20 SDK

通过 SDK 以编程方式调用 pi 的智能体能力，将 pi 嵌入应用、构建自定义界面与自动化集成。

pi 可以帮你使用 SDK。可以请它为你的使用场景构建一个集成。

SDK 提供了对 pi 智能体能力的编程式访问。你可以用它把 pi 嵌入其他应用、构建自定义界面，或与自动化流程集成。

典型使用场景：

构建自定义 UI（Web、桌面、移动端）
将智能体能力集成到现有应用中
借助智能体推理能力创建自动化流水线
构建能派生子智能体的自定义工具
以编程方式测试智能体行为

从最小化接入到完全控制的可运行示例，请参见 examples/sdk/。

快速开始

import { createAgentSession, ModelRuntime, SessionManager } from "@earendil-works/pi-coding-agent";

const modelRuntime = await ModelRuntime.create();
const { session } = await createAgentSession({
  sessionManager: SessionManager.inMemory(),
  modelRuntime,
});

session.subscribe((event) => {
  if (event.type === "message_update" && event.assistantMessageEvent.type === "text_delta") {
    process.stdout.write(event.assistantMessageEvent.delta);
  }
});

await session.prompt("What files are in the current directory?");

安装

npm install @earendil-works/pi-coding-agent

SDK 已包含在主包中，无需单独安装。

核心概念

createAgentSession()

创建单个 AgentSession 的主工厂函数。

createAgentSession() 使用 ResourceLoader 来提供扩展、技能、提示词模板、主题和上下文文件。如果你没有提供，它会使用带标准发现机制的 DefaultResourceLoader。

import { createAgentSession, SessionManager } from "@earendil-works/pi-coding-agent";

// Minimal: defaults with DefaultResourceLoader
const { session } = await createAgentSession();

// Custom: override specific options
const { session } = await createAgentSession({
  model: myModel,
  tools: ["read", "bash"],
  sessionManager: SessionManager.inMemory(),
});

AgentSession

会话负责管理智能体生命周期、消息历史、模型状态、上下文压缩和事件流。

interface AgentSession {
  // Send a prompt and wait for completion
  prompt(text: string, options?: PromptOptions): Promise<void>;

  // Queue messages during streaming
  steer(text: string): Promise<void>;
  followUp(text: string): Promise<void>;

  // Subscribe to events (returns unsubscribe function)
  subscribe(listener: (event: AgentSessionEvent) => void): () => void;

  // Session info
  sessionFile: string | undefined;
  sessionId: string;

  // Model control
  setModel(model: Model): Promise<void>;
  setThinkingLevel(level: ThinkingLevel): void;
  cycleModel(): Promise<ModelCycleResult | undefined>;
  cycleThinkingLevel(): ThinkingLevel | undefined;

  // State access
  agent: Agent;
  model: Model | undefined;
  thinkingLevel: ThinkingLevel;
  messages: AgentMessage[];
  isStreaming: boolean;

  // In-place tree navigation within the current session file
  navigateTree(targetId: string, options?: { summarize?: boolean; customInstructions?: string; replaceInstructions?: boolean; label?: string }): Promise<{ editorText?: string; cancelled: boolean }>;

  // Compaction
  compact(customInstructions?: string): Promise<CompactionResult>;
  abortCompaction(): void;

  // Abort current operation
  abort(): Promise<void>;

  // Cleanup
  dispose(): void;
}

当智能体正在响应、手动或自动上下文压缩正在进行、或另一次树状导航处于活动状态时，session.navigateTree() 会直接拒绝，即使设置了 summarize: false 也不例外。对于这类冲突，它既不会把导航排入队列，也不会返回 { cancelled: true }。请等待当前操作完成（例如使用 await session.waitForIdle()）后重试。被拒绝时，当前活动分支保持不变。

新建会话、恢复、分叉和导入等会话替换 API 位于 AgentSessionRuntime 上，而不是 AgentSession 上。

createAgentSessionRuntime() 与 AgentSessionRuntime

当你需要替换当前活动会话并重建与 cwd 绑定的运行时状态时，请使用运行时 API。内置的交互模式、print 模式和 RPC 模式使用的就是这一层。

createAgentSessionRuntime() 接受一个运行时工厂，以及初始的 cwd/会话目标。该工厂闭包捕获进程级固定输入，为实际生效的 cwd 重建与 cwd 绑定的服务，基于这些服务解析会话选项，并返回完整的运行时结果。

import {
  type CreateAgentSessionRuntimeFactory,
  createAgentSessionFromServices,
  createAgentSessionRuntime,
  createAgentSessionServices,
  getAgentDir,
  SessionManager,
} from "@earendil-works/pi-coding-agent";

const createRuntime: CreateAgentSessionRuntimeFactory = async ({ cwd, sessionManager, sessionStartEvent }) => {
  const services = await createAgentSessionServices({ cwd });
  return {
    ...(await createAgentSessionFromServices({
      services,
      sessionManager,
      sessionStartEvent,
    })),
    services,
    diagnostics: services.diagnostics,
  };
};

const runtime = await createAgentSessionRuntime(createRuntime, {
  cwd: process.cwd(),
  agentDir: getAgentDir(),
  sessionManager: SessionManager.create(process.cwd()),
});

