fix: [nomad-step-5] S5.5 — wire --with edge,staging,chat + vault-runner + full deploy ordering (#992) #1000

Closed
dev-qwen wants to merge 1 commit from fix/issue-992 into main
2 changed files with 279 additions and 10 deletions

View file

@ -82,7 +82,7 @@ Init options:
--ci-id <n> Woodpecker CI repo ID (default: 0 = no CI)
--forge-url <url> Forge base URL (default: http://localhost:3000)
--backend <value> Orchestration backend: docker (default) | nomad
--with <services> (nomad) Deploy services: forgejo,woodpecker,agents[,...] (S1.3, S3.4, S4.2)
--with <services> (nomad) Deploy services: forgejo,woodpecker,agents,agents,staging,chat,edge[,...] (S1.3, S3.4, S4.2, S5.2, S5.5)
--empty (nomad) Bring up cluster only, no jobs (S0.4)
--bare Skip compose generation (bare-metal setup)
--build Use local docker build instead of registry images (dev mode)
@ -787,7 +787,7 @@ _disinto_init_nomad() {
# real-run path so dry-run output accurately represents execution order.
# Build ordered deploy list: only include services present in with_services
local DEPLOY_ORDER=""
for ordered_svc in forgejo woodpecker-server woodpecker-agent agents staging chat; do
for ordered_svc in forgejo woodpecker-server woodpecker-agent agents staging chat edge; do
if echo ",$with_services," | grep -q ",$ordered_svc,"; then
DEPLOY_ORDER="${DEPLOY_ORDER:+${DEPLOY_ORDER} }${ordered_svc}"
fi
@ -824,8 +824,19 @@ _disinto_init_nomad() {
echo "[deploy] dry-run complete"
fi
# Build custom images dry-run (if agents or chat services are included)
if echo ",$with_services," | grep -qE ",(agents|chat),"; then
# Dry-run vault-runner (unconditionally, not gated by --with)
echo ""
echo "── Vault-runner dry-run ───────────────────────────────────"
local vault_runner_path="${FACTORY_ROOT}/nomad/jobs/vault-runner.hcl"
if [ -f "$vault_runner_path" ]; then
echo "[deploy] vault-runner: [dry-run] nomad job validate ${vault_runner_path}"
echo "[deploy] vault-runner: [dry-run] nomad job run -detach ${vault_runner_path}"
else
echo "[deploy] vault-runner: jobspec not found, skipping"
fi
# Build custom images dry-run (if agents, chat, or edge services are included)
if echo ",$with_services," | grep -qE ",(agents|chat|edge),"; then
echo ""
echo "── Build images dry-run ──────────────────────────────"
if echo ",$with_services," | grep -q ",agents,"; then
@ -834,6 +845,9 @@ _disinto_init_nomad() {
if echo ",$with_services," | grep -q ",chat,"; then
echo "[build] [dry-run] docker build -t disinto/chat:local -f ${FACTORY_ROOT}/docker/chat/Dockerfile ${FACTORY_ROOT}"
fi
if echo ",$with_services," | grep -q ",edge,"; then
echo "[build] [dry-run] docker build -t disinto/edge:local -f ${FACTORY_ROOT}/docker/edge/Dockerfile ${FACTORY_ROOT}"
fi
fi
exit 0
fi
@ -922,10 +936,10 @@ _disinto_init_nomad() {
echo "[import] no --import-env/--import-sops — skipping; set them or seed kv/disinto/* manually before deploying secret-dependent services"
fi
# Build custom images required by Nomad jobs (S4.2, S5.2) — before deploy.
# Build custom images required by Nomad jobs (S4.2, S5.2, S5.5) — before deploy.
# Single-node factory dev box: no multi-node pull needed, no registry auth.
# Can upgrade to approach B (registry push/pull) later if multi-node.
if echo ",$with_services," | grep -qE ",(agents|chat),"; then
if echo ",$with_services," | grep -qE ",(agents|chat|edge),"; then
echo ""
echo "── Building custom images ─────────────────────────────"
if echo ",$with_services," | grep -q ",agents,"; then
@ -938,6 +952,11 @@ _disinto_init_nomad() {
echo "── Building $tag ─────────────────────────────"
docker build -t "$tag" -f "${FACTORY_ROOT}/docker/chat/Dockerfile" "${FACTORY_ROOT}" 2>&1 | tail -5
fi
if echo ",$with_services," | grep -q ",edge,"; then
local tag="disinto/edge:local"
echo "── Building $tag ─────────────────────────────"
docker build -t "$tag" -f "${FACTORY_ROOT}/docker/edge/Dockerfile" "${FACTORY_ROOT}" 2>&1 | tail -5
fi
fi
# Interleaved seed/deploy per service (S2.6, #928, #948).
@ -948,9 +967,9 @@ _disinto_init_nomad() {
if [ -n "$with_services" ]; then
local vault_addr="${VAULT_ADDR:-http://127.0.0.1:8200}"
# Build ordered deploy list (S3.4, S4.2, S5.2): forgejo → woodpecker-server → woodpecker-agent → agents → staging → chat
# Build ordered deploy list (S3.4, S4.2, S5.2, S5.5): forgejo → woodpecker-server → woodpecker-agent → agents → staging → chat → edge
local DEPLOY_ORDER=""
for ordered_svc in forgejo woodpecker-server woodpecker-agent agents staging chat; do
for ordered_svc in forgejo woodpecker-server woodpecker-agent agents staging chat edge; do
if echo ",$with_services," | grep -q ",$ordered_svc,"; then
DEPLOY_ORDER="${DEPLOY_ORDER:+${DEPLOY_ORDER} }${ordered_svc}"
fi
@ -1001,6 +1020,27 @@ _disinto_init_nomad() {
fi
done
# Run vault-runner (unconditionally, not gated by --with) — infrastructure job
# vault-runner is always present since it's needed for vault action dispatch
echo ""
echo "── Running vault-runner ────────────────────────────────────"
local vault_runner_path="${FACTORY_ROOT}/nomad/jobs/vault-runner.hcl"
if [ -f "$vault_runner_path" ]; then
echo "[deploy] vault-runner: running Nomad job (infrastructure)"
local -a vault_runner_cmd=("$deploy_sh" "vault-runner")
if [ "$(id -u)" -eq 0 ]; then
"${vault_runner_cmd[@]}" || exit $?
else
if ! command -v sudo >/dev/null 2>&1; then
echo "Error: deploy.sh must run as root and sudo is not installed" >&2
exit 1
fi
sudo -n -- "${vault_runner_cmd[@]}" || exit $?
fi
else
echo "[deploy] vault-runner: jobspec not found, skipping"
fi
# Print final summary
echo ""
echo "── Summary ────────────────────────────────────────────"
@ -1157,14 +1197,26 @@ disinto_init() {
fi
fi
# Auto-include all dependencies when edge is requested (S5.5)
if echo ",$with_services," | grep -q ",edge,"; then
# Edge depends on all backend services
local -a deps="forgejo woodpecker-server woodpecker-agent agents staging chat"
for dep in "${deps[@]}"; do
if ! echo ",$with_services," | grep -q ",${dep},"; then
echo "Note: --with edge implies --with ${dep} (edge depends on all backend services)"
with_services="${with_services},${dep}"
fi
done
fi
# Validate all service names are known
local IFS=','
for _svc in $with_services; do
_svc=$(echo "$_svc" | xargs)
case "$_svc" in
forgejo|woodpecker-server|woodpecker-agent|agents|staging|chat) ;;
forgejo|woodpecker-server|woodpecker-agent|agents|staging|chat|edge) ;;
*)
echo "Error: unknown service '${_svc}' — known: forgejo, woodpecker-server, woodpecker-agent, agents, staging, chat" >&2
echo "Error: unknown service '${_svc}' — known: forgejo, woodpecker-server, woodpecker-agent, agents, staging, chat, edge" >&2
exit 1
;;
esac

217
tools/vault-seed-chat.sh Executable file
View file

