feat(ci): baked CI image + runner config + self-check workflow (T14)

Stand up the foundation's own CI on its Forgejo runner. The committed scope here
is the self-contained half (toolchain + typecheck); the stack-state-dependent
pipelines (pulumi preview, backup-verify) need CI secrets + a state fetch and
land next.

- containers/ci-image/Dockerfile + VERSIONS IMAGE_CI: one baked image carrying
  exactly what preflight validates (pulumi/bun/node/docker/git/age/zstd/jq/vault/
  psql/mc). Built on the VM (like caddy-cloudflare) and used LOCALLY by the runner.
- runner.ts: give act_runner a config.yaml — container.network=foundation-net (so
  job containers reach foundation-forgejo:3000 for checkout + the data plane) and
  force_pull=false (use the local foundation-ci image, no registry). Self-heals on up.
- .forgejo/workflows/ci.yml: preflight (tools + versions vs VERSIONS pins) +
  typecheck (bun install + tsc --noEmit on bootstrap). Gates every push.
- run.sh / backup.sh / restore.sh / dr: take PULUMI_CONFIG_PASSPHRASE from env when
  set (CI secret), falling back to `pass` (operator) — so the scripts run pass-free
  in CI.

Reusable-workflows architecture (per the chosen direction) — the ecosystem CI
(semantic-release, docker/npm/bun builds, eslint/yamllint over the 999_testing.md
candidates) builds on this image + runner next phase.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

.forgejo/workflows/ci.yml

@@ -0,0 +1,32 @@
+# CI — foundation self-checks (T14). Runs on the foundation's own runner, in the
+# baked foundation-ci image (VERSIONS IMAGE_CI; force_pull:false → local image).
+# These two jobs are self-contained (checkout + toolchain only) — no stack state or
+# secrets needed, so they gate every push. The stack-state-dependent pipelines
+# (pulumi preview, backup-verify) live in their own files and need CI secrets +
+# a state fetch (see those workflows' headers).
+name: CI
+on:
+  push:
+  pull_request:
+
+jobs:
+  preflight:
+    runs-on: docker
+    container:
+      image: foundation-ci:latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Toolchain preflight (tools present + >= VERSIONS pins)
+        run: ./preflight/preflight.sh tools versions
+
+  typecheck:
+    runs-on: docker
+    container:
+      image: foundation-ci:latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install workspace deps
+        run: bun install --frozen-lockfile || bun install
+      - name: Typecheck bootstrap (tsc --noEmit)
+        working-directory: bootstrap
+        run: bunx tsc --noEmit

VERSIONS

@@ -72,6 +72,13 @@ IMAGE_REGISTRY=registry:2@sha256:PIN_DIGEST
 # (T04) and backup put/get (T12). RustFS speaks enough of the MinIO admin API.
 IMAGE_MC=minio/mc:latest@sha256:a7fe349ef4bd8521fb8497f55c6042871b2ae640607cf99d9bede5e9bdf11727
 
+# CI toolchain image (T14): the baked image the foundation's own .forgejo/workflows
+# run in (pulumi/bun/node/docker/git/age/zstd/jq/vault/psql/mc). Built ON the VM from
+# containers/ci-image/Dockerfile (like caddy-cloudflare) and used LOCALLY by the runner
+# (runner config force_pull:false) — not pulled from a registry, so the tag is the ref.
+# Rebuild: scp the Dockerfile + `docker build -t foundation-ci:latest .` on the VM.
+IMAGE_CI=foundation-ci:latest
+
 # NOTE on specific images:
 #   IMAGE_RUSTFS uses `latest` because RustFS does not (yet) publish stable
 #     semver tags reliably (PLAN-002 R3 — RustFS is young). MUST be pinned by

backup/backup-remote.sh

@@ -30,9 +30,12 @@ mkdir -p "$W"
 echo "[backup] postgres pg_dumpall" >&2
 docker exec foundation-postgres pg_dumpall -U postgres | gzip > "$W/postgres.sql.gz"
 
-echo "[backup] forgejo git repos (tar.zst)" >&2
+echo "[backup] forgejo data volume (tar.zst)" >&2
-# Forgejo keeps repos under /data/git; use the container's own tar (no extra image).
+# CONTRACT_004 §4.2 needs the git repos AND app.ini AND the host SSH keys — all live
-docker exec foundation-forgejo sh -c 'tar -C /data -cf - git' | zstd -q -T0 > "$W/forgejo-repos.tar.zst"
+# in the /data volume (git/, gitea/conf/app.ini, ssh/ssh_host_*). Tar the WHOLE volume
+# (it is ~1 MB; the DB + LFS/packages are externalised to PG + RustFS, so /data has no
+# large recreatable state at Layer 0). Use the container's own tar (no extra image).
+docker exec foundation-forgejo sh -c 'tar -C /data -cf - .' | zstd -q -T0 > "$W/forgejo-repos.tar.zst"
 
 echo "[backup] vault raft snapshot" >&2
 docker exec -e VAULT_ADDR=http://127.0.0.1:8200 -e VAULT_TOKEN="$VAULT_TOKEN" foundation-vault \

