9.1 Long-Running Agents¶

The campaign form of the outer loop: hours to days, unattended, self-set sub-goals, fresh contexts per session with a progress file, and a human who can still be reached. The loop itself lives in 2.5; the verify-and-retry wrapper in 3.7; this is what happens when both run for a long time.

Also called: autonomous agents, long-horizon agents, campaigns, always-on agents.

Stub: scaffolding, not finished writing · planned for a later release. The skeleton below shows the beats this chapter will hit. Contributions welcome.

Why you'd reach for it¶

The problem, what breaks without it, and when you need it. To be written.

What it actually is¶

A crisp definition, the maturity call argued with cited evidence, and how it differs from its neighbours. To be written.

How to do it¶

Code included from a tested file in listing-studio/, so the prose can't drift from working code. To be written.

Gotchas¶

The real costs and when not to, feeding the Anti-Patterns Catalog. To be written.

In short¶

A weighted recommendation: what you would actually do. To be written.

Maturity: Emerging (real model-driven autonomy is promising and still risky in production) · Grounding: companion repo + research · Last reviewed: 2026-06

Sources¶

Citations added as the chapter is written. Every non-obvious claim gets a footnote.