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 | 211 | coderabbitai | github-actions[bot] | @@ -236,8 +233,7 @@ export class Options {
print(): void {
core.info(`debug: ${this.debug}`)
core.info(`summary_only: ${this.summary_only}`)
- core.info(`max_files_to_summarize: ${this.max_files_to_summarize}`)
- core.info(`max_files_to_review: ${this.max_files_to_review}`)
+ core.info(`max_files: ${this.max_files}`)
core.info(`review_comment_lgtm: ${this.review_comment_lgtm}`)
core.info(`path_filters: ${this.path_filters}`)
core.info(`system_message: ${this.system_message}`) | :robot: OpenAI
The `print` method of the `Options` class has been updated to use the new `max_files` property instead of the old `max_files_to_summarize` and `max_files_to_review` properties. Please ensure that this change does not cause any issues with the output of the method.
```
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 211 | coderabbitai | github-actions[bot] | @@ -22,6 +22,8 @@ NOTES:
has a
[more conservative data usage policy](https://openai.com/policies/api-data-usage-policies)
compared to their ChatGPT offering.
+- This action is not affiliated with OpenAI. | :robot: OpenAI
The statement "This action is not affiliated with OpenAI" is misleading and could potentially cause confusion for users. Consider removing it or rephrasing it to clarify that the action is built using OpenAI's ChatGPT-based API but is not an official OpenAI product.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 211 | coderabbitai | github-actions[bot] | @@ -109,7 +106,7 @@ inputs:
disregarding minor issues.
summarize_file_diff:
required: false
- description: 'The prompt for file'
+ description: 'The prompt for summarizing a file'
default: |
GitHub pull request title:
`$title` | :robot: OpenAI
The prompt for summarizing a file has been updated to include the pull request title.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 210 | 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'),
core.getInput('system_message'), | :robot: OpenAI
The `max_files_to_summarize` and `max_files_to_review` inputs are missing in the new hunk. Please add them back to the options object.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 210 | 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 is a modified version of the old hunk. The changes are minor and do not require any review.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 210 | 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 | 210 | 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
The new hunk is a modified version of the old hunk. The changes are minor and do not require any review.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 210 | 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 description for `max_files` is not accurate as it now refers to both summarization and review. Please update the description to reflect this change. Also, the `review_comment_lgtm` option has been added without any description. Please add a description for this new option.
```suggestion
max_files:
required: false
description:
'Max files to summarize and review. Less than or equal to 0 means no limit.'
default: '0'
review_comment_lgtm:
required: false
description: 'The comment to be posted when a reviewer approves a file change.'
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 210 | 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: |
GitHub pull request title:
`$title` | :robot: OpenAI
The default value for `summarize_file_diff` has been changed to include the pull request title. Please update the description to reflect this change.
```suggestion
summarize_file_diff:
required: false
description: 'The prompt for summarizing a file diff. Includes the GitHub pull request title.'
default: |
GitHub pull request title:
`$title`
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 210 | coderabbitai | github-actions[bot] | @@ -124,27 +121,39 @@ inputs:
$file_content
```
- Diff:
+ Diff for `$filename`:
```diff
$file_diff
```
I would like you to summarize the diff within 50 words.
+ update_summary:
+ required: false
+ description: 'The prompt to update overall summary with file diff'
+ default: |
+ Summary of changes:
+ ```
+ $raw_summary
+ ```
+
+ Update the summary to group together files with related
+ changes to save space and remove repetition by de-duplicating
+ entries.
summarize:
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 code in this section has been significantly refactored. The `summarize` and `update_summary` options have been added with new descriptions. The `summary` variable has been renamed to `raw_summary`. The `diff` section has been updated to include a filename header. The prompt for summarizing a file diff has been updated to include a filename header and a request to summarize within 50 words. The final summary prompt has been updated to include instructions on how to format the response. Please review these changes carefully and ensure that the new descriptions are accurate and clear.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 210 | coderabbitai | github-actions[bot] | @@ -6,6 +6,8 @@ import {
Commenter,
COMMENT_REPLY_TAG,
EXTRA_CONTENT_TAG,
+ RAW_SUMMARY_TAG,
+ RAW_SUMMARY_TAG_END,
SUMMARIZE_TAG
} from './commenter.js' | :robot: OpenAI
The import statements have changed. Please verify that the correct modules are being imported and used.
```suggestion
import {
Commenter,
COMMENT_REPLY_TAG,
EXTRA_CONTENT_TAG,
RAW_SUMMARY_TAG,
RAW_SUMMARY_TAG_END,
SUMMARIZE_TAG
} from './commenter.js'
import {octokit} from './octokit.js'
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 210 | coderabbitai | github-actions[bot] | @@ -47,6 +49,9 @@ export const codeReview = async (
inputs.description = commenter.get_description(
context.payload.pull_request.body
)
+ inputs.release_notes = commenter.get_release_notes(
+ context.payload.pull_request.body
+ )
} | :robot: OpenAI
`inputs.release_notes` is not being set correctly. Please verify that `get_release_notes()` is returning the expected value.
```
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 210 | coderabbitai | github-actions[bot] | @@ -58,13 +63,50 @@ export const codeReview = async (
// as gpt-3.5-turbo isn't paying attention to system message, add to inputs for now
inputs.system_message = options.system_message
- // collect diff chunks
+ // get SUMMARIZE_TAG message
+ const existing_summarize_cmt = await commenter.find_comment_with_tag(
+ SUMMARIZE_TAG,
+ context.payload.pull_request.number
+ )
+ if (existing_summarize_cmt) {
+ inputs.raw_summary = commenter.get_raw_summary(existing_summarize_cmt.body)
+ } | :robot: OpenAI
`existing_summarize_cmt` is not being checked for null before calling `commenter.get_raw_summary()`. Please add a null check to avoid potential errors.
```
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 210 | coderabbitai | github-actions[bot] | @@ -58,13 +63,50 @@ export const codeReview = async (
// as gpt-3.5-turbo isn't paying attention to system message, add to inputs for now
inputs.system_message = options.system_message
- // collect diff chunks
+ // get SUMMARIZE_TAG message
+ const existing_summarize_cmt = await commenter.find_comment_with_tag(
+ SUMMARIZE_TAG,
+ context.payload.pull_request.number
+ )
+ if (existing_summarize_cmt) {
+ inputs.raw_summary = commenter.get_raw_summary(existing_summarize_cmt.body)
+ }
+ const existing_commit_ids_block = getReviewedCommitIdsBlock(
+ inputs.raw_summary
+ )
+
+ const allCommitIds = await getAllCommitIds()
+ // find highest reviewed commit id
+ let highest_reviewed_commit_id = ''
+ if (existing_commit_ids_block) {
+ highest_reviewed_commit_id = getHighestReviewedCommitId(
+ allCommitIds,
+ getReviewedCommitIds(existing_commit_ids_block)
+ )
+ } | :robot: OpenAI
`getReviewedCommitIdsBlock()` and `getReviewedCommitIds()` are not defined in this file. Please verify that they are being imported correctly or define them if necessary.
```
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 210 | coderabbitai | github-actions[bot] | @@ -58,13 +63,50 @@ export const codeReview = async (
// as gpt-3.5-turbo isn't paying attention to system message, add to inputs for now
inputs.system_message = options.system_message
- // collect diff chunks
+ // get SUMMARIZE_TAG message
+ const existing_summarize_cmt = await commenter.find_comment_with_tag(
+ SUMMARIZE_TAG,
+ context.payload.pull_request.number
+ )
+ if (existing_summarize_cmt) {
+ inputs.raw_summary = commenter.get_raw_summary(existing_summarize_cmt.body)
+ }
+ const existing_commit_ids_block = getReviewedCommitIdsBlock(
+ inputs.raw_summary
+ )
+
+ const allCommitIds = await getAllCommitIds()
+ // find highest reviewed commit id
+ let highest_reviewed_commit_id = ''
+ if (existing_commit_ids_block) {
+ highest_reviewed_commit_id = getHighestReviewedCommitId(
+ allCommitIds,
+ getReviewedCommitIds(existing_commit_ids_block)
+ )
+ }
+
+ if (
+ highest_reviewed_commit_id === '' ||
+ highest_reviewed_commit_id === context.payload.pull_request.head.sha
+ ) {
+ core.info(
+ `Will review from the base commit: ${context.payload.pull_request.base.sha}`
+ )
+ highest_reviewed_commit_id = context.payload.pull_request.base.sha
+ }
+
+ 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({
owner: repo.owner,
repo: repo.repo,
- base: context.payload.pull_request.base.sha,
+ base: highest_reviewed_commit_id,
head: context.payload.pull_request.head.sha
})
+ | :robot: OpenAI
`octokit.repos.compareCommits()` is being called with `base` and `head` parameters. Please verify that these parameters are being set correctly and that the function is being called with the correct arguments.
```
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 210 | coderabbitai | github-actions[bot] | @@ -170,6 +212,7 @@ ${hunks.old_hunk}
}
const summaries_failed: string[] = []
+
const do_summary = async ( | :robot: OpenAI
`summaries_failed` is not being used in this function. Please verify that it is being used correctly or remove it if it is unnecessary.
```
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 210 | coderabbitai | github-actions[bot] | @@ -202,7 +245,7 @@ ${hunks.old_hunk}
if (file_content.length > 0) {
// count occurrences of $file_content in prompt
const file_content_count =
- prompts.summarize_file_diff.split('$file_content').length - 1
+ prompts.update_summary.split('$file_content').length - 1
const file_content_tokens = tokenizer.get_token_count(file_content)
if (
file_content_count > 0 && | :robot: OpenAI
`prompts.update_summary` is being used instead of `prompts.summarize_file_diff`. Please verify that the correct prompt is being used.
