图代理

使用原生 ADK-Rust 集成，通过 LangGraph 风格的编排构建复杂、有状态的工作流。

概述

GraphAgent 允许您将工作流定义为带有节点和边的有向图，支持：

AgentNode：将 LLM agents 包装为具有自定义输入/输出映射器的图节点
循环工作流：原生支持循环和迭代推理 (ReAct pattern)
条件路由：基于状态的动态边路由
状态管理：带 reducer 的类型化状态（覆盖、追加、求和、自定义）
检查点：用于容错和人机协作的持久状态
流式传输：多种流模式（值、更新、消息、调试）

adk-graph crate 为构建复杂、有状态的 agent 工作流提供了 LangGraph 风格的工作流编排。它将基于图的工作流功能引入 ADK-Rust 生态系统，同时保持与 ADK 的 agent system 的完全兼容性。

主要优势：

可视化工作流设计：将复杂逻辑定义为直观的节点和边图
并行执行：多个节点可以同时运行以获得更好的性能
状态持久性：内置检查点，用于容错和人机协作
LLM 集成：原生支持将 ADK agents 包装为图节点
灵活路由：静态边、条件路由和动态决策

你将构建什么

在本指南中，你将创建一个并行运行翻译和摘要的文本处理管道：

                        ┌─────────────────────┐
       User Input       │                     │
      ────────────────▶ │       START         │
                        │                     │
                        └──────────┬──────────┘
                                   │
                   ┌───────────────┴───────────────┐
                   │                               │
                   ▼                               ▼
        ┌──────────────────┐            ┌──────────────────┐
        │   TRANSLATOR     │            │   SUMMARIZER     │
        │                  │            │                  │
        │  🇫🇷 French       │            │  📝 One sentence │
        │     Translation  │            │     Summary      │
        └─────────┬────────┘            └─────────┬────────┘
                  │                               │
                  └───────────────┬───────────────┘
                                  │
                                  ▼
                        ┌─────────────────────┐
                        │      COMBINE        │
                        │                     │
                        │  📋 Merge Results   │
                        └──────────┬──────────┘
                                   │
                                   ▼
                        ┌─────────────────────┐
                        │        END          │
                        │                     │
                        │   ✅ Complete       │
                        └─────────────────────┘

核心概念：

Nodes - 执行工作的处理单元（LlmAgent、函数或自定义逻辑）
Edges - 节点之间的控制流（静态连接或条件路由）
State - 在图中流动并在节点之间持久化的共享数据
并行执行 - 多个节点可以同时运行以获得更好的性能

理解核心组件

🔧 Nodes: 工作者 Nodes 是实际工作发生的地方。每个节点可以：

AgentNode: 封装一个 LlmAgent 来处理自然语言
Function Node: 执行自定义 Rust 代码进行数据处理
Built-in Nodes: 使用预定义逻辑，例如计数器或验证器

将 Nodes 想象成装配线上的专业工人——每个都有特定的工作和专长。

🔀 Edges: 流程控制 Edges 决定了执行如何在你的图中移动：

Static Edges: 直接连接（A → B → C）
Conditional Edges: 基于 State 的动态路由（if sentiment == "positive" → positive_handler）
Parallel Edges: 从一个节点出发的多条路径（START → [translator, summarizer]）

Edges 就像红绿灯和路标，指导着工作流。

💾 State: 共享内存 State 是一个键值存储，所有 Nodes 都可以从中读取和写入：

输入数据: 馈入图中的初始信息
中间结果: 一个节点的输出成为另一个节点的输入
最终输出: 所有处理完成后的最终结果

State 就像一个共享白板，Nodes 可以在上面留下信息供其他节点使用。

⚡ 并行执行: 速度提升 当多个 Edges 离开一个节点时，那些目标节点会同时运行：

更快的处理速度: 独立任务同时运行
资源效率: 更好地利用 CPU 和 I/O
可扩展性: 处理更复杂的工作流而不会出现线性减速

这就像让多名工人同时处理一项工作的不同部分，而不是排队等待。

快速开始

1. 创建你的项目

cargo new graph_demo
cd graph_demo

将依赖项添加到 Cargo.toml：

[dependencies]
adk-graph = { version = "0.2", features = ["sqlite"] }
adk-agent = "0.2"
adk-model = "0.2"
adk-core = "0.2"
tokio = { version = "1", features = ["full"] }
dotenvy = "0.15"
serde_json = "1.0"

使用你的 API key 创建 .env 文件：

echo 'GOOGLE_API_KEY=your-api-key' > .env

2. 并行处理示例

这是一个完整的并行处理文本的工作示例：

use adk_agent::LlmAgentBuilder;
use adk_graph::{
    agent::GraphAgent,
    edge::{END, START},
    node::{AgentNode, ExecutionConfig, NodeOutput},
    state::State,
};
use adk_model::GeminiModel;
use serde_json::json;
use std::sync::Arc;

