Harness Class

Added in: @mastra/core@1.1.0

The Harness class orchestrates multiple agent modes, shared state, memory, and storage. It provides a control layer that a TUI or other UI can drive to manage threads, switch models and modes, send messages, handle tool approvals, and track events.

Usage example

import { Harness } from '@mastra/core/harness';
import { LibSQLStore } from '@mastra/libsql';
import { z } from 'zod';

const harness = new Harness({
  id: 'my-coding-agent',
  storage: new LibSQLStore({ url: 'file:./data.db' }),
  stateSchema: z.object({
    currentModelId: z.string().optional(),
  }),
  modes: [
    { id: 'plan', name: 'Plan', default: true, agent: planAgent },
    { id: 'build', name: 'Build', agent: buildAgent },
  ],
});

harness.subscribe((event) => {
  if (event.type === 'message_update') {
    renderMessage(event.message);
  }
});

await harness.init();
await harness.selectOrCreateThread();
await harness.sendMessage({ content: 'Hello!' });

Constructor parameters

id:

string

Unique identifier for this harness instance.

resourceId?:

string

Resource ID for grouping threads (e.g., project identifier). Threads are scoped to this resource ID. Defaults to `id`.

storage?:

MastraCompositeStore

Storage backend for persistence (threads, messages, state).

stateSchema?:

z.ZodObject

Zod schema defining the shape of harness state. Used for validation and extracting defaults.

initialState?:

Partial<z.infer<TState>>

Initial state values. Must conform to the schema if provided.

memory?:

MastraMemory

Memory configuration shared across all modes. Propagated to mode agents that don't have their own memory.

modes:

HarnessMode[]

Available agent modes. At least one mode is required. Each mode defines an agent and optional defaults.

tools?:

ToolsInput | ((ctx) => ToolsInput)

Tools available to all agents across all modes. It can be a static tools object or a dynamic function that receives the request context.

workspace?:

Workspace | WorkspaceConfig | ((ctx) => Workspace)

Workspace configuration. Accepts a pre-constructed Workspace, a WorkspaceConfig for the harness to construct internally, or a dynamic factory function.

subagents?:

HarnessSubagent[]

Subagent definitions. When provided, the harness creates a built-in `subagent` tool that parent agents can call to spawn focused subagents.

resolveModel?:

(modelId: string) => MastraLanguageModel

Converts a model ID string (e.g., `"anthropic/claude-sonnet-4"`) to a language model instance. Used by subagents and observational memory model resolution.

omConfig?:

HarnessOMConfig

Default configuration for observational memory (observer/reflector model IDs and thresholds).

heartbeatHandlers?:

HeartbeatHandler[]

Periodic background tasks started during `init()`. Use for gateway sync, cache refresh, and similar tasks.

idGenerator?:

() => string

= timestamp + random string

Custom ID generator for threads, messages, and other entities.

modelAuthChecker?:

ModelAuthChecker

Custom auth checker for model providers. Return `true`/`false` to override the default environment variable check, or `undefined` to fall back to defaults.

modelUseCountProvider?:

ModelUseCountProvider

Provides per-model use counts for sorting and display in `listAvailableModels()`.

toolCategoryResolver?:

(toolName: string) => ToolCategory | null

Maps tool names to permission categories (`'read'`, `'edit'`, `'execute'`, `'mcp'`, `'other'`). Used by the permission system to resolve category-level policies.

threadLock?:

{ acquire, release }

Thread locking callbacks to prevent concurrent access from multiple processes. `acquire` should throw if the lock is held.

HarnessMode

Each entry in the modes array configures a single agent mode.

id:

string

Unique identifier for this mode (e.g., `"plan"`, `"build"`).

name?:

string

Human-readable name for display.

default?:

boolean

= false

Whether this is the default mode when the harness starts.

defaultModelId?:

string

Default model ID for this mode (e.g., `"anthropic/claude-sonnet-4-20250514"`). Used when no per-mode model has been explicitly selected.

color?:

string

Hex color for the mode indicator (e.g., `"#7c3aed"`).

agent:

Agent | ((state) => Agent)

The agent for this mode. It can be a static Agent instance or a function that receives harness state and returns an Agent.

