RPC protocol

Commands

Stored summaries and workflow history

These read-only commands do not start a model turn. Stored summaries remain available when sessionSummary.enabled is false.

Command	Response `data`	TypeScript `RpcClient` method
`{"type":"get_session_summary"}`	`{ summary: SessionSummaryEntry \| null }`, including `summary` and `summarizedThroughId`	`getSessionSummary()`
`{"type":"list_sessions"}`	`{ sessions: RpcSessionInfo[] }` for the current project/session directory, including `summary` and `summarizedThroughId`; `created` and `modified` are ISO strings	`listSessions()`
`{"type":"list_workflow_runs"}`	`{ runs: WorkflowRunSummary[] }`, including live runs and current-project resumable and completed history	`listWorkflowRuns(status?)`
`{"type":"get_workflow_run_summary","runId":"<uuid>"}`	`WorkflowRunDetail` for that run	`getWorkflowRunSummary(runId)`

Workflow records include runId, name, status, label, identity, summary, and summarizedThrough (Unix milliseconds). Optional summary fields are absent when no summary has been saved. list_workflow_runs accepts an optional status filter. Run detail requests accept full UUIDs for earlier sessions; a missing run returns the normal error response. Summaries describe progress through their marker and may be stale. Stored history follows the SDK’s run-detail access rules: top-level runs with a recorded session owner launched from the current project directory. Runs from other project directories are not included.

Prompting

prompt

Send a user prompt to the agent. The command response is emitted after the prompt is accepted, queued, or handled. Events continue streaming asynchronously after acceptance.

{"id": "req-1", "type": "prompt", "message": "Hello, world!"}

With images:

{"type": "prompt", "message": "What's in this image?", "images": [{"type": "image", "data": "base64-encoded-data", "mimeType": "image/png"}]}

During streaming: If the agent is already streaming, you must specify streamingBehavior to queue the message:

{"type": "prompt", "message": "New instruction", "streamingBehavior": "steer"}

"steer": Queue the message while the agent is running. It is delivered after the current assistant turn finishes executing its tool calls, before the next LLM call.
"followUp": Wait until the agent finishes. Message is delivered only when agent stops.

If the agent is streaming and no streamingBehavior is specified, the command returns an error. Extension commands: If the message is an extension command (e.g., /mycommand), it executes immediately even during streaming. Extension commands manage their own LLM interaction via pi.sendMessage(). Input expansion: Skill commands (/skill:name) and prompt templates (/template) are expanded before sending/queueing. Response:

{"id": "req-1", "type": "response", "command": "prompt", "success": true, "data": {"disposition": "started"}}

data.disposition is "handled" if an extension command or input handler consumed the prompt, "queued" if Atomic queued it during a run, held it because the message queue was paused before its run began, or held it because the session is compacting, or "started" if Atomic started a run for it. A prompt held during compaction is sent once compaction ends. If its turn then fails to start, for example because credentials were removed, Atomic keeps the message queued and emits an agent_continue_error event with source: "post_compaction". This describes the submitted prompt, not independent work started by an extension or a guarantee of completion. If it is "handled", no run started for this prompt, so don’t wait for agent_end or agent_settled. success: true means the prompt was accepted, queued, or handled immediately. success: false means the prompt was rejected before acceptance. Failures after acceptance are reported through the normal event and message stream, not as a second response for the same request id. The images field is optional. Each image uses ImageContent format: {"type": "image", "data": "base64-encoded-data", "mimeType": "image/png"}.

steer

Queue a steering message while the agent is running. It is delivered after the current assistant turn finishes executing its tool calls, before the next LLM call. If no run is active when it arrives and the session already has messages, Atomic starts a turn to deliver it, so a prompt sent while that turn runs needs streamingBehavior. On a session with no messages yet, or after a run was stopped with abort, it stays queued until the next prompt. Skill commands and prompt templates are expanded. Extension commands are not allowed (use prompt instead).

{"type": "steer", "message": "Stop and do this instead"}

With images:

{"type": "steer", "message": "Look at this instead", "images": [{"type": "image", "data": "base64-encoded-data", "mimeType": "image/png"}]}

The images field is optional. Each image uses ImageContent format (same as prompt). Response:

{"type": "response", "command": "steer", "success": true, "data": {"disposition": "queued"}}

data.disposition is "handled" if an input handler consumed this steer, or "queued" if Atomic queued it (including after a handler transformed it). It does not guarantee this message remains queued. See set_steering_mode for controlling how steering messages are processed.

follow_up

Queue a follow-up message to be processed after the agent finishes. Delivered only when agent has no more tool calls or steering messages. If no run is active when it arrives and the session already has messages, Atomic starts a turn to deliver it, so a prompt sent while that turn runs needs streamingBehavior. On a session with no messages yet, or after a run was stopped with abort, it stays queued until the next prompt. Skill commands and prompt templates are expanded. Extension commands are not allowed (use prompt instead).

{"type": "follow_up", "message": "After you're done, also do this"}

With images:

{"type": "follow_up", "message": "Also check this image", "images": [{"type": "image", "data": "base64-encoded-data", "mimeType": "image/png"}]}

The images field is optional. Each image uses ImageContent format (same as prompt). Response:

{"type": "response", "command": "follow_up", "success": true, "data": {"disposition": "queued"}}

data.disposition has the same "handled" or "queued" meaning as for steer, applied to this follow-up. See set_follow_up_mode for controlling how follow-up messages are processed.

abort

Abort the current operation and wait for the session to become idle before responding.

{"type": "abort"}

Response:

{"type": "response", "command": "abort", "success": true}

clear_queue

Remove queued steering and follow-up messages and return their text. The response lists exactly the messages this call removed. It includes a message queued after the last queue_update the client received, and leaves out one the session already took into a turn. A client that restores the queue to an editor should restore this list, not its own copy of the queue: the copy kept from queue_update events trails the session by a round trip.

{"type": "clear_queue"}

Response:

{
  "type": "response",
  "command": "clear_queue",
  "success": true,
  "data": {
    "steering": ["Change direction (rewritten)"],
    "followUp": ["Summarize when finished"],
    "typed": {
      "steering": ["Change direction"],
      "followUp": ["Summarize when finished"]
    }
  }
}

steering and followUp list each message as queued, after input hooks, skills and prompt templates changed it. typed lists the same messages, in the same order, as they were submitted. A client that gives the messages back to the user to send again should restore typed, so those steps run once more and not twice. typed is left out when every message was queued as submitted, and by sessions from before it was added; restore steering and followUp then. To implement interactive Esc behavior, send clear_queue before abort, then restore the returned text in the client editor. abort continues queued messages when they remain in the session.

new_session

Start a fresh session. Can be cancelled by a session_before_switch extension event handler.

{"type": "new_session"}

With optional parent session tracking:

{"type": "new_session", "parentSession": "parent-session-id"}

Response:

{"type": "response", "command": "new_session", "success": true, "data": {"cancelled": false}}

If an extension cancelled:

{"type": "response", "command": "new_session", "success": true, "data": {"cancelled": true}}

delete_session

Delete a stored session and its entries from the active session store (SQLite or JSONL). Use list_sessions to find IDs.

{"id": "req-2", "type": "delete_session", "sessionId": "019fdf86-cf98-7327-8a73-21365028f6ae"}

sessionId names the session to delete. id is the request ID that every command carries and is echoed in the response. When sessionId is omitted, id is also used as the session ID, so {"type": "delete_session", "id": "019fdf86-cf98-7327-8a73-21365028f6ae"} deletes that session and the response echoes the same id. When both are present, sessionId wins. Omitting both returns an error response (delete_session requires sessionId) and changes nothing. Response:

{"id": "req-2", "type": "response", "command": "delete_session", "success": true}

The session currently open in this process cannot be deleted. The command returns an error response and the session stays intact; start or switch to another session first. Deleting an ID that is not in the store succeeds without changing anything.

{"id": "req-2", "type": "response", "command": "delete_session", "success": false, "error": "Cannot delete the session that is currently open: 019fdf86-cf98-7327-8a73-21365028f6ae"}

TypeScript RpcClient method: deleteSession(sessionId), which rejects on an error response.

State

get_state

Get current session state.

{"type": "get_state"}

Response:

{
  "type": "response",
  "command": "get_state",
  "success": true,
  "data": {
    "model": {...},
    "thinkingLevel": "medium",
    "isStreaming": false,
    "isCompacting": false,
    "steeringMode": "all",
    "followUpMode": "one-at-a-time",
    "sessionLocation": "/path/to/session.jsonl",
    "sessionId": "abc123",
    "sessionName": "my-feature-work",
    "autoCompactionEnabled": true,
    "messageCount": 5,
    "pendingMessageCount": 0
  }
}

The model field is a full Model object or null. Its contextWindow is the model’s token budget. The sessionName field is the display name set via set_session_name, or omitted if not set.

get_messages

Get all messages in the conversation.

{"type": "get_messages"}

Response:

{
  "type": "response",
  "command": "get_messages",
  "success": true,
  "data": {"messages": [...]}
}

Messages are AgentMessage objects (see Types).

Model

set_model

Switch to a specific model. Omit persist (or set it false) to change only the current session. Set "persist": true to also save defaultProvider, defaultModel, and the effective thinking level in settings, matching an interactive /model selection.

{"type": "set_model", "provider": "anthropic", "modelId": "claude-sonnet-4-20250514"}

Persist as the startup default:

{"type": "set_model", "provider": "anthropic", "modelId": "claude-sonnet-4-20250514", "persist": true}

Response contains the full Model object:

{
  "type": "response",
  "command": "set_model",
  "success": true,
  "data": {...}
}

cycle_model

Cycle to the next available model. Returns null when fewer than two authenticated models are available in the active scope or catalog. When an unsupported saved default is blocking prompts, a successful cycle that returns a different model clears that condition; a null or unchanged result does not. Set "persist": true to also write the cycled model as the startup default.

{"type": "cycle_model"}

Response:

{
  "type": "response",
  "command": "cycle_model",
  "success": true,
  "data": {
    "model": {...},
    "thinkingLevel": "medium",
    "isScoped": false
  }
}

The model field is a full Model object.

get_available_models

List all configured models.

{"type": "get_available_models"}

Response contains an array of full Model objects:

{
  "type": "response",
  "command": "get_available_models",
  "success": true,
  "data": {
    "models": [...]
  }
}

data also carries scopedModels, oauthProviders, customAuthProviders, and providerAuthStatuses. customAuthProviders lists extension-registered providers ({ id, name }) that accept an API key through login_provider. providerAuthStatuses lists the authentication status of extension-registered providers ({ provider, status }, where status is { configured, source?, label? }) when it does not come from a credential stored in auth.json, for example an environment variable. refresh_models responses carry the same fields. The subprocess protocol returns full Model objects. The exported TypeScript RpcClient.getAvailableModels() keeps its smaller backward-compatible ModelInfo shape (provider, id, contextWindow, reasoning) and adds optional compat. When present, compat exposes constrained-sampling capability claims including supportsStrictTools, supportsStrictMode, canonical supportsOpenAIGrammarTools, and Atomic’s synchronized supportsGrammarTools alias. Treat absence as unknown/unsupported; do not infer enforcement from the provider name.

const models = await client.getAvailableModels();
const capabilities = models[0]?.compat;
if (capabilities?.supportsStrictTools) {
  // The selected model advertises Anthropic/Bedrock strict-tool support.
}

logout_provider

Remove a provider’s stored credential in the authoritative agent process, refresh its available-model catalog, and return the remaining authentication status and new catalog. Environment variables and models.json authentication are reported but are not modified.

