infra(seed): dump encrypted secret columns as NULL, restore via CLI

ASP.NET Data Protection ciphertext is non-deterministic and bound to the
source key ring, so encrypted secret columns (ExternalSystemDefinitions
.AuthConfiguration, SmtpConfigurations.Credentials, DatabaseConnection
Definitions.ConnectionString) cannot be replayed from a static SQL dump —
the app would fail to decrypt them. dump_seed.py now emits those columns
as NULL; reseed.sh adds a post-seed stage that recreates the values
through the ScadaLink CLI so the EF value converter re-encrypts against
the target cluster's key ring.
This commit is contained in:
Joseph Doherty
2026-05-21 01:29:51 -04:00
parent 5492c94e2f
commit 932fda5594
3 changed files with 62 additions and 2 deletions

View File

@@ -183,8 +183,9 @@ INSERT INTO [DataConnections] ([Id], [Name], [Protocol], [PrimaryConfiguration],
SET IDENTITY_INSERT [DataConnections] OFF; SET IDENTITY_INSERT [DataConnections] OFF;
-- ExternalSystemDefinitions (1 rows) -- ExternalSystemDefinitions (1 rows)
-- NOTE: [AuthConfiguration] is an encrypted secret column — dumped as NULL. Restore via the app (CLI/API) post-seed.
SET IDENTITY_INSERT [ExternalSystemDefinitions] ON; SET IDENTITY_INSERT [ExternalSystemDefinitions] ON;
INSERT INTO [ExternalSystemDefinitions] ([Id], [Name], [EndpointUrl], [AuthType], [AuthConfiguration], [MaxRetries], [RetryDelay]) VALUES (1, N'Test REST API', N'http://scadalink-restapi:5200', N'ApiKey', N'scadalink-test-key-1', 0, '00:00:00.000000'); INSERT INTO [ExternalSystemDefinitions] ([Id], [Name], [EndpointUrl], [AuthType], [AuthConfiguration], [MaxRetries], [RetryDelay]) VALUES (1, N'Test REST API', N'http://scadalink-restapi:5200', N'ApiKey', NULL, 0, '00:00:00.000000');
SET IDENTITY_INSERT [ExternalSystemDefinitions] OFF; SET IDENTITY_INSERT [ExternalSystemDefinitions] OFF;
-- ExternalSystemMethods (1 rows) -- ExternalSystemMethods (1 rows)

View File

@@ -114,6 +114,34 @@ docker exec -i scadalink-mssql /opt/mssql-tools18/bin/sqlcmd \
-S localhost -U sa -P 'ScadaLink_Dev1#' -C -d ScadaLinkConfig -b < "$SEED_FILE" -S localhost -U sa -P 'ScadaLink_Dev1#' -C -d ScadaLinkConfig -b < "$SEED_FILE"
echo " Seed replayed." echo " Seed replayed."
echo ""
echo "--- Stage 6d/6: restore encrypted secret config (CLI) ---"
# Configuration that lives in encrypted secret columns cannot be replayed from
# raw SQL: ASP.NET Data Protection ciphertext is non-deterministic and bound to
# the source key ring. Create/restore it through the app so the EF value
# converter encrypts against this cluster's key ring.
CLI="dotnet run --project $PROJECT_ROOT/src/ScadaLink.CLI --"
AUTH="--username multi-role --password password"
# ExternalSystemDefinitions Id 1 ("Test REST API") is inserted by the seed with
# a fixed identity but a NULL AuthConfiguration; set the API key here.
$CLI --url "$MGMT_URL" $AUTH external-system update \
--id 1 \
--name "Test REST API" \
--endpoint-url "http://scadalink-restapi:5200" \
--auth-type ApiKey \
--auth-config "scadalink-test-key-1"
echo " External-system auth config restored (encrypted)."
# The "Machine Data DB" database connection is referenced by name from the
# seeded TestDatabaseQuery script. It is not in seed-config.sql (its
# ConnectionString is an encrypted secret column); create it through the app.
$CLI --url "$MGMT_URL" $AUTH db-connection create \
--name "Machine Data DB" \
--connection-string "Server=scadalink-mssql,1433;Database=ScadaLinkMachineData;User Id=scadalink_app;Password=ScadaLink_Dev1#;TrustServerCertificate=true" \
|| echo " (Machine Data DB connection may already exist)"
echo " Database connection created (encrypted)."
echo "" echo ""
echo "=== Reseed complete ===" echo "=== Reseed complete ==="
echo "" echo ""

View File

@@ -13,6 +13,12 @@ Excluded by design (per-environment, not design-time): Sites (seeded via
seed-sites.sh), Instances + InstanceConnectionBindings + InstanceOverrides, seed-sites.sh), Instances + InstanceConnectionBindings + InstanceOverrides,
NotificationLists/Recipients, SmtpConfigurations, ApiKeys, Areas, NotificationLists/Recipients, SmtpConfigurations, ApiKeys, Areas,
SiteScopeRules, LdapGroupMappings, DataProtectionKeys, audit, deployment. SiteScopeRules, LdapGroupMappings, DataProtectionKeys, audit, deployment.
Encrypted secret columns (see ENCRYPTED_COLUMNS) are emitted as NULL: they
hold ASP.NET Data Protection ciphertext, which is non-deterministic and bound
to the source key ring, so a raw SQL dump can never replay a valid value.
Re-populate them through the application after the seed runs (infra/reseed.sh
does this via the ScadaLink CLI).
""" """
import argparse import argparse
@@ -45,6 +51,18 @@ INSERT_ORDER = [
# the column list. All listed tables happen to use Id as their identity. # the column list. All listed tables happen to use Id as their identity.
IDENTITY_TABLES = set(INSERT_ORDER) IDENTITY_TABLES = set(INSERT_ORDER)
# (table, column) pairs encrypted at rest via ASP.NET Data Protection
# (EncryptedStringConverter in ScadaLink.ConfigurationDatabase). Ciphertext is
# non-deterministic and key-ring-bound, so it cannot be replayed from a static
# SQL dump — the application would fail to decrypt it on read. These columns
# are dumped as NULL; re-seed their values through the app (CLI / API) so the
# value converter encrypts them against the target key ring.
ENCRYPTED_COLUMNS = {
("ExternalSystemDefinitions", "AuthConfiguration"),
("SmtpConfigurations", "Credentials"),
("DatabaseConnectionDefinitions", "ConnectionString"),
}
# Templates has self-FK Templates.ParentTemplateId; emit a single batch that # Templates has self-FK Templates.ParentTemplateId; emit a single batch that
# inserts shallow rows first then deeper ones. pymssql returns rows in Id order # inserts shallow rows first then deeper ones. pymssql returns rows in Id order
# from our ORDER BY, which matches insertion order for this schema (parent Id # from our ORDER BY, which matches insertion order for this schema (parent Id
@@ -175,6 +193,16 @@ def dump(args):
rows = cursor.fetchall() rows = cursor.fetchall()
out.append("-- " + table + " (" + str(len(rows)) + " rows)") out.append("-- " + table + " (" + str(len(rows)) + " rows)")
# Columns encrypted at rest cannot be dumped verbatim; emit NULL and
# note it so the secret value is restored through the app afterwards.
nulled = [c for c in columns if (table, c) in ENCRYPTED_COLUMNS]
for c in nulled:
out.append(
"-- NOTE: [{}] is an encrypted secret column — dumped as NULL. "
"Restore via the app (CLI/API) post-seed.".format(c)
)
if not rows: if not rows:
continue continue
@@ -183,7 +211,10 @@ def dump(args):
if identity: if identity:
out.append("SET IDENTITY_INSERT [{}] ON;".format(table)) out.append("SET IDENTITY_INSERT [{}] ON;".format(table))
for row in rows: for row in rows:
values = ", ".join(quote(v) for v in row) values = ", ".join(
"NULL" if (table, c) in ENCRYPTED_COLUMNS else quote(v)
for c, v in zip(columns, row)
)
out.append( out.append(
"INSERT INTO [{}] ({}) VALUES ({});".format(table, col_list, values) "INSERT INTO [{}] ({}) VALUES ({});".format(table, col_list, values)
) )