Merge 4bd535976f into 0c366fd6a8

__test__/git-source-provider-reference-cache.test.ts

@@ -0,0 +1,182 @@
+import * as path from 'path'
+
+const mockStartGroup = jest.fn()
+const mockEndGroup = jest.fn()
+const mockInfo = jest.fn()
+const mockWarning = jest.fn()
+const mockSetOutput = jest.fn()
+const mockSetSecret = jest.fn()
+
+const mockCreateCommandManager = jest.fn()
+const mockCreateAuthHelper = jest.fn()
+const mockPrepareExistingDirectory = jest.fn()
+const mockGetFetchUrl = jest.fn()
+const mockGetRefSpec = jest.fn()
+const mockTestRef = jest.fn()
+const mockGetCheckoutInfo = jest.fn()
+const mockCheckCommitInfo = jest.fn()
+const mockSetRepositoryPath = jest.fn()
+const mockSetupCache = jest.fn()
+const mockDirectoryExistsSync = jest.fn()
+const mockFileExistsSync = jest.fn()
+
+jest.mock('@actions/core', () => ({
+  startGroup: mockStartGroup,
+  endGroup: mockEndGroup,
+  info: mockInfo,
+  warning: mockWarning,
+  setOutput: mockSetOutput,
+  setSecret: mockSetSecret
+}))
+
+jest.mock('@actions/io', () => ({
+  rmRF: jest.fn(),
+  mkdirP: jest.fn()
+}))
+
+jest.mock('../src/fs-helper', () => ({
+  directoryExistsSync: mockDirectoryExistsSync,
+  fileExistsSync: mockFileExistsSync
+}))
+
+jest.mock('../src/git-command-manager', () => ({
+  MinimumGitSparseCheckoutVersion: {},
+  createCommandManager: mockCreateCommandManager
+}))
+
+jest.mock('../src/git-auth-helper', () => ({
+  createAuthHelper: mockCreateAuthHelper
+}))
+
+jest.mock('../src/git-directory-helper', () => ({
+  prepareExistingDirectory: mockPrepareExistingDirectory
+}))
+
+jest.mock('../src/github-api-helper', () => ({
+  downloadRepository: jest.fn(),
+  getDefaultBranch: jest.fn()
+}))
+
+jest.mock('../src/ref-helper', () => ({
+  getRefSpec: mockGetRefSpec,
+  getCheckoutInfo: mockGetCheckoutInfo,
+  testRef: mockTestRef,
+  checkCommitInfo: mockCheckCommitInfo
+}))
+
+jest.mock('../src/state-helper', () => ({
+  setRepositoryPath: mockSetRepositoryPath
+}))
+
+jest.mock('../src/url-helper', () => ({
+  getFetchUrl: mockGetFetchUrl
+}))
+
+jest.mock('../src/git-cache-helper', () => ({
+  GitCacheHelper: jest.fn().mockImplementation(() => ({
+    setupCache: mockSetupCache
+  }))
+}))
+
+import {getSource} from '../src/git-source-provider'
+
+describe('getSource reference cache regression', () => {
+  beforeEach(() => {
+    jest.clearAllMocks()
+  })
+
+  it('updates the reference cache and reconfigures alternates for existing repositories', async () => {
+    const repositoryPath = '/tmp/work/repo'
+    const repositoryUrl = 'https://github.com/actions/checkout'
+    const cachePath = '/tmp/reference-cache/actions-checkout.git'
+
+    const mockGit = {
+      init: jest.fn(),
+      remoteAdd: jest.fn(),
+      referenceAdd: jest.fn().mockResolvedValue(undefined),
+      tryDisableAutomaticGarbageCollection: jest.fn().mockResolvedValue(true),
+      fetch: jest.fn().mockResolvedValue(undefined),
+      version: jest.fn().mockResolvedValue({
