feat(honcho): async memory integration with prefetch pipeline and recallMode

Adds full Honcho memory integration to Hermes:

- Session manager with async background writes, memory modes (honcho/hybrid/local),
  and dialectic prefetch for first-turn context warming
- Agent integration: prefetch pipeline, tool surface gated by recallMode,
  system prompt context injection, SIGTERM/SIGINT flush handlers
- CLI commands: setup, status, mode, tokens, peer, identity, migrate
- recallMode setting (auto | context | tools) for A/B testing retrieval strategies
- Session strategies: per-session, per-repo (git tree root), per-directory, global
- Polymorphic memoryMode config: string shorthand or per-peer object overrides
- 97 tests covering async writes, client config, session resolution, and memory modes

tools/browser_tool.py

@@ -1640,6 +1640,25 @@ def _cleanup_old_recordings(max_age_hours=72):
         logger.debug("Recording cleanup error (non-critical): %s", e)
 
 
+def _cleanup_old_recordings(max_age_hours=72):
+    """Remove browser recordings older than max_age_hours to prevent disk bloat."""
+    import time
+    try:
+        hermes_home = Path(os.environ.get("HERMES_HOME", Path.home() / ".hermes"))
+        recordings_dir = hermes_home / "browser_recordings"
+        if not recordings_dir.exists():
+            return
+        cutoff = time.time() - (max_age_hours * 3600)
+        for f in recordings_dir.glob("session_*.webm"):
+            try:
+                if f.stat().st_mtime < cutoff:
+                    f.unlink()
+            except Exception:
+                pass
+    except Exception:
+        pass
+
+
 # ============================================================================
 # Cleanup and Management Functions
 # ============================================================================