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
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ensure_running() - backend/base.py: no-op default on BottleBackend - backend/firecracker/consolidated_launch.py: remove superseded _reprovision_running_bottles / _guest_ip_from_config - orchestrator: OrchestratorCore.update_agent_secret + POST /bottles/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:
@@ -43,7 +43,6 @@ from pathlib import Path
|
||||
from typing import Generator
|
||||
|
||||
from ... import resources
|
||||
from ... import release_manifest
|
||||
from ...log import die, info
|
||||
from ..docker import util as docker_mod
|
||||
from . import firecracker_vm, infra_artifact, netpool, util
|
||||
@@ -109,18 +108,6 @@ def _role_version(role: str) -> str:
|
||||
return infra_artifact.infra_artifact_version(role_init(role), role)
|
||||
|
||||
|
||||
def _role_release(role: str) -> tuple[str, str | None]:
|
||||
manifest = release_manifest.packaged_manifest()
|
||||
if manifest is None or release_manifest.local_build_requested():
|
||||
return _role_version(role), None
|
||||
artifact = (
|
||||
manifest.firecracker_orchestrator
|
||||
if role == "orchestrator"
|
||||
else manifest.firecracker_gateway
|
||||
)
|
||||
return artifact.version, artifact.sha256
|
||||
|
||||
|
||||
def ensure_built() -> None:
|
||||
"""Ensure both infra rootfs artifacts are available before boot.
|
||||
|
||||
@@ -130,16 +117,11 @@ def ensure_built() -> None:
|
||||
`BOT_BOTTLE_INFRA_BUILD=local` instead builds the images from source with
|
||||
host Docker (the orchestrator-fc image is `FROM` the orchestrator image, so
|
||||
it must exist first) — for iterating on the Dockerfiles."""
|
||||
if release_manifest.local_build_requested():
|
||||
if infra_artifact.local_build_requested():
|
||||
build_infra_images_with_docker()
|
||||
return
|
||||
for role in infra_artifact.ROLES:
|
||||
version, expected = _role_release(role)
|
||||
infra_artifact.ensure_artifact_gz(
|
||||
version, role=role, expected_sha256=expected)
|
||||
|
||||
|
||||
ensure_available = ensure_built
|
||||
infra_artifact.ensure_artifact_gz(_role_version(role), role=role)
|
||||
|
||||
|
||||
def build_infra_images_with_docker() -> None:
|
||||
@@ -232,9 +214,7 @@ def boot_vm(
|
||||
else:
|
||||
# Prebuilt artifact already carries the role's build slack; expand it to
|
||||
# a fresh writable rootfs for this boot.
|
||||
version, expected = _role_release(role)
|
||||
infra_artifact.materialize_ext4(
|
||||
version, rootfs, role=role, expected_sha256=expected)
|
||||
infra_artifact.materialize_ext4(_role_version(role), rootfs, role=role)
|
||||
private_key, pubkey = _stable_keypair()
|
||||
|
||||
info(f"booting {role} VM on {slot.iface} (guest {slot.guest_ip})")
|
||||
@@ -284,8 +264,7 @@ def _version_file() -> Path:
|
||||
def expected_version() -> str:
|
||||
"""The combined marker for the running pair: both per-plane artifact
|
||||
versions, so a change to either rootfs dislodges the adopted pair."""
|
||||
return " ".join(
|
||||
f"{role}={_role_release(role)[0]}" for role in infra_artifact.ROLES)
|
||||
return " ".join(f"{role}={_role_version(role)}" for role in infra_artifact.ROLES)
|
||||
|
||||
|
||||
def adoptable(key: Path, url: str, want: str) -> bool:
|
||||
|
||||
Reference in New Issue
Block a user