Client Interface

Interface that ACP-compliant clients must implement

Overview

The Client interface defines the interface that ACP-compliant clients must implement.

Clients are typically code editors (IDEs, text editors) that provide the interface between users and AI agents. They manage the environment, handle user interactions, and control access to resources.

Type Definition

export interface Client {
  // Required methods
  requestPermission(
    params: RequestPermissionRequest
  ): Promise<RequestPermissionResponse>;
  sessionUpdate(params: SessionNotification): Promise<void>;
  
  // Optional methods
  writeTextFile?(params: WriteTextFileRequest): Promise<WriteTextFileResponse>;
  readTextFile?(params: ReadTextFileRequest): Promise<ReadTextFileResponse>;
  createTerminal?(params: CreateTerminalRequest): Promise<CreateTerminalResponse>;
  terminalOutput?(params: TerminalOutputRequest): Promise<TerminalOutputResponse>;
  releaseTerminal?(params: ReleaseTerminalRequest): Promise<ReleaseTerminalResponse | void>;
  waitForTerminalExit?(params: WaitForTerminalExitRequest): Promise<WaitForTerminalExitResponse>;
  killTerminal?(params: KillTerminalRequest): Promise<KillTerminalResponse | void>;
  extMethod?(method: string, params: Record<string, unknown>): Promise<Record<string, unknown>>;
  extNotification?(method: string, params: Record<string, unknown>): Promise<void>;
}

Required Methods

requestPermission

requestPermission(
  params: RequestPermissionRequest
): Promise<RequestPermissionResponse>

Requests permission from the user for a tool call operation.

Called by the agent when it needs user authorization before executing a potentially sensitive operation. The client should present the options to the user and return their decision.

If the client cancels the prompt turn via session/cancel, it MUST respond to this request with RequestPermissionOutcome::Cancelled.

params · RequestPermissionRequest · required

The permission request parameters

response · RequestPermissionResponse

The user’s permission decision

See protocol docs: Requesting Permission

sessionUpdate

sessionUpdate(params: SessionNotification): Promise<void>

Handles session update notifications from the agent.

This is a notification endpoint (no response expected) that receives real-time updates about session progress, including message chunks, tool calls, and execution plans.

Note: Clients SHOULD continue accepting tool call updates even after sending a session/cancel notification, as the agent may send final updates before responding with the cancelled stop reason.

params · SessionNotification · required

The session notification parameters containing updates about session progress

Promise<void> · Promise<void>

A promise that resolves when the notification has been processed

See protocol docs: Agent Reports Output

Optional Methods

writeTextFile

writeTextFile?(params: WriteTextFileRequest): Promise<WriteTextFileResponse>

Writes content to a text file in the client’s file system.

Only available if the client advertises the fs.writeTextFile capability. Allows the agent to create or modify files within the client’s environment.

params · WriteTextFileRequest · required

The file write request parameters

response · WriteTextFileResponse

An empty object on success

See protocol docs: Client

readTextFile

readTextFile?(params: ReadTextFileRequest): Promise<ReadTextFileResponse>

Reads content from a text file in the client’s file system.

Only available if the client advertises the fs.readTextFile capability. Allows the agent to access file contents within the client’s environment.

params · ReadTextFileRequest · required

The file read request parameters

response · ReadTextFileResponse

The file contents

See protocol docs: Client

createTerminal

createTerminal?(params: CreateTerminalRequest): Promise<CreateTerminalResponse>

Creates a new terminal to execute a command.

Only available if the terminal capability is set to true.

The Agent must call releaseTerminal when done with the terminal to free resources.

params · CreateTerminalRequest · required

The terminal creation parameters

response · CreateTerminalResponse

The terminal ID

See Terminal Documentation

terminalOutput

terminalOutput?(params: TerminalOutputRequest): Promise<TerminalOutputResponse>

Gets the current output and exit status of a terminal.

Returns immediately without waiting for the command to complete. If the command has already exited, the exit status is included.

params · TerminalOutputRequest · required

The terminal output request parameters

response · TerminalOutputResponse

The current terminal output and exit status (if available)

See Getting Terminal Output

releaseTerminal

releaseTerminal?(params: ReleaseTerminalRequest): Promise<ReleaseTerminalResponse | void>

Releases a terminal and frees all associated resources.

The command is killed if it hasn’t exited yet. After release, the terminal ID becomes invalid for all other terminal methods.

Tool calls that already contain the terminal ID continue to display its output.

params · ReleaseTerminalRequest · required

The release terminal request parameters

response · ReleaseTerminalResponse | void

An empty object on success, or void

See Releasing Terminals

waitForTerminalExit

waitForTerminalExit?(params: WaitForTerminalExitRequest): Promise<WaitForTerminalExitResponse>

Waits for a terminal command to exit and returns its exit status.

This method returns once the command completes, providing the exit code and/or signal that terminated the process.

params · WaitForTerminalExitRequest · required

The wait for exit request parameters

response · WaitForTerminalExitResponse

The exit status of the terminal command

See Waiting for Exit

killTerminal

killTerminal?(params: KillTerminalRequest): Promise<KillTerminalResponse | void>

Kills a terminal command without releasing the terminal.

While releaseTerminal also kills the command, this method keeps the terminal ID valid so it can be used with other methods.

Useful for implementing command timeouts that terminate the command and then retrieve the final output.

Note: Call releaseTerminal when the terminal is no longer needed.

params · KillTerminalRequest · required

The kill terminal request parameters

response · KillTerminalResponse | void

An empty object on success, or void

See Killing Commands

extMethod

extMethod?(method: string, params: Record<string, unknown>): Promise<Record<string, unknown>>

Extension method. Allows the Agent to send an arbitrary request that is not part of the ACP spec.

To help avoid conflicts, it’s a good practice to prefix extension methods with a unique identifier such as domain name.

method · string · required

The extension method name

params · Record<string, unknown> · required

The extension method parameters

response · Record<string, unknown>

The extension method response

extNotification

extNotification?(method: string, params: Record<string, unknown>): Promise<void>

Extension notification. Allows the Agent to send an arbitrary notification that is not part of the ACP spec.

method · string · required

The extension notification name

params · Record<string, unknown> · required

The extension notification parameters

Promise<void> · Promise<void>

A promise that resolves when the notification has been processed