thermograph/infra/deploy/render-secrets.sh

#!/usr/bin/env bash
# Render /etc/thermograph.env from the SOPS-encrypted source of truth
# (deploy/secrets/<env>.yaml, committed encrypted) — sourced by deploy.sh and
# deploy-dev.sh, not run directly.
#
# The encrypted files are the single source of truth; /etc/thermograph.env becomes a
# rendered artifact that the existing seams (docker-compose `env_file:`, the systemd
# unit's EnvironmentFile, and entrypoint.sh's /run/secrets shim) keep consuming
# unchanged. Common secrets + the per-host overrides are concatenated with the host
# file LAST, so a host value wins (env_file and `source` both take the last
# occurrence of a duplicate key).
#
# Presence-detected: a host is "configured for SOPS" only when it has an age key at
# /etc/thermograph/age.key AND an environment name in /etc/thermograph/secrets-env
# (prod|beta|dev). A host without them keeps whatever /etc/thermograph.env it already
# has — so merging this is a safe no-op until a host is deliberately migrated. See
# deploy/secrets/README.md.
render_thermograph_secrets() {
  local repo="${1:-.}"                                   # repo root holding deploy/secrets
  local key="${THERMOGRAPH_AGE_KEY:-/etc/thermograph/age.key}"
  local marker="${THERMOGRAPH_SECRETS_ENV_FILE:-/etc/thermograph/secrets-env}"
  local env_name
  env_name=$(cat "$marker" 2>/dev/null || true)

  # The per-host file is required; common.yaml is optional so the initial cutover can
  # seed each host as an exact copy of its live env (byte-identical render, no value
  # changes) and factor out shared secrets into common.yaml later.
  #
  # These are two different situations and used to share one `return 0`.
  #
  # (a) Not configured for SOPS at all — no env marker, or no age key. The LAN
  #     dev box is legitimately in this state. Saying so and succeeding is right.
  if [ -z "$env_name" ] || [ ! -f "$key" ]; then
    echo "==> SOPS secrets not configured here; using existing /etc/thermograph.env"
    return 0
  fi

  # (b) Configured — there is a key and a named environment — but the vault for
  #     that environment is not where we looked. That is a failure, and it used
  #     to return 0: a silent no-op wearing a success code. A deploy would report
  #     success having rendered nothing, and the host would quietly keep serving
  #     whatever /etc/thermograph.env already held, including after a rotation.
  #
  #     The likely cause is the caller passing the wrong root. This function
  #     wants the directory CONTAINING deploy/secrets — on the hosts that is
  #     /opt/thermograph/infra, not /opt/thermograph. Getting it wrong looked
  #     exactly like "not configured here", which is why it went unnoticed.
  if [ ! -f "$repo/deploy/secrets/${env_name}.yaml" ]; then
    echo "!! this host is configured for SOPS (env='${env_name}', age key present)" >&2
    echo "!! but no vault was found at ${repo}/deploy/secrets/${env_name}.yaml" >&2
    echo "!! pass the directory containing deploy/secrets — on the hosts that is" >&2
    echo "!!   /opt/thermograph/infra — or add ${env_name}.yaml to the vault." >&2
    return 1
  fi
  if ! command -v sops >/dev/null 2>&1; then
    echo "!! sops not installed but this host is configured for SOPS secrets" >&2
    return 1
  fi

  echo "==> Rendering /etc/thermograph.env from deploy/secrets (common + ${env_name})"
  # The age private key is root-owned (0400). Read it directly if we can, else via
  # sudo into SOPS_AGE_KEY — so the key never has to be readable by the deploy user.
  # (The render needs sudo to write /etc/thermograph.env below anyway.)
  local key_env=()
  if [ -r "$key" ]; then
    key_env=("SOPS_AGE_KEY_FILE=$key")
  else
    local keymat; keymat=$(sudo cat "$key" 2>/dev/null | grep '^AGE-SECRET-KEY-' || true)
    [ -n "$keymat" ] || { echo "!! cannot read age key at $key (need sudo)" >&2; return 1; }
    key_env=("SOPS_AGE_KEY=$keymat")
  fi
  local tmp; tmp=$(mktemp)
  # The tmp file holds DECRYPTED secrets, so every exit path below removes it.
  #
  # Deliberately NOT a `trap ... RETURN`, which looks like the tidier way to make
  # that unconditional: a RETURN trap set inside a SOURCED function persists in
  # the CALLER's shell after the function returns, and a RETURN trap also fires
  # when a `.`/source completes. deploy.sh sources /etc/thermograph.env a few
  # lines after calling us, which would re-fire the trap at top level where `tmp`
  # (function-local) is unset -- fatal under deploy.sh's `set -u`, and silent,
  # because that line already redirects stderr to /dev/null. Explicit removal on
  # each path is duller and correct.
  : > "$tmp" || { rm -f "$tmp"; return 1; }
  # Decrypt failures return 1 explicitly, so a partial env is never written and
  # correctness doesn't depend on the caller's shell options. common first, host
  # second, so a host value overrides a shared one (last-wins).
  if [ -f "$repo/deploy/secrets/common.yaml" ]; then
    env "${key_env[@]}" sops -d --input-type yaml --output-type dotenv \
      "$repo/deploy/secrets/common.yaml" >> "$tmp" || { rm -f "$tmp"; return 1; }
  fi
  env "${key_env[@]}" sops -d --input-type yaml --output-type dotenv \
    "$repo/deploy/secrets/${env_name}.yaml" >> "$tmp" || { rm -f "$tmp"; return 1; }

  # Write /etc/thermograph.env. Prefer an in-place write when the existing file is
  # writable by us (e.g. a group-writable 0660 root:<deploygroup> on a box whose CI
  # deploy user isn't root and has no broad sudo — beta's `deploy`), since that needs
  # only file write, not /etc dir write or sudo. Else install; else sudo install (a
  # root/agent deploy) -- and on that sudo path CHOWN the result to the invoking
  # deploy user (-o/-g $(id -un/-gn)), or the file lands root:root 0640 and the very
  # next line of deploy.sh (`. /etc/thermograph.env` as that non-root user) can't read
  # it, so POSTGRES_PASSWORD never enters the env and `docker compose` dies on
  # interpolation. Fail loudly rather than deploy against stale secrets.
  # rc + a single cleanup point: the plaintext tmp must go whichever branch runs,
  # but the old trailing `rm` was also the function's last command, so it masked a
  # failed in-place `cat` write to status 0. Capture the status instead, so a
  # half-written /etc/thermograph.env fails loudly rather than deploying stale.
  local rc=0
  if [ -f /etc/thermograph.env ] && [ -w /etc/thermograph.env ]; then
    cat "$tmp" > /etc/thermograph.env || rc=1
  elif install -m 0640 "$tmp" /etc/thermograph.env 2>/dev/null; then :
  elif sudo install -m 0640 -o "$(id -un)" -g "$(id -gn)" "$tmp" /etc/thermograph.env 2>/dev/null; then :
  else
    echo "!! cannot write /etc/thermograph.env (need file write access or passwordless sudo)" >&2
    rc=1
  fi
  rm -f "$tmp"
  return "$rc"
}