Merge pull request #218 from theta42/release-v2.8.0

release(v2.8.0): promotion/LDAP-orphan fix, site-slug unification, LDAP status UI

CHANGELOG.md

@@ -9,6 +9,53 @@ 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.
 
+## [v2.8.0] - 2026-08-11
+
+Rolls up **sso-manager-node v2.8.0**. Fixes found while auditing the v2.7.0
+multi-site work for gaps, plus the published docs staleness that same audit
+turned up.
+
+### sso-manager-node v2.8.0
+- Promotion no longer orphans the demoted old master's LDAP replication --
+  `/demote` now registers itself with the new master immediately instead of
+  being left with no way to ever get a real `ldapServerId` again.
+- The Directory's site slug and the multi-site replication identity are
+  unified -- previously unrelated values that happened to share a name.
+- LDAP replication status (real vs. advertised ServerID, a `stale` flag) and
+  per-spoke detail (not just an aggregate count) on the Multi-Site modal.
+
+### theta-suite docs
+- Fixed multiple stale/contradictory claims on the published site: the
+  no-inbound relay described as "designed but not automated" (shipped
+  earlier this session), `docs/sso/replication.md` never mentioning the new
+  LDAP MMR auto-config at all, and the homepage feature list only
+  describing the old manual N-way replication.
+
+## [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. |

docs/index.md

@@ -74,10 +74,12 @@ The SSO Manager and the proxy it fronts, both stood up by one `./setup.sh` run:
   management built directly into the web interface, allowing operators to drive
   system administration and automation pipelines programmatically without an
   active browser session.
-- **Multi-Site Geo-Replication**: Built-in support for N-Way Multi-Master LDAP
+- **Multi-Site Geo-Replication**: A master site and any number of spokes join
-  replication, allowing directory states to sync across geographically separated
+  with one key and one URL, staying in sync automatically (no manual LDAP
-  physical hardware or remote data centers for high availability and low-latency
+  config) — see [Multi-Site (Master/Spoke Join)](sso/multi-site.html). Raw
-  local reads.
+  N-Way Multi-Master LDAP replication is also available directly for
+  deployments that want every site independently writable with no
+  master/spoke concept — see [Geo-Location Scaling](sso/replication.html).
 - **Multi-Target Load Balancing**: Native reverse-proxy load balancing that
   distributes traffic across multiple application backends using customizable
   health checks and round-robin strategies.

docs/quickstart.md

@@ -74,6 +74,11 @@ file shape.
 > exist, `./setup.sh` migrates them into `./config/` preserving your existing
 > secrets — no need to write a `setup.env`.
 
+> **Joining an existing Theta Directory cluster instead of seeding a fresh
+> one?** See [Multi-Site (Master/Spoke Join)](sso/multi-site.html) —
+> `spoke.env.example` has the join-a-cluster vars split out into their own
+> file, or set them directly in `setup.env` (which has every option).
+
 ---
 
 ## 3. Run

docs/sso/multi-site.md

@@ -10,10 +10,10 @@ the **master** (single write authority for the shared catalog) and any
 number of **spokes** — read-only replicas that stay in sync automatically and
 run local authentication with zero WAN dependency.
 
-This is a different, higher-level mechanism than [raw LDAP N-way
+This is a higher-level mechanism than [raw LDAP N-way
-replication](replication.html) — see [How this relates to LDAP
+replication](replication.html) — and it now drives that lower-level
-replication](#how-this-relates-to-ldap-replication) below if you're deciding
+replication for you automatically. See [How this relates to LDAP
-between the two.
+replication](#how-this-relates-to-ldap-replication) below.
 
 ## Why and when to use this
 
@@ -45,6 +45,13 @@ between the two.
      stack's setup. Both are read; `spoke.env`'s values win on a conflict.
      No public IP on this site at all? `spoke.env.example` also covers the
      no-inbound relay vars (`CFG_SPOKE_NO_INBOUND`/`CFG_SPOKE_PUBLIC_HOST`).
+
+     Want this spoke reachable at its own public domain rather than sharing
+     the master's? `CFG_DOMAIN` (the LDAP identity namespace) must stay
+     identical across every site in a cluster — MMR replicas can't diverge
+     on base DN — but `CFG_PUBLIC_DOMAIN` overrides just this site's own web
+     hostnames (`sso.*`/`proxy.*`) independently of it. Only meaningful for
+     an inbound spoke serving its own traffic directly.
 3. The spoke pulls the master's full export (LDAP tree, resource catalog,
    agent-signing key) and adopts it, then registers its own reachable URL
    with the master so it can receive live updates going forward.
@@ -82,26 +89,44 @@ so on) are **not** currently synced — each site still generates its own.
 
 - Both sites need a network path to each other's HTTP(S) API — the master to
   pull an export from, the spoke to push replication updates back to. A site
-  with no inbound path at all (e.g. behind CGNAT) can't join yet on its own;
+  with **no inbound path at all** (e.g. behind CGNAT) can still join: set
-  a relay mechanism for that case is designed but not automated (see the
+  `CFG_SPOKE_NO_INBOUND=true` + `CFG_SPOKE_PUBLIC_HOST` (`spoke.env.example`)
-  [architecture spec](https://github.com/theta42/theta-suite/blob/master/docs/MULTI_SITE_SPEC.md)
+  once its jump-host is meshed to the master's over WireGuard (mesh peering
-  for the current status).
+  itself is a manual, one-time step on both jump-hosts — see [Theta Gateway
+  → Mesh](../jump-host/mesh.html)) — the master then relays traffic to it
+  and auto-creates the matching route on its own `theta-proxy`. A spoke with
+  **zero inbound and zero outbound** path still can't join at all (the join
+  itself needs to reach the master's API directly).
 - Joining only ever happens on a **fresh install**. There's no way to merge
   an already-populated directory into a master's — re-provision the host
   first.
+- Promoting a spoke to master doesn't instantly finish reconciling OpenLDAP
+  replication (see below) — re-run `setup.sh` on the newly-promoted node
+  promptly afterward.
 
 ## How this relates to LDAP replication
 
-[N-way LDAP replication](replication.html) is a *lower-level*, different
+[N-way LDAP replication](replication.html) is the *lower-level* mechanism
-mechanism: every site runs a fully independent, fully writable `slapd`, wired
+underneath this: `slapd`'s own `syncrepl`, wired via `LDAP_SERVER_ID` +
-together with raw `syncrepl` environment variables, and there's no concept of
+`LDAP_REPLICATION_HOSTS`. Originally this was hand-configured by the
-a master or a managed join. It predates this feature and is still there for
+operator, separately from the join flow above, for deployments that wanted
-deployments that specifically want every site independently writable.
+every site independently writable with no concept of a master.
 
-Multi-site join (this page) is the opposite design: one write authority, a
+**When you join via this page's flow, that lower-level config is now handled
-managed onboarding flow, and automatic ongoing sync — closer to what most
+for you.** The master auto-assigns each spoke a unique `LDAP_SERVER_ID` at
-"add a second office" or "add a home-lab spoke" setups actually want. **Don't
+join time and derives every site's LDAP URL from its already-known HTTPS
-combine the two** — pick one per deployment.
+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.
+You don't hand-set `LDAP_SERVER_ID`/`LDAP_REPLICATION_HOSTS` for a cluster
+built this way. See [Geo-Location Scaling](replication.html#automatic-config-via-multi-site-join)
+for the mechanics, and its documented limitation: the *master's* own
+replication list only updates on ITS next `setup.sh` run, not live the
+instant a new spoke joins.
+
+Still want fully independent, always-writable sites with no master/spoke
+concept at all? `CFG_LDAP_MMR_MANUAL=true` opts out of the automatic path so
+you can hand-set `LDAP_SERVER_ID`/`LDAP_REPLICATION_HOSTS` directly, same as
+before this integration existed.
 
 ## See also
 

docs/sso/replication.md

@@ -23,33 +23,58 @@ In an N-Way Multi-Master setup, every site runs a fully active OpenLDAP server (
 
 ## Configuration
 
-To enable replication, you must pass two environment variables to the `sso-manager` container:
+The container's entrypoint reads two environment variables to configure this
+-- `LDAP_SERVER_ID` (a unique integer for this node) and
+`LDAP_REPLICATION_HOSTS` (a space-separated list of every **other** node's
+LDAP URL) -- and, when both are set, automatically loads the `syncprov`
+module, enables `mirrormode`, and generates the necessary `syncrepl` blocks
+in `/etc/openldap/slapd.conf`.
 
-1. `LDAP_SERVER_ID`: A unique integer for this node (e.g., `1`, `2`, `3`). This MUST be unique across the cluster.
+### Automatic config via Multi-Site join
-2. `LDAP_REPLICATION_HOSTS`: A space-separated list of the LDAP URLs of all **other** nodes in the cluster.
 
-### Example using `theta-env` / Docker Compose
+**If you're using [Multi-Site join](multi-site.html) (`CFG_MASTER_DIRECTORY_URL`/`spoke.env`),
+you don't set these by hand.** The master assigns each spoke a unique
+`LDAP_SERVER_ID` at join time (the same way it assigns a WireGuard mesh
+index) and derives `LDAP_REPLICATION_HOSTS` from every site's already-known
+HTTPS endpoint (`ldaps://<same-host>:636`) -- `theta-suite`'s `bootstrap/
+site-ldap-register.js` applies it and re-checks on every `setup.sh` run,
+since the peer list grows as new spokes join, restarting `sso-manager` only
+when the computed config actually changed.
 
-**Site 1 (`setup.env` or `docker-compose.yml`)**
+**Known limitation**: the *master's* own `LDAP_REPLICATION_HOSTS` only gets
+recomputed when its `setup.sh` is re-run — there's no live push telling an
+already-running master about a spoke that joined five minutes ago. Re-run
+`setup.sh` on the master after bringing up a new spoke (or after promoting
+one to master) to pick up the current peer list. A spoke's own config, by
+contrast, is re-checked and applied on every `setup.sh` run there, which is
+the common/recurring event.
+
+### Manual configuration
+
+Have a topology outside a `theta-suite`-managed cluster (fully independent,
+always-writable sites, no master/spoke concept)? Set
+`CFG_LDAP_MMR_MANUAL=true` to skip the automatic path entirely and set the
+two variables directly -- without this, the automatic step runs on every
+deployment (every fresh install starts as a master) and will overwrite them.
+
+**Site 1**
 ```env
 LDAP_SERVER_ID=1
 LDAP_REPLICATION_HOSTS="ldaps://sso.site2.com:636 ldaps://sso.site3.com:636"
 ```
 
-**Site 2 (`setup.env` or `docker-compose.yml`)**
+**Site 2**
 ```env
 LDAP_SERVER_ID=2
 LDAP_REPLICATION_HOSTS="ldaps://sso.site1.com:636 ldaps://sso.site3.com:636"
 ```
 
-**Site 3 (`setup.env` or `docker-compose.yml`)**
+**Site 3**
 ```env
 LDAP_SERVER_ID=3
 LDAP_REPLICATION_HOSTS="ldaps://sso.site1.com:636 ldaps://sso.site2.com:636"
 ```
 
-Once configured, the container's entrypoint will automatically load the `syncprov` module, enable `mirrormode`, and generate the necessary `syncrepl` blocks in `/etc/openldap/slapd.conf`.
-
 ## User Locations
 
 When creating or editing a user, you can specify their **Location (Site)**. This maps directly to the standard LDAP `l` (localityName) attribute, allowing you to track which physical site a user belongs to natively within the directory.

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
+# If you're joining a directory cluster (CFG_MASTER_DIRECTORY_URL/spoke.env
-# for directory services, you can enable N-Way Multi-Master OpenLDAP replication.
+# above), N-Way Multi-Master OpenLDAP replication is configured for you
-# This requires assigning a unique ID to each site and listing the LDAPS URLs
+# automatically -- setup.sh's bootstrap/site-ldap-register.js asks the master
-# of all OTHER sites in the cluster.
+# 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).
+# Have a manually-coordinated LDAP MMR topology this script can't derive on
-# LDAP_REPLICATION_HOSTS is a space-separated list of the other sites' LDAP URLs.
+# its own (e.g. peers outside this theta-suite cluster)? Set
-# Example for Site 1:
+# 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}"