Skip to main content
Super Durable
English
English简体中文
GitHubLog inSign up Cloud
Menu

OpenAI Agents SDK

View as Markdown

The OpenAI Agents SDK defines an agent with instructions, function tools, and handoffs. The Dex adapter runs the SDK's runner inside a durable session. It is available for Python and TypeScript.

When to use it​

Use it when your agent already uses the OpenAI Agents SDK, with or without handoffs. Keep the SDK's agent definition, tools, and guardrails, and let Dex own the session.

How a session runs​

The adapter copies the agent graph once and intercepts every function tool. So the SDK stops right after each model call and returns the tool calls the model asks for. Each RunModel Step makes one model call.

Each function tool call runs in its own Step, in parallel: CallTool for a read or an idempotent write, CallSingleAttemptTool for any other write. A call that needs approval waits in AwaitToolApproval first. The next RunModel restores the SDK's run state and gives it the recorded results. The tool does not run again.

A handoff is not a function tool. It runs inside RunModel, so a Step that hands off also makes the next agent's model call.

A turn that looks up an order runs RunModel, CallTool, ResumeTurn, and RunModel.

Install​

Install the adapter with its framework. Each adapter brings in the Dex Agents core.

pip install dex-agents-openai-agents

Example: agents/python/openai-agents/README.md

The example​

The example is the order support agent that every framework page uses.

The Flow type is OpenAIAgentsOrderSupport in Python and OpenAIAgentsOrderSupportAgent in TypeScript. The full example is under examples/python/agent-harnesses and examples/typescript/src/products/agent-harnesses.

Agent and tools​

The tools are function tools of the SDK. The agent is a plain SDK agent. The tool policies name each tool.

openai_agents_order_support.pyPython
def build_openai_agents_order_support_flow(
    order_desk: OrderDesk, model: str | Model, slack_connection: slack.Connection | None
) -> AgentSessionFlow:
    """Builds the session Flow; ``model`` is an OpenAI model name, such as "gpt-5.2"."""

    # The tools are closures, so they call the OrderDesk passed in here.
    @function_tool
    def look_up_order(order_id: str) -> str:
        """Look up one order by its order ID and return its items and status."""
        return order_desk.describe_order(order_id)

    @function_tool
    def cancel_order(order_id: str, reason: str) -> str:
        """Cancel one order that has not shipped yet."""
        return order_desk.cancel_order(order_id, reason)

    agent = Agent(
        name="OrderSupport",
        instructions=ORDER_SUPPORT_INSTRUCTIONS,
        model=model,
        tools=[look_up_order, cancel_order],
    )
    return openai_agents_session_flow(
        agent,
        flow_type=OPENAI_AGENTS_ORDER_SUPPORT_FLOW_TYPE,
        tool_sources=build_slack_tool_sources(slack_connection),
        tool_policies={
            "look_up_order": ToolPolicy(ToolEffect.READ),
            "cancel_order": ToolPolicy(ToolEffect.NON_IDEMPOTENT_WRITE),
        },
    )

Example: examples/python/agent-harnesses/agent_harness_examples/openai_agents_order_support.py

Worker​

One Worker serves the session Flows of every harness in the example. Agent session Steps are async, so the Python Registry allows async handlers. Build the same session Flow in every process that starts sessions or calls their RPCs.

app.pyPython
        # Agent session Steps are async, so the Registry allows async handlers.
        self.registry = Registry(
            tuple(example.session_flow for example in self.examples), allow_async_handlers=True
        )
        config.blob_cache_dir.mkdir(parents=True, exist_ok=True)
        self.blob_cache = open_blob_cache(BlobCacheConfig(str(config.blob_cache_dir), 1 << 30))
        self.worker = AsyncWorker(
            self.registry,
            self.blob_cache,
            WorkerOptions(
                server_address=config.server_address,
                pull=PullWorkerOptions(max_concurrent_tasks=MAX_CONCURRENT_TASKS),
            ),
        )
        self.client = AsyncClient(
            self.registry, self.blob_cache, ClientOptions(server_address=config.server_address)
        )

# ...

def _new_openai_agents_example(
    config: AgentHarnessExamplesConfig, slack_connection: slack.Connection | None
) -> AgentHarnessExample:
    order_desk = OrderDesk()
    model = _openai_agents_model(config.openai_agents_model)
    flow = build_openai_agents_order_support_flow(order_desk, model, slack_connection)
    return AgentHarnessExample("openai-agents", flow, order_desk)

# ...

def _openai_agents_model(model: str) -> str | Model:
    return OpenAIAgentsDemoModel() if is_demo_model(model) else model

