Merge pull request #58 from Jamkris/feat/upstream-drift-tracker

feat: upstream drift detector

Author: Jamkris

.github/workflows/upstream-drift.yml

@@ -0,0 +1,27 @@
+name: Upstream Drift
+
+on:
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+jobs:
+  check:
+    name: Check upstream drift
+    runs-on: ubuntu-latest
+    timeout-minutes: 5
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '20.x'
+
+      - name: Check upstream drift
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: node scripts/upstream/check-upstream-drift.js

scripts/lib/upstream-drift.js

@@ -0,0 +1,178 @@
+/**
+ * Upstream drift engine: pure functions used by the upstream-drift Action.
+ *
+ * `scripts/upstream/check-upstream-drift.js` calls these helpers and drives
+ * the `gh` CLI. Functions here have no I/O so they can be unit-tested in
+ * isolation against `tests/lib/upstream-drift.test.js`.
+ *
+ * State of record:
+ *   - Human:    upstream/README.md (Upstream baseline section)
+ *   - Machine:  upstream/.upstream-sync.json
+ *
+ * Schema for the JSON state file:
+ *   {
+ *     "upstream":      "owner/repo",
+ *     "lastSyncedSha": "<40-char SHA>",
+ *     "lastSyncedAt":  "<YYYY-MM-DD or ISO 8601>",
+ *     "notes":         "optional free text"
+ *   }
+ */
+
+const SHA_RE = /^[0-9a-f]{40}$/;
+const REPO_RE = /^[A-Za-z0-9._-]+\/[A-Za-z0-9._-]+$/;
+const COMMIT_BODY_LIMIT = 50;
+
+/**
+ * Parse and validate the contents of `upstream/.upstream-sync.json`.
+ *
+ * Throws on any structural problem — the workflow should fail fast rather
+ * than silently treat a malformed state file as "no drift".
+ *
+ * @param {string} jsonString
+ * @returns {{ upstream: string, lastSyncedSha: string, lastSyncedAt: string, notes?: string }}
+ */
+function parseUpstreamState(jsonString) {
+  let parsed;
+  try {
+    parsed = JSON.parse(jsonString);
+  } catch (err) {
+    throw new Error(`upstream-sync state is not valid JSON: ${err.message}`, { cause: err });
+  }
+
+  if (parsed === null || typeof parsed !== 'object' || Array.isArray(parsed)) {
+    throw new Error('upstream-sync state must be a JSON object');
+  }
+
+  const { upstream, lastSyncedSha, lastSyncedAt, notes } = parsed;
+
+  if (typeof upstream !== 'string' || !REPO_RE.test(upstream)) {
+    throw new Error(`upstream must be a "owner/repo" string (got: ${JSON.stringify(upstream)})`);
+  }
+
+  if (typeof lastSyncedSha !== 'string' || !SHA_RE.test(lastSyncedSha)) {
+    throw new Error(`lastSyncedSha must be a 40-char hex string (got: ${JSON.stringify(lastSyncedSha)})`);
+  }
+
+  if (typeof lastSyncedAt !== 'string' || lastSyncedAt.length === 0) {
+    throw new Error(`lastSyncedAt must be a non-empty string (got: ${JSON.stringify(lastSyncedAt)})`);
+  }
+
+  if (notes !== undefined && typeof notes !== 'string') {
+    throw new Error(`notes, when present, must be a string (got: ${typeof notes})`);
+  }
+
+  return { upstream, lastSyncedSha, lastSyncedAt, notes };
+}
+
+/**
+ * Short SHA (first 7 chars) for display in titles and URLs.
+ *
+ * @param {string} sha
+ * @returns {string}
+ */
+function shortSha(sha) {
+  if (typeof sha !== 'string') return '';
+  return sha.slice(0, 7);
+}
+
+/**
+ * Title shown on the rolling tracking issue. Recomputed every run so the
+ * title itself encodes the current delta count.
+ *
+ * @param {{ count: number, lastSyncedShaShort: string }} args
+ * @returns {string}
+ */
+function formatIssueTitle({ count, lastSyncedShaShort }) {
+  if (typeof count !== 'number' || count < 0 || !Number.isInteger(count)) {
