Files
hermes-agent/hermes_cli/curator.py
Teknium 436672de0e feat(curator): add archive and prune subcommands (#20200)
* fix(curator): protect hub skills by frontmatter name

* test(skill_usage): add mark_agent_created to regression test

The cherry-picked test predates #19618/#19621 which rewrote
list_agent_created_skill_names() to require an explicit
created_by: 'agent' provenance marker. Without mark_agent_created(),
my-skill is excluded from the list and the positive assertion fails.

* feat(curator): add archive and prune subcommands

Adds 'hermes curator archive <skill>' and 'hermes curator prune
[--days N] [--yes] [--dry-run]' alongside the existing status, run,
pause, resume, pin, unpin, restore, backup, rollback verbs.

These are the two genuinely new user-facing verbs requested in #19384.
The other verbs proposed there ('stats' and 'restore') already exist
as 'curator status' and 'curator restore', so no duplicate surface is
added — all skill lifecycle commands live under the single 'hermes
curator' namespace.

- archive: manual archive of an agent-created skill. Refuses pinned
  skills with a hint pointing at 'hermes curator unpin'.
- prune: bulk-archive unpinned skills idle for >= N days (default 90).
  Falls back to created_at when last_activity_at is null so never-used
  skills can still be pruned. --dry-run previews, --yes skips prompt.

Adapted from @elmatadorgh's PR #19454 which placed the same verbs
under 'hermes skills' with a separate hermes_cli/skills_config.py
handler and rich table for stats. The 'stats' and 'restore' parts of
that PR duplicated existing surface, so only archive and prune are
kept, rewritten to match hermes_cli/curator.py's existing plain-text
handler style. Tests rewritten from scratch against the new handlers.

Closes #19384

Co-authored-by: elmatadorgh <coktinbaran5@gmail.com>

---------

Co-authored-by: LeonSGP43 <cine.dreamer.one@gmail.com>
Co-authored-by: elmatadorgh <coktinbaran5@gmail.com>
2026-05-05 05:15:54 -07:00

