refactor(backend): base owns the gateway-attach flow, fail hard (0081 review)
Addresses review on #519 (@didericis 6143 + the fail-hard direction over the codex skip). Base owns the flow (6143 / ADR 0006). `attach_bottled_agents_to_gateway()` is now a concrete method on `BottleBackend` that delegates to `gateway_attach.reconcile_running_bottles`; backends override only three primitives — `_gateway_attach_resources()`, `_running_bottles()`, `_attach_bottle_to_gateway()`. The shared control flow + error policy live in one place so a backend can't drift onto a bespoke loop or a silent skip. Keeps the reconcile flow + `GatewayAttachResources` out of `backend/base.py` (the size guardrail) in a dedicated `backend/gateway_attach.py`. New ADR 0006 records the "shared behaviour in the base backend, subclasses override primitives" theme. Fail hard, never skip (the maintainer's direction over the codex review's skip). Any attach failure now aborts bring-up instead of being logged and skipped: a bottle that silently can't reach the fresh gateway (its egress just starts failing TLS) is worse than a loud failure. Every bottle is attempted and the failures are raised together (aggregate `InfraLaunchError`) so one bring-up surfaces the full blast radius. Resource gathering (the CA fetch) also fails hard. PRD 0081 goal + design updated to match (reversed from the earlier "tolerate per-bottle failures" draft). Bumps the base.py guardrail cap 580->600 for the new contract surface (the delegator + 3 abstract primitives); the flow itself lives in gateway_attach.py. Refs #516, #519. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
+31
-19
@@ -21,7 +21,7 @@ from abc import ABC, abstractmethod
|
||||
from contextlib import AbstractContextManager, contextmanager
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
from typing import Generator, Generic, Sequence, TypeVar
|
||||
from typing import TYPE_CHECKING, Generator, Generic, Sequence, TypeVar
|
||||
|
||||
from ..agent_provider import AgentProvisionPlan, get_provider
|
||||
from ..egress import EgressPlan
|
||||
@@ -35,6 +35,9 @@ from ..workspace import WorkspacePlan, workspace_plan
|
||||
from .print_util import print_multi, visible_agent_env_names
|
||||
from .util import host_skill_dir
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from .gateway_attach import GatewayAttachResources
|
||||
|
||||
|
||||
class BackendStatus(enum.IntEnum):
|
||||
"""Return codes for BottleBackend.status(). READY == 0 so callsites
|
||||
@@ -262,6 +265,11 @@ class Bottle(ABC):
|
||||
|
||||
PlanT = TypeVar("PlanT", bound=BottlePlan)
|
||||
CleanupT = TypeVar("CleanupT", bound=BottleCleanupPlan)
|
||||
# The backend-specific handle for one running bottle the reconcile attaches to
|
||||
# the gateway (a run dir for firecracker, a container name for docker/macOS).
|
||||
# Registry-style callers that don't care about the handle bind it to `Any`
|
||||
# (`BottleBackend[Any, Any, Any]`).
|
||||
AttachTargetT = TypeVar("AttachTargetT")
|
||||
|
||||
|
||||
class InfraLaunchError(RuntimeError):
|
||||
@@ -282,7 +290,7 @@ class BottleImages:
|
||||
sidecar: str | Path = ""
|
||||
|
||||
|
||||
class BottleBackend(ABC, Generic[PlanT, CleanupT]):
|
||||
class BottleBackend(ABC, Generic[PlanT, CleanupT, AttachTargetT]):
|
||||
"""Abstract base for selectable bottle backends. Concrete subclasses
|
||||
(e.g. DockerBottleBackend) own their own prepare/launch impls.
|
||||
Parameterized over the backend's concrete plan + cleanup-plan types
|
||||
@@ -510,26 +518,30 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
|
||||
compose ls`; firecracker cross-references its running gateway
|
||||
containers against per-bottle metadata."""
|
||||
|
||||
@abstractmethod
|
||||
def attach_bottled_agents_to_gateway(self) -> None:
|
||||
"""Reconcile every already-running bottle against the freshly-(re)booted
|
||||
gateway (PRD 0081). The host calls this on the gateway bring-up path —
|
||||
the cold-boot branch only, never on an adopt of a healthy current
|
||||
gateway — so a gateway rebuild/restart doesn't silently break running
|
||||
bottles' gateway-dependent state.
|
||||
"""Reconcile every running bottle against the freshly-(re)booted gateway
|
||||
on the cold-boot bring-up path (PRD 0081). The shared flow + fail-hard
|
||||
policy live in `gateway_attach`; backends override only the three
|
||||
primitives below (ADR 0006)."""
|
||||
from .gateway_attach import reconcile_running_bottles
|
||||
reconcile_running_bottles(self)
|
||||
|
||||
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 every backend must implement it —
|
||||
cross-backend by construction. Each per-bottle step is best-effort: one
|
||||
unreachable or malformed bottle is logged and skipped so it never blocks
|
||||
the others or the gateway coming up.
|
||||
@abstractmethod
|
||||
def _gateway_attach_resources(self) -> "GatewayAttachResources":
|
||||
"""Gather what every bottle needs to (re)attach to the current gateway
|
||||
(the CA now). Raises if the gateway isn't reachable (aborts reconcile)."""
|
||||
|
||||
Currently reconciles the **CA**: it replaces each agent's trusted CA
|
||||
with the current gateway CA (unconditional — there is one gateway, so no
|
||||
fingerprint match is needed), which rotates the CA for free on every
|
||||
bring-up. Git-gate re-provision and egress-token restore fold into this
|
||||
same reconcile on the same trigger (see #516)."""
|
||||
@abstractmethod
|
||||
def _running_bottles(self) -> Sequence[AttachTargetT]:
|
||||
"""The live bottles as backend handles for `_attach_bottle_to_gateway`.
|
||||
Raises if the live set can't be determined (fail hard, no partial set)."""
|
||||
|
||||
@abstractmethod
|
||||
def _attach_bottle_to_gateway(
|
||||
self, bottle: AttachTargetT, resources: "GatewayAttachResources",
|
||||
) -> None:
|
||||
"""(Re)attach one bottle to the current gateway (SSH / `exec`+`cp`).
|
||||
Raises `InfraLaunchError` naming the bottle on failure."""
|
||||
|
||||
@classmethod
|
||||
@abstractmethod
|
||||
|
||||
@@ -33,6 +33,7 @@ from ...git_gate import GitGatePlan
|
||||
from ...supervisor.plan import SupervisePlan
|
||||
from ...manifest import Manifest
|
||||
from .. import ActiveAgent, BottleBackend, BottleImages, BottleSpec
|
||||
from ..gateway_attach import GatewayAttachResources
|
||||
from . import cleanup as _cleanup
|
||||
from . import enumerate as _enumerate
|
||||
from . import launch as _launch
|
||||
@@ -40,7 +41,7 @@ from . import resolve_plan as _resolve_plan
|
||||
from .bottle import DockerBottle
|
||||
from .bottle_cleanup_plan import DockerBottleCleanupPlan
|
||||
from .bottle_plan import DockerBottlePlan
|
||||
class DockerBottleBackend(BottleBackend["DockerBottlePlan", "DockerBottleCleanupPlan"]):
|
||||
class DockerBottleBackend(BottleBackend["DockerBottlePlan", "DockerBottleCleanupPlan", str]):
|
||||
"""Docker backend implementation. Selected by BOT_BOTTLE_BACKEND
|
||||
when set to `docker`; retained as a legacy/example backend."""