AgentSessionRuntime 负责在以下操作中替换活动运行时：

newSession()
switchSession()
fork()
通过 fork(entryId, { position: "at" }) 实现的克隆流程
importFromJsonl()

重要行为：

这些操作之后 runtime.session 会发生变化
事件订阅绑定在具体的 AgentSession 上，替换后需要重新订阅
如果使用了扩展，需要为新会话再次调用 runtime.session.bindExtensions(...)
创建结果的诊断信息位于 runtime.diagnostics
如果运行时创建或替换失败，方法会抛出异常，由调用方决定如何处理

let session = runtime.session;
let unsubscribe = session.subscribe(() => {});

await runtime.newSession();

unsubscribe();
session = runtime.session;
unsubscribe = session.subscribe(() => {});

提示与消息排队

PromptOptions 用于控制提示词模板展开、流式期间的排队行为，以及提示词预检（preflight）通知：

interface PromptOptions {
  expandPromptTemplates?: boolean;
  images?: ImageContent[];
  streamingBehavior?: "steer" | "followUp";
  source?: InputSource;
  preflightResult?: (success: boolean) => void;
}

preflightResult 在每次 prompt() 调用中只触发一次：

提示词被接受、进入队列或被立即处理时为 true
提示词预检在接受之前被拒绝时为 false

它在 prompt() 完成之前触发。prompt() 仍要等到整个被接受的运行（包括重试）结束后才会完成。接受之后的失败会通过正常的事件和消息流上报，而不会通过 preflightResult(false) 体现。

prompt() 方法负责处理提示词模板、扩展命令和消息发送：

// Basic prompt (when not streaming)
await session.prompt("What files are here?");

// With images
await session.prompt("What's in this image?", {
  images: [{ type: "image", source: { type: "base64", mediaType: "image/png", data: "..." } }]
});

// During streaming: must specify how to queue the message
await session.prompt("Stop and do this instead", { streamingBehavior: "steer" });
await session.prompt("After you're done, also check X", { streamingBehavior: "followUp" });

行为：

扩展命令（例如 /mycommand）：立即执行，流式期间也不例外。它们通过 pi.sendMessage() 自行管理 LLM 交互。
基于文件的提示词模板（来自 .md 文件）：在发送或排队之前展开为其内容。
流式期间未指定 streamingBehavior：会抛出错误。请直接使用 steer() 或 followUp()，或者显式指定该选项。
preflightResult(true)：表示提示词已被接受、进入队列或被立即处理。
preflightResult(false)：表示预检在接受之前被拒绝。

要在流式期间显式排队：

// Queue a steering message for delivery after the current assistant turn finishes its tool calls
await session.steer("New instruction");

// Wait for agent to finish (delivered only when agent stops)
await session.followUp("After you're done, also do this");

steer() 和 followUp() 都会展开基于文件的提示词模板，但遇到扩展命令会报错（扩展命令无法排队）。

Agent 与 AgentState

Agent 类（来自 @earendil-works/pi-agent-core）负责核心的 LLM 交互，可通过 session.agent 访问。

// Access current state
const state = session.agent.state;

// state.messages: AgentMessage[] - conversation history
// state.model: Model - current model
// state.thinkingLevel: ThinkingLevel - current thinking level
// state.systemPrompt: string - system prompt
// state.tools: AgentTool[] - available tools
// state.streamingMessage?: AgentMessage - current partial assistant message
// state.errorMessage?: string - latest assistant error

// Replace messages (useful for branching or restoration)
session.agent.state.messages = messages; // copies the top-level array

// Replace tools
session.agent.state.tools = tools; // copies the top-level array

// Wait for agent to finish processing
await session.agent.waitForIdle();

事件

订阅事件以接收流式输出和生命周期通知。

session.subscribe((event) => {
  switch (event.type) {
    // Streaming text from assistant
    case "message_update":
      if (event.assistantMessageEvent.type === "text_delta") {
        process.stdout.write(event.assistantMessageEvent.delta);
      }
      if (event.assistantMessageEvent.type === "thinking_delta") {
        // Thinking output (if thinking enabled)
      }
      break;
    
