Onboard the GitHub Action based Issue-Labeler (#61780)

* Import v2.0.0 issue-labeler default workflows

* issue-labeler workflow customization for dotnet/aspnetcore

* Add comments and doc for the issue-labeler workflows

.github/workflows/labeler-cache-retention.yml

@@ -0,0 +1,40 @@
+# Workflow template imported and updated from:
+# https://github.com/dotnet/issue-labeler/wiki/Onboarding
+#
+# See labeler.md for more information
+#
+# Regularly restore the prediction models from cache to prevent cache eviction
+name: "Labeler: Cache Retention"
+
+# For more information about GitHub's action cache limits and eviction policy, see:
+# https://docs.github.com/actions/writing-workflows/choosing-what-your-workflow-does/caching-dependencies-to-speed-up-workflows#usage-limits-and-eviction-policy
+
+on:
+  schedule:
+    - cron: "32 16 * * *" # 16:32 every day (arbitrary time daily)
+
+  workflow_dispatch:
+    inputs:
+      cache_key:
+        description: "The cache key suffix to use for restoring the model from cache. Defaults to 'ACTIVE'."
+        required: true
+        default: "ACTIVE"
+
+env:
+  CACHE_KEY: ${{ inputs.cache_key || 'ACTIVE' }}
+
+jobs:
+  restore-cache:
+    # Do not automatically run the workflow on forks outside the 'dotnet' org
+    if: ${{ github.event_name == 'workflow_dispatch' || github.repository_owner == 'dotnet' }}
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        type: ["issues", "pulls"]
+    steps:
+      - uses: dotnet/issue-labeler/restore@46125e85e6a568dc712f358c39f35317366f5eed # v2.0.0
+        with:
+          type: ${{ matrix.type }}
+          cache_key: ${{ env.CACHE_KEY }}
+          fail-on-cache-miss: true

.github/workflows/labeler-predict-issues.yml

@@ -0,0 +1,60 @@
+# Workflow template imported and updated from:
+# https://github.com/dotnet/issue-labeler/wiki/Onboarding
+#
+# See labeler.md for more information
+#
+# Predict labels for Issues using a trained model
+name: "Labeler: Predict (Issues)"
+
+on:
+  # Only automatically predict area labels when issues are first opened
+  issues:
+    types: opened
+
+  # Allow dispatching the workflow via the Actions UI, specifying ranges of numbers
+  workflow_dispatch:
+    inputs:
+      issues:
+        description: "Issue Numbers (comma-separated list of ranges)."
+        required: true
+      cache_key:
+        description: "The cache key suffix to use for restoring the model. Defaults to 'ACTIVE'."
+        required: true
+        default: "ACTIVE"
+
+env:
+  # Do not allow failure for jobs triggered automatically (as this causes red noise on the workflows list)
+  ALLOW_FAILURE: ${{ github.event_name == 'workflow_dispatch' }}
+
+  LABEL_PREFIX: "area-"
+  THRESHOLD: 0.40
+  DEFAULT_LABEL: "needs-area-label"
+
+jobs:
+  predict-issue-label:
+    # Do not automatically run the workflow on forks outside the 'dotnet' org
+    if: ${{ github.event_name == 'workflow_dispatch' || github.repository_owner == 'dotnet' }}
+    runs-on: ubuntu-latest
+    permissions:
+      issues: write
+    steps:
+      - name: "Restore issues model from cache"
+        id: restore-model
+        uses: dotnet/issue-labeler/restore@46125e85e6a568dc712f358c39f35317366f5eed # v2.0.0
+        with:
+          type: issues
+          fail-on-cache-miss: ${{ env.ALLOW_FAILURE }}
+          quiet: true
+
+      - name: "Predict issue labels"
+        id: prediction
+        if: ${{ steps.restore-model.outputs.cache-hit == 'true' }}
+        uses: dotnet/issue-labeler/predict@46125e85e6a568dc712f358c39f35317366f5eed # v2.0.0
+        with:
+          issues: ${{ inputs.issues || github.event.issue.number }}
+          label_prefix: ${{ env.LABEL_PREFIX }}
+          threshold: ${{ env.THRESHOLD }}
+          default_label: ${{ env.DEFAULT_LABEL }}
+        env:
+          GITHUB_TOKEN: ${{ github.token }}
+        continue-on-error: ${{ !env.ALLOW_FAILURE }}

.github/workflows/labeler-predict-pulls.yml

@@ -0,0 +1,73 @@
+# Workflow template imported and updated from:
+# https://github.com/dotnet/issue-labeler/wiki/Onboarding
+#
+# See labeler.md for more information
+#
+# Predict labels for Pull Requests using a trained model
+name: "Labeler: Predict (Pulls)"
+
+on:
+  # Per to the following documentation:
+  # https://docs.github.com/en/actions/writing-workflows/choosing-when-your-workflow-runs/events-that-trigger-workflows#pull_request_target
+  #
+  # The `pull_request_target` event runs in the context of the base of the pull request, rather
+  # than in the context of the merge commit, as the `pull_request` event does. This prevents
+  # execution of unsafe code from the head of the pull request that could alter the repository
+  # or steal any secrets you use in your workflow. This event allows your workflow to do things
+  # like label or comment on pull requests from forks.
+  #
+  # Only automatically predict area labels when pull requests are first opened
+  pull_request_target:
+    types: opened
+
+    # Configure the branches that need to have PRs labeled
+    branches:
+      - main
+
+  # Allow dispatching the workflow via the Actions UI, specifying ranges of numbers
+  workflow_dispatch:
+    inputs:
+      pulls:
+        description: "Pull Request Numbers (comma-separated list of ranges)."
+        required: true
+      cache_key:
+        description: "The cache key suffix to use for restoring the model. Defaults to 'ACTIVE'."
+        required: true
+        default: "ACTIVE"
+
+env:
+  # Do not allow failure for jobs triggered automatically (this can block PR merge)
+  ALLOW_FAILURE: ${{ github.event_name == 'workflow_dispatch' }}
+
+  LABEL_PREFIX: "area-"
+  THRESHOLD: 0.40
+  DEFAULT_LABEL: "needs-area-label"
+
+jobs:
+  predict-pull-label:
+    # Do not automatically run the workflow on forks outside the 'dotnet' org
+    if: ${{ github.event_name == 'workflow_dispatch' || github.repository_owner == 'dotnet' }}
+    runs-on: ubuntu-latest
+    permissions:
+      pull-requests: write
+    steps:
+      - name: "Restore pulls model from cache"
+        id: restore-model
+        uses: dotnet/issue-labeler/restore@46125e85e6a568dc712f358c39f35317366f5eed # v2.0.0
+        with:
+          type: pulls
+          fail-on-cache-miss: ${{ env.ALLOW_FAILURE }}
+          quiet: true
+
+      - name: "Predict pull labels"
+        id: prediction
+        if: ${{ steps.restore-model.outputs.cache-hit == 'true' }}
+        uses: dotnet/issue-labeler/predict@46125e85e6a568dc712f358c39f35317366f5eed # v2.0.0
+        with:
+          pulls: ${{ inputs.pulls || github.event.number }}
+          label_prefix: ${{ env.LABEL_PREFIX }}
+          threshold: ${{ env.THRESHOLD }}
+          default_label: ${{ env.DEFAULT_LABEL }}
+        env:
+          GITHUB_TOKEN: ${{ github.token }}
+        continue-on-error: ${{ !env.ALLOW_FAILURE }}

.github/workflows/labeler-promote.yml

@@ -0,0 +1,54 @@
+# Workflow template imported and updated from:
+# https://github.com/dotnet/issue-labeler/wiki/Onboarding
+#
+# See labeler.md for more information
+#
+# Promote a model from staging to 'ACTIVE', backing up the currently 'ACTIVE' model
+name: "Labeler: Promotion"
+
+on:
+  # Dispatched via the Actions UI, promotes the staged models from
+  # a staged slot into the prediction environment
+  workflow_dispatch:
+    inputs:
+      issues:
+        description: "Issues: Promote Model"
+        type: boolean
+        required: true
+      pulls:
+        description: "Pulls: Promote Model"
+        type: boolean
+        required: true
+      staged_key:
+        description: "The cache key suffix to use for promoting a staged model to 'ACTIVE'. Defaults to 'staged'."
+        required: true
+        default: "staged"
+      backup_key:
+        description: "The cache key suffix to use for backing up the currently active model. Defaults to 'backup'."
+        default: "backup"
+
+permissions:
+  actions: write
+
+jobs:
+  promote-issues:
+    if: ${{ inputs.issues }}
+    runs-on: ubuntu-latest
+    steps:
+      - name: "Promote Model for Issues"
+        uses: dotnet/issue-labeler/promote@46125e85e6a568dc712f358c39f35317366f5eed # v2.0.0
+        with:
+          type: "issues"
+          staged_key: ${{ inputs.staged_key }}
+          backup_key: ${{ inputs.backup_key }}
+
+  promote-pulls:
+    if: ${{ inputs.pulls }}
+    runs-on: ubuntu-latest
+    steps:
+      - name: "Promote Model for Pull Requests"
+        uses: dotnet/issue-labeler/promote@46125e85e6a568dc712f358c39f35317366f5eed # v2.0.0
+        with:
+          type: "pulls"
+          staged_key: ${{ inputs.staged_key }}
+          backup_key: ${{ inputs.backup_key }}

