didericis/bot-bottle
1
0
Fork 0
Code Issues 25 Pull Requests 9 Actions Packages Projects Releases Wiki Activity

feat(firecracker): implement consolidated orchestrator launch (PRD 0070)

Browse Source 
Replace the per-bottle Docker sidecar bundle with the shared per-host
orchestrator + gateway, mirroring what the Docker backend already has.

- Add `bot_bottle/backend/firecracker/consolidated_launch.py`:
  `_FirecrackerOrchestratorService` (subclasses `OrchestratorService`,
  overrides `_gateway()` to return a `DockerGateway` with host port
  bindings so Firecracker VMs can reach it via their TAP link);
  `launch_consolidated()` registers the bottle by guest IP (attribution
  key), provisions git-gate into the shared gateway, and returns the
  shared CA + orchestrator URL for teardown; `teardown_consolidated()`
  deregisters and cleans up.

- Rewrite `bot_bottle/backend/firecracker/launch.py`: removes the
  per-bottle sidecar bundle (`_start_sidecar_bundle`, `_stage_git_gate`,
  etc.) and `_mint_certs`; wires `launch_consolidated()` instead. The VM
  still sends to `host_tap_ip:PORT` — Docker's PREROUTING DNAT + the nft
  `ct status dnat accept` rule in the forward chain route the traffic to
  the shared gateway container.

- Extend `DockerGateway` with `host_port_bindings` so the Firecracker
  gateway publishes its ports on the host (`0.0.0.0:PORT`).

- Parameterise `OrchestratorService` with `orchestrator_name` /
  `orchestrator_label` so Docker and Firecracker orchestrators can
  coexist on the same host (`bot-bottle-orchestrator` vs
  `bot-bottle-fc-orchestrator`).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
didericis (claude)
2026-07-14 07:57:01 +00:00
committed by didericis
parent 3c426f45f5
commit 64ca39ddd4
5 changed files with 421 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files
bot_bottle/backend/firecracker/consolidated_launch.py
+164
View File
@@ -0,0 +1,164 @@
"""Consolidated bottle launch sequence for the Firecracker backend (PRD 0070).
Mirrors bot_bottle.backend.docker.consolidated_launch but wired for
Firecracker's TAP-based network topology instead of a shared Docker bridge.
The per-bottle sidecar bundle (one `docker run` per bottle, published on the
slot's host-side TAP IP) is replaced by a single persistent gateway that
every Firecracker VM shares. The gateway runs as a Docker container in the
dev-harness (a Firecracker VM is stage B per PRD 0070), with its ports
published on the host (`0.0.0.0:PORT`). VMs reach it at their slot's
host-side TAP IP because Docker's iptables PREROUTING DNAT redirects
port 9099/9100/9420 traffic to the gateway container — a path the nft
isolation table already allows via `ct status dnat accept` in the forward
chain.
Attribution is by the VM's guest IP, which is unspoofable by construction:
the /31 point-to-point TAP topology + the `bot_bottle_fc` nft table ensure
that only the expected VM can source-IP that address.
Sequence:
1. ensure the Firecracker-flavoured orchestrator + gateway are up;
2. register the bottle by its guest IP (attribution key) → bottle id +
identity token;
3. provision its git-gate repos/creds into the running gateway;
4. fetch the shared gateway CA for the provisioner to install in the rootfs.
The TAP slot allocation, rootfs build, and VM boot are the caller's job.
"""
from __future__ import annotations
from dataclasses import dataclass
from ...egress import EgressPlan
from ...git_gate import GitGatePlan
from ...orchestrator.client import OrchestratorClient
from ...orchestrator.gateway import (
GATEWAY_NETWORK,
DockerGateway,
)
from ...orchestrator.lifecycle import (
OrchestratorService,
OrchestratorStartError, # re-exported so callers can catch it
)
from ...orchestrator.registration import registration_inputs
from ..docker.egress import EGRESS_PORT
from ..docker.gateway_provision import deprovision_git_gate, provision_git_gate
from ...supervise import SUPERVISE_PORT
_GIT_HTTP_PORT = 9420
# Separate names from the Docker gateway so both backends can coexist on one
# host (and for clarity in `docker ps` output).
_FC_GATEWAY_NAME = "bot-bottle-fc-gateway"
_FC_ORCHESTRATOR_NAME = "bot-bottle-fc-orchestrator"
_FC_ORCHESTRATOR_LABEL = "bot-bottle-fc-orchestrator=1"
# Ports the gateway publishes on the host so Firecracker VMs can reach it
# via their TAP link. Docker's PREROUTING DNAT + nft's `ct status dnat
# accept` in the forward chain route the traffic.
_FC_GATEWAY_HOST_PORTS = (EGRESS_PORT, SUPERVISE_PORT, _GIT_HTTP_PORT)
class ConsolidatedLaunchError(RuntimeError):
"""The consolidated register/provision sequence could not complete."""
@dataclass(frozen=True)
class LaunchContext:
"""What the Firecracker launch needs from the consolidated sequence."""
bottle_id: str
identity_token: str
source_ip: str # the VM's guest IP — the attribution key
gateway_ca_pem: str # the shared gateway CA the provisioner installs
orchestrator_url: str
class _FirecrackerOrchestratorService(OrchestratorService):
"""Dev-harness orchestrator for the Firecracker backend.
Uses a gateway that publishes its ports on the host so Firecracker VMs can
reach it via their TAP link. The gateway and orchestrator containers use
`*-fc-*` names so both backends can run independently on the same host.
"""
def __init__(self, **kwargs: object) -> None:
super().__init__(
orchestrator_name=_FC_ORCHESTRATOR_NAME,
orchestrator_label=_FC_ORCHESTRATOR_LABEL,
**kwargs, # type: ignore[arg-type]
)
def _gateway(self) -> DockerGateway:
# The heavy data-plane image (#384 split it from the lean control-plane
# `image` this service's orchestrator container runs).
return DockerGateway(
self._gateway_image,
name=_FC_GATEWAY_NAME,
network=self.network,
orchestrator_url=self.internal_url,
host_port_bindings=_FC_GATEWAY_HOST_PORTS,
)
def launch_consolidated(
egress_plan: EgressPlan,
git_gate_plan: GitGatePlan,
*,
guest_ip: str,
image_ref: str = "",
tokens: dict[str, str] | None = None,
service: OrchestratorService | None = None,
gateway_name: str = _FC_GATEWAY_NAME,
) -> LaunchContext:
"""Ensure the orchestrator + Firecracker gateway are up, register the
bottle by its guest IP, and provision its git-gate state. Returns the
context the VM launch needs. Raises `ConsolidatedLaunchError` (or the
primitives' own errors) on failure — the caller tears down on failure."""
service = service or _FirecrackerOrchestratorService()
url = service.ensure_running()
client = OrchestratorClient(url)
inputs = registration_inputs(egress_plan)
reg = client.register_bottle(
guest_ip, image_ref=image_ref, policy=inputs.policy,
metadata=inputs.metadata, tokens=tokens,
)
try:
provision_git_gate(gateway_name, reg.bottle_id, git_gate_plan)
except Exception:
client.teardown_bottle(reg.bottle_id)
raise
# Fetch the shared gateway CA here so the caller can install it in the
# rootfs (the same CA every agent on this host trusts for TLS interception).
gateway_ca_pem = DockerGateway(
name=gateway_name, network=GATEWAY_NETWORK,
).ca_cert_pem()
return LaunchContext(
bottle_id=reg.bottle_id,
identity_token=reg.identity_token,
source_ip=guest_ip,
gateway_ca_pem=gateway_ca_pem,
orchestrator_url=url,
)
def teardown_consolidated(
bottle_id: str, *, orchestrator_url: str, gateway_name: str = _FC_GATEWAY_NAME,
) -> None:
"""Deregister the bottle and remove its git-gate state from the gateway.
Both steps are idempotent so this is safe from a cleanup trap."""
OrchestratorClient(orchestrator_url).teardown_bottle(bottle_id)
deprovision_git_gate(gateway_name, bottle_id)
__all__ = [
"LaunchContext",
"launch_consolidated",
"teardown_consolidated",
"ConsolidatedLaunchError",
"OrchestratorStartError",
]
bot_bottle/backend/firecracker/launch.py
+228 -20
View File
@@ -1,25 +1,64 @@
"""Launch flow for the Firecracker backend — temporarily disabled (#385).
"""Launch flow for the Firecracker backend (PRD 0070, consolidated).
The firecracker backend launched a per-bottle companion container (the
egress / git-gate / supervise data plane) alongside each microVM. That
per-bottle-companion architecture was removed in the companion-container removal;
firecracker's replacement — the consolidated per-host gateway — lands in
its own cutover (#354).
Per bottle:
1. build the agent image (docker), export it to a cached ext4 rootfs;
2. ensure the per-host orchestrator + shared gateway are up;
3. claim a free TAP pool slot (rootless flock);
4. register the bottle on the orchestrator by the VM's guest IP (the
attribution key) and provision its git-gate state into the gateway;
5. boot the microVM on that TAP; wait for SSH;
6. provision (shared gateway CA, prompt, skills, workspace, git, supervise)
over SSH.
Until that lands, launching a firecracker bottle fails closed rather than
silently running the removed path. `prepare` / `status` / cleanup still
work, so `backend status --backend=firecracker` and orphan cleanup are
unaffected.
The per-bottle Docker sidecar bundle is gone. The shared gateway handles
egress / git-gate / supervise for every VM; Docker's PREROUTING DNAT routes
the VMs' traffic to it, and the nft table's `ct status dnat accept` rule
in the forward chain lets it pass. The VM still sends to `host_tap_ip:PORT`
— the address its world is, by nft design, limited to.
Isolation is enforced by the operator-provisioned nft table (checked
fail-closed in preflight): a VM reaches only the sidecar (DNAT'd from
the host TAP IP) and nothing else.
"""
from __future__ import annotations
from contextlib import contextmanager
import dataclasses
import os
from contextlib import ExitStack, contextmanager
from pathlib import Path
from typing import Callable, Generator
from ...log import die
from ...agent_provider import runtime_for
from ...bottle_state import (
egress_state_dir,
git_gate_state_dir,
read_committed_image,
)
from ...egress import (
egress_agent_env_entries,
egress_resolve_token_values,
)
from ...git_gate import (
provision_git_gate_dynamic_keys,
revoke_git_gate_provisioned_keys,
)
from ...log import info, warn
from ...supervise import SUPERVISE_PORT
from ..docker import util as docker_mod
from ..docker.egress import EGRESS_PORT
from ..util import AGENT_CA_BUNDLE, AGENT_CA_PATH
from . import firecracker_vm, isolation_probe, netpool, util
from .bottle import FirecrackerBottle
from .bottle_plan import FirecrackerBottlePlan
from .consolidated_launch import (
launch_consolidated,
teardown_consolidated,
)
_REPO_DIR = str(Path(__file__).resolve().parent.parent.parent.parent)
_GIT_HTTP_PORT = 9420
@contextmanager
@@ -28,12 +67,181 @@ def launch(
*,
provision: Callable[[FirecrackerBottlePlan, "FirecrackerBottle"], str | None],
) -> Generator[FirecrackerBottle, None, None]:
"""Fail closed: the firecracker backend is disabled while its
consolidated (gateway-backed) launch is built in #354."""
del plan, provision
die(
"the firecracker backend is temporarily disabled during the "
"companion-container removal (#385); its consolidated relaunch "
"lands in #354. Use --backend=docker for now."
"""Build, launch, and provision a Firecracker bottle via the consolidated
orchestrator. Teardown on exit."""
stack = ExitStack()
bottle_for_revoke = plan.manifest.bottle
git_gate_dir_for_revoke = git_gate_state_dir(plan.slug)
def teardown() -> None:
teardown_exc: BaseException | None = None
try:
stack.close()
except BaseException as exc: # noqa: W0718 - teardown must continue
teardown_exc = exc
warn(f"firecracker teardown failed: {exc!r}")
revoke_git_gate_provisioned_keys(bottle_for_revoke, git_gate_dir_for_revoke)
if teardown_exc is not None:
raise teardown_exc
try:
# Step 1: agent image. The sidecar bundle image is built by the
# orchestrator service (ensure_running → ensure_built); we only
# build the agent image here. Use a committed snapshot when available.
plan = _build_agent_image(plan)
# Step 2: mint the git-gate dynamic (gitea) deploy keys, if any.
git_gate_plan = plan.git_gate_plan
if git_gate_plan.upstreams:
git_gate_plan = provision_git_gate_dynamic_keys(
plan.manifest.bottle, git_gate_plan, git_gate_state_dir(plan.slug),
)
# Step 3: claim a TAP slot; the flock is held until teardown.
slot, lock = netpool.allocate(plan.slug)
stack.callback(lock.close)
info(f"firecracker slot {slot.iface}: host={slot.host_ip} "
f"guest={slot.guest_ip}")
# Step 4: register on the orchestrator + provision this bottle's
# git-gate state into the shared gateway. The per-bottle egress tokens
# are resolved from the host env now and handed to the orchestrator
# (in memory) for the gateway to inject — the agent never sees them.
# Attribution is by the VM's guest IP (unspoofable via /31 TAP + nft).
effective_env = {**os.environ, **plan.agent_provision.provisioned_env}
token_values = egress_resolve_token_values(
plan.egress_plan.token_env_map, effective_env,
)
ctx = launch_consolidated(
plan.egress_plan, git_gate_plan,
guest_ip=slot.guest_ip,
image_ref=plan.image,
tokens=token_values,
)
stack.callback(
teardown_consolidated, ctx.bottle_id,
orchestrator_url=ctx.orchestrator_url,
)
# Step 5: install the SHARED gateway CA (replaces the per-bottle CA).
# Write it to a stable host path so the provisioner can copy it over SSH.
ca_dir = egress_state_dir(plan.slug) / "gateway-ca"
ca_dir.mkdir(parents=True, exist_ok=True)
ca_file = ca_dir / "gateway-ca.pem"
ca_file.write_text(ctx.gateway_ca_pem)
egress_plan = dataclasses.replace(
plan.egress_plan,
mitmproxy_ca_host_path=ca_file,
mitmproxy_ca_cert_only_host_path=ca_file,
)
# Point the agent's git-gate insteadOf rewrites and supervise MCP URL
# at the shared gateway (reached at the slot's host TAP IP — the VM
# sends there and Docker DNAT routes to the gateway container).
git_gate_url = (
f"http://{slot.host_ip}:{_GIT_HTTP_PORT}" if git_gate_plan.upstreams else ""
)
supervise_url = (
f"http://{slot.host_ip}:{SUPERVISE_PORT}/"
if plan.supervise_plan is not None else ""
)
plan = dataclasses.replace(
plan,
git_gate_plan=git_gate_plan,
egress_plan=egress_plan,
agent_proxy_url=f"http://{slot.host_ip}:{EGRESS_PORT}",
agent_git_gate_url=git_gate_url,
agent_supervise_url=supervise_url,
)
# Step 6: build the per-bottle rootfs + SSH key, then boot.
base_dir = util.build_base_rootfs_dir(plan.image)
run_dir = util.cache_dir() / "run" / plan.slug
run_dir.mkdir(parents=True, exist_ok=True)
rootfs = run_dir / "rootfs.ext4"
util.build_rootfs_ext4(base_dir, rootfs)
private_key, pubkey = util.generate_keypair(run_dir)
vm = firecracker_vm.boot(
name=plan.container_name,
rootfs=rootfs,
tap=slot.iface,
guest_ip=slot.guest_ip,
host_ip=slot.host_ip,
pubkey=pubkey,
run_dir=run_dir,
)
stack.callback(vm.terminate)
firecracker_vm.wait_for_ssh(vm, private_key)
