misc/frontier: add sync_runner_nodes, list-runners, move-runner, retry logic

- config.sh: add sync_runner_nodes() — parallel sweep of all login nodes
  that updates runner.node files before any action, ensuring accuracy even
  when runners are manually restarted on different nodes
- make-runner.sh: use gh_latest_runner_version() with pinned fallback
- restart-offline-runners.sh: call sync_runner_nodes first; self-heal
  stale runner.node on restart; retry start_runner once on failure
- check-runners.sh: call sync_runner_nodes first
- list-runners.sh: new — parallel SSH sweep + GitHub API combined view
- move-runner.sh: new — move a runner to a different login node
- misc/common/README.md: new — document shared scripts
- misc/frontier/README.md: update for new scripts and sync behavior

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Author: Spencer Bryngelson

misc/frontier/check-runners.sh

@@ -10,6 +10,9 @@ set -euo pipefail
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 source "$SCRIPT_DIR/config.sh"
 
+echo "==> Syncing runner node locations..."
+sync_runner_nodes
+
 for node in "${NODES[@]}"; do
     echo "=== $node ==="
     ssh $SSH_OPTS "$node" '

misc/frontier/config.sh

@@ -114,3 +114,35 @@ stop_runner() {
     done
     sleep 1
 }
+
+# Sweep all nodes in parallel and update runner.node for any runner
+# found running on a different node than recorded. Called at the top of
+# every primary script to ensure runner.node always reflects reality,
+# even if a runner was manually restarted on a different node.
+sync_runner_nodes() {
+    local tmpdir
+    tmpdir=$(mktemp -d)
+    trap 'rm -rf "$tmpdir"' RETURN
+
+    for node in "${NODES[@]}"; do
+        (
+            ssh $SSH_OPTS "$node" '
+                for p in $(ps aux | grep Runner.Listener | grep -v grep | awk "{print \$2}"); do
+                    cwd=$(readlink -f /proc/$p/cwd 2>/dev/null || true)
+                    [ -n "$cwd" ] && echo "'"$node"' $cwd"
+                done
+            ' 2>/dev/null | grep -E '^[a-z0-9]+ /'
+        ) > "$tmpdir/$node" &
+    done
+    wait
+
+    while IFS=' ' read -r node dir; do
+        [ -f "$dir/runner.node" ] || continue
+        local recorded
+        recorded=$(cat "$dir/runner.node" 2>/dev/null || echo "")
+        if [ "$node" != "$recorded" ]; then
+            echo "==> $(basename "$dir"): runner.node updated $recorded -> $node"
+            echo "$node" > "$dir/runner.node"
+        fi
+    done < <(cat "$tmpdir"/*)
+}

misc/frontier/list-runners.sh

@@ -11,6 +11,9 @@ set -euo pipefail
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 source "$SCRIPT_DIR/config.sh"
 
+echo "==> Syncing runner node locations..."
+sync_runner_nodes
+
 tmpdir=$(mktemp -d)
 trap 'rm -rf "$tmpdir"' EXIT
 

misc/frontier/move-runner.sh

@@ -34,6 +34,10 @@ if [ "$valid" -eq 0 ]; then
     exit 1
 fi
 
+# --- Sync runner.node files before acting ---
+echo "==> Syncing runner node locations..."
+sync_runner_nodes
+
 # --- Find current node ---
 echo "==> Locating ${RUNNER_NAME}..."
 current_node=$(find_node "$RUNNER_DIR")

misc/frontier/restart-offline-runners.sh

@@ -11,6 +11,9 @@ set -euo pipefail
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 source "$SCRIPT_DIR/config.sh"
 
+echo "==> Syncing runner node locations..."
+sync_runner_nodes
+
 echo "==> Checking for offline frontier runners..."
 
 # Collect offline runner names from GitHub API