Compare commits
4 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| c435e9088e | |||
| 3b6f68d26d | |||
| 572904df44 | |||
| 0f98d75eff |
@@ -75,88 +75,6 @@ On compatible macOS hosts, the default backend requires Apple's `container` CLI
|
||||
|
||||
Use `BOT_BOTTLE_BACKEND=docker ./cli.py start <agent>` on hosts where neither Apple Container nor KVM is available and Docker is the desired backend.
|
||||
|
||||
### Containers inside a bottle
|
||||
|
||||
A bottle may set `nested_containers: true`. On the macOS backend this starts a
|
||||
guest-local, rootless **podman** service after the bottle is registered and
|
||||
exposes its Docker-compatible API socket, so the agent still runs `docker` and
|
||||
`docker compose`. Nothing is mounted from the host: Docker Desktop's socket
|
||||
stays out of the bottle and the guest gains no outer VM capabilities. Backends
|
||||
that cannot do this (`docker`, `firecracker`) reject the flag rather than
|
||||
silently ignore it.
|
||||
|
||||
Rootless Docker was tried first and does not work here at all: Apple
|
||||
Container's capability bounding set omits `CAP_SYS_ADMIN`, which the kernel
|
||||
requires to write a multi-range `uid_map`. See
|
||||
[`docs/research/rootless-docker-in-apple-container-spike.md`](docs/research/rootless-docker-in-apple-container-spike.md).
|
||||
|
||||
The tradeoff to understand before enabling it: podman avoids that requirement
|
||||
by falling back to a single-UID mapping, so nested containers provide **no
|
||||
isolation from the agent itself** — `root` inside a nested container is the
|
||||
agent user outside it. Nested containers are a build/test convenience, not a
|
||||
security boundary. The bottle remains the boundary.
|
||||
|
||||
Pulling images goes through the bottle's egress proxy like every other
|
||||
request, so each registry needs a route — **and so does the CDN it redirects
|
||||
layer blobs to**, which is a different host. Without the CDN route the pull
|
||||
authenticates, fetches the manifest, then 403s partway through.
|
||||
|
||||
Docker Hub and GHCR additionally need `preserve_auth: true`: their token dance
|
||||
uses a client-fetched per-scope bearer token that the proxy would otherwise
|
||||
strip. Turn DLP off on every registry and CDN route — the bodies are
|
||||
compressed layer blobs that no detector can read, and buffering them is what
|
||||
triggers the shared-proxy OOM in #455.
|
||||
|
||||
```yaml
|
||||
nested_containers: true
|
||||
egress:
|
||||
routes:
|
||||
# Docker Hub: registry, token endpoint, blob CDN.
|
||||
- host: registry-1.docker.io
|
||||
preserve_auth: true
|
||||
dlp: { outbound_detectors: false, inbound_detectors: false }
|
||||
- host: auth.docker.io
|
||||
preserve_auth: true
|
||||
dlp: { outbound_detectors: false, inbound_detectors: false }
|
||||
- host: production.cloudfront.docker.com
|
||||
dlp: { outbound_detectors: false, inbound_detectors: false }
|
||||
# GHCR: registry + blob CDN.
|
||||
- host: ghcr.io
|
||||
preserve_auth: true
|
||||
dlp: { outbound_detectors: false, inbound_detectors: false }
|
||||
- host: pkg-containers.githubusercontent.com
|
||||
dlp: { outbound_detectors: false, inbound_detectors: false }
|
||||
# quay.io: registry + blob CDNs. No preserve_auth needed for public pulls.
|
||||
- host: quay.io
|
||||
dlp: { outbound_detectors: false, inbound_detectors: false }
|
||||
- host: cdn01.quay.io
|
||||
dlp: { outbound_detectors: false, inbound_detectors: false }
|
||||
- host: cdn02.quay.io
|
||||
dlp: { outbound_detectors: false, inbound_detectors: false }
|
||||
- host: cdn03.quay.io
|
||||
dlp: { outbound_detectors: false, inbound_detectors: false }
|
||||
```
|
||||
|
||||
`mcr.microsoft.com` and `registry.k8s.io` follow the same shape and also
|
||||
redirect blobs elsewhere (`*.data.mcr.microsoft.com` and
|
||||
`us-*-docker.pkg.dev` respectively); route whichever host the 403 names.
|
||||
|
||||
Inside a nested container the same allowlist applies: an allowlisted host
|
||||
returns 200 and anything else gets a 403 straight from the proxy. The
|
||||
gateway's CA bundle and proxy settings are wired in automatically, so
|
||||
`docker run … curl https://…` works with no extra flags — no `--add-host`,
|
||||
`-e`, or `-v`.
|
||||
|
||||
Two things worth knowing when testing that:
|
||||
|
||||
- Public DNS inside a nested container fails **by design**. Everything
|
||||
egresses through the proxy, so `nslookup` failing is expected and is not
|
||||
evidence of a problem.
|
||||
- Alpine's BusyBox `wget` drops the connection after the proxy's TLS
|
||||
interception and reports `error getting response`, even though the proxy
|
||||
logs the decrypted request and returns a response. Use `curl` to test
|
||||
egress; BusyBox `wget` will lie to you.
|
||||
|
||||
### Firecracker on Linux
|
||||
|
||||
On Linux, a KVM-capable host defaults to the Firecracker backend. It needs:
|
||||
|
||||
@@ -302,11 +302,6 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
|
||||
|
||||
name: str
|
||||
|
||||
# Whether this backend can run a container engine *inside* the bottle.
|
||||
# Backends that cannot must reject `nested_containers: true` rather than
|
||||
# reach for a host daemon socket (issue #392).
|
||||
supports_nested_containers: bool = False
|
||||
|
||||
def prepare(self, spec: BottleSpec, stage_dir: Path) -> PlanT:
|
||||
"""Template method: run cross-backend host-side validation, then
|
||||
delegate to the subclass's `_resolve_plan` for the
|
||||
@@ -320,16 +315,12 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
|
||||
prepare_egress,
|
||||
prepare_git_gate,
|
||||
prepare_supervise,
|
||||
reject_nested_containers,
|
||||
resolve_manifest_dockerfile,
|
||||
write_launch_metadata,
|
||||
)
|
||||
|
||||
manifest = self._validate(spec)
|
||||
|
||||
if not self.supports_nested_containers:
|
||||
reject_nested_containers(self.name, manifest)
|
||||
|
||||
self._preflight()
|
||||
|
||||
from ..git_gate_host_key import preflight_host_keys
|
||||
|
||||
@@ -7,10 +7,13 @@ imports it rather than re-implementing it.
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import dataclasses
|
||||
|
||||
from ..egress import EgressPlan
|
||||
from ..git_gate import GitGatePlan
|
||||
from ..orchestrator.client import OrchestratorClient
|
||||
from ..orchestrator.client import OrchestratorClient, RegisteredBottle
|
||||
from ..orchestrator.registration import registration_inputs
|
||||
from ..orchestrator.secret_store import new_env_var_secret
|
||||
from .docker.gateway_provision import GatewayTransport, deprovision_git_gate, provision_git_gate
|
||||
|
||||
|
||||
@@ -23,21 +26,26 @@ def provision_bottle(
|
||||
*,
|
||||
image_ref: str = "",
|
||||
tokens: dict[str, str] | None = None,
|
||||
):
|
||||
) -> RegisteredBottle:
|
||||
"""Register the bottle and provision its git-gate state. Rolls back the
|
||||
registration if provisioning fails so no orphan is left. Returns the
|
||||
`RegisteredBottle` from the orchestrator."""
|
||||
registration if provisioning fails so no orphan is left.
|
||||
|
||||
Generates a fresh ENV_VAR_SECRET, passes it to the orchestrator so it can
|
||||
encrypt the token values at rest, and stamps the secret onto the returned
|
||||
``RegisteredBottle`` so callers can inject it into the agent container's
|
||||
environment."""
|
||||
inputs = registration_inputs(egress_plan)
|
||||
env_var_secret = new_env_var_secret()
|
||||
reg = client.register_bottle(
|
||||
source_ip, image_ref=image_ref, policy=inputs.policy,
|
||||
metadata=inputs.metadata, tokens=tokens,
|
||||
metadata=inputs.metadata, tokens=tokens, env_var_secret=env_var_secret,
|
||||
)
|
||||
try:
|
||||
provision_git_gate(transport, reg.bottle_id, git_gate_plan)
|
||||
except Exception:
|
||||
client.teardown_bottle(reg.bottle_id)
|
||||
raise
|
||||
return reg
|
||||
return dataclasses.replace(reg, env_var_secret=env_var_secret)
|
||||
|
||||
|
||||
def teardown_consolidated(
|
||||
|
||||
@@ -39,6 +39,10 @@ class DockerBottlePlan(BottlePlan):
|
||||
# (egress proxy credentials, git-gate/supervise headers); set by launch
|
||||
# from the orchestrator registration. Empty pre-registration.
|
||||
identity_token: str = ""
|
||||
# Encryption key for the agent's stored egress secrets; injected into the
|
||||
# agent container as ENV_VAR_SECRET via the compose subprocess env (bare
|
||||
# name — value never written to the compose file). Empty pre-registration.
|
||||
env_var_secret: str = ""
|
||||
|
||||
@property
|
||||
def container_name(self) -> str:
|
||||
|
||||
@@ -17,6 +17,7 @@ from __future__ import annotations
|
||||
from typing import Any
|
||||
|
||||
from ...egress import egress_agent_env_entries
|
||||
from ...orchestrator.secret_store import ENV_VAR_SECRET_NAME
|
||||
from ..util import AGENT_CA_BUNDLE, AGENT_CA_PATH
|
||||
from .bottle_plan import DockerBottlePlan
|
||||
from .egress import EGRESS_PORT
|
||||
@@ -58,6 +59,10 @@ def consolidated_agent_compose(
|
||||
# the secret value never lands on argv or in the compose file.
|
||||
for name in sorted(plan.forwarded_env.keys()):
|
||||
env.append(name)
|
||||
# ENV_VAR_SECRET: bare name so the value comes from the compose subprocess
|
||||
# env (set in launch.py) and is never written to the compose file on disk.
|
||||
if getattr(plan, "env_var_secret", ""):
|
||||
env.append(ENV_VAR_SECRET_NAME)
|
||||
env.extend(egress_agent_env_entries(plan.egress_plan))
|
||||
|
||||
service: dict[str, Any] = {
|
||||
|
||||
@@ -15,12 +15,14 @@ from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
|
||||
from ... import log
|
||||
from ...docker_cmd import run_docker
|
||||
from ...egress import EgressPlan
|
||||
from ...git_gate import GitGatePlan
|
||||
from ...orchestrator.client import OrchestratorClient
|
||||
from ...orchestrator.gateway import GATEWAY_NETWORK
|
||||
from ...orchestrator.lifecycle import INFRA_NAME, OrchestratorService
|
||||
from ...orchestrator.secret_store import ENV_VAR_SECRET_NAME
|
||||
from ..consolidated_util import provision_bottle
|
||||
from ..consolidated_util import teardown_consolidated as _teardown_util
|
||||
from .gateway_provision import DockerGatewayTransport
|
||||
@@ -41,6 +43,7 @@ class LaunchContext:
|
||||
network: str # the shared gateway network to attach to
|
||||
gateway_ip: str # the gateway's address — the agent's proxy target
|
||||
orchestrator_url: str
|
||||
env_var_secret: str = "" # encryption key injected into the agent's env
|
||||
|
||||
|
||||
def _network_cidr(network: str) -> str:
|
||||
@@ -85,6 +88,66 @@ def _network_container_ips(network: str) -> list[str]:
|
||||
return ips
|
||||
|
||||
|
||||
def _reprovision_running_bottles(
|
||||
orchestrator_url: str,
|
||||
network: str = GATEWAY_NETWORK,
|
||||
infra_name: str = INFRA_NAME,
|
||||
) -> None:
|
||||
"""Re-inject egress tokens for any registered bottles that lost their
|
||||
in-memory tokens (e.g., after an infra container restart).
|
||||
|
||||
For each registered bottle whose source IP maps to a live container on the
|
||||
gateway network, reads ENV_VAR_SECRET via ``docker exec … printenv`` and
|
||||
calls ``POST /bottles/<id>/reprovision_gateway``. Idempotent — a no-op
|
||||
when the orchestrator already has all tokens loaded. Best-effort: a single
|
||||
container exec failure never blocks a new bottle launch."""
|
||||
client = OrchestratorClient(orchestrator_url)
|
||||
bottles = client.list_bottles()
|
||||
if not bottles:
|
||||
return
|
||||
|
||||
# Build {source_ip: container_name} from live containers on the gateway
|
||||
# network, excluding the infra container itself.
|
||||
proc = run_docker([
|
||||
"docker", "network", "inspect",
|
||||
"--format", "{{range .Containers}}{{.Name}} {{.IPv4Address}}\n{{end}}",
|
||||
network,
|
||||
])
|
||||
ip_to_container: dict[str, str] = {}
|
||||
for line in proc.stdout.splitlines():
|
||||
parts = line.strip().split()
|
||||
if len(parts) >= 2 and parts[0] != infra_name:
|
||||
ip = parts[1].split("/", 1)[0]
|
||||
if ip:
|
||||
ip_to_container[ip] = parts[0]
|
||||
|
||||
reprovisioned = 0
|
||||
for bottle in bottles:
|
||||
bottle_id = bottle.get("bottle_id")
|
||||
source_ip = bottle.get("source_ip")
|
||||
if not isinstance(bottle_id, str) or not isinstance(source_ip, str):
|
||||
continue
|
||||
container_name = ip_to_container.get(source_ip)
|
||||
if not container_name:
|
||||
continue
|
||||
proc = run_docker(
|
||||
["docker", "exec", container_name, "printenv", ENV_VAR_SECRET_NAME]
|
||||
)
|
||||
if proc.returncode != 0 or not proc.stdout.strip():
|
||||
continue
|
||||
try:
|
||||
if client.reprovision_gateway(bottle_id, proc.stdout.strip()):
|
||||
reprovisioned += 1
|
||||
except Exception: # noqa: BLE001 — best-effort, never block a launch
|
||||
pass
|
||||
|
||||
if reprovisioned:
|
||||
log.info(
|
||||
"reprovisioned egress tokens",
|
||||
context={"count": reprovisioned},
|
||||
)
|
||||
|
||||
|
||||
def launch_consolidated(
|
||||
egress_plan: EgressPlan,
|
||||
git_gate_plan: GitGatePlan,
|
||||
@@ -96,9 +159,14 @@ def launch_consolidated(
|
||||
network: str = GATEWAY_NETWORK,
|
||||
) -> LaunchContext:
|
||||
"""Ensure the infra container is up, allocate + register the bottle, and
|
||||
provision its git-gate state. Returns the agent's attach context."""
|
||||
provision its git-gate state. Returns the agent's attach context.
|
||||
|
||||
Also reprovisiones egress tokens for any already-running bottles that lost
|
||||
their in-memory credentials (e.g. after an infra container restart), so
|
||||
they regain egress access before the new bottle is registered."""
|
||||
service = service or OrchestratorService()
|
||||
url = service.ensure_running()
|
||||
_reprovision_running_bottles(url, network=network, infra_name=infra_name)
|
||||
client = OrchestratorClient(url)
|
||||
|
||||
cidr = _network_cidr(network)
|
||||
@@ -117,6 +185,7 @@ def launch_consolidated(
|
||||
network=network,
|
||||
gateway_ip=gateway_ip,
|
||||
orchestrator_url=url,
|
||||
env_var_secret=reg.env_var_secret,
|
||||
)
|
||||
|
||||
|
||||
|
||||
@@ -186,6 +186,7 @@ def launch(
|
||||
agent_git_gate_url=git_gate_url,
|
||||
agent_supervise_url=supervise_url,
|
||||
identity_token=ctx.identity_token,
|
||||
env_var_secret=ctx.env_var_secret,
|
||||
)
|
||||
|
||||
# Step 5: render + up the agent-only compose, pinned on the shared
|
||||
@@ -198,7 +199,12 @@ def launch(
|
||||
project = compose_project_name(plan.slug)
|
||||
# Forwarded vars (OAuth token, host interpolations) flow through the
|
||||
# subprocess env as bare names so values never land in the file.
|
||||
# ENV_VAR_SECRET follows the same pattern: bare name in the compose
|
||||
# spec, value only in the subprocess env so it is never written to disk.
|
||||
compose_env: dict[str, str] = {**os.environ, **plan.forwarded_env}
|
||||
if plan.env_var_secret:
|
||||
from ...orchestrator.secret_store import ENV_VAR_SECRET_NAME
|
||||
compose_env[ENV_VAR_SECRET_NAME] = plan.env_var_secret
|
||||
info(
|
||||
f"docker compose up -d (project {project}, agent on shared "
|
||||
f"gateway {ctx.gateway_ip}, ip {ctx.source_ip})"
|
||||
|
||||
@@ -50,6 +50,7 @@ class LaunchContext:
|
||||
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
|
||||
env_var_secret: str = "" # encryption key injected into the agent's env
|
||||
|
||||
|
||||
def launch_consolidated(
|
||||
@@ -80,6 +81,7 @@ def launch_consolidated(
|
||||
source_ip=guest_ip,
|
||||
gateway_ca_pem=infra.gateway_ca_pem(),
|
||||
orchestrator_url=url,
|
||||
env_var_secret=reg.env_var_secret,
|
||||
)
|
||||
|
||||
|
||||
|
||||
@@ -31,7 +31,6 @@ class MacosContainerBottleBackend(
|
||||
`--backend=macos-container`."""
|
||||
|
||||
name = "macos-container"
|
||||
supports_nested_containers = True
|
||||
|
||||
@classmethod
|
||||
def is_available(cls) -> bool:
|
||||
|
||||
@@ -20,9 +20,6 @@ class MacosContainerBottlePlan(BottlePlan):
|
||||
# bottle is registered. See launch.py's stamp for why it lives here and not
|
||||
# only in the exec-time proxy env.
|
||||
identity_token: str = ""
|
||||
# Guest-local container engine (issue #392). Gates the derived image, the
|
||||
# device-mode relaxation, and the resident podman service.
|
||||
nested_containers: bool = False
|
||||
|
||||
@property
|
||||
def container_name(self) -> str:
|
||||
|
||||
@@ -72,6 +72,7 @@ class LaunchContext:
|
||||
gateway_ip: str
|
||||
network: str
|
||||
orchestrator_url: str
|
||||
env_var_secret: str = "" # encryption key injected into the agent's env
|
||||
|
||||
|
||||
def ensure_gateway(
|
||||
@@ -152,6 +153,7 @@ def register_agent(
|
||||
gateway_ip=endpoint.gateway_ip,
|
||||
network=endpoint.network,
|
||||
orchestrator_url=endpoint.orchestrator_url,
|
||||
env_var_secret=reg.env_var_secret,
|
||||
)
|
||||
|
||||
|
||||
|
||||
@@ -66,7 +66,6 @@ from .gateway_hosts import (
|
||||
refresh_gateway_host,
|
||||
set_gateway_host,
|
||||
)
|
||||
from . import nested_containers as nested_containers_mod
|
||||
from .bottle_plan import MacosContainerBottlePlan
|
||||
from ...orchestrator.config_store import resolve_teardown_timeout
|
||||
from .consolidated_launch import (
|
||||
@@ -83,14 +82,10 @@ _AGENT_SLEEP_SECONDS = "2147483647"
|
||||
def build_or_load_images(plan: MacosContainerBottlePlan) -> BottleImages:
|
||||
"""Resolve the agent image ref for this plan. The gateway's own image is
|
||||
built by `ensure_gateway` — it belongs to the shared singleton."""
|
||||
return BottleImages(agent=_layer_nested_containers(plan, _agent_image(plan)))
|
||||
|
||||
|
||||
def _agent_image(plan: MacosContainerBottlePlan) -> str:
|
||||
committed = read_committed_image(plan.slug)
|
||||
if committed and container_mod.image_exists(committed):
|
||||
info(f"using committed image {committed!r}")
|
||||
return committed
|
||||
return BottleImages(agent=committed)
|
||||
if plan.spec.image_policy == "cached":
|
||||
if not container_mod.image_exists(plan.image):
|
||||
die(
|
||||
@@ -98,31 +93,9 @@ def _agent_image(plan: MacosContainerBottlePlan) -> str:
|
||||
"run without --cached-images to build it"
|
||||
)
|
||||
info(f"using cached agent image {plan.image!r}")
|
||||
return plan.image
|
||||
return BottleImages(agent=plan.image)
|
||||
container_mod.build_image(plan.image, _REPO_DIR, dockerfile=plan.dockerfile_path)
|
||||
return plan.image
|
||||
|
||||
|
||||
def _layer_nested_containers(
|
||||
plan: MacosContainerBottlePlan, agent_image: str,
|
||||
) -> str:
|
||||
"""Add the guest-local container tooling on top of the agent image.
|
||||
|
||||
A separate derived tag, not the provider Dockerfile, so bottles that never
|
||||
ask for nested containers carry none of its weight.
|
||||
"""
|
||||
if not plan.nested_containers:
|
||||
return agent_image
|
||||
derived = f"{agent_image}{nested_containers_mod.IMAGE_SUFFIX}"
|
||||
if plan.spec.image_policy == "cached":
|
||||
if not container_mod.image_exists(derived):
|
||||
die(
|
||||
f"cached nested-container image {derived!r} not found; "
|
||||
"run without --cached-images to build it"
|
||||
)
|
||||
info(f"using cached nested-container image {derived!r}")
|
||||
return derived
|
||||
return nested_containers_mod.build_image(agent_image, container_mod.build_image)
|
||||
return BottleImages(agent=plan.image)
|
||||
|
||||
|
||||
@contextmanager
|
||||
@@ -223,10 +196,6 @@ def launch(
|
||||
# token above, so — unlike the run-time env — the plan CAN carry it.
|
||||
plan = dataclasses.replace(plan, identity_token=ctx.identity_token)
|
||||
|
||||
exec_env = {
|
||||
**_identity_proxy_env(endpoint, ctx.identity_token),
|
||||
**nested_containers_mod.guest_env(plan.nested_containers),
|
||||
}
|
||||
bottle = MacosContainerBottle(
|
||||
plan.container_name,
|
||||
teardown,
|
||||
@@ -240,16 +209,10 @@ def launch(
|
||||
),
|
||||
terminal_color=plan.spec.color,
|
||||
agent_workdir=plan.workspace_plan.workdir,
|
||||
exec_env=exec_env,
|
||||
exec_env=_identity_proxy_env(endpoint, ctx.identity_token),
|
||||
)
|
||||
bottle.prompt_path = provision(plan, bottle)
|
||||
|
||||
if plan.nested_containers:
|
||||
nested_containers_mod.prepare_guest_devices(
|
||||
plan.container_name, container_mod.exec_container_as_root,
|
||||
)
|
||||
nested_containers_mod.start(bottle)
|
||||
|
||||
yield bottle
|
||||
finally:
|
||||
teardown()
|
||||
|
||||
@@ -1,210 +0,0 @@
|
||||
#!/bin/sh
|
||||
set -eu
|
||||
|
||||
uid="$(id -u)"
|
||||
if [ "$uid" -eq 0 ]; then
|
||||
echo "refusing to run the guest container engine as root" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Every piece of podman 5's networking stack is checked here, because each
|
||||
# one fails at a different and misleading layer if it is absent: no pasta and
|
||||
# nothing starts at all; no nft and netavark cannot build the bridge every
|
||||
# compose file expects; no aardvark-dns and DNS inside nested containers fails
|
||||
# while everything else looks healthy.
|
||||
for command in podman docker fuse-overlayfs pasta nft slirp4netns; do
|
||||
command -v "$command" >/dev/null 2>&1 || {
|
||||
echo "missing nested-container prerequisite: $command" >&2
|
||||
exit 1
|
||||
}
|
||||
done
|
||||
|
||||
# The inverse of the rootless-Docker check, and the whole point of the podman
|
||||
# variant: a subordinate range would push podman onto newuidmap, which cannot
|
||||
# write a multi-range uid_map without CAP_SYS_ADMIN in this guest. An empty
|
||||
# range keeps it on the single-UID self-mapping an unprivileged process may
|
||||
# write itself.
|
||||
if grep -q "^$(id -un):" /etc/subuid 2>/dev/null; then
|
||||
echo "unexpected subordinate UID range for $(id -un): podman would" >&2
|
||||
echo "require CAP_SYS_ADMIN via newuidmap in this guest" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
for device in /dev/fuse /dev/net/tun; do
|
||||
[ -r "$device" ] && [ -w "$device" ] || {
|
||||
echo "device $device is not readable/writable by $(id -un)" >&2
|
||||
exit 1
|
||||
}
|
||||
done
|
||||
|
||||
# Short by necessity, not by accident: conmon's attach socket lives under
|
||||
# this directory and must fit in a 108-byte sun_path. See nested_containers.py.
|
||||
# Must stay in step with AGENT_CA_BUNDLE in bot_bottle/backend/util.py; a unit
|
||||
# test pins the two together.
|
||||
CA_BUNDLE="/etc/ssl/certs/ca-certificates.crt"
|
||||
[ -r "$CA_BUNDLE" ] || {
|
||||
echo "gateway CA bundle $CA_BUNDLE is missing or unreadable" >&2
|
||||
exit 1
|
||||
}
|
||||
|
||||
# The proxy URL the agent inherits names `bot-bottle-gateway`, which resolves
|
||||
# only through this bottle's /etc/hosts. A nested container gets its own hosts
|
||||
# file, so it cannot resolve the name and dies at "Could not resolve proxy".
|
||||
#
|
||||
# podman's containers.conf `hosts_file` would fix that, except the
|
||||
# Docker-compatible API ignores it — it only takes effect for native
|
||||
# `podman run`, and the agent types `docker`. So the name is resolved *here*
|
||||
# and the address, not the name, goes into the proxy URL the nested container
|
||||
# receives. Verified on macOS 26 / podman 5.4.2: with the address in place,
|
||||
# https://quay.io returns 200 and a non-allowlisted host still gets 403, so
|
||||
# the egress boundary applies inside nested containers too.
|
||||
GATEWAY_NAME="bot-bottle-gateway"
|
||||
gateway_ip="$(
|
||||
awk -v name="$GATEWAY_NAME" '$2 == name { print $1; exit }' /etc/hosts
|
||||
)"
|
||||
[ -n "$gateway_ip" ] || {
|
||||
echo "no /etc/hosts entry for $GATEWAY_NAME; the gateway address is" >&2
|
||||
echo "needed so nested containers can reach the egress proxy" >&2
|
||||
exit 1
|
||||
}
|
||||
|
||||
export XDG_RUNTIME_DIR="${XDG_RUNTIME_DIR:-/tmp/bbp}"
|
||||
config="$HOME/.config/containers"
|
||||
mkdir -p "$XDG_RUNTIME_DIR" "$config"
|
||||
chmod 700 "$XDG_RUNTIME_DIR"
|
||||
|
||||
# ignore_chown_errors is required, not incidental: with a single-UID mapping
|
||||
# there is no second UID for image layers to be chowned to, so layers that
|
||||
# record other owners would otherwise fail to extract.
|
||||
cat > "$config/storage.conf" <<'CONF'
|
||||
[storage]
|
||||
driver="overlay"
|
||||
[storage.options.overlay]
|
||||
mount_program="/usr/bin/fuse-overlayfs"
|
||||
ignore_chown_errors="true"
|
||||
CONF
|
||||
|
||||
# No cgroup delegation reaches this guest, so asking podman to manage cgroups
|
||||
# fails; events_logger=file avoids the journald socket that is equally absent.
|
||||
#
|
||||
# The rest of this config is what lets a nested container reach the network:
|
||||
#
|
||||
# hosts_file only takes effect for native `podman run` — the
|
||||
# Docker-compatible API ignores it, and the agent types
|
||||
# `docker`. Kept anyway because it costs nothing and makes
|
||||
# podman-native use behave; the compat path is covered by the
|
||||
# address-bearing proxy URL below.
|
||||
# volumes/env the gateway TLS-intercepts, so a container that does not
|
||||
# trust the bottle's CA bundle gets "unable to get local issuer
|
||||
# certificate". Mounting the bundle read-only and pointing the
|
||||
# usual env vars at it covers curl, wget, python, and node
|
||||
# without distro-specific trust commands.
|
||||
#
|
||||
# The proxy URL carries the bottle's identity token. podman already forwards
|
||||
# that same URL into every nested container from the agent's own environment,
|
||||
# so writing it to a 0600 file inside this disposable VM hands it to nobody
|
||||
# new. It is never echoed.
|
||||
CA_BUNDLE="$CA_BUNDLE" GATEWAY_NAME="$GATEWAY_NAME" GATEWAY_IP="$gateway_ip" \
|
||||
CONTAINERS_CONF="$config/containers.conf" python3 - <<'PY'
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
ca = os.environ["CA_BUNDLE"]
|
||||
name = os.environ["GATEWAY_NAME"]
|
||||
ip = os.environ["GATEWAY_IP"]
|
||||
|
||||
entries = [
|
||||
f"SSL_CERT_FILE={ca}",
|
||||
f"CURL_CA_BUNDLE={ca}",
|
||||
f"REQUESTS_CA_BUNDLE={ca}",
|
||||
f"NODE_EXTRA_CA_CERTS={ca}",
|
||||
]
|
||||
# The gateway name resolves only through the bottle's /etc/hosts, which a
|
||||
# nested container does not inherit, so hand it the address instead.
|
||||
for var in ("HTTP_PROXY", "HTTPS_PROXY", "http_proxy", "https_proxy"):
|
||||
value = os.environ.get(var)
|
||||
if value:
|
||||
entries.append(f"{var}={value.replace(name, ip)}")
|
||||
# NO_PROXY keeps the name: it is matched against what a client asks for, and
|
||||
# code inside a nested container still says "bot-bottle-gateway".
|
||||
for var in ("NO_PROXY", "no_proxy"):
|
||||
value = os.environ.get(var)
|
||||
if value:
|
||||
entries.append(f"{var}={value}")
|
||||
|
||||
path = Path(os.environ["CONTAINERS_CONF"])
|
||||
path.write_text("\n".join([
|
||||
"[containers]",
|
||||
'cgroups="disabled"',
|
||||
# podman copies the host's proxy vars into every container by default,
|
||||
# and that copy *wins* over the env below — putting the unresolvable
|
||||
# gateway name back. Turn it off so the address-bearing URLs stand.
|
||||
"http_proxy=false",
|
||||
'hosts_file="/etc/hosts"',
|
||||
f'volumes=["{ca}:{ca}:ro"]',
|
||||
"env=[",
|
||||
*[f' "{entry}",' for entry in entries],
|
||||
"]",
|
||||
"[engine]",
|
||||
'cgroup_manager="cgroupfs"',
|
||||
'events_logger="file"',
|
||||
"",
|
||||
]), encoding="utf-8")
|
||||
path.chmod(0o600)
|
||||
PY
|
||||
|
||||
# Registry pulls egress through the bottle's proxy like everything else. The
|
||||
# token-bearing proxy URL is already in the agent's environment; persisting it
|
||||
# inside this disposable VM does not broaden its authority.
|
||||
#
|
||||
# This file is also what the Docker CLI copies into every container it starts,
|
||||
# and being client-side it beats anything the podman service does — it is why
|
||||
# containers.conf `env`, `http_proxy=false`, and the service's own environment
|
||||
# all failed to change what a nested container saw. The address goes in here
|
||||
# for the same reason it goes everywhere else: `bot-bottle-gateway` resolves
|
||||
# in the bottle, never inside a nested container.
|
||||
GATEWAY_NAME="$GATEWAY_NAME" GATEWAY_IP="$gateway_ip" python3 - <<'PY'
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
name = os.environ["GATEWAY_NAME"]
|
||||
ip = os.environ["GATEWAY_IP"]
|
||||
|
||||
proxy = os.environ.get("HTTPS_PROXY") or os.environ.get("https_proxy", "")
|
||||
# NO_PROXY keeps the name: it is matched against what a client asks for, and
|
||||
# code inside a nested container still says "bot-bottle-gateway".
|
||||
no_proxy = os.environ.get("NO_PROXY") or os.environ.get("no_proxy", "")
|
||||
config = {"proxies": {"default": {
|
||||
"httpProxy": proxy.replace(name, ip),
|
||||
"httpsProxy": proxy.replace(name, ip),
|
||||
"noProxy": no_proxy,
|
||||
}}}
|
||||
path = Path.home() / ".docker" / "config.json"
|
||||
path.parent.mkdir(parents=True, exist_ok=True)
|
||||
path.write_text(json.dumps(config), encoding="utf-8")
|
||||
path.chmod(0o600)
|
||||
PY
|
||||
|
||||
if docker info >/dev/null 2>&1; then
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# Belt to the ~/.docker/config.json braces above, which is what actually
|
||||
# decides this for `docker run`. The service environment is what podman falls
|
||||
# back to for anything the CLI does not stamp — its own registry pulls, and
|
||||
# containers created through the API by something other than the Docker CLI.
|
||||
# Cheap, and it keeps the address consistent across both paths.
|
||||
#
|
||||
# Assigned via parameter expansion, never echoed: these carry the bottle's
|
||||
# identity token.
|
||||
for var in HTTP_PROXY HTTPS_PROXY http_proxy https_proxy; do
|
||||
eval "value=\${$var:-}"
|
||||
[ -n "$value" ] || continue
|
||||
eval "export $var=\"\${value%%$GATEWAY_NAME*}$gateway_ip\${value#*$GATEWAY_NAME}\""
|
||||
done
|
||||
|
||||
log=/tmp/bot-bottle-nested-containers.log
|
||||
nohup podman system service --time=0 \
|
||||
"unix://$XDG_RUNTIME_DIR/podman.sock" \
|
||||
>"$log" 2>&1 </dev/null &
|
||||
@@ -1,162 +0,0 @@
|
||||
"""Guest-local container engine for Apple-container bottles (issue #392).
|
||||
|
||||
The service and every nested container remain inside the existing per-bottle
|
||||
VM. This module refuses to compensate for missing prerequisites with outer
|
||||
capabilities, a privileged container, or a host Docker socket.
|
||||
|
||||
Podman is used rather than rootless Docker for one specific reason: Apple
|
||||
Container's capability bounding set omits `CAP_SYS_ADMIN`, which the kernel
|
||||
requires to write a multi-range `uid_map` via `newuidmap`. Rootless Docker
|
||||
has no path that avoids that write. Podman does — with no subordinate UID
|
||||
range configured it falls back to a single-UID self-mapping, which an
|
||||
unprivileged process may write itself. See
|
||||
`docs/research/rootless-docker-in-apple-container-spike.md`.
|
||||
|
||||
That fallback is why `build_image` *removes* the agent user's `/etc/subuid`
|
||||
and `/etc/subgid` entries instead of adding them: their presence is precisely
|
||||
what would send podman down the `newuidmap` path that cannot work here.
|
||||
|
||||
The agent still talks to `docker` and `docker compose`; those speak to
|
||||
podman's Docker-compatible API socket, so nothing in the agent's habits
|
||||
changes.
|
||||
|
||||
Nested containers run *within* the bottle boundary, not inside a new one: the
|
||||
single-UID mapping means `root` in a nested container is the agent user
|
||||
outside it. This is for build and test workloads, not for sandboxing
|
||||
untrusted code.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import shlex
|
||||
import shutil
|
||||
import tempfile
|
||||
import time
|
||||
from pathlib import Path
|
||||
from typing import Callable
|
||||
|
||||
from ...log import die, info
|
||||
|
||||
_INIT = "/usr/local/libexec/bot-bottle/nested-containers-init"
|
||||
# Deliberately cryptic and short. podman derives conmon's attach socket as
|
||||
# `$XDG_RUNTIME_DIR/libpod/tmp/socket/<64-hex-id>/attach`, and a Unix socket
|
||||
# path may not exceed 108 bytes (`sun_path`). The descriptive
|
||||
# `/tmp/bot-bottle-podman-run` produced a 116-byte path — over the limit, so
|
||||
# attach would have broken as soon as anything got far enough to attach. Do
|
||||
# not lengthen this for readability; it buys 8 bytes of headroom.
|
||||
_RUNTIME_DIR = "/tmp/bbp"
|
||||
_SOCKET = f"{_RUNTIME_DIR}/podman.sock"
|
||||
_LOG = "/tmp/bot-bottle-nested-containers.log"
|
||||
IMAGE_SUFFIX = "-nested-containers"
|
||||
READY_RETRIES = 30
|
||||
|
||||
# Apple Container creates both device nodes 0600 root:root, so the agent user
|
||||
# cannot open them: /dev/fuse blocks the fuse-overlayfs storage driver and
|
||||
# /dev/net/tun blocks slirp4netns, which rootless podman uses for the default
|
||||
# bridge network that stock compose files expect. Relaxing the modes needs no
|
||||
# capability the bottle does not already hold — unlike CAP_SYS_ADMIN, which is
|
||||
# what killed the rootless-Docker approach.
|
||||
_GUEST_DEVICES = ("/dev/fuse", "/dev/net/tun")
|
||||
|
||||
|
||||
def build_image(
|
||||
base_image: str,
|
||||
build: Callable[..., None],
|
||||
) -> str:
|
||||
"""Layer the nested-container tooling onto an already-built agent image.
|
||||
|
||||
Only what the flag is meant to gate lands here. Podman itself is already
|
||||
in every built-in agent image (issue #451); the storage/network helpers,
|
||||
the Docker CLI, and the compose plugin are the ~100MB this flag buys.
|
||||
"""
|
||||
image = f"{base_image}{IMAGE_SUFFIX}"
|
||||
init_script = Path(__file__).with_name("nested-containers-init.sh")
|
||||
with tempfile.TemporaryDirectory(prefix="bot-bottle-nested-containers.") as tmp:
|
||||
context = Path(tmp)
|
||||
shutil.copy2(init_script, context / "nested-containers-init.sh")
|
||||
(context / "Dockerfile").write_text(
|
||||
"FROM docker:28-cli AS docker_cli\n"
|
||||
f"FROM {base_image}\n"
|
||||
"USER root\n"
|
||||
"COPY --from=docker_cli /usr/local/bin/docker /usr/local/bin/docker\n"
|
||||
"COPY --from=docker_cli /usr/local/libexec/docker/cli-plugins/"
|
||||
"docker-compose /usr/local/libexec/docker/cli-plugins/docker-compose\n"
|
||||
"RUN apt-get update \\\n"
|
||||
# podman 5's networking stack, installed explicitly because the
|
||||
# base image's `--no-install-recommends` podman does not pull it
|
||||
# in and each piece fails at a different, misleading layer:
|
||||
# passt -> `pasta`, the default rootless netns helper
|
||||
# (podman 4 used slirp4netns); without it
|
||||
# nothing starts: "could not find pasta"
|
||||
# nftables -> `nft`, which netavark shells out to for the
|
||||
# bridge network every compose file expects
|
||||
# aardvark-dns -> name resolution *inside* nested containers;
|
||||
# without it DNS fails while everything else
|
||||
# looks healthy
|
||||
# slirp4netns stays as the documented fallback for pasta.
|
||||
" && apt-get install -y --no-install-recommends "
|
||||
"aardvark-dns fuse-overlayfs netavark nftables passt "
|
||||
"slirp4netns uidmap \\\n"
|
||||
" && rm -rf /var/lib/apt/lists/* \\\n"
|
||||
# Deliberate: an empty subordinate range keeps podman on the
|
||||
# single-UID mapping that needs no CAP_SYS_ADMIN. Adding ranges
|
||||
# here would reintroduce the newuidmap failure this design exists
|
||||
# to route around.
|
||||
" && sed -i '/^node:/d' /etc/subuid /etc/subgid\n"
|
||||
"COPY nested-containers-init.sh "
|
||||
"/usr/local/libexec/bot-bottle/nested-containers-init\n"
|
||||
"RUN chmod 0755 /usr/local/libexec/bot-bottle/nested-containers-init\n"
|
||||
"USER node\n",
|
||||
encoding="utf-8",
|
||||
)
|
||||
build(image, str(context), dockerfile=str(context / "Dockerfile"))
|
||||
return image
|
||||
|
||||
|
||||
def guest_env(enabled: bool) -> dict[str, str]:
|
||||
"""Environment consumed by the Docker CLI inside an enabled bottle."""
|
||||
if not enabled:
|
||||
return {}
|
||||
return {
|
||||
"DOCKER_HOST": f"unix://{_SOCKET}",
|
||||
"XDG_RUNTIME_DIR": _RUNTIME_DIR,
|
||||
}
|
||||
|
||||
|
||||
def prepare_guest_devices(container_name: str, exec_as_root: Callable[..., None]) -> None:
|
||||
"""Make /dev/fuse and /dev/net/tun openable by the agent user.
|
||||
|
||||
Runs as root inside the bottle because the agent must not be able to
|
||||
re-mode device nodes itself. No outer capability is involved.
|
||||
"""
|
||||
exec_as_root(
|
||||
container_name,
|
||||
["sh", "-c", f"chmod 0666 {' '.join(_GUEST_DEVICES)}"],
|
||||
)
|
||||
|
||||
|
||||
def start(bottle: object) -> None:
|
||||
"""Start and verify the unprivileged service through the bottle exec API."""
|
||||
info("starting guest-local container engine")
|
||||
result = bottle.exec(shlex.quote(_INIT)) # type: ignore[attr-defined]
|
||||
if result.returncode != 0:
|
||||
detail = (result.stderr or result.stdout or "").strip()
|
||||
die(f"nested-container bootstrap failed: {detail or '<no output>'}")
|
||||
|
||||
for _ in range(READY_RETRIES):
|
||||
result = bottle.exec("docker info >/dev/null 2>&1") # type: ignore[attr-defined]
|
||||
if result.returncode == 0:
|
||||
info("guest-local container engine is ready")
|
||||
return
|
||||
time.sleep(0.2)
|
||||
|
||||
logs = bottle.exec( # type: ignore[attr-defined]
|
||||
f"tail -n 80 {_LOG} 2>/dev/null || true"
|
||||
)
|
||||
die(
|
||||
"guest-local container engine did not become ready without additional "
|
||||
f"outer privileges:\n{(logs.stdout or logs.stderr or '<no log>').strip()}"
|
||||
)
|
||||
|
||||
|
||||
__all__ = ["build_image", "guest_env", "prepare_guest_devices", "start"]
|
||||
@@ -44,5 +44,4 @@ def resolve_plan(
|
||||
egress_plan=egress_plan,
|
||||
supervise_plan=supervise_plan,
|
||||
agent_provision=agent_provision_plan,
|
||||
nested_containers=manifest.bottle.nested_containers,
|
||||
)
|
||||
|
||||
@@ -26,7 +26,6 @@ from ..bottle_state import (
|
||||
)
|
||||
from ..egress import Egress, EgressPlan
|
||||
from ..git_gate import GitGate, GitGatePlan
|
||||
from ..log import die
|
||||
from ..manifest import Manifest, ManifestBottle
|
||||
from ..supervise import Supervise, SupervisePlan
|
||||
from . import BottleSpec
|
||||
@@ -113,22 +112,6 @@ def merge_provision_env_vars(provision: AgentProvisionPlan) -> AgentProvisionPla
|
||||
return replace(provision, guest_env=merged)
|
||||
|
||||
|
||||
def reject_nested_containers(backend: str, manifest: Manifest) -> None:
|
||||
"""Fail loudly when a backend cannot honor `nested_containers: true`.
|
||||
|
||||
Silently ignoring it would hand the agent a bottle where `docker` is not
|
||||
there — and the only sound alternatives on these backends (a host daemon
|
||||
socket, a privileged container) are exactly what issue #392 rules out.
|
||||
"""
|
||||
if not manifest.bottle.nested_containers:
|
||||
return
|
||||
die(
|
||||
f"nested_containers is not supported on the {backend} backend. "
|
||||
"Only macos-container runs a guest-local container engine today; "
|
||||
"mounting the host Docker socket is not an option bot-bottle offers."
|
||||
)
|
||||
|
||||
|
||||
def resolve_manifest_dockerfile(path_value: str, spec: BottleSpec) -> str:
|
||||
"""Resolve a manifest-supplied dockerfile path relative to user_cwd."""
|
||||
path = Path(os.path.expanduser(path_value))
|
||||
@@ -139,7 +122,6 @@ def resolve_manifest_dockerfile(path_value: str, spec: BottleSpec) -> str:
|
||||
|
||||
__all__ = [
|
||||
"merge_provision_env_vars",
|
||||
"reject_nested_containers",
|
||||
"mint_slug",
|
||||
"prepare_agent_state_dir",
|
||||
"prepare_egress",
|
||||
|
||||
@@ -524,8 +524,6 @@ def _manifest_to_yaml(manifest: Manifest) -> str:
|
||||
lines.append(f" scheme: {r.AuthScheme}")
|
||||
|
||||
lines.append(f" supervise: {'true' if bottle.supervise else 'false'}")
|
||||
if bottle.nested_containers:
|
||||
lines.append(" nested_containers: true")
|
||||
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
@@ -255,8 +255,6 @@ def _route_to_yaml_fields(r: Route) -> dict[str, object]:
|
||||
fields["matches"] = matches_data
|
||||
if r.git_fetch:
|
||||
fields["git"] = {"fetch": True}
|
||||
if r.preserve_auth:
|
||||
fields["preserve_auth"] = True
|
||||
if (
|
||||
r.outbound_detectors is not None
|
||||
or r.inbound_detectors is not None
|
||||
@@ -337,8 +335,6 @@ def egress_render_routes(
|
||||
lines.append(" git:")
|
||||
if git_dict.get("fetch") is True:
|
||||
lines.append(" fetch: true")
|
||||
if f.get("preserve_auth") is True:
|
||||
lines.append(" preserve_auth: true")
|
||||
if "dlp" in f:
|
||||
dlp_dict: dict[str, object] = f["dlp"] # type: ignore
|
||||
lines.append(" dlp:")
|
||||
|
||||
@@ -20,7 +20,6 @@ Bottle schema (frontmatter):
|
||||
egress: { routes: [ <egress-route>, ... ] }
|
||||
# route keys: host, matches, auth, role, dlp
|
||||
supervise: <bool> # optional (default true)
|
||||
nested_containers: <bool> # optional (default false)
|
||||
|
||||
Agent schema (frontmatter):
|
||||
bottle: <bottle-name> # required
|
||||
|
||||
@@ -44,11 +44,6 @@ class ManifestBottle:
|
||||
# daemon that exposes egress MCP tools to the agent. Set
|
||||
# `supervise: false` to skip the gateway.
|
||||
supervise: bool = True
|
||||
# Guest-local container engine (issue #392). Not a host-daemon grant:
|
||||
# backends implement it inside the bottle or reject it. Gated because it
|
||||
# costs image weight, a resident service, and relaxed guest device modes
|
||||
# that the majority of bottles never need.
|
||||
nested_containers: bool = False
|
||||
|
||||
@classmethod
|
||||
def from_dict(cls, name: str, raw: object) -> "ManifestBottle":
|
||||
@@ -128,15 +123,7 @@ class ManifestBottle:
|
||||
f"(was {type(supervise_raw).__name__})"
|
||||
)
|
||||
|
||||
nested_raw = d.get("nested_containers", False)
|
||||
if not isinstance(nested_raw, bool):
|
||||
raise ManifestError(
|
||||
f"bottle '{name}' nested_containers must be a boolean "
|
||||
f"(was {type(nested_raw).__name__})"
|
||||
)
|
||||
|
||||
return cls(
|
||||
env=env, agent_provider=agent_provider, git=git,
|
||||
git_user=git_user, egress=egress, supervise=supervise_raw,
|
||||
nested_containers=nested_raw,
|
||||
)
|
||||
|
||||
@@ -15,16 +15,7 @@ def merge_bottles_runtime(bottles: "list[ManifestBottle]") -> "ManifestBottle":
|
||||
the same field-merge rules as the file-based extends machinery:
|
||||
env: dict merge, later wins; git_user: per-field overlay, later
|
||||
wins on non-empty; git (repos): union by name, later wins; egress
|
||||
routes: concatenate; agent_provider, supervise: later
|
||||
replaces; nested_containers: OR (see below).
|
||||
|
||||
nested_containers is OR'd rather than replaced because these objects
|
||||
are already resolved: a bottle that never mentions the key is
|
||||
indistinguishable from one that sets it false, so "later replaces"
|
||||
would let any bottle composed after a container-enabled one silently
|
||||
drop the capability. The file-based `extends:` path still sees the
|
||||
raw keys, so there an explicit `nested_containers: false` in a child
|
||||
turns it back off.
|
||||
routes: concatenate; agent_provider, supervise: later replaces.
|
||||
"""
|
||||
if not bottles:
|
||||
raise ValueError("merge_bottles_runtime requires at least one bottle")
|
||||
@@ -63,7 +54,6 @@ def _merge_two_bottles_runtime(base: "ManifestBottle", override: "ManifestBottle
|
||||
git_user=merged_git_user,
|
||||
egress=merged_egress,
|
||||
supervise=override.supervise,
|
||||
nested_containers=base.nested_containers or override.nested_containers,
|
||||
)
|
||||
|
||||
|
||||
@@ -216,7 +206,6 @@ def _fold_two_bottles(
|
||||
git_user=merged_git_user,
|
||||
egress=merged_egress,
|
||||
supervise=later.supervise,
|
||||
nested_containers=earlier.nested_containers or later.nested_containers,
|
||||
), merged_repos_raw
|
||||
|
||||
|
||||
@@ -277,11 +266,6 @@ def _merge_bottles(
|
||||
merged_supervise = (
|
||||
child.supervise if "supervise" in child_raw else parent.supervise
|
||||
)
|
||||
merged_nested_containers = (
|
||||
child.nested_containers
|
||||
if "nested_containers" in child_raw
|
||||
else parent.nested_containers
|
||||
)
|
||||
validate_egress_routes(name, merged_egress.routes)
|
||||
|
||||
return ManifestBottle(
|
||||
@@ -291,7 +275,6 @@ def _merge_bottles(
|
||||
git_user=merged_git_user,
|
||||
egress=merged_egress,
|
||||
supervise=merged_supervise,
|
||||
nested_containers=merged_nested_containers,
|
||||
)
|
||||
|
||||
|
||||
|
||||
@@ -16,10 +16,7 @@ _FILENAME_RX = re.compile(r"^[a-z][a-z0-9-]*$")
|
||||
# sets dies with a "did you mean" pointer: typos should not silently
|
||||
# ghost into an empty config.
|
||||
BOTTLE_KEYS = frozenset(
|
||||
{
|
||||
"env", "extends", "agent_provider", "git-gate", "egress",
|
||||
"supervise", "nested_containers",
|
||||
}
|
||||
{"env", "extends", "agent_provider", "git-gate", "egress", "supervise"}
|
||||
)
|
||||
AGENT_KEYS_REQUIRED: frozenset[str] = frozenset()
|
||||
AGENT_KEYS_OPTIONAL = frozenset({"bottle", "skills", "git-gate"})
|
||||
|
||||
@@ -41,10 +41,13 @@ class OrchestratorClientError(RuntimeError):
|
||||
@dataclass(frozen=True)
|
||||
class RegisteredBottle:
|
||||
"""What `POST /bottles` returns: the minted bottle id and the per-bottle
|
||||
identity token the agent presents for app-layer attribution."""
|
||||
identity token the agent presents for app-layer attribution. `env_var_secret`
|
||||
is set by the caller (not from the server response) and carries the
|
||||
encryption key so it can be injected into the agent container's env."""
|
||||
|
||||
bottle_id: str
|
||||
identity_token: str
|
||||
env_var_secret: str = ""
|
||||
|
||||
|
||||
class OrchestratorClient:
|
||||
@@ -120,17 +123,21 @@ class OrchestratorClient:
|
||||
metadata: str = "",
|
||||
policy: str = "",
|
||||
tokens: dict[str, str] | None = None,
|
||||
env_var_secret: str = "",
|
||||
) -> RegisteredBottle:
|
||||
"""Register a bottle and broker its launch (`POST /bottles`). `tokens`
|
||||
are the per-bottle egress auth values (env_name -> value) the
|
||||
orchestrator holds in memory for the gateway to inject. Returns the
|
||||
minted id + identity token."""
|
||||
orchestrator holds in memory for the gateway to inject. When
|
||||
*env_var_secret* is provided, the orchestrator also encrypts the token
|
||||
values and stores them in ``bottled_agent_secrets`` for restart
|
||||
recovery. Returns the minted id + identity token."""
