Claude Code: Create a scheduled job for Cain's autonomous maintenance. The job should

.openclaw/cron/README.md

@@ -0,0 +1,67 @@
+# OpenClaw Cron System
+
+Cain's autonomous maintenance and health monitoring system.
+
+## Overview
+
+The cron system provides self-healing capabilities for Cain by automatically monitoring health status and recovering from errors.
+
+## Job Configuration
+
+Located in `.openclaw/cron/jobs.json`, following the OpenClaw cron schema:
+
+```json
+{
+  "jobs": [
+    {
+      "id": "health-check",
+      "schedule": "*/30 * * * *",
+      "enabled": true,
+      "description": "Monitor Cain's health and auto-recover from errors",
+      "tool": "hf_space_status",
+      "on_failure": {
+        "tool": "hf_restart_space",
+        "condition": "status in ['RUNTIME_ERROR', 'BUILDING'] and duration_minutes > 10"
+      }
+    }
+  ]
+}
+```
+
+## Current Jobs
+
+### health-check
+- **Schedule**: Every 30 minutes
+- **Purpose**: Monitor Cain's Hugging Face Space status
+- **Tool**: `hf_space_status`
+- **Auto-recovery**: Restarts space if in RUNTIME_ERROR or BUILDING state for >10 minutes
+- **Logs**: `.openclaw/logs/health-check.jsonl`
+
+## Log Format
+
+Health checks are logged in JSONL format:
+
+```json
+{"timestamp":"2026-03-14T00:00:00Z","job_id":"health-check","status":"RUNNING","stage":"RUNNING","detail":"HuggingClaw is running","action":"check"}
+{"timestamp":"2026-03-14T00:30:00Z","job_id":"health-check","status":"RUNTIME_ERROR","action":"recovery_triggered"}
+{"timestamp":"2026-03-14T00:31:00Z","job_id":"health-check","status":"RUNNING","action":"recovery_success"}
+```
+
+## Adding New Jobs
+
+1. Edit `.openclaw/cron/jobs.json`
+2. Add a new job object to the `jobs` array
+3. Set `enabled: true` to activate
+4. Restart the cron daemon
+
+## Monitoring
+
+View recent health checks:
+```bash
+tail -20 .openclaw/logs/health-check.jsonl
+```
+
+Count failures in last 24 hours:
+```bash
+jq -r 'select(.action=="recovery_triggered")' .openclaw/logs/health-checks.jsonl | wc -l
+```

.openclaw/cron/crontab.example

@@ -0,0 +1,24 @@
+# OpenClaw Cron System - Crontab Reference
+# ==========================================
+#
+# To install this cron job, run:
+#   .openclaw/cron/setup.sh
+#
+# Or manually add this line to your crontab (crontab -e):
+
+*/30 * * * * cd /tmp/claude-workspace && /tmp/claude-workspace/.openclaw/cron/executor.py >> /tmp/openclaw-cron.log 2>&1
+
+# Cron schedule format: */30 * * * *
+# - */30: Every 30 minutes
+# - *: Every hour
+# - *: Every day
+# - *: Every month
+# - *: Every day of week
+
+# To view cron logs:
+#   tail -f /tmp/openclaw-cron.log
+
+# To view health check logs:
+#   .openclaw/cron/logs.sh
+
+# To uninstall, edit crontab (crontab -e) and remove the OpenClaw line