+    throw new Error(`formatIssueTitle: count must be a non-negative integer (got: ${count})`);
+  }
+  if (typeof lastSyncedShaShort !== 'string' || lastSyncedShaShort.length === 0) {
+    throw new Error('formatIssueTitle: lastSyncedShaShort must be a non-empty string');
+  }
+  const noun = count === 1 ? 'commit' : 'commits';
+  return `Upstream sync: ${count} new ${noun} in ECC since ${lastSyncedShaShort}`;
+}
+
+/**
+ * Body for the rolling tracking issue. Truncates the commit list at
+ * COMMIT_BODY_LIMIT entries and links to the compare URL for the full diff.
+ *
+ * @param {{
+ *   commits: Array<{ sha: string, author: string, message: string }>,
+ *   lastSyncedSha: string,
+ *   upstreamHeadSha: string,
+ *   upstreamRepo: string,
+ * }} args
+ * @returns {string}
+ */
+function formatIssueBody({ commits, lastSyncedSha, upstreamHeadSha, upstreamRepo }) {
+  if (!Array.isArray(commits)) {
+    throw new Error('formatIssueBody: commits must be an array');
+  }
+  if (!REPO_RE.test(upstreamRepo)) {
+    throw new Error(`formatIssueBody: upstreamRepo must be "owner/repo" (got: ${upstreamRepo})`);
+  }
+
+  const compareUrl = `https://github.com/${upstreamRepo}/compare/${lastSyncedSha}...${upstreamHeadSha}`;
+  const lines = [];
+
+  lines.push(`Upstream \`${upstreamRepo}\` has **${commits.length}** commit(s) ahead of the recorded baseline.`);
+  lines.push('');
+  lines.push(`- **Baseline**: \`${shortSha(lastSyncedSha)}\` (recorded in [\`upstream/.upstream-sync.json\`](../blob/main/upstream/.upstream-sync.json))`);
+  lines.push(`- **Upstream HEAD**: \`${shortSha(upstreamHeadSha)}\``);
+  lines.push(`- **Full diff**: ${compareUrl}`);
+  lines.push('');
+
+  if (commits.length === 0) {
+    lines.push('_No commits to show._');
+    lines.push('');
+  } else {
+    const visible = commits.slice(0, COMMIT_BODY_LIMIT);
+    const truncated = commits.length - visible.length;
+
+    lines.push('<details>');
+    lines.push(`<summary>Commits (${commits.length} total${truncated > 0 ? `, showing first ${visible.length}` : ''})</summary>`);
+    lines.push('');
+    for (const c of visible) {
+      const firstLine = (c.message || '').split('\n')[0].trim();
+      lines.push(`- \`${shortSha(c.sha)}\` ${c.author ? `(@${c.author}) ` : ''}${firstLine}`);
+    }
+    if (truncated > 0) {
+      lines.push(`- _… and ${truncated} more. See the [full diff](${compareUrl})._`);
+    }
+    lines.push('');
+    lines.push('</details>');
+    lines.push('');
+  }
+
+  lines.push('---');
+  lines.push('');
+  lines.push('To close this issue, advance the baseline by following the procedure in [`upstream/README.md`](../blob/main/upstream/README.md#recording-a-sync). This issue is maintained automatically by `.github/workflows/upstream-drift.yml`.');
+
+  return lines.join('\n');
+}
+
+/**
+ * Compare URL for the GitHub UI. Convenience export — also used by the
+ * entry script for the Phase 1 log output.
+ *
+ * @param {string} upstreamRepo
+ * @param {string} baseSha
+ * @param {string} headSha
+ * @returns {string}
+ */
+function compareUrl(upstreamRepo, baseSha, headSha) {
+  if (!REPO_RE.test(upstreamRepo)) {
+    throw new Error(`compareUrl: upstreamRepo must be "owner/repo" (got: ${upstreamRepo})`);
+  }
+  return `https://github.com/${upstreamRepo}/compare/${baseSha}...${headSha}`;
+}
+
+module.exports = {
+  COMMIT_BODY_LIMIT,
+  parseUpstreamState,
+  shortSha,
+  formatIssueTitle,
+  formatIssueBody,
+  compareUrl,
+};