#[tokio::main]
async fn main() -> anyhow::Result<()> {
    dotenvy::dotenv().ok();
    let api_key = std::env::var("GOOGLE_API_KEY")?;
    let model = Arc::new(GeminiModel::new(&api_key, "gemini-2.0-flash")?);

    // Create specialized LLM agents
    let translator_agent = Arc::new(
        LlmAgentBuilder::new("translator")
            .description("Translates text to French")
            .model(model.clone())
            .instruction("Translate the input text to French. Only output the translation.")
            .build()?,
    );

    let summarizer_agent = Arc::new(
        LlmAgentBuilder::new("summarizer")
            .description("Summarizes text")
            .model(model.clone())
            .instruction("Summarize the input text in one sentence.")
            .build()?,
    );

    // Wrap agents as graph nodes with input/output mappers
    let translator_node = AgentNode::new(translator_agent)
        .with_input_mapper(|state| {
            let text = state.get("input").and_then(|v| v.as_str()).unwrap_or("");
            adk_core::Content::new("user").with_text(text)
        })
        .with_output_mapper(|events| {
            let mut updates = std::collections::HashMap::new();
            for event in events {
                if let Some(content) = event.content() {
                    let text: String = content.parts.iter()
                        .filter_map(|p| p.text())
                        .collect::<Vec<_>>()
                        .join("");
                    if !text.is_empty() {
                        updates.insert("translation".to_string(), json!(text));
                    }
                }
            }
            updates
        });

    let summarizer_node = AgentNode::new(summarizer_agent)
        .with_input_mapper(|state| {
            let text = state.get("input").and_then(|v| v.as_str()).unwrap_or("");
            adk_core::Content::new("user").with_text(text)
        })
        .with_output_mapper(|events| {
            let mut updates = std::collections::HashMap::new();
            for event in events {
                if let Some(content) = event.content() {
                    let text: String = content.parts.iter()
                        .filter_map(|p| p.text())
                        .collect::<Vec<_>>()
                        .join("");
                    if !text.is_empty() {
                        updates.insert("summary".to_string(), json!(text));
                    }
                }
            }
            updates
        });

    // Build the graph with parallel execution
    let agent = GraphAgent::builder("text_processor")
        .description("Processes text with translation and summarization in parallel")
        .channels(&["input", "translation", "summary", "result"])
        .node(translator_node)
        .node(summarizer_node)
        .node_fn("combine", |ctx| async move {
            let translation = ctx.get("translation").and_then(|v| v.as_str()).unwrap_or("N/A");
            let summary = ctx.get("summary").and_then(|v| v.as_str()).unwrap_or("N/A");

            let result = format!(
                "=== Processing Complete ===\n\n\
                French Translation:\n{}\n\n\
                Summary:\n{}",
                translation, summary
            );

            Ok(NodeOutput::new().with_update("result", json!(result)))
        })
        // Parallel execution: both nodes start simultaneously
        .edge(START, "translator")
        .edge(START, "summarizer")
        .edge("translator", "combine")
        .edge("summarizer", "combine")
        .edge("combine", END)
        .build()?;

    // Execute the graph
    let mut input = State::new();
    input.insert("input".to_string(), json!("AI is transforming how we work and live."));

    let result = agent.invoke(input, ExecutionConfig::new("thread-1")).await?;
    println!("{}", result.get("result").and_then(|v| v.as_str()).unwrap_or(""));

    Ok(())
}

示例输出:

=== Processing Complete ===

French Translation:
L'IA transforme notre façon de travailler et de vivre.

Summary:
AI is revolutionizing work and daily life through technological transformation.

图执行机制

宏观视图

Graph agents 以 超级步骤 的方式执行——所有就绪的节点并行运行，然后图等待所有节点完成，再进入下一步：

Step 1: START ──┬──▶ translator (running)
                └──▶ summarizer (running)
                
                ⏳ Wait for both to complete...
                
Step 2: translator ──┬──▶ combine (running)
        summarizer ──┘
        
                ⏳ Wait for combine to complete...
                
