.4.0",
- "@typescript-eslint/scope-manager": "5.56.0",
- "@typescript-eslint/type-utils": "5.56.0",
- "@typescript-eslint/utils": "5.56.0",
+ "@typescript-eslint/scope-manager": "5.59.0",
+ "@typescript-eslint/type-utils": "5.59.0",
+ "@typescript-eslint/utils": "5.59.0",
"debug": "^4.3.4",
"grapheme-splitter": "^1.0.4",
"ignore": "^5.2.0", | :robot: OpenAI
The `@typescript-eslint/eslint-plugin` dependency has been updated to version 5.59.0. No issues found.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 227 | coderabbitai | github-actions[bot] | @@ -2257,7 +2262,7 @@
}
}
},
- "node_modules/@typescript-eslint/parser/node_modules/@typescript-eslint/scope-manager": {
+ "node_modules/@typescript-eslint/scope-manager": {
"version": "5.59.0",
"resolved": "https://registry.npmjs.org/@typescript-eslint/scope-manager/-/scope-manager-5.59.0.tgz",
"integrity": "sha512-tsoldKaMh7izN6BvkK6zRMINj4Z2d6gGhO2UsI8zGZY3XhLq1DndP3Ycjhi1JwdwPRwtLMW4EFPgpuKhbCGOvQ==", | :robot: OpenAI
The `@typescript-eslint/scope-manager` dependency has been updated to version 5.59.0. No issues found.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 227 | coderabbitai | github-actions[bot] | @@ -38,16 +38,21 @@
"devDependencies": { | :robot: OpenAI
The `@typescript-eslint/eslint-plugin` dependency is added in the new hunk but not present in the old hunk. Is this intentional? If so, please ignore this comment. Otherwise, please ensure that this dependency is added to the `devDependencies` object in `package.json`.
```suggestion
"@typescript-eslint/eslint-plugin": "^5.59.0",
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 227 | coderabbitai | github-actions[bot] | @@ -38,16 +38,21 @@
"devDependencies": {
"@jest/globals": "^29.5.0",
"@types/node": "^18.15.11",
+ "@typescript-eslint/eslint-plugin": "^5.59.0",
"@typescript-eslint/parser": "^5.59.0", | :robot: OpenAI
The `@typescript-eslint/parser` dependency is added in the new hunk but not present in the old hunk. Is this intentional? If so, please ignore this comment. Otherwise, please ensure that this dependency is added to the `devDependencies` object in `package.json`.
```suggestion
"@typescript-eslint/parser": "^5.59.0",
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 227 | coderabbitai | github-actions[bot] | @@ -38,16 +38,21 @@
"devDependencies": {
"@jest/globals": "^29.5.0",
"@types/node": "^18.15.11",
+ "@typescript-eslint/eslint-plugin": "^5.59.0",
"@typescript-eslint/parser": "^5.59.0",
"@vercel/ncc": "^0.36.1",
"chatgpt": "^5.2.2",
"eslint": "^8.38.0",
+ "eslint-config-standard-with-typescript": "^34.0.1", | :robot: OpenAI
The `eslint-config-standard-with-typescript` dependency is added in the new hunk but not present in the old hunk. Is this intentional? If so, please ignore this comment. Otherwise, please ensure that this dependency is added to the `devDependencies` object in `package.json`.
```suggestion
"eslint-config-standard-with-typescript": "^34.0.1",
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 227 | coderabbitai | github-actions[bot] | @@ -38,16 +38,21 @@
"devDependencies": {
"@jest/globals": "^29.5.0",
"@types/node": "^18.15.11",
+ "@typescript-eslint/eslint-plugin": "^5.59.0",
"@typescript-eslint/parser": "^5.59.0",
"@vercel/ncc": "^0.36.1",
"chatgpt": "^5.2.2",
"eslint": "^8.38.0",
+ "eslint-config-standard-with-typescript": "^34.0.1",
"eslint-plugin-github": "^4.6.1",
+ "eslint-plugin-import": "^2.27.5",
"eslint-plugin-jest": "^27.2.1", | :robot: OpenAI
The `eslint-plugin-import` dependency is added in the new hunk but not present in the old hunk. Is this intentional? If so, please ignore this comment. Otherwise, please ensure that this dependency is added to the `devDependencies` object in `package.json`.
```suggestion
"eslint-plugin-import": "^2.27.5",
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 227 | coderabbitai | github-actions[bot] | @@ -38,16 +38,21 @@
"devDependencies": {
"@jest/globals": "^29.5.0",
"@types/node": "^18.15.11",
+ "@typescript-eslint/eslint-plugin": "^5.59.0",
"@typescript-eslint/parser": "^5.59.0",
"@vercel/ncc": "^0.36.1",
"chatgpt": "^5.2.2",
"eslint": "^8.38.0",
+ "eslint-config-standard-with-typescript": "^34.0.1",
"eslint-plugin-github": "^4.6.1",
+ "eslint-plugin-import": "^2.27.5",
"eslint-plugin-jest": "^27.2.1",
+ "eslint-plugin-n": "^15.7.0",
+ "eslint-plugin-promise": "^6.1.1", | :robot: OpenAI
The `eslint-plugin-n` and `eslint-plugin-promise` dependencies are added in the new hunk but not present in the old hunk. Is this intentional? If so, please ignore this comment. Otherwise, please ensure that these dependencies are added to the `devDependencies` object in `package.json`.
```suggestion
"eslint-plugin-n": "^15.7.0",
"eslint-plugin-promise": "^6.1.1",
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 227 | coderabbitai | github-actions[bot] | @@ -38,16 +38,21 @@
"devDependencies": {
"@jest/globals": "^29.5.0",
"@types/node": "^18.15.11",
+ "@typescript-eslint/eslint-plugin": "^5.59.0",
"@typescript-eslint/parser": "^5.59.0",
"@vercel/ncc": "^0.36.1",
"chatgpt": "^5.2.2",
"eslint": "^8.38.0",
+ "eslint-config-standard-with-typescript": "^34.0.1",
"eslint-plugin-github": "^4.6.1",
+ "eslint-plugin-import": "^2.27.5",
"eslint-plugin-jest": "^27.2.1",
+ "eslint-plugin-n": "^15.7.0",
+ "eslint-plugin-promise": "^6.1.1",
"jest": "^27.2.5",
"js-yaml": "^4.1.0",
"prettier": "2.8.7",
"ts-jest": "^27.1.2",
- "typescript": "^4.4.4"
+ "typescript": "^4.9.5" | :robot: OpenAI
The `typescript` dependency is updated from version `4.4.4` to `4.9.5`. Is this intentional? If so, please ignore this comment. Otherwise, please ensure that the correct version of `typescript` is specified in the `devDependencies` object in `package.json`.
```suggestion
"typescript": "^4.9.5",
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -1,12 +1,11 @@
-/* eslint-disable @typescript-eslint/explicit-function-return-type */
-import * as core from '@actions/core'
-import * as github from '@actions/github'
+import {info, warning} from '@actions/core'
+import {context as github_context} from '@actions/github'
import {octokit} from './octokit.js' | :robot: OpenAI
There's an unused import statement for `info` and `warning`. Please remove it.
```suggestion
import {context as github_context} from '@actions/github'
import {octokit} from './octokit.js'
const context = github_context
const repo = context.repo
export const COMMENT_GREETING = ':robot: OpenAI'
export const COMMENT_TAG = '<!-- This is an auto-generated comment by OpenAI -->'
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -1,12 +1,11 @@
-/* eslint-disable @typescript-eslint/explicit-function-return-type */
-import * as core from '@actions/core'
-import * as github from '@actions/github'
+import {info, warning} from '@actions/core'
+import {context as github_context} from '@actions/github'
import {octokit} from './octokit.js'
-const context = github.context
+const context = github_context
const repo = context.repo | :robot: OpenAI
There's no need to assign `github.context.repo` to a new variable. You can directly use `github.context.repo` instead.
```suggestion
const repo = github_context.repo
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -29,19 +28,22 @@ export const RAW_SUMMARY_TAG =
export const RAW_SUMMARY_TAG_END =
'<!-- end of auto-generated comment: raw summary by openai -->'
+export const COMMIT_ID_TAG = '<!-- commit_ids_reviewed_start -->'
+export const COMMIT_ID_TAG_END = '<!-- commit_ids_reviewed_end -->' | :robot: OpenAI
Please add a description of what these constants are used for.
```suggestion
export const RAW_SUMMARY_TAG_END =
'<!-- end of auto-generated comment: raw summary by openai -->'
/**
* These tags are used to identify the start and end of commit ids that have been reviewed.
*/
export const COMMIT_ID_TAG = '<!-- commit_ids_reviewed_start -->'
export const COMMIT_ID_TAG_END = '<!-- commit_ids_reviewed_end -->'
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -29,19 +28,22 @@ export const RAW_SUMMARY_TAG =
export const RAW_SUMMARY_TAG_END =
'<!-- end of auto-generated comment: raw summary by openai -->'
+export const COMMIT_ID_TAG = '<!-- commit_ids_reviewed_start -->'
+export const COMMIT_ID_TAG_END = '<!-- commit_ids_reviewed_end -->'
+
export class Commenter {
/**
* @param mode Can be "create", "replace". Default is "replace".
*/
async comment(message: string, tag: string, mode: string) {
let target: number
- if (context.payload.pull_request) {
+ if (context.payload.pull_request != null) {
target = context.payload.pull_request.number
- } else if (context.payload.issue) {
+ } else if (context.payload.issue != null) {
target = context.payload.issue.number
} else {
- core.warning(
- `Skipped: context.payload.pull_request and context.payload.issue are both null`
+ warning(
+ 'Skipped: context.payload.pull_request and context.payload.issue are both null'
)
return
} | :robot: OpenAI
> Note: This review was outside of the patch, so it was mapped to the patch with the greatest overlap. Original lines [38-68]
The `comment` function has been refactored. Please review the changes below.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -29,19 +28,22 @@ export const RAW_SUMMARY_TAG =
export const RAW_SUMMARY_TAG_END =
'<!-- end of auto-generated comment: raw summary by openai -->'
+export const COMMIT_ID_TAG = '<!-- commit_ids_reviewed_start -->'
+export const COMMIT_ID_TAG_END = '<!-- commit_ids_reviewed_end -->'
+
export class Commenter {
/**
* @param mode Can be "create", "replace". Default is "replace".
*/
async comment(message: string, tag: string, mode: string) {
let target: number | :robot: OpenAI
The `target` variable is not initialized. Please initialize it to `null`.
```suggestion
async comment(message: string, tag: string, mode: string) {
let target: number | null = null;
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -29,19 +28,22 @@ export const RAW_SUMMARY_TAG =
export const RAW_SUMMARY_TAG_END =
'<!-- end of auto-generated comment: raw summary by openai -->'
+export const COMMIT_ID_TAG = '<!-- commit_ids_reviewed_start -->'
+export const COMMIT_ID_TAG_END = '<!-- commit_ids_reviewed_end -->'
+
export class Commenter {
/**
* @param mode Can be "create", "replace". Default is "replace".
*/
async comment(message: string, tag: string, mode: string) {
let target: number
- if (context.payload.pull_request) {
+ if (context.payload.pull_request != null) {
target = context.payload.pull_request.number
- } else if (context.payload.issue) {
+ } else if (context.payload.issue != null) {
target = context.payload.issue.number
} else {
- core.warning(
- `Skipped: context.payload.pull_request and context.payload.issue are both null`
+ warning(
+ 'Skipped: context.payload.pull_request and context.payload.issue are both null'
) | :robot: OpenAI
The `if` block can be simplified using optional chaining.
```suggestion
if (context.payload.pull_request?.number != null) {
target = context.payload.pull_request.number;
} else if (context.payload.issue?.number != null) {
target = context.payload.issue.number;
} else {
warning(
'Skipped: context.payload.pull_request and context.payload.issue are both null'
);
return;
}
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -61,7 +63,7 @@ ${tag}`
} else if (mode === 'replace') {
await this.replace(body, tag, target)
} else {
- core.warning(`Unknown mode: ${mode}, use "replace" instead`)
+ warning(`Unknown mode: ${mode}, use "replace" instead`)
await this.replace(body, tag, target)
} | :robot: OpenAI
The `if` block can be simplified using a ternary operator.
```suggestion
mode === 'replace' ? await this.replace(body, tag, target) : (
warning(`Unknown mode: ${mode}, use "replace" instead`),
await this.replace(body, tag, target)
);
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -84,7 +86,7 @@ ${tag}`
return content
}
- get_raw_summary(summary: string) {
+ getRawSummary(summary: string) {
const content = this.getContentWithinTags(
summary,
RAW_SUMMARY_TAG, | :robot: OpenAI
The `getRawSummary` function uses `RAW_SUMMARY_TAG` instead of `RAW_SUMMARY_TAG_START`. Please update the constant name.
```suggestion
getRawSummary(summary: string) {
const content = this.getContentWithinTags(
summary,
RAW_SUMMARY_TAG_START,
RAW_SUMMARY_TAG_END
)
return content
}
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -1,25 +1,27 @@
-import * as core from '@actions/core'
-import * as github from '@actions/github'
+import {error, info, warning} from '@actions/core'
+// eslint-disable-next-line camelcase
+import {context as github_context} from '@actions/github' | :robot: OpenAI
The import statements should be sorted alphabetically.
```suggestion
import pLimit from 'p-limit'
import {context as github_context} from '@actions/github'
import {error, info, warning} from '@actions/core'
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -1,25 +1,27 @@
-import * as core from '@actions/core'
-import * as github from '@actions/github'
+import {error, info, warning} from '@actions/core'
+// eslint-disable-next-line camelcase
+import {context as github_context} from '@actions/github'
import pLimit from 'p-limit'
-import {Bot} from './bot.js'
+import {type Bot} from './bot'
import {
Commenter,
COMMENT_REPLY_TAG,
EXTRA_CONTENT_TAG,
RAW_SUMMARY_TAG,
RAW_SUMMARY_TAG_END,
SUMMARIZE_TAG | :robot: OpenAI
The `Commenter` class and its associated constants are not used in this file. Consider removing them.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -1,9 +1,9 @@
-import * as core from '@actions/core'
+import {getInput, warning} from '@actions/core' | :robot: OpenAI
The import statement on line 1 should be updated to only import the `getInput` and `warning` functions from the `@actions/core` module.
```suggestion
import {getInput, warning} from '@actions/core'
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -1,9 +1,9 @@
-import * as core from '@actions/core'
+import {getInput, warning} from '@actions/core'
import {Octokit} from '@octokit/action'
import {retry} from '@octokit/plugin-retry'
import {throttling} from '@octokit/plugin-throttling'
-const token = core.getInput('token') || process.env.GITHUB_TOKEN
+const token = getInput('token') || process.env.GITHUB_TOKEN | :robot: OpenAI
The `token` variable should be declared using `const` instead of `let`.
```suggestion
const token = getInput('token') || process.env.GITHUB_TOKEN
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -12,19 +12,19 @@ export const octokit = new RetryAndThrottlingOctokit({
onRateLimit: (
retryAfter: number,
options: any,
- o: Octokit,
+ _o: Octokit,
retryCount: number
) => {
- core.warning(
+ warning(
`Request quota exhausted for request ${options.method} ${options.url}
Retry after: ${retryAfter} seconds
Retry count: ${retryCount}
`
)
return true
},
- onSecondaryRateLimit: (retryAfter: number, options: any, o: Octokit) => {
- core.warning(
+ onSecondaryRateLimit: (_retryAfter: number, options: any) => {
+ warning(
`SecondaryRateLimit detected for request ${options.method} ${options.url}`
)
return true | :robot: OpenAI
The `core.warning` function calls on lines 18 and 27 should be updated to use the imported `warning` function instead. Additionally, the `_o` parameter on line 15 is unused and can be removed. Finally, the `options` parameter type on lines 14 and 26 should be updated to `Octokit.RequestOptions`.
```suggestion
{
throttle: {
onRateLimit: (
retryAfter: number,
options: Octokit.RequestOptions,
retryCount: number
) => {
warning(
`Request quota exhausted for request ${options.method} ${options.url}
Retry after: ${retryAfter} seconds
Retry count: ${retryCount}
`
)
return true
},
onSecondaryRateLimit: (retryAfter: number, options: Octokit.RequestOptions) => {
warning(
`SecondaryRateLimit detected for request ${options.method} ${options.url}`
)
return true
}
},
retry: {
doNotRetry: ['429'],
maxRetries: 10
}
}
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -35,10 +41,10 @@ async function run(): Promise<void> {
try {
lightBot = new Bot(
options,
- new OpenAIOptions(options.openai_light_model, options.light_token_limits)
+ new OpenAIOptions(options.openaiLightModel, options.lightTokenLimits)
)
} catch (e: any) {
- core.warning(
+ warning(
`Skipped: failed to create summary bot, please check your openai_api_key: ${e}, backtrace: ${e.stack}`
) | :robot: OpenAI
The try-catch block at lines 41-49 is missing an error message. Consider adding a more descriptive error message to help users debug issues.
```suggestion
try {
lightBot = new Bot(
options,
new OpenAIOptions(options.openaiLightModel, options.lightTokenLimits)
)
} catch (e: any) {
warning(
`Failed to create summary bot: ${e.message}, backtrace: ${e.stack}`
)
return
}
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -48,10 +54,10 @@ async function run(): Promise<void> {
try {
heavyBot = new Bot(
options,
- new OpenAIOptions(options.openai_heavy_model, options.heavy_token_limits)
+ new OpenAIOptions(options.openaiHeavyModel, options.heavyTokenLimits)
)
} catch (e: any) {
- core.warning(
+ warning(
`Skipped: failed to create review bot, please check your openai_api_key: ${e}, backtrace: ${e.stack}`
) | :robot: OpenAI
The try-catch block at lines 54-62 is missing an error message. Consider adding a more descriptive error message to help users debug issues.