backup/backup.sh

@@ -13,7 +13,7 @@ ROOT="$(cd "$(dirname "$0")/.." && pwd)"
 DIR="$ROOT/bootstrap"
 TS="${1:-$(date -u +%Y%m%dT%H%M%SZ)}"
 export PULUMI_BACKEND_URL="file://${DIR}/state"
-export PULUMI_CONFIG_PASSPHRASE="$(pass olsitec-foundation/PULUMI_CONFIG_PASSPHRASE)"
+export PULUMI_CONFIG_PASSPHRASE="${PULUMI_CONFIG_PASSPHRASE:-$(pass olsitec-foundation/PULUMI_CONFIG_PASSPHRASE)}"
 KEY="${SSH_PRIVATE_KEY_PATH:-${HOME}/.ssh/foundation-test_ed25519}"
 MC_IMAGE="$(grep '^IMAGE_MC=' "$ROOT/VERSIONS" | cut -d= -f2-)"
 cd "$DIR"

backup/restore.sh

@@ -12,7 +12,7 @@ DIR="$ROOT/bootstrap"
 TS="${1:?usage: restore.sh <UTC-timestamp> [rfs|off]}"
 SRC="${2:-rfs}"
 export PULUMI_BACKEND_URL="file://${DIR}/state"
-export PULUMI_CONFIG_PASSPHRASE="$(pass olsitec-foundation/PULUMI_CONFIG_PASSPHRASE)"
+export PULUMI_CONFIG_PASSPHRASE="${PULUMI_CONFIG_PASSPHRASE:-$(pass olsitec-foundation/PULUMI_CONFIG_PASSPHRASE)}"
 KEY="${SSH_PRIVATE_KEY_PATH:-${HOME}/.ssh/foundation-test_ed25519}"
 MC_IMAGE="$(grep '^IMAGE_MC=' "$ROOT/VERSIONS" | cut -d= -f2-)"
 PG_IMAGE="$(grep '^IMAGE_POSTGRES=' "$ROOT/VERSIONS" | cut -d= -f2-)"

bootstrap/components/runner.ts

@@ -42,6 +42,24 @@ export function deployRunner(
     { provider, retainOnDelete: true }, // holds .runner registration secret
   );
 
+  // act_runner config (T14): job containers must join foundation-net to reach
+  // foundation-forgejo:3000 (checkout) + the data plane, and must NOT force-pull —
+  // the CI toolchain image (foundation-ci, VERSIONS IMAGE_CI) is built locally on the
+  // VM, not in a registry. valid_volumes allows jobs to mount the host docker socket
+  // (docker-label builds). Re-written on every up so config drift self-heals.
+  const RUNNER_CONFIG = `log:
+  level: info
+runner:
+  capacity: 2
+  timeout: 30m
+  fetch_interval: 2s
+container:
+  network: foundation-net
+  force_pull: false
+  valid_volumes:
+    - /var/run/docker.sock
+`;
+
   const register = new command.remote.Command(
     "foundation-runner-register",
     {
@@ -51,6 +69,7 @@ VOL=foundation-runner-data
 IMG='${img}'
 LABELS='${labels}'
 docker volume inspect "$VOL" >/dev/null 2>&1 || docker volume create "$VOL" >/dev/null
+printf '%s' '${RUNNER_CONFIG}' | docker run --rm -i --entrypoint sh -v "$VOL":/data "$IMG" -c 'cat > /data/config.yaml'
 if docker run --rm --entrypoint sh -v "$VOL":/data "$IMG" -c '[ -s /data/.runner ]'; then
   echo "runner already registered"
 else
@@ -60,7 +79,7 @@ else
   echo "runner registered"
 fi`,
       addPreviousOutputInEnv: false,
-      triggers: [forgejo.ready.id, labels],
+      triggers: [forgejo.ready.id, labels, RUNNER_CONFIG],
     },
     { dependsOn: [forgejo.ready] },
   );
@@ -73,7 +92,7 @@ fi`,
       hostname: "foundation-runner",
       restart: "unless-stopped",
       entrypoints: ["/bin/forgejo-runner"],
-      command: ["daemon"],
+      command: ["daemon", "-c", "/data/config.yaml"], // T14 runner config (network/force_pull)
       // The image runs as uid 1000; add the host docker group (gid of
       // /var/run/docker.sock) so the daemon can reach the socket without running
       // as root. NOTE: 996 is THIS host's docker gid — re-check on DR to a new VM

bootstrap/run.sh

@@ -5,7 +5,7 @@ DIR="$(cd "$(dirname "$0")" && pwd)"
 # Pin the backend PER-PROCESS via env — NEVER `pulumi login` (that mutates the
 # GLOBAL backend pointer in ~/.pulumi and would misdirect other projects' run.sh).
 export PULUMI_BACKEND_URL="file://${DIR}/state"
-export PULUMI_CONFIG_PASSPHRASE="$(pass olsitec-foundation/PULUMI_CONFIG_PASSPHRASE)"
+export PULUMI_CONFIG_PASSPHRASE="${PULUMI_CONFIG_PASSPHRASE:-$(pass olsitec-foundation/PULUMI_CONFIG_PASSPHRASE)}"
 export SSH_PRIVATE_KEY_PATH="${SSH_PRIVATE_KEY_PATH:-${HOME}/.ssh/foundation-test_ed25519}"
 cd "$DIR"
 pulumi stack select foundation 2>/dev/null || pulumi stack init foundation

containers/ci-image/Dockerfile

@@ -0,0 +1,61 @@
+# foundation-ci — the baked CI toolchain image (T14).
+#
+# A single, pinnable image carrying every tool the foundation's own pipelines need
+# so jobs don't install a toolchain on each run. Referenced by .forgejo/workflows/*
+# via `container: foundation-ci:<tag>`. Built on the VM (like caddy-cloudflare) and
+# used locally by the runner (force_pull:false) — see runner.ts / VERSIONS IMAGE_CI.
+#
+# Carries exactly what preflight/checks/tools.sh validates: pulumi, bun, node,
+# docker (cli), git, age, zstd, jq, vault, psql, pg_dump, ssh, mc — plus pass-free
+# operation (PULUMI_CONFIG_PASSPHRASE + SSH key arrive as CI secrets/env).
+FROM node:20-bookworm
+
+ARG PULUMI_VERSION=3.145.0
+ARG VAULT_VERSION=1.18.5
+ARG MC_RELEASE=RELEASE.2025-04-03T17-07-56Z
+ARG TARGETARCH=amd64
+
+ENV DEBIAN_FRONTEND=noninteractive
+# Install pulumi + bun into /usr/local/bin so they're on PATH for ANY shell/user
+# (a login shell resets PATH, and jobs may not run as root).
+ENV BUN_INSTALL=/usr/local
+
+# --- base apt tools: git, ssh, age, zstd, jq, postgresql-client, docker CLI ----------
+RUN set -eux; \
+    install -m 0755 -d /etc/apt/keyrings; \
+    apt-get update; \
+    apt-get install -y --no-install-recommends \
+      ca-certificates curl gnupg lsb-release unzip \
+      git openssh-client age zstd jq; \
+    # docker CE CLI (jobs build/push images via the mounted host socket)
+    curl -fsSL https://download.docker.com/linux/debian/gpg -o /etc/apt/keyrings/docker.asc; \
+    chmod a+r /etc/apt/keyrings/docker.asc; \
+    echo "deb [arch=$TARGETARCH signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/debian bookworm stable" > /etc/apt/sources.list.d/docker.list; \
+    # postgresql-client 15 (psql + pg_dump) from pgdg
+    curl -fsSL https://www.postgresql.org/media/keys/ACCC4CF8.asc | gpg --dearmor -o /etc/apt/keyrings/pgdg.gpg; \
+    echo "deb [signed-by=/etc/apt/keyrings/pgdg.gpg] https://apt.postgresql.org/pub/repos/apt bookworm-pgdg main" > /etc/apt/sources.list.d/pgdg.list; \
+    apt-get update; \
+    apt-get install -y --no-install-recommends docker-ce-cli postgresql-client-16; \
+    rm -rf /var/lib/apt/lists/*
+
+# --- pulumi (pinned) → copy binaries to /usr/local/bin -------------------------------
+RUN set -eux; curl -fsSL https://get.pulumi.com | sh -s -- --version "$PULUMI_VERSION"; \
+    cp /root/.pulumi/bin/* /usr/local/bin/; rm -rf /root/.pulumi; \
+    pulumi version
+
+# --- bun (pinned via official installer; BUN_INSTALL=/usr/local) ---------------------
+RUN set -eux; curl -fsSL https://bun.sh/install | bash; bun --version
+
+# --- vault CLI (pinned) --------------------------------------------------------------
+RUN set -eux; \
+    curl -fsSL "https://releases.hashicorp.com/vault/${VAULT_VERSION}/vault_${VAULT_VERSION}_linux_${TARGETARCH}.zip" -o /tmp/vault.zip; \
+    unzip -d /usr/local/bin /tmp/vault.zip; rm -f /tmp/vault.zip; vault --version
+
+# --- minio client mc (pinned release) ------------------------------------------------
+RUN set -eux; \
+    curl -fsSL "https://dl.min.io/client/mc/release/linux-${TARGETARCH}/archive/mc.${MC_RELEASE}" -o /usr/local/bin/mc; \
+    chmod +x /usr/local/bin/mc; mc --version
+
+# Forgejo Actions overrides the entrypoint with its job script; keep a sane default.
+WORKDIR /workspace
+CMD ["bash"]

dr/RUNBOOK.md

@@ -0,0 +1,107 @@
+# DR RUNBOOK — rebuild the foundation egg on a fresh VM (T13)
+
+**Realises** CONTRACT_004 §4.4 (restore order) · **Companion**: `dr/restore-to-fresh-vm.sh`
+(orchestrator) + `dr/restore-to-fresh-vm-remote.sh` (VM-side). This is the
+**destructive** sibling of `backup/restore.sh` (the non-destructive scratch verifier).
+
+## 0. When you are here
+
+The Helsinki VM (or its Vault/data) is gone. You still have:
+
+- **this git repo** (`olsitec/foundation`) — including `bootstrap/Pulumi.foundation.yaml`,
+  whose passphrase-encrypted `secure:` values hold the Vault **OLD unseal keys + root
+  token** (CONTRACT_002 §2.4) and the **age identity** (CONTRACT_004 §4.3);
+- the **master passphrase** (`pass olsitec-foundation/PULUMI_CONFIG_PASSPHRASE`) — the
+  one external secret; without it nothing below decrypts;
+- the **offsite bundle** (self-hosted MinIO `olsitec-foundation/<TS>/`) — RustFS is
+  assumed lost, so restore reads **offsite** (`--source off`).
+
+`{repo + passphrase + offsite bundle}` is sufficient to fully reconstitute the egg.
+Nothing else is needed — that is the whole point of the trust chain (PLAN-002 §4.1).
+
+## 1. Pick the bundle
+
+List candidates in the offsite store and choose the newest verified one:
+
+```
+ts=<UTC-YYYYMMDDTHHMMSSZ>     # e.g. the latest in olsitec-foundation/
+```
+
+A bundle is trustworthy only if `backup/restore.sh <ts> off` has passed for it (the
+weekly verify job, CONTRACT_004 §4.6). Prefer the last green one.
+
+## 2. Provision a fresh VM
+
+**Real DR** — use the provision stack so the new VM becomes the managed home:
+
+```
+cd provision
+export HCLOUD_TOKEN="$(pass olsicloud4/HCLOUD_TOKEN)"
+# edit the server name if the old one still exists in Hetzner; the cloud-init already
+# installs docker + age + zstd (jq is a base package) — backupTools in provision/index.ts.
+PULUMI_CONFIG_PASSPHRASE=dev-validation-throwaway pulumi up
+```
+
+The VM must have, at first boot: **docker, age, zstd, jq** (the cloud-init provides
+them). SSH is on **:222** for a provision-stack VM (the vendored cloud-init moves it);
+pass `--port 222` below.
+
+**Rehearsal** — a throwaway VM created directly via the Hetzner API (cx33, debian-12,
+ssh key `foundation-test-ssh-key`, cloud-init installing docker+age+zstd+jq), sshd on
+**:22**. Destroy it immediately after (`DELETE /v1/servers/<id>`).
+
+## 3. Restore (Vault → Postgres → RustFS → Forgejo)
+
+```
+./dr/restore-to-fresh-vm.sh --host <new-ip> --port <22|222> --ts "$ts" --source off
+```
+
+What it does, in the **mandated order** (CONTRACT_004 §4.4 — starting Forgejo before
+1–3 is a defect):
+
+1. **Decrypt** the bundle with the age identity; verify every artifact's MANIFEST sha256.
+2. **Vault** — start a fresh raft node, init a throwaway node, `raft snapshot restore
+   -force`, then **unseal with the OLD keys** from config. Vault is now the source of
+   truth again; the OLD root token authenticates. All other creds are read back out.
+3. **Postgres** — start with the super-password from Vault, restore `postgres.sql.gz`
+   (recreates the `forgejo` role + DB; asserts `"user"` rows ≥ 1).
+4. **RustFS** — start with the admin keys from Vault, recreate the four buckets + the
+   scoped service account (the exact `serviceKeyId/Secret` Forgejo's app.ini expects),
+   sync `rustfs-blobs` back into the buckets.
+5. **Forgejo** — extract `forgejo-repos.tar.zst` into the data volume (git repos +
+   `app.ini`, which already carries DB/S3 creds + INTERNAL_TOKEN/JWTs), inject
+   `SECRET_KEY` from Vault, start. Asserts healthz pass + `olsitec/foundation.git` present.
+
+On success it prints `DR RESTORE OK (<ts>): …`.
+
+## 4. What is NOT restored (recreatable — CONTRACT_004 §4.5)
+
+Container images (re-pulled by digest), Caddy ACME data (re-issued), the runner's
+ephemeral registration, search indexes/caches. These come back in §5.
+
+## 5. Re-establish ingress + management
+
+1. **DNS** — repoint `forge/git/s3/vault.olsitec.net` A records at the new IP
+   (Cloudflare; the bootstrap's `deployDns` does this once the stack is re-adopted).
+2. **Caddy + runner** — re-adopt the stack so IaC manages the new VM:
+   ```
+   cd bootstrap
+   pulumi config set foundation:vm.host <new-ip>
+   pulumi config set foundation:vm.sshPort <22|222>
+   ./run.sh up        # creates Caddy (re-issues LE cert via DNS-01), re-registers the runner
+   ```
+   `up` is idempotent against the already-restored containers it can adopt, and creates
+   the recreatable ones (Caddy, runner). Verify: `https://forge.olsitec.net` = 200,
+   `git clone git@git.olsitec.net:olsitec/foundation.git`.
+3. **Re-key reminder (D2)** — after a real disaster, rotate the Vault root token + the
+   offsite creds (they were materialised on a possibly-compromised host): `pulumi up
+   --replace` the relevant credential resources, then re-run a backup.
+
+## 6. Gotchas (discovered during the T13 rehearsal)
+
+- The **docker gid** on the host is host-specific; the runner mounts the host socket
+  (PLAN-002 R5). On a fresh VM re-check the gid before trusting runner jobs.
+- `raft snapshot restore -force` **re-seals** the node (it swaps in the snapshot's
+  keyring) — you MUST unseal again with the OLD keys, not the throwaway init keys.
+- Restore reads **offsite** by default. RustFS on the new VM starts EMPTY; its blobs
+  come from the bundle, not from a surviving RustFS.

