feat(firecracker): add Linux microVM backend to replace smolmachines
Adds a Firecracker-based backend for Linux, providing mature KVM-based microVM isolation to replace smolmachines/libkrun (issue #342, closes the dead-end tracked in #332). Architecture: - Guest control over SSH (dropbear injected into the rootfs) on a point-to-point TAP link. `ssh -t` forwards SIGWINCH natively, so no resize bridge is needed. - Networking: a one-time, root-provisioned pool of user-owned TAP devices (no shared bridge → no docker0/virbr0/cni0 collisions) plus a dedicated `table inet bot_bottle_fc` nftables table (independent of Docker/ufw/firewalld rules). `./cli.py firecracker setup` prints the host-appropriate config (NixOS module or sudo script). - Rootfs: `docker export` → ext4 via `mke2fs -d` (rootless, no mount), cached by image digest; per-bottle SSH pubkey + IP passed via the kernel cmdline. - Sidecar: reuses the Docker bundle, published on the slot's host TAP IP. - Fail-closed isolation: TAP pool verified at preflight; the egress boundary is proven empirically post-boot (before the agent runs) by a canary probe — the VM must fail to reach the host directly, or launch is refused. Linux hosts with Firecracker + KVM now default to this backend; macOS stays on macos-container. Not yet validated end-to-end on live hardware (requires the one-time network pool). Unit tests + pyright pass. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01G8p32HJgPoS1hLPWubbftM
This commit is contained in:
@@ -0,0 +1,170 @@
|
||||
"""Bottle handle for a Firecracker microVM, over SSH.
|
||||
|
||||
Every operation routes through SSH to the guest (dropbear, listening on
|
||||
the TAP link). `exec` pipes a script over stdin and captures output;
|
||||
`cp_in` uses scp; `exec_agent` uses `ssh -t` for an interactive PTY
|
||||
session. `ssh -t` forwards the host terminal's SIGWINCH to the remote
|
||||
PTY natively, so — unlike the smolmachines backend — no resize bridge
|
||||
is needed.
|
||||
|
||||
Commands run as the image's `node` user via `runuser`, with HOME/USER/
|
||||
PATH and the bottle env (HTTPS_PROXY at the sidecar, CA paths, …) set
|
||||
per-invocation through `env` (the VM itself just runs the init; it has
|
||||
no baked-in process env like a `docker run` container would).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import shlex
|
||||
import subprocess
|
||||
import sys
|
||||
from pathlib import Path
|
||||
from typing import Mapping, cast
|
||||
|
||||
from ...agent_provider import PromptMode, prompt_args
|
||||
from .. import Bottle, ExecResult
|
||||
from ..terminal import exec_shell_script
|
||||
from . import util
|
||||
|
||||
|
||||
_HOME_FOR = {"node": "/home/node", "root": "/root"}
|
||||
_DEFAULT_PATH_FOR = {
|
||||
"node": (
|
||||
"/home/node/.local/bin:"
|
||||
"/home/node/.codex/packages/standalone/current/bin:"
|
||||
"/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin"
|
||||
),
|
||||
"root": "/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin",
|
||||
}
|
||||
|
||||
|
||||
def _env_assignments_for(user: str, env: Mapping[str, str]) -> list[str]:
|
||||
home = _HOME_FOR.get(user, f"/home/{user}")
|
||||
out = [f"HOME={home}", f"USER={user}"]
|
||||
if "PATH" not in env:
|
||||
out.append(f"PATH={_DEFAULT_PATH_FOR.get(user, _DEFAULT_PATH_FOR['root'])}")
|
||||
for k, v in env.items():
|
||||
out.append(f"{k}={v}")
|
||||
return out
|
||||
|
||||
|
||||
class FirecrackerBottle(Bottle):
|
||||
def __init__(
|
||||
self,
|
||||
name: str,
|
||||
*,
|
||||
private_key: Path,
|
||||
guest_ip: str,
|
||||
guest_env: Mapping[str, str] | None = None,
|
||||
prompt_path_in_guest: str | None = None,
|
||||
agent_command: str = "claude",
|
||||
agent_prompt_mode: PromptMode = "append_file",
|
||||
agent_provider_template: str = "claude",
|
||||
terminal_title: str = "",
|
||||
terminal_color: str = "",
|
||||
agent_workdir: str = "/home/node",
|
||||
) -> None:
|
||||
self.name = name
|
||||
self._private_key = private_key
|
||||
self._guest_ip = guest_ip
|
||||
self._guest_env = dict(guest_env or {})
|
||||
self.prompt_path = prompt_path_in_guest
|
||||
self._agent_prompt_mode = agent_prompt_mode
|
||||
self.agent_command = agent_command
|
||||
self.terminal_title = terminal_title
|
||||
self.terminal_color = terminal_color
|
||||
self.agent_provider_template = agent_provider_template
|
||||
self.agent_workdir = agent_workdir
|
||||
|
||||
def _ssh(self, *, tty: bool) -> list[str]:
|
||||
argv = util.ssh_base_argv(self._private_key, self._guest_ip)
|
||||
if tty:
|
||||
# -t: allocate a remote PTY and forward window-size changes.
|
||||
argv.insert(1, "-t")
|
||||
return argv
|
||||
|
||||
def _agent_remote_argv(self, argv: list[str]) -> list[str]:
|
||||
"""The `runuser … <agent> …` command run inside the guest."""
|
||||
full_argv = list(argv)
|
||||
full_argv.extend(
|
||||
prompt_args(
|
||||
cast(PromptMode, self._agent_prompt_mode),
|
||||
self.prompt_path,
|
||||
argv=full_argv,
|
||||
)
|
||||
)
|
||||
remote = ["runuser", "-u", "node", "--",
|
||||
"env", *_env_assignments_for("node", self._guest_env)]
|
||||
if self.agent_workdir and self.agent_workdir != _HOME_FOR["node"]:
|
||||
remote += ["sh", "-lc", f"cd {self.agent_workdir} && exec \"$@\"",
|
||||
"bot-bottle-agent"]
|
||||
remote += [self.agent_command, *full_argv]
|
||||
return remote
|
||||
|
||||
def agent_argv(self, argv: list[str], *, tty: bool = True) -> list[str]:
|
||||
return [*self._ssh(tty=tty), "--", *self._agent_remote_argv(argv)]
|
||||
|
||||
def exec_agent(self, argv: list[str], *, tty: bool = True) -> int:
|
||||
agent_argv = self.agent_argv(argv, tty=tty)
|
||||
script = (
|
||||
exec_shell_script(agent_argv, self.terminal_title, self.terminal_color)
|
||||
if tty else None
|
||||
)
|
||||
if script is None:
|
||||
return subprocess.run(agent_argv, check=False).returncode
|
||||
return subprocess.run(["sh", "-lc", script], check=False).returncode
|
||||
|
||||
def exec(self, script: str, *, user: str = "node") -> ExecResult:
|
||||
# Pipe the script over stdin (`sh -s`) so nothing needs shell
|
||||
# quoting through the SSH command line.
|
||||
remote = ["runuser", "-u", user, "--",
|
||||
"env", *_env_assignments_for(user, self._guest_env),
|
||||
"/bin/sh", "-s"]
|
||||
result = subprocess.run(
|
||||
[*self._ssh(tty=False), "--", *remote],
|
||||
input=script, capture_output=True, text=True, check=False,
|
||||
)
|
||||
return ExecResult(
|
||||
returncode=result.returncode,
|
||||
stdout=result.stdout,
|
||||
stderr=result.stderr,
|
||||
)
|
||||
|
||||
def cp_in(self, host_path: str, container_path: str) -> None:
|
||||
# Stream a tar over the SSH exec channel rather than scp: the
|
||||
# guest runs dropbear, which ships no sftp-server/scp, but every
|
||||
# agent image has `tar`. Copy so `container_path` becomes a copy
|
||||
# of `host_path` (docker cp semantics — callers rm -rf the
|
||||
# destination first).
|
||||
host_parent = os.path.dirname(host_path.rstrip("/")) or "/"
|
||||
host_base = os.path.basename(host_path.rstrip("/"))
|
||||
guest_parent = os.path.dirname(container_path.rstrip("/")) or "/"
|
||||
guest_base = os.path.basename(container_path.rstrip("/"))
|
||||
remote = (
|
||||
f"mkdir -p {shlex.quote(guest_parent)} && "
|
||||
f"cd {shlex.quote(guest_parent)} && "
|
||||
f"rm -rf {shlex.quote(guest_base)} && tar -xf - && "
|
||||
f"{{ [ {shlex.quote(host_base)} = {shlex.quote(guest_base)} ] || "
|
||||
f"mv {shlex.quote(host_base)} {shlex.quote(guest_base)}; }}"
|
||||
)
|
||||
tar = subprocess.Popen(
|
||||
["tar", "-C", host_parent, "-cf", "-", host_base],
|
||||
stdout=subprocess.PIPE,
|
||||
)
|
||||
ssh = subprocess.run(
|
||||
[*self._ssh(tty=False), "--", "sh", "-c", remote],
|
||||
stdin=tar.stdout, capture_output=True, text=True, check=False,
|
||||
)
|
||||
tar.wait()
|
||||
if tar.returncode != 0 or ssh.returncode != 0:
|
||||
sys.stderr.write(ssh.stderr)
|
||||
raise subprocess.CalledProcessError(
|
||||
ssh.returncode or tar.returncode,
|
||||
["cp_in", host_path, container_path],
|
||||
)
|
||||
|
||||
def close(self) -> None:
|
||||
# Real teardown (VM terminate, TAP release) lives on the launch
|
||||
# ExitStack; this is the idempotent alias the ABC expects.
|
||||
pass
|
||||
Reference in New Issue
Block a user