```
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 210 | coderabbitai | github-actions[bot] | @@ -235,19 +278,16 @@ ${hunks.old_hunk}
}
const summaryPromises = []
- const skipped_files_to_summarize = []
+ const skipped_files = []
for (const [filename, file_content, file_diff] of files_and_changes) {
- if (
- options.max_files_to_summarize <= 0 ||
- summaryPromises.length < options.max_files_to_summarize
- ) {
+ if (options.max_files <= 0 || summaryPromises.length < options.max_files) {
summaryPromises.push(
openai_concurrency_limit(async () =>
do_summary(filename, file_content, file_diff)
)
)
} else {
- skipped_files_to_summarize.push(filename)
+ skipped_files.push(filename)
}
}
| :robot: OpenAI
`skipped_files_to_summarize` has been renamed to `skipped_files`. Please update all references to this variable accordingly.
```
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 209 | 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 is a copy of the old hunk with minor changes. Consider removing line 5 as it does not add any value to the README.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 209 | 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
Consider adding a disclaimer that this action is not affiliated with OpenAI in the README.
26:
Consider adding a note about the rapid iteration cycle of this action and the possibility of breaking changes in the README.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 209 | 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
Consider rephrasing the FAQ section to make it more clear and concise.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 209 | coderabbitai | github-actions[bot] | @@ -6,6 +6,8 @@ import {
Commenter,
COMMENT_REPLY_TAG,
EXTRA_CONTENT_TAG,
+ RAW_SUMMARY_TAG,
+ RAW_SUMMARY_TAG_END,
SUMMARIZE_TAG
} from './commenter.js' | :robot: OpenAI
The import statements have changed. Please verify that the new imports are correct and that all necessary modules are imported.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 209 | coderabbitai | github-actions[bot] | @@ -58,13 +63,50 @@ export const codeReview = async (
// as gpt-3.5-turbo isn't paying attention to system message, add to inputs for now
inputs.system_message = options.system_message
- // collect diff chunks
+ // get SUMMARIZE_TAG message
+ const existing_summarize_cmt = await commenter.find_comment_with_tag(
+ SUMMARIZE_TAG,
+ context.payload.pull_request.number
+ )
+ if (existing_summarize_cmt) { | :robot: OpenAI
Please verify that the `find_comment_with_tag` function is working as expected and that it returns the correct comment.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 209 | coderabbitai | github-actions[bot] | @@ -58,13 +63,50 @@ export const codeReview = async (
// as gpt-3.5-turbo isn't paying attention to system message, add to inputs for now
inputs.system_message = options.system_message
- // collect diff chunks
+ // get SUMMARIZE_TAG message
+ const existing_summarize_cmt = await commenter.find_comment_with_tag(
+ SUMMARIZE_TAG,
+ context.payload.pull_request.number
+ )
+ if (existing_summarize_cmt) {
+ inputs.raw_summary = commenter.get_raw_summary(existing_summarize_cmt.body)
+ } | :robot: OpenAI
Please verify that the `get_raw_summary` function is working as expected and that it returns the correct summary.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 209 | coderabbitai | github-actions[bot] | @@ -58,13 +63,50 @@ export const codeReview = async (
// as gpt-3.5-turbo isn't paying attention to system message, add to inputs for now
inputs.system_message = options.system_message
- // collect diff chunks
+ // get SUMMARIZE_TAG message
+ const existing_summarize_cmt = await commenter.find_comment_with_tag(
+ SUMMARIZE_TAG,
+ context.payload.pull_request.number
+ )
+ if (existing_summarize_cmt) {
+ inputs.raw_summary = commenter.get_raw_summary(existing_summarize_cmt.body)
+ }
+ const existing_commit_ids_block = getReviewedCommitIdsBlock(
+ inputs.raw_summary
+ )
+
+ const allCommitIds = await getAllCommitIds()
+ // find highest reviewed commit id
+ let highest_reviewed_commit_id = ''
+ if (existing_commit_ids_block) {
+ highest_reviewed_commit_id = getHighestReviewedCommitId(
+ allCommitIds,
+ getReviewedCommitIds(existing_commit_ids_block)
+ )
+ } | :robot: OpenAI
Please verify that the `getReviewedCommitIdsBlock`, `getAllCommitIds`, and `getHighestReviewedCommitId` functions are working as expected and that they return the correct values.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 209 | coderabbitai | github-actions[bot] | @@ -58,13 +63,50 @@ export const codeReview = async (
// as gpt-3.5-turbo isn't paying attention to system message, add to inputs for now
inputs.system_message = options.system_message
- // collect diff chunks
+ // get SUMMARIZE_TAG message
+ const existing_summarize_cmt = await commenter.find_comment_with_tag(
+ SUMMARIZE_TAG,
+ context.payload.pull_request.number
+ )
+ if (existing_summarize_cmt) {
+ inputs.raw_summary = commenter.get_raw_summary(existing_summarize_cmt.body)
+ }
+ const existing_commit_ids_block = getReviewedCommitIdsBlock(
+ inputs.raw_summary
+ )
+
+ const allCommitIds = await getAllCommitIds()
+ // find highest reviewed commit id
+ let highest_reviewed_commit_id = ''
+ if (existing_commit_ids_block) {
+ highest_reviewed_commit_id = getHighestReviewedCommitId(
+ allCommitIds,
+ getReviewedCommitIds(existing_commit_ids_block)
+ )
+ }
+
+ if (
+ highest_reviewed_commit_id === '' ||
+ highest_reviewed_commit_id === context.payload.pull_request.head.sha
+ ) {
+ core.info(
+ `Will review from the base commit: ${context.payload.pull_request.base.sha}`
+ )
+ highest_reviewed_commit_id = context.payload.pull_request.base.sha
+ }
+
+ 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({
owner: repo.owner,
repo: repo.repo,
- base: context.payload.pull_request.base.sha,
+ base: highest_reviewed_commit_id,
head: context.payload.pull_request.head.sha
})
+
const {files, commits} = diff.data
if (!files) {
core.warning(`Skipped: diff.data.files is null`) | :robot: OpenAI
Please verify that the `repos.compareCommits` function is working as expected and that it returns the correct diff data.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 209 | coderabbitai | github-actions[bot] | @@ -170,29 +212,28 @@ ${hunks.old_hunk}
}
const summaries_failed: string[] = []
- const do_summary = async (
+
+ const update_summary = async (
filename: string,
file_content: string,
file_diff: string
- ): Promise<[string, string] | null> => {
+ ): Promise<string> => {
const ins = inputs.clone()
if (file_diff.length === 0) {
core.warning(`summarize: file_diff is empty, skip ${filename}`)
summaries_failed.push(`${filename} (empty diff)`)
- return null
+ return ''
}
ins.filename = filename
// render prompt based on inputs so far
- let tokens = tokenizer.get_token_count(
- prompts.render_summarize_file_diff(ins)
- )
+ let tokens = tokenizer.get_token_count(prompts.render_update_summary(ins))
const diff_tokens = tokenizer.get_token_count(file_diff)
if (tokens + diff_tokens > options.light_token_limits.request_tokens) {
core.info(`summarize: diff tokens exceeds limit, skip ${filename}`)
summaries_failed.push(`${filename} (diff tokens exceeds limit)`)
- return null
+ return ''
}
ins.file_diff = file_diff | :robot: OpenAI
Please verify that the `update_summary` function is working as expected and that it updates the summary correctly.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 209 | 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'),
core.getInput('system_message'), | :robot: OpenAI
The `max_files_to_summarize` and `max_files_to_review` inputs have been combined into a single `max_files` input. Please update the code to use `core.getInput('max_files')` instead of `core.getInput('max_files_to_summarize')` and `core.getInput('max_files_to_review')`.
Additionally, the `update_summary` input is no longer used and has been removed. Please remove `core.getInput('update_summary')` from the code.
Finally, please update the descriptions for the `max_files` and `summary_only` inputs to better reflect their purpose.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 208 | 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 is missing some content from the old hunk. Specifically, the image of the AI logo is missing. Please ensure that all relevant content from the old hunk is included in the new hunk.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 208 | 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 the data usage policy is broken. Please update the link to point to the correct URL.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 208 | 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 would be helpful to provide more information about what kind of breaking changes users can expect and how they can prepare for them. Consider adding a brief note about this.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 208 | 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
The comment chain in the old hunk provided more context about why `pull_request_target` event should be used instead of `pull_request`. Consider including this context in the new hunk as well.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 208 | 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'),
core.getInput('system_message'), | :robot: OpenAI
The `Options` constructor has changed. Please update the following inputs:
- `max_files_to_summarize` (line 11) should be changed to `max_files` (line 11).
- `max_files_to_review` (line 12) has been removed and is no longer needed.
```suggestion
const options: Options = new Options(
core.getBooleanInput('debug'),
core.getBooleanInput('summary_only'),
core.getInput('max_files'),
core.getBooleanInput('review_comment_lgtm'),
core.getMultilineInput('path_filters'),
core.getInput('system_message'),
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 208 | coderabbitai | github-actions[bot] | @@ -26,7 +25,7 @@ async function run(): Promise<void> {
const prompts: Prompts = new Prompts(
core.getInput('review_file_diff'),
- core.getInput('summarize_file_diff'),
+ core.getInput('update_summary'), | :robot: OpenAI
The `Prompts` constructor has changed. Please update the following input:
- `summarize_file_diff` (line 28) should be changed to `update_summary` (line 28).
```suggestion
const prompts: Prompts = new Prompts(
core.getInput('review_file_diff'),
core.getInput('update_summary'),
core.getInput('summarize'),
core.getInput('summarize_release_notes'),
core.getInput('comment')
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 207 | 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'),
core.getInput('system_message'), | :robot: OpenAI
The `max_files_to_summarize` and `max_files_to_review` options are missing in the new code. Please add them back to the `Options` constructor.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 207 | 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 | :robot: OpenAI
`max_files_to_summarize` and `max_files_to_review` have been combined into a single `max_files` property. Please update the code accordingly.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 207 | 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 `max_files` property is now a number instead of a string. Please update the code to parse it as a number.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 207 | 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 `max_files_to_summarize` and `max_files_to_review` properties have been combined into a single `max_files` property. Please update the code accordingly.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 207 | coderabbitai | github-actions[bot] | @@ -236,8 +233,7 @@ export class Options {
print(): void {
core.info(`debug: ${this.debug}`)
core.info(`summary_only: ${this.summary_only}`)
- core.info(`max_files_to_summarize: ${this.max_files_to_summarize}`)
- core.info(`max_files_to_review: ${this.max_files_to_review}`)
+ core.info(`max_files: ${this.max_files}`)
core.info(`review_comment_lgtm: ${this.review_comment_lgtm}`)
core.info(`path_filters: ${this.path_filters}`)
core.info(`system_message: ${this.system_message}`) | :robot: OpenAI
The `max_files_to_summarize` and `max_files_to_review` properties have been combined into a single `max_files` property. Please update the code accordingly.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 207 | 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 is missing some important information that was present in the old hunk. Specifically, the old hunk mentioned that this GitHub action uses OpenAI's ChatGPT offering, which is not mentioned in the new hunk. It would be helpful to include this information in the new hunk for clarity.
```suggestion
# OpenAI ChatGPT-based PR reviewer and summarizer
## Overview
This [OpenAI ChatGPT-based](https://platform.openai.com/docs/guides/chat) GitHub Action provides a summary, release notes and review of pull requests using OpenAI's ChatGPT offering. The prompts have been tuned for a concise response. To prevent excessive notifications, this action can be configured to skip adding review comments when
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 207 | 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 new hunk mentions that OpenAI has a more conservative data usage policy compared to their ChatGPT offering, but it doesn't explain what that means or why it's relevant. It would be helpful to provide more context or remove this sentence altogether.
```suggestion
# OpenAI ChatGPT-based PR reviewer and summarizer
## Overview
This [OpenAI ChatGPT-based](https://platform.openai.com/docs/guides/chat) GitHub Action provides a summary, release notes and review of pull requests using OpenAI's ChatGPT offering. The prompts have been tuned for a concise response. To prevent excessive notifications, this action can be configured to skip adding review comments when.
## Usage
```
26:
The new hunk mentions that this action is going through rapid iteration and may have breaking changes, but it doesn't provide any guidance on how users should handle these changes. It would be helpful to provide some guidance or remove this sentence altogether.
```suggestion
# OpenAI ChatGPT-based PR reviewer and summarizer
## Overview
This [OpenAI ChatGPT-based](https://platform.openai.com/docs/guides/chat) GitHub Action provides a summary, release notes and review of pull requests using OpenAI's ChatGPT offering. The prompts have been tuned for a concise response. To prevent excessive notifications, this action can be configured to skip adding review comments when.
## Usage
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 207 | 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
The new hunk mentions that GitHub Actions limits the access of secrets from forked repositories and provides guidance on how to enable this feature, but it doesn't explain why this is relevant or what users should do if they encounter this issue. It would be helpful to provide more context or remove this section altogether.
```suggestion
## FAQs
### 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
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 207 | coderabbitai | github-actions[bot] | @@ -6,6 +6,8 @@ import {
Commenter,
COMMENT_REPLY_TAG,
EXTRA_CONTENT_TAG,
+ RAW_SUMMARY_TAG,
+ RAW_SUMMARY_TAG_END,
SUMMARIZE_TAG
} from './commenter.js'
import {octokit} from './octokit.js' | :robot: OpenAI
The import statements have changed. Please verify that the new imports are correct and that all necessary modules are imported.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 207 | coderabbitai | github-actions[bot] | @@ -47,6 +49,9 @@ export const codeReview = async (
inputs.description = commenter.get_description(
context.payload.pull_request.body
)
+ inputs.release_notes = commenter.get_release_notes(
+ context.payload.pull_request.body
+ )
} | :robot: OpenAI
The `if` statement on line 49 is missing a closing brace. Please add a closing brace to the end of the block.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 207 | coderabbitai | github-actions[bot] | @@ -58,13 +63,50 @@ export const codeReview = async (
// as gpt-3.5-turbo isn't paying attention to system message, add to inputs for now
inputs.system_message = options.system_message
- // collect diff chunks
+ // get SUMMARIZE_TAG message
+ const existing_summarize_cmt = await commenter.find_comment_with_tag(
+ SUMMARIZE_TAG,
+ context.payload.pull_request.number
+ )
+ if (existing_summarize_cmt) { | :robot: OpenAI
The `await` statement on line 67 may throw an error if the comment with the tag `SUMMARIZE_TAG` cannot be found. Please add error handling for this case.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 207 | coderabbitai | github-actions[bot] | @@ -170,29 +212,28 @@ ${hunks.old_hunk}
}
const summaries_failed: string[] = []
- const do_summary = async (
+
+ const update_summary = async (
filename: string,
file_content: string,
file_diff: string
- ): Promise<[string, string] | null> => {
+ ): Promise<string> => {
const ins = inputs.clone()
if (file_diff.length === 0) {
core.warning(`summarize: file_diff is empty, skip ${filename}`)
summaries_failed.push(`${filename} (empty diff)`)
- return null
+ return ''
}
ins.filename = filename
// render prompt based on inputs so far
- let tokens = tokenizer.get_token_count(
- prompts.render_summarize_file_diff(ins)
- )
+ let tokens = tokenizer.get_token_count(prompts.render_update_summary(ins))
const diff_tokens = tokenizer.get_token_count(file_diff)
if (tokens + diff_tokens > options.light_token_limits.request_tokens) {
core.info(`summarize: diff tokens exceeds limit, skip ${filename}`)
summaries_failed.push(`${filename} (diff tokens exceeds limit)`)
- return null
+ return ''
}
ins.file_diff = file_diff | :robot: OpenAI
The function `do_summary` has been renamed to `update_summary`. The input validation has been moved to the beginning of the function. Please verify that the input validation is correct and that all necessary inputs are being validated.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 207 | coderabbitai | github-actions[bot] | @@ -202,7 +243,7 @@ ${hunks.old_hunk}
if (file_content.length > 0) {
// count occurrences of $file_content in prompt
const file_content_count =
- prompts.summarize_file_diff.split('$file_content').length - 1
+ prompts.update_summary.split('$file_content').length - 1
const file_content_tokens = tokenizer.get_token_count(file_content)
if (
file_content_count > 0 && | :robot: OpenAI
The variable names in lines 245-247 do not match the variable names in the previous implementation. Please verify that the variable names are correct and that the logic is still valid.
```suggestion
import {
Commenter,
COMMENT_REPLY_TAG,
EXTRA_CONTENT_TAG,
RAW_SUMMARY_TAG,
RAW_SUMMARY_TAG_END,
SUMMARIZE_TAG
} from './commenter.js'
```
```suggestion
const update_summary = async (
filename: string,
file_content: string,
file_diff: string
): Promise<string> => {
const ins = inputs.clone()
if (!filename) {
throw new Error('Filename is required')
}
if (!file_content) {
throw new Error('File content is required')
}
if (!file_diff) {
throw new Error('File diff is required')
}
if (file_diff.length === 0) {
core.warning(`summarize: file_diff is empty, skip ${filename}`)
summaries_failed.push(`${filename} (empty diff)`)
return ''
}
ins.filename = filename
// render prompt based on inputs so far
let tokens = tokenizer.get_token_count(prompts.render_update_summary(ins))
const diff_tokens = tokenizer.get_token_count(file_diff)
if (tokens + diff_tokens > options.light_token_limits.request_tokens) {
core.info(`summarize: diff tokens exceeds limit, skip ${filename}`)
summaries_failed.push(`${filename} (diff tokens exceeds limit)`)
return ''
}
ins.file_diff = file_diff
}
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 204 | 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 is a copy of the old hunk with minor changes. Consider removing line 5 as it does not add any value to the README.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 204 | 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
Consider adding a disclaimer that this action is not affiliated with OpenAI in the README.
26:
Consider adding a note about the breaking changes in the README.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 204 | 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
Consider rephrasing the FAQ section to make it more clear and concise.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 204 | 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'),
core.getInput('system_message'), | :robot: OpenAI
The `max_files_to_summarize` and `max_files_to_review` inputs have been consolidated into a single `max_files` input. Please update the code to use the new input.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 204 | coderabbitai | github-actions[bot] | @@ -26,7 +25,7 @@ async function run(): Promise<void> {
const prompts: Prompts = new Prompts(
core.getInput('review_file_diff'),
- core.getInput('summarize_file_diff'),
+ core.getInput('update_summary'), | :robot: OpenAI
The `summarize_file_diff` input has been renamed to `update_summary` for clarity. Please update the code to use the new input.
