Safety instructions and safeguards not maintained across long or trimmed contexts

Re-send the system and safety block on every turn, keep it and consent state out of trimming and summaries, and run safety checks on every user message.

In the function that assembles messages for each model call, keep the system and safety instructions outside the trimmable history: pass them on every call (system= for Anthropic, a leading system message for OpenAI) and trim or summarize only the conversation turns that follow. Consent, opt-out, and disclosure state lives in session storage and is re-injected each turn rather than relying on an earlier message surviving. Moderation or crisis checks run on every user message, not only the first, and a session turn cap ends or resets conversations past the length where safeguards are known to weaken.

Where it goes: 1 application source code, 7 prompt construction.

What reviewers look for: message assembly like [system_prompt, *history[-N:], user] or system= passed on each call; trim_messages(..., include_system=True) rather than the default; summaries built from turns only, never replacing the system block; no if len(messages) == 1 or is_first_turn guard around the moderation or crisis call; a turn cap on long sessions.

messages.append({'role': 'user', 'content': text})
messages = messages[-20:]          # messages[0] was the system prompt
reply = client.chat.completions.create(model=MODEL, messages=messages)

history.append({'role': 'user', 'content': text})
if len(history) > MAX_TURNS * 2:
    return end_session('This conversation has reached its length limit. Please start a new one.')
window = [{'role': 'system', 'content': SYSTEM_PROMPT + consent_block(session)},
          *history[-20:]]
reply = client.chat.completions.create(model=MODEL, messages=window)

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.