feat: run smolmachines sidecar as vm

This commit is contained in:
2026-07-09 16:10:42 +00:00
committed by didericis
parent 46a77aec31
commit ce8e2b3874
12 changed files with 739 additions and 113 deletions
@@ -1,20 +1,51 @@
"""Egress apply for the smolmachines backend.
The smolmachines sidecar bundle runs as a host-side Docker container,
so egress signalling is identical to the docker backend.
The smolmachines sidecar bundle runs as a sidecar smolVM. Route-file
inspection and reload signalling therefore go through ``smolvm machine
exec`` instead of Docker.
"""
from __future__ import annotations
from ..docker.egress_apply import ( # noqa: F401
DockerEgressApplicator,
EgressApplyError,
applicator,
fetch_current_routes,
)
from ...egress import EGRESS_ROUTES_IN_CONTAINER
from ...log import warn
from ..egress_apply import EgressApplicator, EgressApplyError
from . import sidecar_bundle as _bundle
from . import smolvm as _smolvm
def fetch_current_routes(slug: str) -> str:
machine = _bundle.bundle_machine_name(slug)
result = _smolvm.machine_exec(machine, ["cat", EGRESS_ROUTES_IN_CONTAINER])
if result.returncode != 0:
raise EgressApplyError(
f"could not read routes.yaml from {machine}: "
f"{(result.stderr or '').strip() or 'sidecar VM not running?'}"
)
return result.stdout
class SmolmachinesEgressApplicator(EgressApplicator):
def _signal_bundle_reload(self, slug: str) -> None:
machine = _bundle.bundle_machine_name(slug)
result = _smolvm.machine_exec(machine, ["sh", "-c", "kill -HUP 1"])
if result.returncode != 0:
last_error = (result.stderr or "").strip() or (result.stdout or "").strip()
warn(
f"egress: routes updated on disk for {slug}, but bundle reload failed: "
f"{last_error or 'smolvm exec failed'}"
)
raise EgressApplyError(
f"could not reload egress bundle {machine}: "
f"{last_error or 'smolvm exec failed'}"
)
applicator = SmolmachinesEgressApplicator()
__all__ = [
"DockerEgressApplicator",
"SmolmachinesEgressApplicator",
"EgressApplyError",
"applicator",
"fetch_current_routes",
+6 -1
View File
@@ -31,6 +31,7 @@ from . import sidecar_bundle as _bundle
# matching the bundle container name pattern. We use the prefix
# both as a filter and to strip back to the slug.
_VM_NAME_PREFIX = "bot-bottle-"
_SIDECAR_VM_PREFIX = _bundle.bundle_machine_name("")
def enumerate_active() -> list[ActiveAgent]:
@@ -54,7 +55,11 @@ def enumerate_active() -> list[ActiveAgent]:
for m in machines:
name = m.get("name") or ""
state = m.get("state") or ""
if state != "running" or not name.startswith(_VM_NAME_PREFIX):
if (
state != "running"
or not name.startswith(_VM_NAME_PREFIX)
or name.startswith(_SIDECAR_VM_PREFIX)
):
continue
slug = name[len(_VM_NAME_PREFIX):]
metadata = read_metadata(slug)
+71 -50
View File
@@ -17,7 +17,6 @@ from __future__ import annotations
import dataclasses
import os
import platform
from contextlib import ExitStack, contextmanager
from pathlib import Path
from typing import Callable, Generator
@@ -53,6 +52,7 @@ from ...bottle_state import (
read_committed_image,
)
from . import loopback_alias as _loopback
from . import port_forward as _forward
from . import sidecar_bundle as _bundle
from . import smolvm as _smolvm
from .bottle import SmolmachinesBottle
@@ -94,7 +94,6 @@ def launch(
plan = _mint_certs(plan)
proxy_host = _proxy_host(plan, loopback_ip)
plan = _start_bundle(plan, network, proxy_host, stack)
plan = _discover_urls(plan, proxy_host)
agent_from_path = _agent_from_path(plan)
@@ -144,19 +143,17 @@ def _allocate_resources(
plan: SmolmachinesBottlePlan,
stack: ExitStack,
) -> tuple[str, str]:
"""Reserve a loopback alias and create the per-bottle docker bridge.