---new_hunk---
```
33: let lightBot: Bot | null = null
34: try {
35: lightBot = new Bot(
36: options,
37: new OpenAIOptions(options.openai_light_model, options.light_token_limits)
38: )
39: } catch (e: any) {
40: core.warning(
41: `Skipped: failed to create summary bot, please check your openai_api_key: ${e}, backtrace: ${e.stack}`
42: )
43: return
44: }
```
---old_hunk---
```
let lightBot: Bot | null = null
try {
lightBot = new Bot(
options,
new OpenAIOptions(options.openai_light_model, options.light_token_limits)
)
} catch (e: any) {
core.warning(
`Skipped: failed to create summary bot, please check your openai_api_key: ${e}, backtrace: ${e.stack}`
)
return
}
```
---end_change_section---
---new_hunk---
```
47: let heavyBot: Bot | null = null
48: try {
49: heavyBot = new Bot(
50: options,
51: new OpenAIOptions(options.openai_heavy_model, options.heavy_token_limits)
52: )
53: } catch (e: any) {
54: core.warning(
55: `Skipped: failed to create review bot, please check your openai_api_key: ${e}, backtrace: ${e.stack}`
56: )
57: return
58: }
```
---old_hunk---
```
let heavyBot: Bot | null = null
try {
heavyBot = new Bot(
options,
new OpenAIOptions(options.openai_heavy_model, options.heavy_token_limits)
)
} catch (e: any) {
core.warning(
`Skipped: failed to create review bot, please check your openai_api_key: ${e}, backtrace: ${e.stack}`
)
return
}
```
---end_change_section---
---new_hunk---
```
61: if (
62: process.env.GITHUB_EVENT_NAME === 'pull_request' ||
63: process.env.GITHUB_EVENT_NAME === 'pull_request_target'
64: ) {
65: await codeReview(lightBot, heavyBot, options, prompts)
66: } else if (
67: process.env.GITHUB_EVENT_NAME === 'pull_request_review_comment'
68: ) {
69: await handleReviewComment(heavyBot, options, prompts)
70: } else {
71: core.warning(
72: 'Skipped: this action only works on push events or pull_request'
73: )
74: }
```
---old_hunk---
```
if (
process.env.GITHUB_EVENT_NAME === 'pull_request' ||
process.env.GITHUB_EVENT_NAME === 'pull_request_target'
) {
await codeReview(lightBot, heavyBot, options, prompts)
} else if (
process.env.GITHUB_EVENT_NAME === 'pull_request_review_comment'
) {
await handleReviewComment(heavyBot, options, prompts)
} else {
core.warning(
'Skipped: this action only works on push events or pull_request'
)
}
```
---end_change_section---
---new_hunk---
```
76: process
77: .on('unhandledRejection', (reason, p) => {
78: core.warning(`Unhandled Rejection at Promise: ${reason}, promise is ${p}`)
79: })
80: .on('uncaughtException', (e: any) => {
81: core.warning(`Uncaught Exception thrown: ${e}, backtrace: ${e.stack}`)
82: })
```
---old_hunk---
```
process
.on('unhandledRejection', (reason, p) => {
core.warning(`Unhandled Rejection at Promise: ${reason}, promise is ${p}`)
})
.on('uncaughtException', (e: any) => {
core.warning(`Uncaught Exception thrown: ${e}, backtrace: ${e.stack}`)
})
```
---end
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 203 | coderabbitai | github-actions[bot] | @@ -177,17 +177,16 @@ inputs:
$description
```
- OpenAI generated summary of overall changes:
+ OpenAI generated notes:
```
- $summary
+ $release_notes
```
- Content of `$filename` prior to changes for context:
+ Content of `$filename` prior to changes:
```
$file_content
```
- Changes for review:
$patches
comment:
required: false | :robot: OpenAI
The new hunk seems to be a copy of the old hunk with some variable names changed. No substantive issues detected.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 203 | coderabbitai | github-actions[bot] | @@ -205,9 +204,9 @@ inputs:
$description
```
- OpenAI generated summary:
+ OpenAI generated notes:
```
- $summary
+ $release_notes
```
Content of file prior to changes: | :robot: OpenAI
The new hunk seems to be a copy of the old hunk with some variable names changed. No substantive issues detected.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 203 | coderabbitai | github-actions[bot] | @@ -48,6 +48,7 @@ export class Inputs {
title: string
description: string
summary: string
+ release_notes: string
filename: string
file_content: string
file_diff: string | :robot: OpenAI
The addition of `release_notes` to the options object is a good improvement. However, it's not clear what `file_diff` is supposed to represent. Please provide more context or documentation on this field.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 203 | coderabbitai | github-actions[bot] | @@ -285,6 +285,7 @@ ${filename}: ${summary}
core.info('release notes: nothing obtained from openai')
} else {
next_summarize_ids = release_notes_ids
+ inputs.release_notes = release_notes_response.replace(/(^|\n)> .*/g, '') | :robot: OpenAI
The `release_notes_response` variable is being modified to remove lines starting with `>`. This could potentially remove important information from the release notes. Instead of modifying the variable, consider using a regular expression to match only the lines that do not start with `>` and assign those lines to `inputs.release_notes`.
```suggestion
let non_quoted_lines = release_notes_response.match(/^[^>].*/gm)
inputs.release_notes = non_quoted_lines.join('\n')
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 201 | coderabbitai | github-actions[bot] | @@ -412,7 +412,8 @@ Important instructions:
<end_line_number>. The line number range is sufficient to map your
comment to the code changes in GitHub pull request.
- Consider the context provided by the old hunk and associated comment
- chain when reviewing the new hunk.
+ chain when reviewing the new hunk. Do not summarize the changes in the
+ review comment and only focus on pointing out substantive issues.
- Use Markdown format for review comment text.
- Fenced code blocks must be used for new content and replacement
code/text snippets and must not be annotated with line numbers. | :robot: OpenAI
The instructions for code review are clear and concise. No issues detected.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 201 | coderabbitai | github-actions[bot] | @@ -432,9 +433,9 @@ Important instructions:
fenced code blocks. These snippets may be added to a different file, such
as test cases. Multiple new code snippets are allowed within a single
review section. | :robot: OpenAI
The instructions for adding new code snippets are clear. No issues detected.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 201 | coderabbitai | github-actions[bot] | @@ -432,9 +433,9 @@ Important instructions:
fenced code blocks. These snippets may be added to a different file, such
as test cases. Multiple new code snippets are allowed within a single
review section.
-- If there are no substantive issues detected at a line range, simply
- comment "LGTM!" for the respective line range in a review section and
- avoid additional commentary/compliments.
+- If there are no substantive issues detected at a line range and/or the
+ implementation looks good, simply comment "LGTM!" for the respective line
+ range in a review section and avoid additional commentary/compliments.
- Reflect on your comments and line number ranges before sending the final
response to ensure accuracy of line number ranges and replacement
snippets. | :robot: OpenAI
The instruction to reflect on comments and line number ranges before sending the final response is important. No issues detected.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 201 | coderabbitai | github-actions[bot] | @@ -102,10 +102,11 @@ inputs:
- Complexity
- Optimization
| :robot: OpenAI
The bullet points in the list should be aligned with each other.
```suggestion
- Complexity
- Optimization
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 201 | coderabbitai | github-actions[bot] | @@ -102,10 +102,11 @@ inputs:
- Complexity
- Optimization
- Refrain from addressing minor code style issues, compliments, or missing
- comments/documentation, unless explicitly requested. Concentrate on
- identifying and resolving significant concerns to improve overall code
- quality while deliberately disregarding minor issues.
+ Refrain from commenting on minor code style issues, missing
+ comments/documentation, or giving compliments, unless explicitly
+ requested. Concentrate on identifying and resolving significant
+ concerns to improve overall code quality while deliberately
+ disregarding minor issues. | :robot: OpenAI
The indentation of the text is incorrect. Please fix it.
```suggestion
Refrain from commenting on minor code style issues, missing
comments/documentation, or giving compliments, unless explicitly
requested. Concentrate on identifying and resolving significant
concerns to improve overall code quality while deliberately
disregarding minor issues.
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 200 | coderabbitai | github-actions[bot] | @@ -184,29 +184,22 @@ ${COMMENT_TAG}`
core.info(
`Creating new review comment for ${comment.path}:${comment.start_line}-${comment.end_line}: ${comment.message}`
)
+ const commentData: any = {
+ owner: repo.owner,
+ repo: repo.repo,
+ pull_number,
+ commit_id,
+ body: comment.message,
+ path: comment.path,
+ line: comment.end_line
+ } | :robot: OpenAI
The code is creating an object `commentData` to hold the data for the review comment. It would be better to define a type/interface for this object instead of using `any`.
```suggestion
interface CommentData {
owner: string;
repo: string;
pull_number: number;
commit_id: string;
body: string;
path: string;
line: number;
start_side?: 'LEFT' | 'RIGHT';
start_line?: number;
}
```
Also, it would be better to use the defined type/interface instead of `any`.
```suggestion
const commentData: CommentData = {
owner: repo.owner,
repo: repo.repo,
pull_number,
commit_id,
body: comment.message,
path: comment.path,
line: comment.end_line
}
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 200 | coderabbitai | github-actions[bot] | @@ -184,29 +184,22 @@ ${COMMENT_TAG}`
core.info(
`Creating new review comment for ${comment.path}:${comment.start_line}-${comment.end_line}: ${comment.message}`
)
+ const commentData: any = {
+ owner: repo.owner,
+ repo: repo.repo,
+ pull_number,
+ commit_id,
+ body: comment.message,
+ path: comment.path,
+ line: comment.end_line
+ }
+
if (comment.start_line !== comment.end_line) {
- await octokit.pulls.createReviewComment({
- owner: repo.owner,
- repo: repo.repo,
- pull_number,
- commit_id,
- body: comment.message,
- path: comment.path,
- line: comment.end_line,
- start_side: 'RIGHT',
- start_line: comment.start_line
- })
- } else {
- await octokit.pulls.createReviewComment({
- owner: repo.owner,
- repo: repo.repo,
- pull_number,
- commit_id,
- body: comment.message,
- path: comment.path,
- line: comment.end_line
- })
+ commentData.start_side = 'RIGHT'
+ commentData.start_line = comment.start_line
} | :robot: OpenAI
The code checks if `start_line` is not equal to `end_line` before setting `start_side` and `start_line` properties in `commentData`. However, it should also check if `start_line` is less than or equal to `end_line` to ensure that `start_line` is not greater than `end_line`.
```suggestion
if (comment.start_line !== comment.end_line && comment.start_line <= comment.end_line) {
commentData.start_side = 'RIGHT'
commentData.start_line = comment.start_line
}
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 195 | coderabbitai | github-actions[bot] | @@ -1926,6 +1927,21 @@
"@octokit/openapi-types": "^12.11.0"
}
},
+ "node_modules/@octokit/plugin-retry": {
+ "version": "4.1.3",
+ "resolved": "https://registry.npmjs.org/@octokit/plugin-retry/-/plugin-retry-4.1.3.tgz",
+ "integrity": "sha512-3YKBj7d0J/4mpEc4xzMociWsMNl5lZqrpAnYcW6mqiSGF3wFjU+c6GHih6GLClk31JNvKDr0x9jc5cfm7evkZg==",
+ "dependencies": {
+ "@octokit/types": "^9.0.0",
+ "bottleneck": "^2.15.3"
+ },
+ "engines": {
+ "node": ">= 14"
+ },
+ "peerDependencies": {
+ "@octokit/core": ">=3"
+ } | :robot: OpenAI
The addition of "@octokit/plugin-retry" package and its dependencies looks good. No issues found.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | others | 195 | coderabbitai | github-actions[bot] | @@ -1926,6 +1927,21 @@
"@octokit/openapi-types": "^12.11.0"
}
},
+ "node_modules/@octokit/plugin-retry": {
+ "version": "4.1.3",
+ "resolved": "https://registry.npmjs.org/@octokit/plugin-retry/-/plugin-retry-4.1.3.tgz",
+ "integrity": "sha512-3YKBj7d0J/4mpEc4xzMociWsMNl5lZqrpAnYcW6mqiSGF3wFjU+c6GHih6GLClk31JNvKDr0x9jc5cfm7evkZg==",
+ "dependencies": {
+ "@octokit/types": "^9.0.0",
+ "bottleneck": "^2.15.3"
+ },
+ "engines": {
+ "node": ">= 14"
+ },
+ "peerDependencies": {
+ "@octokit/core": ">=3"
+ }
+ },
"node_modules/@octokit/plugin-throttling": {
"version": "5.0.1",
"resolved": "https://registry.npmjs.org/@octokit/plugin-throttling/-/plugin-throttling-5.0.1.tgz", | :robot: OpenAI
> Note: This review was outside of the patch, so it was mapped to the patch with the greatest overlap. Original lines [1945-1958]
The addition of "@octokit/plugin-throttling" package and its dependencies looks good. No issues found.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 194 | coderabbitai | github-actions[bot] | @@ -372,7 +372,7 @@ ${
Format for changes:
---new_hunk---
\`\`\`
- <new hunk annotated with line numbers>
+ <line number annotated new hunk>
\`\`\`
---old_hunk--- | :robot: OpenAI
The format for changes section is missing the instructions on how to provide review comments. Please add instructions on how to provide substantive review comments.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 194 | coderabbitai | github-actions[bot] | @@ -415,7 +415,7 @@ Important instructions:
chain when reviewing the new hunk.
- Use Markdown format for review comment text.
- Fenced code blocks must be used for new content and replacement
- code/text snippets.
+ code/text snippets and must not be annotated with line numbers.
- If needed, provide a replacement suggestion using fenced code blocks
with the \`suggestion\` as the language identifier. The line number range
in the review section must map exactly to the line number range (inclusive) | :robot: OpenAI
The instructions mention that fenced code blocks must not be annotated with line numbers. However, in some cases, it may be necessary to annotate specific lines within a fenced code block. Please clarify when it is appropriate to annotate lines within a fenced code block.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 194 | coderabbitai | github-actions[bot] | @@ -432,7 +432,6 @@ Important instructions:
fenced code blocks. These snippets may be added to a different file, such
as test cases. Multiple new code snippets are allowed within a single
review section.
-- Do not annotate code snippets with line numbers inside the code blocks.
- If there are no substantive issues detected at a line range, simply
comment "LGTM!" for the respective line range in a review section and
avoid additional commentary/compliments. | :robot: OpenAI
These instructions are clear and require no further action.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 194 | coderabbitai | github-actions[bot] | @@ -587,7 +586,7 @@ ${comment_chain}
return
}
// parse review
- const reviews = parseReview(response, options.debug)
+ const reviews = parseReview(response, patches, options.debug)
for (const review of reviews) { | :robot: OpenAI
The `parseReview` function has been updated to map reviews to the closest patch and store them in an array. However, the `patches` parameter is not being used in this function call. Please update the function call to include the `patches` parameter.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 194 | coderabbitai | github-actions[bot] | @@ -602,37 +601,6 @@ ${comment_chain}
continue
}
- // sanitize review's start_line and end_line
- // with patches' start_line and end_line
- // if needed adjust start_line and end_line
- // to make it fit within a closest patch
- let within_patch = false
- let closest_start_line = patches[0][0]
- let closest_end_line = patches[0][1]
- for (const [start_line, end_line] of patches) {
- // see if review is within some patch
- if (review.start_line >= start_line) {
- closest_start_line = start_line
- closest_end_line = end_line
- if (
- review.end_line <= end_line &&
- review.end_line >= start_line
- ) {
- within_patch = true
- break
- }
- }
- }
-
- if (!within_patch) {
- // map the review to the closest patch
- review.comment = `> Note: This review was outside of the patch, so it was mapped it to the closest patch. Original lines [${review.start_line}-${review.end_line}]
-
-${review.comment}`
- review.start_line = closest_start_line
- review.end_line = closest_end_line
- }
-
try {
await commenter.buffer_review_comment(
filename, | :robot: OpenAI
This code block is missing the logic to adjust the start_line and end_line of the review to fit within the closest patch. Please add the logic to adjust the start_line and end_line of the review to fit within the closest patch before calling `commenter.buffer_review_comment()`.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 188 | coderabbitai | github-actions[bot] | @@ -610,9 +610,7 @@ ${comment_chain}
continue
}
try {
- await commenter.review_comment(
- context.payload.pull_request.number,
- commits[commits.length - 1].sha,
+ await commenter.buffer_review_comment(
filename,
review.start_line,
review.end_line, | :robot: OpenAI
The new code introduces a try-catch block that wraps the call to `commenter.buffer_review_comment()`. However, there is no error handling in the catch block. Please add appropriate error handling code to the catch block to handle any errors that may occur during the call to `commenter.buffer_review_comment()`.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 188 | coderabbitai | github-actions[bot] | @@ -609,10 +609,34 @@ ${comment_chain}
core.warning('No pull request found, skipping.')
continue
} | :robot: OpenAI
The code should throw an error if no pull request is found instead of skipping it silently. This can lead to confusion and unexpected behavior for users.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 188 | coderabbitai | github-actions[bot] | @@ -609,10 +609,34 @@ ${comment_chain}
core.warning('No pull request found, skipping.')
continue
}
+ // sanitize review's start_line and end_line
+ // with patches' start_line and end_line
+ // if needed adjust start_line and end_line
+ // to make it fit within a closest patch
+ let within_patch = false
+ let closest_start_line = patches[0][0]
+ let closest_end_line = patches[0][1]
+ for (const [start_line, end_line] of patches) {
+ // see if review is within some patch
+ if (review.start_line >= start_line) {
+ closest_start_line = start_line
+ closest_end_line = end_line
+ if (review.end_line <= end_line) {
+ within_patch = true
+ break
+ }
+ }
+ }
+ if (!within_patch) {
+ // map the review to the closest patch
+ review.comment = `> Note: This review was outside of the patch, so it was mapped it to the closest patch. Original lines [${review.start_line}-${review.end_line}]
+${review.comment}`
+ review.start_line = closest_start_line
+ review.end_line = closest_end_line
+ } | :robot: OpenAI
The logic for mapping the review to the closest patch seems correct, but it could be improved by using binary search instead of iterating over all patches. This would make the algorithm more efficient, especially for large diffs with many patches.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 188 | coderabbitai | github-actions[bot] | @@ -609,10 +609,34 @@ ${comment_chain}
core.warning('No pull request found, skipping.')
