Files
hermes-agent/tools/skill_provenance.py
Teknium 3c070f9f9d 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.
2026-05-04 02:42:16 -07:00

79 lines
2.5 KiB
Python

"""Skill write-origin provenance — ContextVar for distinguishing agent-sediment skill writes from foreground user-directed writes.
The curator only consolidates/prunes skills it autonomously created via the
background self-improvement review fork. Skills a user asks a foreground
agent to write belong to the user and must never be auto-curated.
This module exposes a ContextVar that run_agent.py sets before each tool
loop so tool handlers (e.g. skill_manage create) can check whether they
are executing inside the background-review fork.
The signal piggybacks on AIAgent._memory_write_origin, which is already
set to "background_review" for review-fork instances (see
_spawn_background_review in run_agent.py) and defaults to "assistant_tool"
for normal (foreground) agents.
Usage:
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:
... # tool runs here
finally:
reset_current_write_origin(token)
# inside a tool:
if get_current_write_origin() == "background_review":
mark_agent_created(skill_name)
"""
import contextvars
_write_origin: contextvars.ContextVar[str] = contextvars.ContextVar(
"skill_write_origin",
default="foreground",
)
# The sentinel value the background review fork uses; mirrors
# run_agent.py's AIAgent._memory_write_origin override in
# _spawn_background_review().
BACKGROUND_REVIEW = "background_review"
def set_current_write_origin(origin: str) -> contextvars.Token[str]:
"""Bind the active write origin to the current context.
Returns a Token the caller must pass to reset_current_write_origin
in a finally block.
"""
return _write_origin.set(origin or "foreground")
def reset_current_write_origin(token: contextvars.Token[str]) -> None:
"""Restore the prior write origin context."""
_write_origin.reset(token)
def get_current_write_origin() -> str:
"""Return the active write origin.
Default: "foreground" — any tool call made by a regular (non-review)
agent, from the CLI, the gateway, cron, or a subagent.
"background_review" — the self-improvement review fork; only skills
created under this origin should be marked agent-created for curator
management.
"""
return _write_origin.get()
def is_background_review() -> bool:
"""Convenience: True iff the current write origin is the background
review fork."""
return get_current_write_origin() == BACKGROUND_REVIEW