    // Tool execution
    case "tool_execution_start":
      console.log(`Tool: ${event.toolName}`);
      break;
    case "tool_execution_update":
      // Streaming tool output
      break;
    case "tool_execution_end":
      console.log(`Result: ${event.isError ? "error" : "success"}`);
      break;
    
    // Message lifecycle
    case "message_start":
      // New message starting
      break;
    case "message_end":
      // Message complete
      break;
    
    // Agent lifecycle
    case "agent_start":
      // Agent started processing prompt
      break;
    case "agent_end":
      // Agent finished (event.messages contains new messages)
      break;
    
    // Turn lifecycle (one LLM response + tool calls)
    case "turn_start":
      break;
    case "turn_end":
      // event.message: assistant response
      // event.toolResults: tool results from this turn
      break;
    
    // Session events (queue, compaction, retry)
    case "queue_update":
      console.log(event.steering, event.followUp);
      break;
    case "compaction_start":
    case "compaction_end":
    case "auto_retry_start":
    case "auto_retry_end":
    case "summarization_retry_scheduled":
    case "summarization_retry_attempt_start":
    case "summarization_retry_finished":
      break;
  }
});

选项参考

项目扩展（.pi/extensions/）
项目技能：
- .pi/skills/
- cwd 及其祖先目录中的 .agents/skills/（向上直到 git 仓库根目录；不在仓库中时则到文件系统根目录）
项目提示词模板（.pi/prompts/）
上下文文件（从 cwd 向上逐级查找 AGENTS.md）
会话目录命名

DefaultResourceLoader 将 agentDir 用于：

全局扩展（extensions/）
全局技能：
- agentDir 下的 skills/（例如 ~/.pi/agent/skills/）
- ~/.agents/skills/
全局提示词模板（prompts/）
全局上下文文件（AGENTS.md）
设置（settings.json）
自定义模型（models.json）
凭据（auth.json）
会话（sessions/）

当你传入自定义 ResourceLoader 时，cwd 和 agentDir 不再控制资源发现，但它们仍会影响会话命名和工具路径解析。

模型

import { getModel } from "@earendil-works/pi-ai";
import { ModelRuntime } from "@earendil-works/pi-coding-agent";

const modelRuntime = await ModelRuntime.create();

// create() restores cached catalogs but does not refresh them from pi.dev by default.
// Opt in to a create-time network refresh and bound how long it may take:
const refreshedRuntime = await ModelRuntime.create({
  allowModelNetwork: true,
  modelRefreshTimeoutMs: 15_000,
});

// Find specific built-in model (doesn't check if API key exists)
const opus = getModel("anthropic", "claude-opus-4-5");
if (!opus) throw new Error("Model not found");

// Find any model by provider/id, including custom models from models.json
// (doesn't check if API key exists)
const customModel = modelRuntime.getModel("my-provider", "my-model");

// Get only models that have valid authentication configured
const available = await modelRuntime.getAvailable();

const { session } = await createAgentSession({
  model: opus,
  thinkingLevel: "medium", // off, minimal, low, medium, high, xhigh, max
  
  // Models for cycling (Ctrl+P in interactive mode)
  scopedModels: [
    { model: opus, thinkingLevel: "high" },
    { model: haiku, thinkingLevel: "off" },
  ],
  
  modelRuntime,
});

如果没有提供模型：

尝试从会话恢复（如果是继续已有会话）
使用设置中的默认值
回退到第一个可用模型

远程目录会持久化到本地，后续创建的运行时无需网络请求即可恢复它们。默认文件是 ~/.pi/agent/models-store.json；可设置 modelsStorePath 选择其他位置，或注入 modelsStore 来控制持久化。网络刷新有节流限制：除非强制，每个提供商每四小时最多刷新一次。要强制立即刷新，可调用 await modelRuntime.refresh({ allowNetwork: true, force: true, signal })。设置 PI_OFFLINE 会禁用模型网络访问。

要与 CLI 的模型解析行为保持一致，请使用导出的解析辅助函数：

import {
  resolveCliModel,
  resolveModelScopeWithDiagnostics,
} from "@earendil-works/pi-coding-agent";

const cliModel = resolveCliModel({
  cliModel: "anthropic/claude-opus-4-5:high",
  modelRuntime,
});
if (cliModel.error) throw new Error(cliModel.error);
if (cliModel.warning) console.warn(cliModel.warning);

const { scopedModels, diagnostics } = await resolveModelScopeWithDiagnostics(
  ["anthropic/*:high", "gpt-5"],
  modelRuntime,
);
for (const diagnostic of diagnostics) {
  console.warn(diagnostic.message);
}

resolveCliModel() 会使用所有已注册的模型，因此 --api-key 式的首次设置流程可以在存储的凭据存在之前就解析出模型。resolveModelScopeWithDiagnostics() 与 --models 和 enabledModels 的语义一致，但以返回值形式给出警告而不是直接打印。

