Describe v0.8.7

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

.gitea/workflows/release.yml

@@ -55,6 +55,13 @@ jobs:
             (cd dist && sha256sum "${name}" >> checksums.txt)
           done
 
+          # The reverse proxy configurations, so a release page carries
+          # everything install.md asks for and the repository is not needed.
+          for f in deploy/proxy/Caddyfile deploy/proxy/nginx.conf; do
+            cp "$f" dist/
+            (cd dist && sha256sum "$(basename "$f")" >> checksums.txt)
+          done
+
           # An NVML build for nodes with NVLink, which the portable binary
           # cannot serve.
           #

CHANGELOG.md

@@ -18,6 +18,75 @@ is only released once its **exit criterion** is met, not when its code lands.
 Until v1.0.0 the minor version is the breaking one: configuration formats and Go
 APIs change between minors without a deprecation period.
 
+## v0.8.7 — 2026-09-28
+
+### PostgreSQL in one command
+
+```
+sudo llmgw server init --postgres
+```
+
+Installs PostgreSQL with the machine's own package manager when there is none,
+creates the `llmgw` role and database with a generated password kept in
+`/etc/llmgw/secrets/store-dsn`, and checks that it connects. On a control plane
+already running on SQLite it stops the gateway, copies the store across so
+every account and key survives, points `auth.store` at PostgreSQL and starts
+the gateway again; if the move fails, the gateway is started again on SQLite.
+Given on the first run, there is never a SQLite store.
+
+`server.yaml` is edited in place with its comments intact, and the previous
+file is kept beside it. A PostgreSQL that init did not install is left sized as
+it was, since something else may depend on it.
+
+The PostgreSQL installation itself has not yet run on a real machine; the move,
+the configuration edit and the rerun behaviour are tested.
+
+### Fixes
+
+- **A new control plane with no models did not start.** A configuration with
+  no static endpoints and no models was refused as having nothing to serve, so
+  under systemd the unit restarted every two seconds and nothing listened on
+  8080. It now runs as a control plane with an empty catalog.
+
+## v0.8.6 — 2026-09-28
+
+### Reverse proxy configurations
+
+`deploy/proxy/` has a Caddyfile and an nginx configuration for the client
+port, and both are attached to every release beside the binaries. They do not
+buffer streamed replies, their read timeout outlasts a model's wait before its
+first token, their body limit matches the router's, and they set
+`X-Forwarded-Proto` and `X-Forwarded-Host` themselves — llmgw marks session
+cookies `Secure` from the first and shows the second as the base URL on its
+landing page.
+
+## v0.8.5 — 2026-09-28
+
+### A control plane in one command
+
+```
+sudo llmgw server init --admin you@example.com
+```
+
+Creates the llmgw user and its directories, the certificate authority, the
+control plane's certificate for the machine's hostname and every address it
+has, `server.yaml`, the default project, and an administrator whose password is
+generated and printed once — then installs the systemd unit, starts it and
+waits until it answers. What used to be two steps of install.md is now this.
+
+Each step is skipped when its result exists, so running it again finishes an
+install that stopped and changes nothing on one that did not. `--host` adds an
+address the machine cannot see of itself (a DNS alias, a NAT or floating
+address) and reissues the certificate keeping the old ones. It never overwrites
+`server.yaml` or an authority, and certificates issued by an authority kept on
+another machine are left as they are.
+
+### Fixes
+
+- **The configuration install.md showed could not start.** An empty catalog
+  without `control.enabled: true` is refused as having nothing to serve. The
+  documentation and the file `init` writes both set it.
+
 ## v0.8.4 — 2026-09-28
 
 ### Node logs on the admin page

README.md

@@ -66,6 +66,8 @@ on a machine that has them.
   does not exist or miss one that does
 - [deploy/mirror/](deploy/mirror/) — a model mirror, which is the cheapest
   and most useful thing to build around llmgw
+- [deploy/proxy/](deploy/proxy/) — Caddy and nginx in front of the client
+  port, with streaming and the forwarded headers right
 - [deploy/ha/](deploy/ha/) — running two control planes, and the one health
   check that has to be right
 - [docs/node-onboarding.md](docs/node-onboarding.md),

deploy/proxy/Caddyfile

@@ -0,0 +1,41 @@
+# llmgw behind Caddy: the client-facing port (8080) on a public name, with a
+# certificate Caddy obtains and renews by itself.
+#
+# Replace llm.example.com, point its DNS at this machine, open 80 and 443, and
+# run: caddy run --config /etc/caddy/Caddyfile
+#
+# Only 8080 goes through here. 7443 (agents) is mutual TLS with the cluster's
+# own authority and must reach llmgw directly; 9090 and 9091 stay private.
+
+llm.example.com {
+	# The router reads at most 32 MiB of body (router.max_body_bytes). Refusing
+	# more here gives the client a 413 before the upload, not after it.
+	request_body {
+		max_size 32MB
+	}
+
+	reverse_proxy 127.0.0.1:8080 {
+		# Tokens are written the moment they are generated. Without this a
+		# streamed reply can arrive in bursts, and a client measuring time to
+		# first token measures the proxy instead.
+		flush_interval -1
+
+		# Caddy sets X-Forwarded-Proto and X-Forwarded-Host itself and, with
+		# no trusted_proxies, discards whatever the client sent. llmgw relies
+		# on that: the proto decides whether session cookies are Secure, and
+		# the host is the base URL the landing page tells people to use.
+		# Behind a load balancer of your own, name it in trusted_proxies.
+
+		transport http {
+			# A long generation can be silent for a while before the first
+			# token. llmgw has its own limits (timeouts.*); this must not be
+			# the shorter one.
+			response_header_timeout 15m
+		}
+	}
+
+	# No `encode` on purpose: compressing a stream buffers it.
+
+	# Access log to stderr, which under systemd is the journal.
+	log
+}

deploy/proxy/README.md

@@ -0,0 +1,36 @@
+# A reverse proxy in front of llmgw
+
+The client-facing port (8080) is plain HTTP. On anything but a trusted network,
+put it behind a proxy that holds a publicly trusted certificate.
+
+| File | For |
+| --- | --- |
+| [Caddyfile](Caddyfile) | Caddy — obtains and renews its own certificate; the least work |
+| [nginx.conf](nginx.conf) | nginx, with a certificate from certbot |
+
+Both are also attached to every release.
+
+Four things both files get right, and any other proxy has to as well:
+
+- **Streaming is not buffered.** Replies are server-sent events; a buffering
+  proxy delivers them in one burst at the end.
+- **The read timeout is longer than a model's silence.** nginx's default of 60
+  seconds turns a slow first token into a 504.
+- **`X-Forwarded-Proto` and `X-Forwarded-Host` are set by the proxy**, replacing
+  whatever the client sent. llmgw uses the first to mark session cookies
+  `Secure` and the second for the base URL on its landing page.
+- **The body limit matches llmgw's** (32 MiB, `router.max_body_bytes`), so an
+  oversized request is refused before it is uploaded.
+
+Only port 8080 is proxied. Agents reach 7443 directly — it is mutual TLS with
+the cluster's own authority, and a proxy terminating it would take away the
+node identity it carries. 9090 (admin, pprof) stays on loopback; 9091
+(metrics) goes to your monitoring host only.
+
+With a proxy on the same machine, bind llmgw to loopback so nothing reaches it
+around the proxy:
+
+```yaml
+# /etc/llmgw/server.yaml
+listen: "127.0.0.1:8080"
+```

deploy/proxy/nginx.conf

@@ -0,0 +1,63 @@
+# llmgw behind nginx: the client-facing port (8080) on a public name.
+#
+# Put this in /etc/nginx/sites-available/llmgw (or conf.d/llmgw.conf), replace
+# llm.example.com, and get a certificate — certbot --nginx -d llm.example.com
+# fills in the ssl_ lines below. Then: nginx -t && systemctl reload nginx
+#
+# Only 8080 goes through here. 7443 (agents) is mutual TLS with the cluster's
+# own authority and must reach llmgw directly; 9090 and 9091 stay private.
+
+upstream llmgw {
+    server 127.0.0.1:8080;
+    keepalive 32;
+}
+
+server {
+    listen 80;
+    listen [::]:80;
+    server_name llm.example.com;
+    return 301 https://$host$request_uri;
+}
+
+server {
+    # `listen ... http2` rather than `http2 on;`: the latter needs nginx
+    # 1.25.1, and Ubuntu 22.04 and Debian 12 ship older ones. Newer nginx
+    # accepts this form with a deprecation warning.
+    listen 443 ssl http2;
+    listen [::]:443 ssl http2;
+    server_name llm.example.com;
+
+    ssl_certificate     /etc/letsencrypt/live/llm.example.com/fullchain.pem;
+    ssl_certificate_key /etc/letsencrypt/live/llm.example.com/privkey.pem;
+
+    # The router reads at most 32 MiB of body (router.max_body_bytes).
+    client_max_body_size 32m;
+
+    location / {
+        proxy_pass http://llmgw;
+        proxy_http_version 1.1;
+        proxy_set_header Connection "";
+
+        # Set, never appended: llmgw decides from X-Forwarded-Proto whether
+        # session cookies are Secure, and builds the base URL the landing page
+        # shows from X-Forwarded-Host. A value passed through from the client
+        # would be the client's choice.
+        proxy_set_header Host              $host;
+        proxy_set_header X-Forwarded-Host  $host;
+        proxy_set_header X-Forwarded-Proto $scheme;
+        proxy_set_header X-Forwarded-For   $proxy_add_x_forwarded_for;
+
+        # Streamed replies: tokens go out as they are generated. Buffering
+        # turns a stream into one late burst, and gzip buffers too.
+        proxy_buffering off;
+        proxy_cache off;
+        gzip off;
+
+        # nginx's default is 60 seconds between two reads from upstream. A
+        # large model can think longer than that before its first token, and
+        # the client then sees a 504 for a request that was about to succeed.
+        # llmgw has its own limits (timeouts.*); this must not be the shorter.
+        proxy_read_timeout 15m;
+        proxy_send_timeout 15m;
+    }
+}

docs/install.md

@@ -29,7 +29,7 @@ The reason is boring and unavoidable: drivers and engines are platform decisions
 with kernel modules and version matrices attached.
 
 Weights are the one item on that list llmgw does handle. It includes a mirror —
-step 4 — which holds the files on your own network and hands them to the nodes,
+step 3 — which holds the files on your own network and hands them to the nodes,
 so getting weights onto every machine is not a problem you solve before
 starting. What llmgw will not do is choose the models for you.
 
@@ -58,7 +58,8 @@ them, so nodes need no inbound access except your own SSH.
 | 8082 | the control plane administering the mirror | the control plane only — this port can delete models and start downloads |
 
 Decide now which address nodes will use to reach the control plane. It goes into
-a certificate and changing it later means reissuing one.
+a certificate: the machine's own addresses are found for you, and any other name
+— a DNS alias, a NAT or floating address — has to be given with `--host`.
 
 ## 1. The binary
 
@@ -83,141 +84,110 @@ git clone https://gitea.mynodes.xyz/ilker/llmgw && cd llmgw
 CGO_ENABLED=0 go build -o llmgw ./cmd/llmgw
 ```
 
-## 2. The certificate authority
+## 2. The control plane
 
-Agents authenticate to the control plane with mutual TLS, and a node's identity
-is taken from its certificate's common name. A public authority cannot supply
-these: Let's Encrypt and its peers stopped issuing certificates carrying the
-`clientAuth` usage, so nothing they hand out can authenticate an agent.
-
-Run this wherever you intend to keep the authority. It talks to nothing and
-works on files, so it does not have to be a cluster machine — and there is an
-argument that it should not be.
+On the machine that will be the control plane, as root:
 
 ```
-sudo llmgw ctl cert init-ca --dir /etc/llmgw/pki
+sudo llmgw server init --admin you@example.com
 ```
 
-That writes `ca.pem` and `ca-key.pem`. **Whoever holds `ca-key.pem` can mint any
-node's identity**, so it stays here; `ca.pem` is copied to every machine and is
-not a secret.
+That is the whole step. In order, it:
 
-Now the control plane's own certificate. Every address an agent might dial must
-appear in `--host`, bare IP addresses included — hostname verification reads
-subject alternative names and ignores the common name entirely, so a certificate
-naming the host only in its subject is rejected by every client:
+1. creates the `llmgw` system user, `/etc/llmgw` and `/var/lib/llmgw`
+2. creates the cluster's certificate authority in `/etc/llmgw/pki`
+3. issues the control plane's certificate for this machine's hostname and
+   every address it has, and copies `ca.pem` beside it
+4. writes `/etc/llmgw/server.yaml`: mutual TLS, authentication, default limits
+   and a price, and a control plane with an empty catalog
+5. creates the store, the `default` project, and your account, already approved
+   and promoted to administrator — the password is generated and **printed
+   once**
+6. installs the systemd unit, starts it, and waits until `/health` answers
+
+Add `--postgres` to keep accounts and keys in PostgreSQL rather than SQLite:
+init installs it and sets it up, and on a machine already running on SQLite it
+moves everything across. See [PostgreSQL](#postgresql-when-sqlite-is-no-longer-the-right-shape).
+
+Every step looks before it acts. Running it again finishes an install that
+stopped halfway and changes nothing on one that did not; it never overwrites
+`server.yaml`, the authority, or an existing account's password.
+
+**The addresses in the certificate matter.** Agents check that the address
+they dial is named in it, and the certificate names only what this machine
+could see of itself. If nodes will reach it by another name — a DNS alias, a
+NAT address, a floating IP — give it:
 
 ```
-sudo llmgw ctl cert issue-server llmgw-ctl \
-  --host 10.0.0.140 --host llmgw-ctl.internal \
-  --dir /etc/llmgw/pki --out /etc/llmgw
+sudo llmgw server init --host llmgw-ctl.internal --host 203.0.113.10
 ```
 
+Run that at any time: the certificate is reissued with the new names added to
+the old ones, and the service restarted.
+
+**`ca-key.pem` signs every node's identity.** `init` leaves it in
+`/etc/llmgw/pki`, because onboarding a node needs it and the control plane is
+where most people run onboarding from. Back it up; there is no recovering it.
+If this machine is exposed, move the directory elsewhere once the nodes are in
+and pass `--pki` to onboarding.
+
 This covers the fleet-facing port only. The client-facing API is public and
-belongs behind an ordinary publicly trusted certificate, usually terminated by a
-reverse proxy in front of port 8080.
-
-## 3. The control plane
-
-### The user and directories
-
-```
-sudo useradd --system --home /var/lib/llmgw --shell /usr/sbin/nologin llmgw
-sudo install -d -o llmgw -g llmgw -m 0750 /var/lib/llmgw
-sudo install -d -m 0755 /etc/llmgw
-sudo chown root:llmgw /etc/llmgw/ca.pem /etc/llmgw/server.pem /etc/llmgw/server-key.pem
-sudo chmod 0640 /etc/llmgw/server-key.pem
-```
-
-### The configuration
-
-`/etc/llmgw/server.yaml`. This is the smallest file that is not a toy: mutual
-TLS on, authentication on, one model, and limits that apply to anyone nobody has
-given limits to.
-
-```yaml
-listen: ":8080"
-admin_listen: "127.0.0.1:9090"
-agent_listen: ":7443"
-
-agent_tls:
-  ca: /etc/llmgw/ca.pem
-  cert: /etc/llmgw/server.pem
-  key: /etc/llmgw/server-key.pem
-
-auth:
-  enabled: true
-  store: /var/lib/llmgw/llmgw.db
-  signup_open: true
-  # Applied to any key no scope gives a limit to. Without these, a project
-  # created without limits is metered by nothing at all, and the first sign of
-  # that is the bill or the outage.
-  default_rpm: 60
-  default_tpm: 200000
-  # What a request costs, which is what makes a budget mean anything. Without
-  # a price every request costs zero, so a budget is displayed, counted against
-  # nothing, and never binds — and nobody finds out until they expected it to
-  # stop something. Self-hosted models have no per-token price, so the unit is
-  # yours to choose: GPU-seconds, a notional rate, or 1000 everywhere, which
-  # turns a budget into a plain token quota.
-  default_price:
-    prompt_per_1k: 1000
-    completion_per_1k: 1000
-  # pricing:
-  #   qwen2.5-coder-7b-instruct: { prompt_per_1k: 500, completion_per_1k: 1500 }
-
-landing:
-  contact: "platform@example.com"
-
-# Start with none. Models are added while the cluster runs — see step 8 —
-# and anything listed here is declarative: it is in the catalog on every start
-# and cannot be removed without editing this file.
-models: []
-```
-
-`admin_listen` is on loopback on purpose. It serves pprof, which can dump the
-process heap, and API keys sit in that heap in plaintext. To see the dashboard
-from elsewhere, promote an account and use `/admin` on the client port — do not
-move this listener.
-
-The store file is created on first start; there is no separate migration step.
-
-### The service
-
-```
-sudo cp deploy/systemd/llmgw-server.service /etc/systemd/system/
-sudo systemctl daemon-reload
-sudo systemctl enable --now llmgw-server
-systemctl status llmgw-server
-```
-
-### Your account
-
-Accounts are created and approved from a shell on this machine, deliberately:
-having a shell here is what makes someone an administrator, and there are no
-roles to get subtly wrong.
-
-```
-sudo -u llmgw llmgw users create you@example.com --password 'change me now'
-# prints a user id, usr-xxxxxxxx
-sudo -u llmgw llmgw users promote usr-xxxxxxxx
-```
-
-`promote` is what grants `/admin`. Sign in at `http://<control-plane>:8080/login`,
-change the password, and issue yourself a key from the profile page.
+belongs behind an ordinary publicly trusted certificate, terminated by a
+reverse proxy in front of port 8080. [deploy/proxy/](../deploy/proxy/) has a
+Caddyfile and an nginx configuration that get streaming, timeouts and the
+forwarded headers right; both are attached to every release.
 
 ### Check it
 
 ```
-curl -s -o /dev/null -w '%{http_code}\n' http://127.0.0.1:8080/health   # 200, with an empty body
-sudo -u llmgw llmgw ctl status
+curl -s -o /dev/null -w '%{http_code}\n' http://127.0.0.1:8080/health   # 200
+llmgw ctl status
 ```
 
 `ctl status` will report no nodes and no models, which is correct — nothing has
-been added yet. It is worth running now so its output is familiar before you
-need it.
+been added yet. Sign in at `http://<control-plane>:8080/login` with the printed
+password, change it, and issue yourself a key from the profile page.
 
-## 4. The mirror
+### The configuration
+
+`/etc/llmgw/server.yaml` is yours from here on. Three things in it are worth
+knowing before you edit it:
+
+- `admin_listen` is on loopback on purpose. It serves pprof, which can dump the
+  process heap, and API keys sit in that heap in plaintext. To see the dashboard
+  from elsewhere use `/admin` on the client port — do not move this listener.
+- `default_rpm`, `default_tpm` and `default_price` are what make limits and
+  budgets mean anything. Without a price every request costs zero and a budget
+  never binds; without the defaults, a project created without limits is
+  metered by nothing at all.
+- `control.enabled: true` is what makes this a control plane while its catalog
+  is empty. Without it, a file with no models is refused as having nothing to
+  serve.
+
+Every key is in [reference.md](reference.md).
+
+### Keeping the authority off the control plane
+
+Create it on another machine, issue the control plane's certificate there, and
+bring only the results:
+
+```
+# on the authority's machine
+llmgw ctl cert init-ca --dir /etc/llmgw/pki
+llmgw ctl cert issue-server llmgw-ctl --host 10.0.0.140 --host llmgw-ctl.internal \
+  --dir /etc/llmgw/pki --out ./ctl
+
+# copy ca.pem, ctl/server.pem and ctl/server-key.pem into /etc/llmgw on the
+# control plane, then there:
+sudo llmgw server init --admin you@example.com
+```
+
+`init` finds certificates in `/etc/llmgw` and no authority beside them, and
+keeps them as they are. Adding an address later is then done where the
+authority is; `init --host` says so rather than minting a second authority no
+node trusts.
+
+## 3. The mirror
 
 Do this before the nodes, not after. Every node fetches its own copy of a
 model's weights, and where they fetch from decides whether bringing up a cluster
@@ -313,7 +283,7 @@ llmgw mirror fetch --model qwen2.5-14b-instruct --version 2026-03 \
 or from the admin page, or by copying files into the directory by hand — the
 mirror is a directory, and anything that puts files in it works.
 
-## 5. Preparing a node
+## 4. Preparing a node
 
 **Do this before onboarding.** A node missing its driver or engine registers
 healthy and fails on first placement, and the reason is three logs away.
@@ -418,7 +388,7 @@ llmgw ctl engine-check vllm --bin /opt/venvs/vllm/bin/vllm
 
 ### Weights
 
-Nothing to do here if you built the mirror in step 4 — the agent fetches what a
+Nothing to do here if you built the mirror in step 3 — the agent fetches what a
 model's `source` names, and that source is your mirror. This section is for the
 arrangements where the files are already on the machine.
 
@@ -441,7 +411,7 @@ model's `source` at a file to download and the agent fetches it once, before the
 engine is launched:
 
 ```yaml
-# your mirror, which is what step 4 was for
+# your mirror, which is what step 3 was for
 source: http://models.internal:8081/qwen2.5-coder-3b-instruct/2026-03/q4_k_m.gguf
 # a whole version, for a model of several files — the trailing slash is the signal
 source: http://models.internal:8081/llama-3.1-70b-instruct/2026-03/
@@ -498,7 +468,7 @@ How much disk a node needs follows from the models rather than a rule of thumb.
 `llmgw ctl model plan <repo>` prints the sizes; as a starting point, a 70B at
 bf16 is 141 GB and the same model at q4 is 43 GB.
 
-## 6. Adding the node
+## 5. Adding the node
 
 Two halves, because they need different access: building the machine needs the
 hypervisor, and issuing its identity needs the certificate authority. Where one
@@ -555,7 +525,7 @@ Repeat for each node. Nodes in the same fabric must be given the same `--fabric`
 name; nodes with no InfiniBand take no `--fabric` at all and are each their own
 island, which is fine for single-node models.
 
-## 7. Setting the node's CPU model, if it is a VM
+## 6. Setting the node's CPU model, if it is a VM
 
 Proxmox defaults a VM to `kvm64`, which hides AVX, AVX2, FMA and even SSE4.2
 from the guest. Inference then falls back to scalar code and is not slightly
@@ -572,7 +542,7 @@ only change being `--cpu host`:
 probably did not, and nothing about it looks broken — every number is simply
 small. Check with `grep -qw avx2 /proc/cpuinfo` on the node.
 
-## 8. Adding a model
+## 7. Adding a model
 
 Write the definition. This is the same shape a model takes in `server.yaml`, so
 an entry moves between the two by being copied:
@@ -714,7 +684,7 @@ An engine that publishes no metrics endpoint is measured from the outside only.
 The run says so, and queue depth and KV occupancy are then not part of the
 answer.
 
-## 9. The first request
+## 8. The first request
 
 ```
 curl http://<control-plane>:8080/v1/chat/completions \
@@ -777,6 +747,20 @@ turn, which is the first per-request load this store has had; and SQLite takes
 one writer at a time, so those turns serialise. And a second control plane is
 impossible while the store is a file on one machine's disk.
 
+On the control plane, one command does all of it — installs PostgreSQL if the
+machine has none, creates its role and database with a generated password kept
+in `/etc/llmgw/secrets/store-dsn`, stops the gateway, copies the SQLite store
+into it so every account and key survives, points `server.yaml` at it, and
+starts the gateway again:
+
+```
+sudo llmgw server init --postgres
+```
+
+It can be given on the first run too, and then there is never a SQLite store.
+The rest of this section is what that command does, for a PostgreSQL somewhere
+else.
+
 The setting is the same one, and the address decides:
 
 ```yaml
@@ -957,7 +941,7 @@ the choice is yours rather than silent.
 
 Three things, in descending order of how badly you want them.
 
-**The certificate authority.** `ca-key.pem`, wherever you put it in step 2.
+**The certificate authority.** `ca-key.pem`, `/etc/llmgw/pki` unless you kept it elsewhere (step 2).
 Losing it does not stop the cluster, and it means every node identity has to be
 reissued the next time you touch one. Nothing in llmgw can reconstruct it.
 
@@ -1028,7 +1012,7 @@ output, which is the actual diagnosis.
 node and the reason: wrong GPU class, not enough free cards, too little memory,
 no fabric, a label it does not carry.
 
-**Everything is slow.** On a VM, check AVX2 (step 7). On CPU, check the
+**Everything is slow.** On a VM, check AVX2 (step 6). On CPU, check the
 quantisation — the difference between `q8_0` and `q4_k_m` is roughly a factor of
 two. `llmgw ctl status` shows how full the cluster is.
 
@@ -1065,7 +1049,7 @@ requests. On a slow model, set `timeouts.generation` higher.
   those eight local, which is most of the problem; on a fabric where the nodes
   can see each other, seeding between them is the obvious next thing to build.
 - **A budget without a price never binds.** Set `default_price` or `pricing`
-  (step 3) or every request costs zero, and a budget is something the dashboard
+  (step 2) or every request costs zero, and a budget is something the dashboard
   displays rather than something that stops anything. The quotas page says so
   where it can, which is not the same as being told before you rely on it.
 - **Engines are yours to install.** Onboarding verifies one runs; it installs

internal/agent/provision/install.go

@@ -290,6 +290,14 @@ func (in *Installer) packages(ctx context.Context, byFamily map[string][]string,
 	return nil
 }
 
+// InstallPackages installs whichever of these packages the machine lacks,
+// from its own package sources, waiting out another package manager's lock.
+// byFamily is keyed by discovery.Host.Family: "deb" or "rpm".
+func (in *Installer) InstallPackages(ctx context.Context, byFamily map[string][]string) error {
+	var st Status
+	return in.packages(ctx, byFamily, &st)
+}
+
 // lockWait bounds how long a package command waits for another to finish.
 const lockWait = 10 * time.Minute
 

internal/cli/server.go

@@ -350,6 +350,7 @@ func newServerCmd() *cobra.Command {
 	f.StringVar(&metricsListen, "metrics-listen", "", "serve metrics only on this address, safe to expose")
 	f.StringArrayVar(&endpoints, "endpoint", nil, "static endpoint: id=URL=model[,model] (repeatable)")
 
+	cmd.AddCommand(newServerInitCmd())
 	return cmd
 }
 

internal/cli/serverinit.go

@@ -0,0 +1,622 @@
+package cli
+
+import (
+	"context"
+	"crypto/rand"
+	"encoding/base32"
+	"errors"
+	"fmt"
+	"io"
+	"net"
+	"net/http"
+	"os"
+	"os/exec"
+	"os/user"
+	"path/filepath"
+	"runtime"
+	"slices"
+	"strconv"
+	"strings"
+	"time"
+
+	"github.com/spf13/cobra"
+
+	"gitea.mynodes.xyz/ilker/llmgw/internal/account"
+	"gitea.mynodes.xyz/ilker/llmgw/internal/config"
+	"gitea.mynodes.xyz/ilker/llmgw/internal/store"
+	"gitea.mynodes.xyz/ilker/llmgw/internal/tlsconf"
+)
+
+// serverUnit is deploy/systemd/llmgw-server.service. A test holds the two
+// together, because a machine set up by init and one set up from the docs
+// should not differ in a way nobody chose.
+const serverUnit = `[Unit]
+Description=llmgw control plane
+After=network-online.target
+Wants=network-online.target
+
+[Service]
+ExecStart=/usr/local/bin/llmgw server --config /etc/llmgw/server.yaml
+User=llmgw
+Group=llmgw
+Restart=on-failure
+RestartSec=2s
+NoNewPrivileges=true
+ProtectSystem=strict
+ProtectHome=true
+PrivateTmp=true
+StateDirectory=llmgw
+
+[Install]
+WantedBy=multi-user.target
+`
+
+// serverInit is everything a control plane needs before it can start, done in
+// the order it has to be done in. Every step looks before it acts, so running
+// it again finishes an install that stopped halfway and changes nothing on
+// one that did not.
+type serverInit struct {
+	etcDir   string // /etc/llmgw
+	stateDir string // /var/lib/llmgw
+	pkiDir   string // where the authority lives
+	unitPath string // "" leaves systemd alone
+
+	// user owns the state and reads the key; "" means no user is created and
+	// nothing is chowned, which is what a test wants.
+	user  string
+	hosts []string
+	admin string
+	// postgres keeps the store in a PostgreSQL on this machine, installed if
+	// need be, moving whatever SQLite already holds.
+	postgres bool
+	// pgSetup prepares PostgreSQL and returns the store address; a seam for
+	// tests. Nil does it for real.
+	pgSetup func(context.Context) (string, error)
+
+	out io.Writer
+
+	uid, gid int
+	changed  bool
+}
+
+func newServerInitCmd() *cobra.Command {
+	in := serverInit{
+		etcDir:   "/etc/llmgw",
+		stateDir: "/var/lib/llmgw",
+		pkiDir:   defaultPKIDir,
+		unitPath: "/etc/systemd/system/llmgw-server.service",
+		user:     "llmgw",
+	}
+	cmd := &cobra.Command{
+		Use:   "init",
+		Short: "Set this machine up as a control plane and start it",
+		Long: "Creates the llmgw user and its directories, a certificate authority, the\n" +
+			"control plane's certificate for every address this machine has, a\n" +
+			"configuration, an administrator account, and the systemd unit — then\n" +
+			"starts it and waits until it answers.\n\n" +
+			"With --postgres the store is a PostgreSQL database on this machine:\n" +
+			"installed if there is none, with its own role and a generated password\n" +
+			"kept in /etc/llmgw/secrets. An existing SQLite store is copied into it,\n" +
+			"so accounts and keys survive, and server.yaml is pointed at it.\n\n" +
+			"Each step is skipped when its result already exists, so it is safe to run\n" +
+			"again: to finish an install that stopped, or with another --host to\n" +
+			"reissue the certificate. It never overwrites server.yaml or the authority.\n\n" +
+			"The authority's key stays in " + defaultPKIDir + " on this machine. Move it\n" +
+			"somewhere safer once the nodes are onboarded if this machine is exposed.",
+		Args: cobra.NoArgs,
+		RunE: func(cmd *cobra.Command, _ []string) error {
+			if runtime.GOOS != "linux" {
+				return fmt.Errorf("init sets up a Linux machine; this is %s", runtime.GOOS)
+			}
+			if os.Geteuid() != 0 {
+				return errors.New("init creates a user, writes /etc and starts a service: run it as root")
+			}
+			in.out = cmd.OutOrStdout()
+			return in.run(cmd.Context())
+		},
+	}
+	f := cmd.Flags()
+	f.StringArrayVar(&in.hosts, "host", nil,
+		"an address agents dial besides the ones found on this machine; repeatable")
+	f.StringVar(&in.admin, "admin", "", "email of the first administrator; a password is generated and printed once")
+	f.StringVar(&in.pkiDir, "pki", in.pkiDir, "directory holding the certificate authority")
+	f.BoolVar(&in.postgres, "postgres", false,
+		"keep the store in PostgreSQL on this machine, installing it and moving an existing SQLite store into it")
+	return cmd
+}
+
+func (in *serverInit) run(ctx context.Context) error {
+	steps := []struct {
+		name string
+		fn   func(context.Context) error
+	}{
+		{"user", in.ensureUser},
+		{"directories", in.ensureDirs},
+		{"certificates", in.ensureCerts},
+		{"configuration", in.ensureConfig},
+		{"database", in.ensureDatabase},
+		{"store", in.ensureStore},
+	}
+	for _, s := range steps {
+		if err := s.fn(ctx); err != nil {
+			return fmt.Errorf("%s: %w", s.name, err)
+		}
+	}
+	if in.unitPath == "" {
+		return nil
+	}
+	if err := in.ensureService(ctx); err != nil {
+		return fmt.Errorf("service: %w", err)
+	}
+	in.nextSteps()
+	return nil
+}
+
+func (in *serverInit) done(format string, a ...any) {
+	fmt.Fprintf(in.out, "  ok    "+format+"\n", a...)
+	in.changed = true
+}
+
+func (in *serverInit) kept(format string, a ...any) {
+	fmt.Fprintf(in.out, "  kept  "+format+"\n", a...)
+}
+
+func (in *serverInit) ensureUser(context.Context) error {
+	if in.user == "" {
+		return nil
+	}
+	u, err := user.Lookup(in.user)
+	if err != nil {
+		var unknown user.UnknownUserError
+		if !errors.As(err, &unknown) {
+			return err
+		}
+		out, err := exec.Command("useradd", "--system", "--home", in.stateDir,
+			"--shell", "/usr/sbin/nologin", in.user).CombinedOutput()
+		if err != nil {
+			return fmt.Errorf("useradd: %v: %s", err, strings.TrimSpace(string(out)))
+		}
+		if u, err = user.Lookup(in.user); err != nil {
+			return err
+		}
+		in.done("system user %s", in.user)
+	} else {
+		in.kept("system user %s", in.user)
+	}
+	in.uid, _ = strconv.Atoi(u.Uid)
+	in.gid, _ = strconv.Atoi(u.Gid)
+	return nil
+}
+
+func (in *serverInit) ensureDirs(context.Context) error {
+	for _, d := range []struct {
+		path  string
+		mode  os.FileMode
+		owned bool
+	}{
+		{in.etcDir, 0o755, false},
+		{in.pkiDir, 0o700, false},
+		{in.stateDir, 0o750, true},
+	} {
+		if err := os.MkdirAll(d.path, d.mode); err != nil {
+			return err
+		}
+		if d.owned {
+			if err := in.chown(d.path, true); err != nil {
+				return err
+			}
+		}
+	}
+	return nil
+}
+
+// chown gives a path to the service user, or only its group when the user
+// should read and not write.
+func (in *serverInit) chown(path string, own bool) error {
+	if in.user == "" {
+		return nil
+	}
+	uid := 0
+	if own {
+		uid = in.uid
+	}
+	return os.Chown(path, uid, in.gid)
+}
+
+func (in *serverInit) ensureCerts(context.Context) error {
+	certPath := filepath.Join(in.etcDir, "server.pem")
+	_, keyErr := os.Stat(filepath.Join(in.pkiDir, "ca-key.pem"))
+	_, caErr := os.Stat(filepath.Join(in.etcDir, "ca.pem"))
+	_, certErr := os.Stat(certPath)
+	if keyErr != nil && caErr == nil && certErr == nil {
+		// Issued by an authority kept elsewhere, which is the arrangement for
+		// anyone who will not have the CA key on the control plane. Making a
+		// new authority here would replace their certificate with one no node
+		// trusts.
+		if len(in.hosts) > 0 {
+			return fmt.Errorf("%s was issued by an authority that is not in %s; "+
+				"reissue it there with the new --host", certPath, in.pkiDir)
+		}
+		in.kept("certificates in %s, issued elsewhere", in.etcDir)
+		return nil
+	}
+
+	var (
+		ca  *tlsconf.CA
+		err error
+	)
+	if keyErr == nil {
+		if ca, err = loadCA(in.pkiDir); err != nil {
+			return err
+		}
+		in.kept("certificate authority in %s", in.pkiDir)
+	} else {
+		if ca, err = tlsconf.NewCA("llmgw cluster CA"); err != nil {
+			return err
+		}
+		if err := ca.Write(in.pkiDir); err != nil {
+			return err
+		}
+		in.done("certificate authority in %s (ca-key.pem signs every node: back it up)", in.pkiDir)
+	}
+	if err := os.WriteFile(filepath.Join(in.etcDir, "ca.pem"), ca.PEM, 0o644); err != nil {
+		return err
+	}
+
+	want := in.certHosts()
+	if cert, err := readCert(certPath); err == nil {
+		have := strings.Split(sanNames(cert), ", ")
+		var missing []string
+		for _, h := range want {
+			if !slices.Contains(have, h) {
+				missing = append(missing, h)
+			}
+		}
+		// A certificate from this authority naming every address is left
+		// alone. One naming fewer is reissued with the union, so an address
+		// that worked yesterday is never dropped by adding one today.
+		if len(missing) == 0 && cert.CheckSignatureFrom(ca.Cert) == nil {
+			in.kept("server certificate for %s", strings.Join(have, ", "))
+			return nil
+		}
+		for _, h := range have {
+			if h != "" && !slices.Contains(want, h) {
+				want = append(want, h)
+			}
+		}
+	}
+
+	name, _ := os.Hostname()
+	if name == "" {
+		name = "llmgw-control"
+	}
+	leaf, err := ca.IssueServer(name, want)
+	if err != nil {
+		return err
+	}
+	if err := leaf.Write(in.etcDir, "server"); err != nil {
+		return err
+	}
+	// The service runs as llmgw and must read its key; nothing else should.
+	keyPath := filepath.Join(in.etcDir, "server-key.pem")
+	if err := in.chown(keyPath, false); err != nil {
+		return err
+	}
+	if in.user != "" {
+		if err := os.Chmod(keyPath, 0o640); err != nil {
+			return err
+		}
+	}
+	in.done("server certificate for %s", strings.Join(want, ", "))
+	return nil
+}
+
