runs

Represents a wildcard or 'all' selector.

Filter runs by status when bulk-cancelling:

• "pending": Cancel only pending runs.
• "running": Cancel only running runs.
• "all": Cancel all runs regardless of status.

Action to take when cancelling the run.

• "interrupt": Simply cancel the run.
• "rollback": Cancel the run. Then delete the run and associated checkpoints.

Specifies behavior on disconnection:

• "cancel": Cancel the operation on disconnection.
• "continue": Continue the operation even if disconnected.

Durability mode for the graph execution.

• "sync": Changes are persisted synchronously before the next step starts.
• "async": Changes are persisted asynchronously while the next step executes.
• "exit": Changes are persisted only when the graph exits.

Specifies behavior if the thread doesn't exist:

• "create": Create a new thread if it doesn't exist.
• "reject": Reject the operation if the thread doesn't exist.

Defines how to handle multiple tasks:

• "reject": Reject new tasks when busy.
• "interrupt": Interrupt current task for new ones.
• "rollback": Roll back current task and start new one.
• "enqueue": Queue new tasks for later execution.

Defines action after completion:

• "delete": Delete resources after completion.
• "keep": Retain resources after completion.

Represents the status of a run:

• "pending": The run is waiting to start.
• "running": The run is currently executing.
• "error": The run encountered an error and stopped.
• "success": The run completed successfully.
• "timeout": The run exceeded its time limit.
• "interrupted": The run was manually stopped or interrupted.

Defines the mode of streaming:

• "values": Stream only the values.
• "messages": Stream complete messages.
• "updates": Stream updates to the state.
• "events": Stream events occurring during execution.
• "checkpoints": Stream checkpoints as they are created.
• "tasks": Stream task start and finish events.
• "debug": Stream detailed debug information.
• "custom": Stream custom events.

Handle async requests to the LangGraph API.

Adds additional error messaging & content handling above the provided httpx client.

Represents a checkpoint in the execution process.

Represents one or more commands to control graph execution flow and state.

This type defines the control commands that can be returned by nodes to influence graph execution. It lets you navigate to other nodes, update graph state, and resume from interruptions.

Configuration options for a call.

Represents a single execution run.

Defines the parameters for initiating a background run.

Metadata for a run creation request.

Represents a part of a stream response.

Client for managing runs in LangGraph.

A run is a single assistant invocation with optional input, config, context, and metadata. This client manages runs, which can be stateful (on threads) or stateless.

client = get_client(url="http://localhost:2024")
run = await client.runs.create(assistant_id="asst_123", thread_id="thread_456", input={"query": "Hello"})