Files
hermes-agent/agent/prompt_caching.py

71 lines
2.0 KiB
Python

"""Anthropic prompt caching (system_and_3 strategy).
Reduces input token costs by ~75% on multi-turn conversations by caching
the conversation prefix. Uses 4 cache_control breakpoints (Anthropic max):
1. System prompt (stable across all turns)
2-4. Last 3 non-system messages (rolling window)
Pure functions -- no class state, no AIAgent dependency.
"""
import copy
from typing import Any, Dict, List
def _apply_cache_marker(msg: dict, cache_marker: dict) -> None:
"""Add cache_control to a single message, handling all format variations."""
role = msg.get("role", "")
content = msg.get("content")
if role == "tool":
msg["cache_control"] = cache_marker
return
if content is None or content == "":
msg["cache_control"] = cache_marker
return
if isinstance(content, str):
msg["content"] = [
{"type": "text", "text": content, "cache_control": cache_marker}
]
return
if isinstance(content, list) and content:
last = content[-1]
if isinstance(last, dict):
last["cache_control"] = cache_marker
def apply_anthropic_cache_control(
api_messages: List[Dict[str, Any]],
cache_ttl: str = "5m",
) -> List[Dict[str, Any]]:
"""Apply system_and_3 caching strategy to messages for Anthropic models.
Places up to 4 cache_control breakpoints: system prompt + last 3 non-system messages.
Returns:
Deep copy of messages with cache_control breakpoints injected.
"""
messages = copy.deepcopy(api_messages)
if not messages:
return messages
marker = {"type": "ephemeral"}
if cache_ttl == "1h":
marker["ttl"] = "1h"
breakpoints_used = 0
if messages[0].get("role") == "system":
_apply_cache_marker(messages[0], marker)
breakpoints_used += 1
remaining = 4 - breakpoints_used
non_sys = [i for i in range(len(messages)) if messages[i].get("role") != "system"]
for idx in non_sys[-remaining:]:
_apply_cache_marker(messages[idx], marker)
return messages