"""Reserve a per-bottle host address.
The per-bottle alias scopes TSI's allowlist to this bottle's
published ports so the agent can't reach other bottles' or host
services' ports on loopback. On macOS `ensure_pool` first
sudo-aliases the pool on `lo0`; on Linux that's a no-op since
all of 127.0.0.0/8 is already loopback, but the per-bottle
allocation runs on both."""
The per-bottle address scopes TSI's allowlist to this bottle's
forwarder-published ports so the agent can't reach other bottles'
or host services. The returned network name remains in the bundle
spec for compatibility with older helper tests; no Docker sidecar
container is launched."""
del stack
_loopback.ensure_pool()
loopback_ip = _loopback.allocate(plan.slug)
network = _bundle.bundle_network_name(plan.slug)
_bundle.create_bundle_network(network, plan.bundle_subnet, plan.bundle_gateway)
stack.callback(_bundle.remove_bundle_network, network)
return loopback_ip, network
@@ -179,15 +176,40 @@ def _start_bundle(
proxy_host: str,
stack: ExitStack,
) -> SmolmachinesBottlePlan:
"""Build the BundleLaunchSpec, resolve token env, start the
sidecar bundle container, and register teardown."""
"""Build the BundleLaunchSpec, start the sidecar VM, wrap its raw
smolVM-published loopback ports with per-bottle forwarders, stamp
agent URLs from those forwarder ports, and register teardown."""
plan = _provision_git_gate_keys(plan)
bundle_spec = _bundle_launch_spec(plan, network, proxy_host)
token_env = _resolve_token_env(plan, dict(os.environ))
_bundle.ensure_bundle_image(bundle_spec.image)
_bundle.start_bundle(bundle_spec, env={**os.environ, **token_env})
stack.callback(_bundle.stop_bundle, plan.slug)
return plan
artifact = _ensure_smolmachine(
bundle_spec.image,
dockerfile=_bundle.SIDECAR_BUNDLE_DOCKERFILE,
)
launch = _bundle.start_bundle_vm(
bundle_spec,
from_path=artifact,
host_env={**os.environ, **token_env},
)
stack.callback(_bundle.stop_bundle_vm, plan.slug)
forward_specs = tuple(
_forward.ForwardSpec(
label=_label_for_port(container_port),
listen_host=proxy_host,
listen_port=0,
target_host="127.0.0.1",
target_port=host_port,
)
for container_port, host_port in launch.raw_ports.items()
)
handle = _forward.start_forwarder(forward_specs)
stack.callback(_forward.stop_forwarder, handle)
published_ports = {
_port_for_label(spec.label): spec.listen_port
for spec in handle.forwards
}
return _discover_urls(plan, proxy_host, published_ports)
def _provision_git_gate_keys(
@@ -206,35 +228,27 @@ def _provision_git_gate_keys(
def _discover_urls(
plan: SmolmachinesBottlePlan,
proxy_host: str,
published_ports: dict[int, int],
) -> SmolmachinesBottlePlan:
"""Discover host-side ports for published container ports and
return the plan with URLs + guest_env stamped in.
"""Stamp URLs + guest_env from per-bottle forwarder ports.
`proxy_host` is the host IP that both TSI's allowlist and
docker's port-forward bindings are keyed to. On macOS it is the
per-bottle loopback alias; on Linux it is the per-bottle bridge
gateway (see `_proxy_host`). The agent dials the published port
on this IP for all bundle-hosted services.
`proxy_host` is the host IP that both TSI's allowlist and the
forwarder listeners are keyed to. The raw smolVM-published ports
are intentionally not advertised to the agent.
