nanobot/providers/anthropic_oauth.py

@@ -251,10 +251,12 @@ class AnthropicOAuthProvider(LLMProvider):
             payload["temperature"] = temperature
 
         if system:
-            payload["system"] = system
+            payload["system"] = [{"type": "text", "text": system, "cache_control": {"type": "ephemeral", "ttl": "1h"}}]
 
         if tools:
-            payload["tools"] = tools
+            cached_tools = list(tools)
+            cached_tools[-1] = {**cached_tools[-1], "cache_control": {"type": "ephemeral", "ttl": "1h"}}
+            payload["tools"] = cached_tools
 
         logger.info(
             "Anthropic request: model={} max_tokens={} thinking={} tools={}",
@@ -384,11 +386,15 @@ class AnthropicOAuthProvider(LLMProvider):
 
         stop_reason = response.get("stop_reason", "end_turn")
         thinking_chars = sum(len(b.get("thinking", "")) for b in thinking_blocks) if thinking_blocks else 0
+        raw_usage = response.get("usage", {})
+        cache_write = raw_usage.get("cache_creation_input_tokens", 0)
+        cache_read = raw_usage.get("cache_read_input_tokens", 0)
         logger.info(
             "Anthropic response: stop={} tool_calls={} thinking={} chars, "
-            "input={} output={} tokens",
+            "input={} output={} cache_write={} cache_read={} tokens",
             stop_reason, len(tool_calls), thinking_chars,
             usage.get("prompt_tokens", 0), usage.get("completion_tokens", 0),
+            cache_write, cache_read,
         )
 
         return LLMResponse(