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

.gitea/workflows/api-docs.yml

@@ -43,6 +43,7 @@ jobs:
           ${{ runner.os }}-node-${{ matrix.node-version }}-
           ${{ runner.os }}-node-
           ${{ runner.os }}-
+        fail-on-cache-miss: false
       id: npm-cache
       
     - name: Cache status
@@ -136,6 +137,7 @@ jobs:
         restore-keys: |
           ${{ runner.os }}-node-18-
           ${{ runner.os }}-node-
+        fail-on-cache-miss: false
         
     - name: Install dependencies
       run: |

.gitea/workflows/api-gateway.yml

@@ -50,6 +50,7 @@ jobs:
         restore-keys: |
           ${{ runner.os }}-m2-${{ matrix.java-version }}-
           ${{ runner.os }}-m2-
+        fail-on-cache-miss: false
         
     - name: Validate POM
       run: ./mvnw validate
@@ -114,6 +115,7 @@ jobs:
         path: ~/.m2
         key: ${{ runner.os }}-m2-${{ hashFiles('**/pom.xml') }}
         restore-keys: ${{ runner.os }}-m2
+        fail-on-cache-miss: false
         
     - name: Build application
       run: ./mvnw clean package -DskipTests

.gitea/workflows/ci.yml

@@ -34,6 +34,7 @@ jobs:
         path: ~/.m2
         key: ${{ runner.os }}-m2-${{ hashFiles('**/pom.xml') }}
         restore-keys: ${{ runner.os }}-m2
+        fail-on-cache-miss: false
         
     - name: Run tests
       run: mvn test
@@ -69,6 +70,7 @@ jobs:
         path: ~/.cache/pip
         key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements.txt') }}
         restore-keys: ${{ runner.os }}-pip
+        fail-on-cache-miss: false
         
     - name: Install dependencies
       run: |
@@ -121,6 +123,7 @@ jobs:
         restore-keys: |
           ${{ runner.os }}-node-18-
           ${{ runner.os }}-node-
+        fail-on-cache-miss: false
         
     - name: Install dependencies
       run: |
@@ -166,6 +169,7 @@ jobs:
         restore-keys: |
           ${{ runner.os }}-node-18-
           ${{ runner.os }}-node-
+        fail-on-cache-miss: false
         
     - name: Install dependencies
       run: |

.gitea/workflows/frontend.yml

@@ -43,6 +43,7 @@ jobs:
           ${{ runner.os }}-node-${{ matrix.node-version }}-
           ${{ runner.os }}-node-
           ${{ runner.os }}-
+        fail-on-cache-miss: false
         
     - name: Install dependencies
       run: |

.gitea/workflows/service-adapters.yml

@@ -43,6 +43,7 @@ jobs:
           ${{ runner.os }}-pip-${{ matrix.python-version }}-
           ${{ runner.os }}-pip-
           ${{ runner.os }}-
+        fail-on-cache-miss: false
       id: pip-cache
       
