technical-term · Harness & runtime · maturing · Reviewed

Durable execution

Execution that persists state and can resume safely across process, model, context, worker, or environment interruptions.

Definition

Durable execution externalizes an agent’s state transitions, checkpoints, side-effect status, budgets, and evidence so work can resume without replaying unsafe actions or depending on one model context. It applies distributed-systems principles such as idempotency, leases, retries, and compensation to agent runs.

Workflow durability is established; model-driven, stateful agent runtimes are still evolving.

Why it matters

Long-running agency is state-machine engineering as much as model prompting.

Resumption must distinguish work that was proposed, started, committed, verified, or compensated.

System anatomy

Checkpoint
A durable snapshot of task and control state.
Idempotency
Protection against duplicate effects during retry or recovery.
Lease
Time-bounded ownership of work by one executor.
Compensation
A defined way to reverse or remediate partial effects.

Important distinctions

Long context window
More tokens do not provide transactional durability, concurrency control, or safe replay.
Conversation persistence
Saving messages does not capture exact side-effect and verifier state.

Implementation signals

  • Persist state outside model context
  • Make external effects idempotent or compensatable
  • Checkpoint verifier and approval dispositions

Failure modes

  • Recovery repeats a payment, deployment, or message
  • Stale workers continue after lease expiry

Sources and further study

  1. Anthropic — Scaling Managed Agents: Decoupling the brain from the hands

    An architecture separating durable sessions and environment state from changing models and harnesses.

    Use in this library: First-party case study. This first-party account documents one organization, product, or implementation context and should not be generalized without local evidence.

    engineering · engineering · Published 2026-04-08
  2. Anthropic — Effective harnesses for long-running agents

    Patterns for incremental progress and durable handoffs across context windows and extended execution.

    Use in this library: First-party case study. This first-party account documents one organization, product, or implementation context and should not be generalized without local evidence.

    engineering · engineering · Published 2025-11-26
  3. OpenAI — An open-source spec for Codex orchestration: Symphony

    An orchestration specification that connects project work, isolated agent execution, and reviewable delivery state.

    Use in this library: First-party case study. This first-party account documents one organization, product, or implementation context and should not be generalized without local evidence.

    engineering · engineering · Published 2026-04-27