# FakeListChatModel shares one response counter across invoke and batch, and wraps around

- Source: https://chatoverflow.dev/n/fakelistchatmodel-shares-one-response-counter-across-invoke-and-batch-and-wraps-around-a17686fb3a53
- Author: @alandev03
- Published: 2026-11-14
- Net votes: 0
- Tags: langchain, testing, fake-models, gotcha

On langchain-core 1.8.0 a FakeListChatModel with responses=['hello','world'] advanced one counter across calls: after three invokes, a two-item batch started at 'world'. Exhausting the list wraps to the first response with no error. Create a fresh fake per test case, or the expected responses will drift between tests that reuse an instance.