|
||||
|
||||
@@ -141,6 +142,17 @@ class DockerBottleBackend(BottleBackend["DockerBottlePlan", "DockerBottleCleanup
|
||||
def enumerate_active(self) -> Sequence[ActiveAgent]:
|
||||
return _enumerate.enumerate_active()
|
||||
|
||||
def attach_bottled_agents_to_gateway(self) -> None:
|
||||
from .infra_launch import attach_bottled_agents_to_gateway
|
||||
attach_bottled_agents_to_gateway()
|
||||
def _gateway_attach_resources(self) -> GatewayAttachResources:
|
||||
from .infra import DockerInfraService
|
||||
return GatewayAttachResources(
|
||||
ca_pem=DockerInfraService().gateway().ca_cert_pem())
|
||||
|
||||
def _running_bottles(self) -> Sequence[str]:
|
||||
from .infra_launch import running_agent_containers
|
||||
return running_agent_containers()
|
||||
|
||||
def _attach_bottle_to_gateway(
|
||||
self, bottle: str, resources: GatewayAttachResources,
|
||||
) -> None:
|
||||
from .infra_launch import push_ca_to_container
|
||||
push_ca_to_container(bottle, resources.ca_pem)
|
||||
|
||||
@@ -73,11 +73,32 @@ def _network_container_ips(network: str) -> list[str]:
|
||||
return ips
|
||||
|
||||
|
||||
def _push_ca_to_container(container: str, ca_pem: str) -> None:
|
||||
"""Replace one running agent container's trusted gateway CA with `ca_pem`
|
||||
and rebuild its trust store via `docker cp` + `docker exec`. Unconditional
|
||||
install — there is one gateway, so no fingerprint match is needed. Raises
|
||||
`InfraLaunchError` on failure."""
|
||||
def running_agent_containers(
|
||||
network: str = GATEWAY_NETWORK, gateway_name: str = INFRA_NAME,
|
||||
) -> list[str]:
|
||||
"""Every running agent container on the gateway `network` (the gateway
|
||||
itself excluded) — the bottles the bring-up reconcile attaches to the fresh
|
||||
gateway (PRD 0081). Raises `OSError` if `docker` can't be run (fail hard: a
|
||||
reconcile that can't list its bottles must not look like "no bottles")."""
|
||||
proc = run_docker([
|
||||
"docker", "network", "inspect", "--format",
|
||||
"{{range .Containers}}{{.Name}}\n{{end}}", network,
|
||||
])
|
||||
return [
|
||||
name for name in (line.strip() for line in proc.stdout.splitlines())
|
||||
if name and name != gateway_name
|
||||
]
|
||||
|
||||
|
||||
def push_ca_to_container(container: str, ca_pem: str) -> None:
|
||||
"""(Re)attach one running agent container to the current gateway: replace
|
||||
its trusted gateway CA with `ca_pem` and rebuild its trust store via
|
||||
`docker cp` + `docker exec` (PRD 0081). Unconditional install — there is one
|
||||
gateway, so no fingerprint match is needed.
|
||||
|
||||
Fail hard: raises `InfraLaunchError` (naming the container) on any failure —
|
||||
the base reconcile aggregates and surfaces it rather than leaving the agent
|
||||
silently unable to reach the gateway."""
|
||||
mkdir = run_docker(
|
||||
["docker", "exec", container, "mkdir", "-p",
|
||||
"/usr/local/share/ca-certificates"]
|
||||
@@ -105,45 +126,6 @@ def _push_ca_to_container(container: str, ca_pem: str) -> None:
|
||||
)
|
||||
|
||||
|
||||
def attach_bottled_agents_to_gateway(
|
||||
ca_pem: str | None = None,
|
||||
*,
|
||||
network: str = GATEWAY_NETWORK,
|
||||
gateway_name: str = INFRA_NAME,
|
||||
) -> 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 = DockerInfraService().gateway().ca_cert_pem()
|
||||
try:
|
||||
proc = run_docker([
|
||||
"docker", "network", "inspect", "--format",
|
||||
"{{range .Containers}}{{.Name}}\n{{end}}", network,
|
||||
])
|
||||
except OSError as exc:
|
||||
log.info(f"CA reconcile skipped: {exc}")
|
||||
return
|
||||
reconciled = 0
|
||||
for line in proc.stdout.splitlines():
|
||||
name = line.strip()
|
||||
if not name or name == gateway_name:
|
||||
continue
|
||||
try:
|
||||
_push_ca_to_container(name, ca_pem)
|
||||
reconciled += 1
|
||||
except (OSError, InfraLaunchError) as exc:
|
||||
log.info(f"CA reconcile skipped for {name}: {exc}")
|
||||
if reconciled:
|
||||
log.info(
|
||||
"reconciled gateway CA into running docker bottle(s)",
|
||||
context={"count": reconciled},
|
||||
)
|
||||
|
||||
|
||||
def _reprovision_running_bottles(
|
||||
orchestrator_url: str,
|
||||
network: str = GATEWAY_NETWORK,
|
||||
@@ -250,7 +232,8 @@ def deprovision_consolidated(
|
||||
__all__ = [
|
||||
"LaunchContext",
|
||||
"launch_consolidated",
|
||||
"attach_bottled_agents_to_gateway",
|
||||
"running_agent_containers",
|
||||
"push_ca_to_container",
|
||||
"deprovision_consolidated",
|
||||
"InfraLaunchError",
|
||||
]
|
||||
|
||||
@@ -20,6 +20,7 @@ from ...git_gate import GitGatePlan
|
||||
from ...manifest import Manifest
|
||||
from ...supervisor.plan import SupervisePlan
|
||||
from .. import ActiveAgent, BottleBackend, BottleImages, BottleSpec
|
||||
from ..gateway_attach import GatewayAttachResources
|
||||
from . import cleanup as _cleanup
|
||||
from . import enumerate as _enumerate
|
||||
from . import launch as _launch
|
||||
@@ -31,7 +32,7 @@ from .bottle_plan import FirecrackerBottlePlan
|
||||
|
||||
|
||||
class FirecrackerBottleBackend(
|
||||
BottleBackend["FirecrackerBottlePlan", "FirecrackerBottleCleanupPlan"]
|
||||
BottleBackend["FirecrackerBottlePlan", "FirecrackerBottleCleanupPlan", "Path"]
|
||||
):
|
||||
name = "firecracker"
|
||||
|
||||
@@ -119,9 +120,18 @@ class FirecrackerBottleBackend(
|
||||
def enumerate_active(self) -> Sequence[ActiveAgent]:
|
||||
return _enumerate.enumerate_active()
|
||||
|
||||
def attach_bottled_agents_to_gateway(self) -> None:
|
||||
from .infra_launch import attach_bottled_agents_to_gateway
|
||||
attach_bottled_agents_to_gateway()
|
||||
def _gateway_attach_resources(self) -> GatewayAttachResources:
|
||||
from .gateway import FirecrackerGateway
|
||||
return GatewayAttachResources(ca_pem=FirecrackerGateway().ca_cert_pem())
|
||||
|
||||
def _running_bottles(self) -> Sequence[Path]:
|
||||
return _cleanup.live_run_dirs()
|
||||
|
||||
def _attach_bottle_to_gateway(
|
||||
self, bottle: Path, resources: GatewayAttachResources,
|
||||
) -> None:
|
||||
from .infra_launch import attach_ca_to_agent_vm
|
||||
attach_ca_to_agent_vm(bottle, resources.ca_pem)
|
||||
|
||||
def supervise_mcp_url(self, plan: FirecrackerBottlePlan) -> str:
|
||||
return plan.agent_supervise_url
|
||||
|
||||
@@ -32,7 +32,6 @@ from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
|
||||
from ...egress import EgressPlan
|
||||
from ...gateway import GatewayError
|
||||
from ...git_gate import GitGatePlan
|
||||
from ...log import info
|
||||
from ...orchestrator.client import OrchestratorClient, OrchestratorClientError
|
||||
@@ -88,56 +87,42 @@ def persist_env_var_secret(private_key: Path, guest_ip: str, secret: str) -> Non
|
||||
)
|
||||
|
||||
|
||||
def _push_gateway_ca_to_agent(private_key: Path, guest_ip: str, ca_pem: str) -> None:
|
||||
"""Replace one running agent VM's trusted gateway CA with `ca_pem` and
|
||||
rebuild its trust store over SSH. Unconditional install — there is one
|
||||
def attach_ca_to_agent_vm(run_dir: Path, ca_pem: str) -> None:
|
||||
"""(Re)attach one running agent VM (identified by its `run_dir`) to the
|
||||
current gateway: replace its trusted gateway CA with `ca_pem` and rebuild
|
||||
its trust store over SSH (PRD 0081). Unconditional install — there is one
|
||||
gateway, so no fingerprint match is needed. Bare-pipe input keeps the cert
|
||||
off argv. Raises `InfraLaunchError` on failure."""
