ci(infra): require issue link for external PRs (#35690)

Enforce that all external PRs reference an approved issue via GitHub
auto-close keywords (`Fixes #NNN`, `Closes #NNN`, `Resolves #NNN`). This
replaces the previous AI-disclaimer policy in the PR template with a
stricter requirement: external contributors must link to a
maintainer-approved issue before their PR can merge.

## Changes

- Add `require_issue_link.yml` workflow that chains off the `external`
label applied by `tag-external-contributions.yml` — listens for
`labeled`, `edited`, and `reopened` events to avoid duplicating the org
membership API call
- Scan PR body with a case-insensitive regex matching all conjugations
of `close/fix/resolve` + `#NNN`; fail the check and post a deduplicated
comment (via `<!-- require-issue-link -->` HTML marker) when no link is
found
- Apply a `missing-issue-link` label on failure, remove it on pass —
enables bulk cleanup via label filter
- Add `workflow_dispatch` backfill job to `pr_size_labeler.yml` for
retroactively applying size labels to open PRs
- Quote `author` in GitHub search queries in
`tag-external-contributions.yml` to prevent mismatches on usernames with
special characters
- Update `PULL_REQUEST_TEMPLATE.md` to replace the AI-disclaimer
guideline with the new issue-link requirement

> [!NOTE]
> `require_issue_link.yml` depends on `tag-external-contributions.yml`
running first to apply the `external` label. Deploy as a non-required
check initially, then promote to required after validation.

.github/PULL_REQUEST_TEMPLATE.md

@@ -31,7 +31,7 @@ Thank you for contributing to LangChain! Follow these steps to have your pull re
 
 Additional guidelines:
 
-  - We ask that if you use generative AI for your contribution, you include a disclaimer.
+  - All external PRs must link to an issue or discussion where a solution has been approved by a maintainer. PRs without prior approval will be closed.
   - PRs should not touch more than one package unless absolutely necessary.
   - Do not update the `uv.lock` files or add dependencies to `pyproject.toml` files (even optional ones) unless you have explicit permission to do so by a maintainer.
 

.github/workflows/pr_size_labeler.yml

@@ -8,12 +8,19 @@ name: "📏 PR Size Labeler"
 on:
   pull_request_target:
     types: [opened, synchronize, reopened]
+  workflow_dispatch:
+    inputs:
+      max_items:
+        description: "Maximum number of open PRs to process"
+        default: "100"
+        type: string
 
 permissions:
   contents: read
 
 jobs:
   size-label:
+    if: github.event_name != 'workflow_dispatch'
     runs-on: ubuntu-latest
     permissions:
       pull-requests: write
@@ -80,3 +87,88 @@ jobs:
             });
 
             console.log(`PR #${pullRequest.number}: ${totalChangedLines} changed lines → ${targetSizeLabel}`);
+
+  backfill:
+    if: github.event_name == 'workflow_dispatch'
+    runs-on: ubuntu-latest
+    permissions:
+      pull-requests: write
+      issues: write
+
+    steps:
+      - name: Backfill size labels on open PRs
+        uses: actions/github-script@v8
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            const { owner, repo } = context.repo;
+            const maxItems = parseInt('${{ inputs.max_items }}') || 100;
+
+            const sizeLabels = ['size: XS', 'size: S', 'size: M', 'size: L', 'size: XL'];
+            const labelColor = 'b76e79';
+
+            // Ensure labels exist
+            for (const name of sizeLabels) {
+              try {
+                await github.rest.issues.getLabel({ owner, repo, name });
+              } catch (error) {
+                if (error?.status !== 404) throw error;
+                await github.rest.issues.createLabel({
+                  owner, repo, name, color: labelColor,
+                });
+                console.log(`Created label: ${name}`);
+              }
+            }
+
+            function getSizeLabel(totalChangedLines) {
+              if (totalChangedLines < 50) return 'size: XS';
+              if (totalChangedLines < 200) return 'size: S';
+              if (totalChangedLines < 500) return 'size: M';
+              if (totalChangedLines < 1000) return 'size: L';
+              return 'size: XL';
+            }
+
+            const prs = await github.paginate(github.rest.pulls.list, {
+              owner, repo, state: 'open', per_page: 100,
+            });
+
+            let processed = 0;
+            for (const pr of prs) {
+              if (processed >= maxItems) break;
+
+              const files = await github.paginate(github.rest.pulls.listFiles, {
+                owner, repo, pull_number: pr.number, per_page: 100,
+              });
+
+              const excludedFiles = new Set(['poetry.lock', 'uv.lock']);
+              const totalChangedLines = files.reduce((total, file) => {
+                const path = file.filename ?? '';
+                if (path.startsWith('docs/') || excludedFiles.has(path)) return total;
+                return total + (file.additions ?? 0) + (file.deletions ?? 0);
+              }, 0);
+
+              const targetSizeLabel = getSizeLabel(totalChangedLines);
+
+              // Remove stale size labels
+              const currentLabels = await github.paginate(
+                github.rest.issues.listLabelsOnIssue,
+                { owner, repo, issue_number: pr.number, per_page: 100 },
+              );
+              for (const label of currentLabels) {
+                const name = label.name ?? '';
+                if (sizeLabels.includes(name) && name !== targetSizeLabel) {
+                  await github.rest.issues.removeLabel({
+                    owner, repo, issue_number: pr.number, name,
+                  });
+                }
+              }
+
+              await github.rest.issues.addLabels({
+                owner, repo, issue_number: pr.number, labels: [targetSizeLabel],
+              });
+
+              console.log(`PR #${pr.number}: ${totalChangedLines} changed lines → ${targetSizeLabel}`);
+              processed++;
+            }
+
+            console.log(`\nBackfill complete. Processed ${processed} PRs.`);

