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

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

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

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

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

Refs #516. Addresses #510.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

bot_bottle/backend/base.py

@@ -512,6 +512,27 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
         compose ls`; firecracker cross-references its running gateway
         containers against per-bottle metadata."""
 
+    @abstractmethod
+    def attach_bottled_agents_to_gateway(self) -> None:
+        """Reconcile every already-running bottle against the freshly-(re)booted
+        gateway (PRD 0081). The host calls this on the gateway bring-up path —
+        the cold-boot branch only, never on an adopt of a healthy current
+        gateway — so a gateway rebuild/restart doesn't silently break running
+        bottles' gateway-dependent state.
+
+        Reconciling running bottles is a backend responsibility: only the
+        backend can enumerate its agents and reach them (firecracker over SSH,
+        docker/macOS over `exec`/`cp`), so every backend must implement it —
+        cross-backend by construction. Each per-bottle step is best-effort: one
+        unreachable or malformed bottle is logged and skipped so it never blocks
+        the others or the gateway coming up.
+
+        Currently reconciles the **CA**: it replaces each agent's trusted CA
+        with the current gateway CA (unconditional — there is one gateway, so no
+        fingerprint match is needed), which rotates the CA for free on every
+        bring-up. Git-gate re-provision and egress-token restore fold into this
+        same reconcile on the same trigger (see #516)."""
+
     @classmethod
     @abstractmethod
     def is_available(cls) -> bool:

bot_bottle/backend/docker/backend.py

@@ -140,3 +140,7 @@ class DockerBottleBackend(BottleBackend["DockerBottlePlan", "DockerBottleCleanup
 
     def enumerate_active(self) -> Sequence[ActiveAgent]:
         return _enumerate.enumerate_active()
+
+    def attach_bottled_agents_to_gateway(self) -> None:
+        from .consolidated_launch import attach_bottled_agents_to_gateway
+        attach_bottled_agents_to_gateway()

bot_bottle/backend/docker/consolidated_launch.py

@@ -13,6 +13,7 @@ orchestrator-facing wiring so that sequence stays testable in isolation.
 
 from __future__ import annotations
 
+import tempfile
 from dataclasses import dataclass
 
 from ... import log
@@ -25,6 +26,7 @@ from .infra import INFRA_NAME, DockerInfraService
 from ...orchestrator.store.secret_store import ENV_VAR_SECRET_NAME
 from ...orchestrator.reprovision import reprovision_bottles
 from ..provision_bottle import deprovision_bottle, provision_bottle
+from ..util import AGENT_CA_PATH
 from .gateway_transport import DockerGatewayTransport
 from .gateway_net import next_free_ip
 
@@ -79,6 +81,77 @@ def _network_container_ips(network: str) -> list[str]:
     return ips
 
 
+def _push_ca_to_container(container: str, ca_pem: str) -> None:
+    """Replace one running agent container's trusted gateway CA with `ca_pem`
+    and rebuild its trust store via `docker cp` + `docker exec`. Unconditional
+    install — there is one gateway, so no fingerprint match is needed. Raises
+    `ConsolidatedLaunchError` on failure."""
+    mkdir = run_docker(
+        ["docker", "exec", container, "mkdir", "-p",
+         "/usr/local/share/ca-certificates"]
+    )
+    if mkdir.returncode != 0:
+        raise ConsolidatedLaunchError(
+            f"CA push to {container} failed (mkdir): {mkdir.stderr.strip()}"
+        )
+    with tempfile.NamedTemporaryFile("w", suffix=".crt") as tmp:
+        tmp.write(ca_pem)
+        tmp.flush()
+        cp = run_docker(["docker", "cp", tmp.name, f"{container}:{AGENT_CA_PATH}"])
+    if cp.returncode != 0:
+        raise ConsolidatedLaunchError(
+            f"CA push to {container} failed (cp): {cp.stderr.strip()}"
+        )
+    ex = run_docker(
+        ["docker", "exec", container, "sh", "-c",
+         f"chmod 644 {AGENT_CA_PATH} && update-ca-certificates"]
+    )
+    if ex.returncode != 0:
+        raise ConsolidatedLaunchError(
+            f"CA push to {container} failed (update-ca-certificates): "
+            f"{ex.stderr.strip()}"
+        )
+
+
+def attach_bottled_agents_to_gateway(
+    ca_pem: str | None = None,
+    *,
+    network: str = GATEWAY_NETWORK,
+    gateway_name: str = INFRA_NAME,
+) -> None:
+    """Reconcile every running agent container against the freshly-(re)created
+    gateway (PRD 0081): replace each agent's trusted CA with the current gateway
+    CA, so a gateway rebuild doesn't silently break their TLS egress (#510).
+
+    Per-container steps are best-effort: one failure is logged and skipped so it
+    never blocks the others or the gateway coming up."""
+    if ca_pem is None:
+        ca_pem = DockerInfraService().gateway().ca_cert_pem()
+    try:
+        proc = run_docker([
+            "docker", "network", "inspect", "--format",
+            "{{range .Containers}}{{.Name}}\n{{end}}", network,
+        ])
+    except OSError as exc:
+        log.info(f"CA reconcile skipped: {exc}")
+        return
+    reconciled = 0
+    for line in proc.stdout.splitlines():
+        name = line.strip()
+        if not name or name == gateway_name:
+            continue
+        try:
+            _push_ca_to_container(name, ca_pem)
+            reconciled += 1
+        except (OSError, ConsolidatedLaunchError) as exc:
+            log.info(f"CA reconcile skipped for {name}: {exc}")
+    if reconciled:
+        log.info(
+            "reconciled gateway CA into running docker bottle(s)",
+            context={"count": reconciled},
+        )
+
+
 def _reprovision_running_bottles(
     orchestrator_url: str,
     network: str = GATEWAY_NETWORK,
@@ -185,6 +258,7 @@ def deprovision_consolidated(
 __all__ = [
     "LaunchContext",
     "launch_consolidated",
+    "attach_bottled_agents_to_gateway",
     "deprovision_consolidated",
     "ConsolidatedLaunchError",
 ]

bot_bottle/backend/docker/gateway.py

@@ -200,7 +200,7 @@ class DockerGateway(Gateway):
                 f"gateway network {self.network} failed to create: {proc.stderr.strip()}"
             )
 
-    def connect_to_orchestrator(self, orchestrator_url: str, gateway_token: str) -> None:
+    def connect_to_orchestrator(self, orchestrator_url: str, gateway_token: str) -> bool:
         # Bind to this orchestrator (PRD 0070): stash the URL its daemons resolve
         # policy against + the pre-minted `gateway` token they present, then bring
         # the container up. The gateway never mints, so it holds no signing key —
@@ -227,7 +227,7 @@ class DockerGateway(Gateway):
         # just when the container is absent.
         self._ensure_network()
         if self.is_running() and self._running_image_is_current():
-            return
+            return False
         # Clear any stale (stopped OR outdated-image) container holding the
         # fixed name, then start fresh. `rm --force` on an absent name is a
         # tolerated no-op.
@@ -271,6 +271,9 @@ class DockerGateway(Gateway):
         # pre-connect window (they retry /resolve per request).
         if self._control_network:
             self._connect_control_network()
+        # (Re)created a fresh container — signal a cold boot so the caller
+        # reconciles running bottles against it (PRD 0081).
+        return True
 
     def _connect_control_network(self) -> None:
         """Ensure the `--internal` control network exists and attach the gateway

bot_bottle/backend/docker/infra.py

@@ -142,9 +142,16 @@ class DockerInfraService(InfraService):
         # mints the role-scoped `gateway` JWT here and hands it to the gateway,
         # which never sees the key (#469). `connect_to_orchestrator` is
         # idempotent.
-        gateway.connect_to_orchestrator(
+        cold_booted = gateway.connect_to_orchestrator(
             orchestrator.gateway_url(), orchestrator.mint_gateway_token(),
         )
+        # A (re)created gateway container minted/mounted its CA afresh and lost
+        # every bottle's per-bottle state; reconcile the already-running bottles
+        # against it (PRD 0081). Skipped when a healthy current gateway was left
+        # untouched — no cold boot, nothing to reconcile.
+        if cold_booted:
+            from .backend import DockerBottleBackend
+            DockerBottleBackend().attach_bottled_agents_to_gateway()
         return orchestrator.url()
 
     def stop(self) -> None:

bot_bottle/backend/firecracker/backend.py

@@ -119,6 +119,10 @@ class FirecrackerBottleBackend(
     def enumerate_active(self) -> Sequence[ActiveAgent]:
         return _enumerate.enumerate_active()
 
+    def attach_bottled_agents_to_gateway(self) -> None:
+        from .consolidated_launch import attach_bottled_agents_to_gateway
+        attach_bottled_agents_to_gateway()
+
     def supervise_mcp_url(self, plan: FirecrackerBottlePlan) -> str:
         return plan.agent_supervise_url
 

bot_bottle/backend/firecracker/consolidated_launch.py

@@ -32,6 +32,7 @@ from dataclasses import dataclass
 from pathlib import Path
 
 from ...egress import EgressPlan
+from ...gateway import GatewayError
 from ...git_gate import GitGatePlan
 from ...log import info
 from ...orchestrator.client import OrchestratorClient, OrchestratorClientError
@@ -41,6 +42,7 @@ from ...orchestrator.lifecycle import (
 from ...orchestrator.reprovision import reprovision_bottles
 from ...orchestrator.store.secret_store import ENV_VAR_SECRET_NAME
 from ..provision_bottle import deprovision_bottle, provision_bottle
+from ..util import AGENT_CA_PATH
 from . import cleanup, util
 from .gateway import FirecrackerGateway
 from .infra import FirecrackerInfraService
@@ -89,6 +91,56 @@ def persist_env_var_secret(private_key: Path, guest_ip: str, secret: str) -> Non
         )
 
 
+def _push_gateway_ca_to_agent(private_key: Path, guest_ip: str, ca_pem: str) -> None:
+    """Replace one running agent VM's trusted gateway CA with `ca_pem` and
+    rebuild its trust store over SSH. Unconditional install — there is one
+    gateway, so no fingerprint match is needed. Bare-pipe input keeps the cert
+    off argv. Raises `ConsolidatedLaunchError` on failure."""
+    install = (
+        "umask 022; mkdir -p /usr/local/share/ca-certificates && "
+        f"cat > {AGENT_CA_PATH} && chmod 644 {AGENT_CA_PATH} && "
+        "update-ca-certificates"
+    )
+    proc = subprocess.run(
+        util.ssh_base_argv(private_key, guest_ip) + [install],
+        input=ca_pem, capture_output=True, text=True, check=False,
+    )
+    if proc.returncode != 0:
+        raise ConsolidatedLaunchError(
+            f"CA push to {guest_ip} failed: "
+            f"{proc.stderr.strip() or '<no stderr>'}"
+        )
+
+
+def attach_bottled_agents_to_gateway() -> None:
+    """Reconcile every running agent VM against the freshly-booted gateway
+    (PRD 0081). Replaces each agent's trusted CA with the current gateway CA —
+    the gateway rootfs is ephemeral, so a cold boot mints a fresh CA and this is
+    what distributes it (a gateway rebuild doubles as a free CA rotation, #510).
+
+    Per-bottle steps are best-effort: one unreachable or malformed VM is logged
+    and skipped so it never blocks the others or the gateway coming up."""
+    gateway = FirecrackerGateway()
+    try:
+        ca_pem = gateway.ca_cert_pem()
+    except GatewayError as exc:
+        info(f"bring-up reconcile skipped: gateway CA unavailable: {exc}")
+        return
+    reconciled = 0
+    for run_dir in cleanup.live_run_dirs():
+        guest_ip = _guest_ip_from_config(run_dir / "config.json")
+        private_key = run_dir / "bottle_id_ed25519"
+        if not guest_ip or not private_key.is_file():
+            continue
+        try:
+            _push_gateway_ca_to_agent(private_key, guest_ip, ca_pem)
+            reconciled += 1
+        except (OSError, ConsolidatedLaunchError) as exc:
+            info(f"CA reconcile skipped for {guest_ip}: {exc}")
+    if reconciled:
+        info(f"reconciled gateway CA into {reconciled} running Firecracker bottle(s)")
+
+
 def _reprovision_running_bottles(client: OrchestratorClient) -> None:
     """Read keys from live agent VMs and restore the restarted gateway."""
     try:
@@ -161,6 +213,7 @@ def deprovision_consolidated(
 __all__ = [
     "LaunchContext",
     "launch_consolidated",
+    "attach_bottled_agents_to_gateway",
     "deprovision_consolidated",
     "ConsolidatedLaunchError",
     "OrchestratorStartError",

bot_bottle/backend/firecracker/gateway.py

@@ -69,13 +69,17 @@ class FirecrackerGateway(Gateway):
         self._orchestrator_url = ""
         self._gateway_token = ""
 
-    def connect_to_orchestrator(self, orchestrator_url: str, gateway_token: str) -> None:
+    def connect_to_orchestrator(self, orchestrator_url: str, gateway_token: str) -> bool:
         """Boot the gateway VM on its link resolving policy against
         `orchestrator_url`, then seed `gateway_token` over SSH. The orchestrator's
         guest IP is parsed from the URL and passed on the cmdline (`bb_orch=`), so
         the baked init stays IP-independent. Boot the orchestrator first — the
         gateway daemons reach it at startup. The gateway never mints, so it holds
-        no signing key, only this token (#469)."""
+        no signing key, only this token (#469).
+
+        Always returns True: the firecracker gateway VM is booted fresh here
+        (this runs only on the infra cold-boot path), so it is always a cold
+        boot that minted a new CA — the caller reconciles running bottles."""
         self._orchestrator_url = orchestrator_url
         self._gateway_token = gateway_token
         if not self._orchestrator_url:
@@ -105,6 +109,7 @@ class FirecrackerGateway(Gateway):
             "the gateway JWT to the gateway VM (its data plane will not start)",
         )
         self._vm = vm
+        return True
 
     def is_running(self) -> bool:
         return infra_vm._pidfile_alive(infra_vm._gw_dir())

bot_bottle/backend/firecracker/infra.py

@@ -67,9 +67,17 @@ class FirecrackerInfraService(InfraService):
             # holds the signing key) mints the role-scoped `gateway` JWT for the
             # gateway, which never sees the key (#469).
             orchestrator.ensure_running(startup_timeout=startup_timeout)
-            self.gateway().connect_to_orchestrator(
+            cold_booted = self.gateway().connect_to_orchestrator(
                 orchestrator.gateway_url(), orchestrator.mint_gateway_token())
             infra_vm.record_booted_version(want)
+            # The fresh gateway rootfs minted a new CA and lost every bottle's
+            # git-gate/token state; reconcile the already-running bottles against
+            # it so a gateway rebuild doesn't silently break their egress
+            # (PRD 0081). Cold-boot only — the adopt fast-paths above never reach
+            # here, so a healthy current gateway is left untouched.
+            if cold_booted:
+                from .backend import FirecrackerBottleBackend
+                FirecrackerBottleBackend().attach_bottled_agents_to_gateway()
             return url
 
     def stop(self) -> None:

bot_bottle/backend/macos_container/backend.py

@@ -117,5 +117,9 @@ class MacosContainerBottleBackend(
     def enumerate_active(self) -> Sequence[ActiveAgent]:
         return _enumerate.enumerate_active()
 
+    def attach_bottled_agents_to_gateway(self) -> None:
+        from .consolidated_launch import attach_bottled_agents_to_gateway
+        attach_bottled_agents_to_gateway()
+
     def supervise_mcp_url(self, plan: MacosContainerBottlePlan) -> str:
         return plan.agent_supervise_url

bot_bottle/backend/macos_container/consolidated_launch.py

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

bot_bottle/backend/macos_container/gateway.py

@@ -104,11 +104,15 @@ class MacosGateway(Gateway):
         container_mod.build_image(
             self.image_ref, str(self._repo_root), dockerfile="Dockerfile.gateway")
 
-    def connect_to_orchestrator(self, orchestrator_url: str, gateway_token: str) -> None:
+    def connect_to_orchestrator(self, orchestrator_url: str, gateway_token: str) -> bool:
         """Bind the gateway to this orchestrator and (re)start it, dual-homed on
         the agent + control networks, resolving policy against `orchestrator_url`
         (the orchestrator's control-network address — Apple has no container
-        DNS) and presenting `gateway_token`."""
+        DNS) and presenting `gateway_token`.
+
+        Always returns True: this recreates the gateway container unconditionally
+        (a cold boot), so the caller reconciles running bottles against it
+        (PRD 0081)."""
         self._orchestrator_url = orchestrator_url
         self._gateway_token = gateway_token
         # Fail closed on a missing policy source or token: the resolver-only data
@@ -156,6 +160,7 @@ class MacosGateway(Gateway):
                 f"gateway container failed to start: "
                 f"{(result.stderr or '').strip() or '<no stderr>'}"
             )
+        return True
 
     def is_running(self) -> bool:
         return container_mod.container_is_running(self.name)

bot_bottle/backend/macos_container/infra.py

@@ -138,7 +138,15 @@ class MacosInfraService(InfraService):
         # `gateway` JWT and hands it to the gateway, which never sees the key
         # (#469).
         url = orchestrator.url()
-        gateway.connect_to_orchestrator(url, orchestrator.mint_gateway_token())
+        cold_booted = gateway.connect_to_orchestrator(
+            url, orchestrator.mint_gateway_token())
+        # A (re)created gateway container minted/mounted its CA afresh and lost
+        # every bottle's per-bottle state; reconcile the already-running bottles
+        # against it (PRD 0081). Skipped when a healthy current gateway was left
+        # untouched — no cold boot, nothing to reconcile.
+        if cold_booted:
+            from .backend import MacosContainerBottleBackend
+            MacosContainerBottleBackend().attach_bottled_agents_to_gateway()
         return url
 
     def ca_cert_pem(self, *, timeout: float = DEFAULT_CA_TIMEOUT_SECONDS) -> str:

bot_bottle/gateway/__init__.py

@@ -122,12 +122,18 @@ class Gateway(abc.ABC):
         return
 
     @abc.abstractmethod
-    def connect_to_orchestrator(self, orchestrator_url: str, gateway_token: str) -> None:
+    def connect_to_orchestrator(self, orchestrator_url: str, gateway_token: str) -> bool:
         """Bind the gateway to this orchestrator and bring it up: store the URL +
         the pre-minted `gateway` token as instance state, then (re)start the
         gateway unit carrying the mitmproxy CA + that token, resolving policy
         against `orchestrator_url`. Idempotent — a healthy, current gateway on
-        the same binding is left alone; a changed binding reconciles it."""
+        the same binding is left alone; a changed binding reconciles it.
+
+        Returns True when the gateway was actually (re)brought up (a cold boot,
+        so its mitmproxy minted a fresh CA and lost its per-bottle state), False
+        when a healthy current gateway was left untouched. The bring-up flow
+        uses this as the cold-boot signal that gates the running-bottle
+        reconcile (`attach_bottled_agents_to_gateway`, PRD 0081)."""
 
     @abc.abstractmethod
     def is_running(self) -> bool: