Split monolithic workflow into modular components

Separate workflows for flexibility:
- build.yml: Build verification (standalone + reusable)
- runtime.yml: Container & runtime tests with container lifecycle
- inference.yml: Inference tests with optional container management
- full-pipeline.yml: Orchestrates all stages with LLM judge

Each workflow can be triggered independently for targeted testing,
or run the full pipeline for complete validation.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

.github/workflows/full-pipeline.yml

@@ -0,0 +1,176 @@
+name: Full Pipeline
+
+on:
+  workflow_dispatch:  # Manual trigger
+    inputs:
+      skip_llm_judge:
+        description: 'Skip LLM judge evaluation'
+        required: false
+        default: 'false'
+        type: choice
+        options:
+          - 'true'
+          - 'false'
+
+env:
+  OLLAMA_HOST: http://localhost:11434
+
+jobs:
+  build:
+    name: Build Verification
+    uses: ./.github/workflows/build.yml
+
+  start-container:
+    name: Start Container
+    runs-on: self-hosted
+    needs: build
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Start container
+        run: |
+          cd docker
+          docker compose down 2>/dev/null || true
+          docker compose up -d
+          echo "Waiting for container to be ready..."
+          sleep 10
+
+      - name: Verify container health
+        run: |
+          docker ps
+          curl -s http://localhost:11434/api/tags || echo "Ollama not ready yet, continuing..."
+
+  runtime:
+    name: Runtime Tests
+    runs-on: self-hosted
+    needs: start-container
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '20'
+
+      - name: Install test runner dependencies
+        run: cd tests && npm ci
+
+      - name: Run runtime tests
+        id: runtime-tests
+        run: |
+          cd tests
+          npm run --silent dev -- run --suite runtime --no-llm --output json > /tmp/runtime-results.json || true
+
+          echo "--- JSON Results ---"
+          cat /tmp/runtime-results.json
+
+      - name: Upload runtime results
+        uses: actions/upload-artifact@v4
+        if: always()
+        with:
+          name: runtime-test-results
+          path: /tmp/runtime-results.json
+
+  inference:
+    name: Inference Tests
+    runs-on: self-hosted
+    needs: runtime
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '20'
+
+      - name: Install test runner dependencies
+        run: cd tests && npm ci
+
+      - name: Run inference tests
+        id: inference-tests
+        run: |
+          cd tests
+          npm run --silent dev -- run --suite inference --no-llm --output json > /tmp/inference-results.json || true
+
+          echo "--- JSON Results ---"
+          cat /tmp/inference-results.json
+
+      - name: Upload inference results
+        uses: actions/upload-artifact@v4
+        if: always()
+        with:
+          name: inference-test-results
+          path: /tmp/inference-results.json
+
+  llm-judge:
+    name: LLM Judge Evaluation
+    runs-on: self-hosted
+    needs: [build, runtime, inference]
+    if: ${{ inputs.skip_llm_judge != 'true' }}
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '20'
+
+      - name: Install test runner dependencies
+        run: cd tests && npm ci
+
+      - name: Download all test results
+        uses: actions/download-artifact@v4
+        with:
+          path: /tmp/results
+
+      - name: Run LLM judge on all results
+        run: |
+          cd tests
+          echo "Running LLM judge evaluation..."
+          npm run --silent dev -- run --output json > /tmp/llm-judged-results.json || true
+
+          echo "--- JSON Results ---"
+          cat /tmp/llm-judged-results.json
+
+      - name: Upload final results
+        uses: actions/upload-artifact@v4
+        if: always()
+        with:
+          name: llm-judged-results
+          path: /tmp/llm-judged-results.json
+
+  cleanup:
+    name: Cleanup & Summary
+    runs-on: self-hosted
+    needs: [build, runtime, inference, llm-judge]
+    if: always()
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Stop Container
+        run: |
+          cd docker
+          docker compose down || true
+          echo "Container stopped"
+
+      - name: Summary
+        run: |
+          echo "## Full Pipeline Summary" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "| Stage | Status |" >> $GITHUB_STEP_SUMMARY
+          echo "|-------|--------|" >> $GITHUB_STEP_SUMMARY
+          echo "| Build Verification | ${{ needs.build.result }} |" >> $GITHUB_STEP_SUMMARY
+          echo "| Runtime Tests | ${{ needs.runtime.result }} |" >> $GITHUB_STEP_SUMMARY
+          echo "| Inference Tests | ${{ needs.inference.result }} |" >> $GITHUB_STEP_SUMMARY
+          echo "| LLM Judge | ${{ needs.llm-judge.result }} |" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "Commit: ${{ github.sha }}" >> $GITHUB_STEP_SUMMARY