feat(langgraph): optimize interrupt task scheduling

[casparb]

Note

The original PR was reverted in #6252 because it was breaking CI in langgraph-api due to a bug where invoking an interrupted graph with None would cause duplicate interrupt writes to appear in the task. This has been fixed and a test has been added to verify this:

• test_invoke_interrupted_graph_with_none

Description

Prevents interrupt tasks from executing when the resume value has not yet been specified.

Implemented for sync and async Pregel loop

If a task execution is skipped, the skipped interrupt is still included in the graph result for consistency:

result = graph.invoke(...)
interrupts = result.get("__interrupt__", [])   # [interrupt_1, interrupt_2]

partial_result = graph.invoke(Command(resume=interrupt_1_resume_map), ...)
remaining_interrupts = partial_result.get("__interrupt__", [])  # [interrupt_2]

Tests

• test_interrupt_with_send_payloads: test for a single resume map that resumes all interrupts at once
• test_interrupt_with_send_payloads_sequential_resume: test for two resume maps delivered in sequence
• test_node_with_multiple_interrupts_requires_full_resume test optimization for multiple interrupts within a single node

Solves #6208

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

1 Skipped Deployment

Project	Deployment	Preview	Comments	Updated (UTC)
langgraph-docs-preview	Ignored	Preview		Oct 9, 2025 9:37pm