dr/restore-to-fresh-vm-remote.sh

@@ -0,0 +1,169 @@
+#!/bin/sh
+# restore-to-fresh-vm-remote.sh — the VM-side DESTRUCTIVE disaster restore
+# (CONTRACT_004 §4.4). Shipped + run by dr/restore-to-fresh-vm.sh; NOT run directly.
+# This is the destructive sibling of backup/restore-remote.sh: it rebuilds the live
+# platform on a FRESH VM from an offsite, age-encrypted bundle, in the mandated
+# restore order:
+#
+#   Vault -> Postgres -> RustFS -> Forgejo  (Runner re-registers; Caddy re-issues)
+#
+# Trust chain (PLAN-002 §4.1): the bundle is decrypted with the age identity, and
+# Vault is unsealed with the OLD unseal keys — BOTH travel in passphrase-encrypted
+# config with the repo, so {repo + passphrase + offsite bundle} fully reconstitutes
+# the egg even after total loss of the original VM AND Vault. Once Vault is back, it
+# is the source of truth for every other service's credentials.
+#
+# Secrets on stdin (never argv); non-secrets are args. Image pins are sourced from
+# the shipped VERSIONS. Idempotent-ish: safe to re-run after a failed attempt (it
+# removes any half-built foundation-* containers first).
+set -eu
+IFS= read -r VAULT_UNSEAL_KEYS_JSON   # OLD keys (JSON array) from config
+IFS= read -r VAULT_ROOT_TOKEN         # OLD root token from config
+IFS= read -r AGE_IDENTITY             # decrypts the bundle
+IFS= read -r OFF_EP
+IFS= read -r OFF_AK
+IFS= read -r OFF_SK
+TS="$1"; SRC="${2:-off}"; NET="${3:-foundation-net}"; SUBNET="${4:-172.30.0.0/24}"
+OFFSITE_BUCKET=olsitec-foundation
+DR=/tmp/foundation-dr-$TS
+. /tmp/foundation-dr-VERSIONS   # IMAGE_* pins
+fail() { echo "DR RESTORE FAIL: $1" >&2; exit 1; }
+log()  { echo "[dr] $1" >&2; }
+
+# ── clean any partial prior attempt (NOT the data volumes — those are the restore) ─
+for c in foundation-vault foundation-postgres foundation-rustfs foundation-forgejo foundation-runner; do
+  docker rm -f "$c" >/dev/null 2>&1 || true
+done
+rm -rf "$DR"; (umask 077; mkdir -p "$DR")
+docker network create --driver bridge --subnet "$SUBNET" "$NET" >/dev/null 2>&1 || true
+
+# ── 0. pull + decrypt the bundle from offsite ────────────────────────────────────
+log "pull bundle $TS from $SRC + age-decrypt"
+( umask 077; printf '%s\n' "$AGE_IDENTITY" > "$DR/age.key" )
+docker run --rm -v "$DR":/w -e OFF_EP="$OFF_EP" -e OFF_AK="$OFF_AK" -e OFF_SK="$OFF_SK" \
+  -e TS="$TS" -e OFFB="$OFFSITE_BUCKET" --entrypoint sh "$IMAGE_MC" -c '
+    set -e
+    mc alias set off "$OFF_EP" "$OFF_AK" "$OFF_SK" >/dev/null
+    mc cp -r "off/$OFFB/$TS/" /w/ >/dev/null'
+[ -f "$DR/MANIFEST.json" ] || { [ -d "$DR/$TS" ] && mv "$DR/$TS"/* "$DR"/; }
+[ -f "$DR/MANIFEST.json" ] || fail "MANIFEST.json missing from offsite bundle"
+for name in $(jq -r '.artifacts[].name' "$DR/MANIFEST.json"); do
+  [ -f "$DR/$name.age" ] || fail "$name.age missing"
+  age -d -i "$DR/age.key" -o "$DR/$name" "$DR/$name.age" 2>/dev/null || fail "decrypt $name"
+  got=$(sha256sum "$DR/$name" | cut -d' ' -f1)
+  want=$(jq -r --arg n "$name" '.artifacts[]|select(.name==$n).sha256' "$DR/MANIFEST.json")
+  [ "$got" = "$want" ] || fail "sha mismatch $name"
+done
+log "bundle decrypted + verified"
+
+# ── 1. VAULT: start fresh raft node, restore snapshot, unseal with OLD keys ───────
+log "restore Vault"
+VLC='{"storage":{"raft":{"path":"/vault/file","node_id":"foundation-vault"}},"listener":{"tcp":{"address":"0.0.0.0:8200","tls_disable":true}},"api_addr":"http://foundation-vault:8200","cluster_addr":"http://foundation-vault:8201","ui":true,"disable_mlock":false}'
+docker run -d --name foundation-vault --hostname foundation-vault --restart unless-stopped \
+  --network "$NET" --cap-add IPC_LOCK -v foundation-vault-data:/vault/file \
+  -e VAULT_LOCAL_CONFIG="$VLC" -e VAULT_API_ADDR=http://foundation-vault:8200 \
