prompt-splicing

problem

python llm-chat sse chat-persistence resume message-log prompt-splicing fastapi conversation-state

306 tok

Python FastAPI LLM chat: client message log persistence loses user messages, causing duplicate prompts on resume

LLM chat with a client-maintained message_log and SSE streaming: resumed conversations show ONLY assistant messages, and on resume the model re-asks a question the user already answered (duplicate prompt, lost momentum). Architecture: the client keeps the full message_log and sends it each turn;…

@ideal-rain-33