|
||||
payload = self._ok("POST", "/bottles", {
|
||||
"source_ip": source_ip,
|
||||
"image_ref": image_ref,
|
||||
"metadata": metadata,
|
||||
"policy": policy,
|
||||
"tokens": tokens or {},
|
||||
"env_var_secret": env_var_secret,
|
||||
})
|
||||
bottle_id = payload.get("bottle_id")
|
||||
token = payload.get("identity_token")
|
||||
@@ -138,6 +145,24 @@ class OrchestratorClient:
|
||||
raise OrchestratorClientError("register: response missing bottle_id/identity_token")
|
||||
return RegisteredBottle(bottle_id=bottle_id, identity_token=token)
|
||||
|
||||
def reprovision_gateway(self, bottle_id: str, env_var_secret: str) -> bool:
|
||||
"""Re-inject a bottle's egress tokens from its ENV_VAR_SECRET
|
||||
(`POST /bottles/<id>/reprovision_gateway`). Returns True when the
|
||||
orchestrator successfully decrypted and restored the tokens, False
|
||||
when it had no stored secrets for this bottle (404)."""
|
||||
status, _ = self._request(
|
||||
"POST",
|
||||
f"/bottles/{bottle_id}/reprovision_gateway",
|
||||
{"env_var_secret": env_var_secret},
|
||||
)
|
||||
if status == 404:
|
||||
return False
|
||||
if not 200 <= status < 300:
|
||||
raise OrchestratorClientError(
|
||||
f"reprovision_gateway {bottle_id}: HTTP {status}"
|
||||
)
|
||||
return True
|
||||
|
||||
def teardown_bottle(self, bottle_id: str) -> bool:
|
||||
"""Tear a bottle down (`DELETE /bottles/<id>`). False if the
|
||||
orchestrator didn't know it (404) — idempotent for cleanup paths."""
|
||||
|
||||
@@ -9,9 +9,13 @@ vsock / unix-socket portability caveats):
|
||||
GET /bottles -> 200 {"bottles": [ <redacted record>, ...]}
|
||||
POST /bottles -> 201 {"bottle_id","identity_token"} (launch)
|
||||
body: {"source_ip", ["image_ref"],
|
||||
["metadata"], ["policy"]}
|
||||
["metadata"], ["policy"],
|
||||
["tokens"], ["env_var_secret"]}
|
||||
PUT /bottles/<bottle_id>/policy -> 200 {"updated": true} | 404 (live reload)
|
||||
body: {"policy"}
|
||||
POST /bottles/<bottle_id>/reprovision_gateway
|
||||
-> 200 {"reprovisioned": true} | 404
|
||||
body: {"env_var_secret"}
|
||||
DELETE /bottles/<bottle_id> -> 200 {"torn_down": true} | 404 (teardown)
|
||||
POST /reconcile -> 200 {"reaped": [bottle_id, ...]}
|
||||
body: {"live_source_ips": [...],
|
||||
@@ -116,12 +120,14 @@ def dispatch( # pylint: disable=too-many-return-statements,too-many-branches
|
||||
tokens = {
|
||||
k: v for k, v in raw_tokens.items() if isinstance(k, str) and isinstance(v, str)
|
||||
} if isinstance(raw_tokens, dict) else {}
|
||||
env_var_secret = data.get("env_var_secret", "")
|
||||
rec = orch.launch_bottle(
|
||||
source_ip,
|
||||
image_ref=image_ref if isinstance(image_ref, str) else "",
|
||||
metadata=metadata if isinstance(metadata, str) else "",
|
||||
policy=policy if isinstance(policy, str) else "",
|
||||
tokens=tokens,
|
||||
env_var_secret=env_var_secret if isinstance(env_var_secret, str) else "",
|
||||
)
|
||||
return 201, {"bottle_id": rec.bottle_id, "identity_token": rec.identity_token}
|
||||
|
||||
@@ -138,6 +144,23 @@ def dispatch( # pylint: disable=too-many-return-statements,too-many-branches
|
||||
return 200, {"updated": True}
|
||||
return 404, {"error": "no such bottle"}
|
||||
|
||||
if (
|
||||
method == "POST"
|
||||
and route.startswith("/bottles/")
|
||||
and route.endswith("/reprovision_gateway")
|
||||
):
|
||||
bottle_id = route[len("/bottles/") : -len("/reprovision_gateway")]
|
||||
try:
|
||||
data = _parse_json_object(body)
|
||||
except ValueError as e:
|
||||
return 400, {"error": f"invalid JSON: {e}"}
|
||||
env_var_secret = data.get("env_var_secret")
|
||||
if not isinstance(env_var_secret, str) or not env_var_secret:
|
||||
return 400, {"error": "env_var_secret (string) is required"}
|
||||
if orch.reprovision_from_secret(bottle_id, env_var_secret):
|
||||
return 200, {"reprovisioned": True}
|
||||
return 404, {"error": "no stored secrets for this bottle"}
|
||||
|
||||
if method == "DELETE" and route.startswith("/bottles/"):
|
||||
bottle_id = route[len("/bottles/"):]
|
||||
if orch.teardown_bottle(bottle_id):
|
||||
|
||||
@@ -113,6 +113,22 @@ _MIGRATIONS = TableMigrations(
|
||||
# egress allowlist / routes / git config selected by source IP. The
|
||||
# multi-tenant gateway resolves it per request via `attribute`.
|
||||
"ALTER TABLE orchestrator_bottles ADD COLUMN policy TEXT NOT NULL DEFAULT ''",
|
||||
# v4 — per-bottle encrypted egress secrets (PRD prd-new-secret-provider).
|
||||
# One row per env-var: key (env-var name) is plaintext for auditing;
|
||||
# value is the encrypted token string. The encryption key (ENV_VAR_SECRET)
|
||||
# lives only in the agent's environment — a row alone cannot recover the
|
||||
# credential.
|
||||
"""
|
||||
CREATE TABLE IF NOT EXISTS bottled_agent_secrets (
|
||||
bottled_agent_id TEXT NOT NULL,
|
||||
key TEXT NOT NULL,
|
||||
value TEXT NOT NULL,
|
||||
type TEXT NOT NULL DEFAULT 'injected_env_var'
|
||||
)
|
||||
""",
|
||||
# v5 — index for fast per-bottle lookups and bulk DELETE on teardown.
|
||||
"CREATE INDEX IF NOT EXISTS idx_bottled_agent_secrets_id "
|
||||
"ON bottled_agent_secrets (bottled_agent_id, type)",
|
||||
],
|
||||
)
|
||||
|
||||
@@ -326,6 +342,57 @@ class RegistryStore(DbStore):
|
||||
return None
|
||||
return rec
|
||||
|
||||
# --- encrypted egress secret store ------------------------------------
|
||||
|
||||
def store_agent_secrets(
|
||||
self,
|
||||
bottle_id: str,
|
||||
encrypted_values: dict[str, str],
|
||||
secret_type: str = "injected_env_var",
|
||||
) -> None:
|
||||
"""Replace all stored secrets for *bottle_id* with *encrypted_values*
|
||||
(env-var name → encrypted ciphertext). Deletes then re-inserts so a
|
||||
re-registration is always consistent with the current token set."""
|
||||
with self._connection() as conn:
|
||||
conn.execute(
|
||||
"DELETE FROM bottled_agent_secrets "
|
||||
"WHERE bottled_agent_id = ? AND type = ?",
|
||||
(bottle_id, secret_type),
|
||||
)
|
||||
conn.executemany(
|
||||
"INSERT INTO bottled_agent_secrets "
|
||||
"(bottled_agent_id, key, value, type) VALUES (?, ?, ?, ?)",
|
||||
[(bottle_id, k, v, secret_type) for k, v in encrypted_values.items()],
|
||||
)
|
||||
self._chmod()
|
||||
|
||||
def get_agent_secrets(
|
||||
self,
|
||||
bottle_id: str,
|
||||
secret_type: str = "injected_env_var",
|
||||
) -> dict[str, str]:
|
||||
"""Return {env_var_name: encrypted_value} for *bottle_id*, or {} if none."""
|
||||
with self._connection() as conn:
|
||||
rows = conn.execute(
|
||||
"SELECT key, value FROM bottled_agent_secrets "
|
||||
"WHERE bottled_agent_id = ? AND type = ?",
|
||||
(bottle_id, secret_type),
|
||||
).fetchall()
|
||||
return {row[0]: row[1] for row in rows}
|
||||
|
||||
def delete_agent_secrets(
|
||||
self,
|
||||
bottle_id: str,
|
||||
secret_type: str = "injected_env_var",
|
||||
) -> None:
|
||||
"""Remove all stored secrets for *bottle_id* (e.g. on teardown)."""
|
||||
with self._connection() as conn:
|
||||
conn.execute(
|
||||
"DELETE FROM bottled_agent_secrets "
|
||||
"WHERE bottled_agent_id = ? AND type = ?",
|
||||
(bottle_id, secret_type),
|
||||
)
|
||||
|
||||
|
||||
__all__ = [
|
||||
"BottleRecord",
|
||||
|
||||
@@ -0,0 +1,94 @@
|
||||
"""Symmetric encryption for per-bottle egress secrets (PRD prd-new-secret-provider).
|
||||
|
||||
Each agent receives a random ENV_VAR_SECRET at startup — passed as an env var,
|
||||
never logged or persisted. The host uses this key to encrypt each egress auth
|
||||
token value before writing it to the bottled_agent_secrets table; the DB rows
|
||||
(ciphertext, plaintext env-var name) without the key are insufficient to
|
||||
recover the credentials.
|
||||
|
||||
On orchestrator restart the in-memory token map is lost. The host-side
|
||||
reattachment path reads ENV_VAR_SECRET from the running agent container via
|
||||
``docker exec … printenv ENV_VAR_SECRET`` and posts it to
|
||||
``POST /bottles/<id>/reprovision_gateway``; the orchestrator decrypts the
|
||||
stored rows and re-populates ``_tokens``.
|
||||
|
||||
Encryption scheme: HMAC-SHA256 used as a PRF in CTR mode (stdlib-only,
|
||||
no external deps). Each value is encrypted independently. The output blob is
|
||||
``nonce (16 bytes) || ciphertext`` encoded as URL-safe base64 (no padding).
|
||||
|
||||
keystream_block_i = HMAC-SHA256(key, nonce || i.to_bytes(4, "big"))
|
||||
ciphertext_i = plaintext_i XOR keystream_block_i[:len(plaintext_i)]
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import base64
|
||||
import hashlib
|
||||
import hmac
|
||||
import secrets
|
||||
|
||||
_KEY_BYTES = 32 # 256-bit key from ENV_VAR_SECRET
|
||||
_NONCE_BYTES = 16 # 128-bit random nonce per encrypt call
|
||||
_BLOCK = 32 # HMAC-SHA256 output width == one keystream block
|
||||
|
||||
# Env-var name the agent container receives at startup.
|
||||
ENV_VAR_SECRET_NAME = "ENV_VAR_SECRET"
|
||||
|
||||
|
||||
def new_env_var_secret() -> str:
|
||||
"""Generate a fresh ENV_VAR_SECRET: 32 random bytes as URL-safe base64."""
|
||||
return base64.urlsafe_b64encode(secrets.token_bytes(_KEY_BYTES)).rstrip(b"=").decode()
|
||||
|
||||
|
||||
def _b64dec(s: str) -> bytes:
|
||||
return base64.urlsafe_b64decode(s + "=" * (-len(s) % 4))
|
||||
|
||||
|
||||
def _keystream(key: bytes, nonce: bytes, block_index: int) -> bytes:
|
||||
return hmac.new(
|
||||
key, nonce + block_index.to_bytes(4, "big"), hashlib.sha256
|
||||
).digest()
|
||||
|
||||
|
||||
def encrypt_value(secret_b64: str, plaintext: str) -> str:
|
||||
"""Encrypt a single string value with *secret_b64* (the ENV_VAR_SECRET).
|
||||
|
||||
Returns a URL-safe base64 blob ``nonce || ciphertext`` suitable for
|
||||
the ``bottled_agent_secrets.value`` column."""
|
||||
key = _b64dec(secret_b64)
|
||||
pt = plaintext.encode()
|
||||
nonce = secrets.token_bytes(_NONCE_BYTES)
|
||||
ct = bytearray()
|
||||
for i in range(0, len(pt), _BLOCK):
|
||||
chunk = pt[i : i + _BLOCK]
|
||||
ks = _keystream(key, nonce, i)[: len(chunk)]
|
||||
ct.extend(p ^ k for p, k in zip(chunk, ks))
|
||||
return base64.urlsafe_b64encode(nonce + bytes(ct)).rstrip(b"=").decode()
|
||||
|
||||
|
||||
def decrypt_value(secret_b64: str, blob_b64: str) -> str:
|
||||
"""Decrypt a blob produced by :func:`encrypt_value`.
|
||||
|
||||
Returns the original plaintext string. Raises ``ValueError`` for malformed
|
||||
input or a key mismatch (wrong key produces garbage, not an error, unless
|
||||
the plaintext is non-UTF-8 — treat all such failures as wrong key)."""
|
||||
key = _b64dec(secret_b64)
|
||||
try:
|
||||
blob = _b64dec(blob_b64)
|
||||
except Exception as exc:
|
||||
raise ValueError(f"invalid ciphertext blob: {exc}") from exc
|
||||
if len(blob) < _NONCE_BYTES:
|
||||
raise ValueError("ciphertext blob too short")
|
||||
nonce, ciphertext = blob[:_NONCE_BYTES], blob[_NONCE_BYTES:]
|
||||
pt = bytearray()
|
||||
for i in range(0, len(ciphertext), _BLOCK):
|
||||
chunk = ciphertext[i : i + _BLOCK]
|
||||
ks = _keystream(key, nonce, i)[: len(chunk)]
|
||||
pt.extend(c ^ k for c, k in zip(chunk, ks))
|
||||
try:
|
||||
return bytes(pt).decode()
|
||||
except UnicodeDecodeError as exc:
|
||||
raise ValueError(f"decryption produced non-UTF-8 output (wrong key?): {exc}") from exc
|
||||
|
||||
|
||||
__all__ = ["ENV_VAR_SECRET_NAME", "new_env_var_secret", "encrypt_value", "decrypt_value"]
|
||||
@@ -87,13 +87,22 @@ class Orchestrator:
|
||||
metadata: str = "",
|
||||
policy: str = "",
|
||||
tokens: dict[str, str] | None = None,
|
||||
env_var_secret: str = "",
|
||||
) -> BottleRecord:
|
||||
"""Register a bottle (with its gateway policy + in-memory egress auth
|
||||
tokens) and broker its launch. Rolls the registry entry back if the
|
||||
launch doesn't take, so a failure leaves no orphan."""
|
||||
launch doesn't take, so a failure leaves no orphan.
|
||||
|
||||
When *env_var_secret* is provided alongside *tokens*, the token values
|
||||
are also encrypted and written to ``bottled_agent_secrets`` so they can
|
||||
survive an orchestrator restart (see ``reprovision_from_secret``)."""
|
||||
rec = self.registry.register(source_ip, metadata=metadata, policy=policy)
|
||||
if tokens:
|
||||
self._tokens[rec.bottle_id] = dict(tokens)
|
||||
if env_var_secret:
|
||||
from .secret_store import encrypt_value
|
||||
encrypted = {k: encrypt_value(env_var_secret, v) for k, v in tokens.items()}
|
||||
self.registry.store_agent_secrets(rec.bottle_id, encrypted)
|
||||
req = LaunchRequest(
|
||||
op="launch",
|
||||
bottle_id=rec.bottle_id,
|
||||
@@ -284,6 +293,26 @@ class Orchestrator:
|
||||
))
|
||||
return True, ""
|
||||
|
||||
# --- secret reprovision -----------------------------------------------
|
||||
|
||||
def reprovision_from_secret(self, bottle_id: str, env_var_secret: str) -> bool:
|
||||
"""Re-inject a bottle's egress tokens from its ENV_VAR_SECRET.
|
||||
|
||||
Reads the encrypted rows from ``bottled_agent_secrets``, decrypts each
|
||||
value with *env_var_secret*, and restores ``_tokens[bottle_id]``.
|
||||
Returns True on success, False when no stored secrets exist for this
|
||||
bottle or decryption fails (wrong key / corrupt data)."""
|
||||
from .secret_store import decrypt_value
|
||||
encrypted = self.registry.get_agent_secrets(bottle_id)
|
||||
if not encrypted:
|
||||
return False
|
||||
try:
|
||||
self._tokens[bottle_id] = {k: decrypt_value(env_var_secret, v)
|
||||
for k, v in encrypted.items()}
|
||||
except ValueError:
|
||||
return False
|
||||
return True
|
||||
|
||||
# --- consolidated gateway ----------------------------------------------
|
||||
|
||||
def ensure_gateway(self) -> None:
|
||||
|
||||
@@ -1,153 +0,0 @@
|
||||
# PRD prd-new: Containers inside a bottle
|
||||
|
||||
- **Status:** Draft
|
||||
- **Author:** Claude
|
||||
- **Created:** 2026-07-21
|
||||
- **Issue:** #392
|
||||
|
||||
## Summary
|
||||
|
||||
Let an agent run `docker` and `docker compose` *inside* its bottle by starting
|
||||
a guest-local rootless podman service that exposes a Docker-compatible API
|
||||
socket. Gated per bottle by `nested_containers: true`. No host daemon socket is
|
||||
mounted and no capability is added to the guest, on any backend.
|
||||
|
||||
## Problem
|
||||
|
||||
Agent tasks routinely involve containers: `docker compose up` to verify a
|
||||
scaffolded stack, a throwaway database for a test run, building an image to
|
||||
check a Dockerfile works. Bottles have no way to do any of that, so those tasks
|
||||
either fail or get done outside the bottle — which defeats the point of the
|
||||
bottle.
|
||||
|
||||
## Goals / success criteria
|
||||
|
||||
- A bottle with `nested_containers: true` on the `macos-container` backend can
|
||||
run `docker compose up -d --wait` against a stock compose file, pulling from
|
||||
a routed registry and serving from the workspace.
|
||||
- The agent's habits do not change: `docker` and `docker compose`, not
|
||||
`podman`.
|
||||
- No host Docker socket is mounted, on any backend.
|
||||
- No capability is added to the Apple Container guest.
