시스템 프롬프트는 절대 안 바뀌어

import anthropic

client = anthropic.Anthropic()

# Built once per conversation and never edited: identity, memory, formatting.
# It must be at least the model's minimum cacheable length (512 tokens on
# Opus 5.5), or nothing is cached at all.
SYSTEM = "You are Pippa. ...(a very long, stable prompt)..."

SPOKEN_RULES = (
    "[Spoken turn] Dad will hear this reply, not read it. For this turn only, "
    "these rules replace the readability guidance in your system prompt: "
    "lead with the answer, one idea at a time, nothing that only works on a screen."
)
DICTATED_RULES = (
    "[Dictated turn] Dad spoke this and it was transcribed. Read it for what he "
    "meant; never point out a transcription error."
)


def send(history: list, text: str, *, dictated: bool, spoken: bool) -> str:
    prefix = []
    if dictated:
        prefix.append({"type": "text", "text": DICTATED_RULES})
    if spoken:
        prefix.append({"type": "text", "text": SPOKEN_RULES})
    user = {"role": "user", "content": prefix + [{"type": "text", "text": text}]}

    with client.messages.stream(
        model="claude-opus-5-5",
        max_tokens=64000,
        system=[{"type": "text", "text": SYSTEM,
                 "cache_control": {"type": "ephemeral", "ttl": "1h"}}],
        messages=history + [user],
        # One effort for every turn. Changing it per request would invalidate
        # the cached history (and, on some models, the system prompt too).
        output_config={"effort": "medium"},
    ) as stream:
        reply = "".join(stream.text_stream)
        final = stream.get_final_message()

    # Append-only history for the API; the app's own record keeps only `text`.
    history += [user, {"role": "assistant", "content": final.content}]
    print("cache read:", final.usage.cache_read_input_tokens)
    return reply


history: list = []
send(history, "What's on my calendar today?", dictated=True, spoken=True)
send(history, "Put that in a table for me.", dictated=False, spoken=False)
# The second call reads SYSTEM from the cache even though voice switched off:
# same system bytes, same effort, and the voice rules live only in the turn.