+        checkMinimum: jest.fn().mockReturnValue(true)
+      }),
+      disableSparseCheckout: jest.fn().mockResolvedValue(undefined),
+      checkout: jest.fn().mockResolvedValue(undefined),
+      log1: jest
+        .fn()
+        .mockResolvedValueOnce('commit info')
+        .mockResolvedValueOnce('0123456789abcdef'),
+      lfsInstall: jest.fn(),
+      submoduleSync: jest.fn(),
+      submoduleUpdate: jest.fn(),
+      submoduleForeach: jest.fn(),
+      config: jest.fn()
+    }
+
+    const mockAuthHelper = {
+      configureAuth: jest.fn().mockResolvedValue(undefined),
+      configureGlobalAuth: jest.fn().mockResolvedValue(undefined),
+      configureSubmoduleAuth: jest.fn().mockResolvedValue(undefined),
+      configureTempGlobalConfig: jest.fn().mockResolvedValue('/tmp/gitconfig'),
+      removeAuth: jest.fn().mockResolvedValue(undefined),
+      removeGlobalAuth: jest.fn().mockResolvedValue(undefined),
+      removeGlobalConfig: jest.fn().mockResolvedValue(undefined)
+    }
+
+    mockCreateCommandManager.mockResolvedValue(mockGit)
+    mockCreateAuthHelper.mockReturnValue(mockAuthHelper)
+    mockPrepareExistingDirectory.mockResolvedValue(undefined)
+    mockGetFetchUrl.mockReturnValue(repositoryUrl)
+    mockGetRefSpec.mockReturnValue(['+refs/heads/main:refs/remotes/origin/main'])
+    mockTestRef.mockResolvedValue(true)
+    mockGetCheckoutInfo.mockResolvedValue({
+      ref: 'refs/heads/main',
+      startPoint: 'refs/remotes/origin/main'
+    })
+    mockCheckCommitInfo.mockResolvedValue(undefined)
+    mockSetupCache.mockResolvedValue(cachePath)
+    mockFileExistsSync.mockReturnValue(false)
+    mockDirectoryExistsSync.mockImplementation((targetPath: string) => {
+      return (
+        targetPath === repositoryPath ||
+        targetPath === path.join(repositoryPath, '.git') ||
+        targetPath === path.join(cachePath, 'objects')
+      )
+    })
+
+    await getSource({
+      repositoryPath,
+      repositoryOwner: 'actions',
+      repositoryName: 'checkout',
+      ref: 'refs/heads/main',
+      commit: '0123456789abcdef',
+      clean: false,
+      filter: undefined,
+      sparseCheckout: undefined as any,
+      sparseCheckoutConeMode: false,
+      fetchDepth: 1,
+      fetchDepthExplicit: true,
+      fetchTags: false,
+      showProgress: false,
+      referenceCache: '/tmp/reference-cache',
+      lfs: false,
+      submodules: false,
+      nestedSubmodules: false,
+      authToken: 'token',
+      sshKey: '',
+      sshKnownHosts: '',
+      sshStrict: true,
+      sshUser: 'git',
+      persistCredentials: false,
+      workflowOrganizationId: undefined,
+      githubServerUrl: 'https://github.com',
+      setSafeDirectory: false
+    } as any)
+
+    expect(mockGit.init).not.toHaveBeenCalled()
+    expect(mockGit.remoteAdd).not.toHaveBeenCalled()
+    expect(mockSetupCache).toHaveBeenCalledWith(mockGit, repositoryUrl)
+    expect(mockGit.referenceAdd).toHaveBeenCalledWith(
+      path.join(cachePath, 'objects')
+    )
+  })
+})

