SDK

pi 可以說明你使用 SDK。可以讓它為你的使用情境建置整合。

SDK 提供對 pi Agent 能力的程式化存取。使用它可以將 pi 嵌入其他應用、建置自訂介面，或接入自動化工作流程。

使用情境範例：

• 建置自訂 UI（Web、桌面、移動）
• 將 Agent 能力整合到現有應用程式中
• 使用 Agent 推理建立自動化流水線
• 建置可產生子 Agent 的自訂工具
• 以程式開發方式測試 Agent 行為

從最小範例到完全控制的可執行範例，見 examples/sdk/。

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?");

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

SDK 包含在主包中。無需個別安裝。

用於建立單一 AgentSession 的主要工廠函式。

createAgentSession() 使用 ResourceLoader 提供擴充、Skills、Prompt Templates、主題和 context files。未提供時，它會使用 DefaultResourceLoader 執行標準探索。

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(),
});

工作階段管理 Agent 生命週期、訊息歷史、模型狀態、壓縮和事件流。

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;
}

新工作階段、恢復、分叉和匯入等工作階段替換 API 位於 AgentSessionRuntime 上，而不是 AgentSession 上。

當需要替換活動工作階段並重建綁定到 cwd 的執行階段狀態時，請使用執行階段 API。 這與內建互動、列印和 RPC 模式使用的層相同。

createAgentSessionRuntime() 接收執行階段工廠以及初始 cwd/session 目標。工廠會閉包捕獲程序全域的固定輸入，為有效 cwd 重新建立綁定到 cwd 的服務，基於這些服務解析工作階段選項，並傳回完整的執行階段結果。

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 負責在以下流程中替換活動執行階段：

• newSession()
• switchSession()
• fork()
• 透過 fork(entryId, { position: "at" }) 實作的 clone 流程
• importFromJsonl()

重要行為：

• 這些操作之後 runtime.session 會變化
• 事件訂閱附加到特定 AgentSession，因此替換後需要重新訂閱
• 如果使用擴充，請為新工作階段再次呼叫 runtime.session.bindExtensions(...)
• 建立過程會在 runtime.diagnostics 上傳回診斷資訊
• 如果執行階段建立或替換失敗，該方法將拋出異常，呼叫者決定如何處理它

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

await runtime.newSession();

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

PromptOptions 控制 Prompt 展開、串流傳輸時的排隊行為，以及 Prompt 預檢通知：

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

每次 prompt() 呼叫都會呼叫一次 preflightResult：

• true 表示 Prompt 已被接受、排隊或立即處理
• false 表示 Prompt 在接受之前被預檢拒絕

它會在 prompt() resolve 之前觸發。prompt() 仍然只會在完整的已接受執行結束後（包括重試）resolve。接受之後的失敗會透過正常事件和訊息流報告，而不是透過 preflightResult(false)。

prompt() 方法處理 Prompt Templates、擴充指令和訊息傳送：

// 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" });

行為：

• 擴充指令（例如 /mycommand）：即使在串流傳輸期間也會立即執行。它們透過 pi.sendMessage() 管理自己的 LLM 互動。
• 基於檔案的 Prompt Templates（來自 .md 檔案）：傳送或排隊前展開為其內容。
• 串流傳輸期間未指定 streamingBehavior：拋出錯誤。直接使用 steer() 或 followUp()，或指定該選項。
• preflightResult(true)：表示提示已被接受、排隊或立即處理。
• preflightResult(false)：表示在接受之前預檢被拒絕。

對於串流傳輸期間的顯式排隊：

// 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() 都會展開基於檔案的 Prompt Templates，但遇到擴充指令會報錯（擴充指令不能排隊）。

Agent 類（來自 @earendil-works/pi-agent-core）處理核心 LLM 互動。透過 session.agent 存取它。

// 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();

