feat: gate infrastructure changes on provider inventory
Dependency Audit / dependency-audit (push) Successful in 1m43s
Deployment Installer / deployment-installer (push) Successful in 6s
Security Audit / security-audit (push) Failing after 12m3s
Developer Meta-package Release / publish-package (push) Successful in 9s

This commit is contained in:
2026-08-24 15:18:38 +02:00
parent ed6790c057
commit 0b171fbdd4
10 changed files with 743 additions and 18 deletions
@@ -27,6 +27,7 @@ EXISTING_PROXY_FILENAME = "existing-proxy.json"
PLAN_FILENAME = "plan.json"
RECEIPT_FILENAME = "receipt.json"
CAPABILITIES_FILENAME = "infrastructure-capabilities.json"
DEPENDENCY_INVENTORY_FILENAME = "infrastructure-dependency-inventory.json"
MANIFEST_FILENAME = "distribution-manifest.json"
KEYRING_FILENAME = "distribution-keyring.json"
BACKUP_EVIDENCE_FILENAME = "backup-evidence.json"
@@ -116,6 +117,7 @@ class BundlePaths:
plan: Path
receipt: Path
capabilities: Path
dependency_inventory: Path
manifest: Path
keyring: Path
backup_evidence: Path
@@ -141,6 +143,7 @@ def bundle_paths(root: Path) -> BundlePaths:
plan=resolved / PLAN_FILENAME,
receipt=resolved / RECEIPT_FILENAME,
capabilities=resolved / CAPABILITIES_FILENAME,
dependency_inventory=resolved / DEPENDENCY_INVENTORY_FILENAME,
manifest=resolved / MANIFEST_FILENAME,
keyring=resolved / KEYRING_FILENAME,
backup_evidence=resolved / BACKUP_EVIDENCE_FILENAME,
@@ -3,6 +3,7 @@
from __future__ import annotations
from dataclasses import asdict, dataclass
from datetime import UTC, datetime
from typing import Mapping
from urllib.parse import urlsplit
@@ -18,6 +19,10 @@ CAPABILITY_STATES = frozenset(
"unavailable",
}
)
DEPENDENCY_INVENTORY_SCHEMA_VERSION = 1
DEPENDENCY_STATES = frozenset(
{"active", "inactive", "data_present", "pending_work", "runtime_binding"}
)
@dataclass(frozen=True, slots=True)
@@ -50,13 +55,161 @@ class CapabilityChangeImpact:
dependent_modules: tuple[str, ...]
detail: str
required_action: str
actual_dependencies: tuple["CapabilityDependency", ...] = ()
inventory_inspected: bool = False
def to_dict(self) -> dict[str, object]:
value = asdict(self)
value["dependent_modules"] = list(self.dependent_modules)
value["actual_dependencies"] = [
item.to_dict() for item in self.actual_dependencies
]
return value
@dataclass(frozen=True, slots=True)
class CapabilityDependency:
capability_id: str
module_id: str
dependency_type: str
dependency_ref: str
state: str
scope: str
summary: str
metrics: Mapping[str, int]
required_action: str
def to_dict(self) -> dict[str, object]:
return {
"capability_id": self.capability_id,
"module_id": self.module_id,
"dependency_type": self.dependency_type,
"dependency_ref": self.dependency_ref,
"state": self.state,
"scope": self.scope,
"summary": self.summary,
"metrics": dict(sorted(self.metrics.items())),
"required_action": self.required_action,
}
@dataclass(frozen=True, slots=True)
class InfrastructureDependencyInventory:
installation_id: str
generated_at: datetime
complete: bool
inspected_capability_ids: tuple[str, ...]
provider_count: int
dependencies: tuple[CapabilityDependency, ...]
def dependencies_for(
self,
capability_id: str,
) -> tuple[CapabilityDependency, ...]:
return tuple(
item for item in self.dependencies if item.capability_id == capability_id
)
def infrastructure_dependency_inventory_from_mapping(
value: object,
) -> InfrastructureDependencyInventory:
if (
not isinstance(value, Mapping)
or value.get("schema_version") != DEPENDENCY_INVENTORY_SCHEMA_VERSION
):
raise ValueError("Infrastructure dependency inventory schema is unsupported.")
installation_id = _inventory_text(value, "installation_id", maximum=100)
generated_at_text = _inventory_text(value, "generated_at", maximum=100)
try:
generated_at = datetime.fromisoformat(generated_at_text.replace("Z", "+00:00"))
except ValueError as exc:
raise ValueError(
"Infrastructure dependency inventory timestamp is invalid."
