feat(reconcile): reprovision CA, git-gate, and egress tokens on gateway bring-up (PRD 0081)
prd-number-check / require-numbered-prds (pull_request) Successful in 10s
tracker-policy-pr / check-pr (pull_request) Successful in 16s
lint / lint (push) Failing after 1m1s
test / unit (pull_request) Successful in 56s
test / image-input-builds (pull_request) Successful in 1m0s
test / integration-docker (pull_request) Failing after 3m7s
test / coverage (pull_request) Has been skipped
prd-number-check / require-numbered-prds (pull_request) Successful in 10s
tracker-policy-pr / check-pr (pull_request) Successful in 16s
lint / lint (push) Failing after 1m1s
test / unit (pull_request) Successful in 56s
test / image-input-builds (pull_request) Successful in 1m0s
test / integration-docker (pull_request) Failing after 3m7s
test / coverage (pull_request) Has been skipped
On a gateway cold boot, reconcile every live agent VM against the fresh gateway: push the new 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 rather than aborting the whole reconcile. New: reconcile.py — attach_bottled_agents_to_gateway, _push_ca, _reprovision_git_gate, _guest_ip_from_config. New: git_gate/provision.py writes upstreams.json after key provisioning so the bring-up reconcile can reconstruct the upstream table without the manifest. Wired into FirecrackerInfraService.ensure_running() cold-boot path; base.py BottleBackend gets a no-op default. Old _reprovision_running_bottles removed from consolidated_launch.py (superseded by reconcile.py). Tests migrated and extended.
This commit is contained in:
@@ -26,22 +26,19 @@ The TAP slot allocation, rootfs build, and VM boot are the caller's job.
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import subprocess
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
|
||||
from ...egress import EgressPlan
|
||||
from ...git_gate import GitGatePlan
|
||||
from ...log import info
|
||||
from ...orchestrator.client import OrchestratorClient, OrchestratorClientError
|
||||
from ...orchestrator.client import OrchestratorClient
|
||||
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 ..provision_bottle import deprovision_bottle, provision_bottle
|
||||
from . import cleanup, util
|
||||
from . import util
|
||||
from .gateway import FirecrackerGateway
|
||||
from .infra import FirecrackerInfraService
|
||||
|
||||
@@ -64,17 +61,6 @@ class LaunchContext:
|
||||
env_var_secret: str = "" # encryption key injected into the agent's env
|
||||
|
||||
|
||||
def _guest_ip_from_config(config_path: Path) -> str:
|
||||
"""Read the kernel's configured guest IP from a Firecracker config."""
|
||||
try:
|
||||
config = json.loads(config_path.read_text())
|
||||
args = config["boot-source"]["boot_args"]
|
||||
ip_arg = next(part for part in args.split() if part.startswith("ip="))
|
||||
return ip_arg.removeprefix("ip=").split(":", 1)[0]
|
||||
except (OSError, ValueError, KeyError, TypeError, StopIteration):
|
||||
return ""
|
||||
|
||||
|
||||
def persist_env_var_secret(private_key: Path, guest_ip: str, secret: str) -> None:
|
||||
"""Mirror the exec-time key into guest tmpfs for restart recovery."""
|
||||
proc = subprocess.run(
|
||||
@@ -89,29 +75,6 @@ def persist_env_var_secret(private_key: Path, guest_ip: str, secret: str) -> Non
|
||||
)
|
||||
|
||||
|
||||
def _reprovision_running_bottles(client: OrchestratorClient) -> None:
|
||||
"""Read keys from live agent VMs and restore the restarted gateway."""
|
||||
try:
|
||||
secrets_by_ip: dict[str, str] = {}
|
||||
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
|
||||
proc = subprocess.run(
|
||||
util.ssh_base_argv(private_key, guest_ip)
|
||||
+ [f"cat {_ENV_VAR_SECRET_PATH}"],
|
||||
capture_output=True, text=True, check=False,
|
||||
)
|
||||
if proc.returncode == 0 and proc.stdout.strip():
|
||||
secrets_by_ip[guest_ip] = proc.stdout.strip()
|
||||
count = reprovision_bottles(client, secrets_by_ip)
|
||||
if count:
|
||||
info(f"reprovisioned egress tokens for {count} Firecracker bottle(s)")
|
||||
except (OSError, OrchestratorClientError) as exc:
|
||||
info(f"egress token reprovision skipped: {exc}")
|
||||
|
||||
|
||||
def launch_consolidated(
|
||||
egress_plan: EgressPlan,
|
||||
git_gate_plan: GitGatePlan,
|
||||
@@ -126,7 +89,6 @@ def launch_consolidated(
|
||||
service = FirecrackerInfraService()
|
||||
url = service.ensure_running()
|
||||
client = OrchestratorClient(url)
|
||||
_reprovision_running_bottles(client)
|
||||
|
||||
# Read the gateway's provisioning transport + CA off the Gateway service.
|
||||
gateway = service.gateway()
|
||||
|
||||
Reference in New Issue
Block a user