NO_PROXY includes `proxy_host` so supervise + git-gate URLs
bypass HTTPS_PROXY."""
agent_facing_host_port = _bundle.bundle_host_port(
plan.slug, _EGRESS_PORT, host_ip=proxy_host,
)
agent_facing_host_port = published_ports[_EGRESS_PORT]
agent_proxy_url = f"http://{proxy_host}:{agent_facing_host_port}"
agent_git_gate_host = ""
if plan.git_gate_plan.upstreams:
git_gate_host_port = _bundle.bundle_host_port(
plan.slug, _GIT_HTTP_PORT, host_ip=proxy_host,
)
git_gate_host_port = published_ports[_GIT_HTTP_PORT]
agent_git_gate_host = f"{proxy_host}:{git_gate_host_port}"
agent_supervise_url = ""
if plan.supervise_plan is not None:
supervise_host_port = _bundle.bundle_host_port(
plan.slug, _SUPERVISE_PORT, host_ip=proxy_host,
)
supervise_host_port = published_ports[_SUPERVISE_PORT]
agent_supervise_url = f"http://{proxy_host}:{supervise_host_port}/"
existing_no_proxy = plan.guest_env.get("NO_PROXY", "localhost,127.0.0.1")
@@ -328,26 +342,33 @@ def _init_vm(plan: SmolmachinesBottlePlan) -> None:
def _proxy_host(plan: SmolmachinesBottlePlan, loopback_ip: str) -> str:
"""Return the host IP for TSI's allowlist and docker port-forward bindings.
On macOS, the per-bottle loopback alias (e.g. ``127.0.0.16``) works
because macOS's network stack lets TSI intercept 127.x.x.x connects
from the guest before they reach the host's own loopback.
On Linux, the guest kernel's LOCAL routing table routes all
``127.0.0.0/8`` to the guest's own loopback — those packets never
reach eth0 and TSI never sees them. Using the per-bottle bridge
gateway (e.g. ``192.168.N.1``) instead sidesteps the problem: it
is not a loopback address, so the guest routes it via eth0 and TSI
intercepts it normally. The TSI allowlist is ``gateway/32``, which
is distinct from the container IP (``192.168.N.2``), so the agent
still can't reach the egress daemon directly — TSI blocks any
connection to the container IP that isn't via the published port."""
if platform.system() == "Linux":
return plan.bundle_gateway
"""Return the per-bottle host address used for TSI and forwarders."""
del plan
return loopback_ip
def _label_for_port(port: int) -> str:
if port == _EGRESS_PORT:
return "egress"
if port == _GIT_HTTP_PORT:
return "git-http"
if port == _SUPERVISE_PORT:
return "supervise"
return f"port-{port}"
def _port_for_label(label: str) -> int:
if label == "egress":
return _EGRESS_PORT
if label == "git-http":
return _GIT_HTTP_PORT
if label == "supervise":
return _SUPERVISE_PORT
if label.startswith("port-"):
return int(label.removeprefix("port-"))
raise ValueError(f"unknown sidecar forward label: {label}")
def _bundle_launch_spec(
plan: SmolmachinesBottlePlan, network: str, proxy_host: str,
) -> _bundle.BundleLaunchSpec:
@@ -0,0 +1,245 @@
"""Per-bottle TCP forwarder for smolmachines sidecar VMs.
smolVM currently publishes guest ports on host loopback as
``HOST:GUEST`` port pairs, without an address-scoped bind. The agent
VM's TSI allowlist is IP-only, so bot-bottle exposes a second, stricter
surface: listeners bound only to the bottle's allocated host address,
forwarding to the raw smolVM-published loopback ports.
"""
from __future__ import annotations
import argparse
import json
import os
import selectors
import signal
import socket
import subprocess
import sys
import threading
from dataclasses import asdict, dataclass
from typing import Any, Iterable, Sequence
from ...log import die, warn
_BUFFER_SIZE = 64 * 1024
_LOOPBACK_TARGETS = {"127.0.0.1", "::1"}
_FORBIDDEN_LISTEN_HOSTS = {"", "0.0.0.0", "::", "127.0.0.1", "::1"}
@dataclass(frozen=True)
class ForwardSpec:
label: str
listen_host: str
listen_port: int
target_host: str
target_port: int
@dataclass(frozen=True)
class ForwarderHandle:
process: Any
forwards: tuple[ForwardSpec, ...]
def start_forwarder(specs: Sequence[ForwardSpec]) -> ForwarderHandle:
"""Start one helper process for a bottle and wait until all
listeners are bound. ``listen_port`` may be 0; the returned specs
contain the kernel-assigned ports printed by the helper."""
if not specs:
return ForwarderHandle(process=_CompletedProcess(), forwards=())
_validate_specs(specs)
argv = [
sys.executable,
"-c",
"from bot_bottle.backend.smolmachines.port_forward import main; "
"raise SystemExit(main())",
"--spec-json",
json.dumps([asdict(s) for s in specs], separators=(",", ":")),
]
proc = subprocess.Popen(
argv,
stdin=subprocess.DEVNULL,
stdout=subprocess.PIPE,
stderr=None,
text=True,
env=os.environ,
)
assert proc.stdout is not None
line = proc.stdout.readline()
proc.stdout.close()
if not line:
proc.terminate()
proc.wait(timeout=5)
die("smolmachines forwarder failed before reporting readiness")
try:
payload = json.loads(line)
bound = tuple(ForwardSpec(**item) for item in payload["forwards"])
except (KeyError, TypeError, ValueError, json.JSONDecodeError) as exc:
proc.terminate()
proc.wait(timeout=5)
die(f"smolmachines forwarder returned invalid readiness payload: {exc}")
return ForwarderHandle(process=proc, forwards=bound)
def stop_forwarder(handle: ForwarderHandle) -> None:
proc = handle.process
if proc.poll() is not None:
return
proc.terminate()
try:
proc.wait(timeout=5)
except subprocess.TimeoutExpired:
proc.kill()
proc.wait(timeout=5)
def _validate_specs(specs: Iterable[ForwardSpec]) -> None:
for spec in specs:
if spec.listen_host in _FORBIDDEN_LISTEN_HOSTS:
die(f"refusing unsafe smolmachines forwarder bind: {spec.listen_host!r}")
if spec.target_host not in _LOOPBACK_TARGETS:
die(f"refusing non-loopback smolmachines forwarder target: {spec.target_host!r}")
if not 0 <= spec.listen_port <= 65535:
die(f"invalid smolmachines forwarder listen port: {spec.listen_port}")
if not 1 <= spec.target_port <= 65535:
die(f"invalid smolmachines forwarder target port: {spec.target_port}")
class _CompletedProcess:
"""Popen-like no-op used when a bottle has no forwards."""
def poll(self) -> int:
return 0
def terminate(self) -> None:
return None
def kill(self) -> None:
return None
def wait(self, timeout: float | None = None) -> int:
del timeout
return 0
class _Forwarder:
def __init__(self, specs: Sequence[ForwardSpec]):
_validate_specs(specs)
self.specs = tuple(specs)
self.selector = selectors.DefaultSelector()
self.stop_event = threading.Event()
self.listeners: list[tuple[socket.socket, ForwardSpec]] = []
self.bound: list[ForwardSpec] = []
def start(self) -> None:
for spec in self.specs:
listener = socket.create_server(
(spec.listen_host, spec.listen_port),
reuse_port=False,
backlog=64,
)
listener.setblocking(False)
host, port = listener.getsockname()[:2]
bound = ForwardSpec(
label=spec.label,
listen_host=str(host),
listen_port=int(port),
target_host=spec.target_host,
target_port=spec.target_port,
)
self.listeners.append((listener, bound))
self.bound.append(bound)
self.selector.register(listener, selectors.EVENT_READ, bound)
def serve(self) -> None:
while not self.stop_event.is_set():
try:
events = self.selector.select(timeout=0.25)
except OSError:
return
for key, _ in events:
listener = key.fileobj
if not isinstance(listener, socket.socket):
continue
spec = key.data
try:
client, _ = listener.accept()
except OSError:
continue
threading.Thread(
target=self._handle_client,
args=(client, spec),
daemon=True,
).start()
def stop(self) -> None:
self.stop_event.set()
for listener, _ in self.listeners:
try:
self.selector.unregister(listener)
except Exception: # noqa: BLE001 - best effort shutdown
pass
listener.close()
self.selector.close()
def _handle_client(self, client: socket.socket, spec: ForwardSpec) -> None:
with client:
try:
target = socket.create_connection((spec.target_host, spec.target_port))
except OSError as exc:
warn(f"smolmachines forwarder {spec.label}: target connect failed: {exc}")
return
with target:
left = threading.Thread(target=_pipe, args=(client, target), daemon=True)
right = threading.Thread(target=_pipe, args=(target, client), daemon=True)
left.start()
right.start()
left.join()
right.join()
def _pipe(src: socket.socket, dst: socket.socket) -> None:
while True:
try:
data = src.recv(_BUFFER_SIZE)
except OSError:
break
if not data:
break
try:
dst.sendall(data)
except OSError:
break
try:
dst.shutdown(socket.SHUT_WR)
except OSError:
pass
def main(argv: Sequence[str] | None = None) -> int:
parser = argparse.ArgumentParser()
parser.add_argument("--spec-json", required=True)
ns = parser.parse_args(argv)
specs = tuple(ForwardSpec(**item) for item in json.loads(ns.spec_json))
forwarder = _Forwarder(specs)
def request_stop(signum: int, _frame: object) -> None:
del signum
forwarder.stop()
signal.signal(signal.SIGTERM, request_stop)
signal.signal(signal.SIGINT, request_stop)
forwarder.start()
print(json.dumps({"forwards": [asdict(s) for s in forwarder.bound]}), flush=True)
try:
forwarder.serve()
finally:
forwarder.stop()
return 0
if __name__ == "__main__":
raise SystemExit(main())
@@ -23,6 +23,8 @@ Plans (EgressPlan, …) lands in chunk 2d."""
from __future__ import annotations
import os
import socket
import subprocess
from dataclasses import dataclass, field
from pathlib import Path
@@ -34,6 +36,7 @@ from ..docker.sidecar_bundle import (
SIDECAR_BUNDLE_DOCKERFILE,
SIDECAR_BUNDLE_IMAGE,
)
from . import smolvm as _smolvm
_REPO_DIR = str(Path(__file__).resolve().parent.parent.parent.parent)
@@ -54,6 +57,11 @@ def bundle_container_name(slug: str) -> str:
return f"bot-bottle-sidecars-{slug}"
def bundle_machine_name(slug: str) -> str:
"""Sidecar smolVM machine name."""
return bundle_container_name(slug)
@dataclass(frozen=True)
class BundleLaunchSpec:
"""Everything `start_bundle` needs to bring up one bundle
@@ -92,6 +100,11 @@ class BundleLaunchSpec:
publish_host_ip: str = "127.0.0.1"
@dataclass(frozen=True)
class BundleVmLaunch:
raw_ports: dict[int, int]
def ensure_bundle_image(image: str = SIDECAR_BUNDLE_IMAGE) -> None:
"""Build the sidecar bundle image before `docker run`.
@@ -107,6 +120,70 @@ def ensure_bundle_image(image: str = SIDECAR_BUNDLE_IMAGE) -> None:
)
def allocate_raw_host_ports(container_ports: Sequence[int]) -> dict[int, int]:
"""Reserve candidate host loopback ports for smolVM `-p HOST:GUEST`.
The sockets are closed before smolVM binds them, so this remains
best-effort. smolVM failing to bind a selected port is fatal in
the caller's launch path."""
out: dict[int, int] = {}
for container_port in container_ports:
with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as sock:
sock.bind(("127.0.0.1", 0))
out[container_port] = int(sock.getsockname()[1])
return out
def start_bundle_vm(
spec: BundleLaunchSpec,
*,
from_path: Path,
host_env: dict[str, str] | None = None,
) -> BundleVmLaunch:
"""Create and start the sidecar bundle as a smolVM.
smolVM's own published ports are raw host-loopback ports. The
launch flow wraps them with per-bottle address-bound forwarders
before exposing anything to the agent VM."""
raw_ports = allocate_raw_host_ports(spec.ports_to_publish)
effective_host_env = host_env if host_env is not None else os.environ
env: dict[str, str] = {"BOT_BOTTLE_SIDECAR_DAEMONS": spec.daemons_csv}
for entry in spec.environment:
name, sep, value = entry.partition("=")
if sep:
env[name] = value
elif entry in effective_host_env:
env[entry] = effective_host_env[entry]
name = bundle_machine_name(spec.slug)
_smolvm.machine_create(
name,
from_path=from_path,
net=True,
env=env,
volumes=spec.volumes,
ports=tuple(
(host_port, guest_port)
for guest_port, host_port in raw_ports.items()
),
)
_smolvm.machine_start(name)
_smolvm.wait_exec_ready(name)
return BundleVmLaunch(raw_ports=raw_ports)
def stop_bundle_vm(slug: str) -> None:
"""Best-effort sidecar VM teardown."""
name = bundle_machine_name(slug)
try:
_smolvm.machine_stop(name)
except _smolvm.SmolvmError as exc:
warn(f"smolvm machine stop {name} failed: {exc}")
try:
_smolvm.machine_delete(name)
except _smolvm.SmolvmError as exc:
warn(f"smolvm machine delete {name} failed: {exc}")
def create_bundle_network(network_name: str, subnet: str, gateway: str) -> None:
"""`docker network create` with an explicit subnet + gateway
so the bundle's `--ip` lands on the address the Smolfile's
+12 -4
View File
@@ -113,8 +113,11 @@ def machine_create(
*,
image: str | None = None,
from_path: Path | None = None,
net: bool = False,
allow_cidrs: Sequence[str] = (),
env: Mapping[str, str] | None = None,
ports: Sequence[tuple[int, int]] = (),
volumes: Sequence[tuple[str, str, bool]] = (),
) -> None:
"""`smolvm machine create --name NAME [--image IMG | --from PATH]
[--allow-cidr CIDR ...] [-e K=V ...]`. NAME is passed as
@@ -131,19 +134,24 @@ def machine_create(
no-pull-at-start property. The flag form gives the same
result without the Smolfile complication.
`--net` is sent explicitly when `allow_cidrs` is non-empty.
`--allow-cidr` implies `--net` per the CLI help, but sending
`--net` explicitly is harmless and ensures the guest has
`--net` is sent explicitly when `net=True` or `allow_cidrs` is
non-empty. `--allow-cidr` implies `--net` per the CLI help, but
sending `--net` explicitly is harmless and ensures the guest has
network access even if that implication changes across versions."""
args: list[str] = ["machine", "create", "--name", name]
if image is not None:
args += ["--image", image]
if from_path is not None:
args += ["--from", str(from_path)]
if allow_cidrs:
if net or allow_cidrs:
args.append("--net")
for cidr in allow_cidrs:
args += ["--allow-cidr", cidr]
for host_port, guest_port in ports:
args += ["-p", f"{host_port}:{guest_port}"]
for host_path, guest_path, read_only in volumes:
suffix = ":ro" if read_only else ""
args += ["-v", f"{host_path}:{guest_path}{suffix}"]
if env:
for k, v in env.items():
args += ["-e", f"{k}={v}"]