.openclaw/cron/executor.py

@@ -0,0 +1,205 @@
+#!/usr/bin/env python3
+"""
+OpenClaw Cron Executor
+Runs autonomous maintenance jobs for Cain
+"""
+import json
+import os
+import sys
+from datetime import datetime, timedelta
+from pathlib import Path
+import time
+import subprocess
+
+try:
+    from huggingface_hub import HfApi
+except ImportError:
+    print("Error: huggingface_hub not installed. Run: pip install huggingface_hub")
+    sys.exit(1)
+
+JOBS_FILE = Path(__file__).parent / "jobs.json"
+LOGS_DIR = Path(__file__).parent.parent / "logs"
+
+# Space configuration
+SPACE_ID = "tao-shen/HuggingClaw-Cain"
+
+
+def get_hf_api():
+    """Get HuggingFace API instance"""
+    token = os.environ.get("HF_TOKEN")
+    if not token:
+        # Try reading from .env file
+        env_file = Path(__file__).parent.parent.parent / ".env"
+        if env_file.exists():
+            with open(env_file) as f:
+                for line in f:
+                    if line.startswith("HF_TOKEN="):
+                        token = line.strip().split("=", 1)[1].strip('"\'')
+                        break
+    return HfApi(token=token)
+
+
+def hf_space_status(space_id: str = SPACE_ID) -> dict:
+    """Check HuggingFace Space status"""
+    api = get_hf_api()
+    try:
+        info = api.space_info(repo_id=space_id)
+        # Get runtime info - the structure may vary
+        runtime = getattr(info, 'runtime', None)
+        if runtime:
+            stage = getattr(runtime, 'stage', 'UNKNOWN')
+            status = getattr(runtime, 'status', 'UNKNOWN')
+            detail = f"Stage: {stage}, Status: {status}"
+        else:
+            stage = getattr(info, 'stage', 'UNKNOWN')
+            status = 'UNKNOWN'
+            detail = str(info)
+
+        return {
+            "stage": stage,
+            "status": status,
+            "detail": detail,
+            "success": True,
+            "space_info": str(info)
+        }
+    except Exception as e:
+        return {
+            "stage": "UNKNOWN",
+            "status": "ERROR",
+            "detail": str(e),
+            "success": False
+        }
+
+
+def hf_restart_space(space_id: str = SPACE_ID) -> dict:
+    """Restart a HuggingFace Space"""
+    api = get_hf_api()
+    try:
+        api.restart_space(repo_id=space_id)
+        return {
+            "success": True,
+            "detail": f"Restart initiated for {space_id}"
+        }
+    except Exception as e:
+        return {
+            "success": False,
+            "detail": str(e)
+        }
+
+
+def log_event(job_id: str, event_data: dict):
+    """Log an event to the appropriate log file"""
+    log_file = LOGS_DIR / f"{job_id}.jsonl"
+    log_file.parent.mkdir(parents=True, exist_ok=True)
+
+    event = {
+        "timestamp": datetime.utcnow().isoformat() + "Z",
+        "job_id": job_id,
+        **event_data
+    }
+
+    with open(log_file, "a") as f:
+        f.write(json.dumps(event) + "\n")
+
+
+def load_jobs() -> list:
+    """Load jobs from configuration file"""
+    with open(JOBS_FILE) as f:
+        config = json.load(f)
+    return config.get("jobs", [])
+
+
+def check_condition(status: str, condition: str) -> bool:
+    """Evaluate a failure condition"""
+    if "status in [" in condition:
+        allowed_statuses = condition.split("status in [")[1].split("]")[0]
+        allowed_statuses = [s.strip().strip("'\"") for s in allowed_statuses.split(",")]
+        return status in allowed_statuses
+    return False
+
+
+def run_job(job: dict):
+    """Execute a single job"""
+    job_id = job["id"]
+
+    if not job.get("enabled", True):
+        return
+
+    print(f"[{datetime.utcnow().isoformat()}] Running job: {job_id}")
+
+    try:
+        # Get health status
+        result = hf_space_status(space_id="tao-shen/HuggingClaw-Cain")
+
+        status = result.get("stage", "UNKNOWN")
+        detail = result.get("detail", "")
+
+        log_event(job_id, {
+            "status": status,
+            "stage": result.get("stage"),
+            "detail": detail,
+            "action": "check"
+        })
+
+        print(f"  Status: {status} - {detail}")
+
+        # Check failure condition
+        if "on_failure" in job:
+            failure_config = job["on_failure"]
+            condition = failure_config.get("condition", "")
+
+            if check_condition(status, condition):
+                print(f"  Failure condition met: {condition}")
+                log_event(job_id, {
+                    "status": status,
+                    "action": "recovery_triggered",
+                    "condition": condition
+                })
+
+                # Execute recovery action
+                if failure_config.get("tool") == "hf_restart_space":
+                    print("  Attempting recovery via hf_restart_space...")
+                    recovery_result = hf_restart_space(space_id="tao-shen/HuggingClaw-Cain")
+
+                    log_event(job_id, {
+                        "action": "recovery_attempt",
+                        "success": recovery_result.get("success", False),
+                        "detail": recovery_result.get("detail", "")
+                    })
+
+                    if recovery_result.get("success"):
+                        print("  Recovery initiated successfully")
+                    else:
+                        print(f"  Recovery failed: {recovery_result.get('detail')}")
+
+    except Exception as e:
+        print(f"  Error: {e}")
+        log_event(job_id, {
+            "action": "error",
+            "error": str(e)
+        })
+
+
+def main():
+    """Main entry point"""
+    if len(sys.argv) > 1 and sys.argv[1] == "--list":
+        jobs = load_jobs()
+        print("OpenClaw Cron Jobs:")
+        print("-" * 50)
+        for job in jobs:
+            status = "enabled" if job.get("enabled", True) else "disabled"
+            print(f"  {job['id']}: {job.get('schedule', 'N/A')} [{status}]")
+            print(f"    {job.get('description', '')}")
+        return
+
+    jobs = load_jobs()
+    print(f"OpenClaw Cron Executor - {len(jobs)} jobs loaded")
+
+    for job in jobs:
+        run_job(job)
+
+    print("Done.")
+
+
+if __name__ == "__main__":
+    main()