{"type": "logout_provider", "provider": "github-copilot"}

Response:

{
  "type": "response",
  "command": "logout_provider",
  "success": true,
  "data": {
    "provider": "github-copilot",
    "authStatus": {"configured": false},
    "models": [],
    "scopedModels": []
  }
}

models preserves the refreshed catalog order. scopedModels is optional. If authentication remains through an environment variable, authStatus.source is "environment" and authStatus.label names the variable.

Thinking

set_thinking_level

Set the reasoning/thinking level for models that support it. Omit persist (or set it false) to change only the current session. Set "persist": true to also save defaultThinkingLevel and, when a model is active, its per-model override. Interactive /thinking choices request persistence automatically.

{"type": "set_thinking_level", "level": "high"}

Persist as the startup default:

{"type": "set_thinking_level", "level": "high", "persist": true}

Levels: "off", "minimal", "low", "medium", "high", "xhigh", "max". xhigh and max are available only when the active model’s capability mapping supports them; unsupported levels are clamped by the session model controls. Response may omit data for compatibility with older clients:

{"type": "response", "command": "set_thinking_level", "success": true}

Current engines include the effective level after capability clamping and, when a model is active, the provider/model the engine persisted against:

{"type": "response", "command": "set_thinking_level", "success": true, "data": {"level": "high", "provider": "anthropic", "modelId": "claude-sonnet-4-20250514"}}

Use the acknowledgement’s provider/model when recording a persisted thinking override, not whichever model is active when your callback runs. Keep newer thinking_level_changed state if an older acknowledgement arrives later. RpcClient.setThinkingLevel(level) remains a one-argument Promise<void> method.

cycle_thinking_level

Cycle through available thinking levels. Returns null data if model doesn’t support thinking.

{"type": "cycle_thinking_level"}

Response:

{
  "type": "response",
  "command": "cycle_thinking_level",
  "success": true,
  "data": {"level": "high"}
}

get_available_thinking_levels

Return the thinking levels supported by the current model, in cycle order.

{"type": "get_available_thinking_levels"}

Response:

{
  "type": "response",
  "command": "get_available_thinking_levels",
  "success": true,
  "data": {"levels": ["off", "low", "medium", "high"]}
}

Queue Modes

set_steering_mode

Control how steering messages (from steer) are delivered.

{"type": "set_steering_mode", "mode": "one-at-a-time"}

Modes:

"all": Deliver all steering messages after the current assistant turn finishes executing its tool calls
"one-at-a-time": Deliver one steering message per completed assistant turn (default)

Response:

{"type": "response", "command": "set_steering_mode", "success": true}

set_follow_up_mode

Control how follow-up messages (from follow_up) are delivered.

{"type": "set_follow_up_mode", "mode": "one-at-a-time"}

Modes:

"all": Deliver all follow-up messages when agent finishes
"one-at-a-time": Deliver one follow-up message per agent completion (default)

Response:

{"type": "response", "command": "set_follow_up_mode", "success": true}

Compaction

compact

Run verbatim line compaction with the session model. It preserves exactly the newest preserve_recent context-visible messages, default two, without aligning to user turns. Zero compacts the whole active transcript and returns firstKeptEntryId: null. The resulting durable entry uses details.strategy: "verbatim-lines"; see Compaction for behavior and settings.

{"type": "compact"}

Response:

{
  "type": "response",
  "command": "compact",
  "success": true,
  "data": {
    "compactedText": "[User]: fix the test\n(filtered 42 lines)\n[Assistant]: Fixed.",
    "firstKeptEntryId": "m7",
    "tokensBefore": 150000,
    "promptVersion": 3,
    "parameters": {
      "compression_ratio": 0.5,
      "preserve_recent": 2,
      "query": "fix the test"
    },
    "rung": "planned",
    "stats": {
      "linesBefore": 812,
      "linesDeleted": 417,
      "linesKept": 395,
      "rangeCount": 63,
      "tokensBefore": 150000,
      "tokensAfter": 72000,
      "percentReduction": 52
    },
    "backupPath": "/path/to/session.jsonl.2026-06-06T00-00-00-000Z.compact.bak"
  }
}

firstKeptEntryId is a string when at least one ordinary message remains outside compaction and null when none does. RPC clients must accept both values.

set_auto_compaction

Enable or disable automatic compaction when context is nearly full.

{"type": "set_auto_compaction", "enabled": true}

Response:

{"type": "response", "command": "set_auto_compaction", "success": true}

Extension UI

set_extension_ui_capabilities

Say what extension UI the client can show. With questionnaire: true, ask_user_question reaches the client as one questionnaire request instead of failing for lack of a terminal. Off until the client turns it on; an omitted field keeps its value.

{"type": "set_extension_ui_capabilities", "questionnaire": true}

Response:

{"type": "response", "command": "set_extension_ui_capabilities", "success": true}

An Atomic without this command answers it with an error, so a client can send it at startup and keep its previous behavior when it fails.

Retry

set_auto_retry

Enable or disable automatic retry on transient errors (overloaded, rate limit, 5xx).

{"type": "set_auto_retry", "enabled": true}

Response:

{"type": "response", "command": "set_auto_retry", "success": true}

abort_retry

Abort an in-progress retry (cancel the delay and stop retrying).

{"type": "abort_retry"}

Response:

{"type": "response", "command": "abort_retry", "success": true}

Bash

bash

Execute a shell command and add output to conversation context.

{"type": "bash", "command": "ls -la"}

Response:

{
  "type": "response",
  "command": "bash",
  "success": true,
  "data": {
    "output": "total 48\ndrwxr-xr-x ...",
    "exitCode": 0,
    "cancelled": false,
    "truncated": false
  }
}

While the command runs, Atomic emits ordered deltas correlated by the command id:

{"type":"bash_execution_update","id":"req-1","channel":"stdout","delta":"building...\n"}
{"type":"bash_execution_update","id":"req-1","channel":"stderr","delta":"warning\n"}

channel is exactly "stdout" or "stderr". Deltas preserve the observed order for each request. Concurrent bash requests may interleave globally but never share IDs. Request ownership survives new_session, switch_session, import_session, fork, and clone while the command runs. Later deltas keep the original ID and do not contaminate the replacement session. Exactly one ordinary response is the terminal record for completion, cancellation, or error. If output was truncated, includes fullOutputPath. Persisted bash output lives in the owner- and session-scoped temp tree (<tmpdir>/atomic-<uid>/<session-id>/), not at the temp root — see Tools for the layout, permissions, size cap, and retention:

{
  "type": "response",
  "command": "bash",
  "success": true,
  "data": {
    "output": "truncated output...",
    "exitCode": 0,
    "cancelled": false,
    "truncated": true,
    "fullOutputPath": "/tmp/atomic-501/019fdf86-cf98-7327-8a73-21365028f6ae/atomic-bash-abc123.log"
  }
}

fullOutputPath is null when the temp directory could not be created or the write was refused; treat it as absent rather than assuming a path exists. How bash results reach the LLM: The bash command returns a BashResult and saves output in the session where the request started, even if another session becomes active before completion. The saved BashExecutionMessage emits no event of its own. The initiating session’s next prompt includes the output as user context in this format:

Ran `ls -la`
```
total 48
drwxr-xr-x ...
```

This means:

Bash output is included in the LLM context on the next prompt, not immediately
Multiple bash commands can be executed before a prompt; all outputs will be included
No event is emitted for the BashExecutionMessage itself

abort_bash

Abort running bash commands. Omit requestId to retain the legacy behavior of aborting every active RPC-owned bash request, including requests that began before a session replacement, or provide the target bash command’s id to cancel only that request. Targeted and legacy cancellation remain isolated across concurrent IDs. Closing RPC cancels and drains remaining owned requests before shutdown.

{"id":"cancel-1","type":"abort_bash","requestId":"req-1"}

Response:

{"id":"cancel-1","type":"response","command":"abort_bash","success":true}

Session

get_session_stats

Get token usage, cost statistics, and current context window usage.

{"type": "get_session_stats"}

Response:

{
  "type": "response",
  "command": "get_session_stats",
  "success": true,
  "data": {
    "sessionFile": "/path/to/session.jsonl",
    "sessionId": "abc123",
    "userMessages": 5,
    "assistantMessages": 5,
    "toolCalls": 12,
    "toolResults": 12,
    "totalMessages": 22,
    "tokens": {
      "input": 50000,
      "output": 10000,
      "cacheRead": 40000,
      "cacheWrite": 5000,
      "total": 105000
    },
    "cost": 0.45,
    "contextUsage": {
      "tokens": 60000,
      "contextWindow": 200000,
      "percent": 30
    },
    "latestAssistantUsage": {
      "input": 200,
      "output": 800,
      "cacheRead": 59000,
      "cacheWrite": 0,
      "totalTokens": 60000,
      "cost": {"input": 0.0006, "output": 0.012, "cacheRead": 0.0177, "cacheWrite": 0, "total": 0.0303}
    }
  }
}

tokens contains assistant usage totals for the current session state. contextUsage contains the actual current context-window estimate used for compaction and footer display. contextUsage is omitted when no model or context window is available. contextUsage.tokens and contextUsage.percent are null immediately after compaction until a fresh post-compaction assistant response provides valid usage data. latestAssistantUsage is the usage reported by the newest assistant message, including an aborted or failed one; the interactive footer reads its cache-hit rate from it. It is omitted until the session has an assistant message.

get_tools

Explain which tools are active, which are not and why, and which selected tool names nothing registered.

{"type": "get_tools"}

Response, shortened to three tools, for "defaultTools": ["+codemode", "+tool-search"]:

{
  "type": "response",
  "command": "get_tools",
  "success": true,
  "data": {
    "selection": {
      "source": "default-tools-setting",
      "description": "the defaultTools setting",
      "names": ["read", "bash", "kill", "edit", "write", "find", "search", "ask_user_question", "todo", "codemode", "tool-search"],
      "modifiers": []
    },
    "tools": [
      {
        "name": "read",
        "active": true,
        "exposure": "direct",
        "source": "built-in",
        "sourcePath": "<builtin:read>",
        "summary": "Read files, directories, archives, SQLite databases, internal resources, images, documents, and URLs through one path string."
      },
      {
        "name": "codemode",
        "active": true,
        "exposure": "model-only",
        "source": "built-in extension \"codemode\"",
        "sourcePath": "builtin:codemode",
        "summary": "Run JavaScript that composes tool calls in a fresh QuickJS worker sandbox."
      },
      {
        "name": "tool_search",
        "active": false,
        "exposure": "model-only",
        "source": "built-in extension \"tool-search\"",
        "sourcePath": "builtin:tool-search",
        "summary": "Search deferred tool metadata with BM25 and load matching tools for the next model call. Some tools may not have been provided upfront; use tool_search to discover currently registered tools.",
        "inactiveReason": "opt-in; add \"+tool_search\" to defaultTools or --tools to enable it"
      }
    ],
    "missing": [
      {
        "name": "tool-search",
        "reason": "selected by the defaultTools setting, but no built-in, extension, SDK custom tool, or MCP server has registered a tool named \"tool-search\"; did you mean \"tool_search\"?"
      }
    ],
    "excluded": []
  }
}

selection.source is one of default-tools-setting, built-in-defaults, tools-allowlist, explicit-selection, no-built-in-tools, or no-tools; modifiers lists +name/-name entries from --tools. tools lists active tools first. excluded lists selected names that --exclude-tools or a mode without user input removed. The command waits until extensions finish loading, so the report includes their tools. RpcClient.getTools() returns the same data.

export_html

Export session to an HTML file.