continue
}
+ // sanitize review's start_line and end_line
+ // with patches' start_line and end_line
+ // if needed adjust start_line and end_line
+ // to make it fit within a closest patch
+ let within_patch = false
+ let closest_start_line = patches[0][0]
+ let closest_end_line = patches[0][1]
+ for (const [start_line, end_line] of patches) {
+ // see if review is within some patch
+ if (review.start_line >= start_line) {
+ closest_start_line = start_line
+ closest_end_line = end_line
+ if (review.end_line <= end_line) {
+ within_patch = true
+ break
+ }
+ }
+ }
+ if (!within_patch) {
+ // map the review to the closest patch
+ review.comment = `> Note: This review was outside of the patch, so it was mapped it to the closest patch. Original lines [${review.start_line}-${review.end_line}]
+${review.comment}`
+ review.start_line = closest_start_line
+ review.end_line = closest_end_line
+ }
+
try {
- await commenter.review_comment(
- context.payload.pull_request.number,
- commits[commits.length - 1].sha,
+ await commenter.buffer_review_comment(
filename,
review.start_line,
review.end_line, | :robot: OpenAI
The `buffer_review_comment` method should be renamed to something more descriptive, such as `add_review_to_buffer`. This would make the purpose of the method clearer and easier to understand.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 188 | coderabbitai | github-actions[bot] | @@ -752,6 +776,12 @@ ${
// post the final summary comment
await commenter.comment(`${summarize_comment}`, SUMMARIZE_TAG, 'replace')
+
+ // post the review
+ await commenter.submit_review(
+ context.payload.pull_request.number,
+ commits[commits.length - 1].sha
+ )
} | :robot: OpenAI
It's unclear what the `submit_review` method does. It should be renamed to something more descriptive, such as `submit_review_comments_as_single_review`. Additionally, it would be helpful to add a comment explaining that this method submits all buffered comments as a single review.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 192 | coderabbitai | github-actions[bot] | @@ -10,22 +8,10 @@ import {
EXTRA_CONTENT_TAG,
SUMMARIZE_TAG
} from './commenter.js'
+import {octokit} from './octokit.js' | :robot: OpenAI
The import statement for `octokit` should be updated to import the `Octokit` class instead of the instance.
```suggestion
import {Octokit} from '@octokit/rest'
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 192 | coderabbitai | github-actions[bot] | @@ -10,22 +8,10 @@ import {
EXTRA_CONTENT_TAG,
SUMMARIZE_TAG
} from './commenter.js'
+import {octokit} from './octokit.js'
import {Inputs, Options, Prompts} from './options.js' | :robot: OpenAI
The import statements for `Inputs`, `Options`, and `Prompts` should be updated to reflect their new location in `./options/index.js`.
```suggestion
import {Inputs, Options, Prompts} from './options/index.js'
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 192 | coderabbitai | github-actions[bot] | @@ -10,22 +8,10 @@ import {
EXTRA_CONTENT_TAG,
SUMMARIZE_TAG
} from './commenter.js'
+import {octokit} from './octokit.js'
import {Inputs, Options, Prompts} from './options.js'
import * as tokenizer from './tokenizer.js'
-const token = core.getInput('token')
- ? core.getInput('token')
- : process.env.GITHUB_TOKEN
-
-const RetryOctokit = Octokit.plugin(retry)
-const octokit = new RetryOctokit({
- auth: `token ${token}`,
- request: {
- retries: 10,
- retryAfter: 30
- }
-})
-
const context = github.context
const repo = context.repo | :robot: OpenAI
The `repo` variable is not used in this file. Consider removing it.
```suggestion
const context = github.context
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 192 | coderabbitai | github-actions[bot] | @@ -1,7 +1,5 @@
import * as core from '@actions/core'
import * as github from '@actions/github'
-import {Octokit} from '@octokit/action'
-import {retry} from '@octokit/plugin-retry'
import {Bot} from './bot.js'
import {
Commenter, | :robot: OpenAI
> Note: This review was outside of the patch, so it was mapped it to the closest patch. Original lines [5-10]
The import statement for `octokit` has been moved to a new file `octokit.js`. Please ensure that the import statement is correct and that the file exists.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 192 | coderabbitai | github-actions[bot] | @@ -10,22 +8,10 @@ import {
EXTRA_CONTENT_TAG,
SUMMARIZE_TAG
} from './commenter.js'
+import {octokit} from './octokit.js'
import {Inputs, Options, Prompts} from './options.js'
import * as tokenizer from './tokenizer.js'
-const token = core.getInput('token')
- ? core.getInput('token')
- : process.env.GITHUB_TOKEN
-
-const RetryOctokit = Octokit.plugin(retry)
-const octokit = new RetryOctokit({
- auth: `token ${token}`,
- request: {
- retries: 10,
- retryAfter: 30
- }
-})
-
const context = github.context
const repo = context.repo
const ASK_BOT = '@openai' | :robot: OpenAI
The `ASK_BOT` constant is no longer used in this file. Please remove it.
---end_change_section---
---new_hunk---
```
19: async function handleReviewComment(
20: commenter: Commenter,
21: comment: string,
22: prNumber: number
23: ): Promise<void> {
24: const {owner, repo} = github.context.repo
25: const reviews = await octokit.pulls.listReviews({
26: owner,
27: repo,
28: pull_number: prNumber
29: })
30:
31: if (reviews.data.length === 0) {
32: return
33: }
34:
35: const lastReview = reviews.data[reviews.data.length - 1]
36: const lastReviewId = lastReview.id
37: const lastReviewBody = lastReview.body
38:
39: if (!lastReview.user || lastReview.user.login !== 'openai-bot[bot]') {
40: return
41: }
42:
43: const summary = await commenter.getSummary(prNumber)
44:
45: if (comment.trim() === '') {
46: return
47: }
48:
49: const lines = comment.split('\n')
50:
51: if (lines.length === 1) {
52: await octokit.pulls.createReviewComment({
53: owner,
54: repo,
55: pull_number: prNumber,
56: body: summary,
57: in_reply_to: lastReviewId
58: })
59: } else {
60: const comments = lines.map((line) => ({
61: path: lastReview.path,
62: position: lastReview.position,
63: body: line
64: }))
65:
66: await octokit.pulls.createReviewComment({
67: owner,
68: repo,
69: pull_number: prNumber,
70: comments
71: })
72: }
73: }
```
---old_hunk---
```
async function handleReviewComment(
comment: string,
prNumber: number
): Promise<void> {
const reviews = await octokit.pulls.listReviews({
owner: github.context.repo.owner,
repo: github.context.repo.repo,
pull_number: prNumber
})
if (reviews.data.length === 0) {
return
}
const lastReview = reviews.data[reviews.data.length - 1]
const lastReviewId = lastReview.id
const lastReviewBody = lastReview.body
if (!lastReview.user || lastReview.user.login !== 'openai-bot[bot]') {
return
}
const summary = await Bot.getSummary(prNumber)
if (comment.trim() === '') {
return
}
const lines = comment.split('\n')
if (lines.length === 1) {
await octokit.pulls.createReviewComment({
owner: github.context.repo.owner,
repo: github.context.repo.repo,
pull_number: prNumber,
body: summary,
in_reply_to: lastReviewId
})
} else {
const comments = lines.map((line) => ({
path: lastReview.path,
position: lastReview.position,
body: line
}))
await octokit.pulls.createReviewComment({
owner: github.context.repo.owner,
repo: github.context.repo.repo,
pull_number: prNumber,
comments
})
}
}
```
---comment_chains---
@@ -19,5 +19,5 @@
- The `commenter` parameter is not used in this function. Please remove it.
- The `owner` and `repo` variables are now destructured from `github.context.repo`. Please ensure that the import statement for `github` is correct and that the `context` object exists.
- The `Bot` class has been removed. Please replace `Bot.getSummary(prNumber)` with `commenter.getSummary(prNumber)`.
- The `in_reply_to` parameter is now passed to `createReviewComment` instead of `createComment`. Please ensure that the parameter
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 192 | coderabbitai | github-actions[bot] | @@ -1,19 +1,7 @@
/* eslint-disable @typescript-eslint/explicit-function-return-type */
import * as core from '@actions/core'
import * as github from '@actions/github'
-import {Octokit} from '@octokit/action'
-import {retry} from '@octokit/plugin-retry'
-
-const token = core.getInput('token') || process.env.GITHUB_TOKEN
-
-const RetryOctokit = Octokit.plugin(retry)
-const octokit = new RetryOctokit({
- auth: `token ${token}`,
- request: {
- retries: 10,
- retryAfter: 30
- }
-})
+import {octokit} from './octokit.js' | :robot: OpenAI
The `octokit` import is not used in this file anymore. Please remove it.
```suggestion
import { octokit } from './octokit.js'
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 189 | coderabbitai | github-actions[bot] | @@ -609,6 +609,7 @@ ${comment_chain}
core.warning('No pull request found, skipping.')
continue
}
+
// sanitize review's start_line and end_line
// with patches' start_line and end_line
// if needed adjust start_line and end_line | :robot: OpenAI
The comment is not necessary as it only repeats what the code does. Consider removing it.
```
---end_change_section---
---new_hunk---
```
628: }
629: }
630: }
631: if (!within_patch || review.start_line > review.end_line) {
632: // map the review to the closest patch
633: review.comment = `> Note: This review was outside of the patch, so it was mapped it to the closest patch. Original lines [${review.start_line}-${review.end_line}]
634: ${review.comment}`
```
---old_hunk---
```
}
}
}
if (!within_patch) {
// map the review to the closest patch
review.comment = `> Note: This review was outside of the patch, so it was mapped it to the closest patch. Original lines [${review.start_line}-${review.end_line}]
${review.comment}`
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 189 | coderabbitai | github-actions[bot] | @@ -627,7 +628,7 @@ ${comment_chain}
}
}
}
- if (!within_patch) {
+ if (!within_patch || review.start_line > review.end_line) {
// map the review to the closest patch
review.comment = `> Note: This review was outside of the patch, so it was mapped it to the closest patch. Original lines [${review.start_line}-${review.end_line}]
${review.comment}` | :robot: OpenAI
The condition `review.start_line > review.end_line` should be checked before `!within_patch`. Also, the message in `review.comment` can be improved by adding a period at the end of the sentence and changing "it" to "to".
