Add Agents SDK DBOS integration to the docs for long-running agents and human-in-the-loop

[qianl15]

This PR updates the docs to mention DBOS OpenAI Agents integration for long-running and human-in-the-loop agents. Closes #1711

DBOS is a durable execution library, where its only dependency is a database (SQLite or Postgres).

The integration adds a DBOSRunner as a drop-in replacement for Runner, which allows agents to be executed from DBOS workflows and persists LLM calls so they can be deterministically replayed after failures or restarts.

Example (async):

@function_tool
@DBOS.step()
async def get_weather(city: str) -> str:
    ...

agent = Agent(name="weather", tools=[get_weather])

# Call the agent from a DBOS workflow
@DBOS.workflow()
async def run_agent(user_input: str) -> str:
    result = await DBOSRunner.run(agent, user_input)
    return str(result.final_output)

DBOS also supports a synchronous execution model:

@function_tool
@DBOS.step()
def get_weather(city: str) -> str:
    ...

agent = Agent(name="weather", tools=[get_weather])

# Call the agent from a DBOS workflow
@DBOS.workflow()
def run_agent(user_input: str) -> str:
    result = DBOSRunner.run_sync(agent, user_input)
    return str(result.final_output)

Links:

• Integration repo: https://github.com/dbos-inc/dbos-openai-agents
• DBOS docs: https://docs.dbos.dev/integrations/openai-agents

[seratch]

Thank you!