ci: add datagen job, adapt workflow for Gitea runner

- Drop actions/setup-python, use system python3
- Use full Gitea-compatible action URLs
- CPU-only torch via pytorch whl/cpu index
- Add datagen job with cache/checkpoint resume and artifact upload
- Manual dispatch with configurable assembly count and worker count
- Datagen runs on push to main (after tests pass) or manual trigger

.gitea/workflows/ci.yaml

@@ -5,21 +5,41 @@ on:
     branches: [main]
   pull_request:
     branches: [main]
+  workflow_dispatch:
+    inputs:
+      run_datagen:
+        description: "Run dataset generation"
+        required: false
+        type: boolean
+        default: false
+      num_assemblies:
+        description: "Number of assemblies to generate"
+        required: false
+        type: string
+        default: "100000"
+      num_workers:
+        description: "Parallel workers for datagen"
+        required: false
+        type: string
+        default: "4"
+
+env:
+  PIP_CACHE_DIR: /tmp/pip-cache-solver
+  TORCH_INDEX: https://download.pytorch.org/whl/cpu
 
 jobs:
+  # ---------------------------------------------------------------------------
+  # Lint — fast, no torch required
+  # ---------------------------------------------------------------------------
   lint:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - name: Checkout
+        uses: https://github.com/actions/checkout@v4
 
-      - uses: actions/setup-python@v5
-        with:
-          python-version: "3.11"
-
-      - name: Install dependencies
+      - name: Install lint tools
         run: |
-          pip install ruff mypy
-          pip install -e ".[dev]" || pip install ruff mypy numpy
+          python3 -m pip install --cache-dir $PIP_CACHE_DIR ruff
 
       - name: Ruff check
         run: ruff check solver/ freecad/ tests/ scripts/
@@ -27,39 +47,122 @@ jobs:
       - name: Ruff format check
         run: ruff format --check solver/ freecad/ tests/ scripts/
 
+  # ---------------------------------------------------------------------------
+  # Type check
+  # ---------------------------------------------------------------------------
   type-check:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
-
-      - uses: actions/setup-python@v5
-        with:
-          python-version: "3.11"
+      - name: Checkout
+        uses: https://github.com/actions/checkout@v4
 
       - name: Install dependencies
         run: |
-          pip install mypy numpy
-          pip install torch --index-url https://download.pytorch.org/whl/cpu
-          pip install torch-geometric
-          pip install -e ".[dev]"
+          python3 -m pip install --cache-dir $PIP_CACHE_DIR \
+            mypy numpy scipy \
+            torch --index-url $TORCH_INDEX
+          python3 -m pip install --cache-dir $PIP_CACHE_DIR \
+            torch-geometric
+          python3 -m pip install --cache-dir $PIP_CACHE_DIR -e ".[dev]"
 
       - name: Mypy
         run: mypy solver/ freecad/
 
+  # ---------------------------------------------------------------------------
+  # Tests
+  # ---------------------------------------------------------------------------
   test:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
-
-      - uses: actions/setup-python@v5
-        with:
-          python-version: "3.11"
+      - name: Checkout
+        uses: https://github.com/actions/checkout@v4
 
       - name: Install dependencies
         run: |
-          pip install torch --index-url https://download.pytorch.org/whl/cpu
-          pip install torch-geometric
-          pip install -e ".[train,dev]"
+          python3 -m pip install --cache-dir $PIP_CACHE_DIR \
+            torch --index-url $TORCH_INDEX
+          python3 -m pip install --cache-dir $PIP_CACHE_DIR \
+            torch-geometric
+          python3 -m pip install --cache-dir $PIP_CACHE_DIR -e ".[train,dev]"
 
       - name: Run tests
         run: pytest tests/ freecad/tests/ -v --tb=short
+
+  # ---------------------------------------------------------------------------
+  # Dataset generation — manual trigger or on main push
+  # ---------------------------------------------------------------------------
+  datagen:
+    runs-on: ubuntu-latest
+    if: >-
+      (github.event_name == 'workflow_dispatch' && inputs.run_datagen == true) ||
+      (github.event_name == 'push' && github.ref == 'refs/heads/main')
+    needs: [test]
+    steps:
+      - name: Checkout
+        uses: https://github.com/actions/checkout@v4
+
+      - name: Install dependencies
+        run: |
+          python3 -m pip install --cache-dir $PIP_CACHE_DIR \
+            torch --index-url $TORCH_INDEX
+          python3 -m pip install --cache-dir $PIP_CACHE_DIR \
+            torch-geometric
+          python3 -m pip install --cache-dir $PIP_CACHE_DIR -e ".[train]"
+
+      - name: Restore datagen checkpoint
+        id: datagen-cache
+        uses: https://github.com/actions/cache/restore@v4
+        with:
+          path: data/synthetic
+          key: datagen-${{ github.sha }}
+          restore-keys: |
+            datagen-
+
+      - name: Generate dataset
+        run: |
+          NUM=${INPUTS_NUM_ASSEMBLIES:-100000}
+          WORKERS=${INPUTS_NUM_WORKERS:-4}
+          echo "Generating ${NUM} assemblies with ${WORKERS} workers"
+          python3 scripts/generate_synthetic.py \
+            --num-assemblies "${NUM}" \
+            --num-workers "${WORKERS}" \
+            --output-dir data/synthetic
+        env:
+          INPUTS_NUM_ASSEMBLIES: ${{ inputs.num_assemblies }}
+          INPUTS_NUM_WORKERS: ${{ inputs.num_workers }}
+
+      - name: Save datagen checkpoint
+        if: always()
+        uses: https://github.com/actions/cache/save@v4
+        with:
+          path: data/synthetic
+          key: datagen-${{ github.sha }}
+
+      - name: Upload dataset
+        uses: https://github.com/actions/upload-artifact@v3
+        with:
+          name: synthetic-dataset
+          path: |
+            data/synthetic/index.json
+            data/synthetic/stats.json
+            data/synthetic/shards/
+          retention-days: 90
+
+      - name: Print summary
+        if: always()
+        run: |
+          echo "=== Dataset Generation Results ==="
+          if [ -f data/synthetic/stats.json ]; then
+            python3 -c "
+          import json
+          with open('data/synthetic/stats.json') as f:
+              s = json.load(f)
+          print(f'Total examples: {s[\"total_examples\"]}')
+          print(f'Classification: {json.dumps(s[\"classification_distribution\"], indent=2)}')
+          print(f'Rigid: {s[\"rigidity\"][\"rigid_fraction\"]*100:.1f}%')
+          print(f'Degeneracy: {s[\"geometric_degeneracy\"][\"fraction_with_degeneracy\"]*100:.1f}%')
+          "
+          else
+            echo "stats.json not found — generation may have failed"
+            ls -la data/synthetic/ 2>/dev/null || echo "output dir missing"
+          fi