Human-in-the-Loop: Propose-Then-Commit

The 2026 consensus on HITL is specific. It is not "the agent asks, the user clicks Approve." It is propose-then-commit: the proposed action is persisted to a durable store with an idempotency key; surfaced to a reviewer with intent, data lineage, permissions touched, blast radius, and a rollback plan; committed only after positive acknowledgement; verified after execution to confirm the side effect actually happened. LangGraph's `interrupt()` plus PostgreSQL checkpointing, Microsoft Agent Framework's `RequestInfoEvent`, and Cloudflare's `waitForApproval()` all implement the same shape. The canonical failure mode is the rubber-stamp approval: "Approve?" is clicked without review. The documented mitigation is challenge-and-response with an explicit checklist.

Learn 1 hr Python (stdlib, propose-then-commit state machine with idempotency)

Prerequisites: Phase 15 · 12 (Durable execution), Phase 15 · 14 (Tripwires)

#The Problem

An agent takes an action. The user has to decide: approve or not. If the decision is instant, it is probably not a review. If the decision is structured, it is slow but trustworthy. The engineering question is how to make a structured review the path of least resistance.

The 2023-era HITL pattern was a synchronous prompt: "Agent wants to send email to X with body Y — approve?" The user clicks Approve. Everyone feels the system is safe. In practice this surface is heavily rubber-stamped: users approve fast, approvals predict little, and when the agent goes wrong, the audit trail shows a long history of approvals the user cannot recall.

The 2026 pattern — propose-then-commit — moves HITL onto a durable substrate, attaches structured metadata, and requires positive commit. Every managed agent SDK ships a version: LangGraph interrupt(), Microsoft Agent Framework RequestInfoEvent, Cloudflare waitForApproval(). The API names differ; the shape does not.

#The Problem

Keep going. The rest of this lesson is one step away.