Atomic can create extensions. Ask it to build one for your use case.
Extensions
Extensions are TypeScript modules that extend Atomic’s behavior. They can subscribe to lifecycle events, register custom tools callable by the LLM, add commands, and more.Placement for /reload: Put extensions inKey capabilities:~/.atomic/agent/extensions/(global) or.atomic/extensions/(project-local) for auto-discovery; legacy.pipaths remain supported. Useatomic -e ./path.tsonly for quick tests. Extensions in auto-discovered locations can be hot-reloaded with/reload.
- Custom tools - Register tools the LLM can call via
pi.registerTool() - Event interception - Block or modify tool calls, inject context, observe/cancel deletion-only compaction, and customize branch summaries
- User interaction - Prompt users via
ctx.ui(select, confirm, input, notify) - Custom UI components - Full TUI components with keyboard input via
ctx.ui.custom()for complex interactions - Custom commands - Register commands like
/mycommandviapi.registerCommand() - Session persistence - Store state that survives restarts via
pi.appendEntry() - Custom rendering - Control how tool calls/results and messages appear in TUI
- Permission gates (confirm before
rm -rf,sudo, etc.) - Git checkpointing (stash at each turn, restore on branch)
- Path protection (block writes to
.env,node_modules/) - Compaction policies (cancel compaction or provide exact deletion targets)
- Conversation summaries (see
summarize.tsexample) - Interactive tools (questions, wizards, custom dialogs)
- Stateful tools (todo lists, connection pools)
- External integrations (file watchers, webhooks, CI triggers)
- Games while you wait (see
snake.tsexample)
Table of Contents
- Startup and lazy discovery
- Interactive callback isolation
- Quick Start
- Extension Locations
- Available Imports
- Writing an Extension
- Events
- ExtensionContext
- ExtensionCommandContext
- ExtensionAPI Methods
- State Management
- Custom Tools
- Custom UI
- Error Handling
- Mode Behavior
- Examples Reference
Startup and lazy discovery
Atomic keeps the interactive startup path responsive by registering lightweight command/tool wrappers first and deferring noncritical discovery work until after the session is usable. Built-in MCP, workflow, subagent, web-access, and Intercom extensions expose their public commands/tools immediately, but expensive server connections, workflow module evaluation, result-watcher priming, cleanup scans, and browser/provider loading may run in the background or on first explicit use. Commands such as/workflow list, named workflow runs/inputs, failed or durable workflow resume, /mcp, direct MCP tool calls, mcp({ search }), mcp({ describe }), mcp({ server }), and explicit reload/setup flows still wait for the resources they need before returning results; cold-cache MCP proxy describe first narrows hydration to prefix-matched or explicitly requested servers without starting unrelated servers after a prefix-directed miss, cold-cache unscoped MCP proxy search intentionally hydrates all uncached lazy servers so it can search the full configured tool set, env-selected MCP direct tools warm only their selected servers and refresh live tool registration when ready, paused live-workflow resume/pickers bypass full workflow discovery, autocomplete falls back to current/admin completions when lazy discovery fails, and workflow session restore reads only lightweight config during session_start so persisted-run settings apply without evaluating workflow modules.
Web-access and Intercom first-use calls await one shared lazy initializer plus the latest active lifecycle replay before executing. Failed initializer/replay attempts remain retryable. Session-scoped leases retire candidates synchronously on shutdown, reject calls spanning teardown, and require fresh initialization after restart; shutdown awaits retired replay/initializer cleanup before the extension instance can be replaced, and Intercom serializes replay with live lifecycle forwarding so matching ends and newer model selections cannot be overtaken by stale replay. Aborting one web-access caller during a shared wait does not cancel initialization for other callers, and host abort after provider/curator execution preserves the exact abort reason while explicit curator user cancellation remains result-shaped. Non-empty web_search/fetch_content batches with no successful items are marked as tool errors with stage diagnostics; partial successes remain successful and retain their completed items.
Bundled MCP startup, proxy calls, direct tools, and readiness-critical commands share a generation-scoped initializer and exact session lease. Failed background attempts remain retryable and single-flight; stale contexts cannot reuse initialized state; commands keep the state they initialized across lazy imports; and direct/proxy operations revalidate ownership after lifecycle-spanning waits and before metadata or SDK side effects. Caller cancellation races readiness, connection, manager-close, and UI-start waits with the exact reason, closes any UI runtime produced after cancellation, and does not cancel shared producers needed by survivors. Session restart/shutdown retires OAuth ownership immediately and uses bounded, observed cleanup so non-abortable SDK work cannot permanently block replacement sessions while late completion remains fenced. SDK-supported resource/tool requests still receive the call signal, though protocol-level remote cancellation is advisory; UI-backed MCP Apps calls preserve terminal cancellation ordering and keep successful result events mutually exclusive. Per-server timeoutMs applies a validated local-or-remote MCP tool-call inactivity limit at every call path while composing with the host abort signal; progress resets that timer, so a continuously reporting tool can run indefinitely, and omitting the field keeps the MCP SDK default.
Interactive callback isolation
Interactive Atomic sessions run the agent engine, extensions, tools, hooks, workflow code, and extension-owned render components in a supervised child process. The terminal host owns stdin and cached rendering, so a synchronous busy loop in one callback cannot stop keyboard handling, spinners, or render scheduling. The engine sends a heartbeat every 50 ms; Atomic identifies the active callback after a 250 ms heartbeat gap and marks the engine unresponsive after one second. Escape requests cooperative cancellation and escalates to terminating the engine when it cannot acknowledge; the interrupted result is reported as unknown and is never retried automatically. Dialogs andctx.ui.custom() components are proxied to the host as rendered lines with asynchronous input forwarding. Custom UI results must be JSON-safe. APIs that require a synchronous callback in the terminal process—raw onTerminalInput transforms, synchronous getEditorText, custom editor factories, autocomplete wrappers, component-factory widgets, and custom header/footer factories—are unavailable in isolated interactive mode and produce a warning rather than executing extension code in the host. Print and public RPC modes retain their existing execution model.
For session-style list pickers use ctx.ui.hostSessionPicker(request) instead of remote-rendering a selector through ctx.ui.custom(): the terminal host mounts the real built-in session selector natively, fed with JSON-safe rows (HostSessionPickerRow: SessionInfo with createdAt/modifiedAt epoch millis). Arrow-key navigation and search never cross the process boundary; only semantic events do — the returned handle exposes result (resolves with the selected row’s path, or undefined on cancel), update(rows), error(message), and close(), and the request’s onDelete(path) callback owns deletion (the host keeps the row until the extension replies with update or error). Every interactive host implements the identical API — in-process (no IPC) when not isolated, over the engine protocol when isolated — so callers never branch; the member is absent only on non-interactive surfaces (headless RPC, print), where commands should fail with an actionable error. See Host-native session picker for an example.
For structured forms use ctx.ui.hostInputForm(request). It accepts JSON-safe field descriptors (string, text, number, integer, boolean, or select, each with a raw initialValue) and resolves to a raw string record or undefined on cancellation. The terminal host owns the component, focus, validation, configured-keybinding handling, and mutable text state, so Tab, arrows, editing, Enter, Escape, and Ctrl+C are host-local rather than asynchronously forwarded to the engine child. Both interactive modes expose the same optional API; headless RPC and print omit it. See Host-native input form.
Quick Start
Create~/.atomic/agent/extensions/my-extension.ts:
--extension (or -e) flag:
Extension Locations
Security: Extensions run with your full system permissions and can execute arbitrary code. Only install from sources you trust.Extensions are auto-discovered from:
Additional paths via
settings.json:
Available Imports
Registry dependencies work too. Add a
package.json next to your extension (or in a parent directory), then install dependencies with Bun:
node_modules/ are resolved automatically.
For distributed Atomic packages installed with atomic install (npm or git), runtime deps must be in dependencies. Package installation uses production dependency installs by default, so devDependencies are not available at runtime; when npmCommand is configured, git packages use plain install for compatibility with wrappers.
Node.js built-ins (node:fs, node:path, etc.) are also available.
Writing an Extension
An extension exports a default factory function that receivesExtensionAPI. The factory can be synchronous or asynchronous:
Promise, Atomic awaits it before continuing startup. That means async initialization completes before session_start, before resources_discover, and before provider registrations queued via pi.registerProvider() are flushed.
Async factory functions
Use an async factory for one-time startup work such as fetching remote configuration or dynamically discovering available models.atomic --list-models.
Long-lived resources and shutdown
Extension factories may run in invocations that never start a session, such as metadata commands or early configuration checks. Do not start background resources such as processes, sockets, file watchers, or timers from the factory. Defer background resource startup untilsession_start or the command/tool/event that needs the resource. Register an idempotent session_shutdown handler to close any session-scoped resources you start.
Extension Styles
Single file - simplest, for small extensions:atomic here, from the running Atomic package/config), not the extension package’s own "name" field. The legacy pi key is still accepted as a compatibility shim. Run bun install in the extension directory, then imports from node_modules/ work automatically.
Events
Lifecycle Overview
Startup Events
project_trust
Fired before Atomic decides whether to trust a project with dynamic configs (.atomic, legacy .pi, or .agents/skills). It runs during startup and when session replacement (for example /resume) enters a cwd whose trust has not been resolved in the current process. Only user/global extensions and CLI -e extensions participate; project-local extensions are not loaded until after trust is resolved.
project_trust handler must return { trusted: "yes" | "no" | "undecided" }. A user/global or CLI extension that returns "yes" or "no" owns the decision; the first yes/no decision wins and suppresses the built-in trust prompt. Use remember: true to persist a yes/no decision; otherwise it applies only to the current process. Return "undecided" to let later handlers or the built-in trust flow decide. Check ctx.hasUI before prompting. If no handler returns yes/no, normal trust resolution continues: saved trust.json decisions apply first, then defaultProjectTrust controls whether Atomic asks, trusts, or declines by default.
Resource Events
resources_discover
Fired aftersession_start so extensions can contribute additional skill, prompt, and theme paths.
The startup path uses reason: "startup". Reload uses reason: "reload".
Session Events
See Session Format for session storage internals and the SessionManager API.session_start
Fired when a session is started, loaded, or reloaded.session_info_changed
Fired when the current session display name is set via/name, RPC, or pi.setSessionName().
session_before_switch
Fired before starting a new session (/new) or switching sessions (/resume).
session_shutdown for the old extension instance, reloads and rebinds extensions for the new session, then emits session_start with reason: "new" | "resume" and previousSessionFile.
Do cleanup work in session_shutdown, then reestablish any in-memory state in session_start.
session_before_fork
Fired when forking via/fork or cloning via /clone.
session_shutdown for the old extension instance, reloads and rebinds extensions for the new session, then emits session_start with reason: "fork" and previousSessionFile.
Do cleanup work in session_shutdown, then reestablish any in-memory state in session_start.
session_before_compact / session_compact
Fired by/compact and auto-compaction, including a threshold crossing detected after tool results enter the prospective next-turn context. Atomic prepares the complete active transcript except for the exact newest preserve_recent context-visible messages. Extensions may cancel or provide a complete, non-empty compactedText replacement for that region; they cannot move firstKeptEntryId. The override is persisted verbatim and works without provider credentials. A successful post-tool compaction returns its rebuilt context directly to the already-active Pi loop; it does not start a separate continuation. Cancellation or failure prevents that loop’s follow-up provider request.
session_before_tree / session_tree
Fired on/tree navigation. See Sessions for tree navigation concepts.
session_shutdown
Fired before a started session runtime is torn down. Use this to clean up resources opened fromsession_start or other session-scoped hooks.
Agent Events
before_agent_start
Fired after user submits prompt, before agent loop. Can inject a message and/or modify the system prompt.systemPromptOptions field gives extensions access to the same structured data Atomic uses to build the system prompt. This lets you inspect what Atomic has loaded — custom prompts, guidelines, tool snippets, context files, skills — without re-discovering resources or re-parsing flags. Use it when your extension needs to make deep, informed changes to the system prompt while respecting user-provided configuration.
Inside before_agent_start, event.systemPrompt and ctx.getSystemPrompt() both reflect the chained system prompt as of the current handler. Later before_agent_start handlers can still modify it again.
agent_start / agent_end / agent_settled
agent_start begins a low-level run. agent_end fires when that run ends, but Atomic may still retry, compact and retry, or deliver queued follow-ups. Use agent_settled when a status integration needs to know Atomic has no automatic continuation left.
turn_start / turn_end
Fired for each turn (one LLM response + tool calls).message_start / message_update / message_end
Fired for message lifecycle updates.message_startandmessage_endfire for user, assistant, and toolResult messages.message_updatefires for assistant streaming updates.message_endhandlers can return{ message }to replace the finalized message. The replacement must keep the samerole.
tool_execution_start / tool_execution_update / tool_execution_end
Fired for tool execution lifecycle updates. In parallel tool mode:tool_execution_startis emitted in assistant source order during the preflight phasetool_execution_updateevents may interleave across toolstool_execution_endis emitted in tool completion order after each tool is finalized- final
toolResultmessage events are still emitted later in assistant source order
context
Fired before each LLM call. Modify messages non-destructively. See Session Format for message types. When tool output crosses the buffered compaction threshold, the post-tool compaction preflight finishes before this hook runs for the follow-up call, soevent.messages contains the rebuilt compacted context.
before_provider_headers
Fires after outgoing HTTP headers are assembled. Mutateevent.headers to add, override, or remove headers. The event also identifies the provider and model.
before_provider_request
Fired after the provider-specific payload is built, right before the request is sent. Handlers run in extension load order. Returningundefined keeps the payload unchanged. Returning any other value replaces the payload for later handlers and for the actual request.
This hook can rewrite provider-level system instructions or remove them entirely. Those payload-level changes are not reflected by ctx.getSystemPrompt(), which reports Atomic’s system prompt string rather than the final serialized provider payload.
after_provider_response
Fired after an HTTP response is received and before its stream body is consumed. Handlers run in extension load order.Model Events
model_select
Fired when the model changes via/model command, model cycling (CTRL+P), or session restore.
thinking_level_select
Fired when the thinking level changes. This is notification-only; handler return values are ignored.pi.setThinkingLevel(), model changes, or built-in thinking-level controls change the active thinking level.
Tool Events
tool_call
Fired aftertool_execution_start, before the tool executes. Can block. Use isToolCallEventType to narrow and get typed inputs.
Before tool_call runs, Atomic waits for previously emitted Agent events to finish draining through AgentSession. This means ctx.sessionManager is up to date through the current assistant tool-calling message.
In the default parallel tool execution mode, sibling tool calls from the same assistant message are preflighted sequentially, then executed concurrently. tool_call is not guaranteed to see sibling tool results from that same assistant message in ctx.sessionManager.
event.input is mutable. Mutate it in place to patch tool arguments before execution.
Behavior guarantees:
- Mutations to
event.inputaffect the actual tool execution - Later
tool_callhandlers see mutations made by earlier handlers - No re-validation is performed after your mutation
- Return values from
tool_callonly control blocking via{ block: true, reason?: string }
Typing custom tool input
Custom tools should export their input type:isToolCallEventType with explicit type parameters:
tool_result
Fired after tool execution finishes and beforetool_execution_end plus the final tool result message events are emitted. Can modify result.
In parallel tool mode, tool_result and tool_execution_end may interleave in tool completion order, while final toolResult message events are still emitted later in assistant source order.
tool_result handlers chain like middleware:
- Handlers run in extension load order
- Each handler sees the latest result after previous handler changes
- Handlers can return partial patches (
content,details, orisError); omitted fields keep their current values
ctx.signal for nested async work inside the handler. This lets Escape cancel model calls, fetch(), and other abort-aware operations started by the extension.
User Bash Events
user_bash
Fired when user executes! or !! commands. Can intercept.
Input Events
input
Fired when user input is received, after extension commands are checked but before skill and template expansion. The event sees the raw input text, so/skill:foo and /template are not yet expanded.
Processing order:
- Extension commands (
/cmd) checked first - if found, handler runs and input event is skipped inputevent fires - can intercept, transform, or handle- If not handled: skill commands (
/skill:name) expanded to skill content - If not handled: prompt templates (
/template) expanded to template content - Agent processing begins (
before_agent_start, etc.)
continue- pass through unchanged (default if handler returns nothing)transform- modify text/images, then continue to expansionhandled- skip agent entirely (first handler to return this wins)
streamingBehavior-aware routing.
ExtensionContext
All handlers receivectx: ExtensionContext.
ctx.ui
UI methods for user interaction. See Custom UI for full details.ctx.hasUI
false in print mode (-p) and JSON mode. true in interactive and RPC mode. In RPC mode, dialog methods (select, confirm, input, editor) work via the extension UI sub-protocol, and fire-and-forget methods (notify, setStatus, setWidget, setTitle, setEditorText) emit requests to the client. Some TUI-specific methods are no-ops or return defaults (see RPC mode).
ctx.cwd
Current working directory. UseCONFIG_DIR_NAME instead of hardcoding .atomic (or legacy .pi) when constructing project-local config paths. Rebranded distributions can use a different config directory name.
ctx.isProjectTrusted()
Returns whether project-local trust is active for the current session context. This includes temporary trust decisions and CLI trust overrides, not just saved decisions in the global trust store. Use this before reading project-local extension configuration that should only be honored for trusted projects.ctx.sessionManager
Read-only access to session state. See Session Format for the full SessionManager API and entry types. Fortool_call, this state is synchronized through the current assistant message before handlers run. In parallel tool execution mode it is still not guaranteed to include sibling tool results from the same assistant message.
ctx.modelRegistry / ctx.model
Access to models and API keys.ctx.signal
The current agent abort signal, orundefined when no agent turn is active.
Use this for abort-aware nested work started by extension handlers, for example:
fetch(..., { signal: ctx.signal })- model calls that accept
signal - file or process helpers that accept
AbortSignal
ctx.signal is typically defined during active turn events such as tool_call, tool_result, message_update, and turn_end.
It is usually undefined in idle or non-turn contexts such as session events, extension commands, and shortcuts fired while Atomic is idle.
ctx.isIdle() / ctx.abort() / ctx.hasPendingMessages()
Control flow helpers.ctx.isProjectTrusted()
Returns whether project-local trust is active for the current extension context. Use this before reading project-local config, loading project-local resources, or exposing actions that should only run after the user has trusted the cwd.ctx.shutdown()
Request a graceful shutdown of Atomic.- Interactive mode: Deferred until the agent becomes idle (after processing all queued steering and follow-up messages).
- RPC mode: Deferred until the next idle state (after completing the current command response, when waiting for the next command).
- Print mode: No-op. The process exits automatically when all prompts are processed.
session_shutdown event to all extensions before exiting. Available in all contexts (event handlers, tools, commands, shortcuts).
ctx.getContextUsage()
Returns current context usage for the active model. Uses last assistant usage when available, then estimates tokens for trailing messages.ctx.compact()
Trigger Atomic’s verbatim line compactor without awaiting completion. The planner emits numbered deleted-line ranges only; Atomic validates them and reconstructs retained text mechanically. Usecompression_ratio (fraction of compactable lines to keep), client-side preserve_recent (an exact context-visible message count), and query to tune the run, and onComplete/onError for follow-up actions.
query parameter guides relevance selection inside the fixed prompt; it is not replacement prose. Extensions that need an offline replacement can return compactedText from session_before_compact.
ctx.getSystemPrompt()
Returns Atomic’s current system prompt string.- During
before_agent_start, this reflects chained system-prompt changes made so far for the current turn. - It does not include later
contextmessage mutations. - It does not include
before_provider_requestpayload rewrites. - If later-loaded extensions run after yours, they can still change what is ultimately sent.
ExtensionCommandContext
Command handlers receiveExtensionCommandContext, which extends ExtensionContext with session control methods. These are only available in commands because they can deadlock if called from event handlers.
ctx.waitForIdle()
Wait for the agent to finish streaming:ctx.newSession(options?)
Create a new session:parentSession: parent session file to record in the new session headersetup: mutate the new session’sSessionManagerbeforewithSessionrunswithSession: run post-switch work against a fresh replacement-session context. Do not use captured oldpi/ commandctx; see Session replacement lifecycle and footguns.
ctx.fork(entryId, options?)
Fork from a specific entry, creating a new session file:position:"before"(default) forks before the selected user message, restoring that prompt into the editorposition:"at"duplicates the active path through the selected entry without restoring editor textwithSession: run post-switch work against a fresh replacement-session context. Do not use captured oldpi/ commandctx; see Session replacement lifecycle and footguns.
ctx.navigateTree(targetId, options?)
Navigate to a different point in the session tree:summarize: Whether to generate a summary of the abandoned branchcustomInstructions: Custom instructions for the summarizerreplaceInstructions: If true,customInstructionsreplaces the default prompt instead of being appendedlabel: Label to attach to the branch summary entry (or target entry if not summarizing)
ctx.switchSession(sessionPath, options?)
Switch to a different session file:withSession: run post-switch work against a fresh replacement-session context. Do not use captured oldpi/ commandctx; see Session replacement lifecycle and footguns.
SessionManager.list() or SessionManager.listAll() methods:
Session replacement lifecycle and footguns
withSession receives a fresh ReplacedSessionContext, which extends ExtensionCommandContext with async sendMessage() and sendUserMessage() helpers bound to the replacement session.
Lifecycle and footguns:
withSessionruns only after the old session has emittedsession_shutdown, the old runtime has been torn down, the replacement session has been rebound, and the new extension instance has already receivedsession_start.- The callback still executes in the original closure, not inside the new extension instance. That means your old extension instance may already have run its shutdown cleanup before
withSessionstarts. - Captured old
pi/ old commandctxsession-bound objects are stale after replacement and will throw if used. Use only thectxpassed towithSessionfor session-bound work. - Previously extracted raw objects are still your responsibility. For example, if you capture
const sm = ctx.sessionManagerbefore replacement,smis still the oldSessionManagerobject. Do not reuse it after replacement. - Code in
withSessionshould assume any state invalidated by yoursession_shutdownhandler is already gone. Only capture plain data that survives shutdown cleanly, such as strings, ids, and serialized config.
ctx.reload()
Run the same reload flow as/reload.
await ctx.reload()emitssession_shutdownfor the current extension runtime- It then reloads resources and emits
session_startwithreason: "reload"andresources_discoverwith reason"reload" - The currently running command handler still continues in the old call frame
- Code after
await ctx.reload()still runs from the pre-reload version - Code after
await ctx.reload()must not assume old in-memory extension state is still valid - After the handler returns, future commands/events/tool calls use the new extension version
await ctx.reload(); return;).
Tools run with ExtensionContext, so they cannot call ctx.reload() directly. Use a command as the reload entrypoint, then expose a tool that queues that command as a follow-up user message.
Example tool the LLM can call to trigger reload:
ExtensionAPI Methods
pi.on(event, handler)
Subscribe to events. See Events for event types and return values.pi.registerTool(definition)
Register a custom tool callable by the LLM. See Custom Tools for full details.pi.registerTool() works both during extension load and after startup. You can call it inside session_start, command handlers, or other event handlers. New tools are refreshed immediately in the same session, so they appear in pi.getAllTools() and are callable by the LLM without /reload.
Use pi.setActiveTools() to enable or disable tools (including dynamically added tools) at runtime.
Use promptSnippet to opt a custom tool into a one-line entry in Available tools, and promptGuidelines to append tool-specific bullets to the default Guidelines section when the tool is active.
Important: promptGuidelines bullets are appended flat to the Guidelines section with no tool name prefix. Each guideline must name the tool it refers to — avoid “Use this tool when…” because the LLM cannot tell which tool “this” means. Write “Use my_tool when…” instead.
See dynamic-tools.ts for a full example.
Use Atomic’s export rather than importing StringEnum directly from Pi. It preserves Pi’s Google-compatible runtime schema while keeping the schema typed against Atomic’s direct TypeBox version.
pi.sendMessage(message, options?)
Inject a custom message into the session. The call returnsvoid | Promise<void> for compatibility with synchronous hosts; use await Promise.resolve(pi.sendMessage(...)) when admission or routing failure must be observed. Atomic’s AgentSession runtime returns an admission receipt: it settles after the message is accepted by the local queue or workflow late-message route, without waiting for the resulting model turn to finish.
deliverAs- Delivery mode:"steer"(default) - Queues the message while streaming. Delivered after the current assistant turn finishes executing its tool calls, before the next LLM call."followUp"- Waits for agent to finish. Delivered only when agent has no more tool calls."nextTurn"- Queued for next user prompt. Does not interrupt or trigger anything."interrupt"- WithtriggerTurn: true, aborts an active streaming turn and immediately starts a new turn with the custom message. When idle, behaves like a triggered custom message.
triggerTurn: true- If agent is idle, trigger an LLM response immediately. Required for"interrupt"; ignored for"nextTurn".excludeFromContext: true- Render and persist the custom message without adding it to LLM context. With nodeliverAs, this remains display-only even while the agent is streaming.interruptAbortMessage- Optional text used to replace generic abort results (for exampleOperation aborted) whendeliverAs: "interrupt"aborts an active turn.
pi.sendMessages(messages, options?)
Atomically admit a batch of custom messages in array order. The call returnsvoid | Promise<void> for compatibility with synchronous hosts; use await Promise.resolve(pi.sendMessages(...)) when admission or routing failure must be observed. The promise is an admission receipt and does not wait for the resulting model turn. Admission is indivisible; use this when a prelude and terminal notice must stay contiguous without globally serializing other extension work.
triggerTurn, excludeFromContext, and deliverAs: "steer" | "followUp" | "nextTurn". Interrupt delivery remains a single-message operation.
pi.sendUserMessage(content, options?)
Send a user message to the agent. UnlikesendMessage() which sends custom messages, this sends an actual user message that appears as if typed by the user. Always triggers a turn.
deliverAs- Required when agent is streaming:"steer"- Queues the message for delivery after the current assistant turn finishes executing its tool calls"followUp"- Waits for agent to finish all tools
deliverAs, throws an error.
See send-user-message.ts for a complete example.
pi.appendEntry(customType, data?)
Persist extension state (does NOT participate in LLM context).entry_appended with the durable entry. This lets extensions react to session entries without polling.
pi.registerEntryRenderer(customType, renderer)
Register a TUI renderer for durable custom entries created bypi.appendEntry(). These entries render in the transcript but do not enter model context.
pi.setSessionName(name)
Set the session display name (shown in session selector instead of first message).pi.getSessionName()
Get the current session name, if set.pi.setLabel(entryId, label)
Set or clear a label on an entry. Labels are user-defined markers for bookmarking and navigation (shown in/tree selector).
pi.registerCommand(name, options)
Register a command. If multiple extensions register the same command name, Atomic keeps them all and assigns numeric invocation suffixes in load order, for example/review:1 and /review:2.
/command ...:
pi.getCommands()
Get the slash commands available for invocation viaprompt in the current session. Includes extension commands, prompt templates, and skill commands.
The list matches the RPC get_commands ordering: extensions first, then templates, then skills.
sourceInfo as the canonical provenance field. Do not infer ownership from command names or from ad hoc path parsing.
Built-in interactive commands (like /model and /settings) are not included here. They are handled only in interactive
mode and would not execute if sent via prompt.
pi.registerMessageRenderer(customType, renderer)
Register a custom TUI renderer for messages with yourcustomType. See Custom UI.
pi.registerShortcut(shortcut, options)
Register a keyboard shortcut. See Keybindings for the shortcut format and built-in keybindings.pi.registerFlag(name, options)
Register a CLI flag.pi.exec(command, args, options?)
Execute a shell command.pi.getActiveTools() / pi.getAllTools() / pi.setActiveTools(names)
Manage active tools. This works for both built-in tools and dynamically registered tools.pi.getActiveTools() returns the active tool names as string[]; pi.getAllTools() returns metadata for all configured tools.
pi.getAllTools() returns name, description, parameters, promptGuidelines, and sourceInfo.
Typical sourceInfo.source values:
builtinfor built-in toolssdkfor tools passed viacreateAgentSession({ customTools })- extension source metadata for tools registered by extensions
pi.setModel(model)
Set the current model. Returnsfalse if no API key is available for the model. See Custom models for configuring custom models.
pi.getThinkingLevel() / pi.setThinkingLevel(level)
Get or set the thinking level. Level is clamped to model capabilities (non-reasoning models always use"off"; "xhigh" and "max" require model support). Changes emit thinking_level_select.
pi.events
Shared event bus for communication between extensions:Native providers
In addition toregisterProvider(name, config), extensions can register a complete native Provider from @earendil-works/pi-ai with pi.registerProvider(provider). Use the native overload for provider-owned authentication, catalog refresh, and transport behavior; use the config overload for ordinary proxies and custom endpoints.
pi.registerProvider(name, config)
Register or override a model provider dynamically. Useful for proxies, custom endpoints, or team-wide model configurations. Calls made during the extension factory function are queued and applied once the runner initialises. Calls made after that — for example from a command handler following a user setup flow — take effect immediately without requiring a/reload.
If you need to discover models from a remote endpoint, prefer an async extension factory over deferring the fetch to session_start. Atomic waits for the factory before startup continues, so the registered models are available immediately, including to atomic --list-models.
name- Display name for the provider in UI such as/login.baseUrl- API endpoint URL. Required when defining models.apiKey- API key literal or explicit environment variable reference ($ENV_VARor${ENV_VAR}). Required when defining models (unlessoauthprovided).api- API type:"anthropic-messages","openai-completions","openai-responses", etc.headers- Custom headers to include in requests.authHeader- If true, addsAuthorization: Bearerheader automatically.models- Array of model definitions. If provided, replaces all existing models for this provider. Model definitions can setbaseUrlto override the provider endpoint for that model.oauth- OAuth provider config for/loginsupport. When provided, the provider appears in the login menu.auth.apiKey- Provider-owned API-key or connection setup for/login. Itsnameappears in the provider list andlogin({ signal, prompt })returns the credential Atomic persists. Extension providers registered only in the isolated interactive engine child are synchronized into the host’s/loginlist; their login callback and credential-dependent model refresh still execute in the child, while prompts are rendered by the terminal host.streamSimple- Custom streaming implementation for non-standard APIs.
pi.unregisterProvider(name)
Remove a previously registered provider and its models. Built-in models that were overridden by the provider are restored. Has no effect if the provider was not registered. LikeregisterProvider, this takes effect immediately when called after the initial load phase, so a /reload is not required.
State Management
Extensions with state should store it in tool resultdetails for proper branching support:
Custom Tools
Register tools the LLM can call viapi.registerTool(). Tools appear in the system prompt and can have custom rendering.
Use promptSnippet for a short one-line entry in the Available tools section in the default system prompt. If omitted, custom tools are left out of that section.
Use promptGuidelines to add tool-specific bullets to the default system prompt Guidelines section. These bullets are included only while the tool is active (for example, after pi.setActiveTools([...])).
Important: promptGuidelines bullets are appended flat to the Guidelines section with no tool name prefix or grouping. Each guideline must name the tool it refers to — avoid “Use this tool when…” because the LLM cannot tell which tool “this” means. Write “Use my_tool when…” instead.
Note: Some models are idiots and include the @ prefix in tool path arguments. Built-in tools strip a leading @ before resolving paths. If your custom tool accepts a path, normalize a leading @ as well.
If your custom tool mutates files, use withFileMutationQueue() so it participates in the same per-file queue as built-in edit and write. This matters because tool calls run in parallel by default. Without the queue, two tools can read the same old file contents, compute different updates, and then whichever write lands last overwrites the other.
Example failure case: your custom tool edits foo.ts while built-in edit also changes foo.ts in the same assistant turn. If your tool does not participate in the queue, both can read the original foo.ts, apply separate changes, and one of those changes is lost.
Pass the real target file path to withFileMutationQueue(), not the raw user argument. Resolve it to an absolute path first, relative to ctx.cwd or your tool’s working directory. For existing files, the helper canonicalizes through realpath(), so symlink aliases for the same file share one queue. For new files, it falls back to the resolved absolute path because there is nothing to realpath() yet.
Queue the entire mutation window on that target path. That includes read-modify-write logic, not just the final write.
Tool Definition
isError: true on the result and reports it to the LLM), throw an error from execute. Returning a value never sets the error flag regardless of what properties you include in the return object.
Early termination: Return terminate: true from execute() to hint that the automatic follow-up LLM call should be skipped after the current tool batch. This only takes effect when every finalized tool result in that batch is terminating. Atomic does not register structured_output in normal agent sessions by default; use createStructuredOutputTool({ schema, capture, output, name }) when an extension, SDK session, workflow stage, or subagent runtime needs a schema-backed final-answer tool. The factory uses the supplied schema as the tool parameters directly, captures the tool arguments as whatever JSON value matches the schema, emits the same pretty-printed JSON as the terminating tool-result text for atomic -p, optionally writes them to the configured output.outputPath, and terminates the turn. In text print mode, a terminating result from a factory-created structured-output tool is emitted to stdout as the final response. Custom factory names are opt-in tools: if you register final_decision, include final_decision in any explicit tools allowlist; if you register the default structured_output name, it is available only to that session/runtime.
StringEnum from @bastani/atomic for string enums. It retains Pi’s Google-compatible schema and composes with Atomic’s direct TypeBox types; Type.Union/Type.Literal doesn’t work with Google’s API.
Argument preparation: prepareArguments(args) is optional. If defined, it runs before schema validation and before execute(). Use it only when a custom tool must normalize arguments before validation. Return the object you want validated against parameters, keep the public schema strict, and avoid advertising deprecated fields.
Overriding Built-in Tools
Extensions can override built-in tools (read, bash, edit, write, find, search, ask_user_question, todo) by registering a tool with the same name. Interactive mode displays a warning when this happens.
--no-builtin-tools to start without any built-in tools while keeping extension tools enabled:
read with logging and access control.
Rendering: Built-in renderer inheritance is resolved per slot. Execution override and rendering override are independent. If your override omits renderCall, the built-in renderCall is used. If your override omits renderResult, the built-in renderResult is used. If your override omits both, the built-in renderer is used automatically (syntax highlighting, diffs, etc.). This lets you wrap built-in tools for logging or access control without reimplementing the UI.
Prompt metadata: promptSnippet and promptGuidelines are not inherited from the built-in tool. If your override should keep those prompt instructions, define them on the override explicitly.
Your implementation must match the exact result shape, including the details type. The UI and session logic depend on these shapes for rendering and state tracking.
Built-in tool implementations:
- read.ts -
ReadToolDetails - bash.ts -
BashToolDetails - edit.ts
- write.ts
- grep.ts -
GrepToolDetails - find.ts -
FindToolDetails - ls.ts -
LsToolDetails
Remote Execution
Built-in tools support pluggable operations for delegating to remote systems (SSH, containers, etc.):ReadOperations, WriteOperations, EditOperations, BashOperations, LsOperations, GrepOperations, FindOperations
For user_bash, extensions can reuse atomic’s local shell backend via createLocalBashOperations() instead of reimplementing local process spawning, shell resolution, and process-tree termination.
The bash tool also supports a spawn hook to adjust the command, cwd, or env before execution:
--ssh flag.
Output Truncation
Tools MUST truncate their output to avoid overwhelming the LLM context. Large outputs can cause:- Context overflow errors (prompt too long)
- Compaction failures
- Degraded model performance
- Use
truncateHeadfor content where the beginning matters (search results, file reads) - Use
truncateTailfor content where the end matters (logs, command output) - Always inform the LLM when output is truncated and where to find the full version
- Document the truncation limits in your tool’s description
rg (ripgrep) with proper truncation.
Multiple Tools
One extension can register multiple tools with shared state:Custom Rendering
Tools can providerenderCall and renderResult for custom TUI display. See TUI components for the full component API and tool-execution.ts for how tool rows are composed.
By default, tool output is wrapped in a Box that handles padding and background. A defined renderCall or renderResult must return a Component. If a slot renderer is not defined, tool-execution.ts uses fallback rendering for that slot.
Set renderShell: "self" when the tool should render its own shell instead of using the default Box. This is useful for tools that need complete control over framing or background behavior, for example large previews that must stay visually stable after the tool settles.
renderCall and renderResult each receive a context object with:
args- the current tool call argumentsstate- shared row-local state acrossrenderCallandrenderResultlastComponent- the previously returned component for that slot, if anyinvalidate()- request a rerender of this tool rowtoolCallId,cwd,executionStarted,argsComplete,isPartial,expanded,showImages,isError
context.state for cross-slot shared state. Keep slot-local caches on the returned component instance when you want to reuse and mutate the same component across renders.
renderCall
Renders the tool call or header:renderResult
Renders the tool result or output:Component such as an empty Container.
Keybinding Hints
UsekeyHintIfBound() when an affordance should disappear if the action has no effective keybinding. Add surrounding punctuation only when the helper returns text:
keyHint(keybinding, description)- Formats a configured keybinding id such as"app.tools.expand"or"tui.select.confirm"; use it when the binding is required by the surrounding UIkeyHintIfBound(keybinding, description)- Formats the hint only when the action has an effective key list; use it for optional affordances and conditionally compose parentheses or separatorskeyText(keybinding)- Returns the raw configured key text for a keybinding idrawKeyHint(key, description)- Format a raw key string
- Coding-agent ids use the
app.*namespace, for exampleapp.tools.expand,app.editor.external,app.session.rename - Shared TUI ids use the
tui.*namespace, for exampletui.select.confirm,tui.select.cancel,tui.input.tab
keybindings.json uses those same namespaced ids.
Custom editors and ctx.ui.custom() components receive keybindings: KeybindingsManager as an injected argument. They should use that injected manager directly instead of calling getKeybindings() or setKeybindings().
Best Practices
- Use
Textwith padding(0, 0). The default Box handles padding. - Use
\nfor multi-line content. - Handle
isPartialfor streaming progress. - Support
expandedfor detail on demand. - Keep default view compact.
- Read
context.argsinrenderResultinstead of copying args intocontext.state. - Use
context.stateonly for data that must be shared across call and result slots. - Reuse
context.lastComponentwhen the same component instance can be updated in place. - Use
renderShell: "self"only when the default boxed shell gets in the way. In self-shell mode the tool is responsible for its own framing, padding, and background.
Fallback
If a slot renderer is not defined or throws:renderCall: Shows the tool namerenderResult: Shows raw text fromcontent
Custom UI
Extensions can interact with users viactx.ui methods and customize how messages/tools render.
For custom components, see TUI components which has copy-paste patterns for:
- Selection dialogs (SelectList)
- Async operations with cancel (BorderedLoader)
- Settings toggles (SettingsList)
- Status indicators (setStatus)
- Working message, visibility, and indicator during streaming (
setWorkingMessage,setWorkingVisible,setWorkingIndicator) - Widgets above/below editor (setWidget)
- Autocomplete providers layered on top of built-in slash/path completion (addAutocompleteProvider)
- Custom footers (setFooter)
Dialogs
Timed Dialogs with Countdown
Dialogs support atimeout option that auto-dismisses with a live countdown display:
select()returnsundefinedconfirm()returnsfalseinput()returnsundefined
Manual Dismissal with AbortSignal
For more control (e.g., to distinguish timeout from user cancel), useAbortSignal:
Widgets, Status, and Footer
ctx.ui.theme.fg(...).
Autocomplete Providers
Usectx.ui.addAutocompleteProvider() to stack custom autocomplete logic on top of the built-in slash-command and path provider.
Typical pattern:
- inspect the text before the cursor
- return your own suggestions when your extension-specific syntax matches
- otherwise delegate to
current.getSuggestions(...) - delegate
applyCompletion(...)unless you need custom insertion behavior
gh issue list and filters them locally for fast #... completion. It requires GitHub CLI (gh) and a GitHub repository checkout.
Custom Components
For complex UI, usectx.ui.custom(). This temporarily replaces the editor with your component until done() is called:
tui- TUI instance (for screen dimensions, focus management)theme- Current theme for stylingkeybindings- App keybinding manager (for checking shortcuts)done(value)- Call to close component and return value
{ signal } to dismiss the custom UI if an operation is aborted; the returned promise rejects with the signal reason.
See TUI components for the full component API.
Overlay Mode (Experimental)
Pass{ overlay: true } to render the component as a floating modal on top of existing content, without clearing the screen:
overlayOptions. Use onHandle to control visibility programmatically:
OverlayOptions API and overlay-qa-tests.ts for examples.
Custom Editor
Replace the main input editor with a custom implementation (vim mode, emacs mode, etc.):- Extend
CustomEditor(not baseEditor) to get app keybindings (escape to abort, ctrl+d, model switching) - Call
super.handleInput(data)for keys you don’t handle - Factory receives
tui,theme, andkeybindingsfrom the app - Use
ctx.ui.getEditorComponent()beforesetEditorComponent()to wrap the previously configured custom editor - Pass
undefinedto restore default:ctx.ui.setEditorComponent(undefined)
Message Rendering
Register a custom renderer for messages with yourcustomType:
pi.sendMessage():
Theme Colors
All render functions receive atheme object. See Themes for creating custom themes and the full color palette.
Error Handling
- Extension errors are logged, agent continues
tool_callerrors block the tool (fail-safe)- Tool
executeerrors must be signaled by throwing; the thrown error is caught, reported to the LLM withisError: true, and execution continues
Mode Behavior
In non-interactive modes, check
ctx.hasUI before using UI methods.