Cached AI responses or per-user AI state not scoped to the requester

Key every cache of model responses, embeddings, or session state by tenant and user, and check the stored owner against the requester on each read before serving it.

In the cache layer in front of the model call or the conversation store, build every key from the tenant id and user id plus the content digest, so identical prompts from different users never share an entry, and store the owner id with each entry. On read, compare the stored owner with the authenticated requester and treat a mismatch as a miss (or a 404 for history). Do not install a process-wide LLM cache (LangChain set_llm_cache, @lru_cache on a function whose output carries user data) for user-specific answers; a shared cache is acceptable only for content derived from non-personal inputs that every user receives alike.

Where it goes: 1 application source code, 2 data models, 9 AI output handling.

What reviewers look for: cache keys built like f"{tenant_id}:{user_id}:{digest}" rather than hash(prompt) alone or a semantic_cache.lookup(query) shared by all users; an owner == current_user.id check before a cached reply or session history is returned; no global set_llm_cache(InMemoryCache()), RedisCache, RedisSemanticCache, or @lru_cache serving personalized output.

key = 'resp:' + hashlib.sha256(prompt.encode()).hexdigest()
if (cached := r.get(key)) is not None:
    return {'reply': cached.decode()}
reply = ask_model(user, prompt)
r.set(key, reply, ex=3600)

digest = hashlib.sha256(prompt.encode()).hexdigest()
key = f'resp:{user.tenant_id}:{user.id}:{digest}'
if (cached := r.get(key)) is not None:
    return {'reply': cached.decode()}
reply = ask_model(user, prompt)
r.set(key, reply, ex=3600)

Engineering guidance, not legal advice. Each provision below may add its own details (a cadence, a deadline, a required notice element): open it for those.