compose.deploy.yml

@@ -22,12 +22,22 @@ services:
       # /data holds the auto-generated secret key, third-party plugins, and the
       # Ansible playbook cache — all of which must survive image updates. No
       # source bind-mounts: core + first-party plugins live inside the image.
+      #
+      # The container runs as the unprivileged 'app' user (uid 1000), so /data
+      # MUST be writable by uid 1000. A named docker volume (below) gets that
+      # automatically. If you bind-mount a host/NFS path instead, chown it to
+      # 1000:1000 (and mind NFS root_squash) — otherwise the app can't persist
+      # its secret key, mints a fresh one each boot, and every encrypted secret
+      # (managed SSH key, SMTP/OIDC/LDAP creds) becomes unrecoverable. The app
+      # now refuses to start in that state rather than silently degrade.
       - app_data:/data
     environment:
       - STEWARD_DATABASE_URL=postgresql+asyncpg://steward:${POSTGRES_PASSWORD:-steward}@db/steward
       # STEWARD_SECRET_KEY is intentionally absent — the app generates a random
       # key on first boot and persists it to /data/secret.key, which the app_data
-      # volume keeps across image updates.
+      # volume keeps across image updates. On multi-node Swarm with a shared bind
+      # mount, pin STEWARD_SECRET_KEY (env or a docker secret) instead, so the key
+      # never depends on filesystem ownership being correct on every node.
     depends_on:
       db:
         condition: service_healthy

steward/app.py

@@ -1,11 +1,14 @@
 # steward/app.py
 from __future__ import annotations
 import asyncio
+import logging
 from pathlib import Path
 from quart import Quart, render_template
 from .config import load_bootstrap
 from .database import init_db
 
+logger = logging.getLogger(__name__)
+
 
 def create_app(
     config_path: Path | str | None = None,
@@ -50,9 +53,17 @@ def create_app(
     # ── 3b. Encryption-at-rest: bind the encryptor, then encrypt legacy secrets ─
     if not testing:
         from .core.crypto import init_crypto
-        from .core.settings import migrate_plaintext_secrets
+        from .core.settings import migrate_plaintext_secrets, scan_undecryptable_secrets
         init_crypto(app.config["SECRET_KEY"])
         migrate_plaintext_secrets(app.config["DATABASE_URL"])
+        # Flag any secrets sealed under a now-lost key (see the admin banner).
+        undecryptable = scan_undecryptable_secrets(app.config["DATABASE_URL"])
+        if undecryptable:
+            logger.warning(
+                "%d stored secret(s) cannot be decrypted with the current app key "
+                "(re-enter them in Settings): %s",
+                len(undecryptable), ", ".join(undecryptable),
+            )
 
     # ── 4. Load all settings from DB → populate app.config ────────────────────
     if not testing:
@@ -167,6 +178,7 @@ def create_app(
     @app.context_processor
     def _inject_plugin_failures():
         from .core.plugin_manager import get_plugin_failures
+        from .core.settings import get_undecryptable_secrets
         # enabled_plugins lets templates gate cross-plugin embeds (e.g. the
         # Hosts hub only fetches the docker fragment when docker is enabled),
         # avoiding a 404 to a route whose blueprint isn't registered.
@@ -177,6 +189,9 @@ def create_app(
         return {
             "plugin_failures": get_plugin_failures(),
             "enabled_plugins": enabled_plugins,
+            # Read from an in-memory cache (no DB hit per render); kept current by
+            # the startup scan + set_setting's discard-on-write.
+            "undecryptable_secrets": get_undecryptable_secrets(),
         }
 
     # ── 11. Share-token middleware ─────────────────────────────────────────────

steward/config.py

@@ -75,13 +75,27 @@ def load_bootstrap(config_path: Path | str | None = None) -> dict[str, Any]:
 
 
 def _resolve_secret_key(raw: dict) -> str:
-    """Resolve secret_key: env var → file → auto-generate."""
+    """Resolve secret_key: env var → file → auto-generate.
+
+    Refuses to start if a new key must be generated but cannot be persisted: an
+    ephemeral key changes on every restart, which silently renders every
+    encrypted secret (managed SSH key, SMTP/OIDC/LDAP credentials) unrecoverable.
+    Failing loudly with a fix beats limping along and losing data on the next
+    boot — exactly the footgun that bit the vdnt-docker02 deployment.
+    """
     from_env = _env("SECRET_KEY") or raw.get("secret_key")
     if from_env:
         return from_env
 
     if _SECRET_KEY_FILE.exists():
-        key = _SECRET_KEY_FILE.read_text().strip()
+        try:
+            key = _SECRET_KEY_FILE.read_text().strip()
+        except OSError as exc:
+            raise RuntimeError(
+                f"App secret key file {_SECRET_KEY_FILE} exists but cannot be read "
+                f"({exc}). Make it readable by the container user (uid 1000), or set "
+                f"STEWARD_SECRET_KEY."
+            ) from exc
         if key:
             return key
 
@@ -89,11 +103,16 @@ def _resolve_secret_key(raw: dict) -> str:
     try:
         _SECRET_KEY_FILE.parent.mkdir(parents=True, exist_ok=True)
         _SECRET_KEY_FILE.write_text(key)
-        logger.info("Generated new secret key and saved to %s", _SECRET_KEY_FILE)
     except OSError as exc:
-        logger.warning(
-            "Could not write secret key to %s (%s). "
-            "Key will not persist across restarts.",
-            _SECRET_KEY_FILE, exc,
-        )
+        raise RuntimeError(
+            f"Generated a new app secret key but could not persist it to "
+            f"{_SECRET_KEY_FILE} ({exc}). An ephemeral key changes on every restart, "
+            f"which makes all encrypted secrets (managed SSH key, SMTP/OIDC/LDAP "
+            f"credentials) unrecoverable. Fix one of:\n"
+            f"  • set STEWARD_SECRET_KEY to a stable value "
+            f"(recommended for Swarm / multi-node), or\n"
+            f"  • make {_SECRET_KEY_FILE.parent} writable by the container user "
+            f"(uid 1000)."
+        ) from exc
+    logger.info("Generated new secret key and saved to %s", _SECRET_KEY_FILE)
     return key

steward/core/settings.py

@@ -150,6 +150,34 @@ def _decode(value: Any, key: str = "") -> Any:
     return decrypt_secret(value, context=key) if is_encrypted(value) else value
 
 
+# Secret settings that are stored as ciphertext but won't decrypt with the
+# current app key (key rotated or lost). Surfaced as an admin banner so the
+# operator knows precisely which secrets to re-enter — instead of finding out
+# only when something that uses one fails. Refreshed at startup
+# (scan_undecryptable_secrets) and kept live: re-entering a secret clears it
+# without a restart (set_setting discards it on a fresh write).
+_undecryptable_secrets: set[str] = set()
+
+
+def get_undecryptable_secrets() -> list[str]:
+    """Sorted keys whose stored ciphertext won't decrypt (for the UI banner)."""
+    return sorted(_undecryptable_secrets)
+
+
+def _is_undecryptable(stored: Any, key: str = "") -> bool:
+    """True iff `stored` is an encrypted token that fails to decrypt.
+
+    A failed decrypt returns the ciphertext unchanged (still enc-prefixed), so a
+    value that is still encrypted after a decrypt attempt is undecryptable.
+    """
+    from steward.core.crypto import decrypt_secret, is_encrypted
+    return (
+        isinstance(stored, str)
+        and is_encrypted(stored)
+        and is_encrypted(decrypt_secret(stored, context=key))
+    )
+
+
 # ─────────────────────────────────────────────────────────────────────────────
 # Async helpers (use inside request handlers / scheduled tasks)
 # ─────────────────────────────────────────────────────────────────────────────
@@ -182,6 +210,12 @@ async def set_setting(session: AsyncSession, key: str, value: Any) -> None:
         row.value_json = json.dumps(to_store)
         row.updated_at = now
 
+    # A fresh write of a secret is encrypted with the current key (or cleared to
+    # plaintext), so it's decryptable now — drop any stale "undecryptable" flag
+    # so the banner clears without a restart.
+    if key in SECRET_KEYS:
+        _undecryptable_secrets.discard(key)
+
 
 async def get_all_settings(session: AsyncSession) -> dict[str, Any]:
     """Return flat key→value dict with defaults filled in for missing keys."""
@@ -359,6 +393,37 @@ def migrate_plaintext_secrets(db_url: str) -> int:
     return asyncio.run(_run())
 
 
+def scan_undecryptable_secrets(db_url: str) -> list[str]:
+    """Populate the undecryptable-secrets cache from the DB; return the keys found.
+
+    Run once at startup, AFTER migrate_plaintext_secrets and init_crypto: any row
+    that's encrypted but won't decrypt with the current key was sealed under a
+    different (lost/rotated) key and must be re-entered. Surfaced via the admin
+    banner (get_undecryptable_secrets).
+    """
+    async def _run() -> list[str]:
+        from sqlalchemy.ext.asyncio import create_async_engine, async_sessionmaker
+        engine = create_async_engine(db_url, echo=False)
+        factory = async_sessionmaker(engine, expire_on_commit=False)
+        bad: list[str] = []
+        try:
+            async with factory() as session:
+                result = await session.execute(
+                    select(AppSetting).where(AppSetting.key.in_(SECRET_KEYS))
+                )
+                for row in result.scalars():
+                    if _is_undecryptable(json.loads(row.value_json), row.key):
+                        bad.append(row.key)
+        finally:
+            await engine.dispose()
+        return bad
+
+    global _undecryptable_secrets
+    found = asyncio.run(_run())
+    _undecryptable_secrets = set(found)
+    return sorted(found)
+
+
 # ─────────────────────────────────────────────────────────────────────────────
 # External URL helper
 # ─────────────────────────────────────────────────────────────────────────────

steward/templates/base.html

@@ -280,6 +280,34 @@ function setTimeRange(val) {
             </span>
         </div>
         {% endif %}
+        {% if undecryptable_secrets and session.user_role == 'admin' %}
+        {% set _sec_tab = {
+          'smtp.password': '/settings/notifications/',
+          'oidc.client_secret': '/settings/auth/',
+          'ldap.bind_password': '/settings/auth/',
+          'ansible.ssh_private_key': '/settings/ansible/',
+          'ansible.become_password': '/settings/ansible/',
+          'ansible.vault_password': '/settings/ansible/',
+        } %}
+        <div style="background:color-mix(in srgb,var(--red) 12%,var(--bg-elevated));
+                    border:1px solid color-mix(in srgb,var(--red) 35%,var(--border));
+                    border-radius:6px;padding:0.6rem 1rem;margin-bottom:1rem;
+                    font-size:0.84rem;display:flex;align-items:flex-start;gap:0.6rem;">
+            <span style="color:var(--red);flex-shrink:0;">⚠</span>
+            <span>
+                <strong style="color:var(--text);">
+                    {{ undecryptable_secrets | length }} stored secret{{ 's' if undecryptable_secrets | length != 1 }}
+                    can’t be decrypted
+                </strong>
+                — the app secret key changed, so {{ 'they' if undecryptable_secrets | length != 1 else 'it' }}
+                must be re-entered:
+                {% for k in undecryptable_secrets -%}
+                    {%- if _sec_tab.get(k) %}<a href="{{ _sec_tab[k] }}" style="color:var(--accent);">{{ k }}</a>
+                    {%- else %}<code>{{ k }}</code>{% endif %}{% if not loop.last %}, {% endif %}
+                {%- endfor %}.
+            </span>
+        </div>
+        {% endif %}
         {% if error %}
         <div class="alert alert-error">{{ error }}</div>
         {% endif %}

tests/core/test_undecryptable_secrets.py

@@ -0,0 +1,29 @@
+"""Unit tests for undecryptable-secret detection (the admin-banner source)."""
+from steward.core.crypto import encrypt_secret, init_crypto
+from steward.core.settings import _is_undecryptable, get_undecryptable_secrets
+
+
+def test_is_undecryptable_false_for_current_key():
+    init_crypto("key-A")
+    tok = encrypt_secret("hunter2")
+    assert _is_undecryptable(tok, "smtp.password") is False
+
+
+def test_is_undecryptable_true_after_key_rotation():
+    init_crypto("key-A")
+    tok = encrypt_secret("hunter2")          # sealed under key-A
+    init_crypto("key-B")                     # key changed/lost
+    assert _is_undecryptable(tok, "smtp.password") is True
+
+
+def test_is_undecryptable_ignores_plaintext_and_empty():
+    init_crypto("key-A")
+    assert _is_undecryptable("", "smtp.password") is False
+    assert _is_undecryptable("plain-value", "smtp.password") is False
+    assert _is_undecryptable(None, "smtp.password") is False
+
+
+def test_get_undecryptable_secrets_returns_sorted_list():
+    # Default (nothing scanned) is an empty list; the accessor is always safe to
+    # call from the template context processor.
+    assert isinstance(get_undecryptable_secrets(), list)

tests/test_config.py

@@ -1,6 +1,6 @@
 import textwrap
 import pytest
-from steward.config import load_bootstrap
+from steward.config import load_bootstrap, _resolve_secret_key
 
 
 def test_load_bootstrap_from_yaml(tmp_path):
@@ -36,3 +36,32 @@ def test_missing_database_url_raises(tmp_path):
     cfg_file.write_text("secret_key: s\n")
     with pytest.raises(ValueError, match="Database URL is required"):
         load_bootstrap(cfg_file)
+
+
+# ── secret key resolution ──────────────────────────────────────────────────────
+
+def test_secret_key_existing_file_is_reused(tmp_path, monkeypatch):
+    key_file = tmp_path / "secret.key"
+    key_file.write_text("persisted-key\n")
+    monkeypatch.setattr("steward.config._SECRET_KEY_FILE", key_file)
+    monkeypatch.delenv("STEWARD_SECRET_KEY", raising=False)
+    assert _resolve_secret_key({}) == "persisted-key"
+
+
+def test_secret_key_generated_and_persisted_when_writable(tmp_path, monkeypatch):
+    key_file = tmp_path / "sub" / "secret.key"   # parent doesn't exist yet
+    monkeypatch.setattr("steward.config._SECRET_KEY_FILE", key_file)
+    monkeypatch.delenv("STEWARD_SECRET_KEY", raising=False)
+    key = _resolve_secret_key({})
+    assert key and key_file.read_text().strip() == key
+
+
+def test_secret_key_unpersistable_raises_instead_of_ephemeral(tmp_path, monkeypatch):
+    # A file sits where a directory is needed, so mkdir/write fails → must raise
+    # (an ephemeral key would silently orphan every encrypted secret).
+    blocker = tmp_path / "blocker"
+    blocker.write_text("not a dir")
+    monkeypatch.setattr("steward.config._SECRET_KEY_FILE", blocker / "secret.key")
+    monkeypatch.delenv("STEWARD_SECRET_KEY", raising=False)
+    with pytest.raises(RuntimeError, match="could not persist"):
+        _resolve_secret_key({})