Add GitHub Actions CI/CD pipeline and test framework

- Add .github/workflows/build-test.yml for automated testing
- Add tests/ directory with TypeScript test runner
- Add docs/CICD.md documentation
- Remove .gitlab-ci.yml (migrated to GitHub Actions)
- Update .gitignore for test artifacts

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

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

tests/testcases/runtime/TC-RUNTIME-001.yml

@@ -0,0 +1,31 @@
+id: TC-RUNTIME-001
+name: Container Startup
+suite: runtime
+priority: 1
+timeout: 120000
+
+dependencies:
+  - TC-BUILD-002
+
+steps:
+  - name: Stop existing container
+    command: cd docker && docker compose down 2>/dev/null || true
+
+  - name: Start container with GPU
+    command: cd docker && docker compose up -d
+
+  - name: Wait for startup
+    command: sleep 15
+
+  - name: Check container status
+    command: cd docker && docker compose ps
+
+criteria: |
+  The ollama37 container should start successfully with GPU access.
+
+  Expected:
+  - Container starts without errors
+  - docker compose ps shows container in "Up" state
+  - No "Exited" or "Restarting" status
+
+  Accept startup warnings. Container should be running.

tests/testcases/runtime/TC-RUNTIME-002.yml

@@ -0,0 +1,29 @@
+id: TC-RUNTIME-002
+name: GPU Detection
+suite: runtime
+priority: 2
+timeout: 60000
+
+dependencies:
+  - TC-RUNTIME-001
+
+steps:
+  - name: Check nvidia-smi inside container
+    command: docker exec ollama37 nvidia-smi
+
+  - name: Check CUDA libraries
+    command: docker exec ollama37 ldconfig -p | grep -i cuda | head -5
+
+  - name: Check Ollama GPU detection
+    command: cd docker && docker compose logs 2>&1 | grep -i gpu | head -10
+
+criteria: |
+  Tesla K80 GPU should be detected inside the container.
+
+  Expected:
+  - nvidia-smi shows Tesla K80 GPU(s)
+  - Driver version 470.x (or compatible)
+  - CUDA libraries are available (libcuda, libcublas, etc.)
+  - Ollama logs mention GPU detection
+
+  The K80 has 12GB VRAM per GPU. Accept variations in reported memory.

tests/testcases/runtime/TC-RUNTIME-003.yml

@@ -0,0 +1,39 @@
+id: TC-RUNTIME-003
+name: Health Check
+suite: runtime
+priority: 3
+timeout: 180000
+
+dependencies:
+  - TC-RUNTIME-001
+
+steps:
+  - name: Wait for health check
+    command: |
+      for i in {1..30}; do
+        STATUS=$(docker inspect ollama37 --format='{{.State.Health.Status}}' 2>/dev/null || echo "starting")
+        echo "Health status: $STATUS (attempt $i/30)"
+        if [ "$STATUS" = "healthy" ]; then
+          echo "Container is healthy"
+          exit 0
+        fi
+        sleep 5
+      done
+      echo "Health check timeout"
+      exit 1
+
+  - name: Test API endpoint
+    command: curl -s http://localhost:11434/api/tags
+
+  - name: Check Ollama version
+    command: docker exec ollama37 ollama --version
+
+criteria: |
+  Ollama server should be healthy and API responsive.
+
+  Expected:
+  - Container health status becomes "healthy"
+  - /api/tags endpoint returns JSON response (even if empty models)
+  - ollama --version shows version information
+
+  Accept any valid JSON response from API. Version format may vary.