开发指南

本文档为参与 ADK-Rust 开发的开发者提供全面指南。遵循这些标准可确保整个项目的代码质量、一致性和可维护性。

目录

快速入门

前提条件

  • Rust:1.95.0 或更高版本(2024 edition,使用 rustc --version 检查)
  • Cargo:最新稳定版
  • Git:用于版本控制
  • sccache(推荐):编译缓存,可将重建时间缩短约 70%

配置你的环境

# Clone the repository
git clone https://github.com/zavora-ai/adk-rust.git
cd adk-rust

# Option A: Nix/devenv (reproducible — identical on Linux, macOS, CI)
devenv shell

# Option B: Setup script (installs sccache, cmake, etc.)
./scripts/setup-dev.sh

# Option C: Manual
cargo build

# Install cargo-nextest (parallel test runner, ~10x faster)
curl -LsSf https://get.nexte.st/latest/mac | tar zxf - -C ${CARGO_HOME:-~/.cargo}/bin

# Run all tests
cargo nextest run --workspace

# Check for lints
cargo clippy --all-targets --all-features

# Format code
cargo fmt --all

环境变量

用于运行需要 API 密钥的示例和测试:

# Gemini (default provider)
export GOOGLE_API_KEY="your-api-key"

# OpenAI (optional)
export OPENAI_API_KEY="your-api-key"

# Anthropic (optional)
export ANTHROPIC_API_KEY="your-api-key"

项目结构

ADK-Rust 采用包含多个 crate 的 Cargo 工作区组织:

adk-rust/
├── adk-core/       # Foundational traits and types (Agent, Tool, Llm, Event)
├── adk-telemetry/  # OpenTelemetry integration
├── adk-model/      # LLM providers (Gemini, OpenAI, Anthropic)
├── adk-tool/       # Tool system (FunctionTool, MCP, AgentTool)
├── adk-session/    # Session management (in-memory, SQLite)
├── adk-artifact/   # Binary artifact storage
├── adk-memory/     # Long-term memory with search
├── adk-agent/      # Agent implementations (LlmAgent, workflow agents)
├── adk-runner/     # Execution runtime
├── adk-server/     # REST API and A2A protocol
├── adk-cli/        # Command-line launcher
├── adk-realtime/   # Voice/audio streaming agents
├── adk-graph/      # LangGraph-style workflows
├── adk-browser/    # Browser automation tools
├── adk-eval/       # Agent evaluation framework
├── adk-rust/       # Umbrella crate (re-exports all)
└── examples/       # Working examples

Crate 依赖关系

Crate 必须按依赖顺序发布:

  1. adk-core(无内部依赖)
  2. adk-telemetry
  3. adk-model
  4. adk-tool
  5. adk-session
  6. adk-artifact
  7. adk-memory
  8. adk-agent
  9. adk-runner
  10. adk-server
  11. adk-cli
  12. adk-realtime
  13. adk-graph
  14. adk-browser
  15. adk-eval
  16. adk-rust(总包)

代码风格

一般原则

  1. 清晰优先于巧妙:编写易于阅读和理解的代码
  2. 显式优先于隐式:优先使用显式类型和错误处理
  3. 小函数:保持函数聚焦,在可能的情况下控制在 50 行以内
  4. 有意义的命名:使用具有描述性的变量名和函数名

格式化

使用默认设置的 rustfmt

cargo fmt --all

CI 流水线会强制执行格式化。在提交之前务必运行 cargo fmt

命名约定

类型约定示例
Cratesadk-*(kebab-case)adk-core, adk-agent
模块snake_casellm_agent, function_tool
类型/特征PascalCaseLlmAgent, ToolContext
函数snake_caseexecute_tool, run_agent
常量SCREAMING_SNAKE_CASEKEY_PREFIX_APP
类型参数单个大写字母或 PascalCaseT, State

导入

按以下顺序组织导入:

// 1. Standard library
use std::collections::HashMap;
use std::sync::Arc;

// 2. External crates
use async_trait::async_trait;
use serde::{Deserialize, Serialize};
use tokio::sync::RwLock;

// 3. Internal crates (adk-*)
use adk_core::{Agent, Event, Result};

// 4. Local modules
use crate::config::Config;
use super::utils;

Clippy

所有代码必须通过 clippy 且无警告:

cargo clippy --all-targets --all-features

应修复 clippy 警告,而不是抑制它们。如果必须抑制,请说明原因:

#[allow(clippy::too_many_arguments)]
// Builder pattern requires many parameters; refactoring would hurt usability
fn complex_builder(...) { }

错误处理

结构化错误信封

AdkError 是一种结构化错误类型,包含组件(位置)、类别(什么类型)、代码(机器键)、消息(人类文本)、重试提示以及可选详情:

use adk_core::{AdkError, ErrorComponent, ErrorCategory, Result};

// Return Result<T> (aliased to Result<T, AdkError>)
pub async fn my_function() -> Result<String> {
    let data = fetch_data().await?;

    if data.is_empty() {
        return Err(AdkError::new(
            ErrorComponent::Tool,
            ErrorCategory::NotFound,
            "tool.data.not_found",
            "No data found for the given query",
        ));
    }

    Ok(data)
}

选择组件和类别

ErrorComponent 用于标识故障发生的位置(源子系统,而不是它所经过的 trait 边界):

组件使用场景
AgentAgent 编排,子 agent 分发
ModelLLM provider 调用,响应解析
Tool工具执行,参数验证
Session会话持久化,状态管理
Memory内存/RAG 操作
Graph图工作流执行
Auth身份验证、授权
ServerHTTP 服务器、配置

ErrorCategory 对出了什么问题进行分类:

分类HTTP适用时
InvalidInput400参数、配置、请求正文错误
Unauthorized401缺少或无效的凭据
Forbidden403凭证有效,但权限不足
NotFound404资源不存在
RateLimited429上游速率限制(可重试)
Timeout408操作超出时间限制(可重试)
Unavailable503上游服务不可用(可重试)
Cancelled499由调用方或系统取消
Internal500Bug,违反不变量
Unsupported501功能不受支持

便捷构造函数

对于常见模式:

// Structured (preferred for new code)
AdkError::not_found(ErrorComponent::Session, "session.not_found", "Session xyz not found")
AdkError::rate_limited(ErrorComponent::Model, "model.openai.rate_limited", "Too many requests")
AdkError::unauthorized(ErrorComponent::Auth, "auth.token_expired", "Bearer token expired")
AdkError::timeout(ErrorComponent::Tool, "tool.execution_timeout", "Tool timed out after 30s")

// Backward-compatible (for migration — produces .legacy codes)
AdkError::tool("No data found")
AdkError::model("Provider returned 500")
AdkError::session("Session not found")

构建器 API

附加结构化元数据,以提供更丰富的错误上下文:

let err = AdkError::new(
    ErrorComponent::Model,
    ErrorCategory::RateLimited,
    "model.openai.rate_limited",
    "OpenAI rate limit exceeded",
)
.with_provider("openai")
.with_upstream_status(429)
.with_request_id("req-abc123")
.with_retry(RetryHint {
    should_retry: true,
    retry_after_ms: Some(5000),
    max_attempts: Some(3),
});

重试提示

可重试类别(RateLimitedUnavailableTimeout)会自动设置 should_retry: true。使用 err.is_retryable() 检查是否可重试,它将 retry.should_retry 作为唯一事实来源:

if err.is_retryable() {
    if let Some(delay) = err.retry.retry_after() {
        tokio::time::sleep(delay).await;
    }
    // retry the operation
}

类别检查

err.is_retryable()    // retry.should_retry (RateLimited, Unavailable, Timeout by default)
err.is_not_found()    // category == NotFound
err.is_unauthorized() // category == Unauthorized
err.is_rate_limited() // category == RateLimited
err.is_timeout()      // category == Timeout

组件检查(向后兼容)

err.is_model()   // component == Model
err.is_tool()    // component == Tool
err.is_session() // component == Session
err.is_config()  // code == "config.legacy" (temporary bridge)

HTTP 状态和问题 JSON

AdkError 直接映射到 HTTP 响应:

let status = err.http_status_code(); // u16 based on category
let body = err.to_problem_json();    // structured JSON error body
// body: { "error": { "code", "message", "component", "category", "requestId", "retryAfter", ... } }

使用 From 实现的 crate 本地错误

具有领域特定错误的 crate 会实现 From<CrateLocalError> for AdkError

// In your crate
#[derive(Debug, thiserror::Error)]
pub enum MyToolError {
    #[error("connection failed: {0}")]
    ConnectionFailed(String),
    #[error("timeout after {0}ms")]
    Timeout(u64),
}

impl From<MyToolError> for AdkError {
    fn from(err: MyToolError) -> Self {
        let (category, code) = match &err {
            MyToolError::ConnectionFailed(_) => (ErrorCategory::Unavailable, "mytool.connection"),
            MyToolError::Timeout(_) => (ErrorCategory::Timeout, "mytool.timeout"),
        };
        AdkError::new(ErrorComponent::Tool, category, code, err.to_string())
            .with_source(err)
    }
}

不要提供通用 From 实现

std::io::Errorserde_json::Error 跨越了太多子系统边界,无法进行单一的通用转换。请针对正确的组件使用显式 map_err

// Good: explicit component and category
let data = std::fs::read_to_string(path)
    .map_err(|e| AdkError::new(
        ErrorComponent::Session,
        ErrorCategory::Internal,
        "session.io_read",
        format!("failed to read session file: {e}"),
    ).with_source(e))?;

// Good: for quick migration
let data = serde_json::from_str(&raw)
    .map_err(|e| AdkError::session(format!("JSON parse failed: {e}")))?;

错误信息

编写清晰、可操作的错误信息:

// Good: specific and actionable
AdkError::new(
    ErrorComponent::Model,
    ErrorCategory::InvalidInput,
    "model.missing_api_key",
    "API key not found. Set GOOGLE_API_KEY environment variable.",
)

// Bad: vague
AdkError::model("Invalid config")

库代码中不要 panic

库 crate 绝不能在可恢复错误上 panic。在 src/ 代码中避免使用 unwrap()expect()panic!()(测试代码除外)。

RwLock / Mutex:使用优雅降级来代替 unwrap()。锁被 poisoned 说明另一个线程发生了 panic——让当前线程也崩溃只会让情况更糟。

// Bad: panics if lock is poisoned
let state = self.state.write().unwrap();

// Good: log and return a safe default
let Ok(state) = self.state.write() else {
    tracing::error!("state lock poisoned — returning default");
    return Default::default();
};

// Good: recover through the poison (data may be stale but won't crash)
let state = self.state.read().unwrap_or_else(|e| e.into_inner());

构造函数:当初始化可能失败时返回 Result(例如连接外部服务)。

// Bad: panics if Docker is not running
pub fn new(config: Config) -> Self {
    let client = connect().expect("connection failed");
    Self { client }
}

// Good: caller decides how to handle the failure
pub fn new(config: Config) -> Result<Self, MyError> {
    let client = connect().map_err(|e| MyError::Init(e.to_string()))?;
    Ok(Self { client })
}

构建器方法:对于 Arc::get_mut(),使用 if let Some 而不是 expect()

// Bad: panics if Arc is shared
pub fn add_callback(mut self, cb: Callback) -> Self {
    Arc::get_mut(&mut self.callbacks).expect("not shared").push(cb);
    self
}

// Good: silent no-op (builder pattern guarantees single ownership)
pub fn add_callback(mut self, cb: Callback) -> Self {
    if let Some(callbacks) = Arc::get_mut(&mut self.callbacks) {
        callbacks.push(cb);
    }
    self
}

异步模式

使用 Tokio

所有异步代码都使用 Tokio 运行时:

use tokio::sync::{Mutex, RwLock};

// Prefer RwLock for read-heavy data
let state: Arc<RwLock<State>> = Arc::new(RwLock::new(State::default()));

// Use Mutex for write-heavy or simple cases
let counter: Arc<Mutex<u32>> = Arc::new(Mutex::new(0));

Tokio 特性约定

库 crate(adk-*)必须只声明它们实际使用的最小 tokio 特性:

# Library crates — minimal features
tokio = { workspace = true, features = ["rt", "sync", "time"] }

# Binary crates only (adk-cli, examples) — full is acceptable
tokio = { workspace = true, features = ["full"] }

在库 crate 中绝不要使用 features = ["full"]。这会迫使所有下游使用方无论是否需要,都编译 tokio 的每个子系统。

异步 trait

异步 trait 方法使用 async_trait

use async_trait::async_trait;

#[async_trait]
pub trait MyTrait: Send + Sync {
    async fn do_work(&self) -> Result<()>;
}

流式传输

流式响应使用 EventStream

use adk_core::EventStream;
use async_stream::stream;
use futures::Stream;

fn create_stream() -> EventStream {
    let s = stream! {
        yield Ok(Event::new("inv-1"));
        yield Ok(Event::new("inv-2"));
    };
    Box::pin(s)
}

线程安全

所有公共类型都必须是 Send + Sync

// Good: Thread-safe
pub struct MyAgent {
    name: String,
    tools: Vec<Arc<dyn Tool>>,  // Arc for shared ownership
}

// Verify with compile-time checks
fn assert_send_sync<T: Send + Sync>() {}
fn _check() {
    assert_send_sync::<MyAgent>();
}

测试

测试运行器

ADK-Rust 使用 cargo-nextest 执行测试。Nextest 会在独立进程中运行每个测试二进制文件,并进行并行调度,在这个工作区上相比 cargo test 可带来约 10 倍的加速。

# Install (one-time)
curl -LsSf https://get.nexte.st/latest/mac | tar zxf - -C ${CARGO_HOME:-~/.cargo}/bin

# Or via devenv (included automatically)
devenv shell

配置位于 .config/nextest.toml,包含两个配置档案:

  • default — 本地开发(快速失败、无重试)
  • ci — CI 运行(对不稳定测试进行重试、慢测试警告)

测试组织

crate/
├── src/
│   ├── lib.rs          # Unit tests at bottom of file
│   └── module.rs       # Module-specific tests
└── tests/
    └── integration.rs  # Integration tests

单元测试

将单元测试放在与代码相同的文件中:

pub fn add(a: i32, b: i32) -> i32 {
    a + b
}

#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn test_add() {
        assert_eq!(add(2, 3), 5);
    }

    #[tokio::test]
    async fn test_async_function() {
        let result = async_function().await;
        assert!(result.is_ok());
    }
}

集成测试

放在 tests/ 目录中:

// tests/integration_test.rs
use adk_core::*;

#[tokio::test]
async fn test_full_workflow() {
    // Setup
    let service = InMemorySessionService::new();

    // Execute
    let session = service.create(request).await.unwrap();

    // Assert
    assert_eq!(session.id(), "test-session");
}

Mock 测试

使用 MockLlm 在不调用 API 的情况下进行测试:

use adk_model::MockLlm;

#[tokio::test]
async fn test_agent_with_mock() {
    let mock = MockLlm::new(vec![
        "First response".to_string(),
        "Second response".to_string(),
    ]);

    let agent = LlmAgentBuilder::new("test")
        .model(Arc::new(mock))
        .build()
        .unwrap();

    // Test agent behavior
}

测试命令

# Run all tests (nextest — parallel, fast)
cargo nextest run --workspace

# Run specific crate tests
cargo nextest run -p adk-core

# Run with CI profile (retries flaky tests)
cargo nextest run --workspace --profile ci

# Run doctests (nextest doesn't run these — use cargo test)
cargo test --workspace --doc

# Run ignored tests (require API keys)
cargo nextest run --workspace -- --run-ignored

# Run with output (nextest shows output for failing tests by default)
cargo nextest run --workspace --no-capture

# Devenv shortcuts
devenv shell ws-test          # nextest, default profile
devenv shell ws-test-ci       # nextest, CI profile
devenv shell ws-test-slow     # cargo test fallback (includes doctests)

文档

文档注释

公共项使用 ///

/// Creates a new LLM agent with the specified configuration.
///
/// # Arguments
///
/// * `name` - A unique identifier for this agent
/// * `model` - The LLM provider to use for reasoning
///
/// # Examples
///
/// ```rust
/// use adk_agent::LlmAgentBuilder;
///
/// let agent = LlmAgentBuilder::new("assistant")
///     .model(Arc::new(model))
///     .build()?;
/// ```
///
/// # Errors
///
/// Returns an error with component `Agent` if the model is not set.
pub fn new(name: impl Into<String>) -> Self {
    // ...
}

模块文档

lib.rs 顶部添加模块级文档:

//! # adk-core
//!
//! Core types and traits for ADK-Rust.
//!
//! ## Overview
//!
//! This crate provides the foundational types...

README 文件

每个 crate 都应有一个 README.md,其中包括:

  1. 简要说明
  2. 安装说明
  3. 快速示例
  4. 指向完整文档的链接

文档测试

确保文档示例可编译:

cargo test --doc --all

Pull Request 流程

提交前

  1. 运行完整测试套件

    cargo nextest run --workspace
  2. 运行 clippy

    cargo clippy --all-targets --all-features
  3. 格式化代码

    cargo fmt --all
  4. 如果添加/更改了公共 API,请更新文档

  5. 为新功能添加测试

PR 指南

  • 标题:对变更的清晰、简洁描述
  • 描述:解释是什么以及为什么(不是怎么做)
  • 大小:保持 PR 聚焦;拆分大型更改
  • 测试:为新功能包含测试
  • 破坏性变更:在描述中清楚记录

提交信息

遵循 conventional commits:

feat: add OpenAI streaming support
fix: correct tool parameter validation
docs: update quickstart guide
refactor: simplify session state management
test: add integration tests for A2A protocol

项目脚手架

使用 cargo adk newComposable Template System 来搭建新项目。内置注册表提供 12 个模板、9 个附加组件和 5 种企业模式:

# Basic agent (default)
cargo adk new my-agent

# Agent with tools and Docker support
cargo adk new my-agent --template tools --addon docker

# A2A protocol agent with CI and telemetry
cargo adk new my-agent --template a2a --addon ci --addon telemetry

# Graph workflow with enterprise observability
cargo adk new my-agent --template graph --addon telemetry --addon docker --addon ci

--addon 标志是可组合的——将任意基础模板与任意数量的 addons 组合。有关模板、addons 和企业模式的完整列表,请参阅 Composable Templates 文档。

常见任务

添加新工具

  1. 创建工具
use adk_core::{Tool, ToolContext, Result};
use async_trait::async_trait;
use serde_json::Value;

pub struct MyTool {
    // fields
}

#[async_trait]
impl Tool for MyTool {
    fn name(&self) -> &str {
        "my_tool"
    }

    fn description(&self) -> &str {
        "Does something useful"
    }

    fn parameters_schema(&self) -> Option<Value> {
        Some(serde_json::json!({
            "type": "object",
            "properties": {
                "input": { "type": "string" }
            },
            "required": ["input"]
        }))
    }

    async fn execute(&self, ctx: Arc<dyn ToolContext>, args: Value) -> Result<Value> {
        let input = args["input"].as_str().unwrap_or_default();
        Ok(serde_json::json!({ "result": input }))
    }
}
  1. 添加到 agent
let agent = LlmAgentBuilder::new("agent")
    .model(model)
    .tool(Arc::new(MyTool::new()))
    .build()?;

添加新的模型提供方

  1. adk-model/src/ 中创建模块
// adk-model/src/mymodel/mod.rs
mod client;
pub use client::MyModelClient;
  1. 实现 Llm trait
use adk_core::{Llm, LlmRequest, LlmResponse, LlmResponseStream, Result};

pub struct MyModelClient {
    api_key: String,
}

#[async_trait]
impl Llm for MyModelClient {
    fn name(&self) -> &str {
        "my-model"
    }

    async fn generate_content(
        &self,
        request: LlmRequest,
        stream: bool,
    ) -> Result<LlmResponseStream> {
        // Implementation
    }
}
  1. adk-model/Cargo.toml 中添加 feature flag
[features]
mymodel = ["dep:mymodel-sdk"]
  1. 有条件地导出
#[cfg(feature = "mymodel")]
pub mod mymodel;
#[cfg(feature = "mymodel")]
pub use mymodel::MyModelClient;

添加新的 agent 类型

  1. adk-agent/src/ 中创建模块
// adk-agent/src/my_agent.rs
use adk_core::{Agent, EventStream, InvocationContext, Result};
use async_trait::async_trait;

pub struct MyAgent {
    name: String,
}

#[async_trait]
impl Agent for MyAgent {
    fn name(&self) -> &str {
        &self.name
    }

    fn description(&self) -> &str {
        "My custom agent"
    }

    async fn run(&self, ctx: Arc<dyn InvocationContext>) -> Result<EventStream> {
        // Implementation
    }
}
  1. adk-agent/src/lib.rs 中导出
mod my_agent;
pub use my_agent::MyAgent;

调试提示

  1. 启用 tracing

    adk_telemetry::init_telemetry();
  2. 检查事件

    while let Some(event) = stream.next().await {
        eprintln!("Event: {:?}", event);
    }
  3. 使用 RUST_LOG

    RUST_LOG=debug cargo run --example myexample

上一页← 访问控制

有问题?GitHub 上提交 issue。

开发指南 - ADK-Rust 文档 | ADK-Rust