hyperhive/nix/host-modules/hive-gateway/vhosts.nix

# nginx virtual-host tree for the gateway: the `_` default server
# (dashboard, per-agent routing, matrix discovery), the forge, matrix
# and authelia sub-domain vhosts, and the Accept-header SPA map for the
# matrix GUI. Pure function — called from ./default.nix with the
# outer-scope config values as arguments; returns
# `{ virtualHosts, appendHttpConfig }`.
{
  lib,
  cfg, # services.hyperhive.gateway
  matrixCfg,
  autheliaCfg, # services.hyperhive.swarm.authelia
  uiCfg, # services.hyperhive.swarm.ui
  controllerCfg, # services.hyperhive.swarm.controller
  hyperhiveDomain,
  dashboardDist,
  swaggerUiTheme, # nix/packages/swagger-ui-theme.nix: has index.html + hyperhive-theme.css
  errorPages, # ./error-pages.nix: { notFound, unreachable, unauthorized, ssoUnavailable }
  gwLib, # `services.hyperhive.gateway.lib` — ./vhost-lib.nix's kit, via the option
}:
let
  # The kit's three members, bound to the names this file already used.
  # Read through `gwLib` (the published option) rather than importing
  # ./vhost-lib.nix directly: a service module declaring its own vhost
  # gets the same object, so "the forge vhost listens where the gateway
  # listens" is true by construction and not by review.
  inherit (gwLib) securityHeaders;
  vhostListen = gwLib.listen;
  vhostTlsFor = gwLib.tlsFor;

  # Public-facing scheme + port-suffix for URLs the gateway
  # mints into responses (well-known JSON, the deprecated
  # `<hive>/matrix/*` 301 redirect, future absolute-URL needs):
  # always `https://<host>` (matrix-spec compliance) — the canonical
  # 443 elides the port. See `docs/gateway.md` ("Self-signed TLS").
  publicScheme = "https";
  publicPort = cfg.httpsPort;
  publicPortSuffix = if publicPort == 443 then "" else ":${toString publicPort}";

  # Authelia sub-domain vhost. `server_name = authelia.domain`, all of
  # `/` → authelia. Empty attrset unless THIS host runs the container:
  # every hive knows the swarm's `authelia.url`, but only the one
  # serving it may claim the name — a client hive declaring this vhost
  # would answer for a service it does not run.
  #
  # ⚠️ The server name must be exactly `autheliaCfg.domain`, not a
  # near-miss: authelia validates `authelia_url ⊂ session cookie domain`
  # at STARTUP, so a mismatch is a container that refuses to boot rather
  # than a login that misbehaves.
  #
  # ⚠️ And deliberately NO `dashboardAuth` here. That block is the
  # gateway's `auth_basic`; applying it to the SSO provider would put
  # the login page behind the login mechanism it exists to replace.
  autheliaVhost = lib.optionalAttrs autheliaCfg.enable {
    "${autheliaCfg.domain}" = (vhostTlsFor autheliaCfg.domain) // {
      listen = vhostListen;
      extraConfig = securityHeaders;
      locations."/" = {
        proxyPass = "http://127.0.0.1:${toString autheliaCfg.port}/";
        proxyWebsockets = true;
        extraConfig = ''
          proxy_buffering off;
          # authelia decides by the ORIGINAL request, not by the hop it
          # sees — the login redirect and the session cookie's domain
          # both derive from these. Without them every request looks
          # like it arrived at 127.0.0.1 over plain http.
          proxy_set_header X-Forwarded-Proto $scheme;
          proxy_set_header X-Forwarded-Host $host;
          proxy_set_header X-Forwarded-Uri $request_uri;
          proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
          # A dead upstream here means "not bootstrapped" far more often
          # than "misconfigured proxy", and a bare 502 says the opposite.
          proxy_intercept_errors on;
          error_page 502 503 504 = /__hive_sso_unavailable;
        '';
      };
      locations."= /__hive_sso_unavailable" = {
        extraConfig = ''
          internal;
          alias ${errorPages.ssoUnavailable};
          default_type text/html;
        '';
      };
    };
  };

  # Swarm UI vhost — the swarm's front page, on the swarm apex, and the
  # FIRST `auth_request` anywhere in this gateway (everything else is
  # `auth_basic` + htpasswd).
  #
  # ⚠️ `auth_request` answers "is there a session", not "is this an
  # operator". The operator-only part is authelia's `access_control`
  # rule (../swarm-authelia.nix) requiring `group:operators` — agents
  # are getting authelia accounts of their own, and without that rule a
  # session alone would open this page.
  #
  # ⚠️ Failure mode here is LOCKED OUT, not unprotected: a subrequest
  # that wrongly denies takes the whole UI away. That is the reason the
  # redirect target and the header set below are copied from a measured
  # source rather than from an example.
  # ⚠️ `forceSSL`, not `addSSL` like every other vhost — not a hardening
  # preference, the only way this page works at all. authelia answers the
  # auth subrequest for an `http://` target with **400**, and nginx's
  # `auth_request` only understands 2xx/401/403, so a plain-http visit
  # dies as "auth request unexpected status: 400" with no hint a login
  # exists. `vhostListen` binds :80, so without this the door is open on
  # a port the lock cannot work on. Serving forge or matrix over http is
  # merely insecure rather than broken, so they keep `addSSL` and the
  # asymmetry stays local to the vhost whose correctness depends on the
  # scheme. `removeAttrs` because nixos asserts on a vhost declaring both.
  # Shared with every swarm-UI-vhost location below (`/`, `/api/`,
  # `/api/docs/`) — auth_request does not inherit across sibling
  # locations, so each one that should be operator-gated repeats this
  # verbatim rather than only the page itself being protected while its
  # own API and API docs are reachable unauthenticated.
  swarmAuthRequest = ''
    auth_request /__hive_authelia;
    # Captured BEFORE the error_page jump: inside the 401 handler
    # `$request_uri` is the internal one, so building the return
    # link there sends the operator back to the auth subrequest
    # instead of the page they asked for.
    auth_request_set $target_url $scheme://$http_host$request_uri;
    error_page 401 =302 https://${autheliaCfg.domain}/?rd=$target_url;
  '';

  swarmUiVhost = lib.optionalAttrs uiCfg.enable {
    "${uiCfg.domain}" = (builtins.removeAttrs (vhostTlsFor uiCfg.domain) [ "addSSL" ]) // {
      forceSSL = true;
      listen = vhostListen;
      extraConfig = securityHeaders;
      locations = {
        "/" = {
          root = "${uiCfg.package}";
          extraConfig = ''
            ${swarmAuthRequest}
            # SPA: any path the bundle routes client-side is served the
            # entry document rather than a 404 from the filesystem.
            try_files $uri /index.html;
          '';
        };
        # swarm-controller's whole HTTP surface, including the live
        # `/api/openapi.json` spec — proxied untouched (no URI segment
        # after the socket path, same "pass the request through as-is"
        # shape as the per-hive dashboard's own `/api/` proxy) so the
        # path swarm-controller registered a route at is the path
        # nginx forwards, no prefix-stripping to keep in sync by hand.
        "/api/" = {
          proxyPass = "http://unix:${controllerCfg.socketPath}:";
          extraConfig = swarmAuthRequest;
        };
        # Swagger UI: same "nginx hosts the themed dist straight from
        # the store, only /api/openapi.json is dynamic" shape as the
        # per-hive gateway's `swaggerUiLocations` — see that block's
        # comment for why core-equivalent (here, swarm-controller)
        # does not also mount its own copy.
        "= /api/docs" = {
          extraConfig = ''
            return 301 /api/docs/;
          '';
        };
        "/api/docs/" = {
          alias = "${swaggerUiTheme}/";
          extraConfig = ''
            index index.html;
            ${swarmAuthRequest}
          '';
        };
        # The subrequest itself. `auth-request` is the implementation
        # name authelia exposes under `/api/authz/`; `/api/verify` is the
        # LEGACY path every older example shows.
        #
        # Header set measured against the pinned binary (4.39.20), not
        # copied: `X-Original-URL` and `X-Original-Method` are present as
        # literals and are what this implementation reads —
        # `X-Forwarded-Uri` does not appear in it at all, so sending it
        # would look like configuration and be dead weight.
        "= /__hive_authelia" = {
          proxyPass = "http://127.0.0.1:${toString autheliaCfg.port}/api/authz/auth-request";
          extraConfig = ''
            internal;
            # A subrequest carries no body, and forwarding one here makes
            # authelia read a payload it will never use.
            proxy_pass_request_body off;
            proxy_set_header Content-Length "";
            proxy_set_header X-Original-Method $request_method;
            proxy_set_header X-Original-URL $scheme://$http_host$request_uri;
            proxy_set_header X-Forwarded-Proto $scheme;
            proxy_set_header X-Forwarded-Host $http_host;
            proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
          '';
        };
      };
    };
  };