```
if (review.start_line > review.end_line || !within_patch) {
// map the review to the closest patch
review.comment = `> Note: This review was outside of the patch, so it was mapped to the closest patch. Original lines [${review.start_line}-${review.end_line}]. ${review.comment}`;
}
```
---end_change_section---
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 189 | coderabbitai | github-actions[bot] | @@ -148,7 +148,6 @@ ${tag}`
${message}
${tag}`
-
this.reviewCommentsBuffer.push({
path,
start_line, | :robot: OpenAI
The new code adds a check to ensure that `start_line` and `end_line` are not the same before adding `start_line` to the comment data. This is a good improvement to the sanitization of review comments.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 189 | coderabbitai | github-actions[bot] | @@ -609,6 +609,7 @@ ${comment_chain}
core.warning('No pull request found, skipping.')
continue
} | :robot: OpenAI
The `continue` statement should be on the same line as the closing brace of the if statement to improve code readability.
```suggestion
if (!pullRequest) {
core.warning('No pull request found, skipping.')
continue
}
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 189 | coderabbitai | github-actions[bot] | @@ -621,12 +622,16 @@ ${comment_chain}
if (review.start_line >= start_line) {
closest_start_line = start_line
closest_end_line = end_line
- if (review.end_line <= end_line) {
+ if (
+ review.end_line <= end_line &&
+ review.end_line >= start_line
+ ) {
within_patch = true
break
}
} | :robot: OpenAI
The logic for mapping reviews outside of the patch to the closest patch can be improved. The current implementation only checks if the review's end_line is within the patch's range. This may result in incorrect mappings if the review spans multiple patches or is completely outside of all patches. Consider refactoring this section to handle these cases.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 189 | coderabbitai | github-actions[bot] | @@ -621,12 +622,16 @@ ${comment_chain}
if (review.start_line >= start_line) {
closest_start_line = start_line
closest_end_line = end_line
- if (review.end_line <= end_line) {
+ if (
+ review.end_line <= end_line &&
+ review.end_line >= start_line
+ ) {
within_patch = true
break
}
}
}
+
if (!within_patch) {
// map the review to the closest patch
review.comment = `> Note: This review was outside of the patch, so it was mapped it to the closest patch. Original lines [${review.start_line}-${review.end_line}] | :robot: OpenAI
The comment string should end with a period for consistency.
```suggestion
review.comment = `> Note: This review was outside of the patch, so it was mapped to the closest patch. Original lines [${review.start_line}-${review.end_line}].`
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 187 | coderabbitai | github-actions[bot] | @@ -750,12 +752,6 @@ ${
// post the final summary comment
await commenter.comment(`${summarize_comment}`, SUMMARIZE_TAG, 'replace') | :robot: OpenAI
The new hunk removes the code that posts a review and instead only posts a final summary comment. This is a significant change from the previous implementation. Please ensure that this change does not affect the functionality of the code.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 185 | coderabbitai | github-actions[bot] | @@ -752,6 +750,12 @@ ${
// post the final summary comment
await commenter.comment(`${summarize_comment}`, SUMMARIZE_TAG, 'replace')
+
+ // post the review
+ await commenter.submit_review(
+ context.payload.pull_request.number,
+ commits[commits.length - 1].sha
+ ) | :robot: OpenAI
The new code replaces the call to `commenter.comment` with two separate calls: one to `commenter.comment` and another to `commenter.submit_review`. It would be better to submit the review first and then post the final summary comment. This ensures that the review is submitted even if there's an error posting the summary comment. Suggested replacement:
```diff
+ // post the review
+ await commenter.submit_review(
+ context.payload.pull_request.number,
+ commits[commits.length - 1].sha
+ )
+
// post the final summary comment
await commenter.comment(`${summarize_comment}`, SUMMARIZE_TAG, 'replace')
```
761:
The new code defines a new function `split_patch` that splits a patch string into an array of strings. The function is not used in this file and should be moved to a more appropriate location or removed.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 183 | coderabbitai | github-actions[bot] | @@ -4,7 +4,12 @@ import {Octokit} from '@octokit/action'
import {retry} from '@octokit/plugin-retry'
import pLimit from 'p-limit'
import {Bot} from './bot.js'
-import {Commenter, COMMENT_REPLY_TAG, SUMMARIZE_TAG} from './commenter.js'
+import {
+ Commenter,
+ COMMENT_REPLY_TAG,
+ EXTRA_CONTENT_TAG,
+ SUMMARIZE_TAG
+} from './commenter.js'
import {Inputs, Options, Prompts} from './options.js'
import * as tokenizer from './tokenizer.js'
| :robot: OpenAI
The `commenter.ts` file has a new constant variable `EXTRA_CONTENT_TAG`. This tag is used in the `review-comment.ts` file to remove all content below this tag from the summary. The purpose of this change is to improve the readability of the review comments by removing unnecessary information.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 183 | coderabbitai | github-actions[bot] | @@ -91,11 +76,6 @@ export const codeReview = async (
const {files, commits} = diff.data
if (!files) {
core.warning(`Skipped: diff.data.files is null`)
- await commenter.comment(
- `Skipped: no files to review\n${existing_comment_ids_block}`,
- SUMMARIZE_TAG,
- 'replace'
- )
return
} | :robot: OpenAI
In the `handleReviewComment` function, there is a check for `diff.data.files`. If it is null, the function logs a warning and returns. However, in the old code, if `diff.data.files` is null, the function posts a comment to notify the user. It's unclear why this behavior was removed. Consider adding back the functionality to post a comment to notify the user when `diff.data.files` is null.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 183 | coderabbitai | github-actions[bot] | @@ -319,19 +299,84 @@ ${filename}: ${summary}
}
}
- // failed reviews array
- const reviews_failed: string[] = []
- const do_review = async (
- filename: string,
- file_content: string,
- patches: [number, number, string][]
- ): Promise<void> => {
- // make a copy of inputs
- const ins: Inputs = inputs.clone()
- ins.filename = filename
+ let summarize_comment = `${summarize_final_response}
+${EXTRA_CONTENT_TAG}
+---
- // Pack instructions
- ins.patches += `
+### Chat with 🤖 OpenAI Bot (\`@openai\`)
+- Reply on review comments left by this bot to ask follow-up questions. A review comment is a comment on a diff or a file.
+- Invite the bot into a review comment chain by tagging \`@openai\` in a reply.
+
+### Code suggestions
+- The bot may make code suggestions, but please review them carefully before committing since the line number ranges may be misaligned.
+- You can edit the comment made by the bot and manually tweak the suggestion if it is slightly off.
+
+---
+
+${
+ filter_ignored_files.length > 0
+ ? `
+<details>
+<summary>Files ignored due to filter (${filter_ignored_files.length})</summary>
+
+### Ignored files
+
+* ${filter_ignored_files.map(file => file.filename).join('\n* ')}
+
+</details>
+`
+ : ''
+}
+
+${
+ skipped_files_to_summarize.length > 0
+ ? `
+<details>
+<summary>Files not summarized due to max files limit (${
+ skipped_files_to_summarize.length
+ })</summary>
+
+### Not summarized
+
+* ${skipped_files_to_summarize.join('\n* ')}
+
+</details>
+`
+ : ''
+}
+
+${
+ summaries_failed.length > 0
+ ? `
+<details>
+<summary>Files not summarized due to errors (${
+ summaries_failed.length
+ })</summary>
+
+### Failed to summarize
+
+* ${summaries_failed.join('\n* ')}
+
+</details>
+`
+ : ''
+}
+` | :robot: OpenAI
The `summarize_final_response` variable is used to construct the final response message. The message includes several sections such as "Chat with 🤖 OpenAI Bot", "Code suggestions", "Files ignored due to filter", etc. These sections are concatenated using template literals. Consider refactoring this code to make it more modular and easier to read. For example, you could create separate functions for each section and call them in the main function to construct the final message.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 183 | coderabbitai | github-actions[bot] | @@ -319,19 +299,84 @@ ${filename}: ${summary}
}
}
- // failed reviews array
- const reviews_failed: string[] = []
- const do_review = async (
- filename: string,
- file_content: string,
- patches: [number, number, string][]
- ): Promise<void> => {
- // make a copy of inputs
- const ins: Inputs = inputs.clone()
- ins.filename = filename
+ let summarize_comment = `${summarize_final_response}
+${EXTRA_CONTENT_TAG}
+---
- // Pack instructions
- ins.patches += `
+### Chat with 🤖 OpenAI Bot (\`@openai\`)
+- Reply on review comments left by this bot to ask follow-up questions. A review comment is a comment on a diff or a file.
+- Invite the bot into a review comment chain by tagging \`@openai\` in a reply.
+
+### Code suggestions
+- The bot may make code suggestions, but please review them carefully before committing since the line number ranges may be misaligned.
+- You can edit the comment made by the bot and manually tweak the suggestion if it is slightly off.