訂閱事件以接收流輸出和生命週期通知。

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;
  }
});

const { session } = await createAgentSession({
  // Working directory for DefaultResourceLoader discovery
  cwd: process.cwd(), // default
  
  // Global config directory
  agentDir: "~/.pi/agent", // default (expands ~)
});

cwd 由 DefaultResourceLoader 用於：

• 專案擴充 (.pi/extensions/)
• 專案技能：
  • .pi/skills/
  • cwd 和祖先目錄中的 .agents/skills/（直至 git repo 根目錄，或不在repository 中時的檔案系統根目錄）
• 專案 Prompt（.pi/prompts/）
• context files（從 cwd 向上尋找 AGENTS.md）
• 工作階段目錄命名

agentDir 由 DefaultResourceLoader 用於：

• 全域擴充 (extensions/)
• 全域 Skills：
  • skills/ 位於 agentDir 之下（例如 ~/.pi/agent/skills/）
  • ~/.agents/skills/
• 全域 Prompt（prompts/）
• 全域context files (AGENTS.md)
• 設定（settings.json）
• 自訂模型 (models.json)
• 憑證 (auth.json)
• 工作階段 (sessions/)

傳入自訂 ResourceLoader 後，cwd 和 agentDir 不再控制資源探索。它們仍會影響工作階段命名和工具路徑解析。

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

const modelRuntime = await ModelRuntime.create();

// 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,
});

如果沒有提供模型：

1. 嘗試從工作階段中恢復（如果繼續）
2. 使用設定中的預設值
3. fallback 到第一個可用模型

要比對 CLI 模型解析，請使用匯出的解析器助理：

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() 使用所有已註冊的模型，因此 --api-key 樣式首次設定可以在儲存的身分驗證狀態之前解析模型。 resolveModelScopeWithDiagnostics() 比對 --models 和 enabledModels 語義，同時傳回警告而不是列印警告。

見examples/sdk/02-custom-model.ts

身分驗證解析優先級（由 ModelRuntime 處理）：

1. 執行階段覆蓋（透過 setRuntimeApiKey，不持久）
2. 儲存在 auth.json 中的憑證（API Key 或 OAuth token）
3. 環境變數（ANTHROPIC_API_KEY、OPENAI_API_KEY 等）
4. 後備解析器（用於來自 models.json 的自訂 Provider key）

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,
});

在受影響的 Provider 的快取/內建目錄、組合和可用狀態快照本機一致後，login()、logout()、setRuntimeApiKey() 和 removeRuntimeApiKey() 即可解決。他們不會等待遠端目錄的新鮮度。如果憑證已commit但本機同步失敗，它們會拒絕匯出的 CredentialSynchronizationError；檢查其 providerId、operation、credential 和 cause 欄位，而不是盲目地重試憑證突變。

公共模型/驗證操作和 ModelRuntime.create({ signal }) 接受選用的中止信號，並且在省略時不受限制。 SDK 應用程式自己的遠端目錄新鮮度截止日期政策：

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);
}

失敗或超時的網路重新整理不會撤消成功的憑證操作。 refresh() 啟動新的 Provider 產生，因此它不會等待舊的停滯重新整理，並且過時的產生之後無法發佈。

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

使用 ResourceLoader 覆蓋系統提示：

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 });

見examples/sdk/03-custom-prompt.ts

指定要啟用的內建工具：

• 內建工具名稱：read、bash、edit、write、grep、find、ls
• 預設內建：read、bash、edit、write
• noTools: "all" 停用所有工具
• noTools: "builtin" 停用預設內建程式，同時保持擴充和自訂工具啟用
• 應用任何 tools 允許清單後，excludeTools 停用特定的內建、擴充或自訂工具名稱

edit 工具為 Pi 的 TUI 顯示傳回 details.diff，並為 SDK 消費者傳回 details.patch 作為標準統一patch。

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"],
});

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

當你傳遞自訂 cwd 時，createAgentSession() 會為該 cwd 建置選定的內建工具。

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),
});