Step 3: combine ──▶ END ✅

状态在节点间的流动

每个节点都可以读取和写入共享状态：

┌─────────────────────────────────────────────────────────────────────┐
│ STEP 1: 初始状态                                                    │
├─────────────────────────────────────────────────────────────────────┤
│                                                                     │
│   State: { "input": "AI is transforming how we work" }             │
│                                                                     │
│                              ↓                                      │
│                                                                     │
│   ┌──────────────────┐              ┌──────────────────┐           │
│   │   translator     │              │   summarizer     │           │
│   │  读取 "input"    │              │  读取 "input"    │           │
│   └──────────────────┘              └──────────────────┘           │
│                                                                     │
└─────────────────────────────────────────────────────────────────────┘
                              ↓
┌─────────────────────────────────────────────────────────────────────┐
│ STEP 2: 并行执行后                                                  │
├─────────────────────────────────────────────────────────────────────┤
│                                                                     │
│   State: {                                                          │
│     "input": "AI is transforming how we work",                     │
│     "translation": "L'IA transforme notre façon de travailler",    │
│     "summary": "AI is revolutionizing work through technology"     │
│   }                                                                 │
│                                                                     │
│                              ↓                                      │
│                                                                     │
│   ┌──────────────────────────────────────┐                         │
│   │           combine                    │                         │
│   │  读取 "translation" + "summary"      │                         │
│   │  写入 "result"                     │                         │
│   └──────────────────────────────────────┘                         │
│                                                                     │
└─────────────────────────────────────────────────────────────────────┘
                              ↓
┌─────────────────────────────────────────────────────────────────────┐
│ STEP 3: 最终状态                                                    │
├─────────────────────────────────────────────────────────────────────┤
│                                                                     │
│   State: {                                                          │
│     "input": "AI is transforming how we work",                     │
│     "translation": "L'IA transforme notre façon de travailler",    │
│     "summary": "AI is revolutionizing work through technology",    │
│     "result": "=== Processing Complete ===\n\nFrench..."          │
│   }                                                                 │
│                                                                     │
└─────────────────────────────────────────────────────────────────────┘

工作原理

Component	Role
`AgentNode`	使用输入/输出映射器封装 LLM agents
`input_mapper`	将状态转换为 agent input `Content`
`output_mapper`	将 agent 事件转换为状态更新
`channels`	声明图将使用的状态字段
`edge()`	定义节点之间的执行流
`ExecutionConfig`	提供用于检查点的线程 ID

使用 LLM 分类实现条件路由

构建智能路由系统，让 LLM 决定执行路径：

可视化：基于情感的路由

                        ┌─────────────────────┐
       User Feedback    │                     │
      ────────────────▶ │    CLASSIFIER       │
                        │  🧠 Analyze tone    │
                        └──────────┬──────────┘
                                   │
                   ┌───────────────┼───────────────┐
                   │               │               │
                   ▼               ▼               ▼
        ┌──────────────────┐ ┌──────────────────┐ ┌──────────────────┐
        │   POSITIVE       │ │    NEGATIVE      │ │    NEUTRAL       │
        │                  │ │                  │ │                  │
        │  😊 Thank you!   │ │  😔 Apologize    │ │  😐 Ask more     │
        │     Celebrate    │ │     Help fix     │ │     questions    │
        └──────────────────┘ └──────────────────┘ └──────────────────┘

完整示例代码

use adk_agent::LlmAgentBuilder;
use adk_graph::{
    edge::{END, Router, START},
    graph::StateGraph,
    node::{AgentNode, ExecutionConfig},
    state::State,
};
use adk_model::GeminiModel;
use serde_json::json;
use std::sync::Arc;

#[tokio::main]
async fn main() -> anyhow::Result<()> {
    dotenvy::dotenv().ok();
    let api_key = std::env::var("GOOGLE_API_KEY")?;
    let model = Arc::new(GeminiModel::new(&api_key, "gemini-2.0-flash")?);

    // Create classifier agent
    let classifier_agent = Arc::new(
        LlmAgentBuilder::new("classifier")
            .description("Classifies text sentiment")
            .model(model.clone())
            .instruction(
                "You are a sentiment classifier. Analyze the input text and respond with \
                ONLY one word: 'positive', 'negative', or 'neutral'. Nothing else.",
            )
            .build()?,
    );

    // Create response agents for each sentiment
    let positive_agent = Arc::new(
        LlmAgentBuilder::new("positive")
            .description("Handles positive feedback")
            .model(model.clone())
            .instruction(
                "You are a customer success specialist. The customer has positive feedback. \
                Express gratitude, reinforce the positive experience, and suggest ways to \
                share their experience. Be warm and appreciative. Keep response under 3 sentences.",
            )
            .build()?,
    );

    let negative_agent = Arc::new(
        LlmAgentBuilder::new("negative")
            .description("Handles negative feedback")
            .model(model.clone())
            .instruction(
                "You are a customer support specialist. The customer has a complaint. \
                Acknowledge their frustration, apologize sincerely, and offer help. \
                Be empathetic. Keep response under 3 sentences.",
            )
            .build()?,
    );

    let neutral_agent = Arc::new(
        LlmAgentBuilder::new("neutral")
            .description("Handles neutral feedback")
            .model(model.clone())
            .instruction(
                "You are a customer service representative. The customer has neutral feedback. \
                Ask clarifying questions to better understand their needs. Be helpful and curious. \
                Keep response under 3 sentences.",
            )
            .build()?,
    );