) from exc
if generated_at.tzinfo is None:
raise ValueError("Infrastructure dependency inventory timestamp needs a timezone.")
generated_at = generated_at.astimezone(UTC)
complete = value.get("complete")
if type(complete) is not bool:
raise ValueError("Infrastructure dependency inventory completion state is invalid.")
inspected = _inventory_string_list(
value.get("inspected_capability_ids"),
maximum_items=100,
maximum_length=120,
)
if len(inspected) != len(set(inspected)):
raise ValueError("Infrastructure dependency inventory repeats a capability id.")
providers = value.get("providers")
if not isinstance(providers, list) or len(providers) > 100:
raise ValueError("Infrastructure dependency provider reports are invalid.")
provider_states: list[str] = []
provider_declarations: dict[str, tuple[str, ...]] = {}
provider_counts: dict[str, int] = {}
for provider in providers:
if not isinstance(provider, Mapping):
raise ValueError("Infrastructure dependency provider report is invalid.")
module_id = _inventory_text(provider, "module_id", maximum=120)
if module_id in provider_declarations:
raise ValueError("Infrastructure dependency provider is repeated.")
state = _inventory_text(provider, "state", maximum=40)
if state not in {"complete", "error"}:
raise ValueError("Infrastructure dependency provider state is invalid.")
provider_states.append(state)
count = provider.get("dependency_count")
if type(count) is not int or count < 0:
raise ValueError("Infrastructure dependency provider count is invalid.")
capability_ids = _inventory_string_list(
provider.get("capability_ids"),
maximum_items=30,
maximum_length=120,
)
if len(capability_ids) != len(set(capability_ids)):
raise ValueError("Infrastructure dependency provider capability is repeated.")
provider_declarations[module_id] = capability_ids
provider_counts[module_id] = count
if complete and any(state != "complete" for state in provider_states):
raise ValueError("Complete dependency inventory contains a failed provider.")
raw_dependencies = value.get("dependencies")
if not isinstance(raw_dependencies, list) or len(raw_dependencies) > 10_000:
raise ValueError("Infrastructure dependency records are invalid.")
dependencies = tuple(_inventory_dependency(item) for item in raw_dependencies)
if any(
capability_id not in inspected
for capability_ids in provider_declarations.values()
for capability_id in capability_ids
):
raise ValueError(
"Infrastructure dependency provider was not covered by the inspection."
)
if any(item.capability_id not in inspected for item in dependencies):
raise ValueError("Dependency record was not covered by the inventory inspection.")
identities = {
(item.capability_id, item.module_id, item.dependency_type, item.dependency_ref)
for item in dependencies
}
if len(identities) != len(dependencies):
raise ValueError("Infrastructure dependency inventory repeats a record.")
observed_counts = {module_id: 0 for module_id in provider_counts}
for dependency in dependencies:
declarations = provider_declarations.get(dependency.module_id)
if declarations is None or dependency.capability_id not in declarations:
raise ValueError(
"Infrastructure dependency is outside its provider declaration."
)
observed_counts[dependency.module_id] += 1
if observed_counts != provider_counts:
raise ValueError("Infrastructure dependency provider count does not match records.")
return InfrastructureDependencyInventory(
installation_id=installation_id,
generated_at=generated_at,
complete=complete,
inspected_capability_ids=inspected,
provider_count=len(providers),
dependencies=dependencies,
)
def infrastructure_capability_document(
spec: InstallationSpec,
environment: Mapping[str, str],
@@ -89,6 +242,8 @@ def infrastructure_capability_document(
def capability_change_impacts(
previous_document: object,
desired_document: Mapping[str, object],
*,
dependency_inventory: InfrastructureDependencyInventory | None = None,
) -> tuple[CapabilityChangeImpact, ...]:
previous = _capability_map(previous_document)
desired = _capability_map(desired_document)
@@ -141,6 +296,43 @@ def capability_change_impacts(
previous_secret_refs,
desired_secret_refs,
)
actual_dependencies = (
dependency_inventory.dependencies_for(capability_id)
if dependency_inventory is not None
else ()
)
inventory_inspected = bool(
dependency_inventory is not None
and capability_id in dependency_inventory.inspected_capability_ids
)
if inventory_inspected and actual_dependencies:
references = ", ".join(
f"{item.module_id}:{item.dependency_ref}"
for item in actual_dependencies
)
inventory_detail = (
f" Provider inventory reports {len(actual_dependencies)} persisted "
f"dependency record(s): {references}."
