Files
stackpilot/backend/agent_app.py
T
menzeljandClaude Opus 4.8 d46a6c3576 Remote deploy console: stream agent compose up to the browser (0.23.0)
Extends the live deploy console to remote/agent stacks. New agent WS endpoint
`/agent/ws/deploy/{stack_id}` runs `compose up -d` and streams its output; the
central app proxies it through `/ws/agent-deploy/{agent_id}/{stack_id}` (same
pattern + token URL-encoding as the agent-logs proxy) and records an
`agent.stack.start` audit entry. The editor's remote Deploy path now opens the
DeployConsole (agentId) instead of the blocking `agentsApi.action(start)`.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-08 19:44:31 +00:00

678 lines
23 KiB
Python

"""StackPilot agent — a slim, token-guarded Docker Compose API for one host.
The agent runs on each remote host (same image as the backend, different CMD).
It has no users, no database and no UI: it exposes just enough of the stack /
system surface for a central StackPilot to manage this host's compose stacks,
authenticated by a single shared bearer token (``AGENT_TOKEN``).
All compose/Docker logic is reused from the backend's ``compose_service`` and
``docker_client`` so behaviour matches the local host exactly.
"""
from __future__ import annotations
import logging
import os
import shutil
from dataclasses import asdict
import tempfile
import json
from fastapi import (
Depends,
FastAPI,
File,
Form,
Header,
HTTPException,
Query,
Request,
UploadFile,
WebSocket,
WebSocketDisconnect,
)
from fastapi.responses import FileResponse, JSONResponse
from pydantic import BaseModel
from config import settings
from docker_client import DockerError, get_client, safe_call
from services import (
backup_service,
compose_service,
device_service,
file_service,
image_service,
network_service,
stats_service,
update_service,
volume_service,
)
logger = logging.getLogger("stackpilot.agent")
# Map network_service's DockerError codes to HTTP status. forbidden is mapped to
# 400 (not 403) so the central proxy doesn't misread it as a token failure.
_DOCKER_STATUS = {"invalid_request": 400, "forbidden": 400, "not_found": 404}
def _map_docker(exc: DockerError):
code = _DOCKER_STATUS.get(exc.error)
if code:
raise HTTPException(status_code=code, detail=exc.detail or exc.error)
raise exc # falls through to the global 502 DockerError handler
AGENT_VERSION = "0.23.0"
# --------------------------------------------------------------------------- #
# Auth
# --------------------------------------------------------------------------- #
def verify_token(authorization: str = Header(default="")) -> None:
expected = settings.AGENT_TOKEN
if not expected:
raise HTTPException(status_code=503, detail="Agent token not configured")
if authorization != f"Bearer {expected}":
raise HTTPException(status_code=401, detail="Invalid agent token")
# --------------------------------------------------------------------------- #
# Schemas
# --------------------------------------------------------------------------- #
class StackBody(BaseModel):
name: str | None = None
yaml: str | None = None
env: str | None = None
class NetworkCreateBody(BaseModel):
name: str
driver: str = "bridge"
subnet: str | None = None
gateway: str | None = None
internal: bool = False
attachable: bool = True
class ContainerRefBody(BaseModel):
container: str
aliases: list[str] | None = None
force: bool = False
class FileWriteBody(BaseModel):
path: str
content: str
class FileNameBody(BaseModel):
path: str
name: str
class FileRenameBody(BaseModel):
path: str
new_name: str
class FileTransferBody(BaseModel):
src: str
dest_dir: str
overwrite: bool = False
def _file_guard(fn, *args, **kwargs):
try:
return fn(*args, **kwargs)
except file_service.BrowseError as exc:
raise HTTPException(status_code=400, detail=str(exc)) from exc
# --------------------------------------------------------------------------- #
# Helpers
# --------------------------------------------------------------------------- #
def _summary(stack_id: str, summaries: dict | None = None) -> dict:
if summaries is None:
try:
containers = compose_service.containers_for_stack(stack_id)
total = len(containers)
running = sum(1 for c in containers if c.state == "running")
status = compose_service.compute_status(stack_id, containers)
except DockerError:
total = running = 0
status = "unknown"
else:
info = summaries.get(stack_id)
total = info["total"] if info else 0
running = info["running"] if info else 0
if compose_service.is_busy(stack_id):
status = "updating"
else:
status = info["status"] if info else "stopped"
return {
"id": stack_id,
"name": stack_id,
"description": None,
"status": status,
"service_count": total,
"running_count": running,
"created_at": None,
"updated_at": None,
}
def _hostname() -> str:
return os.uname().nodename
def _mem_info() -> tuple[int, int]:
"""Return (total_bytes, used_bytes) from meminfo (used = total - available)."""