Example: examples/python/agent-harnesses/agent_harness_examples/app.py

Session routes​

Every harness serves these same routes. Session routes explains them and the session token.

http_routes.pyPython
    @blueprint.post("/sessions")
    async def start_session() -> Response:
        # The server picks the session ID, so a caller cannot claim an existing session.
        session_id = f"{harness_name}-order-support-{uuid.uuid4()}"
        await sessions.start_session(session_id)
        session_token = sign_session_id(app_state.config.session_key, session_id)
        return jsonify(session_id=session_id, session_token=session_token)

    @blueprint.post("/messages")
    async def send_user_message() -> Response:
        body, session_id = await session_request()
        accepted = await sessions.send_user_message(session_id, _required_string(body, "text"))
        return jsonify(accepted=accepted)

    @blueprint.post("/interrupts/resolve")
    async def resolve_interrupt() -> Response:
        body, session_id = await session_request()
        interrupt_id = _required_string(body, "interrupt_id")
        if not isinstance(approved := body.get("approved"), bool):
            raise BadRequest("approved must be a boolean")
        rejection_message = body.get("rejection_message")
        if rejection_message is not None and not isinstance(rejection_message, str):
            raise BadRequest("rejection_message must be a string")
        accepted = await sessions.resolve_interrupt(
            session_id, interrupt_id, approved=approved, rejection_message=rejection_message
        )
        return jsonify(accepted=accepted)

    @blueprint.get("/snapshot")
    async def get_agent_snapshot() -> Response:
        session_id = request.args.get("session_id", "")
        if not session_id:
            raise BadRequest("session_id is required")
        authorize_session(session_id)
        try:
            snapshot = await read_agent_event_stream_snapshot(
                app_state.client, example.session_flow, session_id
            )
        except FlowNotActiveOrNotFoundError as error:
            raise NotFound("the agent session is missing or no longer retained") from error
        return jsonify(snapshot.to_json())

Example: examples/python/agent-harnesses/agent_harness_examples/http_routes.py

Run it locally​

Start Dex and the example​

In a first terminal, render the session graph, then start Dex. Dex Web reads the graph when it starts, to show the session and its approval controls.

cd examples/python/agent-harnesses
uv sync --locked
mkdir -p definitions
uv run --frozen dex-agents-session-graph --flow-type OpenAIAgentsOrderSupport \
  --permission order-support.operate --out definitions/openai-agents-sdk.json
dexcli dev --flow-rendering-dir ./definitions

Example: examples/python/agent-harnesses/README.md

dexcli dev stays in the foreground. In a second terminal, start the example:

cd examples/python/agent-harnesses
uv run --frozen python -m agent_harness_examples

Example: examples/python/agent-harnesses/README.md

The Python app serves on 127.0.0.1:8081. The TypeScript app serves on 127.0.0.1:8080. Dex Web is at http://127.0.0.1:8802.

Without DEX_OPENAI_AGENTS_MODEL, the Python agent uses mock/order-support, a local demo model that needs no key. It calls look_up_order for "look up order 1001" and cancel_order for "cancel order 1002". The TypeScript example has no demo model, so it needs OPENAI_API_KEY.

VariableDefaultMeaning
DEX_OPENAI_AGENTS_MODELPython: mock/order-support. TypeScript: gpt-5-mini.The OpenAI model name, such as gpt-5.2.
OPENAI_API_KEYnoneThe OpenAI API key, for a real model.
DEX_AGENT_SESSION_KEYa random keyThe key that signs session tokens.

Call the session​

Start a session, ask the agent to cancel order 1002, and approve the call:

base=http://127.0.0.1:8081/products/agent-harnesses/openai-agents
session=$(curl -s -X POST "$base/sessions" -H 'Content-Type: application/json' -d '{}')
id=$(echo "$session" | jq -r .session_id)
token=$(echo "$session" | jq -r .session_token)
curl -s -X POST "$base/messages" -H 'Content-Type: application/json' \
  -H "X-Agent-Session-Token: $token" -d "{\"session_id\": \"$id\", \"text\": \"Cancel order 1002\"}"
until interrupt=$(curl -s "$base/snapshot?session_id=$id" -H "X-Agent-Session-Token: $token" \
  | jq -re '.snapshot.pending_interrupts[0].interrupt_id'); do sleep 1; done
curl -s -X POST "$base/interrupts/resolve" -H 'Content-Type: application/json' \
  -H "X-Agent-Session-Token: $token" \
  -d "{\"session_id\": \"$id\", \"interrupt_id\": \"$interrupt\", \"approved\": true}"

Example: examples/python/agent-harnesses/README.md

The loop reads the snapshot until the agent asks to run cancel_order. That call waits for approval, then runs once. Read the snapshot again to see the agent's answer.