参见 examples/sdk/02-custom-model.ts

API 密钥与 OAuth

认证解析优先级（由 ModelRuntime 处理）：

运行时覆盖（通过 setRuntimeApiKey 设置，不持久化）
auth.json 中存储的凭据（API 密钥或 OAuth 令牌）
环境变量（ANTHROPIC_API_KEY、OPENAI_API_KEY 等）
回退解析器（用于 models.json 中自定义提供商的密钥）

import { InMemoryCredentialStore } from "@earendil-works/pi-ai";
import { createAgentSession, ModelRuntime } from "@earendil-works/pi-coding-agent";

// Default: uses ~/.pi/agent/auth.json and ~/.pi/agent/models.json
const modelRuntime = await ModelRuntime.create();

// Provider-owned auth methods and current status
for (const provider of modelRuntime.getProviders()) {
  const status = await modelRuntime.checkAuth(provider.id);
  console.log(provider.name, provider.auth, status);
}

// Runtime API key override (not persisted to disk)
await modelRuntime.setRuntimeApiKey("anthropic", "sk-my-temp-key");

// Custom credential and model locations
const customRuntime = await ModelRuntime.create({
  authPath: "/my/app/auth.json",
  modelsPath: "/my/app/models.json",
});

// Or inject any pi-ai CredentialStore
const credentials = new InMemoryCredentialStore();
const inMemoryRuntime = await ModelRuntime.create({ credentials });

const { session } = await createAgentSession({
  modelRuntime: customRuntime,
});

login()、logout()、setRuntimeApiKey() 和 removeRuntimeApiKey() 会在受影响提供商的缓存/内置目录、组合信息以及可用性快照在本地达成一致后再完成，不会等待远程目录刷新到最新。如果凭据已提交但本地同步失败，这些方法会以导出的 CredentialSynchronizationError 拒绝；此时应检查其 providerId、operation、credential 和 cause 字段，而不是盲目重试凭据变更。

公开的模型/认证操作以及 ModelRuntime.create({ signal }) 都接受可选的中止信号，省略时不设时限。远程目录新鲜度的截止时间策略由 SDK 应用自己掌握：

const signal = AbortSignal.timeout(15_000);
const result = await modelRuntime.refresh({
  providers: ["anthropic"],
  signal,
});
if (result.aborted) console.warn("Catalog refresh timed out; using cached models");
for (const [providerId, error] of result.errors) {
  console.warn(`Could not refresh ${providerId}:`, error);
}

失败或超时的网络刷新不会撤销已成功的凭据操作。refresh() 会开启新的提供商代（generation），因此不会卡在之前停滞的刷新后面，过期的代此后也无法再发布结果。

参见 examples/sdk/09-api-keys-and-oauth.ts

系统提示词

使用 ResourceLoader 覆盖系统提示词：

import { createAgentSession, DefaultResourceLoader } from "@earendil-works/pi-coding-agent";

const loader = new DefaultResourceLoader({
  systemPromptOverride: () => "You are a helpful assistant.",
});
await loader.reload();

const { session } = await createAgentSession({ resourceLoader: loader });

参见 examples/sdk/03-custom-prompt.ts

工具

指定要启用哪些内置工具：

内置工具名称：read、bash、powershell、edit、write、grep、find、ls
默认内置：read、bash、edit、write
noTools: "all" 禁用所有工具
noTools: "builtin" 禁用默认内置工具，同时保留扩展和自定义工具
excludeTools 在 tools 白名单生效之后禁用指定的内置、扩展或自定义工具名

edit 工具会返回 details.diff 供 pi 的 TUI 显示，并返回 details.patch 作为标准 unified patch 供 SDK 使用方使用。

import { createAgentSession } from "@earendil-works/pi-coding-agent";

// Read-only mode
const { session } = await createAgentSession({
  tools: ["read", "grep", "find", "ls"],
});

// Pick specific tools
const { session } = await createAgentSession({
  tools: ["read", "bash", "grep"],
});

// Use PowerShell instead of Bash on Windows
const { session } = await createAgentSession({
  tools: ["read", "powershell", "edit", "write"],
});

// Disable one tool while keeping the rest available
const { session } = await createAgentSession({
  excludeTools: ["ask_question"],
});

使用自定义 cwd 的工具

当你传入自定义 cwd 时，createAgentSession() 会为该 cwd 构建所选的内置工具。

import { createAgentSession, SessionManager } from "@earendil-works/pi-coding-agent";

const cwd = "/path/to/project";

// Use default tools for custom cwd
const { session } = await createAgentSession({
  cwd,
  sessionManager: SessionManager.inMemory(cwd),
});

// Or pick specific tools for custom cwd
const { session } = await createAgentSession({
  cwd,
  tools: ["read", "bash", "grep"],
  sessionManager: SessionManager.inMemory(cwd),
});

参见 examples/sdk/05-tools.ts

自定义工具

import { Type } from "typebox";
import { createAgentSession, defineTool } from "@earendil-works/pi-coding-agent";

// Inline custom tool
const myTool = defineTool({
  name: "my_tool",
  label: "My Tool",
  description: "Does something useful",
  parameters: Type.Object({
    input: Type.String({ description: "Input value" }),
  }),
  execute: async (_toolCallId, params) => ({
    content: [{ type: "text", text: `Result: ${params.input}` }],
    details: {},
  }),
});

// Pass custom tools directly
const { session } = await createAgentSession({
  customTools: [myTool],
});

对于独立定义以及 customTools: [myTool] 这类数组，请使用 defineTool()。内联的 pi.registerTool({ ... }) 已经能正确推断参数类型。

通过 customTools 传入的自定义工具会与扩展注册的工具合并。ResourceLoader 加载的扩展也可以通过 pi.registerTool() 注册工具。

如果你传入了 tools，请把想要启用的每个自定义或扩展工具名都列进去，例如 tools: ["read", "bash", "my_tool"]。

参见 examples/sdk/05-tools.ts

扩展

扩展由 ResourceLoader 加载。DefaultResourceLoader 会从 ~/.pi/agent/extensions/、.pi/extensions/ 以及 settings.json 中配置的扩展来源发现扩展。

import { createAgentSession, DefaultResourceLoader } from "@earendil-works/pi-coding-agent";

const loader = new DefaultResourceLoader({
  additionalExtensionPaths: ["/path/to/my-extension.ts"],
  extensionFactories: [
    (pi) => {
      pi.on("agent_start", () => {
        console.log("[Inline Extension] Agent starting");
      });
    },
  ],
});
await loader.reload();

const { session } = await createAgentSession({ resourceLoader: loader });

扩展可以注册工具、订阅事件、添加命令等。完整 API 请参见 extensions.md。

具名内联扩展： 默认情况下，内联工厂在启动时的扩展列表中显示为 <inline:1>、<inline:2> 等。要改为显示一个描述性名称，可以这样包装工厂函数：

import type { InlineExtension } from "@earendil-works/pi-coding-agent";

const myProvider: InlineExtension = {
  name: "my-provider",
  factory: (pi) => {
    pi.on("agent_start", () => {
      console.log("[my-provider] Agent starting");
    });
  },
};

const loader = new DefaultResourceLoader({
  extensionFactories: [myProvider],
});

这样就会显示为 <inline:my-provider> 而不是 <inline:1>。为了向后兼容，裸工厂函数仍然可用。

事件总线： 扩展之间可以通过 pi.events 通信。如果需要从外部发送或监听事件，可以向 DefaultResourceLoader 传入一个共享的 eventBus：

import { createEventBus, DefaultResourceLoader } from "@earendil-works/pi-coding-agent";

const eventBus = createEventBus();
const loader = new DefaultResourceLoader({
  eventBus,
});
await loader.reload();

eventBus.on("my-extension:status", (data) => console.log(data));

参见 examples/sdk/06-extensions.ts 和 docs/extensions.md

技能

import {
  createAgentSession,
  DefaultResourceLoader,
  type Skill,
} from "@earendil-works/pi-coding-agent";

const customSkill: Skill = {
  name: "my-skill",
  description: "Custom instructions",
  filePath: "/path/to/SKILL.md",
  baseDir: "/path/to",
  source: "custom",
};

const loader = new DefaultResourceLoader({
  skillsOverride: (current) => ({
    skills: [...current.skills, customSkill],
    diagnostics: current.diagnostics,
  }),
});
await loader.reload();

const { session } = await createAgentSession({ resourceLoader: loader });

参见 examples/sdk/04-skills.ts

上下文文件

import { createAgentSession, DefaultResourceLoader } from "@earendil-works/pi-coding-agent";

const loader = new DefaultResourceLoader({
  agentsFilesOverride: (current) => ({
    agentsFiles: [
      ...current.agentsFiles,
      { path: "/virtual/AGENTS.md", content: "# Guidelines\n\n- Be concise" },
    ],
  }),
});
await loader.reload();

const { session } = await createAgentSession({ resourceLoader: loader });

参见 examples/sdk/07-context-files.ts

斜杠命令

import {
  createAgentSession,
  DefaultResourceLoader,
  type PromptTemplate,
} from "@earendil-works/pi-coding-agent";

const customCommand: PromptTemplate = {
  name: "deploy",
  description: "Deploy the application",
  source: "(custom)",
  content: "# Deploy\n\n1. Build\n2. Test\n3. Deploy",
};

const loader = new DefaultResourceLoader({
  promptsOverride: (current) => ({
    prompts: [...current.prompts, customCommand],
    diagnostics: current.diagnostics,
  }),
});
await loader.reload();

const { session } = await createAgentSession({ resourceLoader: loader });

参见 examples/sdk/08-prompt-templates.ts

会话管理

会话采用树状结构，通过 id/parentId 相互链接，支持原地分支。

import {
  type CreateAgentSessionRuntimeFactory,
  createAgentSession,
  createAgentSessionFromServices,
  createAgentSessionRuntime,
  createAgentSessionServices,
  getAgentDir,
  SessionManager,
} from "@earendil-works/pi-coding-agent";

// In-memory (no persistence)
const { session } = await createAgentSession({
  sessionManager: SessionManager.inMemory(),
});

// New persistent session
const { session: persisted } = await createAgentSession({
  sessionManager: SessionManager.create(process.cwd()),
});

// Continue most recent
const { session: continued, modelFallbackMessage } = await createAgentSession({
  sessionManager: SessionManager.continueRecent(process.cwd()),
});
if (modelFallbackMessage) {
  console.log("Note:", modelFallbackMessage);
}

// Open specific file
const { session: opened } = await createAgentSession({
  sessionManager: SessionManager.open("/path/to/session.jsonl"),
});

// Resume a session kept outside the filesystem, e.g. in a database
const { session: restored } = await createAgentSession({
  sessionManager: SessionManager.inMemory(process.cwd(), { id: sessionId }, entries),
});

// List sessions
const currentProjectSessions = await SessionManager.list(process.cwd());
const allSessions = await SessionManager.listAll(process.cwd());

// Session replacement API for /new, /resume, /fork, /clone, and import flows.
const createRuntime: CreateAgentSessionRuntimeFactory = async ({ cwd, sessionManager, sessionStartEvent }) => {
  const services = await createAgentSessionServices({ cwd });
  return {
    ...(await createAgentSessionFromServices({
      services,
      sessionManager,
      sessionStartEvent,
    })),
    services,
    diagnostics: services.diagnostics,
  };
};

const runtime = await createAgentSessionRuntime(createRuntime, {
  cwd: process.cwd(),
  agentDir: getAgentDir(),
  sessionManager: SessionManager.create(process.cwd()),
});

// Replace the active session with a fresh one
await runtime.newSession();

// Replace the active session with another saved session
await runtime.switchSession("/path/to/session.jsonl");

// Replace the active session with a fork from a specific user entry
await runtime.fork("entry-id");

// Clone the active path through a specific entry
await runtime.fork("entry-id", { position: "at" });

SessionManager 树 API：

const sm = SessionManager.open("/path/to/session.jsonl");

// Session listing
const currentProjectSessions = await SessionManager.list(process.cwd());
const allSessions = await SessionManager.listAll(process.cwd());

// Tree traversal
const entries = sm.getEntries();        // All entries (excludes header)
const tree = sm.getTree();              // Full tree structure
const path = sm.getPath();              // Path from root to current leaf
const leaf = sm.getLeafEntry();         // Current leaf entry
const entry = sm.getEntry(id);          // Get entry by ID
const children = sm.getChildren(id);    // Direct children of entry

// Labels
const label = sm.getLabel(id);          // Get label for entry
sm.appendLabelChange(id, "checkpoint"); // Set label

// Branching
sm.branch(entryId);                     // Move leaf to earlier entry
sm.branchWithSummary(id, "Summary...");  // Branch with context summary
sm.createBranchedSession(leafId);       // Extract path to new file

参见 examples/sdk/11-sessions.ts 和会话格式

设置管理

import { createAgentSession, SettingsManager, SessionManager } from "@earendil-works/pi-coding-agent";

// Default: loads from files (global + project merged)
const { session } = await createAgentSession({
  settingsManager: SettingsManager.create(),
});

