diff --git a/nanobot/agent/loop.py b/nanobot/agent/loop.py
index a66b6fe9..7ddb9bc0 100644
--- a/nanobot/agent/loop.py
+++ b/nanobot/agent/loop.py
@@ -201,7 +201,7 @@ class AgentLoop:
         timezone: str | None = None,
         session_ttl_minutes: int = 0,
         consolidation_ratio: float = 0.5,
-        max_messages: int = 120,
+        max_messages: int = 500,
         hooks: list[AgentHook] | None = None,
         unified_session: bool = False,
         disabled_skills: list[str] | None = None,
@@ -292,7 +292,7 @@ class AgentLoop:
             llm_wall_timeout_for_session=lambda sk: runner_wall_llm_timeout_s(self.sessions, sk),
         )
         self._unified_session = unified_session
-        self._max_messages = max_messages if max_messages > 0 else 120
+        self._max_messages = max_messages if max_messages > 0 else 500
         self._running = False
         self._mcp_servers = mcp_servers or {}
         self._mcp_stacks: dict[str, AsyncExitStack] = {}
diff --git a/nanobot/config/schema.py b/nanobot/config/schema.py
index feb2d62e..e6212323 100644
--- a/nanobot/config/schema.py
+++ b/nanobot/config/schema.py
@@ -155,9 +155,9 @@ class AgentDefaults(Base):
         serialization_alias="idleCompactAfterMinutes",
     )  # Auto-compact idle threshold in minutes (0 = disabled)
     max_messages: int = Field(
-        default=120,
+        default=500,
         ge=0,
-    )  # Max messages to replay from session history (0 = use default 120, respects token budget)
+    )  # Last-resort max messages to replay from session history (0 = use default 500)
     consolidation_ratio: float = Field(
         default=0.5,
         ge=0.1,
diff --git a/nanobot/session/manager.py b/nanobot/session/manager.py
index c4d39446..44e64c96 100644
--- a/nanobot/session/manager.py
+++ b/nanobot/session/manager.py
@@ -132,7 +132,7 @@ class Session:
 
     def get_history(
         self,
-        max_messages: int = 120,
+        max_messages: int = 500,
         *,
         max_tokens: int = 0,
         extend_to_user: bool = False,
@@ -143,7 +143,7 @@ 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 120
+        max_messages = max_messages if max_messages > 0 else 500
         start_idx = recent_message_start_index(
             unconsolidated,
             max_messages,
diff --git a/tests/agent/test_max_messages_config.py b/tests/agent/test_max_messages_config.py
index e7adccec..ff2b48b9 100644
--- a/tests/agent/test_max_messages_config.py
+++ b/tests/agent/test_max_messages_config.py
@@ -13,7 +13,7 @@ from nanobot.bus.queue import MessageBus
 from nanobot.providers.base import LLMResponse
 from nanobot.session.manager import Session
 
-DEFAULT_MAX_MESSAGES = 120
+DEFAULT_MAX_MESSAGES = 500
 
 
 def _make_loop(tmp_path: Path, max_messages: int = DEFAULT_MAX_MESSAGES) -> AgentLoop: