Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 didericis-claude
|
385cca72a7 |
@@ -103,16 +103,14 @@ jobs:
|
||||
- name: Install coverage
|
||||
run: python3 -m pip install --break-system-packages coverage
|
||||
|
||||
# Fail loudly if the backend this job promises isn't actually usable,
|
||||
# rather than letting every test silently `unittest.skip` and the job
|
||||
# go green on zero coverage. `backend status` prints a clear per-check
|
||||
# summary (docker on PATH, daemon reachable) and exits non-zero when a
|
||||
# prerequisite is missing — the same readiness check the skip guards
|
||||
# gate on via `has_backend`.
|
||||
- name: Preflight — Docker backend is ready
|
||||
- name: Show environment
|
||||
run: |
|
||||
python3 --version
|
||||
python3 cli.py backend status --backend=docker
|
||||
if command -v docker >/dev/null 2>&1; then
|
||||
docker version || true
|
||||
else
|
||||
echo "docker not on PATH — integration tests will skip"
|
||||
fi
|
||||
|
||||
- name: Run integration tests (docker) with coverage
|
||||
env:
|
||||
|
||||
@@ -35,7 +35,6 @@ backend remains available with `BOT_BOTTLE_BACKEND=docker` or
|
||||
- `.bot-bottle/` — per-repo agent and bottle manifests (YAML markdown format).
|
||||
- `examples/` — example bottles and agents showing the manifest format.
|
||||
- `docs/README.md` — docs overview; when to write which document.
|
||||
- `docs/glossary.md` — canonical term definitions (Agent Provider, Bottle, Sealed Bottle, etc.).
|
||||
- `docs/prds/` — product requirement docs (see `docs/prds/README.md` for format).
|
||||
- `docs/research/` — research notes (see `docs/research/README.md`).
|
||||
- `docs/decisions/` — decision records (ADR-lite).
|
||||
|
||||
+5
-5
@@ -8,8 +8,8 @@
|
||||
# this image's mitmproxy / git / gitleaks payload.
|
||||
#
|
||||
# Collapses the prior per-daemon images (egress, git-gate,
|
||||
# supervise) into one. A small stdlib-Python init supervisor
|
||||
# (`bot_bottle.gateway.bootstrap`) spawns all daemons, forwards SIGTERM, and
|
||||
# supervise) into one. A small stdlib-Python init supervisor at
|
||||
# /app/gateway_init.py spawns all daemons, forwards SIGTERM, and
|
||||
# propagates per-daemon stdout/stderr to the container log with a
|
||||
# `[name]` prefix. See PRD 0024 for the rationale.
|
||||
#
|
||||
@@ -102,8 +102,8 @@ RUN pip install --no-cache-dir /src/
|
||||
# WORKDIR here also creates /app so the shim + COPYs below can write into it
|
||||
# (nothing created /app before this point).
|
||||
WORKDIR /app
|
||||
RUN printf 'from bot_bottle.gateway.egress.addon import addons\n' > /app/egress_addon.py
|
||||
COPY bot_bottle/gateway/egress/entrypoint.sh /app/egress-entrypoint.sh
|
||||
RUN printf 'from bot_bottle.egress_addon import addons\n' > /app/egress_addon.py
|
||||
COPY bot_bottle/egress_entrypoint.sh /app/egress-entrypoint.sh
|
||||
RUN chmod +x /app/egress-entrypoint.sh
|
||||
|
||||
# Pre-create runtime directories the compose renderer + start
|
||||
@@ -123,4 +123,4 @@ EXPOSE 8888 9099 9418 9420 9100
|
||||
|
||||
# PID 1 is the supervisor. It owns signal handling and exit-code
|
||||
# propagation; no `exec` chain in the entrypoint itself.
|
||||
ENTRYPOINT ["python3", "-m", "bot_bottle.gateway.bootstrap"]
|
||||
ENTRYPOINT ["python3", "-m", "bot_bottle.gateway_init"]
|
||||
|
||||
@@ -5,10 +5,16 @@ from __future__ import annotations
|
||||
import sqlite3
|
||||
from pathlib import Path
|
||||
|
||||
from ..supervisor.types import AuditEntry
|
||||
from ..paths import host_db_path
|
||||
from .db_store import DbStore
|
||||
from .migrations import TableMigrations
|
||||
try:
|
||||
from .supervise_types import AuditEntry
|
||||
from .paths import host_db_path
|
||||
from .db_store import DbStore
|
||||
from .migrations import TableMigrations
|
||||
except ImportError:
|
||||
from supervise_types import AuditEntry # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
from paths import host_db_path # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
from db_store import DbStore # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
from migrations import TableMigrations # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
|
||||
|
||||
class AuditStore(DbStore):
|
||||
+819
-83
@@ -1,115 +1,851 @@
|
||||
"""The bottle-backend package: abstract contract + backend selection.
|
||||
"""Per-backend bottle factories.
|
||||
|
||||
Thin by design — nothing framework-heavy is imported at package init, so
|
||||
importing any `backend.*` submodule (e.g. `backend.docker.util`) doesn't drag
|
||||
the manifest / egress / git-gate framework into memory. The public names are
|
||||
re-exported lazily:
|
||||
A bottle is a running, isolated environment with claude inside. Each
|
||||
backend exposes five methods:
|
||||
|
||||
* the abstract contract (`BottleBackend`, `BottleSpec`, `Bottle`, …) lives in
|
||||
`backend.base`;
|
||||
* backend selection / enumeration (`get_bottle_backend`,
|
||||
`enumerate_active_agents`, …) in `backend.selection`;
|
||||
* the concrete backends and the freeze helpers in their own submodules.
|
||||
prepare(spec, stage_dir=...) -> BottlePlan
|
||||
Resolves names, validates host-side prerequisites, and writes
|
||||
scratch files. No remote/runtime resources are created yet.
|
||||
Safe to call before the y/N preflight.
|
||||
|
||||
`from bot_bottle.backend import X` resolves X on first access via `__getattr__`
|
||||
and caches it at package level, so existing call-sites (and
|
||||
`patch.object(backend_mod, X, …)`) keep working.
|
||||
launch(plan) -> ContextManager[Bottle]
|
||||
Brings up the container (or VM, or remote machine), provisions
|
||||
it, yields a Bottle handle, and tears everything down on exit.
|
||||
|
||||
prepare_cleanup() -> BottleCleanupPlan
|
||||
Enumerates orphaned resources left behind by previous bottles
|
||||
(containers, networks, ...). Idempotent; no side effects.
|
||||
|
||||
cleanup(plan) -> None
|
||||
Actually removes everything described by the cleanup plan.
|
||||
|
||||
enumerate_active() -> Sequence[ActiveAgent]
|
||||
Return every currently-running bottle on this backend, with
|
||||
enough metadata for callers (CLI `list active`, dashboard
|
||||
agents pane) to render a row.
|
||||
|
||||
Selection is driven by `--backend` on `start` or BOT_BOTTLE_BACKEND
|
||||
(env var). When neither is set, compatible macOS hosts default to
|
||||
`macos-container`; Linux hosts with KVM default to `firecracker`;
|
||||
otherwise `docker`. Per PRD 0003 the manifest does not carry a
|
||||
backend field; the host picks.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING, Any
|
||||
import os
|
||||
import shlex
|
||||
import sys
|
||||
from abc import ABC, abstractmethod
|
||||
from contextlib import AbstractContextManager, contextmanager
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
from typing import TYPE_CHECKING, Any, Generator, Generic, Sequence, TypeVar
|
||||
|
||||
from ..agent_provider import AgentProvisionPlan, get_provider, build_agent_provision_plan
|
||||
from ..egress import EgressPlan
|
||||
from ..git_gate import GitGatePlan
|
||||
from ..log import die, info, warn
|
||||
from ..util import read_tty_line
|
||||
from ..manifest import Manifest, ManifestIndex
|
||||
from ..supervise import SupervisePlan
|
||||
from ..util import expand_tilde
|
||||
from ..env import resolve_env, ResolvedEnv
|
||||
from ..workspace import WorkspacePlan, workspace_plan
|
||||
from .print_util import print_multi, visible_agent_env_names
|
||||
from .util import host_skill_dir
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from .base import (
|
||||
ActiveAgent,
|
||||
BackendStatus,
|
||||
Bottle,
|
||||
BottleBackend,
|
||||
BottleCleanupPlan,
|
||||
BottleImages,
|
||||
BottlePlan,
|
||||
BottleSpec,
|
||||
ExecResult,
|
||||
)
|
||||
from .selection import (
|
||||
enumerate_active_agents,
|
||||
get_bottle_backend,
|
||||
has_backend,
|
||||
is_backend_available,
|
||||
is_backend_ready,
|
||||
known_backend_names,
|
||||
)
|
||||
from .docker import DockerBottleBackend
|
||||
from .firecracker import FirecrackerBottleBackend
|
||||
from .macos_container import MacosContainerBottleBackend
|
||||
from .freeze import CommitCancelled, Freezer, get_freezer
|
||||
|
||||
|
||||
# Public name -> submodule that defines it. Contract types resolve from `base`,
|
||||
# selection/enumeration from `selection`, the concrete backends + freeze helpers
|
||||
# from their own subpackages.
|
||||
_LAZY_MODULES: dict[str, str] = {
|
||||
"BottleSpec": "base",
|
||||
"BottlePlan": "base",
|
||||
"BottleCleanupPlan": "base",
|
||||
"ExecResult": "base",
|
||||
"ActiveAgent": "base",
|
||||
"Bottle": "base",
|
||||
"BottleImages": "base",
|
||||
"BottleBackend": "base",
|
||||
"BackendStatus": "base",
|
||||
"get_bottle_backend": "selection",
|
||||
"known_backend_names": "selection",
|
||||
"has_backend": "selection",
|
||||
"is_backend_available": "selection",
|
||||
"is_backend_ready": "selection",
|
||||
"enumerate_active_agents": "selection",
|
||||
"_print_vm_install_instructions": "selection",
|
||||
"DockerBottleBackend": "docker",
|
||||
"FirecrackerBottleBackend": "firecracker",
|
||||
"MacosContainerBottleBackend": "macos_container",
|
||||
"CommitCancelled": "freeze",
|
||||
"Freezer": "freeze",
|
||||
"get_freezer": "freeze",
|
||||
}
|
||||
@dataclass(frozen=True)
|
||||
class BottleSpec:
|
||||
"""CLI-supplied intent. Backend-agnostic — each backend's prepare
|
||||
step consumes it and produces its own backend-specific plan.
|
||||
Resolved values (image names, container name, scratch paths, runsc
|
||||
availability) live on the plan, not the spec."""
|
||||
|
||||
manifest: ManifestIndex
|
||||
agent_name: str
|
||||
copy_cwd: bool
|
||||
user_cwd: str
|
||||
# PRD 0016 follow-up: when set, the backend's prepare step uses
|
||||
# this identity instead of minting a fresh one — the resume path
|
||||
# (`cli.py resume <identity>`) sets this to continue an existing
|
||||
# bottle's state. Empty string for a fresh `start`.
|
||||
identity: str = ""
|
||||
label: str = ""
|
||||
color: str = ""
|
||||
# Ordered bottle names selected at launch (issue #269). When non-empty
|
||||
# they are merged in order and replace the agent's `bottle:` field.
|
||||
bottle_names: tuple[str, ...] = ()
|
||||
# True when launched via --headless (no TTY, no interactive prompts).
|
||||
# The git-gate host-key preflight uses this to error rather than prompt.
|
||||
headless: bool = False
|
||||
# Image startup policy. "fresh" preserves the normal build path;
|
||||
# "cached" reuses the current local image/artifact without rebuilding.
|
||||
image_policy: str = "fresh"
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class BottlePlan(ABC):
|
||||
"""Base output of a backend's prepare step. Concrete subclasses
|
||||
(e.g. DockerBottlePlan) add backend-specific resolved fields."""
|
||||
|
||||
spec: BottleSpec
|
||||
manifest: Manifest
|
||||
stage_dir: Path
|
||||
git_gate_plan: GitGatePlan
|
||||
|
||||
@property
|
||||
def guest_home(self) -> str:
|
||||
return self.agent_provision.guest_home
|
||||
|
||||
@property
|
||||
def git_gate_insteadof_host(self) -> str:
|
||||
"""Host (and optional port) used in git-gate insteadOf URLs.
|
||||
Docker uses the compose-network DNS alias; VM backends may
|
||||
override with an IP:port when the guest has no DNS."""
|
||||
return "git-gate"
|
||||
|
||||
@property
|
||||
def git_gate_insteadof_scheme(self) -> str:
|
||||
"""URL scheme for git-gate insteadOf rewrites. 'git' for
|
||||
Docker (git daemon); VM backends may override (e.g. 'http'
|
||||
over a published host port)."""
|
||||
return "git"
|
||||
egress_plan: EgressPlan
|
||||
supervise_plan: SupervisePlan | None
|
||||
agent_provision: AgentProvisionPlan
|
||||
|
||||
@property
|
||||
def workspace_plan(self) -> WorkspacePlan:
|
||||
return workspace_plan(self.spec, guest_home=self.guest_home)
|
||||
|
||||
def print(self) -> None:
|
||||
"""Render the y/N preflight summary to stderr."""
|
||||
spec = self.spec
|
||||
manifest = self.manifest
|
||||
agent = manifest.agent
|
||||
bottle = manifest.bottle
|
||||
|
||||
env_names = visible_agent_env_names(
|
||||
sorted(
|
||||
set(bottle.env.keys())
|
||||
| set(self.agent_provision.guest_env.keys())
|
||||
),
|
||||
hidden_env_names=self.agent_provision.hidden_env_names,
|
||||
)
|
||||
|
||||
print(file=sys.stderr)
|
||||
info(f"agent : {spec.agent_name}")
|
||||
info(f"provider : {self.agent_provision.template}")
|
||||
print_multi("env ", env_names)
|
||||
print_multi("skills ", list(agent.skills))
|
||||
effective_bottles = (
|
||||
list(spec.bottle_names) if spec.bottle_names
|
||||
else ([agent.bottle] if agent.bottle else [])
|
||||
)
|
||||
print_multi("bottle ", effective_bottles)
|
||||
|
||||
identity = manifest.git_identity_summary()
|
||||
if identity:
|
||||
info(f" git identity : {identity}")
|
||||
|
||||
git_lines = [
|
||||
f"{u.name} → {u.upstream_host}:{u.upstream_port}"
|
||||
for u in self.git_gate_plan.upstreams
|
||||
]
|
||||
if git_lines:
|
||||
print_multi(" git gate ", git_lines)
|
||||
|
||||
if self.egress_plan.routes:
|
||||
egress_lines = []
|
||||
for r in self.egress_plan.routes:
|
||||
auth = f" [auth:{r.auth_scheme}]" if r.auth_scheme else ""
|
||||
egress_lines.append(f"{r.host}{auth}")
|
||||
print_multi(" egress ", egress_lines)
|
||||
print(file=sys.stderr)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class BottleCleanupPlan(ABC):
|
||||
"""Base output of a backend's prepare_cleanup step. Concrete
|
||||
subclasses (e.g. DockerBottleCleanupPlan) carry backend-specific
|
||||
lists of resources to be removed and implement `print` + `empty`."""
|
||||
|
||||
@abstractmethod
|
||||
def print(self) -> None:
|
||||
"""Render the cleanup y/N summary to stderr."""
|
||||
|
||||
@property
|
||||
@abstractmethod
|
||||
def empty(self) -> bool:
|
||||
"""True iff there is nothing to clean up; the CLI uses this to
|
||||
short-circuit before showing the y/N."""
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ExecResult:
|
||||
"""Captured result of `Bottle.exec`. Backend-neutral: the Docker
|
||||
impl populates it from a `subprocess.CompletedProcess`, but a
|
||||
VM backend could populate it from any source that produces a
|
||||
returncode + captured streams."""
|
||||
|
||||
returncode: int
|
||||
stdout: str
|
||||
stderr: str
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ActiveAgent:
|
||||
"""One currently-running agent, as the CLI `list active` and
|
||||
dashboard agents pane render it. ("Agent" is the project's
|
||||
consistent name for the thing running inside a bottle — the
|
||||
bottle is the container, the agent is what runs in it.)
|
||||
|
||||
Fields are deliberately backend-neutral. `services` is the set
|
||||
of gateway daemons currently up for this bottle (`egress`,
|
||||
`git-gate`, `supervise`); the dashboard uses it to
|
||||
gate edit verbs. `backend_name` is the matching key in
|
||||
`_BACKENDS` (`docker` / `firecracker` / `macos-container`) — used by the active-
|
||||
list rendering to disambiguate and by the dashboard's
|
||||
re-attach path."""
|
||||
|
||||
backend_name: str
|
||||
slug: str
|
||||
agent_name: str # from metadata.json; "?" if missing
|
||||
started_at: str # ISO 8601 from metadata.json; "" if missing
|
||||
services: tuple[str, ...] # alphabetical
|
||||
label: str = ""
|
||||
color: str = ""
|
||||
|
||||
|
||||
class Bottle(ABC):
|
||||
"""Handle to a running bottle. Yielded by a backend's launch step.
|
||||
|
||||
`exec_agent` runs the selected agent CLI inside the bottle and
|
||||
blocks until the session ends. `exec` runs a POSIX shell script inside the bottle
|
||||
and returns the captured result. `cp_in` copies a host path into
|
||||
the bottle. `close` is an idempotent alias for context-manager
|
||||
teardown.
|
||||
"""
|
||||
|
||||
name: str
|
||||
|
||||
@abstractmethod
|
||||
def agent_argv(
|
||||
self, argv: list[str], *, tty: bool = True,
|
||||
) -> list[str]:
|
||||
"""Return the host-side argv that runs the selected agent
|
||||
inside the bottle. Used by `exec_agent` for foreground
|
||||
handoffs and by the dashboard's tmux `respawn-pane` flow,
|
||||
which needs the argv up front (it spawns claude in a tmux
|
||||
pane rather than as a child of the current process).
|
||||
|
||||
Implementations transparently inject
|
||||
`--append-system-prompt-file` when the bottle was launched
|
||||
with a provisioned prompt path."""
|
||||
...
|
||||
|
||||
@abstractmethod
|
||||
def exec_agent(self, argv: list[str], *, tty: bool = True) -> int: ...
|
||||
|
||||
@abstractmethod
|
||||
def exec(self, script: str, *, user: str = "node") -> ExecResult:
|
||||
"""Run `script` as a POSIX shell script inside the bottle as
|
||||
`user` (default `node`, matching the agent image's USER
|
||||
directive) and return the captured stdout/stderr/returncode.
|
||||
The bottle's environment (including HTTPS_PROXY pointing at
|
||||
the egress daemon) is inherited by the child. Non-zero
|
||||
exit does not raise — callers inspect `returncode`
|
||||
themselves.
|
||||
|
||||
Pass `user="root"` for shell-outs that need privileged file
|
||||
writes / package install — provisioning calls that need root
|
||||
bypass `Bottle.exec` and use the backend-specific raw
|
||||
machine-exec helper, but the tests have a legitimate use
|
||||
case for arbitrary-user runs."""
|
||||
|
||||
@abstractmethod
|
||||
def cp_in(self, host_path: str, container_path: str) -> None: ...
|
||||
|
||||
@abstractmethod
|
||||
def close(self) -> None: ...
|
||||
|
||||
|
||||
|
||||
|
||||
PlanT = TypeVar("PlanT", bound=BottlePlan)
|
||||
CleanupT = TypeVar("CleanupT", bound=BottleCleanupPlan)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class BottleImages:
|
||||
"""Resolved image references (or artifact paths) for a bottle launch.
|
||||
|
||||
For Docker/macOS-container backends, `agent` and `sidecar` are string
|
||||
image refs. For the smolmachines backend they are Path objects pointing
|
||||
to pre-built `.smolmachine` artifacts."""
|
||||
|
||||
agent: str | Path
|
||||
sidecar: str | Path = ""
|
||||
|
||||
|
||||
class BottleBackend(ABC, Generic[PlanT, CleanupT]):
|
||||
"""Abstract base for selectable bottle backends. Concrete subclasses
|
||||
(e.g. DockerBottleBackend) own their own prepare/launch impls.
|
||||
Parameterized over the backend's concrete plan + cleanup-plan types
|
||||
so subclass methods get the narrow type without isinstance
|
||||
boilerplate."""
|
||||
|
||||
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
|
||||
backend-specific resolution (names, scratch files, etc.). The
|
||||
validation step is enforced here so a future backend cannot
|
||||
accidentally skip it. No remote/runtime resources are created."""
|
||||
from .resolve_common import (
|
||||
merge_provision_env_vars,
|
||||
mint_slug,
|
||||
prepare_agent_state_dir,
|
||||
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
|
||||
manifest = preflight_host_keys(
|
||||
manifest,
|
||||
headless=spec.headless,
|
||||
home_md=spec.manifest.home_md,
|
||||
)
|
||||
|
||||
manifest_bottle = manifest.bottle
|
||||
manifest_agent_provider = manifest_bottle.agent_provider
|
||||
agent_provider = get_provider(manifest_agent_provider.template)
|
||||
resolved_env = resolve_env(manifest)
|
||||
workspace = workspace_plan(spec, guest_home=agent_provider.guest_home)
|
||||
|
||||
slug = mint_slug(spec)
|
||||
write_launch_metadata(slug, spec, compose_project="", backend=self.name)
|
||||
|
||||
# Manifest may override the Dockerfile per-bottle; otherwise fall
|
||||
# back to the provider plugin's bundled Dockerfile (next to its
|
||||
# agent_provider.py module).
|
||||
if manifest_agent_provider.dockerfile:
|
||||
agent_dockerfile_path = resolve_manifest_dockerfile(
|
||||
manifest_agent_provider.dockerfile, spec,
|
||||
)
|
||||
else:
|
||||
agent_dockerfile_path = str(agent_provider.dockerfile)
|
||||
|
||||
agent_dir, prompt_file = prepare_agent_state_dir(slug, manifest)
|
||||
|
||||
agent_provision_plan = build_agent_provision_plan(
|
||||
template=manifest_agent_provider.template,
|
||||
dockerfile=agent_dockerfile_path,
|
||||
state_dir=agent_dir,
|
||||
instance_name=f"bot-bottle-{slug}",
|
||||
prompt_file=prompt_file,
|
||||
guest_env=self._build_guest_env(resolved_env),
|
||||
forward_host_credentials=manifest_agent_provider.forward_host_credentials,
|
||||
auth_token=manifest_agent_provider.auth_token,
|
||||
host_env=dict(os.environ),
|
||||
trusted_project_path=workspace.workdir,
|
||||
label=spec.label,
|
||||
color=spec.color,
|
||||
provider_settings=manifest_agent_provider.settings,
|
||||
)
|
||||
agent_provision_plan = merge_provision_env_vars(agent_provision_plan)
|
||||
egress_plan = prepare_egress(manifest_bottle, slug, agent_provision_plan)
|
||||
supervise_plan = prepare_supervise(manifest_bottle, slug)
|
||||
git_gate_plan = prepare_git_gate(manifest_bottle, slug)
|
||||
|
||||
return self._resolve_plan(
|
||||
spec,
|
||||
manifest=manifest,
|
||||
slug=slug,
|
||||
resolved_env=resolved_env,
|
||||
agent_provision_plan=agent_provision_plan,
|
||||
egress_plan=egress_plan,
|
||||
supervise_plan=supervise_plan,
|
||||
git_gate_plan=git_gate_plan,
|
||||
stage_dir=stage_dir,
|
||||
)
|
||||
|
||||
def _build_guest_env(self, resolved_env: ResolvedEnv) -> dict[str, str]:
|
||||
return {}
|
||||
|
||||
def _preflight(self) -> None:
|
||||
"""
|
||||
tasks to do before resolving a plan
|
||||
"""
|
||||
pass
|
||||
|
||||
def _validate(self, spec: BottleSpec) -> Manifest:
|
||||
"""Cross-backend pre-launch checks. Parses the selected agent and
|
||||
its bottle (raising ManifestError on invalid content), confirms
|
||||
skills are present on the host, and every git IdentityFile resolves.
|
||||
|
||||
Returns the loaded Manifest for the selected agent. Subclasses with
|
||||
additional preconditions should override and call
|
||||
`super()._validate(spec)` first."""
|
||||
manifest = spec.manifest.load_for_agent(spec.agent_name, spec.bottle_names)
|
||||
self._validate_skills(manifest.agent.skills)
|
||||
self._validate_agent_provider_dockerfile(spec, manifest)
|
||||
return manifest
|
||||
|
||||
def _validate_skills(self, skills: Sequence[str]) -> None:
|
||||
"""Each named skill must be a directory under the host's
|
||||
`~/.claude/skills/`. The check is purely host-side, so the
|
||||
default impl covers every backend."""
|
||||
for name in skills:
|
||||
path = host_skill_dir(name)
|
||||
if not os.path.isdir(path):
|
||||
die(
|
||||
f"skill '{name}' not found on host at {path}. "
|
||||
f"Create it under ~/.claude/skills/, then re-run."
|
||||
)
|
||||
|
||||
def _validate_agent_provider_dockerfile(self, spec: BottleSpec, manifest: Manifest) -> None:
|
||||
bottle = manifest.bottle
|
||||
dockerfile = bottle.agent_provider.dockerfile
|
||||
if not dockerfile:
|
||||
return
|
||||
path = Path(expand_tilde(dockerfile))
|
||||
if not path.is_absolute():
|
||||
path = Path(spec.user_cwd) / path
|
||||
if not path.is_file():
|
||||
effective = (
|
||||
", ".join(spec.bottle_names) if spec.bottle_names else manifest.agent.bottle
|
||||
)
|
||||
die(
|
||||
f"agent_provider.dockerfile for bottle "
|
||||
f"'{effective}' not found: {path}"
|
||||
)
|
||||
|
||||
@abstractmethod
|
||||
def _resolve_plan(self,
|
||||
spec: BottleSpec,
|
||||
*,
|
||||
manifest: Manifest,
|
||||
slug: str,
|
||||
resolved_env: ResolvedEnv,
|
||||
agent_provision_plan: AgentProvisionPlan,
|
||||
egress_plan: EgressPlan,
|
||||
git_gate_plan: GitGatePlan,
|
||||
supervise_plan: SupervisePlan | None,
|
||||
stage_dir: Path) -> PlanT:
|
||||
"""Backend-specific plan resolution: image/container names,
|
||||
env-file, prompt-file, proxy plan, runtime detection. Called by
|
||||
`prepare` after `_validate` succeeds. Instance name, image,
|
||||
prompt file, Dockerfile path, and guest home all live on
|
||||
`agent_provision_plan` — the source of truth."""
|
||||
|
||||
def prelaunch_checks(self, plan: PlanT) -> None:
|
||||
"""Raise StaleImageError if any cached image used by this plan is stale.
|
||||
No-op default; backends override to call the shared check_stale*
|
||||
helpers on their image/artifact timestamps. Called by the CLI before
|
||||
launch so the operator can be prompted outside the launch context."""
|
||||
|
||||
@contextmanager
|
||||
def launch(self, plan: PlanT) -> Generator[Bottle, None, None]:
|
||||
"""Template: build or load images, then delegate to _launch_impl."""
|
||||
images = self._build_or_load_images(plan)
|
||||
with self._launch_impl(plan, images) as bottle:
|
||||
yield bottle
|
||||
|
||||
@abstractmethod
|
||||
def _build_or_load_images(self, plan: PlanT) -> BottleImages:
|
||||
"""Return the agent and sidecar image references (or artifact paths)
|
||||
for this plan, building fresh images when the policy requires it."""
|
||||
|
||||
@abstractmethod
|
||||
def _launch_impl(self, plan: PlanT, images: BottleImages) -> AbstractContextManager[Bottle]:
|
||||
"""Bring up the bottle using pre-resolved images; yield a handle; tear down on exit."""
|
||||
|
||||
def provision(self, plan: PlanT, bottle: "Bottle") -> str | None:
|
||||
"""Copy host-side files (CA cert, prompt, skills, .git) into
|
||||
the running bottle. Called from `launch` after the container
|
||||
/ machine is up. Returns the in-container prompt path if a
|
||||
prompt was provisioned, else None — the Bottle handle uses it
|
||||
to decide whether to add provider-specific prompt args to the
|
||||
agent's argv.
|
||||
|
||||
Default orchestration: ca → prompt → provider apply → skills
|
||||
→ workspace → git → supervise-mcp. CA install runs first so
|
||||
the agent's trust store is rebuilt before anything inside the
|
||||
agent makes a TLS call.
|
||||
|
||||
Per PRD 0050 the per-provider steps (prompt, skills,
|
||||
declarative provision-plan apply, supervise MCP registration)
|
||||
live on the `AgentProvider` plugin. The backend only owns the
|
||||
steps that are about backend infrastructure (CA, workspace,
|
||||
git) and surfaces the supervise daemon URL its launch step
|
||||
knows about via `supervise_mcp_url`.
|
||||
|
||||
PRD 0017: cred-proxy's agent-side dotfile rewrites (~/.npmrc,
|
||||
~/.gitconfig insteadOf, tea config) are gone. Egress-proxy is
|
||||
on the agent's HTTP_PROXY path so every tool that respects
|
||||
HTTPS_PROXY (claude-code, git over HTTPS, npm, curl) is
|
||||
intercepted without per-tool reconfiguration."""
|
||||
provider = get_provider(plan.agent_provision.template)
|
||||
provider.provision_ca(bottle, plan)
|
||||
prompt_path = provider.provision_prompt(plan, bottle)
|
||||
provider.provision(plan, bottle)
|
||||
provider.provision_skills(plan, bottle)
|
||||
self.provision_workspace(plan, bottle)
|
||||
provider.provision_git(bottle, plan)
|
||||
provider.provision_supervise_mcp(
|
||||
plan, bottle, self.supervise_mcp_url(plan),
|
||||
)
|
||||
return prompt_path
|
||||
|
||||
def provision_workspace(self, plan: PlanT, bottle: "Bottle") -> None:
|
||||
"""Copy the operator workspace into the running bottle.
|
||||
|
||||
This is the only supported workspace-provisioning path: Docker
|
||||
does not build a derived image containing the current
|
||||
workspace."""
|
||||
workspace = plan.workspace_plan
|
||||
if not (workspace.enabled and workspace.copy_contents):
|
||||
return
|
||||
|
||||
guest_parent = workspace.guest_path.rsplit("/", 1)[0] or "/"
|
||||
guest_path = shlex.quote(workspace.guest_path)
|
||||
guest_parent = shlex.quote(guest_parent)
|
||||
owner = shlex.quote(workspace.owner)
|
||||
mode = shlex.quote(workspace.mode)
|
||||
info(f"copying {workspace.host_path} -> {bottle.name}:{workspace.guest_path}")
|
||||
bottle.exec(
|
||||
f"rm -rf {guest_path} && mkdir -p {guest_parent}",
|
||||
user="root",
|
||||
)
|
||||
bottle.cp_in(str(workspace.host_path), workspace.guest_path)
|
||||
bottle.exec(
|
||||
f"chown -R {owner} {guest_path} && chmod {mode} {guest_path}",
|
||||
user="root",
|
||||
)
|
||||
|
||||
def supervise_mcp_url(self, plan: PlanT) -> str:
|
||||
"""Return the agent-side URL of the per-bottle supervise
|
||||
gateway, or "" when this bottle has no gateway. The provider
|
||||
plugin's `provision_supervise_mcp` uses it to register the
|
||||
MCP entry inside the guest.
|
||||
|
||||
Default returns "" so backends without supervise support
|
||||
don't have to implement it. Docker and firecracker override."""
|
||||
del plan
|
||||
return ""
|
||||
|
||||
def ensure_orchestrator(self) -> str:
|
||||
"""Bring up this backend's per-host orchestrator + shared gateway
|
||||
(idempotent) and return the host-reachable control-plane URL.
|
||||
|
||||
This is the backend-agnostic bring-up entry point: `launch` calls
|
||||
it as part of starting a bottle, and operator tools (`supervise`)
|
||||
call it to start the control plane on demand when none is running
|
||||
yet. Docker starts the orchestrator + gateway containers;
|
||||
firecracker boots the infra VM. Backends with no orchestrator
|
||||
(macos-container) die with a pointer — the default here."""
|
||||
die(f"backend {self.name!r} has no orchestrator control plane")
|
||||
|
||||
@abstractmethod
|
||||
def prepare_cleanup(self) -> CleanupT:
|
||||
"""Enumerate orphaned resources from previous bottles. No side
|
||||
effects; safe to call before the y/N."""
|
||||
|
||||
@abstractmethod
|
||||
def cleanup(self, plan: CleanupT) -> None:
|
||||
"""Remove everything described by the cleanup plan."""
|
||||
|
||||
@abstractmethod
|
||||
def enumerate_active(self) -> Sequence[ActiveAgent]:
|
||||
"""Return every currently-running agent on this backend.
|
||||
Empty when none. Backend-specific: docker queries `docker
|
||||
compose ls`; firecracker cross-references its running gateway
|
||||
containers against per-bottle metadata."""
|
||||
|
||||
@classmethod
|
||||
@abstractmethod
|
||||
def is_available(cls) -> bool:
|
||||
"""Whether this backend's runtime prerequisites are satisfied
|
||||
on the current host. Docker → `docker` on PATH; firecracker →
|
||||
Linux + KVM. Used by the cross-backend
|
||||
`enumerate_active_agents` / `cmd_cleanup` to skip backends
|
||||
the operator hasn't installed, so a docker-only host
|
||||
doesn't fail when `cli.py list active` walks past
|
||||
firecracker."""
|
||||
|
||||
@classmethod
|
||||
@abstractmethod
|
||||
def setup(cls) -> int:
|
||||
"""Emit this backend's one-time host setup — privileged network
|
||||
pool, daemon bring-up, install pointers, etc. — as
|
||||
host-appropriate config or commands. Prints to stdout/stderr and
|
||||
returns a shell exit code (0 = nothing to report / success). A
|
||||
backend that needs no host setup prints a short note and returns
|
||||
0. Invoked generically by `./cli.py backend setup [--backend=…]`
|
||||
so operators can provision any backend without a
|
||||
backend-specific command. Classmethod (like `is_available`) —
|
||||
it's a host query, not per-bottle state."""
|
||||
|
||||
@classmethod
|
||||
@abstractmethod
|
||||
def status(cls) -> int:
|
||||
"""Report whether this backend's prerequisites are satisfied on
|
||||
the host — binaries, daemon reachability, network pool, range
|
||||
conflicts, etc. Prints a human-readable summary; returns 0 when
|
||||
the backend is ready to launch and non-zero when something is
|
||||
missing. Invoked by `./cli.py backend status [--backend=…]`."""
|
||||
|
||||
@classmethod
|
||||
@abstractmethod
|
||||
def teardown(cls) -> int:
|
||||
"""Undo `setup()` — the inverse operation, surfaced as
|
||||
`./cli.py backend teardown [--backend=…]` (uninstall). Symmetric
|
||||
with setup: where setup is advisory (prints the privileged
|
||||
commands / declarative config to apply), teardown prints the
|
||||
commands / config change to remove the host prerequisites. A
|
||||
backend with no host setup prints a short note and returns 0.
|
||||
Not called by the launch path or the test suite."""
|
||||
|
||||
|
||||
# _backends is None until the first call to _get_backends(), at which
|
||||
# point all three concrete backend classes are imported and instantiated.
|
||||
# Keeping the imports out of module scope means that importing any
|
||||
# backend sub-module (e.g. `backend.docker.util`) no longer drags the
|
||||
# firecracker and macos-container implementations into memory.
|
||||
#
|
||||
# Tests may replace _backends with a {name: fake} dict via patch.object;
|
||||
# _get_backends() returns the current module-level value as-is when it
|
||||
# is not None, so test fakes take effect without triggering real imports.
|
||||
_backends: dict[str, BottleBackend[Any, Any]] | None = None
|
||||
|
||||
|
||||
def _get_backends() -> dict[str, BottleBackend[Any, Any]]:
|
||||
"""Return the registry of all backend instances, loading lazily on first call."""
|
||||
global _backends # pylint: disable=global-statement
|
||||
if _backends is None:
|
||||
from .docker import DockerBottleBackend
|
||||
from .firecracker import FirecrackerBottleBackend
|
||||
from .macos_container import MacosContainerBottleBackend
|
||||
_backends = {
|
||||
"docker": DockerBottleBackend(),
|
||||
"firecracker": FirecrackerBottleBackend(),
|
||||
"macos-container": MacosContainerBottleBackend(),
|
||||
}
|
||||
return _backends
|
||||
|
||||
|
||||
def __getattr__(name: str) -> Any:
|
||||
"""Lazily surface the package's public names from their submodules and
|
||||
cache them at package level — so `from bot_bottle.backend import X` and
|
||||
`patch.object(backend_mod, X, …)` keep working without importing the
|
||||
framework (or every backend) at package-init time."""
|
||||
mod = _LAZY_MODULES.get(name)
|
||||
if mod is None:
|
||||
raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
|
||||
from importlib import import_module
|
||||
"""Lazily surface concrete backend classes and freeze symbols at the
|
||||
package level so existing `from bot_bottle.backend import X` and
|
||||
`patch.object(backend_mod, X, ...)` call-sites keep working without
|
||||
forcing an import of every backend at module-init time."""
|
||||
if name == "DockerBottleBackend":
|
||||
from .docker import DockerBottleBackend
|
||||
globals()[name] = DockerBottleBackend
|
||||
return DockerBottleBackend
|
||||
if name == "FirecrackerBottleBackend":
|
||||
from .firecracker import FirecrackerBottleBackend
|
||||
globals()[name] = FirecrackerBottleBackend
|
||||
return FirecrackerBottleBackend
|
||||
if name == "MacosContainerBottleBackend":
|
||||
from .macos_container import MacosContainerBottleBackend
|
||||
globals()[name] = MacosContainerBottleBackend
|
||||
return MacosContainerBottleBackend
|
||||
if name == "CommitCancelled":
|
||||
from .freeze import CommitCancelled
|
||||
globals()[name] = CommitCancelled
|
||||
return CommitCancelled
|
||||
if name == "Freezer":
|
||||
from .freeze import Freezer
|
||||
globals()[name] = Freezer
|
||||
return Freezer
|
||||
if name == "get_freezer":
|
||||
from .freeze import get_freezer
|
||||
globals()[name] = get_freezer
|
||||
return get_freezer
|
||||
raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
|
||||
|
||||
value = getattr(import_module(f"{__name__}.{mod}"), name)
|
||||
globals()[name] = value
|
||||
return value
|
||||
|
||||
def get_bottle_backend(
|
||||
name: str | None = None,
|
||||
*,
|
||||
prompt: bool = True,
|
||||
) -> BottleBackend[Any, Any]:
|
||||
"""Resolve the bottle backend.
|
||||
|
||||
`name` precedence:
|
||||
1. explicit arg (e.g. resume passes the recorded backend name)
|
||||
2. BOT_BOTTLE_BACKEND env var
|
||||
3. auto-selection: VM backend first, docker fallback with prompt
|
||||
|
||||
`prompt` controls whether auto-selection may block on an interactive
|
||||
[i/d/q] prompt when falling back to docker. Pass `prompt=False` in
|
||||
non-interactive contexts (headless launches, CI) so the call dies
|
||||
with an actionable message instead of hanging.
|
||||
|
||||
Dies with a pointer at the known backends if the chosen name
|
||||
isn't implemented."""
|
||||
resolved = name or os.environ.get("BOT_BOTTLE_BACKEND")
|
||||
if resolved is None:
|
||||
resolved = _auto_select_backend(prompt=prompt)
|
||||
backends = _get_backends()
|
||||
if resolved not in backends:
|
||||
known = ", ".join(sorted(backends))
|
||||
die(f"unknown backend {resolved!r}; known backends: {known}")
|
||||
return backends[resolved]
|
||||
|
||||
|
||||
def _platform_vm_suggestion() -> str:
|
||||
"""Platform-appropriate VM backend name for install suggestions."""
|
||||
return "macos-container" if sys.platform == "darwin" else "firecracker"
|
||||
|
||||
|
||||
def _print_vm_install_instructions() -> None:
|
||||
"""Print platform-appropriate VM backend install instructions to stderr."""
|
||||
vm = _platform_vm_suggestion()
|
||||
if vm == "macos-container":
|
||||
info("Install Apple Container: https://github.com/apple/container/releases")
|
||||
info("Then start the service: container system start")
|
||||
else:
|
||||
info("Install Firecracker: https://github.com/firecracker-microvm/firecracker/releases")
|
||||
info("Configure the host: ./cli.py backend setup")
|
||||
|
||||
|
||||
def _auto_select_backend(prompt: bool = True) -> str:
|
||||
"""Tier-1 / tier-2 backend auto-selection.
|
||||
|
||||
Tier 1: VM backend — macos-container on macOS when Apple Container is
|
||||
installed; firecracker on KVM-capable Linux even before the binary is
|
||||
present (its preflight prints an install pointer).
|
||||
|
||||
Tier 2: docker, with a security warning and an interactive prompt.
|
||||
When `prompt=False` (headless / CI), dies with an actionable message
|
||||
instead of blocking on a TTY read. When docker is also absent, prints
|
||||
VM install instructions and exits.
|
||||
"""
|
||||
# --- Tier 1: VM backend -----------------------------------------
|
||||
if has_backend("macos-container"):
|
||||
return "macos-container"
|
||||
# A KVM-capable Linux host defaults to firecracker even when the
|
||||
# `firecracker` binary isn't installed yet: selecting it here routes
|
||||
# start through firecracker's preflight, which prints an install
|
||||
# pointer, instead of silently falling back to docker.
|
||||
from .firecracker import FirecrackerBottleBackend
|
||||
if FirecrackerBottleBackend.is_host_capable():
|
||||
return "firecracker"
|
||||
|
||||
# --- Tier 2: docker fallback ------------------------------------
|
||||
if not has_backend("docker"):
|
||||
info("No backend available on this host.")
|
||||
_print_vm_install_instructions()
|
||||
die("no backend available; install a VM backend and re-run")
|
||||
|
||||
vm = _platform_vm_suggestion()
|
||||
warn(
|
||||
"docker is less secure than VM backends — "
|
||||
"containers share the host kernel."
|
||||
)
|
||||
if not prompt:
|
||||
die(
|
||||
f"no VM backend available; set BOT_BOTTLE_BACKEND=docker to proceed "
|
||||
f"with docker, or install the {vm!r} backend."
|
||||
)
|
||||
sys.stderr.write(
|
||||
f"bot-bottle: For better isolation, install the {vm!r} backend.\n"
|
||||
f" [i] show {vm} install instructions and exit\n"
|
||||
" [d] use docker anyway\n"
|
||||
" [q] quit\n"
|
||||
"bot-bottle: choice [i/d/q]: "
|
||||
)
|
||||
sys.stderr.flush()
|
||||
reply = read_tty_line().strip().lower()
|
||||
if reply == "d":
|
||||
return "docker"
|
||||
if reply == "i":
|
||||
_print_vm_install_instructions()
|
||||
die("not proceeding with docker; install a VM backend or set BOT_BOTTLE_BACKEND=docker")
|
||||
|
||||
|
||||
def known_backend_names() -> tuple[str, ...]:
|
||||
"""Sorted tuple of all backend keys in `_get_backends()`. Used by
|
||||
argparse (`--backend` choices) and the dashboard's backend
|
||||
picker."""
|
||||
return tuple(sorted(_get_backends()))
|
||||
|
||||
|
||||
def has_backend(name: str) -> bool:
|
||||
"""Whether the named backend's runtime prerequisites are
|
||||
available on the current host. Cross-backend callers (list,
|
||||
cleanup) skip unavailable backends so a docker-only host
|
||||
doesn't fail when the firecracker backend isn't usable,
|
||||
and vice versa.
|
||||
|
||||
Returns False for unknown names so callers can pass
|
||||
arbitrary input without separate validation."""
|
||||
backends = _get_backends()
|
||||
if name not in backends:
|
||||
return False
|
||||
return backends[name].is_available()
|
||||
|
||||
|
||||
def enumerate_active_agents() -> list[ActiveAgent]:
|
||||
"""All currently-running agents, across every available
|
||||
backend. Used by CLI `list active` and the dashboard's agents
|
||||
pane so neither has to know which backends exist. Skips
|
||||
backends whose `is_available()` reports False.
|
||||
|
||||
Sorted by `(started_at, slug)` so the list is stable across
|
||||
dashboard refresh ticks — agents don't shift position while
|
||||
the operator navigates with arrow keys. ISO 8601 timestamps
|
||||
sort lexicographically in chronological order; `slug` is the
|
||||
deterministic tiebreaker. Agents with missing metadata
|
||||
(`started_at == ""`) sort first."""
|
||||
out: list[ActiveAgent] = []
|
||||
backends = _get_backends()
|
||||
for name in sorted(backends):
|
||||
if not backends[name].is_available():
|
||||
continue
|
||||
out.extend(backends[name].enumerate_active())
|
||||
out.sort(key=lambda a: (a.started_at, a.slug))
|
||||
return out
|
||||
|
||||
|
||||
__all__ = [
|
||||
"ActiveAgent",
|
||||
"BackendStatus",
|
||||
"Bottle",
|
||||
"BottleBackend",
|
||||
"BottleCleanupPlan",
|
||||
"BottleImages",
|
||||
"BottlePlan",
|
||||
"BottleSpec",
|
||||
"ExecResult",
|
||||
"CommitCancelled",
|
||||
"ExecResult",
|
||||
"Freezer",
|
||||
"get_freezer",
|
||||
"DockerBottleBackend",
|
||||
"FirecrackerBottleBackend",
|
||||
"MacosContainerBottleBackend",
|
||||
"enumerate_active_agents",
|
||||
"get_bottle_backend",
|
||||
"get_freezer",
|
||||
"has_backend",
|
||||
"is_backend_available",
|
||||
"is_backend_ready",
|
||||
"known_backend_names",
|
||||
]
|
||||
|
||||
@@ -1,619 +0,0 @@
|
||||
"""The abstract backend contract (PRD 0018 / 0070).
|
||||
|
||||
The backend-neutral types every bottle backend implements: the launch
|
||||
`BottleSpec`, the `BottlePlan` / `BottleCleanupPlan` ABCs, the running-`Bottle`
|
||||
+ `ExecResult` shapes, `BottleImages`, and the `BottleBackend` ABC itself.
|
||||
|
||||
This carries the framework imports (manifest, egress, git-gate, env, workspace,
|
||||
agent-provider) the contract's signatures and helpers need — which is why it
|
||||
lives here rather than in `backend/__init__.py`: touching an unrelated
|
||||
`backend.*` module then doesn't drag the whole framework into memory. The
|
||||
thin package `__init__` re-exports these names lazily.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import enum
|
||||
import os
|
||||
import shlex
|
||||
import sys
|
||||
from abc import ABC, abstractmethod
|
||||
from contextlib import AbstractContextManager, contextmanager
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
from typing import Generator, Generic, Sequence, TypeVar
|
||||
|
||||
from ..agent_provider import AgentProvisionPlan, get_provider, build_agent_provision_plan
|
||||
from ..egress import EgressPlan
|
||||
from ..git_gate import GitGatePlan
|
||||
from ..log import die, info
|
||||
from ..util import expand_tilde
|
||||
from ..manifest import Manifest, ManifestIndex
|
||||
from ..supervisor.plan import SupervisePlan
|
||||
from ..env import resolve_env, ResolvedEnv
|
||||
from ..workspace import WorkspacePlan, workspace_plan
|
||||
from .print_util import print_multi, visible_agent_env_names
|
||||
from .util import host_skill_dir
|
||||
|
||||
|
||||
class BackendStatus(enum.IntEnum):
|
||||
"""Return codes for BottleBackend.status(). READY == 0 so callsites
|
||||
can compare against 0 or the named constant interchangeably."""
|
||||
READY = 0
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class BottleSpec:
|
||||
"""CLI-supplied intent. Backend-agnostic — each backend's prepare
|
||||
step consumes it and produces its own backend-specific plan.
|
||||
Resolved values (image names, container name, scratch paths, runsc
|
||||
availability) live on the plan, not the spec."""
|
||||
|
||||
manifest: ManifestIndex
|
||||
agent_name: str
|
||||
copy_cwd: bool
|
||||
user_cwd: str
|
||||
# PRD 0016 follow-up: when set, the backend's prepare step uses
|
||||
# this identity instead of minting a fresh one — the resume path
|
||||
# (`cli.py resume <identity>`) sets this to continue an existing
|
||||
# bottle's state. Empty string for a fresh `start`.
|
||||
identity: str = ""
|
||||
label: str = ""
|
||||
color: str = ""
|
||||
# Ordered bottle names selected at launch (issue #269). When non-empty
|
||||
# they are merged in order and replace the agent's `bottle:` field.
|
||||
bottle_names: tuple[str, ...] = ()
|
||||
# True when launched via --headless (no TTY, no interactive prompts).
|
||||
# The git-gate host-key preflight uses this to error rather than prompt.
|
||||
headless: bool = False
|
||||
# Image startup policy. "fresh" preserves the normal build path;
|
||||
# "cached" reuses the current local image/artifact without rebuilding.
|
||||
image_policy: str = "fresh"
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class BottlePlan(ABC):
|
||||
"""Base output of a backend's prepare step. Concrete subclasses
|
||||
(e.g. DockerBottlePlan) add backend-specific resolved fields."""
|
||||
|
||||
spec: BottleSpec
|
||||
manifest: Manifest
|
||||
stage_dir: Path
|
||||
git_gate_plan: GitGatePlan
|
||||
|
||||
@property
|
||||
def guest_home(self) -> str:
|
||||
return self.agent_provision.guest_home
|
||||
|
||||
@property
|
||||
def git_gate_insteadof_host(self) -> str:
|
||||
"""Host (and optional port) used in git-gate insteadOf URLs.
|
||||
Docker uses the compose-network DNS alias; VM backends may
|
||||
override with an IP:port when the guest has no DNS."""
|
||||
return "git-gate"
|
||||
|
||||
@property
|
||||
def git_gate_insteadof_scheme(self) -> str:
|
||||
"""URL scheme for git-gate insteadOf rewrites. 'git' for
|
||||
Docker (git daemon); VM backends may override (e.g. 'http'
|
||||
over a published host port)."""
|
||||
return "git"
|
||||
egress_plan: EgressPlan
|
||||
supervise_plan: SupervisePlan | None
|
||||
agent_provision: AgentProvisionPlan
|
||||
|
||||
@property
|
||||
def workspace_plan(self) -> WorkspacePlan:
|
||||
return workspace_plan(self.spec, guest_home=self.guest_home)
|
||||
|
||||
def print(self) -> None:
|
||||
"""Render the y/N preflight summary to stderr."""
|
||||
spec = self.spec
|
||||
manifest = self.manifest
|
||||
agent = manifest.agent
|
||||
bottle = manifest.bottle
|
||||
|
||||
env_names = visible_agent_env_names(
|
||||
sorted(
|
||||
set(bottle.env.keys())
|
||||
| set(self.agent_provision.guest_env.keys())
|
||||
),
|
||||
hidden_env_names=self.agent_provision.hidden_env_names,
|
||||
)
|
||||
|
||||
print(file=sys.stderr)
|
||||
info(f"agent : {spec.agent_name}")
|
||||
info(f"provider : {self.agent_provision.template}")
|
||||
print_multi("env ", env_names)
|
||||
print_multi("skills ", list(agent.skills))
|
||||
effective_bottles = (
|
||||
list(spec.bottle_names) if spec.bottle_names
|
||||
else ([agent.bottle] if agent.bottle else [])
|
||||
)
|
||||
print_multi("bottle ", effective_bottles)
|
||||
|
||||
identity = manifest.git_identity_summary()
|
||||
if identity:
|
||||
info(f" git identity : {identity}")
|
||||
|
||||
git_lines = [
|
||||
f"{u.name} → {u.upstream_host}:{u.upstream_port}"
|
||||
for u in self.git_gate_plan.upstreams
|
||||
]
|
||||
if git_lines:
|
||||
print_multi(" git gate ", git_lines)
|
||||
|
||||
if self.egress_plan.routes:
|
||||
egress_lines = []
|
||||
for r in self.egress_plan.routes:
|
||||
auth = f" [auth:{r.auth_scheme}]" if r.auth_scheme else ""
|
||||
egress_lines.append(f"{r.host}{auth}")
|
||||
print_multi(" egress ", egress_lines)
|
||||
print(file=sys.stderr)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class BottleCleanupPlan(ABC):
|
||||
"""Base output of a backend's prepare_cleanup step. Concrete
|
||||
subclasses (e.g. DockerBottleCleanupPlan) carry backend-specific
|
||||
lists of resources to be removed and implement `print` + `empty`."""
|
||||
|
||||
@abstractmethod
|
||||
def print(self) -> None:
|
||||
"""Render the cleanup y/N summary to stderr."""
|
||||
|
||||
@property
|
||||
@abstractmethod
|
||||
def empty(self) -> bool:
|
||||
"""True iff there is nothing to clean up; the CLI uses this to
|
||||
short-circuit before showing the y/N."""
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ExecResult:
|
||||
"""Captured result of `Bottle.exec`. Backend-neutral: the Docker
|
||||
impl populates it from a `subprocess.CompletedProcess`, but a
|
||||
VM backend could populate it from any source that produces a
|
||||
returncode + captured streams."""
|
||||
|
||||
returncode: int
|
||||
stdout: str
|
||||
stderr: str
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ActiveAgent:
|
||||
"""One currently-running agent, as the CLI `active` and
|
||||
dashboard agents pane render it. ("Agent" is the project's
|
||||
consistent name for the thing running inside a bottle — the
|
||||
bottle is the container, the agent is what runs in it.)
|
||||
|
||||
Fields are deliberately backend-neutral. `services` is the set
|
||||
of gateway daemons currently up for this bottle (`egress`,
|
||||
`git-gate`, `supervise`); the dashboard uses it to
|
||||
gate edit verbs. `backend_name` is the matching key in
|
||||
`_BACKENDS` (`docker` / `firecracker` / `macos-container`) — used by the active-
|
||||
list rendering to disambiguate and by the dashboard's
|
||||
re-attach path."""
|
||||
|
||||
backend_name: str
|
||||
slug: str
|
||||
agent_name: str # from metadata.json; "?" if missing
|
||||
started_at: str # ISO 8601 from metadata.json; "" if missing
|
||||
services: tuple[str, ...] # alphabetical
|
||||
label: str = ""
|
||||
color: str = ""
|
||||
|
||||
|
||||
class Bottle(ABC):
|
||||
"""Handle to a running bottle. Yielded by a backend's launch step.
|
||||
|
||||
`exec_agent` runs the selected agent CLI inside the bottle and
|
||||
blocks until the session ends. `exec` runs a POSIX shell script inside the bottle
|
||||
and returns the captured result. `cp_in` copies a host path into
|
||||
the bottle. `close` is an idempotent alias for context-manager
|
||||
teardown.
|
||||
"""
|
||||
|
||||
name: str
|
||||
|
||||
@abstractmethod
|
||||
def agent_argv(
|
||||
self, argv: list[str], *, tty: bool = True,
|
||||
) -> list[str]:
|
||||
"""Return the host-side argv that runs the selected agent
|
||||
inside the bottle. Used by `exec_agent` for foreground
|
||||
handoffs and by the dashboard's tmux `respawn-pane` flow,
|
||||
which needs the argv up front (it spawns claude in a tmux
|
||||
pane rather than as a child of the current process).
|
||||
|
||||
Implementations transparently inject
|
||||
`--append-system-prompt-file` when the bottle was launched
|
||||
with a provisioned prompt path."""
|
||||
...
|
||||
|
||||
@abstractmethod
|
||||
def exec_agent(self, argv: list[str], *, tty: bool = True) -> int: ...
|
||||
|
||||
@abstractmethod
|
||||
def exec(self, script: str, *, user: str = "node") -> ExecResult:
|
||||
"""Run `script` as a POSIX shell script inside the bottle as
|
||||
`user` (default `node`, matching the agent image's USER
|
||||
directive) and return the captured stdout/stderr/returncode.
|
||||
The bottle's environment (including HTTPS_PROXY pointing at
|
||||
the egress daemon) is inherited by the child. Non-zero
|
||||
exit does not raise — callers inspect `returncode`
|
||||
themselves.
|
||||
|
||||
Pass `user="root"` for shell-outs that need privileged file
|
||||
writes / package install — provisioning calls that need root
|
||||
bypass `Bottle.exec` and use the backend-specific raw
|
||||
machine-exec helper, but the tests have a legitimate use
|
||||
case for arbitrary-user runs."""
|
||||
|
||||
@abstractmethod
|
||||
def cp_in(self, host_path: str, container_path: str) -> None: ...
|
||||
|
||||
@abstractmethod
|
||||
def close(self) -> None: ...
|
||||
|
||||
|
||||
|
||||
|
||||
PlanT = TypeVar("PlanT", bound=BottlePlan)
|
||||
CleanupT = TypeVar("CleanupT", bound=BottleCleanupPlan)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class BottleImages:
|
||||
"""Resolved image references (or artifact paths) for a bottle launch.
|
||||
|
||||
For Docker/macOS-container backends, `agent` and `sidecar` are string
|
||||
image refs. For the smolmachines backend they are Path objects pointing
|
||||
to pre-built `.smolmachine` artifacts."""
|
||||
|
||||
agent: str | Path
|
||||
sidecar: str | Path = ""
|
||||
|
||||
|
||||
class BottleBackend(ABC, Generic[PlanT, CleanupT]):
|
||||
"""Abstract base for selectable bottle backends. Concrete subclasses
|
||||
(e.g. DockerBottleBackend) own their own prepare/launch impls.
|
||||
Parameterized over the backend's concrete plan + cleanup-plan types
|
||||
so subclass methods get the narrow type without isinstance
|
||||
boilerplate."""
|
||||
|
||||
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
|
||||
backend-specific resolution (names, scratch files, etc.). The
|
||||
validation step is enforced here so a future backend cannot
|
||||
accidentally skip it. No remote/runtime resources are created."""
|
||||
from .resolve_common import (
|
||||
merge_provision_env_vars,
|
||||
mint_slug,
|
||||
prepare_agent_state_dir,
|
||||
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 import GitGate
|
||||
manifest = GitGate().preflight_host_keys(
|
||||
manifest,
|
||||
headless=spec.headless,
|
||||
home_md=spec.manifest.home_md,
|
||||
)
|
||||
|
||||
manifest_bottle = manifest.bottle
|
||||
manifest_agent_provider = manifest_bottle.agent_provider
|
||||
agent_provider = get_provider(manifest_agent_provider.template)
|
||||
resolved_env = resolve_env(manifest)
|
||||
workspace = workspace_plan(spec, guest_home=agent_provider.guest_home)
|
||||
|
||||
slug = mint_slug(spec)
|
||||
write_launch_metadata(slug, spec, compose_project="", backend=self.name)
|
||||
|
||||
# Manifest may override the Dockerfile per-bottle; otherwise fall
|
||||
# back to the provider plugin's bundled Dockerfile (next to its
|
||||
# agent_provider.py module).
|
||||
if manifest_agent_provider.dockerfile:
|
||||
agent_dockerfile_path = resolve_manifest_dockerfile(
|
||||
manifest_agent_provider.dockerfile, spec,
|
||||
)
|
||||
else:
|
||||
agent_dockerfile_path = str(agent_provider.dockerfile)
|
||||
|
||||
agent_dir, prompt_file = prepare_agent_state_dir(slug, manifest)
|
||||
|
||||
agent_provision_plan = build_agent_provision_plan(
|
||||
template=manifest_agent_provider.template,
|
||||
dockerfile=agent_dockerfile_path,
|
||||
state_dir=agent_dir,
|
||||
instance_name=f"bot-bottle-{slug}",
|
||||
prompt_file=prompt_file,
|
||||
guest_env=self._build_guest_env(resolved_env),
|
||||
forward_host_credentials=manifest_agent_provider.forward_host_credentials,
|
||||
auth_token=manifest_agent_provider.auth_token,
|
||||
host_env=dict(os.environ),
|
||||
trusted_project_path=workspace.workdir,
|
||||
label=spec.label,
|
||||
color=spec.color,
|
||||
provider_settings=manifest_agent_provider.settings,
|
||||
)
|
||||
agent_provision_plan = merge_provision_env_vars(agent_provision_plan)
|
||||
egress_plan = prepare_egress(manifest_bottle, slug, agent_provision_plan)
|
||||
supervise_plan = prepare_supervise(manifest_bottle, slug)
|
||||
git_gate_plan = prepare_git_gate(manifest_bottle, slug)
|
||||
|
||||
return self._resolve_plan(
|
||||
spec,
|
||||
manifest=manifest,
|
||||
slug=slug,
|
||||
resolved_env=resolved_env,
|
||||
agent_provision_plan=agent_provision_plan,
|
||||
egress_plan=egress_plan,
|
||||
supervise_plan=supervise_plan,
|
||||
git_gate_plan=git_gate_plan,
|
||||
stage_dir=stage_dir,
|
||||
)
|
||||
|
||||
def _build_guest_env(self, resolved_env: ResolvedEnv) -> dict[str, str]:
|
||||
return {}
|
||||
|
||||
def _preflight(self) -> None:
|
||||
"""
|
||||
tasks to do before resolving a plan
|
||||
"""
|
||||
pass
|
||||
|
||||
def _validate(self, spec: BottleSpec) -> Manifest:
|
||||
"""Cross-backend pre-launch checks. Parses the selected agent and
|
||||
its bottle (raising ManifestError on invalid content), confirms
|
||||
skills are present on the host, and every git IdentityFile resolves.
|
||||
|
||||
Returns the loaded Manifest for the selected agent. Subclasses with
|
||||
additional preconditions should override and call
|
||||
`super()._validate(spec)` first."""
|
||||
manifest = spec.manifest.load_for_agent(spec.agent_name, spec.bottle_names)
|
||||
self._validate_skills(manifest.agent.skills)
|
||||
self._validate_agent_provider_dockerfile(spec, manifest)
|
||||
return manifest
|
||||
|
||||
def _validate_skills(self, skills: Sequence[str]) -> None:
|
||||
"""Each named skill must be a directory under the host's
|
||||
`~/.claude/skills/`. The check is purely host-side, so the
|
||||
default impl covers every backend."""
|
||||
for name in skills:
|
||||
path = host_skill_dir(name)
|
||||
if not os.path.isdir(path):
|
||||
die(
|
||||
f"skill '{name}' not found on host at {path}. "
|
||||
f"Create it under ~/.claude/skills/, then re-run."
|
||||
)
|
||||
|
||||
def _validate_agent_provider_dockerfile(self, spec: BottleSpec, manifest: Manifest) -> None:
|
||||
bottle = manifest.bottle
|
||||
dockerfile = bottle.agent_provider.dockerfile
|
||||
if not dockerfile:
|
||||
return
|
||||
path = Path(expand_tilde(dockerfile))
|
||||
if not path.is_absolute():
|
||||
path = Path(spec.user_cwd) / path
|
||||
if not path.is_file():
|
||||
effective = (
|
||||
", ".join(spec.bottle_names) if spec.bottle_names else manifest.agent.bottle
|
||||
)
|
||||
die(
|
||||
f"agent_provider.dockerfile for bottle "
|
||||
f"'{effective}' not found: {path}"
|
||||
)
|
||||
|
||||
@abstractmethod
|
||||
def _resolve_plan(self,
|
||||
spec: BottleSpec,
|
||||
*,
|
||||
manifest: Manifest,
|
||||
slug: str,
|
||||
resolved_env: ResolvedEnv,
|
||||
agent_provision_plan: AgentProvisionPlan,
|
||||
egress_plan: EgressPlan,
|
||||
git_gate_plan: GitGatePlan,
|
||||
supervise_plan: SupervisePlan | None,
|
||||
stage_dir: Path) -> PlanT:
|
||||
"""Backend-specific plan resolution: image/container names,
|
||||
env-file, prompt-file, proxy plan, runtime detection. Called by
|
||||
`prepare` after `_validate` succeeds. Instance name, image,
|
||||
prompt file, Dockerfile path, and guest home all live on
|
||||
`agent_provision_plan` — the source of truth."""
|
||||
|
||||
def prelaunch_checks(self, plan: PlanT) -> None:
|
||||
"""Raise StaleImageError if any cached image used by this plan is stale.
|
||||
No-op default; backends override to call the shared check_stale*
|
||||
helpers on their image/artifact timestamps. Called by the CLI before
|
||||
launch so the operator can be prompted outside the launch context."""
|
||||
|
||||
@contextmanager
|
||||
def launch(self, plan: PlanT) -> Generator[Bottle, None, None]:
|
||||
"""Template: build or load images, then delegate to _launch_impl."""
|
||||
images = self._build_or_load_images(plan)
|
||||
with self._launch_impl(plan, images) as bottle:
|
||||
yield bottle
|
||||
|
||||
@abstractmethod
|
||||
def _build_or_load_images(self, plan: PlanT) -> BottleImages:
|
||||
"""Return the agent and sidecar image references (or artifact paths)
|
||||
for this plan, building fresh images when the policy requires it."""
|
||||
|
||||
@abstractmethod
|
||||
def _launch_impl(self, plan: PlanT, images: BottleImages) -> AbstractContextManager[Bottle]:
|
||||
"""Bring up the bottle using pre-resolved images; yield a handle; tear down on exit."""
|
||||
|
||||
def provision(self, plan: PlanT, bottle: "Bottle") -> str | None:
|
||||
"""Copy host-side files (CA cert, prompt, skills, .git) into
|
||||
the running bottle. Called from `launch` after the container
|
||||
/ machine is up. Returns the in-container prompt path if a
|
||||
prompt was provisioned, else None — the Bottle handle uses it
|
||||
to decide whether to add provider-specific prompt args to the
|
||||
agent's argv.
|
||||
|
||||
Default orchestration: ca → prompt → provider apply → skills
|
||||
→ workspace → git → supervise-mcp. CA install runs first so
|
||||
the agent's trust store is rebuilt before anything inside the
|
||||
agent makes a TLS call.
|
||||
|
||||
Per PRD 0050 the per-provider steps (prompt, skills,
|
||||
declarative provision-plan apply, supervise MCP registration)
|
||||
live on the `AgentProvider` plugin. The backend only owns the
|
||||
steps that are about backend infrastructure (CA, workspace,
|
||||
git) and surfaces the supervise daemon URL its launch step
|
||||
knows about via `supervise_mcp_url`.
|
||||
|
||||
PRD 0017: cred-proxy's agent-side dotfile rewrites (~/.npmrc,
|
||||
~/.gitconfig insteadOf, tea config) are gone. Egress-proxy is
|
||||
on the agent's HTTP_PROXY path so every tool that respects
|
||||
HTTPS_PROXY (claude-code, git over HTTPS, npm, curl) is
|
||||
intercepted without per-tool reconfiguration."""
|
||||
provider = get_provider(plan.agent_provision.template)
|
||||
provider.provision_ca(bottle, plan)
|
||||
prompt_path = provider.provision_prompt(plan, bottle)
|
||||
provider.provision(plan, bottle)
|
||||
provider.provision_skills(plan, bottle)
|
||||
self.provision_workspace(plan, bottle)
|
||||
provider.provision_git(bottle, plan)
|
||||
provider.provision_supervise_mcp(
|
||||
plan, bottle, self.supervise_mcp_url(plan),
|
||||
)
|
||||
return prompt_path
|
||||
|
||||
def provision_workspace(self, plan: PlanT, bottle: "Bottle") -> None:
|
||||
"""Copy the operator workspace into the running bottle.
|
||||
|
||||
This is the only supported workspace-provisioning path: Docker
|
||||
does not build a derived image containing the current
|
||||
workspace."""
|
||||
workspace = plan.workspace_plan
|
||||
if not (workspace.enabled and workspace.copy_contents):
|
||||
return
|
||||
|
||||
guest_parent = workspace.guest_path.rsplit("/", 1)[0] or "/"
|
||||
guest_path = shlex.quote(workspace.guest_path)
|
||||
guest_parent = shlex.quote(guest_parent)
|
||||
owner = shlex.quote(workspace.owner)
|
||||
mode = shlex.quote(workspace.mode)
|
||||
info(f"copying {workspace.host_path} -> {bottle.name}:{workspace.guest_path}")
|
||||
bottle.exec(
|
||||
f"rm -rf {guest_path} && mkdir -p {guest_parent}",
|
||||
user="root",
|
||||
)
|
||||
bottle.cp_in(str(workspace.host_path), workspace.guest_path)
|
||||
bottle.exec(
|
||||
f"chown -R {owner} {guest_path} && chmod {mode} {guest_path}",
|
||||
user="root",
|
||||
)
|
||||
|
||||
def supervise_mcp_url(self, plan: PlanT) -> str:
|
||||
"""Return the agent-side URL of the per-bottle supervise
|
||||
gateway, or "" when this bottle has no gateway. The provider
|
||||
plugin's `provision_supervise_mcp` uses it to register the
|
||||
MCP entry inside the guest.
|
||||
|
||||
Default returns "" so backends without supervise support
|
||||
don't have to implement it. Docker and firecracker override."""
|
||||
del plan
|
||||
return ""
|
||||
|
||||
def ensure_orchestrator(self) -> str:
|
||||
"""Bring up this backend's per-host orchestrator + shared gateway
|
||||
(idempotent) and return the host-reachable control-plane URL.
|
||||
|
||||
This is the backend-agnostic bring-up entry point: `launch` calls
|
||||
it as part of starting a bottle, and operator tools (`supervise`)
|
||||
call it to start the control plane on demand when none is running
|
||||
yet. Docker starts the orchestrator + gateway containers;
|
||||
firecracker boots the infra VM. Backends with no orchestrator
|
||||
(macos-container) die with a pointer — the default here."""
|
||||
die(f"backend {self.name!r} has no orchestrator control plane")
|
||||
|
||||
@abstractmethod
|
||||
def prepare_cleanup(self) -> CleanupT:
|
||||
"""Enumerate orphaned resources from previous bottles. No side
|
||||
effects; safe to call before the y/N."""
|
||||
|
||||
@abstractmethod
|
||||
def cleanup(self, plan: CleanupT) -> None:
|
||||
"""Remove everything described by the cleanup plan."""
|
||||
|
||||
@abstractmethod
|
||||
def enumerate_active(self) -> Sequence[ActiveAgent]:
|
||||
"""Return every currently-running agent on this backend.
|
||||
Empty when none. Backend-specific: docker queries `docker
|
||||
compose ls`; firecracker cross-references its running gateway
|
||||
containers against per-bottle metadata."""
|
||||
|
||||
@classmethod
|
||||
@abstractmethod
|
||||
def is_available(cls) -> bool:
|
||||
"""Whether this backend's runtime prerequisites are satisfied
|
||||
on the current host. Docker → `docker` on PATH; firecracker →
|
||||
Linux + KVM. Used by the cross-backend
|
||||
`enumerate_active_agents` / `cmd_cleanup` to skip backends
|
||||
the operator hasn't installed, so a docker-only host
|
||||
doesn't fail when `cli.py active` walks past
|
||||
firecracker."""
|
||||
|
||||
@classmethod
|
||||
@abstractmethod
|
||||
def setup(cls) -> int:
|
||||
"""Emit this backend's one-time host setup — privileged network
|
||||
pool, daemon bring-up, install pointers, etc. — as
|
||||
host-appropriate config or commands. Prints to stdout/stderr and
|
||||
returns a shell exit code (0 = nothing to report / success). A
|
||||
backend that needs no host setup prints a short note and returns
|
||||
0. Invoked generically by `./cli.py backend setup [--backend=…]`
|
||||
so operators can provision any backend without a
|
||||
backend-specific command. Classmethod (like `is_available`) —
|
||||
it's a host query, not per-bottle state."""
|
||||
|
||||
@classmethod
|
||||
@abstractmethod
|
||||
def status(cls, *, quiet: bool = False) -> int:
|
||||
"""Report whether this backend's prerequisites are satisfied on
|
||||
the host — binaries, daemon reachability, network pool, range
|
||||
conflicts, etc. Returns BackendStatus.READY (0) when the backend
|
||||
is ready to launch and non-zero when something is missing.
|
||||
|
||||
When quiet=False (default) prints a human-readable summary to
|
||||
stderr. When quiet=True returns the status code silently —
|
||||
useful for cheap programmatic checks.
|
||||
|
||||
Invoked by `./cli.py backend status [--backend=…]` (quiet=False)
|
||||
and by is_backend_ready() (caller-controlled)."""
|
||||
|
||||
@classmethod
|
||||
@abstractmethod
|
||||
def teardown(cls) -> int:
|
||||
"""Undo `setup()` — the inverse operation, surfaced as
|
||||
`./cli.py backend teardown [--backend=…]` (uninstall). Symmetric
|
||||
with setup: where setup is advisory (prints the privileged
|
||||
commands / declarative config to apply), teardown prints the
|
||||
commands / config change to remove the host prerequisites. A
|
||||
backend with no host setup prints a short note and returns 0.
|
||||
Not called by the launch path or the test suite."""
|
||||
@@ -13,7 +13,7 @@ from ..egress import EgressPlan
|
||||
from ..git_gate import GitGatePlan
|
||||
from ..orchestrator.client import OrchestratorClient, RegisteredBottle
|
||||
from ..orchestrator.registration import registration_inputs
|
||||
from ..orchestrator.store.secret_store import new_env_var_secret
|
||||
from ..orchestrator.secret_store import new_env_var_secret
|
||||
from .docker.gateway_provision import GatewayTransport, deprovision_git_gate, provision_git_gate
|
||||
|
||||
|
||||
@@ -58,7 +58,7 @@ def teardown_consolidated(
|
||||
) -> None:
|
||||
"""Deregister the bottle and remove its git-gate state. Both steps are
|
||||
idempotent so this is safe from a cleanup trap."""
|
||||
from ..orchestrator.store.config_store import DEFAULT_TEARDOWN_TIMEOUT_SECONDS
|
||||
from ..orchestrator.config_store import DEFAULT_TEARDOWN_TIMEOUT_SECONDS
|
||||
OrchestratorClient(
|
||||
orchestrator_url,
|
||||
timeout=timeout if timeout is not None else DEFAULT_TEARDOWN_TIMEOUT_SECONDS,
|
||||
|
||||
@@ -11,42 +11,18 @@ The bulk of the implementation lives in sibling modules:
|
||||
- launch: bring-up + teardown context manager
|
||||
- cleanup: orphan enumeration, removal, active listing
|
||||
- backend: DockerBottleBackend façade wiring the above
|
||||
- infra: DockerInfraService (the per-host infra container)
|
||||
|
||||
Thin by design: the public names are re-exported lazily via `__getattr__`, so
|
||||
importing a leaf like `backend.docker.util` doesn't drag `DockerBottleBackend`
|
||||
(and the whole framework it pulls) into memory.
|
||||
This file only re-exports the public names so
|
||||
`from bot_bottle.backend.docker import DockerBottleBackend` keeps
|
||||
working.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING, Any
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from .backend import DockerBottleBackend
|
||||
from .bottle import DockerBottle
|
||||
from .bottle_cleanup_plan import DockerBottleCleanupPlan
|
||||
from .bottle_plan import DockerBottlePlan
|
||||
|
||||
|
||||
_LAZY_MODULES: dict[str, str] = {
|
||||
"DockerBottleBackend": "backend",
|
||||
"DockerBottle": "bottle",
|
||||
"DockerBottleCleanupPlan": "bottle_cleanup_plan",
|
||||
"DockerBottlePlan": "bottle_plan",
|
||||
}
|
||||
|
||||
|
||||
def __getattr__(name: str) -> Any:
|
||||
mod = _LAZY_MODULES.get(name)
|
||||
if mod is None:
|
||||
raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
|
||||
from importlib import import_module
|
||||
|
||||
value = getattr(import_module(f"{__name__}.{mod}"), name)
|
||||
globals()[name] = value
|
||||
return value
|
||||
|
||||
from .backend import DockerBottleBackend
|
||||
from .bottle import DockerBottle
|
||||
from .bottle_cleanup_plan import DockerBottleCleanupPlan
|
||||
from .bottle_plan import DockerBottlePlan
|
||||
|
||||
__all__ = [
|
||||
"DockerBottle",
|
||||
|
||||
@@ -20,17 +20,16 @@ infrastructure: CA install and git copy-in.
|
||||
from __future__ import annotations
|
||||
|
||||
import shutil
|
||||
import io
|
||||
from contextlib import contextmanager, redirect_stderr
|
||||
from contextlib import contextmanager
|
||||
from pathlib import Path
|
||||
from typing import Generator, Sequence
|
||||
|
||||
from ...supervisor.types import SUPERVISE_HOSTNAME, SUPERVISE_PORT
|
||||
from ...supervise import SUPERVISE_HOSTNAME, SUPERVISE_PORT
|
||||
from ...agent_provider import AgentProvisionPlan
|
||||
from ...egress import EgressPlan
|
||||
from ...env import ResolvedEnv
|
||||
from ...git_gate import GitGatePlan
|
||||
from ...supervisor.plan import SupervisePlan
|
||||
from ...supervise import SupervisePlan
|
||||
from ...manifest import Manifest
|
||||
from .. import ActiveAgent, BottleBackend, BottleImages, BottleSpec
|
||||
from . import cleanup as _cleanup
|
||||
@@ -61,11 +60,8 @@ class DockerBottleBackend(BottleBackend["DockerBottlePlan", "DockerBottleCleanup
|
||||
return _setup.setup()
|
||||
|
||||
@classmethod
|
||||
def status(cls, *, quiet: bool = False) -> int:
|
||||
def status(cls) -> int:
|
||||
from . import setup as _setup
|
||||
if quiet:
|
||||
with redirect_stderr(io.StringIO()):
|
||||
return _setup.status()
|
||||
return _setup.status()
|
||||
|
||||
@classmethod
|
||||
@@ -116,8 +112,8 @@ class DockerBottleBackend(BottleBackend["DockerBottlePlan", "DockerBottleCleanup
|
||||
yield bottle
|
||||
|
||||
def ensure_orchestrator(self) -> str:
|
||||
from .infra import DockerInfraService
|
||||
return DockerInfraService().ensure_running()
|
||||
from ...orchestrator.lifecycle import OrchestratorService
|
||||
return OrchestratorService().ensure_running()
|
||||
|
||||
def supervise_mcp_url(self, plan: DockerBottlePlan) -> str:
|
||||
"""Docker bottles reach the supervise daemon via the
|
||||
|
||||
@@ -16,8 +16,8 @@ from __future__ import annotations
|
||||
|
||||
from typing import Any
|
||||
|
||||
from ...egress import Egress
|
||||
from ...orchestrator.store.secret_store import ENV_VAR_SECRET_NAME
|
||||
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
|
||||
@@ -63,7 +63,7 @@ def consolidated_agent_compose(
|
||||
# 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))
|
||||
env.extend(egress_agent_env_entries(plan.egress_plan))
|
||||
|
||||
service: dict[str, Any] = {
|
||||
"image": plan.image,
|
||||
|
||||
@@ -16,13 +16,13 @@ from __future__ import annotations
|
||||
from dataclasses import dataclass
|
||||
|
||||
from ... import log
|
||||
from .util import run_docker
|
||||
from ...docker_cmd import run_docker
|
||||
from ...egress import EgressPlan
|
||||
from ...git_gate import GitGatePlan
|
||||
from ...orchestrator.client import OrchestratorClient
|
||||
from ...gateway import GATEWAY_NETWORK
|
||||
from .infra import INFRA_NAME, DockerInfraService
|
||||
from ...orchestrator.store.secret_store import ENV_VAR_SECRET_NAME
|
||||
from ...orchestrator.gateway import GATEWAY_NETWORK
|
||||
from ...orchestrator.lifecycle import INFRA_NAME, OrchestratorService
|
||||
from ...orchestrator.secret_store import ENV_VAR_SECRET_NAME
|
||||
from ...orchestrator.reprovision import reprovision_bottles
|
||||
from ..consolidated_util import provision_bottle
|
||||
from ..consolidated_util import teardown_consolidated as _teardown_util
|
||||
@@ -144,7 +144,7 @@ def launch_consolidated(
|
||||
*,
|
||||
image_ref: str = "",
|
||||
tokens: dict[str, str] | None = None,
|
||||
service: DockerInfraService | None = None,
|
||||
service: OrchestratorService | None = None,
|
||||
infra_name: str = INFRA_NAME,
|
||||
network: str = GATEWAY_NETWORK,
|
||||
) -> LaunchContext:
|
||||
@@ -154,19 +154,16 @@ def launch_consolidated(
|
||||
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 DockerInfraService()
|
||||
service = service or OrchestratorService()
|
||||
url = service.ensure_running()
|
||||
# Agents attribute against the *gateway* container (data plane), not the
|
||||
# orchestrator — the two planes are now separate containers.
|
||||
gateway_name = service.gateway_name
|
||||
_reprovision_running_bottles(url, network=network, infra_name=gateway_name)
|
||||
_reprovision_running_bottles(url, network=network, infra_name=infra_name)
|
||||
client = OrchestratorClient(url)
|
||||
|
||||
cidr = _network_cidr(network)
|
||||
gateway_ip = _container_ip(gateway_name, network)
|
||||
gateway_ip = _container_ip(infra_name, network)
|
||||
source_ip = next_free_ip(cidr, _network_container_ips(network))
|
||||
|
||||
transport = DockerGatewayTransport(gateway_name)
|
||||
transport = DockerGatewayTransport(infra_name)
|
||||
reg = provision_bottle(
|
||||
client, source_ip, egress_plan, git_gate_plan, transport,
|
||||
image_ref=image_ref, tokens=tokens,
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
"""Active-agent enumeration for the docker backend.
|
||||
|
||||
Returns `ActiveAgent` records the CLI `active` command and the
|
||||
Returns `ActiveAgent` records the CLI `list active` command and the
|
||||
dashboard agents pane consume. Empty when docker isn't reachable
|
||||
— gated by `has_backend('docker')` at the cross-backend caller
|
||||
so this module trusts that docker is available when called.
|
||||
@@ -60,7 +60,7 @@ def _parse_services_by_project(stdout: str) -> dict[str, set[str]]:
|
||||
|
||||
def _query_services_by_project() -> dict[str, set[str]]:
|
||||
"""One `docker ps` call → `{project: {service, ...}}`. Used
|
||||
by the CLI's `active` and the dashboard's agents pane —
|
||||
by the CLI's `list active` and the dashboard's agents pane —
|
||||
one subprocess per refresh tick, not one per bottle."""
|
||||
try:
|
||||
r = subprocess.run(
|
||||
|
||||
@@ -17,7 +17,7 @@ from __future__ import annotations
|
||||
import re
|
||||
from typing import Protocol
|
||||
|
||||
from .util import run_docker
|
||||
from ...docker_cmd import run_docker
|
||||
from ...git_gate import GitGatePlan, git_gate_render_provision
|
||||
|
||||
# bottle ids index the gateway's per-bottle repo + creds dirs; they land in
|
||||
|
||||
@@ -1,285 +0,0 @@
|
||||
"""The per-host control plane + gateway for the docker backend (PRD 0070).
|
||||
|
||||
Runs the orchestrator (control plane) and the gateway (data plane) as **two
|
||||
separate containers**, split now that #469 got the DB off the data plane:
|
||||
|
||||
* `bot-bottle-orchestrator` — the lean control-plane container. Joins the
|
||||
`bot-bottle-orchestrator` **control network** (`--internal`) only, plus a
|
||||
host-loopback publish for the CLI. Sole opener of `bot-bottle.db`; holds the
|
||||
signing key.
|
||||
* `bot-bottle-gateway` — the data-plane container (`DockerGateway`).
|
||||
**Dual-homed** on the agent-facing `bot-bottle-gateway` network *and* the
|
||||
control network, so it reaches the orchestrator by name over docker DNS
|
||||
(`http://bot-bottle-orchestrator:8099`) while agents — which are never on
|
||||
the control network — cannot reach the control plane at all (the L3 block
|
||||
Firecracker's nft already has). Holds the `gateway` JWT + the mitmproxy CA.
|
||||
|
||||
`DockerInfraService` brings both up as an idempotent per-host pair. Callers use
|
||||
`ensure_running()` (returns the host control-plane URL) + `gateway_name` (the
|
||||
container the launch flow attributes agents against).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import time
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
from pathlib import Path
|
||||
|
||||
from ... import log
|
||||
from .util import run_docker
|
||||
from .gateway import DockerGateway
|
||||
from ...paths import (
|
||||
ORCHESTRATOR_TOKEN_ENV,
|
||||
bot_bottle_root,
|
||||
host_orchestrator_token,
|
||||
)
|
||||
from ...gateway import (
|
||||
GATEWAY_DOCKERFILE,
|
||||
GATEWAY_IMAGE,
|
||||
GATEWAY_NAME,
|
||||
GATEWAY_NETWORK,
|
||||
GatewayError,
|
||||
)
|
||||
from ...orchestrator.lifecycle import (
|
||||
DEFAULT_PORT,
|
||||
DEFAULT_STARTUP_TIMEOUT_SECONDS,
|
||||
OrchestratorStartError,
|
||||
source_hash,
|
||||
)
|
||||
|
||||
# The control plane's own container + the dedicated control network the gateway
|
||||
# reaches it over. The network is created `--internal`: the orchestrator and
|
||||
# gateway join it, agents never do, so agents have no route to the control
|
||||
# plane (PRD 0070 "Separating the planes"). Same name across docker + macOS.
|
||||
ORCHESTRATOR_NAME = "bot-bottle-orchestrator"
|
||||
ORCHESTRATOR_LABEL = "bot-bottle-orchestrator=1"
|
||||
ORCHESTRATOR_NETWORK = "bot-bottle-orchestrator"
|
||||
ORCHESTRATOR_IMAGE = os.environ.get(
|
||||
"BOT_BOTTLE_ORCHESTRATOR_IMAGE", "bot-bottle-orchestrator:latest"
|
||||
)
|
||||
ORCHESTRATOR_DOCKERFILE = "Dockerfile.orchestrator"
|
||||
# Baked as a container label so `ensure_running` can detect whether the running
|
||||
# orchestrator is executing the current bind-mounted source.
|
||||
ORCHESTRATOR_SOURCE_HASH_LABEL = "bot-bottle-orchestrator-source-hash"
|
||||
|
||||
# The bind-mount path for the live control-plane source inside the orchestrator
|
||||
# container. PYTHONPATH points here so a code change takes effect on the next
|
||||
# launch without an image rebuild.
|
||||
_SRC_IN_CONTAINER = "/bot-bottle-src"
|
||||
# Bot-bottle host-root bind-mount (DB + state) inside the orchestrator. The
|
||||
# control plane opens bot-bottle.db under here (via BOT_BOTTLE_ROOT ->
|
||||
# host_db_path()); it is the ONLY container with a handle on it (issue #469).
|
||||
_ROOT_IN_CONTAINER = "/bot-bottle-root"
|
||||
|
||||
# The URL the gateway's data plane resolves policy against — the orchestrator
|
||||
# container by name on the control network (docker DNS, container↔container).
|
||||
ORCHESTRATOR_URL_IN_NETWORK = f"http://{ORCHESTRATOR_NAME}:{DEFAULT_PORT}"
|
||||
|
||||
# Back-compat aliases: the split retired the combined `bot-bottle-infra`
|
||||
# container, but the fixed-name constants some callers/tests import still map to
|
||||
# the pair's public identity.
|
||||
INFRA_NAME = GATEWAY_NAME # the container agents attribute against is the gateway
|
||||
|
||||
_HEALTH_POLL_SECONDS = 0.25
|
||||
_HEALTH_REQUEST_TIMEOUT_SECONDS = 1.0
|
||||
|
||||
_REPO_ROOT = Path(__file__).resolve().parents[3]
|
||||
|
||||
|
||||
class DockerInfraService:
|
||||
"""Brings up the per-host control plane + gateway as two containers.
|
||||
|
||||
`orchestrator_name` / `gateway_name` let callers run independent pairs on
|
||||
one host without name collisions (e.g. isolated integration tests that
|
||||
can't share the production singletons)."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
port: int = DEFAULT_PORT,
|
||||
network: str = GATEWAY_NETWORK,
|
||||
control_network: str = ORCHESTRATOR_NETWORK,
|
||||
orchestrator_image: str = ORCHESTRATOR_IMAGE,
|
||||
gateway_image: str = GATEWAY_IMAGE,
|
||||
repo_root: Path = _REPO_ROOT,
|
||||
host_root: Path | None = None,
|
||||
orchestrator_name: str = ORCHESTRATOR_NAME,
|
||||
orchestrator_label: str = ORCHESTRATOR_LABEL,
|
||||
gateway_name: str = GATEWAY_NAME,
|
||||
) -> None:
|
||||
self.port = port
|
||||
self.network = network
|
||||
self.control_network = control_network
|
||||
self.orchestrator_image = orchestrator_image
|
||||
self.gateway_image = gateway_image
|
||||
self._repo_root = repo_root
|
||||
self._host_root = host_root or bot_bottle_root()
|
||||
self._orchestrator_name = orchestrator_name
|
||||
self._orchestrator_label = orchestrator_label
|
||||
self._gateway_name = gateway_name
|
||||
|
||||
@property
|
||||
def gateway_name(self) -> str:
|
||||
"""The gateway container — the address the launch flow attributes agents
|
||||
against (gateway IP, git-gate provisioning transport, CA fetch)."""
|
||||
return self._gateway_name
|
||||
|
||||
@property
|
||||
def url(self) -> str:
|
||||
"""Host-side control-plane URL (the orchestrator's published loopback)."""
|
||||
return f"http://127.0.0.1:{self.port}"
|
||||
|
||||
def is_healthy(self, *, timeout: float = _HEALTH_REQUEST_TIMEOUT_SECONDS) -> bool:
|
||||
try:
|
||||
with urllib.request.urlopen(f"{self.url}/health", timeout=timeout) as resp:
|
||||
return resp.status == 200
|
||||
except (urllib.error.URLError, TimeoutError, OSError):
|
||||
return False
|
||||
|
||||
def _container_running(self, name: str) -> bool:
|
||||
proc = run_docker(["docker", "ps", "--filter", f"name=^/{name}$", "--format", "{{.Names}}"])
|
||||
return name in proc.stdout.split()
|
||||
|
||||
def _orchestrator_source_current(self, current_hash: str) -> bool:
|
||||
"""True iff the running orchestrator was started from the current
|
||||
bind-mounted source."""
|
||||
if not self._container_running(self._orchestrator_name):
|
||||
return False
|
||||
proc = run_docker([
|
||||
"docker", "inspect", "--format",
|
||||
"{{ index .Config.Labels \"" + ORCHESTRATOR_SOURCE_HASH_LABEL + "\" }}",
|
||||
self._orchestrator_name,
|
||||
])
|
||||
if proc.returncode != 0:
|
||||
return True # can't compare → don't churn a working container
|
||||
return proc.stdout.strip() == current_hash
|
||||
|
||||
def _ensure_network(self, name: str, *, internal: bool) -> None:
|
||||
if run_docker(["docker", "network", "inspect", name]).returncode == 0:
|
||||
return
|
||||
argv = ["docker", "network", "create"]
|
||||
if internal:
|
||||
argv.append("--internal")
|
||||
argv.append(name)
|
||||
proc = run_docker(argv)
|
||||
if proc.returncode != 0 and "already exists" not in proc.stderr:
|
||||
raise GatewayError(f"network {name} failed to create: {proc.stderr.strip()}")
|
||||
|
||||
def _build_images(self) -> None:
|
||||
"""Build the gateway (data plane) and orchestrator (control plane)
|
||||
images. Cache-aware: a no-op when nothing changed. The combined
|
||||
`Dockerfile.infra` is no longer built — the planes ship as two images."""
|
||||
for tag, dockerfile in (
|
||||
(self.gateway_image, GATEWAY_DOCKERFILE),
|
||||
(self.orchestrator_image, ORCHESTRATOR_DOCKERFILE),
|
||||
):
|
||||
argv = ["docker", "build", "-t", tag,
|
||||
"-f", str(self._repo_root / dockerfile),
|
||||
str(self._repo_root)]
|
||||
if os.environ.get("BOT_BOTTLE_NO_CACHE"):
|
||||
argv.insert(2, "--no-cache")
|
||||
proc = run_docker(argv)
|
||||
if proc.returncode != 0:
|
||||
raise GatewayError(f"{dockerfile} build failed: {proc.stderr.strip()}")
|
||||
|
||||
def _run_orchestrator_container(self, current_hash: str) -> None:
|
||||
"""Start the lean control-plane container on the control network only,
|
||||
published to host loopback for the CLI. Idempotent (clears a stale
|
||||
fixed-name container first)."""
|
||||
self._ensure_network(self.control_network, internal=True)
|
||||
run_docker(["docker", "rm", "--force", self._orchestrator_name])
|
||||
_signing_key = host_orchestrator_token()
|
||||
proc = run_docker([
|
||||
"docker", "run", "--detach",
|
||||
"--name", self._orchestrator_name,
|
||||
"--label", self._orchestrator_label,
|
||||
"--label", f"{ORCHESTRATOR_SOURCE_HASH_LABEL}={current_hash}",
|
||||
# Control network only — agents are never on it, so they have no
|
||||
# route to the control plane (the L3 block, not just the JWT).
|
||||
"--network", self.control_network,
|
||||
# Host CLI reaches the control plane here (loopback only). The
|
||||
# orchestrator listens on the fixed DEFAULT_PORT inside the
|
||||
# container; self.port is the host-side published port.
|
||||
"--publish", f"127.0.0.1:{self.port}:{DEFAULT_PORT}",
|
||||
# Live control-plane source (code changes without an image rebuild).
|
||||
"--volume", f"{self._repo_root}:{_SRC_IN_CONTAINER}:ro",
|
||||
"--env", f"PYTHONPATH={_SRC_IN_CONTAINER}",
|
||||
# Orchestrator registry DB on the host (sole writer: control plane).
|
||||
"--volume", f"{self._host_root}:{_ROOT_IN_CONTAINER}",
|
||||
"--env", f"BOT_BOTTLE_ROOT={_ROOT_IN_CONTAINER}",
|
||||
# The signing key — held ONLY by the orchestrator (it verifies
|
||||
# tokens); the gateway gets the pre-minted `gateway` JWT, never the
|
||||
# key (issue #469). Bare `--env NAME` keeps the value off argv.
|
||||
"--env", ORCHESTRATOR_TOKEN_ENV,
|
||||
self.orchestrator_image,
|
||||
# Dockerfile.orchestrator ENTRYPOINT is `python3 -m bot_bottle.orchestrator`;
|
||||
# these are its args.
|
||||
"--host", "0.0.0.0", "--port", str(DEFAULT_PORT), "--broker", "stub",
|
||||
], env={**os.environ, ORCHESTRATOR_TOKEN_ENV: _signing_key})
|
||||
if proc.returncode != 0:
|
||||
raise OrchestratorStartError(
|
||||
f"orchestrator container failed to start: {proc.stderr.strip()}"
|
||||
)
|
||||
|
||||
def _gateway(self) -> DockerGateway:
|
||||
"""The data-plane gateway, dual-homed on the agent network + the control
|
||||
network, resolving policy against the orchestrator by name."""
|
||||
return DockerGateway(
|
||||
self.gateway_image,
|
||||
name=self._gateway_name,
|
||||
network=self.network,
|
||||
control_network=self.control_network,
|
||||
orchestrator_url=ORCHESTRATOR_URL_IN_NETWORK,
|
||||
build_context=self._repo_root,
|
||||
dockerfile=None, # images are built by _build_images
|
||||
)
|
||||
|
||||
def ensure_running(
|
||||
self, *, startup_timeout: float = DEFAULT_STARTUP_TIMEOUT_SECONDS,
|
||||
) -> str:
|
||||
"""Ensure the orchestrator + gateway containers are up; return the host
|
||||
control-plane URL. Idempotent — a healthy orchestrator on current source
|
||||
(and a current-image gateway) is left untouched. Raises
|
||||
`OrchestratorStartError` on control-plane startup timeout."""
|
||||
self._build_images()
|
||||
self._ensure_network(self.network, internal=False)
|
||||
|
||||
current_hash = source_hash(self._repo_root)
|
||||
if not (self.is_healthy() and self._orchestrator_source_current(current_hash)):
|
||||
log.info("starting orchestrator container",
|
||||
context={"name": self._orchestrator_name})
|
||||
self._run_orchestrator_container(current_hash)
|
||||
|
||||
deadline = time.monotonic() + startup_timeout
|
||||
while time.monotonic() < deadline:
|
||||
if self.is_healthy():
|
||||
log.info("orchestrator healthy", context={"url": self.url})
|
||||
break
|
||||
time.sleep(_HEALTH_POLL_SECONDS)
|
||||
else:
|
||||
raise OrchestratorStartError(
|
||||
f"orchestrator at {self.url} did not become healthy "
|
||||
f"within {startup_timeout:g}s"
|
||||
)
|
||||
|
||||
# Bring up (or refresh) the gateway once the control plane it resolves
|
||||
# against is healthy. `ensure_running` is itself idempotent.
|
||||
self._gateway().ensure_running()
|
||||
return self.url
|
||||
|
||||
def stop(self) -> None:
|
||||
"""Remove both containers (idempotent)."""
|
||||
run_docker(["docker", "rm", "--force", self._gateway_name])
|
||||
run_docker(["docker", "rm", "--force", self._orchestrator_name])
|
||||
|
||||
|
||||
__all__ = [
|
||||
"DockerInfraService",
|
||||
"ORCHESTRATOR_NAME",
|
||||
"ORCHESTRATOR_NETWORK",
|
||||
"ORCHESTRATOR_IMAGE",
|
||||
"ORCHESTRATOR_SOURCE_HASH_LABEL",
|
||||
"INFRA_NAME",
|
||||
]
|
||||
@@ -37,8 +37,11 @@ from pathlib import Path
|
||||
from typing import Callable, Generator
|
||||
|
||||
from ...agent_provider import runtime_for
|
||||
from ...egress import Egress
|
||||
from ...git_gate import GitGate
|
||||
from ...egress import egress_resolve_token_values
|
||||
from ...git_gate import (
|
||||
provision_git_gate_dynamic_keys,
|
||||
revoke_git_gate_provisioned_keys,
|
||||
)
|
||||
from ...image_cache import check_stale
|
||||
from ...log import die, info, warn
|
||||
from .. import BottleImages
|
||||
@@ -61,10 +64,9 @@ from .compose import (
|
||||
write_compose_file,
|
||||
)
|
||||
from .consolidated_compose import consolidated_agent_compose
|
||||
from ...orchestrator.store.config_store import resolve_teardown_timeout
|
||||
from ...orchestrator.config_store import resolve_teardown_timeout
|
||||
from .consolidated_launch import launch_consolidated, teardown_consolidated
|
||||
from .infra import INFRA_NAME
|
||||
from .gateway import DockerGateway
|
||||
from ...orchestrator.gateway import DockerGateway
|
||||
|
||||
|
||||
# Where the repo root lives, for `docker build` context. Computed once.
|
||||
@@ -123,7 +125,7 @@ def launch(
|
||||
f"teardown failed for container {plan.container_name}"
|
||||
f" (compose-down): {exc!r}"
|
||||
)
|
||||
GitGate().revoke_provisioned_keys(
|
||||
revoke_git_gate_provisioned_keys(
|
||||
_bottle_for_revoke, _git_gate_dir_for_revoke
|
||||
)
|
||||
|
||||
@@ -132,7 +134,7 @@ def launch(
|
||||
# provisioning the bottle's repos into the shared gateway.
|
||||
git_gate_plan = plan.git_gate_plan
|
||||
if git_gate_plan.upstreams:
|
||||
git_gate_plan = GitGate().provision_dynamic_keys(
|
||||
git_gate_plan = provision_git_gate_dynamic_keys(
|
||||
plan.manifest.bottle, git_gate_plan, git_gate_state_dir(plan.slug),
|
||||
)
|
||||
|
||||
@@ -143,7 +145,7 @@ def launch(
|
||||
# handed to the orchestrator (in memory) for the gateway to inject —
|
||||
# the agent never sees them.
|
||||
effective_env = {**os.environ, **plan.agent_provision.provisioned_env}
|
||||
token_values = Egress().resolve_token_values(
|
||||
token_values = egress_resolve_token_values(
|
||||
plan.egress_plan.token_env_map, effective_env,
|
||||
)
|
||||
teardown_timeout = resolve_teardown_timeout()
|
||||
@@ -157,13 +159,11 @@ def launch(
|
||||
)
|
||||
|
||||
# Step 4: install the SHARED gateway CA into the agent (replaces the
|
||||
# per-bottle CA) — read it out of the running gateway container
|
||||
# (INFRA_NAME now aliases the gateway container name; the orchestrator,
|
||||
# split into its own container, holds no CA).
|
||||
# per-bottle CA) — read it out of the running gateway.
|
||||
ca_dir = egress_state_dir(plan.slug) / "gateway-ca"
|
||||
ca_dir.mkdir(parents=True, exist_ok=True)
|
||||
ca_file = ca_dir / "gateway-ca.pem"
|
||||
ca_file.write_text(DockerGateway(name=INFRA_NAME).ca_cert_pem())
|
||||
ca_file.write_text(DockerGateway(network=ctx.network).ca_cert_pem())
|
||||
egress_plan = dataclasses.replace(
|
||||
plan.egress_plan,
|
||||
mitmproxy_ca_host_path=ca_file,
|
||||
@@ -203,7 +203,7 @@ def launch(
|
||||
# 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.store.secret_store import ENV_VAR_SECRET_NAME
|
||||
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 "
|
||||
|
||||
@@ -19,7 +19,7 @@ from ...env import ResolvedEnv
|
||||
from ...agent_provider import AgentProvisionPlan
|
||||
from ...egress import EgressPlan
|
||||
from ...manifest import Manifest
|
||||
from ...supervisor.plan import SupervisePlan
|
||||
from ...supervise import SupervisePlan
|
||||
from ...git_gate import GitGatePlan
|
||||
|
||||
def preflight() -> None:
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
"""Docker host-side primitives used by DockerBottleBackend: the lean
|
||||
`run_docker` subprocess wrapper, probing for docker on PATH, slugifying agent
|
||||
names, checking image/container existence, and building images."""
|
||||
"""Docker host-side primitives used by DockerBottleBackend: probing
|
||||
for docker on PATH, slugifying agent names, checking image/container
|
||||
existence, and building images."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
@@ -11,24 +11,9 @@ import shutil
|
||||
import subprocess
|
||||
from typing import Iterator
|
||||
|
||||
from ...docker_cmd import run_docker
|
||||
from ...log import die, info
|
||||
|
||||
|
||||
def run_docker(
|
||||
argv: list[str], *, env: dict[str, str] | None = None,
|
||||
) -> subprocess.CompletedProcess[str]:
|
||||
"""Run a `docker` command, capturing stdout/stderr as text. Never raises on
|
||||
a non-zero exit — callers inspect `returncode` / `stderr` so they can stay
|
||||
fail-closed or tolerate idempotent no-ops (e.g. removing an already-absent
|
||||
container).
|
||||
|
||||
`env` sets the child process environment — used to hand a secret to a bare
|
||||
`--env NAME` flag (docker inherits its value from this process) so the value
|
||||
never lands on argv or in `docker inspect`'s recorded command line."""
|
||||
return subprocess.run(
|
||||
argv, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True,
|
||||
check=False, env=env,
|
||||
)
|
||||
# from ...workspace import WorkspacePlan
|
||||
|
||||
|
||||
# Cap on the suffix the container-name conflict logic will try before
|
||||
|
||||
@@ -11,7 +11,7 @@ from pathlib import Path
|
||||
|
||||
from ..bottle_state import egress_state_dir
|
||||
from ..egress import EGRESS_ROUTES_FILENAME
|
||||
from ..gateway.egress.addon_core import LOG_OFF, load_config
|
||||
from ..egress_addon_core import LOG_OFF, load_config
|
||||
|
||||
|
||||
class EgressApplyError(RuntimeError):
|
||||
|
||||
@@ -1,25 +1,7 @@
|
||||
"""Firecracker backend: Linux KVM microVM isolation (issue #342).
|
||||
|
||||
Thin by design: `FirecrackerBottleBackend` is re-exported lazily via
|
||||
`__getattr__`, so importing a leaf module under this package doesn't drag the
|
||||
backend (and the framework it pulls) into memory.
|
||||
"""
|
||||
"""Firecracker backend: Linux KVM microVM isolation (issue #342)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING, Any
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from .backend import FirecrackerBottleBackend
|
||||
|
||||
|
||||
def __getattr__(name: str) -> Any:
|
||||
if name == "FirecrackerBottleBackend":
|
||||
from .backend import FirecrackerBottleBackend
|
||||
|
||||
globals()[name] = FirecrackerBottleBackend
|
||||
return FirecrackerBottleBackend
|
||||
raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
|
||||
|
||||
from .backend import FirecrackerBottleBackend
|
||||
|
||||
__all__ = ["FirecrackerBottleBackend"]
|
||||
|
||||
@@ -8,8 +8,7 @@ fail-closed nftables egress boundary. Selected by
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import io
|
||||
from contextlib import contextmanager, redirect_stderr
|
||||
from contextlib import contextmanager
|
||||
from pathlib import Path
|
||||
from typing import Generator, Sequence
|
||||
|
||||
@@ -18,7 +17,7 @@ from ...egress import EgressPlan
|
||||
from ...env import ResolvedEnv
|
||||
from ...git_gate import GitGatePlan
|
||||
from ...manifest import Manifest
|
||||
from ...supervisor.plan import SupervisePlan
|
||||
from ...supervise import SupervisePlan
|
||||
from .. import ActiveAgent, BottleBackend, BottleImages, BottleSpec
|
||||
from . import cleanup as _cleanup
|
||||
from . import enumerate as _enumerate
|
||||
@@ -53,11 +52,8 @@ class FirecrackerBottleBackend(
|
||||
return _setup.setup()
|
||||
|
||||
@classmethod
|
||||
def status(cls, *, quiet: bool = False) -> int:
|
||||
def status(cls) -> int:
|
||||
from . import setup as _setup
|
||||
if quiet:
|
||||
with redirect_stderr(io.StringIO()):
|
||||
return _setup.status()
|
||||
return _setup.status()
|
||||
|
||||
@classmethod
|
||||
@@ -124,4 +120,4 @@ class FirecrackerBottleBackend(
|
||||
|
||||
def ensure_orchestrator(self) -> str:
|
||||
from . import infra_vm
|
||||
return infra_vm.ensure_running().orchestrator_url
|
||||
return infra_vm.ensure_running().control_plane_url
|
||||
|
||||
@@ -1,23 +1,22 @@
|
||||
"""Consolidated bottle launch sequence for the Firecracker backend
|
||||
(PRD 0070, Stage B).
|
||||
|
||||
The orchestrator control plane and the shared gateway run in **two** persistent
|
||||
per-host **infra VMs** (`infra_vm.py`), split per PRD 0070 — not Docker
|
||||
containers. Agent VMs reach the gateway's egress / supervise / git-http ports
|
||||
via a PREROUTING DNAT on their own host-side TAP IP that redirects to the
|
||||
**gateway** VM (see `scripts/firecracker-netpool.sh`) — never the orchestrator,
|
||||
so a breached agent has no L3 route to the control plane. The host CLI reaches
|
||||
the control plane over HTTP at the orchestrator VM's guest IP.
|
||||
The shared gateway + orchestrator control plane run in a single persistent
|
||||
per-host **infra VM** (`infra_vm.py`), not Docker containers. Agent VMs reach
|
||||
the gateway's egress / supervise / git-http ports at the infra VM via a
|
||||
PREROUTING DNAT on their own host-side TAP IP (see
|
||||
`scripts/firecracker-netpool.sh`), and the host CLI reaches the control plane
|
||||
over HTTP at the infra VM's guest IP.
|
||||
|
||||
Attribution is by the agent VM's guest IP, unspoofable by construction: the
|
||||
/31 point-to-point TAP + the `bot_bottle_fc` nft table ensure only the
|
||||
expected VM can source-IP that address.
|
||||
|
||||
Sequence:
|
||||
1. ensure the infra VMs (orchestrator control plane + gateway data plane)
|
||||
are up (a singleton pair — a prior launcher may already have booted them);
|
||||
2. register the bottle on the orchestrator by its guest IP (attribution key)
|
||||
→ bottle id + identity token;
|
||||
1. ensure the infra VM (control plane + gateway) is up (a singleton — a
|
||||
prior launcher may already have booted it);
|
||||
2. register the bottle by its guest IP (attribution key) → bottle id +
|
||||
identity token;
|
||||
3. provision its git-gate repos/creds into the gateway VM (over SSH);
|
||||
4. fetch the shared gateway CA for the provisioner to install in the rootfs.
|
||||
|
||||
@@ -39,7 +38,7 @@ from ...orchestrator.lifecycle import (
|
||||
OrchestratorStartError, # re-exported so callers can catch it
|
||||
)
|
||||
from ...orchestrator.reprovision import reprovision_bottles
|
||||
from ...orchestrator.store.secret_store import ENV_VAR_SECRET_NAME
|
||||
from ...orchestrator.secret_store import ENV_VAR_SECRET_NAME
|
||||
from ..consolidated_util import (
|
||||
provision_bottle,
|
||||
teardown_consolidated as _teardown_util,
|
||||
@@ -125,7 +124,7 @@ def launch_consolidated(
|
||||
provision its git-gate state into the gateway VM. Returns the context the
|
||||
agent-VM launch needs. Raises on failure — the caller tears down."""
|
||||
infra = infra_vm.ensure_running()
|
||||
url = infra.orchestrator_url
|
||||
url = infra.control_plane_url
|
||||
client = OrchestratorClient(url)
|
||||
_reprovision_running_bottles(client)
|
||||
|
||||
@@ -151,7 +150,7 @@ def teardown_consolidated(
|
||||
) -> None:
|
||||
"""Deregister the bottle and remove its git-gate state from the gateway
|
||||
VM. Both steps are idempotent so this is safe from a cleanup trap. Does
|
||||
NOT stop the infra VMs — they're persistent per-host singletons shared by
|
||||
NOT stop the infra VM — it's a persistent per-host singleton shared by
|
||||
every bottle."""
|
||||
_teardown_util(bottle_id, infra_vm.gateway_transport(),
|
||||
orchestrator_url=orchestrator_url, timeout=timeout)
|
||||
|
||||
@@ -60,18 +60,12 @@ class VmHandle:
|
||||
self.process.wait(timeout=5)
|
||||
|
||||
|
||||
def _boot_args(
|
||||
guest_ip: str, host_ip: str, pubkey: str, extra: str = "",
|
||||
) -> str:
|
||||
def _boot_args(guest_ip: str, host_ip: str, pubkey: str) -> str:
|
||||
# ip=<client>::<gw>:<netmask>::<dev>:off — /31 point-to-point link,
|
||||
# so netmask is 255.255.255.254 and the gateway is the host TAP IP.
|
||||
ip_arg = f"ip={guest_ip}::{host_ip}:255.255.255.254::eth0:off"
|
||||
pub_b64 = base64.b64encode(pubkey.encode()).decode()
|
||||
args = f"{_BASE_BOOT_ARGS} {ip_arg} bb_pubkey={pub_b64}"
|
||||
# `extra` carries caller-supplied cmdline params the guest init reads
|
||||
# (e.g. `bb_role=orchestrator|gateway` selecting which infra plane a
|
||||
# shared-rootfs infra VM runs). Agent VMs pass nothing.
|
||||
return f"{args} {extra}".rstrip() if extra else args
|
||||
return f"{_BASE_BOOT_ARGS} {ip_arg} bb_pubkey={pub_b64}"
|
||||
|
||||
|
||||
def _config(
|
||||
@@ -85,7 +79,6 @@ def _config(
|
||||
mem_mib: int,
|
||||
guest_mac: str,
|
||||
data_drive: Path | None = None,
|
||||
extra_boot_args: str = "",
|
||||
) -> dict[str, object]:
|
||||
drives: list[dict[str, object]] = [
|
||||
{
|
||||
@@ -108,7 +101,7 @@ def _config(
|
||||
return {
|
||||
"boot-source": {
|
||||
"kernel_image_path": str(util.kernel_path()),
|
||||
"boot_args": _boot_args(guest_ip, host_ip, pubkey, extra_boot_args),
|
||||
"boot_args": _boot_args(guest_ip, host_ip, pubkey),
|
||||
},
|
||||
"drives": drives,
|
||||
"network-interfaces": [
|
||||
@@ -139,7 +132,6 @@ def boot(
|
||||
guest_mac: str = "06:00:AC:10:00:02",
|
||||
detached: bool = False,
|
||||
data_drive: Path | None = None,
|
||||
extra_boot_args: str = "",
|
||||
) -> VmHandle:
|
||||
"""Write the config and launch the VMM. Returns once the process is
|
||||
spawned; callers wait for SSH readiness separately.
|
||||
@@ -155,7 +147,7 @@ def boot(
|
||||
_config(
|
||||
rootfs=rootfs, tap=tap, guest_ip=guest_ip, host_ip=host_ip,
|
||||
pubkey=pubkey, vcpus=vcpus, mem_mib=mem_mib, guest_mac=guest_mac,
|
||||
data_drive=data_drive, extra_boot_args=extra_boot_args,
|
||||
data_drive=data_drive,
|
||||
),
|
||||
indent=2,
|
||||
))
|
||||
|
||||
@@ -1,17 +1,17 @@
|
||||
"""Docker-free agent-image builds for the Firecracker backend (PRD 0069 Stage 3).
|
||||
|
||||
Agent Dockerfiles build **inside the persistent per-host orchestrator VM**
|
||||
Agent Dockerfiles build **inside the persistent per-host infra VM**
|
||||
(`infra_vm.py`), which carries buildah (rootless, daemonless): no host Docker
|
||||
daemon, no root-equivalent `docker` group. The build runs over SSH against the
|
||||
orchestrator VM and its rootfs streams back to the host, where the existing
|
||||
infra VM and its rootfs streams back to the host, where the existing
|
||||
`mke2fs -d` path (`util.build_rootfs_ext4`) turns it into a bootable ext4.
|
||||
|
||||
Builds run on the control-plane (orchestrator) side — not the data-plane
|
||||
gateway — per PRD 0070 v1 ("builds stay in the orchestrator"): it owns
|
||||
launches and already carries buildah. Tradeoff: an untrusted Dockerfile's
|
||||
`RUN` steps share the VM with the control plane (buildah `--isolation chroot`
|
||||
isn't a hard boundary) — the accepted blast-radius tradeoff, re-splittable
|
||||
into a disposable builder (booted from this same image on its own TAP) later.
|
||||
Building in the infra VM — rather than a throwaway builder VM — means there is
|
||||
one buildah image (`bot-bottle-infra`) and no contention for the orchestrator
|
||||
TAP. Tradeoff: an untrusted Dockerfile's `RUN` steps share the VM with the
|
||||
control plane + gateway (buildah `--isolation chroot` isn't a hard boundary) —
|
||||
the accepted single-VM blast-radius tradeoff, re-splittable into a disposable
|
||||
builder (booted from this same image on its own TAP) later.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -121,12 +121,11 @@ def _build_lock() -> Generator[None, None, None]:
|
||||
def _build_in_infra(
|
||||
dockerfile: Path, base: Path, smoke_test: tuple[str, ...], digest: str,
|
||||
) -> None:
|
||||
"""Ensure the infra VMs are up, `buildah build` the Dockerfile in the
|
||||
orchestrator VM (the build-capable control plane), smoke test the image,
|
||||
and stream its rootfs into `base`. The infra VMs persist; only the
|
||||
per-build container/image/context are cleaned up."""
|
||||
orchestrator = infra_vm.ensure_running().orchestrator
|
||||
key, ip = orchestrator.private_key, orchestrator.guest_ip
|
||||
"""Ensure the infra VM is up, `buildah build` the Dockerfile in it, smoke
|
||||
test the image, and stream its rootfs into `base`. The infra VM persists;
|
||||
only the per-build container/image/context are cleaned up."""
|
||||
infra = infra_vm.ensure_running()
|
||||
key, ip = infra.private_key, infra.guest_ip
|
||||
tag = f"bot-bottle-agent-build-{digest}"
|
||||
ctx = f"/tmp/agent-build-{digest}"
|
||||
smoke_ctr, export_ctr = f"{tag}-smoke", f"{tag}-export"
|
||||
|
||||
@@ -66,7 +66,7 @@ def infra_artifact_version(init_script: str, *, repo_root: Path = _REPO_ROOT) ->
|
||||
|
||||
The package is `COPY bot_bottle /app/bot_bottle`'d wholesale into the image,
|
||||
so hash *every* regular file under it — not just `*.py`. Non-Python inputs
|
||||
(e.g. `gateway/egress/entrypoint.sh`, `netpool.defaults.env`) are baked in too, and
|
||||
(e.g. `egress_entrypoint.sh`, `netpool.defaults.env`) are baked in too, and
|
||||
a change to one must bump the version or a launch host could boot a stale
|
||||
rootfs whose code differs from its checkout. `__pycache__`/`.pyc` are the
|
||||
only exclusions — build artifacts, never copied."""
|
||||
|
||||
@@ -1,30 +1,18 @@
|
||||
"""The per-host infra VMs for the Firecracker backend (PRD 0070).
|
||||
"""The per-host infra VM for the Firecracker backend (PRD 0070 Stage B).
|
||||
|
||||
Two persistent microVMs, split now that #469 got the DB off the data plane
|
||||
(PRD 0070 "Separating the planes"):
|
||||
A single persistent microVM that runs the orchestrator **control plane** (and,
|
||||
in a following step, the gateway **data plane**) — the trusted per-host service
|
||||
the docker backend runs as containers. It boots on the NAT'd orchestrator link
|
||||
(`netpool.orch_slot()`): the host CLI reaches its control plane over HTTP at the
|
||||
guest IP, and agent VMs reach its gateway ports over VM-to-VM routing.
|
||||
|
||||
* **orchestrator VM** — the control plane. Boots on the NAT'd orchestrator
|
||||
link (`netpool.orch_slot()`); the host CLI reaches its `/health` +
|
||||
operator routes over HTTP at the guest IP. Sole opener of `bot-bottle.db`
|
||||
(on its persistent /dev/vdb registry volume); holds the host-canonical
|
||||
signing key (pushed post-boot). Also carries buildah, so in-VM agent-image
|
||||
builds run here (PRD 0070 v1: builds stay with the control plane).
|
||||
* **gateway VM** — the data plane. Boots on its own NAT'd link
|
||||
(`netpool.gw_slot()`); runs the egress / git-http / supervise daemons that
|
||||
agent VMs reach (their gateway-port traffic is DNAT'd here — never to the
|
||||
orchestrator, so a breached agent has no L3 route to the control plane).
|
||||
Holds the mitmproxy CA + a pre-minted `gateway` JWT (never the signing
|
||||
key); reaches the orchestrator's control plane at `orch_guest:8099` over
|
||||
the one nft forward rule that link allows.
|
||||
Build-from-source (the default while the design churns): the rootfs is exported
|
||||
from the locally built orchestrator image, which bakes the stdlib-only
|
||||
control-plane source. A pull-from-registry mode (Gitea's OCI registry) becomes
|
||||
the default later.
|
||||
|
||||
Both VMs boot the **same** shared infra rootfs (gateway + orchestrator +
|
||||
buildah); a `bb_role=` kernel-cmdline arg selects which plane a VM's PID-1
|
||||
init starts, so there is still a single published artifact to build/pull. The
|
||||
gateway VM's slimmer memory ceiling (buildah is present on disk but unused
|
||||
there) is set at boot.
|
||||
|
||||
SSH is left enabled for debugging + provisioning; the control plane is the
|
||||
load-bearing surface.
|
||||
SSH is left enabled for debugging; the control plane is the load-bearing
|
||||
surface.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -45,35 +33,22 @@ from pathlib import Path
|
||||
from typing import Generator
|
||||
|
||||
from ...log import die, info
|
||||
from ...orchestrator_auth import ROLE_GATEWAY, mint
|
||||
from ...paths import host_orchestrator_token
|
||||
from .. import util as backend_util
|
||||
from ..docker import util as docker_mod
|
||||
from ..docker.gateway_provision import GatewayProvisionError
|
||||
from . import firecracker_vm, infra_artifact, netpool, util
|
||||
|
||||
# The orchestrator VM's signing-key path on its persistent /dev/vdb volume
|
||||
# (mounted at BOT_BOTTLE_ROOT=/var/lib/bot-bottle). The launcher seeds this
|
||||
# file with the host-canonical key AFTER boot (over SSH), so the VM verifies
|
||||
# tokens with the same key the host CLI signs with — the host token file stays
|
||||
# the single source of truth, never clobbered per-backend (issue #469 review).
|
||||
_GUEST_SIGNING_KEY_PATH = "/var/lib/bot-bottle/orchestrator-token"
|
||||
# The gateway VM's pre-minted `gateway` JWT path (rootfs, not /dev/vdb — the
|
||||
# data plane has no registry volume and never opens the DB). Pushed post-boot;
|
||||
# the gateway daemons present it to the orchestrator, and never see the key.
|
||||
_GUEST_GATEWAY_JWT_PATH = "/var/lib/bot-bottle/gateway-jwt"
|
||||
|
||||
# The single shared infra image: gateway data plane + baked control-plane
|
||||
# source + buildah (Dockerfile.infra.fc). Built from source by default; a
|
||||
# pull-from-registry mode lands later. Both VMs boot from it.
|
||||
# The single infra-VM image: gateway data plane + baked control-plane source
|
||||
# (Dockerfile.infra FROM the gateway image). Built from source by default;
|
||||
# a pull-from-registry mode lands later.
|
||||
_INFRA_IMAGE = "bot-bottle-infra:latest"
|
||||
_GATEWAY_IMAGE = "bot-bottle-gateway:latest"
|
||||
_ORCHESTRATOR_IMAGE = "bot-bottle-orchestrator:latest"
|
||||
_REPO_ROOT = Path(__file__).resolve().parents[3]
|
||||
|
||||
ORCHESTRATOR_PORT = 8099
|
||||
CONTROL_PLANE_PORT = 8099
|
||||
# Gateway data-plane ports (agent-facing): egress proxy, supervise MCP,
|
||||
# git-http. Reached by agent VMs via the PREROUTING DNAT to the gateway VM.
|
||||
# git-http. Reached by agent VMs over VM-to-VM routing (added next).
|
||||
EGRESS_PORT = 9099
|
||||
SUPERVISE_PORT = 9100
|
||||
GIT_HTTP_PORT = 9420
|
||||
@@ -81,14 +56,7 @@ GIT_HTTP_PORT = 9420
|
||||
# the gateway's TLS interception.
|
||||
_GATEWAY_CA_PATH = "/home/mitmproxy/.mitmproxy/mitmproxy-ca-cert.pem"
|
||||
|
||||
# Memory ceilings (fixed at boot, demand-paged — no balloon reclaim). The
|
||||
# orchestrator keeps the build headroom (buildah's 2-4 GB working set during
|
||||
# in-VM agent builds); the gateway is the slim unit (mitmproxy TLS bump + DLP
|
||||
# body buffering, ~1 GB) — PRD 0070 "Memory: fixed ceilings".
|
||||
_ORCH_MEM_MIB = 4096
|
||||
_GW_MEM_MIB = 2048
|
||||
|
||||
# The infra VMs make direct upstream connections (gateway egress, and buildah
|
||||
# The infra VM makes direct upstream connections (gateway egress, and buildah
|
||||
# during builds), and the kernel `ip=` cmdline sets no resolver. Public for
|
||||
# now; routing DNS through a filtered path is a later refinement.
|
||||
_INFRA_RESOLVER = "1.1.1.1"
|
||||
@@ -96,16 +64,12 @@ _INFRA_RESOLVER = "1.1.1.1"
|
||||
_HEALTH_TIMEOUT_SECONDS = 45.0
|
||||
_HEALTH_POLL_SECONDS = 0.5
|
||||
_CA_TIMEOUT_SECONDS = 30.0
|
||||
# How long the launcher retries pushing a secret while the guest's SSH comes
|
||||
# up. Below the init's own wait window, so a failed push dies here first.
|
||||
_SECRET_PUSH_TIMEOUT_SECONDS = 30.0
|
||||
_SECRET_PUSH_POLL_SECONDS = 0.5
|
||||
|
||||
|
||||
@dataclass
|
||||
class InfraVm:
|
||||
"""A handle to one infra VM: its guest IP and the stable SSH key used to
|
||||
seed secrets / fetch the CA / provision git-gate. `vm` is the live VMM
|
||||
"""A handle to the per-host infra VM: its guest IP and the stable SSH key
|
||||
used to fetch the gateway CA / provision git-gate. `vm` is the live VMM
|
||||
handle when this process booted it, and None when adopting a singleton a
|
||||
prior launcher started (teardown then goes through the PID file)."""
|
||||
|
||||
@@ -114,14 +78,22 @@ class InfraVm:
|
||||
vm: firecracker_vm.VmHandle | None = None
|
||||
|
||||
@property
|
||||
def orchestrator_url(self) -> str:
|
||||
return f"http://{self.guest_ip}:{ORCHESTRATOR_PORT}"
|
||||
def control_plane_url(self) -> str:
|
||||
return f"http://{self.guest_ip}:{CONTROL_PLANE_PORT}"
|
||||
|
||||
def terminate(self) -> None:
|
||||
"""Stop the infra VM — via the live handle if we booted it, else the
|
||||
PID file (adopting-process case)."""
|
||||
if self.vm is not None:
|
||||
self.vm.terminate()
|
||||
else:
|
||||
_kill_pidfile()
|
||||
_pid_file().unlink(missing_ok=True)
|
||||
|
||||
def gateway_ca_pem(self, *, timeout: float = _CA_TIMEOUT_SECONDS) -> str:
|
||||
"""The gateway's mitmproxy CA (PEM) that agents install to trust its
|
||||
TLS interception. Generated a moment after boot, so this polls over
|
||||
SSH until it appears (mirrors DockerGateway.ca_cert_pem). Call on the
|
||||
gateway VM handle."""
|
||||
SSH until it appears (mirrors DockerGateway.ca_cert_pem)."""
|
||||
def _fetch() -> str | None:
|
||||
proc = subprocess.run(
|
||||
util.ssh_base_argv(self.private_key, self.guest_ip)
|
||||
@@ -136,31 +108,13 @@ class InfraVm:
|
||||
die(str(exc))
|
||||
|
||||
|
||||
@dataclass
|
||||
class InfraEndpoint:
|
||||
"""How to reach the running per-host pair. `orchestrator` is the control
|
||||
plane (host CLI + registration + in-VM builds); `gateway` is the data
|
||||
plane (agent egress / git-http / supervise, CA fetch, git-gate
|
||||
provisioning). Mirrors the docker/macOS `InfraEndpoint` shape."""
|
||||
|
||||
orchestrator: InfraVm
|
||||
gateway: InfraVm
|
||||
|
||||
@property
|
||||
def orchestrator_url(self) -> str:
|
||||
return self.orchestrator.orchestrator_url
|
||||
|
||||
def gateway_ca_pem(self, *, timeout: float = _CA_TIMEOUT_SECONDS) -> str:
|
||||
return self.gateway.gateway_ca_pem(timeout=timeout)
|
||||
|
||||
|
||||
def ensure_built() -> None:
|
||||
"""Ensure the infra rootfs is available before boot.
|
||||
|
||||
Default (docker-free, PRD 0069 Stage 2): download + verify the prebuilt
|
||||
rootfs artifact matching this code version (see `infra_artifact`); the
|
||||
launch host needs no Docker. `BOT_BOTTLE_INFRA_BUILD=local` instead builds
|
||||
the fixed images from source with host Docker — the infra image
|
||||
the three fixed images from source with host Docker — the infra image
|
||||
`COPY --from`s the orchestrator image and is `FROM` the gateway image, so
|
||||
both must exist first — for iterating on the Dockerfiles."""
|
||||
if infra_artifact.local_build_requested():
|
||||
@@ -187,10 +141,10 @@ def build_infra_images_with_docker() -> None:
|
||||
|
||||
|
||||
def build_infra_rootfs_dir() -> Path:
|
||||
"""The infra VMs' shared base rootfs: the infra image prepared with the
|
||||
role-branched init as PID 1. The init's content is folded into the cache
|
||||
key so an init change rebuilds the rootfs (the base image digest alone
|
||||
wouldn't catch it)."""
|
||||
"""The infra VM's base rootfs: the infra image prepared with the
|
||||
control-plane + gateway init as PID 1. The init's content is folded into
|
||||
the cache key so an init change rebuilds the rootfs (the base image digest
|
||||
alone wouldn't catch it)."""
|
||||
init = _infra_init()
|
||||
tag = hashlib.sha256(init.encode()).hexdigest()[:8]
|
||||
return util.build_base_rootfs_dir(
|
||||
@@ -198,55 +152,41 @@ def build_infra_rootfs_dir() -> Path:
|
||||
)
|
||||
|
||||
|
||||
def ensure_running() -> InfraEndpoint:
|
||||
"""Idempotent per-host singleton pair. Adopt the running VMs if the
|
||||
orchestrator's control plane is healthy AND the gateway VM is alive AND
|
||||
both booted the CURRENT code version (a prior launcher booted them — they
|
||||
outlive short-lived `start` processes); otherwise clear any stale VMs and
|
||||
boot a fresh pair (orchestrator first, then the gateway that resolves
|
||||
policy against it). Returns handles usable for builds / CA fetch / git-gate
|
||||
provisioning.
|
||||
def ensure_running() -> InfraVm:
|
||||
"""Idempotent per-host singleton. Adopt the infra VM if its control plane
|
||||
is already healthy (a prior launcher booted it — it outlives short-lived
|
||||
`start` processes); otherwise clear any stale VM and boot a fresh one.
|
||||
Returns a handle usable for CA fetch / git-gate provisioning.
|
||||
|
||||
Concurrency-safe: the cold stop/build/boot path is serialized by a host
|
||||
flock, so two simultaneous first launches don't both boot on the same
|
||||
links/PIDs. The healthy fast-path takes no lock."""
|
||||
rootfs/PID. The healthy fast-path takes no lock."""
|
||||
slot = netpool.orch_slot()
|
||||
url = f"http://{slot.guest_ip}:{CONTROL_PLANE_PORT}"
|
||||
key = _infra_dir() / "id_ed25519"
|
||||
url = f"http://{netpool.orch_slot().guest_ip}:{ORCHESTRATOR_PORT}"
|
||||
want = _expected_version()
|
||||
if _adoptable(key, url, want):
|
||||
info(f"adopting running infra VMs (orchestrator at {url})")
|
||||
return _adopt(key)
|
||||
info(f"adopting running infra VM at {url}")
|
||||
return InfraVm(guest_ip=slot.guest_ip, private_key=key)
|
||||
|
||||
with _singleton_lock():
|
||||
# Re-check under the lock: another launcher may have booted them while
|
||||
# Re-check under the lock: another launcher may have booted it while
|
||||
# we waited for the lock (double-checked, so we adopt not re-boot).
|
||||
if _adoptable(key, url, want):
|
||||
info(f"adopting running infra VMs (orchestrator at {url})")
|
||||
return _adopt(key)
|
||||
# Clear stale/hung/OUTDATED VMs holding either link before booting fresh.
|
||||
info(f"adopting running infra VM at {url}")
|
||||
return InfraVm(guest_ip=slot.guest_ip, private_key=key)
|
||||
# Clear a stale/hung/OUTDATED VM holding the link before booting fresh.
|
||||
stop()
|
||||
ensure_built()
|
||||
orchestrator = boot_orchestrator()
|
||||
wait_for_health(orchestrator)
|
||||
gateway = boot_gateway(orchestrator.guest_ip)
|
||||
infra = boot()
|
||||
wait_for_health(infra)
|
||||
_record_booted_version(want)
|
||||
return InfraEndpoint(orchestrator=orchestrator, gateway=gateway)
|
||||
|
||||
|
||||
def _adopt(key: Path) -> InfraEndpoint:
|
||||
"""Build handles to the already-running pair from the stable key + the
|
||||
fixed links (vm=None — teardown then goes through the PID files)."""