561 lines
19 KiB
Python

"""CLI subcommand: `hermes curator <subcommand>`.
Thin shell around agent/curator.py and tools/skill_usage.py. Renders a status
table, triggers a run, pauses/resumes, and pins/unpins skills.
This module intentionally has no side effects at import time — main.py wires
the argparse subparsers on demand.
"""
from __future__ import annotations
import argparse
import sys
from datetime import datetime, timezone
from typing import Optional
def _fmt_ts(ts: Optional[str]) -> str:
if not ts:
return "never"
try:
dt = datetime.fromisoformat(ts)
except (TypeError, ValueError):
return str(ts)
if dt.tzinfo is None:
dt = dt.replace(tzinfo=timezone.utc)
delta = datetime.now(timezone.utc) - dt
secs = int(delta.total_seconds())
if secs < 60:
return f"{secs}s ago"
if secs < 3600:
return f"{secs // 60}m ago"
if secs < 86400:
return f"{secs // 3600}h ago"
return f"{secs // 86400}d ago"
def _cmd_status(args) -> int:
from agent import curator
from tools import skill_usage
state = curator.load_state()
enabled = curator.is_enabled()
paused = state.get("paused", False)
last_run = state.get("last_run_at")
summary = state.get("last_run_summary") or "(none)"
runs = state.get("run_count", 0)
status_line = (
"ENABLED" if enabled and not paused else
"PAUSED" if paused else
"DISABLED"
)
print(f"curator: {status_line}")
print(f" runs: {runs}")
print(f" last run: {_fmt_ts(last_run)}")
print(f" last summary: {summary}")
_report = state.get("last_report_path")
if _report:
print(f" last report: {_report}")
_ih = curator.get_interval_hours()
_interval_label = (
f"{_ih // 24}d" if _ih % 24 == 0 and _ih >= 24
else f"{_ih}h"
)
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")
rows = skill_usage.agent_created_report()
if not rows:
print("\nno agent-created skills")
return 0
by_state = {"active": [], "stale": [], "archived": []}
pinned = []
for r in rows:
state_name = r.get("state", "active")
by_state.setdefault(state_name, []).append(r)
if r.get("pinned"):
pinned.append(r["name"])
print(f"\nagent-created skills: {len(rows)} total")
for state_name in ("active", "stale", "archived"):
bucket = by_state.get(state_name, [])
print(f" {state_name:10s} {len(bucket)}")
if pinned:
print(f"\npinned ({len(pinned)}): {', '.join(pinned)}")
# Show top 5 least-recently-active skills. Views and edits are activity too:
# curator should not report a skill as "never used" right after skill_view()
# or skill_manage() touched it.
active = sorted(
by_state.get("active", []),
key=lambda r: r.get("last_activity_at") or r.get("created_at") or "",
)[:5]
if active:
print("\nleast recently active (top 5):")
for r in active:
last = _fmt_ts(r.get("last_activity_at"))
print(
f" {r['name']:40s} "
f"activity={r.get('activity_count', 0):3d} "
f"use={r.get('use_count', 0):3d} "
f"view={r.get('view_count', 0):3d} "
f"patches={r.get('patch_count', 0):3d} "
f"last_activity={last}"
)
# Show top 5 most-active and least-active skills by activity_count
# (use + view + patch). This is a different signal from
# least-recently-active: activity_count reflects frequency,
# last_activity_at reflects recency. A skill touched 30 times a year
# ago is high-frequency but stale; a skill touched once yesterday is
# recent but low-frequency. Both can matter.
active_all = by_state.get("active", [])
if active_all:
most_active = sorted(
active_all,
key=lambda r: (r.get("activity_count") or 0, r.get("last_activity_at") or ""),
reverse=True,
)[:5]
if most_active and (most_active[0].get("activity_count") or 0) > 0:
print("\nmost active (top 5):")
for r in most_active:
last = _fmt_ts(r.get("last_activity_at"))
print(
f" {r['name']:40s} "
f"activity={r.get('activity_count', 0):3d} "
f"use={r.get('use_count', 0):3d} "
f"view={r.get('view_count', 0):3d} "
f"patches={r.get('patch_count', 0):3d} "
f"last_activity={last}"
)
least_active = sorted(
active_all,
key=lambda r: (r.get("activity_count") or 0, r.get("last_activity_at") or ""),
)[:5]
if least_active:
print("\nleast active (top 5):")
for r in least_active:
last = _fmt_ts(r.get("last_activity_at"))
print(
f" {r['name']:40s} "
f"activity={r.get('activity_count', 0):3d} "
f"use={r.get('use_count', 0):3d} "
f"view={r.get('view_count', 0):3d} "
f"patches={r.get('patch_count', 0):3d} "
f"last_activity={last}"
)
return 0
def _cmd_run(args) -> int:
from agent import curator
if not curator.is_enabled():
print("curator: disabled via config; enable with `curator.enabled: true`")
return 1
dry = bool(getattr(args, "dry_run", False))
if dry:
print("curator: running DRY-RUN (report only, no mutations)...")
else:
print("curator: running review pass...")
def _on_summary(msg: str) -> None:
print(msg)
result = curator.run_curator_review(
on_summary=_on_summary,
synchronous=bool(args.synchronous),
dry_run=dry,
)
auto = result.get("auto_transitions", {})
if auto:
if dry:
print(
f"auto (preview): {auto.get('checked', 0)} candidate skill(s) "
"— no transitions applied in dry-run"
)
else:
print(
f"auto: checked={auto.get('checked', 0)} "
f"stale={auto.get('marked_stale', 0)} "
f"archived={auto.get('archived', 0)} "
f"reactivated={auto.get('reactivated', 0)}"
)
if not args.synchronous:
print("llm pass running in background — check `hermes curator status` later")
if dry:
print(
"dry-run: no changes applied. When the report lands, read it with "