|
||||
- Backends without a guest-local engine reject the flag with a clear error
|
||||
rather than ignoring it.
|
||||
- Bottles that do not set the flag carry none of its cost.
|
||||
|
||||
## Non-goals
|
||||
|
||||
- Nested containers as an isolation layer. The single-UID mapping means `root`
|
||||
inside a nested container is the agent user outside it. This is for build and
|
||||
test workloads; the bottle stays the security boundary.
|
||||
- The `docker` and `firecracker` backends. Both reject the flag for now.
|
||||
- Reaching registries that are not routed through the bottle's egress proxy.
|
||||
|
||||
## Design
|
||||
|
||||
### Why podman, not rootless Docker
|
||||
|
||||
Apple Container's capability bounding set omits `CAP_SYS_ADMIN`, which the
|
||||
kernel requires in order to write a multi-range `uid_map` via `newuidmap`.
|
||||
Rootless Docker has no path that avoids that write, so it cannot run in a
|
||||
bottle without granting `CAP_SYS_ADMIN` — which is close to root in practical
|
||||
terms and gives up most of what the bottle is for.
|
||||
|
||||
Podman does have a path: with **no** subordinate UID range configured it falls
|
||||
back to a single-UID self-mapping, which an unprivileged process may write
|
||||
itself. The image build therefore *removes* the agent user's `/etc/subuid` and
|
||||
`/etc/subgid` entries rather than adding them — their presence is exactly what
|
||||
would send podman down the `newuidmap` path. Full negative result in
|
||||
[`docs/research/rootless-docker-in-apple-container-spike.md`](../research/rootless-docker-in-apple-container-spike.md).
|
||||
|
||||
### The flag, and its name
|
||||
|
||||
The flag is kept because it gates real costs, not because podman needs a
|
||||
privilege grant: ~100MB of derived image, a resident service per bottle, and
|
||||
relaxed modes on `/dev/fuse` and `/dev/net/tun` that the majority of bottles
|
||||
should not get.
|
||||
|
||||
It is named `nested_containers`, not `docker_access`. It implies no Docker and
|
||||
grants access to nothing on the host — naming it after Docker access would
|
||||
describe the one thing the design refuses to do.
|
||||
|
||||
### Shape
|
||||
|
||||
- `bot_bottle/backend/macos_container/nested_containers.py` — derived-image
|
||||
build, guest env, device preparation, service start/readiness.
|
||||
- `bot_bottle/backend/macos_container/nested-containers-init.sh` — the
|
||||
unprivileged bootstrap that runs inside the bottle. Fails closed on every
|
||||
prerequisite it needs (podman, the storage/network helpers, writable device
|
||||
nodes, an *empty* subordinate range) rather than degrading.
|
||||
- The derived image `…-nested-containers` layers the Docker CLI, the compose
|
||||
plugin, and podman 5's networking stack — `passt` (pasta), `netavark`,
|
||||
`nftables`, `aardvark-dns` — plus `fuse-overlayfs`, `slirp4netns`, and
|
||||
`uidmap` onto the agent image. Podman itself already ships in every built-in
|
||||
image (#451), but with `--no-install-recommends`, so none of the networking
|
||||
pieces arrive with it. Each absence fails at a different and misleading
|
||||
layer: no pasta and nothing starts; no `nft` and containers are created but
|
||||
never start; no aardvark-dns and DNS inside a container fails while
|
||||
everything else looks healthy. Image pulls keep working throughout, which is
|
||||
what makes these read as compat-API bugs.
|
||||
- `BottleBackend.supports_nested_containers` — false by default, so a backend
|
||||
that cannot honor the flag fails in the shared `prepare` template.
|
||||
|
||||
Guest configuration the single-UID mapping forces:
|
||||
`ignore_chown_errors` (no second UID for layers to be chowned to),
|
||||
`cgroups="disabled"` and `cgroup_manager="cgroupfs"` (no cgroup delegation
|
||||
reaches the guest), `events_logger="file"` (no journald socket).
|
||||
|
||||
### Registry reach
|
||||
|
||||
Image pulls egress through the bottle's proxy like everything else, so each
|
||||
registry needs a route — **and so does the CDN it redirects blobs to**, which
|
||||
is a separate host: `production.cloudfront.docker.com` for Docker Hub,
|
||||
`pkg-containers.githubusercontent.com` for GHCR, `cdn0*.quay.io` for quay.
|
||||
Without those the pull authenticates, fetches the manifest, and then 403s
|
||||
partway through. Docker Hub and GHCR need `preserve_auth: true` — their
|
||||
token dance uses a client-fetched per-scope bearer token that the proxy would
|
||||
otherwise strip. Layer pulls should also set `dlp.outbound_detectors: false`
|
||||
and `dlp.inbound_detectors: false`: body scanning on a multi-hundred-MB layer
|
||||
is what triggers #455, and a registry route's scanned bodies are compressed
|
||||
layer blobs rather than anything a detector can read.
|
||||
|
||||
### Reaching the network from a nested container
|
||||
|
||||
Public DNS inside a nested container fails by design: everything egresses
|
||||
through the proxy. What was actually broken was reaching the proxy at all, and
|
||||
it took four attempts to fix because podman applies proxy settings at several
|
||||
layers and the last writer wins:
|
||||
|
||||
| Layer | Applies to |
|
||||
|---|---|
|
||||
| `~/.docker/config.json` proxies block | **every container the Docker CLI starts** — client-side, beats everything below |
|
||||
| service environment | podman's own pulls, non-CLI API clients |
|
||||
| `containers.conf` `env` | native `podman run` |
|
||||
| `containers.conf` `hosts_file`, `http_proxy` | native `podman run` only — the compat API ignores both |
|
||||
|
||||
The gateway is named `bot-bottle-gateway`, which resolves only through the
|
||||
bottle's `/etc/hosts`; a nested container gets its own. Since no config key
|
||||
reaches the compat path, the name is resolved in the bottle and the *address*
|
||||
is substituted into the proxy URL at each layer above. `NO_PROXY` keeps the
|
||||
name, which is matched against what a client asks for.
|
||||
|
||||
The gateway TLS-intercepts, so the CA bundle is mounted read-only and
|
||||
`SSL_CERT_FILE`, `CURL_CA_BUNDLE`, `REQUESTS_CA_BUNDLE`, and
|
||||
`NODE_EXTRA_CA_CERTS` point at it — no distro-specific trust commands.
|
||||
|
||||
## Verified on macOS 26 / Apple Container 1.0.0 / podman 5.4.2
|
||||
|
||||
With plain `docker`, no extra flags: image pulls from Docker Hub, GHCR, and
|
||||
quay; `docker run` with correct exit-code propagation; `docker compose` up,
|
||||
logs, down, and a published port curl'd from the bottle; `curl https://quay.io`
|
||||
and `https://pypi.org/simple/` returning 200 from inside a nested container;
|
||||
and `https://example.com` returning **403** — the egress allowlist applies to
|
||||
nested containers, not just the bottle.
|
||||
|
||||
Alpine's BusyBox `wget` drops the connection after TLS interception and
|
||||
reports "error getting response". The proxy logs the decrypted request, and
|
||||
`curl` on the same host succeeds, so this is a BusyBox client limitation
|
||||
rather than anything in the egress path.
|
||||
|
||||
## Open questions
|
||||
|
||||
- Whether the `docker` and `firecracker` backends want an equivalent, or
|
||||
whether guest-local containers stay macOS-only.
|
||||
@@ -0,0 +1,128 @@
|
||||
# PRD prd-new: Encrypted at-rest egress secrets (SecretProvider, interim slice)
|
||||
|
||||
- **Status:** Draft
|
||||
- **Author:** didericis
|
||||
- **Created:** 2026-07-21
|
||||
- **Issue:** #355
|
||||
|
||||
## Summary
|
||||
|
||||
An interim step toward the generic `SecretProvider` (#355) that stops short
|
||||
of per-request minting. Today the orchestrator holds each bottle's egress
|
||||
auth tokens **in process memory only**, so any infra-container recreation
|
||||
silently strips every already-running bottle of its upstream credentials.
|
||||
This PRD makes those secrets survive a gateway restart by persisting them
|
||||
**encrypted**, under a key that is not itself sitting next to the
|
||||
ciphertext.
|
||||
|
||||
The end state in #355 — short-lived, scoped credentials minted per request
|
||||
— removes the need to store anything durable at all. That is a larger
|
||||
change gated on per-upstream minting support. This slice buys back
|
||||
restart-survivability now without regressing to plaintext secrets at rest.
|
||||
|
||||
## Problem
|
||||
|
||||
`Orchestrator._tokens` (`bot_bottle/orchestrator/service.py:74-79`) is a
|
||||
plain in-memory dict, deliberately never written to the registry DB:
|
||||
|
||||
> Held **in memory only** — never written to the registry DB — so the
|
||||
> gateway can inject each bottle's upstream credential without secrets at
|
||||
> rest. Lost on restart (re-launch re-registers them); the future
|
||||
> SecretProvider (#355) replaces this with per-request minting.
|
||||
|
||||
The registry itself *is* durable (SQLite on a container-only volume), and
|
||||
so is the gateway CA since #450 / `2cd44cf7`. The tokens are now the only
|
||||
piece of gateway state that does not survive a restart, which makes the
|
||||
failure mode both silent and confusing.
|
||||
|
||||
### Observed failure
|
||||
|
||||
Checking out a branch that touches `bot_bottle/**/*.py` changes
|
||||
`source_hash()` (`bot_bottle/orchestrator/lifecycle.py:88-99`).
|
||||
`MacosInfraService._source_current()`
|
||||
(`bot_bottle/backend/macos_container/infra.py:159-169`) sees the mismatch
|
||||
and `ensure_running()` force-removes and recreates the infra container
|
||||
(`infra.py:198-208`). The registry rows survive on the DB volume; the CA
|
||||
survives on its host bind-mount; `_tokens` comes back empty.
|
||||
|
||||
Every already-running bottle then fails closed, mid-session, on its next
|
||||
outbound request:
|
||||
|
||||
- `/resolve` succeeds — the bottle is still `active` in
|
||||
`orchestrator_bottles` and its policy blob is served intact, including
|
||||
`- host: "api.anthropic.com"` with `auth_scheme: Bearer` /
|
||||
`token_env: EGRESS_TOKEN_0`.
|
||||
- `tokens_for()` returns `{}`, so the resolved env overlay has no
|
||||
`EGRESS_TOKEN_0`.
|
||||
- `decide()` (`bot_bottle/egress_addon_core.py:644-652`) blocks with
|
||||
`egress: route for 'api.anthropic.com' declared auth but env var
|
||||
'EGRESS_TOKEN_0' is unset` — an 89-byte `403` on every request.
|
||||
|
||||
Confirmed live on the macOS backend on 2026-07-21: two bottles running
|
||||
since 20:29/20:30 were still registered `active` with valid policy after
|
||||
the 23:05 infra recreation, and both took 89-byte `403`s from then on,
|
||||
while a bottle launched *after* the recreation egressed normally. The
|
||||
recovery today is to relaunch every affected bottle.
|
||||
|
||||
Note this is a re-attachment blocker distinct from #443/#445 and from #450
|
||||
— the CA and the gateway address were both fine. It is specifically the
|
||||
credential wipe.
|
||||
|
||||
## Goals / Success criteria
|
||||
|
||||
1. A bottle's egress auth tokens survive infra-container recreation: an
|
||||
already-running bottle keeps egressing across a gateway restart with no
|
||||
relaunch and no operator action.
|
||||
2. Secrets are **never** at rest in plaintext, and never at rest next to a
|
||||
key that trivially decrypts them.
|
||||
3. Compromise of the registry DB file alone does not yield usable
|
||||
upstream credentials.
|
||||
4. The stored form is revocable and rotatable without relaunching bottles
|
||||
that are not affected.
|
||||
5. Reap/teardown destroys a bottle's stored secrets along with its
|
||||
registry row (no ciphertext outliving its bottle).
|
||||
6. Migration is transparent: existing bottles keep working, no manifest
|
||||
changes required.
|
||||
|
||||
## Non-goals
|
||||
|
||||
- **Per-request minting** of short-lived scoped credentials. That is the
|
||||
#355 end state; this PRD is explicitly the interim slice and should not
|
||||
foreclose it.
|
||||
- Generalizing `DeployKeyProvisioner` into the full `SecretProvider` ABC,
|
||||
or the manifest-level `{ provider: <name> }` reference surface.
|
||||
- User-extensible provider discovery (`~/.bot-bottle/contrib/<name>/`).
|
||||
- Changing the `/resolve` contract's shape (it already carries `tokens`).
|
||||
- Fixing the *trigger* — `source_hash` churn on branch switch. Recreating
|
||||
infra is legitimate; it just must not cost running bottles their
|
||||
credentials. A separate guard that refuses recreation while bottles are
|
||||
active is complementary and out of scope here.
|
||||
|
||||
## Design
|
||||
|
||||
> **TODO (didericis):** the encryption flow goes here — key custody, where
|
||||
> the key material lives relative to the ciphertext, the wrap/unwrap path
|
||||
> at register and at `/resolve`, and what an attacker who holds only the
|
||||
> DB (or only the host, or only the infra container) can recover.
|
||||
|
||||
Constraints the design has to satisfy, for reference while drafting:
|
||||
|
||||
- The gateway's `PolicyResolver` needs the cleartext at request time, on
|
||||
the data-plane path, so unwrap has to be cheap enough to sit in a
|
||||
per-flow `/resolve` (or be cached in memory after first unwrap).
|
||||
- The infra container is recreated routinely and unattended. Anything
|
||||
requiring an interactive unlock on every recreation defeats the goal.
|
||||
- The DB lives on a container-only volume that the host does not mount, so
|
||||
host-side and guest-side components see different filesystems — that
|
||||
asymmetry is available as a place to split custody.
|
||||
- The agent must never be able to reach the key material. It is a separate
|
||||
container with no control-plane token, which is the existing boundary.
|
||||
|
||||
## Open questions
|
||||
|
||||
- Where does the unwrap key live, and what recreates/re-derives it when the
|
||||
infra container is rebuilt?
|
||||
- Is the cleartext cached in memory after first unwrap, or unwrapped per
|
||||
request? (Latency vs. exposure window.)
|
||||
- What is the rotation story — re-wrap in place, or force re-registration?
|
||||
- Does this land behind a flag, or replace `_tokens` outright?
|
||||
@@ -1,86 +0,0 @@
|
||||
# Egress proxy OOMs on large downloads
|
||||
|
||||
Found on 2026-07-21 while running the rootless-podman spike
|
||||
(`docs/research/rootless-docker-in-apple-container-spike.md`). Recorded
|
||||
rather than fixed — the fix is a security-relevant decision, not a
|
||||
mechanical patch.
|
||||
|
||||
## Summary
|
||||
|
||||
A single large HTTPS download through the gateway kills the egress
|
||||
proxy. `mitmdump` buffers whole response bodies so the DLP detectors can
|
||||
scan them, grows past the gateway container's memory limit, and is
|
||||
OOM-killed by the cgroup. Nothing restarts it.
|
||||
|
||||
Two properties make this worse than a failed download:
|
||||
|
||||
- **The gateway is a per-host singleton.** Every bottle shares it, so
|
||||
one bottle's download takes egress away from all of them.
|
||||
- **There is no restart on death.** The gateway supervisor is
|
||||
`while : ; do wait ; done`; a killed daemon stays dead until the infra
|
||||
container is recreated.
|
||||
|
||||
So ordinary agent activity — pulling a container image, downloading a
|
||||
model or dataset, fetching a large tarball — is a denial of service
|
||||
against every other bottle on the host. No malice required, though it is
|
||||
trivially reachable on purpose.
|
||||
|
||||
## Evidence
|
||||
|
||||
Triggered by `docker compose up` pulling `quay.io/fedora/python-312`
|
||||
(two layers, ~82MB and ~83MB) inside a bottle. The pull itself
|
||||
succeeded; the *next* request failed:
|
||||
|
||||
```
|
||||
initializing source docker://quay.io/fedora/python-312:latest:
|
||||
pinging container registry quay.io: Get "https://quay.io/v2/":
|
||||
proxyconnect tcp: dial tcp 192.168.128.39:9099: connect: connection refused
|
||||
```
|
||||
|
||||
From the gateway's `dmesg`:
|
||||
|
||||
```
|
||||
python3 invoked oom-killer: gfp_mask=0x100cca(GFP_HIGHUSER_MOVABLE), order=0
|
||||
oom-kill:constraint=CONSTRAINT_MEMCG,
|
||||
oom_memcg=/container/bot-bottle-mac-infra,
|
||||
task_memcg=/container/bot-bottle-mac-infra,task=mitmdump,pid=118
|
||||
Memory cgroup out of memory: Killed process 118 (mitmdump)
|
||||
total-vm:1391936kB, anon-rss:997768kB
|
||||
```
|
||||
|
||||
~1GB RSS against a 1024MB container. Note the amplification: ~165MB of
|
||||
layers produced ~1GB of resident memory, so the buffering is several
|
||||
copies deep (encoded body, decoded body, and the text conversion the
|
||||
regex detectors scan).
|
||||
|
||||
Afterwards the gateway container was still running and healthy-looking —
|
||||
orchestrator, supervise, and git-http all alive — with no `mitmdump`
|
||||
process at all, and it stayed that way until the container was
|
||||
recreated. A liveness check on the container would not have caught this.
|
||||
|
||||
## Reproduction
|
||||
|
||||
1. Launch any bottle with an egress route to a host serving a large file.
|
||||
2. Download >~150MB over HTTPS through the proxy.
|
||||
3. `dmesg | grep -i oom` inside `bot-bottle-mac-infra`, and note that no
|
||||
`mitmdump` process remains.
|
||||
|
||||
Beware a false negative when checking: truncating the process listing
|
||||
(`cut -c1-45`) cuts before the binary name, because `mitmdump` runs as
|
||||
`/usr/local/bin/python3.12 /usr/local/bin/mitmdump …`.
