Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →jeremylongshore/langchain-langgraph-human-in-loop
Build LangGraph 1.0 human-in-the-loop approval flows with `interrupt_before` / `interrupt_after` and `Command(resume=...)` — JSON-serializable state, clean resume semantics, and UI wiring for approval decisions.
Passed 18 of 22 test cases with the skill, and 13 of 22 without it.
and 3 more in the full report
5 fixed13 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
Our agent state includes Python `set` objects for deduplicated category IDs and a NumPy `ndarray` for vector embeddings. What conversion is required before these fields reach a checkpointer interrupt superstep?
| Checked | Without skill | With skill |
|---|---|---|
| Converts Python set objects into sorted lists. | Missed | Passed |
| Converts NumPy ndarray instances using the tolist method. | Passed | Passed |
The instructions your model reads when the skill loads.
A team adds interrupt_before=["send_email"] to require a human approval
before the email goes out. First integration test crashes at the interrupt
boundary with:
TypeError: Object of type datetime is not JSON serializable
The culprit is two nodes upstream: a classify node stashed
"received_at": datetime.utcnow() into state. Every node-level unit test
passed because node completion does not serialize state — only the
checkpointer does, and only at supersteps that include an interrupt. The
failure is invisible until interrupt time (P17).
A week later the resume path ships. The human reviews the draft, clicks "approve with edits," and the backend runs:
graph.invoke(Command(update={"messages": [corrected_msg]}, resume="approved"), config)
The prior 47 messages vanish. messages was typed as plain
list[AnyMessage] with no reducer, so update replaces the field instead of
appending (P18).
This skill covers: three interrupt styles (interrupt_before,
interrupt_after, inline interrupt()), the JSON-only state invariant with
a pre-interrupt scanner, the Command(resume=...) /
Command(update=..., resume=...) contract, an approval UI wire format
(GET pending / POST decision with optimistic concurrency), safe-cancellation
routing to END, and the tradeoff between native interrupts and a separate
approval service. Pin: langgraph 1.0.x, langgraph-checkpoint 2.0.x.
Pain-catalog anchors: P17, P18 (adjacent: P16, P20).
test cases passed, vs 13 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.