     - name: Cache status

runners/config_cache_fixed.yaml

@@ -0,0 +1,109 @@
+# Improved configuration file with cache networking fixes
+# This configuration addresses common cache timeout issues in self-hosted runners
+
+log:
+  # The level of logging, can be trace, debug, info, warn, error, fatal
+  level: info
+
+runner:
+  # Where to store the registration result.
+  file: .runner
+  # Execute how many tasks concurrently at the same time.
+  capacity: 1
+  # Extra environment variables to run jobs.
+  envs:
+    A_TEST_ENV_NAME_1: a_test_env_value_1
+    A_TEST_ENV_NAME_2: a_test_env_value_2
+  # Extra environment variables to run jobs from a file.
+  # It will be ignored if it's empty or the file doesn't exist.
+  env_file: .env
+  # The timeout for a job to be finished.
+  # Please note that the Gitea instance also has a timeout (3h by default) for the job.
+  # So the job could be stopped by the Gitea instance if it's timeout is shorter than this.
+  timeout: 3h
+  # The timeout for the runner to wait for running jobs to finish when shutting down.
+  # Any running jobs that haven't finished after this timeout will be cancelled.
+  shutdown_timeout: 0s
+  # Whether skip verifying the TLS certificate of the Gitea instance.
+  insecure: false
+  # The timeout for fetching the job from the Gitea instance.
+  fetch_timeout: 5s
+  # The interval for fetching the job from the Gitea instance.
+  fetch_interval: 2s
+  # The github_mirror of a runner is used to specify the mirror address of the github that pulls the action repository.
+  # It works when something like `uses: actions/checkout@v4` is used and DEFAULT_ACTIONS_URL is set to github,
+  # and github_mirror is not empty. In this case,
+  # it replaces https://github.com with the value here, which is useful for some special network environments.
+  github_mirror: ''
+  # The labels of a runner are used to determine which jobs the runner can run, and how to run them.
+  # Like: "macos-arm64:host" or "ubuntu-latest:docker://docker.gitea.com/runner-images:ubuntu-latest"
+  # Find more images provided by Gitea at https://gitea.com/docker.gitea.com/runner-images .
+  # If it's empty when registering, it will ask for inputting labels.
+  # If it's empty when execute `daemon`, will use labels in `.runner` file.
+  labels:
+    # Fallback images (checked last)
+    - "ubuntu-latest:docker://docker.gitea.com/runner-images:ubuntu-latest"
+    - "self-hosted:docker://docker.gitea.com/runner-images:ubuntu-latest"
+
+cache:
+  # Enable cache server to use actions/cache.
+  enabled: true
+  # The directory to store the cache data.
+  # If it's empty, the cache data will be stored in $HOME/.cache/actcache.
+  dir: ""
+  # The host of the cache server.
+  # Use host.docker.internal to allow containers to access the host
+  # This fixes the common networking issue where containers can't reach the cache server
+  host: "host.docker.internal"
+  # Use a fixed port instead of random to avoid connection issues
+  port: 44029
+  # The external cache server URL. Valid only when enable is true.
+  # If it's specified, act_runner will use this URL as the ACTIONS_CACHE_URL rather than start a server by itself.
+  # The URL should generally end with "/".
+  external_server: ""
+
+container:
+  # Use host network to avoid Docker networking issues with cache
+  # This ensures containers can access the cache server on the host
+  network: "host"
+  # Whether to use privileged mode or not when launching task containers (privileged mode is required for Docker-in-Docker).
+  privileged: false
+  # And other options to be used when the container is started (eg, --add-host=my.gitea.url:host-gateway).
+  options:
+  # The parent directory of a job's working directory.
+  # NOTE: There is no need to add the first '/' of the path as act_runner will add it automatically. 
+  # If the path starts with '/', the '/' will be trimmed.
+  # For example, if the parent directory is /path/to/my/dir, workdir_parent should be path/to/my/dir
+  # If it's empty, /workspace will be used.
+  workdir_parent:
+  # Volumes (including bind mounts) can be mounted to containers. Glob syntax is supported, see https://github.com/gobwas/glob
+  # You can specify multiple volumes. If the sequence is empty, no volumes can be mounted.
+  # For example, if you only allow containers to mount the `data` volume and all the json files in `/src`, you should change the config to:
+  # valid_volumes:
+  #   - data
+  #   - /src/*.json
+  # If you want to allow any volume, please use the following configuration:
+  # valid_volumes:
+  #   - '**'
+  valid_volumes: []
+  # overrides the docker client host with the specified one.
+  # If it's empty, act_runner will find an available docker host automatically.
+  # If it's "-", act_runner will find an available docker host automatically, but the docker host won't be mounted to the job containers and service containers.
+  # If it's not empty or "-", the specified docker host will be used. An error will be returned if it doesn't work.
+  docker_host: ""
+  # Docker registry authentication to avoid rate limits
+  docker_username: gschrooyen
+  docker_password: ${DOCKER_PASSWORD}
+  # Pull docker image(s) even if already present
+  force_pull: false
+  # Rebuild docker image(s) even if already present
+  force_rebuild: false
+  # Always require a reachable docker daemon, even if not required by act_runner
+  require_docker: false
+  # Timeout to wait for the docker daemon to be reachable, if docker is required by require_docker or act_runner
+  docker_timeout: 0s
+
+host:
+  # The parent directory of a job's working directory.
+  # If it's empty, $HOME/.cache/act/ will be used.
+  workdir_parent:

runners/fix-cache-issues.ps1

@@ -0,0 +1,176 @@
+# Cache Troubleshooting and Fix Script for LabFusion CI/CD
+# This script helps diagnose and fix common cache timeout issues
+
+Write-Host "🔧 LabFusion Cache Troubleshooting Script" -ForegroundColor Cyan
+Write-Host "==========================================" -ForegroundColor Cyan
+
+# Function to check if running in Docker
+function Test-Docker {
+    if (Test-Path "/.dockerenv") {
+        Write-Host "🐳 Running inside Docker container" -ForegroundColor Green
+        return $true
+    } else {
+        Write-Host "🖥️  Running on host system" -ForegroundColor Yellow
+        return $false
+    }
+}
+
+# Function to check cache service status
+function Test-CacheService {
+    Write-Host "📊 Checking cache service status..." -ForegroundColor Cyan
+    
+    # Check if act_runner process is running
+    $processes = Get-Process -Name "act_runner" -ErrorAction SilentlyContinue
+    if ($processes) {
+        Write-Host "✅ act_runner process found" -ForegroundColor Green
+    } else {
+        Write-Host "❌ act_runner process not found" -ForegroundColor Red
+        return $false
+    }
+    
+    # Check cache directory
+    $cacheDir = "$env:USERPROFILE\.cache\actcache"
+    if (Test-Path $cacheDir) {
+        Write-Host "✅ Cache directory exists: $cacheDir" -ForegroundColor Green
+        $size = (Get-ChildItem $cacheDir -Recurse | Measure-Object -Property Length -Sum).Sum
+        Write-Host "   Size: $([math]::Round($size / 1MB, 2)) MB" -ForegroundColor Gray
+    } else {
+        Write-Host "⚠️  Cache directory not found: $cacheDir" -ForegroundColor Yellow
+        Write-Host "   Creating cache directory..." -ForegroundColor Yellow
+        New-Item -ItemType Directory -Path $cacheDir -Force | Out-Null
+    }
+    
+    return $true
+}
+
+# Function to test network connectivity
+function Test-NetworkConnectivity {
+    Write-Host "🌐 Testing network connectivity..." -ForegroundColor Cyan
+    
+    # Test basic connectivity
+    try {
+        $ping = Test-Connection -ComputerName "8.8.8.8" -Count 1 -Quiet
+        if ($ping) {
+            Write-Host "✅ Internet connectivity OK" -ForegroundColor Green
+        } else {
+            Write-Host "❌ Internet connectivity failed" -ForegroundColor Red
+        }
+    } catch {
+        Write-Host "❌ Internet connectivity test failed: $($_.Exception.Message)" -ForegroundColor Red
+    }
+    
+    # Test Docker daemon
+    try {
+        docker info | Out-Null
+        Write-Host "✅ Docker daemon accessible" -ForegroundColor Green
+    } catch {
+        Write-Host "❌ Docker daemon not accessible" -ForegroundColor Red
+    }
+}
+
+# Function to fix common cache issues
+function Fix-CacheIssues {
+    Write-Host "🔧 Applying cache fixes..." -ForegroundColor Cyan
+    
+    # Create cache directory with proper permissions
+    $cacheDir = "$env:USERPROFILE\.cache\actcache"
+    New-Item -ItemType Directory -Path $cacheDir -Force | Out-Null
+    
+    # Set proper environment variables
+    $env:ACTIONS_CACHE_URL = "http://host.docker.internal:44029/"
+    $env:ACTIONS_RUNTIME_URL = "http://host.docker.internal:44029/"
+    
+    Write-Host "✅ Cache directory created and configured" -ForegroundColor Green
+    Write-Host "✅ Environment variables set" -ForegroundColor Green
+}
+
+# Function to restart cache service
+function Restart-CacheService {
+    Write-Host "🔄 Restarting cache service..." -ForegroundColor Cyan
+    
+    # Stop existing runners
+    Get-Process -Name "act_runner" -ErrorAction SilentlyContinue | Stop-Process -Force
+    Start-Sleep -Seconds 2
+    
+    # Start with fixed configuration
+    if (Test-Path "config_cache_fixed.yaml") {
+        Write-Host "✅ Using fixed configuration" -ForegroundColor Green
+        Start-Process -FilePath ".\act_runner.exe" -ArgumentList "daemon", "--config", "config_cache_fixed.yaml" -WindowStyle Hidden