{"type": "export_html"}

With custom path:

{"type": "export_html", "outputPath": "/tmp/session.html"}

Response:

{
  "type": "response",
  "command": "export_html",
  "success": true,
  "data": {"path": "/tmp/session.html"}
}

switch_session

Load a different session by its exact ID. Can be cancelled by a session_before_switch extension event handler. sessionLocation in get_state is optional display text, not a switch target.

{"type": "switch_session", "sessionId": "abc123"}

When choosing a session from another project’s JSONL store, pass sessionDirectory to bind the ID lookup to that directory. IDs may repeat in different project stores; an explicitly selected directory never falls back to another store. cwdOverride changes the resumed working directory, not the store used for lookup.

{"type": "switch_session", "sessionId": "abc123", "sessionDirectory": "/path/to/project-sessions"}

Response:

{"type": "response", "command": "switch_session", "success": true, "data": {"cancelled": false}}

If an extension cancelled the switch:

{"type": "response", "command": "switch_session", "success": true, "data": {"cancelled": true}}

start_pending_recovery

Recover work an earlier process left unfinished in the current session. Send it after you have shown the transcript, at startup or after switch_session. Loading or switching a session never recovers anything by itself. Until a client sends this command, interrupted deliveries stay pending in the session. The command runs once per loaded session; repeating it returns the same report. It does not block other commands, so prompts and abort keep working while it runs.

{"type": "start_pending_recovery", "reason": "resume"}

reason is optional and accepts "startup", "resume", or "workflow_stage_resume". Extensions first restore their background work. Interrupted deliveries that are still wanted are then replayed in a turn, which streams like any other turn. Notices and undelivered background task results are appended without starting a turn. The response arrives when recovery has finished:

{"type": "response", "command": "start_pending_recovery", "success": true, "data": {"replayed": 1, "dropped": 1, "completions": 0, "notices": ["Worker reviewer is gone."]}}

fork

Create a new fork from a previous user message on the active branch. Can be cancelled by a session_before_fork extension event handler. Returns the text of the message being forked from.

{"type": "fork", "entryId": "abc123"}

Response:

{
  "type": "response",
  "command": "fork",
  "success": true,
  "data": {"text": "The original prompt text...", "cancelled": false}
}

If an extension cancelled the fork:

{
  "type": "response",
  "command": "fork",
  "success": true,
  "data": {"text": "The original prompt text...", "cancelled": true}
}

clone

Duplicate the current active branch into a new session at the current position. Can be cancelled by a session_before_fork extension event handler.

{"type": "clone"}

Response:

{
  "type": "response",
  "command": "clone",
  "success": true,
  "data": {"cancelled": false}
}

If an extension cancelled the clone:

{
  "type": "response",
  "command": "clone",
  "success": true,
  "data": {"cancelled": true}
}

get_fork_messages

Get user messages available for forking.

{"type": "get_fork_messages"}

Response:

{
  "type": "response",
  "command": "get_fork_messages",
  "success": true,
  "data": {
    "messages": [
      {"entryId": "abc123", "text": "First prompt..."},
      {"entryId": "def456", "text": "Second prompt..."}
    ]
  }
}

get_entries

Get all session entries in append order, excluding the session header. Unlike get_messages, this includes pre-compaction history and abandoned branches. Entry IDs are stable in the append-only tree. Use the last entry ID you have seen as since to get only entries strictly after it, even across client restarts.

{"type": "get_entries"}

With a cursor:

{"type": "get_entries", "since": "abc123"}

Response:

{
  "type": "response",
  "command": "get_entries",
  "success": true,
  "data": {
    "entries": [
      {"type": "message", "id": "def456", "parentId": "abc123", "timestamp": "...", "message": {"role": "user", "...": "..."}}
    ],
    "leafId": "def456"
  }
}

leafId is the id of the current leaf entry (null for an empty session), so a client can tell in one round trip whether the active branch moved. If since does not match any entry id, the response is success: false.

get_tree

Get the session as a tree of entries. Each node is {entry, children, label?, labelTimestamp?}. A well-formed session has a single root; orphaned entries (broken parent chain) also appear as roots.

{"type": "get_tree"}

Response:

{
  "type": "response",
  "command": "get_tree",
  "success": true,
  "data": {
    "tree": [
      {
        "entry": {"type": "message", "id": "abc123", "parentId": null, "...": "..."},
        "children": [
          {"entry": {"type": "message", "id": "def456", "parentId": "abc123", "...": "..."}, "children": []}
        ]
      }
    ],
    "leafId": "def456"
  }
}

get_last_assistant_text

Get the text content of the last assistant message.

{"type": "get_last_assistant_text"}

Response:

{
  "type": "response",
  "command": "get_last_assistant_text",
  "success": true,
  "data": {"text": "The assistant's response..."}
}

Returns {"text": null} if no assistant messages exist.

set_session_name

Set a display name for the current session. The name appears in session listings and helps identify sessions.

{"type": "set_session_name", "name": "my-feature-work"}

Response:

{
  "type": "response",
  "command": "set_session_name",
  "success": true
}

The current session name is available via get_state in the sessionName field. To set the initial name when starting RPC mode, pass --name <name> or -n <name> to the atomic --mode rpc process.

Commands

get_commands

Get available commands (extension commands, prompt templates, and skills). These can be invoked via the prompt command by prefixing with /.

{"type": "get_commands"}

Response:

{
  "type": "response",
  "command": "get_commands",
  "success": true,
  "data": {
    "commands": [
      {"name": "session-name", "description": "Set or clear session name", "source": "extension", "path": "/home/user/.atomic/agent/extensions/session.ts"},
      {"name": "fix-tests", "description": "Fix failing tests", "source": "prompt", "location": "project", "path": "/home/user/myproject/.atomic/prompts/fix-tests.md"},
      {"name": "skill:brave-search", "description": "Web search via Brave API", "source": "skill", "location": "user", "path": "/home/user/.atomic/agent/skills/brave-search/SKILL.md"}
    ]
  }
}

Each command has:

name: Command name (invoke with /name)
description: Human-readable description (optional for extension commands)
source: What kind of command:
- "extension": Registered via pi.registerCommand() in an extension
- "prompt": Loaded from a prompt template .md file
- "skill": Loaded from a skill directory (name is prefixed with skill:)
location: Where it was loaded from (optional, not present for extensions):
- "user": User-level (~/.atomic/agent/)
- "project": Project-level (./.atomic/)
- "path": Explicit path via CLI or settings
path: Absolute file path to the command source (optional)

Note: Built-in TUI commands (/settings, /hotkeys, etc.) are not included. They are handled only in interactive mode and would not execute if sent via prompt.

Events

Events are streamed to stdout as JSON lines. Most events do not include an id; bash_execution_update is the deliberate exception and uses the originating bash request ID.

Event Types

Event	Description
`agent_start`	Agent begins processing
`agent_end`	Agent completes (includes all generated messages)
`turn_start`	New turn begins
`turn_end`	Turn completes (includes assistant message and tool results)
`message_start`	Message begins
`message_update`	Streaming update (text/thinking/toolcall deltas)
`message_end`	Message completes
`tool_execution_start`	Tool begins execution; includes `toolCallId`, `toolName`, and initial arguments
`tool_execution_update`	Tool execution progress (streaming output)
`tool_execution_end`	Tool completes
`bash_execution_update`	Correlated direct-bash stdout/stderr delta
`queue_update`	Pending steering/follow-up queue changed
`compaction_start`	Verbatim line compaction begins
`compaction_end`	Verbatim line compaction completes
`auto_retry_start`	Auto-retry begins (after transient error)
`auto_retry_end`	Auto-retry completes (success or final failure)
`summarization_retry_scheduled`	Retry scheduled for a transient compaction or branch-summary provider error
`summarization_retry_attempt_start`	Retried summarization request starts
`summarization_retry_finished`	Summarization retry loop completes
`extension_error`	Extension threw an error

agent_start

Emitted when the agent begins processing a prompt.

{"type": "agent_start"}

agent_end

Emitted when the agent completes. Contains all messages generated during this run.

{
  "type": "agent_end",
  "messages": [...]
}

turn_start / turn_end

A turn consists of one assistant response plus any resulting tool calls and results.

{"type": "turn_start"}

{
  "type": "turn_end",
  "message": {...},
  "toolResults": [...]
}

message_start / message_end

Emitted when a message begins and completes. The message field contains an AgentMessage.

{"type": "message_start", "message": {...}}
{"type": "message_end", "message": {...}}

message_update (Streaming)

Emitted during streaming of assistant messages. Carries the streaming delta plus the latest cumulative usage. message_update has no cumulative message, and assistantMessageEvent has no partial. Build your message from message_start and deltas, then use message_end as the final authoritative message. The top-level usage field carries the latest cumulative provider-reported usage; it may remain zero until completion when a provider does not report usage during streaming. When the provider reports an explicit end-of-turn signal (pi-ai’s AssistantMessage.endTurn, for example OpenAI Codex end_turn), the update carries it as a top-level endTurn boolean — present only when the provider reported one.

{
  "type": "message_update",
  "usage": {
    "input": 100,
    "output": 1,
    "cacheRead": 0,
    "cacheWrite": 0,
    "totalTokens": 101,
    "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0, "total": 0}
  },
  "assistantMessageEvent": {
    "type": "text_delta",
    "contentIndex": 0,
    "delta": "Hello "
  }
}

The assistantMessageEvent field contains one of these delta types:

Type	Description
`start`	Message generation started
`text_start`	Text content block started
`text_delta`	Text content chunk
`text_end`	Text content block ended
`thinking_start`	Thinking block started
`thinking_delta`	Thinking content chunk
`thinking_end`	Thinking block ended
`toolcall_start`	Tool call started
`toolcall_delta`	Tool call arguments chunk
`toolcall_end`	Tool call ended (includes full `toolCall` object)
`done`	Message complete (reason: `"stop"`, `"length"`, `"toolUse"`)
`error`	Error occurred (reason: `"aborted"`, `"error"`)

Example streaming a text response:

{"type":"message_update","usage":{...},"assistantMessageEvent":{"type":"text_start","contentIndex":0}}
{"type":"message_update","usage":{...},"assistantMessageEvent":{"type":"text_delta","contentIndex":0,"delta":"Hello"}}
{"type":"message_update","usage":{...},"assistantMessageEvent":{"type":"text_delta","contentIndex":0,"delta":" world"}}
{"type":"message_update","usage":{...},"assistantMessageEvent":{"type":"text_end","contentIndex":0,"content":"Hello world"}}

tool_execution_start / tool_execution_update / tool_execution_end

Emitted when a tool begins, streams progress, and completes execution.