HarnessSubagent

Each entry in the subagents array defines a subagent the harness can spawn.

id:

string

Unique identifier for this subagent type (e.g., `"explore"`, `"execute"`).

name:

string

Human-readable name shown in tool output.

description:

string

Description of what this subagent does. Used in the auto-generated tool description.

instructions:

string

System prompt for this subagent.

tools?:

ToolsInput

Tools this subagent has direct access to.

allowedHarnessTools?:

string[]

Tool IDs from the harness's shared `tools` config. Merged with `tools` above to let subagents use a subset of harness tools.

defaultModelId?:

string

Default model ID for this subagent type.

Properties

id:

string

Harness identifier, set at construction.

Methods

Lifecycle

init()

Initialize the harness. Loads storage, initializes the workspace, propagates memory and workspace to mode agents, and starts heartbeat handlers. Call this before using the harness.

await harness.init();

selectOrCreateThread()

Select the most recent thread for the current resource, or create one if none exist. Loads thread metadata and acquires a thread lock.

const thread = await harness.selectOrCreateThread();

destroy()

Stop all heartbeat handlers and clean up resources.

await harness.destroy();

State

getState()

Return a read-only snapshot of the current harness state.

const state = harness.getState();

setState(updates)

Update the harness state. Validates against stateSchema if provided, and emits a state_changed event with the new state and changed keys.

await harness.setState({ currentModelId: 'anthropic/claude-sonnet-4-20250514' });

Modes

listModes()

Return all configured HarnessMode instances.

const modes = harness.listModes();

getCurrentModeId()

Return the ID of the currently active mode.

const modeId = harness.getCurrentModeId();

getCurrentMode()

Return the HarnessMode object for the current mode.

const mode = harness.getCurrentMode();

switchMode({ modeId })

Switch to a different mode. Aborts any in-progress generation, saves the current model to the outgoing mode, loads the incoming mode's model, and emits mode_changed and model_changed events.

await harness.switchMode({ modeId: 'build' });

Models

getCurrentModelId()

Return the ID of the currently selected model from state.

const modelId = harness.getCurrentModelId();

getModelName()

Return a short display name from the current model ID. For example, "claude-sonnet-4" from "anthropic/claude-sonnet-4".

const name = harness.getModelName();

getFullModelId()

Return the complete model ID string.

const fullId = harness.getFullModelId();

hasModelSelected()

Check if a model ID is currently selected.

if (harness.hasModelSelected()) {
  // Ready to send messages
}

switchModel({ modelId, scope?, modeId? })

Switch the active model. When scope is 'thread', the model ID is persisted to thread metadata so it's restored when switching back. Emits a model_changed event.

// Set for current session only
await harness.switchModel({ modelId: 'anthropic/claude-sonnet-4-20250514' });

// Persist to the current thread
await harness.switchModel({ modelId: 'anthropic/claude-sonnet-4-20250514', scope: 'thread' });

getCurrentModelAuthStatus()

Check if the current model's provider has authentication configured. Uses modelAuthChecker if provided, falling back to environment variable checks from the provider registry.

const status = await harness.getCurrentModelAuthStatus();
// { hasAuth: true, apiKeyEnvVar: 'ANTHROPIC_API_KEY' }

listAvailableModels()

Retrieve all available models from the provider registry, including their authentication status and use counts.

const models = await harness.listAvailableModels();
// [{ id, provider, modelName, hasApiKey, apiKeyEnvVar, useCount }]

Threads

getCurrentThreadId()

Return the ID of the currently active thread.

const threadId = harness.getCurrentThreadId();

createThread({ title? })

Create a new thread. Initializes thread metadata, saves it to storage, acquires a thread lock, and emits a thread_created event.

const thread = await harness.createThread({ title: 'New conversation' });

switchThread({ threadId })

Switch to a different thread. Aborts any in-progress operations, acquires a lock on the new thread, releases the lock on the previous thread, loads the thread's metadata, and emits a thread_changed event.

await harness.switchThread({ threadId: 'thread-abc123' });

listThreads(options?)