"`hermes curator status` and run `hermes curator run` (no flag) to apply."
)
return 0
def _cmd_pause(args) -> int:
from agent import curator
curator.set_paused(True)
print("curator: paused")
return 0
def _cmd_resume(args) -> int:
from agent import curator
curator.set_paused(False)
print("curator: resumed")
return 0
def _cmd_pin(args) -> int:
from tools import skill_usage
if not skill_usage.is_agent_created(args.skill):
print(
f"curator: '{args.skill}' is bundled or hub-installed — cannot pin "
"(only agent-created skills participate in curation)"
)
return 1
skill_usage.set_pinned(args.skill, True)
print(f"curator: pinned '{args.skill}' (will bypass auto-transitions)")
return 0
def _cmd_unpin(args) -> int:
from tools import skill_usage
if not skill_usage.is_agent_created(args.skill):
print(
f"curator: '{args.skill}' is bundled or hub-installed — "
"there's nothing to unpin (curator only tracks agent-created skills)"
)
return 1
skill_usage.set_pinned(args.skill, False)
print(f"curator: unpinned '{args.skill}'")
return 0
def _cmd_restore(args) -> int:
from tools import skill_usage
ok, msg = skill_usage.restore_skill(args.skill)
print(f"curator: {msg}")
return 0 if ok else 1
def _cmd_archive(args) -> int:
"""Manually archive an agent-created skill. Refuses if pinned.
The auto-curator archives stale skills on its own schedule; this verb is
for the user who wants to archive *now* without waiting for a run.
"""
from tools import skill_usage
if skill_usage.get_record(args.skill).get("pinned"):
print(
f"curator: '{args.skill}' is pinned — unpin first with "
f"`hermes curator unpin {args.skill}`"
)
return 1
ok, msg = skill_usage.archive_skill(args.skill)
print(f"curator: {msg}")
return 0 if ok else 1
def _idle_days(record: dict) -> Optional[int]:
"""Days since the skill's last activity (view / use / patch).
Falls back to ``created_at`` so a skill that was authored but never used
can still be pruned — otherwise never-touched skills would be immortal.
Returns None only when both fields are missing or unparseable.
"""
ts = record.get("last_activity_at") or record.get("created_at")
if not ts:
return None
try:
dt = datetime.fromisoformat(str(ts))
except (TypeError, ValueError):
return None
if dt.tzinfo is None:
dt = dt.replace(tzinfo=timezone.utc)
return max(0, (datetime.now(timezone.utc) - dt).days)
def _cmd_prune(args) -> int:
"""Bulk-archive agent-created skills idle for >= N days.
Pinned skills are exempt. Already-archived skills are skipped. Default
``--days 90`` matches a conservative read of the curator's own archive
threshold; adjust with ``--days``. Use ``--dry-run`` to preview.
"""
from tools import skill_usage
days = getattr(args, "days", 90)
if days < 1:
print(f"curator: --days must be >= 1 (got {days})", file=sys.stderr)
return 2
dry_run = bool(getattr(args, "dry_run", False))
skip_confirm = bool(getattr(args, "yes", False))
candidates = []
for r in skill_usage.agent_created_report():
if r.get("pinned"):
continue
if r.get("state") == skill_usage.STATE_ARCHIVED:
continue
idle = _idle_days(r)
if idle is None or idle < days:
continue
candidates.append((r["name"], idle))
if not candidates:
print(f"curator: nothing to prune (no unpinned skills idle >= {days}d)")
return 0
candidates.sort(key=lambda c: -c[1])
print(f"curator: {len(candidates)} skill(s) idle >= {days}d:")
for name, idle in candidates:
print(f" {name:40s} idle {idle}d")
if dry_run:
print("\n(dry run — no changes made)")
return 0
if not skip_confirm:
try:
reply = input(f"\nArchive {len(candidates)} skill(s)? [y/N] ").strip().lower()
except (EOFError, KeyboardInterrupt):
print("\ncurator: aborted")
return 1
if reply not in ("y", "yes"):
print("curator: aborted")
return 1
archived = 0
failures = []
for name, _ in candidates:
ok, msg = skill_usage.archive_skill(name)
if ok:
archived += 1
else:
failures.append((name, msg))
print(f"\ncurator: archived {archived}/{len(candidates)}")
if failures:
print("failures:")
for name, msg in failures:
print(f" {name}: {msg}")
return 1
return 0
def _cmd_backup(args) -> int:
"""Take a manual snapshot of the skills tree. Same mechanism as the
automatic pre-run snapshot, just user-initiated."""
from agent import curator_backup
if not curator_backup.is_enabled():
print(
"curator: backups are disabled via config "
"(`curator.backup.enabled: false`); re-enable to snapshot"
)
return 1
reason = getattr(args, "reason", None) or "manual"
snap = curator_backup.snapshot_skills(reason=reason)
if snap is None:
print("curator: snapshot failed — check logs (backup disabled or IO error)")
return 1
print(f"curator: snapshot created at ~/.hermes/skills/.curator_backups/{snap.name}")
return 0
def _cmd_rollback(args) -> int:
"""Restore the skills tree from a snapshot. Defaults to newest.
``--list`` prints available snapshots and exits. ``--id <stamp>`` picks
a specific one. Without ``-y``, prompts for confirmation. A safety
snapshot of the current tree is always taken first, so rollbacks are
themselves undoable.
"""
from agent import curator_backup
if getattr(args, "list", False):
print(curator_backup.summarize_backups())
return 0
backup_id = getattr(args, "backup_id", None)
target_path = curator_backup._resolve_backup(backup_id)
if target_path is None:
rows = curator_backup.list_backups()
