key-cape/workplans/KEY-WP-0026-packaging-bootstrap-and-credential-handling.md
tegwick 2ab70924a1 chore(consistency): register KEY-WP-0026 [auto]
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01NV9oijZukGyGbRQGGKnK4P

Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 713576@bnt-lap001
Assistant-Session: 384c511d-9bce-4cb8-a676-2aef6c0c8df6
2026-09-08 09:52:42 +02:00

4.5 KiB

id type title domain repo status owner topic_slug created updated state_hub_workstream_id
KEY-WP-0026 workplan Reconcile packaging, bootstrap and migration credential handling infotech key-cape finished claude packaging-bootstrap-and-credential-handling 2026-09-08 2026-09-08 d2b04d59-41b1-531b-8cab-a980328611b4

Closes gap G09. Five separate defects, only loosely related: the dev stack could not start from a clean checkout, the image shipped one binary of five, the publish workflow named a different registry than the one the cluster pulls from, the exporter took a password on argv, and every migration artifact was written world-readable.

Take the bind password off argv

id: KEY-WP-0026-T01
status: done
priority: medium
state_hub_task_id: "510a4603-337f-5ceb-b6b7-b9126d8605f0"

lldap-export took --bind-pw, so the service account password was visible to any local user through ps, and captured by shell history and process accounting. It now prefers KEYCAPE_LLDAP_BIND_PW, accepts --bind-pw-file, and keeps --bind-pw working with a warning — deprecated rather than removed, because existing runbooks use it and silently breaking them would be worse than the exposure for one more cycle.

Conflicting sources are rejected rather than silently ranked: with two supplied, an operator cannot tell which bind was attempted. A password file has its trailing newline trimmed, since editors and heredocs add one and binding with it fails confusingly. Both migration scripts now pass the password by environment.

Stop writing migration artifacts world-readable

id: KEY-WP-0026-T02
status: done
priority: medium
state_hub_task_id: "679e21a1-e37b-574b-bc25-b9fd46bdfd16"

The canonical export, the generated LDIF and the Keycloak realm were all written 0644. None carries credential material, but the snapshot is a directory dump — every username, display name, email and group membership in the estate — and it tended to land in /tmp. All three are 0600 now.

Ship every binary in the image

id: KEY-WP-0026-T03
status: done
priority: medium
state_hub_task_id: "5252a13c-cd5d-5686-a7f5-04587d7d9b1d"

The image packaged keycape alone, so the validator and the three migration binaries needed a Go toolchain on the host — which defeats shipping an image for the cutover work they exist to support. All five are built and copied; the issuer remains the entrypoint and the rest are reachable by overriding it. Verified by building the image and running each binary inside it.

Reconcile the publish target

id: KEY-WP-0026-T04
status: done
priority: medium
state_hub_task_id: "45b8c386-41bd-514c-9247-5eba9663d8fb"

The workflow published to 92.205.130.254:32166/coulomb/key-cape while the cluster runs forgejo.coulomb.social/coulomb/key-cape (KEY-WP-0013). Whether those are one registry behind two names or two registries is not determinable from this repository, which is exactly the problem: a push could not be assumed to have deployed the current source. Now defaults to the recorded Forgejo name and stays overridable through a repository variable.

Unverified, and needs an operator's eye: this repository cannot test that the runner resolves that hostname or that REGISTRY_USER/REGISTRY_TOKEN are valid for it. If the next publish fails, set the REGISTRY repository variable back to the address.

Make the dev stack bootstrappable

id: KEY-WP-0026-T05
status: done
priority: medium
state_hub_task_id: "a750ac2f-cad2-5e7f-a505-2ca6b94f1a5a"

docker-compose.dev.yml mounts config/dev-key.pem and config/authelia/, neither in the checkout — correctly, since one is a private key and the other carries a password hash. scripts/bootstrap-dev.sh generates both locally: an RSA key created under umask 077 rather than chmodded afterwards, so it is never briefly world-readable, plus an Authelia configuration, its OIDC signing key and a user fixture. Everything it writes is git-ignored, and re-running it leaves existing material alone.

The fixture password is published in the script deliberately: a reader can see exactly what it unlocks, which is nothing deployed.

Reconcile the records

id: KEY-WP-0026-T06
status: done
priority: medium
state_hub_task_id: "cc7c86ae-9c78-5422-8f3c-19441ceeb513"

SCOPE.md and G09's status record what is fixed and what is not: the registry change is unverified from here, and a documented external bootstrap remains the route for anything beyond development.