    // Create AgentNodes with mappers
    let classifier_node = AgentNode::new(classifier_agent)
        .with_input_mapper(|state| {
            let text = state.get("feedback").and_then(|v| v.as_str()).unwrap_or("");
            adk_core::Content::new("user").with_text(text)
        })
        .with_output_mapper(|events| {
            let mut updates = std::collections::HashMap::new();
            for event in events {
                if let Some(content) = event.content() {
                    let text: String = content.parts.iter()
                        .filter_map(|p| p.text())
                        .collect::<Vec<_>>()
                        .join("")
                        .to_lowercase()
                        .trim()
                        .to_string();
                    
                    let sentiment = if text.contains("positive") { "positive" }
                        else if text.contains("negative") { "negative" }
                        else { "neutral" };
                    
                    updates.insert("sentiment".to_string(), json!(sentiment));
                }
            }
            updates
        });

    // Response nodes (similar pattern for each)
    let positive_node = AgentNode::new(positive_agent)
        .with_input_mapper(|state| {
            let text = state.get("feedback").and_then(|v| v.as_str()).unwrap_or("");
            adk_core::Content::new("user").with_text(text)
        })
        .with_output_mapper(|events| {
            let mut updates = std::collections::HashMap::new();
            for event in events {
                if let Some(content) = event.content() {
                    let text: String = content.parts.iter()
                        .filter_map(|p| p.text())
                        .collect::<Vec<_>>()
                        .join("");
                    updates.insert("response".to_string(), json!(text));
                }
            }
            updates
        });

    // Build graph with conditional routing
    let graph = StateGraph::with_channels(&["feedback", "sentiment", "response"])
        .add_node(classifier_node)
        .add_node(positive_node)
        // ... add negative_node and neutral_node similarly
        .add_edge(START, "classifier")
        .add_conditional_edges(
            "classifier",
            Router::by_field("sentiment"),  // Route based on sentiment field
            [
                ("positive", "positive"),
                ("negative", "negative"),
                ("neutral", "neutral"),
            ],
        )
        .add_edge("positive", END)
        .add_edge("negative", END)
        .add_edge("neutral", END)
        .compile()?;

    // Test with different feedback
    let mut input = State::new();
    input.insert("feedback".to_string(), json!("Your product is amazing! I love it!"));

    let result = graph.invoke(input, ExecutionConfig::new("feedback-1")).await?;
    println!("Sentiment: {}", result.get("sentiment").and_then(|v| v.as_str()).unwrap_or(""));
    println!("Response: {}", result.get("response").and_then(|v| v.as_str()).unwrap_or(""));

    Ok(())
}

示例流程：

Input: "Your product is amazing! I love it!"
       ↓
Classifier: "positive"
       ↓
Positive Agent: "Thank you so much for the wonderful feedback! 
                We're thrilled you love our product. 
                Would you consider leaving a review to help others?"

ReAct 模式：推理 + 行动

构建能够迭代使用工具来解决复杂问题的 Agent：

视觉：ReAct 循环

                        ┌─────────────────────┐
       User Question    │                     │
      ────────────────▶ │      REASONER       │
                        │  🧠 Think + Act     │
                        └──────────┬──────────┘
                                   │
                                   ▼
                        ┌─────────────────────┐
                        │   Has tool calls?   │
                        │                     │
                        └──────────┬──────────┘
                                   │
                   ┌───────────────┴───────────────┐
                   │                               │
                   ▼                               ▼
        ┌──────────────────┐            ┌──────────────────┐
        │       YES        │            │        NO         │
        │                  │            │                   │
        │  🔄 Loop back    │            │  ✅ Final answer  │
        │     to reasoner  │            │      END          │
        └─────────┬────────┘            └───────────────────┘
                  │
                  └─────────────────┐
                                    │
                                    ▼
                        ┌─────────────────────┐
                        │      REASONER       │
                        │  🧠 Think + Act     │
                        │   (next iteration)  │
                        └─────────────────────┘

完整的 ReAct 示例

use adk_agent::LlmAgentBuilder;
use adk_core::{Part, Tool};
use adk_graph::{
    edge::{END, START},
    graph::StateGraph,
    node::{AgentNode, ExecutionConfig, NodeOutput},
    state::State,
};
use adk_model::GeminiModel;
use adk_tool::FunctionTool;
use serde_json::json;
use std::sync::Arc;

#[tokio::main]
async fn main() -> anyhow::Result<()> {
    dotenvy::dotenv().ok();
    let api_key = std::env::var("GOOGLE_API_KEY")?;
    let model = Arc::new(GeminiModel::new(&api_key, "gemini-2.0-flash")?);

