active_learning.yml

name: Active Learning Pipeline

on:
  schedule:
    # Run every Monday at 08:00 UTC
    - cron: "0 8 * * 1"
  workflow_dispatch:
    inputs:
      strategy:
        description: "Query strategy"
        default: "committee_disagreement"
        required: false
      batch_size:
        description: "Number of wallets to select"
        default: "20"
        required: false
      pool_path:
        description: "Path to unscored wallet parquet"
        default: "data/unscored_wallets.parquet"
        required: false

jobs:
  active-learning:
    runs-on: ubuntu-latest

    steps:
      - uses: actions/checkout@v4

      - name: Set up Python 3.11
        uses: actions/setup-python@v5
        with:
          python-version: "3.11"
          cache: pip

      - name: Install dependencies
        run: pip install -r requirements.txt

      - name: Run active learning loop
        env:
          AL_QUERY_STRATEGY: ${{ github.event.inputs.strategy || 'committee_disagreement' }}
          AL_BATCH_SIZE: ${{ github.event.inputs.batch_size || '20' }}
          AL_QUEUE_PATH: data/annotation_queue.json
          ANNOTATION_HMAC_SECRET: ${{ secrets.ANNOTATION_HMAC_SECRET }}
          MODEL_DIR: ${{ vars.MODEL_DIR || './models' }}
        run: |
          python -m scripts.run_active_learning \
            --pool "${{ github.event.inputs.pool_path || 'data/unscored_wallets.parquet' }}" \
            --strategy "$AL_QUERY_STRATEGY" \
            --batch-size "$AL_BATCH_SIZE" \
            --queue "$AL_QUEUE_PATH"

      - name: Upload annotation queue artifact
        uses: actions/upload-artifact@v4
        with:
          name: annotation-queue-${{ github.run_id }}
          path: data/annotation_queue.json
          retention-days: 30