Approve in Dex Web​

Instead of the last command, you can approve the call in Dex Web. Follow the steps in Approve in Dex Web.

Connect Connectors​

The agent can call Connector operations as tools, as Connectors as tools describes. The example adds the Slack tool slack_post_thread_reply, which replies in a Slack thread.

Offer the tool​

In Python, install the connectors extra of dex-agents and the Connector package, such as dex-connector-slack. In TypeScript, install @superdurable/connectors-sdk and the Connector package, such as @superdurable/connector-slack. The install commands are in Connector tools.

The Worker opens the Slack connection support-slack from the project configuration. connector_tool in Python and connectorTool in TypeScript turns the operation into a tool, and ConnectorToolSource holds it. Without the connection, the agent gets no Slack tool.

slack_connector_tools.pyPython
def build_slack_tool_sources(connection: slack.Connection | None) -> list[ToolSource]:
    """Returns the Slack tool source, or no source when Slack is not configured."""
    if connection is None:
        return []
    return [
        ConnectorToolSource([
            # The manifest does not ask for approval; this agent asks before every post.
            connector_tool(
                connection.post_thread_reply(), connection.reference, requires_approval=True
            ),
        ]),
    ]

# ...

async def open_slack_project_connection(
    environment: Mapping[str, str] = os.environ,
) -> SlackProjectConnection | None:
    # ...
    # An incomplete or invalid configuration raises here, so the Worker fails at startup.
    try:
        project = await load_from_environment(environment)
    except FileNotFoundError:
        _log_slack_not_set_up("the connector configuration file does not exist")
        return None
    # ...
    try:
        connection = slack.new_project_connection(project, SLACK_CONNECTION_NAME)
    except BaseException:
        await project.close()
        raise
    return SlackProjectConnection(project, connection)

Example: examples/python/agent-harnesses/agent_harness_examples/slack_connector_tools.py

The Worker opens the connection once, at startup, and every agent uses it:

__main__.pyPython
async def main() -> None:
    config = AgentHarnessExamplesConfig.from_env()
    slack_setup = await open_slack_project_connection()
    try:
        app_state = AgentHarnessExamplesApp(config, slack_setup.connection if slack_setup else None)
        # ...
    finally:
        if slack_setup is not None:
            await slack_setup.aclose()

Example: examples/python/agent-harnesses/agent_harness_examples/__main__.py

The agent passes the tool source next to its own tools:

openai_agents_order_support.pyPython
    return openai_agents_session_flow(
        agent,
        flow_type=OPENAI_AGENTS_ORDER_SUPPORT_FLOW_TYPE,
        tool_sources=build_slack_tool_sources(slack_connection),
        # ...
    )

Example: examples/python/agent-harnesses/agent_harness_examples/openai_agents_order_support.py

How a call runs​

Each call of slack_post_thread_reply runs once, in its own CallSingleAttemptTool Step, after a person approves it. The Slack Connector tool explains why.

Every agent of the graph offers the Connector tools after its own tools. In Python, the adapter builds a function tool for each tool in the source's cached listing, its cached_tools(); ConnectorToolSource caches its whole listing. In TypeScript, they are non-strict function tools, and a tool's needsApproval and input guardrails do not apply to them. A call never runs inside the SDK; the source decides approval.

Configure the connection​

Connections explains where the Worker finds the support-slack connection and what the Slack app needs.

To try it, start the example with DEX_CONNECTOR_CONFIG_FILE set. Then ask the agent to reply in a Slack thread, with the channel ID and the thread timestamp:

Reply in Slack thread C0123456789 1710000000.000100: Order 1002 ships on Thursday.

The post waits for approval, like cancel_order.

Limits​

  • Only function tools get their own Steps. Hosted tools, such as web search, run at the provider during the model call. They repeat when RunModel reruns.
  • Tools the SDK runs itself, such as MCP server tools and local shell tools, cannot wait for approval. The adapter refuses them by default. Wrap a write in a function tool to give it its own Step.
  • Function tool names must be unique across the agent graph. The graph is copied when the Flow is built, so later changes to it do not reach the Flow.
  • The session is the history. Do not use server-managed conversation state or SDK sessions.
  • An agent used as a tool runs its nested run inside one tool Step in Python. TypeScript rejects it; hand off instead.

The adapter README lists every limit. See Limits for long sessions for the server limits.