bot-bottle/bot_bottle/backend/macos_container/consolidated_launch.py

"""Consolidated bottle launch sequence for the macOS backend (PRD 0070).

The docker backend allocates a free address, pins the agent to it with
`--ip`, registers it, *then* starts the agent — registration precedes launch
because the pinned address is known up front.

**Apple Container 1.0.0 has no `--ip`.** The `--network` flag takes only
`<name>[,mac=…][,mtu=…]`; the address is assigned by vmnet's DHCP and is
knowable only once the container is running. So the macOS order inverts:

    ensure_gateway()  ->  caller starts the agent  ->  register_agent(source_ip)

That is why this module exposes two functions where docker has one — the
caller has to start the agent in between. `ensure_gateway` runs first because
the agent's proxy env needs the gateway's address at `container run` time; the
agent's *own* address (the attribution key) only exists afterwards.

The control plane and the gateway are one **infra container** here (see
`infra`), so `gateway_ip` and the control-plane host are the same address.

The consequence for the identity token: it is minted by registration, i.e.
*after* the agent container exists, so it cannot be baked into the run-time
env the way docker's compose spec does. It is delivered at `container exec`
time instead — see `bottle.MacosContainerBottle`.

That delivery is load-bearing, not a nicety: `/resolve` requires a matching
`(source_ip, identity_token)` pair and fail-closes with no source-IP-only
fallback (#366). So egress that does not carry the token is denied — which is
the safe direction, and is why the agent's init process is a bare `sleep` and
every real command arrives through `container exec`.
"""

from __future__ import annotations

from dataclasses import dataclass

from ...egress import EgressPlan
from ...git_gate import GitGatePlan
from ...orchestrator.client import OrchestratorClient
from ...orchestrator.registration import registration_inputs
from ..docker.gateway_provision import deprovision_git_gate, provision_git_gate
from .gateway import GATEWAY_NETWORK
from .gateway_provision import AppleGatewayTransport
from .infra import MacosInfraService, OrchestratorStartError


class ConsolidatedLaunchError(RuntimeError):
    """The consolidated register/provision sequence could not complete."""


@dataclass(frozen=True)
class GatewayEndpoint:
    """What the agent `container run` needs to reach the shared gateway (the
    infra container). `gateway_ip` is that container's host-only address, the
    same host the control-plane URL points at."""

    orchestrator_url: str
    gateway_ip: str         # the gateway's address — the agent's proxy target
    gateway_ca_pem: str     # the shared CA the provisioner installs
    network: str            # the shared host-only network to attach to


@dataclass(frozen=True)
class LaunchContext:
    """What the running agent needs once it has been registered."""

    bottle_id: str
    identity_token: str
    source_ip: str          # the agent's DHCP-assigned address (attribution key)
    gateway_ip: str
    network: str
    orchestrator_url: str


def ensure_gateway(
    *, service: MacosInfraService | None = None,
) -> GatewayEndpoint:
    """Ensure the per-host infra container (control plane + gateway) is up and
    report how to reach it. Idempotent — one singleton, so N bottle launches
    share it. Call before starting the agent container: the agent's proxy env
    needs `gateway_ip` at run time."""
    service = service or MacosInfraService()
    infra = service.ensure_running()
    return GatewayEndpoint(
        orchestrator_url=infra.control_plane_url,
        gateway_ip=infra.gateway_ip,
        gateway_ca_pem=service.ca_cert_pem(),
        network=service.network,
    )


def register_agent(
    egress_plan: EgressPlan,
    git_gate_plan: GitGatePlan,
    *,
    source_ip: str,
    endpoint: GatewayEndpoint,
    image_ref: str = "",
    tokens: dict[str, str] | None = None,
) -> LaunchContext:
    """Register the (already running) agent by its address and provision its
    git-gate state into the gateway. `source_ip` must be read from the live
    container — it is the attribution key the gateway resolves policy by.
    Raises on failure; the caller tears down."""
    client = OrchestratorClient(endpoint.orchestrator_url)
    inputs = registration_inputs(egress_plan)
    reg = client.register_bottle(
        source_ip, image_ref=image_ref, policy=inputs.policy,
        metadata=inputs.metadata, tokens=tokens,
    )
    try:
        provision_git_gate(AppleGatewayTransport(), reg.bottle_id, git_gate_plan)
    except Exception:
        # Roll the registration back so a provisioning failure leaves no orphan.
        client.teardown_bottle(reg.bottle_id)
        raise
    return LaunchContext(
        bottle_id=reg.bottle_id,
        identity_token=reg.identity_token,
        source_ip=source_ip,
        gateway_ip=endpoint.gateway_ip,
        network=endpoint.network,
        orchestrator_url=endpoint.orchestrator_url,
    )


def teardown_consolidated(
    bottle_id: str, *, orchestrator_url: str, timeout: float | None = None,
) -> None:
    """Deregister the bottle and remove its git-gate state from the gateway.
    Both steps are idempotent so this is safe from a cleanup trap. Does NOT
    stop the gateway — it's a persistent per-host singleton."""
    from ...orchestrator.config_store import DEFAULT_TEARDOWN_TIMEOUT_SECONDS
    OrchestratorClient(
        orchestrator_url,
        timeout=timeout if timeout is not None else DEFAULT_TEARDOWN_TIMEOUT_SECONDS,
    ).teardown_bottle(bottle_id)
    deprovision_git_gate(AppleGatewayTransport(), bottle_id)


__all__ = [
    "GatewayEndpoint",
    "LaunchContext",
    "ensure_gateway",
    "register_agent",
    "teardown_consolidated",
    "ConsolidatedLaunchError",
    "OrchestratorStartError",
    "GATEWAY_NETWORK",
]