|
||||
return InfraEndpoint(
|
||||
orchestrator=InfraVm(
|
||||
guest_ip=netpool.orch_slot().guest_ip, private_key=key),
|
||||
gateway=InfraVm(
|
||||
guest_ip=netpool.gw_slot().guest_ip, private_key=key),
|
||||
)
|
||||
return infra
|
||||
|
||||
|
||||
@contextmanager
|
||||
def _singleton_lock() -> Generator[None, None, None]:
|
||||
"""Host-level exclusive lock serializing the infra pair's cold create path
|
||||
"""Host-level exclusive lock serializing the infra VM's cold create path
|
||||
(`stop`/`ensure_built`/`boot`). flock auto-releases if the launcher
|
||||
crashes, so the lock is never leaked."""
|
||||
lock_path = _infra_dir() / "singleton.lock"
|
||||
@@ -259,78 +199,26 @@ def _singleton_lock() -> Generator[None, None, None]:
|
||||
|
||||
|
||||
def stop() -> None:
|
||||
"""Stop BOTH infra VMs (idempotent — absent is success). Reaps the
|
||||
recorded VMMs AND any orphaned firecracker still bound to either infra
|
||||
config — the PID files drift after crashes / out-of-band kills, and a
|
||||
survivor would hold a link's TAP so the next boot dies with "tap …
|
||||
Resource busy". Also reaps a surviving *legacy* single combined-VM (the
|
||||
pre-split layout booted from `<infra>/config.json` on the orchestrator
|
||||
link): the two-VM `stop` otherwise wouldn't know about it, and it would
|
||||
hold the orchestrator TAP so the first split boot fails — so the cutover
|
||||
is self-healing, no manual host teardown. Drops the version marker so a
|
||||
stopped pair is never treated as adoptable."""
|
||||
_kill_pidfile(_orch_dir())
|
||||
_kill_pidfile(_gw_dir())
|
||||
_kill_pidfile(_infra_dir()) # legacy pre-split combined VM (migration)
|
||||
"""Stop the infra VM singleton (idempotent — absent is success). Reaps the
|
||||
recorded VMM AND any orphaned firecracker still bound to the infra config —
|
||||
the PID file drifts after crashes / out-of-band kills, and a survivor would
|
||||
hold the orchestrator TAP so the next boot dies with "tap … Resource busy".
|
||||
Drops the version marker so a stopped VM is never treated as adoptable."""
|
||||
_kill_pidfile()
|
||||
_kill_infra_firecrackers()
|
||||
_pid_file(_orch_dir()).unlink(missing_ok=True)
|
||||
_pid_file(_gw_dir()).unlink(missing_ok=True)
|
||||
_pid_file(_infra_dir()).unlink(missing_ok=True) # legacy
|
||||
_pid_file().unlink(missing_ok=True)
|
||||
_version_file().unlink(missing_ok=True)
|
||||
|
||||
|
||||
def boot_orchestrator() -> InfraVm:
|
||||
"""Boot the orchestrator (control-plane) VM (detached, so it outlives the
|
||||
launcher) on the orchestrator link, and seed its signing key. Prefer
|
||||
`ensure_running`."""
|
||||
def boot() -> InfraVm:
|
||||
"""Boot the infra VM (detached, so it outlives the launcher) on the
|
||||
orchestrator link, recording its PID. Prefer `ensure_running`."""
|
||||
slot = netpool.orch_slot()
|
||||
orch = _boot_vm(
|
||||
name="bot-bottle-orchestrator", slot=slot, run_dir=_orch_dir(),
|
||||
role="orchestrator", mem_mib=_ORCH_MEM_MIB,
|
||||
data_drive=_ensure_registry_volume(),
|
||||
)
|
||||
# Push the host-canonical signing key over SSH (the init waits for it
|
||||
# before starting the control plane). The host token file stays the single
|
||||
# source of truth, so a co-running Docker/macOS control plane keeps working.
|
||||
_push_signing_key(orch)
|
||||
return orch
|
||||
|
||||
|
||||
def boot_gateway(orchestrator_guest_ip: str) -> InfraVm:
|
||||
"""Boot the gateway (data-plane) VM (detached) on the gateway link, and
|
||||
seed its pre-minted `gateway` JWT. Its daemons resolve policy against the
|
||||
orchestrator at `orchestrator_guest_ip:8099` (passed on the cmdline, so the
|
||||
baked init stays IP-independent). Boot the orchestrator first — the gateway
|
||||
daemons reach it at startup. Prefer `ensure_running`."""
|
||||
slot = netpool.gw_slot()
|
||||
gateway = _boot_vm(
|
||||
name="bot-bottle-gateway", slot=slot, run_dir=_gw_dir(),
|
||||
role="gateway", mem_mib=_GW_MEM_MIB,
|
||||
extra_boot_args=f"bb_orch={orchestrator_guest_ip}",
|
||||
)
|
||||
# Push the pre-minted `gateway` JWT (never the signing key — issue #469).
|
||||
# The init waits for it before starting the data plane.
|
||||
_push_gateway_jwt(gateway)
|
||||
return gateway
|
||||
|
||||
|
||||
def _boot_vm(
|
||||
*,
|
||||
name: str,
|
||||
slot: netpool.Slot,
|
||||
run_dir: Path,
|
||||
role: str,
|
||||
mem_mib: int,
|
||||
data_drive: Path | None = None,
|
||||
extra_boot_args: str = "",
|
||||
) -> InfraVm:
|
||||
"""Boot one infra VM from the shared rootfs on `slot`'s link, tagged with
|
||||
its `bb_role` so the guest init starts the right plane. Records the PID."""
|
||||
if not netpool.tap_present(slot.iface):
|
||||
die(f"infra link {slot.iface} not present.\n"
|
||||
die(f"orchestrator link {slot.iface} not present.\n"
|
||||
f" ./cli.py backend setup --backend=firecracker")
|
||||
|
||||
run_dir.mkdir(parents=True, exist_ok=True)
|
||||
run_dir = _infra_dir()
|
||||
rootfs = run_dir / "rootfs.ext4"
|
||||
if infra_artifact.local_build_requested():
|
||||
util.build_rootfs_ext4(build_infra_rootfs_dir(), rootfs, slack_mib=8192)
|
||||
@@ -341,17 +229,14 @@ def _boot_vm(
|
||||
infra_artifact.infra_artifact_version(_infra_init()), rootfs)
|
||||
private_key, pubkey = _stable_keypair()
|
||||
|
||||
info(f"booting {role} VM on {slot.iface} (guest {slot.guest_ip})")
|
||||
boot_args = f"bb_role={role}"
|
||||
if extra_boot_args:
|
||||
boot_args = f"{boot_args} {extra_boot_args}"
|
||||
info(f"booting infra VM on {slot.iface} (guest {slot.guest_ip})")
|
||||
vm = firecracker_vm.boot(
|
||||
name=name, rootfs=rootfs, tap=slot.iface,
|
||||
name="bot-bottle-infra", rootfs=rootfs, tap=slot.iface,
|
||||
guest_ip=slot.guest_ip, host_ip=slot.host_ip, pubkey=pubkey,
|
||||
run_dir=run_dir, mem_mib=mem_mib, detached=True,
|
||||
data_drive=data_drive, extra_boot_args=boot_args,
|
||||
run_dir=run_dir, mem_mib=4096, detached=True,
|
||||
data_drive=_ensure_registry_volume(),
|
||||
)
|
||||
_pid_file(run_dir).write_text(str(vm.process.pid))
|
||||
_pid_file().write_text(str(vm.process.pid))
|
||||
return InfraVm(guest_ip=slot.guest_ip, private_key=private_key, vm=vm)
|
||||
|
||||
|
||||
@@ -361,29 +246,16 @@ def _infra_dir() -> Path:
|
||||
return d
|
||||
|
||||
|
||||
def _orch_dir() -> Path:
|
||||
d = _infra_dir() / "orchestrator"
|
||||
d.mkdir(parents=True, exist_ok=True)
|
||||
return d
|
||||
|
||||
|
||||
def _gw_dir() -> Path:
|
||||
d = _infra_dir() / "gateway"
|
||||
d.mkdir(parents=True, exist_ok=True)
|
||||
return d
|
||||
|
||||
|
||||
def _pid_file(run_dir: Path) -> Path:
|
||||
return run_dir / "vm.pid"
|
||||
def _pid_file() -> Path:
|
||||
return _infra_dir() / "vm.pid"
|
||||
|
||||
|
||||
def _version_file() -> Path:
|
||||
"""Records the infra-artifact version the *running* pair booted from, so a
|
||||
later launcher can tell whether the singletons it found are the current
|
||||
code. Without it, a healthy pair built from an older image gets adopted
|
||||
forever and the new code never boots — every infra change would need an
|
||||
out-of-band kill to dislodge the stale VMs (and races whatever launched
|
||||
next). Both VMs boot the same artifact, so one marker covers the pair."""
|
||||
"""Records the infra-artifact version the *running* VM booted from, so a
|
||||
later launcher can tell whether the singleton it found is the current code.
|
||||
Without it, a healthy VM built from an older image gets adopted forever and
|
||||
the new code never boots — every infra change would need an out-of-band
|
||||
kill to dislodge the stale VM (and races whatever launched next)."""
|
||||
return _infra_dir() / "booted-version"
|
||||
|
||||
|
||||
@@ -392,35 +264,28 @@ def _expected_version() -> str:
|
||||
|
||||
|
||||
def _adoptable(key: Path, url: str, want: str) -> bool:
|
||||
"""Adopt the running pair only if it booted from the CURRENT version, the
|
||||
orchestrator's control plane is healthy, and the gateway VM is still alive.
|
||||
A missing/mismatched marker means a prior launcher booted an older infra
|
||||
image; a dead gateway means the pair is half-down — reboot both rather than
|
||||
reuse stale or partial state."""
|
||||
"""Adopt a running infra VM only if it booted from the CURRENT version and
|
||||
its control plane is healthy. A missing/mismatched marker means a prior
|
||||
launcher booted an older infra image — reboot rather than reuse stale code."""
|
||||
if not key.exists():
|
||||
return False
|
||||
try:
|
||||
booted = _version_file().read_text(encoding="utf-8").strip()
|
||||
except OSError:
|
||||
return False
|
||||
if booted != want:
|
||||
return False
|
||||
if not _health_ok(url):
|
||||
return False
|
||||
return _pidfile_alive(_gw_dir())
|
||||
return booted == want and _health_ok(url)
|
||||
|
||||
|
||||
def _record_booted_version(version: str) -> None:
|
||||
_version_file().write_text(version + "\n", encoding="utf-8")
|
||||
|
||||
|
||||
# The registry "volume": a host-side ext4 file attached to the orchestrator VM
|
||||
# as a second virtio-block device (guest /dev/vdb), mounted at the control
|
||||
# plane's DB dir. It outlives the ephemeral rootfs, so the bottle registry
|
||||
# survives an orchestrator-VM restart — the firecracker analogue of a docker
|
||||
# volume. It is a plain ext4 file: `sudo mount -o loop <path>` on the host
|
||||
# (with the VM stopped) to inspect bot-bottle.db directly. The gateway VM has
|
||||
# no such volume — the data plane never opens the DB (#469).
|
||||
# The registry "volume": a host-side ext4 file attached to the infra VM as a
|
||||
# second virtio-block device (guest /dev/vdb), mounted at the control plane's
|
||||
# DB dir. It outlives the ephemeral rootfs, so the bottle registry survives an
|
||||
# infra-VM restart — the firecracker analogue of a docker volume. It is a
|
||||
# plain ext4 file: `sudo mount -o loop <path>` on the host (with the VM
|
||||
# stopped) to inspect bot-bottle.db directly.
|
||||
_REGISTRY_SIZE = "512M"
|
||||
|
||||
|
||||
@@ -444,56 +309,10 @@ def _ensure_registry_volume() -> Path:
|
||||
return vol
|
||||
|
||||
|
||||
def _push_signing_key(infra: InfraVm) -> None:
|
||||
"""Push the host-canonical signing key into the freshly booted orchestrator
|
||||
VM over SSH (atomic write), so its control plane verifies tokens with the
|
||||
same key the host CLI signs from. Retries until the guest's SSH is up (it
|
||||
comes up before the init waits for this file); dies if it never lands,
|
||||
since the VM then refuses to start its control plane rather than run OPEN."""
|
||||
_push_secret(
|
||||
infra, host_orchestrator_token(), _GUEST_SIGNING_KEY_PATH,
|
||||
"the control-plane signing key to the orchestrator VM "
|
||||
"(its control plane will not start)",
|
||||
)
|
||||
|
||||
|
||||
def _push_gateway_jwt(infra: InfraVm) -> None:
|
||||
"""Push the pre-minted `gateway` JWT into the freshly booted gateway VM
|
||||
over SSH (atomic write). Minted on the HOST from the canonical signing key
|
||||
so the data plane never holds the key itself (issue #469); the gateway
|
||||
daemons present it to the orchestrator. Retries until SSH is up; dies if it
|
||||
never lands, since the VM then refuses to start the data plane."""
|
||||
_push_secret(
|
||||
infra, mint(ROLE_GATEWAY, host_orchestrator_token()),
|
||||
_GUEST_GATEWAY_JWT_PATH,
|
||||
"the gateway JWT to the gateway VM (its data plane will not start)",
|
||||
)
|
||||
|
||||
|
||||
def _push_secret(infra: InfraVm, secret: str, dest: str, what: str) -> None:
|
||||
"""Pipe `secret` to an atomic write of `dest` in the guest over SSH,
|
||||
retrying while the guest's SSH comes up; die (naming `what`) if it never
|
||||
succeeds. Bare-pipe input keeps the value off argv."""
|
||||
push = f"umask 077; cat > {dest}.tmp && mv {dest}.tmp {dest}"
|
||||
deadline = time.monotonic() + _SECRET_PUSH_TIMEOUT_SECONDS
|
||||
last = ""
|
||||
while time.monotonic() < deadline:
|
||||
proc = subprocess.run(
|
||||
util.ssh_base_argv(infra.private_key, infra.guest_ip) + [push],
|
||||
input=secret, capture_output=True, text=True, check=False,
|
||||
)
|
||||
if proc.returncode == 0:
|
||||
return
|
||||
last = proc.stderr.strip()
|
||||
time.sleep(_SECRET_PUSH_POLL_SECONDS)
|
||||
die(f"could not push {what}: {last or '<no stderr>'}")
|
||||
|
||||
|
||||
def _stable_keypair() -> tuple[Path, str]:
|
||||
"""The infra VMs' shared SSH keypair — generated once and reused, so any
|
||||
later launcher can SSH in (seed secrets / fetch CA / provision) even though
|
||||
a different process booted the VMs. Both VMs get the same pubkey re-injected
|
||||
on every boot via the cmdline."""
|
||||
"""The infra VM's SSH keypair — generated once and reused, so any later
|
||||
launcher can SSH in (fetch CA / provision) even though a different process
|
||||
booted the VM. The pubkey is re-injected on every boot via the cmdline."""
|
||||
d = _infra_dir()
|
||||
key, pub = d / "id_ed25519", d / "id_ed25519.pub"
|
||||
if key.exists() and pub.exists():
|
||||
@@ -508,24 +327,11 @@ def _stable_keypair() -> tuple[Path, str]:
|
||||
return key, pub.read_text().strip()
|
||||
|
||||
|
||||
def _pidfile_alive(run_dir: Path) -> bool:
|
||||
"""True iff `run_dir`'s recorded VMM is still a live firecracker (guards a
|
||||
recycled PID by checking `comm`)."""
|
||||
try:
|
||||
pid = int(_pid_file(run_dir).read_text().strip())
|
||||
except (OSError, ValueError):
|
||||
return False
|
||||
try:
|
||||
return Path(f"/proc/{pid}/comm").read_text().strip() == "firecracker"
|
||||
except OSError:
|
||||
return False
|
||||
|
||||
|
||||
def _kill_pidfile(run_dir: Path) -> None:
|
||||
"""SIGTERM (then SIGKILL) the VMM recorded in `run_dir`, if it's still ours.
|
||||
def _kill_pidfile() -> None:
|
||||
"""SIGTERM (then SIGKILL) the recorded infra VMM, if it's still ours.
|
||||
Guards against a recycled PID by checking the process is firecracker."""
|
||||
try:
|
||||
pid = int(_pid_file(run_dir).read_text().strip())
|
||||
pid = int(_pid_file().read_text().strip())
|
||||
except (OSError, ValueError):
|
||||
return
|
||||
try:
|
||||
@@ -546,18 +352,11 @@ def _kill_pidfile(run_dir: Path) -> None:
|
||||
|
||||
|
||||
def _kill_infra_firecrackers(proc_root: Path = Path("/proc")) -> None:
|
||||
"""SIGKILL any firecracker VMM whose `--config-file` is one of this host's
|
||||
infra configs (orchestrator or gateway), independent of the PID files —
|
||||
reaps orphans it lost track of so both links' TAPs are free to rebind.
|
||||
Also matches the *legacy* pre-split combined-VM config (`<infra>/config.json`)
|
||||
so a surviving old singleton is cleared off the orchestrator link during the
|
||||
cutover. Scoped to these infra config paths, so the pool's agent VMs (other
|
||||
config paths) are untouched."""
|
||||
cfgs = {
|
||||
str(_orch_dir() / "config.json"),
|
||||
str(_gw_dir() / "config.json"),
|
||||
str(_infra_dir() / "config.json"), # legacy pre-split combined VM
|
||||
}
|
||||
"""SIGKILL any firecracker VMM whose `--config-file` is this host's infra
|
||||
config, independent of the PID file — reaps orphans it lost track of so the
|
||||
orchestrator TAP is free to rebind. Scoped to the infra config path, so the
|
||||
interactive pool's agent/infra VMs (other config paths) are untouched."""
|
||||
cfg = str(_infra_dir() / "config.json")
|
||||
for entry in proc_root.iterdir():
|
||||
if not entry.name.isdigit():
|
||||
continue
|
||||
@@ -567,7 +366,7 @@ def _kill_infra_firecrackers(proc_root: Path = Path("/proc")) -> None:
|
||||
args = (entry / "cmdline").read_bytes().split(b"\0")
|
||||
except OSError:
|
||||
continue # process vanished / not ours
|
||||
if any(a.decode("utf-8", "replace") in cfgs for a in args):
|
||||
if any(a.decode("utf-8", "replace") == cfg for a in args):
|
||||
try:
|
||||
os.kill(int(entry.name), signal.SIGKILL)
|
||||
except (OSError, ValueError):
|
||||
@@ -583,8 +382,8 @@ def _health_ok(url: str) -> bool:
|
||||
|
||||
|
||||
class SshGatewayTransport:
|
||||
"""`GatewayTransport` for the gateway running in the gateway VM — the
|
||||
docker exec/cp equivalents over SSH (dropbear + the stable infra key)."""
|
||||
"""`GatewayTransport` for the gateway running in the infra VM — the docker
|
||||
exec/cp equivalents over SSH (dropbear + the stable infra key)."""
|
||||
|
||||
def __init__(self, private_key: Path, guest_ip: str) -> None:
|
||||
self._key = private_key
|
||||
@@ -617,51 +416,42 @@ class SshGatewayTransport:
|
||||
|
||||
|
||||
def gateway_transport() -> SshGatewayTransport:
|
||||
"""git-gate provisioning transport for the gateway VM, built from the
|
||||
stable key + the gateway link's guest IP. Needs no live VM handle, so
|
||||
teardown can use it too."""
|
||||
"""git-gate provisioning transport for the gateway in the infra VM, built
|
||||
from the stable key + the orchestrator link's guest IP. Needs no live VM
|
||||
handle, so teardown can use it too."""
|
||||
return SshGatewayTransport(
|
||||
_infra_dir() / "id_ed25519", netpool.gw_slot().guest_ip)
|
||||
_infra_dir() / "id_ed25519", netpool.orch_slot().guest_ip)
|
||||
|
||||
|
||||
def wait_for_health(
|
||||
infra: InfraVm, *, timeout: float = _HEALTH_TIMEOUT_SECONDS,
|
||||
) -> None:
|
||||
"""Poll the orchestrator's /health until it answers 200 or the deadline
|
||||
"""Poll the control plane's /health until it answers 200 or the deadline
|
||||
passes. Dies (with the console tail) if the VMM exits early."""
|
||||
url = f"{infra.orchestrator_url}/health"
|
||||
url = f"{infra.control_plane_url}/health"
|
||||
deadline = time.monotonic() + timeout
|
||||
while time.monotonic() < deadline:
|
||||
if infra.vm is not None and not infra.vm.is_alive():
|
||||
die(f"orchestrator VM exited during boot (rc={infra.vm.process.returncode}).\n"
|
||||
die(f"infra VM exited during boot (rc={infra.vm.process.returncode}).\n"
|
||||
f"{firecracker_vm._console_tail(infra.vm.console_log)}")
|
||||
try:
|
||||
with urllib.request.urlopen(url, timeout=1.0) as resp:
|
||||
if resp.status == 200:
|
||||
info(f"orchestrator control plane healthy at {infra.orchestrator_url}")
|
||||
info(f"infra control plane healthy at {infra.control_plane_url}")
|
||||
return
|
||||
except (urllib.error.URLError, TimeoutError, OSError):
|
||||
pass
|
||||
time.sleep(_HEALTH_POLL_SECONDS)
|
||||
tail = (firecracker_vm._console_tail(infra.vm.console_log)
|
||||
if infra.vm is not None else "")
|
||||
die(f"orchestrator control plane at {url} did not become healthy within "
|
||||
die(f"infra control plane at {url} did not become healthy within "
|
||||
f"{timeout:.0f}s.\n{tail}")
|
||||
|
||||
|
||||
def _infra_init() -> str:
|
||||
"""PID-1 init for the infra VMs. Shared setup (pseudo-filesystems, PATH,
|
||||
resolver, debug SSH), then a `bb_role` cmdline branch selecting the plane:
|
||||
|
||||
* orchestrator — mount the persistent registry volume, wait for the
|
||||
host-seeded signing key, start ONLY the control plane;
|
||||
* gateway — wait for the host-seeded `gateway` JWT, start ONLY the
|
||||
data-plane daemons (multi-tenant against the orchestrator at the
|
||||
`bb_orch` cmdline address).
|
||||
|
||||
Both VMs boot this same init (one published artifact); the cmdline selects
|
||||
the role, so no orchestrator IP is baked in (an IP_BASE override doesn't
|
||||
change the artifact version)."""
|
||||
"""PID-1 init for the infra VM: mount the pseudo-filesystems, wire a
|
||||
resolver, start dropbear (debug SSH), then launch the control plane and
|
||||
the gateway data plane (multi-tenant against the local control plane)."""
|
||||
return f"""#!/bin/sh
|
||||
# bot-bottle Firecracker infra VM init (PID 1).
|
||||
mount -t proc proc /proc 2>/dev/null
|
||||
@@ -689,63 +479,26 @@ fi
|
||||
chown -R 0:0 /root 2>/dev/null || true
|
||||
mkdir -p /etc/dropbear /run /var/lib/bot-bottle
|
||||
|
||||
# Persistent registry volume (second virtio-block device, /dev/vdb) mounted
|
||||
# at the control plane's DB dir, so bot-bottle.db survives infra-VM restarts.
|
||||
mount -t ext4 /dev/vdb /var/lib/bot-bottle 2>/dev/null || true
|
||||
|
||||
/bb-dropbear -R -E -p 22 &
|
||||
|
||||
ROLE=$(sed -n 's/.*bb_role=\\([^ ]*\\).*/\\1/p' /proc/cmdline)
|
||||
# Control plane. Source is baked at /app; the package is stdlib-only.
|
||||
cd /app
|
||||
BOT_BOTTLE_ROOT=/var/lib/bot-bottle python3 -m bot_bottle.orchestrator \\
|
||||
--host 0.0.0.0 --port {CONTROL_PLANE_PORT} --broker stub &
|
||||
|
||||
if [ "$ROLE" = gateway ]; then
|
||||
# Gateway data plane, multi-tenant: each request resolves source-IP ->
|
||||
# policy against the orchestrator VM (its guest IP is on the cmdline as
|
||||
# bb_orch). The VM backend reaches git over git-http (9420), so the git://
|
||||
# daemon (git-gate, needs a per-bottle entrypoint the consolidated model
|
||||
# doesn't use) is left out. No SUPERVISE_DB_PATH: the data plane reaches the
|
||||
# supervise queue over the control-plane RPC and never opens bot-bottle.db
|
||||
# (PRD 0070 / #469). It presents the pre-minted `gateway` JWT the launcher
|
||||
# pushed; if it never arrives, REFUSE to start rather than run without auth.
|
||||
ORCH=$(sed -n 's/.*bb_orch=\\([^ ]*\\).*/\\1/p' /proc/cmdline)
|
||||
GW_JWT=""
|
||||
i=0
|
||||
while [ "$i" -lt 600 ]; do
|
||||
GW_JWT=$(cat {_GUEST_GATEWAY_JWT_PATH} 2>/dev/null)
|
||||
[ -n "$GW_JWT" ] && break
|
||||
i=$((i + 1))
|
||||
sleep 0.1
|
||||
done
|
||||
if [ -z "$GW_JWT" ]; then
|
||||
echo "infra gateway: gateway JWT never arrived; refusing to start the data plane" >&2
|
||||
else
|
||||
chmod 600 {_GUEST_GATEWAY_JWT_PATH} 2>/dev/null || true
|
||||
BOT_BOTTLE_GATEWAY_DAEMONS=egress,git-http,supervise \\
|
||||
BOT_BOTTLE_ORCHESTRATOR_URL=http://$ORCH:{ORCHESTRATOR_PORT} \\
|
||||
BOT_BOTTLE_ORCHESTRATOR_AUTH_JWT="$GW_JWT" \\
|
||||
python3 -m bot_bottle.gateway.bootstrap &
|
||||
fi
|
||||
else
|
||||
# Control plane. Source is baked at /app; the package is stdlib-only.
|
||||
# Persistent registry volume (second virtio-block device, /dev/vdb) mounted
|
||||
# at the DB dir, so bot-bottle.db survives orchestrator-VM restarts.
|
||||
mount -t ext4 /dev/vdb /var/lib/bot-bottle 2>/dev/null || true
|
||||
# Wait for the launcher to push the host-canonical signing key over SSH,
|
||||
# then hand it ONLY to the orchestrator (to verify tokens). If it never
|
||||
# arrives, REFUSE to start rather than run OPEN — open mode would grant
|
||||
# every unauthenticated caller the `cli` role (issue #469).
|
||||
CP_KEY=""
|
||||
i=0
|
||||
while [ "$i" -lt 600 ]; do
|
||||
CP_KEY=$(cat {_GUEST_SIGNING_KEY_PATH} 2>/dev/null)
|
||||
[ -n "$CP_KEY" ] && break
|
||||
i=$((i + 1))
|
||||
sleep 0.1
|
||||
done
|
||||
if [ -z "$CP_KEY" ]; then
|
||||
echo "infra: control-plane signing key never arrived; refusing to start the control plane (would run OPEN)" >&2
|
||||
else
|
||||
chmod 600 {_GUEST_SIGNING_KEY_PATH} 2>/dev/null || true
|
||||
BOT_BOTTLE_ROOT=/var/lib/bot-bottle BOT_BOTTLE_ORCHESTRATOR_TOKEN="$CP_KEY" python3 -m bot_bottle.orchestrator \\
|
||||
--host 0.0.0.0 --port {ORCHESTRATOR_PORT} --broker stub &
|
||||
fi
|
||||
fi
|
||||
# Gateway data plane, multi-tenant: each request resolves source-IP ->
|
||||
# policy against the local control plane. The VM backend reaches git over
|
||||
# git-http (9420), so the git:// daemon (git-gate, needs a per-bottle
|
||||
# entrypoint the consolidated model doesn't use) is left out. No
|
||||
# SUPERVISE_DB_PATH: the data plane reaches the supervise queue over the
|
||||
# control-plane RPC and never opens bot-bottle.db (PRD 0070 / #469).
|
||||
BOT_BOTTLE_GATEWAY_DAEMONS=egress,git-http,supervise \\
|
||||
BOT_BOTTLE_ORCHESTRATOR_URL=http://127.0.0.1:{CONTROL_PLANE_PORT} \\
|
||||
python3 -m bot_bottle.gateway_init &
|
||||
|
||||
# Reap as PID 1; children are backgrounded, so `wait` blocks.
|
||||
while : ; do wait ; done
|
||||
|
||||
@@ -11,16 +11,15 @@ Per bottle:
|
||||
6. provision (shared gateway CA, prompt, skills, workspace, git, supervise)
|
||||
over SSH.
|
||||
|
||||
The per-bottle Docker sidecar bundle is gone. The shared gateway (its own
|
||||
data-plane VM) handles egress / git-gate / supervise for every VM; the nft
|
||||
netpool's PREROUTING DNAT routes the VMs' gateway-port traffic to that gateway
|
||||
VM, and the nft table's `ct status dnat accept` rule in the forward chain lets
|
||||
it pass. The VM still sends to `host_tap_ip:PORT` — the address its world is,
|
||||
by nft design, limited to.
|
||||
The per-bottle Docker sidecar bundle is gone. The shared gateway handles
|
||||
egress / git-gate / supervise for every VM; Docker's PREROUTING DNAT routes
|
||||
the VMs' traffic to it, and the nft table's `ct status dnat accept` rule
|
||||
in the forward chain lets it pass. The VM still sends to `host_tap_ip:PORT`
|
||||
— the address its world is, by nft design, limited to.
|
||||
|
||||
Isolation is enforced by the operator-provisioned nft table (checked
|
||||
fail-closed in preflight): a VM reaches only the gateway (DNAT'd from the host
|
||||
TAP IP) and nothing else — not even the orchestrator control plane.
|
||||
fail-closed in preflight): a VM reaches only the sidecar (DNAT'd from
|
||||
the host TAP IP) and nothing else.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -39,18 +38,24 @@ from ...bottle_state import (
|
||||
git_gate_state_dir,
|
||||
read_committed_image,
|
||||
)
|
||||
from ...egress import Egress
|
||||
from ...git_gate import GitGate
|
||||
from ...egress import (
|
||||
egress_agent_env_entries,
|
||||
egress_resolve_token_values,
|
||||
)
|
||||
from ...git_gate import (
|
||||
provision_git_gate_dynamic_keys,
|
||||
revoke_git_gate_provisioned_keys,
|
||||
)
|
||||
from ...image_cache import check_stale_path
|
||||
from ...log import die, info, warn
|
||||
from ...supervisor.types import SUPERVISE_PORT
|
||||
from ...supervise import SUPERVISE_PORT
|
||||
from ..docker.egress import EGRESS_PORT
|
||||
from ..util import AGENT_CA_BUNDLE, AGENT_CA_PATH
|
||||
from . import firecracker_vm, image_builder, isolation_probe, netpool, util
|
||||
from .bottle import FirecrackerBottle
|
||||
from .bottle_plan import FirecrackerBottlePlan
|
||||
from ...orchestrator.store.config_store import resolve_teardown_timeout
|
||||
from ...orchestrator.store.secret_store import ENV_VAR_SECRET_NAME
|
||||
from ...orchestrator.config_store import resolve_teardown_timeout
|
||||
from ...orchestrator.secret_store import ENV_VAR_SECRET_NAME
|
||||
from .consolidated_launch import (
|
||||
launch_consolidated,
|
||||
persist_env_var_secret,
|
||||
@@ -81,7 +86,7 @@ def launch(
|
||||
except BaseException as exc: # noqa: W0718 - teardown must continue
|
||||
teardown_exc = exc
|
||||
warn(f"firecracker teardown failed: {exc!r}")
|
||||
GitGate().revoke_provisioned_keys(bottle_for_revoke, git_gate_dir_for_revoke)
|
||||
revoke_git_gate_provisioned_keys(bottle_for_revoke, git_gate_dir_for_revoke)
|
||||
if teardown_exc is not None:
|
||||
raise teardown_exc
|
||||
|
||||
@@ -92,7 +97,7 @@ def launch(
|
||||
# Step 2: mint the git-gate dynamic (gitea) deploy keys, if any.
|
||||
git_gate_plan = plan.git_gate_plan
|
||||
if git_gate_plan.upstreams:
|
||||
git_gate_plan = GitGate().provision_dynamic_keys(
|
||||
git_gate_plan = provision_git_gate_dynamic_keys(
|
||||
plan.manifest.bottle, git_gate_plan, git_gate_state_dir(plan.slug),
|
||||
)
|
||||
|
||||
@@ -108,7 +113,7 @@ def launch(
|
||||
# (in memory) for the gateway to inject — the agent never sees them.
|
||||
# Attribution is by the VM's guest IP (unspoofable via /31 TAP + nft).
|
||||
effective_env = {**os.environ, **plan.agent_provision.provisioned_env}
|
||||
token_values = Egress().resolve_token_values(
|
||||
token_values = egress_resolve_token_values(
|
||||
plan.egress_plan.token_env_map, effective_env,
|
||||
)
|
||||
teardown_timeout = resolve_teardown_timeout()
|
||||
@@ -137,7 +142,7 @@ def launch(
|
||||
)
|
||||
# Point the agent's git-gate insteadOf rewrites and supervise MCP URL
|
||||
# at the shared gateway (reached at the slot's host TAP IP — the VM
|
||||
# sends there and the nft netpool DNAT routes to the gateway VM).
|
||||
# sends there and Docker DNAT routes to the gateway container).
|
||||
git_gate_url = (
|
||||
f"http://{slot.host_ip}:{_GIT_HTTP_PORT}" if git_gate_plan.upstreams else ""
|
||||
)
|
||||
@@ -282,7 +287,7 @@ def _agent_guest_env(plan: FirecrackerBottlePlan, host_ip: str) -> dict[str, str
|
||||
env["MCP_SUPERVISE_URL"] = plan.agent_supervise_url
|
||||
if plan.env_var_secret:
|
||||
env[ENV_VAR_SECRET_NAME] = plan.env_var_secret
|
||||
for entry in Egress().agent_env_entries(plan.egress_plan):
|
||||
for entry in egress_agent_env_entries(plan.egress_plan):
|
||||
key, _, value = entry.partition("=")
|
||||
env[key] = value
|
||||
env.update(plan.agent_provision.guest_env)
|
||||
|
||||
@@ -15,19 +15,11 @@ BOT_BOTTLE_FC_POOL_SIZE=8
|
||||
BOT_BOTTLE_FC_IP_BASE=10.243.0.0
|
||||
BOT_BOTTLE_FC_IFACE_PREFIX=bbfc
|
||||
BOT_BOTTLE_FC_NFT_TABLE=bot_bottle_fc
|
||||
# The orchestrator VM's own TAP — a dedicated link OUTSIDE the bbfc*
|
||||
# agent pool. Unlike agent VMs (which reach only their gateway), the
|
||||
# orchestrator is trusted infra that needs real NAT'd internet egress:
|
||||
# to FROM-pull + apt/npm during in-VM agent-image builds (buildah). Its
|
||||
# The orchestrator/gateway VM's own TAP — a dedicated link OUTSIDE the
|
||||
# bbfc* agent pool. Unlike agent VMs (which reach only their gateway),
|
||||
# the orchestrator is trusted infra that needs real NAT'd internet
|
||||
# egress: to FROM-pull + apt/npm during in-VM agent-image builds
|
||||
# (buildah) and to forward agent egress upstream (Stage B gateway). Its
|
||||
# /31 is the top of the IP_BASE /16 (host x.y.255.0, guest x.y.255.1),
|
||||
# clear of the pool near the bottom of the block.
|
||||
BOT_BOTTLE_FC_ORCH_IFACE=bborch0
|
||||
# The gateway (data-plane) VM's own TAP — the second infra link, split
|
||||
# from the orchestrator now that #469 got the DB off the data plane (PRD
|
||||
# 0070 "Separating the planes"). It mirrors the orchestrator link: NAT'd
|
||||
# internet egress (the gateway forwards agent egress upstream) plus a
|
||||
# forward path to reach the orchestrator's control plane. Its /31 is the
|
||||
# next one above the orchestrator link (host x.y.255.2, guest x.y.255.3).
|
||||
# Agents DNAT their gateway-port traffic here (not to the orchestrator),
|
||||
# so a breached agent has no L3 route to the control plane.
|
||||
BOT_BOTTLE_FC_GW_IFACE=bbgw0
|
||||
|
||||
@@ -79,19 +79,12 @@ def _cfg(key: str) -> str:
|
||||
IFACE_PREFIX = _cfg("BOT_BOTTLE_FC_IFACE_PREFIX")
|
||||
NFT_TABLE = _cfg("BOT_BOTTLE_FC_NFT_TABLE")
|
||||
|
||||
# The orchestrator VM's dedicated TAP — outside the bbfc* agent pool
|
||||
# and, unlike it, NAT'd to the internet (see `orch_slot`). The
|
||||
# The orchestrator/gateway VM's dedicated TAP — outside the bbfc* agent
|
||||
# pool and, unlike it, NAT'd to the internet (see `orch_slot`). The
|
||||
# orchestrator is trusted infra: it builds agent images in-VM (buildah
|
||||
# needs to FROM-pull + apt/npm).
|
||||
# needs to FROM-pull + apt/npm) and forwards agent egress upstream.
|
||||
ORCH_IFACE = _cfg("BOT_BOTTLE_FC_ORCH_IFACE")
|
||||
|
||||
# The gateway (data-plane) VM's dedicated TAP — the second infra link
|
||||
# (see `gw_slot`), split from the orchestrator per PRD 0070. Like the
|
||||
# orchestrator link it is NAT'd to the internet (the gateway forwards
|
||||
# agent egress upstream); unlike it, agents DNAT here, never to the
|
||||
# orchestrator, so a breached agent has no L3 route to the control plane.
|
||||
GW_IFACE = _cfg("BOT_BOTTLE_FC_GW_IFACE")
|
||||
|
||||
|
||||
def pool_size() -> int:
|
||||
return int(_cfg("BOT_BOTTLE_FC_POOL_SIZE"))
|
||||
@@ -137,12 +130,12 @@ def all_slots() -> list[Slot]:
|
||||
|
||||
|
||||
def orch_slot() -> Slot:
|
||||
"""The orchestrator VM's dedicated link — its own TAP (`ORCH_IFACE`)
|
||||
on a /31 at the TOP of the IP_BASE /16 (host x.y.255.0, guest
|
||||
x.y.255.1), well clear of the agent pool near the bottom of the
|
||||
block. Unlike a pool `Slot`, this link is NAT'd out to the internet
|
||||
by the setup (the orchestrator is trusted infra), so it is
|
||||
deliberately *not* one of the isolated `bbfc*` slots.
|
||||
"""The orchestrator/gateway VM's dedicated link — its own TAP
|
||||
(`ORCH_IFACE`) on a /31 at the TOP of the IP_BASE /16 (host
|
||||
x.y.255.0, guest x.y.255.1), well clear of the agent pool near the
|
||||
bottom of the block. Unlike a pool `Slot`, this link is NAT'd out to
|
||||
the internet by the setup (the orchestrator is trusted infra), so it
|
||||
is deliberately *not* one of the isolated `bbfc*` slots.
|
||||
|
||||
`index` is -1 (sentinel: not a pool index)."""
|
||||
base16 = int(ipaddress.IPv4Address(ip_base())) & 0xFFFF0000
|
||||
@@ -155,25 +148,6 @@ def orch_slot() -> Slot:
|
||||
)
|
||||
|
||||
|
||||
def gw_slot() -> Slot:
|
||||
"""The gateway (data-plane) VM's dedicated link — its own TAP
|
||||
(`GW_IFACE`) on the /31 immediately above the orchestrator link (host
|
||||
x.y.255.2, guest x.y.255.3), still clear of the agent pool at the
|
||||
bottom of the block. Mirrors `orch_slot`: NAT'd to the internet (the
|
||||
gateway forwards agent egress upstream), not one of the isolated
|
||||
`bbfc*` slots. Agents DNAT their gateway-port traffic to this guest.
|
||||
|
||||
`index` is -2 (sentinel: not a pool index)."""
|
||||
base16 = int(ipaddress.IPv4Address(ip_base())) & 0xFFFF0000
|
||||
host = base16 + 0xFF02
|
||||
return Slot(
|
||||
index=-2,
|
||||
iface=GW_IFACE,
|
||||
host_ip=str(ipaddress.IPv4Address(host)),
|
||||
guest_ip=str(ipaddress.IPv4Address(host + 1)),
|
||||
)
|
||||
|
||||
|
||||
# --- fail-closed verification ---------------------------------------
|
||||
|
||||
def _run_ok(argv: list[str]) -> bool:
|
||||
|
||||
@@ -9,7 +9,7 @@ from ...egress import EgressPlan
|
||||
from ...env import ResolvedEnv
|
||||
from ...git_gate import GitGatePlan
|
||||
from ...manifest import Manifest
|
||||
from ...supervisor.plan import SupervisePlan
|
||||
from ...supervise import SupervisePlan
|
||||
from .. import BottleSpec
|
||||
from . import util
|
||||
from .bottle_plan import FirecrackerBottlePlan
|
||||
|
||||
@@ -13,7 +13,6 @@ generic `./cli.py backend {setup,status}` command dispatches to.
