Merge pull request #216 from theta42/release-v2.7.0

release(v2.7.0): auto-configured OpenLDAP multi-master replication

CHANGELOG.md

@@ -9,6 +9,31 @@ orchestration code; see each submodule's own `CHANGELOG.md`
 [jump-host](https://github.com/theta42/jump-host/blob/master/CHANGELOG.md))
 for what changed inside the apps it composes.
 
+## [v2.7.0] - 2026-08-11
+
+Rolls up **sso-manager-node v2.7.0**. Closes the last "operator hand-sets
+this" item on the multi-site TODO: OpenLDAP N-way multi-master replication
+now configures itself.
+
+### theta-suite orchestration
+- **`bootstrap/site-ldap-register.js`**: runs on every `setup.sh` invocation
+  (master and spoke), fetches this node's auto-assigned `LDAP_SERVER_ID` +
+  current peer list from sso-manager-node's new endpoints, and restarts
+  `sso-manager` only when the computed config actually changed.
+- `CFG_LDAP_MMR_MANUAL=true` skips the automatic step for a topology outside
+  this cluster the script can't derive on its own -- otherwise it always
+  runs (every fresh install starts as a master) and would overwrite
+  hand-set values.
+- `setup.env.example`'s old `#LDAP_SERVER_ID=1`/`#LDAP_REPLICATION_HOSTS=`
+  manual-config prompt is gone for the common case.
+
+### sso-manager-node v2.7.0
+- `SiteSpoke.ldapServerId` auto-assigned at registration (same pattern as
+  jump-host's mesh index); each site's LDAP URL derived from its
+  already-known HTTP(S) endpoint. New `GET /api/site/ldap-peers`
+  (spoke-facing) and `GET /directory-admin/ldap-replication-config`
+  (master-local). Verified against real running containers.
+
 ## [v2.6.0] - 2026-08-11
 
 Rolls up **sso-manager-node v2.6.0** and **jump-host v2.1.1** (already

bootstrap/site-ldap-register.js

@@ -0,0 +1,139 @@
+#!/usr/bin/env node
+/*
+ * theta-suite site-ldap-register — runs inside the sso-manager container on
+ * every setup.sh run (both master and spoke) to keep OpenLDAP N-way
+ * multi-master replication config (docs/replication.md) in sync without an
+ * operator hand-maintaining LDAP_SERVER_ID/LDAP_REPLICATION_HOSTS.
+ *
+ * The master assigns each spoke a unique LDAP_SERVER_ID at join time (same
+ * mechanism as jump-host's WireGuard mesh index) and derives every site's
+ * LDAP URL from its already-known HTTPS endpoint -- see sso-manager-node's
+ * GET /api/site/ldap-peers (spoke-facing) and
+ * GET /directory-admin/ldap-replication-config (master-local).
+ *
+ * This script fetches whichever of those two applies to this node's role,
+ * and writes the result to /config/ldap-replication.env (KEY=VALUE, the
+ * same shape setup.env/spoke.env use) if it changed since last run. setup.sh
+ * sources that file before starting sso-manager on every invocation, and
+ * restarts the container when this script reports a change -- OpenLDAP's
+ * static slapd.conf is only read at process start, so a config change needs
+ * a restart to take effect; there's no live push, which is why this has to
+ * be re-run periodically (every setup.sh invocation) rather than working
+ * once at join time and never again, especially on the MASTER, whose peer
+ * list changes every time a new spoke joins.
+ *
+ *   docker compose exec sso-manager node /bootstrap/site-ldap-register.js <selfUrl>
+ *
+ * Self-contained (Node built-ins + global fetch), same rule as
+ * bootstrap.js/site-join.js -- does NOT require the SSO's internal models.
+ *
+ * Output (stdout, KEY=VALUE for setup.sh): LDAP_CONFIG_CHANGED=<yes|no>,
+ * LDAP_SERVER_ID=<n>, LDAP_REPLICATION_HOSTS=<space-separated, may be empty>.
+ * Progress logs go to stderr.
+ */
+'use strict';
+
+const fs = require('fs');
+
+const SITE_CONFIG = '/config/site.json';
+const LDAP_CONFIG_FILE = '/config/ldap-replication.env';
+const SSO_INTERNAL = 'http://localhost:3001';
+
+const selfUrl = process.argv[2];
+
+function log(msg) { console.error('[site-ldap-register] ' + msg); }
+
+function readPersisted() {
+  if (!fs.existsSync(LDAP_CONFIG_FILE)) return { LDAP_SERVER_ID: '', LDAP_REPLICATION_HOSTS: '' };
+  const out = { LDAP_SERVER_ID: '', LDAP_REPLICATION_HOSTS: '' };
+  for (const line of fs.readFileSync(LDAP_CONFIG_FILE, 'utf8').split('\n')) {
+    const m = line.match(/^([A-Z_]+)=(.*)$/);
+    if (m && m[1] in out) out[m[1]] = m[2];
+  }
+  return out;
+}
+
+async function fetchMasterConfig() {
+  const sso = require('/config/sso-secrets.js');
+  const adminUid = (sso.bootstrap && sso.bootstrap.adminUid) || 'admin';
+  const adminPass = (sso.bootstrap && sso.bootstrap.adminPass) || '';
+
+  const loginRes = await fetch(`${SSO_INTERNAL}/api/auth/login`, {
+    method: 'POST',
+    headers: { 'Content-Type': 'application/json' },
+    body: JSON.stringify({ uid: adminUid, password: adminPass }),
+  });
+  if (!loginRes.ok) throw new Error(`local admin login failed (${loginRes.status}): ${await loginRes.text().catch(() => '')}`);
+  const { token } = await loginRes.json();
+  if (!token) throw new Error('local admin login returned no token');
+
+  const cfgRes = await fetch(`${SSO_INTERNAL}/api/directory-admin/ldap-replication-config`, {
+    headers: { 'auth-token': token },
+  });
+  if (!cfgRes.ok) throw new Error(`ldap-replication-config failed (${cfgRes.status}): ${await cfgRes.text().catch(() => '')}`);
+  return cfgRes.json();
+}
+
+async function fetchSpokeConfig(site, selfUrl) {
+  const url = `${site.masterUrl.replace(/\/+$/, '')}/api/site/ldap-peers?endpoint=${encodeURIComponent(selfUrl)}`;
+  const res = await fetch(url, { headers: { Authorization: 'Bearer ' + site.masterJoinKey } });
+  const text = await res.text().catch(() => '');
+  let data = null;
+  try { data = JSON.parse(text); } catch (e) { /* not JSON */ }
+  if (!res.ok) {
+    if (res.status === 404) {
+      log('This site is not registered as a spoke on the master yet (join with selfUrl, or re-run site-relay-register.js). Skipping.');
+      return null;
+    }
+    throw new Error(`ldap-peers failed (${res.status}): ${(data && data.message) || text}`);
+  }
+  return data;
+}
+
+async function main() {
+  if (!fs.existsSync(SITE_CONFIG)) {
+    log('No /config/site.json yet. Skipping.');
+    console.log('LDAP_CONFIG_CHANGED=no');
+    return;
+  }
+  const site = JSON.parse(fs.readFileSync(SITE_CONFIG, 'utf8'));
+
+  let result;
+  if (site.isMaster) {
+    result = await fetchMasterConfig();
+  } else {
+    if (!site.masterUrl || !site.masterJoinKey) {
+      log('Spoke role but missing masterUrl/masterJoinKey. Skipping.');
+      console.log('LDAP_CONFIG_CHANGED=no');
+      return;
+    }
+    if (!selfUrl) throw new Error('usage: node /bootstrap/site-ldap-register.js <selfUrl> (required for a spoke)');
+    result = await fetchSpokeConfig(site, selfUrl);
+    if (!result) {
+      console.log('LDAP_CONFIG_CHANGED=no');
+      return;
+    }
+  }
+
+  const serverId = String(result.ldapServerId || '');
+  const hosts = (result.peers || []).map((p) => p.ldapHost).filter(Boolean).join(' ');
+
+  const before = readPersisted();
+  const changed = before.LDAP_SERVER_ID !== serverId || before.LDAP_REPLICATION_HOSTS !== hosts;
+
+  if (changed) {
+    fs.writeFileSync(LDAP_CONFIG_FILE, `LDAP_SERVER_ID=${serverId}\nLDAP_REPLICATION_HOSTS=${hosts}\n`);
+    log(`Replication config changed -- ServerID ${serverId}, ${(result.peers || []).length} peer(s). Wrote ${LDAP_CONFIG_FILE}.`);
+  } else {
+    log(`Replication config unchanged -- ServerID ${serverId}, ${(result.peers || []).length} peer(s).`);
+  }
+
+  console.log(`LDAP_CONFIG_CHANGED=${changed ? 'yes' : 'no'}`);
+  console.log(`LDAP_SERVER_ID=${serverId}`);
+  console.log(`LDAP_REPLICATION_HOSTS=${hosts}`);
+}
+
+main().catch((e) => {
+  console.error('[site-ldap-register] FAILED: ' + e.message);
+  process.exit(1);
+});

docs/MULTI_SITE_SPEC.md

@@ -259,6 +259,7 @@ See [`AGENT_LOCAL_DISCOVERY_SPEC.md`](./AGENT_LOCAL_DISCOVERY_SPEC.md) — split
 | `setup.env` / `setup.sh` join wiring | **Shipped** — `CFG_MASTER_DIRECTORY_URL` / `CFG_MASTER_DIRECTORY_JOIN_KEY`, `bootstrap/site-join.js` (theta-suite v2.2.0). Also readable from a dedicated `spoke.env` (`spoke.env.example`, layered on top of `setup.env`) for operators who want join-a-cluster config kept separate from the rest of first-run setup. |
 | Continuous/live replication (vs. one-time export-on-join) | **Shipped** (`sso-manager-node`) — a spoke registers its own endpoint at join time (`POST /api/site/spokes`), and every successful master catalog write fires a fire-and-forget push (`utils/site_replicate.js`) at every registered spoke, which re-pulls a fresh export. Verified end-to-end in `docker-compose.multisite-e2e.yml`. |
 | Identical-directory signing key | **Shipped** — `POST /api/site/export` includes the master's agent-signing key; a spoke adopts it via `agent_keys.adopt()` on join and every resync. OpenBao secret replication *beyond* this one key is still not built. |
+| OpenLDAP N-way multi-master replication auto-config | **Shipped** — the master auto-assigns each spoke a unique `LDAP_SERVER_ID` at registration (`SiteSpoke.ldapServerId`, same pattern as jump-host's mesh index) and derives every site's LDAP URL from its already-known HTTPS endpoint; `theta-suite`'s `bootstrap/site-ldap-register.js` applies it, re-checked on every `setup.sh` run since the peer list grows as spokes join. Verified against real running containers. Known gap: the master's own config only updates when ITS `setup.sh` is re-run, not live the moment a new spoke joins (see `docs/replication.md`). |
 | Coordinated master promotion (demote the old master as one action) | **Shipped** — `POST /api/site/demote` + `site-promote`'s handoff logic. Fixed two real pre-existing bugs while wiring this in: `site-promote`'s god_admin check read a `req.user.groups` field nothing ever populated (permanently 403'd for everyone), and the read-only write-gate 403'd `site-promote` itself before the handler could run. |
 | WireGuard gateway-to-gateway mesh (`theta-gateway`) | **Shipped** — `POST /api/mesh/register`/`/join` (join-token bootstrap), `utils/wg_iface.js` (kernel WireGuard, falls back to userspace `wireguard-go`). Verified with a real two-container test: actual encrypted tunnel, real ICMP traffic across it, 0% loss. `wg_iface.removePeer()` also cleans up the kernel routes `setPeer()` added (verified live: routes present after `setPeer`, gone after `removePeer`, own local route untouched), and `DELETE /api/mesh/gateways/:id` exposes it from the mesh UI. |
 | Cross-component routing (replication over the mesh) | **Shipped** — `utils/site_replicate.js` tries a registered spoke's `meshIp` first (falling back to its public `endpoint` on failure) when pushing resync pings; a spoke with no `meshIp` on file behaves exactly as before. |

setup.env.example

@@ -152,14 +152,20 @@ CFG_DOMAIN=example.com
 #CFG_THETA_AGENT_FULL_CONTROL=1
 
 # ── Geo-Location Scaling (N-Way Multi-Master LDAP) ───────────────────────────
-# If deploying this stack across multiple physical sites to provide local HA
-# for directory services, you can enable N-Way Multi-Master OpenLDAP replication.
-# This requires assigning a unique ID to each site and listing the LDAPS URLs
-# of all OTHER sites in the cluster.
+# If you're joining a directory cluster (CFG_MASTER_DIRECTORY_URL/spoke.env
+# above), N-Way Multi-Master OpenLDAP replication is configured for you
+# automatically -- setup.sh's bootstrap/site-ldap-register.js asks the master
+# for a unique LDAP_SERVER_ID and the current list of every other site's LDAP
+# URL on every run (see docs/replication.md), restarting sso-manager only
+# when that config actually changed. Nothing to set here for the common case.
 #
-# Each site MUST have a unique LDAP_SERVER_ID (e.g. 1, 2, 3).
-# LDAP_REPLICATION_HOSTS is a space-separated list of the other sites' LDAP URLs.
-# Example for Site 1:
+# Have a manually-coordinated LDAP MMR topology this script can't derive on
+# its own (e.g. peers outside this theta-suite cluster)? Set
+# CFG_LDAP_MMR_MANUAL=true to skip the automatic step entirely and set
+# LDAP_SERVER_ID/LDAP_REPLICATION_HOSTS directly -- without this, the
+# automatic step runs on every deployment (every fresh install starts as a
+# master) and will overwrite them.
+#CFG_LDAP_MMR_MANUAL=true
 #LDAP_SERVER_ID=1
 #LDAP_REPLICATION_HOSTS="ldaps://sso.site2.com:636 ldaps://sso.site3.com:636"
 # ── Proxy HTTP/HTTPS Defaults ────────────────────────────────────────────────

setup.sh

@@ -1060,6 +1060,15 @@ info "Starting bao-renewer (service-token renewal sidecar)..."
 SSO_GIT_COMMIT="$(git -C sso-manager-node rev-parse --short HEAD 2>/dev/null || echo unknown)"
 export SSO_GIT_COMMIT
 env_upsert SSO_GIT_COMMIT "$SSO_GIT_COMMIT"
+# OpenLDAP multi-master replication (docs/replication.md, auto-configured --
+# see step 7e below and bootstrap/site-ldap-register.js): pick up whatever
+# LDAP_SERVER_ID/LDAP_REPLICATION_HOSTS a PRIOR run already computed, so a
+# restart doesn't silently drop back to standalone (no LDAP_SERVER_ID env at
+# all). A truly fresh install has no file yet -- that's fine, it just starts
+# standalone until step 7e computes and applies real values. Skipped under
+# CFG_LDAP_MMR_MANUAL=true so a manually hand-set LDAP_SERVER_ID/
+# LDAP_REPLICATION_HOSTS in setup.env isn't clobbered by a stale auto file.
+[[ "${CFG_LDAP_MMR_MANUAL:-false}" != "true" && -f "$CONFIG_DIR/ldap-replication.env" ]] && parse_kv_file "$CONFIG_DIR/ldap-replication.env"
 info "Building + starting sso-manager (first run builds the image; this takes a while)..."
 "${COMPOSE[@]}" up -d --build sso-manager
 
@@ -1322,6 +1331,40 @@ if [[ "${CFG_SPOKE_NO_INBOUND:-false}" == "true" ]]; then
 	fi
 fi
 
+# ── 7e. OpenLDAP multi-master replication auto-config (every run) ────────────
+# docs/replication.md: the master assigns each spoke a unique LDAP_SERVER_ID
+# and derives every site's LDAP URL automatically (bootstrap/
+# site-ldap-register.js) instead of an operator hand-maintaining
+# LDAP_SERVER_ID/LDAP_REPLICATION_HOSTS. Runs on every invocation -- both
+# master (its peer list grows as spokes join) and spoke -- and restarts
+# sso-manager only when the computed config actually changed, since
+# OpenLDAP's static slapd.conf is only read at process start.
+#
+# CFG_LDAP_MMR_MANUAL=true skips this entirely -- every fresh install starts
+# as a master, so without this escape hatch an operator's own hand-set
+# LDAP_SERVER_ID/LDAP_REPLICATION_HOSTS (a topology outside this theta-suite
+# cluster this script can't derive) would get silently overwritten.
+if [[ "${CFG_LDAP_MMR_MANUAL:-false}" == "true" ]]; then
+	info "CFG_LDAP_MMR_MANUAL=true — skipping automatic LDAP replication config."
+	LDAP_REG_OUT=""
+else
+LDAP_REG_OUT=$("${COMPOSE[@]}" exec -T sso-manager node /bootstrap/site-ldap-register.js "https://$CFG_SSO_HOST" 2>&1) || warn "LDAP replication config check failed — check: ${COMPOSE[*]} exec sso-manager node /bootstrap/site-ldap-register.js https://$CFG_SSO_HOST"
+echo "$LDAP_REG_OUT" | sed 's/^/[setup] /'
+fi
+if echo "$LDAP_REG_OUT" | grep -q '^LDAP_CONFIG_CHANGED=yes'; then
+	info "LDAP replication config changed — restarting sso-manager to apply it..."
+	[[ -f "$CONFIG_DIR/ldap-replication.env" ]] && parse_kv_file "$CONFIG_DIR/ldap-replication.env"
+	"${COMPOSE[@]}" up -d --force-recreate sso-manager
+	info "Waiting for sso-manager to be healthy again..."
+	for i in $(seq 1 60); do
+		if docker exec sso-manager wget -q -O- http://localhost:3001/health >/dev/null 2>&1; then
+			info "sso-manager is healthy."; break
+		fi
+		if (( i == 60 )); then warn "sso-manager did not become healthy in 120s after the LDAP config restart. Check: ${COMPOSE[*]} logs sso-manager"; break; fi
+		sleep 2
+	done
+fi
+
 # ── 7c. Install theta-agent on the host ──────────────────────────────────────
 # Controlled by CFG_THETA_AGENT_ENABLE (default: 1 = enabled)
 CFG_THETA_AGENT_ENABLE="${CFG_THETA_AGENT_ENABLE:-1}"