feat(prd-0081): reprovision CA, git-gate, and egress tokens on gateway bring-up
prd-number-check / require-numbered-prds (pull_request) Successful in 13s
tracker-policy-pr / check-pr (pull_request) Successful in 7s
test / image-input-builds (pull_request) Successful in 41s
test / unit (pull_request) Successful in 51s
test / integration-docker (pull_request) Successful in 58s
test / coverage (pull_request) Successful in 41s
test / image-input-builds (push) Successful in 48s
test / unit (push) Successful in 56s
lint / lint (push) Successful in 1m2s
Update Quality Badges / update-badges (push) Successful in 1m4s
test / integration-docker (push) Failing after 2m53s
test / coverage (push) Has been skipped

On a Firecracker gateway cold boot, reconcile every live agent VM against
the fresh gateway: push the new mitmproxy CA into each agent's trust store,
re-provision git-gate repos/creds from the persisted upstreams snapshot,
and restore egress tokens. Per-bottle failures are logged and skipped so
one unreachable VM does not block the rest.

New modules / changes:
- backend/firecracker/reconcile.py: attach_bottled_agents_to_gateway,
  _push_ca, _reprovision_git_gate, _guest_ip_from_config
- git_gate/provision.py: write upstreams.json after key provisioning so
  the bring-up reconcile can reconstruct the upstream table without the
  manifest
- backend/firecracker/infra.py: call attach_bottled_agents_to_gateway in
  the cold-boot branch of ensure_running()
- backend/base.py: no-op default on BottleBackend
- backend/firecracker/consolidated_launch.py: remove superseded
  _reprovision_running_bottles / _guest_ip_from_config
- orchestrator: OrchestratorCore.update_agent_secret + POST
  /bottles/<id>/secret + client.update_agent_secret (single-secret
  in-place update, the reusable primitive from the 2026-07-26 hotfix)
- tests: 15 new tests in test_firecracker_reconcile.py; updated
  test_firecracker_infra.py cold-boot cases; stale FC reprovision tests
  removed from test_backend_secret_reprovision.py

