feat(backend): reconcile running bottles' CA on gateway bring-up (0081)

Add `attach_bottled_agents_to_gateway()` as an `@abc.abstractmethod` on
`BottleBackend` and implement the first reconcile step across all three
backends: on a gateway cold boot, replace every already-running agent's
trusted CA with the freshly-minted gateway CA. Reconciling running bottles
is a backend responsibility (only the backend can enumerate its agents and
reach them — firecracker over SSH, docker/macOS over exec/cp), so making it
an abstract method keeps the fix cross-backend by construction.

The gateway rootfs is ephemeral, so a rebuild mints a new CA that every
running bottle distrusts (SSL verification fails — #510). This reconcile is
what distributes the fresh CA, so a routine gateway rebuild now doubles as a
free CA rotation. Per-bottle steps are best-effort: one unreachable or
malformed bottle is logged and skipped, never blocking the others.

Trigger — `Gateway.connect_to_orchestrator` now returns a cold-boot bool
(True when it actually (re)brought the gateway up, False when a healthy
current gateway was left untouched); each infra `ensure_running` gates the
reconcile on it, so it fires exactly on cold boot and never on an adopt.

Git-gate re-provision and egress-token restore fold into this same reconcile
on the same trigger in follow-up PRs (#516).

Refs #516. Addresses #510.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
2026-07-26 23:54:27 +00:00
committed by didericis
parent 314b30c013
commit 36f594b770
21 changed files with 488 additions and 15 deletions
@@ -34,6 +34,7 @@ every real command arrives through `container exec`.
from __future__ import annotations
import tempfile
from dataclasses import dataclass
from ...egress import EgressPlan
@@ -43,6 +44,7 @@ from ...orchestrator.client import OrchestratorClient, OrchestratorClientError
from ...orchestrator.reprovision import reprovision_bottles
from ...orchestrator.store.secret_store import ENV_VAR_SECRET_NAME
from ..provision_bottle import deprovision_bottle, provision_bottle
from ..util import AGENT_CA_PATH
from . import util as container_mod
from .enumerate import CONTAINER_NAME_PREFIX, EnumerationError, enumerate_active
from .gateway import GATEWAY_NETWORK
@@ -98,6 +100,66 @@ def ensure_gateway(
return endpoint
def _push_ca_to_container(name: str, ca_pem: str) -> None:
"""Replace one running agent container's trusted gateway CA with `ca_pem`
and rebuild its trust store via `container cp` + `container exec`.
Unconditional install — there is one gateway, so no fingerprint match is
needed. Raises `ConsolidatedLaunchError` on failure."""
mkdir = container_mod.run_container_argv(
["container", "exec", name, "mkdir", "-p",
"/usr/local/share/ca-certificates"]
)
if mkdir.returncode != 0:
raise ConsolidatedLaunchError(
f"CA push to {name} failed (mkdir): {(mkdir.stderr or '').strip()}"
)
with tempfile.NamedTemporaryFile("w", suffix=".crt") as tmp:
tmp.write(ca_pem)
tmp.flush()
cp = container_mod.run_container_argv(
["container", "cp", tmp.name, f"{name}:{AGENT_CA_PATH}"]
)
if cp.returncode != 0:
raise ConsolidatedLaunchError(
f"CA push to {name} failed (cp): {(cp.stderr or '').strip()}"
)
ex = container_mod.run_container_argv(
["container", "exec", name, "sh", "-c",
f"chmod 644 {AGENT_CA_PATH} && update-ca-certificates"]
)
if ex.returncode != 0:
raise ConsolidatedLaunchError(
f"CA push to {name} failed (update-ca-certificates): "
f"{(ex.stderr or '').strip()}"
)
def attach_bottled_agents_to_gateway(ca_pem: str | None = None) -> None:
"""Reconcile every running agent container against the freshly-(re)created
gateway (PRD 0081): replace each agent's trusted CA with the current gateway
CA, so a gateway rebuild doesn't silently break their TLS egress (#510).
Per-container steps are best-effort: one failure is logged and skipped so it
never blocks the others or the gateway coming up."""
if ca_pem is None:
ca_pem = MacosInfraService().ca_cert_pem()
try:
agents = list(enumerate_active())
except (EnumerationError, OSError) as exc:
info(f"CA reconcile skipped: {exc}")
return
reconciled = 0
for agent in agents:
name = f"{CONTAINER_NAME_PREFIX}{agent.slug}"
try:
_push_ca_to_container(name, ca_pem)
reconciled += 1
except (OSError, ConsolidatedLaunchError) as exc:
info(f"CA reconcile skipped for {name}: {exc}")
if reconciled:
info(f"reconciled gateway CA into {reconciled} running macOS bottle(s)")
def _reprovision_running_bottles(endpoint: GatewayEndpoint) -> None:
"""Recover keys from live Apple containers and restore gateway tokens."""
try:
@@ -200,6 +262,7 @@ __all__ = [
"GatewayEndpoint",
"LaunchContext",
"ensure_gateway",
"attach_bottled_agents_to_gateway",
"live_source_ips",
"register_agent",
"deprovision_consolidated",