feat(bots): reviewer-bot live workflows (review + follow-up)

.github/actions/setup-claude-sdk/action.yml

@@ -0,0 +1,54 @@
+# Copyright (c) 2025 ADBC Drivers Contributors
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+
+# Install the Claude Agent SDK (pip) + the Claude Code CLI (npm) that the bots
+# now spawn, via Databricks' internal JFrog mirror. The protected runner group
+# is egress-blocked from pypi.org and registry.npmjs.org, so this configures
+# both package managers through JFrog (same mechanism as setup-jfrog / the
+# sdk-smoke workflow, which is verified working end-to-end against the gateway).
+#
+# Requires `id-token: write` on the calling job (for the JFrog OIDC exchange).
+# Idempotent w.r.t. a prior setup-jfrog step (re-exchanging the token + re-
+# setting PIP_INDEX_URL is harmless).
+name: Setup Claude Agent SDK
+description: Install claude-agent-sdk (pip) + Claude Code CLI (npm) via the internal JFrog mirror.
+
+inputs:
+  requirements-file:
+    description: >-
+      Path to the SDK requirements file, relative to the job working directory
+      ($GITHUB_WORKSPACE — composite `run:` steps always execute there, not at
+      the caller's working-directory). Defaults to scripts/requirements-sdk.txt,
+      correct when the repo is checked out at the workspace root (e.g. the
+      reviewer bots). Workflows that check the repo into a subdir (the engineer
+      bots use `path: internal-repo`) MUST pass the prefixed path, e.g.
+      internal-repo/scripts/requirements-sdk.txt.
+    required: false
+    default: scripts/requirements-sdk.txt
+
+runs:
+  using: composite
+  steps:
+    - name: Setup Node (for the Claude Code CLI the SDK spawns)
+      uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4.4.0
+      with:
+        node-version: '20'
+
+    - name: Configure JFrog (pip + npm internal mirror)
+      uses: ./.github/actions/setup-jfrog
+      with:
+        configure-pip: 'true'
+        configure-npm: 'true'
+
+    - name: Install claude-agent-sdk + Claude Code CLI
+      shell: bash
+      run: |
+        python -m pip install --upgrade pip
+        # Install the SDK from the documented requirements file (not a bare
+        # `pip install claude-agent-sdk`) so CI and local docs share one
+        # dependency source and future pins land in a single place. (Review)
+        pip install -r "${{ inputs.requirements-file }}"
+        npm i -g @anthropic-ai/claude-code
+        echo "claude CLI: $(command -v claude || echo 'NOT FOUND')"

.github/actions/setup-jfrog/setup-jfrog/action.yml

@@ -0,0 +1,78 @@
+name: Setup JFrog OIDC
+description: Obtain a JFrog access token via GitHub OIDC and configure package managers
+
+inputs:
+  configure-pip:
+    description: Configure pip to use JFrog PyPI proxy
+    default: "true"
+  configure-cargo:
+    description: Configure Cargo to use JFrog crates proxy
+    default: "false"
+  configure-npm:
+    description: Configure npm to use JFrog npm proxy
+    default: "false"
+
+runs:
+  using: composite
+  steps:
+    - name: Get JFrog OIDC token
+      shell: bash
+      run: |
+        set -euo pipefail
+        ID_TOKEN=$(curl -sLS \
+          -H "User-Agent: actions/oidc-client" \
+          -H "Authorization: Bearer $ACTIONS_ID_TOKEN_REQUEST_TOKEN" \
+          "${ACTIONS_ID_TOKEN_REQUEST_URL}&audience=jfrog-github" | jq .value | tr -d '"')
+        echo "::add-mask::${ID_TOKEN}"
+        ACCESS_TOKEN=$(curl -sLS -XPOST -H "Content-Type: application/json" \
+          "https://databricks.jfrog.io/access/api/v1/oidc/token" \
+          -d "{\"grant_type\": \"urn:ietf:params:oauth:grant-type:token-exchange\", \"subject_token_type\":\"urn:ietf:params:oauth:token-type:id_token\", \"subject_token\": \"${ID_TOKEN}\", \"provider_name\": \"github-actions\"}" | jq .access_token | tr -d '"')
+        echo "::add-mask::${ACCESS_TOKEN}"
+        if [ -z "$ACCESS_TOKEN" ] || [ "$ACCESS_TOKEN" = "null" ]; then
+          echo "FAIL: Could not extract JFrog access token"
+          exit 1
+        fi
+        echo "JFROG_ACCESS_TOKEN=${ACCESS_TOKEN}" >> "$GITHUB_ENV"
+        echo "JFrog OIDC token obtained successfully"
+
+    - name: Configure pip
+      if: inputs.configure-pip == 'true'
+      shell: bash
+      run: |
+        set -euo pipefail
+        echo "PIP_INDEX_URL=https://gha-service-account:${JFROG_ACCESS_TOKEN}@databricks.jfrog.io/artifactory/api/pypi/db-pypi/simple" >> "$GITHUB_ENV"
+        echo "pip configured to use JFrog registry"
+
+    - name: Configure Cargo
+      if: inputs.configure-cargo == 'true'
+      shell: bash
+      run: |
+        set -euo pipefail
+        mkdir -p ~/.cargo
+        cat > ~/.cargo/config.toml << EOF
+        [source.crates-io]
+        replace-with = "jfrog"
+        [source.jfrog]
+        registry = "sparse+https://databricks.jfrog.io/artifactory/api/cargo/db-cargo-remote/index/"
+        [registries.jfrog]
+        index = "sparse+https://databricks.jfrog.io/artifactory/api/cargo/db-cargo-remote/index/"
+        credential-provider = ["cargo:token"]
+        EOF
+        cat > ~/.cargo/credentials.toml << EOF
+        [registries.jfrog]
+        token = "Bearer ${JFROG_ACCESS_TOKEN}"
+        EOF
+        echo "CARGO_REGISTRIES_JFROG_TOKEN=Bearer ${JFROG_ACCESS_TOKEN}" >> "$GITHUB_ENV"
+        echo "Cargo configured to use JFrog registry"
+
+    - name: Configure npm
+      if: inputs.configure-npm == 'true'
+      shell: bash
+      run: |
+        set -euo pipefail
+        cat > ~/.npmrc << EOF
+        registry=https://databricks.jfrog.io/artifactory/api/npm/db-npm/
+        //databricks.jfrog.io/artifactory/api/npm/db-npm/:_authToken=${JFROG_ACCESS_TOKEN}
+        always-auth=true
+        EOF
+        echo "npm configured to use JFrog registry"

