State at scale
How LangGraph.js 1.5.1 merges writes to one state key: StateSchema fields with and without reducers, the order of parallel writes, Overwrite and UntrackedValue.
State at scale, Command and Send, subgraphs, time travel, loops that survive and loops that stop, planning, deep agents, and jobs that span sessions.
For developers who can already build agent systems. You work with large graphs and their state, route with Command and Send, rewind and fork runs, build loops that recover from failure and know when to stop, compare planning patterns, and run a deep-agent harness on a long job. Each lab runs real LangGraph.js 1.5.1 in your browser with a scripted model. The deep-agent harness is re-created, and the screens say so.
How LangGraph.js 1.5.1 merges writes to one state key: StateSchema fields with and without reducers, the order of parallel writes, Overwrite and UntrackedValue.
A node can update state and choose the next node in one step with Command, and fan work out to parallel workers with Send, as many as the model asks for.
Build teams of agents from subgraphs, decide how they share state, read their namespaces in the stream, and compare multi-agent patterns by model calls and tokens.
Every superstep saves a checkpoint, so you can read a run's history, replay from a past step, edit a past state and fork a second ending.
Retry policies, timeouts, error handlers and checkpoints keep a long run going when a tool fails or the process stops.
A loop needs stops that hold whatever the model does: a recursion limit, a budget of calls, a detector for repeated calls, and a person who can say no.
Plan-and-execute, ReWOO and LLMCompiler plan the work before they do it, and they differ in model calls, supersteps and time.
Evaluator-optimizer loops, reflection, best-of-n and tree search spend more model calls to get a better answer, and each needs a budget.
A deep agent plans with a todo list, keeps notes in virtual files, hands parts of a job to subagents with a fresh context, and pauses before the tools you name.
A job that spans sessions needs compaction inside a session, hand-off files and memory between sessions, and a check of its whole trajectory.