fix(curator): only mark agent-created for background-review sediment (#19621)

Tighten the provenance semantics added in #19618: skills a user asks a
foreground agent to write via skill_manage(create) now stay invisible to
the curator. Only skills the background self-improvement review fork
sediments through skill_manage get the created_by=agent marker.

- tools/skill_provenance.py — new ContextVar module mirroring the
  _approval_session_key pattern: set_current_write_origin / reset /
  get / is_background_review. Default origin is 'foreground'; the
  review fork sets 'background_review'.
- run_agent.py — run_conversation() binds the ContextVar from
  self._memory_write_origin at the top of each call. The review fork
  runs on its own thread (fresh context), so foreground and review
  contexts never cross-contaminate.
- tools/skill_manager_tool.py — skill_manage(action='create') now
  only calls mark_agent_created() when is_background_review(). All
  other cases (foreground create, patch, edit, write_file, delete)
  continue as before.
- tests: test_skill_provenance.py (6 tests covering the ContextVar
  surface), split test_full_create_via_dispatcher into foreground
  vs. review-fork variants, curator status tests now mark-first.

Why: the agent routinely edits existing user skills on the user's
behalf; those writes must never flip provenance. And when a user
explicitly asks the foreground agent to create a skill, that skill
belongs to the user. The curator should only be cleaning up after
its own autonomous sediment from the review nudge loop.

tools/skill_manager_tool.py

@@ -784,11 +784,16 @@ def skill_manage(
             pass
         # Curator telemetry: bump patch_count on edit/patch/write_file (the actions
         # that mutate an existing skill's guidance), drop the record on delete.
-        # Best-effort; telemetry failures never break the tool.
+        # Only mark a skill as agent-created when the background self-improvement
+        # review fork creates it — foreground `skill_manage(create)` calls are
+        # user-directed, and those skills belong to the user (the curator must
+        # not touch them). Best-effort; telemetry failures never break the tool.
         try:
             from tools.skill_usage import bump_patch, forget, mark_agent_created
+            from tools.skill_provenance import is_background_review
             if action == "create":
-                mark_agent_created(name)
+                if is_background_review():
+                    mark_agent_created(name)
             elif action in ("patch", "edit", "write_file", "remove_file"):
                 bump_patch(name)
             elif action == "delete":