docs(kanban): clarify decomposer profile roles

hermes_cli/config.py

@@ -2016,11 +2016,11 @@ DEFAULT_CONFIG = {
         # raise these to keep more early failure evidence.
         "worker_log_rotate_bytes": 2 * 1024 * 1024,
         "worker_log_backup_count": 1,
-        # Profile that decomposes tasks in the Triage column. When unset,
-        # falls back to the default profile (the one `hermes` launches with
-        # no -p flag). Set this to a dedicated 'orchestrator' profile if you
-        # want decomposition to use a different model/skills from your main
-        # working profile.
+        # Profile assigned to the root/orchestration task after Triage
+        # decomposition. When unset, falls back to the default profile (the
+        # one `hermes` launches with no -p flag). This does not control the
+        # decomposer prompt, model, or skills; configure that LLM path under
+        # auxiliary.kanban_decomposer.
         "orchestrator_profile": "",
         # Where a child task lands if the orchestrator can't match an
         # assignee to any installed profile. When unset, falls back to the

hermes_cli/kanban_decompose.py

@@ -20,7 +20,7 @@ Design notes
 
 * The system prompt sees the *configured* profile roster — names plus
   descriptions plus the default fallback. Profiles without a
-  description are still listed (with a note) so the orchestrator can
+  description are still listed (with a note) so the decomposer can
   match on name as a fallback, but the user has an obvious incentive
   to describe them.
 
@@ -178,7 +178,7 @@ def _load_config() -> dict:
 
 
 def _resolve_orchestrator_profile(cfg: dict) -> str:
-    """Resolve which profile owns decomposition.
+    """Resolve which profile owns the root/orchestration task after fan-out.
 
     Falls back to the active default profile when ``kanban.orchestrator_profile``
     is unset, so a task is never stranded for lack of an orchestrator.