Merge branch 'main' into main

Author: gouthamyoyo112-crypto

.devcontainer/Dockerfile

@@ -1,5 +1,3 @@
 # To find available Node images, see https://mcr.microsoft.com/en-us/product/devcontainers/javascript-node/tags
-
-# [Choice] Node.js version
-ARG VARIANT="dev-24-bullseye"
-FROM mcr.microsoft.com/devcontainers/javascript-node:${VARIANT}
+ARG VARIANT=dev-24-bullseye
+FROM mcr.microsoft.com/devcontainers/javascript-node:dev-24-bullseye@sha256:3502f1f21b1989500e8c72ada7d6e496dc4540b0707d4ea4ff743077f88a6c2d

.github/actions/labeler/labeler.ts

@@ -1,6 +1,6 @@
 /* See function main in this file for documentation */
 
-import coreLib from '@actions/core'
+import * as coreLib from '@actions/core'
 import { type Octokit } from '@octokit/rest'
 import { CoreInject } from '@/links/scripts/action-injections'
 

.github/instructions/all.instructions.md

@@ -12,9 +12,9 @@ When you create a pull request:
 
 1. **Always** make the first line of the PR description the following (in italics):
 
-   `_Copilot Chat generated this pull request._`
+   `_GitHub Copilot generated this pull request._`
 
-2. Optionally, you may include a collapsed section summarizing the prompt or discussion with Copilot Chat:
+2. Optionally, you may include a collapsed section summarizing the prompt or discussion with Copilot:
 
    ```markdown
    <details><summary>Prompt summary - submitted by @GITHUB-USER-ID</summary>
@@ -29,4 +29,4 @@ When you create a pull request:
 3. Label with "llm-generated". 
 4. If an issue exists, include "fixes owner/repo#issue" or "towards owner/repo#issue" as appropriate. 
 5. Always create PRs in **draft mode** using `--draft` flag.
-6. Always _escape backticks_ when you use gh cli.
+6. When you are using gh cli, always _escape backticks_.

.github/instructions/code.instructions.md

@@ -9,10 +9,10 @@ For code reviews, follow guidelines, tests, and validate instructions. For creat
 ## Guidelines
 
 - If available, use ripgrep (`rg`) instead of `grep`.
-- Make sure to always _escape backticks_ when using gh cli.
+- When using gh cli, always _escape backticks_.
 - All scripts should be listed in `package.json` and use `tsx`.
-- Whenever you create or comment on an issue or pull request, indicate you are an LLM.
-- Be careful fetching full HTML pages off the internet. Prefer to use gh cli whenever possible for github.com. Limit the number of tokens when grabbing HTML.
+- Whenever you create or comment on an issue or pull request, indicate you are GitHub Copilot.
+- Be careful fetching full HTML pages off the internet. Prefer to use MCP or gh cli whenever possible for github.com. Limit the number of tokens when grabbing HTML.
 - Avoid pull requests with over 300 lines of code changed. When significantly larger, offer to split up into smaller pull requests if possible.
 - All new code should be written in TypeScript and not JavaScript.
 - We use absolute imports, relative to the `src` directory, using the `@` symbol. For example, `getRedirect` which lives in `src/redirects/lib/get-redirect.ts` can be imported with `import getRedirect from '@/redirects/lib/get-redirect'`. The same rule applies for TypeScript (`.ts`) imports, e.g. `import type { GeneralSearchHit } from '@/search/types'`
@@ -43,7 +43,7 @@ Run the following commands to validate your changes:
 
 0. Ask the human if they would like you to follow these steps.
 1. If this is new work, make sure you have the latest changes by running `git checkout main && git pull`. If this is existing work, update the branch you are working on with the head branch -- usually `main`.
-2. If the human provides a GitHub issue, use gh cli to read the issue and all comments.
+2. If the human provides a GitHub issue, use MCP or gh cli to read the issue and all comments.
 3. Begin by evaluating impact, effort, and estimate non-test lines of code that will change. Ask for more context and examples if needed.
 4. If you are running in agentic mode, _stop_ at this point and request approval from the human.
 5. If you need to add or change tests, work on tests before implementing.
@@ -52,7 +52,7 @@ Run the following commands to validate your changes:
 8. Validate that any new or changed tests pass. See "Tests".
 9. Validate that these changes meet our guidelines. See "Guidelines".
 10. If you are running in agentic mode, _stop_ at this point and request review before continuing. Suggest how the human should review the changes.
-11. If a branch and pull request already exist, commit and push, then _concisely_ comment on the pull request that you are an LLM and what changes you made and why. 
+11. If a branch and pull request already exist, commit and push, then _concisely_ comment on the pull request that you are GitHub Copilot and what changes you made and why. 
 12. If this is new work and no pull request exists yet, make a pull request:
     - label "llm-generated"
     - draft mode
@@ -61,4 +61,4 @@ Run the following commands to validate your changes:
 14. If you are in agentic mode, offer to do any or all of:
     - mark the pull request as ready,
     - assign the issue to the human if it is not already assigned, 
-    - _concisely_ comment on the issue explaining the change, indicating you are an LLM.
+    - _concisely_ comment on the issue explaining the change, indicating you are GitHub Copilot.

