LlamaIndex

"""A LlamaIndex support agent on AgentOS. The refund tool waits for a person with the workflow's own
`wait_for_event`; the agent keeps the workflow's context in run state, asks through AgentOS, and on the resume
sends the decision back in as a HumanResponseEvent."""
import hashlib
import json

import agentos
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.core.workflow import Context, HumanResponseEvent, InputRequiredEvent, JsonPickleSerializer
from llama_index.llms.openai_like import OpenAILike

ORDERS = {  # stands in for your order system
    "A-1001": {"status": "delivered", "total": "49.90", "items": ["Desk lamp"], "delivered": "2026-10-02"},
    "A-1002": {"status": "in transit", "total": "129.00", "items": ["Office chair"], "delivered": None},
}


def build_agent(inv: agentos.Invocation) -> FunctionAgent:
    """Built per invocation: the model client carries this run's token."""
    llm = OpenAILike(
        model=inv.llm.model("main"),          # config.models.main, sent to the gateway as it is
        api_base=inv.llm.base_url,            # the AgentOS model gateway
        api_key=inv.llm.api_key,              # ignored by the gateway
        default_headers=inv.llm.headers,      # x-agentos-run-token
        async_http_client=inv.llm.httpx_client(asynchronous=True),  # the token never leaves the platform
        is_chat_model=True, is_function_calling_model=True, context_window=200_000,
        max_retries=0,                        # a guardrail block is a 400: don't retry it
    )

    async def lookup_order(order_id: str) -> str:
        """Look an order up by its id (like A-1001): its status, items, total and delivery date."""
        order = ORDERS.get(order_id.strip().upper())
        return json.dumps(order) if order else f"There is no order {order_id}."

    async def issue_refund(ctx: Context, order_id: str, amount: str, reason: str) -> str:
        """Refund `amount` (a decimal string like 49.90) on an order. A person approves every refund."""
        # The step runs again from here when the answer arrives: keep this part free of side effects.
        answer = await ctx.wait_for_event(
            HumanResponseEvent, waiter_id=f"refund:{order_id}",
            waiter_event=InputRequiredEvent(prefix="refund", order_id=order_id, amount=amount, reason=reason))
        decision = json.loads(answer.response)
        if decision["action"] in ("reject", "expired"):
            return f"The refund was not approved. {decision.get('comment') or ''}".strip()
        amount = decision["data"]["amount"]  # as approved, or as the reviewer edited it
        # Stands in for your payment provider; key the real call by run id so a retried run never pays twice.
        refund_id = "rf_" + hashlib.sha256(f"{inv.run_id}:{order_id}:{amount}".encode()).hexdigest()[:12]
        return f"Refunded {amount} on {order_id}: {refund_id}"

    return FunctionAgent(tools=[lookup_order, issue_refund], llm=llm, system_prompt=inv.config["prompts"]["system"])


async def support(inv: agentos.Invocation):
    agent = build_agent(inv)
    if inv.resume is None:  # the start
        handler = agent.run(user_msg=inv.input["message"])
    else:  # a person decided: restore the workflow and hand it their decision
        ctx = Context.from_dict(agent, await inv.state.run.aget("context"), serializer=JsonPickleSerializer())
        handler = agent.run(ctx=ctx)
        item = inv.resume.decided_items[0] if inv.resume.decided_items else None
        decision = ({"action": item.action, "data": item.data, "comment": item.comment} if item
                    else {"action": "expired"})
        handler.ctx.send_event(HumanResponseEvent(response=json.dumps(decision)))
    try:
        async for event in handler.stream_events():
            if isinstance(event, InputRequiredEvent):  # the refund tool waits: keep the context, ask a person
                await inv.state.run.aput("context", handler.ctx.to_dict(serializer=JsonPickleSerializer()))
                await handler.cancel_run()
                await inv.aask(f"Refund {event.amount} on order {event.order_id}?",
                               [{"id": event.order_id, "title": f"{event.order_id} · {event.amount}",
                                 "data": {"order_id": event.order_id, "amount": event.amount}}],
                               actions=["approve", "edit", "reject"],
                               details=f"Reason given by the agent: {event.reason}")
        response = await handler
    except Exception as error:
        if block := agentos.guardrail_block(error):
            raise block  # the run fails with blocked_by_guardrail and the guardrail's message
        raise
    return {"answer": str(response)}


agentos.serve({"support": support}, port=8080)

name: llamaindex-support
title: Support agent (LlamaIndex)
description: Answers order questions with a lookup tool; refunds go through a person first.
runtime: stateless
port: 8080
capabilities:
  support:
    description: Handles a customer's message. A refund the model wants to issue waits for a person's approval.
    input:
      type: object
      properties: {message: {type: string, minLength: 1}}
      required: [message]
    output:
      type: object
      properties: {answer: {type: string}}
      required: [answer]
    timeout: 120s
config:
  models:
    main: anthropic/claude-sonnet-4-5    # a model from your Models page: <provider slug>/<model ID>
  prompts:
    system: >-
      You are a support agent for an online shop. Look orders up with lookup_order before you
      answer anything about an order. Use issue_refund only for delivered orders that arrived
      damaged. Answer in at most three sentences.

FROM python:3.13-slim
WORKDIR /app
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt
# the AgentOS SDK wheel, from the bundle's vendor/ folder
COPY vendor/ vendor/
RUN pip install --no-cache-dir vendor/*.whl
COPY app.py .
USER nobody
EXPOSE 8080
CMD ["python", "-u", "app.py"]

llama-index-core==0.14.25
llama-index-llms-openai-like==0.8.1