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import fcntl
|
||||
import os
|
||||
import shutil
|
||||
import subprocess
|
||||
@@ -23,9 +22,6 @@ from pathlib import Path
|
||||
from . import netpool
|
||||
from . import util
|
||||
|
||||
# KVM_GET_API_VERSION = _IO(KVMIO=0xAE, 0x00): cheapest proof of KVM access.
|
||||
_KVM_GET_API_VERSION = 0xAE00
|
||||
|
||||
|
||||
_FC_RELEASES = "https://github.com/firecracker-microvm/firecracker/releases"
|
||||
_UNIT_PATH = Path("/etc/systemd/system") / netpool.SYSTEMD_UNIT
|
||||
@@ -223,90 +219,14 @@ def teardown() -> int:
|
||||
return 0
|
||||
|
||||
|
||||
def _firecracker_binary_ok() -> bool:
|
||||
"""True iff the firecracker binary is on PATH and `--version` exits 0."""
|
||||
if shutil.which("firecracker") is None:
|
||||
return False
|
||||
try:
|
||||
return subprocess.run(
|
||||
["firecracker", "--version"],
|
||||
capture_output=True, check=False, timeout=5,
|
||||
).returncode == 0
|
||||
except (OSError, subprocess.TimeoutExpired):
|
||||
return False
|
||||
|
||||
|
||||
def _kvm_accessible() -> bool:
|
||||
"""True iff /dev/kvm can be opened read-write and responds to KVM_GET_API_VERSION.
|
||||
|
||||
VM creation requires write access; opening read-only may satisfy the
|
||||
ioctl but fails at boot time, so O_RDWR is the permission check."""
|
||||
if not os.path.exists(util._KVM_DEVICE):
|
||||
return False
|
||||
try:
|
||||
fd = os.open(util._KVM_DEVICE, os.O_RDWR | os.O_CLOEXEC)
|
||||
try:
|
||||
fcntl.ioctl(fd, _KVM_GET_API_VERSION)
|
||||
finally:
|
||||
os.close(fd)
|
||||
return True
|
||||
except OSError:
|
||||
return False
|
||||
|
||||
|
||||
def status() -> int:
|
||||
# Readiness == what the launch preflight hard-requires: the binary
|
||||
# executable, /dev/kvm accessible, the TAP pool present, and no range
|
||||
# overlap. Listing the nft table usually needs root, so — like the
|
||||
# preflight — an unconfirmable table is reported but NOT treated as
|
||||
# not-ready; the post-boot isolation probe is the authoritative check.
|
||||
# This keeps an unprivileged `backend status` usable as a launch gate.
|
||||
# Readiness == what the launch preflight hard-requires: the TAP pool
|
||||
# present (unprivileged, authoritative) and no range overlap. Listing
|
||||
# the nft table usually needs root, so — like the preflight — an
|
||||
# unconfirmable table is reported but NOT treated as not-ready; the
|
||||
# post-boot isolation probe is the authoritative check. This keeps an
|
||||
# unprivileged `backend status` usable as a launch gate.
|
||||
ok = True
|
||||
if _firecracker_binary_ok():
|
||||
sys.stderr.write(f"firecracker binary: ok ({shutil.which('firecracker')})\n")
|
||||
else:
|
||||
fc_path = shutil.which("firecracker")
|
||||
if fc_path is None:
|
||||
sys.stderr.write("firecracker binary: NOT found on PATH\n")
|
||||
else:
|
||||
sys.stderr.write(
|
||||
f"firecracker binary: found ({fc_path}) but `--version` failed\n"
|
||||
)
|
||||
ok = False
|
||||
if _kvm_accessible():
|
||||
sys.stderr.write(f"KVM: {util._KVM_DEVICE} accessible\n")
|
||||
else:
|
||||
if not os.path.exists(util._KVM_DEVICE):
|
||||
sys.stderr.write(f"KVM: {util._KVM_DEVICE} not present\n")
|
||||
else:
|
||||
sys.stderr.write(
|
||||
f"KVM: {util._KVM_DEVICE} not accessible (open/ioctl failed)\n"
|
||||
)
|
||||
ok = False
|
||||
kernel = util.kernel_path()
|
||||
if kernel.is_file():
|
||||
sys.stderr.write(f"guest kernel: {kernel}\n")
|
||||
else:
|
||||
sys.stderr.write(
|
||||
f"guest kernel: NOT found at {kernel} "
|
||||
f"(set BOT_BOTTLE_FC_KERNEL or cache a vmlinux there)\n"
|
||||
)
|
||||
ok = False
|
||||
dropbear = util.dropbear_path()
|
||||
if dropbear.is_file():
|
||||
sys.stderr.write(f"dropbear: {dropbear}\n")
|
||||
else:
|
||||
sys.stderr.write(
|
||||
f"dropbear: NOT found at {dropbear} "
|
||||
f"(set BOT_BOTTLE_FC_DROPBEAR or cache a static binary)\n"
|
||||
)
|
||||
ok = False
|
||||
mke2fs = shutil.which("mke2fs")
|
||||
if mke2fs is not None:
|
||||
sys.stderr.write(f"mke2fs: {mke2fs}\n")
|
||||
else:
|
||||
sys.stderr.write("mke2fs: NOT found on PATH (install e2fsprogs)\n")
|
||||
ok = False
|
||||
missing = netpool.missing_taps()
|
||||
total = netpool.pool_size()
|
||||
if missing:
|
||||
|
||||
@@ -1,29 +1,10 @@
|
||||
"""macOS Apple Container backend.
|
||||
|
||||
Selectable via `BOT_BOTTLE_BACKEND=macos-container`. This package owns the Apple
|
||||
`container` CLI integration; launch remains gated until the gateway network
|
||||
enforcement shape is implemented.
|
||||
|
||||
Thin by design: `MacosContainerBottleBackend` is re-exported lazily via
|
||||
`__getattr__`, so importing a leaf module under this package doesn't drag the
|
||||
backend (and the framework it pulls) into memory.
|
||||
Selectable via `BOT_BOTTLE_BACKEND=macos-container`. This package owns
|
||||
the Apple `container` CLI integration; launch remains gated until the
|
||||
gateway network enforcement shape is implemented.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING, Any
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from .backend import MacosContainerBottleBackend
|
||||
|
||||
|
||||
def __getattr__(name: str) -> Any:
|
||||
if name == "MacosContainerBottleBackend":
|
||||
from .backend import MacosContainerBottleBackend
|
||||
|
||||
globals()[name] = MacosContainerBottleBackend
|
||||
return MacosContainerBottleBackend
|
||||
raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
|
||||
|
||||
from .backend import MacosContainerBottleBackend
|
||||
|
||||
__all__ = ["MacosContainerBottleBackend"]
|
||||
|
||||
@@ -2,8 +2,7 @@
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import io
|
||||
from contextlib import contextmanager, redirect_stderr
|
||||
from contextlib import contextmanager
|
||||
from pathlib import Path
|
||||
from typing import Generator, Sequence
|
||||
|
||||
@@ -11,7 +10,7 @@ from ...agent_provider import AgentProvisionPlan
|
||||
from ...egress import EgressPlan
|
||||
from ...env import ResolvedEnv
|
||||
from ...git_gate import GitGatePlan
|
||||
from ...supervisor.plan import SupervisePlan
|
||||
from ...supervise import SupervisePlan
|
||||
from ...manifest import Manifest
|
||||
from .. import ActiveAgent, BottleBackend, BottleImages, BottleSpec
|
||||
from . import cleanup as _cleanup
|
||||
@@ -44,11 +43,8 @@ class MacosContainerBottleBackend(
|
||||
return _setup.setup()
|
||||
|
||||
@classmethod
|
||||
def status(cls, *, quiet: bool = False) -> int:
|
||||
def status(cls) -> int:
|
||||
from . import setup as _setup
|
||||
if quiet:
|
||||
with redirect_stderr(io.StringIO()):
|
||||
return _setup.status()
|
||||
return _setup.status()
|
||||
|
||||
@classmethod
|
||||
@@ -106,7 +102,7 @@ class MacosContainerBottleBackend(
|
||||
(`supervise`) call when no control plane is running yet. Mirrors
|
||||
firecracker's infra-VM bring-up."""
|
||||
from .infra import MacosInfraService
|
||||
return MacosInfraService().ensure_running().orchestrator_url
|
||||
return MacosInfraService().ensure_running().control_plane_url
|
||||
|
||||
def prepare_cleanup(self) -> MacosContainerBottleCleanupPlan:
|
||||
return _cleanup.prepare_cleanup()
|
||||
|
||||
@@ -39,7 +39,7 @@ from ...git_gate import GitGatePlan
|
||||
from ...log import info
|
||||
from ...orchestrator.client import OrchestratorClient, OrchestratorClientError
|
||||
from ...orchestrator.reprovision import reprovision_bottles
|
||||
from ...orchestrator.store.secret_store import ENV_VAR_SECRET_NAME
|
||||
from ...orchestrator.secret_store import ENV_VAR_SECRET_NAME
|
||||
from ..consolidated_util import (
|
||||
provision_bottle,
|
||||
teardown_consolidated as _teardown_util,
|
||||
@@ -90,7 +90,7 @@ def ensure_gateway(
|
||||
service = service or MacosInfraService()
|
||||
infra = service.ensure_running()
|
||||
endpoint = GatewayEndpoint(
|
||||
orchestrator_url=infra.orchestrator_url,
|
||||
orchestrator_url=infra.control_plane_url,
|
||||
gateway_ip=infra.gateway_ip,
|
||||
gateway_ca_pem=service.ca_cert_pem(),
|
||||
network=service.network,
|
||||
|
||||
@@ -12,47 +12,34 @@ from __future__ import annotations
|
||||
|
||||
import os
|
||||
|
||||
from ...gateway import GatewayError
|
||||
from ...orchestrator.gateway import GatewayError
|
||||
from . import util as container_mod
|
||||
|
||||
# The shared host-only network the infra container and every agent bottle sit
|
||||
# on. The agent's address here is the attribution key. Distinct from the docker
|
||||
# names so both backends can coexist on one host.
|
||||
GATEWAY_NETWORK = "bot-bottle-mac-gateway"
|
||||
# The NAT network that gives the gateway (and only it) a route out.
|
||||
# The NAT network that gives the infra container (and only it) a route out.
|
||||
GATEWAY_EGRESS_NETWORK = "bot-bottle-mac-egress"
|
||||
# The control network the gateway reaches the orchestrator over (host-only).
|
||||
# Only the orchestrator + gateway join it; agents never do, so agents have no
|
||||
# route to the control plane (PRD 0070 "Separating the planes").
|
||||
CONTROL_NETWORK = "bot-bottle-mac-control"
|
||||
|
||||
GATEWAY_IMAGE = os.environ.get("BOT_BOTTLE_GATEWAY_IMAGE", "bot-bottle-gateway:latest")
|
||||
ORCHESTRATOR_IMAGE = os.environ.get(
|
||||
"BOT_BOTTLE_ORCHESTRATOR_IMAGE", "bot-bottle-orchestrator:latest"
|
||||
)
|
||||
|
||||
DEFAULT_CA_TIMEOUT_SECONDS = 30.0
|
||||
|
||||
|
||||
def ensure_networks(
|
||||
network: str = GATEWAY_NETWORK,
|
||||
egress_network: str = GATEWAY_EGRESS_NETWORK,
|
||||
control_network: str = CONTROL_NETWORK,
|
||||
network: str = GATEWAY_NETWORK, egress_network: str = GATEWAY_EGRESS_NETWORK,
|
||||
) -> None:
|
||||
"""Create the shared host-only agent network, the NAT egress network, and
|
||||
the host-only control network. Idempotent — `create_network` tolerates
|
||||
'already exists'."""
|
||||
"""Create the shared host-only network + the NAT egress network. Idempotent
|
||||
— `create_network` tolerates 'already exists'."""
|
||||
container_mod.create_network(egress_network)
|
||||
container_mod.create_network(network, internal=True)
|
||||
container_mod.create_network(control_network, internal=True)
|
||||
|
||||
|
||||
__all__ = [
|
||||
"GATEWAY_NETWORK",
|
||||
"GATEWAY_EGRESS_NETWORK",
|
||||
"CONTROL_NETWORK",
|
||||
"GATEWAY_IMAGE",
|
||||
"ORCHESTRATOR_IMAGE",
|
||||
"GatewayError",
|
||||
"DEFAULT_CA_TIMEOUT_SECONDS",
|
||||
"ensure_networks",
|
||||
|
||||
@@ -1,22 +1,34 @@
|
||||
"""The per-host control plane + gateway for the macOS backend (PRD 0070).
|
||||
"""The per-host infra container for the macOS backend (PRD 0070).
|
||||
|
||||
Two Apple containers — the orchestrator (control plane) and the gateway (data
|
||||
plane) — split now that #469 got the DB off the data plane. The single-container
|
||||
model existed only because two Apple-Container guests writing one `bot-bottle.db`
|
||||
over virtiofs would race incoherent `fcntl` locks; with the data plane no longer
|
||||
opening the DB at all, only the orchestrator does, so the split is safe.
|
||||
A single persistent Apple container that runs BOTH the orchestrator control
|
||||
plane and the gateway data plane — the macOS analogue of the Firecracker infra
|
||||
VM (`backend/firecracker/infra_vm.py`), not the docker backend's two separate
|
||||
containers.
|
||||
|
||||
* `bot-bottle-mac-orchestrator` — the lean control plane. Joins the host-only
|
||||
**control network** (`bot-bottle-mac-control`) only. Sole opener of the
|
||||
container-only DB volume; holds the signing key. The host CLI reaches it at
|
||||
its control-network address; the gateway reaches it there too.
|
||||
* `bot-bottle-mac-infra` — the gateway data plane. Triple-homed: the NAT
|
||||
egress network (route out), the host-only agent network (agents + CLI reach
|
||||
the gateway), and the control network (reach the orchestrator by IP — Apple
|
||||
has no container DNS). Holds the mitmproxy CA + the `gateway` JWT.
|
||||
Why one container, not two: Apple Containers are lightweight VMs, each with its
|
||||
own kernel. The docker backend runs the orchestrator and gateway as two
|
||||
containers safely because they share the host kernel, so their concurrent
|
||||
writes to the one `bot-bottle.db` (the orchestrator's registry + the gateway
|
||||
supervise daemon's queue) are serialized by coherent `fcntl` locks. Across two
|
||||
*guest* kernels sharing a virtiofs-mounted DB those locks are not coherent, and
|
||||
concurrent writers can corrupt the file. Firecracker solved this by putting
|
||||
both services in one guest with the DB on a device only that guest mounts; this
|
||||
does the same with Apple primitives.
|
||||
|
||||
Agents sit on the agent network only, never the control network, so they have no
|
||||
route to the control plane (the L3 block, not just the JWT).
|
||||
Two consequences fall out of the single container, both simplifications:
|
||||
|
||||
- **No DNS dance.** The control plane and the gateway daemons reach each other
|
||||
over `127.0.0.1`, so nothing depends on Apple's (absent) container DNS and
|
||||
there is no orchestrator-before-gateway ordering to get right.
|
||||
- **The DB is never host-shared.** It lives on a container-only volume, so no
|
||||
host process opens the live file. The host CLI reaches registry + supervise
|
||||
state through the control-plane HTTP surface (`cli/supervise.py` already uses
|
||||
`OrchestratorClient`), exactly as it does for firecracker.
|
||||
|
||||
The control-plane source is bind-mounted (like the docker orchestrator), so a
|
||||
code change takes effect on the next launch without an image rebuild; the
|
||||
gateway daemons are baked in the gateway image and rebuild through its own
|
||||
digest check.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -29,47 +41,39 @@ from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
|
||||
from ... import log
|
||||
from ...gateway import GATEWAY_CA_CERT, MITMPROXY_HOME
|
||||
from ...orchestrator.gateway import GATEWAY_CA_CERT, MITMPROXY_HOME
|
||||
from ...orchestrator.lifecycle import (
|
||||
DEFAULT_PORT,
|
||||
DEFAULT_STARTUP_TIMEOUT_SECONDS,
|
||||
OrchestratorStartError,
|
||||
source_hash,
|
||||
)
|
||||
from ...orchestrator_auth import ROLE_GATEWAY, mint
|
||||
from ...paths import (
|
||||
ORCHESTRATOR_AUTH_JWT_ENV,
|
||||
ORCHESTRATOR_TOKEN_ENV,
|
||||
CONTROL_PLANE_TOKEN_ENV,
|
||||
HOST_DB_FILENAME,
|
||||
host_orchestrator_token,
|
||||
host_control_plane_token,
|
||||
host_gateway_ca_dir,
|
||||
)
|
||||
from .. import util as backend_util
|
||||
from . import util as container_mod
|
||||
from .gateway import (
|
||||
CONTROL_NETWORK,
|
||||
DEFAULT_CA_TIMEOUT_SECONDS,
|
||||
GATEWAY_EGRESS_NETWORK,
|
||||
GATEWAY_IMAGE,
|
||||
GATEWAY_NETWORK,
|
||||
GatewayError,
|
||||
ORCHESTRATOR_IMAGE,
|
||||
ensure_networks,
|
||||
)
|
||||
|
||||
# The orchestrator (control plane) container + the gateway (data plane)
|
||||
# container. `INFRA_NAME` is kept — now the gateway container — for callers that
|
||||
# still import it (probe / reprovision attribute against the gateway).
|
||||
ORCHESTRATOR_NAME = "bot-bottle-mac-orchestrator"
|
||||
ORCHESTRATOR_LABEL = "bot-bottle-mac-orchestrator=1"
|
||||
INFRA_NAME = "bot-bottle-mac-infra" # the gateway container
|
||||
# The one per-host infra container: control plane + gateway data plane.
|
||||
INFRA_NAME = "bot-bottle-mac-infra"
|
||||
INFRA_LABEL = "bot-bottle-mac-infra=1"
|
||||
# Container-only volume holding bot-bottle.db, mounted ONLY into the
|
||||
# orchestrator. One kernel writes it (never host-shared or cross-guest).
|
||||
# Container-only volume holding bot-bottle.db. No host bind-mount, so the DB is
|
||||
# written by exactly one kernel (this container's). Survives recreation.
|
||||
INFRA_DB_VOLUME = "bot-bottle-mac-db"
|
||||
|
||||
# BOT_BOTTLE_ROOT inside the orchestrator; host_db_path() resolves the DB to
|
||||
# <root>/db/<filename>.
|
||||
# BOT_BOTTLE_ROOT inside the container; host_db_path() resolves the DB to
|
||||
# <root>/db/<filename> and the supervise daemon writes the same file.
|
||||
_DB_ROOT_IN_CONTAINER = "/var/lib/bot-bottle"
|
||||
_DB_PATH_IN_CONTAINER = f"{_DB_ROOT_IN_CONTAINER}/db/{HOST_DB_FILENAME}"
|
||||
_SRC_IN_CONTAINER = "/bot-bottle-src"
|
||||
@@ -78,23 +82,45 @@ _REPO_ROOT = Path(__file__).resolve().parents[3]
|
||||
|
||||
_HEALTH_POLL_SECONDS = 0.25
|
||||
_HEALTH_REQUEST_TIMEOUT_SECONDS = 1.0
|
||||
_CA_POLL_SECONDS = 0.5
|
||||
|
||||
# The gateway subset the consolidated model runs (no per-bottle git:// daemon).
|
||||
_GATEWAY_DAEMONS = "egress,git-http,supervise"
|
||||
|
||||
|
||||
def _init_script(port: int) -> str:
|
||||
"""PID-1 init: start the control plane and the gateway daemons, both in
|
||||
this container, reaching each other over loopback. Backgrounded so `wait`
|
||||
reaps as PID 1. No `set -e` — a transient daemon failure must not kill the
|
||||
whole container (gateway_init applies the same 'stay up' policy)."""
|
||||
return (
|
||||
"export PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin\n"
|
||||
f"mkdir -p $(dirname {_DB_PATH_IN_CONTAINER})\n"
|
||||
# Control plane, from the bind-mounted source (stdlib-only package).
|
||||
f"( cd {_SRC_IN_CONTAINER} && BOT_BOTTLE_ROOT={_DB_ROOT_IN_CONTAINER} "
|
||||
f"python3 -m bot_bottle.orchestrator --host 0.0.0.0 --port {port} "
|
||||
"--broker stub ) &\n"
|
||||
# Gateway data plane, multi-tenant against the local control plane. No
|
||||
# SUPERVISE_DB_PATH: the data plane reaches the supervise queue over the
|
||||
# control-plane RPC and never opens bot-bottle.db (PRD 0070 / #469).
|
||||
f"( cd /app && BOT_BOTTLE_GATEWAY_DAEMONS={_GATEWAY_DAEMONS} "
|
||||
f"BOT_BOTTLE_ORCHESTRATOR_URL=http://127.0.0.1:{port} "
|
||||
f"python3 -m bot_bottle.gateway_init ) &\n"
|
||||
"while : ; do wait ; done\n"
|
||||
)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class InfraEndpoint:
|
||||
"""How to reach the running pair. `orchestrator_url` is the orchestrator's
|
||||
control-network address (host CLI + registration); `gateway_ip` is the
|
||||
gateway's agent-network address (proxy / git-http / MCP target)."""
|
||||
"""How to reach the running infra container. The control plane and the
|
||||
gateway are the same container, so one address serves both."""
|
||||
|
||||
orchestrator_url: str
|
||||
gateway_ip: str
|
||||
control_plane_url: str # http://<infra ip>:8099 — host CLI + registration
|
||||
gateway_ip: str # same container; agents' proxy / git-http / MCP target
|
||||
|
||||
|
||||
class MacosInfraService:
|
||||
"""Manages the per-host orchestrator + gateway containers. Callers use
|
||||
"""Manages the single per-host infra container. Callers use
|
||||
`ensure_running()` (returns the endpoint) and `ca_cert_pem()`."""
|
||||
|
||||
def __init__(
|
||||
@@ -103,41 +129,24 @@ class MacosInfraService:
|
||||
port: int = DEFAULT_PORT,
|
||||
network: str = GATEWAY_NETWORK,
|
||||
egress_network: str = GATEWAY_EGRESS_NETWORK,
|
||||
control_network: str = CONTROL_NETWORK,
|
||||
gateway_image: str = GATEWAY_IMAGE,
|
||||
orchestrator_image: str = ORCHESTRATOR_IMAGE,
|
||||
image: str = GATEWAY_IMAGE,
|
||||
repo_root: Path = _REPO_ROOT,
|
||||
orchestrator_name: str = ORCHESTRATOR_NAME,
|
||||
gateway_name: str = INFRA_NAME,
|
||||
name: str = INFRA_NAME,
|
||||
db_volume: str = INFRA_DB_VOLUME,
|
||||
) -> None:
|
||||
self.port = port
|
||||
self.network = network
|
||||
self.egress_network = egress_network
|
||||
self.control_network = control_network
|
||||
self.gateway_image = gateway_image
|
||||
self.orchestrator_image = orchestrator_image
|
||||
self.image = image
|
||||
self._repo_root = repo_root
|
||||
self._orchestrator_name = orchestrator_name
|
||||
self._gateway_name = gateway_name
|
||||
self._name = name
|
||||
self._db_volume = db_volume
|
||||
|
||||
@property
|
||||
def gateway_name(self) -> str:
|
||||
return self._gateway_name
|
||||
|
||||
def _resolve_orchestrator_url(self) -> str:
|
||||
"""The control-plane URL (orchestrator's control-network address), or ""
|
||||
while it has no address."""
|
||||
ip = container_mod.try_container_ipv4_on_network(
|
||||
self._orchestrator_name, self.control_network)
|
||||
def _resolve_url(self) -> str:
|
||||
"""The control-plane URL, or "" while the container has no address."""
|
||||
ip = container_mod.try_container_ipv4_on_network(self._name, self.network)
|
||||
return f"http://{ip}:{self.port}" if ip else ""
|
||||
|
||||
def _resolve_gateway_ip(self) -> str:
|
||||
"""The gateway's agent-network address, or "" while it has none."""
|
||||
return container_mod.try_container_ipv4_on_network(
|
||||
self._gateway_name, self.network)
|
||||
|
||||
def is_healthy(
|
||||
self, url: str, *, timeout: float = _HEALTH_REQUEST_TIMEOUT_SECONDS,
|
||||
) -> bool:
|
||||
@@ -149,165 +158,150 @@ class MacosInfraService:
|
||||
except (urllib.error.URLError, TimeoutError, OSError):
|
||||
return False
|
||||
|
||||
def _orchestrator_source_current(self, current_hash: str) -> bool:
|
||||
"""True iff the running orchestrator was created from the current
|
||||
bind-mounted control-plane source (it loads that code at startup and
|
||||
won't reload it)."""
|
||||
if not container_mod.container_is_running(self._orchestrator_name):
|
||||
def _source_current(self, current_hash: str) -> bool:
|
||||
"""True iff the running infra container was created from the current
|
||||
bind-mounted control-plane source. The control-plane process loads that
|
||||
code at startup and won't reload it, so a stale container keeps serving
|
||||
OLD code."""
|
||||
if not container_mod.container_is_running(self._name):
|
||||
return False
|
||||
env = container_mod.container_env(self._orchestrator_name)
|
||||
env = container_mod.container_env(self._name)
|
||||
if not env:
|
||||
return True # can't compare → don't churn a working container
|
||||
return env.get("BOT_BOTTLE_SOURCE_HASH") == current_hash
|
||||
|
||||
def _running_healthy_endpoint(self, current_hash: str) -> InfraEndpoint | None:
|
||||
"""The endpoint if the running container is BOTH source-current and
|
||||
answering /health, else None (→ recreate). Health, not just the source
|
||||
label, is what lets a wedged-but-current container self-heal instead of
|
||||
being polled to death forever."""
|
||||
if not self._source_current(current_hash):
|
||||
return None
|
||||
url = self._resolve_url()
|
||||
if url and self.is_healthy(url):
|
||||
return InfraEndpoint(control_plane_url=url, gateway_ip=_ip_of(url))
|
||||
return None
|
||||
|
||||
def ensure_built(self) -> None:
|
||||
"""Ensure the gateway + orchestrator images exist. The control-plane
|
||||
source is bind-mounted, so a code change takes effect without a rebuild;
|
||||
the images still carry the package for their entrypoints."""
|
||||
"""Ensure the gateway data-plane image exists. The control-plane source
|
||||
is bind-mounted, not baked, so only the gateway image needs building."""
|
||||
container_mod.build_image(
|
||||
self.gateway_image, str(self._repo_root), dockerfile="Dockerfile.gateway")
|
||||
container_mod.build_image(
|
||||
self.orchestrator_image, str(self._repo_root),
|
||||
dockerfile="Dockerfile.orchestrator")
|
||||
self.image, str(self._repo_root), dockerfile="Dockerfile.gateway",
|
||||
)
|
||||
|
||||
def ensure_running(
|
||||
self, *, startup_timeout: float = DEFAULT_STARTUP_TIMEOUT_SECONDS,
|
||||
) -> InfraEndpoint:
|
||||
"""Ensure the orchestrator + gateway containers are up; return how to
|
||||
reach them. Idempotent per-host singleton — a healthy orchestrator on
|
||||
current source is left untouched. Raises `OrchestratorStartError` on
|
||||
control-plane startup timeout."""
|
||||
self.ensure_built()
|
||||
ensure_networks(self.network, self.egress_network, self.control_network)
|
||||
|
||||
"""Ensure the single infra container is up; return how to reach it.
|
||||
Idempotent per-host singleton — a healthy container on current source
|
||||
is left untouched, so N launches share the one control plane + gateway.
|
||||
Raises `OrchestratorStartError` on startup timeout."""
|
||||
current_hash = source_hash(self._repo_root)
|
||||
url = self._resolve_orchestrator_url()
|
||||
if not (self._orchestrator_source_current(current_hash)
|
||||
and url and self.is_healthy(url)):
|
||||
log.info("starting orchestrator container",
|
||||
context={"name": self._orchestrator_name})
|
||||
self._run_orchestrator_container(current_hash)
|
||||
url = self._wait_healthy(startup_timeout)
|
||||
endpoint = self._running_healthy_endpoint(current_hash)
|
||||
if endpoint is not None:
|
||||
return endpoint
|
||||
self.ensure_built()
|
||||
log.info("starting infra container", context={"name": self._name})
|
||||
self._run_container(current_hash)
|
||||
return self._wait_healthy(startup_timeout)
|
||||
|
||||
# (Re)ensure the gateway once the control plane it resolves against is
|
||||
# healthy — it needs the orchestrator's control-network address.
|
||||
self._ensure_gateway_container(url)
|
||||
return InfraEndpoint(orchestrator_url=url, gateway_ip=self._resolve_gateway_ip())
|
||||
|
||||
def _run_orchestrator_container(self, current_hash: str) -> None:
|
||||
container_mod.force_remove_container(self._orchestrator_name)
|
||||
_signing_key = host_orchestrator_token()
|
||||
def _run_container(self, current_hash: str) -> None:
|
||||
ensure_networks(self.network, self.egress_network)
|
||||
container_mod.force_remove_container(self._name)
|
||||
argv = [
|
||||
"container", "run", "--detach",
|
||||
"--name", self._orchestrator_name,
|
||||
"--name", self._name,
|
||||
"--label", "bot-bottle.backend=macos-container",
|
||||
"--label", ORCHESTRATOR_LABEL,
|
||||
# Control network only — agents are never on it (L3-isolated).
|
||||
"--network", self.control_network,
|
||||
"--label", INFRA_LABEL,
|
||||
# NAT network FIRST so the gateway's egress has a default route;
|
||||
# the host-only network is where agents (and the host CLI) reach it.
|
||||
"--network", self.egress_network,
|
||||
"--network", self.network,
|
||||
"--dns", container_mod.dns_server(),
|
||||
# Container-only DB volume: exactly one kernel writes bot-bottle.db.
|
||||
# Container-only DB volume: one kernel writes bot-bottle.db, never
|
||||
# shared with the host or another guest.
|
||||
"--volume", f"{self._db_volume}:{_DB_ROOT_IN_CONTAINER}",
|
||||
# Live control-plane source (a code change takes effect on relaunch).
|
||||
# The DB needs a container-only ext4 volume for coherent SQLite
|
||||
# locking, but the CA has no such constraint. Keep it in the host
|
||||
# app-data root so infra-container recreation and Apple Container
|
||||
# volume pruning cannot silently rotate every bottle's trust
|
||||
# anchor (issue #450).
|
||||
"--mount",
|
||||
container_mod.bind_mount_spec(
|
||||
str(host_gateway_ca_dir()), MITMPROXY_HOME),
|
||||
# Bind-mount the control-plane source (read-only); a code change
|
||||
# takes effect on relaunch with no image rebuild.
|
||||
"--mount",
|
||||
container_mod.bind_mount_spec(
|
||||
str(self._repo_root), _SRC_IN_CONTAINER, readonly=True),
|
||||
"--env", f"PYTHONPATH={_SRC_IN_CONTAINER}",
|
||||
"--env", f"BOT_BOTTLE_ROOT={_DB_ROOT_IN_CONTAINER}",
|
||||
# Detect a real control-plane code change and recreate.
|
||||
# Baked onto the container so `_source_current` can detect a real
|
||||
# control-plane code change and recreate.
|
||||
"--env", f"BOT_BOTTLE_SOURCE_HASH={current_hash}",
|
||||
# The signing key — held ONLY by the orchestrator (issue #469). Bare
|
||||
# `--env NAME` keeps the value off argv / `container inspect`.
|
||||
"--env", ORCHESTRATOR_TOKEN_ENV,
|
||||
self.orchestrator_image,
|
||||
# Dockerfile.orchestrator ENTRYPOINT is `-m bot_bottle.orchestrator`.
|
||||
"--host", "0.0.0.0", "--port", str(self.port), "--broker", "stub",
|
||||
# The control-plane secret, for BOTH the control plane (to require
|
||||
# it) and the gateway's PolicyResolver (to present it) — they share
|
||||
# this one container. Bare `--env NAME` inherits the value from the
|
||||
# run process below, so the secret never lands on argv or in
|
||||
# `container inspect`'s command line. The agent runs in a SEPARATE
|
||||
# container that is never given this var, which is the whole point.
|
||||
"--env", CONTROL_PLANE_TOKEN_ENV,
|
||||
"--entrypoint", "sh",
|
||||
self.image,
|
||||
"-c", _init_script(self.port),
|
||||
]
|
||||
result = container_mod.run_container_argv(
|
||||
argv, env={**os.environ, ORCHESTRATOR_TOKEN_ENV: _signing_key})
|
||||
if result.returncode != 0:
|
||||
raise OrchestratorStartError(
|
||||
f"orchestrator container failed to start: "
|
||||
f"{(result.stderr or '').strip() or '<no stderr>'}"
|
||||
)
|
||||
|
||||
def _ensure_gateway_container(self, orchestrator_url: str) -> None:
|
||||
"""Start (recreate) the gateway container, dual-homed on the agent +
|
||||
control networks, resolving policy against `orchestrator_url` (the
|
||||
orchestrator's control-network address — Apple has no DNS)."""
|
||||
container_mod.force_remove_container(self._gateway_name)
|
||||
_signing_key = host_orchestrator_token()
|
||||
argv = [
|
||||
"container", "run", "--detach",
|
||||
"--name", self._gateway_name,
|
||||
"--label", "bot-bottle.backend=macos-container",
|
||||
"--label", INFRA_LABEL,
|
||||
# NAT egress FIRST (default route out); the host-only agent network
|
||||
# is where agents reach the gateway; the control network reaches the
|
||||
# orchestrator.
|
||||
"--network", self.egress_network,
|
||||
"--network", self.network,
|
||||
"--network", self.control_network,
|
||||
"--dns", container_mod.dns_server(),
|
||||
# The mitmproxy CA on a host bind-mount (survives recreation +
|
||||
# volume pruning — issue #450). No DB mount: the data plane never
|
||||
# opens bot-bottle.db (#469).
|
||||
"--mount",
|
||||
container_mod.bind_mount_spec(str(host_gateway_ca_dir()), MITMPROXY_HOME),
|
||||
"--env", f"BOT_BOTTLE_GATEWAY_DAEMONS={_GATEWAY_DAEMONS}",
|
||||
"--env", f"BOT_BOTTLE_ORCHESTRATOR_URL={orchestrator_url}",
|
||||
# The pre-minted `gateway` JWT (never the signing key). Bare
|
||||
# `--env NAME` inherits the value from run_env below.
|
||||
"--env", ORCHESTRATOR_AUTH_JWT_ENV,
|
||||
self.gateway_image,
|
||||
]
|
||||
run_env = {**os.environ, ORCHESTRATOR_AUTH_JWT_ENV: mint(ROLE_GATEWAY, _signing_key)}
|
||||
run_env = {**os.environ, CONTROL_PLANE_TOKEN_ENV: host_control_plane_token()}
|
||||
result = container_mod.run_container_argv(argv, env=run_env)
|
||||
if result.returncode != 0:
|
||||
raise GatewayError(
|
||||
f"gateway container failed to start: "
|
||||
raise OrchestratorStartError(
|
||||
f"infra container failed to start: "
|
||||
f"{(result.stderr or '').strip() or '<no stderr>'}"
|
||||
)
|
||||
|
||||
def _wait_healthy(self, startup_timeout: float) -> str:
|
||||
def _wait_healthy(self, startup_timeout: float) -> InfraEndpoint:
|
||||
deadline = time.monotonic() + startup_timeout
|
||||
while True:
|
||||
url = self._resolve_orchestrator_url()
|
||||
url = self._resolve_url()
|
||||
if url and self.is_healthy(url):
|
||||
log.info("orchestrator healthy", context={"url": url})
|
||||
return url
|
||||
log.info("infra container healthy", context={"url": url})
|
||||
return InfraEndpoint(control_plane_url=url, gateway_ip=_ip_of(url))
|
||||
if time.monotonic() >= deadline:
|
||||
raise OrchestratorStartError(
|
||||
f"orchestrator did not become healthy within "
|
||||
f"infra container did not become healthy within "
|
||||
f"{startup_timeout:g}s"
|
||||
)
|
||||
time.sleep(_HEALTH_POLL_SECONDS)
|
||||
|
||||
def ca_cert_pem(self, *, timeout: float = DEFAULT_CA_TIMEOUT_SECONDS) -> str:
|
||||
"""The gateway's mitmproxy CA (PEM) agents install to trust its TLS
|
||||
interception. Read from the gateway container; polls because mitmproxy
|
||||
writes it a beat after start."""
|
||||
interception. Read through the container path backed by the persistent
|
||||
host CA directory; polls because mitmproxy writes it a beat after
|
||||
start."""
|
||||
def _fetch() -> str | None:
|
||||
result = container_mod.run_container_argv(
|
||||
["container", "exec", self._gateway_name, "cat", GATEWAY_CA_CERT])
|
||||
["container", "exec", self._name, "cat", GATEWAY_CA_CERT])
|
||||
return result.stdout if result.returncode == 0 and result.stdout.strip() else None
|
||||
try:
|
||||
return backend_util.poll_ca_cert(_fetch, timeout=timeout)
|
||||
except TimeoutError as exc:
|
||||
raise GatewayError(
|
||||
f"gateway CA not available in {self._gateway_name} after {timeout:g}s"
|
||||
f"gateway CA not available in {self._name} after {timeout:g}s"
|
||||
) from exc
|
||||
|
||||
def stop(self) -> None:
|
||||
"""Remove both containers (idempotent). The DB volume persists."""
|
||||
container_mod.force_remove_container(self._gateway_name)
|
||||
container_mod.force_remove_container(self._orchestrator_name)
|
||||
"""Remove the infra container (idempotent). The DB volume persists."""
|
||||
container_mod.force_remove_container(self._name)
|
||||
|
||||
|
||||
def probe_orchestrator_url(port: int = DEFAULT_PORT) -> str:
|
||||
"""The running orchestrator's control-plane URL, or "" if it isn't up. Used
|
||||
by host-side control-plane discovery; safe on any host (returns "" when the
|
||||
container or the `container` CLI isn't present)."""
|
||||
ip = container_mod.try_container_ipv4_on_network(ORCHESTRATOR_NAME, CONTROL_NETWORK)
|
||||
def _ip_of(url: str) -> str:
|
||||
"""The host from an http://host:port URL."""
|
||||
return url.split("://", 1)[-1].rsplit(":", 1)[0]
|
||||
|
||||
|
||||
def probe_control_plane_url(port: int = DEFAULT_PORT) -> str:
|
||||
"""The running infra container's control-plane URL, or "" if it isn't up.
|
||||
Used by host-side control-plane discovery (`discover_orchestrator_url`);
|
||||
safe to call on any host — returns "" when the container or the `container`
|
||||
CLI isn't present."""
|
||||
ip = container_mod.try_container_ipv4_on_network(INFRA_NAME, GATEWAY_NETWORK)
|
||||
return f"http://{ip}:{port}" if ip else ""
|
||||
|
||||
|
||||
@@ -316,7 +310,6 @@ __all__ = [
|
||||
"InfraEndpoint",
|
||||
"OrchestratorStartError",
|
||||
"GatewayError",
|
||||
"ORCHESTRATOR_NAME",
|
||||
"INFRA_NAME",
|
||||
"INFRA_DB_VOLUME",
|
||||
]
|
||||
|
||||
@@ -44,13 +44,19 @@ from ...bottle_state import (
|
||||
git_gate_state_dir,
|
||||
read_committed_image,
|
||||
)
|
||||
from ...egress import Egress
|
||||
from ...git_gate import GitGate
|
||||
from ...gateway.git_gate.http_backend import DEFAULT_PORT as _GIT_HTTP_PORT
|
||||
from ...egress import (
|
||||
egress_agent_env_entries,
|
||||
egress_resolve_token_values,
|
||||
)
|
||||
from ...git_gate import (
|
||||
provision_git_gate_dynamic_keys,
|
||||
revoke_git_gate_provisioned_keys,
|
||||
)
|
||||
from ...git_http_backend import DEFAULT_PORT as _GIT_HTTP_PORT
|
||||
from ...image_cache import check_stale
|
||||
from ...log import die, info, warn
|
||||
from .. import BottleImages
|
||||
from ...supervisor.types import SUPERVISE_PORT
|
||||
from ...supervise import SUPERVISE_PORT
|
||||
from ..docker.egress import EGRESS_PORT
|
||||
from ..util import AGENT_CA_BUNDLE, AGENT_CA_PATH
|
||||
from . import util as container_mod
|
||||
@@ -62,8 +68,8 @@ from .gateway_hosts import (
|
||||
)
|
||||
from . import nested_containers as nested_containers_mod
|
||||
from .bottle_plan import MacosContainerBottlePlan
|
||||
from ...orchestrator.store.config_store import resolve_teardown_timeout
|
||||
from ...orchestrator.store.secret_store import ENV_VAR_SECRET_NAME, new_env_var_secret
|
||||
from ...orchestrator.config_store import resolve_teardown_timeout
|
||||
from ...orchestrator.secret_store import ENV_VAR_SECRET_NAME, new_env_var_secret
|
||||
from .consolidated_launch import (
|
||||
GatewayEndpoint,
|
||||
ensure_gateway,
|
||||
@@ -145,7 +151,7 @@ def launch(
|
||||
except BaseException as exc: # noqa: W0718 - teardown must continue
|
||||
teardown_exc = exc
|
||||
warn(f"macos-container teardown failed: {exc!r}")
|
||||
GitGate().revoke_provisioned_keys(bottle_for_revoke, git_gate_dir_for_revoke)
|
||||
revoke_git_gate_provisioned_keys(bottle_for_revoke, git_gate_dir_for_revoke)
|
||||
if teardown_exc is not None:
|
||||
raise teardown_exc
|
||||
|
||||
@@ -188,7 +194,7 @@ def launch(
|
||||
f"{endpoint.network}"
|
||||
)
|
||||
effective_env = {**os.environ, **plan.agent_provision.provisioned_env}
|
||||
token_values = Egress().resolve_token_values(
|
||||
token_values = egress_resolve_token_values(
|
||||
plan.egress_plan.token_env_map, effective_env,
|
||||
)
|
||||
teardown_timeout = resolve_teardown_timeout()
|
||||
@@ -276,7 +282,7 @@ def _provision_git_gate_keys(
|
||||
) -> MacosContainerBottlePlan:
|
||||
if not plan.git_gate_plan.upstreams:
|
||||
return plan
|
||||
git_gate_plan = GitGate().provision_dynamic_keys(
|
||||
git_gate_plan = provision_git_gate_dynamic_keys(
|
||||
plan.manifest.bottle,
|
||||
plan.git_gate_plan,
|
||||
git_gate_state_dir(plan.slug),
|
||||
@@ -448,7 +454,7 @@ def _agent_env_entries(
|
||||
# so the secret value never lands on argv.
|
||||
for name in sorted(plan.forwarded_env.keys()):
|
||||
env.append(name)
|
||||
env.extend(Egress().agent_env_entries(plan.egress_plan))
|
||||
env.extend(egress_agent_env_entries(plan.egress_plan))
|
||||
return tuple(env)
|
||||
|
||||
|
||||
|
||||
@@ -8,7 +8,7 @@ from ...agent_provider import AgentProvisionPlan
|
||||
from ...egress import EgressPlan
|
||||
from ...env import ResolvedEnv
|
||||
from ...git_gate import GitGatePlan
|
||||
from ...supervisor.plan import SupervisePlan
|
||||
from ...supervise import SupervisePlan
|
||||
from ...manifest import Manifest
|
||||
from .. import BottleSpec
|
||||
from . import util as container_mod
|
||||
|
||||
@@ -28,8 +28,7 @@ from ..egress import Egress, EgressPlan
|
||||
from ..git_gate import GitGate, GitGatePlan
|
||||
from ..log import die
|
||||
from ..manifest import Manifest, ManifestBottle
|
||||
from ..supervisor.plan import SupervisePlan
|
||||
from ..orchestrator.supervisor import Supervisor
|
||||
from ..supervise import Supervise, SupervisePlan
|
||||
from . import BottleSpec
|
||||
|
||||
|
||||
@@ -102,7 +101,7 @@ def prepare_supervise(bottle: ManifestBottle, slug: str) -> SupervisePlan | None
|
||||
return None
|
||||
supervise_dir = supervise_state_dir(slug)
|
||||
supervise_dir.mkdir(parents=True, exist_ok=True)
|
||||
return Supervisor().prepare(slug, supervise_dir)
|
||||
return Supervise().prepare(slug, supervise_dir)
|
||||
|
||||
|
||||
def merge_provision_env_vars(provision: AgentProvisionPlan) -> AgentProvisionPlan:
|
||||
|
||||
@@ -1,211 +0,0 @@
|
||||
"""Backend registry, selection, and active-agent enumeration.
|
||||
|
||||
Resolves which bottle backend to use (explicit name / `BOT_BOTTLE_BACKEND` /
|
||||
auto-select), and enumerates running agents across every available backend. The
|
||||
three concrete backends are imported lazily inside `_get_backends` so this
|
||||
module — and anything that only needs to *select* a backend — stays cheap.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import sys
|
||||
from typing import Any
|
||||
|
||||
from ..log import die, info, warn
|
||||
from ..util import read_tty_line
|
||||
from .base import ActiveAgent, BackendStatus, BottleBackend
|
||||
|
||||
|
||||
# _backends is None until the first call to _get_backends(), at which
|
||||
# point all three concrete backend classes are imported and instantiated.
|
||||
# Keeping the imports out of module scope means that importing any
|
||||
# backend sub-module (e.g. `backend.docker.util`) no longer drags the
|
||||
# firecracker and macos-container implementations into memory.
|
||||
#
|
||||
# Tests may replace _backends with a {name: fake} dict via patch.object;
|
||||
# _get_backends() returns the current module-level value as-is when it
|
||||
# is not None, so test fakes take effect without triggering real imports.
|
||||
_backends: dict[str, BottleBackend[Any, Any]] | None = None
|
||||
|
||||
|
||||
def _get_backends() -> dict[str, BottleBackend[Any, Any]]:
|
||||
"""Return the registry of all backend instances, loading lazily on first call."""
|
||||
global _backends # pylint: disable=global-statement
|
||||
if _backends is None:
|
||||
from .docker import DockerBottleBackend
|
||||
from .firecracker import FirecrackerBottleBackend
|
||||
from .macos_container import MacosContainerBottleBackend
|
||||
_backends = {
|
||||
"docker": DockerBottleBackend(),
|
||||
"firecracker": FirecrackerBottleBackend(),
|
||||
"macos-container": MacosContainerBottleBackend(),
|
||||
}
|
||||
return _backends
|
||||
|
||||
|
||||
def get_bottle_backend(
|
||||
name: str | None = None,
|
||||
*,
|
||||
prompt: bool = True,
|
||||
) -> BottleBackend[Any, Any]:
|
||||
"""Resolve the bottle backend.
|
||||
|
||||
`name` precedence:
|
||||
1. explicit arg (e.g. resume passes the recorded backend name)
|
||||
2. BOT_BOTTLE_BACKEND env var
|
||||
3. auto-selection: VM backend first, docker fallback with prompt
|
||||
|
||||
`prompt` controls whether auto-selection may block on an interactive
|
||||
[i/d/q] prompt when falling back to docker. Pass `prompt=False` in
|
||||
non-interactive contexts (headless launches, CI) so the call dies
|
||||
with an actionable message instead of hanging.
|
||||
|
||||
Dies with a pointer at the known backends if the chosen name
|
||||
isn't implemented."""
|
||||
resolved = name or os.environ.get("BOT_BOTTLE_BACKEND")
|
||||
if resolved is None:
|
||||
resolved = _auto_select_backend(prompt=prompt)
|
||||
backends = _get_backends()
|
||||
if resolved not in backends:
|
||||
known = ", ".join(sorted(backends))
|
||||
die(f"unknown backend {resolved!r}; known backends: {known}")
|
||||
return backends[resolved]
|
||||
|
||||
|
||||
def _platform_vm_suggestion() -> str:
|
||||
"""Platform-appropriate VM backend name for install suggestions."""
|
||||
return "macos-container" if sys.platform == "darwin" else "firecracker"
|
||||
|
||||
|
||||
def _print_vm_install_instructions() -> None:
|
||||
"""Print platform-appropriate VM backend install instructions to stderr."""
|
||||
vm = _platform_vm_suggestion()
|
||||
if vm == "macos-container":
|
||||
info("Install Apple Container: https://github.com/apple/container/releases")
|
||||
info("Then start the service: container system start")
|
||||
else:
|
||||
info("Install Firecracker: https://github.com/firecracker-microvm/firecracker/releases")
|
||||
info("Configure the host: ./cli.py backend setup")
|
||||
|
||||
|
||||
def _auto_select_backend(prompt: bool = True) -> str:
|
||||
"""Tier-1 / tier-2 backend auto-selection.
|
||||
|
||||
Tier 1: VM backend — macos-container on macOS when Apple Container is
|
||||
installed; firecracker on KVM-capable Linux even before the binary is
|
||||
present (its preflight prints an install pointer).
|
||||
|
||||
Tier 2: docker, with a security warning and an interactive prompt.
|
||||
When `prompt=False` (headless / CI), dies with an actionable message
|
||||
instead of blocking on a TTY read. When docker is also absent, prints
|
||||
VM install instructions and exits.
|
||||
"""
|
||||
# --- Tier 1: VM backend -----------------------------------------
|
||||
if has_backend("macos-container"):
|
||||
return "macos-container"
|
||||
# A KVM-capable Linux host defaults to firecracker even when the
|
||||
# `firecracker` binary isn't installed yet: selecting it here routes
|
||||
# start through firecracker's preflight, which prints an install
|
||||
# pointer, instead of silently falling back to docker.
|
||||
from .firecracker import FirecrackerBottleBackend
|
||||
if FirecrackerBottleBackend.is_host_capable():
|
||||
return "firecracker"
|
||||
|
||||
# --- Tier 2: docker fallback ------------------------------------
|
||||
if not has_backend("docker"):
|
||||
info("No backend available on this host.")
|
||||
_print_vm_install_instructions()
|
||||
die("no backend available; install a VM backend and re-run")
|
||||
|
||||
vm = _platform_vm_suggestion()
|
||||
warn(
|
||||
"docker is less secure than VM backends — "
|
||||
"containers share the host kernel."
|
||||
)
|
||||
if not prompt:
|
||||
die(
|
||||
f"no VM backend available; set BOT_BOTTLE_BACKEND=docker to proceed "
|
||||
f"with docker, or install the {vm!r} backend."
|
||||
)
|
||||
sys.stderr.write(
|
||||
f"bot-bottle: For better isolation, install the {vm!r} backend.\n"
|
||||
f" [i] show {vm} install instructions and exit\n"
|
||||
" [d] use docker anyway\n"
|
||||
" [q] quit\n"
|
||||
"bot-bottle: choice [i/d/q]: "
|
||||
)
|
||||
sys.stderr.flush()
|
||||
reply = read_tty_line().strip().lower()
|
||||
if reply == "d":
|
||||
return "docker"
|
||||
if reply == "i":
|
||||
_print_vm_install_instructions()
|
||||
die("not proceeding with docker; install a VM backend or set BOT_BOTTLE_BACKEND=docker")
|
||||
|
||||
|
||||
def known_backend_names() -> tuple[str, ...]:
|
||||
"""Sorted tuple of all backend keys in `_get_backends()`. Used by
|
||||
argparse (`--backend` choices) and the dashboard's backend
|
||||
picker."""
|
||||
return tuple(sorted(_get_backends()))
|
||||
|
||||
|
||||
def has_backend(name: str) -> bool:
|
||||
"""Whether the named backend's runtime prerequisites are
|
||||
available on the current host. Cross-backend callers (list,
|
||||
cleanup) skip unavailable backends so a docker-only host
|
||||
doesn't fail when the firecracker backend isn't usable,
|
||||
and vice versa.
|
||||
|
||||
Returns False for unknown names so callers can pass
|
||||
arbitrary input without separate validation."""
|
||||
backends = _get_backends()
|
||||
if name not in backends:
|
||||
return False
|
||||
return backends[name].is_available()
|
||||
|
||||
|
||||
def is_backend_available(name: str) -> bool:
|
||||
"""Cheap availability check: is the backend's binary on PATH?
|
||||
|
||||
Suitable for cleanup enumeration and auto-selection — does NOT probe
|
||||
the daemon or network pool. Use is_backend_ready() for a full
|
||||
readiness check before launching tests."""
|
||||
return has_backend(name)
|
||||
|
||||
|
||||
def is_backend_ready(name: str, *, quiet: bool = False) -> bool:
|
||||
"""Full readiness check: passes all of the backend's status() checks.
|
||||
|
||||
When quiet=False the backend prints diagnostic output explaining what
|
||||
is missing — intended for test-suite guards that run at discovery time
|
||||
so the operator sees a concrete failure reason for each skip.
|
||||
|
||||
Returns False for unknown backend names."""
|
||||
backends = _get_backends()
|
||||
if name not in backends:
|
||||
return False
|
||||
return backends[name].status(quiet=quiet) == BackendStatus.READY
|
||||
|
||||
|
||||
def enumerate_active_agents() -> list[ActiveAgent]:
|
||||
"""All currently-running agents, across every available
|
||||
backend. Used by CLI `active` and the dashboard's agents
|
||||
pane so neither has to know which backends exist. Skips
|
||||
backends whose `is_available()` reports False.
|
||||
|
||||
Sorted by `(started_at, slug)` so the list is stable across
|
||||
dashboard refresh ticks — agents don't shift position while
|
||||
the operator navigates with arrow keys. ISO 8601 timestamps
|
||||
sort lexicographically in chronological order; `slug` is the
|
||||
deterministic tiebreaker. Agents with missing metadata
|
||||
(`started_at == ""`) sort first."""
|
||||
out: list[ActiveAgent] = []
|
||||
backends = _get_backends()
|
||||
for name in sorted(backends):
|
||||
if not backends[name].is_available():
|
||||
continue
|
||||
out.extend(backends[name].enumerate_active())
|
||||
out.sort(key=lambda a: (a.started_at, a.slug))
|
||||
return out
|
||||
+110
-9
@@ -1,15 +1,116 @@
|
||||
"""bot-bottle CLI package.
|
||||
"""Main CLI dispatcher.
|
||||
|
||||
The subcommand handlers live in `commands/` and are assembled into the
|
||||
COMMANDS registry by `commands/__init__.py`; the dispatcher `main()` lives
|
||||
in `__main__.py`. They are re-exported here so `bot_bottle.cli.main`,
|
||||
`bot_bottle.cli.COMMANDS`, and `bot_bottle.cli.NO_MIGRATION_COMMANDS` stay
|
||||
importable (the repo-root `cli.py` entry point and the tests use them).
|
||||
Commands: backend, cleanup, commit, edit, info, init, list, resume, start, supervise
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from .__main__ import main
|
||||
from .commands import COMMANDS, NO_MIGRATION_COMMANDS
|
||||
import sys
|
||||
|
||||
__all__ = ["main", "COMMANDS", "NO_MIGRATION_COMMANDS"]
|
||||
from ..errors import MissingEnvVarError
|
||||
from ..log import Die, die, error
|
||||
from ..manifest import ManifestError
|
||||
from ..store_manager import StoreManager
|
||||
from ._common import PROG
|
||||
from . import list as _list_mod
|
||||
from .backend import cmd_backend
|
||||
from .cleanup import cmd_cleanup
|
||||
from .commit import cmd_commit
|
||||
from .edit import cmd_edit
|
||||
from .info import cmd_info
|
||||
from .init import cmd_init
|
||||
from .login import cmd_login
|
||||
from .resume import cmd_resume
|
||||
from .start import cmd_start
|
||||
from .supervise import cmd_supervise
|
||||
|
||||
cmd_list = _list_mod.cmd_list
|
||||
|
||||
COMMANDS = {
|
||||
"backend": cmd_backend,
|
||||
"cleanup": cmd_cleanup,
|
||||
"commit": cmd_commit,
|
||||
"edit": cmd_edit,
|
||||
"info": cmd_info,
|
||||
"init": cmd_init,
|
||||
"list": cmd_list,
|
||||
"login": cmd_login,
|
||||
"resume": cmd_resume,
|
||||
"start": cmd_start,
|
||||
"supervise": cmd_supervise,
|
||||
}
|
||||
|
||||
# Commands that manage host prerequisites (or are otherwise store-free) and
|
||||
# must run before — or without — a migrated DB. `backend` provisions/probes
|
||||
# the host (TAP pool, /dev/kvm, firecracker) and never opens the store, so
|
||||
# gating it on the schema breaks preflight on a fresh CI runner where stdin
|
||||
# isn't a TTY and the migration prompt can't be answered.
|
||||
NO_MIGRATION_COMMANDS = frozenset({"backend", "login"})
|
||||
|
||||
|
||||
def usage() -> None:
|
||||
sys.stderr.write(f"usage: {PROG} <command> [args...]\n\n")
|
||||
sys.stderr.write("Commands:\n")
|
||||
sys.stderr.write(" backend set up / check / undo a backend's host prerequisites (setup|status|teardown)\n")
|
||||
sys.stderr.write(" cleanup stop and remove all active bot-bottle containers\n")
|
||||
sys.stderr.write(" commit snapshot a running bottle's container state to a Docker image\n")
|
||||
sys.stderr.write(" edit open an agent in vim for editing\n")
|
||||
sys.stderr.write(" info print env, skills, and prompt details for a named agent\n")
|
||||
sys.stderr.write(" init interactively create a new agent and add it to bot-bottle.json\n")
|
||||
sys.stderr.write(" list list available agents or active containers\n")
|
||||
sys.stderr.write(" login register this host with a bot-bottle console\n")
|
||||
sys.stderr.write(
|
||||
" resume re-launch a bottle by its identity "
|
||||
"(continues state from PRD 0016)\n"
|
||||
)
|
||||
sys.stderr.write(
|
||||
" start boot a container for a named agent and "
|
||||
"attach an interactive session\n"
|
||||
)
|
||||
sys.stderr.write(
|
||||
" supervise view + approve/modify/reject pending supervise "
|
||||
"proposals (PRD 0013)\n\n"
|
||||
)
|
||||
sys.stderr.write(f"Run '{PROG} <command> --help' for command-specific usage.\n")
|
||||
|
||||
|
||||
def main(argv: list[str] | None = None) -> int:
|
||||
if argv is None:
|
||||
argv = sys.argv[1:]
|
||||
if not argv:
|
||||
usage()
|
||||
return 2
|
||||
command = argv[0]
|
||||
rest = argv[1:]
|
||||
if command in ("-h", "--help"):
|
||||
usage()
|
||||
return 0
|
||||
handler = COMMANDS.get(command)
|
||||
if handler is None:
|
||||
usage()
|
||||
die(f"unknown command: {command}")
|
||||
mgr = StoreManager.instance()
|
||||
if command not in NO_MIGRATION_COMMANDS and not mgr.is_migrated():
|
||||
sys.stderr.write("bot-bottle: database schema is out of date\n")
|
||||
sys.stderr.write("Migrate now? [y/N] ")
|
||||
sys.stderr.flush()
|
||||
try:
|
||||
answer = sys.stdin.readline().strip().lower()
|
||||
except EOFError:
|
||||
answer = ""
|
||||
if answer != "y":
|
||||
error("migration required — re-run and confirm to migrate")
|
||||
return 1
|
||||
mgr.migrate()
|
||||
try:
|
||||
return handler(rest) or 0
|
||||
except MissingEnvVarError as e:
|
||||
error(str(e))
|
||||
return 1
|
||||
except ManifestError as e:
|
||||
error(str(e))
|
||||
return 1
|
||||
except Die as e:
|
||||
return e.code if isinstance(e.code, int) else 1
|
||||
except KeyboardInterrupt:
|
||||
return 130
|
||||
|
||||
@@ -1,65 +1,15 @@
|
||||
"""Entry point + dispatcher for `python -m bot_bottle.cli`.
|
||||
"""Entry point for `python -m bot_bottle.cli`.
|
||||
|
||||
Maps `bot-bottle <command>` to its handler in the COMMANDS registry
|
||||
(`bot_bottle.cli.commands`), enforces the schema-migration gate, and
|
||||
translates handler exceptions into process exit codes. The repo-root
|
||||
`cli.py` is the usual way in; this makes the package runnable too, so the
|
||||
CLI works from an installed copy where there is no `cli.py` on disk.
|
||||
`cli.py` at the repo root is the usual way in; this makes the package
|
||||
runnable too, so the CLI works from an installed copy where there is no
|
||||
`cli.py` on disk to point at.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import sys
|
||||
|
||||
from ..errors import MissingEnvVarError
|
||||
from ..log import Die, die, error
|
||||
from ..manifest import ManifestError
|
||||
from ..orchestrator.store.store_manager import StoreManager
|
||||
from .commands import COMMANDS, NO_MIGRATION_COMMANDS
|
||||
from .commands.help import cmd_help
|
||||
|
||||
|
||||
def main(argv: list[str] | None = None) -> int:
|
||||
if argv is None:
|
||||
argv = sys.argv[1:]
|
||||
if not argv:
|
||||
cmd_help()
|
||||
return 2
|
||||
command = argv[0]
|
||||
rest = argv[1:]
|
||||
if command in ("-h", "--help"):
|
||||
cmd_help()
|
||||
return 0
|
||||
handler = COMMANDS.get(command)
|
||||
if handler is None:
|
||||
cmd_help()
|
||||
die(f"unknown command: {command}")
|
||||
mgr = StoreManager.instance()
|
||||
if command not in NO_MIGRATION_COMMANDS and not mgr.is_migrated():
|
||||
sys.stderr.write("bot-bottle: database schema is out of date\n")
|
||||
sys.stderr.write("Migrate now? [y/N] ")
|
||||
sys.stderr.flush()
|
||||
try:
|
||||
answer = sys.stdin.readline().strip().lower()
|
||||
except EOFError:
|
||||
answer = ""
|
||||
if answer != "y":
|
||||
error("migration required — re-run and confirm to migrate")
|
||||
return 1
|
||||
mgr.migrate()
|
||||
try:
|
||||
return handler(rest) or 0
|
||||
except MissingEnvVarError as e:
|
||||
error(str(e))
|
||||
return 1
|
||||
except ManifestError as e:
|
||||
error(str(e))
|
||||
return 1
|
||||
except Die as e:
|
||||
return e.code if isinstance(e.code, int) else 1
|
||||
except KeyboardInterrupt:
|
||||
return 130
|
||||
|
||||
from . import main
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
|
||||
@@ -0,0 +1,12 @@
|
||||
"""Shared constants and tty helper for cli subcommands."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
from ..util import read_tty_line as read_tty_line
|
||||
|
||||
PROG = "cli.py"
|
||||
USER_CWD = os.getcwd()
|
||||
REPO_DIR = str(Path(__file__).resolve().parent.parent.parent)
|
||||
@@ -15,8 +15,8 @@ from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
|
||||
from ...backend import get_bottle_backend, known_backend_names
|
||||
from ..constants import PROG
|
||||
from ..backend import get_bottle_backend, known_backend_names
|
||||
from ._common import PROG
|
||||
|
||||
|
||||
def cmd_backend(args: list[str]) -> int:
|
||||
@@ -21,9 +21,9 @@ from __future__ import annotations
|
||||
|
||||
import sys
|
||||
|
||||
from ...backend import get_bottle_backend, has_backend, known_backend_names
|
||||
from ...log import info
|
||||
from ...util import read_tty_line
|
||||
from ..backend import get_bottle_backend, has_backend, known_backend_names
|
||||
from ..log import info
|
||||
from ._common import read_tty_line
|
||||
|
||||
|
||||
def cmd_cleanup(_argv: list[str]) -> int:
|
||||
@@ -1,58 +0,0 @@
|
||||
"""CLI subcommand registry.
|
||||
|
||||
One module per `bot-bottle <command>`, each exposing a `cmd_<name>(argv)`
|
||||
handler. This package `__init__` maps command names to their handlers
|
||||
**lazily**: a short-lived CLI run dispatches exactly one command, so
|
||||
importing all twelve handlers (and their transitive deps — backend,
|
||||
manifest, orchestrator, …) up front is wasted work. Each COMMANDS value is
|
||||
a thin wrapper that imports its handler's module on first call. Shared CLI
|
||||
helpers (`constants`, `tui`) stay one level up in the `cli` package.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from importlib import import_module
|
||||
from typing import Callable
|
||||
|
||||
# command name -> "<submodule>:<handler attr>". Kept as strings so building
|
||||
# the registry imports nothing; the module loads only when dispatched.
|
||||
_HANDLERS: dict[str, str] = {
|
||||
"active": "active:cmd_active",
|
||||
"backend": "backend:cmd_backend",
|
||||
"cleanup": "cleanup:cmd_cleanup",
|
||||
"commit": "commit:cmd_commit",
|
||||
"edit": "edit:cmd_edit",
|
||||
"help": "help:cmd_help",
|
||||
"init": "init:cmd_init",
|
||||
"list": "list:cmd_list",
|
||||
"login": "login:cmd_login",
|
||||
"resume": "resume:cmd_resume",
|
||||
"start": "start:cmd_start",
|
||||
"supervise": "supervise:cmd_supervise",
|
||||
}
|
||||
|
||||
|
||||
def _lazy(spec: str) -> Callable[[list[str]], "int | None"]:
|
||||
"""Wrap a `<module>:<attr>` handler so its module is imported only when
|
||||
the command is actually dispatched, not when the registry is built."""
|
||||
module, attr = spec.split(":")
|
||||
|
||||
def run(argv: list[str]) -> "int | None":
|
||||
handler = getattr(import_module(f".{module}", __name__), attr)
|
||||
return handler(argv)
|
||||
|
||||
run.__name__ = attr
|
||||
return run
|
||||
|
||||
|
||||
COMMANDS = {name: _lazy(spec) for name, spec in _HANDLERS.items()}
|
||||
|
||||
# Commands that manage host prerequisites (or are otherwise store-free) and
|
||||
# must run before — or without — a migrated DB. `backend` provisions/probes
|
||||
# the host (TAP pool, /dev/kvm, firecracker) and never opens the store, so
|
||||
# gating it on the schema breaks preflight on a fresh CI runner where stdin
|
||||
# isn't a TTY and the migration prompt can't be answered. `help` and `login`
|
||||
# likewise never touch the store.
|
||||
NO_MIGRATION_COMMANDS = frozenset({"backend", "help", "login"})
|
||||
|
||||
__all__ = ["COMMANDS", "NO_MIGRATION_COMMANDS"]
|
||||
@@ -1,37 +0,0 @@
|
||||
"""help: print the top-level command list and usage.
|
||||
|
||||
Rendered by the dispatcher for the `help` command and for its
|
||||
`-h`/`--help`, no-args, and unknown-command fallbacks. The per-command
|
||||
summaries live here; keep them in sync with the COMMANDS table in
|
||||
`bot_bottle.cli`.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import sys
|
||||
|
||||
from ..constants import PROG
|
||||
|
||||
|
||||
def cmd_help(argv: list[str] | None = None) -> int:
|
||||
"""Write the top-level usage + command list to stderr. Returns 0;
|
||||
the dispatcher chooses the process exit code per entry path (0 for an
|
||||
explicit `help`/`-h`, 2 for the bare no-args usage error)."""
|
||||
del argv # help takes no arguments
|
||||
w = sys.stderr.write
|
||||
w(f"usage: {PROG} <command> [args...]\n\n")
|
||||
w("Commands:\n")
|
||||
w(" active list currently-running bot-bottle bottles\n")
|
||||
w(" backend set up / check / undo a backend's host prerequisites (setup|status|teardown)\n")
|
||||
w(" cleanup stop and remove all active bot-bottle containers\n")
|
||||
w(" commit snapshot a running bottle's container state to a Docker image\n")
|
||||
w(" edit open an agent in vim for editing\n")
|
||||
w(" help show this command list\n")
|
||||
w(" init interactively create a new agent and add it to bot-bottle.json\n")
|
||||
w(" list list available agents from bot-bottle.json\n")
|
||||
w(" login register this host with a bot-bottle console\n")
|
||||
w(" resume re-launch a bottle by its identity (continues state from PRD 0016)\n")
|
||||
w(" start boot a container for a named agent and attach an interactive session\n")
|
||||
w(" supervise view + approve/modify/reject pending supervise proposals (PRD 0013)\n\n")
|
||||
w(f"Run '{PROG} <command> --help' for command-specific usage.\n")
|
||||
return 0
|
||||
@@ -1,21 +0,0 @@
|
||||
"""list: list available agents."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import sys
|
||||
|
||||
from ...manifest import ManifestIndex
|
||||
from ..constants import PROG
|
||||
|
||||
|
||||
def cmd_list(argv: list[str]) -> int:
|
||||
if argv and argv[0] in ("-h", "--help"):
|
||||
sys.stderr.write(f"usage: {PROG} list\n")
|
||||
sys.stderr.write("\nList all available agents from bot-bottle.json.\n")
|
||||
return 0
|
||||
|
||||
manifest = ManifestIndex.resolve(os.getcwd())
|
||||
for name in manifest.all_agent_names:
|
||||
print(name)
|
||||
return 0
|
||||
@@ -12,12 +12,12 @@ from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
|
||||
from ...backend import enumerate_active_agents
|
||||
from ...backend.freeze import CommitCancelled, get_freezer
|
||||
from ...bottle_state import read_metadata
|
||||
from ...log import die
|
||||
from ..constants import PROG
|
||||
from .. import tui
|
||||
from ..backend import enumerate_active_agents
|
||||
from ..backend.freeze import CommitCancelled, get_freezer
|
||||
from ..bottle_state import read_metadata
|
||||
from ..log import die
|
||||
from ._common import PROG
|
||||
from . import tui
|
||||
|
||||
|
||||
def cmd_commit(argv: list[str]) -> int:
|
||||
@@ -27,7 +27,7 @@ def cmd_commit(argv: list[str]) -> int:
|
||||
nargs="?",
|
||||
default=None,
|
||||
help=(
|
||||
"bottle slug from `cli.py active` "
|
||||
"bottle slug from `cli.py list active` "
|
||||
"(omit to pick interactively)"
|
||||
),
|
||||
)
|
||||
@@ -1,8 +0,0 @@
|
||||
"""Shared CLI constants.
|
||||
|
||||
Kept as a leaf module (imports nothing from the `cli` package) so both the
|
||||
dispatcher (`cli/__init__.py`) and the command modules it imports can share
|
||||
`PROG` without a circular import.
|
||||
"""
|
||||
|
||||
PROG = "cli.py"
|
||||
@@ -7,8 +7,8 @@ import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
from ...log import die
|
||||
from ..constants import PROG
|
||||
from ..log import die
|
||||
from ._common import PROG, USER_CWD
|
||||
|
||||
|
||||
def cmd_edit(argv: list[str]) -> int:
|
||||
@@ -20,7 +20,7 @@ def cmd_edit(argv: list[str]) -> int:
|
||||
if args.scope == "user":
|
||||
target_file = Path(os.environ["HOME"]) / "bot-bottle.json"
|
||||
else:
|
||||
target_file = Path(os.getcwd()) / "bot-bottle.json"
|
||||
target_file = Path(USER_CWD) / "bot-bottle.json"
|
||||
|
||||
if not target_file.is_file():
|
||||
die(f"{target_file} does not exist")
|
||||
@@ -0,0 +1,49 @@
|
||||
"""info: print env, skills, and prompt details for a named agent."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
|
||||
from ..log import info
|
||||
from ..manifest import ManifestIndex
|
||||
from ._common import PROG, USER_CWD
|
||||
|
||||
|
||||
def cmd_info(argv: list[str]) -> int:
|
||||
parser = argparse.ArgumentParser(prog=f"{PROG} info", add_help=True)
|
||||
parser.add_argument("name", help="agent name defined in bot-bottle.json")
|
||||
args = parser.parse_args(argv)
|
||||
|
||||
names = ManifestIndex.resolve(USER_CWD)
|
||||
names.require_agent(args.name)
|
||||
manifest = names.load_for_agent(args.name)
|
||||
|
||||
agent = manifest.agent
|
||||
bottle = manifest.bottle
|
||||
env_names = list(bottle.env.keys())
|
||||
prompt_first_line = agent.prompt.splitlines()[0] if agent.prompt else ""
|
||||
|
||||
print()
|
||||
info(f"agent : {args.name}")
|
||||
info(f"env (names only): {', '.join(env_names) if env_names else '(none)'}")
|
||||
info(f"skills : {' '.join(agent.skills) if agent.skills else '(none)'}")
|
||||
info(
|
||||
f"prompt : {len(agent.prompt)} chars; "
|
||||
f"first line: {prompt_first_line or '(empty)'}"
|
||||
)
|
||||
info(f"bottle : {agent.bottle}")
|
||||
identity = manifest.git_identity_summary()
|
||||
if identity:
|
||||
info(f" git identity : {identity}")
|
||||
if bottle.git:
|
||||
for e in bottle.git:
|
||||
info(
|
||||
f" git remote : {e.Name} -> {e.Upstream} "
|
||||
f"(IdentityFile={e.IdentityFile})"
|
||||
)
|
||||
if e.KnownHostKey:
|
||||
info(f" KnownHostKey: {e.KnownHostKey}")
|
||||
else:
|
||||
info(" git remotes : (none)")
|
||||
print()
|
||||
return 0
|
||||
@@ -10,9 +10,8 @@ import sys
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
from ...log import die, info, warn
|
||||
from ..constants import PROG
|
||||
from ...util import read_tty_line
|
||||
from ..log import die, info, warn
|
||||
from ._common import PROG, USER_CWD, read_tty_line
|
||||
|
||||
|
||||
def cmd_init(argv: list[str]) -> int:
|
||||
@@ -23,7 +22,7 @@ def cmd_init(argv: list[str]) -> int:
|
||||
if args.scope == "user":
|
||||
target_file = Path(os.environ["HOME"]) / "bot-bottle.json"
|
||||
else:
|
||||
target_file = Path(os.getcwd()) / "bot-bottle.json"
|
||||
target_file = Path(USER_CWD) / "bot-bottle.json"
|
||||
|
||||
print(file=sys.stderr)
|
||||
info(f"bot-bottle init — adding a new agent to {target_file}")
|
||||
@@ -1,12 +1,14 @@
|
||||
"""active: list currently-running bot-bottle bottles."""
|
||||
"""list: list available agents or active bottles."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import os
|
||||
import sys
|
||||
|
||||
from ...backend import enumerate_active_agents
|
||||
from ..constants import PROG
|
||||
from ..backend import enumerate_active_agents
|
||||
from ..manifest import ManifestIndex
|
||||
from ._common import PROG, USER_CWD
|
||||
|
||||
_ANSI_COLOR_CODES: dict[str, str] = {
|
||||
"red": "\033[91m",
|
||||
@@ -32,13 +34,20 @@ def _ansi_label(text: str, color: str) -> str:
|
||||
return f"{code}{text}{_ANSI_RESET}"
|
||||
|
||||
|
||||
def cmd_active(argv: list[str]) -> int:
|
||||
if argv and argv[0] in ("-h", "--help"):
|
||||
sys.stderr.write(f"usage: {PROG} active\n")
|
||||
sys.stderr.write("\nList all currently-running bot-bottle bottles.\n")
|
||||
sys.stderr.write("Output: <backend>\\t<slug>\\t<label>\\t<services>\n")
|
||||
def cmd_list(argv: list[str]) -> int:
|
||||
parser = argparse.ArgumentParser(prog=f"{PROG} list", add_help=True)
|
||||
parser.add_argument("scope", choices=["available", "active"])
|
||||
args = parser.parse_args(argv)
|
||||
|
||||
if args.scope == "available":
|
||||
manifest = ManifestIndex.resolve(USER_CWD)
|
||||
for name in manifest.all_agent_names:
|
||||
print(name)
|
||||
return 0
|
||||
|
||||
# `active` enumerates every backend (docker, firecracker,
|
||||
# macos-container) so non-docker bottles aren't hidden behind
|
||||
# the env var.
|
||||
active = enumerate_active_agents()
|
||||
if not active:
|
||||
print("no active bot-bottle bottles", file=sys.stderr)
|
||||
@@ -25,7 +25,7 @@ import urllib.request
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
from ...paths import bot_bottle_root
|
||||
from ..paths import bot_bottle_root
|
||||
|
||||
_CONSOLE_URL_ENV = "BB_CONSOLE_URL"
|
||||
_POLL_SLEEP = 2 # seconds between polls; matches console's poll_interval default
|
||||
@@ -15,13 +15,12 @@ to bring up the replacement from the recorded state.
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import os
|
||||
|
||||
from ...backend import BottleSpec
|
||||
from ...bottle_state import read_metadata
|
||||
from ...log import die
|
||||
from ...manifest import ManifestIndex
|
||||
from ..constants import PROG
|
||||
from ..backend import BottleSpec
|
||||
from ..bottle_state import read_metadata
|
||||
from ..log import die
|
||||
from ..manifest import ManifestIndex
|
||||
from ._common import PROG, USER_CWD
|
||||
from .start import _launch_bottle
|
||||
|
||||
|
||||
@@ -41,14 +40,14 @@ def cmd_resume(argv: list[str]) -> int:
|
||||
f"check ~/.bot-bottle/state/ or run `cli.py start` to create a new bottle"
|
||||
)
|
||||
|
||||
manifest = ManifestIndex.resolve(os.getcwd())
|
||||
manifest = ManifestIndex.resolve(USER_CWD)
|
||||
manifest.require_agent(metadata.agent_name)
|
||||
|
||||
spec = BottleSpec(
|
||||
manifest=manifest,
|
||||
agent_name=metadata.agent_name,
|
||||
copy_cwd=metadata.copy_cwd,
|
||||
user_cwd=metadata.cwd or os.getcwd(),
|
||||
user_cwd=metadata.cwd or USER_CWD,
|
||||
identity=metadata.identity,
|
||||
bottle_names=tuple(metadata.bottle_names),
|
||||
)
|
||||
@@ -22,26 +22,25 @@ import tempfile
|
||||
from pathlib import Path
|
||||
from typing import Callable
|
||||
|
||||
from ...agent_provider import get_provider, runtime_for
|
||||
from ...backend import (
|
||||
from ..agent_provider import get_provider, runtime_for
|
||||
from ..backend import (
|
||||
Bottle,
|
||||
BottleSpec,
|
||||
enumerate_active_agents,
|
||||
get_bottle_backend,
|
||||
)
|
||||
from ...backend.docker import util as docker_mod
|
||||
from ...backend.docker.bottle_plan import DockerBottlePlan
|
||||
from ...bottle_state import (
|
||||
from ..backend.docker import util as docker_mod
|
||||
from ..backend.docker.bottle_plan import DockerBottlePlan
|
||||
from ..bottle_state import (
|
||||
cleanup_state,
|
||||
is_preserved,
|
||||
mark_preserved,
|
||||
)
|
||||
from ...image_cache import StaleImageError
|
||||
from ...log import info, die
|
||||
from ...manifest import Manifest, ManifestIndex
|
||||
from ..constants import PROG
|
||||
from ...util import read_tty_line
|
||||
from .. import tui
|
||||
from ..image_cache import StaleImageError
|
||||
from ..log import info, die
|
||||
from ..manifest import Manifest, ManifestIndex
|
||||
from ._common import PROG, USER_CWD, read_tty_line
|
||||
from . import tui
|
||||
|
||||
|
||||
def cmd_start(argv: list[str]) -> int:
|
||||
@@ -117,7 +116,7 @@ def cmd_start(argv: list[str]) -> int:
|
||||
# threading a no_cache field through every backend's plan dataclass.
|
||||
os.environ["BOT_BOTTLE_NO_CACHE"] = "1"
|
||||
|
||||
manifest = ManifestIndex.resolve(os.getcwd())
|
||||
manifest = ManifestIndex.resolve(USER_CWD)
|
||||
|
||||
if args.headless:
|
||||
return _start_headless(
|
||||
@@ -168,7 +167,7 @@ def cmd_start(argv: list[str]) -> int:
|
||||
manifest=manifest,
|
||||
agent_name=agent_name,
|
||||
copy_cwd=args.cwd,
|
||||
user_cwd=os.getcwd(),
|
||||
user_cwd=USER_CWD,
|
||||
label=label,
|
||||
color=color,
|
||||
bottle_names=bottle_names,
|
||||
@@ -236,7 +235,7 @@ def _start_headless(
|
||||
manifest=manifest,
|
||||
agent_name=agent_name,
|
||||
copy_cwd=args.cwd,
|
||||
user_cwd=os.getcwd(),
|
||||
user_cwd=USER_CWD,
|
||||
label=label,
|
||||
color=args.color or "",
|
||||
bottle_names=bottle_names,
|
||||
@@ -381,8 +380,8 @@ def _peek_agent_bottle(manifest: ManifestIndex, agent_name: str) -> str:
|
||||
return manifest.agents[agent_name].bottle
|
||||
return ""
|
||||
|
||||
from ...manifest.loader import scan_agent_names
|
||||
from ...yaml_subset import YamlSubsetError, parse_frontmatter
|
||||
from ..manifest_loader import scan_agent_names
|
||||
from ..yaml_subset import YamlSubsetError, parse_frontmatter
|
||||
|
||||
home_agents = scan_agent_names(manifest.home_md / "agents")
|
||||
cwd_agents: dict[str, Path] = {}
|
||||
@@ -450,7 +449,7 @@ def _bottle_lineage(manifest: ManifestIndex) -> dict[str, str]:
|
||||
if not bottles_dir.is_dir():
|
||||
return {}
|
||||
|
||||
from ...yaml_subset import YamlSubsetError, parse_frontmatter
|
||||
from ..yaml_subset import YamlSubsetError, parse_frontmatter
|
||||
|
||||
extends_of: dict[str, str] = {}
|
||||
for path in bottles_dir.glob("*.md"):
|
||||
@@ -19,22 +19,22 @@ from dataclasses import dataclass
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
|
||||
from ...paths import bot_bottle_root
|
||||
from ...log import Die, error, info
|
||||
from ...orchestrator.client import (
|
||||
from ..paths import bot_bottle_root
|
||||
from ..log import Die, error, info
|
||||
from ..orchestrator.client import (
|
||||
OrchestratorClient,
|
||||
OrchestratorClientError,
|
||||
discover_orchestrator_url,
|
||||
)
|
||||
|
||||
from ...supervisor.types import (
|
||||
from ..supervise import (
|
||||
Proposal,
|
||||
TOOL_EGRESS_ALLOW,
|
||||
TOOL_EGRESS_BLOCK,
|
||||
TOOL_GITLEAKS_ALLOW,
|
||||
TOOL_EGRESS_TOKEN_ALLOW,
|
||||
)
|
||||
from ..constants import PROG
|
||||
from ._common import PROG
|
||||
|
||||
|
||||
_REFRESH_INTERVAL_MS = 1000
|
||||
@@ -81,7 +81,7 @@ def _resolve_orchestrator_url() -> str:
|
||||
try:
|
||||
return discover_orchestrator_url()
|
||||
except OrchestratorClientError:
|
||||
from ...backend import get_bottle_backend
|
||||
from ..backend import get_bottle_backend
|
||||
backend = get_bottle_backend()
|
||||
info(f"no orchestrator control plane running; starting one ({backend.name})…")
|
||||
return backend.ensure_orchestrator()
|
||||
@@ -4,9 +4,14 @@ from __future__ import annotations
|
||||
|
||||
from pathlib import Path
|
||||
|
||||
from .db_store import DbStore
|
||||
from .migrations import TableMigrations
|
||||
from ..paths import host_db_path
|
||||
try:
|
||||
from .db_store import DbStore
|
||||
from .migrations import TableMigrations
|
||||
from .paths import host_db_path
|
||||
except ImportError:
|
||||
from db_store import DbStore # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
from migrations import TableMigrations # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
from paths import host_db_path # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
|
||||
|
||||
DEFAULT_CACHED_IMAGE_STALE_WARNING_DAYS = 1
|
||||
@@ -6,7 +6,10 @@ import sqlite3
|
||||
from contextlib import contextmanager
|
||||
from pathlib import Path
|
||||
|
||||
from .migrations import TableMigrations
|
||||
try:
|
||||
from .migrations import TableMigrations
|
||||
except ImportError:
|
||||
from migrations import TableMigrations # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
|
||||
|
||||
class DbVersionError(Exception):
|
||||
@@ -49,7 +49,7 @@ def get_provisioner(
|
||||
GiteaDeployKeyProvisioner,
|
||||
)
|
||||
return GiteaDeployKeyProvisioner(token=token, api_url=api_url)
|
||||
from .manifest.util import ManifestError
|
||||
from .manifest_util import ManifestError
|
||||
raise ManifestError(
|
||||
f"unknown provisioned_key provider: {provider!r}; "
|
||||
f"available: gitea"
|
||||
|
||||
@@ -19,7 +19,7 @@ from math import log2
|
||||
from collections import Counter
|
||||
from urllib.parse import quote as url_quote
|
||||
|
||||
from .addon_core import ScanResult
|
||||
from .egress_addon_core import ScanResult
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -0,0 +1,34 @@
|
||||
"""Lean, framework-free `docker` subprocess primitive.
|
||||
|
||||
Deliberately a top-level module with a single stdlib import so it can be
|
||||
reused from anywhere without cost. It is intentionally *not* placed in
|
||||
`backend.docker.util`: importing that module runs `backend/__init__.py`,
|
||||
which eagerly loads all three bottle backends (docker + firecracker +
|
||||
macos) plus the manifest/egress/git-gate/supervise framework — ~76 modules
|
||||
— which would drag the whole backend layer into the deliberately-lean
|
||||
orchestrator. This primitive stays free of that so both the orchestrator's
|
||||
docker components and (in time) `backend.docker.util` can share it."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import subprocess
|
||||
|
||||
|
||||
def run_docker(
|
||||
argv: list[str], *, env: dict[str, str] | None = None,
|
||||
) -> subprocess.CompletedProcess[str]:
|
||||
"""Run a `docker` command, capturing stdout/stderr as text. Never raises
|
||||
on a non-zero exit — callers inspect `returncode` / `stderr` so they can
|
||||
stay fail-closed or tolerate idempotent no-ops (e.g. removing an
|
||||
already-absent container).
|
||||
|
||||
`env` sets the child process environment — used to hand a secret to a bare
|
||||
`--env NAME` flag (docker inherits its value from this process) so the
|
||||
value never lands on argv or in `docker inspect`'s recorded command line."""
|
||||
return subprocess.run(
|
||||
argv, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True,
|
||||
check=False, env=env,
|
||||
)
|
||||
|
||||
|
||||
__all__ = ["run_docker"]
|
||||
@@ -1,33 +1,33 @@
|
||||
"""The `Egress` host-side service (PRD 0017).
|
||||
"""Per-bottle egress proxy (PRD 0017, PRD 0053).
|
||||
|
||||
`Egress` builds a bottle's egress plan at launch: resolve the manifest's egress
|
||||
routes, render the gateway's `routes.yaml`, assign per-route token slots, and
|
||||
plant the exfil canary. The service also resolves the launch-time token values
|
||||
and the agent/gateway env entries the backend injects. The runtime enforcement
|
||||
(the mitmproxy addon) lives in `bot_bottle.gateway.egress.addon*`.
|
||||
This module defines the abstract proxy (`Egress`), its plan
|
||||
dataclass (`EgressPlan`), and the resolved per-route shape
|
||||
(`EgressRoute`). The gateway's start/stop lifecycle is backend-
|
||||
specific and lives on concrete subclasses (see
|
||||
`bot_bottle/backend/docker/egress.py`).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import dataclasses
|
||||
import secrets
|
||||
from abc import ABC
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
from ..gateway.egress.addon_core import (
|
||||
from .egress_addon_core import (
|
||||
ON_MATCH_REDACT,
|
||||
HeaderMatch as CoreHeaderMatch,
|
||||
MatchEntry as CoreMatchEntry,
|
||||
PathMatch as CorePathMatch,
|
||||
Route,
|
||||
)
|
||||
from ..errors import MissingEnvVarError
|
||||
from ..log import die
|
||||
from .plan import EgressPlan, EgressRoute
|
||||
from .errors import MissingEnvVarError
|
||||
from .log import die
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from ..manifest import ManifestBottle
|
||||
|
||||
from .manifest import ManifestBottle
|
||||
|
||||
CODEX_HOST_CREDENTIAL_TOKEN_REF = "BOT_BOTTLE_CODEX_HOST_ACCESS_TOKEN"
|
||||
CLAUDE_HOST_CREDENTIAL_TOKEN_REF = "BOT_BOTTLE_CLAUDE_HOST_ACCESS_TOKEN"
|
||||
@@ -82,6 +82,39 @@ def egress_agent_env_entries(plan: "EgressPlan") -> tuple[str, ...]:
|
||||
return ()
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class EgressRoute(Route):
|
||||
"""Host-side extension of the addon's `Route`.
|
||||
|
||||
Inherits `host`, `matches`, `auth_scheme`, and `token_env`
|
||||
from `egress_addon_core.Route` — those are the fields that cross the
|
||||
YAML wire into the gateway. The fields below are host-only and
|
||||
are never serialised to the addon.
|
||||
|
||||
`token_ref` is the host env var the CLI reads at launch and forwards
|
||||
into the container's environ under `token_env`.
|
||||
|
||||
`roles` carries the manifest route's role tuple (reserved for
|
||||
future use; always empty today)."""
|
||||
|
||||
token_ref: str = ""
|
||||
roles: tuple[str, ...] = ()
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class EgressPlan:
|
||||
slug: str
|
||||
routes_path: Path
|
||||
routes: tuple[EgressRoute, ...]
|
||||
token_env_map: dict[str, str]
|
||||
internal_network: str = ""
|
||||
egress_network: str = ""
|
||||
mitmproxy_ca_host_path: Path = Path()
|
||||
mitmproxy_ca_cert_only_host_path: Path = Path()
|
||||
log: int = 0
|
||||
canary: str = ""
|
||||
canary_env: str = ""
|
||||
|
||||
|
||||
def egress_manifest_routes(
|
||||
bottle: ManifestBottle,
|
||||
@@ -356,11 +389,7 @@ def egress_resolve_token_values(
|
||||
return out
|
||||
|
||||
|
||||
class Egress:
|
||||
"""The host-side egress service. The backend drives `prepare` at launch,
|
||||
then `resolve_token_values` to resolve the routes' upstream credentials and
|
||||
`agent_env_entries` for the agent's egress env. Stateless."""
|
||||
|
||||
class Egress(ABC):
|
||||
def prepare(
|
||||
self,
|
||||
bottle: ManifestBottle,
|
||||
@@ -387,13 +416,20 @@ class Egress:
|
||||
canary_env=_random_canary_env(),
|
||||
)
|
||||
|
||||
def resolve_token_values(
|
||||
self, token_env_map: dict[str, str], host_env: dict[str, str],
|
||||
) -> dict[str, str]:
|
||||
"""Resolve each route's upstream credential from the host env at launch.
