Open Models Almanac
Methodsinference & servingreasoning control

specific method · filed under inference & serving

Persistent reasoning history

Prior reasoning blocks remain available in context across conversation turns, rather than retaining only the latest turn's thinking.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See reasoning control for the methods filed beside it.

Also called persistent reasoning-history chat template, persistent thinking history.

sources
3
models
4
labs adopt it
3
strongest
used

Documented in

Evidence

3 quotes from 3 sources, one card per model, each opening with its strongest.

How sources treat it
used 3

Laguna-S-2.1

Poolsideadopted1 source

We train with persistent thinking history, where all prior reasoning blocks remain visible in the context during each generation step.

usedsoftware implementationin Laguna XS.2Poolside
↑