hyperhive/nix/agent-modules/github-token.nix

# This agent's GitHub personal access token, fetched from the swarm secret
# store by the agent itself, into the file ./github.nix's readers use.
#
# An operator links the token in the swarm UI; `swarm-controller` stores it at
# `swarm/agents/<agent>/github-token` (`swarm_secret_client::github`). The
# agent's own read grant covers that path, so this unit reads it and writes
# `<state>/github-token`, which the `gh` wrapper, the git credential helper and
# `hive-github-notify` read.
#
# It never deletes. A `github-token` already in place stays when the store has
# none or cannot be read. The file is replaced by rename, and only when its
# bytes changed.
{
  pkgs,
  lib,
  config,
  ...
}:
let
  cfg = config.services.hyperhive.agent.bao;

  agentName = config.services.hyperhive.agent.user.name;
  stateDir = "/agents/${agentName}/state";

  # The same three ids ./bao.nix and ./forge-accounts.nix load.
  certCredential = "hive-agent-bao-cert";
  keyCredential = "hive-agent-bao-key";
  serverCaCredential = "hive-agent-bao-server-ca";

  unitName = "hive-agent-github-token";

  # The nix half of `swarm_secret_client::github::account_path` plus
  # `path::MOUNT`.
  tokenPath = "secret/swarm/agents/${agentName}/github-token";

  runtimeDir = unitName;
  # The store's whole answer, token included: kept in the unit's own `0700`
  # directory, never in the state dir.
  rawFile = "/run/${runtimeDir}/account.json";
  errFile = "/run/${runtimeDir}/bao.err";

  tokenFile = "${stateDir}/github-token";
  stagedFile = "${stateDir}/.github-token.new";

  configured = cfg.addr != null && config.services.hyperhive.agent.github.enable;

  storeRetry = import ../host-modules/lib/store-retry.nix { };
in
{
  config = lib.mkIf configured {
    systemd.services.${unitName} = {
      description = "fetch this agent's GitHub token from the secret store";
      after = [
        "network.target"
        "hive-agent-bao-identity.service"
      ];
      # The poller reads the token once at start.
      before = [ "hive-github-notify.service" ];
      wantedBy = [ "multi-user.target" ];
      path = [
        pkgs.openbao
        pkgs.coreutils
        pkgs.diffutils
        pkgs.jq
      ];
      # ../host-modules/lib/store-retry.nix.
      inherit (storeRetry) startLimitBurst startLimitIntervalSec;
      serviceConfig = storeRetry.serviceConfig // {
        Type = "oneshot";
        # Not `RemainAfterExit`, so the timer below can start it again.
        RemainAfterExit = false;
        TimeoutStartSec = 30;
        User = agentName;
        Group = agentName;
        RuntimeDirectory = runtimeDir;
        RuntimeDirectoryMode = "0700";
        # `0600`, the mode `github-token` has always had.
        UMask = "0077";
        LoadCredential = [
          certCredential
          keyCredential
          serverCaCredential
        ];
      };
      environment = {
        BAO_ADDR = cfg.addr;
        BAO_CLIENT_CERT = "%d/${certCredential}";
        BAO_CLIENT_KEY = "%d/${keyCredential}";
      };
      script = ''
        set -euo pipefail

        # No identity delivered: ./bao.nix's check reports that.
        for id in ${lib.escapeShellArg certCredential} ${lib.escapeShellArg keyCredential}; do
          if [ ! -s "$CREDENTIALS_DIRECTORY/$id" ]; then
            echo "this agent has no store identity, so it cannot fetch its GitHub token." >&2
            exit 0
          fi
        done

        if [ -s "$CREDENTIALS_DIRECTORY/${serverCaCredential}" ]; then
          export BAO_CACERT="$CREDENTIALS_DIRECTORY/${serverCaCredential}"
        fi

        err=${lib.escapeShellArg errFile}
        raw=${lib.escapeShellArg rawFile}
        staged=${lib.escapeShellArg stagedFile}
        token=${lib.escapeShellArg tokenFile}
        trap 'rm -f "$err" "$raw" "$staged"' EXIT

        if ! BAO_TOKEN="$(bao login -method=cert -token-only 2>"$err")"; then
          echo "the swarm secret store at $BAO_ADDR did not accept this agent's certificate login:" >&2
          if [ -s "$err" ]; then cat "$err" >&2; fi
          exit 1
        fi
        export BAO_TOKEN

        # No token linked and a store that cannot answer look alike here, and
        # either way the file in place, if any, is kept.
        if ! bao kv get -format=json ${lib.escapeShellArg tokenPath} >"$raw" 2>"$err"; then
          echo "no GitHub token read from ${tokenPath}; github-token left as it is:" >&2
          if [ -s "$err" ]; then cat "$err" >&2; fi
          exit 0
        fi

        # ⚠️ The token goes from the store's answer straight into a file; it is
        # never in a variable or an argument. A malformed object exits 0:
        # failing the unit would only restart it into the same answer.
        rm -f "$staged"
        if ! jq -er '.data.data.value | strings' "$raw" >"$staged"; then
          echo "${tokenPath} holds no string value; github-token left as it is." >&2
          exit 0
        fi

        if cmp -s "$staged" "$token"; then
          echo "this agent's GitHub token at ${tokenPath} is unchanged."
          exit 0
        fi
        mv -f "$staged" "$token"
        echo "fetched this agent's GitHub token from ${tokenPath}."
      '';
    };

    # The same cadence as ./forge-accounts.nix.
    systemd.timers.${unitName} = {
      description = "re-fetch this agent's GitHub token from the secret store";
      wantedBy = [ "timers.target" ];
      timerConfig = {
        OnUnitInactiveSec = "2min";
        RandomizedDelaySec = "20s";
      };
    };
  };
}