{
  "type": "tool_execution_start",
  "toolCallId": "call_abc123",
  "toolName": "bash",
  "args": {"command": "ls -la"}
}

During execution, tool_execution_update events stream partial results (e.g., bash output as it arrives):

{
  "type": "tool_execution_update",
  "toolCallId": "call_abc123",
  "toolName": "bash",
  "args": {"command": "ls -la"},
  "partialResult": {
    "content": [{"type": "text", "text": "partial output so far..."}],
    "details": {"truncation": null, "fullOutputPath": null}
  }
}

When complete:

{
  "type": "tool_execution_end",
  "toolCallId": "call_abc123",
  "toolName": "bash",
  "result": {
    "content": [{"type": "text", "text": "total 48\n..."}],
    "details": {...}
  },
  "isError": false
}

Use toolCallId to correlate events. The partialResult in tool_execution_update contains the accumulated output so far (not just the delta), allowing clients to simply replace their display on each update.

bash_execution_update

Emitted only for direct bash and non-intercepted user_bash RPC execution. Each event is {type, id?, channel, delta} where channel is "stdout" or "stderr"; use id to keep concurrent streams separate. Tool-call bash continues to use tool_execution_update and its toolCallId.

queue_update

Emitted whenever the pending steering or follow-up queue changes.

{
  "type": "queue_update",
  "steering": ["Focus on error handling"],
  "followUp": ["After that, summarize the result"]
}

compaction_start / compaction_end

Emitted when default Verbatim Compaction runs, whether manual or automatic. The result records deletion targets and stats rather than a generated summary.

{"type": "compaction_start", "reason": "threshold"}

The reason field is "manual", "threshold", or "overflow".

{
  "type": "compaction_end",
  "reason": "threshold",
  "result": {
    "compactedText": "[User]: fix the test\n(filtered 42 lines)",
    "firstKeptEntryId": "m7",
    "tokensBefore": 150000,
    "promptVersion": 3,
    "parameters": {"compression_ratio": 0.5, "preserve_recent": 2, "query": "fix the test"},
    "rung": "planned",
    "stats": {
      "linesBefore": 812,
      "linesDeleted": 417,
      "linesKept": 395,
      "rangeCount": 63,
      "tokensBefore": 150000,
      "tokensAfter": 72000,
      "percentReduction": 52
    }
  },
  "aborted": false,
  "willRetry": false
}

If reason was "overflow" and compaction succeeds, willRetry is true and the agent will automatically retry the prompt. Public prompt/RPC callers wait for that post-compaction continuation before the prompt is considered complete. If compaction was aborted, result is null and aborted is true. If compaction failed (e.g., API quota exceeded), result is null, aborted is false, and errorMessage contains the error description. result and errorMessage are independent. A mid-turn post-tool compaction can commit a boundary and then fail the provider hard-input-limit gate, so one compaction_end may carry both a non-null result and an errorMessage. Treat the result as a committed durable boundary in that case; the error describes the follow-up request that was not sent. If overflow recovery exhausts the same-model compact-and-retry attempt, compaction_end includes "unresolvedOverflow": true and an errorMessage. Workflow orchestration treats that signal as a context-length failure that can advance configured model fallback tiers. There is no context_compact command; Atomic reports it as an unknown command. Use compact. Only compaction_start and compaction_end events are emitted.

auto_retry_start / auto_retry_end

Emitted when automatic retry is triggered after a transient error (overloaded, rate limit, 5xx).

{
  "type": "auto_retry_start",
  "attempt": 1,
  "maxAttempts": 3,
  "delayMs": 2000,
  "errorMessage": "529 {\"type\":\"error\",\"error\":{\"type\":\"overloaded_error\",\"message\":\"Overloaded\"}}"
}

{
  "type": "auto_retry_end",
  "success": true,
  "attempt": 2
}

On final failure (max retries exceeded):

{
  "type": "auto_retry_end",
  "success": false,
  "attempt": 3,
  "finalError": "529 overloaded_error: Overloaded"
}

summarization_retry_scheduled / summarization_retry_attempt_start / summarization_retry_finished

Emitted when compaction planning or branch summarization retries after a transient provider error. These events use the same retry settings as automatic assistant-turn retries.

{
  "type": "summarization_retry_scheduled",
  "attempt": 1,
  "maxAttempts": 3,
  "delayMs": 2000,
  "errorMessage": "terminated"
}

{
  "type": "summarization_retry_attempt_start",
  "source": "compaction",
  "reason": "threshold"
}

For branch summaries, source is "branchSummary" and no reason is present. The loop then emits:

{"type": "summarization_retry_finished"}

extension_error

Emitted when an extension throws an error.

{
  "type": "extension_error",
  "extensionPath": "/path/to/extension.ts",
  "event": "tool_call",
  "error": "Error message..."
}

Error Handling

Failed commands return a response with success: false:

{
  "type": "response",
  "command": "set_model",
  "success": false,
  "error": "Model not found: invalid/model"
}

Parse errors:

{
  "type": "response",
  "command": "parse",
  "success": false,
  "error": "Failed to parse command: Unexpected token..."
}

Types

Source files and installed definitions:

node_modules/@bastani/pi-ai/dist/types.d.ts - Model, UserMessage, AssistantMessage, ToolResultMessage
node_modules/@earendil-works/pi-agent-core/dist/types.d.ts - AgentMessage, AgentEvent
src/core/messages.ts - BashExecutionMessage
src/modes/rpc/rpc-types.ts - RPC command/response types, extension UI request/response types

Model

{
  "id": "claude-sonnet-4-20250514",
  "name": "Claude Sonnet 4",
  "api": "anthropic-messages",
  "provider": "anthropic",
  "baseUrl": "https://api.anthropic.com",
  "reasoning": true,
  "input": ["text", "image"],
  "contextWindow": 200000,
  "maxTokens": 16384,
  "cost": {
    "input": 3.0,
    "output": 15.0,
    "cacheRead": 0.3,
    "cacheWrite": 3.75
  }
}

contextWindow is the model’s token budget used by Atomic’s local budgeting, footer/stats, and compaction logic.

