feat(sidecars): bundle image + Python init supervisor (PRD 0024 chunk 1)
New Dockerfile.sidecars multi-stage build: pulls the pinned
pipelock and gitleaks binaries into a mitmproxy-base final image,
installs git + openssh-client, and ships the project's egress
addon + supervise server alongside a stdlib-Python init at
/app/sidecar_init.py.
The init supervisor (claude_bottle/sidecar_init.py) is PID 1 in
the bundle. It spawns the daemons named in
CLAUDE_BOTTLE_SIDECAR_DAEMONS (or all four by default),
propagates SIGTERM/SIGINT to children with an 8s grace before
SIGKILL, and exits with the first-unexpected-child exit code so
a daemon crash tears down the bundle (per PRD 0024 open
question 1's default).
claude_bottle/egress_entrypoint.sh extracted verbatim from
Dockerfile.egress's prior inline sh -c so the supervisor can
call it as a normal child.
Tests:
- unit: _selected_daemons env-var subset behavior (7 cases),
_Supervisor signal/exit-code semantics including SIGKILL
escalation, and end-to-end main() via subprocess.
- integration: builds the image and probes that pipelock,
gitleaks, mitmdump, and the supervise Python module are
present + executable, plus a no-daemons-selected smoke test
of the entrypoint wiring. Skipped under act_runner (200+MB
base pulls + multi-stage build).
Renderer collapse and the deletion of Dockerfile.{egress,git-gate,
supervise} land in chunk 2 + 3.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
@@ -0,0 +1,209 @@
|
||||
"""Per-bottle sidecar supervisor (PRD 0024 chunk 1).
|
||||
|
||||
PID 1 inside the `claude-bottle-sidecars` bundle image. Spawns
|
||||
the configured daemons (egress, pipelock, git-gate, supervise),
|
||||
forwards SIGTERM/SIGINT to each child, propagates per-daemon
|
||||
stdout+stderr to the container log with a `[name] ` prefix, and
|
||||
exits with the first unexpected child exit code. If every child
|
||||
exits 0 after a graceful shutdown was requested, exit 0.
|
||||
|
||||
Per the PRD's "init failure semantics" open question, this
|
||||
implementation goes with "any unexpected child death tears down
|
||||
the rest" — bundling means the daemons share fate. Restart-just-
|
||||
this-one logic can land later if operators hit pain.
|
||||
|
||||
Daemon subset is env-driven. The compose renderer narrows it via
|
||||
`CLAUDE_BOTTLE_SIDECAR_DAEMONS=egress,pipelock` for bottles that
|
||||
don't use git-gate or supervise. Default: all four.
|
||||
|
||||
Stdlib-only by design — adding supervisord/s6/runit for four
|
||||
daemons is heavier than this script.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import signal
|
||||
import subprocess
|
||||
import sys
|
||||
import threading
|
||||
import time
|
||||
from dataclasses import dataclass
|
||||
from typing import IO, Sequence
|
||||
|
||||
|
||||
# Below compose's default 10s `stop_grace_period`. After this many
|
||||
# seconds past SIGTERM, escalate to SIGKILL on any still-running
|
||||
# child.
|
||||
_GRACE_SECONDS = 8.0
|
||||
|
||||
# Tight enough that exits and signals propagate without lag; loose
|
||||
# enough that the main loop isn't a CPU hog.
|
||||
_POLL_INTERVAL = 0.1
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class _DaemonSpec:
|
||||
name: str
|
||||
argv: Sequence[str]
|
||||
|
||||
|
||||
# Order matters only for first-launch race-window reasons: egress
|
||||
# starts first so pipelock's upstream connect succeeds during
|
||||
# pipelock's own startup. git-gate and supervise are independent.
|
||||
_DAEMONS: tuple[_DaemonSpec, ...] = (
|
||||
_DaemonSpec("egress", ("/bin/sh", "/app/egress-entrypoint.sh")),
|
||||
_DaemonSpec(
|
||||
"pipelock",
|
||||
("/usr/local/bin/pipelock", "run", "--config", "/etc/pipelock.yaml"),
|
||||
),
|
||||
_DaemonSpec("git-gate", ("/bin/sh", "/git-gate-entrypoint.sh")),
|
||||
_DaemonSpec("supervise", ("python3", "/app/supervise_server.py")),
|
||||
)
|
||||
|
||||
|
||||
def _selected_daemons(
|
||||
env: dict[str, str],
|
||||
all_daemons: Sequence[_DaemonSpec] | None = None,
|
||||
) -> tuple[_DaemonSpec, ...]:
|
||||
"""Filter the daemon set by the CLAUDE_BOTTLE_SIDECAR_DAEMONS env
|
||||
var. Unknown names in the list are ignored — the renderer is the
|
||||
source of truth for which daemons are wired.
|
||||
|
||||
`all_daemons` defaults to `_DAEMONS` resolved at call time (not
|
||||
at definition time), so tests can monkey-patch the module-level
|
||||
`_DAEMONS` and have the new value take effect."""
|
||||
if all_daemons is None:
|
||||
all_daemons = _DAEMONS
|
||||
raw = env.get("CLAUDE_BOTTLE_SIDECAR_DAEMONS", "").strip()
|
||||
if not raw:
|
||||
return tuple(all_daemons)
|
||||
wanted = {n.strip() for n in raw.split(",") if n.strip()}
|
||||
return tuple(d for d in all_daemons if d.name in wanted)
|
||||
|
||||
|
||||
def _log(msg: str) -> None:
|
||||
sys.stdout.write(f"sidecar-init: {msg}\n")
|
||||
sys.stdout.flush()
|
||||
|
||||
|
||||
def _pump(name: str, stream: IO[bytes]) -> None:
|
||||
"""Read lines from `stream`, prefix with `[name]`, write to
|
||||
stdout. Runs in its own thread per child; daemon=True so a
|
||||
blocked read doesn't keep the process alive after main exits."""
|
||||
for raw in iter(stream.readline, b""):
|
||||
line = raw.decode("utf-8", errors="replace").rstrip("\n")
|
||||
sys.stdout.write(f"[{name}] {line}\n")
|
||||
sys.stdout.flush()
|
||||
|
||||
|
||||
def _spawn(spec: _DaemonSpec) -> subprocess.Popen:
|
||||
proc = subprocess.Popen(
|
||||
list(spec.argv),
|
||||
stdout=subprocess.PIPE,
|
||||
stderr=subprocess.STDOUT,
|
||||
bufsize=0,
|
||||
)
|
||||
threading.Thread(
|
||||
target=_pump, args=(spec.name, proc.stdout), daemon=True
|
||||
).start()
|
||||
return proc
|
||||
|
||||
|
||||
class _Supervisor:
|
||||
"""Holds the running children + shutdown state. Pulled out so
|
||||
the test suite can drive it with fake commands."""
|
||||
|
||||
def __init__(self, specs: Sequence[_DaemonSpec]):
|
||||
self.specs = tuple(specs)
|
||||
self.procs: list[tuple[_DaemonSpec, subprocess.Popen]] = []
|
||||
self.shutdown_at: float | None = None
|
||||
self.first_unexpected_rc: int | None = None
|
||||
self.first_unexpected_name: str | None = None
|
||||
|
||||
def start_all(self) -> None:
|
||||
for spec in self.specs:
|
||||
_log(f"starting {spec.name}")
|
||||
self.procs.append((spec, _spawn(spec)))
|
||||
|
||||
def request_shutdown(self, reason: str) -> None:
|
||||
if self.shutdown_at is not None:
|
||||
return
|
||||
self.shutdown_at = time.monotonic()
|
||||
_log(f"shutting down ({reason}); forwarding SIGTERM")
|
||||
for _, p in self.procs:
|
||||
if p.poll() is None:
|
||||
try:
|
||||
p.terminate()
|
||||
except ProcessLookupError:
|
||||
pass
|
||||
|
||||
def tick(self) -> bool:
|
||||
"""One iteration of the watch loop. Returns True when every
|
||||
child has exited and the supervisor can return."""
|
||||
for spec, p in self.procs:
|
||||
rc = p.poll()
|
||||
if rc is None:
|
||||
continue
|
||||
if self.first_unexpected_rc is None and self.shutdown_at is None:
|
||||
# First exit BEFORE we asked for shutdown: that's
|
||||
# the failure signal. Record it and tear down.
|
||||
self.first_unexpected_rc = rc
|
||||
self.first_unexpected_name = spec.name
|
||||
_log(
|
||||
f"{spec.name} exited unexpectedly with code {rc}; "
|
||||
"tearing down"
|
||||
)
|
||||
self.request_shutdown(reason="child_exit")
|
||||
|
||||
if self.shutdown_at is not None:
|
||||
elapsed = time.monotonic() - self.shutdown_at
|
||||
if elapsed > _GRACE_SECONDS:
|
||||
still_running = [
|
||||
spec.name for spec, p in self.procs if p.poll() is None
|
||||
]
|
||||
if still_running:
|
||||
_log(
|
||||
f"grace ({_GRACE_SECONDS:.0f}s) elapsed; SIGKILL on "
|
||||
f"{', '.join(still_running)}"
|
||||
)
|
||||
for _, p in self.procs:
|
||||
if p.poll() is None:
|
||||
try:
|
||||
p.kill()
|
||||
except ProcessLookupError:
|
||||
pass
|
||||
|
||||
return all(p.poll() is not None for _, p in self.procs)
|
||||
|
||||
def exit_code(self) -> int:
|
||||
if self.first_unexpected_rc is not None:
|
||||
return self.first_unexpected_rc
|
||||
# Graceful shutdown — surface the worst child code so a
|
||||
# daemon that died nonzero during teardown is visible.
|
||||
return max((p.returncode for _, p in self.procs), default=0)
|
||||
|
||||
|
||||
def main(argv: Sequence[str] | None = None) -> int:
|
||||
del argv # no flags yet; env-driven only
|
||||
specs = _selected_daemons(dict(os.environ))
|
||||
if not specs:
|
||||
_log("no daemons selected; nothing to do")
|
||||
return 0
|
||||
|
||||
sup = _Supervisor(specs)
|
||||
sup.start_all()
|
||||
|
||||
signal.signal(signal.SIGTERM, lambda *_: sup.request_shutdown("SIGTERM"))
|
||||
signal.signal(signal.SIGINT, lambda *_: sup.request_shutdown("SIGINT"))
|
||||
|
||||
while not sup.tick():
|
||||
time.sleep(_POLL_INTERVAL)
|
||||
|
||||
rc = sup.exit_code()
|
||||
_log(f"exit {rc}")
|
||||
return rc
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
Reference in New Issue
Block a user