Oikos Week 1: kernel policy, ontology, service contract, topology gen

Adds the Oikos agent-OS kernel: oikos/policy.yaml (risk classes +
approval rules for every homelab/MCP command), oikos/ontology.yaml
(8-domain systems model, typed relationships, node lifecycle), and
OIKOS.md (OODA loop operating brief, linked from AGENTS.md).

Extends inventory.yaml with a stable service contract (doc_page,
config_repo, risk_notes) on all 17 services, and a structured
archaeology: section for the 13 destroyed LXCs (was scattered
comments + a narrative table). Fixes stale drift found in the
process: authentik's backend pointed at a retired LXC (124); core
has run on the VPS since 2026-05-31.

Adds oikos/gen-topology.py, generating infrastructure/topology.md
(Mermaid compute/ingress + storage views) from inventory.yaml.
build_host_files.py now carries state/storage/depends_on into
generated hosts/*.yaml.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
2026-07-05 22:50:34 +02:00
parent 7e8860ab47
commit b230ab5937
34 changed files with 832 additions and 8 deletions

178
oikos/gen-topology.py Normal file
View File

@@ -0,0 +1,178 @@
#!/usr/bin/env python3
"""
Generate infrastructure/topology.md (Mermaid views) from inventory.yaml.
Views:
1. Compute & ingress — hypervisors → guests → services → public URLs
2. Storage — mounts and pools per guest
Run from the repo root:
python3 oikos/gen-topology.py # writes infrastructure/topology.md
python3 oikos/gen-topology.py --check # exit 1 if output would change
Wired into the same regeneration path as mcp/build_host_files.py so the
diagrams never drift from inventory. Edges follow oikos/ontology.yaml
(hosts, provides, routes-to, mounts, stores-on).
"""
from __future__ import annotations
import argparse
import sys
from pathlib import Path
try:
import yaml
except ImportError: # pragma: no cover
print("PyYAML is required: pip install pyyaml", file=sys.stderr)
sys.exit(2)
REPO = Path(__file__).resolve().parent.parent
INVENTORY = REPO / "inventory.yaml"
OUTPUT = REPO / "infrastructure" / "topology.md"
BANNER = (
"<!-- Generated by oikos/gen-topology.py from inventory.yaml. -->\n"
"<!-- Do NOT edit by hand - your changes will be overwritten. -->\n"
)
def node_id(name: str) -> str:
"""Mermaid-safe node id."""
return name.replace("-", "_").replace(".", "_").replace("/", "_").strip("_")
def guest_label(name: str, entry: dict) -> str:
pve = entry.get("pve_id")
role = entry.get("role", "")
tag = f"LXC {pve}" if entry.get("kind") == "lxc" and pve else \
f"VM {pve}" if entry.get("kind") == "vm" and pve else entry.get("kind", "")
ip = entry.get("lan_ip", "")
parts = [name, tag, role, ip]
return "<br/>".join(str(p) for p in parts if p)
def compute_view(inv: dict) -> list[str]:
hosts = inv.get("hosts", {})
services = inv.get("services", {})
lines = ["```mermaid", "flowchart LR"]
hypervisors = {n: e for n, e in hosts.items() if e.get("kind") == "proxmox-host"}
guests = {n: e for n, e in hosts.items() if e.get("kind") in ("lxc", "vm")}
others = {n: e for n, e in hosts.items()
if e.get("kind") in ("workstation", "external")}
for hv in hypervisors:
lines.append(f' subgraph {node_id(hv)}_sub["{hv} (Proxmox)"]')
for g, e in guests.items():
if e.get("host") == hv:
lines.append(f' {node_id(g)}["{guest_label(g, e)}"]')
lines.append(" end")
# guests without a parent hypervisor recorded (e.g. rclone)
for g, e in guests.items():
if e.get("host") not in hypervisors:
lines.append(f' {node_id(g)}["{guest_label(g, e)}"]')
for n, e in others.items():
shape = "([{}])" if e.get("kind") == "workstation" else "[[{}]]"
lines.append(f' {node_id(n)}{shape.format(guest_label(n, e))}')
# ingress: public URL -> backend (routes-to)
for svc, e in sorted(services.items()):
if not isinstance(e, dict):
continue
backend = e.get("backend")
url = e.get("url") or (
f'https://{e["public_host"]}' if e.get("public_host") else None)
if backend and url and backend in hosts:
host = url.removeprefix("https://").removeprefix("http://")
# hypervisors are rendered as subgraphs; point edges at the subgraph id
target = node_id(backend) + ("_sub" if backend in hypervisors else "")
lines.append(
f' {node_id("url_" + svc)}(["{host}"]) -->|routes-to| {target}')
lines.append("```")
return lines
def storage_view(inv: dict) -> list[str]:
hosts = inv.get("hosts", {})
lines = ["```mermaid", "flowchart LR"]
pools: set[str] = set()
edges: list[str] = []
for name, e in hosts.items():
for mount in e.get("mounts", []):
pools.add(mount)
edges.append(f' {node_id(name)}["{name}"] -->|mounts| {node_id(mount)}')
for pool in sorted(pools):
lines.append(f' {node_id(pool)}[("{pool}")]')
lines.extend(sorted(set(edges)))
lines.append("```")
return lines
def archaeology_table(inv: dict) -> list[str]:
arch = inv.get("archaeology", {})
if not arch:
return []
lines = ["| Node | ID | Destroyed | Reason |", "|---|---|---|---|"]
entries = sorted(arch.items(), key=lambda kv: str(kv[1].get("destroyed", "")),
reverse=True)
for name, e in entries:
lines.append(
f'| {name} | {e.get("pve_id", "")} | {e.get("destroyed", "")} '
f'| {e.get("reason", "")} |')
return lines
def render(inv: dict) -> str:
hosts = inv.get("hosts", {})
services = inv.get("services", {})
counts = (
f"{sum(1 for e in hosts.values() if e.get('kind') == 'proxmox-host')} hypervisors, "
f"{sum(1 for e in hosts.values() if e.get('kind') == 'lxc')} LXCs, "
f"{sum(1 for e in hosts.values() if e.get('kind') == 'vm')} VMs, "
f"{sum(1 for e in hosts.values() if e.get('kind') == 'workstation')} workstations, "
f"{len(services)} services"
)
parts = [
BANNER,
"# Topology (generated)\n",
f"Source: [inventory.yaml](../inventory.yaml) — {counts}.",
"Edge semantics: [oikos/ontology.yaml](../oikos/ontology.yaml). "
"Operating model: [OIKOS.md](../OIKOS.md).\n",
"## Compute & ingress\n",
"\n".join(compute_view(inv)) + "\n",
"## Storage (mounts)\n",
"\n".join(storage_view(inv)) + "\n",
]
arch = archaeology_table(inv)
if arch:
parts += ["## Archaeology (destroyed nodes)\n", "\n".join(arch) + "\n"]
return "\n".join(parts)
def main() -> int:
parser = argparse.ArgumentParser()
parser.add_argument("--check", action="store_true",
help="exit 1 if output would change (don't write)")
args = parser.parse_args()
inv = yaml.safe_load(INVENTORY.read_text())
content = render(inv)
existing = OUTPUT.read_text() if OUTPUT.exists() else ""
if existing == content:
return 0
if args.check:
print(f"{OUTPUT.relative_to(REPO)} would change", file=sys.stderr)
return 1
OUTPUT.write_text(content)
print(f"wrote {OUTPUT.relative_to(REPO)}")
return 0
if __name__ == "__main__":
sys.exit(main())