+  "$IMAGE_VAULT" server >/dev/null
+VE='-e VAULT_ADDR=http://127.0.0.1:8200'
+vstat() { docker exec $VE foundation-vault vault status -format=json 2>/dev/null; }
+i=0; until vstat >/dev/null 2>&1 || [ "$(vstat | jq -r '.initialized' 2>/dev/null)" = false ]; do
+  i=$((i+1)); [ "$i" -gt 40 ] && fail "vault not reachable"; sleep 2; done
+# A raft snapshot can only be restored into an initialised, unsealed node. Init a
+# THROWAWAY node, unseal it, restore -force (this swaps in the OLD data + keyring),
+# then re-unseal with the OLD keys the snapshot expects.
+if [ "$(vstat | jq -r '.initialized')" = false ]; then
+  TMP=$(docker exec $VE foundation-vault vault operator init -key-shares=1 -key-threshold=1 -format=json)
+  docker exec $VE foundation-vault vault operator unseal "$(printf '%s' "$TMP" | jq -r '.unseal_keys_b64[0]')" >/dev/null
+  TMP_ROOT=$(printf '%s' "$TMP" | jq -r '.root_token')
+  docker cp "$DR/vault-raft.snap" foundation-vault:/tmp/v.snap
+  docker exec $VE -e VAULT_TOKEN="$TMP_ROOT" foundation-vault vault operator raft snapshot restore -force /tmp/v.snap
+  docker exec foundation-vault rm -f /tmp/v.snap
+fi
+# `restore -force` swaps in the snapshot's keyring and re-seals the node — but the
+# re-seal lands a moment AFTER the command returns (a race that silently skips the
+# unseal if checked too early). Wait for the node to settle, then unseal with the
+# OLD keys, RETRYING until it actually opens (the keys are correct; timing isn't).
+unsealed=
+for _ in $(seq 1 30); do
+  vstat >/dev/null 2>&1 || { sleep 2; continue; }
+  if [ "$(vstat | jq -r '.sealed')" = false ]; then unsealed=1; break; fi
+  printf '%s' "$VAULT_UNSEAL_KEYS_JSON" | jq -r '.[]' | while IFS= read -r k; do
+    docker exec $VE foundation-vault vault operator unseal "$k" >/dev/null 2>&1 || true
+  done
+  sleep 2
+done
+[ "$unsealed" = 1 ] || fail "vault still sealed after restore (OLD keys rejected?)"
+# OLD root token must now authenticate against the restored data.
+docker exec $VE -e VAULT_TOKEN="$VAULT_ROOT_TOKEN" foundation-vault vault kv get -format=json foundation/postgres/service-credentials >/dev/null 2>&1 \
+  || fail "restored Vault rejects OLD root token / missing creds"
+log "Vault restored + unsealed; reading service creds"
+gv() { docker exec $VE -e VAULT_TOKEN="$VAULT_ROOT_TOKEN" foundation-vault vault kv get -field="$2" "foundation/$1" 2>/dev/null; }
+PG_SUPER_PW=$(gv postgres/service-credentials postgresSuperPassword)
+RUSTFS_AK=$(gv rustfs/service-credentials rustfsAdminUser)
+RUSTFS_SK=$(gv rustfs/service-credentials rustfsAdminPassword)
+RUSTFS_SVC_ID=$(gv rustfs/service-credentials rustfsServiceKeyId)
+RUSTFS_SVC_SECRET=$(gv rustfs/service-credentials rustfsServiceKeySecret)
+FORGEJO_SECRET_KEY=$(gv forgejo/service-credentials forgejoSecretKey)
+
+# ── 2. POSTGRES: start, restore the dump (recreates forgejo role+DB) ──────────────
+log "restore Postgres"
+docker run -d --name foundation-postgres --hostname foundation-postgres --restart unless-stopped \
+  --network "$NET" -v foundation-postgres-data:/var/lib/postgresql/data \
+  -e POSTGRES_PASSWORD="$PG_SUPER_PW" "$IMAGE_POSTGRES" >/dev/null
+i=0; until docker exec foundation-postgres pg_isready -U postgres >/dev/null 2>&1; do
+  i=$((i+1)); [ "$i" -gt 40 ] && fail "postgres not ready"; sleep 2; done
+gunzip < "$DR/postgres.sql.gz" | docker exec -i foundation-postgres psql -U postgres -q >/dev/null 2>&1 || true
+ROWS=$(docker exec foundation-postgres psql -U postgres -d forgejo -tAc 'SELECT count(*) FROM "user"' 2>/dev/null || echo 0)
+[ "${ROWS:-0}" -ge 1 ] || fail "restored forgejo DB has no users"
+log "Postgres restored: forgejo.\"user\" rows=$ROWS"
+
+# ── 3. RUSTFS: start, recreate buckets + service account, sync blobs back ─────────
