feat(firecracker): Linux microVM backend to replace smolmachines #343

Open
didericis-claude wants to merge 13 commits from firecracker-backend into main
7 changed files with 324 additions and 17 deletions
Showing only changes of commit ce3fad9320 - Show all commits
+2 -2
View File
@@ -82,13 +82,13 @@ On Linux, a KVM-capable host defaults to the Firecracker backend. It needs:
- **`/dev/kvm`** present and accessible. Load `kvm-intel` or `kvm-amd` (and enable virtualization in BIOS/firmware). The invoking user must be in the `kvm` group: `sudo usermod -aG kvm "$USER"` then re-login. bot-bottle preflights this and reports exactly what's missing.
- **`firecracker`** on `PATH`: grab a release from <https://github.com/firecracker-microvm/firecracker/releases>. Start flows print this pointer when the binary is missing.
- **Docker** for the sidecar bundle and image build.
- **A one-time privileged network setup** — the per-bottle TAP pool plus the fail-closed `nftables` isolation table. Run `./cli.py firecracker setup` for the host-appropriate command (a declarative module on NixOS, a `sudo` script elsewhere); `./cli.py firecracker status` reports what's present.
- **A one-time privileged network setup** — the per-bottle TAP pool plus the fail-closed `nftables` isolation table. Run `./cli.py backend setup --backend=firecracker` for the host-appropriate config (a NixOS module, a `sudo` script elsewhere); `./cli.py backend status --backend=firecracker` reports what's present, including whether the pool range collides with an existing route. The pool defaults to `10.243.0.0/16` (an obscure RFC-1918 block that dodges docker/libvirt/LAN and, deliberately, Tailscale's `100.64.0.0/10` CGNAT range); override with `BOT_BOTTLE_FC_IP_BASE` if it clashes on your host.
```sh
BOT_BOTTLE_BACKEND=firecracker ./cli.py start <agent>
```
> **NixOS:** enable `virtualisation.docker`, ensure the KVM module is loaded (`boot.kernelModules = [ "kvm-intel" ];` or `kvm-amd`), and add your user to the `kvm` and `docker` groups. Apply the network-pool module from `./cli.py firecracker setup` and `nixos-rebuild switch` (imperative nft/TAP rules don't survive a rebuild). `firecracker` isn't in nixpkgs by default as a user binary — install the release binary (pin the version) and put it on `PATH`.
> **NixOS:** enable `virtualisation.docker`, ensure the KVM module is loaded (`boot.kernelModules = [ "kvm-intel" ];` or `kvm-amd`), and add your user to the `kvm` and `docker` groups. For the network pool, consume the flake module — `imports = [ inputs.bot-bottle.nixosModules.firecracker-netpool ]; services.bot-bottle-firecracker = { enable = true; owner = "you"; };` — then `nixos-rebuild switch` (imperative nft/TAP rules don't survive a rebuild; channel users can `imports = [ <bot-bottle>/nix/firecracker-netpool.nix ]`). `firecracker` isn't in nixpkgs by default as a user binary — install the release binary (pin the version) and put it on `PATH`.
```sh
./cli.py start <agent> # builds the image on first run, drops you into claude
+81 -6
View File
@@ -17,8 +17,16 @@ Topology (per slot i):
* isolation via ``table inet bot_bottle_fc``: a VM reaches only its
own sidecar (DNAT'd from the host TAP IP) and nothing else.
The default IP block is RFC-6598 shared address space (100.64.0.0/10),
which is purpose-built to avoid colliding with LAN/VPN private ranges.
The default IP block is ``10.243.0.0/16`` — an intentionally obscure
corner of RFC-1918 private space. RFC-1918 is the range *designated*
for private links; we pick a high, unusual /16 to steer clear of the
common occupants (Docker's 172.17-31, libvirt's 192.168.122, k8s
10.42/10.244, and typical home LANs on 192.168.0/1.x or 10.0.0.x).
We deliberately avoid ``100.64.0.0/10`` (RFC-6598 CGNAT) because
Tailscale hands out node addresses from exactly that range. No default
is collision-proof, so `overlapping_routes()` is the real guard —
`backend setup`/`status` and the launch preflight call it to catch
a base that clashes with something already on the host.
"""
from __future__ import annotations
@@ -45,7 +53,7 @@ def pool_size() -> int:
def ip_base() -> str:
return os.environ.get("BOT_BOTTLE_FC_IP_BASE", "100.64.0.0")
return os.environ.get("BOT_BOTTLE_FC_IP_BASE", "10.243.0.0")
# Sidecar ports the VM reaches at its host-side TAP IP. Kept in sync
@@ -119,6 +127,73 @@ def missing_taps() -> list[str]:
return [s.iface for s in all_slots() if not tap_present(s.iface)]
@dataclass(frozen=True)
class RouteConflict:
"""An existing host route whose destination overlaps the pool range
but isn't one of our own bbfc TAPs — i.e. the chosen IP base clashes
with something already on the host (a Tailscale CGNAT peer, a
docker/libvirt bridge, the LAN…)."""
dst: str
dev: str
def _pool_span() -> tuple[int, int]:
"""Inclusive [first, last] integer bounds of every address the pool
occupies: base .. base + 2*pool_size - 1."""
base = int(ipaddress.IPv4Address(ip_base()))
return base, base + 2 * pool_size() - 1
def overlapping_routes() -> list[RouteConflict]:
"""Existing routes whose destination overlaps the pool's address
range, excluding our own `bbfc*` TAP routes and the default route.
A non-empty result means `BOT_BOTTLE_FC_IP_BASE` collides with
something already configured on this host, so the pool would shadow
(or be shadowed by) it. Empty on success — or when `ip` is missing
or unparseable, since this is an advisory guard, not the fail-closed
isolation check (that's the nft table + post-boot probe)."""
import json
try:
proc = subprocess.run(
["ip", "-json", "route", "show", "table", "all"],
capture_output=True, text=True, check=False,
)
except FileNotFoundError:
return []
if proc.returncode != 0 or not proc.stdout.strip():
return []
try:
routes = json.loads(proc.stdout)
except json.JSONDecodeError:
return []
lo, hi = _pool_span()
conflicts: list[RouteConflict] = []
for r in routes:
if not isinstance(r, dict):
continue
dst = r.get("dst")
dev = r.get("dev", "")
if not isinstance(dst, str) or dst in ("", "default"):
continue
if isinstance(dev, str) and dev.startswith(IFACE_PREFIX):
continue # our own pool link
try:
net = ipaddress.ip_network(dst, strict=False)
except ValueError:
continue
if net.version != 4:
continue
r_lo = int(net.network_address)
r_hi = int(net.broadcast_address)
if r_lo <= hi and lo <= r_hi: # ranges intersect
conflicts.append(RouteConflict(dst=dst, dev=str(dev)))
return conflicts
# --- allocation ------------------------------------------------------
def _lock_dir() -> Path:
@@ -149,11 +224,11 @@ def allocate(slug: str) -> tuple[Slot, IO[str]]:
return s, handle
die(f"Firecracker TAP pool exhausted ({pool_size()} slots, all in "
f"use). Stop a running bottle or raise BOT_BOTTLE_FC_POOL_SIZE "
f"and re-run `./cli.py firecracker setup`.")
f"and re-run `./cli.py backend setup --backend=firecracker`.")
raise AssertionError("unreachable")
# --- config renderers (shown by `./cli.py firecracker setup`) --------
# --- config renderers (shown by `./cli.py backend setup`) -----------
def render_shell_setup() -> str:
"""The imperative command for non-NixOS hosts."""
@@ -190,7 +265,7 @@ def render_nixos_module() -> str:
)
return f"""# bot-bottle Firecracker network pool ({len(slots)} slots, base {ip_base()}).
# Generated by `./cli.py firecracker setup`; owner user = {owner!r}.
# Generated by `./cli.py backend setup --backend=firecracker`; owner user = {owner!r}.
{{ ... }}:
{{
boot.kernel.sysctl."net.ipv4.ip_forward" = 1;
+11 -3
View File
@@ -9,7 +9,7 @@ generation.
The privileged network setup (TAP pool + nft table) is a one-time
operator step — see `netpool.py`, `scripts/firecracker-netpool.sh`,
and `./cli.py firecracker setup`.
and `./cli.py backend setup --backend=firecracker`.
"""
from __future__ import annotations
@@ -124,17 +124,25 @@ def _require_network_pool() -> None:
empirical isolation probe run after boot, before the agent starts
(see isolation_probe.verify_isolation). What we must never do is
boot without the TAP pool."""
conflicts = netpool.overlapping_routes()
if conflicts:
detail = "; ".join(f"{c.dst} dev {c.dev}" for c in conflicts)
warn(f"Firecracker pool range ({netpool.ip_base()}, "
f"{netpool.pool_size()} slots) overlaps existing routes: "
f"{detail}. This can shadow or be shadowed by that route; "
f"set BOT_BOTTLE_FC_IP_BASE to a free range and re-run "
f"./cli.py backend setup --backend=firecracker.")
missing = netpool.missing_taps()
if missing:
die(f"network pool incomplete — missing TAP devices: "
f"{', '.join(missing)}.\n ./cli.py firecracker setup")
f"{', '.join(missing)}.\n ./cli.py backend setup --backend=firecracker")
if shutil.which("nft") is not None and not netpool.nft_table_present():
# nft is queryable and says the table is absent — that's a
# definite, catchable misconfiguration; fail early.
warn(f"isolation table `inet {netpool.NFT_TABLE}` not found via nft. "
"If this is a permissions issue it will be re-checked "
"empirically after boot; otherwise run: "
"./cli.py firecracker setup")
"./cli.py backend setup --backend=firecracker")
# --- rootfs pipeline (rootless) -------------------------------------
+18
View File
@@ -0,0 +1,18 @@
{
description = "bot-bottle sandboxed runtime for AI coding agents";
outputs = { self, ... }: {
# Declarative host setup for the Firecracker backend's network pool.
# Consume from a flake-based NixOS config:
#
# inputs.bot-bottle.url = "git+ssh://<your-bot-bottle-remote>"; # or path:/…
# # then, in your host module:
# imports = [ inputs.bot-bottle.nixosModules.firecracker-netpool ];
# services.bot-bottle-firecracker = { enable = true; owner = "you"; };
#
# The module is plain (no nixpkgs pin), so channel users can import
# ./nix/firecracker-netpool.nix directly without the flake.
nixosModules.firecracker-netpool = import ./nix/firecracker-netpool.nix;
nixosModules.default = self.nixosModules.firecracker-netpool;
};
}
+152
View File
@@ -0,0 +1,152 @@
# bot-bottle Firecracker network pool — declarative NixOS module.
#
# The one-time privileged setup the Firecracker backend needs: a pool of
# user-owned point-to-point TAP devices plus a fail-closed nftables table
# that confines every microVM to its own sidecar. Enabling this module is
# the NixOS equivalent of `sudo ./scripts/firecracker-netpool.sh up` — but
# declarative, so the taps/table survive `nixos-rebuild` and are only
# reconfigured when this config changes (running VMs aren't dropped).
#
# The option defaults MUST match the backend constants in
# bot_bottle/backend/firecracker/netpool.py (pool size, IP base, iface
# prefix, table name). The backend reads the same values at launch from
# the BOT_BOTTLE_FC_* env vars; if you override an option here, override
# the matching env var for the CLI too (or set writeEnvFile = true below
# to have this module emit them). Keep the two sides in lockstep.
{ config, lib, ... }:
let
cfg = config.services.bot-bottle-firecracker;
# --- IPv4 <-> int (full 32-bit carry math) -------------------------
toOctets = s: map lib.toInt (lib.splitString "." s);
ipToInt = s:
let o = toOctets s; in
(lib.elemAt o 0) * 16777216
+ (lib.elemAt o 1) * 65536
+ (lib.elemAt o 2) * 256
+ (lib.elemAt o 3);
intToIp = n:
let
b0 = n / 16777216; r0 = n - b0 * 16777216;
b1 = r0 / 65536; r1 = r0 - b1 * 65536;
b2 = r1 / 256;
b3 = r1 - b2 * 256;
in "${toString b0}.${toString b1}.${toString b2}.${toString b3}";
baseInt = ipToInt cfg.ipBase;
# Slot i: host = base + 2i (the VM's gateway), on its own /31.
slots = lib.genList (i: {
iface = "${cfg.ifacePrefix}${toString i}";
hostIp = intToIp (baseInt + 2 * i);
}) cfg.poolSize;
mkAttr = f: lib.listToAttrs (map (s: lib.nameValuePair "10-${s.iface}" (f s)) slots);
in
{
options.services.bot-bottle-firecracker = {
enable = lib.mkEnableOption "the bot-bottle Firecracker network pool (TAP devices + isolation nftables table)";
poolSize = lib.mkOption {
type = lib.types.ints.positive;
default = 8;
description = "Number of pool slots (concurrent bottles). Must match BOT_BOTTLE_FC_POOL_SIZE.";
};
ipBase = lib.mkOption {
type = lib.types.str;
default = "10.243.0.0";
description = ''
Base IPv4 of the /31 pool; slot i uses host = base + 2i. Must
be /31-aligned (even final address) and must match
BOT_BOTTLE_FC_IP_BASE. Default is an obscure RFC-1918 /16 that
dodges docker/libvirt/k8s/LAN and, deliberately, Tailscale's
100.64.0.0/10 CGNAT range.
'';
};
ifacePrefix = lib.mkOption {
type = lib.types.str;
default = "bbfc";
description = "TAP interface name prefix. Must match BOT_BOTTLE_FC_IFACE_PREFIX.";
};
owner = lib.mkOption {
type = lib.types.str;
example = "alice";
description = "User that owns the TAP devices, so `./cli.py start` opens them without root.";
};
tableName = lib.mkOption {
type = lib.types.str;
default = "bot_bottle_fc";
description = "nftables table name for the isolation boundary. Must match netpool.NFT_TABLE.";
};
writeEnvFile = lib.mkOption {
type = lib.types.bool;
default = false;
description = ''
When true, write /etc/bot-bottle/firecracker.env with the
matching BOT_BOTTLE_FC_* values, so the host pool and the CLI
launcher can't drift. Source it before running `./cli.py`.
'';
};
};
config = lib.mkIf cfg.enable {
assertions = [
{
assertion = lib.mod baseInt 2 == 0;
message = "services.bot-bottle-firecracker.ipBase must be /31-aligned (even final octet); got ${cfg.ipBase}.";
}
];
# VM->sidecar traffic is DNAT'd and forwarded, so forwarding must be on.
boot.kernel.sysctl."net.ipv4.ip_forward" = 1;
systemd.network.enable = true;
systemd.network.netdevs = mkAttr (s: {
netdevConfig = { Name = s.iface; Kind = "tap"; };
tapConfig = { User = cfg.owner; };
});
systemd.network.networks = mkAttr (s: {
matchConfig.Name = s.iface;
address = [ "${s.hostIp}/31" ];
networkConfig.ConfigureWithoutCarrier = true;
});
# Independent, fail-closed table — coexists with Docker/ufw/firewalld
# rather than replacing the ruleset. A VM (traffic from a
# ${cfg.ifacePrefix}* TAP) may reach only its own sidecar (DNAT'd from
# the host TAP IP); everything else is dropped.
networking.nftables.enable = true;
networking.nftables.tables.${cfg.tableName} = {
family = "inet";
content = ''
chain forward {
type filter hook forward priority -10; policy accept;
iifname != "${cfg.ifacePrefix}*" return
ct state established,related accept
ct status dnat accept
drop
}
chain input {
type filter hook input priority -10; policy accept;
iifname != "${cfg.ifacePrefix}*" return
ct state established,related accept
drop
}
'';
};
environment.etc."bot-bottle/firecracker.env" = lib.mkIf cfg.writeEnvFile {
text = ''
BOT_BOTTLE_FC_POOL_SIZE=${toString cfg.poolSize}
BOT_BOTTLE_FC_IP_BASE=${cfg.ipBase}
BOT_BOTTLE_FC_IFACE_PREFIX=${cfg.ifacePrefix}
'';
};
};
}
+8 -5
View File
@@ -19,11 +19,14 @@
# virbr0 (libvirt), cni0 (k8s) or br-* (docker networks).
# * Own nftables table `bot_bottle_fc` — independent of the iptables
# filter/nat tables Docker/ufw/firewalld use, so nothing is stomped.
# * Default IP block is RFC-6598 shared address space (100.64.0.0/10),
# purpose-built to not collide with LAN/VPN private ranges.
# * Default IP block is an obscure RFC-1918 /16 (10.243.0.0/16),
# chosen to dodge the usual occupants (docker 172.17-31, libvirt
# 192.168.122, k8s 10.42/10.244, home LANs). NOT 100.64.0.0/10 —
# that's RFC-6598 CGNAT, which Tailscale hands node addresses from.
#
# NixOS: imperative rules here do NOT survive nixos-rebuild. Use the
# declarative module in docs/firecracker/nixos-netpool.nix instead.
# declarative module in nix/firecracker-netpool.nix instead (exposed as
# the flake output nixosModules.firecracker-netpool).
#
# Usage:
# sudo ./scripts/firecracker-netpool.sh up
@@ -32,14 +35,14 @@
#
# Env overrides (must match the backend's util.py constants):
# BOT_BOTTLE_FC_POOL_SIZE number of slots (default 8)
# BOT_BOTTLE_FC_IP_BASE base IPv4 of the /31 pool (default 100.64.0.0)
# BOT_BOTTLE_FC_IP_BASE base IPv4 of the /31 pool (default 10.243.0.0)
# BOT_BOTTLE_FC_IFACE_PREFIX TAP name prefix (default bbfc)
# BOT_BOTTLE_FC_OWNER owning user (default $SUDO_USER or $USER)
set -euo pipefail
POOL_SIZE="${BOT_BOTTLE_FC_POOL_SIZE:-8}"
IP_BASE="${BOT_BOTTLE_FC_IP_BASE:-100.64.0.0}"
IP_BASE="${BOT_BOTTLE_FC_IP_BASE:-10.243.0.0}"
PREFIX="${BOT_BOTTLE_FC_IFACE_PREFIX:-bbfc}"
OWNER="${BOT_BOTTLE_FC_OWNER:-${SUDO_USER:-$USER}}"
TABLE="bot_bottle_fc"
+52 -1
View File
@@ -38,7 +38,15 @@ class TestNetpoolSlots(unittest.TestCase):
(s1.iface, s1.host_ip, s1.guest_ip))
def test_guest_cidr_is_31(self):
self.assertEqual("100.64.0.1/31", netpool.slot(0).guest_cidr)
with patch.dict(os.environ, {"BOT_BOTTLE_FC_IP_BASE": "100.64.0.0"}):
self.assertEqual("100.64.0.1/31", netpool.slot(0).guest_cidr)
def test_default_base_avoids_cgnat_and_common_private_ranges(self):
# The default base must NOT sit in 100.64.0.0/10 (RFC-6598 CGNAT,
# which Tailscale hands node addresses from); it's an obscure
# RFC-1918 block instead.
with patch.dict(os.environ, {}, clear=True):
self.assertEqual("10.243.0.0", netpool.ip_base())
def test_pool_size_env_override(self):
with patch.dict(os.environ, {"BOT_BOTTLE_FC_POOL_SIZE": "4"}):
@@ -65,6 +73,49 @@ class TestNetpoolRenderers(unittest.TestCase):
self.assertIn("firecracker-netpool.sh up", out)
class TestNetpoolOverlap(unittest.TestCase):
"""`overlapping_routes()` flags a pool base that collides with an
existing host route (Tailscale CGNAT peer, docker/libvirt bridge,
LAN) and ignores our own bbfc TAPs + the default route."""
def _routes(self, entries: list[dict]) -> object:
import json
import subprocess
def fake_run(argv, **kwargs):
return subprocess.CompletedProcess(
argv, 0, stdout=json.dumps(entries), stderr="",
)
return patch.object(netpool.subprocess, "run", side_effect=fake_run)
def test_flags_route_overlapping_pool(self):
# base 100.64.0.0 + a Tailscale peer /32 inside the pool window.
with patch.dict(os.environ, {"BOT_BOTTLE_FC_IP_BASE": "100.64.0.0",
"BOT_BOTTLE_FC_POOL_SIZE": "8"}), \
self._routes([
{"dst": "default", "dev": "enp4s0"},
{"dst": "100.64.0.5", "dev": "tailscale0"},
]):
conflicts = netpool.overlapping_routes()
self.assertEqual(1, len(conflicts))
self.assertEqual("tailscale0", conflicts[0].dev)
def test_ignores_own_taps_and_default(self):
with patch.dict(os.environ, {"BOT_BOTTLE_FC_IP_BASE": "10.243.0.0",
"BOT_BOTTLE_FC_POOL_SIZE": "8"}), \
self._routes([
{"dst": "default", "dev": "enp4s0"},
{"dst": "10.243.0.0/31", "dev": "bbfc0"},
{"dst": "192.168.1.0/24", "dev": "enp4s0"},
]):
self.assertEqual([], netpool.overlapping_routes())
def test_empty_when_ip_missing(self):
with self._routes([]) as run:
run.side_effect = FileNotFoundError()
self.assertEqual([], netpool.overlapping_routes())
class TestNetpoolAllocation(unittest.TestCase):
def test_allocate_is_mutually_exclusive(self):
with patch.dict(os.environ, {"BOT_BOTTLE_FC_POOL_SIZE": "1"}):