)
elif inventory_inspected:
inventory_detail = (
" Provider inventory reports no persisted module-owned dependencies."
)
else:
inventory_detail = " Provider inventory did not inspect this capability."
dependency_actions = tuple(
dict.fromkeys(
item.required_action
for item in actual_dependencies
if item.required_action.strip()
)
)
required_action = (
"Review module-owned configuration and data migration or recovery "
"evidence before apply."
)
if dependency_actions:
required_action = f"{required_action} {' '.join(dependency_actions)}"
impacts.append(
CapabilityChangeImpact(
capability_id=capability_id,
@@ -153,11 +345,11 @@ def capability_change_impacts(
detail=(
f"{capability_id} changes from {previous_state}/{previous_source} "
f"to {desired_state}/{desired_source}{binding_change}; "
f"declared consumers: {dependent_label}."
),
required_action=(
"Review module-owned configuration and data migration or recovery evidence before apply."
f"declared consumers: {dependent_label}.{inventory_detail}"
),
required_action=required_action,
actual_dependencies=actual_dependencies,
inventory_inspected=inventory_inspected,
)
)
return tuple(impacts)
@@ -487,3 +679,73 @@ def _binding_change_label(
if previous_secret_refs != desired_secret_refs:
changes.append("secret-reference binding")
return f" with changed {' and '.join(changes)}" if changes else ""
def _inventory_text(
value: Mapping[str, object],
key: str,
*,
maximum: int,
) -> str:
raw = value.get(key)
if not isinstance(raw, str):
raise ValueError(f"Infrastructure dependency inventory {key} is invalid.")
result = raw.strip()
if not result or len(result) > maximum or any(ord(char) < 32 for char in result):
raise ValueError(f"Infrastructure dependency inventory {key} is invalid.")
return result
def _inventory_string_list(
value: object,
*,
maximum_items: int,
maximum_length: int,
) -> tuple[str, ...]:
if not isinstance(value, list) or len(value) > maximum_items:
raise ValueError("Infrastructure dependency inventory list is invalid.")
items: list[str] = []
for raw in value:
if not isinstance(raw, str):
raise ValueError("Infrastructure dependency inventory list is invalid.")
item = raw.strip()
if (
not item
or len(item) > maximum_length
or any(ord(char) < 32 for char in item)
):
raise ValueError("Infrastructure dependency inventory list is invalid.")
items.append(item)
return tuple(items)
def _inventory_dependency(value: object) -> CapabilityDependency:
if not isinstance(value, Mapping):
raise ValueError("Infrastructure dependency record is invalid.")
state = _inventory_text(value, "state", maximum=40)
if state not in DEPENDENCY_STATES:
raise ValueError("Infrastructure dependency state is invalid.")
raw_metrics = value.get("metrics")
if not isinstance(raw_metrics, Mapping) or len(raw_metrics) > 20:
raise ValueError("Infrastructure dependency metrics are invalid.")
metrics: dict[str, int] = {}
for raw_key, raw_count in raw_metrics.items():
if not isinstance(raw_key, str):
raise ValueError("Infrastructure dependency metric name is invalid.")
key = raw_key.strip()
if not key or len(key) > 80 or any(ord(char) < 32 for char in key):
raise ValueError("Infrastructure dependency metric name is invalid.")
if type(raw_count) is not int or raw_count < 0:
raise ValueError("Infrastructure dependency metric value is invalid.")
