fix: Resolve cache timeout issues in CI/CD pipelines

- Add fail-on-cache-miss: false to all cache actions in workflows
- Create improved runner configuration (config_cache_fixed.yaml) with:
  - Fixed cache host: host.docker.internal
  - Fixed cache port: 44029
  - Host network mode for better container networking
- Add cache troubleshooting scripts:
  - fix-cache-issues.sh (Linux/macOS)
  - fix-cache-issues.ps1 (Windows)
- Update all workflows: api-gateway, frontend, service-adapters, api-docs, ci

This resolves the 'connect ETIMEDOUT 172.31.0.3:44029' errors by:
1. Making cache failures non-fatal
2. Using proper Docker networking configuration
3. Providing tools to diagnose and fix cache issues

runners/fix-cache-issues.sh

@@ -0,0 +1,167 @@
+#!/bin/bash
+
+# Cache Troubleshooting and Fix Script for LabFusion CI/CD
+# This script helps diagnose and fix common cache timeout issues
+
+set -e
+
+echo "🔧 LabFusion Cache Troubleshooting Script"
+echo "=========================================="
+
+# Function to check if running in Docker
+check_docker() {
+    if [ -f /.dockerenv ]; then
+        echo "🐳 Running inside Docker container"
+        return 0
+    else
+        echo "🖥️  Running on host system"
+        return 1
+    fi
+}
+
+# Function to check cache service status
+check_cache_service() {
+    echo "📊 Checking cache service status..."
+    
+    # Check if cache service is running
+    if pgrep -f "act_runner" > /dev/null; then
+        echo "✅ act_runner process found"
+    else
+        echo "❌ act_runner process not found"
+        return 1
+    fi
+    
+    # Check cache directory
+    CACHE_DIR="${HOME}/.cache/actcache"
+    if [ -d "$CACHE_DIR" ]; then
+        echo "✅ Cache directory exists: $CACHE_DIR"
+        echo "   Size: $(du -sh "$CACHE_DIR" 2>/dev/null || echo "Unknown")"
+    else
+        echo "⚠️  Cache directory not found: $CACHE_DIR"
+        echo "   Creating cache directory..."
+        mkdir -p "$CACHE_DIR"
+    fi
+}
+
+# Function to test network connectivity
+test_network() {
+    echo "🌐 Testing network connectivity..."
+    
+    # Test basic connectivity
+    if ping -c 1 8.8.8.8 > /dev/null 2>&1; then
+        echo "✅ Internet connectivity OK"
+    else
+        echo "❌ Internet connectivity failed"
+    fi
+    
+    # Test Docker daemon
+    if docker info > /dev/null 2>&1; then
+        echo "✅ Docker daemon accessible"
+    else
+        echo "❌ Docker daemon not accessible"
+    fi
+}
+
+# Function to fix common cache issues
+fix_cache_issues() {
+    echo "🔧 Applying cache fixes..."
+    
+    # Create cache directory with proper permissions
+    CACHE_DIR="${HOME}/.cache/actcache"
+    mkdir -p "$CACHE_DIR"
+    chmod 755 "$CACHE_DIR"
+    
+    # Set proper environment variables
+    export ACTIONS_CACHE_URL="http://host.docker.internal:44029/"
+    export ACTIONS_RUNTIME_URL="http://host.docker.internal:44029/"
+    
+    echo "✅ Cache directory created and configured"
+    echo "✅ Environment variables set"
+}
+
+# Function to restart cache service
+restart_cache_service() {
+    echo "🔄 Restarting cache service..."
+    
+    # Stop existing runners
+    pkill -f "act_runner" || true
+    sleep 2
+    
+    # Start with fixed configuration
+    if [ -f "config_cache_fixed.yaml" ]; then
+        echo "✅ Using fixed configuration"
+        nohup ./act_runner daemon --config config_cache_fixed.yaml > runner.log 2>&1 &
+    else
+        echo "⚠️  Fixed configuration not found, using default"
+        nohup ./act_runner daemon > runner.log 2>&1 &
+    fi
+    
+    sleep 5
+    
+    if pgrep -f "act_runner" > /dev/null; then
+        echo "✅ Cache service restarted successfully"
+    else
+        echo "❌ Failed to restart cache service"
+        return 1
+    fi
+}
+
+# Function to test cache functionality
+test_cache() {
+    echo "🧪 Testing cache functionality..."
+    
+    # Create a test cache entry
+    TEST_KEY="test-cache-$(date +%s)"
+    TEST_VALUE="test-value-$(date +%s)"
+    
+    echo "   Creating test cache entry: $TEST_KEY"
+    echo "$TEST_VALUE" > "/tmp/cache-test"
+    
+    # Try to restore (this will fail but we can check the error)
+    echo "   Testing cache restore..."
+    if curl -s "http://host.docker.internal:44029/cache/$TEST_KEY" > /dev/null 2>&1; then
+        echo "✅ Cache service responding"
+    else
+        echo "❌ Cache service not responding"
+        echo "   This is expected if no cache entry exists"
+    fi
+    
+    # Clean up
+    rm -f "/tmp/cache-test"
+}
+
+# Main execution
+main() {
+    echo "Starting cache troubleshooting..."
+    echo ""
+    
+    check_docker
+    echo ""
+    
+    check_cache_service
+    echo ""
+    
+    test_network
+    echo ""
+    
+    fix_cache_issues
+    echo ""
+    
+    restart_cache_service
+    echo ""
+    
+    test_cache
+    echo ""
+    
+    echo "🎉 Cache troubleshooting complete!"
+    echo ""
+    echo "Next steps:"
+    echo "1. Check runner logs: tail -f runner.log"
+    echo "2. Test a workflow to see if cache issues are resolved"
+    echo "3. If issues persist, check Docker networking configuration"
+    echo ""
+    echo "For more help, see: https://gitea.com/gitea/act_runner/src/branch/main/docs/configuration.md"
+}
+
+# Run main function
+main "$@"