+// certHosts is every address an agent could plausibly dial: the hostname and
+// each address on this machine, plus whatever --host added. Asking the
+// operator to list them is how a certificate ends up naming the one address
+// nobody uses, and that is found out by the first node refusing it.
+func (in *serverInit) certHosts() []string {
+	var out []string
+	add := func(h string) {
+		if h != "" && !slices.Contains(out, h) {
+			out = append(out, h)
+		}
+	}
+	for _, h := range in.hosts {
+		add(h)
+	}
+	if name, err := os.Hostname(); err == nil {
+		add(name)
+	}
+	for _, ip := range localAddrs() {
+		add(ip.String())
+	}
+	return out
+}
+
+// localAddrs are this machine's addresses another machine could reach:
+// loopback and link-local are left out.
+func localAddrs() []net.IP {
+	addrs, err := net.InterfaceAddrs()
+	if err != nil {
+		return nil
+	}
+	var out []net.IP
+	for _, a := range addrs {
+		n, ok := a.(*net.IPNet)
+		if !ok || !n.IP.IsGlobalUnicast() {
+			continue
+		}
+		out = append(out, n.IP)
+	}
+	return out
+}
+
+func (in *serverInit) configPath() string { return filepath.Join(in.etcDir, "server.yaml") }
+
+func (in *serverInit) ensureConfig(context.Context) error {
+	path := in.configPath()
+	if _, err := os.Stat(path); err == nil {
+		in.kept("%s (never overwritten)", path)
+	} else {
+		contact := in.admin
+		if contact == "" {
+			contact = "platform@example.com"
+		}
+		body := fmt.Sprintf(serverConfigTemplate, in.etcDir, in.etcDir, in.etcDir,
+			in.storeAddress(), contact)
+		if err := os.WriteFile(path, []byte(body), 0o640); err != nil {
+			return err
+		}
+		if err := in.chown(path, false); err != nil {
+			return err
+		}
+		in.done("%s", path)
+	}
+
+	// Checked whether written now or years ago: a configuration that will not
+	// load is better found here than as a unit restarting every two seconds.
+	cfg, err := config.Load(path)
+	if err != nil {
+		return err
+	}
+	if err := cfg.Validate(); err != nil {
+		return fmt.Errorf("%s: %w", path, err)
+	}
+	return nil
+}
+
+// serverConfigTemplate is the smallest file that is not a toy: mutual TLS,
+// authentication, default limits and a price, and a control plane with an
+// empty catalog.
+const serverConfigTemplate = `# Written by 'llmgw server init'. Every key: docs/reference.md
+listen: ":8080"
+admin_listen: "127.0.0.1:9090"   # serves pprof, which can dump API keys: keep it local
+agent_listen: ":7443"
+
+agent_tls:
+  ca: %s/ca.pem
+  cert: %s/server.pem
+  key: %s/server-key.pem
+
+# A control plane with nothing in its catalog yet. Models are added while it
+# runs, with 'llmgw ctl model add' or from /admin/mirror.
+control:
+  enabled: true
+
+auth:
+  enabled: true
+  store: "%s"   # a SQLite path, or @file holding a PostgreSQL address
+  signup_open: true
+  # Applied to any key no scope gives a limit to. Without them, a project
+  # created without limits is metered by nothing at all.
+  default_rpm: 60
+  default_tpm: 200000
+  # Without a price every request costs zero and no budget ever binds. 1000
+  # everywhere turns a budget into a plain token quota.
+  default_price:
+    prompt_per_1k: 1000
+    completion_per_1k: 1000
+
+landing:
+  contact: "%s"
+
+# The engines every node installs for itself. Omitted, each gets the llama.cpp
+# build this release was checked against.
+# engines:
+#   llamacpp: b10991
+
+# A model mirror, once there is one (docs/install.md, step 3):
+# mirror:
+#   api: https://models.internal:8082
+#   tls: { ca: /etc/llmgw/ca.pem, cert: /etc/llmgw/server.pem, key: /etc/llmgw/server-key.pem }
+`
+
+func (in *serverInit) ensureStore(ctx context.Context) error {
+	cfg, err := config.Load(in.configPath())
+	if err != nil {
+		return err
+	}
+	address := cfg.Auth.Store
+	if address == "" {
+		address = filepath.Join(in.stateDir, "llmgw.db")
+	}
+	s, err := store.Open(ctx, address)
+	if err != nil {
+		return fmt.Errorf("opening %s: %w", address, err)
+	}
+	// Opened as root, so a SQLite file created just now belongs to root and
+	// the service could not write it. Given back before anything else runs.
+	defer in.chownSQLite(address)
+	defer s.Close()
+
+	// The tree an approved account hangs off. Approving into a project that
+	// does not exist succeeds, and the first key that person makes does not.
+	if err := s.PutOrg(ctx, store.Org{ID: "default", Name: "default"}); err != nil {
+		return err
+	}
+	if err := s.PutTeam(ctx, store.Team{ID: "default", OrgID: "default", Name: "default"}); err != nil {
+		return err
+	}
+	if err := s.PutProject(ctx, store.Project{ID: "default", TeamID: "default", Name: "default"}); err != nil {
+		return err
+	}
+
+	if in.admin == "" {
+		in.kept("store at %s (no --admin: create an account with 'llmgw users create')", address)
+		return nil
+	}
+	if u, err := s.UserByEmail(ctx, in.admin); err == nil {
+		if !u.IsAdmin {
+			if err := s.SetAdmin(ctx, u.ID, true); err != nil {
+				return err
+			}
+		}
+		in.kept("administrator %s (%s); its password is unchanged", in.admin, u.ID)
+		return nil
+	} else if !errors.Is(err, store.ErrNotFound) {
+		return err
+	}
+
+	password := randomPassword()
+	hash, err := account.HashPassword(password)
+	if err != nil {
+		return err
+	}
+	id := randomID("usr")
+	now := time.Now()
+	if err := s.CreateUser(ctx, store.User{
+		ID: id, Email: in.admin, Name: in.admin,
+		PasswordHash: hash, State: store.UserPending, CreatedAt: now,
+	}); err != nil {
+		return err
+	}
+	if err := s.ApproveUser(ctx, id, "default", "init", now); err != nil {
+		return err
+	}
+	if err := s.SetAdmin(ctx, id, true); err != nil {
+		return err
+	}
+	in.done("administrator %s (%s)", in.admin, id)
+	fmt.Fprintf(in.out, "\n        password: %s\n        shown once — sign in and change it from /profile\n\n", password)
+	return nil
+}
+
+func (in *serverInit) chownSQLite(address string) {
+	if strings.Contains(address, "://") || strings.HasPrefix(address, "@") {
+		return
+	}
+	for _, suffix := range []string{"", "-wal", "-shm"} {
+		if _, err := os.Stat(address + suffix); err == nil {
+			_ = in.chown(address+suffix, true)
+		}
+	}
+}
+
+func randomPassword() string {
+	var buf [15]byte
+	_, _ = rand.Read(buf[:])
+	return strings.ToLower(base32.StdEncoding.WithPadding(base32.NoPadding).EncodeToString(buf[:]))
+}
+
+func (in *serverInit) ensureService(ctx context.Context) error {
+	if _, err := exec.LookPath("systemctl"); err != nil {
+		fmt.Fprintf(in.out, "  skip  no systemd here; start it with:\n"+
+			"        sudo -u %s llmgw server --config %s\n", in.user, in.configPath())
+		return nil
+	}
+	if b, err := os.ReadFile(in.unitPath); err == nil && string(b) == serverUnit {
+		in.kept("%s", in.unitPath)
+	} else {
+		if err == nil {
+			// Somebody's edits. Kept beside it, because the unit is also where
+			// people put environment overrides and those are not ours to lose.
+			_ = os.WriteFile(in.unitPath+".bak", b, 0o644)
+		}
+		if err := os.WriteFile(in.unitPath, []byte(serverUnit), 0o644); err != nil {
+			return err
+		}
+		in.done("%s", in.unitPath)
+	}
+
+	systemctl := func(args ...string) error {
+		out, err := exec.CommandContext(ctx, "systemctl", args...).CombinedOutput()
+		if err != nil {
+			return fmt.Errorf("systemctl %s: %v: %s", strings.Join(args, " "), err, strings.TrimSpace(string(out)))
+		}
+		return nil
+	}
+	if err := systemctl("daemon-reload"); err != nil {
+		return err
+	}
+	active := exec.CommandContext(ctx, "systemctl", "is-active", "--quiet", "llmgw-server").Run() == nil
+	switch {
+	case !active:
+		if err := systemctl("enable", "--now", "llmgw-server"); err != nil {
+			return err
+		}
+		in.done("llmgw-server started")
+	case in.changed:
+		// A certificate or configuration it has not read is one it is not
+		// using, and the difference shows up as a node that cannot connect.
+		if err := systemctl("restart", "llmgw-server"); err != nil {
+			return err
+		}
+		in.done("llmgw-server restarted to pick up the changes")
+	default:
+		in.kept("llmgw-server running")
+	}
+	return in.waitHealthy(ctx)
+}
+
+func (in *serverInit) waitHealthy(ctx context.Context) error {
+	cfg, err := config.Load(in.configPath())
+	if err != nil {
+		return err
+	}
+	_, port, err := net.SplitHostPort(cfg.Listen)
+	if err != nil {
+		return fmt.Errorf("listen %q: %w", cfg.Listen, err)
+	}
+	url := "http://127.0.0.1:" + port + "/health"
+	deadline := time.Now().Add(30 * time.Second)
+	for {
+		req, _ := http.NewRequestWithContext(ctx, http.MethodGet, url, nil)
+		resp, err := http.DefaultClient.Do(req)
+		if err == nil {
+			resp.Body.Close()
+			if resp.StatusCode == http.StatusOK {
+				in.kept("answering on %s", url)
+				return nil
+			}
+		}
+		if time.Now().After(deadline) {
+			return fmt.Errorf("not answering on %s after 30s; 'journalctl -u llmgw-server -n 50' says why", url)
+		}
+		select {
+		case <-ctx.Done():
+			return ctx.Err()
+		case <-time.After(time.Second):
+		}
+	}
+}
+
+func (in *serverInit) nextSteps() {
+	server := "https://<this machine>:7443"
+	if ips := localAddrs(); len(ips) > 0 {
+		server = "https://" + net.JoinHostPort(ips[0].String(), "7443")
+	}
+	fmt.Fprintf(in.out, `
+The control plane is up. Next:
+
+  llmgw ctl status                      # no nodes, no models: correct for now
+
+  # each node, from this machine (it holds the authority):
+  deploy/bootstrap/onboard-node.sh --node <name> --addr <node ip> --server %s
+
+  # then a model:
+  llmgw ctl model add -f model.yaml
+
+The web UI is on port 8080; /admin once you are signed in as the administrator.
+`, server)
+}

internal/cli/serverinit_postgres.go

@@ -0,0 +1,396 @@
+package cli
+
+import (
+	"context"
+	"crypto/rand"
+	"encoding/hex"
+	"fmt"
+	"log/slog"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"strings"
+	"time"
+
+	"gitea.mynodes.xyz/ilker/llmgw/internal/agent/discovery"
+	"gitea.mynodes.xyz/ilker/llmgw/internal/agent/provision"
+	"gitea.mynodes.xyz/ilker/llmgw/internal/config"
+	"gitea.mynodes.xyz/ilker/llmgw/internal/store"
+)
+
+// pgRole and pgDatabase are what init creates in a PostgreSQL it manages.
+const (
+	pgRole     = "llmgw"
+	pgDatabase = "llmgw"
+)
+
+// dsnPath is where the PostgreSQL address is kept, out of server.yaml, so the
+// password in it is not in a file that gets copied, diffed and pasted.
+func (in *serverInit) dsnPath() string { return filepath.Join(in.etcDir, "secrets", "store-dsn") }
+
+// storeAddress is what auth.store says for the store init manages.
+func (in *serverInit) storeAddress() string {
+	if in.postgres {
+		return "@" + in.dsnPath()
+	}
+	return filepath.Join(in.stateDir, "llmgw.db")
+}
+
+// ensureDatabase puts the store in PostgreSQL when asked to, moving whatever
+// the SQLite store already holds.
+//
+// The move is the point. Keys are stored hashed, so starting PostgreSQL empty
+// means reissuing every key and being unable to say which was which; and the
+// administrator init created a minute ago would be gone too.
+func (in *serverInit) ensureDatabase(ctx context.Context) (err error) {
+	if !in.postgres {
+		return nil
+	}
+	setup := in.pgSetup
+	if setup == nil {
+		setup = in.setupPostgres
+	}
+	target, err := setup(ctx)
+	if err != nil {
+		return err
+	}
+
+	cfg, err := config.Load(in.configPath())
+	if err != nil {
+		return err
+	}
+	current := cfg.Auth.Store
+	if current == target {
+		in.kept("store in PostgreSQL (%s)", in.dsnPath())
+		return nil
+	}
+	if isPostgresAddress(current) {
+		// Two PostgreSQL stores, and a guess about which is meant would lose
+		// one of them.
+		return fmt.Errorf("server.yaml already names a PostgreSQL store (%s); "+
+			"init moves SQLite into PostgreSQL, not one PostgreSQL into another", current)
+	}
+
+	// Nothing may write the store while it is copied: a row landing after its
+	// table has been passed would be absent, and nothing would say so.
+	stopped, err := in.stopService(ctx)
+	if err != nil {
+		return err
+	}
+	defer func() {
+		// A move that failed leaves the configuration naming SQLite, which
+		// still holds everything: start the service on it again rather than
+		// leave the gateway down over a database that did not work out.
+		if err != nil && stopped {
+			_ = exec.Command("systemctl", "start", "llmgw-server").Run()
+			fmt.Fprintf(in.out, "  ..    llmgw-server started again on its SQLite store\n")
+		}
+	}()
+
+	if current != "" {
+		if _, err := os.Stat(current); err == nil {
+			if err := in.copyStore(ctx, current, target); err != nil {
+				return err
+			}
+		}
+	}
+
+	if err := setAuthStore(in.configPath(), target); err != nil {
+		return err
+	}
+	in.done("server.yaml now keeps the store in PostgreSQL")
+	return nil
+}
+
+func (in *serverInit) copyStore(ctx context.Context, from, to string) error {
+	src, err := store.Open(ctx, from)
+	if err != nil {
+		return fmt.Errorf("opening %s: %w", from, err)
+	}
+	defer src.Close()
+	dst, err := store.Open(ctx, to)
+	if err != nil {
+		return fmt.Errorf("opening PostgreSQL: %w", err)
+	}
+	defer dst.Close()
+
+	empty, err := dst.Empty(ctx)
+	if err != nil {
+		return err
+	}
+	if !empty {
+		// A previous run that copied and then stopped before changing the
+		// configuration. The service was stopped for that copy too, so what
+		// is there is what SQLite held.
+		in.kept("PostgreSQL already holds a store; %s is left as it is", from)
+		return nil
+	}
+	res, err := src.CopyTo(ctx, dst)
+	if err != nil {
+		return fmt.Errorf("copying %s into PostgreSQL: %w", from, err)
+	}
+	var rows int64
+	for _, r := range res {
+		rows += r.Rows
+	}
+	in.done("copied %d rows from %s into PostgreSQL (the SQLite file is kept)", rows, from)
+	return nil
+}
+
+func isPostgresAddress(a string) bool {
+	return strings.HasPrefix(a, "@") || strings.HasPrefix(a, "postgres://") ||
+		strings.HasPrefix(a, "postgresql://")
+}
+
+// setAuthStore changes auth.store in server.yaml and nothing else.
+//
+// Edited as text rather than unmarshalled and written back, because writing
+// it back would drop every comment in a file people annotate. The old file is
+// kept beside it.
+func setAuthStore(path, address string) error {
+	b, err := os.ReadFile(path)
+	if err != nil {
+		return err
+	}
+	lines := strings.Split(string(b), "\n")
+	value := fmt.Sprintf("%q", address)
+
+	authAt, storeAt, indent := -1, -1, "  "
+	for i, l := range lines {
+		trimmed := strings.TrimSpace(l)
+		top := l != "" && l[0] != ' ' && l[0] != '\t' && !strings.HasPrefix(trimmed, "#")
+		if top {
+			if authAt >= 0 && i > authAt {
+				break // past the auth block
+			}
+			if strings.HasPrefix(trimmed, "auth:") {
+				authAt = i
+			}
+			continue
+		}
+		if authAt >= 0 && strings.HasPrefix(trimmed, "store:") {
+			storeAt = i
+			indent = l[:len(l)-len(strings.TrimLeft(l, " \t"))]
+			break
+		}
+	}
+	switch {
+	case storeAt >= 0:
+		lines[storeAt] = indent + "store: " + value
+	case authAt >= 0:
+		lines = append(lines[:authAt+1], append([]string{indent + "store: " + value}, lines[authAt+1:]...)...)
+	default:
+		lines = append(lines, "auth:", "  enabled: true", "  store: "+value)
+	}
+
+	backup := fmt.Sprintf("%s.bak-%s", path, time.Now().Format("20060102-150405"))
+	if err := os.WriteFile(backup, b, 0o640); err != nil {
+		return err
+	}
+	info, err := os.Stat(path)
+	if err != nil {
+		return err
+	}
+	return os.WriteFile(path, []byte(strings.Join(lines, "\n")), info.Mode().Perm())
+}
+
+// setupPostgres makes sure a PostgreSQL on this machine holds a database for
+// llmgw, installing the server if there is none, and returns the store
+// address.
+func (in *serverInit) setupPostgres(ctx context.Context) (string, error) {
+	installed, err := in.installPostgres(ctx)
+	if err != nil {
+		return "", err
+	}
+	if err := waitForPostgres(ctx); err != nil {
+		return "", err
+	}
+
+	exists, err := psqlBool(ctx, "SELECT 1 FROM pg_roles WHERE rolname = '"+pgRole+"'")
+	if err != nil {
+		return "", err
+	}
+	_, statErr := os.Stat(in.dsnPath())
+	if exists && statErr == nil {
+		in.kept("PostgreSQL role %s", pgRole)
+	} else {
+		// A role with no address written down is one whose password nobody
+		// knows; giving it a new one is the only way to use it.
+		password := make([]byte, 24)
+		_, _ = rand.Read(password)
+		pass := hex.EncodeToString(password)
+		verb := "CREATE ROLE"
+		if exists {
+			verb = "ALTER ROLE"
+		}
+		if _, err := psql(ctx, verb+" "+pgRole+" WITH LOGIN PASSWORD '"+pass+"'"); err != nil {
+			return "", err
+		}
+		dsn := fmt.Sprintf("postgres://%s:%s@127.0.0.1:5432/%s?sslmode=disable", pgRole, pass, pgDatabase)
+		if err := in.writeDSN(dsn); err != nil {
+			return "", err
+		}
+		in.done("PostgreSQL role %s, its address in %s", pgRole, in.dsnPath())
+	}
+
+	exists, err = psqlBool(ctx, "SELECT 1 FROM pg_database WHERE datname = '"+pgDatabase+"'")
+	if err != nil {
+		return "", err
+	}
+	if exists {
+		in.kept("PostgreSQL database %s", pgDatabase)
+	} else {
+		if _, err := psql(ctx, "CREATE DATABASE "+pgDatabase+" OWNER "+pgRole); err != nil {
+			return "", err
+		}
+		in.done("PostgreSQL database %s", pgDatabase)
+	}
+
+	if installed {
+		// Its defaults assume it owns the machine. A gateway swapped out to
+		// give the database cache is worse than a smaller cache, and a store
+		// whose working set is megabytes needs little. Only a PostgreSQL init
+		// installed itself: one that was already here may serve something
+		// else that needs its connections.
+		for _, q := range []string{
+			"ALTER SYSTEM SET shared_buffers = '96MB'",
+			"ALTER SYSTEM SET max_connections = 40",
+		} {
+			if _, err := psql(ctx, q); err != nil {
+				return "", err
+			}
+		}
+		if out, err := exec.CommandContext(ctx, "systemctl", "restart", "postgresql").CombinedOutput(); err != nil {
+			return "", fmt.Errorf("restarting PostgreSQL: %v: %s", err, strings.TrimSpace(string(out)))
+		}
+		if err := waitForPostgres(ctx); err != nil {
+			return "", err
+		}
+		in.done("PostgreSQL sized for a machine it shares (shared_buffers 96MB, 40 connections)")
+	}
+
+	// Proof the address works, before anything is moved into it.
+	address := "@" + in.dsnPath()
+	s, err := store.Open(ctx, address)
+	if err != nil {
+		return "", fmt.Errorf("connecting with %s: %w", in.dsnPath(), err)
+	}
+	_ = s.Close()
+	return address, nil
+}
+
+func (in *serverInit) writeDSN(dsn string) error {
+	dir := filepath.Dir(in.dsnPath())
+	if err := os.MkdirAll(dir, 0o750); err != nil {
+		return err
+	}
+	if err := in.chown(dir, false); err != nil {
+		return err
+	}
+	if err := os.WriteFile(in.dsnPath(), []byte(dsn+"\n"), 0o600); err != nil {
+		return err
+	}
+	// Read by the service, which runs as llmgw; root reads it anyway.
+	return in.chown(in.dsnPath(), true)
+}
+
+// installPostgres installs the server when this machine has none, and says
+// whether it did.
+func (in *serverInit) installPostgres(ctx context.Context) (bool, error) {
+	if exec.CommandContext(ctx, "systemctl", "cat", "postgresql.service").Run() == nil {
+		in.kept("PostgreSQL server")
+		return false, nil
+	}
+	host := discovery.DiscoverHost()
+	family := host.Family()
+	if family == "" {
+		return false, fmt.Errorf("no PostgreSQL here and no package manager init knows (%s); "+
+			"install PostgreSQL and run init again", host.OSID)
+	}
+	fmt.Fprintf(in.out, "  ..    installing PostgreSQL (a minute or two)\n")
+	pi := &provision.Installer{Host: host, Log: slog.Default()}
+	if err := pi.InstallPackages(ctx, map[string][]string{
+		"deb": {"postgresql"},
+		"rpm": {"postgresql-server", "postgresql"},
+	}); err != nil {
+		return false, err
+	}
+
+	if family == "rpm" {
+		// Debian's package creates and starts a cluster; RHEL's leaves an
+		// empty data directory. Password authentication over TCP is asked
+		// for, because RHEL's default for it is ident, which no service
+		// account passes.
+		if _, err := os.Stat("/var/lib/pgsql/data/PG_VERSION"); err != nil {
+			cmd := exec.CommandContext(ctx, "postgresql-setup", "--initdb")
+			cmd.Env = append(os.Environ(), "PGSETUP_INITDB_OPTIONS=--auth-host=scram-sha-256 --auth-local=peer")
+			if out, err := cmd.CombinedOutput(); err != nil {
+				return false, fmt.Errorf("postgresql-setup --initdb: %v: %s", err, strings.TrimSpace(string(out)))
+			}
+		}
+	}
+	if out, err := exec.CommandContext(ctx, "systemctl", "enable", "--now", "postgresql").CombinedOutput(); err != nil {
+		return false, fmt.Errorf("starting PostgreSQL: %v: %s", err, strings.TrimSpace(string(out)))
+	}
+	in.done("PostgreSQL installed and started")
+	return true, nil
+}
+
+// psql runs one statement as the postgres superuser, over the local socket.
+func psql(ctx context.Context, query string) (string, error) {
+	cmd := exec.CommandContext(ctx, "runuser", "-u", "postgres", "--",
+		"psql", "-v", "ON_ERROR_STOP=1", "-qAtX", "-c", query)
+	// postgres cannot enter root's home, and psql says so on every call.
+	cmd.Dir = "/"
+	out, err := cmd.CombinedOutput()
+	if err != nil {
+		// The statement can hold a password; the error names only its verb.
+		verb := strings.Join(strings.Fields(query)[:2], " ")
+		return "", fmt.Errorf("psql (%s): %v: %s", verb, err, strings.TrimSpace(string(out)))
+	}
+	return strings.TrimSpace(string(out)), nil
+}
+
+func psqlBool(ctx context.Context, query string) (bool, error) {
+	out, err := psql(ctx, query)
+	return out == "1", err
+}
+
+// waitForPostgres waits for a server that was just started or restarted to
+// take connections.
+func waitForPostgres(ctx context.Context) error {
+	deadline := time.Now().Add(60 * time.Second)
+	for {
+		_, err := psql(ctx, "SELECT 1")
+		if err == nil {
+			return nil
+		}
+		if time.Now().After(deadline) {
+			return fmt.Errorf("PostgreSQL is not taking connections after 60s: %w", err)
+		}
+		select {
+		case <-ctx.Done():
+			return ctx.Err()
+		case <-time.After(2 * time.Second):
+		}
+	}
+}
+
+// stopService stops the control plane if it runs, so the store is still.
+// It says whether it stopped it, so a failed move can start it again.
+func (in *serverInit) stopService(ctx context.Context) (bool, error) {
+	if in.unitPath == "" {
+		return false, nil
+	}
+	if _, err := exec.LookPath("systemctl"); err != nil {
+		return false, nil
+	}
+	if exec.CommandContext(ctx, "systemctl", "is-active", "--quiet", "llmgw-server").Run() != nil {
+		return false, nil
+	}
+	if out, err := exec.CommandContext(ctx, "systemctl", "stop", "llmgw-server").CombinedOutput(); err != nil {
+		return false, fmt.Errorf("stopping llmgw-server to move its store: %v: %s", err, strings.TrimSpace(string(out)))
+	}
+	in.done("llmgw-server stopped while its store moves")
+	return true, nil
+}

internal/cli/serverinit_postgres_test.go

@@ -0,0 +1,168 @@
+package cli
+
+import (
+	"context"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+
+	"gitea.mynodes.xyz/ilker/llmgw/internal/config"
+	"gitea.mynodes.xyz/ilker/llmgw/internal/store"
+)
+
+func TestSetAuthStoreChangesOnlyAuthStore(t *testing.T) {
+	p := filepath.Join(t.TempDir(), "server.yaml")
+	body := `# my notes
+threads:
+  store: /var/lib/llmgw/threads.db   # not this one
+  retain_hours: 24
+auth:
+  enabled: true
+  # the store
+  store: /var/lib/llmgw/llmgw.db
+  signup_open: true
+landing:
+  contact: "x"
+`
+	if err := os.WriteFile(p, []byte(body), 0o640); err != nil {
+		t.Fatal(err)
+	}
+	if err := setAuthStore(p, "@/etc/llmgw/secrets/store-dsn"); err != nil {
+		t.Fatal(err)
+	}
+	got, _ := os.ReadFile(p)
+	want := strings.Replace(body, "  store: /var/lib/llmgw/llmgw.db",
+		`  store: "@/etc/llmgw/secrets/store-dsn"`, 1)
+	if string(got) != want {
+		t.Errorf("got:\n%s\nwant:\n%s", got, want)
+	}
+	cfg, err := config.Load(p)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if cfg.Auth.Store != "@/etc/llmgw/secrets/store-dsn" || cfg.Threads.Store != "/var/lib/llmgw/threads.db" {
+		t.Errorf("auth.store %q, threads.store %q", cfg.Auth.Store, cfg.Threads.Store)
+	}
+	backups, _ := filepath.Glob(p + ".bak-*")
+	if len(backups) != 1 {
+		t.Errorf("the old file should be kept beside it, found %v", backups)
+	}
+}
+
+func TestSetAuthStoreAddsTheLineWhenAuthHasNone(t *testing.T) {
+	p := filepath.Join(t.TempDir(), "server.yaml")
+	if err := os.WriteFile(p, []byte("auth:\n  enabled: true\nlanding:\n  contact: x\n"), 0o640); err != nil {
+		t.Fatal(err)
+	}
+	if err := setAuthStore(p, "@/x"); err != nil {
+		t.Fatal(err)
+	}
+	cfg, err := config.Load(p)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if cfg.Auth.Store != "@/x" || !cfg.Auth.Enabled {
+		t.Errorf("auth = %+v", cfg.Auth)
+	}
+}
+
+// fakePostgres stands in for setupPostgres the way it really answers: an
+// address file under /etc/llmgw/secrets, returned as "@file". What the file
+// holds is a SQLite path, so everything after the setup runs for real.
+func fakePostgres(t *testing.T, in *serverInit) (address, db string) {
+	t.Helper()
+	db = filepath.Join(t.TempDir(), "pg-standin.db")
+	in.pgSetup = func(context.Context) (string, error) {
+		if err := os.MkdirAll(filepath.Dir(in.dsnPath()), 0o750); err != nil {
+			return "", err
+		}
+		return "@" + in.dsnPath(), os.WriteFile(in.dsnPath(), []byte(db+"\n"), 0o600)
+	}
+	return "@" + in.dsnPath(), db
+}
+
+// Moving an install that began on SQLite: the administrator it created must
+// be in the new store, the configuration must name it, and the SQLite file
+// must still be there. The new store is SQLite too here — what PostgreSQL
+// adds is the setup, which needs a machine to run on.
+func TestInitMovesAnExistingStore(t *testing.T) {
+	in, out := newTestInit(t)
+	if err := in.run(context.Background()); err != nil {
+		t.Fatalf("%v\n%s", err, out)
+	}
+	old := filepath.Join(in.stateDir, "llmgw.db")
+
+	in.postgres = true
+	target, db := fakePostgres(t, in)
+	out.Reset()
+	if err := in.run(context.Background()); err != nil {
+		t.Fatalf("%v\n%s", err, out)
+	}
+	if !strings.Contains(out.String(), "copied") {
+		t.Errorf("nothing was copied:\n%s", out)
+	}
+
+	cfg, err := config.Load(in.configPath())
+	if err != nil {
+		t.Fatal(err)
+	}
+	if cfg.Auth.Store != target {
+		t.Fatalf("server.yaml still names %q", cfg.Auth.Store)
+	}
+	s, err := store.Open(context.Background(), db)
+	if err != nil {
+		t.Fatal(err)
+	}
+	u, err := s.UserByEmail(context.Background(), "admin@example.com")
+	s.Close()
+	if err != nil || !u.IsAdmin {
+		t.Fatalf("the administrator did not move: %v %+v", err, u)
+	}
+	if _, err := os.Stat(old); err != nil {
+		t.Error("the SQLite store should be kept")
+	}
+
+	// And once moved, again is nothing.
+	in.changed = false
+	out.Reset()
+	if err := in.run(context.Background()); err != nil {
+		t.Fatalf("%v\n%s", err, out)
+	}
+	if in.changed {
+		t.Errorf("a run after the move changed something:\n%s", out)
+	}
+}
+
+func TestInitWritesAPostgresConfigurationFromTheStart(t *testing.T) {
+	in, out := newTestInit(t)
+	in.postgres = true
+	target, _ := fakePostgres(t, in)
+	if err := in.run(context.Background()); err != nil {
+		t.Fatalf("%v\n%s", err, out)
+	}
+	cfg, _ := config.Load(in.configPath())
+	if cfg.Auth.Store != target {
+		t.Errorf("auth.store = %q", cfg.Auth.Store)
+	}
+	if _, err := os.Stat(filepath.Join(in.stateDir, "llmgw.db")); err == nil {
+		t.Error("a PostgreSQL install should not leave a SQLite store behind")
+	}
+}
+
+func TestInitWillNotMoveOnePostgresIntoAnother(t *testing.T) {
+	in, out := newTestInit(t)
+	if err := os.MkdirAll(in.etcDir, 0o755); err != nil {
+		t.Fatal(err)
+	}
+	cfg := "control:\n  enabled: true\nauth:\n  enabled: true\n  store: postgres://elsewhere/llmgw\n"
+	if err := os.WriteFile(in.configPath(), []byte(cfg), 0o640); err != nil {
+		t.Fatal(err)
+	}
+	in.postgres = true
+	in.pgSetup = func(context.Context) (string, error) { return "@/somewhere/else", nil }
+	err := in.run(context.Background())
+	if err == nil || !strings.Contains(err.Error(), "already names a PostgreSQL store") {
+		t.Fatalf("expected a refusal, got %v\n%s", err, out)
+	}
+}

internal/cli/serverinit_test.go

@@ -0,0 +1,173 @@
+package cli
+
+import (
+	"bytes"
+	"context"
+	"os"
+	"path/filepath"
+	"slices"
+	"strings"
+	"testing"
+
+	"gitea.mynodes.xyz/ilker/llmgw/internal/config"
+	"gitea.mynodes.xyz/ilker/llmgw/internal/store"
+)
+
+func newTestInit(t *testing.T) (*serverInit, *bytes.Buffer) {
+	t.Helper()
+	root := t.TempDir()
+	var out bytes.Buffer
+	return &serverInit{
+		etcDir:   filepath.Join(root, "etc"),
+		stateDir: filepath.Join(root, "state"),
+		pkiDir:   filepath.Join(root, "etc", "pki"),
+		admin:    "admin@example.com",
+		out:      &out,
+	}, &out
+}
+
+func TestInitLeavesAControlPlaneThatStarts(t *testing.T) {
+	in, out := newTestInit(t)
+	if err := in.run(context.Background()); err != nil {
+		t.Fatalf("%v\n%s", err, out)
+	}
+
+	cfg, err := config.Load(in.configPath())
+	if err != nil {
+		t.Fatal(err)
+	}
+	// The configuration install.md used to show had an empty catalog and no
+	// control.enabled, which the server refuses as having nothing to serve.
+	if !cfg.ControlPlaneMode() {
+		t.Error("the written configuration does not run a control plane")
+	}
+	if !cfg.AgentTLS.Enabled() || !cfg.Auth.Enabled {
+		t.Error("mutual TLS and authentication should both be on")
+	}
+	for _, f := range []string{"ca.pem", "server.pem", "server-key.pem"} {
+		if _, err := os.Stat(filepath.Join(in.etcDir, f)); err != nil {
+			t.Error(err)
+		}
+	}
+
+	s, err := store.Open(context.Background(), cfg.Auth.Store)
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer s.Close()
+	u, err := s.UserByEmail(context.Background(), "admin@example.com")
+	if err != nil {
+		t.Fatal(err)
+	}
+	if !u.IsAdmin || u.State != store.UserActive || u.ProjectID != "default" {
+		t.Errorf("administrator not ready to use: %+v", u)
+	}
+	if !strings.Contains(out.String(), "password: ") {
+		t.Error("the generated password was not shown")
+	}
+}
+
+func TestInitAgainChangesNothing(t *testing.T) {
+	in, out := newTestInit(t)
+	if err := in.run(context.Background()); err != nil {
+		t.Fatalf("%v\n%s", err, out)
+	}
+	cert, _ := os.ReadFile(filepath.Join(in.etcDir, "server.pem"))
+
+	again := *in
+	again.changed = false
+	out.Reset()
+	if err := again.run(context.Background()); err != nil {
+		t.Fatalf("%v\n%s", err, out)
+	}
+	if again.changed {
+		t.Errorf("a second run changed something:\n%s", out)
+	}
+	if strings.Contains(out.String(), "password: ") {
+		t.Error("a second run must not reset the administrator's password")
+	}
+	if now, _ := os.ReadFile(filepath.Join(in.etcDir, "server.pem")); !bytes.Equal(now, cert) {
+		t.Error("the certificate was reissued without reason")
+	}
+}
+
+func TestInitWithANewHostKeepsTheOldOnes(t *testing.T) {
+	in, out := newTestInit(t)
+	in.hosts = []string{"old.internal"}
+	if err := in.run(context.Background()); err != nil {
+		t.Fatalf("%v\n%s", err, out)
+	}
+	in.hosts = []string{"new.internal"}
+	if err := in.run(context.Background()); err != nil {
+		t.Fatalf("%v\n%s", err, out)
+	}
+	cert, err := readCert(filepath.Join(in.etcDir, "server.pem"))
+	if err != nil {
+		t.Fatal(err)
+	}
+	for _, h := range []string{"old.internal", "new.internal"} {
+		if !slices.Contains(cert.DNSNames, h) {
+			t.Errorf("certificate lost %s: %v", h, cert.DNSNames)
+		}
+	}
+}
+
+func TestInitNeverOverwritesTheConfiguration(t *testing.T) {
+	in, out := newTestInit(t)
+	if err := os.MkdirAll(in.etcDir, 0o755); err != nil {
+		t.Fatal(err)
+	}
+	mine := "# mine\ncontrol:\n  enabled: true\nauth:\n  enabled: true\n  store: " +
+		filepath.Join(in.stateDir, "mine.db") + "\n"
+	if err := os.WriteFile(in.configPath(), []byte(mine), 0o640); err != nil {
+		t.Fatal(err)
+	}
+	if err := in.run(context.Background()); err != nil {
+		t.Fatalf("%v\n%s", err, out)
+	}
+	if got, _ := os.ReadFile(in.configPath()); string(got) != mine {
+		t.Error("an existing server.yaml was rewritten")
+	}
+	// And the store it names is the one used.
+	if _, err := os.Stat(filepath.Join(in.stateDir, "mine.db")); err != nil {
+		t.Error(err)
+	}
+}
+
+func TestTheInitUnitIsTheShippedUnit(t *testing.T) {
+	b, err := os.ReadFile("../../deploy/systemd/llmgw-server.service")
+	if err != nil {
+		t.Fatal(err)
+	}
+	if string(b) != serverUnit {
+		t.Error("deploy/systemd/llmgw-server.service and the unit 'server init' writes have drifted")
+	}
+}
+
+func TestInitKeepsCertificatesFromAnAuthorityElsewhere(t *testing.T) {
+	in, out := newTestInit(t)
+	// Issued on another machine by an authority that never comes here.
+	elsewhere := &serverInit{etcDir: in.etcDir, pkiDir: filepath.Join(t.TempDir(), "pki"), out: &bytes.Buffer{}}
+	if err := os.MkdirAll(in.etcDir, 0o755); err != nil {
+		t.Fatal(err)
+	}
+	if err := elsewhere.ensureCerts(context.Background()); err != nil {
+		t.Fatal(err)
+	}
+	before, _ := os.ReadFile(filepath.Join(in.etcDir, "server.pem"))
+
+	if err := in.run(context.Background()); err != nil {
+		t.Fatalf("%v\n%s", err, out)
+	}
+	if after, _ := os.ReadFile(filepath.Join(in.etcDir, "server.pem")); !bytes.Equal(before, after) {
+		t.Error("a certificate from another authority was replaced")
+	}
+	if _, err := os.Stat(filepath.Join(in.pkiDir, "ca-key.pem")); err == nil {
+		t.Error("an authority was created beside one that already exists elsewhere")
+	}
+
+	in.hosts = []string{"new.internal"}
+	if err := in.run(context.Background()); err == nil {
+		t.Error("--host cannot be honoured without the authority, and should say so")
+	}
+}

internal/config/config.go

@@ -540,8 +540,14 @@ func (s Server) Catalog() (*catalog.Catalog, error) {
 // A model with no profiles cannot be placed, so a configuration of bare names
 // plus a static endpoint list is the router-only mode used for testing against
 // sim-engines.
+//
+// With no static endpoints there is nothing a router-only process could serve,
+// so a configuration naming neither endpoints nor models is a control plane
+// with an empty catalog — which is what every new cluster is. It used to be
+// refused as having nothing to serve, and under systemd that is a unit
+// restarting every two seconds with nothing on 8080.
 func (s Server) ControlPlaneMode() bool {
-	if s.Control.Enabled {
+	if s.Control.Enabled || len(s.Endpoints) == 0 {
 		return true
 	}
 	for _, m := range s.Models {

internal/config/config_test.go

@@ -155,19 +155,26 @@ func TestValidateAcceptsDistinctAliases(t *testing.T) {
 	}
 }
 
-func TestAControlPlaneCanBeAskedForWithNoModelsInTheFile(t *testing.T) {
-	// Without this, a deployment whose catalog lives entirely in the database
-	// cannot start: the mode is inferred from the file, an empty models block
-	// reads as "router only", and the process refuses to start for want of
-	// anything to serve — so the stored models it would have loaded are never
-	// read at all.
+func TestAnEmptyConfigurationIsAControlPlane(t *testing.T) {
+	// A new cluster has no models and no endpoints. Refusing it as having
+	// nothing to serve left a systemd unit restarting every two seconds and
+	// nothing listening on 8080 — on the first start anyone ever made.
 	var s Server
+	if !s.ControlPlaneMode() {
+		t.Fatal("a configuration with no endpoints and no models should run a control plane")
+	}
+}
+
+func TestStaticEndpointsAloneAreRouterOnly(t *testing.T) {
+	var s Server
+	s.Endpoints = []Endpoint{{ID: "e", URL: "http://127.0.0.1:1"}}
+	s.Models = []catalog.Model{{Name: "m"}}
 	if s.ControlPlaneMode() {
-		t.Fatal("an empty configuration is not a control plane")
+		t.Error("static endpoints and bare model names are the router-only mode")
 	}
 	s.Control.Enabled = true
 	if !s.ControlPlaneMode() {
-		t.Error("control.enabled should run the control plane with no models declared")
+		t.Error("control.enabled should run the control plane alongside static endpoints")
 	}
 }
 

internal/store/copy.go

@@ -96,6 +96,13 @@ func (s *DB) CopyTo(ctx context.Context, dst *DB) ([]CopyResult, error) {
 }
 
 // isEmpty reports whether any table has rows, and which one first does.
+// Empty reports whether the store holds no rows at all, which is what CopyTo
+// needs of its destination.
+func (s *DB) Empty(ctx context.Context) (bool, error) {
+	empty, _, err := s.isEmpty(ctx)
+	return empty, err
+}
+
 func (s *DB) isEmpty(ctx context.Context) (bool, string, error) {
 	for _, table := range copyOrder {
 		var n int64