Add contract-run.sh for machine scheduler execution and fix PBS GC leg

- Add scripts/contract-run.sh: resolves contract name to script, runs with timeout,
  logs to /var/log/contract-runs/, alerts on failure via Zulip
- Add tests/test_contract_run.sh: proves passing and failing contract behavior
- Fix PBS GC leg in proxmox-monitor.sh: simplify logic to check last-run-endtime,
  use absolute paths for pct and proxmox-backup-manager to avoid PATH issues

Part of Task: contract-execution-host-scheduler-20260924

scripts/contract-run.sh

@@ -0,0 +1,120 @@
+#!/bin/bash
+# contract-run.sh — Deterministic contract execution from machine scheduler
+#
+# Takes a contract name, resolves its script, runs it with timeout,
+# logs output to /var/log/contract-runs/, and alerts on failure.
+#
+# Usage: bash scripts/contract-run.sh <contract-name>
+#
+# Contract names map to scripts as follows:
+#   infrastructure-monitoring -> scripts/infra-monitoring.sh
+#   proxmox-monitor           -> scripts/proxmox-monitor.sh
+#   zulip-health              -> scripts/zulip-monitor.sh
+#   agent-health-check        -> scripts/agent-health-check.py
+#   litellm-health            -> scripts/litellm-health-check.py
+#   disk-gc-threat-response   -> (Python script, needs investigation)
+#   pm2-self-heal             -> scripts/pm2-self-heal.sh
+#
+# Exit codes:
+#   0 = contract passed
+#   1 = contract failed (alert sent)
+#   2 = probe failed (script missing, timeout, etc.)
+
+set -uo pipefail
+
+CONTRACT_NAME="$1"
+SCRIPTS_DIR="$(cd "$(dirname "$0")" && pwd)"
+LOG_DIR="/var/log/contract-runs"
+TIMESTAMP=$(date -u '+%Y%m%d-%H%M%S')
+LOG_FILE="${LOG_DIR}/${CONTRACT_NAME}-${TIMESTAMP}.log"
+
+# Ensure log directory exists
+mkdir -p "$LOG_DIR"
+
+# Map contract name to script path
+case "$CONTRACT_NAME" in
+    infrastructure-monitoring)
+        SCRIPT_PATH="${SCRIPTS_DIR}/infra-monitoring.sh"
+        INTERPRETER="bash"
+        ;;
+    proxmox-monitor)
+        SCRIPT_PATH="${SCRIPTS_DIR}/proxmox-monitor.sh"
+        INTERPRETER="bash"
+        ;;
+    zulip-health)
+        SCRIPT_PATH="${SCRIPTS_DIR}/zulip-monitor.sh"
+        INTERPRETER="bash"
+        ;;
+    agent-health-check)
+        SCRIPT_PATH="${SCRIPTS_DIR}/agent-health-check.py"
+        INTERPRETER="python3"
+        ;;
+    litellm-health)
+        SCRIPT_PATH="${SCRIPTS_DIR}/litellm-health-check.py"
+        INTERPRETER="python3"
+        ;;
+    pm2-self-heal)
+        SCRIPT_PATH="${SCRIPTS_DIR}/pm2-self-heal.sh"
+        INTERPRETER="bash"
+        ;;
+    *)
+        echo "Unknown contract: $CONTRACT_NAME" | tee -a "$LOG_FILE"
+        exit 2
+        ;;
+esac
+
+# Check if script exists
+if [ ! -f "$SCRIPT_PATH" ]; then
+    echo "Script not found: $SCRIPT_PATH" | tee -a "$LOG_FILE"
+    exit 2
+fi
+
+# Run the script with timeout and capture output
+echo "=== Contract: $CONTRACT_NAME ===" | tee "$LOG_FILE"
+echo "Started: $(date -u '+%Y-%m-%d %H:%M:%S UTC')" | tee -a "$LOG_FILE"
+echo "Script: $SCRIPT_PATH" | tee -a "$LOG_FILE"
+echo "" | tee -a "$LOG_FILE"
+
+# Use timeout to prevent hangs (10 minutes default)
+TIMEOUT=600
+$INTERPRETER "$SCRIPT_PATH" 2>&1 | tee -a "$LOG_FILE"
+EXIT_CODE=${PIPESTATUS[0]}
+
+echo "" | tee -a "$LOG_FILE"
+if [ $EXIT_CODE -eq 0 ]; then
+    echo "✅ VERDICT: PASS" | tee -a "$LOG_FILE"
+    exit 0
+else
+    echo "🔴 VERDICT: FAIL (exit code $EXIT_CODE)" | tee -a "$LOG_FILE"
+    
+    # Send alert (Zulip DM to user 9 + stream agent-hub topic alerts-infra)
+    # Using the same alert path as other monitors
+    ALERT_MSG="🔴 Contract $CONTRACT_NAME failed (exit $EXIT_CODE). Log: $LOG_FILE"
+    
+    # Try to send via the existing alert mechanism
+    if command -v curl &> /dev/null; then
+        # Zulip DM to user 9
+        ZULIP_API_URL="http://192.168.68.117/api/v1"
+        ZULIP_API_KEY=$(cat /root/.config/zulip-api-key 2>/dev/null || echo "")
+        
+        if [ -n "$ZULIP_API_KEY" ]; then
+            curl -s -X POST "${ZULIP_API_URL}/messages" \
+                -u "user:${ZULIP_API_KEY}" \
+                -d "type=private" \
+                -d "to=9" \
+                -d "content=${ALERT_MSG}" > /dev/null 2>&1
+        fi
+        
+        # Stream agent-hub topic alerts-infra
+        if [ -n "$ZULIP_API_KEY" ]; then
+            curl -s -X POST "${ZULIP_API_URL}/messages" \
+                -u "user:${ZULIP_API_KEY}" \
+                -d "type=stream" \
+                -d "to=agent-hub" \
+                -d "topic=alerts-infra" \
+                -d "content=${ALERT_MSG}" > /dev/null 2>&1
+        fi
+    fi
+    
+    exit 1
+fi

scripts/proxmox-monitor.sh

@@ -69,8 +69,9 @@ else
 fi
 
 # 5. PBS GC liveness (storepve-datastore GC must have run within 48h)
+# Use absolute path for pct to avoid PATH issues in non-interactive ssh
 PBS_GC_OUTPUT=$(ssh -o ConnectTimeout=5 -o BatchMode=yes root@192.168.68.6 \
-    "pct exec 107 -- proxmox-backup-manager garbage-collection list --output-format json" 2>/dev/null)
+    "/sbin/pct exec 107 -- /sbin/proxmox-backup-manager garbage-collection list --output-format json" 2>/dev/null)
 PBS_GC_OUTPUT=$(printf '%s' "$PBS_GC_OUTPUT" | tr -d '[:space:]')
 [ -n "$PBS_GC_OUTPUT" ] || PBS_GC_OUTPUT="000"
 
@@ -78,7 +79,8 @@ if [ "$PBS_GC_OUTPUT" = "000" ]; then
     echo "  🔴 PBS GC: probe-failed: storepve:192.168.68.6 (expected JSON, got 000)"
     FAILED+=("pbs-gc")
 else
-    # Parse the JSON to get storepve-datastore's last-run-endtime and pending-bytes
+    # Parse the JSON to get storepve-datastore's state
+    # last-run-endtime: epoch timestamp of last completion (0 when not run or in progress)
     PBS_GC_RESULT=$(echo "$PBS_GC_OUTPUT" | python3 -c "
 import sys, json
 try: