Files
bot-bottle/bot_bottle/backend/firecracker/image_builder.py
T
didericis 914f01fa8f
lint / lint (push) Successful in 2m8s
test / unit (pull_request) Successful in 1m8s
test / integration (pull_request) Successful in 27s
test / coverage (pull_request) Successful in 1m22s
fix(firecracker): serialize infra-VM create + agent builds (PR #354 review)
Codex flagged that parallel `start`s race on shared state: two cold
launches could both stop/build/boot the singleton on the same rootfs/PID,
concurrent builds share the infra VM's buildah store, the cleanup did
`buildah rm -a` (nuking a peer build's container), and the rootfs cache
was populated non-atomically.

- `infra_vm.ensure_running`: a host flock (`singleton.lock`) around the
  cold stop/build/boot path, with a double-checked health re-test under
  the lock so a second launcher adopts rather than re-boots. The healthy
  fast-path stays lock-free.
- `image_builder.build_agent_rootfs_dir`: a host flock (`.build.lock`)
  around cache-lookup + build + publish; build into `.building-<digest>`
  and publish by atomic `os.rename`, so a partial build never appears as
  `agent-<digest>`.
- scoped cleanup: per-build named working containers
  (`<tag>-smoke`/`-export`) removed by name instead of `buildah rm -a`;
  also cleared before the build to recover from a crashed prior run.

Verified: agent image builds via the locked/atomic path, infra VM stays
healthy, agent boots, `claude --version` = 2.1.172. Full unit suite +
pyright green.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WBMWTEtQdJ4W5UrWuLHCck
2026-07-16 16:15:58 -04:00

208 lines
8.8 KiB
Python

"""Docker-free agent-image builds for the Firecracker backend (PRD 0069 Stage 3).
Agent Dockerfiles build **inside the persistent per-host infra VM**
(`infra_vm.py`), which carries buildah (rootless, daemonless): no host Docker
daemon, no root-equivalent `docker` group. The build runs over SSH against the
infra VM and its rootfs streams back to the host, where the existing
`mke2fs -d` path (`util.build_rootfs_ext4`) turns it into a bootable ext4.
Building in the infra VM — rather than a throwaway builder VM — means there is
one buildah image (`bot-bottle-infra`) and no contention for the orchestrator
TAP. Tradeoff: an untrusted Dockerfile's `RUN` steps share the VM with the
control plane + gateway (buildah `--isolation chroot` isn't a hard boundary) —
the accepted single-VM blast-radius tradeoff, re-splittable into a disposable
builder (booted from this same image on its own TAP) later.
"""
from __future__ import annotations
import fcntl
import hashlib
import os
import shutil
import subprocess
from contextlib import contextmanager
from pathlib import Path
from typing import Generator
from ...log import die, info
from . import infra_vm, util
# vfs + chroot: buildah works as root in the microVM (no fuse-overlayfs /
# overlay module / subuid maps). `--isolation` is a build/run-only flag;
# `from`/`mount` take just the store.
_BUILD_FLAGS = "--isolation chroot --storage-driver vfs"
_STORE_FLAG = "--storage-driver vfs"
_BUILD_TIMEOUT_SECONDS = 900.0
def _dockerfile_hash(dockerfile: Path) -> str:
"""Cache key: the Dockerfile's content. The shipped agent Dockerfiles
COPY nothing from the build context (see .dockerignore), so their content
fully determines the image; a Dockerfile that adds COPY will want the
context folded in here too."""
return hashlib.sha256(dockerfile.read_bytes()).hexdigest()[:16]
def build_agent_rootfs_dir(
dockerfile: Path, *, image_tag: str, smoke_test: tuple[str, ...] = (),
) -> Path:
"""Build `dockerfile` in the infra VM (buildah, no host docker), export its
rootfs, inject the guest boot bits, and return the cached base dir — the
same shape `util.build_rootfs_ext4` consumes. Cached by Dockerfile content,
so a repeat launch skips the rebuild.
`smoke_test` (the provider's declared argv, e.g. `("claude","--version")`)
is run in the freshly built image before export, catching an npm
silent-failure image at build time rather than at first agent use."""
digest = _dockerfile_hash(dockerfile)
base = util.cache_dir() / "rootfs" / f"agent-{digest}"
if (base / ".bb-ready").is_file():
info(f"using cached agent rootfs {base.name}")
return base
# Serialize builds: the infra VM's buildah store + this cache dir are
# shared, so concurrent `start`s must not build into them at once. The
# lock covers the cache lookup + build + atomic publish; the ready
# fast-path above takes no lock.
with _build_lock():
if (base / ".bb-ready").is_file(): # another build finished while we waited
info(f"using cached agent rootfs {base.name}")
return base
# Build into a temp dir and publish by atomic rename, so a partial
# build is never visible as `agent-<digest>`.
staging = util.cache_dir() / "rootfs" / f".building-{digest}"
shutil.rmtree(staging, ignore_errors=True)
staging.mkdir(parents=True)
info(f"building agent image {image_tag!r} in the infra VM")
_build_in_infra(dockerfile, staging, smoke_test, digest)
util.inject_guest_boot(staging)
(staging / ".bb-ready").write_text("ok\n")
shutil.rmtree(base, ignore_errors=True)
os.rename(staging, base)
return base
@contextmanager
def _build_lock() -> Generator[None, None, None]:
"""Host-level exclusive lock serializing agent-image builds (shared infra
buildah store + cache dir). flock auto-releases on a crash."""
lock_path = util.cache_dir() / "rootfs" / ".build.lock"
lock_path.parent.mkdir(parents=True, exist_ok=True)
handle = open(lock_path, "w", encoding="utf-8")
try:
fcntl.flock(handle, fcntl.LOCK_EX)
yield
finally:
handle.close()
def _build_in_infra(
dockerfile: Path, base: Path, smoke_test: tuple[str, ...], digest: str,
) -> None:
"""Ensure the infra VM is up, `buildah build` the Dockerfile in it, smoke
test the image, and stream its rootfs into `base`. The infra VM persists;
only the per-build container/image/context are cleaned up."""
infra = infra_vm.ensure_running()
key, ip = infra.private_key, infra.guest_ip
tag = f"bot-bottle-agent-build-{digest}"
ctx = f"/tmp/agent-build-{digest}"
smoke_ctr, export_ctr = f"{tag}-smoke", f"{tag}-export"
def _cleanup() -> None:
# Remove only THIS build's working containers/image/context — never
# `buildah rm -a`, which would nuke a concurrent build's container.
_ssh(key, ip,
f"buildah rm {smoke_ctr} {export_ctr} >/dev/null 2>&1; "
f"buildah rmi {_STORE_FLAG} {tag} >/dev/null 2>&1; rm -rf {ctx}",
timeout=60)
_cleanup() # clear leftovers from a crashed prior build of this digest
try:
prep = _ssh(key, ip, f"mkdir -p {ctx}/ctx")
if prep.returncode != 0:
die(f"preparing build dir in the infra VM failed: {prep.stderr.strip()}")
_send_dockerfile(key, ip, dockerfile, ctx)
_buildah_build(key, ip, ctx, tag)
_smoke_test(key, ip, tag, smoke_ctr, smoke_test)
_stream_rootfs(key, ip, tag, export_ctr, base)
finally:
_cleanup()
def _ssh(private_key: Path, guest_ip: str, script: str,
*, timeout: float = 60.0) -> subprocess.CompletedProcess[str]:
return subprocess.run(
util.ssh_base_argv(private_key, guest_ip) + [script],
capture_output=True, text=True, timeout=timeout, check=False,
)
def _send_dockerfile(private_key: Path, guest_ip: str, dockerfile: Path, ctx: str) -> None:
proc = subprocess.run(
util.ssh_base_argv(private_key, guest_ip) + [f"cat > {ctx}/Dockerfile"],
input=dockerfile.read_bytes(), capture_output=True, timeout=30, check=False,
)
if proc.returncode != 0:
die(f"sending Dockerfile to the infra VM failed: "
f"{proc.stderr.decode(errors='replace').strip()}")
def _buildah_build(private_key: Path, guest_ip: str, ctx: str, tag: str) -> None:
build = _ssh(
private_key, guest_ip,
f"buildah build {_BUILD_FLAGS} -t {tag} -f {ctx}/Dockerfile {ctx}/ctx",
timeout=_BUILD_TIMEOUT_SECONDS,
)
if build.returncode != 0:
tail = "\n".join((build.stdout + build.stderr).strip().splitlines()[-20:])
die(f"buildah build in the infra VM failed:\n{tail}")
def _smoke_test(private_key: Path, guest_ip: str, tag: str, ctr: str,
argv: tuple[str, ...]) -> None:
"""Run the provider's smoke argv inside the freshly built image
(`buildah run`, which uses the image's own PATH), failing the build
loudly if the CLI is a broken stub. No-op without a declared test. Uses a
named working container (`ctr`) so cleanup is scoped to this build."""
if not argv:
return
cmd = (
f"set -e; buildah from {_STORE_FLAG} --name {ctr} {tag} >/dev/null; "
f"buildah run {_BUILD_FLAGS} {ctr} -- {' '.join(argv)}; rc=$?; "
f"buildah rm {ctr} >/dev/null 2>&1 || true; exit $rc"
)
result = _ssh(private_key, guest_ip, cmd, timeout=120)
if result.returncode != 0:
detail = (result.stdout + result.stderr).strip().splitlines()[-10:]
die(f"agent image failed its post-build smoke test "
f"({' '.join(argv)}):\n" + "\n".join(detail))
def _stream_rootfs(private_key: Path, guest_ip: str, tag: str, ctr: str, base: Path) -> None:
"""`buildah mount` the built image in the infra VM and pipe its rootfs tar
straight into `base` on the host (extracted as the non-root host user, so
uid 0 isn't preserved — the guest init restores /root ownership). Uses a
named working container so cleanup is scoped to this build."""
export = (
f"set -e; buildah from {_STORE_FLAG} --name {ctr} {tag} >/dev/null; "
f"mnt=$(buildah mount {_STORE_FLAG} {ctr}); "
f"tar -C \"$mnt\" -cf - ."
)
ssh_proc = subprocess.Popen(
util.ssh_base_argv(private_key, guest_ip) + [export],
stdout=subprocess.PIPE, stderr=subprocess.PIPE,
)
assert ssh_proc.stdout is not None
untar = subprocess.run(
["tar", "-x", "-C", str(base)], stdin=ssh_proc.stdout, check=False,
)
ssh_proc.stdout.close()
ssh_err = (ssh_proc.stderr.read().decode(errors="replace")
if ssh_proc.stderr else "")
rc = ssh_proc.wait()
if rc != 0 or untar.returncode != 0:
die(f"exporting the built rootfs from the infra VM failed: "
f"{ssh_err.strip() or '<no stderr>'}")