List threads from storage. By default, only threads for the current resource are returned.

// List threads for current resource
const threads = await harness.listThreads();

// List all threads across resources
const allThreads = await harness.listThreads({ allResources: true });

renameThread({ title })

Update the title of the current thread.

await harness.renameThread({ title: 'Updated title' });

getResourceId()

Return the current resource ID.

const resourceId = harness.getResourceId();

setResourceId({ resourceId })

Set the resource ID and clear the current thread.

harness.setResourceId({ resourceId: 'project-xyz' });

getSession()

Return current session information including thread ID, mode ID, and the list of threads.

const session = await harness.getSession();
// { currentThreadId, currentModeId, threads }

Messages

sendMessage({ content, images? })

Send a message to the current agent. Creates a thread if none exists, builds a RequestContext and toolsets, and streams the agent's response. Handles tool calls, approvals, and errors automatically.

await harness.sendMessage({ content: 'Explain the authentication flow' });

listMessages(options?)

Retrieve messages for the current thread.

const messages = await harness.listMessages();

// Limit to the last 50 messages
const recent = await harness.listMessages({ limit: 50 });

listMessagesForThread({ threadId, limit? })

Retrieve messages for a specific thread.

const messages = await harness.listMessagesForThread({ threadId: 'thread-abc123' });

getFirstUserMessageForThread({ threadId })

Retrieve the first user message for a given thread.

const firstMsg = await harness.getFirstUserMessageForThread({ threadId: 'thread-abc123' });

Flow control

abort()

Abort any in-progress generation.

harness.abort();

steer({ content })

Steer the agent mid-stream by injecting an instruction into the current generation.

harness.steer({ content: 'Focus on security implications' });

followUp({ content })

Queue a follow-up message to be sent after the current generation completes. If no operation is running, sends the message immediately.

harness.followUp({ content: 'Now apply those changes' });

Tool approvals

respondToToolApproval({ decision })

Respond to a pending tool approval request. Called when a tool_approval_required event is received.

harness.respondToToolApproval({ decision: 'approve' });
harness.respondToToolApproval({ decision: 'decline' });

Questions and plans

respondToQuestion({ questionId, answer })

Respond to a pending question from the ask_user built-in tool.

harness.respondToQuestion({ questionId: 'q-123', answer: 'Yes, proceed with the refactor' });

respondToPlanApproval({ planId, response })

Respond to a pending plan approval from the submit_plan built-in tool. The response object contains action ('approved' or 'rejected') and an optional feedback string.

harness.respondToPlanApproval({ planId: 'plan-123', response: { action: 'approved' } });
harness.respondToPlanApproval({ planId: 'plan-123', response: { action: 'rejected', feedback: 'Needs more detail' } });

Permissions

grantSessionCategory({ category })

Grant a tool category for the current session. Tools in this category are auto-approved without prompting.

harness.grantSessionCategory({ category: 'edit' });

grantSessionTool({ toolName })

Grant a specific tool for the current session.

harness.grantSessionTool({ toolName: 'mastra_workspace_execute_command' });

getSessionGrants()

Return currently granted session categories and tools.

const grants = harness.getSessionGrants();
// { categories: Set<string>, tools: Set<string> }

setPermissionForCategory({ category, policy })

Set the permission policy for a tool category.

harness.setPermissionForCategory({ category: 'execute', policy: 'ask' });

setPermissionForTool({ toolName, policy })

Set the permission policy for a specific tool. Per-tool policies take precedence over category policies.

harness.setPermissionForTool({ toolName: 'dangerous_tool', policy: 'deny' });

getPermissionRules()

Return the current permission rules.

const rules = harness.getPermissionRules();
// { categories: { execute: 'ask' }, tools: { dangerous_tool: 'deny' } }

getToolCategory({ toolName })

Resolve a tool's category using the configured toolCategoryResolver.

const category = harness.getToolCategory({ toolName: 'mastra_workspace_write_file' });
// 'edit'

Observational memory

loadOMProgress()

Load observational memory records for the current thread and emit an om_status event with reconstructed progress.