metrics[key] = raw_count
return CapabilityDependency(
capability_id=_inventory_text(value, "capability_id", maximum=120),
module_id=_inventory_text(value, "module_id", maximum=120),
dependency_type=_inventory_text(value, "dependency_type", maximum=120),
dependency_ref=_inventory_text(value, "dependency_ref", maximum=240),
state=state,
scope=_inventory_text(value, "scope", maximum=120),
summary=_inventory_text(value, "summary", maximum=1000),
metrics=metrics,
required_action=_inventory_text(value, "required_action", maximum=1000),
)
+129 -2
View File
@@ -18,7 +18,8 @@ import sys
import time
from typing import Iterator, Mapping, Sequence
from urllib.error import URLError
from urllib.request import urlopen
from urllib.parse import urlsplit
from urllib.request import Request, urlopen
from .backup_evidence import (
DEFAULT_MAX_BACKUP_AGE_SECONDS,
@@ -28,6 +29,7 @@ from .backup_evidence import (
)
from .bundle import (
BACKUP_RUNTIME_ENV_KEYS,
BundlePaths,
atomic_write,
bundle_paths,
canonical_json,
@@ -45,7 +47,11 @@ from .bundle import (
service_names,
write_env,
)
from .capabilities import infrastructure_capability_document
from .capabilities import (
InfrastructureDependencyInventory,
infrastructure_capability_document,
infrastructure_dependency_inventory_from_mapping,
)
from .cluster_evidence import collect_kubernetes_evidence
from .distribution import (
MAX_KEYRING_BYTES,
@@ -81,6 +87,7 @@ from .kubernetes import (
write_secret_creation_hint,
)
from .planning import (
MAX_DEPENDENCY_INVENTORY_BYTES,
DeploymentPlan,
build_plan,
release_change_requires_backup,
@@ -152,6 +159,39 @@ def build_parser() -> argparse.ArgumentParser:
default=120.0,
help="Maximum time to wait for the public health endpoint.",
)
apply_parser.add_argument(
"--ops-url",
help=(
"Dependency inventory URL; defaults to "
"<public-url>/api/v1/ops/infrastructure/dependencies."
),
)
apply_parser.add_argument(
"--api-key-env",
default="GOVOPLAN_OPS_API_KEY",
help=(
"Environment variable containing an API key authorized to read "
"Ops dependency inventory."
),
)
collect_inventory = subparsers.add_parser(
"collect-infrastructure-inventory",
help="Collect current module-owned capability dependencies from Ops.",
)
_directory_argument(collect_inventory)
collect_inventory.add_argument(
"--ops-url",
help=(
"Dependency inventory URL; defaults to "
"<public-url>/api/v1/ops/infrastructure/dependencies."
),
)
collect_inventory.add_argument(
"--api-key-env",
default="GOVOPLAN_OPS_API_KEY",
help="Environment variable containing an authorized Ops API key.",
)
status = subparsers.add_parser(
"status", help="Show desired state and current Compose process state."
@@ -425,6 +465,8 @@ def main(argv: Sequence[str] | None = None) -> int:
return _render_or_doctor(args)
if args.command == "apply":
return _apply(args)
if args.command == "collect-infrastructure-inventory":
return _collect_infrastructure_inventory(args)
if args.command == "status":
return _status(args)
if args.command == "verify-release":
@@ -586,6 +628,25 @@ def _apply(args: argparse.Namespace) -> int:
)
secrets = reconcile_runtime_environment(spec, read_env(paths.env))
secrets = _write_bundle(spec, paths, secrets)
preliminary_plan = build_plan(spec, paths, include_host_checks=False)
api_key_env = str(
getattr(args, "api_key_env", "GOVOPLAN_OPS_API_KEY")
).strip()
api_key = os.environ.get(api_key_env, "").strip()
if preliminary_plan.capability_impacts and api_key:
try:
_collect_dependency_inventory(
spec,
paths,
ops_url=getattr(args, "ops_url", None),
api_key=api_key,
)
print("Refreshed infrastructure dependency inventory from Ops.")
