Permission modes

A permission mode puts an agent in a named state instead of writing rules: look but do not touch (plan), edit files without asking (acceptEdits), or never pause (dontAsk). Switch it in the middle of a session, the way you would work with a coding agent: plan first, then let it edit.

import { createAgent, createFsTools, MemoryWorkspace } from '@lousho/build-ai-agent';
import { mockModel } from '@lousho/build-ai-agent/testing';

const workspace = new MemoryWorkspace({ files: { 'notes.md': '# Notes\n' } });
const agent = createAgent({
  provider: mockModel(['I would add a "Todo" section to notes.md.', 'Done.']),
  instructions: 'You are a coding agent.',
  tools: createFsTools(workspace, { needsApproval: { write_file: true, edit_file: true } }),
});

const session = agent.session({ permissionMode: 'plan' });
await session.send('Plan how to add a todo list to notes.md.'); // reads only; writes are refused
session.setPermissionMode('acceptEdits');
await session.send('Apply the plan.'); // write_file and edit_file run without asking

The modes are presets over the permission rules and needsApproval, not a second system: they apply last, to what the rules, guardrails and the tool’s own needsApproval decided.

The modes

Mode	Read-only tools	File edits	Other tools that ask	Other tools that do not ask
`'default'`	Normal gate	Normal gate	Pause for approval	Run
`'plan'`	Normal gate (they may still ask)	Denied	Denied	Denied
`'acceptEdits'`	Normal gate	Run without asking	Pause for approval	Run
`'dontAsk'`	Normal gate, but a call that would ask is denied	Denied when they would ask	Denied	Run

plan: a call to a tool that is not read-only is refused with kind: 'denied' and the reason The agent is in plan mode: it may read but not change anything. Describe the change instead. - also when an allow rule matched it. A run that starts in plan mode also gets one paragraph in its system prompt telling the model so. A call to an unknown tool still gets the normal not-found error, so the model sees the real problem.
acceptEdits: a call that would pause for approval runs without asking when its tool is a file edit (editsFiles, below). Everything else is unchanged.
dontAsk: a call that would pause for approval - an ask rule, needsApproval, or ask_question - is refused with the reason The agent is in dontAsk mode: calls that need approval are refused. Calls an allow rule approved and calls that need no approval run. Nothing pauses, so an approve callback is never called.

Which tools are read-only

Plan mode lets a tool run only when it says it changes nothing. A tool that says nothing is treated as one with side effects and is refused.

A tool with annotations: { readOnlyHint: true }. Built in: read_file, list_dir, glob, grep, todo_read, current_date, day_name, web_fetch, load_skill, every recall_<name> memory tool, and agent_status / agent_await (they watch background sub-agents). An OpenAPI tool for a GET operation has it too, and an MCP tool keeps the hint its server sent: it is the server’s word, not a guarantee, so only connect servers you trust.
The built-in ask_question (it only asks; the call still pauses for the answer) and task (its sub-agent inherits plan mode, see below).
Hosted provider tools run inside the provider’s request, so no call can be refused. Plan mode sends webSearch() and fileSearch() (they read) and leaves codeInterpreter() and every hostedTool() out of the model request; the other modes send them all.

Declare a custom read-only tool like this:

import { defineTool } from '@lousho/build-ai-agent';
import { z } from 'zod';

const lookUpOrder = defineTool({
  name: 'look_up_order',
  description: 'Read an order by id',
  input: z.object({ id: z.string() }),
  annotations: { readOnlyHint: true },
  execute: async ({ id }) => ({ id, status: 'shipped' }),
});

The hint is a promise you make about your tool: plan mode trusts it.

File edits: the `editsFiles` marker

acceptEdits approves only tools marked as file edits: write_file and edit_file from createFsTools(), and any tool defined with editsFiles: true (stored as metadata.editsFiles). A tool is never a file edit by its name alone, so a tool of your own named write_file is not approved silently.

import { defineTool } from '@lousho/build-ai-agent';
import { z } from 'zod';

const appendLine = defineTool({
  name: 'append_line',
  description: 'Append a line to a file in the project',
  input: z.object({ path: z.string(), line: z.string() }),
  needsApproval: true,
  editsFiles: true,
  execute: async ({ path, line }) => `appended to ${path}: ${line}`,
});

Order of evaluation

For each tool call, in this order:

Argument validation, then preToolCall hooks. A hook deny ends here.
Permission rules (permissions). A deny rule ends here.
Tool guardrails. A block ends the run.
The tool’s own needsApproval. A deny ends here; an allow or ask rule replaces its ask.
The permission mode, on what is left.

