From f6991d283d14c81da0eb2048eab4822436c22638 Mon Sep 17 00:00:00 2001
From: Ryan VanGundy <85766511+rmvangun@users.noreply.github.com>
Date: Mon, 27 Oct 2025 12:05:58 -0400
Subject: [PATCH 01/11] chore: Collect talos node support bundles

Signed-off-by: Ryan VanGundy <85766511+rmvangun@users.noreply.github.com>
---
 .github/scripts/collect-talos-diagnostics.sh | 151 +++++++++++++++++++
 .github/workflows/ci.yaml                    |  17 +++
 2 files changed, 168 insertions(+)
 create mode 100755 .github/scripts/collect-talos-diagnostics.sh

diff --git a/.github/scripts/collect-talos-diagnostics.sh b/.github/scripts/collect-talos-diagnostics.sh
new file mode 100755
index 00000000..77a8339c
--- /dev/null
+++ b/.github/scripts/collect-talos-diagnostics.sh
@@ -0,0 +1,151 @@
+#!/bin/bash
+
+# Script to collect talosctl diagnostics for support bundle
+# This script will be run as part of the support bundle collection process
+
+set -euo pipefail
+
+# Create output directory
+TALOS_DIAGNOSTICS_DIR="${1:-/tmp/talos-diagnostics}"
+mkdir -p "$TALOS_DIAGNOSTICS_DIR"
+
+# Function to safely run talosctl commands
+run_talosctl() {
+    local cmd="$1"
+    local output_file="$2"
+    local description="$3"
+    
+    echo "Collecting: $description"
+    if eval "$cmd" > "$output_file" 2>&1; then
+        echo "✓ Successfully collected: $description"
+    else
+        echo "⚠ Failed to collect: $description (exit code: $?)"
+        echo "Command failed: $cmd" > "$output_file"
+    fi
+}
+
+# Check if talosctl is available
+if ! command -v talosctl &> /dev/null; then
+    echo "talosctl not found, skipping talos diagnostics"
+    exit 0
+fi
+
+# Get cluster nodes (if available)
+NODES=""
+if kubectl get nodes -o jsonpath='{.items[*].status.addresses[?(@.type=="InternalIP")].address}' 2>/dev/null | grep -q .; then
+    NODES=$(kubectl get nodes -o jsonpath='{.items[*].status.addresses[?(@.type=="InternalIP")].address}' 2>/dev/null | tr ' ' ',')
+fi
+
+# If no nodes found via kubectl, try to get from talosctl config
+if [ -z "$NODES" ]; then
+    if talosctl config info 2>/dev/null | grep -q "endpoints:"; then
+        NODES=$(talosctl config info 2>/dev/null | grep "endpoints:" | cut -d: -f2 | tr -d ' ' | tr ',' ' ')
+    fi
+fi
+
+# Set node flag if we have nodes
+NODE_FLAG=""
+if [ -n "$NODES" ]; then
+    NODE_FLAG="--nodes $NODES"
+fi
+
+echo "Collecting Talos diagnostics to: $TALOS_DIAGNOSTICS_DIR"
+echo "Target nodes: ${NODES:-'auto-detect'}"
+
+# 1. Comprehensive support bundle (most important)
+run_talosctl "talosctl support $NODE_FLAG --output $TALOS_DIAGNOSTICS_DIR/talos-support-bundle.tar.gz" \
+    "$TALOS_DIAGNOSTICS_DIR/talos-support-bundle.tar.gz" \
+    "Complete Talos support bundle"
+
+# 2. Cluster health check
+run_talosctl "talosctl health $NODE_FLAG" \
+    "$TALOS_DIAGNOSTICS_DIR/talos-health.txt" \
+    "Cluster health status"
+
+# 3. Version information
+run_talosctl "talosctl version $NODE_FLAG" \
+    "$TALOS_DIAGNOSTICS_DIR/talos-version.txt" \
+    "Talos version information"
+
+# 4. Node information (if we have specific nodes)
+if [ -n "$NODES" ]; then
+    for node in $(echo "$NODES" | tr ',' ' '); do
+        node_dir="$TALOS_DIAGNOSTICS_DIR/node-$node"
+        mkdir -p "$node_dir"
+        
+        # Kernel logs
+        run_talosctl "talosctl dmesg --nodes $node" \
+            "$node_dir/dmesg.txt" \
+            "Kernel logs for node $node"
+        
+        # Running processes
+        run_talosctl "talosctl processes --nodes $node" \
+            "$node_dir/processes.txt" \
+            "Running processes for node $node"
+        
+        # Memory usage
+        run_talosctl "talosctl memory --nodes $node" \
+            "$node_dir/memory.txt" \
+            "Memory usage for node $node"
+        
+        # Network connections
+        run_talosctl "talosctl netstat --nodes $node" \
+            "$node_dir/netstat.txt" \
+            "Network connections for node $node"
+        
+        # Disk usage
+        run_talosctl "talosctl usage --nodes $node" \
+            "$node_dir/disk-usage.txt" \
+            "Disk usage for node $node"
+        
+        # Running containers
+        run_talosctl "talosctl containers --nodes $node" \
+            "$node_dir/containers.txt" \
+            "Running containers for node $node"
+        
+        # Service status
+        run_talosctl "talosctl service --nodes $node" \
+            "$node_dir/services.txt" \
+            "Service status for node $node"
+        
+        # Mount information
+        run_talosctl "talosctl mounts --nodes $node" \
+            "$node_dir/mounts.txt" \
+            "Mount information for node $node"
+    done
+fi
+
+# 5. etcd status (control plane nodes)
+run_talosctl "talosctl etcd status $NODE_FLAG" \
+    "$TALOS_DIAGNOSTICS_DIR/etcd-status.txt" \
+    "etcd cluster status"
+
+# 6. Cluster configuration
+run_talosctl "talosctl get config $NODE_FLAG -o yaml" \
+    "$TALOS_DIAGNOSTICS_DIR/talos-config.yaml" \
+    "Talos cluster configuration"
+
+# 7. Available resource definitions
+run_talosctl "talosctl get rd $NODE_FLAG" \
+    "$TALOS_DIAGNOSTICS_DIR/resource-definitions.txt" \
+    "Available resource definitions"
+
+# 8. COSI resources (if accessible)
+run_talosctl "talosctl get machines $NODE_FLAG -o yaml" \
+    "$TALOS_DIAGNOSTICS_DIR/machines.yaml" \
+    "Machine resources"
+
+# 9. Events (if accessible)
+run_talosctl "talosctl events $NODE_FLAG --duration 1h" \
+    "$TALOS_DIAGNOSTICS_DIR/talos-events.txt" \
+    "Talos events (last hour)"
+
+echo "Talos diagnostics collection completed"
+echo "Output directory: $TALOS_DIAGNOSTICS_DIR"
+ls -la "$TALOS_DIAGNOSTICS_DIR"
+
+# Create tar.gz archive in the parent directory (same pattern as Windsor state)
+TAR_FILE="$(dirname "$TALOS_DIAGNOSTICS_DIR")/talos-diagnostics.tar.gz"
+echo "Creating archive: $TAR_FILE"
+tar -czf "$TAR_FILE" -C "$(dirname "$TALOS_DIAGNOSTICS_DIR")" "$(basename "$TALOS_DIAGNOSTICS_DIR")"
+echo "✓ Talos diagnostics archived to: $TAR_FILE"
diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
index 109594f3..647171a7 100644
--- a/.github/workflows/ci.yaml
+++ b/.github/workflows/ci.yaml
@@ -165,6 +165,23 @@ jobs:
         run: |
           tar --exclude='.docker-cache' --exclude='.terraform' -czf support-bundles/windsor-state.tar.gz contexts/local .windsor
 
+      - name: Collect Talos Diagnostics
+        if: always()
+        run: |
+          # Install talosctl if not available
+          if ! command -v talosctl &> /dev/null; then
+            echo "Installing talosctl..."
+            cd "$(mktemp -d)" &&
+            curl -fsSLO "https://github.com/siderolabs/talos/releases/latest/download/talosctl-linux-amd64" &&
+            chmod +x talosctl-linux-amd64 &&
+            sudo mv talosctl-linux-amd64 /usr/local/bin/talosctl &&
+            cd - &&
+            rm -rf "$OLDPWD"
+          fi
+          
+          # Run talos diagnostics collection
+          .github/scripts/collect-talos-diagnostics.sh support-bundles/talos-diagnostics
+
       - name: Collect support bundle
         if: always()
         run: |

From 50716face6b599cac44a61350dc2fc5dd512cf91 Mon Sep 17 00:00:00 2001
From: Ryan VanGundy <85766511+rmvangun@users.noreply.github.com>
Date: Mon, 27 Oct 2025 13:41:13 -0400
Subject: [PATCH 02/11] Test

Signed-off-by: Ryan VanGundy <85766511+rmvangun@users.noreply.github.com>
---
 .github/scripts/collect-talos-diagnostics.sh | 34 ++++++++++++++++----
 1 file changed, 28 insertions(+), 6 deletions(-)

diff --git a/.github/scripts/collect-talos-diagnostics.sh b/.github/scripts/collect-talos-diagnostics.sh
index 77a8339c..c61cb9ad 100755
--- a/.github/scripts/collect-talos-diagnostics.sh
+++ b/.github/scripts/collect-talos-diagnostics.sh
@@ -16,11 +16,16 @@ run_talosctl() {
     local description="$3"
     
     echo "Collecting: $description"
+    echo "Command: $cmd"
     if eval "$cmd" > "$output_file" 2>&1; then
         echo "✓ Successfully collected: $description"
     else
-        echo "⚠ Failed to collect: $description (exit code: $?)"
+        local exit_code=$?
+        echo "⚠ Failed to collect: $description (exit code: $exit_code)"
         echo "Command failed: $cmd" > "$output_file"
+        echo "Exit code: $exit_code" >> "$output_file"
+        echo "Error output:" >> "$output_file"
+        eval "$cmd" >> "$output_file" 2>&1 || true
     fi
 }
 
@@ -52,9 +57,16 @@ fi
 echo "Collecting Talos diagnostics to: $TALOS_DIAGNOSTICS_DIR"
 echo "Target nodes: ${NODES:-'auto-detect'}"
 
+# Debug: Show talosctl version and available commands
+echo "Talosctl version:"
+talosctl version --client 2>/dev/null || echo "Failed to get version"
+echo "Available talosctl commands:"
+talosctl --help 2>/dev/null | grep -A 100 "Available Commands:" | head -20 || echo "Failed to get help"
+
 # 1. Comprehensive support bundle (most important)
-run_talosctl "talosctl support $NODE_FLAG --output $TALOS_DIAGNOSTICS_DIR/talos-support-bundle.tar.gz" \
-    "$TALOS_DIAGNOSTICS_DIR/talos-support-bundle.tar.gz" \
+# Note: talosctl support requires specific node targeting, so we'll try without --output first
+run_talosctl "talosctl support $NODE_FLAG" \
+    "$TALOS_DIAGNOSTICS_DIR/talos-support-bundle.txt" \
     "Complete Talos support bundle"
 
 # 2. Cluster health check
@@ -93,8 +105,8 @@ if [ -n "$NODES" ]; then
             "$node_dir/netstat.txt" \
             "Network connections for node $node"
         
-        # Disk usage
-        run_talosctl "talosctl usage --nodes $node" \
+        # Disk usage (using df instead of usage which might not be available)
+        run_talosctl "talosctl df --nodes $node" \
             "$node_dir/disk-usage.txt" \
             "Disk usage for node $node"
         
@@ -120,11 +132,16 @@ run_talosctl "talosctl etcd status $NODE_FLAG" \
     "$TALOS_DIAGNOSTICS_DIR/etcd-status.txt" \
     "etcd cluster status"
 
-# 6. Cluster configuration
+# 6. Cluster configuration (try different approaches)
 run_talosctl "talosctl get config $NODE_FLAG -o yaml" \
     "$TALOS_DIAGNOSTICS_DIR/talos-config.yaml" \
     "Talos cluster configuration"
 
+# Alternative: try to get machine config
+run_talosctl "talosctl get machineconfig $NODE_FLAG -o yaml" \
+    "$TALOS_DIAGNOSTICS_DIR/talos-machine-config.yaml" \
+    "Talos machine configuration"
+
 # 7. Available resource definitions
 run_talosctl "talosctl get rd $NODE_FLAG" \
     "$TALOS_DIAGNOSTICS_DIR/resource-definitions.txt" \
@@ -135,6 +152,11 @@ run_talosctl "talosctl get machines $NODE_FLAG -o yaml" \
     "$TALOS_DIAGNOSTICS_DIR/machines.yaml" \
     "Machine resources"
 
+# Alternative: try to get nodes
+run_talosctl "talosctl get nodes $NODE_FLAG -o yaml" \
+    "$TALOS_DIAGNOSTICS_DIR/nodes.yaml" \
+    "Node resources"
+
 # 9. Events (if accessible)
 run_talosctl "talosctl events $NODE_FLAG --duration 1h" \
     "$TALOS_DIAGNOSTICS_DIR/talos-events.txt" \

From 8310f1b80828f6733c8672bc7c63ec935899138f Mon Sep 17 00:00:00 2001
From: Ryan VanGundy <85766511+rmvangun@users.noreply.github.com>
Date: Mon, 27 Oct 2025 15:37:14 -0400
Subject: [PATCH 03/11] Grab talos support diagnostics

Signed-off-by: Ryan VanGundy <85766511+rmvangun@users.noreply.github.com>
---
 .github/scripts/collect-talos-diagnostics.sh | 228 ++++++++++---------
 .github/workflows/ci.yaml                    |   4 +-
 2 files changed, 123 insertions(+), 109 deletions(-)

diff --git a/.github/scripts/collect-talos-diagnostics.sh b/.github/scripts/collect-talos-diagnostics.sh
index c61cb9ad..5f41fcc2 100755
--- a/.github/scripts/collect-talos-diagnostics.sh
+++ b/.github/scripts/collect-talos-diagnostics.sh
@@ -5,6 +5,9 @@
 
 set -euo pipefail
 
+# Handle script interruption gracefully
+trap 'echo "Script interrupted, cleaning up..."; exit 130' INT TERM
+
 # Create output directory
 TALOS_DIAGNOSTICS_DIR="${1:-/tmp/talos-diagnostics}"
 mkdir -p "$TALOS_DIAGNOSTICS_DIR"
@@ -29,29 +32,80 @@ run_talosctl() {
     fi
 }
 
+# Function to run commands with timeout (fallback if timeout command not available)
+run_with_timeout() {
+    local timeout_seconds="$1"
+    local cmd="$2"
+    local output_file="$3"
+    local description="$4"
+    
+    echo "Collecting: $description"
+    echo "Command: $cmd"
+    
+    # Try to use timeout command if available
+    if command -v timeout >/dev/null 2>&1; then
+        if timeout "$timeout_seconds" bash -c "$cmd" > "$output_file" 2>&1; then
+            echo "✓ Successfully collected: $description"
+        else
+            local exit_code=$?
+            echo "⚠ Failed to collect: $description (exit code: $exit_code)"
+            echo "Command failed: $cmd" > "$output_file"
+            echo "Exit code: $exit_code" >> "$output_file"
+        fi
+    else
+        # Fallback: run without timeout but with background process and kill
+        echo "Warning: timeout command not available, using background process with kill"
+        (
+            eval "$cmd" > "$output_file" 2>&1 &
+            local pid=$!
+            sleep "$timeout_seconds"
+            if kill -0 "$pid" 2>/dev/null; then
+                echo "Command timed out, killing process"
+                kill -TERM "$pid" 2>/dev/null
+                sleep 2
+                kill -KILL "$pid" 2>/dev/null
+                echo "Command timed out after ${timeout_seconds}s" >> "$output_file"
+                echo "⚠ Failed to collect: $description (timeout)"
+            else
+                wait "$pid"
+                local wait_exit_code=$?
+                if [ $wait_exit_code -eq 0 ]; then
+                    echo "✓ Successfully collected: $description"
+                else
+                    echo "⚠ Failed to collect: $description (exit code: $wait_exit_code)"
+                fi
+            fi
+        )
+    fi
+}
+
 # Check if talosctl is available
 if ! command -v talosctl &> /dev/null; then
     echo "talosctl not found, skipping talos diagnostics"
     exit 0
 fi
 
-# Get cluster nodes (if available)
+# Determine node targeting strategy based on environment
+NODE_FLAG=""
 NODES=""
-if kubectl get nodes -o jsonpath='{.items[*].status.addresses[?(@.type=="InternalIP")].address}' 2>/dev/null | grep -q .; then
-    NODES=$(kubectl get nodes -o jsonpath='{.items[*].status.addresses[?(@.type=="InternalIP")].address}' 2>/dev/null | tr ' ' ',')
-fi
-
-# If no nodes found via kubectl, try to get from talosctl config
-if [ -z "$NODES" ]; then
-    if talosctl config info 2>/dev/null | grep -q "endpoints:"; then
-        NODES=$(talosctl config info 2>/dev/null | grep "endpoints:" | cut -d: -f2 | tr -d ' ' | tr ',' ' ')
-    fi
-fi
 
-# Set node flag if we have nodes
-NODE_FLAG=""
-if [ -n "$NODES" ]; then
-    NODE_FLAG="--nodes $NODES"
+# Check if we're in a local Docker Desktop environment (has controlplane-1 node)
+if talosctl get nodes 2>/dev/null | grep -q "controlplane-1"; then
+    echo "Detected local Docker Desktop environment, using node names"
+    NODE_FLAG="-n controlplane-1"
+    NODES="controlplane-1"
+# Check if we have specific node IPs from kubectl (CI environment)
+elif kubectl get nodes -o jsonpath='{.items[*].status.addresses[?(@.type=="InternalIP")].address}' 2>/dev/null | grep -q .; then
+    NODES=$(kubectl get nodes -o jsonpath='{.items[*].status.addresses[?(@.type=="InternalIP")].address}' 2>/dev/null | tr ' ' ',')
+    NODE_FLAG="-n $NODES"
+    echo "Detected CI environment, using node IPs: $NODES"
+# Fallback: try to get from talosctl config
+elif talosctl config info 2>/dev/null | grep -q "endpoints:"; then
+    NODES=$(talosctl config info 2>/dev/null | grep "endpoints:" | cut -d: -f2 | tr -d ' ' | tr ',' ' ')
+    NODE_FLAG="-n $NODES"
+    echo "Using endpoints from talosctl config: $NODES"
+else
+    echo "No nodes detected, will attempt commands without node targeting"
 fi
 
 echo "Collecting Talos diagnostics to: $TALOS_DIAGNOSTICS_DIR"
@@ -63,105 +117,58 @@ talosctl version --client 2>/dev/null || echo "Failed to get version"
 echo "Available talosctl commands:"
 talosctl --help 2>/dev/null | grep -A 100 "Available Commands:" | head -20 || echo "Failed to get help"
 
+# Test connectivity to nodes before proceeding
+if [ -n "$NODES" ]; then
+    echo "Testing connectivity to nodes..."
+    for node in $(echo "$NODES" | tr ',' ' '); do
+        echo "Testing node: $node"
+        if timeout 10s talosctl version --nodes "$node" >/dev/null 2>&1; then
+            echo "✓ Node $node is reachable"
+        else
+            echo "⚠ Node $node is not reachable or not responding"
+        fi
+    done
+fi
+
 # 1. Comprehensive support bundle (most important)
-# Note: talosctl support requires specific node targeting, so we'll try without --output first
-run_talosctl "talosctl support $NODE_FLAG" \
-    "$TALOS_DIAGNOSTICS_DIR/talos-support-bundle.txt" \
-    "Complete Talos support bundle"
+# This creates a complete tar.gz file with all diagnostics
+echo "Collecting comprehensive Talos support bundle..."
+
+# Change to the diagnostics directory to avoid conflicts with existing support.zip
+cd "$TALOS_DIAGNOSTICS_DIR"
+
+if [ -n "$NODE_FLAG" ]; then
+    echo "Using node targeting: $NODE_FLAG"
+    echo "Running: talosctl support $NODE_FLAG --output talos-support-bundle.tar.gz"
+    if talosctl support $NODE_FLAG --output talos-support-bundle.tar.gz; then
+        echo "✓ Successfully created talos-support-bundle.tar.gz"
+    else
+        exit_code=$?
+        echo "⚠ Support bundle creation failed (exit code: $exit_code)"
+        echo "Command failed: talosctl support $NODE_FLAG --output talos-support-bundle.tar.gz" > support-bundle-output.txt
+        echo "Exit code: $exit_code" >> support-bundle-output.txt
+    fi
+else
+    echo "No node targeting available, attempting support bundle without targeting"
+    echo "Running: talosctl support --output talos-support-bundle.tar.gz"
+    if talosctl support --output talos-support-bundle.tar.gz; then
+        echo "✓ Successfully created talos-support-bundle.tar.gz"
+    else
+        exit_code=$?
+        echo "⚠ Support bundle creation failed (exit code: $exit_code)"
+        echo "Command failed: talosctl support --output talos-support-bundle.tar.gz" > support-bundle-output.txt
+        echo "Exit code: $exit_code" >> support-bundle-output.txt
+    fi
+fi
 
-# 2. Cluster health check
-run_talosctl "talosctl health $NODE_FLAG" \
-    "$TALOS_DIAGNOSTICS_DIR/talos-health.txt" \
-    "Cluster health status"
+# Change back to original directory
+cd - > /dev/null
 
-# 3. Version information
+# 2. Basic version info (always works)
 run_talosctl "talosctl version $NODE_FLAG" \
     "$TALOS_DIAGNOSTICS_DIR/talos-version.txt" \
     "Talos version information"
 
-# 4. Node information (if we have specific nodes)
-if [ -n "$NODES" ]; then
-    for node in $(echo "$NODES" | tr ',' ' '); do
-        node_dir="$TALOS_DIAGNOSTICS_DIR/node-$node"
-        mkdir -p "$node_dir"
-        
-        # Kernel logs
-        run_talosctl "talosctl dmesg --nodes $node" \
-            "$node_dir/dmesg.txt" \
-            "Kernel logs for node $node"
-        
-        # Running processes
-        run_talosctl "talosctl processes --nodes $node" \
-            "$node_dir/processes.txt" \
-            "Running processes for node $node"
-        
-        # Memory usage
-        run_talosctl "talosctl memory --nodes $node" \
-            "$node_dir/memory.txt" \
-            "Memory usage for node $node"
-        
-        # Network connections
-        run_talosctl "talosctl netstat --nodes $node" \
-            "$node_dir/netstat.txt" \
-            "Network connections for node $node"
-        
-        # Disk usage (using df instead of usage which might not be available)
-        run_talosctl "talosctl df --nodes $node" \
-            "$node_dir/disk-usage.txt" \
-            "Disk usage for node $node"
-        
-        # Running containers
-        run_talosctl "talosctl containers --nodes $node" \
-            "$node_dir/containers.txt" \
-            "Running containers for node $node"
-        
-        # Service status
-        run_talosctl "talosctl service --nodes $node" \
-            "$node_dir/services.txt" \
-            "Service status for node $node"
-        
-        # Mount information
-        run_talosctl "talosctl mounts --nodes $node" \
-            "$node_dir/mounts.txt" \
-            "Mount information for node $node"
-    done
-fi
-
-# 5. etcd status (control plane nodes)
-run_talosctl "talosctl etcd status $NODE_FLAG" \
-    "$TALOS_DIAGNOSTICS_DIR/etcd-status.txt" \
-    "etcd cluster status"
-
-# 6. Cluster configuration (try different approaches)
-run_talosctl "talosctl get config $NODE_FLAG -o yaml" \
-    "$TALOS_DIAGNOSTICS_DIR/talos-config.yaml" \
-    "Talos cluster configuration"
-
-# Alternative: try to get machine config
-run_talosctl "talosctl get machineconfig $NODE_FLAG -o yaml" \
-    "$TALOS_DIAGNOSTICS_DIR/talos-machine-config.yaml" \
-    "Talos machine configuration"
-
-# 7. Available resource definitions
-run_talosctl "talosctl get rd $NODE_FLAG" \
-    "$TALOS_DIAGNOSTICS_DIR/resource-definitions.txt" \
-    "Available resource definitions"
-
-# 8. COSI resources (if accessible)
-run_talosctl "talosctl get machines $NODE_FLAG -o yaml" \
-    "$TALOS_DIAGNOSTICS_DIR/machines.yaml" \
-    "Machine resources"
-
-# Alternative: try to get nodes
-run_talosctl "talosctl get nodes $NODE_FLAG -o yaml" \
-    "$TALOS_DIAGNOSTICS_DIR/nodes.yaml" \
-    "Node resources"
-
-# 9. Events (if accessible)
-run_talosctl "talosctl events $NODE_FLAG --duration 1h" \
-    "$TALOS_DIAGNOSTICS_DIR/talos-events.txt" \
-    "Talos events (last hour)"
-
 echo "Talos diagnostics collection completed"
 echo "Output directory: $TALOS_DIAGNOSTICS_DIR"
 ls -la "$TALOS_DIAGNOSTICS_DIR"
@@ -169,5 +176,12 @@ ls -la "$TALOS_DIAGNOSTICS_DIR"
 # Create tar.gz archive in the parent directory (same pattern as Windsor state)
 TAR_FILE="$(dirname "$TALOS_DIAGNOSTICS_DIR")/talos-diagnostics.tar.gz"
 echo "Creating archive: $TAR_FILE"
+
+# Include the talos support bundle if it was created
+if [ -f "$TALOS_DIAGNOSTICS_DIR/talos-support-bundle.tar.gz" ]; then
+    echo "Including talos support bundle in archive"
+    cp "$TALOS_DIAGNOSTICS_DIR/talos-support-bundle.tar.gz" "$(dirname "$TALOS_DIAGNOSTICS_DIR")/"
+fi
+
 tar -czf "$TAR_FILE" -C "$(dirname "$TALOS_DIAGNOSTICS_DIR")" "$(basename "$TALOS_DIAGNOSTICS_DIR")"
 echo "✓ Talos diagnostics archived to: $TAR_FILE"
diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
index 647171a7..f13d84ae 100644
--- a/.github/workflows/ci.yaml
+++ b/.github/workflows/ci.yaml
@@ -179,8 +179,8 @@ jobs:
             rm -rf "$OLDPWD"
           fi
           
-          # Run talos diagnostics collection
-          .github/scripts/collect-talos-diagnostics.sh support-bundles/talos-diagnostics
+          # Run talos diagnostics collection within Windsor environment
+          windsor exec -- .github/scripts/collect-talos-diagnostics.sh support-bundles/talos-diagnostics
 
       - name: Collect support bundle
         if: always()

From c3ccfd53dfce53113a4c81f58aeb1833484f1b69 Mon Sep 17 00:00:00 2001
From: Ryan VanGundy <85766511+rmvangun@users.noreply.github.com>
Date: Mon, 27 Oct 2025 21:17:16 -0400
Subject: [PATCH 04/11] Correct talos support bundle

Signed-off-by: Ryan VanGundy <85766511+rmvangun@users.noreply.github.com>
---
 .github/scripts/collect-talos-diagnostics.sh | 30 ++++++++++++--------
 1 file changed, 18 insertions(+), 12 deletions(-)

diff --git a/.github/scripts/collect-talos-diagnostics.sh b/.github/scripts/collect-talos-diagnostics.sh
index 5f41fcc2..c8c2ac69 100755
--- a/.github/scripts/collect-talos-diagnostics.sh
+++ b/.github/scripts/collect-talos-diagnostics.sh
@@ -86,23 +86,23 @@ if ! command -v talosctl &> /dev/null; then
 fi
 
 # Determine node targeting strategy based on environment
-NODE_FLAG=""
+NODE_ARGS=()
 NODES=""
 
 # Check if we're in a local Docker Desktop environment (has controlplane-1 node)
 if talosctl get nodes 2>/dev/null | grep -q "controlplane-1"; then
     echo "Detected local Docker Desktop environment, using node names"
-    NODE_FLAG="-n controlplane-1"
+    NODE_ARGS=(-n controlplane-1)
     NODES="controlplane-1"
 # Check if we have specific node IPs from kubectl (CI environment)
 elif kubectl get nodes -o jsonpath='{.items[*].status.addresses[?(@.type=="InternalIP")].address}' 2>/dev/null | grep -q .; then
     NODES=$(kubectl get nodes -o jsonpath='{.items[*].status.addresses[?(@.type=="InternalIP")].address}' 2>/dev/null | tr ' ' ',')
-    NODE_FLAG="-n $NODES"
+    NODE_ARGS=(-n "$NODES")
     echo "Detected CI environment, using node IPs: $NODES"
 # Fallback: try to get from talosctl config
 elif talosctl config info 2>/dev/null | grep -q "endpoints:"; then
     NODES=$(talosctl config info 2>/dev/null | grep "endpoints:" | cut -d: -f2 | tr -d ' ' | tr ',' ' ')
-    NODE_FLAG="-n $NODES"
+    NODE_ARGS=(-n "$NODES")
     echo "Using endpoints from talosctl config: $NODES"
 else
     echo "No nodes detected, will attempt commands without node targeting"
@@ -137,15 +137,15 @@ echo "Collecting comprehensive Talos support bundle..."
 # Change to the diagnostics directory to avoid conflicts with existing support.zip
 cd "$TALOS_DIAGNOSTICS_DIR"
 
-if [ -n "$NODE_FLAG" ]; then
-    echo "Using node targeting: $NODE_FLAG"
-    echo "Running: talosctl support $NODE_FLAG --output talos-support-bundle.tar.gz"
-    if talosctl support $NODE_FLAG --output talos-support-bundle.tar.gz; then
+if [ ${#NODE_ARGS[@]} -gt 0 ]; then
+    echo "Using node targeting: ${NODE_ARGS[*]}"
+    echo "Running: talosctl support ${NODE_ARGS[*]} --output talos-support-bundle.tar.gz"
+    if talosctl support "${NODE_ARGS[@]}" --output talos-support-bundle.tar.gz; then
         echo "✓ Successfully created talos-support-bundle.tar.gz"
     else
         exit_code=$?
         echo "⚠ Support bundle creation failed (exit code: $exit_code)"
-        echo "Command failed: talosctl support $NODE_FLAG --output talos-support-bundle.tar.gz" > support-bundle-output.txt
+        echo "Command failed: talosctl support ${NODE_ARGS[*]} --output talos-support-bundle.tar.gz" > support-bundle-output.txt
         echo "Exit code: $exit_code" >> support-bundle-output.txt
     fi
 else
@@ -165,9 +165,15 @@ fi
 cd - > /dev/null
 
 # 2. Basic version info (always works)
-run_talosctl "talosctl version $NODE_FLAG" \
-    "$TALOS_DIAGNOSTICS_DIR/talos-version.txt" \
-    "Talos version information"
+if [ ${#NODE_ARGS[@]} -gt 0 ]; then
+    run_talosctl "talosctl version ${NODE_ARGS[*]}" \
+        "$TALOS_DIAGNOSTICS_DIR/talos-version.txt" \
+        "Talos version information"
+else
+    run_talosctl "talosctl version" \
+        "$TALOS_DIAGNOSTICS_DIR/talos-version.txt" \
+        "Talos version information"
+fi
 
 echo "Talos diagnostics collection completed"
 echo "Output directory: $TALOS_DIAGNOSTICS_DIR"

From d2882d3fed3f8e5bfc7f0f8ed1a84798432baa30 Mon Sep 17 00:00:00 2001
From: Ryan VanGundy <85766511+rmvangun@users.noreply.github.com>
Date: Mon, 27 Oct 2025 22:04:30 -0400
Subject: [PATCH 05/11] Try to add support.zip bundle

Signed-off-by: Ryan VanGundy <85766511+rmvangun@users.noreply.github.com>
---
 .github/scripts/collect-talos-diagnostics.sh | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/.github/scripts/collect-talos-diagnostics.sh b/.github/scripts/collect-talos-diagnostics.sh
index c8c2ac69..7c89bf6c 100755
--- a/.github/scripts/collect-talos-diagnostics.sh
+++ b/.github/scripts/collect-talos-diagnostics.sh
@@ -187,7 +187,11 @@ echo "Creating archive: $TAR_FILE"
 if [ -f "$TALOS_DIAGNOSTICS_DIR/talos-support-bundle.tar.gz" ]; then
     echo "Including talos support bundle in archive"
     cp "$TALOS_DIAGNOSTICS_DIR/talos-support-bundle.tar.gz" "$(dirname "$TALOS_DIAGNOSTICS_DIR")/"
+    # Create archive with both the diagnostics directory and the support bundle
+    tar -czf "$TAR_FILE" -C "$(dirname "$TALOS_DIAGNOSTICS_DIR")" "$(basename "$TALOS_DIAGNOSTICS_DIR")" "talos-support-bundle.tar.gz"
+else
+    # Create archive with just the diagnostics directory
+    tar -czf "$TAR_FILE" -C "$(dirname "$TALOS_DIAGNOSTICS_DIR")" "$(basename "$TALOS_DIAGNOSTICS_DIR")"
 fi
 
-tar -czf "$TAR_FILE" -C "$(dirname "$TALOS_DIAGNOSTICS_DIR")" "$(basename "$TALOS_DIAGNOSTICS_DIR")"
 echo "✓ Talos diagnostics archived to: $TAR_FILE"

From 0d9deed5309040d95e389fafc300f1b3aaf0a6b1 Mon Sep 17 00:00:00 2001
From: Ryan VanGundy <85766511+rmvangun@users.noreply.github.com>
Date: Tue, 28 Oct 2025 12:20:20 -0400
Subject: [PATCH 06/11] Collect talos docker logs

Signed-off-by: Ryan VanGundy <85766511+rmvangun@users.noreply.github.com>
---
 .github/scripts/collect-talos-diagnostics.sh | 24 ++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/.github/scripts/collect-talos-diagnostics.sh b/.github/scripts/collect-talos-diagnostics.sh
index 7c89bf6c..6606a94b 100755
--- a/.github/scripts/collect-talos-diagnostics.sh
+++ b/.github/scripts/collect-talos-diagnostics.sh
@@ -175,6 +175,30 @@ else
         "Talos version information"
 fi
 
+# 3. Collect Docker logs from Talos nodes
+echo "Collecting Docker logs from Talos nodes..."
+docker_logs_dir="$TALOS_DIAGNOSTICS_DIR/docker-logs"
+mkdir -p "$docker_logs_dir"
+
+# Get list of Talos containers
+talos_containers=$(docker ps --format "table {{.Names}}\t{{.Image}}" | grep -E "(talos|controlplane|worker)" | awk '{print $1}')
+
+if [ -n "$talos_containers" ]; then
+    echo "Found Talos containers: $talos_containers"
+    for container in $talos_containers; do
+        echo "Collecting logs for container: $container"
+        if docker logs "$container" > "$docker_logs_dir/${container}.log" 2>&1; then
+            echo "✓ Successfully collected logs for $container"
+        else
+            echo "⚠ Failed to collect logs for $container"
+            echo "Failed to collect logs for container: $container" > "$docker_logs_dir/${container}.log"
+        fi
+    done
+else
+    echo "No Talos containers found"
+    echo "No Talos containers found" > "$docker_logs_dir/no-containers.txt"
+fi
+
 echo "Talos diagnostics collection completed"
 echo "Output directory: $TALOS_DIAGNOSTICS_DIR"
 ls -la "$TALOS_DIAGNOSTICS_DIR"

From 0e417d4bbaa61b492e355e759211743dc6377108 Mon Sep 17 00:00:00 2001
From: Ryan VanGundy <85766511+rmvangun@users.noreply.github.com>
Date: Wed, 29 Oct 2025 09:16:56 -0400
Subject: [PATCH 07/11] debug

Signed-off-by: Ryan VanGundy <85766511+rmvangun@users.noreply.github.com>
---
 .github/workflows/ci.yaml | 59 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 59 insertions(+)

diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
index f13d84ae..c7c61ba7 100644
--- a/.github/workflows/ci.yaml
+++ b/.github/workflows/ci.yaml
@@ -157,8 +157,67 @@ jobs:
 
       - name: Windsor Up
         run: |
+          echo "=== DEBUG: Starting Windsor Up process ==="
+          echo "Current working directory: $(pwd)"
+          echo "WINDSOR_PROJECT_ROOT: $WINDSOR_PROJECT_ROOT"
+          
+          echo "=== DEBUG: Running windsor init ==="
           windsor init local --set dns.enabled=false --reset
+          
+          echo "=== DEBUG: Checking windsor.yaml after init ==="
+          echo "windsor.yaml content:"
+          cat contexts/local/windsor.yaml
+          echo ""
+          
+          echo "=== DEBUG: Checking if DNS is disabled ==="
+          if grep -q "dns:" contexts/local/windsor.yaml; then
+            echo "DNS section found in windsor.yaml:"
+            grep -A 5 "dns:" contexts/local/windsor.yaml
+          else
+            echo "No DNS section found in windsor.yaml"
+          fi
+          
+          echo "=== DEBUG: Checking docker-compose.yaml after init ==="
+          if [ -f .windsor/docker-compose.yaml ]; then
+            echo "docker-compose.yaml exists, checking for DNS services:"
+            if grep -q "dns:" .windsor/docker-compose.yaml; then
+              echo "WARNING: DNS service found in docker-compose.yaml after init!"
+              grep -A 10 -B 2 "dns:" .windsor/docker-compose.yaml
+            else
+              echo "No DNS service found in docker-compose.yaml after init"
+            fi
+            echo "Services in docker-compose.yaml:"
+            grep "container_name:" .windsor/docker-compose.yaml || echo "No container_name found"
+          else
+            echo "docker-compose.yaml does not exist after init"
+          fi
+          
+          echo "=== DEBUG: Running windsor up ==="
           windsor up --install --verbose --wait
+          
+          echo "=== DEBUG: Checking docker-compose.yaml after windsor up ==="
+          if [ -f .windsor/docker-compose.yaml ]; then
+            echo "docker-compose.yaml exists after windsor up, checking for DNS services:"
+            if grep -q "dns:" .windsor/docker-compose.yaml; then
+              echo "ERROR: DNS service found in docker-compose.yaml after windsor up!"
+              grep -A 10 -B 2 "dns:" .windsor/docker-compose.yaml
+            else
+              echo "No DNS service found in docker-compose.yaml after windsor up"
+            fi
+            echo "All services in docker-compose.yaml:"
+            grep "container_name:" .windsor/docker-compose.yaml || echo "No container_name found"
+            echo "File size: $(wc -l < .windsor/docker-compose.yaml) lines"
+          else
+            echo "docker-compose.yaml does not exist after windsor up"
+          fi
+          
+          echo "=== DEBUG: Checking IP addresses ==="
+          if [ -f .windsor/docker-compose.yaml ]; then
+            echo "IP addresses in docker-compose.yaml:"
+            grep -A 1 "ipv4_address:" .windsor/docker-compose.yaml || echo "No ipv4_address found"
+          fi
+          
+          echo "=== DEBUG: Windsor Up process complete ==="
 
       - name: Collect Windsor State
         if: always()

From 57d85976409d86da0c0d1d25aef107383c8c82ff Mon Sep 17 00:00:00 2001
From: Ryan VanGundy <85766511+rmvangun@users.noreply.github.com>
Date: Wed, 29 Oct 2025 09:17:11 -0400
Subject: [PATCH 08/11] debug

Signed-off-by: Ryan VanGundy <85766511+rmvangun@users.noreply.github.com>
---
 .github/workflows/ci.yaml | 37 +++++++++++++++++++++++++++++++++++++
 1 file changed, 37 insertions(+)

diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
index c7c61ba7..25191bc2 100644
--- a/.github/workflows/ci.yaml
+++ b/.github/workflows/ci.yaml
@@ -227,6 +227,17 @@ jobs:
       - name: Collect Talos Diagnostics
         if: always()
         run: |
+          echo "=== DEBUG: Before talosctl installation ==="
+          echo "Checking docker-compose.yaml before talosctl installation:"
+          if [ -f .windsor/docker-compose.yaml ]; then
+            if grep -q "dns:" .windsor/docker-compose.yaml; then
+              echo "WARNING: DNS service found before talosctl installation!"
+              grep -A 5 -B 2 "dns:" .windsor/docker-compose.yaml
+            else
+              echo "No DNS service found before talosctl installation"
+            fi
+          fi
+          
           # Install talosctl if not available
           if ! command -v talosctl &> /dev/null; then
             echo "Installing talosctl..."
@@ -238,8 +249,34 @@ jobs:
             rm -rf "$OLDPWD"
           fi
           
+          echo "=== DEBUG: Before windsor exec ==="
+          echo "Checking docker-compose.yaml before windsor exec:"
+          if [ -f .windsor/docker-compose.yaml ]; then
+            if grep -q "dns:" .windsor/docker-compose.yaml; then
+              echo "WARNING: DNS service found before windsor exec!"
+              grep -A 5 -B 2 "dns:" .windsor/docker-compose.yaml
+            else
+              echo "No DNS service found before windsor exec"
+            fi
+            echo "File timestamp: $(stat -c %y .windsor/docker-compose.yaml 2>/dev/null || stat -f %Sm .windsor/docker-compose.yaml 2>/dev/null || echo 'unknown')"
+          fi
+          
           # Run talos diagnostics collection within Windsor environment
+          echo "=== DEBUG: Running windsor exec ==="
           windsor exec -- .github/scripts/collect-talos-diagnostics.sh support-bundles/talos-diagnostics
+          
+          echo "=== DEBUG: After windsor exec ==="
+          echo "Checking docker-compose.yaml after windsor exec:"
+          if [ -f .windsor/docker-compose.yaml ]; then
+            if grep -q "dns:" .windsor/docker-compose.yaml; then
+              echo "ERROR: DNS service found after windsor exec!"
+              grep -A 10 -B 2 "dns:" .windsor/docker-compose.yaml
+            else
+              echo "No DNS service found after windsor exec"
+            fi
+            echo "File timestamp: $(stat -c %y .windsor/docker-compose.yaml 2>/dev/null || stat -f %Sm .windsor/docker-compose.yaml 2>/dev/null || echo 'unknown')"
+            echo "File size: $(wc -l < .windsor/docker-compose.yaml) lines"
+          fi
 
       - name: Collect support bundle
         if: always()

From 18d873f2e82ad35ff9438e88da102d7110b88121 Mon Sep 17 00:00:00 2001
From: Ryan VanGundy <85766511+rmvangun@users.noreply.github.com>
Date: Wed, 29 Oct 2025 09:17:38 -0400
Subject: [PATCH 09/11] debug

Signed-off-by: Ryan VanGundy <85766511+rmvangun@users.noreply.github.com>
---
 .github/workflows/ci.yaml | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
index 25191bc2..0cbdbc0c 100644
--- a/.github/workflows/ci.yaml
+++ b/.github/workflows/ci.yaml
@@ -160,9 +160,15 @@ jobs:
           echo "=== DEBUG: Starting Windsor Up process ==="
           echo "Current working directory: $(pwd)"
           echo "WINDSOR_PROJECT_ROOT: $WINDSOR_PROJECT_ROOT"
+          echo "Windsor CLI version:"
+          windsor --version || echo "Failed to get Windsor version"
+          echo "Environment variables:"
+          env | grep -E "(WINDSOR|DOCKER)" | sort || echo "No Windsor/Docker env vars found"
           
           echo "=== DEBUG: Running windsor init ==="
+          echo "Command: windsor init local --set dns.enabled=false --reset"
           windsor init local --set dns.enabled=false --reset
+          echo "windsor init exit code: $?"
           
           echo "=== DEBUG: Checking windsor.yaml after init ==="
           echo "windsor.yaml content:"
@@ -193,7 +199,9 @@ jobs:
           fi
           
           echo "=== DEBUG: Running windsor up ==="
+          echo "Command: windsor up --install --verbose --wait"
           windsor up --install --verbose --wait
+          echo "windsor up exit code: $?"
           
           echo "=== DEBUG: Checking docker-compose.yaml after windsor up ==="
           if [ -f .windsor/docker-compose.yaml ]; then

From 967df4961600e8b07eba4b680de8d77e755b6379 Mon Sep 17 00:00:00 2001
From: Ryan VanGundy <85766511+rmvangun@users.noreply.github.com>
Date: Wed, 29 Oct 2025 09:23:21 -0400
Subject: [PATCH 10/11] Enforce regeneration of windsor.yaml

Signed-off-by: Ryan VanGundy <85766511+rmvangun@users.noreply.github.com>
---
 .github/workflows/ci.yaml | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
index 0cbdbc0c..2953d8df 100644
--- a/.github/workflows/ci.yaml
+++ b/.github/workflows/ci.yaml
@@ -165,6 +165,27 @@ jobs:
           echo "Environment variables:"
           env | grep -E "(WINDSOR|DOCKER)" | sort || echo "No Windsor/Docker env vars found"
           
+          echo "=== DEBUG: Cleaning up existing configuration ==="
+          echo "Removing existing windsor.yaml if it exists:"
+          if [ -f contexts/local/windsor.yaml ]; then
+            echo "Found existing windsor.yaml, removing it:"
+            cat contexts/local/windsor.yaml
+            rm -f contexts/local/windsor.yaml
+            echo "windsor.yaml removed"
+          else
+            echo "No existing windsor.yaml found"
+          fi
+          
+          echo "Removing existing .windsor directory if it exists:"
+          if [ -d .windsor ]; then
+            echo "Found existing .windsor directory, removing it:"
+            ls -la .windsor/
+            rm -rf .windsor
+            echo ".windsor directory removed"
+          else
+            echo "No existing .windsor directory found"
+          fi
+          
           echo "=== DEBUG: Running windsor init ==="
           echo "Command: windsor init local --set dns.enabled=false --reset"
           windsor init local --set dns.enabled=false --reset

From 08769406ef9b0de610bb8f9990d090ba3316888b Mon Sep 17 00:00:00 2001
From: Ryan VanGundy <85766511+rmvangun@users.noreply.github.com>
Date: Wed, 29 Oct 2025 09:31:21 -0400
Subject: [PATCH 11/11] Remove debug statements

Signed-off-by: Ryan VanGundy <85766511+rmvangun@users.noreply.github.com>
---
 .github/workflows/ci.yaml | 128 ++------------------------------------
 1 file changed, 4 insertions(+), 124 deletions(-)

diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
index 2953d8df..9538b3b7 100644
--- a/.github/workflows/ci.yaml
+++ b/.github/workflows/ci.yaml
@@ -157,96 +157,13 @@ jobs:
 
