Merge pull request 'Stage 18 — prod contour deploy (two-host registry rollout, rolling + auto-rollback)' (#103) from feature/prod-contour-deploy into development

2026-06-22 04:59:46 +00:00
parent b54cb8878d 9f970495ee
commit 520a9092fe
23 changed files with 1021 additions and 33 deletions
@@ -301,8 +301,11 @@ jobs:
          # App version for the About screen: the git tag if present, else the short SHA
          # (the test checkout is shallow/untagged, so this is the SHA here — fine).
          export APP_VERSION="$(git -C "$GITHUB_WORKSPACE" describe --tags --always 2>/dev/null || echo dev)"
-          docker compose --ansi never build --progress plain
-          docker compose --ansi never up -d --remove-orphans
+          # The telegram-local profile brings the bot + its VPN sidecar; prod runs the
+          # bot on its own host instead (deploy/docker-compose.bot.yml), and the prod
+          # main host omits both. Without the profile they would not start here.
+          docker compose --ansi never --profile telegram-local build --progress plain
+          docker compose --ansi never --profile telegram-local up -d --remove-orphans
          # The config-only services bind-mount the reseeded config dir. A plain `up -d`
          # leaves them on the previous bind mount (the dir was rm'd + recreated), so a
          # changed Caddyfile or Grafana dashboard is ignored — force-recreate them to
@@ -0,0 +1,219 @@
+# Manual production rollout. Runs ONLY from master, ONLY on an explicit
+# workflow_dispatch with confirm=deploy (development->master is merged + green first;
+# this is the separate, deliberate prod step). It builds and pushes the images to the
+# registry, then deploys over SSH: the main host via deploy/prod-deploy.sh (rolling,
+# health-gated, auto-rollback; a maintenance window + consistent dump on a migration),
+# then the bot host. See deploy/README.md (prod runbook) for operator steps.
+name: prod-deploy
+run-name: "prod deploy ${{ github.sha }}"
+
+on:
+  workflow_dispatch:
+    inputs:
+      confirm:
+        description: 'Type "deploy" to confirm a production rollout from master.'
+        required: true
+        default: ""
+
+permissions:
+  contents: read
+
+jobs:
+  deploy:
+    if: ${{ github.ref == 'refs/heads/master' && inputs.confirm == 'deploy' }}
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        shell: bash
+    env:
+      NO_COLOR: "1"
+      DOCKER_CLI_HINTS: "false"
+      REGISTRY: docker.iliadenisov.ru/developer
+      # SSH + registry
+      PROD_REGISTRY_USER: ${{ vars.PROD_REGISTRY_USER }}
+      PROD_REGISTRY_PASSWORD: ${{ secrets.PROD_REGISTRY_PASSWORD }}
+      PROD_SSH_KEY: ${{ secrets.PROD_SSH_KEY }}
+      PROD_SSH_KNOWN_HOSTS: ${{ secrets.PROD_SSH_KNOWN_HOSTS }}
+      MAIN_HOST: ${{ vars.PROD_MAIN_HOST }}
+      TG_HOST: ${{ vars.PROD_TG_HOST }}
+      # SPA build args (baked into the gateway/landing images)
+      VITE_TELEGRAM_BOT_ID: ${{ vars.PROD_VITE_TELEGRAM_BOT_ID }}
+      VITE_TELEGRAM_LINK: ${{ vars.PROD_VITE_TELEGRAM_LINK }}
+      VITE_TELEGRAM_GAME_CHANNEL_NAME: ${{ vars.PROD_VITE_TELEGRAM_GAME_CHANNEL_NAME }}
+      VITE_GATEWAY_URL: ${{ vars.PROD_VITE_GATEWAY_URL }}
+      # Runtime secrets
+      POSTGRES_PASSWORD: ${{ secrets.PROD_POSTGRES_PASSWORD }}
+      GM_BASICAUTH_HASH: ${{ secrets.PROD_GM_BASICAUTH_HASH }}
+      GRAFANA_ADMIN_PASSWORD: ${{ secrets.PROD_GRAFANA_ADMIN_PASSWORD }}
+      TELEGRAM_BOT_TOKEN: ${{ secrets.PROD_TELEGRAM_BOT_TOKEN }}
+      TELEGRAM_PROMO_BOT_TOKEN: ${{ secrets.PROD_TELEGRAM_PROMO_BOT_TOKEN }}
+      PROD_BOTLINK_CA: ${{ secrets.PROD_BOTLINK_CA }}
+      PROD_BOTLINK_GATEWAY_CERT: ${{ secrets.PROD_BOTLINK_GATEWAY_CERT }}
+      PROD_BOTLINK_GATEWAY_KEY: ${{ secrets.PROD_BOTLINK_GATEWAY_KEY }}
+      PROD_BOTLINK_BOT_CERT: ${{ secrets.PROD_BOTLINK_BOT_CERT }}
+      PROD_BOTLINK_BOT_KEY: ${{ secrets.PROD_BOTLINK_BOT_KEY }}
+      # Runtime variables
+      GM_BASICAUTH_USER: ${{ vars.PROD_GM_BASICAUTH_USER }}
+      GRAFANA_ROOT_URL: ${{ vars.PROD_GRAFANA_ROOT_URL }}
+      CADDY_SITE_ADDRESS: ${{ vars.PROD_CADDY_SITE_ADDRESS }}
+      LOG_LEVEL: ${{ vars.PROD_LOG_LEVEL }}
+      DICT_VERSION: ${{ vars.PROD_DICT_VERSION }}
+      POSTGRES_DB: ${{ vars.PROD_POSTGRES_DB }}
+      POSTGRES_USER: ${{ vars.PROD_POSTGRES_USER }}
+      TELEGRAM_MINIAPP_URL: ${{ vars.PROD_TELEGRAM_MINIAPP_URL }}
+      TELEGRAM_GAME_CHANNEL_ID: ${{ vars.PROD_TELEGRAM_GAME_CHANNEL_ID }}
+      TELEGRAM_CHAT_ID: ${{ vars.PROD_TELEGRAM_CHAT_ID }}
+      TELEGRAM_BOT_USERNAME: ${{ vars.PROD_TELEGRAM_BOT_USERNAME }}
+      TELEGRAM_BOT_LINK: ${{ vars.PROD_VITE_TELEGRAM_LINK }}
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Compute image tag and app version
+        run: |
+          echo "TAG=$(git rev-parse --short=12 HEAD)" >> "$GITHUB_ENV"
+          echo "APP_VERSION=$(git describe --tags --always)" >> "$GITHUB_ENV"
+
+      - name: Registry login
+        run: echo "$PROD_REGISTRY_PASSWORD" | docker login "${REGISTRY%%/*}" -u "$PROD_REGISTRY_USER" --password-stdin
+
+      - name: Build and push images
+        working-directory: deploy
+        run: |
+          export TAG SCRABBLE_CONFIG_DIR=.
+          # The four main-stack images via compose (reuses the compose build args); the
+          # bot separately, since it is profiled out of the prod compose.
+          docker compose -f docker-compose.yml -f docker-compose.prod.yml build
+          docker compose -f docker-compose.yml -f docker-compose.prod.yml push backend gateway landing validator
+          docker build -f ../platform/telegram/Dockerfile --target bot -t "$REGISTRY/scrabble-telegram-bot:$TAG" ..
+          docker push "$REGISTRY/scrabble-telegram-bot:$TAG"
+
+      - name: Set up SSH
+        run: |
+          mkdir -p ~/.ssh && chmod 700 ~/.ssh
+          printf '%s\n' "$PROD_SSH_KEY" > ~/.ssh/id_deploy
+          chmod 600 ~/.ssh/id_deploy
+          printf '%s\n' "$PROD_SSH_KNOWN_HOSTS" > ~/.ssh/known_hosts
+
+      - name: Determine previous tag and migration
+        run: |
+          ssh_main() { ssh -i ~/.ssh/id_deploy -o BatchMode=yes "deploy@$MAIN_HOST" "$@"; }
+          PREV_TAG="$(ssh_main 'cat /opt/scrabble/DEPLOYED_TAG 2>/dev/null || echo none')"
+          MIGRATION=0
+          if [ "$PREV_TAG" != none ]; then
+            if ! git cat-file -e "$PREV_TAG^{commit}" 2>/dev/null; then
+              MIGRATION=1   # unknown previous tag: take the safe window + dump
+            elif git diff --name-only "$PREV_TAG..$TAG" -- backend/internal/postgres/migrations/ | grep -q .; then
+              MIGRATION=1
+            fi
+          fi
+          echo "PREV_TAG=$PREV_TAG" >> "$GITHUB_ENV"
+          echo "MIGRATION=$MIGRATION" >> "$GITHUB_ENV"
+          echo "prev=$PREV_TAG migration=$MIGRATION"
+
+      - name: Render env files and certs
+        run: |
+          umask 077
+          mkdir -p stage/certs-main stage/certs-bot
+          # Main-host runtime env (single-quoted so the literal '$' in the bcrypt hash
+          # survives; prod-deploy.sh sources this, compose reads it from the environment).
+          cat > stage/env.sh <<EOF
+          export REGISTRY='$REGISTRY'
+          export SCRABBLE_CONFIG_DIR='/opt/scrabble'
+          export POSTGRES_DB='${POSTGRES_DB:-scrabble}'
+          export POSTGRES_USER='${POSTGRES_USER:-scrabble}'
+          export POSTGRES_PASSWORD='$POSTGRES_PASSWORD'
+          export GM_BASICAUTH_USER='${GM_BASICAUTH_USER:-gm}'
+          export GM_BASICAUTH_HASH='$GM_BASICAUTH_HASH'
+          export GRAFANA_ADMIN_PASSWORD='$GRAFANA_ADMIN_PASSWORD'
+          export GRAFANA_ROOT_URL='$GRAFANA_ROOT_URL'
+          export CADDY_SITE_ADDRESS='$CADDY_SITE_ADDRESS'
+          export LOG_LEVEL='${LOG_LEVEL:-info}'
+          export DICT_VERSION='$DICT_VERSION'
+          export TELEGRAM_BOT_TOKEN='$TELEGRAM_BOT_TOKEN'
+          export TELEGRAM_MINIAPP_URL='$TELEGRAM_MINIAPP_URL'
+          export GATEWAY_ABUSE_BAN_ENABLED='true'
+          EOF
+          # Bot-host runtime env.
+          cat > stage/env.bot.sh <<EOF
+          export SCRABBLE_CONFIG_DIR='/opt/scrabble'
+          export BOT_IMAGE='$REGISTRY/scrabble-telegram-bot:$TAG'
+          export BOTLINK_GATEWAY_ADDR='$MAIN_HOST:9443'
+          export TELEGRAM_BOT_TOKEN='$TELEGRAM_BOT_TOKEN'
+          export TELEGRAM_MINIAPP_URL='$TELEGRAM_MINIAPP_URL'
+          export TELEGRAM_GAME_CHANNEL_ID='$TELEGRAM_GAME_CHANNEL_ID'
+          export TELEGRAM_CHAT_ID='$TELEGRAM_CHAT_ID'
+          export TELEGRAM_PROMO_BOT_TOKEN='$TELEGRAM_PROMO_BOT_TOKEN'
+          export TELEGRAM_BOT_USERNAME='$TELEGRAM_BOT_USERNAME'
+          export TELEGRAM_BOT_LINK='$TELEGRAM_BOT_LINK'
+          export LOG_LEVEL='${LOG_LEVEL:-info}'
+          EOF
+          # Bot-link certs (world-readable: the distroless gateway/bot run as UID 65532
+          # and bind-mount the dir read-only).
+          printf '%s\n' "$PROD_BOTLINK_CA"           > stage/certs-main/ca.crt
+          printf '%s\n' "$PROD_BOTLINK_GATEWAY_CERT" > stage/certs-main/gateway.crt
+          printf '%s\n' "$PROD_BOTLINK_GATEWAY_KEY"  > stage/certs-main/gateway.key
+          printf '%s\n' "$PROD_BOTLINK_CA"           > stage/certs-bot/ca.crt
+          printf '%s\n' "$PROD_BOTLINK_BOT_CERT"     > stage/certs-bot/bot.crt
+          printf '%s\n' "$PROD_BOTLINK_BOT_KEY"      > stage/certs-bot/bot.key
+          chmod 644 stage/certs-main/* stage/certs-bot/*
+
+      - name: Deploy the main host
+        run: |
+          ssh_main() { ssh -i ~/.ssh/id_deploy -o BatchMode=yes "deploy@$MAIN_HOST" "$@"; }
+          ssh_main 'mkdir -p /opt/scrabble/compose'
+          # Compose files + config + script.
+          tar -C deploy -czf - docker-compose.yml docker-compose.prod.yml prod-deploy.sh \
+            | ssh_main 'tar -C /opt/scrabble/compose -xzf -'
+          tar -C deploy -czf - caddy otelcol prometheus tempo grafana \
+            | ssh_main 'tar -C /opt/scrabble -xzf -'
+          tar -C stage -czf - certs-main \
+            | ssh_main 'rm -rf /opt/scrabble/certs && mkdir -p /opt/scrabble/certs && tar -C /opt/scrabble/certs --strip-components=1 -xzf -'
+          scp -i ~/.ssh/id_deploy -o BatchMode=yes stage/env.sh "deploy@$MAIN_HOST:/opt/scrabble/env.sh"
+          # Registry login on the host so compose can pull the private images.
+          echo "$PROD_REGISTRY_PASSWORD" | ssh_main "docker login ${REGISTRY%%/*} -u $PROD_REGISTRY_USER --password-stdin"
+          ssh_main "TAG='$TAG' PREV_TAG='$PREV_TAG' MIGRATION='$MIGRATION' bash /opt/scrabble/compose/prod-deploy.sh"
+
+      - name: Deploy the bot host
+        run: |
+          ssh_tg() { ssh -i ~/.ssh/id_deploy -o BatchMode=yes "deploy@$TG_HOST" "$@"; }
+          ssh_tg 'mkdir -p /opt/scrabble/compose'
+          tar -C deploy -czf - docker-compose.bot.yml | ssh_tg 'tar -C /opt/scrabble/compose -xzf -'
+          tar -C stage -czf - certs-bot \
+            | ssh_tg 'rm -rf /opt/scrabble/certs && mkdir -p /opt/scrabble/certs && tar -C /opt/scrabble/certs --strip-components=1 -xzf -'
+          scp -i ~/.ssh/id_deploy -o BatchMode=yes stage/env.bot.sh "deploy@$TG_HOST:/opt/scrabble/env.bot.sh"
+          echo "$PROD_REGISTRY_PASSWORD" | ssh_tg "docker login ${REGISTRY%%/*} -u $PROD_REGISTRY_USER --password-stdin"
+          ssh_tg 'set -a; . /opt/scrabble/env.bot.sh; set +a; cd /opt/scrabble/compose;
+            docker compose -f docker-compose.bot.yml pull;
+            docker compose -f docker-compose.bot.yml up -d'
+          # Bot liveness: running, not restarting, stable restart count.
+          ssh_tg 'for i in $(seq 1 20); do
+              s=$(docker inspect -f "{{.State.Status}}" scrabble-telegram-bot 2>/dev/null || echo missing)
+              r=$(docker inspect -f "{{.State.Restarting}}" scrabble-telegram-bot 2>/dev/null || echo true)
+              if [ "$s" = running ] && [ "$r" = false ]; then
+                c1=$(docker inspect -f "{{.RestartCount}}" scrabble-telegram-bot); sleep 5
+                c2=$(docker inspect -f "{{.RestartCount}}" scrabble-telegram-bot)
+                [ "$c1" = "$c2" ] && { echo "bot healthy"; exit 0; }
+              fi
+              sleep 3
+            done
+            echo "bot not healthy:"; docker logs --tail 80 scrabble-telegram-bot; exit 1'
+
+      - name: Verify the public site
+        run: |
+          ssh_main() { ssh -i ~/.ssh/id_deploy -o BatchMode=yes "deploy@$MAIN_HOST" "$@"; }
+          domain="${CADDY_SITE_ADDRESS%% *}"   # first domain of "erudit-game.ru www..."
+          # Probe through caddy with the right vhost (force-resolved to the host); -k
+          # tolerates an ACME-pending cert. Also check the backend is actually ready.
+          ssh_main "for i in \$(seq 1 20); do
+              if curl -fsS -k --resolve $domain:443:127.0.0.1 https://$domain/ -o /dev/null &&
+                 curl -fsS -k --resolve $domain:443:127.0.0.1 https://$domain/app/ -o /dev/null &&
+                 docker run --rm --network scrabble-internal alpine:3.20 wget -q -T 5 -O /dev/null http://backend:8080/readyz; then
+                echo 'public site + /app/ + backend healthy'; exit 0
+              fi
+              sleep 5
+            done
+            echo 'public verify failed; recent caddy + gateway + backend logs:'
+            docker logs --tail 40 scrabble-caddy; docker logs --tail 40 scrabble-gateway; docker logs --tail 40 scrabble-backend
+            exit 1"
@@ -51,7 +51,7 @@ independent (see ARCHITECTURE §9.1).
 | 15 | Dual Telegram bots & language-gated variants | **done** |
 | 16 | Deploy infra & test contour (Dockerfiles, gateway static UI, compose, observability) | **done** |
 | 17 | Test-contour verification & defect fixes | **done** |
-| 18 | Prod contour deploy (SSH export/import, manual after merge) | todo |
+| 18 | Prod contour deploy (registry, two-host, rolling + auto-rollback; manual after merge) | machinery built; first cutover pending DNS |
 | 19 | User feedback (in-app submit + attachment, admin review/reply, account roles) | **done** |

