Skip to main content

Human-in-the-loop for the OpenAI Agents SDK: a function tool that asks a real human on their phone and blocks on a fail-closed answer.

Project description

pushary-openai-agents

Human-in-the-loop for the OpenAI Agents SDK (Python). A function tool that asks a real human to approve, delivered to their phone, and blocks on a fail-closed answer.

Requires the Pushary Partner plan.

Install

pip install pushary-openai-agents

Set PUSHARY_API_KEY (get it in your dashboard).

Connect a phone once

from pushary_openai_agents import connect

link = connect("user_123")  # show this to your end-user; one tap connects their phone

The tool

from agents import Agent, Runner
from pushary_openai_agents import pushary_tool

agent = Agent(
    name="Support",
    instructions="Call ask_human before issuing any refund.",
    tools=[pushary_tool("user_123")],
)
result = await Runner.run(agent, "Refund order 5?")

When the model calls the tool, Pushary delivers the question to that user's phone and the call blocks until they answer. The tool returns a fail-closed instruction. The external_id is bound when you build the tool, never taken from the model, so a prompt-injected agent cannot ask the wrong person.

Durable approvals

For a wait longer than a request can hold, drive your own flow off ask_human with a callback_url on decisions.create and resolve the signed callback:

from pushary_openai_agents import resolve_pushary_callback, SIGNATURE_HEADER

def callback(request):
    cb = resolve_pushary_callback(request.body, request.headers.get(SIGNATURE_HEADER), SECRET)
    if not cb:
        return ("bad signature", 401)
    # look up your parked run by cb["correlationId"], approve/reject, resume
    return ("ok", 200)

For TypeScript, use npm i @pushary/openai-agents.

API

  • connect(external_id, *, api_key=None, base_url=None) — enroll an end-user's phone.
  • pushary_tool(external_id, *, name="ask_human", ...) — an OpenAI Agents function tool bound to that user.
  • ask_human(question, *, external_id, type="confirm", ...) — blocking, returns the decision dict.
  • resolve_pushary_callback(raw_body, signature, secret) — verify + parse a callback for the durable path.
  • describe_answer(type, result), is_affirmative(answer), deterministic_key(parts), SIGNATURE_HEADER.

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

pushary_openai_agents-0.1.0.tar.gz (6.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

pushary_openai_agents-0.1.0-py3-none-any.whl (5.5 kB view details)

Uploaded Python 3

File details

Details for the file pushary_openai_agents-0.1.0.tar.gz.

File metadata

  • Download URL: pushary_openai_agents-0.1.0.tar.gz
  • Upload date:
  • Size: 6.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.9.6

File hashes

Hashes for pushary_openai_agents-0.1.0.tar.gz
Algorithm Hash digest
SHA256 9e6ca374d6ea6ed549facb614cc9c1441b805177e769b1c61aa2f6818786d916
MD5 759529f3ca9bc71c40b646f9bedbde75
BLAKE2b-256 62b7293f9cdb9c7766f57485fef4b56e138abf753d4e0ef7f764c2f7f95633e3

See more details on using hashes here.

File details

Details for the file pushary_openai_agents-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for pushary_openai_agents-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 ce51ca2e77f252cc950cb71dfdedcae8948258a9389ca917cdd7a309b655c90e
MD5 26b341888e40e1e97ffcfff19d9b2a59
BLAKE2b-256 ef3a0c2ee807833f63e9acfcd5110868830b33874e5c46d13938ab45f5132278

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page