prowlarr: handle bitmagnet restart

services/bitmagnet.nix

@@ -5,6 +5,57 @@
   lib,
   ...
 }:
+let
+  prowlarrPort = toString service_configs.ports.private.prowlarr.port;
+  sonarrPort = toString service_configs.ports.private.sonarr.port;
+  radarrPort = toString service_configs.ports.private.radarr.port;
+  bitmagnetPort = toString service_configs.ports.private.bitmagnet.port;
+  bridgeAddr = config.vpnNamespaces.wg.bridgeAddress;
+
+  prowlarrConfigXml = "${service_configs.prowlarr.dataDir}/config.xml";
+  sonarrConfigXml = "${service_configs.sonarr.dataDir}/config.xml";
+  radarrConfigXml = "${service_configs.radarr.dataDir}/config.xml";
+
+  curl = "${pkgs.curl}/bin/curl";
+  jq = "${pkgs.jq}/bin/jq";
+
+  # Clears the escalating failure backoff for the Bitmagnet indexer across
+  # Prowlarr, Sonarr, and Radarr so searches resume immediately after
+  # Bitmagnet restarts instead of waiting hours for disable timers to expire.
+  recoveryScript = pkgs.writeShellScript "prowlarr-bitmagnet-recovery" ''
+    set -euo pipefail
+
+    wait_for() {
+      for _ in $(seq 1 "$2"); do
+        ${curl} -sf --max-time 5 "$1" > /dev/null && return 0
+        sleep 5
+      done
+      echo "$1 not reachable, aborting" >&2; exit 1
+    }
+
+    # Test a Bitmagnet-named indexer to clear its failure status.
+    # A successful test triggers RecordSuccess() which resets the backoff.
+    clear_status() {
+      local key indexer
+      key=$(${lib.extractArrApiKey ''"$3"''}) || return 0
+      indexer=$(${curl} -sf --max-time 10 \
+        -H "X-Api-Key: $key" "$2/api/$1/indexer" | \
+        ${jq} 'first(.[] | select(.name | test("Bitmagnet"; "i")))') || return 0
+      [ -n "$indexer" ] && [ "$indexer" != "null" ] || return 0
+      ${curl} -sf --max-time 30 \
+        -H "X-Api-Key: $key" -H "Content-Type: application/json" \
+        -X POST "$2/api/$1/indexer/test" -d "$indexer" > /dev/null
+    }
+
+    wait_for "http://localhost:${bitmagnetPort}" 12
+    wait_for "http://localhost:${prowlarrPort}/ping" 6
+
+    # Prowlarr first — downstream apps route searches through it.
+    clear_status v1 "http://localhost:${prowlarrPort}" "${prowlarrConfigXml}" || true
+    clear_status v3 "http://${bridgeAddr}:${sonarrPort}" "${sonarrConfigXml}" || true
+    clear_status v3 "http://${bridgeAddr}:${radarrPort}" "${radarrConfigXml}" || true
+  '';
+in
 {
   imports = [
     (lib.vpnNamespaceOpenPort service_configs.ports.private.bitmagnet.port "bitmagnet")
@@ -25,9 +76,38 @@
       };
       http_server = {
         # TODO! make issue about this being a string and not a `port` type
-        port = ":" + (builtins.toString service_configs.ports.private.bitmagnet.port);
+        port = ":" + (toString service_configs.ports.private.bitmagnet.port);
       };
     };
   };
 
+  # The upstream default (Restart=on-failure) leaves Bitmagnet dead after
+  # clean exits (e.g. systemd stop during deploy). Always restart it.
+  systemd.services.bitmagnet.serviceConfig = {
+    Restart = lib.mkForce "always";
+    RestartSec = 10;
+  };
+
+  # After Bitmagnet restarts, clear the escalating failure backoff across
+  # Prowlarr, Sonarr, and Radarr so searches resume immediately instead of
+  # waiting hours for the disable timers to expire.
+  systemd.services.prowlarr-bitmagnet-recovery = {
+    description = "Clear Prowlarr/Sonarr/Radarr failure status for Bitmagnet indexer";
+    after = [
+      "bitmagnet.service"
+      "prowlarr.service"
+      "sonarr.service"
+      "radarr.service"
+    ];
+    bindsTo = [ "bitmagnet.service" ];
+    wantedBy = [ "bitmagnet.service" ];
+
+    serviceConfig = {
+      Type = "oneshot";
+      RemainAfterExit = true;
+      ExecStart = recoveryScript;
+      # Same VPN namespace as Bitmagnet and Prowlarr.
+      NetworkNamespacePath = "/run/netns/wg";
+    };
+  };
 }