mirror of
https://github.com/VectifyAI/PageIndex.git
synced 2026-04-25 16:16:22 +02:00
Refactor issue dedup system to use claude-code-action with /dedupe command
Replace the copilot-generated inline search logic with a claude-code-action based architecture inspired by anthropic/claude-code's approach: - Add .claude/commands/dedupe.md with 5-parallel-search strategy - Add scripts/comment-on-duplicates.sh with 3-day grace period warning - Rewrite issue-dedupe.yml to use claude-code-action + /dedupe command - Rewrite autoclose script to check bot comments, human activity, and thumbsdown - Rewrite backfill to trigger dedupe workflow per issue with rate limiting - Add concurrency control, timeout, input validation, and rate limit retry - Remove gh.sh (unnecessary), backfill-dedupe.js (replaced by workflow trigger)
This commit is contained in:
BukeLy
parent
b3cb9531a4
commit
fd9330c434
8 changed files with 413 additions and 752 deletions
|
|
@ -1,34 +1,32 @@
|
|||
/**
|
||||
* scripts/autoclose-labeled-issues.js
|
||||
*
|
||||
* Closes open issues that carry the "autoclose" label and have been inactive
|
||||
* (no updates) for more than INACTIVITY_DAYS days.
|
||||
* Auto-closes issues that have a bot "possible duplicate" comment older than
|
||||
* 3 days, unless:
|
||||
* - A human has commented after the bot's duplicate comment
|
||||
* - The author reacted with thumbs-down on the duplicate comment
|
||||
*
|
||||
* Required environment variables:
|
||||
* GITHUB_TOKEN – GitHub Actions token (or PAT with repo:issues write access)
|
||||
* REPO_OWNER – Repository owner (e.g. VectifyAI)
|
||||
* REPO_NAME – Repository name (e.g. PageIndex)
|
||||
* GITHUB_TOKEN - GitHub Actions token
|
||||
* REPO_OWNER - Repository owner
|
||||
* REPO_NAME - Repository name
|
||||
*
|
||||
* Optional environment variables:
|
||||
* INACTIVITY_DAYS – Days of inactivity before closing (default: 7)
|
||||
* DRY_RUN – If "true", report but do not close issues (default: false)
|
||||
* Optional:
|
||||
* DRY_RUN - If "true", report but do not close (default: false)
|
||||
*/
|
||||
|
||||
'use strict';
|
||||
|
||||
const https = require('https');
|
||||
|
||||
// ── Configuration ─────────────────────────────────────────────────────────────
|
||||
const GITHUB_TOKEN = process.env.GITHUB_TOKEN;
|
||||
const REPO_OWNER = process.env.REPO_OWNER;
|
||||
const REPO_NAME = process.env.REPO_NAME;
|
||||
const DRY_RUN = process.env.DRY_RUN === 'true';
|
||||
|
||||
const GITHUB_TOKEN = process.env.GITHUB_TOKEN;
|
||||
const REPO_OWNER = process.env.REPO_OWNER;
|
||||
const REPO_NAME = process.env.REPO_NAME;
|
||||
const INACTIVITY_DAYS = parseInt(process.env.INACTIVITY_DAYS || '7', 10);
|
||||
const DRY_RUN = process.env.DRY_RUN === 'true';
|
||||
const THREE_DAYS_MS = 3 * 24 * 60 * 60 * 1000;
|
||||
|
||||
// ── HTTP helper ───────────────────────────────────────────────────────────────
|
||||
|
||||
function githubRequest(method, path, body = null) {
|
||||
function githubRequest(method, path, body = null, retried = false) {
|
||||
return new Promise((resolve, reject) => {
|
||||
const payload = body ? JSON.stringify(body) : null;
|
||||
const options = {
|
||||
|
|
@ -37,29 +35,31 @@ function githubRequest(method, path, body = null) {
|
|||
method,
|
||||
headers: {
|
||||
'Authorization': `Bearer ${GITHUB_TOKEN}`,
|
||||
'Accept': 'application/vnd.github+json',
|
||||
'User-Agent': 'PageIndex-Autoclose-Script/1.0',
|
||||
'Accept': 'application/vnd.github+json',
|
||||
'User-Agent': 'PageIndex-Autoclose/1.0',
|
||||
'X-GitHub-Api-Version': '2022-11-28',
|
||||
...(payload ? {
|
||||
'Content-Type': 'application/json',
|
||||
'Content-Length': Buffer.byteLength(payload),
|
||||
} : {}),
|
||||
...(payload ? { 'Content-Type': 'application/json', 'Content-Length': Buffer.byteLength(payload) } : {}),
|
||||
},
|
||||
};
|
||||
|
||||
const req = https.request(options, (res) => {
|
||||
let data = '';
|
||||
res.on('data', chunk => (data += chunk));
|
||||
res.on('end', () => {
|
||||
if (res.statusCode >= 400) {
|
||||
reject(new Error(`GitHub API ${method} ${path} → ${res.statusCode}: ${data}`));
|
||||
res.on('end', async () => {
|
||||
if ((res.statusCode === 403 || res.statusCode === 429) && !retried) {
|
||||
const retryAfter = parseInt(res.headers['retry-after'] || '60', 10);
|
||||
console.log(` Rate limited on ${method} ${path}, retrying after ${retryAfter}s...`);
|
||||
await sleep(retryAfter * 1000);
|
||||
try { resolve(await githubRequest(method, path, body, true)); }
|
||||
catch (err) { reject(err); }
|
||||
return;
|
||||
}
|
||||
try {
|
||||
resolve(data ? JSON.parse(data) : {});
|
||||
} catch {
|
||||
resolve({});
|
||||
if (res.statusCode >= 400) {
|
||||
reject(new Error(`GitHub API ${method} ${path} -> ${res.statusCode}: ${data}`));
|
||||
return;
|
||||
}
|
||||
try { resolve(data ? JSON.parse(data) : {}); }
|
||||
catch { resolve({}); }
|
||||
});
|
||||
});
|
||||
req.on('error', reject);
|
||||
|
|
@ -68,113 +68,162 @@ function githubRequest(method, path, body = null) {
|
|||
});
|
||||
}
|
||||
|
||||
/** Simple sleep helper for rate-limiting. */
|
||||
const sleep = (ms) => new Promise(r => setTimeout(r, ms));
|
||||
|
||||
// ── Core logic ────────────────────────────────────────────────────────────────
|
||||
|
||||
/**
|
||||
* Fetches all open issues with the "autoclose" label, paginating as needed.
|
||||
* Fetches open issues with the "duplicate" label, paginating as needed.
|
||||
* Only returns issues created more than 3 days ago.
|
||||
*/
|
||||
async function fetchAutocloseIssues() {
|
||||
async function fetchDuplicateIssues() {
|
||||
const issues = [];
|
||||
let page = 1;
|
||||
while (true) {
|
||||
const data = await githubRequest(
|
||||
'GET',
|
||||
`/repos/${REPO_OWNER}/${REPO_NAME}/issues?state=open&labels=autoclose&per_page=100&page=${page}`
|
||||
`/repos/${REPO_OWNER}/${REPO_NAME}/issues?state=open&labels=duplicate&per_page=100&page=${page}`
|
||||
);
|
||||
if (!Array.isArray(data) || data.length === 0) break;
|
||||
// Filter out any pull requests that may surface
|
||||
issues.push(...data.filter(i => !i.pull_request));
|
||||
if (data.length < 100) break;
|
||||
page++;
|
||||
}
|
||||
return issues;
|
||||
|
||||
const cutoff = new Date(Date.now() - THREE_DAYS_MS);
|
||||
return issues.filter(i => new Date(i.created_at) < cutoff);
|
||||
}
|
||||
|
||||
/**
|
||||
* Closes a single issue with a polite explanatory comment.
|
||||
* Finds the bot's duplicate comment on an issue (contains "possible duplicate").
|
||||
*/
|
||||
async function closeIssue(issueNumber, inactivityDays) {
|
||||
const body =
|
||||
`This issue has been automatically closed because it was marked as a **duplicate** ` +
|
||||
`and has had no new activity for ${inactivityDays} day(s).\n\n` +
|
||||
`If you believe this was closed in error, please reopen the issue and leave a comment. ` +
|
||||
`New human activity will prevent automatic closure in the future.\n\n` +
|
||||
`Thank you for your contribution! 🙏`;
|
||||
function findDuplicateComment(comments) {
|
||||
return comments.find(c =>
|
||||
(c.user.type === 'Bot' || c.user.login === 'github-actions[bot]') &&
|
||||
c.body.includes('possible duplicate')
|
||||
);
|
||||
}
|
||||
|
||||
/**
|
||||
* Checks if there are human comments after the duplicate comment.
|
||||
*/
|
||||
function hasHumanCommentAfter(comments, afterDate) {
|
||||
return comments.some(c => {
|
||||
if (c.user.type === 'Bot' || c.user.login.endsWith('[bot]') || c.user.login === 'github-actions') {
|
||||
return false;
|
||||
}
|
||||
return new Date(c.created_at) > afterDate;
|
||||
});
|
||||
}
|
||||
|
||||
/**
|
||||
* Checks if the duplicate comment has a thumbs-down reaction.
|
||||
*/
|
||||
async function hasThumbsDownReaction(commentId) {
|
||||
const reactions = await githubRequest(
|
||||
'GET',
|
||||
`/repos/${REPO_OWNER}/${REPO_NAME}/issues/comments/${commentId}/reactions`
|
||||
);
|
||||
return Array.isArray(reactions) && reactions.some(r => r.content === '-1');
|
||||
}
|
||||
|
||||
/**
|
||||
* Closes an issue as duplicate with a comment.
|
||||
*/
|
||||
async function closeAsDuplicate(issueNumber) {
|
||||
const body =
|
||||
'This issue has been automatically closed as a duplicate. ' +
|
||||
'No human activity or objection was received within the 3-day grace period.\n\n' +
|
||||
'If you believe this was closed in error, please reopen the issue and leave a comment.';
|
||||
|
||||
// Post closing comment first
|
||||
await githubRequest(
|
||||
'POST',
|
||||
`/repos/${REPO_OWNER}/${REPO_NAME}/issues/${issueNumber}/comments`,
|
||||
{ body }
|
||||
);
|
||||
|
||||
// Close the issue
|
||||
await githubRequest(
|
||||
'PATCH',
|
||||
`/repos/${REPO_OWNER}/${REPO_NAME}/issues/${issueNumber}`,
|
||||
{ state: 'closed', state_reason: 'not_planned' }
|
||||
{ state: 'closed', state_reason: 'completed' }
|
||||
);
|
||||
|
||||
await githubRequest(
|
||||
'POST',
|
||||
`/repos/${REPO_OWNER}/${REPO_NAME}/issues/${issueNumber}/labels`,
|
||||
{ labels: ['duplicate'] }
|
||||
);
|
||||
}
|
||||
|
||||
// ── Entry point ───────────────────────────────────────────────────────────────
|
||||
async function processIssue(issue) {
|
||||
const num = issue.number;
|
||||
console.log(`\nChecking issue #${num}: ${issue.title}`);
|
||||
|
||||
const comments = await githubRequest(
|
||||
'GET',
|
||||
`/repos/${REPO_OWNER}/${REPO_NAME}/issues/${num}/comments?per_page=100`
|
||||
);
|
||||
|
||||
if (!Array.isArray(comments)) {
|
||||
console.log(` -> Could not fetch comments, skipping.`);
|
||||
return false;
|
||||
}
|
||||
|
||||
const dupeComment = findDuplicateComment(comments);
|
||||
if (!dupeComment) {
|
||||
console.log(` -> No duplicate comment found, skipping.`);
|
||||
return false;
|
||||
}
|
||||
|
||||
const commentDate = new Date(dupeComment.created_at);
|
||||
const ageMs = Date.now() - commentDate.getTime();
|
||||
|
||||
if (ageMs < THREE_DAYS_MS) {
|
||||