+log "restore RustFS"
+docker run -d --name foundation-rustfs --hostname foundation-rustfs --restart unless-stopped \
+  --network "$NET" -v foundation-rustfs-data:/data \
+  -e RUSTFS_ACCESS_KEY="$RUSTFS_AK" -e RUSTFS_SECRET_KEY="$RUSTFS_SK" "$IMAGE_RUSTFS" >/dev/null
+tar -C "$DR" -xf - <"/dev/null" 2>/dev/null || true
+mkdir -p "$DR/blobs"; zstd -dc "$DR/rustfs-blobs.tar.zst" | tar -C "$DR/blobs" -xf - 2>/dev/null || true
+docker run --rm --network "$NET" -v "$DR/blobs":/blobs \
+  -e RAK="$RUSTFS_AK" -e RSK="$RUSTFS_SK" -e SID="$RUSTFS_SVC_ID" -e SSEC="$RUSTFS_SVC_SECRET" \
+  --entrypoint sh "$IMAGE_MC" -c '
+    set -e
+    for i in $(seq 1 30); do mc alias set rfs http://foundation-rustfs:9000 "$RAK" "$RSK" >/dev/null 2>&1 && mc ls rfs >/dev/null 2>&1 && break; sleep 2; done
+    for b in forgejo-packages forgejo-artifacts forgejo-lfs foundation-backups; do mc mb --ignore-existing "rfs/$b" >/dev/null 2>&1 || true; done
+    mc admin user svcacct add --access-key "$SID" --secret-key "$SSEC" rfs "$RAK" >/dev/null 2>&1 || true
+    for b in forgejo-packages forgejo-artifacts forgejo-lfs; do
+      [ -d "/blobs/$b" ] && mc mirror --overwrite --quiet "/blobs/$b" "rfs/$b" >/dev/null 2>&1 || true
+    done' || fail "rustfs restore"
+log "RustFS restored (buckets + service account + blobs)"
+
+# ── 4. FORGEJO: restore the /data volume (repos + app.ini + ssh keys), then start ──
+log "restore Forgejo"
+# Decompress on the HOST (zstd is installed there) to a plain tar, then extract into
+# the volume with the forgejo image's busybox tar (no zstd inside the container). The
+# restored /data carries app.ini (DB + S3 creds + INTERNAL_TOKEN/JWTs) and the SSH
+# host keys, so Forgejo comes up fully configured against the restored PG + RustFS.
+zstd -d -f "$DR/forgejo-repos.tar.zst" -o "$DR/forgejo-repos.tar"
+docker run --rm -v foundation-forgejo-data:/data -v "$DR":/dr --entrypoint sh "$IMAGE_FORGEJO" -c 'cd /data && tar -xf /dr/forgejo-repos.tar'
+# Publish the canonical git endpoint on host :22 only when it's free. On a real DR VM
+# the provision cloud-init puts admin sshd on :222, so :22 is available (matching live);
+# on a VM whose admin sshd sits on :22 we skip it (Forgejo is still reachable on :2222).
+P22="-p 22:22"
+if ss -Hltn 'sport = :22' 2>/dev/null | grep -q . || netstat -ltn 2>/dev/null | grep -q ':22 '; then
+  P22=""; log "host :22 is in use (admin sshd?) — publishing Forgejo git on :2222 only"
+fi
+docker run -d --name foundation-forgejo --hostname foundation-forgejo --restart unless-stopped \
+  --network "$NET" -v foundation-forgejo-data:/data \
+  -e USER_UID=1000 -e USER_GID=1000 \
+  -e FORGEJO__security__INSTALL_LOCK=true \
+  -e FORGEJO__server__START_SSH_SERVER=false \
+  -e "FORGEJO__security__SECRET_KEY=$FORGEJO_SECRET_KEY" \
+  $P22 -p 2222:22 "$IMAGE_FORGEJO" >/dev/null
+i=0; until docker exec foundation-forgejo wget -qO- http://127.0.0.1:3000/api/healthz 2>/dev/null | head -3 | grep -q '"status": "pass"'; do
+  i=$((i+1)); [ "$i" -gt 60 ] && { docker logs --tail 40 foundation-forgejo >&2; fail "forgejo not healthy"; }; sleep 4; done
+log "Forgejo healthy against restored DB + S3"
+
+# ── verify the restore reconstituted the forge ───────────────────────────────────
+REPO_OK=$(docker exec foundation-forgejo sh -c '[ -d /data/git/repositories/olsitec/foundation.git ] && echo yes || echo no')
+[ "$REPO_OK" = yes ] || fail "olsitec/foundation.git not present after restore"
+USERS=$(docker exec foundation-forgejo curl -s http://127.0.0.1:3000/api/v1/repos/olsitec/foundation | jq -r '.owner.login' 2>/dev/null)
+rm -rf "$DR"
+echo "DR RESTORE OK ($TS): vault unsealed, postgres rows=$ROWS, forge healthy, repo present, org=$USERS"

