Fix/await run cycle

.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,31 @@
+## 🚀 Pull Request Checklist
+
+### CI & Quality
+- [ ] CI ✔️ (no fails, ≤ 2 skips)
+- [ ] All tests passing locally
+- [ ] Code follows style guidelines
+- [ ] No new warnings introduced
+
+### Evidence & Validation
+- [ ] Evidence artifacts attached if run type = validation
+- [ ] Performance benchmarks updated if applicable
+- [ ] Documentation updated if needed
+
+### Review
+- [ ] Self-review completed
+- [ ] Code review requested from appropriate reviewers
+- [ ] All feedback addressed
+
+---
+
+## 📋 Changes Summary
+
+<!-- Describe the changes made in this PR -->
+
+## 🧪 Testing
+
+<!-- Describe how you tested these changes -->
+
+## 📊 Evidence
+
+<!-- If this PR includes validation runs, attach evidence artifacts here --> 

.github/workflows/ci.yml

@@ -0,0 +1,147 @@
+name: CI
+
+on:
+  push:
+    branches: [ main, develop ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        run_external: [false]  # fast lane only
+      fail-fast: false
+
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.12'
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install -e .
+        pip install -e ".[dev]"
+
+    - name: Export & mask dummy secret
+      run: |
+        echo "CLAUDE_API_KEY=dummy" >> $GITHUB_ENV
+        echo "::add-mask::dummy"
+
+    - name: Run tests
+      run: |
+        pytest -m "not external"
+
+    - name: Upload coverage
+      uses: actions/upload-artifact@v4
+      with:
+        name: coverage
+        path: coverage.xml
+        if-no-files-found: ignore
+
+    - name: Upload test summary
+      uses: actions/upload-artifact@v4
+      with:
+        name: test-summary
+        path: artifacts/test_summary.json
+        if-no-files-found: ignore
+
+  qa:
+    runs-on: ubuntu-latest
+    needs: test
+    steps:
+    - uses: actions/checkout@v3
+
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.9'
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install -r requirements.txt
+        pip install pytest pytest-cov
+
+    - name: Run QA Checklist
+      run: |
+        python scripts/qa_checklist.py --verbose
+      env:
+        CLAUDE_API_KEY: ${{ secrets.CLAUDE_API_KEY }}
+
+    - name: Upload QA artifacts
+      uses: actions/upload-artifact@v3
+      if: always()
+      with:
+        name: qa-artifacts-${{ github.run_number }}
+        path: |
+          artifacts/
+          coverage.xml
+          htmlcov/
+          logs/
+        retention-days: 7
+
+  safety:
+    runs-on: ubuntu-latest
+    needs: test
+    steps:
+    - uses: actions/checkout@v3
+
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.9'
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install -r requirements.txt
+
+    - name: Run safety tests
+      run: |
+        python scripts/safety_dashboard.py --test
+      env:
+        CLAUDE_API_KEY: ${{ secrets.CLAUDE_API_KEY }}
+
+    - name: Upload safety results
+      uses: actions/upload-artifact@v3
+      if: always()
+      with:
+        name: safety-results-${{ github.run_number }}
+        path: logs/safety_test_*.json
+        retention-days: 7
+
+  dashboard:
+    runs-on: ubuntu-latest
+    needs: [test, qa, safety]
+    steps:
+    - uses: actions/checkout@v3
+
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.9'
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install -r requirements.txt
+
+    - name: Generate dashboard
+      run: |
+        python scripts/progress_monitor.py --dashboard --html results/dashboard_${{ github.run_number }}.html
+      env:
+        CLAUDE_API_KEY: ${{ secrets.CLAUDE_API_KEY }}
+
+    - name: Upload dashboard
+      uses: actions/upload-artifact@v3
+      if: always()
+      with:
+        name: dashboard-${{ github.run_number }}
+        path: results/dashboard_${{ github.run_number }}.html
+        retention-days: 7 

.gitignore

@@ -0,0 +1,5 @@
+venv/
+.cache/
+__pycache__/
+*.pyc
+.env

.pre-commit-config.yaml

@@ -0,0 +1 @@
+repos:

CITATION.cff

@@ -0,0 +1,23 @@
+cff-version: 1.2.0
+message: "If you use this software, please cite it as below."
+authors:
+  - family-names: "Oversight Curriculum"
+    given-names: "Team"
+    orcid: "https://orcid.org/0000-0000-0000-0000"
+title: "Oversight Curriculum - AI Safety & Reasoning System"
+version: 1.0.0
+doi: 10.5281/zenodo.0000000
+date-released: 2024-12-21
+url: "https://github.com/oversight-curriculum/oversight-curriculum"
+repository-code: "https://github.com/oversight-curriculum/oversight-curriculum"
+license: MIT
+keywords:
+  - "ai-safety"
+  - "reasoning"
+  - "oversight"
+  - "curriculum"
+  - "claude"
+  - "anthropic"
+  - "machine-learning"
+  - "python"
+abstract: "Advanced AI safety and reasoning system that combines Absolute Zero Reasoner (AZR) self-play, best-of-n sampling, and HHH safety filtering to create a robust oversight curriculum for AI safety evaluation and improvement."