.openclaw/cron/jobs.json

@@ -0,0 +1,31 @@
+{
+  "jobs": [
+    {
+      "id": "health-check",
+      "schedule": "*/30 * * * *",
+      "enabled": true,
+      "description": "Monitor Cain's health and auto-recover from errors",
+      "tool": "hf_space_status",
+      "params": {
+        "space_id": "tao-shen/HuggingClaw-Cain"
+      },
+      "on_failure": {
+        "tool": "hf_restart_space",
+        "condition": "status in ['RUNTIME_ERROR', 'BUILDING'] and duration_minutes > 10",
+        "params": {
+          "space_id": "tao-shen/HuggingClaw-Cain"
+        }
+      },
+      "logging": {
+        "file": ".openclaw/logs/health-check.jsonl",
+        "format": "jsonl",
+        "retention_days": 30
+      }
+    }
+  ],
+  "metadata": {
+    "version": "1.0",
+    "created_at": "2026-03-14T00:00:00Z",
+    "description": "OpenClaw Cron Job Configuration for Cain Autonomous Maintenance"
+  }
+}

.openclaw/cron/logs.sh

@@ -0,0 +1,82 @@
+#!/bin/bash
+# View OpenClaw Cron Logs
+# Utility to view health check history
+
+LOG_FILE="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/../logs/health-check.jsonl"
+
+usage() {
+    echo "Usage: $0 [OPTIONS]"
+    echo ""
+    echo "Options:"
+    echo "  -n, --lines N     Show last N entries (default: 20)"
+    echo "  -f, --follow      Follow log output (like tail -f)"
+    echo "  -s, --summary     Show summary statistics"
+    echo "  -h, --help        Show this help message"
+    exit 1
+}
+
+lines=20
+follow=false
+summary=false
+
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        -n|--lines)
+            lines="$2"
+            shift 2
+            ;;
+        -f|--follow)
+            follow=true
+            shift
+            ;;
+        -s|--summary)
+            summary=true
+            shift
+            ;;
+        -h|--help)
+            usage
+            ;;
+        *)
+            echo "Unknown option: $1"
+            usage
+            ;;
+    esac
+done
+
+if [ "$summary" = true ]; then
+    echo "OpenClaw Health Check Summary"
+    echo "=============================="
+    echo ""
+
+    if [ ! -f "$LOG_FILE" ] || [ ! -s "$LOG_FILE" ]; then
+        echo "No logs found."
+        exit 0
+    fi
+
+    total=$(wc -l < "$LOG_FILE")
+    echo "Total entries: $total"
+    echo ""
+
+    echo "Action breakdown:"
+    jq -r '.action' "$LOG_FILE" 2>/dev/null | sort | uniq -c | sort -rn || echo "  (Unable to parse)"
+    echo ""
+
+    echo "Status breakdown:"
+    jq -r '.status // "N/A"' "$LOG_FILE" 2>/dev/null | sort | uniq -c | sort -rn || echo "  (Unable to parse)"
+    echo ""
+
+    echo "Recent failures:"
+    jq -r 'select(.action == "recovery_triggered" or .action == "error") | "\(.timestamp) - \(.status) - \(.action)"' "$LOG_FILE" 2>/dev/null | tail -5 || echo "  None"
+
+elif [ "$follow" = true ]; then
+    tail -f "$LOG_FILE" | while read -r line; do
+        echo "$line" | jq -r '[.timestamp, .action, .status // "N/A", .detail // ""] | @tsv' 2>/dev/null || echo "$line"
+    done
+else
+    echo "OpenClaw Health Checks (last $lines entries)"
+    echo "============================================"
+    echo ""
+    tail -n "$lines" "$LOG_FILE" | while read -r line; do
+        echo "$line" | jq -r '[.timestamp, .action, .status // "N/A", .detail // ""] | @tsv' 2>/dev/null || echo "$line"
+    done
+fi

.openclaw/cron/setup.sh

@@ -0,0 +1,51 @@
+#!/bin/bash
+# OpenClaw Cron Setup Script
+# Installs the health check cron job for Cain
+
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+PROJECT_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
+EXECUTOR="$SCRIPT_DIR/executor.py"
+
+echo "OpenClaw Cron Setup for Cain"
+echo "=============================="
+
+# Check if executor exists
+if [ ! -f "$EXECUTOR" ]; then
+    echo "Error: Executor not found at $EXECUTOR"
+    exit 1
+fi
+
+# Make sure executor is executable
+chmod +x "$EXECUTOR"
+
+# Create crontab entry
+CRON_ENTRY="*/30 * * * * cd $PROJECT_ROOT && $EXECUTOR >> /tmp/openclaw-cron.log 2>&1"
+
+echo "Cron entry to be installed:"
+echo "$CRON_ENTRY"
+echo ""
+
+# Check if entry already exists
+if crontab -l 2>/dev/null | grep -q "openclaw-cron"; then
+    echo "Cron entry already exists. Updating..."
+    # Remove old entry and add new one
+    crontab -l 2>/dev/null | grep -v "openclaw-cron" | crontab -
+fi
+
+# Install new cron entry
+(crontab -l 2>/dev/null; echo "$CRON_ENTRY") | crontab -
+
+echo "Cron job installed successfully!"
+echo ""
+echo "Cain will now perform health checks every 30 minutes."
+echo "Logs will be saved to:"
+echo "  - $PROJECT_ROOT/.openclaw/logs/health-checks.jsonl (job execution logs)"
+echo "  - /tmp/openclaw-cron.log (cron daemon logs)"
+echo ""
+echo "To view recent health checks:"
+echo "  tail -20 $PROJECT_ROOT/.openclaw/logs/health-checks.jsonl"
+echo ""
+echo "To manually run a health check:"
+echo "  $EXECUTOR"

.openclaw/logs/.gitignore

@@ -0,0 +1,3 @@
+# OpenClaw Cron Logs
+*.jsonl
+*.log