 Scaffolding is incremental: `go.work` lists only existing modules; each stage
@@ -413,18 +413,28 @@ raw list is kept here as the record of what the first contour run surfaced.
  "что-то пошло не так". при этом "new -> эрудит" работает. Попробуй посмотреть в логах сейчас, может что-то есть. Или как-то иначе проанализируй, или давай вместе будем смотреть, если не получится.

 ### Stage 18 — Prod contour deploy
-Scope: the **production contour** on a remote host over SSH. Deploy by **container export/import**
-(`docker save` → `scp`/ssh → `docker load` → `docker compose up` on the remote), the SSH key + host IP
-in Gitea secrets; **strictly manual** (`workflow_dispatch`) after `development` is merged to `master`
-(the Stage 16 branch model: `feature/* → development → master`, merge gated green). Two-contour config
-uses **`TEST_`/`PROD_` secret/variable prefixes** — Gitea 1.26 has no deployment environments (verified:
-the `environments` API 404s), so a flat prefixed namespace is the convention.
-Reuses the Stage 16 `deploy/docker-compose.yml` as-is, mapping the **`PROD_`** set onto the same
-unprefixed compose vars. **No host caddy on prod**, so the contour's own caddy terminates TLS — set
-`CADDY_SITE_ADDRESS` to the prod domain so caddy does its own ACME (the Caddyfile is already
-parameterised for this; the test contour leaves it `:80` behind the host caddy).
-Open details (re-interview): export/import vs a registry trade-off; prod domain/cert source (ACME vs a
-provided cert) at the contour caddy; prod VPN; rollback.
+Scope: the **production contour** on **two remote hosts** over SSH — main (full stack, `erudit-game.ru`)
+and tg (the bot only). Resolved open details (re-interviewed):
+- **Transport: a registry** (not export/import) — build + push to `docker.iliadenisov.ru`, the hosts pull by tag.
+- **Cert: ACME** at the contour caddy (`CADDY_SITE_ADDRESS=erudit-game.ru www.erudit-game.ru`, no host caddy).
+- **No prod VPN** — the bot host has native Bot API egress (verified `api.telegram.org` → 200).
+- **Rollback** — rolling per-service deploy (least → most dependent), health-gated, auto-rollback to the
+  previous image tag; a maintenance window + consistent `pg_dump` only on a schema migration
+  (expand-contract keeps the auto-rollback image-only; the dump is a manual safety net).
+
+**Strictly manual** (`workflow_dispatch` from `master`, `confirm=deploy`) after `development → master`
+is merged green. `TEST_`/`PROD_` prefixed Gitea secrets/variables (Gitea 1.26 has no deployment
+environments — the `environments` API 404s). Hosts are provisioned by **`deploy/ansible/`** (docker, a
+non-sudo `deploy` user with the CI key, key-only sshd, ufw, fail2ban). The main host is **launch-sized**
+(2 vCPU / 1.9 GiB): `docker-compose.prod.yml` trims the R7 limits (`GOMAXPROCS=2`, smaller caps, 7d
+Prometheus retention) and adds `node_exporter` for host-memory monitoring (launch undersized, resize at
+Selectel reactively). `vpn`+`bot` are gated to a `telegram-local` compose profile (test only); the prod
+bot runs standalone from `docker-compose.bot.yml`. `GATEWAY_ABUSE_BAN_ENABLED=true`.
+
+**Built:** `deploy/ansible/` (both hosts provisioned + verified), the compose split + `node_exporter`,
+`.gitea/workflows/prod-deploy.yaml` + `deploy/prod-deploy.sh`, the full `PROD_` secret/variable set.
+**Remaining (acceptance):** the **first live cutover** — waits on the `erudit-game.ru` DNS delegation
+(`A`/`www` → the main host) that ACME requires; then run the workflow and verify the public site end-to-end.

 ### Stage 19 — User feedback *(done)*
 A user→operator feedback channel, sequenced after the numbered stages but shipped **before** the Stage 18
@@ -39,8 +39,8 @@ the edge before prod. Each phase maps back to the owner's raw pre-release TODO l
 | FM | First-move tile draw (official rules): each seated player draws a tile, the one closest to "A" leads (a blank beats every letter), ties re-drawing until a single leader; **honest per-draw `crypto/rand` entropy**, not the bag seed, so the **record** (`game_setup_draws`, migration `00013`) — not a seed — is the only account of the outcome, kept for future **tournaments** (designed as a discrete per-tile "player N draws" step). Friend/AI draws at create; **auto-match draws at *open*** against a synthetic `uuid.Nil` opponent whose draw rows are back-filled on join, so the opener's seat is fixed up front and the existing open-game pre-move is preserved (no reseating, no play-gating). Admin `/_gm/games/:id` gains the recorded draw list + a simple **step-by-step board replay** (`ReplayTimeline`). | owner ad-hoc | **done** |
 | SB | Single Telegram bot + per-user variant preferences: the two per-language bots collapse into **one** (drop `accounts.service_language`, `supported_languages`, the `*_EN`/`*_RU` env vars and game-language push routing — the single bot renders in the recipient's `preferred_language`); New Game variant gating moves to a profile **`variant_preferences`** set (default Erudit only, Erudit-first, server-enforced on the caller's auto-match/vs-AI/invitation-create paths, an invited friend may accept any variant); env vars collapse to unsuffixed `TELEGRAM_BOT_TOKEN`/`TELEGRAM_GAME_CHANNEL_ID`/`VITE_TELEGRAM_LINK`/`VITE_TELEGRAM_GAME_CHANNEL_NAME` and `GATEWAY_DEFAULT_SUPPORTED_LANGUAGES` is removed; wire drops `service_language`/`supported_languages` (Session, ValidateInitDataResponse) + the push `language` routing field and adds `variant_preferences` to Profile/UpdateProfile. | owner ad-hoc | **done** |
 | DV | Dictionary version hygiene: CI + image/compose seed track the current release (`v1.2.1`); a **seed-drift guard** records the flat dir's seed in an authoritative `.seed_version` marker so a bumped build seed on a live volume is ignored (it can't relabel live bytes — which would mis-serve the dictionary + void games pinned to the prior label); `DICT_VERSION` is the fresh-volume seed only, a live contour migrates through the admin console | owner ad-hoc | **done** |
-| TX | Telegram egress off the main host: split the connector into a home **validator** (Mini App / Login-Widget HMAC, no VPN, no Bot API — so game login no longer depends on Telegram being reachable) and a remote **bot** (Bot API long-poll + `sendMessage`) that holds **no inbound port** and dials the gateway over a reverse **mTLS bot-link** (`pkg/proto/botlink/v1`); the gateway funnels out-of-app push (fire-and-forget, at-most-once) and the backend admin broadcasts (a relay that awaits the bot's ack) down the link. The bot is Telegram-rate-limited; **one bot now**, with seams (a bot registry + `owns_updates` + command ids) for N later; **no webhook** (rejected: one URL per token, adds inbound + a static address). The **unified test contour** runs the split (the bot keeps its VPN sidecar and dials the gateway by its internal name; certs from `deploy/gen-certs.sh`). The **prod** wiring — the bot on a separate host (no VPN), the gateway bot-link port published, `PROD_` certs with scheduled rotation, an SSH deploy of both hosts together — is the **deferred final stage** (Stage 18). | owner ad-hoc | **done** (code + test contour; prod wiring → Stage 18) |
-| AG | Anti-abuse IP ban + honeypot/honeytoken (prod-only): a fail2ban-style in-memory `ratelimit.Banlist` keyed by client IP, fed by sustained rate-limiter rejections (the IP-keyed public/email/admin classes — the user class stays the soft-flag's concern), a **honeypot** decoy path (the contour caddy tags `/.env`, `/.git`, `/wp-*`, … with `X-Scrabble-Honeypot` and routes them to the gateway), and a **honeytoken** (`GATEWAY_HONEYTOKEN`, a planted bearer). The `abuseGuard` edge middleware refuses a banned IP with **429** before any work — closing the R3 gap that the static SPA/landing was outside the token bucket. Off by default — it keys by the real client IP the shared-NAT test contour does not expose (detection still logs there); enabled in prod via `GATEWAY_ABUSE_BAN_ENABLED`. Operators see + lift bans on the console **Throttled** page; the gateway syncs its active set to the backend (`/api/v1/internal/bans/sync`, `internal/banview`) every 30 s and applies operator unbans. | owner ad-hoc | **done** (code + test contour; ban enabled in prod → Stage 18) |
+| TX | Telegram egress off the main host: split the connector into a home **validator** (Mini App / Login-Widget HMAC, no VPN, no Bot API — so game login no longer depends on Telegram being reachable) and a remote **bot** (Bot API long-poll + `sendMessage`) that holds **no inbound port** and dials the gateway over a reverse **mTLS bot-link** (`pkg/proto/botlink/v1`); the gateway funnels out-of-app push (fire-and-forget, at-most-once) and the backend admin broadcasts (a relay that awaits the bot's ack) down the link. The bot is Telegram-rate-limited; **one bot now**, with seams (a bot registry + `owns_updates` + command ids) for N later; **no webhook** (rejected: one URL per token, adds inbound + a static address). The **unified test contour** runs the split (the bot keeps its VPN sidecar and dials the gateway by its internal name; certs from `deploy/gen-certs.sh`). The **prod** wiring — the bot on a separate host (no VPN), the gateway bot-link port published, `PROD_` certs, an SSH deploy of both hosts together — is **built in Stage 18** (the two-host registry rollout; first cutover pending the `erudit-game.ru` DNS). | owner ad-hoc | **done** (code + test contour; prod wiring built — Stage 18) |
+| AG | Anti-abuse IP ban + honeypot/honeytoken (prod-only): a fail2ban-style in-memory `ratelimit.Banlist` keyed by client IP, fed by sustained rate-limiter rejections (the IP-keyed public/email/admin classes — the user class stays the soft-flag's concern), a **honeypot** decoy path (the contour caddy tags `/.env`, `/.git`, `/wp-*`, … with `X-Scrabble-Honeypot` and routes them to the gateway), and a **honeytoken** (`GATEWAY_HONEYTOKEN`, a planted bearer). The `abuseGuard` edge middleware refuses a banned IP with **429** before any work — closing the R3 gap that the static SPA/landing was outside the token bucket. Off by default — it keys by the real client IP the shared-NAT test contour does not expose (detection still logs there); enabled in prod via `GATEWAY_ABUSE_BAN_ENABLED`. Operators see + lift bans on the console **Throttled** page; the gateway syncs its active set to the backend (`/api/v1/internal/bans/sync`, `internal/banview`) every 30 s and applies operator unbans. | owner ad-hoc | **done** (code + test contour; ban on in prod via Stage 18 — machinery built, cutover pending DNS) |
 | CM | Channel-chat moderation + promo bot: a second standalone bot in the bot container answers `/start` with a localized message + a **URL** button into the **main** bot's Mini App (`?startapp`; a `web_app` button would sign initData with the promo token, which the main validator rejects). The **main** bot gates write access in a channel's linked discussion chat. The chat **allows sending by default** and the bot only restricts (Telegram intersects the chat default with the per-user permission, so a per-user grant cannot exceed a deny-by-default group): it **mutes** a member who is not registered or is admin-suspended or holding a new **`chat_muted`** role, and **un-mutes** an eligible one it had muted, for a member currently in the chat (a `getChatMember` guard, since bots cannot list members). Eligibility = `registered AND NOT suspended AND NOT chat_muted` (the game suspension dominates), resolved once in the backend and reached two ways: the bot's `ResolveChatEligibility` on a `chat_member` event over the existing mTLS bot-link, and a backend `chat_access_changed` event → gateway → `ChatGate` command (emitted on block/unblock, a `chat_muted` change, a first registration, or a temporary-block expiry via a sweeper; idempotent). No schema change — `chat_muted` reuses `account_roles`. | owner ad-hoc | **done** |
 | → | Stage 18 — prod contour deploy | — | see [`PLAN.md`](PLAN.md) |

@@ -17,11 +17,12 @@ operational reference for **every environment variable**.
 | `backend` | built (`backend/Dockerfile`) | Domain service; bakes in the DAWG dictionaries; runs migrations at boot. |
 | `postgres` | `postgres:17-alpine` | Database (named volume, `pg_isready` healthcheck). |
 | `validator` | built (`platform/telegram/Dockerfile`, target `validator`) | Telegram HMAC validator (no VPN, no Bot API); internal gRPC at `validator:9091`. Game login depends only on this. |
-| `vpn` + `bot` | sidecar + built (`platform/telegram/Dockerfile`, target `bot`) | Telegram bot; egresses through the AmneziaWG sidecar; holds no inbound port — dials the gateway bot-link (mTLS) at `gateway:9443`. |
+| `vpn` + `bot` | sidecar + built (`platform/telegram/Dockerfile`, target `bot`) | Telegram bot, gated to the **`telegram-local`** profile; egresses through the AmneziaWG sidecar and dials the gateway bot-link (mTLS) at `gateway:9443`. The test contour activates the profile; the prod **main** host omits it and runs the bot standalone on its **own host** (`docker-compose.bot.yml`, no VPN — native Bot API egress). |
 | `otelcol` | `otel/opentelemetry-collector-contrib` | OTLP/gRPC `:4317` → Prometheus scrape (`:9464`) + Tempo. |
-| `prometheus` | `prom/prometheus` | Metrics, 15d retention. |
+| `prometheus` | `prom/prometheus` | Metrics, 15d retention (7d in prod). |
 | `tempo` | `grafana/tempo` | Traces, 72h retention. |
 | `grafana` | `grafana/grafana` | Dashboards (provisioned), anonymous-admin behind caddy's `/_gm/grafana`. |
+| `node_exporter` | `quay.io/prometheus/node-exporter` | Host CPU/memory/disk metrics (Prometheus job `node`); the OOM signal on the tight prod main host (2 vCPU / 1.9 GiB). |

 Networking: inter-service traffic is on the private `internal` network
 (project-scoped DNS); only `caddy` joins the shared external `edge` network so the
@@ -59,7 +60,6 @@ compose binds from this directory.
 | Variable | Gitea kind | Purpose |
 | --- | --- | --- |
 | `POSTGRES_PASSWORD` | secret | Postgres password (also embedded in `BACKEND_POSTGRES_DSN`). |
-| `AWG_CONF` | secret | AmneziaWG config for the VPN sidecar (the bot's only Telegram egress in the test contour). **Must not contain a `DNS=` line** — it hijacks the shared netns's resolv.conf and breaks the bot resolving `otelcol` / `gateway`. Without it, Docker's resolver handles `otelcol`, `gateway` and `api.telegram.org`. |
 | `GM_BASICAUTH_HASH` | secret | bcrypt hash gating `/_gm` (admin console + Grafana). Generate with `docker run --rm caddy:2-alpine caddy hash-password --plaintext '<pw>'`. |
 | `TELEGRAM_MINIAPP_URL` | variable | The Mini App URL the bot hands out in deep links / buttons. |

@@ -67,6 +67,13 @@ compose binds from this directory.
 secret) and the bot (Bot API). It defaults to empty in compose, but both **fail at
 boot** when it is empty.

+**Conditionally — `AWG_CONF`** (secret): the AmneziaWG config for the VPN sidecar, needed
+only when the `telegram-local` profile runs (the test contour and local runs with the
+bot). It is **not** `:?`-guarded — compose interpolates profiled-out services too, so the
+prod main host (no VPN) must not require it. It **must not contain a `DNS=` line** — that
+hijacks the shared netns's resolv.conf and breaks the bot resolving `otelcol` / `gateway`;
+without it Docker's resolver handles `otelcol`, `gateway` and `api.telegram.org`.
+
 ## Optional variables (with defaults)

 | Variable | Gitea kind | Default | Purpose |
@@ -110,6 +117,47 @@ collector's / gateway's internal IP is fine (connected route), but its `AWG_CONF
 which resolves `otelcol`, `gateway` and `api.telegram.org`. `GATEWAY_ADMIN_*` is
 intentionally **unset** — caddy owns `/_gm` in the contour.

+## Production rollout
+
+Prod runs on **two hosts** (main = full stack + ACME on the domain; tg = the bot only,
+native Bot API, no VPN), one-time provisioned by **[`ansible/`](ansible/)** (docker, a
+non-sudo `deploy` user holding the CI key, key-only sshd, default-deny ufw, fail2ban).
+Re-run `ansible/` after a host resize — it is idempotent.
+
+**To roll out:** merge `development → master` (CI green), then run the **`prod-deploy`**
+workflow manually (Gitea → Actions → prod-deploy → run from `master`, input
+`confirm=deploy`). It builds + pushes the images to the registry, ships the
+compose/config/certs/env over SSH, deploys the main host with `prod-deploy.sh` (rolling,
+health-gated, **auto-rollback to the previous tag**), then the bot host, then probes the
+public site. After `master` is green this workflow is the **only** thing that touches
+prod — nothing auto-deploys there.
+
+**Migrations** must be **expand-contract** (backward-compatible; goose is forward-only):
+the automatic rollback is image-only and never restores the DB. A deploy that changes
+`backend/internal/postgres/migrations/` opens a maintenance window — the backend (sole
+writer) is stopped for a consistent `pg_dump` into `/opt/scrabble/dumps` before the new
+backend migrates. **Manual DB restore** (only if a migration was destructive):
+`docker exec -i scrabble-postgres psql -U scrabble -d scrabble -c 'DROP SCHEMA backend CASCADE'`,
+then pipe the dump into the same `psql`, and redeploy the matching old tag.
+
+**bot-link cert rotation:** regenerate (`deploy/gen-certs.sh /tmp/c --force`), reset the
+five `PROD_BOTLINK_*` secrets from `/tmp/c`, and re-run the workflow — both hosts redeploy
+together with the fresh CA.
+
+**Sizing / monitoring:** the main host launches undersized (2 vCPU / 1.9 GiB); the prod
+overlay trims limits + `GOMAXPROCS=2` + 7d Prometheus retention, and `node_exporter` feeds
+host memory to Grafana (`/_gm/grafana/`). Watch host memory and resize at Selectel when
+players arrive.
+
+**`PROD_` Gitea set** (mirrors `TEST_`, mapped onto the unprefixed names above) — secrets:
+`PROD_{POSTGRES_PASSWORD, GM_BASICAUTH_HASH, GRAFANA_ADMIN_PASSWORD, TELEGRAM_BOT_TOKEN,
+TELEGRAM_PROMO_BOT_TOKEN, REGISTRY_PASSWORD, SSH_KEY, SSH_KNOWN_HOSTS, BOTLINK_CA,
+BOTLINK_GATEWAY_CERT, BOTLINK_GATEWAY_KEY, BOTLINK_BOT_CERT, BOTLINK_BOT_KEY}`; variables:
+`PROD_{REGISTRY_USER, MAIN_HOST, TG_HOST, CADDY_SITE_ADDRESS, GM_BASICAUTH_USER,
+GRAFANA_ROOT_URL, LOG_LEVEL, DICT_VERSION, TELEGRAM_MINIAPP_URL, TELEGRAM_GAME_CHANNEL_ID,
+TELEGRAM_CHAT_ID, TELEGRAM_BOT_USERNAME, VITE_TELEGRAM_BOT_ID, VITE_TELEGRAM_LINK,
+VITE_TELEGRAM_GAME_CHANNEL_NAME}`.
+
 ## Host-side setup (outside this repo)