__test__/git-source-provider.test.ts

@@ -1,5 +1,10 @@
 import * as core from '@actions/core'
-import {adjustFetchDepthForCache} from '../src/git-source-provider'
+import * as fsHelper from '../src/fs-helper'
+import {GitCacheHelper} from '../src/git-cache-helper'
+import {
+  adjustFetchDepthForCache,
+  setupReferenceCache
+} from '../src/git-source-provider'
 
 // Mock @actions/core
 jest.mock('@actions/core')
@@ -86,3 +91,73 @@ describe('adjustFetchDepthForCache', () => {
     )
   })
 })
+
+describe('setupReferenceCache', () => {
+  beforeEach(() => {
+    jest.clearAllMocks()
+  })
+
+  afterEach(() => {
+    jest.restoreAllMocks()
+  })
+
+  it('does nothing when referenceCache is not set', async () => {
+    const git = {
+      referenceAdd: jest.fn()
+    } as any
+
+    await setupReferenceCache(git, '', 'https://github.com/actions/checkout.git')
+
+    expect(git.referenceAdd).not.toHaveBeenCalled()
+    expect(core.startGroup).not.toHaveBeenCalled()
+  })
+
+  it('updates the cache and configures alternates when cache objects exist', async () => {
+    const git = {
+      referenceAdd: jest.fn().mockResolvedValue(undefined)
+    } as any
+    const setupCacheSpy = jest
+      .spyOn(GitCacheHelper.prototype, 'setupCache')
+      .mockResolvedValue('/tmp/reference-cache/repo.git')
+    jest
+      .spyOn(fsHelper, 'directoryExistsSync')
+      .mockReturnValue(true)
+
+    await setupReferenceCache(
+      git,
+      '/tmp/reference-cache',
+      'https://github.com/actions/checkout.git'
+    )
+
+    expect(setupCacheSpy).toHaveBeenCalledWith(
+      git,
+      'https://github.com/actions/checkout.git'
+    )
+    expect(git.referenceAdd).toHaveBeenCalledWith(
+      '/tmp/reference-cache/repo.git/objects'
+    )
+  })
+
+  it('warns when the cache objects directory is missing', async () => {
+    const git = {
+      referenceAdd: jest.fn().mockResolvedValue(undefined)
+    } as any
+    jest
+      .spyOn(GitCacheHelper.prototype, 'setupCache')
+      .mockResolvedValue('/tmp/reference-cache/repo.git')
+    jest
+      .spyOn(fsHelper, 'directoryExistsSync')
+      .mockReturnValue(false)
+
+    await setupReferenceCache(
+      git,
+      '/tmp/reference-cache',
+      'https://github.com/actions/checkout.git'
+    )
+
+    expect(git.referenceAdd).not.toHaveBeenCalled()
+    expect(core.warning).toHaveBeenCalledWith(
+      'Reference repository cache objects directory /tmp/reference-cache/repo.git/objects does not exist'
+    )
+  })
+})

adrs/2303-reference-cache.md

@@ -1,37 +1,127 @@
-# Reference Cache für schnelle Checkouts
+# ADR 2303: Reference cache for faster checkouts
 
-## Zusammenfassung
-Einführung eines lokal verwalteten Git-Referenz-Caches für Haupt-Repositories und Submodule, um Netzwerk-Traffic und Checkout-Zeiten auf persistenten Runnern (z.B. Self-Hosted) massiv zu reduzieren.
+**Date**: 2026-03-10
 
-## Implementierungsplan
+**Status**: Proposed
 
-1. **Inputs:**
-   - In `action.yml` einen neuen Input `reference-cache` (Pfad zum Cache-Verzeichnis) hinzufügen. Default ist leer.
-   - In `src/git-source-settings.ts` und `src/input-helper.ts` den Input auslesen und bereitstellen (`settings.referenceCache`).
+## Context
 
-2. **Cache Manager (`src/git-cache-helper.ts`):**
-   - Eine neue Klasse/Helper-Logik, die das Erstellen (`git clone --bare`) und Aktualisieren (`git fetch --force`) von Bare Cache-Repos übernimmt.
-   - **Namenskonvention Cache-Verzeichnis:** Damit Admin-Lesbarkeit und Kollisionsfreiheit gewährleistet sind, wird das Cache-Verzeichnis aus der Repository-URL gebildet:
-     - Alle Sonderzeichen in der URL durch `_` ersetzen.
-     - Ein kurzer Hash (z. B. erste 8 Zeichen des SHA256) der echten URL zur Eindeutigkeit anhängen.
-     - Beispiel: `<reference-cache>/https___github_com_actions_checkout_8f9b1c2a.git`
+Repeated checkouts of the same repositories are expensive on runners with persistent storage.
+This is especially noticeable for self-hosted runners and custom runner images that execute
+many jobs against the same repositories and submodules.
 
-3. **Haupt-Repo Checkout (`src/git-source-provider.ts`):**
-   - Vor dem Setup des Checkouts prüfen, ob `reference-cache` gesetzt ist.
-   - Wenn ja: den Cache-Ordner für die Haupt-URL aktualisieren/anlegen.
-   - Nach dem initialen `git.init()` den Pfad in `.git/objects/info/alternates` schreiben, der auf das `objects`-Verzeichnis des Cache-Ordners zeigt.
+Today, each checkout fetches objects from the remote even when the runner already has most of
+the repository history available locally from previous jobs. This increases network traffic,
+slows down checkout time, and makes recursive submodule initialization more expensive than
+necessary.
 
-4. **Submodule Checkouts (Iterativ statt monolithisch):**
-   - Der aktuelle Befehl `git submodule update --recursive` funktioniert nicht out-of-the-box mit `reference`, wenn jedes Submodul seinen individuellen Referenz-Cache benötigt.
-   - Wenn `reference-cache` aktiv ist und Submodule initialisiert werden sollen:
-     - Lese `.gitmodules` aus (alle Sub-URLs ermitteln).
-     - Für jedes Submodul den Cache (genauso wie in Step 2) anlegen oder aktualisieren.
-     - Submodul einzeln auschecken per `git submodule update --init --reference <cache-pfad/.git> <pfad>`.
-     - Bei der Einstellung `recursive`: In jedes Submodul-Verzeichnis wechseln und den Vorgang für `.gitmodules` rekursiv auf Skript-Ebene durchführen (anstatt Git's `--recursive` Flag einfach weiterzugeben).
+Git supports reference repositories and alternates, which allow one working repository to reuse
+objects from another local repository. This mechanism is a good fit for persistent runners,
+provided the cache is managed safely and works for both the main repository and submodules.
 
