Bound versioned retrieval RPC match_count to prevent unbounded results

supabase/migrations/20260717162000_bound_versioned_retrieval_match_count.sql

@@ -0,0 +1,86 @@
+-- Bound the result cardinality of the two versioned owner-plus-public retrieval
+-- entry points. PostgREST permits explicitly-null RPC arguments; PostgreSQL
+-- interprets LIMIT NULL (and a negative LIMIT) as no limit. Before this guard,
+-- a malformed or compromised service-role caller could turn the final LIMIT
+-- into an unbounded result within each helper's candidate window, multiplying
+-- JSON hydration and response size on a hot retrieval path.
+--
+-- Keep the public signatures and defaults intact for generated types and
+-- callers. The inner helpers already cap candidate work; this outer clamp
+-- makes the exposed result contract deterministic: 1..96 rows.
+--
+-- Rollback / forward repair: re-create these wrappers from
+-- 20260717160000_optimize_owner_public_retrieval.sql to restore the former
+-- pass-through count behaviour. No data is changed.
+
+create or replace function public.match_document_chunks_text_v2(
+  query_text text,
+  match_count integer default 12,
+  document_filters uuid[] default null,
+  owner_filter uuid default '00000000-0000-0000-0000-000000000000'::uuid,
+  include_public boolean default true
+)
+returns table (
+  id uuid, document_id uuid, title text, file_name text, page_number integer,
+  chunk_index integer, section_heading text, content text, retrieval_synopsis text,
+  image_ids uuid[], source_metadata jsonb, document_labels jsonb, document_summary text,
+  similarity double precision, text_rank double precision, hybrid_score double precision,
+  lexical_score double precision, images jsonb
+)
+language sql
+stable
+set search_path = public, extensions, pg_temp
+as $$
+  select *
+  from public.match_document_chunks_text_scoped(
+    $1,
+    least(greatest(coalesce($2, 12), 1), 96),
+    $3,
+    $4,
+    $5
+  );
+$$;
+
+create or replace function public.match_document_index_units_hybrid_v2(
+  query_embedding extensions.vector(1536),
+  query_text text,
+  match_count integer default 24,
+  min_similarity double precision default 0.1,
+  document_filters uuid[] default null,
+  owner_filter uuid default '00000000-0000-0000-0000-000000000000'::uuid,
+  include_public boolean default true
+)
+returns table (
+  id uuid, document_id uuid, source_chunk_id uuid, source_image_id uuid, unit_type text, title text,
+  content text, page_start integer, page_end integer, heading_path text[], normalized_terms text[],
+  source_span jsonb, quality_score real, extraction_mode text, similarity double precision,
+  text_rank double precision, hybrid_score double precision, metadata jsonb
+)
+language sql
+stable
+set search_path = public, extensions, pg_temp
+as $$
+  select *
+  from public.match_document_index_units_hybrid_scoped(
+    $1,
+    $2,
+    least(greatest(coalesce($3, 24), 1), 96),
+    $4,
+    $5,
+    $6,
+    $7
+  );
+$$;
+
+-- CREATE OR REPLACE preserves privileges in PostgreSQL, but re-state the
+-- service-role-only contract so future function changes cannot reopen it.
+revoke all on function public.match_document_chunks_text_v2(text, integer, uuid[], uuid, boolean)
+  from public, anon, authenticated;
+grant execute on function public.match_document_chunks_text_v2(text, integer, uuid[], uuid, boolean)
+  to service_role;
+revoke all on function public.match_document_index_units_hybrid_v2(
+  extensions.vector, text, integer, double precision, uuid[], uuid, boolean
+) from public, anon, authenticated;
+grant execute on function public.match_document_index_units_hybrid_v2(
+  extensions.vector, text, integer, double precision, uuid[], uuid, boolean
+) to service_role;

tests/retrieval-access-scope.test.ts

@@ -8,6 +8,10 @@ const optimizedRetrievalMigration = readFileSync(
   join(root, "supabase/migrations/20260717160000_optimize_owner_public_retrieval.sql"),
   "utf8",
 );
+const boundedRetrievalMigration = readFileSync(
+  join(root, "supabase/migrations/20260717162000_bound_versioned_retrieval_match_count.sql"),
+  "utf8",
+);
 const canonicalSchema = readFileSync(join(root, "supabase/schema.sql"), "utf8");
 
 function between(source: string, start: string, end: string): string {
@@ -111,6 +115,28 @@ describe("owner-plus-public retrieval contract", () => {
     }
   });
 
+  it("bounds nullable and negative result counts at the exposed versioned RPCs", () => {
+    // LIMIT NULL and LIMIT -1 mean "no limit" in PostgreSQL. The wrappers are
+    // the RPC boundary, so clamp here rather than trusting every service-role
+    // caller to validate an optional PostgREST argument.
+    expect(boundedRetrievalMigration).toContain("coalesce($2, 12)");
+    expect(boundedRetrievalMigration).toContain("coalesce($3, 24)");
+    expect(boundedRetrievalMigration).toContain("least(greatest(coalesce($2, 12), 1), 96)");
+    expect(boundedRetrievalMigration).toContain("least(greatest(coalesce($3, 24), 1), 96)");
+    expect(boundedRetrievalMigration).toContain(
+      "revoke all on function public.match_document_chunks_text_v2(text, integer, uuid[], uuid, boolean)\n  from public, anon, authenticated;",
+    );
+    expect(boundedRetrievalMigration).toContain(
+      "grant execute on function public.match_document_chunks_text_v2(text, integer, uuid[], uuid, boolean)\n  to service_role;",
+    );
+    expect(boundedRetrievalMigration).toContain(
+      "revoke all on function public.match_document_index_units_hybrid_v2(\n  extensions.vector, text, integer, double precision, uuid[], uuid, boolean\n) from public, anon, authenticated;",
+    );
+    expect(boundedRetrievalMigration).toContain(
+      "grant execute on function public.match_document_index_units_hybrid_v2(\n  extensions.vector, text, integer, double precision, uuid[], uuid, boolean\n) to service_role;",
+    );
+  });
+
   it("merges exact-owner and public rows when a versioned RPC is not deployed yet", async () => {
     const { callVersionedRetrievalRpc } = await import("../src/lib/rag");
     const rpc = vi.fn(async (name: string, args: Record<string, unknown>) => {