feat(memory): enable idle auto compact by default

docs/configuration.md

@@ -1865,7 +1865,7 @@ When a user is idle for longer than a configured threshold, nanobot **proactivel
 
 | Option | Default | Description |
 |--------|---------|-------------|
-| `agents.defaults.idleCompactAfterMinutes` | `0` (disabled) | Minutes of idle time before auto-compaction starts. Set to `0` to disable. Recommended: `15` — close to a typical LLM KV cache expiry window, so stale sessions get compacted before the user returns. |
+| `agents.defaults.idleCompactAfterMinutes` | `15` | Minutes of idle time before auto-compaction starts. Set to `0` to disable. The default is close to a typical LLM KV cache expiry window, so stale sessions get compacted before the user returns. |
 
 `sessionTtlMinutes` remains accepted as a legacy alias for backward compatibility, but `idleCompactAfterMinutes` is the preferred config key going forward.
 
@@ -1880,7 +1880,7 @@ How it works:
 >
 > Concretely, auto compact rewrites `sessions/<key>.jsonl` in place: older messages (including their structured `tool_calls` / `tool_call_id` / `reasoning_content`) are replaced by just the retained recent suffix (currently 8 messages), while the archived prefix is preserved only as a plain-text summary appended to `memory/history.jsonl` (or a `[RAW] ...` flattened dump if LLM summarization fails). The original structured JSON of those turns is no longer recoverable from the session file.
 >
-> This differs from the **token-driven soft consolidation** that fires when a prompt exceeds the context budget: that path only advances an internal `last_consolidated` cursor and leaves the session file untouched, so the raw tool-call trail stays on disk and can still be replayed or audited. If you rely on that trail for debugging or auditing, leave `idleCompactAfterMinutes` at the default `0` and let only the token-driven path run.
+> This differs from the **token-driven soft consolidation** that fires when a prompt exceeds the context budget: that path only advances an internal `last_consolidated` cursor and leaves the session file untouched, so the raw tool-call trail stays on disk and can still be replayed or audited. If you rely on that trail for debugging or auditing, set `idleCompactAfterMinutes` to `0` and let only the token-driven path run.
 
 ## Timezone
 

nanobot/config/schema.py

@@ -145,7 +145,7 @@ class AgentDefaults(Base):
     unified_session: bool = False  # Share one session across all channels (single-user multi-device)
     disabled_skills: list[str] = Field(default_factory=list)  # Skill names to exclude from loading (e.g. ["summarize", "skill-creator"])
     session_ttl_minutes: int = Field(
-        default=0,
+        default=15,
         ge=0,
         validation_alias=AliasChoices("idleCompactAfterMinutes", "sessionTtlMinutes"),
         serialization_alias="idleCompactAfterMinutes",

tests/agent/test_auto_compact.py

@@ -151,9 +151,14 @@ async def _drain_background_tasks(loop: AgentLoop) -> None:
 class TestSessionTTLConfig:
     """Test session TTL configuration."""
 
-    def test_default_ttl_is_zero(self):
-        """Default TTL should be 0 (disabled)."""
+    def test_default_ttl_is_fifteen_minutes(self):
+        """Default TTL should proactively compact stale sessions."""
         defaults = AgentDefaults()
+        assert defaults.session_ttl_minutes == 15
+
+    def test_explicit_zero_disables_ttl(self):
+        """Explicit 0 should still disable idle auto-compact."""
+        defaults = AgentDefaults(session_ttl_minutes=0)
         assert defaults.session_ttl_minutes == 0
 
     def test_custom_ttl(self):