except (OSError, ValueError, json.JSONDecodeError) as exc:
print(
f"warning: could not refresh dependency inventory: {exc}",
file=sys.stderr,
)
plan = build_plan(spec, paths, include_host_checks=True)
_write_plan(paths.plan, plan)
effective_errors = [
@@ -613,6 +674,8 @@ def _apply(args: argparse.Namespace) -> int:
if effective_errors:
_print_plan(plan)
raise ValueError("deployment plan is blocked; resolve doctor errors first")
if plan.capability_impacts:
_print_plan(plan)
docker = shutil.which("docker")
if docker is None:
raise ValueError("Docker CLI is required for apply")
@@ -761,6 +824,70 @@ def _apply(args: argparse.Namespace) -> int:
return 0
def _collect_infrastructure_inventory(args: argparse.Namespace) -> int:
paths = bundle_paths(args.directory)
spec = load_spec(paths.spec)
api_key_env = str(args.api_key_env).strip()
api_key = os.environ.get(api_key_env, "").strip()
if not api_key:
raise ValueError(f"{api_key_env} must contain an authorized Ops API key")
inventory = _collect_dependency_inventory(
spec,
paths,
ops_url=args.ops_url,
api_key=api_key,
)
state = "complete" if inventory.complete else "incomplete"
print(
f"Collected {state} provider dependency inventory with "
f"{len(inventory.dependencies)} record(s) at {paths.dependency_inventory}."
)
return 0 if inventory.complete else 1
def _collect_dependency_inventory(
spec: InstallationSpec,
paths: BundlePaths,
*,
ops_url: str | None,
api_key: str,
) -> InfrastructureDependencyInventory:
url = str(ops_url or "").strip() or (
spec.public_url.rstrip("/")
+ "/api/v1/ops/infrastructure/dependencies"
)
_validate_ops_inventory_url(url)
request = Request(
url,
headers={"Accept": "application/json", "X-API-Key": api_key},
)
with urlopen(request, timeout=15) as response: # noqa: S310
_validate_ops_inventory_url(response.geturl())
encoded = response.read(MAX_DEPENDENCY_INVENTORY_BYTES + 1)
if len(encoded) > MAX_DEPENDENCY_INVENTORY_BYTES:
raise ValueError("Ops dependency inventory exceeds its size limit")
value = json.loads(encoded)
inventory = infrastructure_dependency_inventory_from_mapping(value)
if inventory.installation_id != spec.installation_id:
raise ValueError(
"Ops dependency inventory belongs to a different installation"
)
ensure_private_directory(paths.root)
atomic_write(paths.dependency_inventory, canonical_json(value), mode=0o600)
return inventory
def _validate_ops_inventory_url(url: str) -> None:
parsed = urlsplit(url)
if not parsed.hostname or parsed.username or parsed.password or parsed.fragment:
raise ValueError("Ops dependency inventory URL is invalid")
loopback = parsed.hostname in {"localhost", "127.0.0.1", "::1"}
if parsed.scheme != "https" and not (parsed.scheme == "http" and loopback):
raise ValueError(
"Ops dependency inventory URL requires HTTPS except on loopback"
)
def _status(args: argparse.Namespace) -> int:
paths = bundle_paths(args.directory)
spec = load_spec(paths.spec)
@@ -3,6 +3,7 @@
from __future__ import annotations
from dataclasses import asdict, dataclass
from datetime import UTC, datetime
import hashlib
import json
import os
@@ -37,8 +38,10 @@ from .bundle import (
)
from .capabilities import (
CapabilityChangeImpact,
InfrastructureDependencyInventory,
capability_change_impacts,
infrastructure_capability_document,
infrastructure_dependency_inventory_from_mapping,
)
from .distribution import (
MAX_KEYRING_BYTES,
@@ -110,6 +113,9 @@ class DeploymentPlan:
CommandRunner = Callable[[Sequence[str], Path], subprocess.CompletedProcess[str]]
MAX_DEPENDENCY_INVENTORY_BYTES = 2 * 1024 * 1024
DEPENDENCY_INVENTORY_MAX_AGE_SECONDS = 300
DEPENDENCY_INVENTORY_MAX_FUTURE_SECONDS = 60
def build_plan(
@@ -135,9 +141,13 @@ def build_plan(
spec,
read_env(paths.env),
)
dependency_inventory, dependency_inventory_error = (
_read_dependency_inventory(paths.dependency_inventory)
)
capability_impacts = capability_change_impacts(
previous.get("infrastructure_capabilities"),
infrastructure_capabilities,
dependency_inventory=dependency_inventory,
)
actions: list[PlanAction] = []
@@ -215,6 +225,14 @@ def build_plan(