```suggestion
try {
heavyBot = new Bot(
options,
new OpenAIOptions(options.openaiHeavyModel, options.heavyTokenLimits)
)
} catch (e: any) {
warning(
`Failed to create review bot: ${e.message}, backtrace: ${e.stack}`
)
return
}
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -69,25 +75,23 @@ async function run(): Promise<void> {
) {
await handleReviewComment(heavyBot, options, prompts)
} else {
- core.warning(
- 'Skipped: this action only works on push events or pull_request'
- )
+ warning('Skipped: this action only works on push events or pull_request')
}
} catch (e: any) {
if (e instanceof Error) {
- core.setFailed(`Failed to run: ${e.message}, backtrace: ${e.stack}`)
+ setFailed(`Failed to run: ${e.message}, backtrace: ${e.stack}`)
} else {
- core.setFailed(`Failed to run: ${e}, backtrace: ${e.stack}`)
+ setFailed(`Failed to run: ${e}, backtrace: ${e.stack}`)
} | :robot: OpenAI
Consider adding more specific error handling for the `setFailed` function call at lines 82-84. It would be helpful to include the exact error message in the failure output.
```suggestion
try {
if (process.env.GITHUB_EVENT_NAME === 'push' || process.env.GITHUB_EVENT_NAME === 'pull_request') {
await handleReviewComment(heavyBot, options, prompts)
} else {
warning('Skipped: this action only works on push events or pull_request')
}
} catch (e: any) {
if (e instanceof Error) {
setFailed(`Failed to run: ${e.message}, backtrace: ${e.stack}`)
} else {
setFailed(`Failed to run: ${e}, backtrace: ${e.stack}`)
}
}
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -69,25 +75,23 @@ async function run(): Promise<void> {
) {
await handleReviewComment(heavyBot, options, prompts)
} else {
- core.warning(
- 'Skipped: this action only works on push events or pull_request'
- )
+ warning('Skipped: this action only works on push events or pull_request')
}
} catch (e: any) {
if (e instanceof Error) {
- core.setFailed(`Failed to run: ${e.message}, backtrace: ${e.stack}`)
+ setFailed(`Failed to run: ${e.message}, backtrace: ${e.stack}`)
} else {
- core.setFailed(`Failed to run: ${e}, backtrace: ${e.stack}`)
+ setFailed(`Failed to run: ${e}, backtrace: ${e.stack}`)
}
}
}
process
.on('unhandledRejection', (reason, p) => {
- core.warning(`Unhandled Rejection at Promise: ${reason}, promise is ${p}`)
+ warning(`Unhandled Rejection at Promise: ${reason}, promise is ${p}`)
})
.on('uncaughtException', (e: any) => {
- core.warning(`Uncaught Exception thrown: ${e}, backtrace: ${e.stack}`)
+ warning(`Uncaught Exception thrown: ${e}, backtrace: ${e.stack}`)
})
await run() | :robot: OpenAI
Consider adding more specific error handling for the `warning` function calls at lines 90 and 94. It would be helpful to include the exact error message in the warning output.
```suggestion
process
.on('unhandledRejection', (reason, p) => {
warning(`Unhandled Rejection at Promise: ${reason}, promise is ${p}`)
})
.on('uncaughtException', (e: any) => {
warning(`Uncaught Exception thrown: ${e}, backtrace: ${e.stack}`)
})
await run()
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -1,12 +1,13 @@
-/* eslint-disable @typescript-eslint/explicit-function-return-type */
-import * as core from '@actions/core'
-import * as github from '@actions/github'
-import {octokit} from './octokit.js'
+import {info, warning} from '@actions/core'
+// eslint-disable-next-line camelcase
+import {context as github_context} from '@actions/github' | :robot: OpenAI
The import statements should be sorted alphabetically.
```suggestion
import {context as github_context} from '@actions/github'
import {info, warning} from '@actions/core'
import {octokit} from './octokit'
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -1,12 +1,13 @@
-/* eslint-disable @typescript-eslint/explicit-function-return-type */
-import * as core from '@actions/core'
-import * as github from '@actions/github'
-import {octokit} from './octokit.js'
+import {info, warning} from '@actions/core'
+// eslint-disable-next-line camelcase
+import {context as github_context} from '@actions/github'
+import {octokit} from './octokit'
-const context = github.context
+// eslint-disable-next-line camelcase
+const context = github_context
const repo = context.repo
-export const COMMENT_GREETING = `:robot: OpenAI`
+export const COMMENT_GREETING = ':robot: OpenAI'
export const COMMENT_TAG =
'<!-- This is an auto-generated comment by OpenAI -->' | :robot: OpenAI
The `COMMENT_TAG` constant is not used in the code. Please remove it.
```suggestion
export const COMMENT_GREETING = ':robot: OpenAI'
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -29,19 +30,22 @@ export const RAW_SUMMARY_TAG =
export const RAW_SUMMARY_TAG_END =
'<!-- end of auto-generated comment: raw summary by openai -->'
+export const COMMIT_ID_TAG = '<!-- commit_ids_reviewed_start -->'
+export const COMMIT_ID_TAG_END = '<!-- commit_ids_reviewed_end -->'
+
export class Commenter {
/**
* @param mode Can be "create", "replace". Default is "replace".
*/ | :robot: OpenAI
The `mode` parameter should have a default value of `"replace"`.
```suggestion
async comment(message: string, tag: string, mode: string = "replace") {
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -29,19 +30,22 @@ export const RAW_SUMMARY_TAG =
export const RAW_SUMMARY_TAG_END =
'<!-- end of auto-generated comment: raw summary by openai -->'
+export const COMMIT_ID_TAG = '<!-- commit_ids_reviewed_start -->'
+export const COMMIT_ID_TAG_END = '<!-- commit_ids_reviewed_end -->'
+
export class Commenter {
/**
* @param mode Can be "create", "replace". Default is "replace".
*/
async comment(message: string, tag: string, mode: string) {
let target: number
- if (context.payload.pull_request) {
+ if (context.payload.pull_request != null) {
target = context.payload.pull_request.number
- } else if (context.payload.issue) {
+ } else if (context.payload.issue != null) {
target = context.payload.issue.number
} else {
- core.warning(
- `Skipped: context.payload.pull_request and context.payload.issue are both null`
+ warning(
+ 'Skipped: context.payload.pull_request and context.payload.issue are both null'
)
return | :robot: OpenAI
Instead of logging a warning and returning, it would be better to throw an error if both `context.payload.pull_request` and `context.payload.issue` are null.
```suggestion
if (!context.payload.pull_request && !context.payload.issue) {
throw new Error('Both context.payload.pull_request and context.payload.issue are null')
}
let target = context.payload.pull_request?.number || context.payload.issue?.number
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -61,7 +65,7 @@ ${tag}`
} else if (mode === 'replace') {
await this.replace(body, tag, target)
} else {
- core.warning(`Unknown mode: ${mode}, use "replace" instead`)
+ warning(`Unknown mode: ${mode}, use "replace" instead`)
await this.replace(body, tag, target)
} | :robot: OpenAI
Instead of logging a warning and replacing the comment, it would be better to throw an error if an unknown mode is passed.
```suggestion
if (mode === 'replace') {
await this.replace(body, tag, target)
} else if (mode === 'create') {
await this.create(body)
} else {
throw new Error(`Unknown mode: ${mode}, use "replace" or "create" instead`)
}
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -100,83 +104,71 @@ ${tag}`
return lines.join('\n')
}
| :robot: OpenAI
The `replace` function should have a more descriptive name, such as `replaceCommentBody`.
```suggestion
async replaceCommentBody(body: string, tag: string, target: number) {
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -100,83 +104,71 @@ ${tag}`
return lines.join('\n')
}
- get_description(description: string) {
+ getDescription(description: string) {
return this.removeContentWithinTags(
description,
DESCRIPTION_TAG, | :robot: OpenAI
The `create` function should have a more descriptive name, such as `createNewComment`.
```suggestion
async createNewComment(body: string) {
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -100,83 +104,71 @@ ${tag}`
return lines.join('\n')
}
- get_description(description: string) {
+ getDescription(description: string) {
return this.removeContentWithinTags(
description,
DESCRIPTION_TAG,
DESCRIPTION_TAG_END
)
}
| :robot: OpenAI
The `update` function should have a more descriptive name, such as `updateExistingComment`.
```suggestion
async updateExistingComment(body: string, commentId: number) {
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -100,83 +104,71 @@ ${tag}`
return lines.join('\n')
}
- get_description(description: string) {
+ getDescription(description: string) {
return this.removeContentWithinTags(
description,
DESCRIPTION_TAG,
DESCRIPTION_TAG_END
)
}
- get_release_notes(description: string) {
- const release_notes = this.getContentWithinTags(
+ getReleaseNotes(description: string) {
+ const releaseNotes = this.getContentWithinTags(
description,
DESCRIPTION_TAG, | :robot: OpenAI
The `getComments` function should have a more descriptive name, such as `getCommentsForIssueOrPR`.
```suggestion
async getCommentsForIssueOrPR(issueNumber: number) {
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -100,83 +104,71 @@ ${tag}`
return lines.join('\n')
}
- get_description(description: string) {
+ getDescription(description: string) {
return this.removeContentWithinTags(
description,
DESCRIPTION_TAG,
DESCRIPTION_TAG_END
)
}
- get_release_notes(description: string) {
- const release_notes = this.getContentWithinTags(
+ getReleaseNotes(description: string) {
+ const releaseNotes = this.getContentWithinTags(
description,
DESCRIPTION_TAG,
DESCRIPTION_TAG_END
)
- return release_notes.replace(/(^|\n)> .*/g, '')
+ return releaseNotes.replace(/(^|\n)> .*/g, '')
} | :robot: OpenAI
The `deleteComment` function should have a more descriptive name, such as `deleteExistingComment`.
```suggestion
async deleteExistingComment(commentId: number) {
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -100,83 +104,71 @@ ${tag}`
return lines.join('\n')
}
- get_description(description: string) {
+ getDescription(description: string) {
return this.removeContentWithinTags(
description,
DESCRIPTION_TAG,
DESCRIPTION_TAG_END
)
}
- get_release_notes(description: string) {
- const release_notes = this.getContentWithinTags(
+ getReleaseNotes(description: string) {
+ const releaseNotes = this.getContentWithinTags(
description,
DESCRIPTION_TAG,
DESCRIPTION_TAG_END
)
- return release_notes.replace(/(^|\n)> .*/g, '')
+ return releaseNotes.replace(/(^|\n)> .*/g, '')
}
- async update_description(pull_number: number, message: string) {
+ async updateDescription(pullNumber: number, message: string) {
// add this response to the description field of the PR as release notes by looking
// for the tag (marker) | :robot: OpenAI
The `getCommentBody` function should have a more descriptive name, such as `getCommentBodyById`.
```suggestion
async getCommentBodyById(commentId: number) {
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -100,83 +104,71 @@ ${tag}`
return lines.join('\n')
}
- get_description(description: string) {
+ getDescription(description: string) {
return this.removeContentWithinTags(
description,
DESCRIPTION_TAG,
DESCRIPTION_TAG_END
)
}
- get_release_notes(description: string) {
- const release_notes = this.getContentWithinTags(
+ getReleaseNotes(description: string) {
+ const releaseNotes = this.getContentWithinTags(
description,
DESCRIPTION_TAG,
DESCRIPTION_TAG_END
)
- return release_notes.replace(/(^|\n)> .*/g, '')
+ return releaseNotes.replace(/(^|\n)> .*/g, '')
}
- async update_description(pull_number: number, message: string) {
+ async updateDescription(pullNumber: number, message: string) {
// add this response to the description field of the PR as release notes by looking
// for the tag (marker)
try {
// get latest description from PR
const pr = await octokit.pulls.get({
owner: repo.owner, | :robot: OpenAI
The `getCommentId` function should have a more descriptive name, such as `getCommentIdByTag`.
```suggestion
async getCommentIdByTag(tag: string, issueNumber: number) {
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -100,83 +104,71 @@ ${tag}`
return lines.join('\n')
}
- get_description(description: string) {
+ getDescription(description: string) {
return this.removeContentWithinTags(
description,
DESCRIPTION_TAG,
DESCRIPTION_TAG_END
)
}
- get_release_notes(description: string) {
- const release_notes = this.getContentWithinTags(
+ getReleaseNotes(description: string) {
+ const releaseNotes = this.getContentWithinTags(
description,
DESCRIPTION_TAG,
DESCRIPTION_TAG_END
)
- return release_notes.replace(/(^|\n)> .*/g, '')
+ return releaseNotes.replace(/(^|\n)> .*/g, '')
}
- async update_description(pull_number: number, message: string) {
+ async updateDescription(pullNumber: number, message: string) {
// add this response to the description field of the PR as release notes by looking
// for the tag (marker)
try {
// get latest description from PR
const pr = await octokit.pulls.get({
owner: repo.owner,
repo: repo.repo,
- pull_number
+ // eslint-disable-next-line camelcase
+ pull_number: pullNumber
}) | :robot: OpenAI
The `getCommentsByTag` function should have a more descriptive name, such as `getCommentsByTagForIssueOrPR`.
```suggestion
async getCommentsByTagForIssueOrPR(tag: string, issueNumber: number) {
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -100,83 +104,71 @@ ${tag}`
return lines.join('\n')
}
- get_description(description: string) {
+ getDescription(description: string) {
return this.removeContentWithinTags(
description,
DESCRIPTION_TAG,
DESCRIPTION_TAG_END
)
}
- get_release_notes(description: string) {
- const release_notes = this.getContentWithinTags(
+ getReleaseNotes(description: string) {
+ const releaseNotes = this.getContentWithinTags(
description,
DESCRIPTION_TAG,
DESCRIPTION_TAG_END
)
- return release_notes.replace(/(^|\n)> .*/g, '')
+ return releaseNotes.replace(/(^|\n)> .*/g, '')
}
- async update_description(pull_number: number, message: string) {
+ async updateDescription(pullNumber: number, message: string) {
// add this response to the description field of the PR as release notes by looking
// for the tag (marker)
try {
// get latest description from PR
const pr = await octokit.pulls.get({
owner: repo.owner,
repo: repo.repo,
- pull_number
+ // eslint-disable-next-line camelcase
+ pull_number: pullNumber
})
let body = ''
if (pr.data.body) {
body = pr.data.body
} | :robot: OpenAI
The `getCommentIdsByTag` function should have a more descriptive name, such as `getCommentIdsByTagForIssueOrPR`.
```suggestion
async getCommentIdsByTagForIssueOrPR(tag: string, issueNumber: number) {
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 227 | coderabbitai | github-actions[bot] | @@ -100,83 +104,71 @@ ${tag}`
return lines.join('\n')
}
- get_description(description: string) {
+ getDescription(description: string) {
return this.removeContentWithinTags(
description,
DESCRIPTION_TAG,
DESCRIPTION_TAG_END
)
}
- get_release_notes(description: string) {
- const release_notes = this.getContentWithinTags(
+ getReleaseNotes(description: string) {
+ const releaseNotes = this.getContentWithinTags(
description,
DESCRIPTION_TAG,
DESCRIPTION_TAG_END
)
- return release_notes.replace(/(^|\n)> .*/g, '')
+ return releaseNotes.replace(/(^|\n)> .*/g, '')
}
- async update_description(pull_number: number, message: string) {
+ async updateDescription(pullNumber: number, message: string) {
// add this response to the description field of the PR as release notes by looking
// for the tag (marker)
try {
// get latest description from PR
const pr = await octokit.pulls.get({
owner: repo.owner,
repo: repo.repo,
- pull_number
+ // eslint-disable-next-line camelcase
+ pull_number: pullNumber
})
let body = ''
if (pr.data.body) {
body = pr.data.body
}
- const description = this.get_description(body)
-
- // find the tag in the description and replace the content between the tag and the tag_end
- // if not found, add the tag and the content to the end of the description
- const tag_index = description.indexOf(DESCRIPTION_TAG)
- const tag_end_index = description.indexOf(DESCRIPTION_TAG_END)
- const comment = `${DESCRIPTION_TAG}\n${message}\n${DESCRIPTION_TAG_END}`
- if (tag_index === -1 || tag_end_index === -1) {
- const new_description = `${description}\n${comment}`
- await octokit.pulls.update({
- owner: repo.owner,
- repo: repo.repo,
- pull_number,
- body: new_description
- })
- } else {
- let new_description = description.substring(0, tag_index)
- new_description += comment
- new_description += description.substring(
- tag_end_index + DESCRIPTION_TAG_END.length
- )
- await octokit.pulls.update({
- owner: repo.owner,
- repo: repo.repo,
- pull_number,
- body: new_description
- })
- }
+ const description = this.getDescription(body)
+
+ const messageClean = this.removeContentWithinTags(
+ message, | :robot: OpenAI
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 226 | coderabbitai | github-actions[bot] | @@ -0,0 +1,275 @@
+import {Inputs} from './inputs.js'
+
+export class Prompts {
+ summarize: string
+ summarize_release_notes: string | :robot: OpenAI
The `prompts.ts` file has been completely removed. No review is necessary.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 218 | coderabbitai | github-actions[bot] | @@ -29,22 +29,19 @@ export class Prompts {
render_summarize_file_diff(inputs: Inputs): string {
const prompt = `${this.summarize_file_diff}
-Below the summary, I would also like you to triage the diff
-as \`NEEDS_REVIEW\` or \`APPROVED\` based on the following
-criteria:
+Below the summary, I would also like you to triage the diff as \`NEEDS_REVIEW\` or
+\`APPROVED\` based on the following criteria:
-- If the diff introduces new functionality, modifies existing logic,
- or has potential for bugs, triage it as \`NEEDS_REVIEW\`.
-- If the diff only contains minor changes, such as fixing typos,
- formatting, renaming variables, triage it as \`APPROVED\`.
+- If the diff involves any modifications to the logic or functionality, even if they
+ seem minor, triage it as \`NEEDS_REVIEW\`. This includes changes to control structures,
+ function calls, or variable assignments that might impact the behavior of the code.
+- If the diff only contains very minor changes that don't affect the code logic, such as
+ fixing typos, formatting, or renaming variables for clarity, triage it as \`APPROVED\`.
-Please evaluate the diff thoroughly and take into account factors
-such as the number of lines changed, the potential impact on the
-overall system, and the likelihood of introducing new bugs or
-security vulnerabilities.
-
-Use the following format to triage the diff and add no additional text:
-[TRIAGE]: <NEEDS_REVIEW or APPROVED>
+Please evaluate the diff thoroughly and take into account factors such as the number of
+lines changed, the potential impact on the overall system, and the likelihood of
+introducing new bugs or security vulnerabilities.
