> ## Documentation Index > Fetch the complete documentation index at: https://praison.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # In Process Turn Executor • AI Agent SDK > InProcessTurnExecutor: Default turn executor — today's on-loop behaviour, no isolation. # InProcessTurnExecutor > Defined in the [**protocols**](../modules/protocols) module. AI Agent Default turn executor — today's on-loop behaviour, no isolation. Zero-cost, dependency-free implementation of :class:`TurnExecutorProtocol` for single-process deployments. It runs each turn directly on the current event loop exactly as the gateway does today, so selecting it (or leaving the executor unset) is byte-for-byte backward compatible and introduces no dependency. It provides **no** blast-radius isolation: a turn that wedges the loop still affects the process — choosing an isolated executor (subprocess / container / remote, in the wrapper) is what contains a bad turn to its own worker. All turns share one worker (the current process/loop), so every placement carries the same constant `worker_id` at `epoch` 0, and `teardown` is inert — an in-process turn is cancelled through the existing `cancel_token` when the holding task exits, so there is no worker to reclaim. The `limits` argument is accepted for protocol symmetry but is inert here (no separate worker to bound). ## Methods Instance method. Instance method. Instance method. ## Source `praisonaiagents/gateway/protocols.py` at line 5729