+
+---
+
+${
+ filter_ignored_files.length > 0
+ ? `
+<details>
+<summary>Files ignored due to filter (${filter_ignored_files.length})</summary>
+
+### Ignored files
+
+* ${filter_ignored_files.map(file => file.filename).join('\n* ')}
+
+</details>
+`
+ : ''
+}
+
+${
+ skipped_files_to_summarize.length > 0
+ ? `
+<details>
+<summary>Files not summarized due to max files limit (${
+ skipped_files_to_summarize.length
+ })</summary>
+
+### Not summarized
+
+* ${skipped_files_to_summarize.join('\n* ')}
+
+</details>
+`
+ : ''
+}
+
+${
+ summaries_failed.length > 0
+ ? `
+<details>
+<summary>Files not summarized due to errors (${
+ summaries_failed.length
+ })</summary>
+
+### Failed to summarize
+
+* ${summaries_failed.join('\n* ')}
+
+</details>
+`
+ : ''
+}
+`
+
+ if (options.summary_only !== true) {
+ // failed reviews array
+ const reviews_failed: string[] = []
+ const do_review = async (
+ filename: string,
+ file_content: string,
+ patches: [number, number, string][]
+ ): Promise<void> => {
+ // make a copy of inputs
+ const ins: Inputs = inputs.clone()
+ ins.filename = filename
+
+ // Pack instructions
+ ins.patches += `
Format for changes: | :robot: OpenAI
In the `do_review` function, there is a comment block that describes the format for changes. This comment block is duplicated in multiple places throughout the codebase. Consider creating a separate module or utility function to store this comment block and import it wherever it is needed to avoid duplication.
```suggestion
// Example implementation of a utility function to store the comment block
export function getChangeFormatComment(): string {
return `
Format for changes:
---new_hunk---
\`\`\`
<new hunk annotated with line numbers>
\`\`\`
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 181 | coderabbitai | github-actions[bot] | @@ -49,11 +49,15 @@ export class Commenter {
tag = COMMENT_TAG
}
- const body = `${COMMENT_GREETING}
+ let body = `${message}`
+
+ if (mode === 'create' || mode === 'replace') {
+ body = `${COMMENT_GREETING}
${message}
${tag}` | :robot: OpenAI
The new code introduces a change to the body of the comment based on the mode parameter. However, there is a potential issue with the formatting of the comment body. The current implementation assumes that `message` is a single line of text, which may not always be the case. If `message` contains multiple lines, the formatting of the comment body will be incorrect. Consider using a template literal with string interpolation instead of hardcoding the comment body to ensure proper formatting regardless of the length of `message`.
```suggestion
let body = `${COMMENT_GREETING}
${message}
${tag}`
```
<!-- This is an auto-generated reply by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 181 | coderabbitai | github-actions[bot] | @@ -49,11 +49,15 @@ export class Commenter {
tag = COMMENT_TAG
}
- const body = `${COMMENT_GREETING}
+ let body = `${message}`
+
+ if (mode === 'create' || mode === 'replace') {
+ body = `${COMMENT_GREETING}
${message}
${tag}`
+ }
if (mode === 'create') {
await this.create(body, target) | :robot: OpenAI
The `create` method now takes a `message` parameter, but it is not being used in this call. Consider passing the `message` parameter to the `create` method to ensure consistency and avoid potential issues.
```suggestion
await this.create(body, target, message)
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 181 | coderabbitai | github-actions[bot] | @@ -52,12 +52,26 @@ export const codeReview = async (
)
}
+ // get SUMMARIZE_TAG message
+ const existing_summarize_cmt = await commenter.find_comment_with_tag(
+ SUMMARIZE_TAG,
+ context.payload.pull_request.number
+ )
+ let existing_summarize_comment = ''
+ if (existing_summarize_cmt) {
+ existing_summarize_comment = existing_summarize_cmt.body
+ }
+
+ const existing_comment_ids_block = getReviewedCommitIdsBlock(
+ existing_summarize_comment
+ )
+
// if the description contains ignore_keyword, skip
if (inputs.description.includes(ignore_keyword)) {
core.info(`Skipped: description contains ignore_keyword`)
// post a comment to notify the user
await commenter.comment(
- `Skipped: ignored by the user`,
+ `Skipped: description contains ignore_keyword\n${existing_comment_ids_block}`,
SUMMARIZE_TAG,
'replace'
) | :robot: OpenAI
The `find_comment_with_tag` method is called to retrieve an existing comment with the `SUMMARIZE_TAG`. If it exists, the body of the comment is stored in `existing_summarize_comment`. The `getReviewedCommitIdsBlock` function is then called to extract the block of text containing the reviewed commit IDs from the existing comment. If the description of the pull request contains the `ignore_keyword`, the review process is skipped and a comment is posted to notify the user.
It's not clear what the `replace` parameter does in the `comment` method call on line 77. Please provide more context or remove this parameter if it's not needed.
Also, it would be helpful to add a comment explaining what the `SUMMARIZE_TAG` is and how it's used in the code.
---new_hunk---
```
52: )
53: }
54:
55: // get SUMMARIZE_TAG message
56: const existing_summarize_cmt = await commenter.find_comment_with_tag(
57: SUMMARIZE_TAG,
58: context.payload.pull_request.number
59: )
60: let existing_summarize_comment = ''
61: if (existing_summarize_cmt) {
62: existing_summarize_comment = existing_summarize_cmt.body
63: }
64:
65: const existing_comment_ids_block = getReviewedCommitIdsBlock(
66: existing_summarize_comment
67: )
68:
69: // if the description contains ignore_keyword, skip
70: if (inputs.description.includes(ignore_keyword)) {
71: core.info(`Skipped: description contains ignore_keyword`)
72: // post a comment to notify the user
73: await commenter.comment(
74: `Skipped: description contains ignore_keyword\n${existing_comment_ids_block}`,
75: SUMMARIZE_TAG,
76: )
```
---comment_chains---
```
Line 57: Please add a comment explaining what the `SUMMARIZE_TAG` is and how it's used in the code.
Lines 73-76: It's not clear what the `replace` parameter does in the `comment` method call on line 77. Please provide more context or remove this parameter if it's not needed.
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 181 | coderabbitai | github-actions[bot] | @@ -30,7 +30,7 @@ export const DESCRIPTION_TAG_END =
export class Commenter {
/**
- * @param mode Can be "create", "replace", "append" and "prepend". Default is "replace".
+ * @param mode Can be "create", "replace". Default is "replace".
*/ | :robot: OpenAI
The `mode` parameter in the `comment` method has been simplified to only accept "create" and "replace". The "append" and "prepend" modes have been removed.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 181 | coderabbitai | github-actions[bot] | @@ -424,6 +420,7 @@ ${chain}
async create(body: string, target: number) {
try {
+ // get commend ID from the response
await octokit.issues.createComment({ | :robot: OpenAI
The `create` method now includes a try-catch block to handle errors that may occur when creating a comment.
```suggestion
async create(body: string, target: number) {
try {
const response = await octokit.issues.createComment({
owner: repo.owner,
repo: repo.repo,
issue_number: target,
body: body
})
return response.data.id
} catch (e) {
core.warning(`Failed to create comment: ${e}`)
}
}
```
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 181 | coderabbitai | github-actions[bot] | @@ -286,72 +319,6 @@ ${filename}: ${summary}
} else {
inputs.summary = summarize_final_response
- const summarize_comment = `${summarize_final_response}
-
----
-
-### Chat with 🤖 OpenAI Bot (\`@openai\`)
-- Reply on review comments left by this bot to ask follow-up questions. A review comment is a comment on a diff or a file.
-- Invite the bot into a review comment chain by tagging \`@openai\` in a reply.
-
-### Code suggestions
-- The bot may make code suggestions, but please review them carefully before committing since the line number ranges may be misaligned.
-- You can edit the comment made by the bot and manually tweak the suggestion if it is slightly off.
-
----
-
-${
- filter_ignored_files.length > 0
- ? `
-<details>
-<summary>Files ignored due to filter (${filter_ignored_files.length})</summary>
-
-### Ignored files
-
-* ${filter_ignored_files.map(file => file.filename).join('\n* ')}
-
-</details>
-`
- : ''
-}
-
-${
- skipped_files_to_summarize.length > 0
- ? `
-<details>
-<summary>Files not summarized due to max files limit (${
- skipped_files_to_summarize.length
- })</summary>
-
-### Not summarized
-
-* ${skipped_files_to_summarize.join('\n* ')}
-
-</details>
-`
- : ''
-}
-
-${
- summaries_failed.length > 0
- ? `
-<details>
-<summary>Files not summarized due to errors (${
- summaries_failed.length
- })</summary>
-
-### Failed to summarize
-
-* ${summaries_failed.join('\n* ')}
-
-</details>
-`
- : ''
-}
-`
-
- await commenter.comment(`${summarize_comment}`, SUMMARIZE_TAG, 'replace')
-
// final release notes
next_summarize_ids = summarize_final_response_ids
const [release_notes_response, release_notes_ids] = await heavyBot.chat( | :robot: OpenAI
The `summarize_comment` variable is no longer needed and can be removed. The comment that was being set in this variable has been moved to line 623.
<!-- This is an auto-generated comment by OpenAI --> |
ai-pr-reviewer | github_2023 | typescript | 181 | coderabbitai | github-actions[bot] | @@ -368,11 +335,6 @@ ${
}
}
- if (options.summary_only === true) {
- core.info('summary_only is true, exiting')
- return
- }
-
// failed reviews array | :robot: OpenAI
The `do_review` function declaration should be moved outside of the `if` block on line 332, so that it can be used later in the code.
<!-- 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.