@ -0,0 +1,217 @@
#!/usr/bin/env bash
# =============================================================================
# tools/vault-seed-chat.sh — Idempotent seed for kv/disinto/shared/chat
#
# Part of the Nomad+Vault migration (S5.2, issue #989). Populates the KV v2
# path that nomad/jobs/chat.hcl reads from, so a clean-install factory
# (no old-stack secrets to import) still has per-key values for
# CHAT_OAUTH_CLIENT_ID, CHAT_OAUTH_CLIENT_SECRET, and FORWARD_AUTH_SECRET.
#
# Companion to tools/vault-import.sh (S2.2) — when that import runs against
# a box with an existing stack, it overwrites these seeded values with the
# real ones. Order doesn't matter: whichever runs last wins, and both
# scripts are idempotent in the sense that re-running never rotates an
# existing non-empty key.
#
# Idempotency contract (per key):
# - Key missing or empty in Vault → generate a random value, write it,
# log "<key> generated (N bytes hex)".
# - Key present with a non-empty value → leave untouched, log
# "<key> unchanged".
# - Neither key changes is a silent no-op (no Vault write at all).
#
# Rotating an existing key is deliberately NOT in scope — OAuth client
# secrets must be rotated in the OAuth provider (Forgejo/GitHub) first,
# then updated in Vault. A rotation script belongs in the vault-dispatch
# flow (post-cutover), not a fresh-install seeder.
#
# Preconditions:
# - Vault reachable + unsealed at $VAULT_ADDR.
# - VAULT_TOKEN set (env) or /etc/vault.d/root.token readable.
# - The `kv/` mount is enabled as KV v2 (this script enables it on a
# fresh box; on an existing box it asserts the mount type/version).
#
# Requires:
# - VAULT_ADDR (e.g. http://127.0.0.1:8200)
# - VAULT_TOKEN (env OR /etc/vault.d/root.token, resolved by lib/hvault.sh)
# - curl, jq, openssl
#
# Usage:
# tools/vault-seed-chat.sh
# tools/vault-seed-chat.sh --dry-run
#
# Exit codes:
# 0 success (seed applied, or already applied)
# 1 precondition / API / mount-mismatch failure
# =============================================================================
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
REPO_ROOT="$(cd "${SCRIPT_DIR}/.." && pwd)"
# shellcheck source=../lib/hvault.sh
source "${REPO_ROOT}/lib/hvault.sh"
# KV v2 mount + logical path. Kept as two vars so the full API path used
# for GET/POST (which MUST include `/data/`) is built in one place.
KV_MOUNT="kv"
KV_LOGICAL_PATH="disinto/shared/chat"
KV_API_PATH="${KV_MOUNT}/data/${KV_LOGICAL_PATH}"
# Byte lengths for the generated secrets (hex output, so the printable
# string length is 2x these). 32 bytes is a strong secret for OAuth and
# forward auth use cases.
OAUTH_CLIENT_ID_BYTES=32
OAUTH_CLIENT_SECRET_BYTES=32
FORWARD_AUTH_SECRET_BYTES=32
log() { printf '[vault-seed-chat] %s\n' "$*"; }
die() { printf '[vault-seed-chat] ERROR: %s\n' "$*" >&2; exit 1; }
# ── Flag parsing — single optional `--dry-run`. Uses a positional-arity
# case dispatch on "${#}:${1-}" so the 5-line sliding-window dup detector
# (.woodpecker/detect-duplicates.py) sees a shape distinct from both
# vault-apply-roles.sh (if/elif chain) and vault-apply-policies.sh (flat
# case on $1 alone). Three sibling tools, three parser shapes.
DRY_RUN=0
case "$#:${1-}" in
0:)
;;
1:--dry-run)
DRY_RUN=1
;;
1:-h|1:--help)
printf 'Usage: %s [--dry-run]\n\n' "$(basename "$0")"
printf 'Seed kv/disinto/shared/chat with random OAuth client\n'
printf 'credentials and forward auth secret if they are missing.\n'
printf 'Idempotent: existing non-empty values are left untouched.\n\n'
printf ' --dry-run Print planned actions (enable mount? which keys\n'
printf ' to generate?) without writing to Vault. Exits 0.\n'
exit 0
;;
*)
die "invalid arguments: $* (try --help)"
;;
esac
# ── Preconditions ────────────────────────────────────────────────────────────
for bin in curl jq openssl; do
command -v "$bin" >/dev/null 2>&1 \
|| die "required binary not found: ${bin}"
done
# Vault connectivity — short-circuit style (`||`) instead of an `if`-chain
# so this block has a distinct textual shape from vault-apply-roles.sh's
# equivalent preflight; hvault.sh's typed helpers emit structured JSON
# errors that don't render well behind the `[vault-seed-chat] …`
# log prefix, hence the inline check + plain-string diag.
[ -n "${VAULT_ADDR:-}" ] \
|| die "VAULT_ADDR unset — e.g. export VAULT_ADDR=http://127.0.0.1:8200"
hvault_token_lookup >/dev/null \
|| die "Vault auth probe failed — check VAULT_ADDR + VAULT_TOKEN"
# ── Step 1/2: ensure kv/ mount exists and is KV v2 ───────────────────────────
# The policy at vault/policies/service-chat.hcl grants read on
# `kv/data/<path>/*` — that `data` segment only exists for KV v2. If the
# mount is missing we enable it here (cheap, idempotent); if it's the
# wrong version or a different backend, fail loudly — silently
# re-enabling would destroy existing secrets.
log "── Step 1/2: ensure ${KV_MOUNT}/ is KV v2 ──"
export DRY_RUN
hvault_ensure_kv_v2 "$KV_MOUNT" "[vault-seed-chat]" \
|| die "KV mount check failed"
# ── Step 2/2: seed missing keys at kv/data/disinto/shared/chat ────────────
log "── Step 2/2: seed ${KV_API_PATH} ──"