)
for impact in capability_impacts
)
checks.extend(
_dependency_inventory_checks(
spec,
capability_impacts,
dependency_inventory,
dependency_inventory_error,
)
)
if include_host_checks:
checks.extend(host_checks(spec, paths, command_runner=command_runner))
return DeploymentPlan(
@@ -1187,6 +1205,106 @@ def _read_receipt(path: Path) -> Mapping[str, object]:
return value if isinstance(value, dict) else {}
def _read_dependency_inventory(
path: Path,
) -> tuple[InfrastructureDependencyInventory | None, str]:
if not path.exists():
return None, "missing"
try:
value = load_bounded_json(
path,
maximum_bytes=MAX_DEPENDENCY_INVENTORY_BYTES,
)
return infrastructure_dependency_inventory_from_mapping(value), ""
except (DistributionError, ValueError) as exc:
return None, str(exc)
def _dependency_inventory_checks(
spec: InstallationSpec,
impacts: tuple[CapabilityChangeImpact, ...],
inventory: InfrastructureDependencyInventory | None,
inventory_error: str,
) -> tuple[Check, ...]:
if not impacts:
return ()
collect_action = (
"Run govoplan-deploy collect-infrastructure-inventory with an Ops API "
"key, then review the capability impacts before apply."
)
if inventory is None:
if inventory_error == "missing":
message = "Current provider dependency inventory is missing."
check_id = "capability.dependency_inventory.missing"
else:
message = f"Provider dependency inventory is invalid: {inventory_error}"
check_id = "capability.dependency_inventory.invalid"
return (Check(check_id, "error", message, collect_action),)
if inventory.installation_id != spec.installation_id:
return (
Check(
"capability.dependency_inventory.installation",
"error",
"Provider dependency inventory belongs to a different installation.",
collect_action,
),
)
if not inventory.complete:
return (
Check(
"capability.dependency_inventory.incomplete",
"error",
"Provider dependency inventory is incomplete because at least one provider failed.",
"Resolve the provider failure and collect the inventory again.",
),
)
age_seconds = (datetime.now(UTC) - inventory.generated_at).total_seconds()
if age_seconds < -DEPENDENCY_INVENTORY_MAX_FUTURE_SECONDS:
return (
Check(
"capability.dependency_inventory.future",
"error",
"Provider dependency inventory timestamp is in the future.",
"Correct host clock skew and collect the inventory again.",
),
)
if age_seconds > DEPENDENCY_INVENTORY_MAX_AGE_SECONDS:
return (
Check(
"capability.dependency_inventory.stale",
"error",
"Provider dependency inventory is older than five minutes.",
collect_action,
),
)
impacted_ids = {item.capability_id for item in impacts}
missing_ids = sorted(impacted_ids - set(inventory.inspected_capability_ids))
if missing_ids:
return (
Check(
"capability.dependency_inventory.coverage",
"error",
"Provider dependency inventory did not inspect impacted capabilities: "
+ ", ".join(missing_ids)
+ ".",
collect_action,
),
)
matching_dependencies = sum(
len(inventory.dependencies_for(capability_id))
for capability_id in impacted_ids
)
return (
Check(
"capability.dependency_inventory.current",
"ok",
"Current provider inventory inspected every impacted capability and "
f"reported {matching_dependencies} persisted dependency record(s) from "
f"{inventory.provider_count} provider(s).",
),
)
def _memory_bytes() -> int | None:
try:
for line in Path("/proc/meminfo").read_text(encoding="utf-8").splitlines():
@@ -34,6 +34,7 @@ _BUNDLE_FILES = (
"backup-verification.json",
"receipt.json",
"infrastructure-capabilities.json",
"infrastructure-dependency-inventory.json",
)
@@ -1379,6 +1379,13 @@
"rationale": "Operational worker, scheduler, reconciliation, or health endpoint; it is not a direct user surface.",
"repository": "govoplan-notifications"
},
{
"category": "intentionally_headless",
"method": "GET",
"path": "/ops/infrastructure/dependencies",
"rationale": "Authorized host-deployer preflight consumes this provider inventory directly; it is private operational evidence rather than a product page.",
"repository": "govoplan-ops"
},
{
"category": "worker_internal",
"method": "GET",