Node Types Reference

This auto-generated reference documents the Input and Output schemas for workflow node types. Descriptions are extracted from proto annotations in workflow_v2.proto.

Common Node Fields

These fields are available on all node types. They provide shared functionality for node identification, conditional execution, thread management, and output handling.

Field	Type	Required
`id`	string	Yes
`type`	string	Yes
`condition`	string	No
`timeout`	string	No
`save_message`	SaveMessageConfig	No
`daemon`	CelDaemonSelector	No
`outcome`	string	No

Thread Configuration

The thread field controls conversation context:

- id: analyze
  type: call_llm
  thread:
    mode: fork      # fork, new, or inherit (default)
    memo: true      # reuse across loop iterations
    inject:
      role: user
      content: "Analyze: {{inputs.data}}"

Conditional Execution

Use condition to skip nodes based on runtime state:

- id: cleanup
  type: run
  condition: "{{nodes.process.exit_code != 0}}"
  run: "rm -rf temp/"

Automatic Message Saving

Use save_message to capture output without a separate save_message node:

- id: summarize
  type: workflow
  ref: builtin://summarizer
  thread:
    mode: fork
  save_message:
    role: assistant
    content: "{{output.summary}}"

Agent

Invoke an agent or sub-workflow

Inputs

Field	Type	Required	Default	Description
`ref`	string	No	-	Workflow reference (builtin://name or project://name)
`args`	map	No	-	Input values for the sub-workflow
`presets`	map	No	-	Preset configurations for sub-workflow inputs
`passthrough`	string	No	-	Input names to forward from parent to child workflow

Ask Question

Pause workflow execution to ask the user a question

Inputs

Field	Type	Required	Default	Description
`metadata`	string	No	-	JSON metadata with question text and options

Outputs

Field	Type	Description
`has_feedback`	boolean	-
`response`	string	-

Call LLM

Send a prompt to a language model and get a response

Inputs

Field	Type	Required	Default	Description
`model`	model	No	-	Model selector using tags (e.g. flagship) or explicit ID
`temperature`	number	No	0.7	Temperature (0-1) controls randomness (range: 0-2)
`thinking_level`	string	No	none	Extended thinking level for complex reasoning (enum: none\|low\|medium\|high\|xhigh)
`system_prompt`	string	No	-	System message for this LLM call
`skills`	array	No	-	Namespaced skill paths to preload for this call (seeded as skill tool-interactions)

Outputs

Field	Type	Description
`response_text`	string	-
`token_count`	integer	-
`upstream_request_id`	string	-
`upstream_proxyman_id`	string	-
`cost`	number	-
`compaction_threshold`	integer	-
`model`	string	-
`pending_inbox`	boolean	-
`message_id`	string	-
`last_stream_seq`	integer	-

Compact

Compact conversation context to reduce token usage

Inputs

Field	Type	Required	Default	Description
`model`	model	No	-	Model used to summarize the conversation (defaults to the built-in summarization tier)

Create Worktree

Create a git worktree for isolated development

Inputs

Field	Type	Required	Default	Description
`name`	string	No	-	Worktree name, used in path
`base_branch`	string	No	-	Base branch to branch from
`copy_files`	string	No	-	Files to copy from source repo (e.g. .env)
`force`	boolean	No	-	Force creation by deleting existing worktree

Outputs

Field	Type	Description
`id`	string	-
`name`	string	-
`path`	string	-
`branch`	string	-
`base_branch`	string	-
`repo_id`	string	-
`status`	string	-

Execute Tools

Execute tool calls from an LLM response

Inputs

Field	Type	Required	Default	Description
`tool_calls`	string	No	-	CEL expression for tool calls to execute

Outputs

Field	Type	Description
`thread_token_count`	integer	-
`total_result_chars`	integer	-

Join

Wait for parallel branches to complete before continuing

Loop

Execute a sub-workflow in a loop with conditions

Inputs

Field	Type	Required	Default	Description
`while`	boolean	No	-	CEL condition: loop continues while true
`parallel`	boolean	No	-	Execute all iterations concurrently
`items`	string	No	-	CEL expression evaluating to a list or map to iterate over
`key`	string	No	-	CEL expression for output map key per iteration
`on_failure`	string	No	-	Failure policy for parallel iterations (enum: continue\|fail_fast\|fail_all)
`passthrough`	string	No	-	Input names to forward from parent to child workflow

Outputs

Field	Type	Description
`iterations`	integer	-
`results`	map	-
`completed`	integer	-
`failed`	integer	-
`parallel`	boolean	-

Router

Route to a workflow or node based on LLM classification

Inputs

Field	Type	Required	Default	Description
`system_prompt`	string	No	-	Custom system prompt for the routing LLM
`model`	model	No	-	Model for routing decision (defaults to fast model)
`fallback`	string	No	-	Fallback preset or node ID if routing decision fails
`outputs`	map	No	-	Declared output mappings (name → CEL expression)

Outputs

Field	Type	Description
`selected_workflow`	string	-
`selected_preset`	string	-
`prompt`	string	-
`reasoning`	string	-
`selected_node`	string	-

Run Command

Execute a shell command

Inputs

Field	Type	Required	Default	Description
`command`	string	No	-	Shell command to execute

Outputs

Field	Type	Description
`exit_code`	integer	-
`stdout`	string	-
`stderr`	string	-
`working_dir`	string	-
`log_file`	string	-

Save Message

Save a message to the conversation thread

Inputs

Field	Type	Required	Default	Description
`role`	string	No	-	Message role (enum: user\|assistant\|system\|tool)
`content`	string	No	-	Message content
`tool_calls`	string	No	-	Tool calls from LLM response
`display_style`	string	No	-	UI display style hint (enum: info\|warning\|success\|hidden)

Outputs

Field	Type	Description
`message`	object	-
`message.id`	string
`message.role`	string
`message.text`	string
`message_id`	string	-
`thread`	string	-
`tool_calls`	array	-
`tool_calls[].id`	string
`tool_calls[].name`	string
`tool_calls[].input`	string
`tool_results`	array	-
`tool_results[].tool_call_id`	string
`tool_results[].name`	string
`tool_results[].content`	string
`tool_results[].is_error`	bool
`thread_token_count`	integer	-
`message_count`	integer	-

​Common Node Fields

​Thread Configuration

​Conditional Execution

​Automatic Message Saving

​Agent

​Inputs

​Ask Question

​Inputs

​Outputs

​Call LLM

​Inputs

​Outputs

​Compact

​Inputs

​Create Worktree

​Inputs

​Outputs

​Execute Tools

​Inputs

​Outputs

​Join

​Loop

​Inputs

​Outputs

​Router

​Inputs

​Outputs

​Run Command

​Inputs

​Outputs

​Save Message

​Inputs

​Outputs

Common Node Fields

Thread Configuration

Conditional Execution

Automatic Message Saving

Agent

Inputs

Ask Question

Inputs

Outputs

Call LLM

Inputs

Outputs

Compact

Inputs

Create Worktree

Inputs

Outputs

Execute Tools

Inputs

Outputs

Join

Loop

Inputs

Outputs

Router

Inputs

Outputs

Run Command

Inputs

Outputs

Save Message

Inputs

Outputs