Closes #516.
This commit was merged in pull request #517.
This commit is contained in:
2026-07-28 01:50:15 +00:00
parent 6f997bf118
commit dee0121e8d
69 changed files with 937 additions and 4015 deletions
@@ -84,7 +84,6 @@ class MacosGateway(Gateway):
egress_network: str = GATEWAY_EGRESS_NETWORK,
control_network: str = CONTROL_NETWORK,
repo_root: Path | None = None,
local_build: bool = True,
) -> None:
self.image_ref = image_ref
self.name = name
@@ -94,7 +93,6 @@ class MacosGateway(Gateway):
# Build context: the repo root in a checkout, a staged copy from the
# installed wheel otherwise (bot_bottle.resources).
self._repo_root = repo_root if repo_root is not None else resources.build_root()
self._local_build = local_build
# Set by `connect_to_orchestrator`: the URL the daemons resolve policy
# against + the pre-minted `gateway` token they present. The gateway
# never mints, so it never holds the signing key (#469).
@@ -103,11 +101,8 @@ class MacosGateway(Gateway):
def ensure_built(self) -> None:
"""Build the data-plane image from `Dockerfile.gateway`."""
if self._local_build:
container_mod.build_image(
self.image_ref, str(self._repo_root), dockerfile="Dockerfile.gateway")
else:
container_mod.pull_image(self.image_ref)
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:
"""Bind the gateway to this orchestrator and (re)start it, dual-homed on
+2 -13
View File
@@ -25,7 +25,6 @@ from __future__ import annotations
from pathlib import Path
from ... import resources
from ... import release_manifest
from ...orchestrator.lifecycle import (
DEFAULT_PORT,
DEFAULT_STARTUP_TIMEOUT_SECONDS,
@@ -87,14 +86,6 @@ class MacosInfraService(InfraService):
self._orchestrator_name = orchestrator_name
self._gateway_name = gateway_name
self._db_volume = db_volume
resolved_orchestrator, orchestrator_local = release_manifest.oci_image(
"orchestrator", orchestrator_image)
resolved_gateway, gateway_local = release_manifest.oci_image(
"gateway", gateway_image)
self.orchestrator_image = resolved_orchestrator
self.gateway_image = resolved_gateway
self._orchestrator_local = orchestrator_local
self._gateway_local = gateway_local
def orchestrator(self) -> MacosOrchestrator:
"""The control-plane service on the host-only control network. Cheap to
@@ -107,7 +98,6 @@ class MacosInfraService(InfraService):
control_network=self.control_network,
repo_root=self._repo_root,
db_volume=self._db_volume,
local_build=self._orchestrator_local,
)
def gateway(self) -> MacosGateway:
@@ -122,7 +112,6 @@ class MacosInfraService(InfraService):
egress_network=self.egress_network,
control_network=self.control_network,
repo_root=self._repo_root,
local_build=self._gateway_local,
)
def ensure_running(
@@ -138,8 +127,8 @@ class MacosInfraService(InfraService):
orchestrator = self.orchestrator()
gateway = self.gateway()
orchestrator.ensure_available()
gateway.ensure_available()
orchestrator.ensure_built()
gateway.ensure_built()
orchestrator.ensure_running(startup_timeout=startup_timeout)
+1 -9
View File
@@ -38,7 +38,6 @@ import subprocess
from contextlib import ExitStack, contextmanager
from typing import Callable, Generator
from ...agent_provider import runtime_for
from ...bottle_state import (
egress_state_dir,
git_gate_state_dir,
@@ -94,14 +93,7 @@ def _agent_image(plan: MacosContainerBottlePlan) -> str:
)
info(f"using cached agent image {plan.image!r}")
return plan.image
if "@sha256:" in plan.image:
container_mod.pull_image(plan.image)
container_mod.verify_agent_image(
plan.image, runtime_for(plan.agent_provider_template).smoke_test,
)
return plan.image
container_mod.build_image(
plan.image, str(resources.build_root()), dockerfile=plan.dockerfile_path)
container_mod.build_image(plan.image, str(resources.build_root()), dockerfile=plan.dockerfile_path)
return plan.image
@@ -63,7 +63,6 @@ class MacosOrchestrator(Orchestrator):
control_network: str = CONTROL_NETWORK,
repo_root: Path | None = None,
db_volume: str = ORCHESTRATOR_DB_VOLUME,
local_build: bool = True,
) -> None:
self.image_ref = image_ref
self.name = name
@@ -74,7 +73,6 @@ class MacosOrchestrator(Orchestrator):
# staged copy from the installed wheel otherwise (bot_bottle.resources).
self._repo_root = repo_root if repo_root is not None else resources.build_root()
self._db_volume = db_volume
self._local_build = local_build
def url(self) -> str:
"""The orchestrator's control-network address (host CLI + registration),
@@ -116,12 +114,8 @@ class MacosOrchestrator(Orchestrator):
"""Build the control-plane image. The source is bind-mounted so a code
change takes effect without a rebuild; the image still carries the
package for its entrypoint."""
if self._local_build:
container_mod.build_image(
self.image_ref, str(self._repo_root),
dockerfile="Dockerfile.orchestrator")
else:
container_mod.pull_image(self.image_ref)
container_mod.build_image(
self.image_ref, str(self._repo_root), dockerfile="Dockerfile.orchestrator")
def ensure_running(
self, *, startup_timeout: float = DEFAULT_STARTUP_TIMEOUT_SECONDS,
@@ -152,6 +146,11 @@ class MacosOrchestrator(Orchestrator):
"--dns", container_mod.dns_server(),
# Container-only DB volume: exactly one kernel writes bot-bottle.db.
"--volume", f"{self._db_volume}:{_DB_ROOT_IN_CONTAINER}",
# Live control-plane source (a code change takes effect on relaunch).
"--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.
"--env", f"BOT_BOTTLE_SOURCE_HASH={current_hash}",
@@ -162,14 +161,6 @@ class MacosOrchestrator(Orchestrator):
# Dockerfile.orchestrator ENTRYPOINT is `-m bot_bottle.orchestrator`.
"--host", "0.0.0.0", "--port", str(self.port), "--broker", "stub",
]
if self._local_build:
image_index = argv.index(self.image_ref)
argv[image_index:image_index] = [
"--mount",
container_mod.bind_mount_spec(
str(self._repo_root), _SRC_IN_CONTAINER, readonly=True),
"--env", f"PYTHONPATH={_SRC_IN_CONTAINER}",
]
result = container_mod.run_container_argv(
argv, env={**os.environ, ORCHESTRATOR_TOKEN_ENV: _signing_key})
if result.returncode != 0:
@@ -101,19 +101,6 @@ def build_image(
subprocess.run(args, check=True)
def pull_image(ref: str) -> None:
"""Acquire an immutable OCI reference through Apple Container."""
result = subprocess.run(
[_CONTAINER, "image", "pull", ref],
capture_output=True,
text=True,
check=False,
)
if result.returncode != 0:
detail = (result.stderr or result.stdout or "").strip()
raise RuntimeError(f"container image pull failed for {ref}: {detail}")
def verify_agent_image(image: str, argv: tuple[str, ...]) -> None:
"""Run `argv` inside a throwaway container of a freshly built agent
image and die loudly if it fails, instead of shipping an image