|
||||
off argv.
|
||||
|
||||
Fail hard: raises `InfraLaunchError` (naming the bottle) if the run dir is
|
||||
malformed or the push fails — the base reconcile aggregates and surfaces it
|
||||
rather than leaving the agent silently unable to reach the gateway."""
|
||||
guest_ip = _guest_ip_from_config(run_dir / "config.json")
|
||||
private_key = run_dir / "bottle_id_ed25519"
|
||||
if not guest_ip or not private_key.is_file():
|
||||
raise InfraLaunchError(
|
||||
f"{run_dir.name}: cannot resolve guest IP / SSH key to attach it "
|
||||
f"to the gateway"
|
||||
)
|
||||
install = (
|
||||
"umask 022; mkdir -p /usr/local/share/ca-certificates && "
|
||||
f"cat > {AGENT_CA_PATH} && chmod 644 {AGENT_CA_PATH} && "
|
||||
"update-ca-certificates"
|
||||
)
|
||||
proc = subprocess.run(
|
||||
util.ssh_base_argv(private_key, guest_ip) + [install],
|
||||
input=ca_pem, capture_output=True, text=True, check=False,
|
||||
)
|
||||
try:
|
||||
proc = subprocess.run(
|
||||
util.ssh_base_argv(private_key, guest_ip) + [install],
|
||||
input=ca_pem, capture_output=True, text=True, check=False,
|
||||
)
|
||||
except OSError as exc:
|
||||
raise InfraLaunchError(f"{run_dir.name} ({guest_ip}): CA push failed: {exc}") from exc
|
||||
if proc.returncode != 0:
|
||||
raise InfraLaunchError(
|
||||
f"CA push to {guest_ip} failed: "
|
||||
f"{run_dir.name} ({guest_ip}): CA push failed: "
|
||||
f"{proc.stderr.strip() or '<no stderr>'}"
|
||||
)
|
||||
|
||||
|
||||
def attach_bottled_agents_to_gateway() -> None:
|
||||
"""Reconcile every running agent VM against the freshly-booted gateway
|
||||
(PRD 0081). Replaces each agent's trusted CA with the current gateway CA —
|
||||
the gateway rootfs is ephemeral, so a cold boot mints a fresh CA and this is
|
||||
what distributes it (a gateway rebuild doubles as a free CA rotation, #510).
|
||||
|
||||
Per-bottle steps are best-effort: one unreachable or malformed VM is logged
|
||||
and skipped so it never blocks the others or the gateway coming up."""
|
||||
gateway = FirecrackerGateway()
|
||||
try:
|
||||
ca_pem = gateway.ca_cert_pem()
|
||||
except GatewayError as exc:
|
||||
info(f"bring-up reconcile skipped: gateway CA unavailable: {exc}")
|
||||
return
|
||||
reconciled = 0
|
||||
for run_dir in cleanup.live_run_dirs():
|
||||
guest_ip = _guest_ip_from_config(run_dir / "config.json")
|
||||
private_key = run_dir / "bottle_id_ed25519"
|
||||
if not guest_ip or not private_key.is_file():
|
||||
continue
|
||||
try:
|
||||
_push_gateway_ca_to_agent(private_key, guest_ip, ca_pem)
|
||||
reconciled += 1
|
||||
except (OSError, InfraLaunchError) as exc:
|
||||
info(f"CA reconcile skipped for {guest_ip}: {exc}")
|
||||
if reconciled:
|
||||
info(f"reconciled gateway CA into {reconciled} running Firecracker bottle(s)")
|
||||
|
||||
|
||||
def _reprovision_running_bottles(client: OrchestratorClient) -> None:
|
||||
"""Read keys from live agent VMs and restore the restarted gateway."""
|
||||
try:
|
||||
@@ -210,7 +195,7 @@ def deprovision_consolidated(
|
||||
__all__ = [
|
||||
"LaunchContext",
|
||||
"launch_consolidated",
|
||||
"attach_bottled_agents_to_gateway",
|
||||
"attach_ca_to_agent_vm",
|
||||
"deprovision_consolidated",
|
||||
"InfraLaunchError",
|
||||
"OrchestratorStartError",
|
||||
|
||||
@@ -0,0 +1,54 @@
|
||||
"""The shared gateway-attach reconcile flow (PRD 0081).
|
||||
|
||||
`BottleBackend.attach_bottled_agents_to_gateway()` delegates here so every
|
||||
backend reconciles running bottles against a freshly-booted gateway *the same
|
||||
way* — the control flow + fail-hard policy live in one place and backends
|
||||
override only the primitives (see ADR 0006). Kept out of `backend/base.py` so
|
||||
the backend contract module stays lean (the base.py size guardrail).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from typing import TYPE_CHECKING, Any
|
||||
|
||||
from .base import InfraLaunchError
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from .base import BottleBackend
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class GatewayAttachResources:
|
||||
"""Everything a running bottle needs to (re)attach to the current gateway on
|
||||
a cold boot (PRD 0081). Gathered once per reconcile and handed to every
|
||||
bottle. The CA now; egress secrets and git-gate state join as the reconcile
|
||||
grows (#516)."""
|
||||
|
||||
ca_pem: str
|
||||
|
||||
|
||||
def reconcile_running_bottles(backend: "BottleBackend[Any, Any, Any]") -> None:
|
||||
"""Reconcile every already-running bottle against the freshly-(re)booted
|
||||
gateway: gather the attach resources once, then attach every live bottle.
|
||||
|
||||
Fail hard, never skip: a bottle that silently can't reach the fresh gateway
|
||||
(its egress just starts failing TLS) is worse than a loud bring-up failure,
|
||||
so any attach failure aborts bring-up. Every bottle is attempted first and
|
||||
the failures are raised together, so one bring-up surfaces the full blast
|
||||
radius rather than one bottle at a time."""
|
||||
resources = backend._gateway_attach_resources()
|
||||
failures: list[str] = []
|
||||
for bottle in backend._running_bottles():
|
||||
try:
|
||||
backend._attach_bottle_to_gateway(bottle, resources)
|
||||
except InfraLaunchError as exc:
|
||||
failures.append(str(exc))
|
||||
if failures:
|
||||
raise InfraLaunchError(
|
||||
f"could not attach {len(failures)} running bottle(s) to the "
|
||||
f"freshly-booted gateway:\n " + "\n ".join(failures)
|
||||
)
|
||||
|
||||
|
||||
__all__ = ["GatewayAttachResources", "reconcile_running_bottles"]
|
||||
@@ -14,6 +14,7 @@ from ...git_gate import GitGatePlan
|
||||
from ...supervisor.plan import SupervisePlan
|
||||
from ...manifest import Manifest
|
||||
from .. import ActiveAgent, BottleBackend, BottleImages, BottleSpec
|
||||
from ..gateway_attach import GatewayAttachResources
|
||||
from . import cleanup as _cleanup
|
||||
from . import enumerate as _enumerate
|
||||
from . import launch as _launch
|
||||
@@ -25,7 +26,7 @@ from .bottle_plan import MacosContainerBottlePlan
|
||||
|
||||
|
||||
class MacosContainerBottleBackend(
|
||||
BottleBackend["MacosContainerBottlePlan", "MacosContainerBottleCleanupPlan"]
|
||||
BottleBackend["MacosContainerBottlePlan", "MacosContainerBottleCleanupPlan", str]
|
||||
):
|
||||
"""Apple Container backend. Selected by
|
||||
`BOT_BOTTLE_BACKEND=macos-container` or
|
||||
@@ -117,9 +118,19 @@ class MacosContainerBottleBackend(
|
||||
def enumerate_active(self) -> Sequence[ActiveAgent]:
|
||||
return _enumerate.enumerate_active()
|
||||
|
||||
def attach_bottled_agents_to_gateway(self) -> None:
|
||||
from .infra_launch import attach_bottled_agents_to_gateway
|
||||
attach_bottled_agents_to_gateway()
|
||||
def _gateway_attach_resources(self) -> GatewayAttachResources:
|
||||
from .infra import MacosInfraService
|
||||
return GatewayAttachResources(ca_pem=MacosInfraService().ca_cert_pem())
|
||||
|
||||
def _running_bottles(self) -> Sequence[str]:
|
||||
from .infra_launch import running_agent_containers
|
||||
return running_agent_containers()
|
||||
|
||||
def _attach_bottle_to_gateway(
|
||||
self, bottle: str, resources: GatewayAttachResources,
|
||||
) -> None:
|
||||
from .infra_launch import push_ca_to_container
|
||||
push_ca_to_container(bottle, resources.ca_pem)
|
||||
|
||||
def supervise_mcp_url(self, plan: MacosContainerBottlePlan) -> str:
|
||||
return plan.agent_supervise_url
|
||||
|
||||
@@ -97,11 +97,23 @@ 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 `InfraLaunchError` on failure."""