|
||||
|
||||
## Fix options, not yet chosen
|
||||
|
||||
1. **Restart dead daemons.** Smallest change and strictly an
|
||||
improvement: an OOM then degrades one download instead of removing
|
||||
egress for every bottle. Does not stop the OOM.
|
||||
2. **Cap the scanned body size.** Above a threshold, stop buffering —
|
||||
either skip the scan or stream it. This is the root-cause fix and a
|
||||
security decision: a size threshold is exactly the hole an exfiltrator
|
||||
would aim for, so "skip above N" trades a DoS for a covert channel.
|
||||
Streaming with a bounded window keeps coverage, at more complexity.
|
||||
3. **Raise the gateway's memory limit.** Moves the threshold; does not
|
||||
remove it.
|
||||
|
||||
Worth noting that (1) and (2) are complementary — the restart gap is
|
||||
worth closing regardless of how the memory behaviour is resolved.
|
||||
@@ -1,359 +0,0 @@
|
||||
# Rootless Docker inside Apple Container bottles
|
||||
|
||||
Spike branch: `spike/rootless-docker-macos` (`a4d8461`)
|
||||
|
||||
**Outcome:** the podman recommendation below shipped as the
|
||||
`nested_containers` bottle flag — see
|
||||
[`docs/prds/prd-new-nested-containers.md`](../prds/prd-new-nested-containers.md).
|
||||
The `docker_access` name used throughout the spike text was renamed on the
|
||||
way in; it granted no access to anything on the host.
|
||||
|
||||
## Summary
|
||||
|
||||
**Negative result.** Rootless Docker cannot run inside an Apple
|
||||
Container bottle without granting the bottle `CAP_SYS_ADMIN`. This is a
|
||||
kernel constraint on writing multi-range `uid_map`, not a packaging gap
|
||||
we can close with a better init script, a different base image, or more
|
||||
careful `/etc/subuid` handling.
|
||||
|
||||
The spike was built on the premise — stated in
|
||||
`bot_bottle/backend/macos_container/rootless_docker.py` — that it would
|
||||
*"deliberately refuse to compensate for missing prerequisites with outer
|
||||
capabilities, a privileged container, or a host Docker socket."* That
|
||||
premise is exactly what the experiment falsified. The two ways forward
|
||||
are to abandon the premise (add `CAP_SYS_ADMIN` to the bottle, and with
|
||||
it most of the isolation the bottle exists to provide) or to abandon
|
||||
rootless Docker.
|
||||
|
||||
Recommendation: abandon rootless Docker. Podman does not have this
|
||||
problem — see [Podman is not blocked by
|
||||
this](#podman-is-not-blocked-by-this) below.
|
||||
|
||||
## Local environment
|
||||
|
||||
Tested on 2026-07-21:
|
||||
|
||||
```console
|
||||
$ sw_vers
|
||||
ProductName: macOS
|
||||
ProductVersion: 26.5.1
|
||||
BuildVersion: 25F80
|
||||
|
||||
$ container --version
|
||||
container CLI version 1.0.0 (build: release, commit: ee848e3)
|
||||
|
||||
$ uname -a # inside the bottle
|
||||
Linux ... 6.18.15 #1 SMP Tue Mar 17 01:36:53 UTC 2026 aarch64 GNU/Linux
|
||||
```
|
||||
|
||||
## The failure
|
||||
|
||||
`tests/integration/test_macos_rootless_docker_spike.py` builds the
|
||||
image, launches the bottle, and dies in `rootless_docker.start`:
|
||||
|
||||
```
|
||||
+ exec rootlesskit --net=slirp4netns --mtu=65520 ... dockerd-rootless.sh
|
||||
[rootlesskit:parent] error: failed to setup UID/GID map:
|
||||
newuidmap 1100 [0 1000 1 1 100000 65536] failed:
|
||||
newuidmap: write to uid_map failed: Operation not permitted
|
||||
```
|
||||
|
||||
## Why it fails
|
||||
|
||||
Every prerequisite you would normally suspect is present and correct in
|
||||
the guest:
|
||||
|
||||
| Check | Result |
|
||||
| --- | --- |
|
||||
| `/usr/bin/newuidmap` | `-rwsr-xr-x root root` — setuid bit intact, survived the OCI export |
|
||||
| `/` mount options | `rw,relatime` — **not** `nosuid` |
|
||||
| `NoNewPrivs` | `0` |
|
||||
| `Seccomp` | `0`, no filters |
|
||||
| `/etc/subuid`, `/etc/subgid` | `node:100000:65536` in both |
|
||||
| user namespace | `user:[4026531837]`, identical to pid 1 — the *initial* userns |
|
||||
| `unshare -U -r true` | succeeds |
|
||||
| `/proc/sys/user/max_user_namespaces` | `4505` |
|
||||
|
||||
The one thing that is missing is in the capability bounding set that
|
||||
Apple Container gives the container:
|
||||
|
||||
```
|
||||
CapBnd: 00000000a80425fb
|
||||
= chown, dac_override, fowner, fsetid, kill, setgid, setuid, setpcap,
|
||||
net_bind_service, net_raw, sys_chroot, mknod, audit_write, setfcap
|
||||
```
|
||||
|
||||
No `CAP_SYS_ADMIN`. That is the whole story, and the chain is:
|
||||
|
||||
1. The kernel's `map_write()` gates writing a `uid_map` on
|
||||
`file_ns_capable(file, ns, CAP_SYS_ADMIN)` — capability over the
|
||||
**new** user namespace, evaluated against the credentials that opened
|
||||
`/proc/<pid>/uid_map`.
|
||||
2. `newuidmap` is setuid-root, so it runs with euid 0 — but its
|
||||
capability sets are clamped by the bounding set, which has no
|
||||
`CAP_SYS_ADMIN`.
|
||||
3. `cap_capable()` has a shortcut that grants *all* capabilities when
|
||||
the caller's userns is the new namespace's parent **and**
|
||||
`ns->owner == cred->euid`. It does not apply: the namespace was
|
||||
created by `node` (uid 1000) while `newuidmap` runs as euid 0.
|
||||
4. So the check falls through to the effective-set test in the initial
|
||||
userns, which fails. `EPERM`.
|
||||
|
||||
Note that the single-line unprivileged path (`unshare -U -r`) works
|
||||
precisely because it does not go through `newuidmap` and does not need
|
||||
`CAP_SYS_ADMIN`. Only the multi-range subuid mapping that rootless
|
||||
Docker requires does.
|
||||
|
||||
This is the same constraint that makes upstream's `dind-rootless` image
|
||||
require `--privileged`. It is not specific to Apple Container, except
|
||||
that Apple Container gives us no bounding set that includes
|
||||
`CAP_SYS_ADMIN` by default.
|
||||
|
||||
## It does work with the capability — which is the point
|
||||
|
||||
Adding the capability clears the failure immediately, and exposes one
|
||||
further, much smaller blocker: `/dev/net/tun` exists (the kernel has
|
||||
tun; `/proc/misc` lists `200 tun`) but Apple Container creates it
|
||||
`crw------- root root`, so uid 1000 cannot open it and `slirp4netns`
|
||||
fails with `open: Permission denied`. A `chmod 0666 /dev/net/tun` as
|
||||
root inside the bottle fixes that, and needs no capability beyond what
|
||||
the bottle already has.
|
||||
|
||||
With both applied by hand, the daemon comes up completely:
|
||||
|
||||
```console
|
||||
$ container run --rm -u root --cap-add CAP_SYS_ADMIN \
|
||||
bot-bottle-claude:latest-rootless-docker sh -c '...'
|
||||
Server Version: 20.10.24+dfsg1
|
||||
Storage Driver: fuse-overlayfs
|
||||
Cgroup Driver: none
|
||||
Cgroup Version: 2
|
||||
API listen on /tmp/rt/docker.sock
|
||||
```
|
||||
|
||||
So `rootless-docker-init.sh` and `rootless_docker.py` are *correct*.
|
||||
The spike did not fail on a bug. It failed on its own premise.
|
||||
|
||||
Two secondary findings from that run, relevant if anyone revisits this:
|
||||
|
||||
- Debian's `docker.io` package pins Docker **20.10** (EOL), not the 28.x
|
||||
implied by the `docker:28-cli` compose plugin the image copies in.
|
||||
- `Cgroup Driver: none` — no resource limits on nested containers.
|
||||
|
||||
## Why we should not just add the capability
|
||||
|
||||
`CAP_SYS_ADMIN` is close to a superset of "root" in practical terms —
|
||||
mount, `pivot_root`, namespace manipulation, and a long tail of
|
||||
subsystem-specific powers. Granting it to the agent bottle would
|
||||
undercut the containment argument the rest of the backend is built
|
||||
around, including the deliberately narrow choices immediately adjacent
|
||||
to it in `launch.py` (`--cap-drop CAP_NET_RAW`, no `NET_ADMIN`, a
|
||||
host-only agent network). Trading all of that for nested `docker
|
||||
compose` is a bad exchange.
|
||||
|
||||
## Podman is not blocked by this
|
||||
|
||||
Sanity-checked on the same host, same kernel, same runtime, so the
|
||||
comparison is apples to apples:
|
||||
|
||||
| Scenario | Result |
|
||||
| --- | --- |
|
||||
| Podman rootless, `/etc/subuid` populated | **Fails identically** — `newuidmap: write to uid_map failed: Operation not permitted` |
|
||||
| Podman rootless, no subuid ranges, `--network=host` | **Works**, no added capabilities |
|
||||
| Podman rootless, no subuid ranges, default netns, `/dev/net/tun` at `0600` | Fails — `slirp4netns: open("/dev/net/tun"): Permission denied` |
|
||||
| Podman rootless, no subuid ranges, default netns, `/dev/net/tun` at `0666` | **Works**, no added capabilities |
|
||||
|
||||
The difference is that podman degrades gracefully when no subuid range
|
||||
is available: it falls back to a single-UID self-mapping, which an
|
||||
unprivileged process may write itself, so `newuidmap` is never invoked
|
||||
and `CAP_SYS_ADMIN` is never needed. Docker's rootless mode has no
|
||||
equivalent fallback.
|
||||
|
||||
The cost of that fallback is real and should be weighed before building
|
||||
on it: with a single-UID mapping, every UID inside a nested container
|
||||
collapses onto the bottle's own uid 1000. There is no UID separation
|
||||
between the agent and anything it runs — `root` in a nested container is
|
||||
the agent user outside it. It also requires `ignore_chown_errors` on the
|
||||
storage driver. Whether that is acceptable depends on whether the bottle
|
||||
boundary (which is unchanged) or the nested-container boundary (which is
|
||||
effectively nil) is the one we are relying on.
|
||||
|
||||
## What the podman spike then needed
|
||||
|
||||
The podman implementation that replaced the Docker one on this branch
|
||||
turned up two more device-node blockers of the same shape as
|
||||
`/dev/net/tun` — Apple Container creates the node, but 0600 root:root:
|
||||
|
||||
- **`/dev/fuse`** — blocks the `fuse-overlayfs` storage driver
|
||||
(`fuse: failed to open /dev/fuse: Permission denied`). Without it the
|
||||
only working driver is `vfs`, which copies whole layers per container.
|
||||
- **`/dev/net/tun`** — blocks `slirp4netns`, which rootless podman uses
|
||||
for the default bridge network.
|
||||
|
||||
Both are fixed by `chmod 0666` as root inside the bottle, which needs no
|
||||
capability the bottle does not already hold. This is categorically
|
||||
different from the `CAP_SYS_ADMIN` requirement: it is a permission on a
|
||||
node that already exists, not an outer privilege grant.
|
||||
|
||||
One design note worth recording: the agent-facing surface stays `docker`
|
||||
and `docker compose`, pointed at podman's Docker-compatible API socket
|
||||
via `DOCKER_HOST`. Setting `netns="host"` in `containers.conf` does *not*
|
||||
propagate through that compat API — stock `docker run` and compose files
|
||||
request bridge networking explicitly — so slirp4netns (and therefore the
|
||||
`/dev/net/tun` chmod) is required for ordinary compose files to work at
|
||||
all. Host networking remains available per-workload via
|
||||
`--network=host`.
|
||||
|
||||
Verified working in a bottle with zero added capabilities: fuse-overlayfs
|
||||
storage, the compat API socket, `docker run` on both bridge and host
|
||||
networking, and published ports.
|
||||
|
||||
### Nested pulls collide with our own egress DLP
|
||||
|
||||
The first live run got podman up and `docker compose` running, then
|
||||
failed on the image pull:
|
||||
|
||||
```
|
||||
web Pulling
|
||||
initializing source docker://python:3.12-alpine: reading manifest ...
|
||||
StatusCode: 403, egress DLP: Generic Bearer JWT found in body
|
||||
```
|
||||
|
||||
This is bot-bottle's own egress scanner, not a podman problem. The
|
||||
Docker registry auth flow carries a bearer JWT *by protocol*, and the
|
||||
`token_patterns` detector's `Generic Bearer JWT` rule
|
||||
(`Bearer\s+[A-Za-z0-9._\-]{50,}`) matches it on every pull. Any bottle
|
||||
that pulls images will hit this.
|
||||
|
||||
The fix is per-route detector scoping, which the egress config already
|
||||
supports — drop `token_patterns` on the registry hosts and keep
|
||||
`known_secrets`:
|
||||
|
||||
```json
|
||||
{"host": "registry-1.docker.io",
|
||||
"dlp": {"outbound_detectors": ["known_secrets"]}}
|
||||
```
|
||||
|
||||
That is the right trade rather than a grudging one: `known_secrets`
|
||||
matches the bottle's *actual* credential values, so real exfil through a
|
||||
registry host is still caught. `token_patterns` on a registry route only
|
||||
ever produces protocol noise.
|
||||
|
||||
Worth generalising later: any manifest enabling `nested_containers` needs
|
||||
this on its registry routes, so it probably belongs in a shared
|
||||
registry-route snippet rather than being copy-pasted per bottle.
|
||||
|
||||
### And then registry auth collides with the Authorization strip
|
||||
|
||||
With DLP scoped, the pull failed differently: `unauthorized:
|
||||
authentication required`. This one is architectural.
|
||||
|
||||
`egress_addon.py` strips agent-set `Authorization` unconditionally
|
||||
before forwarding — deliberately, so an agent cannot smuggle a
|
||||
credential out in a header the DLP detectors don't recognise. A route
|
||||
may carry gateway-injected auth instead, but only from a *static* token
|
||||
in an env var (`auth_scheme` + `token_env`).
|
||||
|
||||
Docker registry auth doesn't fit that shape. The client fetches a
|
||||
short-lived, per-repository-scope bearer token from `auth.docker.io` and
|
||||
presents it to `registry-1.docker.io`. There is no static token to
|
||||
inject, and the token the client legitimately obtained is stripped.
|
||||
|
||||
Measured inside a bottle, by hand:
|
||||
|
||||
| Step | Result |
|
||||
| --- | --- |
|
||||
| Fetch token from `auth.docker.io` | 200, 5409-byte token body |
|
||||
| Manifest request **with** that valid token | 401 |
|
||||
| Manifest request with **no** Authorization | 401 — identical |
|
||||
|
||||
A valid token behaves exactly like sending none, which is direct
|
||||
evidence the header never arrives. Any nested-container workflow that
|
||||
pulls from a registry is blocked on this, so it is not a detail that can
|
||||
be deferred: pulling base images is most of what nested containers are
|
||||
for.
|
||||
|
||||
### Registries that skip the token dance work today
|
||||
|
||||
Not every registry needs the stripped header. Measured directly:
|
||||
|
||||
| Registry | Manifest request with no `Authorization` |
|
||||
| --- | --- |
|
||||
| `quay.io` | 200 |
|
||||
| `mcr.microsoft.com` | 200 |
|
||||
| `registry.k8s.io` | 307 (redirect, no auth) |
|
||||
| `ghcr.io` | 401 |
|
||||
| `registry-1.docker.io` | 401 |
|
||||
|
||||
So "just add the registry to the bottle config" genuinely works — for
|
||||
quay, MCR, registry.k8s.io, or any unauthenticated internal registry.
|
||||
Docker Hub and GHCR are the ones that need the strip resolved. The
|
||||
acceptance test uses quay for exactly this reason.
|
||||
|
||||
Resolving it for Docker Hub means picking one of:
|
||||
|
||||
1. **Per-route opt-in to preserve client Authorization.** Smallest
|
||||
change. Note the compounding effect on exactly these routes: the DLP
|
||||
scoping above already removed `token_patterns` there, so a
|
||||
preserved-auth registry route is one where the agent may send bearer
|
||||
tokens that neither the strip nor the pattern detector inspects.
|
||||
`known_secrets` still applies, so the bottle's real credentials are
|
||||
still caught.
|
||||
2. **A registry-aware gateway** that performs the token dance itself and
|
||||
injects the result. Preserves the invariant fully; materially more
|
||||
work, and it makes the gateway speak a specific registry protocol.
|
||||
3. **Pre-seed images at provision time** (host-side `container image
|
||||
save` into podman storage), so bottles never pull at runtime.
|
||||
Preserves the invariant, and limits nested containers to
|
||||
pre-approved images — which fits the custody positioning, at the cost
|
||||
of no ad-hoc `docker pull`.
|
||||
4. **Stop.** Nested containers are not supported on this backend.
