apply_anthropic_cache_control (agent/prompt_caching.py)

Applies Anthropic prompt caching to reduce input token costs by caching system prompt and last 3 messages.

# Source: https://github.com/seojcarlos/hermes-agent | License: MIT | Copyright 2025 Nous Research
# Provided via justclaw.it.com; keep this notice with the code.
"""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, native_anthropic: bool = False) -> None:
    """Add cache_control to a single message, handling all format variations."""
    role = msg.get("role", "")
    content = msg.g

... (truncated -- full source via MCP)