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ensure_running() - backend/base.py: no-op default on BottleBackend - backend/firecracker/consolidated_launch.py: remove superseded _reprovision_running_bottles / _guest_ip_from_config - orchestrator: OrchestratorCore.update_agent_secret + POST /bottles/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:
@@ -89,10 +89,6 @@ class DockerGateway(Gateway):
|
||||
when no dockerfile is configured (a pre-pulled image). BOT_BOTTLE_NO_CACHE
|
||||
forces a full rebuild (parity with `start --no-cache`)."""
|
||||
if self._dockerfile is None:
|
||||
proc = run_docker(["docker", "pull", self.image_ref])
|
||||
if proc.returncode != 0:
|
||||
raise GatewayError(
|
||||
f"gateway image pull failed: {proc.stderr.strip()}")
|
||||
return
|
||||
context = self._build_context or resources.build_root()
|
||||
argv = ["docker", "build", "-t", self.image_ref,
|
||||
|
||||
@@ -34,7 +34,6 @@ from .orchestrator import (
|
||||
ORCHESTRATOR_NETWORK,
|
||||
)
|
||||
from ... import resources
|
||||
from ... import release_manifest
|
||||
from ...gateway import (
|
||||
GATEWAY_IMAGE,
|
||||
GATEWAY_NAME,
|
||||
@@ -91,14 +90,6 @@ class DockerInfraService(InfraService):
|
||||
self._orchestrator_name = orchestrator_name
|
||||
self._orchestrator_label = orchestrator_label
|
||||
self._gateway_name = gateway_name
|
||||
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) -> DockerOrchestrator:
|
||||
"""The control-plane service. Cheap to reconstruct — `ensure_built`
|
||||
@@ -113,8 +104,6 @@ class DockerInfraService(InfraService):
|
||||
repo_root=self._repo_root,
|
||||
host_root=self._host_root,
|
||||
root_mount_source=self._root_mount_source,
|
||||
dockerfile=(
|
||||
"Dockerfile.orchestrator" if self._orchestrator_local else None),
|
||||
)
|
||||
|
||||
def gateway(self) -> DockerGateway:
|
||||
@@ -130,7 +119,6 @@ class DockerInfraService(InfraService):
|
||||
control_network=self.control_network,
|
||||
build_context=self._repo_root,
|
||||
ca_mount_source=self._gateway_ca_mount_source,
|
||||
dockerfile="Dockerfile.gateway" if self._gateway_local else None,
|
||||
)
|
||||
|
||||
def ensure_running(
|
||||
@@ -144,8 +132,8 @@ class DockerInfraService(InfraService):
|
||||
gateway = self.gateway()
|
||||
# Build both images (cache-aware; a no-op when nothing changed) before
|
||||
# bringing either plane up.
|
||||
orchestrator.ensure_available()
|
||||
gateway.ensure_available()
|
||||
orchestrator.ensure_built()
|
||||
gateway.ensure_built()
|
||||
|
||||
orchestrator.ensure_running(startup_timeout=startup_timeout)
|
||||
|
||||
|
||||
@@ -84,15 +84,6 @@ def build_or_load_images(plan: DockerBottlePlan) -> BottleImages:
|
||||
)
|
||||
info(f"using cached agent image {plan.image!r}")
|
||||
return BottleImages(agent=plan.image)
|
||||
if "@sha256:" in plan.image:
|
||||
pulled = docker_mod.run_docker(["docker", "pull", plan.image])
|
||||
if pulled.returncode != 0:
|
||||
die(f"pulling packaged agent image {plan.image!r} failed: "
|
||||
f"{pulled.stderr.strip()}")
|
||||
docker_mod.verify_agent_image(
|
||||
plan.image, runtime_for(plan.agent_provider_template).smoke_test,
|
||||
)
|
||||
return BottleImages(agent=plan.image)
|
||||
docker_mod.build_image(plan.image, str(resources.build_root()), dockerfile=plan.dockerfile_path)
|
||||
docker_mod.verify_agent_image(
|
||||
plan.image, runtime_for(plan.agent_provider_template).smoke_test,
|
||||
|
||||
@@ -125,10 +125,6 @@ class DockerOrchestrator(Orchestrator):
|
||||
no-op when nothing changed). No-op when no dockerfile is configured (a
|
||||
pre-pulled image). BOT_BOTTLE_NO_CACHE forces a full rebuild."""
|
||||
if self._dockerfile is None:
|
||||
proc = run_docker(["docker", "pull", self.image_ref])
|
||||
if proc.returncode != 0:
|
||||
raise GatewayError(
|
||||
f"orchestrator image pull failed: {proc.stderr.strip()}")
|
||||
return
|
||||
argv = ["docker", "build", "-t", self.image_ref,
|
||||
"-f", str(self._repo_root / self._dockerfile),
|
||||
|
||||
Reference in New Issue
Block a user