.github/workflows/reviewer-bot-followup.yml

@@ -0,0 +1,117 @@
+name: Reviewer Bot — Follow-up
+
+on:
+  pull_request_review_comment:
+    types: [created]
+
+permissions:
+  # The workflow GITHUB_TOKEN is not used to interact with the PR — we mint a
+  # dedicated peco-review-bot App installation token and use that everywhere.
+  # Required App permissions on the installation (NOT this workflow):
+  #   Pull requests: Read & Write — posting inline replies
+  #   Issues:        Read & Write — comment plumbing
+  #   Contents:      Read & Write — resolveReviewThread mutation
+  #     (Pull-requests:write is NOT sufficient for the resolve mutation;
+  #     GitHub gates it behind Contents.)
+  contents: read
+  id-token: write   # JFrog OIDC exchange for the SDK/CLI install (setup-claude-sdk)
+
+jobs:
+  followup:
+    # SECURITY: skip fork PRs — keep DATABRICKS_TOKEN out of untrusted code's
+    # reach. Mirrors the guard in reviewer-bot.yml.
+    if: github.event.pull_request.head.repo.fork == false && github.event.pull_request.state == 'open'
+    runs-on:
+      group: databricks-protected-runner-group
+      labels: [linux-ubuntu-latest]
+    timeout-minutes: 10
+    steps:
+      - name: Mint review-bot App token
+        id: app-token
+        uses: actions/create-github-app-token@fee1f7d63c2ff003460e3d139729b119787bc349 # v2.2.2
+        with:
+          app-id: ${{ secrets.REVIEW_BOT_APP_ID }}
+          private-key: ${{ secrets.REVIEW_BOT_APP_PRIVATE_KEY }}
+
+      - name: Cheap pre-checkout filter
+        id: filter
+        env:
+          GH_TOKEN: ${{ steps.app-token.outputs.token }}
+          REPO: ${{ github.repository }}
+          TRIGGER_ID: ${{ github.event.comment.id }}
+          IN_REPLY_TO: ${{ github.event.comment.in_reply_to_id }}
+          COMMENT_USER: ${{ github.event.comment.user.login }}
+          COMMENT_BODY: ${{ github.event.comment.body }}
+        run: |
+          # Cheap filters first — skip the expensive checkout / python setup
+          # when the event is already known to be irrelevant. The Python entry
+          # point repeats these checks (defense in depth), so being slightly
+          # over-permissive here is safe.
+          #
+          # Filter 1: must be a reply to another inline comment.
+          if [ -z "$IN_REPLY_TO" ] || [ "$IN_REPLY_TO" = "null" ]; then
+            echo "skip=true" >> "$GITHUB_OUTPUT"
+            echo "reason=no in_reply_to_id (top-level review comment, not a thread reply)" >> "$GITHUB_OUTPUT"
+            exit 0
+          fi
+          # Filter 2: skip our own follow-up AND reconcile replies (loop
+          # prevention). MARKER-based — never login-based.
+          if printf '%s' "$COMMENT_BODY" | grep -q '<!-- pr-review-bot:v1 followup'; then
+            echo "skip=true" >> "$GITHUB_OUTPUT"
+            echo "reason=trigger comment is itself a bot follow-up (loop prevention)" >> "$GITHUB_OUTPUT"
+            exit 0
+          fi
+          if printf '%s' "$COMMENT_BODY" | grep -q '<!-- pr-review-bot:v1 reconcile -->'; then
+            echo "skip=true" >> "$GITHUB_OUTPUT"
+            echo "reason=trigger comment is itself a bot reconcile reply (loop prevention)" >> "$GITHUB_OUTPUT"
+            exit 0
+          fi
+          echo "skip=false" >> "$GITHUB_OUTPUT"
+
+      - name: Announce skip in step summary
+        if: steps.filter.outputs.skip == 'true'
+        run: |
+          {
+            echo "## Reviewer Bot — Follow-up"
+            echo ""
+            echo "**Skipped:** ${{ steps.filter.outputs.reason }}"
+          } >> "$GITHUB_STEP_SUMMARY"
+
+      - name: Checkout
+        if: steps.filter.outputs.skip != 'true'
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          fetch-depth: 0
+          ref: ${{ github.event.pull_request.head.sha }}
+          # The followup reads this checkout via read_paths/grep, so the
+          # persisted GITHUB_TOKEN must NOT sit in .git/config. The followup
+          # only POSTS replies via the minted App token.
+          persist-credentials: false
+
+      - name: Setup Python
+        if: steps.filter.outputs.skip != 'true'
+        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
+        with:
+          python-version: '3.11'
+
+      - name: Setup Claude Agent SDK + CLI
+        if: steps.filter.outputs.skip != 'true'
+        uses: ./.github/actions/setup-claude-sdk
+
+      - name: Run follow-up agent
+        if: steps.filter.outputs.skip != 'true'
+        env:
+          GH_TOKEN: ${{ steps.app-token.outputs.token }}
+          GITHUB_REPOSITORY: ${{ github.repository }}
+          PR_NUMBER: ${{ github.event.pull_request.number }}
+          TRIGGER_COMMENT_ID: ${{ github.event.comment.id }}
+          # PR SHA range — used by followup.py to restrict `git show` to commits
+          # actually in this PR (allowlist for SHA-diff verification).
+          PR_BASE_SHA: ${{ github.event.pull_request.base.sha }}
+          HEAD_SHA: ${{ github.event.pull_request.head.sha }}
+          DATABRICKS_TOKEN: ${{ secrets.DATABRICKS_TOKEN }}
+          MODEL_ENDPOINT: ${{ secrets.MODEL_ENDPOINT }}
+          DRY_RUN: 'false'
+          RUNNER_TEMP: ${{ runner.temp }}
+        run: |
+          python -m scripts.reviewer_bot.followup

.github/workflows/reviewer-bot-unit-tests.yml

@@ -0,0 +1,34 @@
+# Unit tests for the migrated PR-review bot (scripts/reviewer_bot + scripts/shared).
+#
+# Pure-logic tests — no secrets, no model calls, no Claude Agent SDK install
+# (the SDK import is guarded, so the tests run with just pytest, which the
+# connector's poetry dev-deps already provide). Runs only when the bot code
+# changes, so it doesn't add load to every connector PR.
+name: Reviewer Bot Unit Tests
+
+on:
+  pull_request:
+    paths:
+      - 'scripts/shared/**'
+      - 'scripts/reviewer_bot/**'
+      - '.github/workflows/reviewer-bot-unit-tests.yml'
+
+permissions:
+  contents: read
+
+jobs:
+  unit-tests:
+    name: Reviewer Bot Unit Tests
+    runs-on:
+      group: databricks-protected-runner-group
+      labels: linux-ubuntu-latest
+    timeout-minutes: 15
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
+      - name: Setup Poetry
+        uses: ./.github/actions/setup-poetry
+        with:
+          python-version: "3.11"
+      - name: Run reviewer-bot + shared unit tests
+        run: poetry run python -m pytest scripts/reviewer_bot/tests scripts/shared/tests