Harden Gemini scripts with verified SSH trust
Some checks failed
Architecture Lint / Linter Tests (pull_request) Successful in 8s
Validate Config / YAML Lint (pull_request) Failing after 5s
Validate Config / JSON Validate (pull_request) Successful in 6s
PR Checklist / pr-checklist (pull_request) Failing after 1m11s
Smoke Test / smoke (pull_request) Failing after 7s
Validate Config / Python Syntax & Import Check (pull_request) Failing after 9s
Validate Config / Shell Script Lint (pull_request) Successful in 15s
Validate Config / Cron Syntax Check (pull_request) Successful in 5s
Validate Config / Deploy Script Dry Run (pull_request) Successful in 5s
Validate Config / Playbook Schema Validation (pull_request) Successful in 7s
Architecture Lint / Lint Repository (pull_request) Failing after 6s
Some checks failed
Architecture Lint / Linter Tests (pull_request) Successful in 8s
Validate Config / YAML Lint (pull_request) Failing after 5s
Validate Config / JSON Validate (pull_request) Successful in 6s
PR Checklist / pr-checklist (pull_request) Failing after 1m11s
Smoke Test / smoke (pull_request) Failing after 7s
Validate Config / Python Syntax & Import Check (pull_request) Failing after 9s
Validate Config / Shell Script Lint (pull_request) Successful in 15s
Validate Config / Cron Syntax Check (pull_request) Successful in 5s
Validate Config / Deploy Script Dry Run (pull_request) Successful in 5s
Validate Config / Playbook Schema Validation (pull_request) Successful in 7s
Architecture Lint / Lint Repository (pull_request) Failing after 6s
This commit is contained in:
@@ -10,12 +10,17 @@ Safe-by-default: runs in dry-run mode unless --execute is given.
|
||||
|
||||
import os
|
||||
import sys
|
||||
import subprocess
|
||||
import argparse
|
||||
import requests
|
||||
import datetime
|
||||
from typing import Sequence
|
||||
|
||||
SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
|
||||
if SCRIPT_DIR not in sys.path:
|
||||
sys.path.insert(0, SCRIPT_DIR)
|
||||
|
||||
from ssh_trust import VerifiedSSHExecutor
|
||||
|
||||
# --- CONFIGURATION ---
|
||||
FLEET = {
|
||||
"mac": {"ip": "10.1.10.77", "port": 8080},
|
||||
@@ -25,54 +30,24 @@ FLEET = {
|
||||
}
|
||||
|
||||
class SelfHealer:
|
||||
def __init__(self, dry_run=True, confirm_kill=False, yes=False):
|
||||
def __init__(self, dry_run=True, confirm_kill=False, yes=False, executor=None):
|
||||
self.dry_run = dry_run
|
||||
self.confirm_kill = confirm_kill
|
||||
self.yes = yes
|
||||
self.executor = executor or VerifiedSSHExecutor()
|
||||
|
||||
def log(self, message: str):
|
||||
timestamp = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||||
print(f"[{timestamp}] {message}")
|
||||
|
||||
def run_remote(self, host: str, command: str):
|
||||
ip = FLEET[host]["ip"]
|
||||
ssh_cmd = ["ssh", "-o", "StrictHostKeyChecking=no", "-o", "ConnectTimeout=5", f"root@{ip}", command]
|
||||
if host == "mac":
|
||||
ssh_cmd = ["bash", "-c", command]
|
||||
ip = FLEET[host]['ip']
|
||||
try:
|
||||
return subprocess.run(ssh_cmd, capture_output=True, text=True, timeout=15)
|
||||
return self.executor.run_script(ip, command, local=(host == 'mac'), timeout=15)
|
||||
except Exception as e:
|
||||
self.log(f" [ERROR] Failed to run remote command on {host}: {e}")
|
||||
return None
|
||||
|
||||
def confirm(self, prompt: str) -> bool:
|
||||
"""Ask for confirmation unless --yes flag is set."""
|
||||
if self.yes:
|
||||
return True
|
||||
while True:
|
||||
response = input(f"{prompt} [y/N] ").strip().lower()
|
||||
if response in ("y", "yes"):
|
||||
return True
|
||||
elif response in ("n", "no", ""):
|
||||
return False
|
||||
print("Please answer 'y' or 'n'.")
|
||||
|
||||
def check_llama_server(self, host: str):
|
||||
ip = FLEET[host]["ip"]
|
||||
port = FLEET[host]["port"]
|
||||
try:
|
||||
requests.get(f"http://{ip}:{port}/health", timeout=2)
|
||||
except:
|
||||
self.log(f" [!] llama-server down on {host}.")
|
||||
if self.dry_run:
|
||||
self.log(f" [DRY-RUN] Would restart llama-server on {host}")
|
||||
else:
|
||||
if self.confirm(f" Restart llama-server on {host}?"):
|
||||
self.log(f" Restarting llama-server on {host}...")
|
||||
self.run_remote(host, "systemctl restart llama-server")
|
||||
else:
|
||||
self.log(f" Skipped restart on {host}.")
|
||||
|
||||
def check_disk_space(self, host: str):
|
||||
res = self.run_remote(host, "df -h / | tail -1 | awk '{print $5}' | sed 's/%//'")
|
||||
if res and res.returncode == 0:
|
||||
|
||||
Reference in New Issue
Block a user