scripts/upstream/check-upstream-drift.js

@@ -0,0 +1,187 @@
+#!/usr/bin/env node
+
+/**
+ * Upstream drift detector — Phase 1 (log-only).
+ *
+ * Reads `upstream/.upstream-sync.json`, asks the GitHub API how many
+ * commits the upstream repo is ahead of the recorded baseline, and logs
+ * the result. Does NOT create or update GitHub issues yet — that lands
+ * in Phase 2.
+ *
+ * Designed to run in `.github/workflows/upstream-drift.yml`:
+ *   - Uses `gh api` via execFileSync (argv array — no shell parsing).
+ *   - Exits 0 on success and on tolerated upstream errors (the repo
+ *     itself was renamed/archived/deleted) so weekly cron does not
+ *     produce red runs nobody triages.
+ *   - Exits non-zero on programmer/config errors: a malformed state
+ *     file, or a baseline SHA that doesn't exist in an otherwise
+ *     reachable upstream repo (almost always a typo).
+ */
+
+const fs = require('fs');
+const path = require('path');
+const { execFileSync } = require('child_process');
+
+const lib = require('../lib/upstream-drift');
+
+const REPO_ROOT = path.join(__dirname, '..', '..');
+const STATE_PATH = path.join(REPO_ROOT, 'upstream', '.upstream-sync.json');
+
+function log(message) {
+  console.log(`[upstream-drift] ${message}`);
+}
+
+function warn(message) {
+  console.error(`[upstream-drift] ${message}`);
+}
+
+function readState() {
+  let raw;
+  try {
+    raw = fs.readFileSync(STATE_PATH, 'utf8');
+  } catch (err) {
+    throw new Error(`Could not read state file at ${STATE_PATH}: ${err.message}`, { cause: err });
+  }
+  return lib.parseUpstreamState(raw);
+}
+
+/**
+ * Invoke `gh api` for the given endpoint and return the parsed JSON.
+ * Uses execFileSync with an argv array so the endpoint never reaches
+ * a shell — defense-in-depth against future inputs that might bypass
+ * the JSON-schema validation upstream.
+ *
+ * 404s are surfaced as a typed error (`err.is404 === true`) so callers
+ * can distinguish tolerable cases (upstream repo gone) from hard
+ * failures (invalid baseline SHA against a repo that does exist).
+ *
+ * @param {string} endpoint - path like "repos/owner/repo/compare/A...B"
+ * @returns {object}
+ */
+function ghApi(endpoint) {
+  let stdout;
+  try {
+    stdout = execFileSync('gh', ['api', endpoint], {
+      encoding: 'utf8',
+      stdio: ['ignore', 'pipe', 'pipe'],
+      // The compare endpoint can return well over 1 MB of JSON when
+      // the delta includes hundreds of commits. Default maxBuffer is
+      // 1 MB and the process is killed with SIGTERM on overflow.
+      maxBuffer: 50 * 1024 * 1024,
+    });
+  } catch (err) {
+    const stderr = (err.stderr || '').toString();
+    const is404 = stderr.includes('HTTP 404') || stderr.includes('Not Found');
+    const apiError = new Error(`gh api failed for "${endpoint}": ${stderr || err.message}`, { cause: err });
+    apiError.stderr = stderr;
+    apiError.is404 = is404;
+    throw apiError;
+  }
+  try {
+    return JSON.parse(stdout);
+  } catch (err) {
+    throw new Error(`gh api returned non-JSON for "${endpoint}": ${err.message}`, { cause: err });
+  }
+}
+
+/**
+ * Pre-flight: check whether the upstream repo itself is reachable. A
