agent.run

# Option 1: rolling window — keep only the last N messages
MAX_MESSAGES = 10
messages = messages[-MAX_MESSAGES:]

# Option 2: summarise when context exceeds a threshold
def trim_context(messages, max_tokens=3000):
    total = count_tokens(messages)
    if total <= max_tokens:
        return messages
    # Summarise the oldest half, keep the recent half verbatim
    old = messages[:-5]
    recent = messages[-5:]
    summary = llm.summarise(old)
    return [{"role": "system", "content": f"Earlier context: {summary}"}] + recent