 - **`edge` network** must exist on the host (`docker network create edge`).
@@ -0,0 +1,49 @@
+# Prod host provisioning (Stage 18)
+
+Idempotent Ansible that prepares the two production hosts. It installs Docker, a
+non-sudo `deploy` service account, SSH hardening, a default-deny firewall,
+fail2ban, unattended security upgrades and time sync. It does **not** deploy the
+application — that is `.gitea/workflows/prod-deploy.yaml`'s job, running as the
+`deploy` account this playbook creates.
+
+Hosts are referenced by `~/.ssh/config` aliases (`scrabble-main-ops`,
+`scrabble-tg-ops`), so no IPs or key paths live in the repo.
+
+## Prerequisites (controller)
+
+- `ansible` with the bundled collections (`community.general`, `community.docker`,
+  `ansible.posix`).
+- The two hosts reachable as root via the ssh-config aliases, host keys already
+  accepted into `known_hosts` (`host_key_checking = True`).
+
+## One-time: the CI deploy key
+
+The CI prod-deploy workflow logs into the hosts as `deploy` using a dedicated
+key. Generate it once on the controller, authorize its public half via the
+playbook, and store its private half **only** in the Gitea `PROD_SSH_KEY` secret:
+
+```sh
+ssh-keygen -t ed25519 -N '' -C scrabble-ci-deploy \
+  -f ~/.ssh/scrabble_ci_deploy_ed25519
+# private half -> Gitea secret PROD_SSH_KEY (set via API); never commit it
+```
+
+## Run
+
+```sh
+cd deploy/ansible
+ansible-playbook site.yml
+```
+
+The playbook reads the public key from `~/.ssh/scrabble_ci_deploy_ed25519.pub` by
+default; override with `-e deploy_ci_pubkey_path=/path/to/key.pub`. Re-running is
+safe (idempotent) and survives a host resize.
+
+## What each host gets
+
+- **both** (`common`): docker-ce + compose plugin, `daemon.json` (live-restore,
+  10m×3 log rotation), `deploy` user (docker group, no sudo), key-only sshd,
+  `ufw` default-deny incoming + allow SSH, fail2ban sshd jail, unattended
+  upgrades, chrony, `/opt/scrabble/{config,certs,dumps,images}`.
+- **main**: `ufw` opens 80/443/9443; the external `edge` docker network.
+- **tg**: verifies direct `api.telegram.org` egress (the no-VPN assumption).
@@ -0,0 +1,11 @@
+[defaults]
+inventory = inventory.ini
+roles_path = roles
+interpreter_python = /usr/bin/python3
+host_key_checking = True
+stdout_callback = yaml
+deprecation_warnings = False
+retry_files_enabled = False
+
+[ssh_connection]
+pipelining = True
@@ -0,0 +1,21 @@
+---
+# Service account the CI prod-deploy workflow uses to drive docker on the hosts.
+# Membership in the docker group is root-equivalent (docker socket access), which
+# is all the deploy workflow needs; the account is deliberately not given sudo.
+deploy_user: deploy
+
+# Public half of the dedicated CI deploy SSH key, read from the controller at run
+# time. The private half is generated on the controller during provisioning and
+# stored ONLY in the Gitea PROD_SSH_KEY secret; it is never committed. Override the
+# path with -e deploy_ci_pubkey_path=/path/to/key.pub if the key lives elsewhere.
+deploy_ci_pubkey_path: "{{ lookup('env', 'HOME') }}/.ssh/scrabble_ci_deploy_ed25519.pub"
+deploy_ci_pubkey: "{{ lookup('file', deploy_ci_pubkey_path) }}"
+
+# Base directory the deploy workflow rsyncs compose files, config, certs and dumps
+# into. Owned by deploy_user so the workflow needs no elevation.
+scrabble_base_dir: /opt/scrabble
+
+# Docker daemon json-file log rotation, mirroring the compose x-logging anchor so
+# the host's own containers (and any ad-hoc runs) rotate identically.
+docker_log_max_size: "10m"
+docker_log_max_file: "3"
@@ -0,0 +1,19 @@
+# Production inventory for Stage 18.
+#
+# Hosts resolve through the operator's ~/.ssh/config aliases, so HostName (public
+# IP), User and IdentityFile live there — no IPs or key paths are committed here.
+#   scrabble-main-ops -> main stack host (public IP, domain erudit-game.ru)
+#   scrabble-tg-ops   -> Telegram bot host (direct Bot API egress, no VPN)
+
+[main]
+scrabble-main-ops
+
+[tg]
+scrabble-tg-ops
+
+[prod:children]
+main
+tg
+
+[prod:vars]
+ansible_user=root
@@ -0,0 +1,15 @@
+---
+- name: restart docker
+  ansible.builtin.service:
+    name: docker
+    state: restarted
+
+- name: reload sshd
+  ansible.builtin.service:
+    name: ssh
+    state: reloaded
+
+- name: restart fail2ban
+  ansible.builtin.service:
+    name: fail2ban
+    state: restarted
@@ -0,0 +1,167 @@
+---
+# Common baseline applied to both prod hosts: Docker engine, a non-sudo deploy
+# service account, SSH hardening, a default-deny firewall, fail2ban, unattended
+# security upgrades and time sync. Every task is idempotent.
+
+- name: Install base packages
+  ansible.builtin.apt:
+    name:
+      - ca-certificates
+      - curl
+      - gnupg
+      - ufw
+      - fail2ban
+      - unattended-upgrades
+      - chrony
+    state: present
+    update_cache: true
+    cache_valid_time: 3600
+
+# --- Docker engine (official repo; trixie is published upstream) ---------------
+
+- name: Create apt keyring directory
+  ansible.builtin.file:
+    path: /etc/apt/keyrings
+    state: directory
+    mode: "0755"
+
+- name: Install Docker apt GPG key
+  ansible.builtin.get_url:
+    url: https://download.docker.com/linux/debian/gpg
+    dest: /etc/apt/keyrings/docker.asc
+    mode: "0644"
+
+- name: Add Docker apt repository
+  ansible.builtin.apt_repository:
+    repo: >-
+      deb [arch=amd64 signed-by=/etc/apt/keyrings/docker.asc]
+      https://download.docker.com/linux/debian {{ ansible_distribution_release }} stable
+    filename: docker
+    state: present
+
+- name: Install Docker engine and the compose plugin
+  ansible.builtin.apt:
+    name:
+      - docker-ce
+      - docker-ce-cli
+      - containerd.io
+      - docker-buildx-plugin
+      - docker-compose-plugin
+    state: present
+    update_cache: true
+
+- name: Configure the Docker daemon (live-restore + log rotation)
+  ansible.builtin.template:
+    src: daemon.json.j2
+    dest: /etc/docker/daemon.json
+    mode: "0644"
+  notify: restart docker
+
+- name: Enable and start Docker
+  ansible.builtin.service:
+    name: docker
+    enabled: true
+    state: started
+
+# --- Deploy service account ----------------------------------------------------
+
+- name: Create the deploy service account
+  ansible.builtin.user:
+    name: "{{ deploy_user }}"
+    groups: docker
+    append: true
+    shell: /bin/bash
+    create_home: true
+
+- name: Ensure the deploy .ssh directory
+  ansible.builtin.file:
+    path: "/home/{{ deploy_user }}/.ssh"
+    state: directory
+    owner: "{{ deploy_user }}"
+    group: "{{ deploy_user }}"
+    mode: "0700"
+
+- name: Authorize the CI deploy SSH key (exclusive)
+  ansible.builtin.copy:
+    dest: "/home/{{ deploy_user }}/.ssh/authorized_keys"
+    content: "{{ deploy_ci_pubkey }}\n"
+    owner: "{{ deploy_user }}"
+    group: "{{ deploy_user }}"
+    mode: "0600"
+
+# --- SSH hardening -------------------------------------------------------------
+
+- name: Harden sshd (key-only auth)
+  ansible.builtin.template:
+    src: sshd-hardening.conf.j2
+    dest: /etc/ssh/sshd_config.d/10-scrabble-hardening.conf
+    mode: "0644"
+    validate: sshd -t -f %s
+  notify: reload sshd
+
+# --- Firewall (default deny incoming) ------------------------------------------
+# SSH is allowed before the policy flips so enabling ufw never locks us out.
+
+- name: Allow SSH through the firewall
+  community.general.ufw:
+    rule: allow
+    name: OpenSSH
+
+- name: Default-deny incoming, allow outgoing
+  community.general.ufw:
+    direction: "{{ item.direction }}"
+    policy: "{{ item.policy }}"
+  loop:
+    - { direction: incoming, policy: deny }
+    - { direction: outgoing, policy: allow }
+
+- name: Enable the firewall
+  community.general.ufw:
+    state: enabled
+
+# --- fail2ban ------------------------------------------------------------------
+
+- name: Configure the fail2ban sshd jail
+  ansible.builtin.template:
+    src: jail.local.j2
+    dest: /etc/fail2ban/jail.local
+    mode: "0644"
+  notify: restart fail2ban
+
+- name: Enable and start fail2ban
+  ansible.builtin.service:
+    name: fail2ban
+    enabled: true
+    state: started
+
+# --- Unattended security upgrades + time sync ----------------------------------
+
+- name: Enable unattended upgrades
+  ansible.builtin.copy:
+    dest: /etc/apt/apt.conf.d/20auto-upgrades
+    mode: "0644"
+    content: |
+      APT::Periodic::Update-Package-Lists "1";
+      APT::Periodic::Unattended-Upgrade "1";
+
+- name: Enable and start chrony
+  ansible.builtin.service:
+    name: chrony
+    enabled: true
+    state: started
+
+# --- Deploy directories --------------------------------------------------------
+
+- name: Create the scrabble base directories
+  ansible.builtin.file:
+    path: "{{ scrabble_base_dir }}/{{ item }}"
+    state: directory
+    owner: "{{ deploy_user }}"
+    group: "{{ deploy_user }}"
+    mode: "0750"
+  loop:
+    - ""
+    - config
+    - certs
+    - dumps
+    - images
@@ -0,0 +1,8 @@
+{
+  "live-restore": true,
+  "log-driver": "json-file",
+  "log-opts": {
+    "max-size": "{{ docker_log_max_size }}",
+    "max-file": "{{ docker_log_max_file }}"
+  }
+}
@@ -0,0 +1,9 @@
+# Managed by Ansible (deploy/ansible).
+[DEFAULT]
+bantime = 1h
+findtime = 10m
+maxretry = 5
+backend = systemd
+
+[sshd]
+enabled = true
@@ -0,0 +1,6 @@
+# Managed by Ansible (deploy/ansible). Key-only authentication.
+# root stays reachable by key (prohibit-password) for provisioning re-runs.
+PasswordAuthentication no
+PermitRootLogin prohibit-password
+PubkeyAuthentication yes
+KbdInteractiveAuthentication no
@@ -0,0 +1,18 @@
+---
+# Main stack host: public web + bot-link ports and the external 'edge' network
+# the compose stack attaches caddy to.
+
+- name: Open public web and bot-link ports
+  community.general.ufw:
+    rule: allow
+    port: "{{ item }}"
+    proto: tcp
+  loop:
+    - "80"    # HTTP (ACME challenge + redirect to HTTPS)
+    - "443"   # HTTPS (caddy edge)
+    - "9443"  # bot-link mTLS (remote bot dials in; mutual TLS gates access)
+
+- name: Ensure the external 'edge' docker network exists
+  community.docker.docker_network:
+    name: edge
+    state: present
@@ -0,0 +1,19 @@
+---
+# Telegram bot host: holds no inbound port beyond SSH (the bot dials out to the
+# Bot API and into the main host's bot-link). We only verify direct Bot API
+# egress here, since the "no VPN" decision depends on it.
+
+- name: Verify direct Telegram Bot API egress (no VPN on this host)
+  ansible.builtin.uri:
+    url: https://api.telegram.org/
+    method: GET
+    status_code: [200, 301, 302, 401, 404]   # any HTTP reply proves reachability
+    timeout: 10
+  register: tg_egress
+  failed_when: false
+
+- name: Report Telegram reachability
+  ansible.builtin.debug:
+    msg: >-
+      api.telegram.org reachable:
+      {{ (tg_egress.status | default(0) | int) > 0 }} (status {{ tg_egress.status | default('none') }})
@@ -0,0 +1,31 @@
+---
+# Stage 18 host provisioning. Idempotent: safe to re-run after a host resize.
+# Prepares hosts only (docker, hardening, service account, firewall); the
+# application is deployed separately by .gitea/workflows/prod-deploy.yaml.
+
+- name: Common baseline (both hosts)
+  hosts: prod
+  become: true
+  pre_tasks:
+    - name: Require a well-formed CI deploy public key
+      ansible.builtin.assert:
+        that:
+          - deploy_ci_pubkey | length > 0
+          - deploy_ci_pubkey is search('^(ssh|ecdsa)-')
+        fail_msg: >-
+          deploy_ci_pubkey is empty or malformed. Generate the key first
+          (see deploy/ansible/README.md) or override deploy_ci_pubkey_path.
+  roles:
+    - common
+
+- name: Main stack host
+  hosts: main
+  become: true
+  roles:
+    - main
+
+- name: Telegram bot host
+  hosts: tg
+  become: true
+  roles:
+    - tg
@@ -0,0 +1,53 @@
+# Production Telegram bot host descriptor (standalone — NOT an overlay). Run only on
+# the bot host:
+#   docker compose -f docker-compose.bot.yml up -d
+#
+# The bot egresses to the Bot API directly (no VPN sidecar) and dials the main host's
+# published bot-link :9443 over mTLS. It exports no telemetry — otelcol lives on the
+# main host and is unreachable from here — so observe it via `docker logs` on this host.
+# Values come from the prod-deploy workflow (PROD_ secrets/variables); BOT_IMAGE is the
+# pushed registry tag and BOTLINK_GATEWAY_ADDR is the main host's <ip>:9443.
+name: scrabble-bot
+
+services:
+  bot:
+    container_name: scrabble-telegram-bot
+    image: ${BOT_IMAGE:?set BOT_IMAGE to the registry tag}
+    restart: unless-stopped
+    logging:
+      driver: json-file
+      options:
+        max-size: "10m"
+        max-file: "3"
+    environment:
+      TELEGRAM_BOT_TOKEN: ${TELEGRAM_BOT_TOKEN:?set TELEGRAM_BOT_TOKEN}
+      TELEGRAM_GAME_CHANNEL_ID: ${TELEGRAM_GAME_CHANNEL_ID:-}
+      TELEGRAM_CHAT_ID: ${TELEGRAM_CHAT_ID:-}
+      TELEGRAM_PROMO_BOT_TOKEN: ${TELEGRAM_PROMO_BOT_TOKEN:-}
+      TELEGRAM_BOT_USERNAME: ${TELEGRAM_BOT_USERNAME:-}
+      TELEGRAM_BOT_LINK: ${TELEGRAM_BOT_LINK:-}
+      TELEGRAM_MINIAPP_URL: ${TELEGRAM_MINIAPP_URL:?set TELEGRAM_MINIAPP_URL}
+      # Real Bot API in prod (the test contour pins TELEGRAM_TEST_ENV=true instead).
+      TELEGRAM_TEST_ENV: "false"
+      TELEGRAM_API_BASE_URL: ${TELEGRAM_API_BASE_URL:-}
+      TELEGRAM_OWNS_UPDATES: "true"
+      # Dials the main host's published bot-link. ServerName stays `gateway` (the cert
+      # SAN), so TLS validation is independent of the dial address.
+      TELEGRAM_GATEWAY_ADDR: ${BOTLINK_GATEWAY_ADDR:?set BOTLINK_GATEWAY_ADDR (main:9443)}
+      TELEGRAM_BOTLINK_SERVER_NAME: gateway
+      TELEGRAM_BOTLINK_TLS_CERT: /certs/bot.crt
+      TELEGRAM_BOTLINK_TLS_KEY: /certs/bot.key
+      TELEGRAM_BOTLINK_TLS_CA: /certs/ca.crt
+      TELEGRAM_LOG_LEVEL: ${LOG_LEVEL:-info}
+      TELEGRAM_SERVICE_NAME: scrabble-telegram-bot
+      # No telemetry export: otelcol is on the main host, unreachable from here.
+      TELEGRAM_OTEL_TRACES_EXPORTER: none
+      TELEGRAM_OTEL_METRICS_EXPORTER: none
+      GOMAXPROCS: "1"
+    volumes:
+      - ${SCRABBLE_CONFIG_DIR:-.}/certs:/certs:ro
+    deploy:
+      resources:
+        limits:
+          cpus: "1.0"
+          memory: 256M
@@ -0,0 +1,98 @@
+# Production main-host overlay, applied on top of docker-compose.yml on the main host:
+#   docker compose -f docker-compose.yml -f docker-compose.prod.yml up -d
+#
+# It (1) publishes caddy 80/443 — there is no host caddy in prod, so the contour caddy
+# owns the edge and does its own ACME on CADDY_SITE_ADDRESS — and the gateway bot-link
+# :9443 the remote bot dials in over mTLS; and (2) retunes the R7 limits down for the
+# 2 vCPU / 1.9 GiB host (GOMAXPROCS=2, smaller memory caps, shorter Prometheus
+# retention). The contour launches deliberately undersized at zero players; the added
+# node_exporter + Grafana watch host memory so it can be resized at Selectel when
+# traffic arrives.
+#
+# The bot + its VPN sidecar are absent here (the telegram-local profile is not
+# activated); the prod bot runs on its own host from docker-compose.bot.yml.
+
+services:
+  caddy:
+    ports:
+      - "80:80"
+      - "443:443"
+    deploy:
+      resources:
+        limits:
+          memory: 96M
+
+  gateway:
+    # Prod pulls the pushed image by tag instead of building locally; the base
+    # build: section stays dormant because the deploy always pulls first.
+    image: ${REGISTRY:?set REGISTRY}/scrabble-gateway:${TAG:?set TAG}
+    ports:
+      - "9443:9443"
+    environment:
+      # 2 vCPU host: align the Go scheduler with the cgroup quota (R7's 3 needs 3 cores).
+      GOMAXPROCS: "2"
+    deploy:
+      resources:
+        limits:
+          cpus: "2.0"
+          memory: 384M
+
+  backend:
+    image: ${REGISTRY:?set REGISTRY}/scrabble-backend:${TAG:?set TAG}
+    deploy:
+      resources:
+        limits:
+          memory: 384M
+
+  postgres:
+    deploy:
+      resources:
+        limits:
+          memory: 384M
+
+  validator:
+    image: ${REGISTRY:?set REGISTRY}/scrabble-telegram-validator:${TAG:?set TAG}
+    deploy:
+      resources:
+        limits:
+          memory: 96M
+
+  landing:
+    image: ${REGISTRY:?set REGISTRY}/scrabble-landing:${TAG:?set TAG}
+    deploy:
+      resources:
+        limits:
+          memory: 64M
+
+  otelcol:
+    deploy:
+      resources:
+        limits:
+          memory: 256M
+
+  prometheus:
+    command:
+      - --config.file=/etc/prometheus/prometheus.yml
+      - --storage.tsdb.retention.time=7d
+    deploy:
+      resources:
+        limits:
+          memory: 256M
+
+  tempo:
+    deploy:
+      resources:
+        limits:
+          memory: 384M
+
+  grafana:
+    deploy:
+      resources:
+        limits:
+          memory: 256M
+
+  postgres_exporter:
+    deploy:
+      resources:
+        limits:
+          memory: 64M
@@ -240,14 +240,22 @@ services:
    networks: [internal]

  # --- Telegram bot (egress via the VPN sidecar in test; dials the gateway) ---
+  # vpn + bot are gated to the `telegram-local` profile: the test contour runs them
+  # locally (CI passes --profile telegram-local), the prod main host omits them, and
+  # the prod bot runs on its own host from deploy/docker-compose.bot.yml.
  vpn:
    container_name: scrabble-telegram-vpn
    image: docker.iliadenisov.ru/developer/amneziawg-sidecar:latest
+    profiles: ["telegram-local"]
    restart: unless-stopped
    logging: *default-logging
    privileged: true
    environment:
-      AWG_CONF: ${AWG_CONF:?set AWG_CONF}
+      # Required by the vpn sidecar, which is gated to the telegram-local profile.
+      # Compose can't scope a `:?` guard to a profile (interpolation runs for
+      # profiled-out services too) and the prod main host has no VPN, so this is a soft
+      # default; the test contour always supplies TEST_AWG_CONF and the sidecar validates it.
+      AWG_CONF: ${AWG_CONF:-}
    networks:
      internal:
        aliases: [telegram]
@@ -255,6 +263,7 @@ services:
  bot:
    container_name: scrabble-telegram-bot
    image: scrabble-telegram-bot:latest
+    profiles: ["telegram-local"]
    build:
      context: ..
      dockerfile: platform/telegram/Dockerfile
@@ -444,6 +453,26 @@ services:
          memory: 128M
    networks: [internal]

+  # node_exporter exports host CPU/memory/disk metrics. The prod main host runs a tight
+  # 1.9 GiB budget, so host memory pressure — not just per-container docker_stats — is
+  # what warns before an OOM. Prometheus scrapes it at :9100 (see prometheus.yml).
+  node_exporter:
+    container_name: scrabble-node-exporter
+    image: quay.io/prometheus/node-exporter:v1.8.2
+    restart: unless-stopped
+    logging: *default-logging
+    command:
+      - --path.rootfs=/host
+      - --collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host)($|/)
+    pid: host
+    volumes:
+      - /:/host:ro,rslave
+    deploy:
+      resources:
+        limits:
+          memory: 64M
+    networks: [internal]
+
 networks:
  internal:
    name: scrabble-internal
@@ -0,0 +1,134 @@
+#!/usr/bin/env bash
+# Production main-host deploy driver. Runs ON the main host, invoked over SSH by
+# .gitea/workflows/prod-deploy.yaml as the deploy user (which must already be
+# `docker login`ed to the registry). It pulls the images at the new tag and rolls
+# the stack ONE service at a time in dependency order (least -> most dependent),
+# health-checking after each; any failure rolls the whole stack back to the
+# previously deployed tag.
+#
+# A schema migration adds a maintenance window: the backend (the only writer) is
+# stopped so a consistent pg_dump is taken before the new backend migrates forward.
+# Image rollback alone is safe under the expand-contract migration rule, so the
+# automatic rollback never touches the database; the dump is kept for a MANUAL
+# restore if a migration turned out to be destructive (see deploy/prod/README.md).
+#
+# Required env (exported by the workflow over SSH):
+#   REGISTRY   registry namespace, e.g. docker.iliadenisov.ru/developer
+#   TAG        new image tag (the deployed git SHA)
+#   PREV_TAG   previously deployed tag, or "none" on the first deploy
+#   MIGRATION  "1" when the deploy carries a schema migration, else "0"
+# Optional: COMPOSE_DIR ENV_FILE DUMP_DIR STATE_FILE POSTGRES_USER POSTGRES_DB
+set -uo pipefail
+
+# Runtime compose vars (POSTGRES_*, GM_*, GRAFANA_*, CADDY_*, TELEGRAM_*, REGISTRY,
+# SCRABBLE_CONFIG_DIR, ...) come from a shell-sourceable env file the workflow writes
+# with single-quoted values. Exporting them into the process environment lets compose
+# interpolate ${...} without re-parsing the value — a plain --env-file would mangle the
+# literal '$' in the bcrypt GM_BASICAUTH_HASH.
+ENV_FILE="${ENV_FILE:-/opt/scrabble/env.sh}"
+# shellcheck disable=SC1090
+[ -f "$ENV_FILE" ] && . "$ENV_FILE"
+
+REGISTRY="${REGISTRY:?REGISTRY required (env.sh)}"
+TAG="${TAG:?TAG required}"
+PREV_TAG="${PREV_TAG:-none}"
+MIGRATION="${MIGRATION:-0}"
+COMPOSE_DIR="${COMPOSE_DIR:-/opt/scrabble/compose}"
+DUMP_DIR="${DUMP_DIR:-/opt/scrabble/dumps}"
+STATE_FILE="${STATE_FILE:-/opt/scrabble/DEPLOYED_TAG}"
+PG_USER="${POSTGRES_USER:-scrabble}"
+PG_DB="${POSTGRES_DB:-scrabble}"
+
+cd "$COMPOSE_DIR" || { echo "compose dir $COMPOSE_DIR missing"; exit 1; }
+export REGISTRY
+# otelcol joins the host docker group to read the socket; the GID varies per host.
+DOCKER_GID="$(getent group docker | cut -d: -f3)"
+export DOCKER_GID
+
+dc() { docker compose -f docker-compose.yml -f docker-compose.prod.yml "$@"; }
+use_tag() { export TAG="$1"; }
+
+# --- health probes (one-off containers on the contour networks, like CI) --------
+_probe() { docker run --rm --network "$1" alpine:3.20 wget -q -T 5 -O /dev/null "$2"; }
+health_backend() { for _ in $(seq 1 20); do _probe scrabble-internal http://backend:8080/readyz && return 0; sleep 3; done; return 1; }
+health_landing() { for _ in $(seq 1 20); do _probe scrabble-internal http://landing:80/ && return 0; sleep 3; done; return 1; }
+health_postgres() { for _ in $(seq 1 30); do [ "$(docker inspect -f '{{.State.Health.Status}}' scrabble-postgres 2>/dev/null)" = healthy ] && return 0; sleep 2; done; return 1; }
+health_running() { # health_running <container>: running, not restarting, stable restart count
+  local n="$1" s r c1 c2
+  for _ in $(seq 1 20); do
+    s="$(docker inspect -f '{{.State.Status}}' "$n" 2>/dev/null || echo missing)"
+    r="$(docker inspect -f '{{.State.Restarting}}' "$n" 2>/dev/null || echo true)"
+    if [ "$s" = running ] && [ "$r" = false ]; then
+      c1="$(docker inspect -f '{{.RestartCount}}' "$n")"; sleep 5
+      c2="$(docker inspect -f '{{.RestartCount}}' "$n")"
+      [ "$c1" = "$c2" ] && return 0
+    fi
+    sleep 3
+  done
+  return 1
+}
+
+roll() { # roll <service> <health-cmd...>
+  local svc="$1"; shift
+  echo ">>> rolling $svc -> $TAG"
+  dc up -d --no-build --no-deps "$svc" || return 1
+  "$@" || { echo "!!! $svc failed health check"; return 1; }
+  echo "<<< $svc healthy"
+}
+
+rollback() {
+  echo "########## ROLLBACK -> $PREV_TAG ##########"
+  if [ "$PREV_TAG" = none ]; then
+    echo "no previous tag (first deploy): cannot roll back; leaving the stack up for inspection."
+    return
+  fi
+  use_tag "$PREV_TAG"
+  dc up -d --no-build --remove-orphans
+  echo "rolled back to $PREV_TAG."
+  [ "$MIGRATION" = 1 ] && echo "NOTE: the DB is forward-migrated; a pre-deploy dump is in $DUMP_DIR — restore manually ONLY if the migration was destructive (see deploy/README.md, prod runbook)."
+}
+
+mkdir -p "$DUMP_DIR"
+echo "=== prod deploy: tag=$TAG prev=$PREV_TAG migration=$MIGRATION ==="
+use_tag "$TAG"
+dc pull
+
+# First deploy: nothing to roll from; bring the whole stack up and gate on health.
+if [ -z "$(docker ps -aq -f name=scrabble-backend)" ]; then
+  echo "first deploy: bringing the whole stack up"
+  dc up -d --no-build --remove-orphans || { echo "compose up failed"; exit 1; }
+  health_backend || { echo "backend not ready"; exit 1; }
+  health_landing || { echo "landing not ready"; exit 1; }
+  echo "$TAG" > "$STATE_FILE"
+  echo "first deploy healthy ($TAG)."
+  exit 0
+fi
+
+# Migration deploy: freeze writes and snapshot a consistent dump before migrating.
+if [ "$MIGRATION" = 1 ]; then
+  echo "migration deploy: opening maintenance window (stopping the backend = the only writer)"
+  dc stop backend
+  dump="$DUMP_DIR/pre-$TAG-$(date +%Y%m%d-%H%M%S).sql"
+  if ! docker exec scrabble-postgres pg_dump -U "$PG_USER" -d "$PG_DB" -n backend > "$dump"; then
+    echo "pg_dump failed; restarting the old backend and aborting"
+    dc start backend
+    exit 1
+  fi
+  echo "consistent dump: $dump"
+fi
+
+# Roll one service at a time, least -> most dependent; any failure rolls everything back.
+roll postgres  health_postgres                              || { rollback; exit 1; }
+roll backend   health_backend                               || { rollback; exit 1; }
+roll gateway   health_running scrabble-gateway              || { rollback; exit 1; }
+roll landing   health_landing                               || { rollback; exit 1; }
+roll validator health_running scrabble-telegram-validator   || { rollback; exit 1; }
+roll caddy     health_running scrabble-caddy                || { rollback; exit 1; }
+
+# Observability + node_exporter: bring up the remainder and pick up any config changes.
+dc up -d --no-build --remove-orphans || { rollback; exit 1; }
+
+# Final internal sanity before committing the new tag.
+health_backend || { rollback; exit 1; }
+echo "$TAG" > "$STATE_FILE"
+echo "=== deploy healthy ($TAG) ==="
@@ -18,3 +18,8 @@ scrape_configs:
  - job_name: postgres_exporter
    static_configs:
      - targets: ["postgres_exporter:9187"]
+  # Host-level metrics (memory/CPU/disk). Matters most on the prod main host's tight
+  # 1.9 GiB budget, where total host memory is the OOM-proximity signal.
+  - job_name: node
+    static_configs:
+      - targets: ["node_exporter:9100"]
@@ -1056,8 +1056,10 @@ plaintext relay (`GATEWAY_BOTLINK_RELAY_ADDR`) the backend admin console calls.

 The full contour (`deploy/docker-compose.yml`) runs one `gateway`, one `backend`,
 one Postgres, the static `landing`, the Telegram `validator` and `bot` (+ the bot's VPN
-sidecar) and the **observability stack** —
-OTel Collector (OTLP/gRPC ingest → Prometheus metrics + Tempo traces) and Grafana
+sidecar — the `bot`+`vpn` pair is gated to a `telegram-local` compose profile so the prod
+main host can omit them) and the **observability stack** —
+OTel Collector (OTLP/gRPC ingest → Prometheus metrics + Tempo traces), a `node_exporter`
+for host CPU/memory (the prod main host's OOM signal), and Grafana
 with provisioned datasources and dashboards. All services export OTLP to the
 collector; the bot shares the VPN sidecar's netns, so its `AWG_CONF` must not
 carry a `DNS=` directive (that would hijack resolv.conf and stop it resolving
@@ -1081,16 +1083,30 @@ Two contours, two secret/variable prefixes (`TEST_` / `PROD_`):
  generated by `deploy/gen-certs.sh` before `compose up`; the bot keeps its VPN sidecar
  for Telegram egress and dials the gateway by its internal name, so the bot-link stays
  on the internal network.
- **Prod**: a manual SSH deploy after `development → master`. There is no
-  host caddy, so the contour ships its own caddy terminating TLS — set
-  `CADDY_SITE_ADDRESS` to the domain and the caddy does its own ACME. The **bot runs
-  on a separate host** with native Telegram access (no VPN), deployed by SSH alongside
-  the main app (rolled together so the bot-link protocol versions never skew); the
-  gateway **publishes** the bot-link port and the certificates come from `PROD_`
-  secrets — a long-lived CA with leaves rotated by a scheduled job. The bot dials the
-  gateway's public bot-link endpoint and holds no inbound port; login is unaffected if
-  that host or the link is down. *(This prod wiring is the deferred final stage; the
-  code and the unified test contour land first — see `PRERELEASE.md`.)*
+- **Prod**: a **manual** rollout — `.gitea/workflows/prod-deploy.yaml`, `workflow_dispatch`
+  only (from `master`, `confirm=deploy`), run after `development → master` is merged green.
+  It builds and pushes the images to the registry (`docker.iliadenisov.ru`), then deploys
+  over SSH onto **two hosts** provisioned by `deploy/ansible/` (docker, a non-sudo `deploy`
+  service account holding a dedicated CI key, key-only sshd, default-deny ufw, fail2ban):
+  the **main host** runs the full stack (`docker-compose.yml` + `docker-compose.prod.yml`),
+  the **bot host** runs only the bot (`docker-compose.bot.yml`, no VPN — native Bot API
+  egress, telemetry off). There is no host caddy, so the contour caddy terminates TLS —
+  `CADDY_SITE_ADDRESS` is the domain and caddy does its own ACME. The gateway **publishes**
+  the bot-link `:9443`; the remote bot dials it over mTLS (certs from `PROD_BOTLINK_*`,
+  ServerName `gateway`, so TLS validation is independent of the public dial address), holds
+  no inbound port, and login is unaffected if that host or the link is down.
+  `deploy/prod-deploy.sh` rolls the main stack **one service at a time in dependency order**
+  (postgres → backend → gateway → landing → validator → caddy), health-checking after each;
+  any failure **rolls the whole stack back to the previous image tag**. A **schema migration**
+  adds a maintenance window: the backend (the sole writer) is stopped for a consistent
+  `pg_dump` before the new backend migrates forward — image rollback stays DB-safe under the
+  expand-contract migration rule, and the dump is kept for a manual restore. The main host is
+  intentionally **launch-sized** (2 vCPU / 1.9 GiB): the prod overlay trims the R7 limits
+  (`GOMAXPROCS=2`, smaller caps, 7d Prometheus retention) and a **node_exporter** feeds
+  host-memory metrics to Grafana so it can be resized reactively as players arrive.
+  `GATEWAY_ABUSE_BAN_ENABLED=true` in prod (the per-IP ban is meaningful only with real
+  client IPs). The `vpn`+`bot` pair is gated to a `telegram-local` compose profile the test
+  contour activates; the prod main host omits it.

 ## 14. CI & branches