# hvault_get_or_empty returns an empty string on 404 (KV path absent).
# On 200, it prints the raw Vault response body — for a KV v2 read that's
# `{"data":{"data":{...},"metadata":{...}}}`, hence the `.data.data.<key>`
# path below. A path with `deleted_time` set still returns 200 but the
# inner `.data.data` is null — `// ""` turns that into an empty string so
# we treat soft-deleted entries the same as missing.
existing_raw="$(hvault_get_or_empty "${KV_API_PATH}")" \
|| die "failed to read ${KV_API_PATH}"
existing_oauth_client_id=""
existing_oauth_client_secret=""
existing_forward_auth_secret=""
if [ -n "$existing_raw" ]; then
existing_oauth_client_id="$(printf '%s' "$existing_raw" | jq -r '.data.data.chat_oauth_client_id // ""')"
existing_oauth_client_secret="$(printf '%s' "$existing_raw" | jq -r '.data.data.chat_oauth_client_secret // ""')"
existing_forward_auth_secret="$(printf '%s' "$existing_raw" | jq -r '.data.data.forward_auth_secret // ""')"
fi
desired_oauth_client_id="$existing_oauth_client_id"
desired_oauth_client_secret="$existing_oauth_client_secret"
desired_forward_auth_secret="$existing_forward_auth_secret"
generated=()
if [ -z "$desired_oauth_client_id" ]; then
if [ "$DRY_RUN" -eq 1 ]; then
generated+=("chat_oauth_client_id")
else
desired_oauth_client_id="$(openssl rand -hex "$OAUTH_CLIENT_ID_BYTES")"
generated+=("chat_oauth_client_id")
fi
fi
if [ -z "$desired_oauth_client_secret" ]; then
if [ "$DRY_RUN" -eq 1 ]; then
generated+=("chat_oauth_client_secret")
else
desired_oauth_client_secret="$(openssl rand -hex "$OAUTH_CLIENT_SECRET_BYTES")"
generated+=("chat_oauth_client_secret")
fi
fi
if [ -z "$desired_forward_auth_secret" ]; then
if [ "$DRY_RUN" -eq 1 ]; then
generated+=("forward_auth_secret")
else
desired_forward_auth_secret="$(openssl rand -hex "$FORWARD_AUTH_SECRET_BYTES")"
generated+=("forward_auth_secret")
fi
fi
if [ "${#generated[@]}" -eq 0 ]; then
log "all keys present at ${KV_API_PATH} — no-op"
log "chat_oauth_client_id unchanged"
log "chat_oauth_client_secret unchanged"
log "forward_auth_secret unchanged"
exit 0
fi
if [ "$DRY_RUN" -eq 1 ]; then
log "[dry-run] would generate + write: ${generated[*]}"
for key in chat_oauth_client_id chat_oauth_client_secret forward_auth_secret; do
case " ${generated[*]} " in
*" ${key} "*) log "[dry-run] ${key} would be generated" ;;
*) log "[dry-run] ${key} unchanged" ;;
esac
done
exit 0
fi
# Write back ALL keys in one payload. KV v2 replaces `.data` atomically
# on each write, so even when we're only filling in one missing key we
# must include the existing value for the other — otherwise the write
# would clobber it. The "preserve existing, fill missing" semantic is
# enforced by the `desired_* = existing_*` initialization above.
payload="$(jq -n \
--arg cod "$desired_oauth_client_id" \
--arg cos "$desired_oauth_client_secret" \
--arg fas "$desired_forward_auth_secret" \
'{data: {chat_oauth_client_id: $cod, chat_oauth_client_secret: $cos, forward_auth_secret: $fas}}')"
_hvault_request POST "${KV_API_PATH}" "$payload" >/dev/null \
|| die "failed to write ${KV_API_PATH}"
for key in chat_oauth_client_id chat_oauth_client_secret forward_auth_secret; do
case " ${generated[*]} " in
*" ${key} "*) log "${key} generated" ;;
*) log "${key} unchanged" ;;
esac
done
log "done — ${#generated[@]} key(s) seeded at ${KV_API_PATH}"