|
||||
Raises `MissingEnvVarError` for an unset/empty referenced host var."""
|
||||
return egress_resolve_token_values(token_env_map, host_env)
|
||||
|
||||
def agent_env_entries(self, plan: EgressPlan) -> tuple[str, ...]:
|
||||
"""The agent-visible egress env entries (the exfil canary)."""
|
||||
return egress_agent_env_entries(plan)
|
||||
__all__ = [
|
||||
"CLAUDE_HOST_CREDENTIAL_TOKEN_REF",
|
||||
"CODEX_HOST_CREDENTIAL_TOKEN_REF",
|
||||
"EGRESS_HOSTNAME",
|
||||
"EGRESS_ROUTES_FILENAME",
|
||||
"EGRESS_ROUTES_IN_CONTAINER",
|
||||
"Egress",
|
||||
"EgressPlan",
|
||||
"EgressRoute",
|
||||
"egress_manifest_routes",
|
||||
"egress_render_routes",
|
||||
"egress_resolve_token_values",
|
||||
"egress_routes_for_bottle",
|
||||
"egress_agent_env_entries",
|
||||
"egress_gateway_env_entries",
|
||||
"egress_token_env_map",
|
||||
]
|
||||
@@ -1,90 +0,0 @@
|
||||
"""Per-agent egress (PRD 0017).
|
||||
|
||||
The egress gateway is a TLS-terminating forward proxy that allow-lists a
|
||||
bottle's outbound HTTP(S), scans payloads for secret exfil, and injects
|
||||
per-route upstream credentials the agent never sees.
|
||||
|
||||
Layout:
|
||||
|
||||
* `service` — the `Egress` host-side service (`prepare` the launch plan,
|
||||
`resolve_token_values`, `agent_env_entries`) + the route-building /
|
||||
rendering functions.
|
||||
* `plan` — `EgressPlan` / `EgressRoute`, the launch DTOs (in the backend
|
||||
contract).
|
||||
|
||||
The runtime enforcement (the mitmproxy addon) lives in
|
||||
`bot_bottle.gateway.egress.addon*`. Public names are re-exported lazily via
|
||||
`__getattr__`, so `from bot_bottle.egress import …` keeps working and importing
|
||||
`egress.plan` (the contract's dependency) stays light.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING, Any
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from .plan import EgressPlan, EgressRoute
|
||||
from .service import (
|
||||
CLAUDE_HOST_CREDENTIAL_TOKEN_REF,
|
||||
CODEX_HOST_CREDENTIAL_TOKEN_REF,
|
||||
EGRESS_HOSTNAME,
|
||||
EGRESS_ROUTES_FILENAME,
|
||||
EGRESS_ROUTES_IN_CONTAINER,
|
||||
Egress,
|
||||
egress_agent_env_entries,
|
||||
egress_gateway_env_entries,
|
||||
egress_manifest_routes,
|
||||
egress_render_routes,
|
||||
egress_resolve_token_values,
|
||||
egress_routes_for_bottle,
|
||||
egress_token_env_map,
|
||||
)
|
||||
|
||||
|
||||
_LAZY: dict[str, str] = {
|
||||
"EgressPlan": ".plan",
|
||||
"EgressRoute": ".plan",
|
||||
"Egress": ".service",
|
||||
"CLAUDE_HOST_CREDENTIAL_TOKEN_REF": ".service",
|
||||
"CODEX_HOST_CREDENTIAL_TOKEN_REF": ".service",
|
||||
"EGRESS_HOSTNAME": ".service",
|
||||
"EGRESS_ROUTES_FILENAME": ".service",
|
||||
"EGRESS_ROUTES_IN_CONTAINER": ".service",
|
||||
"egress_agent_env_entries": ".service",
|
||||
"egress_gateway_env_entries": ".service",
|
||||
"egress_manifest_routes": ".service",
|
||||
"egress_render_routes": ".service",
|
||||
"egress_resolve_token_values": ".service",
|
||||
"egress_routes_for_bottle": ".service",
|
||||
"egress_token_env_map": ".service",
|
||||
}
|
||||
|
||||
|
||||
def __getattr__(name: str) -> Any:
|
||||
src = _LAZY.get(name)
|
||||
if src is None:
|
||||
raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
|
||||
from importlib import import_module
|
||||
|
||||
value = getattr(import_module(src, __name__), name)
|
||||
globals()[name] = value
|
||||
return value
|
||||
|
||||
|
||||
__all__ = [
|
||||
"CLAUDE_HOST_CREDENTIAL_TOKEN_REF",
|
||||
"CODEX_HOST_CREDENTIAL_TOKEN_REF",
|
||||
"EGRESS_HOSTNAME",
|
||||
"EGRESS_ROUTES_FILENAME",
|
||||
"EGRESS_ROUTES_IN_CONTAINER",
|
||||
"Egress",
|
||||
"EgressPlan",
|
||||
"EgressRoute",
|
||||
"egress_manifest_routes",
|
||||
"egress_render_routes",
|
||||
"egress_resolve_token_values",
|
||||
"egress_routes_for_bottle",
|
||||
"egress_agent_env_entries",
|
||||
"egress_gateway_env_entries",
|
||||
"egress_token_env_map",
|
||||
]
|
||||
@@ -1,48 +0,0 @@
|
||||
"""Egress launch DTOs (PRD 0017).
|
||||
|
||||
`EgressRoute` (the host-side extension of the addon's wire `Route`) and
|
||||
`EgressPlan` (the launch plan the backend contract references). Pure value
|
||||
types — the route-building / rendering logic and the `Egress` service live in
|
||||
`egress.service`.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
|
||||
from ..gateway.egress.addon_core import Route
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class EgressRoute(Route):
|
||||
"""Host-side extension of the addon's `Route`.
|
||||
|
||||
Inherits `host`, `matches`, `auth_scheme`, and `token_env`
|
||||
from `egress_addon_core.Route` — those are the fields that cross the
|
||||
YAML wire into the gateway. The fields below are host-only and
|
||||
are never serialised to the addon.
|
||||
|
||||
`token_ref` is the host env var the CLI reads at launch and forwards
|
||||
into the container's environ under `token_env`.
|
||||
|
||||
`roles` carries the manifest route's role tuple (reserved for
|
||||
future use; always empty today)."""
|
||||
|
||||
token_ref: str = ""
|
||||
roles: tuple[str, ...] = ()
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class EgressPlan:
|
||||
slug: str
|
||||
routes_path: Path
|
||||
routes: tuple[EgressRoute, ...]
|
||||
token_env_map: dict[str, str]
|
||||
internal_network: str = ""
|
||||
egress_network: str = ""
|
||||
mitmproxy_ca_host_path: Path = Path()
|
||||
mitmproxy_ca_cert_only_host_path: Path = Path()
|
||||
log: int = 0
|
||||
canary: str = ""
|
||||
canary_env: str = ""
|
||||
@@ -16,8 +16,8 @@ import typing
|
||||
from mitmproxy import http # type: ignore[import-not-found] # pylint: disable=import-error
|
||||
|
||||
from bot_bottle.constants import IDENTITY_HEADER
|
||||
from bot_bottle.gateway.egress.dlp_detectors import redact_tokens, strip_crlf
|
||||
from bot_bottle.gateway.egress.addon_core import (
|
||||
from bot_bottle.dlp_detectors import redact_tokens, strip_crlf
|
||||
from bot_bottle.egress_addon_core import (
|
||||
LOG_BLOCKS,
|
||||
LOG_FULL,
|
||||
DEFAULT_OUTBOUND_ON_MATCH,
|
||||
@@ -40,8 +40,8 @@ from bot_bottle.gateway.egress.addon_core import (
|
||||
scan_inbound,
|
||||
scan_outbound,
|
||||
)
|
||||
from bot_bottle.gateway.policy_resolver import PolicyResolveError, PolicyResolver
|
||||
from bot_bottle.supervisor.types import (
|
||||
from bot_bottle.policy_resolver import PolicyResolveError, PolicyResolver
|
||||
from bot_bottle.supervise_types import (
|
||||
STATUS_APPROVED,
|
||||
STATUS_MODIFIED,
|
||||
STATUSES,
|
||||
@@ -16,11 +16,11 @@ import re
|
||||
import typing
|
||||
from dataclasses import dataclass
|
||||
|
||||
from ...yaml_subset import YamlSubsetError, parse_yaml_subset
|
||||
from .yaml_subset import YamlSubsetError, parse_yaml_subset
|
||||
|
||||
# DLP detector-config parsing lives in a sibling module. Re-exported below
|
||||
# so existing `from egress_addon_core import ON_MATCH_*` callers keep working.
|
||||
from .dlp_config import (
|
||||
from .egress_dlp_config import (
|
||||
DEFAULT_OUTBOUND_ON_MATCH,
|
||||
INBOUND_DETECTOR_NAMES,
|
||||
ON_MATCH_BLOCK,
|
||||
@@ -1,119 +0,0 @@
|
||||
"""The consolidated per-host gateway (PRD 0070).
|
||||
|
||||
The core consolidation win: **one** persistent gateway per host, shared by
|
||||
every bottle, instead of a gateway per bottle. It's safe to share
|
||||
because the attribution invariant (source IP + identity token, see
|
||||
`registry`) lets the gateway attribute each request to the right bottle —
|
||||
so per-bottle policy lives in one long-lived process keyed on who's calling.
|
||||
|
||||
`Gateway` is the backend-neutral lifecycle contract (mirrors `LaunchBroker`):
|
||||
ensure the single instance is up, report it, tear it down. The docker
|
||||
implementation (`DockerGateway`) lives in `backend/docker/gateway.py`; a
|
||||
firecracker gateway VM slots in later.
|
||||
|
||||
The defining behaviour is **idempotent singleton**: `ensure_running` starts
|
||||
the instance if absent and is a no-op if it's already up, so N bottle
|
||||
launches never spawn N gateways.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import abc
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
from ..paths import host_gateway_ca_dir
|
||||
|
||||
# The gateway's mitmproxy writes its CA a beat after the container starts, so
|
||||
# reads poll for it rather than assuming it's there on a fresh launch.
|
||||
CA_POLL_SECONDS = 0.5
|
||||
DEFAULT_CA_TIMEOUT_SECONDS = 30.0
|
||||
|
||||
GATEWAY_NAME = "bot-bottle-orch-gateway"
|
||||
GATEWAY_LABEL = "bot-bottle-orch-gateway=1"
|
||||
# The single user-defined network the gateway and every agent bottle share.
|
||||
# Agents attach here with a pinned IP and reach the gateway's egress /
|
||||
# git-http / supervise ports by its address — no host port publishing, and
|
||||
# the source IP the gateway attributes by is the address on this network.
|
||||
GATEWAY_NETWORK = "bot-bottle-gateway"
|
||||
|
||||
# mitmproxy's CA dir in the bundle. The host's gateway-CA dir (see
|
||||
# `host_gateway_ca_dir`) is bind-mounted here so the gateway's self-generated
|
||||
# CA stays STABLE across container recreation — every agent installs this one
|
||||
# CA to trust the shared gateway's TLS interception, so it must not rotate when
|
||||
# the gateway restarts. A host bind-mount rather than a named volume: a named
|
||||
# volume is silently wiped by `docker volume prune`, minting a fresh CA that
|
||||
# breaks every running bottle (issue #450).
|
||||
MITMPROXY_HOME = "/home/mitmproxy/.mitmproxy"
|
||||
GATEWAY_CA_CERT = f"{MITMPROXY_HOME}/mitmproxy-ca-cert.pem"
|
||||
|
||||
# The CA material mitmproxy writes into its confdir. mitmproxy reuses these on
|
||||
# startup when present and generates them only on first run, so persisting them
|
||||
# is what makes the CA stable; deleting them (see `rotate_gateway_ca`) forces a
|
||||
# fresh CA on the next start. `mitmproxy-ca.pem` (cert + private key) is the
|
||||
# signing identity; the rest are derived encodings agents/clients consume.
|
||||
GATEWAY_CA_GLOB = "mitmproxy-ca*"
|
||||
|
||||
# The gateway data-plane image + its Dockerfile. Kept as a local constant
|
||||
# rather than imported from the backend layer, which would drag
|
||||
# the whole backend layer into the lean orchestrator (see #359); unify when
|
||||
# that lands. Env override matches the backend's BOT_BOTTLE_GATEWAY_IMAGE.
|
||||
GATEWAY_IMAGE = os.environ.get("BOT_BOTTLE_GATEWAY_IMAGE", "bot-bottle-gateway:latest")
|
||||
GATEWAY_DOCKERFILE = "Dockerfile.gateway"
|
||||
REPO_ROOT = Path(__file__).resolve().parents[2]
|
||||
|
||||
|
||||
def rotate_gateway_ca(ca_dir: Path | None = None) -> list[Path]:
|
||||
"""Delete the persisted mitmproxy CA so the next gateway start mints a
|
||||
fresh one — the explicit, deliberate CA-rollover path (issue #450).
|
||||
|
||||
Persistence keeps the CA stable across restarts precisely because mitmproxy
|
||||
reuses the on-disk CA; rotation is therefore just removing that material.
|
||||
Returns the files removed (empty when there was no CA yet); idempotent.
|
||||
|
||||
This only clears the on-disk CA. It does NOT stop the running gateway (whose
|
||||
mitmproxy still holds the old CA in memory) or re-provision agents — the
|
||||
caller recreates the gateway to mint the new CA and re-attaches bottles.
|
||||
`rotate-ca` on the orchestrator CLI wires those steps together."""
|
||||
ca_dir = ca_dir if ca_dir is not None else host_gateway_ca_dir()
|
||||
removed: list[Path] = []
|
||||
for path in sorted(ca_dir.glob(GATEWAY_CA_GLOB)):
|
||||
path.unlink()
|
||||
removed.append(path)
|
||||
return removed
|
||||
|
||||
|
||||
class GatewayError(Exception):
|
||||
"""The shared gateway failed to build/start/stop (non-zero `docker` exit)."""
|
||||
|
||||
|
||||
class Gateway(abc.ABC):
|
||||
"""Lifecycle of the single per-host gateway. Backend-neutral."""
|
||||
|
||||
name: str
|
||||
|
||||
def ensure_built(self) -> None:
|
||||
"""Ensure the gateway's image / rootfs exists, building it if needed.
|
||||
Default: nothing to build (e.g. a stub or a pre-pulled image)."""
|
||||
return
|
||||
|
||||
@abc.abstractmethod
|
||||
def ensure_running(self) -> None:
|
||||
"""Start the gateway if it isn't already up. Idempotent: a no-op
|
||||
when it's already running (that's the whole point — one per host).
|
||||
Assumes the image exists — call `ensure_built()` first."""
|
||||
|
||||
@abc.abstractmethod
|
||||
def is_running(self) -> bool:
|
||||
"""True iff the gateway instance is currently up."""
|
||||
|
||||
@abc.abstractmethod
|
||||
def stop(self) -> None:
|
||||
"""Remove the gateway. Idempotent — absent is success."""
|
||||
|
||||
|
||||
__all__ = [
|
||||
"Gateway", "GatewayError", "rotate_gateway_ca",
|
||||
"GATEWAY_NAME", "GATEWAY_LABEL", "GATEWAY_IMAGE", "GATEWAY_NETWORK",
|
||||
"GATEWAY_CA_CERT", "GATEWAY_CA_GLOB",
|
||||
]
|
||||
@@ -1,9 +0,0 @@
|
||||
"""Gateway-side (data-plane) egress service: the mitmproxy addon and its
|
||||
pure decision core, DLP detectors, and route/DLP config parsing.
|
||||
|
||||
These are the long-running data-plane pieces (loaded by mitmdump inside the
|
||||
`bot-bottle-gateway` image), distinct from the host-side `bot_bottle.egress`
|
||||
service that renders routes and prepares env. Import the concrete modules
|
||||
directly (`from bot_bottle.gateway.egress.addon_core import ...`) — this
|
||||
package deliberately does no eager work so leaf imports stay cheap.
|
||||
"""
|
||||
@@ -1,7 +0,0 @@
|
||||
"""Gateway-side (data-plane) git-gate service: pure host-side hook rendering
|
||||
(PRD 0008) and the smart-HTTP backend that fronts git-gate repos.
|
||||
|
||||
The host-side git-gate service (provisioning, preflight) lives in
|
||||
`bot_bottle.git_gate`; this is the data-plane counterpart. Import the concrete
|
||||
modules directly (`from bot_bottle.gateway.git_gate.render import ...`).
|
||||
"""
|
||||
@@ -1,7 +0,0 @@
|
||||
"""Gateway-side (data-plane) supervise service: the supervise daemon's HTTP
|
||||
server (PRD 0013).
|
||||
|
||||
The host-side supervise control lives in `bot_bottle.orchestrator.supervisor`;
|
||||
this is the in-gateway daemon the agents reach. Import the concrete module
|
||||
directly (`from bot_bottle.gateway.supervisor.server import ...`).
|
||||
"""
|
||||
@@ -54,15 +54,6 @@ class _DaemonSpec:
|
||||
_EGRESS_ONLY_ENV_PREFIXES: tuple[str, ...] = ("EGRESS_TOKEN_",)
|
||||
_READY_GATED_DAEMONS: tuple[str, ...] = ("git-gate", "git-http")
|
||||
|
||||
# The control-plane signing key is the orchestrator's alone — verifying tokens.
|
||||
# The data-plane daemons instead hold the pre-minted `gateway` JWT they present.
|
||||
# Scoping each to its process (even in the combined infra container) keeps a
|
||||
# compromised data-plane daemon from reading the key and minting a `cli` token
|
||||
# (issue #469 review). Values match paths.ORCHESTRATOR_TOKEN_ENV /
|
||||
# ORCHESTRATOR_AUTH_JWT_ENV; hardcoded here so this supervisor stays import-light.
|
||||
_SIGNING_KEY_ENV = "BOT_BOTTLE_ORCHESTRATOR_TOKEN"
|
||||
_GATEWAY_JWT_ENV = "BOT_BOTTLE_ORCHESTRATOR_AUTH_JWT"
|
||||
|
||||
# Daemons that must be requested explicitly via BOT_BOTTLE_GATEWAY_DAEMONS
|
||||
# and are NOT started in the default (env-var-unset) case. The orchestrator
|
||||
# only runs in the combined infra container, never in a standalone gateway.
|
||||
@@ -70,24 +61,16 @@ _OPT_IN_DAEMONS: frozenset[str] = frozenset({"orchestrator"})
|
||||
|
||||
|
||||
def _env_for_daemon(name: str, base_env: dict[str, str]) -> dict[str, str]:
|
||||
"""Per-daemon env, scoped to what each process legitimately needs.
|
||||
Returns a fresh dict — callers can mutate without affecting `base_env`.
|
||||
|
||||
* `EGRESS_TOKEN_*` upstream-auth slots go to egress only.
|
||||
* the control-plane signing key goes to the orchestrator only.
|
||||
* the pre-minted `gateway` JWT goes to the data-plane daemons only (the
|
||||
orchestrator verifies tokens, it never presents one)."""
|
||||
env = dict(base_env)
|
||||
if name != "egress":
|
||||
env = {
|
||||
k: v for k, v in env.items()
|
||||
if not any(k.startswith(p) for p in _EGRESS_ONLY_ENV_PREFIXES)
|
||||
}
|
||||
if name == "orchestrator":
|
||||
env.pop(_GATEWAY_JWT_ENV, None)
|
||||
else:
|
||||
env.pop(_SIGNING_KEY_ENV, None)
|
||||
return env
|
||||
"""Egress sees the full bundle env. Everyone else gets a copy
|
||||
with `EGRESS_TOKEN_*` (and any other future egress-only
|
||||
credential slots) stripped. Returns a fresh dict — callers
|
||||
can mutate without affecting `base_env`."""
|
||||
if name == "egress":
|
||||
return dict(base_env)
|
||||
return {
|
||||
k: v for k, v in base_env.items()
|
||||
if not any(k.startswith(p) for p in _EGRESS_ONLY_ENV_PREFIXES)
|
||||
}
|
||||
|
||||
|
||||
# The orchestrator is listed first so it starts before the gateway daemons,
|
||||
@@ -100,8 +83,8 @@ _DAEMONS: tuple[_DaemonSpec, ...] = (
|
||||
)),
|
||||
_DaemonSpec("egress", ("/bin/sh", "/app/egress-entrypoint.sh")),
|
||||
_DaemonSpec("git-gate", ("/bin/sh", "/git-gate-entrypoint.sh")),
|
||||
_DaemonSpec("git-http", ("python3", "-m", "bot_bottle.gateway.git_gate.http_backend")),
|
||||
_DaemonSpec("supervise", ("python3", "-m", "bot_bottle.gateway.supervisor.server")),
|
||||
_DaemonSpec("git-http", ("python3", "-m", "bot_bottle.git_http_backend")),
|
||||
_DaemonSpec("supervise", ("python3", "-m", "bot_bottle.supervise_server")),
|
||||
)
|
||||
|
||||
|
||||
@@ -173,7 +156,7 @@ def _spawn(spec: _DaemonSpec) -> subprocess.Popen[bytes]:
|
||||
return proc
|
||||
|
||||
|
||||
class _DaemonManager:
|
||||
class _Supervisor:
|
||||
"""Holds the running children + shutdown state. Pulled out so
|
||||
the test suite can drive it with fake commands."""
|
||||
|
||||
@@ -387,7 +370,7 @@ def main(argv: Sequence[str] | None = None) -> int:
|
||||
_log("no daemons selected; nothing to do")
|
||||
return 0
|
||||
|
||||
sup = _DaemonManager(specs)
|
||||
sup = _Supervisor(specs)
|
||||
sup.start_all()
|
||||
|
||||
signal.signal(signal.SIGTERM, lambda *_: sup.request_shutdown("SIGTERM")) # type: ignore
|
||||
@@ -0,0 +1,169 @@
|
||||
"""Per-agent git-gate (PRD 0008).
|
||||
|
||||
A third per-agent daemon that fronts the bottle's declared git
|
||||
upstreams as a transparent mirror. Each `bottle.git` entry maps to
|
||||
a bare repo on the gate; `git daemon` serves the bare repos over
|
||||
`git://<gate>/<name>.git`. Two hooks make the mirror bidirectional:
|
||||
|
||||
- **`pre-receive`** (push path) — gitleaks-scans incoming refs and,
|
||||
on clean, forwards them to the real upstream with the
|
||||
gate-resident credential.
|
||||
- **`--access-hook`** (fetch path) — runs `git fetch origin --prune`
|
||||
against the real upstream before every `upload-pack`, so an
|
||||
agent fetch returns whatever the upstream has *now*. Fail-closed
|
||||
if the upstream is unreachable.
|
||||
|
||||
The agent never sees the upstream credential under either path.
|
||||
|
||||
Why a separate daemon (not folded into egress or ssh-gate): the
|
||||
gate is the only one of the three that holds upstream push
|
||||
credentials. Mixing it with egress would put push creds in the
|
||||
same blast radius as internet-facing TLS interception; mixing it
|
||||
with ssh-gate would force ssh-gate above L4 and into git-protocol
|
||||
land. See `docs/prds/0008-git-gate.md`.
|
||||
|
||||
This module defines the abstract gate (`GitGate`) and its plan
|
||||
dataclass (`GitGatePlan`). The gateway's start/stop lifecycle is
|
||||
backend-specific and lives on concrete subclasses (see
|
||||
`bot_bottle/backend/docker/git_gate.py`)."""
|
||||
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from abc import ABC
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
|
||||
from .manifest import ManifestBottle
|
||||
|
||||
# Rendering and the deploy-key lifecycle live in sibling modules; the
|
||||
# names are re-exported here (see __all__) so existing
|
||||
# `from bot_bottle.git_gate import …` callers are unchanged.
|
||||
from .git_gate_render import (
|
||||
GIT_GATE_HOSTNAME,
|
||||
GIT_GATE_TIMEOUT_SECS,
|
||||
GitGateUpstream,
|
||||
git_gate_known_hosts_line,
|
||||
git_gate_render_access_hook,
|
||||
git_gate_render_entrypoint,
|
||||
git_gate_render_provision,
|
||||
git_gate_render_gitconfig,
|
||||
git_gate_render_hook,
|
||||
git_gate_upstreams_for_bottle,
|
||||
_gitconfig_validate_value,
|
||||
)
|
||||
from .git_gate_provision import (
|
||||
provision_git_gate_dynamic_keys,
|
||||
revoke_git_gate_provisioned_keys,
|
||||
_provision_dynamic_key,
|
||||
_resolve_identity_file,
|
||||
)
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class GitGatePlan:
|
||||
"""Output of GitGate.prepare; consumed by .start.
|
||||
|
||||
The script + slug + upstream fields are filled at prepare time
|
||||
(host-side, side-effect-free on docker). The network fields are
|
||||
populated by the backend's launch step via `dataclasses.replace`
|
||||
once those networks exist. Empty defaults are sentinels meaning
|
||||
"not yet set"; `.start` validates that they are populated.
|
||||
|
||||
`hook_script` is the shared `pre-receive` for push-time gating;
|
||||
`access_hook_script` is `git daemon`'s `--access-hook` for the
|
||||
fetch-time upstream refresh."""
|
||||
|
||||
slug: str
|
||||
entrypoint_script: Path
|
||||
hook_script: Path
|
||||
access_hook_script: Path
|
||||
upstreams: tuple[GitGateUpstream, ...]
|
||||
internal_network: str = ""
|
||||
egress_network: str = ""
|
||||
|
||||
|
||||
|
||||
|
||||
class GitGate(ABC):
|
||||
"""The per-agent git-gate. Encapsulates the host-side prepare
|
||||
(upstream lift + entrypoint/hook render); the gateway's
|
||||
start/stop lifecycle is backend-specific and lives on concrete
|
||||
subclasses."""
|
||||
|
||||
def prepare(self, bottle: ManifestBottle, slug: str, stage_dir: Path) -> GitGatePlan:
|
||||
"""Compute the upstream table from `bottle.git` and write the
|
||||
entrypoint, pre-receive hook, and access-hook scripts (mode
|
||||
600) under `stage_dir`. Pure host-side, no docker subprocess.
|
||||
|
||||
For `gitea` key entries, the returned upstream intentionally
|
||||
has an empty identity file. Backend launch fills that in after
|
||||
the operator confirms the preflight.
|
||||
|
||||
Returned plan is incomplete: the launch step must fill
|
||||
`internal_network` / `egress_network` via `dataclasses.replace`
|
||||
before passing the plan to `.start`."""
|
||||
upstreams = git_gate_upstreams_for_bottle(bottle)
|
||||
entrypoint = stage_dir / "git_gate_entrypoint.sh"
|
||||
entrypoint.write_text(git_gate_render_entrypoint(upstreams))
|
||||
entrypoint.chmod(0o600)
|
||||
hook = stage_dir / "git_gate_pre_receive.sh"
|
||||
hook.write_text(git_gate_render_hook())
|
||||
hook.chmod(0o600)
|
||||
access_hook = stage_dir / "git_gate_access_hook.sh"
|
||||
access_hook.write_text(git_gate_render_access_hook())
|
||||
# 0o700 (not 0o600): git daemon execs --access-hook directly,
|
||||
# not via `sh`, so the script needs the x bit. The gateway copy
|
||||
# does not necessarily preserve this mode (`docker cp` does, the
|
||||
# Apple `container cp` does not), so provision_git_gate re-applies
|
||||
# +x on the gateway side — see backend/docker/gateway_provision.py.
|
||||
access_hook.chmod(0o700)
|
||||
upstreams_with_files: list[GitGateUpstream] = []
|
||||
for u in upstreams:
|
||||
known_hosts_file = Path()
|
||||
if u.known_host_key:
|
||||
known_hosts_file = stage_dir / f"{u.name}-known_hosts"
|
||||
known_hosts_file.write_text(
|
||||
git_gate_known_hosts_line(
|
||||
u.upstream_host, u.upstream_port, u.known_host_key,
|
||||
)
|
||||
)
|
||||
known_hosts_file.chmod(0o600)
|
||||
upstreams_with_files.append(
|
||||
GitGateUpstream(
|
||||
name=u.name,
|
||||
upstream_url=u.upstream_url,
|
||||
upstream_host=u.upstream_host,
|
||||
upstream_port=u.upstream_port,
|
||||
identity_file=u.identity_file,
|
||||
known_host_key=u.known_host_key,
|
||||
known_hosts_file=known_hosts_file,
|
||||
)
|
||||
)
|
||||
return GitGatePlan(
|
||||
slug=slug,
|
||||
entrypoint_script=entrypoint,
|
||||
hook_script=hook,
|
||||
access_hook_script=access_hook,
|
||||
upstreams=tuple(upstreams_with_files),
|
||||
)
|
||||
|
||||
|
||||
__all__ = [
|
||||
"GIT_GATE_HOSTNAME",
|
||||
"GIT_GATE_TIMEOUT_SECS",
|
||||
"GitGateUpstream",
|
||||
"GitGatePlan",
|
||||
"GitGate",
|
||||
"git_gate_upstreams_for_bottle",
|
||||
"git_gate_render_gitconfig",
|
||||
"git_gate_known_hosts_line",
|
||||
"git_gate_render_entrypoint",
|
||||
"git_gate_render_provision",
|
||||
"git_gate_render_hook",
|
||||
"git_gate_render_access_hook",
|
||||
"provision_git_gate_dynamic_keys",
|
||||
"revoke_git_gate_provisioned_keys",
|
||||
"_gitconfig_validate_value",
|
||||
"_provision_dynamic_key",
|
||||
"_resolve_identity_file",
|
||||
]
|
||||
@@ -1,98 +0,0 @@
|
||||
"""Per-agent git-gate (PRD 0008).
|
||||
|
||||
The git-gate fronts a bottle's declared git upstreams as a transparent mirror:
|
||||
a `pre-receive` hook gitleaks-scans pushes and forwards clean refs to the real
|
||||
upstream with a gate-resident credential; an `--access-hook` refreshes from the
|
||||
upstream before fetches. The agent never sees the upstream credential.
|
||||
|
||||
Layout:
|
||||
|
||||
* `service` — the `GitGate` host-side service (prepare / provision / revoke /
|
||||
preflight) the backend drives at launch.
|
||||
* `plan` — `GitGatePlan`, the launch DTO (in the backend contract).
|
||||
* `provision`, `host_key` — the deploy-key + host-key host-side helpers the
|
||||
service delegates to.
|
||||
|
||||
The rendering + the in-gateway hook execution live in
|
||||
`bot_bottle.gateway.git_gate.render`. The public names are re-exported lazily
|
||||
via `__getattr__`, so `from bot_bottle.git_gate import …` keeps working and
|
||||
importing `git_gate.plan` (the contract's dependency) doesn't drag in the
|
||||
provisioning / forge-API code.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING, Any
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from .service import GitGate
|
||||
from .plan import GitGatePlan
|
||||
from .provision import (
|
||||
provision_git_gate_dynamic_keys,
|
||||
revoke_git_gate_provisioned_keys,
|
||||
)
|
||||
from ..gateway.git_gate.render import (
|
||||
GIT_GATE_HOSTNAME,
|
||||
GIT_GATE_TIMEOUT_SECS,
|
||||
GitGateUpstream,
|
||||
git_gate_known_hosts_line,
|
||||
git_gate_render_access_hook,
|
||||
git_gate_render_entrypoint,
|
||||
git_gate_render_gitconfig,
|
||||
git_gate_render_hook,
|
||||
git_gate_render_provision,
|
||||
git_gate_upstreams_for_bottle,
|
||||
)
|
||||
|
||||
|
||||
# Public name -> relative module that defines it. Render/hook names come from
|
||||
# the gateway (where the in-gateway execution lives); the service, plan, and
|
||||
# provisioning are this package's own submodules.
|
||||
_LAZY: dict[str, str] = {
|
||||
"GitGate": ".service",
|
||||
"GitGatePlan": ".plan",
|
||||
"provision_git_gate_dynamic_keys": ".provision",
|
||||
"revoke_git_gate_provisioned_keys": ".provision",
|
||||
"_provision_dynamic_key": ".provision",
|
||||
"_resolve_identity_file": ".provision",
|
||||
"GIT_GATE_HOSTNAME": "..gateway.git_gate.render",
|
||||
"GIT_GATE_TIMEOUT_SECS": "..gateway.git_gate.render",
|
||||
"GitGateUpstream": "..gateway.git_gate.render",
|
||||
"git_gate_upstreams_for_bottle": "..gateway.git_gate.render",
|
||||
"git_gate_render_gitconfig": "..gateway.git_gate.render",
|
||||
"git_gate_known_hosts_line": "..gateway.git_gate.render",
|
||||
"git_gate_render_entrypoint": "..gateway.git_gate.render",
|
||||
"git_gate_render_provision": "..gateway.git_gate.render",
|
||||
"git_gate_render_hook": "..gateway.git_gate.render",
|
||||
"git_gate_render_access_hook": "..gateway.git_gate.render",
|
||||
"_gitconfig_validate_value": "..gateway.git_gate.render",
|
||||
}
|
||||
|
||||
|
||||
def __getattr__(name: str) -> Any:
|
||||
src = _LAZY.get(name)
|
||||
if src is None:
|
||||
raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
|
||||
from importlib import import_module
|
||||
|
||||
value = getattr(import_module(src, __name__), name)
|
||||
globals()[name] = value
|
||||
return value
|
||||
|
||||
|
||||
__all__ = [
|
||||
"GitGate",
|
||||
"GitGatePlan",
|
||||
"GitGateUpstream",
|
||||
"GIT_GATE_HOSTNAME",
|
||||
"GIT_GATE_TIMEOUT_SECS",
|
||||
"git_gate_upstreams_for_bottle",
|
||||
"git_gate_render_gitconfig",
|
||||
"git_gate_known_hosts_line",
|
||||
"git_gate_render_entrypoint",
|
||||
"git_gate_render_provision",
|
||||
"git_gate_render_hook",
|
||||
"git_gate_render_access_hook",
|
||||
"provision_git_gate_dynamic_keys",
|
||||
"revoke_git_gate_provisioned_keys",
|
||||
]
|
||||
@@ -1,36 +0,0 @@
|
||||
"""`GitGatePlan` — the git-gate launch plan (DTO).
|
||||
|
||||
The output of `GitGate.prepare`, consumed by the backend launch step and the
|
||||
`BottlePlan` contract. A pure value type (its `upstreams` element type
|
||||
`GitGateUpstream` is the neutral render dataclass).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
|
||||
from ..gateway.git_gate.render import GitGateUpstream
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class GitGatePlan:
|
||||
"""Output of GitGate.prepare; consumed by .start.
|
||||
|
||||
The script + slug + upstream fields are filled at prepare time (host-side,
|
||||
side-effect-free on docker). The network fields are populated by the
|
||||
backend's launch step via `dataclasses.replace` once those networks exist.
|
||||
Empty defaults are sentinels meaning "not yet set"; `.start` validates that
|
||||
they are populated.
|
||||
|
||||
`hook_script` is the shared `pre-receive` for push-time gating;
|
||||
`access_hook_script` is `git daemon`'s `--access-hook` for the fetch-time
|
||||
upstream refresh."""
|
||||
|
||||
slug: str
|
||||
entrypoint_script: Path
|
||||
hook_script: Path
|
||||
access_hook_script: Path
|
||||
upstreams: tuple[GitGateUpstream, ...]
|
||||
internal_network: str = ""
|
||||
egress_network: str = ""
|
||||
@@ -1,114 +0,0 @@
|
||||
"""The `GitGate` host-side service (PRD 0008).
|
||||
|
||||
The git-gate fronts a bottle's declared git upstreams as a transparent mirror:
|
||||
a `pre-receive` hook gitleaks-scans pushes and forwards clean refs to the real
|
||||
upstream with a gate-resident credential; an `--access-hook` refreshes from the
|
||||
upstream before fetches. The agent never sees the upstream credential.
|
||||
|
||||
`GitGate` is the host-side service the backend drives at launch: build the plan
|
||||
(`prepare`), provision / revoke the per-upstream deploy keys, and preflight the
|
||||
upstream host keys. The rendering it emits + the in-gateway hook execution live
|
||||
in `bot_bottle.gateway.git_gate.render`.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from pathlib import Path
|
||||
|
||||
from ..manifest import Manifest, ManifestBottle
|
||||
from ..gateway.git_gate.render import (
|
||||
GitGateUpstream,
|
||||
git_gate_known_hosts_line,
|
||||
git_gate_render_access_hook,
|
||||
git_gate_render_entrypoint,
|
||||
git_gate_render_hook,
|
||||
git_gate_upstreams_for_bottle,
|
||||
)
|
||||
from .plan import GitGatePlan
|
||||
from . import provision as _provision
|
||||
from . import host_key as _host_key
|
||||
|
||||
|
||||
class GitGate:
|
||||
"""The per-agent git-gate host-side service. Stateless — the backend's
|
||||
launch step drives `prepare` → `provision_dynamic_keys` and, at teardown,
|
||||
`revoke_provisioned_keys`; `preflight_host_keys` gates a launch on the
|
||||
upstream host keys being known."""
|
||||
|
||||
def prepare(self, bottle: ManifestBottle, slug: str, stage_dir: Path) -> GitGatePlan:
|
||||
"""Compute the upstream table from `bottle.git` and write the
|
||||
entrypoint, pre-receive hook, and access-hook scripts (mode 600) under
|
||||
`stage_dir`. Pure host-side, no docker subprocess.
|
||||
|
||||
For `gitea` key entries, the returned upstream intentionally has an
|
||||
empty identity file. Backend launch fills that in after the operator
|
||||
confirms the preflight.
|
||||
|
||||
Returned plan is incomplete: the launch step must fill
|
||||
`internal_network` / `egress_network` via `dataclasses.replace` before
|
||||
passing the plan to `.start`."""
|
||||
upstreams = git_gate_upstreams_for_bottle(bottle)
|
||||
entrypoint = stage_dir / "git_gate_entrypoint.sh"
|
||||
entrypoint.write_text(git_gate_render_entrypoint(upstreams))
|
||||
entrypoint.chmod(0o600)
|
||||
hook = stage_dir / "git_gate_pre_receive.sh"
|
||||
hook.write_text(git_gate_render_hook())
|
||||
hook.chmod(0o600)
|
||||
access_hook = stage_dir / "git_gate_access_hook.sh"
|
||||
access_hook.write_text(git_gate_render_access_hook())
|
||||
# 0o700 (not 0o600): git daemon execs --access-hook directly, not via
|
||||
# `sh`, so the script needs the x bit. The gateway copy does not
|
||||
# necessarily preserve this mode (`docker cp` does, the Apple `container
|
||||
# cp` does not), so provisioning re-applies +x on the gateway side — see
|
||||
# backend/docker/gateway_provision.py.
|
||||
access_hook.chmod(0o700)
|
||||
upstreams_with_files: list[GitGateUpstream] = []
|
||||
for u in upstreams:
|
||||
known_hosts_file = Path()
|
||||
if u.known_host_key:
|
||||
known_hosts_file = stage_dir / f"{u.name}-known_hosts"
|
||||
known_hosts_file.write_text(
|
||||
git_gate_known_hosts_line(
|
||||
u.upstream_host, u.upstream_port, u.known_host_key,
|
||||
)
|
||||
)
|
||||
known_hosts_file.chmod(0o600)
|
||||
upstreams_with_files.append(
|
||||
GitGateUpstream(
|
||||
name=u.name,
|
||||
upstream_url=u.upstream_url,
|
||||
upstream_host=u.upstream_host,
|
||||
upstream_port=u.upstream_port,
|
||||
identity_file=u.identity_file,
|
||||
known_host_key=u.known_host_key,
|
||||
known_hosts_file=known_hosts_file,
|
||||
)
|
||||
)
|
||||
return GitGatePlan(
|
||||
slug=slug,
|
||||
entrypoint_script=entrypoint,
|
||||
hook_script=hook,
|
||||
access_hook_script=access_hook,
|
||||
upstreams=tuple(upstreams_with_files),
|
||||
)
|
||||
|
||||
def provision_dynamic_keys(
|
||||
self, bottle: ManifestBottle, plan: GitGatePlan, stage_dir: Path,
|
||||
) -> GitGatePlan:
|
||||
"""Mint the `gitea` upstreams' ephemeral deploy keys via the forge API
|
||||
and return the plan with their identity files filled in."""
|
||||
return _provision.provision_git_gate_dynamic_keys(bottle, plan, stage_dir)
|
||||
|
||||
def revoke_provisioned_keys(self, bottle: ManifestBottle, stage_dir: Path) -> None:
|
||||
"""Revoke every deploy key provisioned for `bottle` (teardown)."""
|
||||
_provision.revoke_git_gate_provisioned_keys(bottle, stage_dir)
|
||||
|
||||
def preflight_host_keys(
|
||||
self, manifest: Manifest, *, headless: bool, home_md: Path | None,
|
||||
) -> Manifest:
|
||||
"""Ensure every git-gate upstream has a known host key, populating
|
||||
missing ones (or erroring in headless mode). Returns the manifest,
|
||||
possibly updated with fetched keys."""
|
||||
return _host_key.preflight_host_keys(
|
||||
manifest, headless=headless, home_md=home_md,
|
||||
)
|
||||
@@ -16,9 +16,9 @@ import sys
|
||||
from pathlib import Path
|
||||
from typing import cast
|
||||
|
||||
from ..log import die, info
|
||||
from ..manifest import Manifest
|
||||
from ..yaml_subset import YamlSubsetError, parse_frontmatter, serialize_yaml_subset
|
||||
from .log import die, info
|
||||
from .manifest import Manifest
|
||||
from .yaml_subset import YamlSubsetError, parse_frontmatter, serialize_yaml_subset
|
||||
|
||||
|
||||
# Preferred key types, most secure first.
|
||||
@@ -13,14 +13,14 @@ import dataclasses
|
||||
from pathlib import Path
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
from ..bottle_state import globalize_slug
|
||||
from ..errors import MissingEnvVarError
|
||||
from ..log import info
|
||||
from ..manifest import ManifestBottle, ManifestGitEntry
|
||||
from ..gateway.git_gate.render import GitGateUpstream
|
||||
from .bottle_state import globalize_slug
|
||||
from .errors import MissingEnvVarError
|
||||
from .log import info
|
||||
from .manifest import ManifestBottle, ManifestGitEntry
|
||||
from .git_gate_render import GitGateUpstream
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from .plan import GitGatePlan
|
||||
from .git_gate import GitGatePlan
|
||||
|
||||
def _provision_dynamic_key(
|
||||
entry: ManifestGitEntry,
|
||||
@@ -32,7 +32,7 @@ def _provision_dynamic_key(
|
||||
|
||||
Returns the host-side path to the private key file so the caller
|
||||
can inject it into the GitGateUpstream as `identity_file`."""
|
||||
from ..deploy_key_provisioner import get_provisioner
|
||||
from .deploy_key_provisioner import get_provisioner
|
||||
pk = entry.Key
|
||||
token = os.environ.get(pk.forge_token_env)
|
||||
if token is None:
|
||||
@@ -70,7 +70,7 @@ def revoke_git_gate_provisioned_keys(bottle: ManifestBottle, stage_dir: Path) ->
|
||||
Called at teardown after containers stop. Raises if any revocation
|
||||
fails — a stranded key is a security concern that the operator must
|
||||
address manually."""
|
||||
from ..deploy_key_provisioner import get_provisioner
|
||||
from .deploy_key_provisioner import get_provisioner
|
||||
for entry in bottle.git:
|
||||
if entry.Key.provider != "gitea":
|
||||
continue
|
||||
@@ -3,9 +3,9 @@
|
||||
Builds the agent's `.gitconfig` insteadOf rewrites, the known_hosts
|
||||
line, and the entrypoint / pre-receive / access-hook scripts the gateway
|
||||
runs. No docker or forge calls — exposed for tests and reuse across
|
||||
backends. The host-side service (`git_gate.GitGate`) and the deploy-key
|
||||
lifecycle (`git_gate.provision`) each read on their own; `git_gate`
|
||||
re-exports these names for API stability."""