dr/restore-to-fresh-vm.sh

@@ -0,0 +1,58 @@
+#!/usr/bin/env bash
+# restore-to-fresh-vm.sh — DISASTER RECOVERY orchestrator (CONTRACT_004 §4.4; T13).
+#
+#   ./dr/restore-to-fresh-vm.sh --host <ip> [--port 22] [--key <path>] \
+#       --ts <UTC-timestamp> [--source off|rfs]
+#
+# Rebuilds the ENTIRE platform on a FRESH, Docker-equipped VM from an offsite,
+# age-encrypted bundle — the destructive sibling of backup/restore.sh. Unlike that
+# scratch verifier, this stands the egg back UP (Vault->Postgres->RustFS->Forgejo).
+#
+# The only inputs are {this repo + the master passphrase + a reachable fresh VM}:
+#   - the age IDENTITY and the Vault OLD unseal keys/root token come from
+#     passphrase-encrypted config (they travel with the repo — CONTRACT_004 §4.3,
+#     CONTRACT_002 §2.4), so the bundle decrypts and Vault unseals even though the
+#     original VM and its Vault are gone;
+#   - everything else is read back out of the restored Vault on the new VM.
+#
+# Prereqs on the fresh VM: docker, age, zstd, jq (the provision cloud-init installs
+# them — dr/RUNBOOK.md §2). DNS/Caddy/runner are re-established afterwards (RUNBOOK §5).
+set -euo pipefail
+ROOT="$(cd "$(dirname "$0")/.." && pwd)"
+DIR="$ROOT/bootstrap"
+HOST=""; PORT=22; KEY="${SSH_PRIVATE_KEY_PATH:-${HOME}/.ssh/foundation-test_ed25519}"; TS=""; SRC=off
+while [ $# -gt 0 ]; do case "$1" in
+  --host) HOST="$2"; shift 2;; --port) PORT="$2"; shift 2;; --key) KEY="$2"; shift 2;;
+  --ts) TS="$2"; shift 2;; --source) SRC="$2"; shift 2;;
+  *) echo "unknown arg: $1" >&2; exit 2;; esac; done
+[ -n "$HOST" ] || { echo "usage: restore-to-fresh-vm.sh --host <ip> --ts <TS> [--port N] [--key P] [--source off|rfs]" >&2; exit 2; }
+[ -n "$TS" ]   || { echo "--ts <UTC-timestamp> required (a bundle in the offsite bucket)" >&2; exit 2; }
+
+export PULUMI_BACKEND_URL="file://${DIR}/state"
+export PULUMI_CONFIG_PASSPHRASE="${PULUMI_CONFIG_PASSPHRASE:-$(pass olsitec-foundation/PULUMI_CONFIG_PASSPHRASE)}"
+cd "$DIR"; pulumi stack select foundation >/dev/null
+
+# Secrets from passphrase-encrypted config (the disaster-survivable set).
+UK=$(pulumi config get vaultCredentials:unsealKeys)
+RTOK=$(pulumi config get vaultCredentials:rootToken)
+AGE_ID=$(pulumi config get foundation:backup.ageIdentity)
+OFF_EP=$(pulumi config get foundation:backup.offsiteEndpoint)
+OFF_AK=$(pulumi config get foundation:backup.offsiteAccessKey)
+OFF_SK=$(pulumi config get foundation:backup.offsiteSecretKey)
+NET=$(pulumi config get foundation:network.name)
+SUBNET=$(pulumi config get foundation:network.subnet)
+
+SSHX="ssh -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null -o ConnectTimeout=20 -i $KEY -p $PORT root@$HOST"
+
+echo "dr: restoring bundle $TS ($SRC) onto fresh VM $HOST:$PORT"
+$SSHX "for t in docker age zstd jq; do command -v \$t >/dev/null || { echo \"missing \$t on target VM\" >&2; exit 1; }; done" \
+  || { echo "dr: target VM missing prereqs (docker/age/zstd/jq) — see dr/RUNBOOK.md §2" >&2; exit 1; }
+
+# Ship the image pins + the VM-side restorer.
+$SSHX "cat > /tmp/foundation-dr-VERSIONS" < "$ROOT/VERSIONS"
+$SSHX "cat > /tmp/foundation-dr-remote-$TS.sh" < "$ROOT/dr/restore-to-fresh-vm-remote.sh"
+# Secrets on stdin (never argv): unseal keys, root token, age identity, offsite creds.
+printf '%s\n%s\n%s\n%s\n%s\n%s\n' "$UK" "$RTOK" "$AGE_ID" "$OFF_EP" "$OFF_AK" "$OFF_SK" \
+  | $SSHX "sh /tmp/foundation-dr-remote-$TS.sh '$TS' '$SRC' '$NET' '$SUBNET'; rc=\$?; rm -f /tmp/foundation-dr-remote-$TS.sh /tmp/foundation-dr-VERSIONS; exit \$rc"
+echo "dr: restore complete. Next (RUNBOOK §5): re-point DNS to $HOST, bring up Caddy + runner,"
+echo "dr: then re-adopt the stack with vm.host=$HOST (pulumi up) to resume IaC management."