.github/workflows/check-broken-links-github-github.yml

@@ -44,10 +44,9 @@ jobs:
           PORT: 4000
           ENABLED_LANGUAGES: en
         run: |
-
-          npm run start &
+          npm run start-for-ci &
           sleep 5
-          curl --retry-connrefused --retry 3 -I http://localhost:4000/
+          curl --retry-connrefused --retry 5 -I http://localhost:4000/
 
       - name: Run broken github/github link check
         run: |

.github/workflows/index-general-search.yml

@@ -26,9 +26,11 @@ on:
 permissions:
   contents: read
 
-# This allows a subsequently queued workflow run to cancel previous runs
+# This allows a subsequently queued workflow run to cancel previous runs.
+# Include the triggering workflow's conclusion in the group so that runs triggered
+# by skipped Purge Fastly workflows don't cancel runs triggered by successful ones.
 concurrency:
-  group: '${{ github.workflow }} @ ${{ github.head_ref }} ${{ github.event_name }}'
+  group: '${{ github.workflow }} @ ${{ github.head_ref }} ${{ github.event_name }} ${{ github.event.workflow_run.conclusion }}'
   cancel-in-progress: true
 
 env:
@@ -40,7 +42,9 @@ env:
 
 jobs:
   figureOutMatrix:
-    if: ${{ github.repository == 'github/docs-internal' }}
+    # Skip immediately if triggered by a non-successful Purge Fastly run.
+    # This prevents skipped runs from canceling valid indexing runs via concurrency.
+    if: ${{ github.repository == 'github/docs-internal' && (github.event_name != 'workflow_run' || github.event.workflow_run.conclusion == 'success') }}
     runs-on: ubuntu-latest
     outputs:
       matrix: ${{ steps.set-matrix.outputs.result }}
@@ -55,11 +59,13 @@ jobs:
             const allPossible = ["en", ...allNonEnglish]
 
             if (context.eventName === "workflow_run") {
+              // Job-level `if` already ensures we only get here for successful runs,
+              // but keep this as a safety check.
               if (context.payload.workflow_run.conclusion === "success") {
                 return ["en"]
               }
-              console.warn(`NOTE! It was a workflow_run but not success ('${context.payload.workflow_run.conclusion}')`)
-              console.warn("This means we're not going to index anything in the next dependent step.")
+              // This shouldn't happen due to job-level filter, but handle gracefully.
+              console.warn(`Unexpected: workflow_run with conclusion '${context.payload.workflow_run.conclusion}'`)
               return []
             }
 
@@ -224,21 +230,64 @@ jobs:
           FASTLY_SURROGATE_KEY: api-search:${{ matrix.language }}
         run: npm run purge-fastly-edge-cache
 
-      - name: Alert on scraping failures
-        if: ${{ steps.check-failures.outputs.has_failures == 'true' && github.event_name != 'workflow_dispatch' }}
-        uses: ./.github/actions/slack-alert
+      - name: Upload failures artifact
+        if: ${{ steps.check-failures.outputs.has_failures == 'true' }}
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
+        with:
+          name: search-failures-${{ matrix.language }}
+          path: /tmp/records/failures-summary.json
+          retention-days: 1
+
+      - uses: ./.github/actions/slack-alert
+        if: ${{ failure() && github.event_name != 'workflow_dispatch' }}
         with:
           slack_channel_id: ${{ secrets.DOCS_ALERTS_SLACK_CHANNEL_ID }}
           slack_token: ${{ secrets.SLACK_DOCS_BOT_TOKEN }}
-          message: |
-            :warning: ${{ steps.check-failures.outputs.failed_pages }} page(s) failed to scrape for general search indexing (language: ${{ matrix.language }})
 
-            The indexing completed but some pages could not be scraped. This may affect search results for those pages.
+  notifyScrapingFailures:
+    name: Notify scraping failures
+    needs: updateElasticsearchIndexes
+    if: ${{ always() && github.repository == 'github/docs-internal' && github.event_name != 'workflow_dispatch' && needs.updateElasticsearchIndexes.result != 'cancelled' }}
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out repo
+        uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
+
+      - name: Download all failure artifacts
+        uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
+        with:
+          pattern: search-failures-*
+          path: /tmp/failures
+        continue-on-error: true
 
-            Workflow: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
+      - name: Check if any failures were downloaded
+        id: check-artifacts
+        run: |
+          if [ -d /tmp/failures ] && [ "$(ls -A /tmp/failures 2>/dev/null)" ]; then
+            echo "has_artifacts=true" >> $GITHUB_OUTPUT
+          else
+            echo "has_artifacts=false" >> $GITHUB_OUTPUT
+          fi
 
-      - uses: ./.github/actions/slack-alert
-        if: ${{ failure() && github.event_name != 'workflow_dispatch' }}
+      - uses: ./.github/actions/node-npm-setup
+        if: ${{ steps.check-artifacts.outputs.has_artifacts == 'true' }}
+
+      - name: Aggregate failures and format message
+        if: ${{ steps.check-artifacts.outputs.has_artifacts == 'true' }}
+        id: aggregate
+        run: |
+          RESULT=$(npx tsx src/search/scripts/aggregate-search-index-failures.ts /tmp/failures \
+            --workflow-url "${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}")
+          {
+            echo 'result<<EOF'
+            echo "$RESULT"
+            echo 'EOF'
+          } >> "$GITHUB_OUTPUT"
+
+      - name: Send consolidated Slack notification
+        if: ${{ steps.check-artifacts.outputs.has_artifacts == 'true' }}
+        uses: ./.github/actions/slack-alert
         with:
           slack_channel_id: ${{ secrets.DOCS_ALERTS_SLACK_CHANNEL_ID }}
           slack_token: ${{ secrets.SLACK_DOCS_BOT_TOKEN }}
+          message: ${{ fromJSON(steps.aggregate.outputs.result).message }}

.github/workflows/link-check-daily.yml

@@ -0,0 +1,78 @@
+name: Check External Links
+
+# Runs weekly (Wednesday) at 16:20 UTC
+# Validates external URLs in content files
+
+on:
+  schedule:
+    - cron: '20 16 * * 3' # Wednesday at 16:20 UTC
+  workflow_dispatch:
+    inputs:
+      max_urls:
+        description: 'Maximum number of URLs to check (leave blank for all)'
+        type: number
+
+permissions:
+  contents: read
+  issues: write
+
+jobs:
+  check-external-links:
+    if: github.repository == 'github/docs-internal'
+    runs-on: ubuntu-latest
+    timeout-minutes: 180 # 3 hours for external checks
+    steps:
+      - name: Checkout
+        uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
+
+      - uses: ./.github/actions/node-npm-setup
+
+      - name: Install dependencies
+        run: npm ci
+
+      - name: Check external links
+        env:
+          ACTION_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
+          CACHE_MAX_AGE_DAYS: '7'
+        run: |
+          if [[ -n "${{ inputs.max_urls }}" ]]; then
+            npm run check-links-external -- --max ${{ inputs.max_urls }}
+          else
+            npm run check-links-external
+          fi
+
+      - name: Upload report artifact
+        if: always()
+        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6.0.0
+        with:
+          name: external-link-report
+          path: artifacts/external-link-report.*
+          retention-days: 14
+          if-no-files-found: ignore
+
+      - name: Check if report exists
+        if: always()
+        id: check_report
+        run: |
+          if [ -f "artifacts/external-link-report.md" ]; then
+            echo "has_report=true" >> $GITHUB_OUTPUT
+          else
+            echo "has_report=false" >> $GITHUB_OUTPUT
+            echo "No broken link report generated - all links valid!"
+          fi
+
+      - name: Create issue if broken links found
+        if: always() && steps.check_report.outputs.has_report == 'true'
+        uses: peter-evans/create-issue-from-file@fca9117c27cdc29c6c4db3b86c48e4115a786710 # v5
+        with:
+          token: ${{ secrets.DOCS_BOT_PAT_BASE }}
+          repository: github/docs-content
+          title: '🌐 Broken External Links Report'
+          content-filepath: artifacts/external-link-report.md
+          labels: broken link report
+
+      - uses: ./.github/actions/slack-alert
+        if: ${{ failure() && github.event_name != 'workflow_dispatch' }}
+        with:
+          slack_channel_id: ${{ secrets.DOCS_ALERTS_SLACK_CHANNEL_ID }}
+          slack_token: ${{ secrets.SLACK_DOCS_BOT_TOKEN }}