|
||||
backends. Split out of `git_gate.py` so the control surface (`GitGate`)
|
||||
and the deploy-key lifecycle (`git_gate_provision`) each read on their
|
||||
own; `git_gate` re-exports these names for API stability."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
@@ -14,8 +14,8 @@ import shlex
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
|
||||
from ...constants import GIT_GATE_TIMEOUT_SECS, IDENTITY_HEADER
|
||||
from ...manifest import ManifestBottle, ManifestGitEntry
|
||||
from .constants import GIT_GATE_TIMEOUT_SECS, IDENTITY_HEADER
|
||||
from .manifest import ManifestBottle, ManifestGitEntry
|
||||
|
||||
# Short network alias for git-gate inside the gateway. The
|
||||
# agent's `.gitconfig` insteadOf rewrites resolve through this name.
|
||||
@@ -282,11 +282,11 @@ from pathlib import Path
|
||||
# identity_token), resolved server-side, so the proposal lands under the
|
||||
# calling bottle exactly as a direct write once did.
|
||||
try:
|
||||
from bot_bottle.gateway.policy_resolver import PolicyResolver, PolicyResolveError
|
||||
from bot_bottle.supervisor.types import TOOL_GITLEAKS_ALLOW
|
||||
from bot_bottle.policy_resolver import PolicyResolver, PolicyResolveError
|
||||
from bot_bottle.supervise_types import TOOL_GITLEAKS_ALLOW
|
||||
except ImportError:
|
||||
from policy_resolver import PolicyResolver, PolicyResolveError
|
||||
from supervisor.types import TOOL_GITLEAKS_ALLOW
|
||||
from supervise_types import TOOL_GITLEAKS_ALLOW
|
||||
|
||||
report_path = Path(sys.argv[1])
|
||||
source_ip = os.environ.get("SUPERVISE_SOURCE_IP", "")
|
||||
@@ -374,7 +374,7 @@ import sys
|
||||
# Non-blocking poll over the control plane. A decided proposal is archived
|
||||
# server-side on read, so no separate archive step is needed here.
|
||||
try:
|
||||
from bot_bottle.gateway.policy_resolver import PolicyResolver, PolicyResolveError
|
||||
from bot_bottle.policy_resolver import PolicyResolver, PolicyResolveError
|
||||
except ImportError:
|
||||
from policy_resolver import PolicyResolver, PolicyResolveError
|
||||
|
||||
@@ -27,7 +27,7 @@ from pathlib import Path
|
||||
from urllib.parse import urlsplit
|
||||
|
||||
from bot_bottle.constants import GIT_GATE_TIMEOUT_SECS, IDENTITY_HEADER
|
||||
from bot_bottle.gateway.policy_resolver import PolicyResolveError, PolicyResolver
|
||||
from bot_bottle.policy_resolver import PolicyResolveError, PolicyResolver
|
||||
|
||||
|
||||
DEFAULT_PORT = 9420
|
||||
@@ -5,7 +5,10 @@ from __future__ import annotations
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
|
||||
from .store.config_store import ConfigStore
|
||||
try:
|
||||
from .config_store import ConfigStore
|
||||
except ImportError:
|
||||
from config_store import ConfigStore # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
|
||||
|
||||
class StaleImageError(Exception):
|
||||
|
||||
@@ -1,10 +1,59 @@
|
||||
"""The `Manifest` / `ManifestIndex` aggregate model.
|
||||
"""Manifest dataclasses (PRD 0011 layout).
|
||||
|
||||
The parsed manifest document (`Manifest`) and the multi-agent index over it
|
||||
(`ManifestIndex`), plus the bottle-resolution helpers that stitch the pieces
|
||||
(`agent`, `bottle`, `egress`, `git`, `extends`, `loader`, `schema`) into an
|
||||
effective manifest. This is the heavy aggregate — the thin package `__init__`
|
||||
re-exports `Manifest` / `ManifestIndex` lazily.
|
||||
Reads the per-file manifest tree:
|
||||
|
||||
$HOME/.bot-bottle/bottles/<name>.md — one bottle per file
|
||||
$HOME/.bot-bottle/agents/<name>.md — home-resident agents
|
||||
$CWD/.bot-bottle/agents/<name>.md — cwd-supplied agents
|
||||
|
||||
Each file is Markdown with YAML frontmatter. The frontmatter holds
|
||||
the structured config (see schema below); for agents the body is
|
||||
the system prompt, for bottles the body is human documentation
|
||||
(ignored by the parser).
|
||||
|
||||
Bottle schema (frontmatter):
|
||||
extends: <bottle-name> # optional (PRD 0025)
|
||||
env: { <NAME>: <env-entry>, ... }
|
||||
git-gate: # optional (PRD 0047)
|
||||
user: { name: <str>, email: <str> } # optional
|
||||
repos: { <name>: <git-gate-entry>, ... } # optional
|
||||
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
|
||||
skills: [ <skill-name>, ... ] # optional
|
||||
git-gate:
|
||||
user: { name: <str>, email: <str> } # optional; overlays bottle
|
||||
# Claude Code subagent passthrough fields — accepted, ignored:
|
||||
name, description, model, color, memory
|
||||
|
||||
The agent file's Markdown body is the system prompt (stripped).
|
||||
Unknown top-level frontmatter keys raise ManifestError with a hint.
|
||||
|
||||
Bottles can ONLY live under $HOME. A bottles/ dir under $CWD is a
|
||||
warn at load time and contributes nothing. The trust boundary is
|
||||
expressed as filesystem layout rather than resolver logic.
|
||||
|
||||
Two types are exported:
|
||||
|
||||
ManifestIndex — the multi-agent/bottle collection returned by
|
||||
resolve() and from_json_obj(). Used for agent
|
||||
selection (all_agent_names), validation
|
||||
(require_agent), and lazy loading (load_for_agent).
|
||||
This is the pre-preflight form.
|
||||
|
||||
Manifest — a single-agent/bottle value type holding exactly
|
||||
one agent: ManifestAgent and one bottle:
|
||||
ManifestBottle (with the agent's git-gate.user
|
||||
already overlaid). Returned by load_for_agent().
|
||||
This is the post-preflight form passed to backends.
|
||||
|
||||
ManifestIndex.from_json_obj is preserved as a programmatic entry
|
||||
point (used by tests) that takes a dict with the same field names —
|
||||
useful for building manifests without on-disk files.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -14,20 +63,41 @@ from dataclasses import dataclass, field, replace
|
||||
from pathlib import Path
|
||||
from typing import Mapping
|
||||
|
||||
from ..log import warn
|
||||
from .util import ManifestError, as_json_object
|
||||
from .agent import ManifestAgent
|
||||
from .bottle import ManifestBottle
|
||||
from .extends import merge_bottles_runtime, resolve_bottles
|
||||
from .git import ManifestGitUser
|
||||
from .loader import (
|
||||
from .log import warn
|
||||
from .manifest_util import ManifestError, as_json_object
|
||||
from .manifest_agent import ManifestAgent, ManifestAgentProvider
|
||||
from .manifest_bottle import ManifestBottle
|
||||
from .manifest_egress import (
|
||||
EGRESS_AUTH_SCHEMES,
|
||||
ManifestEgressConfig,
|
||||
ManifestEgressRoute,
|
||||
)
|
||||
from .manifest_extends import merge_bottles_runtime, resolve_bottles
|
||||
from .manifest_git import ManifestGitEntry, ManifestGitUser, ManifestKeyConfig
|
||||
from .manifest_loader import (
|
||||
check_stale_json,
|
||||
load_bottle_chain_from_dir,
|
||||
scan_agent_names,
|
||||
scan_bottle_names,
|
||||
)
|
||||
from .schema import validate_agent_frontmatter_keys
|
||||
from ..yaml_subset import YamlSubsetError, parse_frontmatter
|
||||
from .manifest_schema import validate_agent_frontmatter_keys
|
||||
from .yaml_subset import YamlSubsetError, parse_frontmatter
|
||||
|
||||
# Re-export everything that callers currently import from this module.
|
||||
__all__ = [
|
||||
"ManifestError",
|
||||
"ManifestGitEntry",
|
||||
"ManifestGitUser",
|
||||
"ManifestKeyConfig",
|
||||
"ManifestAgentProvider",
|
||||
"EGRESS_AUTH_SCHEMES",
|
||||
"ManifestEgressRoute",
|
||||
"ManifestEgressConfig",
|
||||
"ManifestAgent",
|
||||
"ManifestBottle",
|
||||
"ManifestIndex",
|
||||
"Manifest",
|
||||
]
|
||||
|
||||
|
||||
def _section_dict(value: object, label: str) -> dict[str, object]:
|
||||
@@ -1,118 +0,0 @@
|
||||
"""Manifest dataclasses (PRD 0011 layout).
|
||||
|
||||
Reads the per-file manifest tree:
|
||||
|
||||
$HOME/.bot-bottle/bottles/<name>.md — one bottle per file
|
||||
$HOME/.bot-bottle/agents/<name>.md — home-resident agents
|
||||
$CWD/.bot-bottle/agents/<name>.md — cwd-supplied agents
|
||||
|
||||
Each file is Markdown with YAML frontmatter. The frontmatter holds
|
||||
the structured config (see schema below); for agents the body is
|
||||
the system prompt, for bottles the body is human documentation
|
||||
(ignored by the parser).
|
||||
|
||||
Bottle schema (frontmatter):
|
||||
extends: <bottle-name> # optional (PRD 0025)
|
||||
env: { <NAME>: <env-entry>, ... }
|
||||
git-gate: # optional (PRD 0047)
|
||||
user: { name: <str>, email: <str> } # optional
|
||||
repos: { <name>: <git-gate-entry>, ... } # optional
|
||||
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
|
||||
skills: [ <skill-name>, ... ] # optional
|
||||
git-gate:
|
||||
user: { name: <str>, email: <str> } # optional; overlays bottle
|
||||
# Claude Code subagent passthrough fields — accepted, ignored:
|
||||
name, description, model, color, memory
|
||||
|
||||
The agent file's Markdown body is the system prompt (stripped).
|
||||
Unknown top-level frontmatter keys raise ManifestError with a hint.
|
||||
|
||||
Bottles can ONLY live under $HOME. A bottles/ dir under $CWD is a
|
||||
warn at load time and contributes nothing. The trust boundary is
|
||||
expressed as filesystem layout rather than resolver logic.
|
||||
|
||||
Two types are exported:
|
||||
|
||||
ManifestIndex — the multi-agent/bottle collection returned by
|
||||
resolve() and from_json_obj(). Used for agent
|
||||
selection (all_agent_names), validation
|
||||
(require_agent), and lazy loading (load_for_agent).
|
||||
This is the pre-preflight form.
|
||||
|
||||
Manifest — a single-agent/bottle value type holding exactly
|
||||
one agent: ManifestAgent and one bottle:
|
||||
ManifestBottle (with the agent's git-gate.user
|
||||
already overlaid). Returned by load_for_agent().
|
||||
This is the post-preflight form passed to backends.
|
||||
|
||||
ManifestIndex.from_json_obj is preserved as a programmatic entry
|
||||
point (used by tests) that takes a dict with the same field names —
|
||||
useful for building manifests without on-disk files.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING, Any
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from .index import Manifest, ManifestIndex
|
||||
from .util import ManifestError
|
||||
from .agent import ManifestAgent, ManifestAgentProvider
|
||||
from .bottle import ManifestBottle
|
||||
from .egress import EGRESS_AUTH_SCHEMES, ManifestEgressConfig, ManifestEgressRoute
|
||||
from .git import ManifestGitEntry, ManifestGitUser, ManifestKeyConfig
|
||||
|
||||
|
||||
# Facade name -> submodule that defines it. The aggregate model (`Manifest`,
|
||||
# `ManifestIndex`) lives in `index`; the piece types in their own modules.
|
||||
_LAZY_MODULES: dict[str, str] = {
|
||||
"Manifest": "index",
|
||||
"ManifestIndex": "index",
|
||||
"ManifestError": "util",
|
||||
"ManifestAgent": "agent",
|
||||
"ManifestAgentProvider": "agent",
|
||||
"ManifestBottle": "bottle",
|
||||
"EGRESS_AUTH_SCHEMES": "egress",
|
||||
"ManifestEgressRoute": "egress",
|
||||
"ManifestEgressConfig": "egress",
|
||||
"ManifestGitEntry": "git",
|
||||
"ManifestGitUser": "git",
|
||||
"ManifestKeyConfig": "git",
|
||||
}
|
||||
|
||||
|
||||
def __getattr__(name: str) -> Any:
|
||||
"""Lazily surface the manifest facade names from their submodules and cache
|
||||
them at package level — so importing a leaf (e.g. `manifest.util`) doesn't
|
||||
build the whole manifest model, while `from bot_bottle.manifest import
|
||||
Manifest` keeps working."""
|
||||
mod = _LAZY_MODULES.get(name)
|
||||
if mod is None:
|
||||
raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
|
||||
from importlib import import_module
|
||||
|
||||
value = getattr(import_module(f"{__name__}.{mod}"), name)
|
||||
globals()[name] = value
|
||||
return value
|
||||
|
||||
|
||||
__all__ = [
|
||||
"Manifest",
|
||||
"ManifestIndex",
|
||||
"ManifestError",
|
||||
"ManifestGitEntry",
|
||||
"ManifestGitUser",
|
||||
"ManifestKeyConfig",
|
||||
"ManifestAgentProvider",
|
||||
"ManifestAgent",
|
||||
"ManifestBottle",
|
||||
"EGRESS_AUTH_SCHEMES",
|
||||
"ManifestEgressRoute",
|
||||
"ManifestEgressConfig",
|
||||
]
|
||||
@@ -5,10 +5,10 @@ from __future__ import annotations
|
||||
from dataclasses import dataclass, field
|
||||
from typing import cast
|
||||
|
||||
from ..agent_provider import PROVIDER_TEMPLATES
|
||||
from .util import ManifestError, as_json_object
|
||||
from .git import ManifestGitUser
|
||||
from .schema import AGENT_MODEL_KEYS, is_valid_entity_name
|
||||
from .agent_provider import PROVIDER_TEMPLATES
|
||||
from .manifest_util import ManifestError, as_json_object
|
||||
from .manifest_git import ManifestGitUser
|
||||
from .manifest_schema import AGENT_MODEL_KEYS, is_valid_entity_name
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
@@ -1,13 +1,13 @@
|
||||
"""The `ManifestBottle` value type.
|
||||
|
||||
Split out of the package facade (`manifest/__init__.py`) so the `extends:`/
|
||||
loader resolvers can import it without a circular dependency: the facade
|
||||
imports those resolvers, while they only need this value type. Everything here
|
||||
depends on leaf modules (`util`, `agent`, `egress`, `git`, `schema`), so this
|
||||
module sits at the bottom of the manifest layer.
|
||||
Split out of `manifest.py` so the `extends:`/loader resolvers can import it
|
||||
without a circular dependency: `manifest.py` imports those resolvers, while
|
||||
they only need this value type. Everything here depends on leaf modules
|
||||
(`manifest_util`, `manifest_agent`, `manifest_egress`, `manifest_git`,
|
||||
`manifest_schema`), so this module sits at the bottom of the manifest layer.
|
||||
|
||||
The facade re-exports `ManifestBottle`, so existing
|
||||
`from bot_bottle.manifest import ManifestBottle` callers are unaffected.
|
||||
`manifest.py` re-exports `ManifestBottle`, so existing
|
||||
`from .manifest import ManifestBottle` callers are unaffected.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -15,11 +15,11 @@ from __future__ import annotations
|
||||
from dataclasses import dataclass, field
|
||||
from typing import Mapping
|
||||
|
||||
from .util import ManifestError, as_json_object
|
||||
from .agent import ManifestAgentProvider
|
||||
from .egress import ManifestEgressConfig
|
||||
from .git import ManifestGitEntry, ManifestGitUser, parse_git_gate_config
|
||||
from .schema import BOTTLE_KEYS
|
||||
from .manifest_util import ManifestError, as_json_object
|
||||
from .manifest_agent import ManifestAgentProvider
|
||||
from .manifest_egress import ManifestEgressConfig
|
||||
from .manifest_git import ManifestGitEntry, ManifestGitUser, parse_git_gate_config
|
||||
from .manifest_schema import BOTTLE_KEYS
|
||||
|
||||
__all__ = ["ManifestBottle"]
|
||||
|
||||
@@ -6,7 +6,7 @@ import re
|
||||
from dataclasses import dataclass
|
||||
from typing import cast
|
||||
|
||||
from .util import ManifestError, as_json_object
|
||||
from .manifest_util import ManifestError, as_json_object
|
||||
|
||||
EGRESS_AUTH_SCHEMES = ("Bearer", "token")
|
||||
|
||||
@@ -2,10 +2,10 @@
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from .bottle import ManifestBottle
|
||||
from .egress import ManifestEgressConfig, validate_egress_routes
|
||||
from .git import ManifestGitUser, parse_git_gate_config
|
||||
from .util import ManifestError, as_json_object
|
||||
from .manifest_bottle import ManifestBottle
|
||||
from .manifest_egress import ManifestEgressConfig, validate_egress_routes
|
||||
from .manifest_git import ManifestGitUser, parse_git_gate_config
|
||||
from .manifest_util import ManifestError, as_json_object
|
||||
|
||||
|
||||
def _overlay_declared_bool(
|
||||
@@ -5,7 +5,7 @@ from __future__ import annotations
|
||||
import re
|
||||
from dataclasses import dataclass
|
||||
|
||||
from .util import ManifestError, as_json_object
|
||||
from .manifest_util import ManifestError, as_json_object
|
||||
|
||||
# Shell-safe characters for git-gate repo names. Names are embedded in
|
||||
# the generated entrypoint shell script (shlex.quote is the primary
|
||||
@@ -4,15 +4,15 @@ from __future__ import annotations
|
||||
|
||||
from pathlib import Path
|
||||
|
||||
from ..log import warn
|
||||
from .bottle import ManifestBottle
|
||||
from .extends import resolve_bottles
|
||||
from .schema import (
|
||||
from .log import warn
|
||||
from .manifest_bottle import ManifestBottle
|
||||
from .manifest_extends import resolve_bottles
|
||||
from .manifest_schema import (
|
||||
entity_name_from_path,
|
||||
validate_bottle_frontmatter_keys,
|
||||
)
|
||||
from .util import ManifestError
|
||||
from ..yaml_subset import YamlSubsetError, parse_frontmatter
|
||||
from .manifest_util import ManifestError
|
||||
from .yaml_subset import YamlSubsetError, parse_frontmatter
|
||||
|
||||
|
||||
def check_stale_json(dir_path: Path, md_dir: Path, label: str) -> None:
|
||||
@@ -68,7 +68,7 @@ def _validate_frontmatter_keys(
|
||||
keys: object,
|
||||
allowed_keys: frozenset[str],
|
||||
) -> None:
|
||||
from .util import ManifestError
|
||||
from .manifest_util import ManifestError
|
||||
|
||||
key_set = set(keys) # type: ignore
|
||||
unknown = key_set - allowed_keys # type: ignore
|
||||
@@ -5,19 +5,19 @@ A single persistent per-host service that will run the gateway functions
|
||||
agent launches. This package is being built bottom-up, starting with the
|
||||
backend-neutral "consolidation core" that needs no VM packaging:
|
||||
|
||||
* `store.registry_store` — the SQLite runtime-state store + fail-closed
|
||||
* `registry` — the SQLite runtime-state store + fail-closed
|
||||
attribution (source IP + per-bottle identity token).
|
||||
* `broker` — the signed, structured launch-request contract + a
|
||||
`LaunchBroker` (stub for the harness) that verifies
|
||||
provenance before acting.
|
||||
* `gateway` — the consolidated per-host gateway: the `Gateway`
|
||||
lifecycle contract (idempotent singleton). One
|
||||
gateway shared by all bottles instead of one per
|
||||
bottle; backend impls live under `backend/*/gateway`.
|
||||
* `gateway` — the consolidated per-host gateway: a `Gateway`
|
||||
lifecycle contract (idempotent singleton) + a
|
||||
`DockerGateway` impl. One gateway shared by all
|
||||
bottles instead of one per bottle.
|
||||
* `service` — the `Orchestrator`: owns the registry, brokers the
|
||||
launch lifecycle (launch/teardown), manages the
|
||||
shared gateway, attributes.
|
||||
* `server` — the HTTP control-plane RPC (launch / teardown /
|
||||
* `control_plane` — the HTTP control-plane RPC (launch / teardown /
|
||||
list / attribute / gateway / health).
|
||||
|
||||
The actual backend-native launch (a real docker/firecracker broker) and
|
||||
@@ -28,59 +28,19 @@ orchestrator -> firecracker).
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING, Any
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from .store.registry_store import BottleRecord, RegistryStore, new_identity_token
|
||||
from .broker import (
|
||||
BrokerAuthError,
|
||||
LaunchBroker,
|
||||
LaunchRequest,
|
||||
StubBroker,
|
||||
sign_request,
|
||||
verify_request,
|
||||
)
|
||||
from .docker_broker import DockerBroker, DockerBrokerError
|
||||
from ..gateway import Gateway, GatewayError
|
||||
from .service import Orchestrator
|
||||
from .server import OrchestratorServer, dispatch, make_server
|
||||
|
||||
|
||||
# Facade name -> submodule that defines it. Lazy so importing a leaf (or the
|
||||
# parent package, e.g. via `orchestrator.store.store_manager`) doesn't drag the
|
||||
# whole orchestrator — server, docker_broker + the docker backend, http — while
|
||||
# `from bot_bottle.orchestrator import RegistryStore` keeps working.
|
||||
_LAZY: dict[str, str] = {
|
||||
"BottleRecord": ".store.registry_store",
|
||||
"RegistryStore": ".store.registry_store",
|
||||
"new_identity_token": ".store.registry_store",
|
||||
"BrokerAuthError": ".broker",
|
||||
"LaunchBroker": ".broker",
|
||||
"LaunchRequest": ".broker",
|
||||
"StubBroker": ".broker",
|
||||
"sign_request": ".broker",
|
||||
"verify_request": ".broker",
|
||||
"DockerBroker": ".docker_broker",
|
||||
"DockerBrokerError": ".docker_broker",
|
||||
"Gateway": "..gateway",
|
||||
"GatewayError": "..gateway",
|
||||
"Orchestrator": ".service",
|
||||
"OrchestratorServer": ".server",
|
||||
"dispatch": ".server",
|
||||
"make_server": ".server",
|
||||
}
|
||||
|
||||
|
||||
def __getattr__(name: str) -> Any:
|
||||
src = _LAZY.get(name)
|
||||
if src is None:
|
||||
raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
|
||||
from importlib import import_module
|
||||
|
||||
value = getattr(import_module(src, __name__), name)
|
||||
globals()[name] = value
|
||||
return value
|
||||
|
||||
from .registry import BottleRecord, RegistryStore, new_identity_token
|
||||
from .broker import (
|
||||
BrokerAuthError,
|
||||
LaunchBroker,
|
||||
LaunchRequest,
|
||||
StubBroker,
|
||||
sign_request,
|
||||
verify_request,
|
||||
)
|
||||
from .docker_broker import DockerBroker, DockerBrokerError
|
||||
from .gateway import DockerGateway, Gateway, GatewayError
|
||||
from .service import Orchestrator
|
||||
from .control_plane import ControlPlaneServer, dispatch, make_server
|
||||
|
||||
__all__ = [
|
||||
"BottleRecord",
|
||||
@@ -90,14 +50,15 @@ __all__ = [
|
||||
"LaunchBroker",
|
||||
"LaunchRequest",
|
||||
"StubBroker",
|
||||
"sign_request",
|
||||
"verify_request",
|
||||
"DockerBroker",
|
||||
"DockerBrokerError",
|
||||
"Gateway",
|
||||
"DockerGateway",
|
||||
"GatewayError",
|
||||
"sign_request",
|
||||
"verify_request",
|
||||
"Orchestrator",
|
||||
"OrchestratorServer",
|
||||
"ControlPlaneServer",
|
||||
"dispatch",
|
||||
"make_server",
|
||||
]
|
||||
|
||||
@@ -16,12 +16,13 @@ import secrets
|
||||
from pathlib import Path
|
||||
|
||||
from .. import log
|
||||
from .store.store_manager import StoreManager
|
||||
from ..store_manager import StoreManager
|
||||
from .broker import LaunchBroker, StubBroker
|
||||
from .server import make_server
|
||||
from .control_plane import make_server
|
||||
from .docker_broker import DockerBroker
|
||||
from .store.registry_store import RegistryStore, default_db_path
|
||||
from .registry import RegistryStore, default_db_path
|
||||
from .service import Orchestrator
|
||||
from .gateway import DockerGateway, Gateway
|
||||
|
||||
|
||||
def main(argv: list[str] | None = None) -> int:
|
||||
@@ -37,6 +38,10 @@ def main(argv: list[str] | None = None) -> int:
|
||||
"--broker", choices=("stub", "docker"), default="stub",
|
||||
help="launch broker: 'stub' records requests; 'docker' runs containers",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--gateway", action="store_true",
|
||||
help="run one consolidated per-host gateway (build-if-missing)",
|
||||
)
|
||||
args = parser.parse_args(argv)
|
||||
|
||||
registry = RegistryStore(args.db)
|
||||
@@ -52,7 +57,20 @@ def main(argv: list[str] | None = None) -> int:
|
||||
# anything; 'docker' runs real containers (firecracker drops in later).
|
||||
secret = secrets.token_bytes(32)
|
||||
broker: LaunchBroker = DockerBroker(secret) if args.broker == "docker" else StubBroker(secret)
|
||||
orchestrator = Orchestrator(registry, broker, secret)
|
||||
# Standalone `--gateway` (not the consolidated flow, where the host
|
||||
# lifecycle runs the gateway). The gateway resolves against this same
|
||||
# process; the URL is only reachable when they share a docker network.
|
||||
gateway: Gateway | None = (
|
||||
DockerGateway(orchestrator_url=f"http://{args.host}:{args.port}")
|
||||
if args.gateway else None
|
||||
)
|
||||
orchestrator = Orchestrator(registry, broker, secret, gateway)
|
||||
|
||||
# One persistent per-host gateway, shared by every bottle: build the
|
||||
# bundle image if missing, then bring the singleton up (idempotent).
|
||||
if gateway is not None:
|
||||
orchestrator.ensure_gateway()
|
||||
log.info("consolidated gateway ensured", context={"name": gateway.name})
|
||||
|
||||
server = make_server(orchestrator, host=args.host, port=args.port)
|
||||
bound_host, bound_port = server.server_address[0], server.server_address[1]
|
||||
|
||||
@@ -18,22 +18,19 @@ import urllib.request
|
||||
from collections.abc import Iterable
|
||||
from dataclasses import dataclass
|
||||
|
||||
from ..orchestrator_auth import ROLE_CLI, mint
|
||||
from ..paths import host_orchestrator_token
|
||||
from .server import ORCHESTRATOR_AUTH_HEADER
|
||||
from ..paths import host_control_plane_token
|
||||
from .control_plane import CONTROL_AUTH_HEADER
|
||||
|
||||
DEFAULT_TIMEOUT_SECONDS = 5.0
|
||||
|
||||
|
||||
def _host_auth_token() -> str:
|
||||
"""A freshly minted `cli`-role token, signed with the host control-plane
|
||||
key, or "" if the key can't be read. The host CLI shares the orchestrator's
|
||||
trust domain, so it holds the signing key and mints its own operator token;
|
||||
"" means 'send no auth header' — correct against an open (unconfigured)
|
||||
control plane, and harmlessly rejected by a secured one."""
|
||||
"""The per-host control-plane secret, or "" if it can't be read. "" means
|
||||
'send no auth header' — correct against an open (unconfigured) control
|
||||
plane, and harmlessly rejected by a secured one."""
|
||||
try:
|
||||
return mint(ROLE_CLI, host_orchestrator_token())
|
||||
except (OSError, ValueError):
|
||||
return host_control_plane_token()
|
||||
except OSError:
|
||||
return ""
|
||||
|
||||
|
||||
@@ -83,7 +80,7 @@ class OrchestratorClient:
|
||||
data = json.dumps(body).encode() if body is not None else None
|
||||
headers = {"Content-Type": "application/json"} if data is not None else {}
|
||||
if self._auth_token:
|
||||
headers[ORCHESTRATOR_AUTH_HEADER] = self._auth_token
|
||||
headers[CONTROL_AUTH_HEADER] = self._auth_token
|
||||
req = urllib.request.Request(
|
||||
f"{self._base}{path}", data=data, method=method, headers=headers,
|
||||
)
|
||||
@@ -252,14 +249,14 @@ def discover_orchestrator_url(*, timeout: float = 2.0) -> str:
|
||||
candidates.append("http://127.0.0.1:8099")
|
||||
try: # firecracker: infra VM control plane on the orchestrator TAP
|
||||
from ..backend.firecracker import netpool
|
||||
from ..backend.firecracker.infra_vm import ORCHESTRATOR_PORT
|
||||
from ..backend.firecracker.infra_vm import CONTROL_PLANE_PORT
|
||||
candidates.append(
|
||||
f"http://{netpool.orch_slot().guest_ip}:{ORCHESTRATOR_PORT}")
|
||||
f"http://{netpool.orch_slot().guest_ip}:{CONTROL_PLANE_PORT}")
|
||||
except Exception: # noqa: BLE001 — backend optional / not firecracker
|
||||
pass
|
||||
try: # macOS: infra container control plane on its host-only address
|
||||
from ..backend.macos_container.infra import probe_orchestrator_url
|
||||
url = probe_orchestrator_url()
|
||||
from ..backend.macos_container.infra import probe_control_plane_url
|
||||
url = probe_control_plane_url()
|
||||
if url:
|
||||
candidates.append(url)
|
||||
except Exception: # noqa: BLE001 — backend optional / not macOS
|
||||
|
||||
+3
-3
@@ -11,9 +11,9 @@ import os
|
||||
import sqlite3
|
||||
from pathlib import Path
|
||||
|
||||
from ...store.db_store import DbStore
|
||||
from ...store.migrations import TableMigrations
|
||||
from ...paths import host_db_path
|
||||
from ..db_store import DbStore
|
||||
from ..migrations import TableMigrations
|
||||
from ..paths import host_db_path
|
||||
|
||||
TEARDOWN_TIMEOUT_ENV = "BOT_BOTTLE_ORCHESTRATOR_TEARDOWN_TIMEOUT_SECONDS"
|
||||
DEFAULT_TEARDOWN_TIMEOUT_SECONDS = 30.0
|
||||
@@ -35,12 +35,10 @@ vsock / unix-socket portability caveats):
|
||||
"proposal_id"}
|
||||
|
||||
The `/supervise/propose` + `/supervise/poll` pair is the **agent** half of the
|
||||
supervise flow: the data plane (supervise / egress / git-gate) queues a proposal
|
||||
and polls for its response over RPC instead of opening `bot-bottle.db` directly.
|
||||
`poll` is idempotent — it never archives, so a dropped connection can't lose an
|
||||
operator decision (the row is reaped when the bottle is torn down / reconciled).
|
||||
Both attribute the caller by `(source_ip, identity_token)` exactly like
|
||||
`/resolve`, so a bottle can only ever queue or read its own proposals.
|
||||
supervise flow: the data plane (supervise / egress / git-gate) queues a
|
||||
proposal and polls for its response over RPC instead of opening `bot-bottle.db`
|
||||
directly. Both attribute the caller by `(source_ip, identity_token)` exactly
|
||||
like `/resolve`, so a bottle can only ever queue or read its own proposals.
|
||||
|
||||
`POST /bottles` / `DELETE` drive the full launch lifecycle: they mint (or
|
||||
tear down) the bottle in the registry AND broker the backend-native launch
|
||||
@@ -48,13 +46,14 @@ via the orchestrator. Register/deregister without a launch are internal to
|
||||
`Orchestrator`, not exposed here.
|
||||
|
||||
Routing/handling is the pure function `dispatch()` so it is unit-testable
|
||||
without a socket; `Handler` / `OrchestratorServer` / `make_server` are a
|
||||
without a socket; `Handler` / `ControlPlaneServer` / `make_server` are a
|
||||
thin stdlib adapter around it. Listing redacts identity tokens — they are
|
||||
returned only once, to the caller that launches the bottle.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import hmac
|
||||
import http.server
|
||||
import json
|
||||
import os
|
||||
@@ -63,39 +62,20 @@ import sys
|
||||
import typing
|
||||
from urllib.parse import urlsplit
|
||||
|
||||
from ..orchestrator_auth import ROLE_CLI, ROLES, verify
|
||||
from ..paths import ORCHESTRATOR_TOKEN_ENV
|
||||
from ..supervisor.types import TOOLS
|
||||
from ..paths import CONTROL_PLANE_TOKEN_ENV
|
||||
from ..supervise_types import TOOLS
|
||||
from .service import Orchestrator
|
||||
|
||||
# JSON body payload type (parsed request / rendered response).
|
||||
Json = dict[str, object]
|
||||
|
||||
# The request header carrying the caller's role-scoped control-plane token (a
|
||||
# signed JWT naming the caller's role — see orchestrator_auth). The role gates which
|
||||
# routes the caller may reach: the data plane holds a `gateway` token good only
|
||||
# for the agent-facing lookups; the host CLI holds a `cli` token for the
|
||||
# operator/mutating routes. An agent that can merely *reach* the port holds no
|
||||
# token at all, and a compromised gateway holds only `gateway` — neither can
|
||||
# drive the operator routes (approve proposals, rewrite policy, read tokens).
|
||||
ORCHESTRATOR_AUTH_HEADER = "x-bot-bottle-orchestrator-auth"
|
||||
|
||||
# The routes the data plane (role `gateway`) is allowed to reach — exactly the
|
||||
# per-request lookups PolicyResolver makes. Every other authenticated route is
|
||||
# operator-only. `cli` is a superset role: it may reach any route.
|
||||
_GATEWAY_ROUTES: frozenset[tuple[str, str]] = frozenset({
|
||||
("POST", "/resolve"),
|
||||
("POST", "/supervise/propose"),
|
||||
("POST", "/supervise/poll"),
|
||||
})
|
||||
|
||||
|
||||
def _allowed_roles(method: str, route: str) -> frozenset[str]:
|
||||
"""The roles permitted on `(method, route)`: `gateway` or `cli` on the
|
||||
data-plane routes, `cli`-only everywhere else."""
|
||||
if (method, route) in _GATEWAY_ROUTES:
|
||||
return ROLES
|
||||
return frozenset({ROLE_CLI})
|
||||
# The request header carrying the per-host control-plane secret. Every route
|
||||
# except `GET /health` requires it (see `dispatch`). The trusted callers hold
|
||||
# the secret (the gateway's PolicyResolver, the host CLI's OrchestratorClient);
|
||||
# an agent that can merely *reach* the port cannot present it, so it can't
|
||||
# enumerate bottles, rewrite policy, read injected upstream tokens, or approve
|
||||
# its own supervise proposals.
|
||||
CONTROL_AUTH_HEADER = "x-bot-bottle-control-auth"
|
||||
|
||||
|
||||
def _parse_json_object(body: bytes) -> Json:
|
||||
@@ -109,33 +89,28 @@ def _parse_json_object(body: bytes) -> Json:
|
||||
|
||||
|
||||
def dispatch( # pylint: disable=too-many-return-statements,too-many-branches
|
||||
orch: Orchestrator, method: str, path: str, body: bytes, *, role: str | None = ROLE_CLI,
|
||||
orch: Orchestrator, method: str, path: str, body: bytes, *, authorized: bool = True,
|
||||
) -> tuple[int, Json]:
|
||||
"""Route one control-plane request to a (status, payload) pair. Pure —
|
||||
no I/O beyond the orchestrator — so it is fully testable without a socket.
|
||||
|
||||
`role` is the caller's verified control-plane role (`gateway` or `cli`), or
|
||||
None for an unauthenticated request; an open-mode server (no signing key
|
||||
configured — see `OrchestratorServer`) passes `cli`. Every route except
|
||||
`GET /health` requires a role: a missing role is 401, and a role that
|
||||
doesn't cover the route is 403 — so a `gateway` data-plane token can reach
|
||||
`/resolve` + `/supervise/{propose,poll}` but not the operator routes
|
||||
(rewrite policy, read injected tokens, approve its own supervise proposals).
|
||||
The source-IP + identity-token checks inside `/resolve` and `/attribute`
|
||||
authenticate the *bottle* a request is about, not the *caller*, so this role
|
||||
gate is what protects the caller-privileged routes. Defaults `cli` so unit
|
||||
tests of the routing logic don't have to thread it through."""
|
||||
`authorized` is whether the request presented the control-plane secret (or
|
||||
no secret is configured — see `ControlPlaneServer`). Every route except
|
||||
`GET /health` requires it: the source-IP + identity-token checks inside
|
||||
`/resolve` and `/attribute` authenticate the *bottle* a request is about,
|
||||
not the *caller*, so without this gate any agent that can reach the port
|
||||
could rewrite another bottle's policy, read the injected upstream tokens,
|
||||
or approve its own supervise proposals. Defaults True so unit tests of the
|
||||
routing logic don't have to thread it through."""
|
||||
route = urlsplit(path).path.rstrip("/") or "/"
|
||||
|
||||
if method == "GET" and route == "/health":
|
||||
return 200, {"status": "ok"}
|
||||
|
||||
# Role gate — every route below is a trusted-caller operation. Deny before
|
||||
# touching the registry / broker / supervise store.
|
||||
if role is None:
|
||||
if not authorized:
|
||||
# Everything below is a trusted-caller operation. Deny before touching
|
||||
# the registry / broker / supervise store.
|
||||
return 401, {"error": "control-plane authentication required"}
|
||||
if role not in _allowed_roles(method, route):
|
||||
return 403, {"error": "insufficient role for this route"}
|
||||
|
||||
if method == "GET" and route == "/gateway":
|
||||
return 200, orch.gateway_status()
|
||||
@@ -365,13 +340,13 @@ class Handler(http.server.BaseHTTPRequestHandler):
|
||||
crashing the connection, so one bad request can't take the control
|
||||
plane down for the caller."""
|
||||
server = self.server
|
||||
assert isinstance(server, OrchestratorServer)
|
||||
assert isinstance(server, ControlPlaneServer)
|
||||
length = int(self.headers.get("Content-Length") or 0)
|
||||
body = self.rfile.read(length) if length > 0 else b""
|
||||
role = server.role_for(self.headers.get(ORCHESTRATOR_AUTH_HEADER, ""))
|
||||
authorized = server.is_authorized(self.headers.get(CONTROL_AUTH_HEADER, ""))
|
||||
try:
|
||||
status, payload = dispatch(
|
||||
server.orchestrator, method, self.path, body, role=role)
|
||||
server.orchestrator, method, self.path, body, authorized=authorized)
|
||||
except Exception as e: # noqa: BLE001 — the control plane must stay up
|
||||
sys.stderr.write(f"orchestrator: {method} {self.path} failed: {e!r}\n")
|
||||
sys.stderr.flush()
|
||||
@@ -396,28 +371,26 @@ class Handler(http.server.BaseHTTPRequestHandler):
|
||||
self._serve("DELETE")
|
||||
|
||||
|
||||
class OrchestratorServer(socketserver.ThreadingMixIn, http.server.HTTPServer):
|
||||
class ControlPlaneServer(socketserver.ThreadingMixIn, http.server.HTTPServer):
|
||||
"""Threading HTTP server that carries the orchestrator for its handlers.
|
||||
|
||||
Holds the per-host control-plane *signing key* (from
|
||||
`$BOT_BOTTLE_ORCHESTRATOR_TOKEN`, injected by the launcher into the
|
||||
orchestrator process only) and verifies each request's role-scoped token
|
||||
against it. When a key is set, every route but `/health` requires a valid
|
||||
token whose role covers the route; when it is unset the server runs **open**
|
||||
(full `cli` access) and says so loudly at startup — a fail-visible fallback
|
||||
for tests and any backend that hasn't wired the key yet (e.g. Firecracker,
|
||||
whose nft boundary already blocks agents from the control-plane port)."""
|
||||
Holds the per-host control-plane secret (from `$BOT_BOTTLE_CONTROL_PLANE_TOKEN`,
|
||||
injected by the launcher into this container only). When a secret is set,
|
||||
every route but `/health` requires it; when it is unset the server runs
|
||||
**open** and says so loudly at startup — a fail-visible fallback for tests
|
||||
and any backend that hasn't wired the secret yet (e.g. Firecracker, whose
|
||||
nft boundary already blocks agents from the control-plane port)."""
|
||||
|
||||
daemon_threads = True
|
||||
allow_reuse_address = True
|
||||
|
||||
def __init__(self, address: tuple[str, int], orchestrator: Orchestrator) -> None:
|
||||
self.orchestrator = orchestrator
|
||||
self._signing_key = os.environ.get(ORCHESTRATOR_TOKEN_ENV, "").strip()
|
||||
if not self._signing_key:
|
||||
self._auth_token = os.environ.get(CONTROL_PLANE_TOKEN_ENV, "").strip()
|
||||
if not self._auth_token:
|
||||
sys.stderr.write(
|
||||
"orchestrator: WARNING — no control-plane signing key "
|
||||
f"(${ORCHESTRATOR_TOKEN_ENV}); running WITHOUT caller "
|
||||
"orchestrator: WARNING — no control-plane secret "
|
||||
f"(${CONTROL_PLANE_TOKEN_ENV}); running WITHOUT caller "
|
||||
"authentication. Any client that can reach this port can drive "
|
||||
"it. Backends that put the control plane on an agent-reachable "
|
||||
"network MUST set this.\n"
|
||||
@@ -425,26 +398,24 @@ class OrchestratorServer(socketserver.ThreadingMixIn, http.server.HTTPServer):
|
||||
sys.stderr.flush()
|
||||
super().__init__(address, Handler)
|
||||
|
||||
def role_for(self, presented: str) -> str | None:
|
||||
"""The role the request is authorized as, or None if unauthenticated.
|
||||
Open mode (no signing key) grants full `cli` access — the fail-visible
|
||||
fallback. Otherwise verify the presented signed token; a missing/invalid
|
||||
token yields None (→ 401), a valid one yields its `gateway`/`cli`
|
||||
role (→ per-route 401/403 in `dispatch`)."""
|
||||
if not self._signing_key:
|
||||
return ROLE_CLI
|
||||
return verify(presented, self._signing_key)
|
||||
def is_authorized(self, presented: str) -> bool:
|
||||
"""True iff the request may proceed past `/health`: either no secret is
|
||||
configured (open mode) or the presented header matches it. Constant-time
|
||||
compare so a wrong token leaks nothing timing-wise."""
|
||||
if not self._auth_token:
|
||||
return True
|
||||
return hmac.compare_digest(presented, self._auth_token)
|
||||
|
||||
|
||||
def make_server(
|
||||
orchestrator: Orchestrator, host: str = "127.0.0.1", port: int = 0
|
||||
) -> OrchestratorServer:
|
||||
) -> ControlPlaneServer:
|
||||
"""Build (but do not start) a control-plane server. `port=0` binds an
|
||||
ephemeral port — read `server.server_address` for the actual one."""
|
||||
return OrchestratorServer((host, port), orchestrator)
|
||||
return ControlPlaneServer((host, port), orchestrator)
|
||||
|
||||
|
||||
__all__ = [
|
||||
"dispatch", "Handler", "OrchestratorServer", "make_server", "Json",
|
||||
"ORCHESTRATOR_AUTH_HEADER",
|
||||
"dispatch", "Handler", "ControlPlaneServer", "make_server", "Json",
|
||||
"CONTROL_AUTH_HEADER",
|
||||
]
|
||||
@@ -15,7 +15,7 @@ from __future__ import annotations
|
||||
|
||||
import subprocess
|
||||
|
||||
from ..backend.docker.util import run_docker
|
||||
from ..docker_cmd import run_docker
|
||||
from .broker import LaunchBroker, LaunchRequest
|
||||
|
||||
CONTAINER_PREFIX = "bot-bottle-orch-"
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user