feat(2/n): agent return turn awaiting input for tool calls

[yanxi0830]

What does this PR do?

• 1/n: feat(1/n): api: unify agents for handling server & client tools #1178

This is a backward compat change. Default allow_resume_turn=False to work with client v0.1.3.

Expected Behaviour

1. User sends out agent.create_turn. When user receives a custom client_tool_call. The last chunk should be

chunk = AgentTurnResponseStreamChunk(
        event=AgentTurnResponseEvent(
        payload=AgentTurnResponseTurnAwaitingInputPayload(
            turn=turn,
       )
    )
)

There should be a tool_execution step.

2. When user sees turn_pending as the event_type or if there's tool call in the response. They will execute the client tools, and submits back the tool response. E.g.

client.continue_turn(
    [ToolResponseMessage(...)]
)

The agent will then send back & record tool_execution step finish on server. and continue with the execution.

NOTE: This PR handles (1). Next PR handle (2).

Test Plan

• Testing w/ Client SDK 0.1.3

LLAMA_STACK_BASE_URL=http://localhost:8321 pytest -v tests/client-sdk/agents/test_agents.py --inference-model meta-llama/Llama-3.1-8B-Instruct

[ashwinb]

This is a backward compat change.

You mean this is a backward incompatible change, right?

[yanxi0830]

This is a backward compat change.

You mean this is a backward incompatible change, right?

Actually, I was referring to backward compat in that this change won't impact anything if client wants to create a separate turn. But I agree that the turn_awaiting_input may not be available for client with older versions.