+ * 404 here genuinely means "rename / archive / deletion" — a tolerable
+ * config drift the workflow should warn about, not fail on. A 404 on
+ * the *compare* endpoint after this check passes is a hard error
+ * (almost certainly a malformed `lastSyncedSha`).
+ *
+ * @param {string} repo - "owner/repo"
+ * @returns {boolean} true if reachable; false if the repo returns 404
+ */
+function isUpstreamReachable(repo) {
+  try {
+    ghApi(`repos/${repo}`);
+    return true;
+  } catch (err) {
+    if (err.is404) {
+      warn(`Upstream repo "${repo}" returned 404. Treating as tolerated upstream-unreachable (rename, archive, or deletion).`);
+      return false;
+    }
+    throw err;
+  }
+}
+
+function summarize(state, compare) {
+  const status = compare.status;
+  const ahead = compare.ahead_by;
+  const behind = compare.behind_by;
+  const headSha = compare.commits && compare.commits.length > 0
+    ? compare.commits[compare.commits.length - 1].sha
+    : state.lastSyncedSha;
+
+  log(`Status: ${status} (ahead_by=${ahead}, behind_by=${behind})`);
+  log(`Baseline: ${lib.shortSha(state.lastSyncedSha)} (recorded ${state.lastSyncedAt})`);
+  log(`Upstream HEAD: ${lib.shortSha(headSha)}`);
+  log(`Compare: ${lib.compareUrl(state.upstream, state.lastSyncedSha, headSha)}`);
+
+  if (status === 'identical' || ahead === 0) {
+    log('No drift — baseline matches upstream HEAD.');
+    return;
+  }
+
+  if (status === 'ahead' || status === 'diverged') {
+    log(`Drift detected: upstream is ${ahead} commit(s) ahead.`);
+    return;
+  }
+
+  if (status === 'behind') {
+    log('Baseline is ahead of upstream HEAD — likely a manual cherry-pick or upstream reset.');
+    return;
+  }
+
+  log(`Unknown compare status "${status}" — surfacing as drift for review.`);
+}
+
+function main() {
+  let state;
+  try {
+    state = readState();
+  } catch (err) {
+    console.error(err.message);
+    process.exit(1);
+  }
+
+  log(`Upstream: ${state.upstream}`);
+
+  // Pre-flight: if the repo itself is 404, treat it as tolerable
+  // (rename/archive/deletion) and exit 0. Phase 2 will optionally post
+  // a comment on the existing tracking issue in this branch.
+  if (!isUpstreamReachable(state.upstream)) {
+    process.exit(0);
+  }
+
+  // Repo exists. A 404 on the compare endpoint now means the recorded
+  // baseline SHA is not reachable in the upstream repo — almost always
+  // a typo in upstream/.upstream-sync.json. Fail loudly so the
+  // operator notices.
+  const endpoint = `repos/${state.upstream}/compare/${state.lastSyncedSha}...HEAD`;
+  let compare;
+  try {
+    compare = ghApi(endpoint);
+  } catch (err) {
+    if (err.is404) {
+      console.error(
+        `Baseline SHA "${state.lastSyncedSha}" is not reachable in ${state.upstream}. ` +
+          `Check upstream/.upstream-sync.json — the SHA may be malformed or refer to a commit ` +
+          `that was force-removed from the upstream history.`,
+      );
+      process.exit(1);
+    }
+    console.error(err.message);
+    process.exit(1);
+  }
+
+  summarize(state, compare);
+}
+
+if (require.main === module) {
+  main();
+}
+
+module.exports = { readState, ghApi, isUpstreamReachable, summarize };