Shell: Cur isteach orduithe
Ar an leathanach seo
Shell: Cur isteach orduithe
Seo an uirlis is cumhachtaí sa chúrsa seo, agus an t-aon cheann ar féidir le botún a chumhacht a chasadh in aghaidh tú. Léann uirlisí eile, ríomhann siad nó cuardaíonn siad; gníomhaíonn an ceann seo ar mheaisín. Fanann diagnóis chórais mífhoirmithe ina diagnóis amháin; scriosann ordú glantáin mífhoirmithe comhaid.
Clúdaíonn an ceacht seo úsáid agus cosaintí le chéile toisc nach féidir iad a scaradh. An riail órga: níor chóir don mhúnla ordú a chur i gcrích riamh nár údarásaigh tú go sainráite roimh ré.
Coincheap agus Ailtireacht
Tá an difríocht ón Ateangaire Cóid ríthábhachtach, agus tagann sí anuas ar fhocal amháin: leithlisiú. Rithann an tAteangaire Cóid i ngaineamhlach in-idirdhealaithe, leithlisithe ón líonra, áit arb é an measctha is measa ná ríomh mícheart. Rithann Shell i dtimpeallacht a chumraíonn tú féin – d’fhéadfadh sé a bheith ar do mheaisín áitiúil, nó ar fhreastalaí – áit arb é an measctha is measa ná oibríocht dochúlaithe.
Is é an tsaoirse seo an pointe: gan í, tá imlonnú agus cothabháil uathoibrithe dodhéanta. Éilíonn sé ort, áfach, an raon feidhme feidhmiúcháin a roghnú go feasach. Is beagnach i gcónaí an rogha cheart coimeádán tiomnaithe le pribhléidí teoranta seachas rochtain dhíreach ar an óstach.
from openai import OpenAI
client = OpenAI()
# The Shell tool is used via the Agents SDK
# because it requires a controlled execution environment
from agents import Agent, Runner
agent = Agent(
name="devops-assistant",
model="gpt-5.6-terra",
instructions=(
"You are a DevOps assistant. You execute system commands "
"to diagnose and resolve infrastructure issues. "
"Explain each command before executing it."
),
tools=[{"type": "shell"}]
)
Cás Úsáide: Diagnóis Córais
# The agent can execute diagnostic commands
agent = Agent(
name="diagnostic",
model="gpt-5.6-terra",
instructions=(
"Diagnose the system state by executing appropriate commands. "
"Start with basic checks (disk, memory, CPU) "
"then dig deeper based on symptoms."
),
tools=[{"type": "shell"}]
)
# The agent will execute commands like:
# df -h -> disk space
# free -m -> memory
# top -bn1 -> CPU load
# systemctl status nginx -> service status
Feidhmiú a Dhaingniú
Oibríonn trí chosaint le chéile, agus níl aon cheann acu leordhóthanach leis féin. Is é an liosta ceadaithe an bonn: liostaíonn tú cad atá ceadaithe seachas cad atá toirmiscthe, toisc go mbíonn leagan éagsúil in easnamh i gcónaí ar liosta blocála – agus ní theastaíonn ach ceann amháin. Cuireann teorainn ama cosc ar ordú greamaithe an córas a chur ar ceal. Teorannaíonn comhadlann oibre shrianta an damáiste má dhíríonn ordú dlisteanach ar an áit mhícheart.
Is é an ceathrú cosaint, nach bhfuil teicniúil ach fiú na trí cinn eile le chéile: éiligh deimhniú daonna ar aon oibríocht scriosach nó dochúlaithe. Déanann múnla botúin leis an muinín chéanna agus atá aige nuair atá sé ceart.
# Pattern: wrapper function with validation
import subprocess
import shlex
ALLOWED_COMMANDS = {
"diagnostic": ["df", "free", "top", "uptime", "ps", "netstat", "curl", "ping"],
"deployment": ["git", "docker", "npm", "pip"],
"files": ["ls", "cat", "head", "tail", "wc", "grep", "find"],
}
FORBIDDEN_COMMANDS = ["rm", "dd", "mkfs", "shutdown", "reboot", "kill", "passwd"]
def execute_secure_command(command: str, category: str = "diagnostic") -> dict:
"""Executes a command with security validation."""
# Parse the command
parts = shlex.split(command)
executable = parts[0]
# Check prohibitions
if executable in FORBIDDEN_COMMANDS:
return {
"error": f"Forbidden command: {executable}",
"reason": "This command is on the blocklist"
}
# Check permissions
allowed = ALLOWED_COMMANDS.get(category, [])
if executable not in allowed:
return {
"error": f"Command not allowed in category '{category}'",
"allowed": allowed
}
# Execute with timeout
try:
result = subprocess.run(
parts,
capture_output=True,
text=True,
timeout=30,
cwd="/tmp" # Restricted working directory
)
return {
"stdout": result.stdout,
"stderr": result.stderr,
"return_code": result.returncode
}
except subprocess.TimeoutExpired:
return {"error": "Timeout: command exceeded 30 seconds"}
Cur i bhFeidhm mar Fheidhm Shaincheaptha
Tá buntáiste ag baint leis an méid seo a chur i bhfeidhm tú féin trí ghlao feidhme nach ba chóir duit a mheas mar rogha thánaisteach: tá an bailíochtú i do chód féin. Is tú a chinneann an liosta ceadaithe, an logáil, agus na céimeanna deimhnithe, agus is féidir leat gach rud a iniúchadh. Maidir le huirlis a bhfuil an leibhéal riosca seo aici, is fearr smacht a choinneáil ar an bpointe seiceála, fiú nuair a bheidh leagan dúchasach ar fáil.
tools = [
{
"type": "function",
"name": "execute_command",
"description": (
"Execute a shell command on the server. "
"Allowed commands: system diagnostics (df, free, top, uptime, ps), "
"file reading (ls, cat, head, tail, grep), "
"network (curl, ping, netstat). "
"Destructive commands are forbidden."
),
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "The shell command to execute"
},
"directory": {
"type": "string",
"description": "Working directory (default: /tmp)"
}
},
"required": ["command"],
"additionalProperties": False
},
"strict": True
}
]
import json
def handle_calls(response):
results = []
for item in response.output:
if item.type == "function_call" and item.name == "execute_command":
args = json.loads(item.arguments)
result = execute_secure_command(
args["command"],
category="diagnostic"
)
results.append({
"type": "function_call_output",
"call_id": item.call_id,
"output": json.dumps(result)
})
return results
# Full loop
response = client.responses.create(
model="gpt-5.6-terra",
input="Check disk space and available memory",
tools=tools
)
results = handle_calls(response)
final_response = client.responses.create(
model="gpt-5.6-terra",
input=response.output + results,
tools=tools
)
print(final_response.output_text)
Sruthanna Oibre Uathoibrithe
Imlonnú Uathoibrithe
Is é an imlonnú an cás úsáide is luachmhaire, ar choinníoll go dtuigeann tú cad atá tú a tharmligean. Ní chruthaíonn an múnla an nós imeachta: slabhraíonn sé céimeanna a shainigh tú, fíoraíonn sé aschuir idirmheánacha, agus stopann sé ar aon ainrialtacht. Is oibreoir aireach é, ní cinnteoir.
tools_deploy = [
{
"type": "function",
"name": "execute_deploy_step",
"description": (
"Execute a deployment step. "
"Possible steps: git_pull, tests, build, deploy, rollback. "
"Each step is validated before proceeding to the next."
),
"parameters": {
"type": "object",
"properties": {
"step": {
"type": "string",
"enum": ["git_pull", "tests", "build", "deploy", "rollback"]
},
"parameters": {
"type": "object",
"properties": {
"branch": {"type": "string"},
"environment": {"type": "string", "enum": ["staging", "production"]}
}
}
},
"required": ["step"],
"additionalProperties": False
},
"strict": True
}
]
def execute_step(step: str, params: dict) -> dict:
scripts = {
"git_pull": "cd /app && git pull origin {branch}",
"tests": "cd /app && npm test",
"build": "cd /app && npm run build",
"deploy": "cd /app && ./deploy.sh {environment}",
"rollback": "cd /app && ./rollback.sh {environment}"
}
command = scripts[step].format(**params)
return execute_secure_command(command, "deployment")
Monatóireacht agus Foláirimh
Casann monatóireacht loighic an chuid eile den cheacht seo bun os cionn: tá na horduithe anseo inléite amháin, mar sin tá siad díobhálach, agus tá an luach sa léirmhíniú. Aithníonn múnla a léann spás diosca, ualach, agus logaí earráide comhcheangail nach mbraitheann tairseach leithlisithe – rud a fhágann gurb é seo an pointe iontrála is sábháilte chun tosú leis an uirlis seo.
def check_system_health() -> dict:
"""Checks system health and returns a report."""
checks = {}
# Disk space
r = execute_secure_command("df -h /", "diagnostic")
checks["disk"] = r
# Memory
r = execute_secure_command("free -m", "diagnostic")
checks["memory"] = r
# Services
for service in ["nginx", "postgresql", "redis"]:
r = execute_secure_command(
f"systemctl is-active {service}",
"diagnostic"
)
checks[f"service_{service}"] = r
return checks
# The AI analyzes the results and suggests actions
response = client.responses.create(
model="gpt-5.6-terra",
input=f"Analyze this system health report and identify issues:\n"
f"{json.dumps(check_system_health(), indent=2)}",
tools=tools
)
Príomhphointí
- Nascann an uirlis Shell an múnla le d’bonneagar
- Cuir liostaí ceadaithe agus liostaí blocála i bhfeidhm d’orduithe
- Úsáid teorainneacha ama agus comhadlanna oibre srianta
- Ligeann glao feidhme duit Shell a chur i bhfeidhm mar uirlis saincheaptha
- Comhcheangail Shell le huirlisí eile le haghaidh sruthanna oibre DevOps iomlána