+    } else {
+        Write-Host "⚠️  Fixed configuration not found, using default" -ForegroundColor Yellow
+        Start-Process -FilePath ".\act_runner.exe" -ArgumentList "daemon" -WindowStyle Hidden
+    }
+    
+    Start-Sleep -Seconds 5
+    
+    $processes = Get-Process -Name "act_runner" -ErrorAction SilentlyContinue
+    if ($processes) {
+        Write-Host "✅ Cache service restarted successfully" -ForegroundColor Green
+    } else {
+        Write-Host "❌ Failed to restart cache service" -ForegroundColor Red
+        return $false
+    }
+    
+    return $true
+}
+
+# Function to test cache functionality
+function Test-CacheFunctionality {
+    Write-Host "🧪 Testing cache functionality..." -ForegroundColor Cyan
+    
+    # Create a test cache entry
+    $testKey = "test-cache-$(Get-Date -Format 'yyyyMMddHHmmss')"
+    $testValue = "test-value-$(Get-Date -Format 'yyyyMMddHHmmss')"
+    
+    Write-Host "   Creating test cache entry: $testKey" -ForegroundColor Gray
+    $testValue | Out-File -FilePath "C:\temp\cache-test.txt" -Force
+    
+    # Try to test cache service (this will fail but we can check the error)
+    Write-Host "   Testing cache service response..." -ForegroundColor Gray
+    try {
+        $response = Invoke-WebRequest -Uri "http://host.docker.internal:44029/cache/$testKey" -TimeoutSec 5 -ErrorAction SilentlyContinue
+        Write-Host "✅ Cache service responding" -ForegroundColor Green
+    } catch {
+        Write-Host "❌ Cache service not responding: $($_.Exception.Message)" -ForegroundColor Yellow
+        Write-Host "   This is expected if no cache entry exists" -ForegroundColor Gray
+    }
+    
+    # Clean up
+    Remove-Item "C:\temp\cache-test.txt" -ErrorAction SilentlyContinue
+}
+
+# Main execution
+function Main {
+    Write-Host "Starting cache troubleshooting..." -ForegroundColor Cyan
+    Write-Host ""
+    
+    Test-Docker
+    Write-Host ""
+    
+    Test-CacheService
+    Write-Host ""
+    
+    Test-NetworkConnectivity
+    Write-Host ""
+    
+    Fix-CacheIssues
+    Write-Host ""
+    
+    Restart-CacheService
+    Write-Host ""
+    
+    Test-CacheFunctionality
+    Write-Host ""
+    
+    Write-Host "🎉 Cache troubleshooting complete!" -ForegroundColor Green
+    Write-Host ""
+    Write-Host "Next steps:" -ForegroundColor Yellow
+    Write-Host "1. Check runner logs in the current directory" -ForegroundColor White
+    Write-Host "2. Test a workflow to see if cache issues are resolved" -ForegroundColor White
+    Write-Host "3. If issues persist, check Docker networking configuration" -ForegroundColor White
+    Write-Host ""
+    Write-Host "For more help, see: https://gitea.com/gitea/act_runner/src/branch/main/docs/configuration.md" -ForegroundColor Cyan
+}
+
+# Run main function
+Main

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/$TEST_KEY" > /dev/null 2>&1; then
+        echo "✅ Cache service responding"
+    else
+        echo "❌ Cache service not responding"
+        echo "   This is expected if no cache entry exists"
+    fi
+    
+    # Clean up
+    rm -f "/tmp/cache-test"
+}
+
+# Main execution
+main() {
+    echo "Starting cache troubleshooting..."
+    echo ""
+    
+    check_docker
+    echo ""
+    
+    check_cache_service
+    echo ""
+    
+    test_network
+    echo ""
+    
+    fix_cache_issues
+    echo ""
+    
+    restart_cache_service
+    echo ""
+    
+    test_cache
+    echo ""
+    
+    echo "🎉 Cache troubleshooting complete!"
+    echo ""
+    echo "Next steps:"
+    echo "1. Check runner logs: tail -f runner.log"
+    echo "2. Test a workflow to see if cache issues are resolved"
+    echo "3. If issues persist, check Docker networking configuration"
+    echo ""
+    echo "For more help, see: https://gitea.com/gitea/act_runner/src/branch/main/docs/configuration.md"
+}
+
+# Run main function
+main "$@"