# Authoritative fail-closed egress-boundary check, before the agent
# runs: prove the VM cannot reach the host directly.
isolation_probe.verify_isolation(private_key, slot.guest_ip)
bottle = FirecrackerBottle(
plan.container_name,
private_key=private_key,
guest_ip=slot.guest_ip,
guest_env=_agent_guest_env(plan, slot.host_ip),
agent_command=plan.agent_command,
agent_prompt_mode=plan.agent_prompt_mode,
agent_provider_template=plan.agent_provider_template,
terminal_title=(
f"{plan.spec.label} ({plan.spec.agent_name})"
if plan.spec.label else plan.spec.agent_name
),
terminal_color=plan.spec.color,
agent_workdir=plan.workspace_plan.workdir,
)
bottle.prompt_path = provision(plan, bottle)
yield bottle
finally:
teardown()
def _build_agent_image(plan: FirecrackerBottlePlan) -> FirecrackerBottlePlan:
committed = read_committed_image(plan.slug)
if committed and docker_mod.image_exists(committed):
info(f"using committed image {committed!r}")
return dataclasses.replace(
plan,
agent_provision=dataclasses.replace(plan.agent_provision, image=committed),
)
docker_mod.build_image(plan.image, _REPO_DIR, dockerfile=plan.dockerfile_path)
docker_mod.verify_agent_image(
plan.image, runtime_for(plan.agent_provider_template).smoke_test,
)
yield # unreachable — `die` raises; keeps this a generator/contextmanager
return plan
# --- agent guest env -------------------------------------------------
def _agent_guest_env(plan: FirecrackerBottlePlan, host_ip: str) -> dict[str, str]:
"""Env injected into every agent/exec call over SSH. The VM has no
baked process env (it just runs init), so the proxy/CA/git/supervise
wiring is applied per-invocation."""
proxy_url = f"http://{host_ip}:{EGRESS_PORT}"
no_proxy = f"localhost,127.0.0.1,{host_ip}"
env: dict[str, str] = {
"HTTPS_PROXY": proxy_url, "HTTP_PROXY": proxy_url,
"https_proxy": proxy_url, "http_proxy": proxy_url,
"NO_PROXY": no_proxy, "no_proxy": no_proxy,
"NODE_EXTRA_CA_CERTS": AGENT_CA_PATH,
"SSL_CERT_FILE": AGENT_CA_BUNDLE,
"REQUESTS_CA_BUNDLE": AGENT_CA_BUNDLE,
}
if plan.agent_git_gate_url:
env["GIT_GATE_URL"] = plan.agent_git_gate_url
if plan.agent_supervise_url:
env["MCP_SUPERVISE_URL"] = plan.agent_supervise_url
for entry in egress_agent_env_entries(plan.egress_plan):
key, _, value = entry.partition("=")
env[key] = value
env.update(plan.agent_provision.guest_env)
# Forwarded (bare-name) env: resolve host values now, since the VM
# can't inherit them from a `docker run --env NAME`.
for name in plan.forwarded_env:
value = os.environ.get(name)
if value is not None:
env[name] = value
return env
bot_bottle/orchestrator/gateway.py
+7
View File
@@ -100,6 +100,7 @@ class DockerGateway(Gateway):
orchestrator_url: str = "",
build_context: Path | None = None,
dockerfile: str | None = GATEWAY_DOCKERFILE,
host_port_bindings: tuple[int, ...] = (),
) -> None:
self.image_ref = image_ref
self.name = name
@@ -110,6 +111,10 @@ class DockerGateway(Gateway):
self._orchestrator_url = orchestrator_url
self._build_context = build_context or _REPO_ROOT
self._dockerfile = dockerfile
# Ports published on the host (0.0.0.0). Used by the Firecracker
# backend's dev-harness gateway so VMs can reach it via their TAP link;
# Docker's DNAT + the nft `ct status dnat accept` rule handle the rest.
self._host_port_bindings = host_port_bindings
def image_exists(self) -> bool:
return run_docker(["docker", "image", "inspect", self.image_ref]).returncode == 0
@@ -188,6 +193,8 @@ class DockerGateway(Gateway):
# trust it) — see GATEWAY_CA_VOLUME.
"--volume", f"{GATEWAY_CA_VOLUME}:{MITMPROXY_HOME}",
]
for port in self._host_port_bindings:
argv += ["--publish", f"0.0.0.0:{port}:{port}"]
if self._orchestrator_url:
# Makes the gateway's egress / git / supervise daemons multi-tenant:
# each request resolves source-IP -> policy against the control plane.
bot_bottle/orchestrator/lifecycle.py
+22 -9
View File
@@ -78,7 +78,13 @@ def _source_hash(repo_root: Path) -> str:
class OrchestratorService:
"""Manages the orchestrator control-plane container + the shared gateway.
Callers only need `ensure_running()` + `url`."""
Callers only need `ensure_running()` + `url`.
`orchestrator_name` / `orchestrator_label` let backends run independent
orchestrators on the same host without name collisions (e.g. the
Firecracker backend uses `bot-bottle-fc-orchestrator` alongside the Docker
backend's `bot-bottle-orchestrator`). Subclass and override `_gateway()`
to supply a backend-specific gateway variant."""
def __init__(
self,
@@ -89,6 +95,8 @@ class OrchestratorService:
gateway_image: str = GATEWAY_IMAGE,
repo_root: Path = _REPO_ROOT,
host_root: Path | None = None,
orchestrator_name: str = ORCHESTRATOR_NAME,
orchestrator_label: str = ORCHESTRATOR_LABEL,
) -> None:
self.port = port
self.network = network
@@ -100,6 +108,8 @@ class OrchestratorService:
self._gateway_image = gateway_image
self._repo_root = repo_root
self._host_root = host_root or bot_bottle_root()
self._orchestrator_name = orchestrator_name
self._orchestrator_label = orchestrator_label
@property
def url(self) -> str:
@@ -111,7 +121,7 @@ class OrchestratorService:
"""Control-plane URL as the gateway container reaches it — by name over
docker DNS on the shared network. This is the gateway's
BOT_BOTTLE_ORCHESTRATOR_URL."""
return f"http://{ORCHESTRATOR_NAME}:{self.port}"
return f"http://{self._orchestrator_name}:{self.port}"
def is_healthy(self, *, timeout: float = _HEALTH_REQUEST_TIMEOUT_SECONDS) -> bool:
try:
@@ -129,11 +139,11 @@ class OrchestratorService:
fixed-name container first). Register-only broker → no docker socket.
Labels the container with `source_hash` so a later `ensure_running`
can detect a real code change (see `_source_hash`)."""
run_docker(["docker", "rm", "--force", ORCHESTRATOR_NAME])
run_docker(["docker", "rm", "--force", self._orchestrator_name])
proc = run_docker([
"docker", "run", "--detach",
"--name", ORCHESTRATOR_NAME,
"--label", ORCHESTRATOR_LABEL,
"--name", self._orchestrator_name,
"--label", self._orchestrator_label,
"--label", f"{ORCHESTRATOR_SOURCE_HASH_LABEL}={source_hash}",
"--network", self.network,
# Host CLI reaches the control plane here; bound to loopback so it
@@ -185,12 +195,12 @@ class OrchestratorService:
*current* bind-mounted source. Mirrors `DockerGateway`'s
image-staleness check, but by content hash rather than image id since
the orchestrator runs bind-mounted source, not a built image."""
if not self._container_running(ORCHESTRATOR_NAME):
if not self._container_running(self._orchestrator_name):
return False
proc = run_docker([
"docker", "inspect", "--format",
"{{ index .Config.Labels \"" + ORCHESTRATOR_SOURCE_HASH_LABEL + "\" }}",
ORCHESTRATOR_NAME,
self._orchestrator_name,
])
if proc.returncode != 0:
return True # can't compare -> don't churn a working container
@@ -219,7 +229,10 @@ class OrchestratorService:
return self.url
self._ensure_orchestrator_image()
log.info("starting orchestrator container", context={"name": ORCHESTRATOR_NAME})
log.info(
"starting orchestrator container",
context={"name": self._orchestrator_name},
)
self._run_orchestrator_container(current_hash)
deadline = time.monotonic() + startup_timeout
@@ -234,7 +247,7 @@ class OrchestratorService:
def stop(self) -> None:
"""Remove the orchestrator + gateway containers (idempotent)."""
run_docker(["docker", "rm", "--force", ORCHESTRATOR_NAME])
run_docker(["docker", "rm", "--force", self._orchestrator_name])
self._gateway().stop()
tests/unit/test_docker_launch_committed_image.py
-1
View File
@@ -88,7 +88,6 @@ class TestLaunchCommittedImage(unittest.TestCase):
del ctx, dockerfile
built.append(image)
<<<<<<< HEAD
with mock.patch.object(launch_mod, "read_committed_image", return_value=committed_tag), \
mock.patch.object(launch_mod.docker_mod, "image_exists", return_value=image_present), \
mock.patch.object(launch_mod.docker_mod, "build_image", side_effect=_build), \