Skip to main content

Writing extensions

Writing an Extension

An extension exports a default factory function that receives ExtensionAPI. The factory can be synchronous or asynchronous:
Editable user, project, and package extensions and user workflows are loaded through jiti, so TypeScript works without compilation. /reload uses content-hash invalidation across the complete imported file graph: an unchanged graph can reuse its evaluated factory, while a direct edit or a transitive dependency edit re-evaluates that extension’s modules. Imports from Atomic’s supplied core packages keep the running host’s classes and shared state across /reload, including on Windows. The supported @earendil-works/pi-coding-agent compatibility import shares those exports with @bastani/atomic, so class comparisons and instanceof checks work across both names after reload. Edits to your extension and its imported local helpers still take effect; restart Atomic after updating Atomic itself. In Bun compiled or bundled single-file builds, Atomic’s five fixed installed builtin extension bundles (workflows, subagents, MCP, web access, and Intercom) take a separate startup path. Atomic installs its live host-module bridge, imports each precompiled bundle natively once, and reuses the evaluated factory across /reload. This avoids jiti source reads, transforms, hashing, and graph manifests for immutable shipped code. A builtin bundle’s module-scoped state is therefore not re-evaluated by /reload in those builds. This optimization is limited to exact installed entries of identity-verified Atomic packages; editable extensions and workflows retain the dynamic behavior above. If the factory returns a 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.
This pattern makes the fetched models available during normal startup and to 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 until session_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:
Directory with index.ts - for multi-file extensions:
Package with dependencies - for extensions that need npm packages:
The manifest key is the configured Atomic app name (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.

State Management

Choose the store that matches the lifetime you need:
  • Tool result details — reconstructs across /branch and /resume from the transcript.
  • pi.appendEntry() — durable custom entries that survive process restart. They do not enter model context.
  • sessionScopedExtensionState() — in-memory objects that survive /reload for the current process. They do not survive process restart.
In Bun single-file builds, an editable file extension whose imported graph is unchanged can reuse its evaluated factory, so its module-scoped variables may survive /reload. An edit anywhere in that graph re-evaluates its modules and resets those singletons. The five fixed installed builtin bundles always reuse their evaluated factories and module state across /reload, as described above. Extensions with state that must follow conversation branches should store it in tool result details:

Session-scoped in-memory state

Import sessionScopedExtensionState from @bastani/atomic when an extension must keep a live object across /reload — registries, abort controllers, connection pools, or any other handle that cannot be rebuilt from the transcript.
Required scope. Pass the extension’s pi.events facade (or the session EventBus itself). The host resolves that facade to the canonical session bus, so every load generation of one session re-binds to the same object. Two in-process sessions with distinct buses stay isolated. Do not pass an arbitrary object: an unregistered scope is treated as its own bus and will not re-bind after reload. Session-wide key namespace. Keys are not automatically namespaced by extension. Two extensions that pass the same key on the same session receive the first extension’s object; the later factory is not called. Prefix every key with a stable extension identity. Key-versioning. Append a version suffix and bump it when the stored shape changes, for example "my-extension:counter:v1""my-extension:counter:v2". The new key declines the incompatible predecessor instead of reusing it under a new type. Reload behavior. /reload builds a new pi.events facade that still forwards to the same bus. Calling sessionScopedExtensionState again with the same namespaced key returns the existing object and does not invoke create. The reload transaction does not clone this object or roll back mutations that extension factory code makes to it. Keep factory setup idempotent, and mutate durable state only after the new generation starts when failed reloads must not affect it. Entries live exactly as long as that bus. They are not written to the session file; use pi.appendEntry() when the data must survive process restart. Shutdown. session_shutdown still runs for resources you opened. If the object holds sockets, watchers, or timers, close them there. The next session_start or first use can recreate them inside the same session-scoped object.

Custom Tools

Register tools the LLM can call via pi.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

parameters is required, including for no-argument tools (use Type.Object({})). Registration rejects missing, null, array, and primitive schema values before they can break a provider request. This checks the schema container, not its JSON Schema type: object-valued union and non-object-type schemas remain accepted and unchanged.
Signaling errors: To mark a tool execution as failed (sets 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, or workflow stage 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.
Important: Use 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.

Constrained sampling

ToolDefinition.constrainedSampling is preserved for extension tools, SDK customTools, wrappers, and isolated execution. It accepts false or the exported ConstrainedSamplingConfig:
Exact modes:
  • { type: "json_schema", strict: "prefer" } requests strict provider enforcement and falls back to ordinary tool calling when unavailable.
  • { type: "json_schema", strict: "require" } fails the request rather than silently weakening the constraint.
  • { type: "grammar", variants: { openai_lark?: string, openai_regex?: string } } requests an OpenAI custom grammar tool; Lark wins when both non-empty variants are present.
  • false explicitly opts out. Its runtime effect matches omission, but public tool inspection preserves false as a present property.
Built-in read, edit, write, bash, and its Windows PowerShell variant request strict JSON-schema sampling with prefer by default. This is a provider hint, not a schema rewrite or a sandbox. Unsupported providers retain ordinary tool calling. Other experimental tool hints still follow the experimental environment flag. Atomic preserves the optional property’s exact own-key state across wrappers, active-session inspection, staged extension inspection, bundled tools, and isolated transport: omission stays absent; explicitly present undefined stays present; false and config objects remain unchanged. This distinction matters to SDK/extension code that uses Object.hasOwn() rather than an ordinary property read. Grammar tools require an object schema with exactly one required string property. They are emitted only when model metadata advertises supportsOpenAIGrammarTools (also exposed as Atomic’s supportsGrammarTools alias); otherwise provider handling falls back to the normal function/JSON-schema path. Older OpenAI models and gateways that rewrite schemas cannot honor custom grammar tools. Typed RPC clients receive these claims through optional ModelInfo.compat. See Custom Models and RPC. 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.

Fireworks deferred tool loading

Extensions making requests directly through @bastani/pi-ai can use native deferred tool loading with Fireworks anthropic-messages models. Supply the tool definitions in context.tools and record newly loaded tool names in the loader result’s addedToolNames field. The provider serializes deferred definitions with defer_loading and inserts tool_reference content at the load point. Name the loader ToolSearch or tool_search to keep deferred schemas out of the initial prompt prefix. Other names work, but Fireworks includes the schemas in the prefix and loses that cache benefit. Fireworks GLM models and Kimi K3 still use Chat Completions; this feature does not change their routing. This is an AI SDK capability. Atomic’s pi.setActiveTools() updates the active tool list but does not automatically populate addedToolNames. See the AI SDK deferred tool-loading guide for details.

Overriding Built-in Tools

Extensions can override built-in tools (read, bash, powershell, edit, write, find, search, ask_user_question, todo) by registering a tool with the same name. Interactive mode displays a warning when this happens.
Alternatively, use --no-builtin-tools to start without any built-in tools while keeping extension tools enabled:
See examples/extensions/tool-override.ts for a complete example that overrides 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:

Remote Execution

Built-in tools support pluggable operations for delegating to remote systems (SSH, containers, etc.):
ReadOperations may also provide stat and listDir to keep directory-tree reads on the injected filesystem. The Harness factory supplies both. A custom read backend without both members keeps the existing file-only remote behavior. Archive, SQLite, internal-resource, notebook, and path-variant helpers still use Atomic’s local filesystem unless the tool gains dedicated remote seams. Operations interfaces: 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:
See examples/extensions/ssh.ts for a complete SSH example with --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
The built-in limit is 50KB (~10k tokens) and 2000 lines, whichever is hit first. Use the exported truncation utilities:
Key points:
  • Use truncateHead for content where the beginning matters (search results, file reads)
  • Use truncateTail for 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
See examples/extensions/truncated-tool.ts for a complete example wrapping rg (ripgrep) with proper truncation.

Multiple Tools

One extension can register multiple tools with shared state:

Custom Rendering

Tools can provide renderCall 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 arguments
  • state - shared row-local state across renderCall and renderResult
  • lastComponent - the previously returned component for that slot, if any
  • invalidate() - request a rerender of this tool row
  • toolCallId, cwd, executionStarted, argsComplete, isPartial, expanded, showImages, isError
Use 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:
If a slot intentionally has no visible content, return an empty Component such as an empty Container.

Keybinding Hints

Use keyHintIfBound() when an affordance should disappear if the action has no effective keybinding. Add surrounding punctuation only when the helper returns text:
Available functions:
  • 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 UI
  • keyHintIfBound(keybinding, description) - Formats the hint only when the action has an effective key list; use it for optional affordances and conditionally compose parentheses or separators
  • keyText(keybinding) - Returns the raw configured key text for a keybinding id
  • rawKeyHint(key, description) - Format a raw key string
Use namespaced keybinding ids:
  • Coding-agent ids use the app.* namespace, for example app.tools.expand, app.editor.external, app.session.rename
  • Shared TUI ids use the tui.* namespace, for example tui.select.confirm, tui.select.cancel, tui.input.tab
For the exhaustive list of keybinding ids and defaults, see Keybindings. 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 Text with padding (0, 0). The default Box handles padding.
  • Use \n for multi-line content.
  • Handle isPartial for streaming progress.
  • Support expanded for detail on demand.
  • Keep default view compact.
  • Read context.args in renderResult instead of copying args into context.state.
  • Use context.state only for data that must be shared across call and result slots.
  • Reuse context.lastComponent when 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 name
  • renderResult: Shows raw text from content

Next steps

Continue with extension events to hook into the session lifecycle. Use the Extension API reference to look up context properties and registration methods.