await harness.loadOMProgress();

getObserverModelId()

Return the observer model ID from state or the default from omConfig.

const modelId = harness.getObserverModelId();

getReflectorModelId()

Return the reflector model ID from state or the default from omConfig.

const modelId = harness.getReflectorModelId();

switchObserverModel({ modelId })

Switch the observer model. Persists the setting to thread metadata and emits an om_model_changed event.

await harness.switchObserverModel({ modelId: 'anthropic/claude-haiku-3.5' });

switchReflectorModel({ modelId })

Switch the reflector model. Persists the setting to thread metadata and emits an om_model_changed event.

await harness.switchReflectorModel({ modelId: 'anthropic/claude-haiku-3.5' });

getObservationThreshold()

Return the observation threshold in tokens from state or the default from omConfig.

const threshold = harness.getObservationThreshold();

getReflectionThreshold()

Return the reflection threshold in tokens from state or the default from omConfig.

const threshold = harness.getReflectionThreshold();

Subagents

getSubagentModelId({ agentType? })

Retrieve the subagent model ID. Prioritizes per-type settings over the global setting.

const modelId = harness.getSubagentModelId({ agentType: 'explore' });

setSubagentModelId({ modelId, agentType? })

Set the subagent model ID. Pass an agentType to set a per-type override, or omit it to set the global default. Persists to thread settings and emits a subagent_model_changed event.

// Set global subagent model
await harness.setSubagentModelId({ modelId: 'anthropic/claude-sonnet-4-20250514' });

// Set per-type model
await harness.setSubagentModelId({ modelId: 'anthropic/claude-haiku-3.5', agentType: 'explore' });

Events

subscribe(listener)

Register an event listener. Returns an unsubscribe function.

const unsubscribe = harness.subscribe((event) => {
  switch (event.type) {
    case 'message_update':
      renderMessage(event.message);
      break;
    case 'tool_approval_required':
      showApprovalPrompt(event.toolName);
      break;
    case 'error':
      console.error(event.error);
      break;
  }
});

// Later:
unsubscribe();

Events

The harness emits events through registered listeners. The following table lists the available event types:

Event type	Description
mode_changed	The active mode changed.
model_changed	The active model changed.
thread_changed	The active thread changed.
thread_created	A new thread was created.
state_changed	Harness state was updated.
agent_start	The agent started processing.
agent_end	The agent finished processing.
message_start	A new message started streaming.
message_update	A message was updated with new content.
message_end	A message finished streaming.
tool_start	A tool call started.
tool_approval_required	A tool call requires user approval.
tool_update	A tool call was updated with progress.
tool_end	A tool call finished.
tool_input_start	Tool input started streaming.
tool_input_delta	Tool input received a streaming delta.
tool_input_end	Tool input finished streaming.
usage_update	Token usage was updated.
error	An error occurred.
info	An informational message was emitted.
follow_up_queued	A follow-up message was queued.
workspace_status_changed	The workspace status changed.
workspace_ready	The workspace finished initializing.
workspace_error	The workspace encountered an error.
om_status	Observational memory status update.
om_observation_start	An observation started.
om_observation_end	An observation completed.
om_reflection_start	A reflection started.
om_reflection_end	A reflection completed.
ask_question	The agent asked a question via the ask_user tool.
plan_approval_required	The agent submitted a plan for approval via the submit_plan tool.
plan_approved	A plan was approved.
subagent_start	A subagent started processing.
subagent_text_delta	A subagent emitted a text delta.
subagent_tool_start	A subagent started a tool call.
subagent_tool_end	A subagent finished a tool call.
subagent_end	A subagent finished processing.
subagent_model_changed	A subagent's model changed.
task_updated	A task list was updated.

Built-in tools

The harness provides built-in tools to agents in every mode:

Tool	Description
ask_user	Ask the user a question and wait for their response.
submit_plan	Submit a plan for user review and approval.
task_write	Create or update a structured task list for tracking progress.
task_check	Check the completion status of the current task list.
subagent	Spawn a focused subagent with constrained tools (only available when subagents is configured).