name: Update Model Catalog

on:
  schedule:
    # Run every weekday (Mon-Fri) at 00:00 and 12:00 UTC
    - cron: "0 0,12 * * 1-5"
  workflow_dispatch:

defaults:
  run:
    shell: bash

permissions: {}

jobs:
  update-model-catalog:
    if: github.repository == 'mlflow/mlflow'
    runs-on: ubuntu-latest
    timeout-minutes: 10
    permissions:
      contents: write
      pull-requests: write
    steps:
      - uses: actions/create-github-app-token@1b10c78c7865c340bc4f6099eb2f838309f1e8c3 # v3.1.1
        id: app-token
        with:
          client-id: ${{ secrets.APP_CLIENT_ID }}
          private-key: ${{ secrets.APP_PRIVATE_KEY }}
          permission-contents: write
          permission-pull-requests: write

      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
        with:
          persist-credentials: true
          token: ${{ steps.app-token.outputs.token }}

      - uses: ./.github/actions/setup-python
        with:
          pin-micro-version: false

      - uses: ./.github/actions/setup-node

      - name: Fetch and transform model catalog
        run: uv run python dev/update_model_catalog.py

      - name: Run pre-commit on generated files
        run: |
          uv sync --locked --only-group lint
          uv run --no-sync pre-commit install --install-hooks
          uv run --no-sync pre-commit run install-bin -a -v
          # pre-commit exits 1 when it auto-fixes files (e.g. prettier reformats JSON).
          # That's expected — the fixes are picked up by the subsequent git diff.
          uv run --no-sync pre-commit run --files mlflow/utils/model_catalog/*.json || true

      - name: Check for changes
        id: diff
        run: |
          if git diff --quiet mlflow/utils/model_catalog/; then
            echo "changed=false" >> "$GITHUB_OUTPUT"
          else
            echo "changed=true" >> "$GITHUB_OUTPUT"
          fi

      - name: Update model-catalog/latest tag
        if: steps.diff.outputs.changed == 'true'
        run: |
          git fetch origin master --depth=1
          git tag -f model-catalog/latest origin/master
          git push -f origin refs/tags/model-catalog/latest

      - name: Create or update pull request
        id: pr
        if: steps.diff.outputs.changed == 'true'
        env:
          GH_TOKEN: ${{ steps.app-token.outputs.token }}
        run: |
          git config user.name 'mlflow-app[bot]'
          git config user.email 'mlflow-app[bot]@users.noreply.github.com'
          branch="update-model-catalog"
          git checkout -b "$branch"
          git add mlflow/utils/model_catalog/
          git commit -m "Update model catalog from upstream sources"
          git push -f -u origin "$branch"
          existing_pr=$(gh pr list --head "$branch" --state open --json number --jq '.[0].number // empty')
          if [ -n "$existing_pr" ]; then
            echo "Existing open PR #$existing_pr found for branch $branch — skipping PR creation."
            echo "number=$existing_pr" >> "$GITHUB_OUTPUT"
            echo "is_new_pr=false" >> "$GITHUB_OUTPUT"
          else
            pr_url=$(gh pr create \
              --title "Update model catalog from upstream sources" \
              --body "Daily refresh of model pricing and context window data from LiteLLM, transformed to MLflow-native schema." \
              --reviewer "TomeHirata")
            echo "number=${pr_url##*/}" >> "$GITHUB_OUTPUT"
            echo "is_new_pr=true" >> "$GITHUB_OUTPUT"
          fi

      - name: Enable auto-merge
        if: steps.pr.outputs.is_new_pr == 'true'
        env:
          GH_TOKEN: ${{ steps.app-token.outputs.token }}
          PR_NUMBER: ${{ steps.pr.outputs.number }}
        run: |
          output=$(gh pr merge "$PR_NUMBER" --auto --squash 2>&1) && exit 0
          echo "$output" | grep -qi "auto-merge is already enabled" && exit 0
          echo "$output" >&2
          exit 1

      - name: Publish to GitHub Releases
        if: steps.diff.outputs.changed == 'true'
        env:
          GH_TOKEN: ${{ steps.app-token.outputs.token }}
        run: bash dev/publish_model_catalog.sh