chore: import upstream snapshot with attribution
Continuous Integration / Pre-commit Linter (push) Has been cancelled
Continuous Integration / Mypy Check (Python 3.10) (push) Has been cancelled
Continuous Integration / Mypy Check (Python 3.11) (push) Has been cancelled
Continuous Integration / Mypy Check (Python 3.12) (push) Has been cancelled
Continuous Integration / Mypy Check (Python 3.13) (push) Has been cancelled
Continuous Integration / Unit Tests (Python 3.10) (push) Has been cancelled
Continuous Integration / Unit Tests (Python 3.11) (push) Has been cancelled
Continuous Integration / Unit Tests (Python 3.12) (push) Has been cancelled
Continuous Integration / Unit Tests (Python 3.13) (push) Has been cancelled
Continuous Integration / Unit Tests (Python 3.14) (push) Has been cancelled
Continuous Integration / A2A v0.3 Tests (Python 3.10) (push) Has been cancelled
Continuous Integration / A2A v0.3 Tests (Python 3.11) (push) Has been cancelled
Continuous Integration / A2A v0.3 Tests (Python 3.12) (push) Has been cancelled
Copybara PR Handler / close-imported-pr (push) Has been cancelled
Continuous Integration / A2A v0.3 Tests (Python 3.13) (push) Has been cancelled
Continuous Integration / A2A v0.3 Tests (Python 3.14) (push) Has been cancelled

This commit is contained in:
wehub-resource-sync
2026-07-13 13:25:13 +08:00
commit ec2b666284
2231 changed files with 491535 additions and 0 deletions
@@ -0,0 +1,56 @@
# ADK Single-turn Agent as Sub-agent Sample
## Overview
This sample demonstrates how a "single_turn" mode agent can act as an autonomous sub-agent to an LLM agent, utilizing schemas and tools without ever interacting with the user.
**Note**: This is the recommended mechanism to replace the older `AgentTool` pattern. Unlike `AgentTool`, using a `single_turn` sub-agent preserves the sub-agent's internal interactions (like tool calls) in the session history.
Single-turn agents are designed to execute their function fully in one prompt-response cycle. In this sample:
1. `phone_recommender`: A single-turn agent that receives structured input (`UserPreferences`), uses a mocked tool (`check_phone_price`), and returns structured output (`PhoneRecommendation`).
1. `root_agent`: The main agent that interacts with the user, translates their natural language request into the structured `UserPreferences`, and delegates to `phone_recommender`.
## Sample Inputs
- `I need a phone mostly for gaming. I have about $1000 to spend.`
- `What is a good cheap phone from Google for basic tasks?`
- `I love photography but prefer smaller phones. My budget is $600.`
## Graph
```mermaid
graph TD
root_agent --> phone_recommender
phone_recommender -.->|uses| check_phone_price[check_phone_price tool]
```
## How To
1. Define a sub-agent with `mode="single_turn"`, `input_schema`, `output_schema`:
```python
phone_recommender = Agent(
name="phone_recommender",
mode="single_turn",
input_schema=UserPreferences,
output_schema=PhoneRecommendation,
tools=[check_phone_price],
...
)
```
1. Assign it to a parent agent:
```python
root_agent = Agent(
sub_agents=[phone_recommender],
...
)
```
## Related Guides
- [LlmAgent Single-Turn Mode](../../../../docs/guides/agents/llm_agent/single_turn.md) - Guide explaining the behavior and configuration of single-turn agents.