refactor(context): trim replay cap plumbing

nanobot/session/manager.py

@@ -29,7 +29,6 @@ from nanobot.utils.subagent_channel_display import scrub_subagent_announce_body
 FILE_MAX_MESSAGES = 2000
 MIN_REPLAY_MAX_MESSAGES = 120
 REPLAY_TOKENS_PER_MESSAGE = 100
-DEFAULT_REPLAY_MAX_MESSAGES = FILE_MAX_MESSAGES
 _MESSAGE_TIME_PREFIX_RE = re.compile(r"^\[Message Time: [^\]]+\]\n?")
 _LOCAL_IMAGE_BREADCRUMB_RE = re.compile(r"^\[image: (?:/|~)[^\]]+\]\s*$")
 _TOOL_CALL_ECHO_RE = re.compile(r'^\s*(?:generate_image|message)\([^)]*\)\s*$')
@@ -48,7 +47,7 @@ _FORK_VOLATILE_METADATA_KEYS = {
 
 def replay_max_messages_for_context(context_window_tokens: int | None) -> int:
     if not context_window_tokens or context_window_tokens <= 0:
-        return DEFAULT_REPLAY_MAX_MESSAGES
+        return FILE_MAX_MESSAGES
     return min(
         FILE_MAX_MESSAGES,
         max(MIN_REPLAY_MAX_MESSAGES, context_window_tokens // REPLAY_TOKENS_PER_MESSAGE),
@@ -144,7 +143,7 @@ class Session:
 
     def get_history(
         self,
-        max_messages: int = DEFAULT_REPLAY_MAX_MESSAGES,
+        max_messages: int = FILE_MAX_MESSAGES,
         *,
         max_tokens: int = 0,
         extend_to_user: bool = False,
@@ -155,7 +154,7 @@ class Session:
         token budget from the tail (``max_tokens``) when provided.
         """
         unconsolidated = self.messages[self.last_consolidated:]
-        max_messages = max_messages if max_messages > 0 else DEFAULT_REPLAY_MAX_MESSAGES
+        max_messages = max_messages if max_messages > 0 else FILE_MAX_MESSAGES
         start_idx = recent_message_start_index(
             unconsolidated,
             max_messages,