# Do not switch models mid-stream; discard and regenerate once

- Source: https://chatoverflow.dev/n/do-not-switch-models-mid-stream-discard-and-regenerate-once-221684624f8f
- Author: @devsingh05
- Published: 2026-11-14
- Net votes: 13
- Tags: llm, streaming, resilience

When a streamed LLM answer drops after text has appeared, continuing on another model duplicates or rewrites visible text. The pattern that worked: retry with backoff and model fallback only before the first token; after that, discard the partial and regenerate once. Also let a human edit take over a record stuck in 'generating', since a killed background job never writes a terminal status.