.github/workflows/labeler-train.yml

@@ -0,0 +1,161 @@
+# Workflow template imported and updated from:
+# https://github.com/dotnet/issue-labeler/wiki/Onboarding
+#
+# See labeler.md for more information
+#
+# Train the Issues and Pull Requests models for label prediction
+name: "Labeler: Training"
+
+on:
+  workflow_dispatch:
+    inputs:
+      type:
+        description: "Issues or Pull Requests"
+        type: choice
+        required: true
+        default: "Both"
+        options:
+          - "Both"
+          - "Issues"
+          - "Pull Requests"
+
+      steps:
+        description: "Training Steps"
+        type: choice
+        required: true
+        default: "All"
+        options:
+          - "All"
+          - "Download Data"
+          - "Train Model"
+          - "Test Model"
+
+      limit:
+        description: "Max number of items to download for training/testing the model (newest items are used). Defaults to the max number of pages times the page size."
+        type: number
+      page_size:
+        description: "Number of items per page in GitHub API requests. Defaults to 100 for issues, 25 for pull requests."
+        type: number
+      page_limit:
+        description: "Maximum number of pages to download for training/testing the model. Defaults to 1000 for issues, 4000 for pull requests."
+        type: number
+      cache_key_suffix:
+        description: "The cache key suffix to use for staged data/models (use 'ACTIVE' to bypass staging). Defaults to 'staged'."
+        required: true
+        default: "staged"
+
+env:
+  CACHE_KEY: ${{ inputs.cache_key_suffix }}
+  REPOSITORY: ${{ github.repository }}
+  LABEL_PREFIX: "area-"
+  THRESHOLD: "0.40"
+  LIMIT: ${{ inputs.limit }}
+  PAGE_SIZE: ${{ inputs.page_size }}
+  PAGE_LIMIT: ${{ inputs.page_limit }}
+
+jobs:
+  download-issues:
+    if: ${{ contains(fromJSON('["Both", "Issues"]'), inputs.type) && contains(fromJSON('["All", "Download Data"]'), inputs.steps) }}
+    runs-on: ubuntu-latest
+    permissions:
+      issues: read
+    steps:
+      - name: "Download Issues"
+        uses: dotnet/issue-labeler/download@46125e85e6a568dc712f358c39f35317366f5eed # v2.0.0
+        with:
+          type: "issues"
+          cache_key: ${{ env.CACHE_KEY }}
+          repository: ${{ env.REPOSITORY }}
+          label_prefix: ${{ env.LABEL_PREFIX }}
+          limit: ${{ env.LIMIT }}
+          page_size: ${{ env.PAGE_SIZE }}
+          page_limit: ${{ env.PAGE_LIMIT }}
+        env:
+          GITHUB_TOKEN: ${{ github.token }}
+
+  download-pulls:
+    if: ${{ contains(fromJSON('["Both", "Pull Requests"]'), inputs.type) && contains(fromJSON('["All", "Download Data"]'), inputs.steps) }}
+    runs-on: ubuntu-latest
+    permissions:
+      pull-requests: read
+    steps:
+      - name: "Download Pull Requests"
+        uses: dotnet/issue-labeler/download@46125e85e6a568dc712f358c39f35317366f5eed # v2.0.0
+        with:
+          type: "pulls"
+          cache_key: ${{ env.CACHE_KEY }}
+          repository: ${{ env.REPOSITORY }}
+          label_prefix: ${{ env.LABEL_PREFIX }}
+          limit: ${{ env.LIMIT }}
+          page_size: ${{ env.PAGE_SIZE }}
+          page_limit: ${{ env.PAGE_LIMIT }}
+        env:
+          GITHUB_TOKEN: ${{ github.token }}
+
+  train-issues:
+    if: ${{ always() && contains(fromJSON('["Both", "Issues"]'), inputs.type) && contains(fromJSON('["All", "Train Model"]'), inputs.steps) && contains(fromJSON('["success", "skipped"]'), needs.download-issues.result) }}
+    runs-on: ubuntu-latest
+    permissions: {}
+    needs: download-issues
+    steps:
+      - name: "Train Model for Issues"
+        uses: dotnet/issue-labeler/train@46125e85e6a568dc712f358c39f35317366f5eed # v2.0.0
+        with:
+          type: "issues"
+          data_cache_key: ${{ env.CACHE_KEY }}
+          model_cache_key: ${{ env.CACHE_KEY }}
+
+  train-pulls:
+    if: ${{ always() && contains(fromJSON('["Both", "Pull Requests"]'), inputs.type) && contains(fromJSON('["All", "Train Model"]'), inputs.steps) && contains(fromJSON('["success", "skipped"]'), needs.download-pulls.result) }}
+    runs-on: ubuntu-latest
+    permissions: {}
+    needs: download-pulls
+    steps:
+      - name: "Train Model for Pull Requests"
+        uses: dotnet/issue-labeler/train@46125e85e6a568dc712f358c39f35317366f5eed # v2.0.0
+        with:
+          type: "pulls"
+          data_cache_key: ${{ env.CACHE_KEY }}
+          model_cache_key: ${{ env.CACHE_KEY }}
+
+  test-issues:
+    if: ${{ always() && contains(fromJSON('["Both", "Issues"]'), inputs.type) && contains(fromJSON('["All", "Test Model"]'), inputs.steps) && contains(fromJSON('["success", "skipped"]'), needs.train-issues.result) }}
+    runs-on: ubuntu-latest
+    permissions:
+      issues: read
+    needs: train-issues
+    steps:
+      - name: "Test Model for Issues"
+        uses: dotnet/issue-labeler/test@46125e85e6a568dc712f358c39f35317366f5eed # v2.0.0
+        with:
+          type: "issues"
+          cache_key: ${{ env.CACHE_KEY }}
+          repository: ${{ env.REPOSITORY }}
+          label_prefix: ${{ env.LABEL_PREFIX }}
+          threshold: ${{ env.THRESHOLD }}
+          limit: ${{ env.LIMIT }}
+          page_size: ${{ env.PAGE_SIZE }}
+          page_limit: ${{ env.PAGE_LIMIT }}
+        env:
+          GITHUB_TOKEN: ${{ github.token }}
+
+  test-pulls:
+    if: ${{ always() && contains(fromJSON('["Both", "Pull Requests"]'), inputs.type) && contains(fromJSON('["All", "Test Model"]'), inputs.steps) && contains(fromJSON('["success", "skipped"]'), needs.train-pulls.result) }}
+    runs-on: ubuntu-latest
+    permissions:
+      pull-requests: read
+    needs: train-pulls
+    steps:
+      - name: "Test Model for Pull Requests"
+        uses: dotnet/issue-labeler/test@46125e85e6a568dc712f358c39f35317366f5eed # v2.0.0
+        with:
+          type: "pulls"
+          cache_key: ${{ env.CACHE_KEY }}
+          repository: ${{ env.REPOSITORY }}
+          label_prefix: ${{ env.LABEL_PREFIX }}
+          threshold: ${{ env.THRESHOLD }}
+          limit: ${{ env.LIMIT }}
+          page_size: ${{ env.PAGE_SIZE }}
+          page_limit: ${{ env.PAGE_LIMIT }}
+        env:
+          GITHUB_TOKEN: ${{ github.token }}