.github/workflows/require_issue_link.yml

@@ -0,0 +1,120 @@
+# Require external PRs to link to an approved issue or discussion using
+# GitHub auto-close keywords (Fixes #NNN, Closes #NNN, Resolves #NNN).
+#
+# - Reacts to the "external" label applied by tag-external-contributions.yml,
+#   avoiding a duplicate org membership check.
+# - Also re-checks on PR edits/reopens for PRs that already have the label.
+# - Adds a "missing-issue-link" label on failure; removes it on pass.
+# - Posts a comment explaining the requirement on failure.
+# - Deduplicates comments via an HTML marker so re-runs don't spam.
+#
+# Dependency: tag-external-contributions.yml must run first to apply the
+# "external" label on new PRs. Both workflows trigger on pull_request_target
+# opened events; this workflow additionally listens for the "labeled" event
+# to chain off the external classification.
+
+name: Require Issue Link
+
+on:
+  pull_request_target:
+    types: [opened, edited, reopened, labeled]
+
+permissions:
+  contents: read
+
+jobs:
+  check-issue-link:
+    # Run when the "external" label is added, or on edit/reopen if already labeled
+    if: >-
+      (github.event.action == 'labeled' && github.event.label.name == 'external') ||
+      (github.event.action != 'labeled' && contains(github.event.pull_request.labels.*.name, 'external'))
+    runs-on: ubuntu-latest
+    permissions:
+      pull-requests: write
+
+    steps:
+      - name: Check for issue link
+        id: check-link
+        uses: actions/github-script@v8
+        with:
+          script: |
+            const body = context.payload.pull_request.body || '';
+            const pattern = /(?:close[sd]?|fix(?:e[sd])?|resolve[sd]?)\s*#(\d+)/gi;
+            const matches = [...body.matchAll(pattern)];
+
+            if (matches.length > 0) {
+              const issues = matches.map(m => `#${m[1]}`).join(', ');
+              console.log(`Found issue link(s): ${issues}`);
+              core.setOutput('has-link', 'true');
+            } else {
+              console.log('No issue link found in PR body');
+              core.setOutput('has-link', 'false');
+            }
+
+      - name: Add missing-issue-link label
+        if: steps.check-link.outputs.has-link != 'true'
+        uses: actions/github-script@v8
+        with:
+          script: |
+            const { owner, repo } = context.repo;
+            const prNumber = context.payload.pull_request.number;
+            await github.rest.issues.addLabels({
+              owner, repo, issue_number: prNumber, labels: ['missing-issue-link'],
+            });
+
+      - name: Remove missing-issue-link label
+        if: steps.check-link.outputs.has-link == 'true'
+        uses: actions/github-script@v8
+        with:
+          script: |
+            const { owner, repo } = context.repo;
+            const prNumber = context.payload.pull_request.number;
+            try {
+              await github.rest.issues.removeLabel({
+                owner, repo, issue_number: prNumber, name: 'missing-issue-link',
+              });
+            } catch (error) {
+              if (error.status !== 404) throw error;
+            }
+
+      - name: Post comment and fail
+        if: steps.check-link.outputs.has-link != 'true'
+        uses: actions/github-script@v8
+        with:
+          script: |
+            const { owner, repo } = context.repo;
+            const prNumber = context.payload.pull_request.number;
+            const marker = '<!-- require-issue-link -->';
+
+            const body = [
+              marker,
+              '**This PR is missing a linked issue.** All external contributions must reference an approved issue or discussion.',
+              '',
+              'Please add one of the following to your PR description:',
+              '- `Fixes #<issue_number>`',
+              '- `Closes #<issue_number>`',
+              '- `Resolves #<issue_number>`',
+              '',
+              'If no issue exists yet, [open one](https://github.com/' + owner + '/' + repo + '/issues/new/choose) and wait for maintainer approval before proceeding.',
+            ].join('\n');
+
+            // Deduplicate: check for existing comment with the marker
+            const comments = await github.paginate(
+              github.rest.issues.listComments,
+              { owner, repo, issue_number: prNumber, per_page: 100 },
+            );
+            const existing = comments.find(c => c.body && c.body.includes(marker));
+
+            if (!existing) {
+              await github.rest.issues.createComment({
+                owner,
+                repo,
+                issue_number: prNumber,
+                body,
+              });
+              console.log('Posted issue-link requirement comment');
+            } else {
+              console.log('Comment already exists — skipping');
+            }
+
+            core.setFailed('PR must reference an issue using auto-close keywords (e.g., "Fixes #123").');

.github/workflows/tag-external-contributions.yml

@@ -187,7 +187,7 @@ jobs:
             const TRUSTED_THRESHOLD = 4;
             const EXPERIENCED_THRESHOLD = 10;
 
-            const mergedQuery = `repo:${owner}/${repo} is:pr is:merged author:${author}`;
+            const mergedQuery = `repo:${owner}/${repo} is:pr is:merged author:"${author}"`;
             let mergedCount = 0;
             try {
               const result = await github.rest.search.issuesAndPullRequests({
@@ -287,7 +287,7 @@ jobs:
               if (isExternal) {
                 try {
                   const result = await github.rest.search.issuesAndPullRequests({
-                    q: `repo:${owner}/${repo} is:pr is:merged author:${author}`,
+                    q: `repo:${owner}/${repo} is:pr is:merged author:"${author}"`,
                     per_page: 1,
                   });
                   mergedCount = result?.data?.total_count ?? 0;