|
||||
|
||||
### Podman 4.3.1 silently swallows container exit codes
|
||||
|
||||
Debian bookworm — which the current agent base image is built on —
|
||||
ships podman 4.3.1. Through its Docker-compatible API, `docker run`
|
||||
returns 0 no matter what the container did:
|
||||
|
||||
| Command | podman 4.3.1 | podman 5.4.2 |
|
||||
| --- | --- | --- |
|
||||
| `docker run … sh -c 'exit 7'` (compat API) | **0** | 7 |
|
||||
| `docker run … sh -c 'exit 0'` (compat API) | 0 | 0 |
|
||||
| `podman run … sh -c 'exit 7'` (native) | 7 | 7 |
|
||||
|
||||
This is worse than a broken feature: every failing command an agent runs
|
||||
via `docker run` reports success. A test suite, a build step, or a CI
|
||||
script inside a bottle would pass while failing. It also silently
|
||||
defeated the acceptance test's egress-containment assertion, which is
|
||||
why that assertion now checks an in-band marker rather than an exit
|
||||
code.
|
||||
|
||||
Podman 5.4.2 (Debian trixie) fixes it, but needs two packages that
|
||||
bookworm's podman does not: `passt` (podman 5's default network tool)
|
||||
and `nftables` (netavark shells out to `nft`; without it every run fails
|
||||
with `unable to upgrade to tcp, received 500`). With both installed,
|
||||
exit codes propagate correctly and the compat API behaves.
|
||||
|
||||
The open question this leaves is where podman 5 comes from, since the
|
||||
agent base is bookworm-based:
|
||||
|
||||
1. **Move the agent images to Debian trixie.** Trixie is current stable.
|
||||
Correct, and the blast radius is every bottle, not just this feature.
|
||||
2. **Drop the compat socket and use podman natively** (`podman-docker`
|
||||
provides a `docker` shim; compose comes from `podman-compose`).
|
||||
Native podman propagates exit codes correctly even on 4.3.1. Contained
|
||||
to this feature, at the cost of `docker compose` becoming
|
||||
`docker-compose`/`podman-compose`.
|
||||
3. **Ship bookworm's podman 4.3.1 with the compat socket** — not viable.
|
||||
Silent false success is a correctness bug agents cannot see.
|
||||
|
||||
## Recommendation
|
||||
|
||||
1. Do not revive rootless Docker on this backend. This document is the
|
||||
record of why.
|
||||
2. Nested containers, if wanted, come from podman under the
|
||||
single-mapping constraint — with the explicit understanding that the
|
||||
nested-container boundary carries no security weight. `root` in a
|
||||
nested container is the agent user outside it.
|
||||
3. Nested containers are therefore a build/test convenience. The bottle
|
||||
remains the security boundary, exactly as it was.
|
||||
@@ -21,7 +21,7 @@ from bot_bottle.backend.firecracker import FirecrackerBottleBackend
|
||||
from bot_bottle.manifest import ManifestIndex
|
||||
|
||||
|
||||
def _manifest(*, nested_containers: bool = False) -> ManifestIndex:
|
||||
def _manifest() -> ManifestIndex:
|
||||
return ManifestIndex.from_json_obj({
|
||||
"bottles": {
|
||||
"dev": {
|
||||
@@ -29,7 +29,6 @@ def _manifest(*, nested_containers: bool = False) -> ManifestIndex:
|
||||
"LITERAL_ENV": "literal-value",
|
||||
"FORWARDED_ENV": "${HOST_SECRET_ENV}",
|
||||
},
|
||||
"nested_containers": nested_containers,
|
||||
},
|
||||
},
|
||||
"agents": {
|
||||
@@ -42,11 +41,9 @@ def _manifest(*, nested_containers: bool = False) -> ManifestIndex:
|
||||
})
|
||||
|
||||
|
||||
def _spec(
|
||||
tmp: Path, *, identity: str, nested_containers: bool = False,
|
||||
) -> BottleSpec:
|
||||
def _spec(tmp: Path, *, identity: str) -> BottleSpec:
|
||||
return BottleSpec(
|
||||
manifest=_manifest(nested_containers=nested_containers),
|
||||
manifest=_manifest(),
|
||||
agent_name="demo",
|
||||
copy_cwd=False,
|
||||
user_cwd=str(tmp),
|
||||
@@ -116,42 +113,6 @@ class TestFirecrackerPrepare(_FakeStateMixin, unittest.TestCase):
|
||||
self.assertEqual({"FORWARDED_ENV": "secret-value"}, plan.forwarded_env)
|
||||
|
||||
|
||||
class TestNestedContainersRejection(_FakeStateMixin, unittest.TestCase):
|
||||
"""A backend with no guest-local engine must refuse the flag outright.
|
||||
|
||||
Ignoring it would leave the agent without `docker`, and the only ways to
|
||||
fake it here (a host daemon socket, a privileged container) are what
|
||||
issue #392 rules out.
|
||||
"""
|
||||
|
||||
def test_docker_backend_refuses_the_flag(self) -> None:
|
||||
backend = DockerBottleBackend()
|
||||
spec = _spec(
|
||||
Path(self.tmp.name), identity="demo-docker", nested_containers=True,
|
||||
)
|
||||
with (
|
||||
patch(
|
||||
"bot_bottle.backend.resolve_common.die", side_effect=RuntimeError,
|
||||
) as die,
|
||||
self.assertRaises(RuntimeError),
|
||||
):
|
||||
backend.prepare(spec, Path(self.tmp.name) / "stage")
|
||||
self.assertIn("nested_containers", die.call_args.args[0])
|
||||
self.assertIn("docker", die.call_args.args[0])
|
||||
|
||||
def test_firecracker_backend_refuses_the_flag(self) -> None:
|
||||
backend = FirecrackerBottleBackend()
|
||||
spec = _spec(Path(self.tmp.name), identity="demo-fc", nested_containers=True)
|
||||
with (
|
||||
patch(
|
||||
"bot_bottle.backend.resolve_common.die", side_effect=RuntimeError,
|
||||
) as die,
|
||||
self.assertRaises(RuntimeError),
|
||||
):
|
||||
backend.prepare(spec, Path(self.tmp.name) / "stage")
|
||||
self.assertIn("firecracker", die.call_args.args[0])
|
||||
|
||||
|
||||
class TestMintSlug(unittest.TestCase):
|
||||
def _spec(self, *, label: str = "", identity: str = "") -> BottleSpec:
|
||||
manifest = _manifest()
|
||||
|
||||
@@ -379,25 +379,6 @@ class TestRenderRoutes(unittest.TestCase):
|
||||
addon_routes = load_config(rendered).routes
|
||||
self.assertTrue(addon_routes[0].git_fetch)
|
||||
|
||||
def test_preserve_auth_round_trips_to_the_addon(self):
|
||||
"""Regression: the manifest parsed preserve_auth and the addon honored
|
||||
it, but the renderer in between dropped it — so the flag never reached
|
||||
the proxy and registry pulls kept failing with "unauthorized" while
|
||||
the config looked correct everywhere it was inspected."""
|
||||
from bot_bottle.egress_addon_core import load_config
|
||||
b = _bottle([{"host": "registry-1.docker.io", "preserve_auth": True}])
|
||||
routes = egress_routes_for_bottle(b)
|
||||
rendered = egress_render_routes(routes)
|
||||
self.assertIn("preserve_auth: true", rendered)
|
||||
self.assertTrue(load_config(rendered).routes[0].preserve_auth)
|
||||
|
||||
def test_preserve_auth_omitted_when_unset(self):
|
||||
b = _bottle([{"host": "x.example"}])
|
||||
rendered = egress_render_routes(egress_routes_for_bottle(b))
|
||||
self.assertNotIn("preserve_auth", rendered)
|
||||
from bot_bottle.egress_addon_core import load_config
|
||||
self.assertFalse(load_config(rendered).routes[0].preserve_auth)
|
||||
|
||||
def test_log_zero_omitted_from_render(self):
|
||||
b = _bottle([{"host": "x.example"}])
|
||||
routes = egress_routes_for_bottle(b)
|
||||
|
||||
@@ -49,7 +49,6 @@ def _plan(
|
||||
agent_git_gate_url: str = "",
|
||||
agent_supervise_url: str = "",
|
||||
image_policy: str = "fresh",
|
||||
nested_containers: bool = False,
|
||||
) -> MacosContainerBottlePlan:
|
||||
routes_path = stage_dir / "routes.yaml"
|
||||
routes_path.write_text("routes: []\n", encoding="utf-8")
|
||||
@@ -68,7 +67,6 @@ def _plan(
|
||||
manifest=_MANIFEST,
|
||||
stage_dir=stage_dir,
|
||||
slug="dev-abc",
|
||||
nested_containers=nested_containers,
|
||||
container_name="bot-bottle-dev-abc",
|
||||
image="bot-bottle-agent:latest",
|
||||
dockerfile_path="/repo/Dockerfile",
|
||||
|
||||
@@ -1,333 +0,0 @@
|
||||
"""Unit coverage for the fail-closed guest-local container engine (#392)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import unittest
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
from types import SimpleNamespace
|
||||
from typing import cast
|
||||
from unittest.mock import patch
|
||||
|
||||
from bot_bottle.backend.macos_container import nested_containers
|
||||
from bot_bottle.backend.macos_container import launch as launch_mod
|
||||
from bot_bottle.backend.macos_container.bottle_plan import MacosContainerBottlePlan
|
||||
|
||||
|
||||
class _Bottle:
|
||||
def __init__(self, results: list[SimpleNamespace]) -> None:
|
||||
self.results = results
|
||||
self.commands: list[str] = []
|
||||
|
||||
def exec(self, command: str) -> SimpleNamespace:
|
||||
self.commands.append(command)
|
||||
return self.results.pop(0)
|
||||
|
||||
|
||||
def _result(returncode: int, *, stdout: str = "", stderr: str = "") -> SimpleNamespace:
|
||||
return SimpleNamespace(returncode=returncode, stdout=stdout, stderr=stderr)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class _AgentProvision:
|
||||
image: str
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class _Spec:
|
||||
image_policy: str = "build"
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class _Plan:
|
||||
slug: str
|
||||
image: str
|
||||
dockerfile_path: str
|
||||
nested_containers: bool
|
||||
agent_provision: _AgentProvision
|
||||
spec: _Spec = _Spec()
|
||||
|
||||
|
||||
def _base_image_only(ref: str) -> bool:
|
||||
"""Only the un-derived agent image is cached on the host."""
|
||||
return not ref.endswith(nested_containers.IMAGE_SUFFIX)
|
||||
|
||||
|
||||
def _plan(**kwargs: object) -> MacosContainerBottlePlan:
|
||||
return cast(MacosContainerBottlePlan, cast(object, _Plan(**kwargs))) # type: ignore[arg-type]
|
||||
|
||||
|
||||
class TestNestedContainersStart(unittest.TestCase):
|
||||
def test_bootstraps_then_waits_for_guest_local_service(self) -> None:
|
||||
bottle = _Bottle([_result(0), _result(1), _result(0)])
|
||||
with patch.object(nested_containers.time, "sleep"):
|
||||
nested_containers.start(bottle)
|
||||
self.assertIn("nested-containers-init", bottle.commands[0])
|
||||
self.assertEqual(2, bottle.commands.count("docker info >/dev/null 2>&1"))
|
||||
|
||||
def test_bootstrap_failure_is_fatal_without_privilege_fallback(self) -> None:
|
||||
bottle = _Bottle([_result(1, stderr="slirp4netns missing")])
|
||||
with patch.object(nested_containers, "die", side_effect=RuntimeError) as die:
|
||||
with self.assertRaises(RuntimeError):
|
||||
nested_containers.start(bottle)
|
||||
self.assertIn("slirp4netns missing", die.call_args.args[0])
|
||||
self.assertEqual(1, len(bottle.commands))
|
||||
|
||||
def test_timeout_reports_guest_log(self) -> None:
|
||||
bottle = _Bottle(
|
||||
[_result(0)]
|
||||
+ [_result(1) for _ in range(nested_containers.READY_RETRIES)]
|
||||
+ [_result(0, stdout="operation not permitted")]
|
||||
)
|
||||
with patch.object(nested_containers.time, "sleep"), \
|
||||
patch.object(nested_containers, "die", side_effect=RuntimeError) as die:
|
||||
with self.assertRaises(RuntimeError):
|
||||
nested_containers.start(bottle)
|
||||
self.assertIn("operation not permitted", die.call_args.args[0])
|
||||
|
||||
|
||||
class TestNestedContainersDevices(unittest.TestCase):
|
||||
def test_relaxes_only_the_two_blocked_device_nodes_as_root(self) -> None:
|
||||
calls: list[tuple[str, list[str]]] = []
|
||||
|
||||
def record(name: str, argv: list[str]) -> None:
|
||||
calls.append((name, argv))
|
||||
|
||||
nested_containers.prepare_guest_devices("bottle-1", record)
|
||||
self.assertEqual(1, len(calls))
|
||||
name, argv = calls[0]
|
||||
self.assertEqual("bottle-1", name)
|
||||
self.assertIn("chmod 0666 /dev/fuse /dev/net/tun", argv[-1])
|
||||
|
||||
|
||||
class TestNestedContainersImage(unittest.TestCase):
|
||||
def test_layers_tooling_without_changing_base_image(self) -> None:
|
||||
calls: list[tuple[str, str, str]] = []
|
||||
|
||||
def build(image: str, context: str, *, dockerfile: str) -> None:
|
||||
calls.append((image, context, dockerfile))
|
||||
text = Path(dockerfile).read_text(encoding="utf-8")
|
||||
self.assertIn("FROM agent:base", text)
|
||||
self.assertIn("aardvark-dns fuse-overlayfs netavark nftables passt", text)
|
||||
self.assertIn("USER node", text)
|
||||
self.assertTrue((Path(context) / "nested-containers-init.sh").is_file())
|
||||
|
||||
image = nested_containers.build_image("agent:base", build)
|
||||
self.assertEqual("agent:base-nested-containers", image)
|
||||
self.assertEqual("agent:base-nested-containers", calls[0][0])
|
||||
|
||||
def test_installs_the_whole_podman_5_networking_stack(self) -> None:
|
||||
"""Each missing piece fails at a different, misleading layer: no pasta
|
||||
and nothing starts; no nft and netavark cannot build the bridge that
|
||||
compose expects; no aardvark-dns and DNS inside nested containers
|
||||
fails while everything else looks healthy. Image pulls keep working
|
||||
throughout, which is what made these read as compat-API bugs."""
|
||||
seen: list[str] = []
|
||||
|
||||
def build(_image: str, _context: str, *, dockerfile: str) -> None:
|
||||
seen.append(Path(dockerfile).read_text(encoding="utf-8"))
|
||||
|
||||
nested_containers.build_image("agent:base", build)
|
||||
for package in ("passt", "nftables", "aardvark-dns"):
|
||||
self.assertIn(package, seen[0])
|
||||
|
||||
def test_strips_subordinate_ranges_so_podman_avoids_newuidmap(self) -> None:
|
||||
"""The single-UID fallback is the entire reason podman works here.
|
||||
|
||||
A subordinate range would send podman down the newuidmap path, which
|
||||
cannot write a multi-range uid_map without CAP_SYS_ADMIN in an Apple
|
||||
Container guest — the failure that killed the rootless-Docker spike.
|
||||
"""
|
||||
seen: list[str] = []
|
||||
|
||||
def build(_image: str, _context: str, *, dockerfile: str) -> None:
|
||||
seen.append(Path(dockerfile).read_text(encoding="utf-8"))
|
||||
|
||||
nested_containers.build_image("agent:base", build)
|
||||
text = seen[0]
|
||||
self.assertIn("sed -i '/^node:/d' /etc/subuid /etc/subgid", text)
|
||||
self.assertNotIn("subuid", text.replace(
|
||||
"sed -i '/^node:/d' /etc/subuid /etc/subgid", "",
|
||||
))
|
||||
|
||||
|
||||
class TestInitScript(unittest.TestCase):
|
||||
"""The bootstrap runs inside the bottle, so its wiring is only checkable
|
||||
here or on a live macOS host."""
|
||||
|
||||
def setUp(self) -> None:
|
||||
self.script = (
|
||||
Path(nested_containers.__file__).with_name("nested-containers-init.sh")
|
||||
.read_text(encoding="utf-8")
|
||||
)
|
||||
|
||||
def test_ca_bundle_path_matches_the_backend_constant(self) -> None:
|
||||
from bot_bottle.backend.util import AGENT_CA_BUNDLE
|
||||
self.assertIn(f'CA_BUNDLE="{AGENT_CA_BUNDLE}"', self.script)
|
||||
|
||||
def test_resolves_the_gateway_address_for_nested_containers(self) -> None:
|
||||
"""podman's hosts_file only applies to native `podman run` — the
|
||||
Docker-compat API ignores it, and the agent types `docker`. So the
|
||||
gateway name is resolved here and the *address* goes into the proxy
|
||||
URL; otherwise every nested container dies at "Could not resolve
|
||||
proxy", which reads like broken DNS but is a missing hosts entry."""
|
||||
self.assertIn('$2 == name { print $1; exit }', self.script)
|
||||
self.assertIn('value.replace(name, ip)', self.script)
|
||||
|
||||
def test_docker_cli_proxy_config_uses_the_address(self) -> None:
|
||||
"""The Docker CLI copies ~/.docker/config.json's proxies block into
|
||||
every container it starts. Being client-side it beats the podman
|
||||
service, so this — not containers.conf — is what decides whether a
|
||||
nested container can reach the proxy."""
|
||||
block = self.script[self.script.index('"proxies"'):]
|
||||
self.assertIn('"httpProxy": proxy.replace(name, ip)', block)
|
||||
self.assertIn('"httpsProxy": proxy.replace(name, ip)', block)
|
||||
self.assertIn('"noProxy": no_proxy', block)
|
||||
|
||||
def test_substitutes_the_address_into_the_service_environment(self) -> None:
|
||||
"""Covers what the Docker CLI does not stamp: podman's own registry
|
||||
pulls, and containers created through the API by another client."""