const daysLeft = Math.ceil((THREE_DAYS_MS - ageMs) / (24 * 60 * 60 * 1000));
|
||||
console.log(` -> Duplicate comment is less than 3 days old (${daysLeft}d remaining), skipping.`);
|
||||
return false;
|
||||
}
|
||||
|
||||
if (hasHumanCommentAfter(comments, commentDate)) {
|
||||
console.log(` -> Human commented after duplicate comment, skipping.`);
|
||||
return false;
|
||||
}
|
||||
|
||||
if (await hasThumbsDownReaction(dupeComment.id)) {
|
||||
console.log(` -> Author reacted with thumbs-down, skipping.`);
|
||||
return false;
|
||||
}
|
||||
|
||||
if (DRY_RUN) {
|
||||
console.log(` [DRY RUN] Would close issue #${num}`);
|
||||
return true;
|
||||
}
|
||||
|
||||
await closeAsDuplicate(num);
|
||||
console.log(` -> Closed issue #${num} as duplicate`);
|
||||
return true;
|
||||
}
|
||||
|
||||
async function main() {
|
||||
// Validate required env vars
|
||||
const missing = ['GITHUB_TOKEN', 'REPO_OWNER', 'REPO_NAME']
|
||||
.filter(k => !process.env[k]);
|
||||
const missing = ['GITHUB_TOKEN', 'REPO_OWNER', 'REPO_NAME'].filter(k => !process.env[k]);
|
||||
if (missing.length) {
|
||||
console.error(`Missing required environment variables: ${missing.join(', ')}`);
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
const cutoff = new Date(Date.now() - INACTIVITY_DAYS * 24 * 60 * 60 * 1000);
|
||||
console.log('Auto-close duplicate issues');
|
||||
console.log(` Repository: ${REPO_OWNER}/${REPO_NAME}`);
|
||||
console.log(` Dry run: ${DRY_RUN}`);
|
||||
|
||||
console.log(`Auto-close inactive labelled issues`);
|
||||
console.log(` Repository: ${REPO_OWNER}/${REPO_NAME}`);
|
||||
console.log(` Inactivity days: ${INACTIVITY_DAYS} (cutoff: ${cutoff.toISOString()})`);
|
||||
console.log(` Dry run: ${DRY_RUN}`);
|
||||
|
||||
const issues = await fetchAutocloseIssues();
|
||||
console.log(`\nFound ${issues.length} open issue(s) with "autoclose" label.`);
|
||||
const issues = await fetchDuplicateIssues();
|
||||
console.log(`\nFound ${issues.length} duplicate-labeled issue(s) older than 3 days.`);
|
||||
|
||||
let closedCount = 0;
|
||||
let skippedCount = 0;
|
||||
|
||||
for (const issue of issues) {
|
||||
const lastActivity = new Date(issue.updated_at);
|
||||
const inactive = lastActivity < cutoff;
|
||||
const daysSince = Math.floor((Date.now() - lastActivity.getTime()) / (1000 * 60 * 60 * 24));
|
||||
|
||||
if (!inactive) {
|
||||
console.log(` #${issue.number} — active ${daysSince}d ago, skipping.`);
|
||||
skippedCount++;
|
||||
continue;
|
||||
}
|
||||
|
||||
console.log(` #${issue.number} — inactive for ${daysSince}d: "${issue.title}"`);
|
||||
|
||||
if (DRY_RUN) {
|
||||
console.log(` [DRY RUN] Would close issue #${issue.number}`);
|
||||
closedCount++;
|
||||
continue;
|
||||
}
|
||||
|
||||
try {
|
||||
await closeIssue(issue.number, INACTIVITY_DAYS);
|
||||
console.log(` ✅ Closed issue #${issue.number}`);
|
||||
closedCount++;
|
||||
} catch (err) {
|
||||
console.error(` ❌ Failed to close #${issue.number}: ${err.message}`);
|
||||
}
|
||||
|
||||
// Respect GitHub's secondary rate limit
|
||||
const closed = await processIssue(issue);
|
||||
if (closed) closedCount++;
|
||||
await sleep(1000);
|
||||
}
|
||||
|
||||
console.log(`\nSummary: ${closedCount} closed, ${skippedCount} still active.`);
|
||||
console.log(`\nSummary: ${closedCount} issue(s) closed.`);
|
||||
}
|
||||
|
||||
main().catch(err => {
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue