OpenAI

The files-sdk/openai subpath ships two factories targeting OpenAI directly - one for the native Responses API and one for the OpenAI Agents SDK (@openai/agents). Both wrap the same eight file operations as the Vercel subpath, with the same approval-gating defaults.

openai and @openai/agents are optional peer dependencies - install only the one(s) you use. The subpath requires Zod 4: @openai/agents peer-requires it, and Zod 4's built-in toJSONSchema powers the Responses tool definitions.

Responses API

createResponsesFileTools returns { definitions, execute, needsApproval }. Pass definitions straight to openai.responses.create({ tools }), then call execute(call) on each function_call item in the response output to get a function_call_output ready to push into the next turn's input.

npm install openai zod

import OpenAI from "openai";
import { Files } from "files-sdk";
import { s3 } from "files-sdk/s3";
import { createResponsesFileTools } from "files-sdk/openai";

const client = new OpenAI();
const files = new Files({ adapter: s3({ bucket: "uploads" }) });
const ft = createResponsesFileTools({ files });

const input: any[] = [{ role: "user", content: "List my files." }];
while (true) {
  const res = await client.responses.create({
    model: "gpt-4.1",
    input,
    tools: ft.definitions,
  });

  const calls = res.output.filter((o) => o.type === "function_call");
  if (calls.length === 0) {
    console.log(res.output_text);
    break;
  }

  for (const call of calls) {
    if (ft.needsApproval(call.name)) {
      // surface approval UX, then continue or break
    }
    input.push(call, await ft.execute(call));
  }
}

execute returns JSON parse failures and Zod validation errors as the tool's output, so the model can self-correct on the next turn. FilesError from the underlying SDK is rethrown - you decide how to surface it. needsApproval(name) is informational; checking it is the caller's responsibility.

Agents SDK

createAgentsFileTools returns a record of tool() outputs keyed by tool name - spread Object.values() into new Agent({ tools }). Write tools default to needsApproval: true; the Agents SDK runner surfaces an interruption that your program resolves by approving or rejecting the call.

npm install @openai/agents zod

import { Agent, run } from "@openai/agents";
import { Files } from "files-sdk";
import { s3 } from "files-sdk/s3";
import { createAgentsFileTools } from "files-sdk/openai";

const files = new Files({ adapter: s3({ bucket: "uploads" }) });
const tools = createAgentsFileTools({ files });

const agent = new Agent({
  instructions: "Help the user manage their files.",
  name: "Files agent",
  tools: Object.values(tools),
});

const result = await run(agent, "List my files.");

Errors thrown from execute() are wrapped by the Agents SDK's default errorFunction into a model-visible string - the model sees the message and can self-correct on the next turn. This is the standard Agents-SDK pattern, and differs from the Responses flow where FilesError rethrows.

Approval, read-only, overrides

Both factories accept the same options shape as the Vercel createFileTools: requireApproval (boolean or per-tool record), readOnly (strips writes entirely), and overrides (description, plus strict for Responses or needsApproval for Agents).

// Same shape across both factories.

createResponsesFileTools({ files }); // all writes gated (default)
createResponsesFileTools({ files, requireApproval: false }); // disabled
createResponsesFileTools({
  files,
  requireApproval: { deleteFile: true, uploadFile: false },
});

createAgentsFileTools({ files, readOnly: true });
// → only listFiles, getFileMetadata, downloadFile, getFileUrl