flex-auth/workplans/FLEX-WP-0016-ops-warden-incluster-policy-pin.md
codex 1d90aac30f
All checks were successful
CI Smoke / host-smoke (push) Successful in 0s
CI Smoke / container-smoke (push) Successful in 1s
fix(workplans): adopt ADR-007 derived identifiers for unregistered records
These workplans exist only in the retired local hub. Their random pre-ADR-007
identifiers are refused by C-06 as stale references, so they cannot be
registered. Deriving from the canonical record id takes no identity from
anything: central does not hold them and the old ids die with the cache.

Records central already holds were deliberately left untouched.

Refs CUST-WP-0068-T06

Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 2583210@bnt-lap001
Assistant-Session: f2bff2d5-e9b2-4338-92ca-10282a927006
2026-08-25 20:10:35 +02:00

159 lines
6.8 KiB
Markdown

---
id: FLEX-WP-0016
type: workplan
title: "In-cluster ops-warden policy pin so policy.enabled can flip"
domain: infotech
repo: flex-auth
status: finished
owner: grok
topic_slug: netkingdom
planning_priority: P1
planning_order: 160
depends_on_workplans:
- FLEX-WP-0007
- FLEX-WP-0015
related_workplans:
- WARDEN-WP-0009
created: "2026-08-19"
updated: "2026-08-19"
state_hub_workstream_id: "f29f159c-c79e-5c78-b1e8-569a5b63d231"
---
# FLEX-WP-0016 - In-cluster ops-warden policy pin so policy.enabled can flip
FLEX-WP-0007 is **finished**. Its repo-side artifacts, tunnel smoke, and
vault-backed joint evidence already exist. What it deliberately deferred is
the production `policy.enabled: true` flip.
That flip is not a flex-auth kubectl of FLEX-WP-0007 leftovers. Three facts
now make a new workplan the honest vehicle:
1. FLEX-WP-0015 closed A0 on the two live pins. ops-warden's own sequencing
rule (ADHOC-2026-08-17-T01) was: `policy.enabled` must not flip anywhere
while `/v1/check` still answers unauthenticated callers. That condition
now holds for `flex-auth-user-engine` and `flex-auth-tenant-engine`.
2. Those pins cannot serve ops-warden. Each has an exact
`resource.system` → ServiceAccount binding. A `warden sign` check with
`system: ops-warden` against either pin is 403, not a signing decision.
3. There is no in-cluster ops-warden policy Service. FLEX-WP-0007 smoke used
a workstation runtime on `127.0.0.1:18090` via `flex-auth-coulombcore`.
Example `flex_auth_url` `http://flex-auth.flex-auth.svc.cluster.local:8080`
does not exist.
## Ownership
| Concern | Owner |
| --- | --- |
| Independently rollable in-cluster pin with the ops-warden policy package and production registry | flex-auth |
| Workstation/CoulombCore `flex_auth_url` (tunnel or port-forward) | ops-warden / operator |
| Calling-side identity on `warden sign` (TokenReview or later mTLS) | ops-warden, on its own schedule |
| `policy.enabled: true` in `warden.yaml` | ops-warden operator |
`warden sign` on a laptop is not a Kubernetes ServiceAccount. ADR 0004's
choke point therefore cannot be `enforce` on this pin until ops-warden has a
calling identity. First pin is **warn**. Enforce and the `policy.enabled`
flip wait on that calling side.
## Tasks
```task
id: FLEX-WP-0016-T01
status: done
priority: high
state_hub_task_id: "b2f8052e-3686-593f-9359-dfd08d530a26"
```
**Overlay pin.** Add `values/ops-warden.yaml`: same digest as the A2 pins,
`--registry` / `--policy` for `examples/ops-warden/production_registry_snapshot.json`
and `policy_package.md`, `callerAuth.mode: warn`, binding
`ops-warden=system:serviceaccount:ops-warden:ops-warden`. `consumer.isolated:
true` until there is an in-cluster PEP namespace to admit. Include it in
`tests/stage1.sh`.
Done 2026-08-19: `values/ops-warden.yaml` on digest `sha256:138aa347…`,
warn, isolated, production registry. `tests/stage1.sh` renders it.
```task
id: FLEX-WP-0016-T02
status: done
priority: high
state_hub_task_id: "aa65f534-7401-5231-ae82-ea6e3d09b40c"