    // Create tools
    let weather_tool = Arc::new(FunctionTool::new(
        "get_weather",
        "Get the current weather for a location. Takes a 'location' parameter (city name).",
        |_ctx, args| async move {
            let location = args.get("location").and_then(|v| v.as_str()).unwrap_or("unknown");
            Ok(json!({
                "location": location,
                "temperature": "72°F",
                "condition": "Sunny",
                "humidity": "45%"
            }))
        },
    )) as Arc<dyn Tool>;

    let calculator_tool = Arc::new(FunctionTool::new(
        "calculator",
        "Perform mathematical calculations. Takes an 'expression' parameter (string).",
        |_ctx, args| async move {
            let expr = args.get("expression").and_then(|v| v.as_str()).unwrap_or("0");
            let result = match expr {
                "2 + 2" => "4",
                "10 * 5" => "50",
                "100 / 4" => "25",
                "15 - 7" => "8",
                _ => "Unable to evaluate",
            };
            Ok(json!({ "result": result, "expression": expr }))
        },
    )) as Arc<dyn Tool>;

    // Create reasoner agent with tools
    let reasoner_agent = Arc::new(
        LlmAgentBuilder::new("reasoner")
            .description("Reasoning agent with tools")
            .model(model.clone())
            .instruction(
                "You are a helpful assistant with access to tools. Use tools when needed to answer questions. \
                When you have enough information, provide a final answer without using more tools.",
            )
            .tool(weather_tool)
            .tool(calculator_tool)
            .build()?,
    );

    // Create reasoner node that detects tool usage
    let reasoner_node = AgentNode::new(reasoner_agent)
        .with_input_mapper(|state| {
            let question = state.get("question").and_then(|v| v.as_str()).unwrap_or("");
            adk_core::Content::new("user").with_text(question)
        })
        .with_output_mapper(|events| {
            let mut updates = std::collections::HashMap::new();
            let mut has_tool_calls = false;
            let mut response = String::new();

            for event in events {
                if let Some(content) = event.content() {
                    for part in &content.parts {
                        match part {
                            Part::FunctionCall { .. } => {
                                has_tool_calls = true;
                            }
                            Part::Text { text } => {
                                response.push_str(text);
                            }
                            _ => {}
                        }
                    }
                }
            }

            updates.insert("has_tool_calls".to_string(), json!(has_tool_calls));
            updates.insert("response".to_string(), json!(response));
            updates
        });

    // Build ReAct graph with cycle
    let graph = StateGraph::with_channels(&["question", "has_tool_calls", "response", "iteration"])
        .add_node(reasoner_node)
        .add_node_fn("counter", |ctx| async move {
            let i = ctx.get("iteration").and_then(|v| v.as_i64()).unwrap_or(0);
            Ok(NodeOutput::new().with_update("iteration", json!(i + 1)))
        })
        .add_edge(START, "counter")
        .add_edge("counter", "reasoner")
        .add_conditional_edges(
            "reasoner",
            |state| {
                let has_tools = state.get("has_tool_calls").and_then(|v| v.as_bool()).unwrap_or(false);
                let iteration = state.get("iteration").and_then(|v| v.as_i64()).unwrap_or(0);

                // Safety limit
                if iteration >= 5 { return END.to_string(); }

                if has_tools {
                    "counter".to_string()  // Loop back for more reasoning
                } else {
                    END.to_string()  // Done - final answer
                }
            },
            [("counter", "counter"), (END, END)],
        )
        .compile()?
        .with_recursion_limit(10);

    // Test the ReAct agent
    let mut input = State::new();
    input.insert("question".to_string(), json!("What's the weather in Paris and what's 15 + 25?"));

    let result = graph.invoke(input, ExecutionConfig::new("react-1")).await?;
    println!("Final answer: {}", result.get("response").and_then(|v| v.as_str()).unwrap_or(""));
    println!("Iterations: {}", result.get("iteration").and_then(|v| v.as_i64()).unwrap_or(0));

    Ok(())
}

示例流程：

Question: "What's the weather in Paris and what's 15 + 25?"

Iteration 1:
  Reasoner: "I need to get weather info and do math"
  → Calls get_weather(location="Paris") and calculator(expression="15 + 25")
  → has_tool_calls = true → Loop back

Iteration 2:
  Reasoner: "Based on the results: Paris is 72°F and sunny, 15 + 25 = 40"
  → No tool calls → has_tool_calls = false → END

Final Answer: "The weather in Paris is 72°F and sunny with 45% humidity. 
              And 15 + 25 equals 40."

AgentNode

将任何 ADK Agent（通常是 LlmAgent）封装为图节点：

let node = AgentNode::new(llm_agent)
    .with_input_mapper(|state| {
        // Transform graph state to agent input Content
        let text = state.get("input").and_then(|v| v.as_str()).unwrap_or("");
        adk_core::Content::new("user").with_text(text)
    })
    .with_output_mapper(|events| {
        // Transform agent events to state updates
        let mut updates = std::collections::HashMap::new();
        for event in events {
            if let Some(content) = event.content() {
                let text: String = content.parts.iter()
                    .filter_map(|p| p.text())
                    .collect::<Vec<_>>()
                    .join("");
                updates.insert("output".to_string(), json!(text));
            }
        }
        updates
    });

功能节点

处理状态的简单 async 函数：

.node_fn("process", |ctx| async move {
    let input = ctx.state.get("input").unwrap();
    let output = process_data(input).await?;
    Ok(NodeOutput::new().with_update("output", output))
})

边类型

静态边

节点之间的直接连接：

.edge(START, "first_node")
.edge("first_node", "second_node")
.edge("second_node", END)

条件边

基于状态的动态路由：

.conditional_edge(
    "router",
    |state| {
        match state.get("next").and_then(|v| v.as_str()) {
            Some("research") => "research_node".to_string(),
            Some("write") => "write_node".to_string(),
            _ => END.to_string(),
        }
    },
    [
        ("research_node", "research_node"),
        ("write_node", "write_node"),
        (END, END),
    ],
)

路由器助手

使用内置路由器实现常见模式：

use adk_graph::edge::Router;

// 根据状态字段值进行路由
.conditional_edge("classifier", Router::by_field("sentiment"), [
    ("positive", "positive_handler"),
    ("negative", "negative_handler"),
    ("neutral", "neutral_handler"),
])

// 根据布尔字段进行路由
.conditional_edge("check", Router::by_bool("approved"), [
    ("true", "execute"),
    ("false", "reject"),
])

// 限制迭代次数
.conditional_edge("loop", Router::max_iterations("count", 5), [
    ("continue", "process"),
    ("done", END),
])

并行执行

来自单个节点的多个边并行执行：

let agent = GraphAgent::builder("parallel_processor")
    .channels(&["input", "translation", "summary", "analysis"])
    .node(translator_node)
    .node(summarizer_node)
    .node(analyzer_node)
    .node(combiner_node)
    // 三个同时启动
    .edge(START, "translator")
    .edge(START, "summarizer")
    .edge(START, "analyzer")
    // 等待所有完成后再合并
    .edge("translator", "combiner")
    .edge("summarizer", "combiner")
    .edge("analyzer", "combiner")
    .edge("combiner", END)
    .build()?;

循环图 (ReAct 模式)

构建具有循环的迭代推理 Agent：

use adk_core::Part;

// Create agent with tools
let reasoner = Arc::new(
    LlmAgentBuilder::new("reasoner")
        .model(model)
        .instruction("Use tools to answer questions. Provide final answer when done.")
        .tool(search_tool)
        .tool(calculator_tool)
        .build()?
);

let reasoner_node = AgentNode::new(reasoner)
    .with_input_mapper(|state| {
        let question = state.get("question").and_then(|v| v.as_str()).unwrap_or("");
        adk_core::Content::new("user").with_text(question)
    })
    .with_output_mapper(|events| {
        let mut updates = std::collections::HashMap::new();
        let mut has_tool_calls = false;
        let mut response = String::new();

        for event in events {
            if let Some(content) = event.content() {
                for part in &content.parts {
                    match part {
                        Part::FunctionCall { name, .. } => {
                            has_tool_calls = true;
                        }
                        Part::Text { text } => {
                            response.push_str(text);
                        }
                        _ => {}
                    }
                }
            }
        }

        updates.insert("has_tool_calls".to_string(), json!(has_tool_calls));
        updates.insert("response".to_string(), json!(response));
        updates
    });

// Build graph with cycle
let react_agent = StateGraph::with_channels(&["question", "has_tool_calls", "response", "iteration"])
    .add_node(reasoner_node)
    .add_node_fn("counter", |ctx| async move {
        let i = ctx.get("iteration").and_then(|v| v.as_i64()).unwrap_or(0);
        Ok(NodeOutput::new().with_update("iteration", json!(i + 1)))
    })
    .add_edge(START, "counter")
    .add_edge("counter", "reasoner")
    .add_conditional_edges(
        "reasoner",
        |state| {
            let has_tools = state.get("has_tool_calls").and_then(|v| v.as_bool()).unwrap_or(false);
            let iteration = state.get("iteration").and_then(|v| v.as_i64()).unwrap_or(0);

            // Safety limit
            if iteration >= 5 { return END.to_string(); }

            if has_tools {
                "counter".to_string()  // Loop back
            } else {
                END.to_string()  // Done
            }
        },
        [("counter", "counter"), (END, END)],
    )
    .compile()?
    .with_recursion_limit(10);

多智能体主管

将任务路由给专业智能体：

// Create supervisor agent
let supervisor = Arc::new(
    LlmAgentBuilder::new("supervisor")
        .model(model.clone())
        .instruction("Route tasks to: researcher, writer, or coder. Reply with agent name only.")
        .build()?
);

let supervisor_node = AgentNode::new(supervisor)
    .with_output_mapper(|events| {
        let mut updates = std::collections::HashMap::new();
        for event in events {
            if let Some(content) = event.content() {
                let text: String = content.parts.iter()
                    .filter_map(|p| p.text())
                    .collect::<Vec<_>>()
                    .join("")
                    .to_lowercase();

                let next = if text.contains("researcher") { "researcher" }
                    else if text.contains("writer") { "writer" }
                    else if text.contains("coder") { "coder" }
                    else { "done" };

                updates.insert("next_agent".to_string(), json!(next));
            }
        }
        updates
    });

// Build supervisor graph
let graph = StateGraph::with_channels(&["task", "next_agent", "research", "content", "code"])
    .add_node(supervisor_node)
    .add_node(researcher_node)
    .add_node(writer_node)
    .add_node(coder_node)
    .add_edge(START, "supervisor")
    .add_conditional_edges(
        "supervisor",
        Router::by_field("next_agent"),
        [
            ("researcher", "researcher"),
            ("writer", "writer"),
            ("coder", "coder"),
            ("done", END),
        ],
    )
    // Agents report back to supervisor
    .add_edge("researcher", "supervisor")
    .add_edge("writer", "supervisor")
    .add_edge("coder", "supervisor")
    .compile()?;

状态管理

带有 Reducer 的状态模式

控制状态更新的合并方式：

let schema = StateSchema::builder()
    .channel("current_step")                    // Overwrite (default)
    .list_channel("messages")                   // Append to list
    .channel_with_reducer("count", Reducer::Sum) // Sum values
    .channel_with_reducer("data", Reducer::Custom(Arc::new(|old, new| {
        // Custom merge logic
        merge_json(old, new)
    })))
    .build();

let agent = GraphAgent::builder("stateful")
    .state_schema(schema)
    // ... nodes and edges
    .build()?;

Reducer 类型

Reducer	行为
`Overwrite`	用新值替换旧值（默认）
`Append`	追加到列表中
`Sum`	累加数值
`Custom`	自定义合并函数

检查点

启用持久化状态以实现容错和人机协作：

内存中（开发环境）

use adk_graph::checkpoint::MemoryCheckpointer;

let checkpointer = Arc::new(MemoryCheckpointer::new());

let graph = StateGraph::with_channels(&["task", "result"])
    // ... nodes and edges
    .compile()?
    .with_checkpointer_arc(checkpointer.clone());

SQLite（生产环境）

use adk_graph::checkpoint::SqliteCheckpointer;

let checkpointer = SqliteCheckpointer::new("checkpoints.db").await?;

let graph = StateGraph::with_channels(&["task", "result"])
    // ... nodes and edges
    .compile()?
    .with_checkpointer(checkpointer);

检查点历史（时间旅行）

// List all checkpoints for a thread
let checkpoints = checkpointer.list("thread-id").await?;
for cp in checkpoints {
    println!("Step {}: {:?}", cp.step, cp.state.get("status"));
}

// Load a specific checkpoint
if let Some(checkpoint) = checkpointer.load_by_id(&checkpoint_id).await? {
    println!("State at step {}: {:?}", checkpoint.step, checkpoint.state);
}

人机协作

使用动态中断暂停执行以待人工批准：

use adk_graph::{error::GraphError, node::NodeOutput};

// Planner agent assesses risk
let planner_node = AgentNode::new(planner_agent)
    .with_output_mapper(|events| {
        let mut updates = std::collections::HashMap::new();
        for event in events {
            if let Some(content) = event.content() {
                let text: String = content.parts.iter()
                    .filter_map(|p| p.text())
                    .collect::<Vec<_>>()
                    .join("");

                // Extract risk level from LLM response
                let risk = if text.to_lowercase().contains("risk: high") { "high" }
                    else if text.to_lowercase().contains("risk: medium") { "medium" }
                    else { "low" };

                updates.insert("plan".to_string(), json!(text));
                updates.insert("risk_level".to_string(), json!(risk));
            }
        }
        updates
    });

// Review node with dynamic interrupt
let graph = StateGraph::with_channels(&["task", "plan", "risk_level", "approved", "result"])
    .add_node(planner_node)
    .add_node(executor_node)
    .add_node_fn("review", |ctx| async move {
        let risk = ctx.get("risk_level").and_then(|v| v.as_str()).unwrap_or("low");
        let approved = ctx.get("approved").and_then(|v| v.as_bool());

        // Already approved - continue
        if approved == Some(true) {
            return Ok(NodeOutput::new());
        }

        // High/medium risk - interrupt for approval
        if risk == "high" || risk == "medium" {
            return Ok(NodeOutput::interrupt_with_data(
                &format!("{} RISK: Human approval required", risk.to_uppercase()),
                json!({
                    "plan": ctx.get("plan"),
                    "risk_level": risk,
                    "action": "Set 'approved' to true to continue"
                })
            ));
        }

        // Low risk - auto-approve
        Ok(NodeOutput::new().with_update("approved", json!(true)))
    })
    .add_edge(START, "planner")
    .add_edge("planner", "review")
    .add_edge("review", "executor")
    .add_edge("executor", END)
    .compile()?
    .with_checkpointer_arc(checkpointer.clone());

// Execute - may pause for approval
let thread_id = "task-001";
let result = graph.invoke(input, ExecutionConfig::new(thread_id)).await;

match result {
    Err(GraphError::Interrupted(interrupt)) => {
        println!("*** EXECUTION PAUSED ***");
        println!("Reason: {}", interrupt.interrupt);
        println!("Plan awaiting approval: {:?}", interrupt.state.get("plan"));

        // Human reviews and approves...

        // Update state with approval
        graph.update_state(thread_id, [("approved".to_string(), json!(true))]).await?;

        // Resume execution
        let final_result = graph.invoke(State::new(), ExecutionConfig::new(thread_id)).await?;
        println!("Final result: {:?}", final_result.get("result"));
    }
    Ok(result) => {
        println!("Completed without interrupt: {:?}", result);
    }
    Err(e) => {
        println!("Error: {}", e);
    }
}

静态中断

使用 interrupt_before 或 interrupt_after 设置强制暂停点：

let graph = StateGraph::with_channels(&["task", "plan", "result"])
    .add_node(planner_node)
    .add_node(executor_node)
    .add_edge(START, "planner")
    .add_edge("planner", "executor")
    .add_edge("executor", END)
    .compile()?
    .with_interrupt_before(&["executor"]);  // Always pause before execution

流式执行

在图执行时流式传输事件：

use futures::StreamExt;
use adk_graph::stream::StreamMode;

let stream = agent.stream(input, config, StreamMode::Updates);

while let Some(event) = stream.next().await {
    match event? {
        StreamEvent::NodeStart(name) => println!("Starting: {}", name),
        StreamEvent::Updates { node, updates } => {
            println!("{} updated state: {:?}", node, updates);
        }
        StreamEvent::NodeEnd(name) => println!("Completed: {}", name),
        StreamEvent::Done(state) => println!("Final state: {:?}", state),
        _ => {}
    }
}

流模式

Mode	Description
`Values`	在每个节点后流式传输完整状态
`Updates`	仅流式传输状态更改
`Messages`	流式传输消息类型更新
`Debug`	流式传输所有内部事件

ADK 集成

GraphAgent 实现了 ADK Agent trait，因此它支持：

Runner: 配合 adk-runner 进行标准执行
Callbacks: 全面支持前/后回调
Sessions: 配合 adk-session 记录会话历史
Streaming: 返回 ADK EventStream

use adk_runner::Runner;

let graph_agent = GraphAgent::builder("workflow")
    .before_agent_callback(|ctx| async {
        println!("Starting graph execution for session: {}", ctx.session_id());
        Ok(())
    })
    .after_agent_callback(|ctx, event| async {
        if let Some(content) = event.content() {
            println!("Graph completed with content");
        }
        Ok(())
    })
    // ... graph definition
    .build()?;

// GraphAgent implements Agent trait - use with Launcher or Runner
// See adk-runner README for Runner configuration

示例

所有示例都使用 AgentNode 与真实 LlmAgent 的集成：

# Parallel LLM agents with before/after callbacks
cargo run --example graph_agent

# Sequential multi-agent pipeline (extractor → analyzer → formatter)
cargo run --example graph_workflow

# LLM-based sentiment classification and conditional routing
cargo run --example graph_conditional

# ReAct pattern with tools and cyclic execution
cargo run --example graph_react

# Multi-agent supervisor routing to specialists
cargo run --example graph_supervisor

# Human-in-the-loop with risk-based interrupts
cargo run --example graph_hitl

# Checkpointing and time travel debugging
cargo run --example graph_checkpoint

与 LangGraph 的比较

Feature	LangGraph	adk-graph
状态管理	TypedDict + Reducers	StateSchema + Reducers
执行模型	Pregel super-steps	Pregel super-steps
检查点	Memory, SQLite, Postgres	Memory, SQLite
人机协作	interrupt_before/after	interrupt_before/after + dynamic
流式传输	5 modes	5 modes
循环	原生支持	原生支持
类型安全	Python typing	Rust type system
LlmAgent 集成	LangChain	AgentNode + ADK agents

Previous: ← 多智能体系统 | Next: 实时智能体 →