feat(curator): make skill consolidation opt-in (prune stays default-on) (#47840)

The curator now defaults to prune-only: the deterministic inactivity pass
(mark stale / archive long-unused skills) still runs whenever the curator is
enabled, but the opinionated LLM umbrella-building consolidation fork is OFF
by default.

- agent/curator.py: add DEFAULT_CONSOLIDATE=False + get_consolidate(); gate
  the forked aux-model review in run_curator_review behind it (new consolidate
  param, None=read config). When off, the LLM pass is skipped entirely (no
  aux-model cost); the run is still recorded and reported.
- config.py: add curator.consolidate (default false); v29->v30 migration seeds
  the key for existing installs without clobbering a user-set value.
- hermes_cli/curator.py: 'hermes curator run --consolidate' override; status
  shows consolidate state; prune-only notice on run.
- docs + tests.

hermes_cli/config.py

@@ -1895,6 +1895,14 @@ DEFAULT_CONFIG = {
         # Archive a skill (move to skills/.archive/) after this many days
         # without use. Archived skills are recoverable — no auto-deletion.
         "archive_after_days": 90,
+        # Run the LLM consolidation (umbrella-building) pass. OFF by default.
+        # When off, a curator run does ONLY the deterministic inactivity prune
+        # (mark stale / archive long-unused skills) and skips the forked
+        # aux-model review entirely — no umbrella-building, no aux-model cost.
+        # Set to true to opt back into merging overlapping skills into
+        # class-level umbrellas. `hermes curator run --consolidate` overrides
+        # this for a single invocation.
+        "consolidate": False,
         # Also prune (archive) bundled built-in skills after the inactivity
         # period, not just agent-created ones. ON by default. Built-ins are
         # normally restored on every `hermes update`, so pruning them only
@@ -2569,7 +2577,7 @@ DEFAULT_CONFIG = {
 
 
     # Config schema version - bump this when adding new required fields
-    "_config_version": 29,
+    "_config_version": 30,
 }
 
 # =============================================================================
@@ -4858,6 +4866,29 @@ def migrate_config(interactive: bool = True, quiet: bool = False) -> Dict[str, A
             if not quiet:
                 print("  ✓ Renamed write_mode → write_approval (boolean gate)")
 
+    # ── Version 29 → 30: seed curator.consolidate (default false) ──
+    # Consolidation (the LLM umbrella-building fork) is now an opt-in toggle,
+    # OFF by default. The deterministic inactivity prune still runs whenever
+    # the curator is enabled; only the opinionated, aux-model-cost LLM pass is
+    # gated. The runtime deep-merge already supplies the default, but we seed
+    # the key so it's visible/editable in config.yaml. Existing installs that
+    # WANT the old always-consolidate behavior must set it to true explicitly.
+    # Only add the key when a curator section exists and lacks it — never
+    # clobber a value the user already set.
+    if current_ver < 30:
+        config = read_raw_config()
+        raw_curator = config.get("curator")
+        if isinstance(raw_curator, dict) and "consolidate" not in raw_curator:
+            raw_curator["consolidate"] = False
+            config["curator"] = raw_curator
+            save_config(config)
+            results["config_added"].append("curator.consolidate=false")
+            if not quiet:
+                print(
+                    "  ✓ Seeded curator.consolidate: false "
+                    "(LLM consolidation is now opt-in; pruning stays on)"
+                )
+
     # ── Post-migration: disable exfiltration-shaped MCP stdio entries ──
     # Users can hand-edit mcp_servers, and older installs may already contain a
     # malicious entry. Preserve the stanza for auditability but mark it

hermes_cli/curator.py

@@ -77,6 +77,10 @@ def _cmd_status(args) -> int:
     print(f"  interval:       every {_interval_label}")
     print(f"  stale after:    {curator.get_stale_after_days()}d unused")
     print(f"  archive after:  {curator.get_archive_after_days()}d unused")
+    print(
+        f"  consolidate:    {'on' if curator.get_consolidate() else 'off'}"
+        f"{'' if curator.get_consolidate() else ' (prune-only; LLM merge pass opt-in)'}"
+    )
 
     rows = skill_usage.agent_created_report()
     if not rows:
@@ -174,10 +178,20 @@ def _cmd_run(args) -> int:
     dry = bool(getattr(args, "dry_run", False))
     background = bool(getattr(args, "background", False))
     synchronous = bool(getattr(args, "synchronous", False)) or not background
+    # --consolidate forces the LLM umbrella-building pass on for this run,
+    # overriding the config default (off). When the flag is absent, pass None
+    # so run_curator_review reads curator.consolidate from config.
+    consolidate = True if bool(getattr(args, "consolidate", False)) else None
     if dry:
         print("curator: running DRY-RUN (report only, no mutations)...")
     else:
         print("curator: running review pass...")
+    if consolidate is None and not curator.get_consolidate():
+        print(
+            "curator: consolidation is off — running prune-only "
+            "(deterministic stale/archive). Pass --consolidate or set "
+            "`curator.consolidate: true` to enable the LLM merge pass."
+        )
 
     def _on_summary(msg: str) -> None:
         print(msg)
@@ -186,6 +200,7 @@ def _cmd_run(args) -> int:
         on_summary=_on_summary,
         synchronous=synchronous,
         dry_run=dry,
+        consolidate=consolidate,
     )
     auto = result.get("auto_transitions", {})
     if auto:
@@ -503,6 +518,12 @@ def register_cli(parent: argparse.ArgumentParser) -> None:
         help="Report only — no state changes, no archives, no consolidation "
              "(use this to preview what curator would do)",
     )
+    p_run.add_argument(
+        "--consolidate", dest="consolidate", action="store_true",
+        help="Force the LLM umbrella-building consolidation pass on for this "
+             "run, overriding the config default (off). Without this flag the "
+             "run is prune-only unless `curator.consolidate: true` is set.",
+    )
     p_run.set_defaults(func=_cmd_run)
 
     p_pause = subs.add_parser("pause", help="Pause the curator until resumed")