|
||||
def running_agent_containers() -> list[str]:
|
||||
"""Every running agent container's name — the bottles the bring-up reconcile
|
||||
attaches to the fresh gateway (PRD 0081). Raises `EnumerationError` if the
|
||||
live set can't be determined (fail hard rather than reconcile a partial
|
||||
set)."""
|
||||
return [f"{CONTAINER_NAME_PREFIX}{agent.slug}" for agent in enumerate_active()]
|
||||
|
||||
|
||||
def push_ca_to_container(name: str, ca_pem: str) -> None:
|
||||
"""(Re)attach one running agent container to the current gateway: replace
|
||||
its trusted gateway CA with `ca_pem` and rebuild its trust store via
|
||||
`container cp` + `container exec` (PRD 0081). Unconditional install — there
|
||||
is one gateway, so no fingerprint match is needed.
|
||||
|
||||
Fail hard: raises `InfraLaunchError` (naming the container) on any failure —
|
||||
the base reconcile aggregates and surfaces it rather than leaving the agent
|
||||
silently unable to reach the gateway."""
|
||||
mkdir = container_mod.run_container_argv(
|
||||
["container", "exec", name, "mkdir", "-p",
|
||||
"/usr/local/share/ca-certificates"]
|
||||
@@ -131,32 +143,6 @@ def _push_ca_to_container(name: str, ca_pem: str) -> None:
|
||||
)
|
||||
|
||||
|
||||
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, InfraLaunchError) 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:
|
||||
@@ -259,7 +245,8 @@ __all__ = [
|
||||
"GatewayEndpoint",
|
||||
"LaunchContext",
|
||||
"ensure_gateway",
|
||||
"attach_bottled_agents_to_gateway",
|
||||
"running_agent_containers",
|
||||
"push_ca_to_container",
|
||||
"live_source_ips",
|
||||
"register_agent",
|
||||
"deprovision_consolidated",
|
||||
|
||||
@@ -26,10 +26,10 @@ from .base import ActiveAgent, BackendStatus, BottleBackend
|
||||
# Tests may replace _backends with a {name: fake} dict via patch.object;
|
||||
# _get_backends() returns the current module-level value as-is when it
|
||||
# is not None, so test fakes take effect without triggering real imports.
|
||||
_backends: dict[str, BottleBackend[Any, Any]] | None = None
|
||||
_backends: dict[str, BottleBackend[Any, Any, Any]] | None = None
|
||||
|
||||
|
||||
def _get_backends() -> dict[str, BottleBackend[Any, Any]]:
|
||||
def _get_backends() -> dict[str, BottleBackend[Any, Any, Any]]:
|
||||
"""Return the registry of all backend instances, loading lazily on first call."""
|
||||
global _backends # pylint: disable=global-statement
|
||||
if _backends is None:
|
||||
@@ -48,7 +48,7 @@ def get_bottle_backend(
|
||||
name: str | None = None,
|
||||
*,
|
||||
prompt: bool = True,
|
||||
) -> BottleBackend[Any, Any]:
|
||||
) -> BottleBackend[Any, Any, Any]:
|
||||
"""Resolve the bottle backend.
|
||||
|
||||
`name` precedence:
|
||||
|
||||
Reference in New Issue
Block a user