```
**Deploy warn.** `helm upgrade --install flex-auth-ops-warden` from the
overlay. Prove `/healthz` and one allow `/v1/check` from an operator
port-forward (isolated NetworkPolicy admits no consumer ingress). Do not
flip `policy.enabled`.
Done 2026-08-19: Helm release `flex-auth-ops-warden` rev 1, Service
`flex-auth-ops-warden.flex-auth.svc.cluster.local:8080`. Port-forward
`:19090` `/healthz` 200; `agt-state-hub-bridge` allow
`decision:49350f1064f674d7`; TTL 999 deny `ttl_out_of_bounds`
`decision:ad1620ffa431efe0`. Unauthenticated calls log
`caller authentication warning` and still return a decision (warn).
user-engine and tenant-engine pins were not moved.
```task
id: FLEX-WP-0016-T03
status: done
priority: medium
state_hub_task_id: "351f502f-f0cf-5a70-86da-10b1fbe39dae"
```
**Handoff for the flip.** Tell ops-warden the Service DNS, digest, warn mode,
and that `policy.py` currently sends no `Authorization` header. They adopt
the calling side; then this pin can enforce; then they set
`policy.enabled: true` with `fail_closed: true`. Flex-auth does not edit
`~/.config/warden/warden.yaml`.
Asked 2026-08-19. Cluster DNS from a warden workstation is not assumed;
they pick tunnel or port-forward.
WARDEN-WP-0031 T04 (2026-08-19): ServiceAccount `ops-warden/ops-warden`
exists; `policy.caller_auth mode: command` mints `--audience flex-auth`
per call; authenticated gate against warn held the warning count at 4
(`decision:f3f7c88f9585582a`). They asked for enforce.
**Enforce live 2026-08-19** Helm rev 2, same digest. Probe via port-forward
`:19090` with `kubectl create token ops-warden -n ops-warden --audience flex-auth`:
(1) Bearer → 200 `decision:49350f1064f674d7`;
(2) no Authorization → **401** `unauthenticated`;
(3) `resource.system=user-engine`**403** `forbidden`.
user-engine and tenant-engine pins were not moved. `policy.enabled` remains
ops-warden's flip.
## Disposition — closed 2026-08-19, not waiting on the flip
This workplan's title says "so `policy.enabled` can flip", and the flip is not
coming. Recording why that closes it rather than stalls it.
ops-warden set `ADR-0006` on 2026-08-19: *enforcement is zone-scoped, never a
global flag*. `policy.enabled` is one repo-wide boolean, and with
`fail_closed: true` it makes flex-auth a hard dependency of every `warden sign`
— including the SSH certificates the ops-bridge tunnels depend on, one of which
now carries the policy call itself. That is a **deliberate deferral of the
control's shape**, not a delay in ops-warden's adoption. The successor is
`zone-engine` `ZONE-WP-0001` (the model) and ops-warden `WARDEN-WP-0032` (the
consumer side); the eventual control will be zone-aware and will not be this
boolean. Nothing in flex-auth's scope will be re-run when it lands.
Everything this workplan owned is delivered and verified:
- T01 overlay pin — `values/ops-warden.yaml`, production registry and policy.
- T02 deployed and proven — allow, deny, `/healthz`.
- T03 handoff — ops-warden adopted the calling side (`WARDEN-WP-0031`), the pin
moved to `enforce`, and enforcement is independently verified by both sides:
Bearer → 200 `decision:f3f7c88f9585582a`, anonymous → **401**, wrong system →
**403**.
**The pin stays `enforce` and is not reverted to `warn`.** An enforcing pin with
no enforcing consumer is not waste: it makes the anonymous path a 401 rather than
a decision, which was the `ADHOC-2026-08-17-T01` condition regardless of whether
ops-warden calls it. Re-verified live 2026-08-19 —
`deploy/flex-auth-ops-warden` carries `--caller-auth-mode enforce` and
`/healthz` is 200 through the managed tunnel
`flex-auth-ops-warden-railiance01` (`:19090`).
The one open flex-auth-side item is a heads-up obligation, not a task: the tunnel
pins the Service ClusterIP `10.43.1.165`. If that Service is recreated the pin
breaks and ops-warden needs telling.