Add modes self and self_sliding_window for prompt caching (#9372)

* add self compaction method with proper caching (pass in tools, don't refresh sys prompt beforehand) + sliding fallback

* updated prompts for self compaction

* add tests for self, self_sliding_window modes and w/o refresh messages before compaction

* add cache logging to summarization

* better handling to prevent agent from continuing convo on self modes

* if mode changes via summarize endpoint, will use default prompt for the new mode

---------

Co-authored-by: Amy Guan <amy@letta.com>

letta/llm_api/llm_client_base.py

@@ -61,8 +61,11 @@ class LLMClientBase:
         user_id: Optional[str] = None,
         compaction_settings: Optional[Dict] = None,
         llm_config: Optional[Dict] = None,
+        actor: Optional["User"] = None,
     ) -> None:
         """Set telemetry context for provider trace logging."""
+        if actor is not None:
+            self.actor = actor
         self._telemetry_manager = telemetry_manager
         self._telemetry_agent_id = agent_id
         self._telemetry_agent_tags = agent_tags