-## Akzeptanzkriterien
-1. **Neue Option konfigurierbar**: Der Input `reference-cache` kann übergeben werden, der Code reagiert darauf.
-2. **Ordnerstruktur korrekt**: Der Cache-Ordner für das Hauptrepo und Submodule erhält Namen nach der "URL_Sonderzeichen_Ersetzt+SHA_Cut"-Logik.
-3. **Bandbreite gespart / Alternates genutzt**: Beim Hauptcheckout wird eine `.git/objects/info/alternates`-Datei mit Pfad zum lokalen Cache erzeugt. Danach ausgeführte `git fetch`-Befehle sind signifikant schneller bzw. laden deutlich weniger Bytes herunter.
-4. **Submodule erhalten Caches**: Auch tiefe (rekursive) Submodule profitieren für deren jeweilige Remote-URL vom Cache, da pro Submodul ein passender `--reference` Punkt dynamisch berechnet und übergeben wird.
-5. **Kein --dissociate**: Aus Performance-Gründen bleibt der Arbeitsordner an den Cache gebunden (`git repack` ist zeitaufwändig). Fällt der Cache weg, muss der Workspace erst einmal neu erzeugt werden (was bei Action Runnern die Norm ist, falls es nicht ohnehin "single-use" Runner sind).
+## Decision
+
+Add an optional `reference-cache` input that points to a local directory used to store managed
+bare repositories for the primary repository and its submodules.
+
+### Input
+
+Add a new input in `action.yml`:
+
+```yaml
+  reference-cache:
+    description: >
+      Path to a local directory used as a reference cache for Git clones.
+```
+
+The value is exposed through `settings.referenceCache`.
+
+### Cache layout
+
+Each cached repository is stored as a bare repository inside the configured cache directory.
+
+The cache directory name is derived from the repository URL by:
+
+- replacing non-alphanumeric characters with `_`
+- appending a short SHA-256 hash of the original URL to avoid collisions
+
+Example:
+
+```text
+<reference-cache>/https___github_com_actions_checkout_8f9b1c2a.git
+```
+
+### Cache lifecycle
+
+Introduce helper logic in `src/git-cache-helper.ts` responsible for:
+
+- creating a bare cache repository with `git clone --bare`
+- updating an existing bare cache repository with `git fetch --force`
+- serializing access with file-based locking so concurrent jobs do not corrupt the cache
+- using a temporary clone-and-rename flow to avoid leaving behind partial repositories
+
+### Main repository checkout
+
+When `reference-cache` is configured:
+
+- prepare or update the cache for the main repository URL
+- configure the checkout repository to use the cache through Git alternates
+- keep the working repository attached to the cache instead of dissociating it
+
+This allows later fetch operations to reuse local objects instead of downloading them again.
+
+### Submodules
+
+When submodules are enabled together with `reference-cache`, submodules are processed one by one
+instead of relying solely on a monolithic `git submodule update --recursive` flow.
+
+For each submodule:
+
+- read the submodule URL from `.gitmodules`
+- resolve relative URLs where possible
+- create or update a dedicated cache for that submodule repository
+- run `git submodule update --init --reference <cache> <path>` for that submodule
+
+When recursive submodules are requested, repeat the same process inside each initialized submodule.
+
+### Fetch depth behavior
+
+When `reference-cache` is enabled, shallow fetches are usually counterproductive because object
+negotiation overhead can outweigh the benefit of a local object store.
+
+For that reason:
+
+- the default `fetch-depth` is overridden to `0` when `reference-cache` is enabled
+- if the user explicitly sets `fetch-depth`, keep the user-provided value and emit a warning
+
+### No `--dissociate`
+
+The checkout should remain connected to the reference cache.
+
+Using `--dissociate` would copy objects into the working repository and typically require extra
+repacking work, which reduces the performance benefit of the cache. If the cache is removed, the
+workspace is expected to be recreated, which is acceptable for the target runner scenarios.
+
+## Consequences
+
+### Positive
+
+- reduces network traffic for repeated checkouts on persistent runners
+- improves checkout performance for the main repository and submodules
+- reuses standard Git mechanisms instead of introducing a custom object store
+- keeps cache naming deterministic and readable for administrators
+
+### Trade-offs
+
+- adds cache management complexity, including locking and recovery from interrupted operations
+- submodule handling becomes more complex because each submodule may require its own cache
+- benefits are limited on ephemeral runners, where the cache is not reused across jobs
+- workspaces remain dependent on the presence of the cache until they are recreated
+
+## Acceptance criteria
+
+1. The `reference-cache` input can be configured and is exposed through the action settings.
+2. Cache directories for the main repository and submodules follow the sanitized-URL-plus-hash naming scheme.
+3. The main checkout uses Git alternates so later fetches can reuse local cached objects.
+4. Submodules, including recursive submodules, can use repository-specific caches.
+5. The checkout does not use `--dissociate` and remains attached to the cache for performance.

package.json

@@ -33,6 +33,7 @@
     "@actions/github": "^6.0.0",
     "@actions/io": "^1.1.3",
     "@actions/tool-cache": "^2.0.1",
+    "proper-lockfile": "^4.1.2",
     "uuid": "^9.0.1"
   },
   "devDependencies": {
@@ -50,7 +51,6 @@
     "jest-circus": "^29.7.0",
     "js-yaml": "^4.1.0",
     "prettier": "^3.3.3",
-    "proper-lockfile": "^4.1.2",
     "ts-jest": "^29.2.5",
     "typescript": "^5.5.4"
   }

src/git-cache-helper.ts

@@ -68,8 +68,8 @@ export class GitCacheHelper {
           await git.execGit(args)
           
           if (fs.existsSync(cachePath)) {
-             // In rare cases where it somehow exists but objects/ didn't, clean it up
-             await fs.promises.rm(cachePath, { recursive: true, force: true })
+            // In rare cases where it somehow exists but objects/ didn't, clean it up
+            await fs.promises.rm(cachePath, { recursive: true, force: true })
           }
           await fs.promises.rename(tmpPath, cachePath)
         } catch (cloneErr) {

src/git-source-provider.ts

@@ -23,7 +23,33 @@ interface SubmoduleInfo {
   url: string
 }
 
-async function iterativeSubmoduleUpdate(
+export async function setupReferenceCache(
+  git: IGitCommandManager,
+  referenceCache: string,
+  repositoryUrl: string
+): Promise<void> {
+  if (!referenceCache) {
+    return
+  }
+
+  core.startGroup('Setting up reference repository cache')
+  try {
+    const cacheHelper = new GitCacheHelper(referenceCache)
+    const cachePath = await cacheHelper.setupCache(git, repositoryUrl)
+    const cacheObjects = path.join(cachePath, 'objects')
+    if (fsHelper.directoryExistsSync(cacheObjects, false)) {
+      await git.referenceAdd(cacheObjects)
+    } else {
+      core.warning(
+        `Reference repository cache objects directory ${cacheObjects} does not exist`
+      )
+    }
+  } finally {
+    core.endGroup()
+  }
+}
+
+async function recursiveSubmoduleUpdate(
   git: IGitCommandManager,
   cacheHelper: GitCacheHelper,
   repositoryPath: string,
@@ -145,7 +171,7 @@ async function iterativeSubmoduleUpdate(
     // Recursive update inside the submodule
     if (nestedSubmodules) {
       const subRepoPath = path.join(repositoryPath, info.path)
-      await iterativeSubmoduleUpdate(
+      await recursiveSubmoduleUpdate(
         git,
         cacheHelper,
         subRepoPath,
@@ -276,22 +302,10 @@ export async function getSource(settings: IGitSourceSettings): Promise<void> {
       await git.init()
       await git.remoteAdd('origin', repositoryUrl)
       core.endGroup()
-
-      // Setup reference cache if requested
-      if (settings.referenceCache) {
-        core.startGroup('Setting up reference repository cache')
-        const cacheHelper = new GitCacheHelper(settings.referenceCache)
-        const cachePath = await cacheHelper.setupCache(git, repositoryUrl)
-        const cacheObjects = path.join(cachePath, 'objects')
-        if (fsHelper.directoryExistsSync(cacheObjects, false)) {
-          await git.referenceAdd(cacheObjects)
-        } else {
-          core.warning(`Reference repository cache objects directory ${cacheObjects} does not exist`)
-        }
-        core.endGroup()
-      }
     }
 
+    await setupReferenceCache(git, settings.referenceCache, repositoryUrl)
+
     // Remove global auth if it was set for reference cache,
     // to avoid duplicate AUTHORIZATION headers during fetch
     if (settings.referenceCache) {
@@ -451,9 +465,9 @@ export async function getSource(settings: IGitSourceSettings): Promise<void> {
       await git.submoduleSync(settings.nestedSubmodules)
       
       if (settings.referenceCache) {
-        core.info('Iterative submodule update using reference cache')
+        core.info('Recursive submodule update using reference cache')
         const cacheHelper = new GitCacheHelper(settings.referenceCache)
-        await iterativeSubmoduleUpdate(
+        await recursiveSubmoduleUpdate(
           git,
           cacheHelper,
           settings.repositoryPath,