+When in doubt, always err on the side of caution and triage the diff as \`NEEDS_REVIEW\`. | :robot: OpenAI
The new prompt provides clearer guidelines for triaging code changes based on their potential impact. However, the instructions could be further improved by providing more specific examples of what constitutes a minor change versus a modification to logic or functionality. Consider adding more detailed examples to help users better understand how to triage the diff.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 218 | coderabbitai | github-actions[bot] | @@ -155,7 +155,7 @@ export const codeReview = async (
}
}
} catch (error) {
- core.warning(`Failed to get file contents: ${error}, skipping.`)
+ core.warning(`Failed to get file contents: ${error}`)
} | :robot: OpenAI
The error message should not be logged as a warning. It should be logged as an error instead.
```suggestion
} catch (error) {
core.error(`Failed to get file contents: ${error}`)
}
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 218 | coderabbitai | github-actions[bot] | @@ -324,12 +324,13 @@ ${filename}: ${summary}
}
// ask chatgpt to summarize the summaries
const prompt = `
-Provided below are changesets in this pull request.
-The format consists of filename(s) and the summary of changes
-for those files. There is a separator between each changeset.
+Provided below are changesets in this pull request. Changesets
+are in chronlogical order and new changesets are appended to the
+end of the list. The format consists of filename(s) and the summary
+of changes for those files. There is a separator between each changeset.
Your task is to de-deduplicate and group together files with
-related/similar changes into a single changeset. Respond with the
-updated changesets using the same format as the input.
+related/similar changes into a single changeset. Respond with the updated
+changesets using the same format as the input.
${inputs.raw_summary}
` | :robot: OpenAI
The prompt is unclear and difficult to understand. Consider rephrasing it to make it more concise and easier to follow. Additionally, the prompt should be split into multiple lines for better readability.
```suggestion
Provided below are changesets in this pull request. Changesets are in chronological order and new changesets are appended to the end of the list. The format consists of filename(s) and the summary of changes for those files. There is a separator between each changeset.
Your task is to group together files with related/similar changes into a single changeset and provide an updated summary using the same format as the input.
Changesets:
${inputs.raw_summary}
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 218 | coderabbitai | github-actions[bot] | @@ -110,7 +110,7 @@ changes (`openai_light_model` in configuration) and `gpt-4` for more complex
review and commenting tasks (`openai_heavy_model` in configuration). | :robot: OpenAI
The phrase "review and commenting tasks" is vague. Please provide more specific details about what these tasks entail.
```suggestion
# Please replace this line with a more specific description of the review and commenting tasks.
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 218 | coderabbitai | github-actions[bot] | @@ -110,7 +110,7 @@ changes (`openai_light_model` in configuration) and `gpt-4` for more complex
review and commenting tasks (`openai_heavy_model` in configuration).
Costs: `gpt-3.5-turbo` is dirt cheap. `gpt-4` is orders of magnitude more
-expensive, but the results are vastly superior. We are typically spending $50 a
+expensive, but the results are vastly superior. We are typically spending $20 a
day for a 20 developer team with `gpt-4` based review and commenting. | :robot: OpenAI
Please provide more context around the cost comparison between `gpt-3.5-turbo` and `gpt-4`. What are the specific benefits of using `gpt-4` that justify the increased cost? Also, please clarify whether the $20/day cost for `gpt-4` is per developer or for the entire team.
```suggestion
# Please replace this line with a more detailed explanation of the benefits of using gpt-4 and the cost breakdown.
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 218 | coderabbitai | github-actions[bot] | @@ -110,7 +110,7 @@ changes (`openai_light_model` in configuration) and `gpt-4` for more complex
review and commenting tasks (`openai_heavy_model` in configuration).
Costs: `gpt-3.5-turbo` is dirt cheap. `gpt-4` is orders of magnitude more
-expensive, but the results are vastly superior. We are typically spending $50 a
+expensive, but the results are vastly superior. We are typically spending $20 a
day for a 20 developer team with `gpt-4` based review and commenting.
| :robot: OpenAI
Please clarify whether the $20/day cost for `gpt-4` is per developer or for the entire team.
```suggestion
# Please replace this line with a clarification of whether the $20/day cost for gpt-4 is per developer or for the entire team.
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 222 | coderabbitai | github-actions[bot] | @@ -98,20 +98,46 @@ export const codeReview = async (
core.info(`Will review from commit: ${highest_reviewed_commit_id}`)
}
- // get the list of files changed between the highest reviewed commit
- // and the latest (head) commit
- // use octokit.pulls.compareCommits to get the list of files changed
- // between the highest reviewed commit and the latest (head) commit
- const diff = await octokit.repos.compareCommits({
+ // Fetch the diff between the highest reviewed commit and the latest commit of the PR branch
+ const incrementalDiff = await octokit.repos.compareCommits({
owner: repo.owner,
repo: repo.repo,
base: highest_reviewed_commit_id,
head: context.payload.pull_request.head.sha | :robot: OpenAI
`octokit.repos.compareCommits()` is called twice with almost identical parameters. Consider refactoring this code to avoid duplication. One way to do this would be to create a function that takes in the `base` and `head` commit IDs as arguments and returns the diff between them. This function can then be called twice with different arguments.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 219 | coderabbitai | github-actions[bot] | @@ -42,6 +42,10 @@ Please evaluate the diff thoroughly and take into account factors such as the nu
lines changed, the potential impact on the overall system, and the likelihood of
introducing new bugs or security vulnerabilities.
When in doubt, always err on the side of caution and triage the diff as \`NEEDS_REVIEW\`.
+
+You must follow the format below strictly for triaging the diff and
+do not add any additional text in your response: | :robot: OpenAI
The new hunk adds a strict format for triaging pull requests. It is good to have a standard format for triaging, but it would be helpful to provide more context on what `NEEDS_REVIEW` and `APPROVED` mean in this context. Also, it might be useful to add an example of how to use the format. Consider adding a comment explaining these points.
```suggestion
// Please add a comment here explaining what NEEDS_REVIEW and APPROVED mean in this context and provide an example of how to use the format.
[TRIAGE]: <NEEDS_REVIEW or APPROVED>
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 214 | coderabbitai | github-actions[bot] | @@ -29,24 +29,22 @@ export class Prompts {
render_summarize_file_diff(inputs: Inputs): string {
const prompt = `${this.summarize_file_diff}
-Below the summary, I would also like you to classify the complexity
-of the diff as \`COMPLEX\` or \`SIMPLE\` based on the following
+Below the summary, I would also like you to triage the diff
+as \`NEEDS_REVIEW\` or \`APPROVED\` based on the following
criteria:
-- If the diff introduces new functionality, modifies existing logic
- significantly, or has potential security implications,
- classify it as \`COMPLEX\`.
+- If the diff introduces new functionality, modifies existing logic,
+ or has potential for bugs, triage it as \`NEEDS_REVIEW\`.
- If the diff only contains minor changes, such as fixing typos,
- formatting, or updating documentation, classify it as \`SIMPLE\`.
+ formatting, renaming variables, triage it as \`APPROVED\`.
Please evaluate the diff thoroughly and take into account factors
such as the number of lines changed, the potential impact on the
overall system, and the likelihood of introducing new bugs or
security vulnerabilities. | :robot: OpenAI
The new hunk has replaced the old hunk that classified the complexity of the diff. The new hunk now asks for a triage system to evaluate diffs in the codebase. However, the instructions provided in the new hunk are not clear and may lead to confusion. It is recommended to provide more detailed instructions on how to evaluate the diff and what factors to consider when triaging it. Additionally, it would be helpful to provide examples of what constitutes a "minor change" versus a change that "introduces new functionality" or "modifies existing logic significantly".
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 213 | coderabbitai | github-actions[bot] | @@ -29,13 +29,23 @@ export class Prompts {
render_summarize_file_diff(inputs: Inputs): string {
const prompt = `${this.summarize_file_diff}
-Below the summary, I would also like you to classify the
-complexity of the diff as \`COMPLEX\` or \`SIMPLE\` based
-on whether the diff is a simple change that looks good as it
-is or a complex change that needs thorough review.
+Below the summary, I would also like you to classify the complexity
+of the diff as \`COMPLEX\` or \`SIMPLE\` based on the following
+criteria:
-Use the following format to classify the complexity of the
-diff and add no additional text:
+- If the diff introduces new functionality, modifies existing logic
+ significantly, or has potential security implications,
+ classify it as \`COMPLEX\`.
+- If the diff only contains minor changes, such as fixing typos,
+ formatting, or updating documentation, classify it as \`SIMPLE\`.
+
+Please evaluate the diff thoroughly and take into account factors
+such as the number of lines changed, the potential impact on the
+overall system, and the likelihood of introducing new bugs or
+security vulnerabilities.
+
+Use the following format to classify the complexity of the diff
+and add no additional text:
[COMPLEXITY]: <COMPLEX or SIMPLE>
` | :robot: OpenAI
The new prompt added to `render_summarize_file_diff` method is a good addition. However, the criteria for classifying the complexity of the diff seems incomplete and subjective. It would be better to provide more objective criteria such as the number of lines changed, the potential impact on the overall system, and the likelihood of introducing new bugs or security vulnerabilities. Additionally, it would be helpful to provide examples of what constitutes a complex or simple change. Consider revising the prompt to include these suggestions.