|
||||
launch = self.script[self.script.index("podman system service"):]
|
||||
self.assertNotIn("$GATEWAY_NAME", launch) # substitution precedes it
|
||||
setup = self.script[:self.script.index("podman system service")]
|
||||
self.assertIn("for var in HTTP_PROXY HTTPS_PROXY http_proxy https_proxy",
|
||||
setup)
|
||||
|
||||
def test_disables_podmans_own_proxy_passthrough(self) -> None:
|
||||
"""podman copies the host's proxy vars into every container by
|
||||
default, and that copy overrides the env we set — putting the
|
||||
unresolvable gateway name back and leaving nested containers at
|
||||
"bad address 'bot-bottle-gateway'"."""
|
||||
self.assertIn('"http_proxy=false"', self.script)
|
||||
|
||||
def test_keeps_the_gateway_name_in_no_proxy(self) -> None:
|
||||
"""NO_PROXY is matched against what a client asks for, and code inside
|
||||
a nested container still says bot-bottle-gateway."""
|
||||
start = self.script.index('for var in ("NO_PROXY"')
|
||||
loop = self.script[start:self.script.index("path = Path(", start)]
|
||||
self.assertIn('entries.append(f"{var}={value}")', loop)
|
||||
self.assertNotIn("replace(name, ip)", loop)
|
||||
self.assertIn('"noProxy": no_proxy', self.script)
|
||||
|
||||
def test_fails_closed_without_a_gateway_address(self) -> None:
|
||||
self.assertIn('[ -n "$gateway_ip" ] || {', self.script)
|
||||
|
||||
def test_mounts_and_trusts_the_gateway_ca(self) -> None:
|
||||
"""The gateway TLS-intercepts, so without the bundle every HTTPS call
|
||||
from a nested container fails with "unable to get local issuer
|
||||
certificate"."""
|
||||
self.assertIn('volumes=["{ca}:{ca}:ro"]', self.script)
|
||||
for var in (
|
||||
"SSL_CERT_FILE", "CURL_CA_BUNDLE", "REQUESTS_CA_BUNDLE",
|
||||
"NODE_EXTRA_CA_CERTS",
|
||||
):
|
||||
self.assertIn(f'f"{var}={{ca}}"', self.script)
|
||||
|
||||
def test_writes_the_token_bearing_config_unreadable_to_others(self) -> None:
|
||||
"""The proxy URL carries the bottle's identity token."""
|
||||
self.assertIn("path.chmod(0o600)", self.script)
|
||||
|
||||
|
||||
class TestGuestEnvironment(unittest.TestCase):
|
||||
def test_disabled_bottle_gets_no_docker_environment(self) -> None:
|
||||
self.assertEqual({}, nested_containers.guest_env(False))
|
||||
|
||||
def test_enabled_bottle_uses_only_the_guest_local_socket(self) -> None:
|
||||
env = nested_containers.guest_env(True)
|
||||
self.assertEqual("unix:///tmp/bbp/podman.sock", env["DOCKER_HOST"])
|
||||
self.assertNotIn("/var/run/docker.sock", " ".join(env.values()))
|
||||
|
||||
def test_runtime_dir_leaves_room_for_conmons_attach_socket(self) -> None:
|
||||
"""podman builds `$XDG_RUNTIME_DIR/libpod/tmp/socket/<64-hex>/attach`,
|
||||
which must fit in sun_path (108 bytes). A descriptive runtime dir blew
|
||||
past it and every attached `docker run` failed with "unable to upgrade
|
||||
to tcp, received 500" while pulls and detached runs looked fine."""
|
||||
attach = (
|
||||
nested_containers.guest_env(True)["XDG_RUNTIME_DIR"]
|
||||
+ "/libpod/tmp/socket/" + "a" * 64 + "/attach"
|
||||
)
|
||||
self.assertLessEqual(len(attach), 107, attach)
|
||||
|
||||
def test_macos_backend_declares_support(self) -> None:
|
||||
from bot_bottle.backend.macos_container.backend import (
|
||||
MacosContainerBottleBackend,
|
||||
)
|
||||
self.assertTrue(MacosContainerBottleBackend.supports_nested_containers)
|
||||
|
||||
|
||||
class TestBuildOrLoadImages(unittest.TestCase):
|
||||
def test_disabled_bottle_keeps_the_plain_agent_image(self) -> None:
|
||||
plan = _plan(
|
||||
slug="dev-abc", image="agent:base", dockerfile_path="/repo/Dockerfile",
|
||||
nested_containers=False, agent_provision=_AgentProvision("agent:base"),
|
||||
)
|
||||
with patch.object(launch_mod, "read_committed_image", return_value=None), \
|
||||
patch.object(launch_mod.container_mod, "build_image"), \
|
||||
patch.object(launch_mod.nested_containers_mod, "build_image") as derived:
|
||||
images = launch_mod.build_or_load_images(plan)
|
||||
derived.assert_not_called()
|
||||
self.assertEqual("agent:base", images.agent)
|
||||
|
||||
def test_enabled_bottle_builds_base_then_derived_variant(self) -> None:
|
||||
plan = _plan(
|
||||
slug="dev-abc", image="agent:base", dockerfile_path="/repo/Dockerfile",
|
||||
nested_containers=True, agent_provision=_AgentProvision("agent:base"),
|
||||
)
|
||||
with patch.object(launch_mod, "read_committed_image", return_value=None), \
|
||||
patch.object(launch_mod.container_mod, "build_image") as build, \
|
||||
patch.object(
|
||||
launch_mod.nested_containers_mod,
|
||||
"build_image",
|
||||
return_value="agent:base-nested-containers",
|
||||
) as derived:
|
||||
images = launch_mod.build_or_load_images(plan)
|
||||
|
||||
build.assert_called_once_with(
|
||||
"agent:base", launch_mod._REPO_DIR, # pylint: disable=protected-access
|
||||
dockerfile="/repo/Dockerfile",
|
||||
)
|
||||
derived.assert_called_once_with("agent:base", build)
|
||||
self.assertEqual("agent:base-nested-containers", images.agent)
|
||||
|
||||
def test_derived_image_layers_onto_a_committed_image(self) -> None:
|
||||
plan = _plan(
|
||||
slug="dev-abc", image="agent:base", dockerfile_path="/repo/Dockerfile",
|
||||
nested_containers=True, agent_provision=_AgentProvision("agent:base"),
|
||||
)
|
||||
with patch.object(
|
||||
launch_mod, "read_committed_image", return_value="agent:committed",
|
||||
), \
|
||||
patch.object(launch_mod.container_mod, "image_exists", return_value=True), \
|
||||
patch.object(launch_mod.container_mod, "build_image") as build, \
|
||||
patch.object(
|
||||
launch_mod.nested_containers_mod,
|
||||
"build_image",
|
||||
return_value="agent:committed-nested-containers",
|
||||
) as derived:
|
||||
images = launch_mod.build_or_load_images(plan)
|
||||
|
||||
build.assert_not_called()
|
||||
derived.assert_called_once_with("agent:committed", build)
|
||||
self.assertEqual("agent:committed-nested-containers", images.agent)
|
||||
|
||||
def test_cached_policy_refuses_to_build_the_derived_image(self) -> None:
|
||||
plan = _plan(
|
||||
slug="dev-abc", image="agent:base", dockerfile_path="/repo/Dockerfile",
|
||||
nested_containers=True, agent_provision=_AgentProvision("agent:base"),
|
||||
spec=_Spec(image_policy="cached"),
|
||||
)
|
||||
with patch.object(launch_mod, "read_committed_image", return_value=None), \
|
||||
patch.object(
|
||||
launch_mod.container_mod, "image_exists",
|
||||
side_effect=_base_image_only,
|
||||
), \
|
||||
patch.object(launch_mod.nested_containers_mod, "build_image") as derived, \
|
||||
patch.object(launch_mod, "die", side_effect=RuntimeError) as die:
|
||||
with self.assertRaises(RuntimeError):
|
||||
launch_mod.build_or_load_images(plan)
|
||||
derived.assert_not_called()
|
||||
self.assertIn("agent:base-nested-containers", die.call_args.args[0])
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -56,16 +56,6 @@ class TestMergeBottlesRuntime(unittest.TestCase):
|
||||
result = merge_bottles_runtime([base, override])
|
||||
self.assertFalse(result.supervise)
|
||||
|
||||
def test_nested_containers_survives_a_later_bottle(self):
|
||||
"""OR, not replace: a resolved bottle that never mentioned the key is
|
||||
indistinguishable from one that set it false, so `--bottle with-docker
|
||||
--bottle claude-dev` must not silently drop the capability."""
|
||||
enabled = _bottle(nested_containers=True)
|
||||
quiet = _bottle(env={"X": "1"})
|
||||
self.assertTrue(merge_bottles_runtime([enabled, quiet]).nested_containers)
|
||||
self.assertTrue(merge_bottles_runtime([quiet, enabled]).nested_containers)
|
||||
self.assertFalse(merge_bottles_runtime([quiet, quiet]).nested_containers)
|
||||
|
||||
def test_three_bottles_merged_left_to_right(self):
|
||||
b1 = _bottle(env={"A": "1", "B": "1", "C": "1"})
|
||||
b2 = _bottle(env={"B": "2", "C": "2"})
|
||||
|
||||
@@ -44,17 +44,6 @@ class TestBottleValidation(unittest.TestCase):
|
||||
with self.assertRaises(ManifestError):
|
||||
ManifestBottle.from_dict("b", {"supervise": "yes"})
|
||||
|
||||
def test_nested_containers_not_bool(self) -> None:
|
||||
with self.assertRaises(ManifestError):
|
||||
ManifestBottle.from_dict("b", {"nested_containers": "yes"})
|
||||
|
||||
def test_nested_containers_defaults_off(self) -> None:
|
||||
self.assertFalse(ManifestBottle.from_dict("b", {}).nested_containers)
|
||||
self.assertTrue(
|
||||
ManifestBottle.from_dict("b", {"nested_containers": True})
|
||||
.nested_containers
|
||||
)
|
||||
|
||||
def test_removed_runtime_field(self) -> None:
|
||||
with self.assertRaises(ManifestError):
|
||||
ManifestBottle.from_dict("b", {"runtime": "runsc"})
|
||||
|
||||
@@ -173,6 +173,58 @@ if __name__ == "__main__":
|
||||
unittest.main()
|
||||
|
||||
|
||||
class TestAgentSecrets(unittest.TestCase):
|
||||
"""store/get/delete for the bottled_agent_secrets table."""
|
||||
|
||||
def setUp(self) -> None:
|
||||
self._tmp = tempfile.TemporaryDirectory()
|
||||
self.db = Path(self._tmp.name) / "registry.db"
|
||||
self.store = RegistryStore(self.db)
|
||||
self.store.migrate()
|
||||
|
||||
def tearDown(self) -> None:
|
||||
self._tmp.cleanup()
|
||||
|
||||
def test_store_and_get_roundtrip(self) -> None:
|
||||
self.store.store_agent_secrets("bottle-1", {"EGRESS_TOKEN_1": "enc-val-a"})
|
||||
got = self.store.get_agent_secrets("bottle-1")
|
||||
self.assertEqual({"EGRESS_TOKEN_1": "enc-val-a"}, got)
|
||||
|
||||
def test_get_returns_empty_when_none_stored(self) -> None:
|
||||
self.assertEqual({}, self.store.get_agent_secrets("no-such-bottle"))
|
||||
|
||||
def test_store_replaces_existing_rows(self) -> None:
|
||||
self.store.store_agent_secrets("bottle-1", {"K": "old"})
|
||||
self.store.store_agent_secrets("bottle-1", {"K": "new", "K2": "v2"})
|
||||
got = self.store.get_agent_secrets("bottle-1")
|
||||
self.assertEqual({"K": "new", "K2": "v2"}, got)
|
||||
|
||||
def test_delete_removes_secrets(self) -> None:
|
||||
self.store.store_agent_secrets("bottle-1", {"K": "v"})
|
||||
self.store.delete_agent_secrets("bottle-1")
|
||||
self.assertEqual({}, self.store.get_agent_secrets("bottle-1"))
|
||||
|
||||
def test_delete_is_idempotent_on_missing(self) -> None:
|
||||
self.store.delete_agent_secrets("no-such-bottle") # must not raise
|
||||
|
||||
def test_secrets_are_isolated_by_bottle_id(self) -> None:
|
||||
self.store.store_agent_secrets("bottle-1", {"K": "for-1"})
|
||||
self.store.store_agent_secrets("bottle-2", {"K": "for-2"})
|
||||
self.assertEqual({"K": "for-1"}, self.store.get_agent_secrets("bottle-1"))
|
||||
self.assertEqual({"K": "for-2"}, self.store.get_agent_secrets("bottle-2"))
|
||||
|
||||
def test_secrets_isolated_by_type(self) -> None:
|
||||
self.store.store_agent_secrets("bottle-1", {"K": "injected"}, secret_type="injected_env_var")
|
||||
self.store.store_agent_secrets("bottle-1", {"K": "other"}, secret_type="other_type")
|
||||
self.assertEqual({"K": "injected"}, self.store.get_agent_secrets("bottle-1"))
|
||||
self.assertEqual({"K": "other"}, self.store.get_agent_secrets("bottle-1", secret_type="other_type"))
|
||||
|
||||
def test_secrets_persist_across_reopen(self) -> None:
|
||||
self.store.store_agent_secrets("bottle-1", {"K": "v"})
|
||||
reopened = RegistryStore(self.db)
|
||||
self.assertEqual({"K": "v"}, reopened.get_agent_secrets("bottle-1"))
|
||||
|
||||
|
||||
class TestReapAbsent(unittest.TestCase):
|
||||
"""`reap_absent` — the self-heal for rows whose bottle is gone.
|
||||
|
||||
|
||||
@@ -0,0 +1,96 @@
|
||||
"""Unit tests for per-bottle egress secret encryption (PRD prd-new-secret-provider)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import unittest
|
||||
|
||||
from bot_bottle.orchestrator.secret_store import (
|
||||
ENV_VAR_SECRET_NAME,
|
||||
decrypt_value,
|
||||
encrypt_value,
|
||||
new_env_var_secret,
|
||||
)
|
||||
|
||||
|
||||
class TestNewEnvVarSecret(unittest.TestCase):
|
||||
def test_returns_non_empty_string(self) -> None:
|
||||
s = new_env_var_secret()
|
||||
self.assertIsInstance(s, str)
|
||||
self.assertTrue(len(s) > 0)
|
||||
|
||||
def test_secrets_are_unique(self) -> None:
|
||||
keys = {new_env_var_secret() for _ in range(50)}
|
||||
self.assertEqual(50, len(keys))
|
||||
|
||||
def test_no_padding_characters(self) -> None:
|
||||
# URL-safe base64, padding stripped — should round-trip cleanly
|
||||
for _ in range(20):
|
||||
self.assertNotIn("=", new_env_var_secret())
|
||||
|
||||
|
||||
class TestEncryptDecryptRoundtrip(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self.secret = new_env_var_secret()
|
||||
|
||||
def _rt(self, plaintext: str) -> str:
|
||||
return decrypt_value(self.secret, encrypt_value(self.secret, plaintext))
|
||||
|
||||
def test_roundtrip_short_value(self) -> None:
|
||||
self.assertEqual("sk-abc123", self._rt("sk-abc123"))
|
||||
|
||||
def test_roundtrip_empty_string(self) -> None:
|
||||
self.assertEqual("", self._rt(""))
|
||||
|
||||
def test_roundtrip_long_value_crosses_block_boundary(self) -> None:
|
||||
# 32 bytes is exactly one HMAC-SHA256 block; 65 bytes crosses two.
|
||||
plaintext = "x" * 65
|
||||
self.assertEqual(plaintext, self._rt(plaintext))
|
||||
|
||||
def test_roundtrip_unicode(self) -> None:
|
||||
self.assertEqual("héllo wörld", self._rt("héllo wörld"))
|
||||
|
||||
def test_encrypt_produces_different_ciphertexts_each_call(self) -> None:
|
||||
ct1 = encrypt_value(self.secret, "same")
|
||||
ct2 = encrypt_value(self.secret, "same")
|
||||
self.assertNotEqual(ct1, ct2) # fresh nonce each call
|
||||
|
||||
def test_ciphertext_is_url_safe_base64(self) -> None:
|
||||
ct = encrypt_value(self.secret, "hello")
|
||||
# no '+', '/', '=' — URL-safe and padding-stripped
|
||||
for ch in ("+", "/", "="):
|
||||
self.assertNotIn(ch, ct)
|
||||
|
||||
|
||||
class TestDecryptErrors(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self.secret = new_env_var_secret()
|
||||
|
||||
def test_wrong_key_raises_value_error(self) -> None:
|
||||
ct = encrypt_value(self.secret, "secret-token")
|
||||
other_key = new_env_var_secret()
|
||||
# Wrong key produces garbage bytes; decrypt_value raises ValueError
|
||||
# when the result is non-UTF-8 (which is very likely for 12-char data).
|
||||
# We allow it to succeed only if garbage happens to be valid UTF-8, but
|
||||
# the plaintext must not match.
|
||||
try:
|
||||
result = decrypt_value(other_key, ct)
|
||||
self.assertNotEqual("secret-token", result)
|
||||
except ValueError:
|
||||
pass
|
||||
|
||||
def test_truncated_blob_raises_value_error(self) -> None:
|
||||
with self.assertRaises(ValueError):
|
||||
decrypt_value(self.secret, "dG9vc2hvcnQ") # "tooshort" — under 16 nonce bytes
|
||||
|
||||
def test_invalid_base64_raises_value_error(self) -> None:
|
||||
with self.assertRaises(ValueError):
|
||||
decrypt_value(self.secret, "!!not-base64!!")
|
||||
|
||||
|
||||
class TestConstant(unittest.TestCase):
|
||||
def test_env_var_secret_name(self) -> None:
|
||||
self.assertEqual("ENV_VAR_SECRET", ENV_VAR_SECRET_NAME)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
Reference in New Issue
Block a user