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 +1,49 @@
# Request Input Tool Sample
## Overview
This sample demonstrates how an LLM agent can proactively request clarification or confirmation from the user using the built-in `request_input` tool without losing its context/flow.
It showcases a highly realistic support assistant that dynamically constructs a JSON schema to only ask for missing details when creating IT support tickets.
## Sample Inputs
- `I want to file a technical ticket for a database crash.`
The agent will analyze the prompt, identify that the `title` and `category` are already provided, and dynamically call `request_input` with a schema requesting only `description` and `priority`.
- `File a priority HIGH technical ticket titled database crash explained as the MySQL server throwing OOM errors.`
The agent has all required details and will call `create_support_ticket` immediately without needing clarification.
## Graph
```mermaid
graph TD
User[User Prompt] --> Agent[Support Assistant Agent]
Agent -->|Needs Clarification| RequestInput[request_input tool]
RequestInput -->|User Response| Agent
Agent -->|All Details Gathered| CreateTicket[create_support_ticket tool]
```
## How To
This sample uses **Pattern B: Standalone Agents** with the `request_input` tool:
1. **Import `request_input`**:
```python
from google.adk.tools import request_input
```
1. **Add it to the LLM Agent's tools list**:
```python
root_agent = Agent(
name="support_assistant_agent",
tools=[create_support_ticket, request_input],
...
)
```
When the LLM decides it needs clarification, it calls `request_input` with a question and a dynamic `response_schema`. The ADK framework automatically intercepts this, yields a long-running interrupt to the client, and injects the user's reply back as a `FunctionResponse` into the LLM's chat history.
@@ -0,0 +1,62 @@
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from google.adk import Agent
from google.adk.tools import request_input
from google.genai import types
from pydantic import BaseModel
from pydantic import Field
class SupportTicket(BaseModel):
"""Details of the IT support ticket to be created."""
title: str = Field(description="A brief summary of the issue.")
description: str = Field(description="Detailed explanation of the problem.")
priority: str = Field(
default="MEDIUM",
description="Ticket priority: LOW, MEDIUM, HIGH, or CRITICAL.",
)
category: str = Field(
description=(
"Issue category, e.g., billing, technical, account, or database."
)
)
def create_support_ticket(ticket: SupportTicket) -> dict[str, str]:
"""Create a support ticket in the IT ticketing system."""
return {
"status": "success",
"message": (
f"Successfully created ticket '{ticket.title}'"
f" [Category: {ticket.category}, Priority: {ticket.priority}]."
),
"ticket_id": "INC-98471",
}
root_agent = Agent(
name="support_assistant_agent",
instruction="""
You are a helpful IT support assistant responsible for creating support tickets.
When the user requests to create or file a ticket:
1. Identify which ticket details (title, description, priority, category) are already provided in the conversation.
2. If any mandatory details are missing, call the `request_input` tool.
3. When calling `request_input`, you must construct a dynamic JSON `response_schema` (type: "object") that ONLY requests the missing details, and specify a helpful message explaining what is needed.
4. Once all details are gathered, call `create_support_ticket` with the complete SupportTicket details.
""",
tools=[create_support_ticket, request_input],
generate_content_config=types.GenerateContentConfig(temperature=0.1),
)
@@ -0,0 +1,159 @@
{
"events": [
{
"author": "user",
"content": {
"parts": [
{
"text": "I want to file a technical ticket for a database crash."
}
],
"role": "user"
},
"id": "e-1",
"invocationId": "i-1",
"nodeInfo": {
"path": ""
}
},
{
"author": "support_assistant_agent",
"content": {
"parts": [
{
"functionCall": {
"args": {
"message": "I can help with that. Please provide the description and priority of the database crash:",
"response_schema": {
"properties": {
"description": {
"description": "Detailed explanation of the database crash problem.",
"title": "Description",
"type": "string"
},
"priority": {
"description": "Ticket priority: LOW, MEDIUM, HIGH, or CRITICAL.",
"title": "Priority",
"type": "string"
}
},
"required": [
"description",
"priority"
],
"title": "TicketClarification",
"type": "object"
}
},
"id": "fc-1",
"name": "adk_request_input"
}
}
],
"role": "model"
},
"finishReason": "STOP",
"id": "e-2",
"invocationId": "i-1",
"longRunningToolIds": [
"fc-1"
],
"nodeInfo": {
"path": "support_assistant_agent@1"
}
},
{
"author": "user",
"content": {
"parts": [
{
"functionResponse": {
"id": "fc-1",
"name": "adk_request_input",
"response": {
"description": "The MySQL server is throwing OOM errors and restarting repeatedly.",
"priority": "HIGH"
}
}
}
],
"role": "user"
},
"id": "e-3",
"invocationId": "i-1",
"nodeInfo": {
"path": ""
}
},
{
"author": "support_assistant_agent",
"content": {
"parts": [
{
"functionCall": {
"args": {
"ticket": {
"category": "database",
"description": "The MySQL server is throwing OOM errors and restarting repeatedly.",
"priority": "HIGH",
"title": "Database crash"
}
},
"id": "fc-2",
"name": "create_support_ticket"
}
}
],
"role": "model"
},
"finishReason": "STOP",
"id": "e-4",
"invocationId": "i-1",
"longRunningToolIds": [],
"nodeInfo": {
"path": "support_assistant_agent@1"
}
},
{
"author": "support_assistant_agent",
"content": {
"parts": [
{
"functionResponse": {
"id": "fc-2",
"name": "create_support_ticket",
"response": {
"message": "Successfully created ticket 'Database crash' [Category: database, Priority: HIGH].",
"status": "success",
"ticket_id": "INC-98471"
}
}
}
],
"role": "user"
},
"id": "e-5",
"invocationId": "i-1",
"nodeInfo": {
"path": "support_assistant_agent@1"
}
},
{
"author": "support_assistant_agent",
"content": {
"parts": [
{
"text": "Successfully created ticket 'Database crash' [Category: database, Priority: HIGH] with ticket ID INC-98471."
}
],
"role": "model"
},
"finishReason": "STOP",
"id": "e-6",
"invocationId": "i-1",
"nodeInfo": {
"path": "support_assistant_agent@1"
}
}
]
}