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.

tests/hermes_cli/test_curator_status.py

@@ -114,6 +114,12 @@ def test_status_shows_most_and_least_used_sections(curator_status_env):
     env["make_skill"]("top-dog")
     env["make_skill"]("middling")
     env["make_skill"]("never-used")
+    # Mark all three as agent-created so they enter the curator's catalog.
+    # Under the provenance-marker semantics, skills must be explicitly opted
+    # into curator management (normally via the background-review fork when
+    # it creates a skill through skill_manage).
+    for n in ("top-dog", "middling", "never-used"):
+        env["skill_usage"].mark_agent_created(n)
 
     # Bump use_count differentially. All three counters (use/view/patch) feed
     # into activity_count, so bumping use alone is enough to make activity
@@ -150,7 +156,9 @@ def test_status_hides_most_active_when_all_zero(curator_status_env):
     env = curator_status_env
     env["make_skill"]("a")
     env["make_skill"]("b")
-    # No bumps.
+    # Mark both as agent-created so the catalog lists them. No bumps.
+    env["skill_usage"].mark_agent_created("a")
+    env["skill_usage"].mark_agent_created("b")
 
     out = _capture_status(env["curator_cli"])
 

tests/tools/test_skill_manager_tool.py

@@ -531,13 +531,41 @@ class TestSkillManageDispatcher:
         assert result["success"] is False
 
     def test_full_create_via_dispatcher(self, tmp_path):
+        """Foreground create does NOT mark the skill as agent-created.
+
+        Skills created by user-directed foreground turns belong to the user;
+        only the background self-improvement review fork should mark its
+        own sediment as agent-created (so the curator can later consolidate
+        or prune it).
+        """
         with _skill_dir(tmp_path):
             raw = skill_manage(action="create", name="test-skill", content=VALID_SKILL_CONTENT)
             from tools.skill_usage import load_usage
             usage = load_usage()
         result = json.loads(raw)
         assert result["success"] is True
-        assert usage["test-skill"]["created_by"] == "agent"
+        # No provenance marker on a foreground create — record either missing
+        # entirely (telemetry best-effort) or present with created_by unset.
+        rec = usage.get("test-skill") or {}
+        assert rec.get("created_by") in (None, "", False)
+
+    def test_create_from_background_review_marks_agent_created(self, tmp_path):
+        """Background-review fork creates ARE marked as agent-created."""
+        from tools.skill_provenance import set_current_write_origin, BACKGROUND_REVIEW
+        token = set_current_write_origin(BACKGROUND_REVIEW)
+        try:
+            with _skill_dir(tmp_path):
+                raw = skill_manage(
+                    action="create", name="review-sediment", content=VALID_SKILL_CONTENT
+                )
+                from tools.skill_usage import load_usage
+                usage = load_usage()
+        finally:
+            from tools.skill_provenance import reset_current_write_origin
+            reset_current_write_origin(token)
+        result = json.loads(raw)
+        assert result["success"] is True
+        assert usage["review-sediment"]["created_by"] == "agent"
 
     def test_delete_via_dispatcher_threads_absorbed_into(self, tmp_path):
         # Dispatcher must plumb absorbed_into through to _delete_skill so the

tests/tools/test_skill_provenance.py

@@ -0,0 +1,102 @@
+"""Tests for tools/skill_provenance.py — write-origin ContextVar."""
+
+import contextvars
+
+import pytest
+
+
+def test_default_origin_is_foreground():
+    from tools.skill_provenance import get_current_write_origin
+    # In a fresh ContextVar context, default kicks in.
+    ctx = contextvars.copy_context()
+    origin = ctx.run(get_current_write_origin)
+    assert origin == "foreground"
+
+
+def test_set_and_get_origin():
+    from tools.skill_provenance import (
+        set_current_write_origin,
+        reset_current_write_origin,
+        get_current_write_origin,
+    )
+    token = set_current_write_origin("background_review")
+    try:
+        assert get_current_write_origin() == "background_review"
+    finally:
+        reset_current_write_origin(token)
+
+
+def test_reset_restores_prior_origin():
+    from tools.skill_provenance import (
+        set_current_write_origin,
+        reset_current_write_origin,
+        get_current_write_origin,
+    )
+    outer = set_current_write_origin("assistant_tool")
+    try:
+        inner = set_current_write_origin("background_review")
+        try:
+            assert get_current_write_origin() == "background_review"
+        finally:
+            reset_current_write_origin(inner)
+        assert get_current_write_origin() == "assistant_tool"
+    finally:
+        reset_current_write_origin(outer)
+
+
+def test_is_background_review_truthy_only_for_review():
+    from tools.skill_provenance import (
+        set_current_write_origin,
+        reset_current_write_origin,
+        is_background_review,
+        BACKGROUND_REVIEW,
+    )
+    for origin, expected in (
+        ("foreground", False),
+        ("assistant_tool", False),
+        ("random_other_value", False),
+        (BACKGROUND_REVIEW, True),
+    ):
+        token = set_current_write_origin(origin)
+        try:
+            assert is_background_review() is expected, (
+                f"is_background_review() wrong for origin={origin!r}"
+            )
+        finally:
+            reset_current_write_origin(token)
+
+
+def test_empty_origin_falls_back_to_foreground():
+    from tools.skill_provenance import (
+        set_current_write_origin,
+        reset_current_write_origin,
+        get_current_write_origin,
+    )
+    token = set_current_write_origin("")
+    try:
+        # Empty is coerced to "foreground" at the set() boundary.
+        assert get_current_write_origin() == "foreground"
+    finally:
+        reset_current_write_origin(token)
+
+
+def test_context_isolation_between_copies():
+    """ContextVar scoping: modifications in one copy do not leak out."""
+    from tools.skill_provenance import (
+        set_current_write_origin,
+        get_current_write_origin,
+        BACKGROUND_REVIEW,
+    )
+
+    # Start at the module default.
+    original = get_current_write_origin()
+
+    def _run_in_copy():
+        set_current_write_origin(BACKGROUND_REVIEW)
+        return get_current_write_origin()
+
+    ctx = contextvars.copy_context()
+    inside = ctx.run(_run_in_copy)
+    assert inside == BACKGROUND_REVIEW
+    # Parent context unaffected.
+    assert get_current_write_origin() == original