       - name: Windsor Up
         run: |
-          echo "=== DEBUG: Starting Windsor Up process ==="
-          echo "Current working directory: $(pwd)"
-          echo "WINDSOR_PROJECT_ROOT: $WINDSOR_PROJECT_ROOT"
-          echo "Windsor CLI version:"
-          windsor --version || echo "Failed to get Windsor version"
-          echo "Environment variables:"
-          env | grep -E "(WINDSOR|DOCKER)" | sort || echo "No Windsor/Docker env vars found"
+          # Clean up any existing configuration
+          rm -f contexts/local/windsor.yaml
+          rm -rf .windsor
           
-          echo "=== DEBUG: Cleaning up existing configuration ==="
-          echo "Removing existing windsor.yaml if it exists:"
-          if [ -f contexts/local/windsor.yaml ]; then
-            echo "Found existing windsor.yaml, removing it:"
-            cat contexts/local/windsor.yaml
-            rm -f contexts/local/windsor.yaml
-            echo "windsor.yaml removed"
-          else
-            echo "No existing windsor.yaml found"
-          fi
-          
-          echo "Removing existing .windsor directory if it exists:"
-          if [ -d .windsor ]; then
-            echo "Found existing .windsor directory, removing it:"
-            ls -la .windsor/
-            rm -rf .windsor
-            echo ".windsor directory removed"
-          else
-            echo "No existing .windsor directory found"
-          fi
-          
-          echo "=== DEBUG: Running windsor init ==="
-          echo "Command: windsor init local --set dns.enabled=false --reset"
+          # Initialize and start Windsor
           windsor init local --set dns.enabled=false --reset
-          echo "windsor init exit code: $?"
-          
-          echo "=== DEBUG: Checking windsor.yaml after init ==="
-          echo "windsor.yaml content:"
-          cat contexts/local/windsor.yaml
-          echo ""
-          
-          echo "=== DEBUG: Checking if DNS is disabled ==="
-          if grep -q "dns:" contexts/local/windsor.yaml; then
-            echo "DNS section found in windsor.yaml:"
-            grep -A 5 "dns:" contexts/local/windsor.yaml
-          else
-            echo "No DNS section found in windsor.yaml"
-          fi
-          
-          echo "=== DEBUG: Checking docker-compose.yaml after init ==="
-          if [ -f .windsor/docker-compose.yaml ]; then
-            echo "docker-compose.yaml exists, checking for DNS services:"
-            if grep -q "dns:" .windsor/docker-compose.yaml; then
-              echo "WARNING: DNS service found in docker-compose.yaml after init!"
-              grep -A 10 -B 2 "dns:" .windsor/docker-compose.yaml
-            else
-              echo "No DNS service found in docker-compose.yaml after init"
-            fi
-            echo "Services in docker-compose.yaml:"
-            grep "container_name:" .windsor/docker-compose.yaml || echo "No container_name found"
-          else
-            echo "docker-compose.yaml does not exist after init"
-          fi
-          
-          echo "=== DEBUG: Running windsor up ==="
-          echo "Command: windsor up --install --verbose --wait"
           windsor up --install --verbose --wait
-          echo "windsor up exit code: $?"
-          
-          echo "=== DEBUG: Checking docker-compose.yaml after windsor up ==="
-          if [ -f .windsor/docker-compose.yaml ]; then
-            echo "docker-compose.yaml exists after windsor up, checking for DNS services:"
-            if grep -q "dns:" .windsor/docker-compose.yaml; then
-              echo "ERROR: DNS service found in docker-compose.yaml after windsor up!"
-              grep -A 10 -B 2 "dns:" .windsor/docker-compose.yaml
-            else
-              echo "No DNS service found in docker-compose.yaml after windsor up"
-            fi
-            echo "All services in docker-compose.yaml:"
-            grep "container_name:" .windsor/docker-compose.yaml || echo "No container_name found"
-            echo "File size: $(wc -l < .windsor/docker-compose.yaml) lines"
-          else
-            echo "docker-compose.yaml does not exist after windsor up"
-          fi
-          
-          echo "=== DEBUG: Checking IP addresses ==="
-          if [ -f .windsor/docker-compose.yaml ]; then
-            echo "IP addresses in docker-compose.yaml:"
-            grep -A 1 "ipv4_address:" .windsor/docker-compose.yaml || echo "No ipv4_address found"
-          fi
-          
-          echo "=== DEBUG: Windsor Up process complete ==="
 
       - name: Collect Windsor State
         if: always()
@@ -256,17 +173,6 @@ jobs:
       - name: Collect Talos Diagnostics
         if: always()
         run: |
-          echo "=== DEBUG: Before talosctl installation ==="
-          echo "Checking docker-compose.yaml before talosctl installation:"
-          if [ -f .windsor/docker-compose.yaml ]; then
-            if grep -q "dns:" .windsor/docker-compose.yaml; then
-              echo "WARNING: DNS service found before talosctl installation!"
-              grep -A 5 -B 2 "dns:" .windsor/docker-compose.yaml
-            else
-              echo "No DNS service found before talosctl installation"
-            fi
-          fi
-          
           # Install talosctl if not available
           if ! command -v talosctl &> /dev/null; then
             echo "Installing talosctl..."
@@ -278,34 +184,8 @@ jobs:
             rm -rf "$OLDPWD"
           fi
           
-          echo "=== DEBUG: Before windsor exec ==="
-          echo "Checking docker-compose.yaml before windsor exec:"
-          if [ -f .windsor/docker-compose.yaml ]; then
-            if grep -q "dns:" .windsor/docker-compose.yaml; then
-              echo "WARNING: DNS service found before windsor exec!"
-              grep -A 5 -B 2 "dns:" .windsor/docker-compose.yaml
-            else
-              echo "No DNS service found before windsor exec"
-            fi
-            echo "File timestamp: $(stat -c %y .windsor/docker-compose.yaml 2>/dev/null || stat -f %Sm .windsor/docker-compose.yaml 2>/dev/null || echo 'unknown')"
-          fi
-          
           # Run talos diagnostics collection within Windsor environment
-          echo "=== DEBUG: Running windsor exec ==="
           windsor exec -- .github/scripts/collect-talos-diagnostics.sh support-bundles/talos-diagnostics
-          
-          echo "=== DEBUG: After windsor exec ==="
-          echo "Checking docker-compose.yaml after windsor exec:"
-          if [ -f .windsor/docker-compose.yaml ]; then
-            if grep -q "dns:" .windsor/docker-compose.yaml; then
-              echo "ERROR: DNS service found after windsor exec!"
-              grep -A 10 -B 2 "dns:" .windsor/docker-compose.yaml
-            else
-              echo "No DNS service found after windsor exec"
-            fi
-            echo "File timestamp: $(stat -c %y .windsor/docker-compose.yaml 2>/dev/null || stat -f %Sm .windsor/docker-compose.yaml 2>/dev/null || echo 'unknown')"
-            echo "File size: $(wc -l < .windsor/docker-compose.yaml) lines"
-          fi
 
       - name: Collect support bundle
         if: always()