```suggestion
render_summarize_file_diff(inputs: Inputs): string {
const prompt = `${this.summarize_file_diff}
Below the summary, please classify the complexity of the diff as \`COMPLEX\` or \`SIMPLE\` based on the following criteria:
- If the diff introduces new functionality, modifies existing logic significantly, or has potential security implications, classify it as \`COMPLEX\`.
- If the diff only contains minor changes, such as fixing typos, formatting, or updating documentation, classify it as \`SIMPLE\`.
Please evaluate the diff thoroughly and take into account factors such as the number of lines changed, the potential impact on the overall system, and the likelihood of introducing new bugs or security vulnerabilities.
Examples of complex changes include but are not limited to:
- Changes that introduce new functionality
- Changes that modify existing logic significantly
- Changes that have potential security implications
Examples of simple changes include but are not limited to:
- Changes that fix typos
- Changes that update documentation
- Changes that reformat code
Use the following format to classify the complexity of the diff and add no additional text:
[COMPLEXITY]: <COMPLEX or SIMPLE>
`
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 212 | coderabbitai | github-actions[bot] | @@ -27,7 +27,21 @@ export class Prompts {
}
render_summarize_file_diff(inputs: Inputs): string { | :robot: OpenAI
There's a missing backtick at the end of the `prompt` string.
```suggestion
const prompt = `${this.summarize_file_diff}`;
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 212 | coderabbitai | github-actions[bot] | @@ -27,7 +27,21 @@ export class Prompts {
}
render_summarize_file_diff(inputs: Inputs): string {
- return inputs.render(this.summarize_file_diff)
+ const prompt = `${this.summarize_file_diff}
+
+Below the summary, I would also like you to classify the
+complexity of the diff as \`COMPLEX\` or \`SIMPLE\` based
+on whether the change is a simple chore such are renaming
+a variable or a complex change such as adding a new feature.
+Any change that does not change the logic of the code is
+considered a simple change.
+
+Use the following format to classify the complexity of the
+diff and add no additional text:
+[COMPLEXITY]: <COMPLEX or SIMPLE>
+` | :robot: OpenAI
There's a missing space after the colon in the `[COMPLEXITY]:` tag.
```suggestion
[COMPLEXITY]: <COMPLEX or SIMPLE>
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 212 | coderabbitai | github-actions[bot] | @@ -217,7 +217,7 @@ ${hunks.old_hunk}
filename: string,
file_content: string,
file_diff: string
- ): Promise<[string, string] | null> => {
+ ): Promise<[string, string, boolean] | null> => {
const ins = inputs.clone()
if (file_diff.length === 0) {
core.warning(`summarize: file_diff is empty, skip ${filename}`) | :robot: OpenAI
Consider renaming the function `summarize_file_diff` to `summarize_complexity_of_file_diff` to reflect the new return type of `[string, string, boolean] | null`.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 212 | coderabbitai | github-actions[bot] | @@ -226,6 +226,7 @@ ${hunks.old_hunk}
}
ins.filename = filename
+
// render prompt based on inputs so far
let tokens = tokenizer.get_token_count(
prompts.render_summarize_file_diff(ins) | :robot: OpenAI
The `filename` property is being set on the `ins` object but it is not clear what this object is used for. Consider adding a comment explaining the purpose of the `ins` object and how it is used in the subsequent code.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 212 | coderabbitai | github-actions[bot] | @@ -268,7 +269,15 @@ ${hunks.old_hunk}
summaries_failed.push(`${filename} (nothing obtained from openai)`)
return null
} else {
- return [filename, summarize_resp]
+ // parse the comment to look for complexity classification
+ // Format is : [COMPLEXITY]: <COMPLEX or SIMPLE>
+ // if the change is complex return true, else false
+ const complexity = summarize_resp
+ .split('[COMPLEXITY]: ')[1]
+ .split('\n')[0]
+ const is_complex = complexity === 'COMPLEX' ? true : false
+ core.info(`filename: ${filename}, complexity: ${complexity}`)
+ return [filename, summarize_resp, is_complex]
} | :robot: OpenAI
The logic for parsing the complexity classification from the OpenAI response seems brittle. It assumes that the format of the response will always be `[COMPLEXITY]: <COMPLEX or SIMPLE>` and that the complexity classification will always be on the first line after the `[COMPLEXITY]:` tag. If the format of the response changes, this code will break. Consider using a more robust method for parsing the complexity classification, such as regular expressions.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 212 | coderabbitai | github-actions[bot] | @@ -293,7 +302,7 @@ ${hunks.old_hunk}
const summaries = (await Promise.all(summaryPromises)).filter(
summary => summary !== null
- ) as [string, string][]
+ ) as [string, string, boolean][]
if (summaries.length > 0) { | :robot: OpenAI
The return type of the `summarizeFiles` function has changed from `[string, string][]` to `[string, string, boolean][]`. This change is not reflected in the function name and may cause confusion for users who are calling this function. Consider renaming the function to reflect the new return type.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 212 | coderabbitai | github-actions[bot] | @@ -420,6 +429,20 @@ ${
`
if (options.summary_only !== true) {
+ let files_and_changes_review = files_and_changes
+ const reviews_skipped: string[] = []
+ // filter out files that are less complex and remove them from the review
+ // loop through summaries and check the complexity flag
+ for (const [filename, , is_complex] of summaries) {
+ if (!is_complex) {
+ // remove the file from the review
+ files_and_changes_review = files_and_changes_review.filter(
+ ([file]) => file !== filename
+ )
+ reviews_skipped.push(filename)
+ }
+ }
+ | :robot: OpenAI
The logic for filtering out files with low complexity seems correct, but it modifies the `files_and_changes_review` array in place. This can make the code harder to reason about and lead to bugs. Consider creating a new array instead of modifying the existing one.
<!-- This is an auto-generated reply by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 212 | coderabbitai | github-actions[bot] | @@ -684,7 +707,12 @@ ${comment_chain}
}
const reviewPromises = []
- for (const [filename, file_content, , patches] of files_and_changes) {
+ for (const [
+ filename,
+ file_content,
+ ,
+ patches
+ ] of files_and_changes_review) { | :robot: OpenAI
The `patches` variable is unused in this loop. Consider removing it to make the code clearer.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 212 | coderabbitai | github-actions[bot] | @@ -710,6 +738,22 @@ ${
* ${reviews_failed.join('\n* ')}
+</details>
+`
+ : ''
+}
+
+${
+ reviews_skipped.length > 0
+ ? `<details>
+<summary>Files not reviewed due to simple changes (${
+ reviews_skipped.length
+ })</summary>
+
+### Skipped review
+
+* ${reviews_skipped.join('\n* ')}
+
</details>
`
: '' | :robot: OpenAI
The logic for displaying skipped and failed reviews seems correct, but the formatting of the output could be improved. Consider using a table or bullet points to make the output easier to read.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 212 | coderabbitai | github-actions[bot] | @@ -27,7 +27,21 @@ export class Prompts {
}
render_summarize_file_diff(inputs: Inputs): string {
- return inputs.render(this.summarize_file_diff)
+ const prompt = `${this.summarize_file_diff}
+
+Below the summary, I would also like you to classify the
+complexity of the diff as \`COMPLEX\` or \`SIMPLE\` based
+on whether the change is a simple chore such are renaming
+a variable or a complex change such as adding a new feature.
+Any change that does not change the logic of the code is
+considered a simple change. | :robot: OpenAI
The implementation of classifying the complexity of the diff is not clear. Please provide more details on how this will be implemented and what criteria will be used to classify a change as complex or simple. Additionally, please consider adding comments to the code to make it more readable and maintainable.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 212 | coderabbitai | github-actions[bot] | @@ -226,6 +226,7 @@ ${hunks.old_hunk}
}
ins.filename = filename
+
// render prompt based on inputs so far | :robot: OpenAI
The `filename` variable is assigned to `ins.filename` on line 228. However, it is not clear what `ins` is and where it comes from. Consider adding a comment explaining what `ins` is and how it is related to `filename`.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 212 | coderabbitai | github-actions[bot] | @@ -293,7 +311,7 @@ ${hunks.old_hunk}
const summaries = (await Promise.all(summaryPromises)).filter(
summary => summary !== null
- ) as [string, string][]
+ ) as [string, string, boolean][]
if (summaries.length > 0) {
// join summaries into one in the batches of 20 | :robot: OpenAI
The return type of the `summaries` array has changed from `[string, string][]` to `[string, string, boolean][]`. This change is not reflected in the code that follows and may cause issues. Consider updating the code that follows to handle the new return type.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 212 | coderabbitai | github-actions[bot] | @@ -420,6 +438,20 @@ ${
`
if (options.summary_only !== true) {
+ let files_and_changes_review = files_and_changes
+ const reviews_skipped: string[] = []
+ // filter out files that are less complex and remove them from the review
+ // loop through summaries and check the complexity flag
+ for (const [filename, , is_complex] of summaries) {
+ if (!is_complex) {
+ // remove the file from the review
+ files_and_changes_review = files_and_changes_review.filter(
+ ([file]) => file !== filename
+ )
+ reviews_skipped.push(filename)
+ }
+ }
+ | :robot: OpenAI
A new feature has been added to filter out files that are less complex and remove them from the review. This feature is implemented using the `summaries` array that is generated earlier in the code. While this feature is useful, it may be confusing for users who are not aware of this behavior. Consider adding a comment explaining how this feature works and how it affects the review process.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 212 | coderabbitai | github-actions[bot] | @@ -684,7 +716,12 @@ ${comment_chain}
}
const reviewPromises = []
- for (const [filename, file_content, , patches] of files_and_changes) {
+ for (const [
+ filename,
+ file_content,
+ ,
+ patches
+ ] of files_and_changes_review) {
if (options.max_files <= 0 || reviewPromises.length < options.max_files) { | :robot: OpenAI
The `files_and_changes_review` array is initialized with `files_and_changes` on line 441. However, it is not clear why this is necessary and how it affects the review process. Consider adding a comment explaining why `files_and_changes_review` is needed and how it differs from `files_and_changes`.
