feat: protect sensitive catalog samples

backend/src/routes/catalog-description-generation.ts

@@ -11,6 +11,12 @@ import {
   type DescriptionGenerationWorker,
 } from "../catalog/description-generation-worker.js";
 import { MetadataGenerationModelUnavailableError } from "../catalog/metadata-generation-models.js";
+import { ModelCompletionProviderError } from "../catalog/model-completer.js";
+import {
+  SensitiveDataSuggester,
+  SensitiveDataSuggestionInvalidResponseError,
+  SensitiveDataSuggestionTargetNotFoundError,
+} from "../catalog/sensitive-data-suggester.js";
 import {
   CatalogOperationInProgressError,
   CatalogUnavailableError,
@@ -22,6 +28,7 @@ import {
 
 const idSchema = z.uuid();
 const modelIdSchema = z.string().regex(/^[a-z][a-z0-9._-]{0,63}$/);
+const suggestionSchema = z.object({ modelId: modelIdSchema }).strict();
 const selectedTargetIdsSchema = z.array(idSchema).min(1);
 const startSchema = z.discriminatedUnion("scope", [
   z.object({
@@ -116,6 +123,19 @@ function safeError(reply: FastifyReply, error: unknown) {
       message: "The selected metadata-generation model is unavailable.",
     });
   }
+  if (error instanceof SensitiveDataSuggestionTargetNotFoundError) {
+    return reply.code(404).send({
+      code: "database_not_found",
+      message: "Database configuration was not found.",
+    });
+  }
+  if (error instanceof SensitiveDataSuggestionInvalidResponseError
+    || error instanceof ModelCompletionProviderError) {
+    return reply.code(502).send({
+      code: "sensitive_data_suggestion_failed",
+      message: "Sensitive-data suggestions could not be prepared.",
+    });
+  }
   if (error instanceof DescriptionGenerationDuplicateTargetIdsError) {
     return reply.code(400).send({
       code: "description_generation_target_ids_duplicate",
@@ -172,8 +192,28 @@ function safeError(reply: FastifyReply, error: unknown) {
 
 export function catalogDescriptionGenerationRoutes(
   app: FastifyInstance,
-  deps: { repository: CatalogRepository; worker: DescriptionGenerationWorker },
+  deps: {
+    repository: CatalogRepository;
+    worker: DescriptionGenerationWorker;
+    sensitiveDataSuggester: SensitiveDataSuggester;
+  },
 ): void {
+  app.post("/catalog/databases/:databaseId/sensitive-data-suggestions", async (request, reply) => {
+    if (!manage(request, reply)) return reply;
+    try {
+      const databaseId = idSchema.parse((request.params as { databaseId?: unknown }).databaseId);
+      const input = suggestionSchema.parse(request.body);
+      const suggestions = await deps.sensitiveDataSuggester.suggest(
+        databaseId,
+        input.modelId,
+        new AbortController().signal,
+      );
+      return { suggestions };
+    } catch (error) {
+      return safeError(reply, error);
+    }
+  });
+
   app.post("/catalog/databases/:databaseId/description-generation-runs", async (request, reply) => {
     if (!manage(request, reply)) return reply;
     try {

backend/src/routes/catalog-schema.ts

@@ -18,6 +18,7 @@ const metadataSchema = z.object({
   version: z.number().int().positive(),
   description: z.string().max(20_000).nullable(),
   generatedDescription: z.string().max(20_000).nullable(),
+  sensitive: z.boolean().optional(),
 }).strict();
 const createRunSchema = z.object({
   version: z.number().int().positive(),
@@ -117,6 +118,7 @@ export function catalogSchemaRoutes(
           input.version,
           normalized(input.description),
           normalized(input.generatedDescription),
+          input.sensitive,
         );
         if (!updated) return reply.code(409).send({ code: "column_stale", message: "Column metadata changed. Reload and try again." });
         return updated;