  # Matrix sub-domain vhost. `server_name = matrixCfg.gatewayHost`.
  # `/_matrix/*` → tuwunel (CORS *, 50M body cap, 1h long-poll
  # timeout). `/` serves fluffychat or 404 if GUI off. nginx
  # longer-prefix-wins puts `/_matrix/` ahead of `/`. See
  # `docs/gateway.md`. Empty attrset when matrix has no gateway host.
  matrixVhost = lib.optionalAttrs (matrixCfg.enable && matrixCfg.gatewayHost != null) {
    "${matrixCfg.gatewayHost}" = (vhostTlsFor matrixCfg.gatewayHost) // {
      listen = vhostListen;
      extraConfig = securityHeaders;
      locations = {
        "/_matrix/" = {
          proxyPass = "http://127.0.0.1:${toString matrixCfg.httpPort}";
          proxyWebsockets = true;
          extraConfig = ''
            proxy_buffering off;
            client_max_body_size 50M;
            proxy_read_timeout 1h;
            proxy_send_timeout 1h;
            ${securityHeaders}
            add_header Access-Control-Allow-Origin *;
          '';
        };
      }
      // lib.optionalAttrs (matrixCfg.gui.enable) (
        {
          # fluffychat at sub-domain root, SPA-fallback via
          # the Accept-header `$matrix_spa_target` map.
          "/" = {
            alias = "${matrixCfg.gui.package}/";
            extraConfig = ''
              try_files $uri $uri/ $matrix_spa_target =404;
            '';
          };
        }
        // {
          # FluffyChat boot-config pre-fill so the client's
          # `.well-known/matrix/client` lookup hits the
          # right delegation endpoint. `domain` is required, so
          # this is always present.
          "= /config.json" = {
            extraConfig = ''
              default_type application/json;
              return 200 '{"defaultHomeserver":"${hyperhiveDomain}"}';
            '';
          };
        }
      )
      // lib.optionalAttrs (!matrixCfg.gui.enable) {
        "/" = {
          return = "404";
        };
      };
    };
  };

  # `<hive>/matrix/*` → 301 → `matrix.<hive>/$1` (legacy deep-link
  # shim during the fluffychat sub-domain move). See `docs/gateway.md`.
  matrixRedirectLocations =
    lib.optionalAttrs (matrixCfg.enable && matrixCfg.gui.enable && matrixCfg.gatewayHost != null)
      (
        let
          target = "${publicScheme}://${matrixCfg.gatewayHost}${publicPortSuffix}";
        in
        {
          "/matrix/" = {
            extraConfig = ''
              rewrite ^/matrix/(.*)$ ${target}/$1 permanent;
            '';
          };
        }
      );

  # `.well-known/matrix/{client,server}` discovery JSON. Points
  # clients at `matrixCfg.gatewayHost` when set; falls back to direct
  # `<hive>:<httpPort>`. CORS `*` per matrix spec. The `m.server`
  # port-8448 carve-out is documented inline. See `docs/gateway.md`.
  wellKnownLocations = lib.optionalAttrs matrixCfg.enable (
    let
      clientBaseUrl =
        if matrixCfg.gatewayHost != null then
          "${publicScheme}://${matrixCfg.gatewayHost}${publicPortSuffix}"
        else
          "${publicScheme}://${hyperhiveDomain}:${toString matrixCfg.httpPort}";
      # `m.server` is NOT a URL: per the matrix server-server spec
      # (Resolving Server Names) a delegated host with NO port resolves
      # to the federation default 8448 (after the SRV check) — the
      # https-implies-443 rule does NOT apply here. So the port must be
      # explicit even when it's the HTTPS default; `publicPortSuffix`
      # (which drops :443) is right for the client base_url above but
      # wrong for federation delegation. Without this, peers federate to
      # <gatewayHost>:8448 (closed) while the endpoint actually lives on
      # the gateway's 443 vhost. See docs/gateway.md discovery flow.
      serverHostPort =
        if matrixCfg.gatewayHost != null then
          "${matrixCfg.gatewayHost}:${toString publicPort}"
        else
          "${hyperhiveDomain}:${toString matrixCfg.httpPort}";
    in
    {
      "= /.well-known/matrix/client" = {
        extraConfig = ''
          default_type application/json;
          ${securityHeaders}
          add_header Access-Control-Allow-Origin *;
          return 200 '{"m.homeserver":{"base_url":"${clientBaseUrl}"}}';
        '';
      };
      "= /.well-known/matrix/server" = {
        extraConfig = ''
          default_type application/json;
          return 200 '{"m.server":"${serverHostPort}"}';
        '';
      };
    }
  );

  # `/agent/` catch-all 404 + the two internal error-page targets it
  # points at. Per-agent `location /agent/<name>/` blocks live in the
  # runtime-generated `/var/lib/hive-gateway/conf/agents.conf` (included via
  # `extraConfig` on the vhost); nginx longest-prefix-match makes a
  # real `/agent/<name>/` beat this catch-all. `internal` keeps the
  # error pages reachable only through nginx's error handling.
  agentLocations = {
    "/agent/" = {
      extraConfig = ''
        error_page 404 = /__hive_agent_not_found;
        return 404;
      '';
    };
    "= /__hive_agent_not_found" = {
      extraConfig = ''
        internal;
        alias ${errorPages.notFound};
        default_type text/html;
      '';
    };
    "= /__hive_agent_unreachable" = {
      extraConfig = ''
        internal;
        alias ${errorPages.unreachable};
        default_type text/html;
      '';
    };
  };

  # Shared auth block — separate locations don't inherit auth_basic, so
  # each dashboard location (`/`, `/api/`) needs it or that surface is
  # unauthed. `/webhook/` is intentionally excluded: Forgejo cannot
  # send HTTP Basic credentials with webhook deliveries, and the HMAC
  # secret (`X-Hub-Signature-256`) protects those endpoints instead.
  dashboardAuth = lib.optionalString cfg.auth.enable ''
    auth_basic "${cfg.auth.realm}";
    auth_basic_user_file /var/lib/hive-gateway/conf/gateway.htpasswd;
    # `=401` keeps the status 401 so the login dialog shows; the
    # internal page explains `hivectl gateway create-user`.
    error_page 401 =401 /__hive_auth_unauthorized;
  '';

  # Dashboard: nginx static-serves the dist, c0re is API-only. Routing
  # is by PATH, never content-type. c0re serves exactly three prefixes —
  # `/api/` (all dashboard data + actions + the SSE streams), `/webhook/`
  # (knowledge push + config-PR approval triggers, HMAC-guarded), and
  # `/health/` (liveness + readiness) — so those proxy to c0re and
  # everything else serves the dist with an SPA fallback to index.html.
  # Path routing is deterministic where an Accept-header split would make
  # the SAME url behave differently by content-type (e.g. `/api/state`
  # fetched with `Accept: text/html` wrongly getting index.html). A new
  # top-level c0re route prefix (beyond /api + /webhook + /health) needs
  # a matching location added here.
  dashboardProxyLocation = {
    "/" = {
      root = dashboardDist;
      extraConfig = ''
        try_files $uri /index.html;
        ${dashboardAuth}
      '';
    };
    "/api/" = {
      proxyPass = "http://${cfg.upstreamHost}:${toString cfg.upstreamPort}";
      proxyWebsockets = true;
      extraConfig = ''
        # off + 1d keep the SSE streams (/api/dashboard/stream,
        # /api/build-logs/id/{id}/stream) live.
        proxy_buffering off;
        proxy_read_timeout 1d;
        ${dashboardAuth}
      '';
    };
    "/webhook/" = {
      # No dashboardAuth here: Forgejo cannot send HTTP Basic credentials
      # with webhook deliveries. HMAC (X-Hub-Signature-256) is the auth
      # for these endpoints; hive-c0re verifies it in the handler.
      proxyPass = "http://${cfg.upstreamHost}:${toString cfg.upstreamPort}";
    };
    "/health/" = {
      # No dashboardAuth here either, for a different reason than
      # /webhook/: an external uptime monitor generally can't do
      # interactive HTTP Basic. The endpoints themselves are scoped to
      # status + warning kind/message (see hive-c0re/src/dashboard/
      # health.rs) — no tokens, no agent detail — so exposing them
      # unauthenticated isn't a new secret surface.
      proxyPass = "http://${cfg.upstreamHost}:${toString cfg.upstreamPort}";
    };
  };

  # Swagger UI: nginx hosts the FULL themed dist (`swaggerUiTheme` —
  # vendored Swagger UI + our overlay, see nix/packages/swagger-ui-
  # dist.nix + swagger-ui-theme.nix) straight from the store, with NO
  # fallback to hive-c0re at all — per the operator's shape: "core
  # should not need the swagger ui at all if it is hosted in gateway"
  # / "core only hosts the json". Only `/api/openapi.json`
  # (the live-generated spec `index.html` fetches; not under this
  # prefix) still proxies to c0re via "/api/" below — that's the one
  # thing that has to stay dynamic.
  #
  # Prefix location, not exact-match: wins over "/api/" on plain
  # prefix length (no ordering/`=` needed), and now needs to cover
  # every file in the tree (bundle.js, maps, favicons, …), not just
  # our 2 override files — hive-c0re no longer serves any of this as
  # a fallback once its own `utoipa-swagger-ui` mount is removed.
  # `= /api/docs` (no trailing slash) issues the same redirect
  # `utoipa-swagger-ui`'s router used to: that mount is going away
  # too, so nginx has to own it now, or the H0M3 hub's own `/api/docs`
  # link (no trailing slash) would 404 once hive-c0re drops the route.
  swaggerUiLocations = {
    "= /api/docs" = {
      extraConfig = ''
        return 301 /api/docs/;
      '';
    };
    "/api/docs/" = {
      alias = "${swaggerUiTheme}/";
      extraConfig = ''
        index index.html;
        ${dashboardAuth}
      '';
    };
  };
in
{
  # Accept-header SPA map for the matrix GUI only (see docs/gateway.md
  # "SPA fallback"): text/html → index.html, else a sentinel so
  # try_files falls through to 404. The dashboard doesn't use an
  # Accept-header map — it routes by path (see dashboardProxyLocation).
  appendHttpConfig = lib.optionalString (matrixCfg.enable && matrixCfg.gui.enable) ''
    map $http_accept $matrix_spa_target {
      default              "/__matrix_spa_no_html_fallback";
      "~*text/html"        "/index.html";
    }
  '';

  virtualHosts = {
    # `tlsFor "_"`, not a separate binding: the default server is a
    # vhost named `_`, and a name that is not a swarm service domain
    # (`_` never is) resolves to the hive's own leaf — which is what
    # this vhost has always served.
    "_" = (vhostTlsFor "_") // {
      listen = vhostListen;
      locations =
        matrixRedirectLocations
        // wellKnownLocations
        // agentLocations
        // dashboardProxyLocation
        // swaggerUiLocations
        // lib.optionalAttrs cfg.auth.enable {
          # Internal-only target for the 401 error_page above.
          # `internal` prevents direct client access; `alias` serves
          # the pre-built HTML from the Nix store.
          "= /__hive_auth_unauthorized" = {
            extraConfig = ''
              internal;
              alias ${errorPages.unauthorized};
              default_type text/html;
            '';
          };
        };
      # Per-agent location blocks, generated at runtime by
      # hive-c0re and written to /var/lib/hive-gateway/conf/agents.conf
      # on the host — the same machine nginx runs on. nginx parses
      # `include` at config-load time so a reload (triggered by c0re
      # after each agents.conf write) picks up new or removed
      # agents without a nixos-rebuild. nginx's longest-prefix-
      # match rule ensures `/agent/<name>/` from this file beats
      # the `/agent/` catch-all above.
      extraConfig = securityHeaders + ''
        include /var/lib/hive-gateway/conf/agents.conf;
      '';
    };
  }
  // autheliaVhost
  // matrixVhost
  // swarmUiVhost;
}