UserMessage

{
  "role": "user",
  "content": "Hello!",
  "timestamp": 1733234567890
}

The content field can be a string or an array of TextContent/ImageContent blocks.

AssistantMessage

{
  "role": "assistant",
  "content": [
    {"type": "text", "text": "Hello! How can I help?"},
    {"type": "thinking", "thinking": "User is greeting me..."},
    {"type": "toolCall", "id": "call_123", "name": "bash", "arguments": {"command": "ls"}}
  ],
  "api": "anthropic-messages",
  "provider": "anthropic",
  "model": "claude-sonnet-4-20250514",
  "usage": {
    "input": 100,
    "output": 50,
    "cacheRead": 0,
    "cacheWrite": 0,
    "cost": {"input": 0.0003, "output": 0.00075, "cacheRead": 0, "cacheWrite": 0, "total": 0.00105}
  },
  "stopReason": "stop",
  "timestamp": 1733234567890
}

Stop reasons: "stop", "length", "toolUse", "error", "aborted". A streaming message carries "pending" until the terminal event replaces it, so a client that switches on the reason needs that case; a completed message never carries it. On the wire the pending reason appears on the message_start message — message_update frames carry no message at all — and message_end carries the terminal reason. A provider that reports an explicit end-of-turn signal (pi-ai’s AssistantMessage.endTurn, for example OpenAI Codex end_turn) sets endTurn: true on the assistant message; message_update frames echo it as a top-level boolean only when the provider reported one.

ToolResultMessage

{
  "role": "toolResult",
  "toolCallId": "call_123",
  "toolName": "bash",
  "content": [{"type": "text", "text": "total 48\ndrwxr-xr-x ..."}],
  "isError": false,
  "timestamp": 1733234567890
}

BashExecutionMessage

Created by the bash RPC command (not by LLM tool calls):

{
  "role": "bashExecution",
  "command": "ls -la",
  "output": "total 48\ndrwxr-xr-x ...",
  "exitCode": 0,
  "cancelled": false,
  "truncated": false,
  "fullOutputPath": null,
  "timestamp": 1733234567890
}

Attachment

{
  "id": "img1",
  "type": "image",
  "fileName": "photo.jpg",
  "mimeType": "image/jpeg",
  "size": 102400,
  "content": "base64-encoded-data...",
  "extractedText": null,
  "preview": null
}

​RPC protocol

​Commands

​Stored summaries and workflow history

​Prompting

​prompt

​steer

​follow_up

​abort

​clear_queue

​new_session

​delete_session

​State

​get_state

​get_messages

​Model

​set_model

​cycle_model

​get_available_models

​logout_provider

​Thinking

​set_thinking_level

​cycle_thinking_level

​get_available_thinking_levels

​Queue Modes

​set_steering_mode

​set_follow_up_mode

​Compaction

​compact

​set_auto_compaction

​Extension UI

​set_extension_ui_capabilities

​Retry

​set_auto_retry

​abort_retry

​Bash

​bash

​abort_bash

​Session

​get_session_stats

​get_tools

​export_html

​switch_session

​start_pending_recovery

​fork

​clone

​get_fork_messages

​get_entries

​get_tree

​get_last_assistant_text

​set_session_name

​Commands

​get_commands

​Events

​Event Types

​agent_start

​agent_end

​turn_start / turn_end

​message_start / message_end

​message_update (Streaming)

​tool_execution_start / tool_execution_update / tool_execution_end

​bash_execution_update

​queue_update

​compaction_start / compaction_end

​auto_retry_start / auto_retry_end

​summarization_retry_scheduled / summarization_retry_attempt_start / summarization_retry_finished

​extension_error

​Error Handling

​Types

​Model

​UserMessage

​AssistantMessage

​ToolResultMessage

​BashExecutionMessage

​Attachment

RPC protocol

Commands

Stored summaries and workflow history

Prompting

prompt

steer

follow_up

abort

clear_queue

new_session

delete_session

State

get_state

get_messages

Model

set_model

cycle_model

get_available_models

logout_provider

Thinking

set_thinking_level

cycle_thinking_level

get_available_thinking_levels

Queue Modes

set_steering_mode

set_follow_up_mode

Compaction

compact

set_auto_compaction

Extension UI

set_extension_ui_capabilities

Retry

set_auto_retry

abort_retry

Bash

bash

abort_bash

Session

get_session_stats

get_tools

export_html

switch_session

start_pending_recovery

fork

clone

get_fork_messages

get_entries

get_tree

get_last_assistant_text

set_session_name

Commands

get_commands

Events

Event Types

agent_start

agent_end

turn_start / turn_end

message_start / message_end

message_update (Streaming)

tool_execution_start / tool_execution_update / tool_execution_end

bash_execution_update

queue_update

compaction_start / compaction_end

auto_retry_start / auto_retry_end

summarization_retry_scheduled / summarization_retry_attempt_start / summarization_retry_finished

extension_error

Error Handling

Types

Model

UserMessage

AssistantMessage

ToolResultMessage

BashExecutionMessage

Attachment