見examples/sdk/05-tools.ts

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],
});

使用 defineTool() 進行獨立定義和陣列，如 customTools: [myTool]。內聯 pi.registerTool({ ... }) 已經正確推斷參數類型。

透過 customTools 傳遞的自訂工具與擴充註冊的工具相結合。 ResourceLoader 載入的 Extensions 也可以透過 pi.registerTool() 註冊工具。

如果你傳遞 tools，請包含你想要啟用的每個自訂或擴充工具名稱，例如 tools: ["read", "bash", "my_tool"]。

見examples/sdk/05-tools.ts

Extensions 由 ResourceLoader 載入。 DefaultResourceLoader 從 ~/.pi/agent/extensions/、.pi/extensions/ 和 settings.json 擴充源探索擴充。

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 });

Extensions 可以註冊工具、訂閱事件、新增指令等。完整的 API 請參見extensions.md。

命名內聯擴充： 預設情況下，內聯工廠在啟動 Extensions 清單中顯示為 <inline:1>、<inline:2> 等。要顯示描述性名稱，請包裝工廠：

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],
});

這顯示為 <inline:my-provider> 而不是 <inline:1>。為了向後相容，裸工廠函式仍然被接受。

事件總線： Extensions 可以透過 pi.events 進行通信。如果你需要從外部發出或監聽，請將共享的 eventBus 傳遞給 DefaultResourceLoader：

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));

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

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 });

見examples/sdk/04-skills.ts

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 });

見examples/sdk/07-context-files.ts

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 });

見examples/sdk/08-prompt-templates.ts

工作階段使用具有 id/parentId 連結的樹結構，從而實作就地分支。

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"),
});

// 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 樹 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

參見 examples/sdk/11-sessions.ts 和 Session Format

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"),
});

靜態工廠：

• SettingsManager.create(cwd?, agentDir?) - 從檔案載入
• SettingsManager.inMemory(settings?) - 無檔案 I/O

專案特定設定：

設定從兩個位置載入並合併：

1. 全域：~/.pi/agent/settings.json
2. 專案：<cwd>/.pi/settings.json

專案設定會覆蓋全域設定。巢狀物件按鍵合併。setter 預設修改全域設定。

持久性和錯誤處理語義：

• 設定 getter/setter 對於記憶體狀態是同步的。
• Setters 將持久化寫入佇列async寫入。
• 當你需要持久性邊界時（例如，在程序退出之前或在測試中斷言檔案內容之前），請呼叫 await settingsManager.flush()。
• SettingsManager 不列印設定 I/O 錯誤。使用 settingsManager.drainErrors() 並在你的應用程式層中報告它們。

見examples/sdk/10-settings.ts

使用 DefaultResourceLoader 探索擴充、技能、提示、主題和 context files。

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;

createAgentSession() 傳回：

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;
}

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.");

SDK 匯出執行模式實用程式，用於在 createAgentSession() 之上建置自訂介面：

完整的 TUI 互動模式，包含編輯器、聊天歷史記錄和所有內建指令：

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();

單次模式：傳送提示、輸出結果、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"],
});

子流程整合的 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);

請參閱RPC documentation瞭解 JSON 協議。

對於不使用 SDK 建置的基於子流程的整合，請直接使用 CLI：

pi --mode rpc --no-session

請參閱RPC documentation瞭解 JSON 協議。

在以下情況下，偏好 SDK：

• 你想要類型安全
• 你們處於同一個 Node.js 流程中
• 需要直接存取 Agent 狀態
• 需要以程式開發方式自訂工具或擴充

在以下情況下，偏好 RPC 模式：

• 需要從另一種語言整合
• 需要程序隔離
• 正在建置與語言無關的客戶端

主要入口點匯出：

// 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, createEditTool, createWriteTool
createGrepTool, createFindTool, createLsTool

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

對於擴充類型，請參閱 extensions.md 瞭解完整的 API。