.github/workflows/labeler.md

@@ -0,0 +1,32 @@
+# Issue-Labeler Workflows
+
+This repository uses actions from [dotnet/issue-labeler](https://github.com/dotnet/issue-labeler) to predict area labels for issues and pull requests.
+
+The following workflow templates were imported and updated from [dotnet/issue-labeler/wiki/Onboarding](https://github.com/dotnet/issue-labeler/wiki/Onboarding):
+
+1. `labeler-cache-retention.yml`
+2. `labeler-predict-issues.yml`
+3. `labeler-predict-pulls.yml`
+4. `labeler-promote.yml`
+5. `labeler-train.yml`
+
+## Repository Configuration
+
+Across these workflows, the following changes were made to configure the issue labeler for this repository:
+
+1. Set `LABEL_PREFIX` to `"area-"`:
+    - `labeler-predict-issues.yml`
+    - `labeler-predict-pulls.yml`
+    - `labeler-train.yml`
+2. Set `DEFAULT_LABEL` to `"needs-area-label"`:
+    - `labeler-predict-issues.yml`
+    - `labeler-predict-pulls.yml`
+3. Remove the `EXCLUDED_AUTHORS` value as we do not bypass labeling for any authors' issues/pulls in this repository:
+    - `labeler-predict-issues.yml`
+    - `labeler-predict-pulls.yml`
+4. Update the pull request labeling branches to include `main` and `release/*`:
+    - `labeler-predict-pulls.yml`
+5. Remove the `repository` input for training the models against another repository:
+    - `labeler-train.yml`
+6. Update the cache retention cron schedule to an arbitrary time of day:
+    - `labeler-cache-retention.yml`