// With overrides
const settingsManager = SettingsManager.create();
settingsManager.applyOverrides({
  compaction: { enabled: false },
  retry: { enabled: true, maxRetries: 5 },
});
const { session } = await createAgentSession({ settingsManager });

// In-memory (no file I/O, for testing)
const { session } = await createAgentSession({
  settingsManager: SettingsManager.inMemory({ compaction: { enabled: false } }),
  sessionManager: SessionManager.inMemory(),
});

// Custom directories
const { session } = await createAgentSession({
  settingsManager: SettingsManager.create("/custom/cwd", "/custom/agent"),
});

静态工厂：

SettingsManager.create(cwd?, agentDir?) - 从文件加载
SettingsManager.inMemory(settings?) - 无文件 I/O

项目级设置：

设置从两个位置加载并合并：

全局：~/.pi/agent/settings.json
项目：<cwd>/.pi/settings.json

项目设置覆盖全局设置，嵌套对象按键合并。setter 默认修改全局设置。

持久化与错误处理语义：

设置的 getter/setter 对内存中的状态是同步的。
setter 会异步地把持久化写入排入队列。
当需要一个持久化边界时（例如进程退出前，或测试中断言文件内容之前），请调用 await settingsManager.flush()。
SettingsManager 不会打印设置 I/O 错误。请使用 settingsManager.drainErrors() 并在你的应用层上报。

参见 examples/sdk/10-settings.ts

ResourceLoader

使用 DefaultResourceLoader 发现扩展、技能、提示词模板、主题和上下文文件。

import {
  DefaultResourceLoader,
  getAgentDir,
} from "@earendil-works/pi-coding-agent";

const loader = new DefaultResourceLoader({
  cwd,
  agentDir: getAgentDir(),
});
await loader.reload();

const extensions = loader.getExtensions();
const skills = loader.getSkills();
const prompts = loader.getPrompts();
const themes = loader.getThemes();
const contextFiles = loader.getAgentsFiles().agentsFiles;

返回值

createAgentSession() 返回：

interface CreateAgentSessionResult {
  // The session
  session: AgentSession;
  
  // Extensions result (for runner setup)
  extensionsResult: LoadExtensionsResult;
  
  // Warning if session model couldn't be restored
  modelFallbackMessage?: string;
}

interface LoadExtensionsResult {
  extensions: Extension[];
  errors: Array<{ path: string; error: string }>;
  runtime: ExtensionRuntime;
}

完整示例

import { getModel } from "@earendil-works/pi-ai";
import { Type } from "typebox";
import {
  createAgentSession,
  DefaultResourceLoader,
  defineTool,
  ModelRuntime,
  SessionManager,
  SettingsManager,
} from "@earendil-works/pi-coding-agent";

const modelRuntime = await ModelRuntime.create({
  authPath: "/custom/agent/auth.json",
  modelsPath: "/custom/agent/models.json",
});
if (process.env.MY_KEY) {
  await modelRuntime.setRuntimeApiKey("anthropic", process.env.MY_KEY);
}

// Inline tool
const statusTool = defineTool({
  name: "status",
  label: "Status",
  description: "Get system status",
  parameters: Type.Object({}),
  execute: async () => ({
    content: [{ type: "text", text: `Uptime: ${process.uptime()}s` }],
    details: {},
  }),
});

const model = getModel("anthropic", "claude-opus-4-5");
if (!model) throw new Error("Model not found");

// In-memory settings with overrides
const settingsManager = SettingsManager.inMemory({
  compaction: { enabled: false },
  retry: { enabled: true, maxRetries: 2 },
});

const loader = new DefaultResourceLoader({
  cwd: process.cwd(),
  agentDir: "/custom/agent",
  settingsManager,
  systemPromptOverride: () => "You are a minimal assistant. Be concise.",
});
await loader.reload();

const { session } = await createAgentSession({
  cwd: process.cwd(),
  agentDir: "/custom/agent",

  model,
  thinkingLevel: "off",
  modelRuntime,

  tools: ["read", "bash", "status"],
  customTools: [statusTool],
  resourceLoader: loader,

  sessionManager: SessionManager.inMemory(),
  settingsManager,
});

session.subscribe((event) => {
  if (event.type === "message_update" && event.assistantMessageEvent.type === "text_delta") {
    process.stdout.write(event.assistantMessageEvent.delta);
  }
});

await session.prompt("Get status and list files.");

