fix(ai) - optimize crud tools (#21133)

- **Add delete many**, `delete_many_{object}` added alongside the
existing `delete_one_{object}`.
- **Uniformize naming**, crud module, type names, and MCP helper
constants renamed for consistency.
- **Optimize tool schema (learn phase)**
  - `find_many(_companies)`: **7 158 → 2 700 tokens**
  - `find_one(_company)`: **280 → 126 tokens**
  -  ....
- Main mechanism: `reused: 'ref'` (line 7 of
`to-tool-json-schema.util.ts`). Zod walks the schema tree, tracks which
Zod schema instances appear more than once, and emits each reused
instance exactly once in `$defs`, replacing all subsequent occurrences
with a `$ref`. Works because filter and value schemas are now extracted
as shared objects.

- **Optimize system prompt (tool catalog)**, DATABASE_CRUD section
restructured to list operation patterns (`find_many_{object}`, …) once +
objects once, instead of the full N×M cross-product of tool names.
- **Optimize execute_tool**, shared record-properties schema (same
`$defs` deduplication applies at call time); introduced `upsert_many`;
added `selectedFields` to `find_*` so the agent only fetches the fields
it needs.

packages/twenty-server/src/engine/api/common/common-args-processors/data-arg-processor/validator-utils/validate-files-field-or-throw.util.ts

@@ -16,7 +16,7 @@ import {
 
 const fileItemSchema = z
   .object({
-    fileId: z.string().uuidv4(),
+    fileId: z.uuidv4(),
     label: z.string(),
   })
   .strict();

packages/twenty-server/src/engine/api/mcp/services/__tests__/mcp-protocol.service.spec.ts

@@ -273,7 +273,7 @@ describe('McpProtocolService', () => {
         method: 'tools/call',
         params: {
           name: 'execute_tool',
-          arguments: { toolName: 'find_companies', arguments: {} },
+          arguments: { toolName: 'find_many_companies', arguments: {} },
         },
         id: '123',
       };

packages/twenty-server/src/engine/api/mcp/utils/build-mcp-server-instructions.util.ts

@@ -19,8 +19,8 @@ export const buildMcpServerInstructions = (
     ``,
     ...(skillNames ? [`Available skills: ${skillNames}.`, ``] : []),
     `CRUD tool name grammar — construct names directly without prior discovery:`,
-    `  Read:  find_{objects} | find_one_{object} | group_by_{objects}`,
-    `  Write: create_{object} | create_many_{objects} | update_{object} | update_many_{objects} | delete_{object}`,
+    `  Read:  find_many_{objects} | find_one_{object} | group_by_{objects}`,
+    `  Write: create_one_{object} | create_many_{objects} | update_one_{object} | update_many_{objects} | delete_one_{object} | delete_many_{objects} | upsert_many_{objects}. Use upsert_many_{objects} instead of update_many_{objects} when each record has its own individual data.`,
     ``,
     `Non-CRUD tools — use learn_tools for schemas:`,
     `  ACTION:           http_request | send_email | draft_email | navigate_app | code_interpreter | search_help_center`,
@@ -39,8 +39,8 @@ export const buildMcpServerInstructions = (
     `  ⚠️ Never call workflow, dashboard, or metadata tools without loading their skill first.`,
     ``,
     `Route by intent:`,
-    `  Named entity ("Acme company")   → find_{objects} to resolve id first, then operate on id`,
-    `  Retrieve records                → find_{objects} (default limit: 10, always report total count)`,
+    `  Named entity ("Acme company")   → find_many_{objects} to resolve id first, then operate on id`,
+    `  Retrieve records                → find_many_{objects} (default limit: 10, always report total count)`,
     `  Single record by id             → find_one_{object}`,
     `  Analytics / grouped metrics     → group_by_{objects} (COUNT, SUM, AVG, MIN, MAX)`,
     `  Multiple metrics                → run parallel group_by calls, merge results`,