if not rows:
print(
"curator: no snapshots exist yet. Take one with "
"`hermes curator backup` or wait for the next curator run."
)
else:
print(
f"curator: no snapshot matching "
f"{'id ' + repr(backup_id) if backup_id else 'your query'}."
)
print("Available:")
print(curator_backup.summarize_backups())
return 1
manifest = curator_backup._read_manifest(target_path)
print(f"Rollback target: {target_path.name}")
if manifest:
print(f" reason: {manifest.get('reason', '?')}")
print(f" created_at: {manifest.get('created_at', '?')}")
print(f" skill files: {manifest.get('skill_files', '?')}")
cron = manifest.get("cron_jobs") or {}
if isinstance(cron, dict):
if cron.get("backed_up"):
print(
f" cron jobs: {cron.get('jobs_count', 0)} "
f"(will be restored for skill-link fields only)"
)
else:
reason = cron.get("reason", "not captured")
print(f" cron jobs: not in snapshot ({reason})")
print(
"\nThis will replace the current ~/.hermes/skills/ tree (a safety "
"snapshot of the current state is taken first so this is undoable). "
"Cron jobs that still exist will have their skills/skill fields "
"restored from the snapshot; all other cron fields are left alone."
)
if not getattr(args, "yes", False):
try:
ans = input("Proceed? [y/N] ").strip().lower()
except (EOFError, KeyboardInterrupt):
print("\ncancelled")
return 1
if ans not in ("y", "yes"):
print("cancelled")
return 1
ok, msg, _ = curator_backup.rollback(backup_id=target_path.name)
if ok:
print(f"curator: {msg}")
return 0
print(f"curator: rollback failed — {msg}")
return 1
# ---------------------------------------------------------------------------
# argparse wiring (called from hermes_cli.main)
# ---------------------------------------------------------------------------
def register_cli(parent: argparse.ArgumentParser) -> None:
"""Attach `curator` subcommands to *parent*.
main.py calls this with the ArgumentParser returned by
``subparsers.add_parser("curator", ...)``.
"""
parent.set_defaults(func=lambda a: (parent.print_help(), 0)[1])
subs = parent.add_subparsers(dest="curator_command")
p_status = subs.add_parser("status", help="Show curator status and skill stats")
p_status.set_defaults(func=_cmd_status)
p_run = subs.add_parser("run", help="Trigger a curator review now")
p_run.add_argument(
"--sync", "--synchronous", dest="synchronous", action="store_true",
help="Wait for the LLM review pass to finish (default: background thread)",
)
p_run.add_argument(
"--dry-run", dest="dry_run", action="store_true",
help="Report only — no state changes, no archives, no consolidation "
"(use this to preview what curator would do)",
)
p_run.set_defaults(func=_cmd_run)
p_pause = subs.add_parser("pause", help="Pause the curator until resumed")
p_pause.set_defaults(func=_cmd_pause)
p_resume = subs.add_parser("resume", help="Resume a paused curator")
p_resume.set_defaults(func=_cmd_resume)
p_pin = subs.add_parser("pin", help="Pin a skill so the curator never auto-transitions it")
p_pin.add_argument("skill", help="Skill name")
p_pin.set_defaults(func=_cmd_pin)
p_unpin = subs.add_parser("unpin", help="Unpin a skill")
p_unpin.add_argument("skill", help="Skill name")
p_unpin.set_defaults(func=_cmd_unpin)
p_restore = subs.add_parser("restore", help="Restore an archived skill")
p_restore.add_argument("skill", help="Skill name")
p_restore.set_defaults(func=_cmd_restore)
p_archive = subs.add_parser(
"archive",
help="Manually archive a skill (move to .archive/, excluded from prompt)",
)
p_archive.add_argument("skill", help="Skill name")
p_archive.set_defaults(func=_cmd_archive)
p_prune = subs.add_parser(
"prune",
help="Bulk-archive agent-created skills idle for >= N days (default 90)",
)
p_prune.add_argument(
"--days", type=int, default=90,
help="Archive skills idle for at least N days (default: 90)",
)
p_prune.add_argument(
"-y", "--yes", action="store_true",
help="Skip the confirmation prompt",
)
p_prune.add_argument(
"--dry-run", dest="dry_run", action="store_true",
help="Show what would be archived without doing it",
)
p_prune.set_defaults(func=_cmd_prune)
p_backup = subs.add_parser(
"backup",
help="Take a manual tar.gz snapshot of ~/.hermes/skills/ "
"(curator also does this automatically before every real run)",
)
p_backup.add_argument(
"--reason", default=None,
help="Free-text label stored in manifest.json (default: 'manual')",
)
p_backup.set_defaults(func=_cmd_backup)
p_rollback = subs.add_parser(
"rollback",
help="Restore ~/.hermes/skills/ from a curator snapshot "
"(defaults to the newest)",
)
p_rollback.add_argument(
"--list", action="store_true",
help="List available snapshots and exit without restoring",
)
p_rollback.add_argument(
"--id", dest="backup_id", default=None,
help="Snapshot id to restore (see `--list`); default: newest",
)
p_rollback.add_argument(
"-y", "--yes", action="store_true",
help="Skip confirmation prompt",
)
p_rollback.set_defaults(func=_cmd_rollback)
def cli_main(argv=None) -> int:
"""Standalone entry (also usable by hermes_cli.main fallthrough)."""
parser = argparse.ArgumentParser(prog="hermes curator")
register_cli(parser)
args = parser.parse_args(argv)
fn = getattr(args, "func", None)
if fn is None:
parser.print_help()
return 0
return int(fn(args) or 0)
if __name__ == "__main__": # pragma: no cover
sys.exit(cli_main())