运行模式

SDK 导出了一组运行模式工具，用于在 createAgentSession() 之上构建自定义界面：

InteractiveMode

完整的 TUI 交互模式，带编辑器、聊天历史和所有内置命令：

import {
  type CreateAgentSessionRuntimeFactory,
  createAgentSessionFromServices,
  createAgentSessionRuntime,
  createAgentSessionServices,
  getAgentDir,
  InteractiveMode,
  SessionManager,
} from "@earendil-works/pi-coding-agent";

const createRuntime: CreateAgentSessionRuntimeFactory = async ({ cwd, sessionManager, sessionStartEvent }) => {
  const services = await createAgentSessionServices({ cwd });
  return {
    ...(await createAgentSessionFromServices({ services, sessionManager, sessionStartEvent })),
    services,
    diagnostics: services.diagnostics,
  };
};
const runtime = await createAgentSessionRuntime(createRuntime, {
  cwd: process.cwd(),
  agentDir: getAgentDir(),
  sessionManager: SessionManager.create(process.cwd()),
});

const mode = new InteractiveMode(runtime, {
  migratedProviders: [],
  modelFallbackMessage: undefined,
  initialMessage: "Hello",
  initialImages: [],
  initialMessages: [],
});

await mode.run();

runPrintMode

单次模式：发送提示词、输出结果、退出：

import {
  type CreateAgentSessionRuntimeFactory,
  createAgentSessionFromServices,
  createAgentSessionRuntime,
  createAgentSessionServices,
  getAgentDir,
  runPrintMode,
  SessionManager,
} from "@earendil-works/pi-coding-agent";

const createRuntime: CreateAgentSessionRuntimeFactory = async ({ cwd, sessionManager, sessionStartEvent }) => {
  const services = await createAgentSessionServices({ cwd });
  return {
    ...(await createAgentSessionFromServices({ services, sessionManager, sessionStartEvent })),
    services,
    diagnostics: services.diagnostics,
  };
};
const runtime = await createAgentSessionRuntime(createRuntime, {
  cwd: process.cwd(),
  agentDir: getAgentDir(),
  sessionManager: SessionManager.create(process.cwd()),
});

await runPrintMode(runtime, {
  mode: "text",
  initialMessage: "Hello",
  initialImages: [],
  messages: ["Follow up"],
});

runRpcMode

用于子进程集成的 JSON-RPC 模式：

import {
  type CreateAgentSessionRuntimeFactory,
  createAgentSessionFromServices,
  createAgentSessionRuntime,
  createAgentSessionServices,
  getAgentDir,
  runRpcMode,
  SessionManager,
} from "@earendil-works/pi-coding-agent";

const createRuntime: CreateAgentSessionRuntimeFactory = async ({ cwd, sessionManager, sessionStartEvent }) => {
  const services = await createAgentSessionServices({ cwd });
  return {
    ...(await createAgentSessionFromServices({ services, sessionManager, sessionStartEvent })),
    services,
    diagnostics: services.diagnostics,
  };
};
const runtime = await createAgentSessionRuntime(createRuntime, {
  cwd: process.cwd(),
  agentDir: getAgentDir(),
  sessionManager: SessionManager.create(process.cwd()),
});

await runRpcMode(runtime);

JSON 协议请参见 RPC 文档。

RPC 模式替代方案

如果要做基于子进程的集成，又不想基于 SDK 构建，可以直接使用 CLI：

pi --mode rpc --no-session

JSON 协议请参见 RPC 文档。

以下情况优先选择 SDK：

需要类型安全
你在同一个 Node.js 进程中
需要直接访问智能体状态
想以编程方式定制工具/扩展

以下情况优先选择 RPC 模式：

从其他语言集成
需要进程隔离
在构建与语言无关的客户端

导出

主入口导出：

// Factory
createAgentSession
createAgentSessionRuntime
AgentSessionRuntime

// Auth and Models
ModelRuntime // implements pi-ai Models and owns credential storage
ModelRegistry // synchronous extension compatibility facade
CredentialSynchronizationError
resolveCliModel
resolveModelScopeWithDiagnostics

// Resource loading
DefaultResourceLoader
type ResourceLoader
createEventBus

// Constants and helpers
CONFIG_DIR_NAME
defineTool
getAgentDir
getPackageDir
getReadmePath
getDocsPath
getExamplesPath

// Session management
SessionManager
SettingsManager

// Tool factories
createCodingTools
createReadOnlyTools
createReadTool, createBashTool, createPowerShellTool, createEditTool, createWriteTool
createGrepTool, createFindTool, createLsTool

// Types
type CreateAgentSessionOptions
type CreateAgentSessionResult
type ExtensionFactory
type InlineExtension
type ExtensionAPI
type ToolDefinition
type Skill
type PromptTemplate
type Tool

关于扩展类型，完整 API 请参见 extensions.md。