for base in (settings.HOST_PROC_PATH, "/proc"):
try:
vals: dict[str, int] = {}
with open(os.path.join(base, "meminfo"), "r", encoding="utf-8") as fh:
for line in fh:
parts = line.split(":")
if len(parts) == 2 and parts[0] in ("MemTotal", "MemAvailable", "MemFree"):
try:
vals[parts[0]] = int(parts[1].split()[0]) * 1024 # kB -> bytes
except ValueError:
pass
total = vals.get("MemTotal", 0)
available = vals.get("MemAvailable", vals.get("MemFree", 0))
return total, max(total - available, 0)
except OSError:
continue
return 0, 0
def _disk_info() -> tuple[int, int]:
"""Return (total_bytes, used_bytes) for the host disk backing the stacks dir."""
for path in (settings.STACKS_DIR, "/"):
try:
usage = shutil.disk_usage(path)
return usage.total, usage.used
except OSError:
continue
return 0, 0
def _system_info() -> dict:
docker_version = ""
host_os = ""
running = total = 0
try:
client = get_client()
docker_version = safe_call(client.version).get("Version", "")
info = safe_call(client.info)
host_os = info.get("OperatingSystem", "")
running = info.get("ContainersRunning", 0)
total = info.get("Containers", 0)
except DockerError as exc:
docker_version = f"unavailable ({exc.error})"
mem_total, mem_used = _mem_info()
disk_total, disk_used = _disk_info()
return {
"hostname": _hostname(),
"docker_version": docker_version,
"host_os": host_os,
"cpu_cores": os.cpu_count() or 0,
"mem_total": mem_total,
"mem_used": mem_used,
"disk_total": disk_total,
"disk_used": disk_used,
"containers_running": running,
"containers_total": total,
}
# --------------------------------------------------------------------------- #
# App
# --------------------------------------------------------------------------- #
app = FastAPI(title="StackPilot Agent", version=AGENT_VERSION)
@app.exception_handler(DockerError)
async def _docker_error(_request: Request, exc: DockerError):
return JSONResponse(status_code=502, content={"error": exc.error, "detail": exc.detail})
@app.get("/agent/ping", dependencies=[Depends(verify_token)])
def ping() -> dict:
return {"ok": True, "hostname": _hostname(), "version": AGENT_VERSION}
@app.get("/agent/system", dependencies=[Depends(verify_token)])
def system() -> dict:
return _system_info()
@app.get("/agent/stacks", dependencies=[Depends(verify_token)])
def list_stacks() -> list[dict]:
try:
summaries = compose_service.stack_status_summaries()
except DockerError:
summaries = {}
return [_summary(sid, summaries) for sid in compose_service.discover_stacks()]
@app.get("/agent/stacks/stats", dependencies=[Depends(verify_token)])
def stacks_stats() -> dict:
return stats_service.stack_stats()
@app.get("/agent/stacks/{stack_id}", dependencies=[Depends(verify_token)])
def get_stack(stack_id: str) -> dict:
directory = compose_service.stack_dir(stack_id)
if not os.path.isdir(directory):
raise HTTPException(status_code=404, detail=f"Stack '{stack_id}' not found")
try:
raw = compose_service.containers_for_stack(stack_id)
containers = [asdict(c) for c in raw]
status = compose_service.compute_status(stack_id, raw)
except DockerError:
containers = []
status = "unknown"
return {
"id": stack_id,
"name": stack_id,
"description": None,
"status": status,
"yaml": compose_service.read_compose(stack_id),
"env": compose_service.read_env(stack_id),
"containers": containers,
"created_at": None,
"updated_at": None,
}
@app.post("/agent/stacks", dependencies=[Depends(verify_token)], status_code=201)
def create_stack(body: StackBody) -> dict:
if not body.name:
raise HTTPException(status_code=400, detail="name is required")
stack_id = compose_service.slugify(body.name)
if os.path.isdir(compose_service.stack_dir(stack_id)):
raise HTTPException(status_code=409, detail=f"Stack '{stack_id}' already exists")
compose_service.write_compose(stack_id, body.yaml or "services:\n")
if body.env:
compose_service.write_env(stack_id, body.env)
return _summary(stack_id)
@app.put("/agent/stacks/{stack_id}", dependencies=[Depends(verify_token)])
def update_stack(stack_id: str, body: StackBody) -> dict:
if not os.path.isdir(compose_service.stack_dir(stack_id)):
raise HTTPException(status_code=404, detail=f"Stack '{stack_id}' not found")
if body.yaml is not None:
compose_service.write_compose(stack_id, body.yaml)
if body.env is not None:
compose_service.write_env(stack_id, body.env)
return _summary(stack_id)
@app.delete("/agent/stacks/{stack_id}", dependencies=[Depends(verify_token)])
async def delete_stack(stack_id: str, delete_files: bool = Query(True)) -> dict:
if not os.path.isdir(compose_service.stack_dir(stack_id)):
raise HTTPException(status_code=404, detail=f"Stack '{stack_id}' not found")
try:
await compose_service.down(stack_id)
except Exception: # noqa: BLE001 - best-effort teardown
pass
if delete_files:
compose_service.delete_stack_files(stack_id)
return {"ok": True}
_ACTIONS = {
"start": compose_service.up,
"stop": compose_service.stop,
"restart": compose_service.restart,
"pull": compose_service.pull,
"update": compose_service.update,
"down": compose_service.down,
}
@app.post("/agent/stacks/{stack_id}/{action}", dependencies=[Depends(verify_token)])
async def lifecycle(stack_id: str, action: str) -> dict:
fn = _ACTIONS.get(action)
if not fn:
raise HTTPException(status_code=400, detail=f"Unknown action '{action}'")
if not os.path.isdir(compose_service.stack_dir(stack_id)):
raise HTTPException(status_code=404, detail=f"Stack '{stack_id}' not found")
result = await fn(stack_id)
if result.get("returncode") not in (0, None):
raise HTTPException(
status_code=500,
detail={
"error": f"compose {action} failed",
"detail": result.get("stderr", "").strip()[-2000:],
},
)
return result
@app.get("/agent/stacks/{stack_id}/logs", dependencies=[Depends(verify_token)])
async def stack_logs(stack_id: str, tail: int = Query(200, le=2000)) -> dict:
if not os.path.isdir(compose_service.stack_dir(stack_id)):
raise HTTPException(status_code=404, detail=f"Stack '{stack_id}' not found")
result = await compose_service.logs(stack_id, tail=tail)
return {"logs": result.get("stdout", "") + result.get("stderr", "")}
@app.get("/agent/stacks/{stack_id}/backup", dependencies=[Depends(verify_token)])
async def backup_stack(
stack_id: str,
include_volumes: bool = Query(True),
stop_first: bool = Query(True),
):
if not os.path.isdir(compose_service.stack_dir(stack_id)):
raise HTTPException(status_code=404, detail=f"Stack '{stack_id}' not found")
try:
path = await backup_service.create_backup(
stack_id, stack_id, include_volumes=include_volumes, stop_first=stop_first,
)
except backup_service.BackupError as exc:
raise HTTPException(status_code=400, detail=str(exc)) from exc
return FileResponse(
path,
media_type="application/gzip",
filename=backup_service.backup_filename(stack_id, include_volumes),
)
@app.post("/agent/stacks/restore", dependencies=[Depends(verify_token)])
async def restore_stack(
file: UploadFile = File(...),
target_id: str | None = Form(None),
overwrite: bool = Form(False),
restore_volumes: bool = Form(True),
) -> dict:
tmp = tempfile.NamedTemporaryFile(delete=False, suffix=".tar.gz")
try:
while chunk := await file.read(1024 * 1024):
tmp.write(chunk)
tmp.close()
target = compose_service.slugify(target_id) if target_id else None
try:
return backup_service.restore_backup(
tmp.name, target_id=target, overwrite=overwrite, restore_volumes=restore_volumes,
)
except backup_service.BackupError as exc:
code = 409 if "already exists" in str(exc) else 400
raise HTTPException(status_code=code, detail=str(exc)) from exc
finally:
if os.path.exists(tmp.name):
os.unlink(tmp.name)
# --------------------------------------------------------------------------- #
# Networks
# --------------------------------------------------------------------------- #
@app.get("/agent/networks", dependencies=[Depends(verify_token)])
def list_networks() -> list[dict]:
return network_service.list_networks()
@app.get("/agent/networks/{network_id}", dependencies=[Depends(verify_token)])
def inspect_network(network_id: str) -> dict:
try:
return network_service.inspect_network(network_id)
except DockerError as exc:
_map_docker(exc)
@app.get("/agent/networks/{network_id}/containers", dependencies=[Depends(verify_token)])
def network_containers(network_id: str) -> list[dict]:
try:
return network_service.connectable_containers(network_id)
except DockerError as exc:
_map_docker(exc)
@app.post("/agent/networks/{network_id}/connect", dependencies=[Depends(verify_token)])
def connect_container(network_id: str, body: ContainerRefBody) -> dict:
try:
network_service.connect_container(network_id, body.container, body.aliases)
except DockerError as exc:
_map_docker(exc)
return {"ok": True}
@app.post("/agent/networks/{network_id}/disconnect", dependencies=[Depends(verify_token)])
def disconnect_container(network_id: str, body: ContainerRefBody) -> dict:
try:
network_service.disconnect_container(network_id, body.container, body.force)
except DockerError as exc:
_map_docker(exc)
return {"ok": True}
@app.post("/agent/networks", dependencies=[Depends(verify_token)], status_code=201)
def create_network(body: NetworkCreateBody) -> dict:
try:
return network_service.create_network(body.model_dump())
except DockerError as exc:
_map_docker(exc)
@app.delete("/agent/networks/{network_id}", dependencies=[Depends(verify_token)])
def delete_network(network_id: str) -> dict:
try:
network_service.delete_network(network_id)
except DockerError as exc:
_map_docker(exc)
return {"ok": True}
@app.post("/agent/networks/prune", dependencies=[Depends(verify_token)])
def prune_networks() -> dict:
return network_service.prune_networks()
# --------------------------------------------------------------------------- #
# Images
# --------------------------------------------------------------------------- #
@app.get("/agent/images", dependencies=[Depends(verify_token)])
def list_images() -> list[dict]:
return image_service.list_images()
@app.get("/agent/images/updates", dependencies=[Depends(verify_token)])
def image_updates() -> dict:
return update_service.get_cache()
@app.post("/agent/images/check", dependencies=[Depends(verify_token)])
async def image_check() -> dict:
return await update_service.check_all()
# --------------------------------------------------------------------------- #
# Volumes
# --------------------------------------------------------------------------- #
@app.get("/agent/volumes", dependencies=[Depends(verify_token)])
def list_volumes() -> list[dict]:
return volume_service.list_volumes()
@app.get("/agent/volumes/sizes", dependencies=[Depends(verify_token)])
def volume_sizes(force: bool = Query(False)) -> dict:
return volume_service.volume_sizes(force=force)
@app.delete("/agent/volumes/{name}", dependencies=[Depends(verify_token)])
def delete_volume(name: str, force: bool = Query(False)) -> dict:
vols = {v["name"]: v for v in volume_service.list_volumes()}
if name in vols and vols[name]["in_use"] and not force:
raise HTTPException(
status_code=409,
detail={
"error": "volume_in_use",
"detail": f"Volume '{name}' is used by: {', '.join(vols[name]['used_by'])}",
},
)
volume_service.remove_volume(name, force=force)
return {"ok": True}
@app.post("/agent/volumes/prune", dependencies=[Depends(verify_token)])
def prune_volumes() -> dict:
return volume_service.prune_volumes()
# --------------------------------------------------------------------------- #
# File browser (sandboxed by this agent's ALLOWED_BROWSE_ROOTS/HOST_ROOT_PREFIX)
# --------------------------------------------------------------------------- #
@app.get("/agent/files/list", dependencies=[Depends(verify_token)])
def files_list(path: str = Query("/"), show_hidden: bool = Query(False)) -> dict:
return _file_guard(device_service.browse, path, show_hidden)
@app.get("/agent/files/read", dependencies=[Depends(verify_token)])
def files_read(path: str = Query(...)) -> dict:
return _file_guard(file_service.read_file, path)
@app.get("/agent/files/download", dependencies=[Depends(verify_token)])
def files_download(path: str = Query(...)):
real, filename = _file_guard(file_service.resolve_download, path)
return FileResponse(real, filename=filename, media_type="application/octet-stream")
@app.put("/agent/files/write", dependencies=[Depends(verify_token)])
def files_write(body: FileWriteBody) -> dict:
return _file_guard(file_service.write_file, body.path, body.content)
@app.post("/agent/files/mkdir", dependencies=[Depends(verify_token)])
def files_mkdir(body: FileNameBody) -> dict:
return _file_guard(file_service.create_dir, body.path, body.name)
@app.post("/agent/files/touch", dependencies=[Depends(verify_token)])
def files_touch(body: FileNameBody) -> dict:
return _file_guard(file_service.create_file, body.path, body.name)
@app.post("/agent/files/rename", dependencies=[Depends(verify_token)])
def files_rename(body: FileRenameBody) -> dict:
return _file_guard(file_service.rename, body.path, body.new_name)
@app.post("/agent/files/copy", dependencies=[Depends(verify_token)])
def files_copy(body: FileTransferBody) -> dict:
return _file_guard(file_service.copy, body.src, body.dest_dir, body.overwrite)
@app.post("/agent/files/move", dependencies=[Depends(verify_token)])
def files_move(body: FileTransferBody) -> dict:
return _file_guard(file_service.move, body.src, body.dest_dir, body.overwrite)
@app.delete("/agent/files", dependencies=[Depends(verify_token)])
def files_delete(path: str = Query(...), recursive: bool = Query(False)) -> dict:
return _file_guard(file_service.delete, path, recursive)
@app.post("/agent/files/upload", dependencies=[Depends(verify_token)])
async def files_upload(
path: str = Form(...),
overwrite: bool = Form(False),
rel_path: str = Form(""),
file: UploadFile = File(...),
) -> dict:
real = _file_guard(
file_service.upload_target, path, file.filename or "", overwrite, rel_path or None
)
tmp = tempfile.NamedTemporaryFile(delete=False, dir=os.path.dirname(real))
try:
while chunk := await file.read(1024 * 1024):
tmp.write(chunk)
tmp.close()
os.replace(tmp.name, real)
except OSError as exc:
if os.path.exists(tmp.name):
os.unlink(tmp.name)
raise HTTPException(status_code=400, detail=f"Upload failed: {exc}") from exc
return {"ok": True, "name": rel_path or file.filename}
@app.websocket("/agent/ws/logs/{stack_id}")
async def ws_logs(websocket: WebSocket, stack_id: str, token: str | None = Query(default=None)):
"""Stream `docker compose logs -f` to the central app (token via query param)."""
await websocket.accept()
expected = settings.AGENT_TOKEN
if not expected or token != expected:
await websocket.close(code=4401)
return
if not os.path.isdir(compose_service.stack_dir(stack_id)):
await websocket.send_text(json.dumps({"type": "error", "detail": "stack not found"}))
await websocket.close()
return
args = ["logs", "--no-color", "--tail", "200", "--timestamps", "-f"]
try:
async for line in compose_service.stream_compose(stack_id, args):
await websocket.send_text(
json.dumps({"type": "log", "stack_id": stack_id, "service": None, "line": line})
)
except WebSocketDisconnect:
pass
except Exception as exc: # noqa: BLE001
try:
await websocket.send_text(json.dumps({"type": "error", "detail": str(exc)}))
except Exception: # noqa: BLE001
pass
@app.websocket("/agent/ws/deploy/{stack_id}")
async def ws_deploy(websocket: WebSocket, stack_id: str, token: str | None = Query(default=None)):
"""Run `docker compose up -d` and stream its output to the central app so the
browser sees deploy progress live (token via query param)."""
await websocket.accept()
expected = settings.AGENT_TOKEN
if not expected or token != expected:
await websocket.close(code=4401)
return
if not os.path.isdir(compose_service.stack_dir(stack_id)):
await websocket.send_text(json.dumps({"type": "error", "detail": "stack not found"}))
await websocket.close()
return
compose_service.mark_busy(stack_id)
try:
async for kind, payload in compose_service.stream_up(stack_id):
if kind == "log":
await websocket.send_text(json.dumps({"type": "log", "line": payload}))
else:
await websocket.send_text(json.dumps({"type": "done", "returncode": payload}))
except WebSocketDisconnect:
# Browser navigated away; the compose subprocess keeps running.
pass
except Exception as exc: # noqa: BLE001
try:
await websocket.send_text(json.dumps({"type": "error", "detail": str(exc)}))
except Exception: # noqa: BLE001
pass
finally:
compose_service.clear_busy(stack_id)
@app.get("/agent/health")
def health() -> dict:
return {"status": "ok"}