747:
Consider adding a blank line after this line for better readability.
No substantive issues were found in the remaining code hunks.
```suggestion
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 212 | coderabbitai | github-actions[bot] | @@ -27,7 +27,21 @@ export class Prompts {
}
render_summarize_file_diff(inputs: Inputs): string {
- return inputs.render(this.summarize_file_diff)
+ const prompt = `${this.summarize_file_diff}
+
+Below the summary, I would also like you to classify the
+complexity of the diff as \`COMPLEX\` or \`SIMPLE\` based
+on whether the change is a simple chore or a complex change
+that needs further review. If the diff does not substantively
+change the logic/functionality of the code, then it is a
+simple change. | :robot: OpenAI
The comment is unclear and could be improved. Consider rephrasing it to something like:
"Classify the complexity of the diff as either `COMPLEX` or `SIMPLE`. If the change is a simple chore that does not substantively change the logic/functionality of the code, then it is a simple change. Otherwise, if the change is complex and needs further review, classify it as complex. Use the following format to classify the complexity of the diff and add no additional text: [COMPLEXITY]: <COMPLEX or SIMPLE>"
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 212 | coderabbitai | github-actions[bot] | @@ -27,7 +27,19 @@ export class Prompts {
}
render_summarize_file_diff(inputs: Inputs): string {
- return inputs.render(this.summarize_file_diff)
+ const prompt = `${this.summarize_file_diff} | :robot: OpenAI
The `summarize_file_diff` prompt is missing a closing backtick.
```suggestion
const prompt = `${this.summarize_file_diff}`
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 212 | coderabbitai | github-actions[bot] | @@ -27,7 +27,19 @@ export class Prompts {
}
render_summarize_file_diff(inputs: Inputs): string {
- return inputs.render(this.summarize_file_diff)
+ const prompt = `${this.summarize_file_diff}
+
+Below the summary, I would also like you to classify the
+complexity of the diff as \`COMPLEX\` or \`SIMPLE\` based
+on whether the diff is a simple change that looks good as it
+is or a complex change that needs thorough review.
+
+Use the following format to classify the complexity of the
+diff and add no additional text:
+[COMPLEXITY]: <COMPLEX or SIMPLE>
+`
+
+ return inputs.render(prompt)
}
| :robot: OpenAI
The new code adds a feature to classify the complexity of a diff as either `COMPLEX` or `SIMPLE` based on whether the change is a simple chore or a complex change that needs further review. However, the implementation is incomplete and does not actually classify the complexity of the diff. Please complete the implementation and add error handling for invalid input. Consider using an enum for the complexity values instead of strings.
```typescript
enum Complexity {
SIMPLE = "SIMPLE",
COMPLEX = "COMPLEX"
}
function classifyComplexity(complexity: string): Complexity {
if (complexity === Complexity.SIMPLE || complexity === Complexity.COMPLEX) {
return complexity;
} else {
throw new Error("Invalid complexity value");
}
}
render_summarize_file_diff(inputs: Inputs): string {
const prompt = `${this.summarize_file_diff}
Below the summary, I would also like you to classify the
complexity of the diff as \`COMPLEX\` or \`SIMPLE\` based
on whether the diff is a simple change that looks good as it
is or a complex change that needs thorough review.
Use the following format to classify the complexity of the
diff and add no additional text:
[COMPLEXITY]: <COMPLEX or SIMPLE>
`
const complexityRegex = /\[COMPLEXITY\]:\s*(\w+)/;
const match = inputs.prompt(prompt).match(complexityRegex);
if (!match) {
throw new Error("Invalid input format");
}
const complexity = classifyComplexity(match[1]);
// TODO: classify the complexity of the diff
return inputs.render(prompt);
}
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 211 | coderabbitai | github-actions[bot] | @@ -8,8 +8,7 @@ async function run(): Promise<void> {
const options: Options = new Options(
core.getBooleanInput('debug'),
core.getBooleanInput('summary_only'),
- core.getInput('max_files_to_summarize'),
- core.getInput('max_files_to_review'),
+ core.getInput('max_files'), | :robot: OpenAI
The `max_files` input is not defined. Did you mean to use `max_files_to_summarize` or `max_files_to_review`?
```suggestion
core.getInput('max_files_to_summarize'),
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 211 | coderabbitai | github-actions[bot] | @@ -1,10 +1,10 @@
-# OpenAI ChatGPT based PR reviewer and summarizer
+# OpenAI ChatGPT-based PR reviewer and summarizer
## Overview
-This [OpenAI ChatGPT](https://platform.openai.com/docs/guides/chat) based GitHub
+This [OpenAI ChatGPT-based](https://platform.openai.com/docs/guides/chat) GitHub
Action provides a summary, release notes and review of pull requests. The
prompts have been tuned for a concise response. To prevent excessive
notifications, this action can be configured to skip adding review comments when | :robot: OpenAI
The new hunk looks good. No substantive issues detected.
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 211 | coderabbitai | github-actions[bot] | @@ -22,6 +22,8 @@ NOTES:
has a
[more conservative data usage policy](https://openai.com/policies/api-data-usage-policies)
compared to their ChatGPT offering. | :robot: OpenAI
The link to OpenAI's data usage policy is broken. Please update it to the correct URL.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 211 | coderabbitai | github-actions[bot] | @@ -22,6 +22,8 @@ NOTES:
has a
[more conservative data usage policy](https://openai.com/policies/api-data-usage-policies)
compared to their ChatGPT offering.
+- This action is not affiliated with OpenAI.
+- This action is going through rapid iteration, so expect breaking changes. | :robot: OpenAI
It's unclear what the purpose of these two lines is. Please provide more context or remove them.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 211 | coderabbitai | github-actions[bot] | @@ -178,7 +180,7 @@ $ npm run build && npm run package
## FAQs
-### Review pull request from forks
+### Review pull requests from forks
GitHub Actions limits the access of secrets from forked repositories. To enable
this feature, you need to use the `pull_request_target` event instead of | :robot: OpenAI
Please provide more context on what `pull_request_target` event is and how it enables access to secrets from forked repositories.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 211 | coderabbitai | github-actions[bot] | @@ -47,7 +47,7 @@ export class Inputs {
system_message: string
title: string
description: string
- summary: string
+ raw_summary: string
release_notes: string
filename: string
file_content: string | :robot: OpenAI
The `Options` class has a new property `raw_summary` added to it. Please ensure that this property is being used correctly throughout the codebase.
```
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 211 | coderabbitai | github-actions[bot] | @@ -8,8 +8,7 @@ async function run(): Promise<void> {
const options: Options = new Options(
core.getBooleanInput('debug'),
core.getBooleanInput('summary_only'),
- core.getInput('max_files_to_summarize'),
- core.getInput('max_files_to_review'),
+ core.getInput('max_files'),
core.getBooleanInput('review_comment_lgtm'),
core.getMultilineInput('path_filters'), | :robot: OpenAI
The `path_filters` input is not specific enough. It should be either `summarize_path_filters` or `review_path_filters`, depending on the intended use.
```suggestion
core.getMultilineInput('summarize_path_filters'),
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 211 | coderabbitai | github-actions[bot] | @@ -22,6 +22,8 @@ NOTES:
has a
[more conservative data usage policy](https://openai.com/policies/api-data-usage-policies)
compared to their ChatGPT offering.
+- This action is not affiliated with OpenAI.
+- This action is going through rapid iteration, so expect breaking changes.
## Usage
| :robot: OpenAI
No substantive issues were detected in this line range.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 211 | coderabbitai | github-actions[bot] | @@ -24,6 +24,11 @@ export const DESCRIPTION_TAG =
export const DESCRIPTION_TAG_END =
'<!-- end of auto-generated comment: release notes by openai -->'
+export const RAW_SUMMARY_TAG =
+ '<!-- This is an auto-generated comment: raw summary by openai -->'
+export const RAW_SUMMARY_TAG_END =
+ '<!-- end of auto-generated comment: raw summary by openai -->'
+ | :robot: OpenAI
The new constants `RAW_SUMMARY_TAG` and `RAW_SUMMARY_TAG_END` have been added to the code. These constants are used to identify the start and end of the raw summary generated by OpenAI. The `Commenter` class has also been modified to include a new method `getContentWithinTags()`. This method takes in a string, a start tag, and an end tag, and returns the content between the start and end tags. A new method `removeContentWithinTags()` has also been added to remove the content between the start and end tags from a given string.
<!-- This is an auto-generated reply by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 211 | coderabbitai | github-actions[bot] | @@ -61,32 +66,52 @@ ${tag}`
}
}
- get_description(description: string) {
- // remove our summary from description by looking for description_tag and description_tag_end
- const start = description.indexOf(DESCRIPTION_TAG)
- const end = description.indexOf(DESCRIPTION_TAG_END)
+ getContentWithinTags(content: string, startTag: string, endTag: string) {
+ const start = content.indexOf(startTag)
+ const end = content.indexOf(endTag)
if (start >= 0 && end >= 0) {
- return (
- description.slice(0, start) +
- description.slice(end + DESCRIPTION_TAG_END.length)
- )
+ return content.slice(start + startTag.length, end)
}
- return description
+ return ''
}
- get_release_notes(description: string) {
- // get our summary from description by looking for description_tag and description_tag_end
- // and remove any content within that which is in markdown quote (>)
- const start = description.indexOf(DESCRIPTION_TAG)
- const end = description.indexOf(DESCRIPTION_TAG_END)
+ removeContentWithinTags(content: string, startTag: string, endTag: string) {
+ const start = content.indexOf(startTag)
+ const end = content.indexOf(endTag)
if (start >= 0 && end >= 0) {
- const release_notes = description.slice(
- start + DESCRIPTION_TAG.length,
- end
- )
- return release_notes.replace(/(^|\n)> .*/g, '')
+ return content.slice(0, start) + content.slice(end + endTag.length)
}
- return ''
+ return content
+ } | :robot: OpenAI
The `getContentWithinTags()` and `removeContentWithinTags()` methods have been implemented. These methods take in a string, a start tag, and an end tag, and return the content between the start and end tags or remove the content between the start and end tags from the given string.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 211 | coderabbitai | github-actions[bot] | @@ -61,32 +66,52 @@ ${tag}`
}
}
- get_description(description: string) {
- // remove our summary from description by looking for description_tag and description_tag_end
- const start = description.indexOf(DESCRIPTION_TAG)
- const end = description.indexOf(DESCRIPTION_TAG_END)
+ getContentWithinTags(content: string, startTag: string, endTag: string) {
+ const start = content.indexOf(startTag)
+ const end = content.indexOf(endTag)
if (start >= 0 && end >= 0) {
- return (
- description.slice(0, start) +
- description.slice(end + DESCRIPTION_TAG_END.length)
- )
+ return content.slice(start + startTag.length, end)
}
- return description
+ return ''
}
- get_release_notes(description: string) {
- // get our summary from description by looking for description_tag and description_tag_end
- // and remove any content within that which is in markdown quote (>)
- const start = description.indexOf(DESCRIPTION_TAG)
- const end = description.indexOf(DESCRIPTION_TAG_END)
+ removeContentWithinTags(content: string, startTag: string, endTag: string) {
+ const start = content.indexOf(startTag)
+ const end = content.indexOf(endTag)
if (start >= 0 && end >= 0) {
- const release_notes = description.slice(
- start + DESCRIPTION_TAG.length,
- end
- )
- return release_notes.replace(/(^|\n)> .*/g, '')
+ return content.slice(0, start) + content.slice(end + endTag.length)
}
- return ''
+ return content
+ }
+
+ get_raw_summary(summary: string) {
+ const content = this.getContentWithinTags(
+ summary,
+ RAW_SUMMARY_TAG,
+ RAW_SUMMARY_TAG_END
+ )
+ // remove the first and last line
+ const lines = content.split('\n')
+ lines.shift()
+ lines.pop()
+ return lines.join('\n')
+ } | :robot: OpenAI
A new method `get_raw_summary()` has been added to the `Commenter` class. This method takes in a summary string and returns the raw summary generated by OpenAI. It does this by calling the `getContentWithinTags()` method with the `RAW_SUMMARY_TAG` and `RAW_SUMMARY_TAG_END` constants as arguments. It then removes the first and last lines of the returned content.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 211 | coderabbitai | github-actions[bot] | @@ -9,14 +9,11 @@ inputs:
required: false
description: 'Enable debug mode'
default: 'false'
- max_files_to_summarize:
+ max_files:
required: false
description:
- 'Max files to summarize. Less than or equal to 0 means no limit.'
- default: '40'
- max_files_to_review:
- required: false
- description: 'Max files to review. Less than or equal to 0 means no limit.'
+ 'Max files to summarize and review. Less than or equal to 0 means no
+ limit.'
default: '0'
review_comment_lgtm:
required: false | :robot: OpenAI
The `max_files_to_summarize` and `max_files_to_review` options have been replaced with a single `max_files` option. The `review_comment_lgtm` option has been moved to a different location in the file. Please update the documentation accordingly.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 211 | coderabbitai | github-actions[bot] | @@ -109,7 +106,7 @@ inputs:
disregarding minor issues.
summarize_file_diff:
required: false
- description: 'The prompt for file'
+ description: 'The prompt for summarizing a file'
default: | | :robot: OpenAI
The description for the `summarize_file_diff` input is not accurate. Please update the description to reflect that this input is used for prompting the user to summarize a file diff.
```suggestion
summarize_file_diff:
required: false
description: 'The prompt for summarizing a file diff'
default: |
GitHub pull request title:
`$title`
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 211 | coderabbitai | github-actions[bot] | @@ -124,7 +121,7 @@ inputs:
$file_content
```
- Diff:
+ Diff for `$filename`:
```diff
$file_diff
``` | :robot: OpenAI
The format of the diff output has been changed to include the filename before the diff.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 211 | coderabbitai | github-actions[bot] | @@ -134,17 +131,17 @@ inputs:
required: false
description: 'The prompt for final summarization response'
default: |
- Here is the summary of changes you have generated for each file:
+ Here is the summary of changes you have generated for files:
```
- $summary
+ $raw_summary
```
Provide your final response in the `markdown` format with
the following content:
- High-level summary (comment on the overall change instead of
specific files within 80 words)
- Table of files and their summaries. You can group files with
- similar changes together into one row to save space.
+ similar changes together into a single row to save space.
Avoid additional commentary as this summary will be added as a
comment on the GitHub pull request. | :robot: OpenAI
The prompt for the final summarization response has been updated to reflect changes in the summary format. Please update the documentation accordingly.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 211 | coderabbitai | github-actions[bot] | @@ -74,7 +74,7 @@ export class Inputs {
this.system_message = system_message
this.title = title
this.description = description
- this.summary = summary
+ this.raw_summary = summary
this.release_notes = release_notes
this.filename = filename
this.file_content = file_content | :robot: OpenAI
The `Options` class has a new property `raw_summary` added to it. Please ensure that this property is being used correctly throughout the codebase.
```
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 211 | coderabbitai | github-actions[bot] | @@ -90,7 +90,7 @@ export class Inputs {
this.system_message,
this.title,
this.description,
- this.summary,
+ this.raw_summary,
this.release_notes,
this.filename,
this.file_content, | :robot: OpenAI
The `Options` class has a new property `raw_summary` added to it. Please ensure that this property is being used correctly throughout the codebase.
```
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 211 | coderabbitai | github-actions[bot] | @@ -115,8 +115,8 @@ export class Inputs {
if (this.description) {
content = content.replace('$description', this.description)
}
- if (this.summary) {
- content = content.replace('$summary', this.summary)
+ if (this.raw_summary) {
+ content = content.replace('$raw_summary', this.raw_summary)
}
if (this.release_notes) {
content = content.replace('$release_notes', this.release_notes) | :robot: OpenAI
The `Options` class has a new property `raw_summary` added to it. Please ensure that this property is being used correctly throughout the codebase.
```
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 211 | coderabbitai | github-actions[bot] | @@ -186,8 +186,7 @@ export class OpenAIOptions {
export class Options {
debug: boolean
summary_only: boolean
- max_files_to_summarize: number
- max_files_to_review: number
+ max_files: number
review_comment_lgtm: boolean
path_filters: PathFilter
system_message: string | :robot: OpenAI
The `Options` class has two properties renamed: `max_files_to_summarize` to `max_files` and `max_files_to_review` to `review_comment_lgtm`. Please ensure that these properties are being used correctly throughout the codebase.
```
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 211 | coderabbitai | github-actions[bot] | @@ -203,8 +202,7 @@ export class Options {
constructor(
debug: boolean,
summary_only: boolean,
- max_files_to_summarize = '40',
- max_files_to_review = '0',
+ max_files = '0',
review_comment_lgtm = false,
path_filters: string[] | null = null,
system_message = '', | :robot: OpenAI
The `Options` class has two properties renamed: `max_files_to_summarize` to `max_files` and `max_files_to_review` to `review_comment_lgtm`. Please ensure that these properties are being used correctly throughout the codebase.
```
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 211 | coderabbitai | github-actions[bot] | @@ -217,8 +215,7 @@ export class Options {
) {
this.debug = debug
this.summary_only = summary_only
- this.max_files_to_summarize = parseInt(max_files_to_summarize)
- this.max_files_to_review = parseInt(max_files_to_review)
+ this.max_files = parseInt(max_files)
this.review_comment_lgtm = review_comment_lgtm
this.path_filters = new PathFilter(path_filters)
this.system_message = system_message | :robot: OpenAI
The `Options` class has two properties renamed: `max_files_to_summarize` to `max_files` and `max_files_to_review` to `review_comment_lgtm`. Please ensure that these properties are being used correctly throughout the codebase.
```
```
<!-- This is an auto-generated comment by OpenAI --> |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.