So no mode turns a deny into a run: a hook deny, a deny rule and a needsApproval deny still deny in every mode, and acceptEdits never approves a call a guardrail blocked.

Setting and switching the mode

createAgent({ permissionMode }): the agent’s mode. A function is read at every tool call, so a mode you switch while a run is going applies to its next call.
agent.send(message, { permissionMode }) / agent.stream(...): the mode for that run only.
agent.session({ permissionMode }), then session.setPermissionMode(mode) and the session.permissionMode getter. The session reads its mode at every tool call of a turn, so setPermissionMode() during a turn (from a tool.start listener, say) applies from the next tool call of that turn. A session defaults to the agent’s mode.

Switching is always an explicit call to setPermissionMode(). Each switch is reported to onPermissionModeChange with { sessionId, from, to, at }:

import { createAgent } from '@lousho/build-ai-agent';

const agent = createAgent({
  provider,
  instructions: 'You are a coding agent.',
  onPermissionDecision: (entry) => console.log(entry.toolName, entry.decision, entry.mode),
  onPermissionModeChange: ({ sessionId, from, to, at }) => console.log(at, sessionId, `${from} -> ${to}`),
});

The system prompt is set when a run starts: only a run (or session turn) that starts in plan mode is told about it. A switch during a run is enforced by the tool-call gate alone, which is enough because the denied call’s reason tells the model.

The audit log

While a mode other than 'default' is set, every tool call’s decision is audited, even when the agent sets neither permissions nor onPermissionDecision: it goes to onPermissionDecision (when set) and is streamed as a permission.decision event. The entry’s mode field is set when the mode changed the call’s outcome: 'plan' or 'dontAsk' with decision: 'deny' and the mode’s reason, 'acceptEdits' with decision: 'allow'. When the mode denied a call an allow rule matched, the entry keeps that rule’s rule.index. Mode switches go to onPermissionModeChange. onPermissionDecision gets who the run acts for as its second argument, { principal }; the entry and the event carry no caller identity (see auth).

Sub-agents

A sub-agent (the task tool, a background task, createDelegateTool()) runs under the lead’s mode while the lead’s mode is not 'default', and under its own permissionMode otherwise. A sub-agent created with permissionMode: 'plan' stays in plan mode whatever the lead’s mode is. The mode is read at each of the sub-agent’s tool calls, so switching the lead’s session mode applies to a sub-agent that is running. That is what makes task safe in plan mode: the sub-agent cannot change anything either. A remote sub-agent (remoteAgent()) runs on another server under that server’s own permissions, so it cannot be held to the lead’s mode: in plan mode a task call to it is refused without contacting it, and in dontAsk mode a remote approval fails the task instead of pausing the lead.

Resuming after an approval

The mode is not saved in checkpoints or approval snapshots. A run continued by agent.approvals.resolve() uses the paused session’s current mode when the paused run belonged to a session, else the agent’s mode (not the mode a send() call passed). So a turn paused in 'default' and resolved after session.setPermissionMode('dontAsk') runs the approved call and then refuses the calls after it that would ask. In plan mode the approved call itself is refused too when its tool is not read-only. A resume in another process uses the mode the resuming agent or session has.

Get started

Build an agent

Compose agents

Run it reliably

Put it in front of people

Test and observe

Ship

Permission modes

The modes

Which tools are read-only

File edits: the `editsFiles` marker

Order of evaluation

Setting and switching the mode

The audit log

Sub-agents

Resuming after an approval

​The modes

​Which tools are read-only

​File edits: the editsFiles marker

​Order of evaluation

​Setting and switching the mode

​The audit log

​Sub-agents

​Resuming after an approval

The modes

Which tools are read-only

File edits: the `editsFiles` marker

Order of evaluation

Setting and switching the mode

The audit log

Sub-agents

Resuming after an approval