feat(curator): background skill maintenance (issue #7816)
Adds the Curator — an auxiliary-model background task that periodically
reviews AGENT-CREATED skills and keeps the collection tidy: tracks usage,
transitions unused skills through active → stale → archived, and spawns
a forked AIAgent to consolidate overlaps and patch drift.
Default: enabled, inactivity-triggered (no cron daemon). Runs on CLI
startup and gateway boot when the last run is older than interval_hours
(default 24) AND the agent has been idle for min_idle_hours (default 2).
Invariants (all load-bearing):
- Never touches bundled or hub-installed skills (.bundled_manifest +
.hub/lock.json double-filter)
- Never auto-deletes — archive only. Archives are recoverable
via `hermes curator restore <skill>`
- Pinned skills bypass all auto-transitions
- Uses the aux client; never touches the main session's prompt cache
New files:
- tools/skill_usage.py — sidecar .usage.json telemetry, atomic writes,
provenance filter
- agent/curator.py — orchestrator: config, idle gating, state-machine
transitions (pure, no LLM), forked-agent review prompt
- hermes_cli/curator.py — `hermes curator {status,run,pause,resume,
pin,unpin,restore}` subcommand
- tests/tools/test_skill_usage.py — 29 tests
- tests/agent/test_curator.py — 25 tests
Modified files (surgical patches):
- tools/skills_tool.py — bump view_count on successful skill_view
- tools/skill_manager_tool.py — bump patch_count on skill_manage
patch/edit/write_file/remove_file; forget record on delete
- hermes_cli/config.py — add curator: section to DEFAULT_CONFIG
- hermes_cli/commands.py — add /curator CommandDef with subcommands
- hermes_cli/main.py — register `hermes curator` subparser via
register_cli() from hermes_cli.curator
- cli.py — /curator slash-command dispatch + startup hook
- gateway/run.py — gateway-boot hook (mirrors CLI)
Validation:
- 54 new tests across skill_usage + curator, all passing in 3s
- 346 tests across all touched files' neighbors green
- 2783 tests across hermes_cli/ + gateway/test_run_progress_topics.py green
- CLI smoke: `hermes curator status/pause/resume` work end-to-end
Companion to PR #16026 (class-first skill review prompt) — together
they form a loop: the review prompt stops near-duplicate skill creation
at the source, and the curator prunes/consolidates what still accumulates.
Refs #7816.
2026-04-26 06:08:39 -07:00
|
|
|
"""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}")
|
feat(curator): per-run reports — run.json + REPORT.md under logs/curator/ (#17307)
Every curator pass now emits a dated report directory under
`~/.hermes/logs/curator/{YYYYMMDD-HHMMSS}/` with two files:
- `run.json` — machine-readable full record (before/after snapshot,
state transitions, all tool calls, model/provider, timing, full LLM
final response untruncated, error if any)
- `REPORT.md` — human-readable markdown: model + duration header,
auto-transition counts, LLM consolidation stats, archived-this-run
list, new-skills-this-run list, state transitions, the full LLM
final summary, and a recovery footer pointing at the archive + the
`hermes curator restore` command
Reports live under `logs/curator/`, not inside `skills/` — they're
operational telemetry, not user-authored skill data, and belong
alongside `agent.log` / `gateway.log`.
Internals:
- `_run_llm_review()` now returns a dict (final, summary, model,
provider, tool_calls, error) instead of a bare truncated string so
the reporter has full fidelity
- Report writer is fully best-effort — any failure logs at DEBUG and
never breaks the curator itself. Same-second rerun gets a numeric
suffix so reports can't clobber each other
- Report path stamped into `.curator_state` as `last_report_path`
- `hermes curator status` surfaces a "last report:" line so users
can immediately open the latest run
Tests (all green):
- 7 new tests in tests/agent/test_curator_reports.py covering: report
location (logs not skills), both files written, run.json shape and
diff accuracy, markdown structure, error path still writes, state
transitions captured, same-second runs get unique dirs
- Existing test_run_review_synchronous_invokes_llm_stub updated to
stub the new dict-returning _run_llm_review signature
Live E2E: ran a synchronous pass against a 1-skill test collection
with a stubbed LLM; report written correctly, state stamped with
last_report_path, markdown human-readable, run.json machine-parseable.
2026-04-28 23:23:11 -07:00
|
|
|
_report = state.get("last_report_path")
|
|
|
|
|
if _report:
|
|
|
|
|
print(f" last report: {_report}")
|
2026-04-26 06:32:18 -07:00
|
|
|
_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}")
|
feat(curator): background skill maintenance (issue #7816)
Adds the Curator — an auxiliary-model background task that periodically
reviews AGENT-CREATED skills and keeps the collection tidy: tracks usage,
transitions unused skills through active → stale → archived, and spawns
a forked AIAgent to consolidate overlaps and patch drift.
Default: enabled, inactivity-triggered (no cron daemon). Runs on CLI
startup and gateway boot when the last run is older than interval_hours
(default 24) AND the agent has been idle for min_idle_hours (default 2).
Invariants (all load-bearing):
- Never touches bundled or hub-installed skills (.bundled_manifest +
.hub/lock.json double-filter)
- Never auto-deletes — archive only. Archives are recoverable
via `hermes curator restore <skill>`
- Pinned skills bypass all auto-transitions
- Uses the aux client; never touches the main session's prompt cache
New files:
- tools/skill_usage.py — sidecar .usage.json telemetry, atomic writes,
provenance filter
- agent/curator.py — orchestrator: config, idle gating, state-machine
transitions (pure, no LLM), forked-agent review prompt
- hermes_cli/curator.py — `hermes curator {status,run,pause,resume,
pin,unpin,restore}` subcommand
- tests/tools/test_skill_usage.py — 29 tests
- tests/agent/test_curator.py — 25 tests
Modified files (surgical patches):
- tools/skills_tool.py — bump view_count on successful skill_view
- tools/skill_manager_tool.py — bump patch_count on skill_manage
patch/edit/write_file/remove_file; forget record on delete
- hermes_cli/config.py — add curator: section to DEFAULT_CONFIG
- hermes_cli/commands.py — add /curator CommandDef with subcommands
- hermes_cli/main.py — register `hermes curator` subparser via
register_cli() from hermes_cli.curator
- cli.py — /curator slash-command dispatch + startup hook
- gateway/run.py — gateway-boot hook (mirrors CLI)
Validation:
- 54 new tests across skill_usage + curator, all passing in 3s
- 346 tests across all touched files' neighbors green
- 2783 tests across hermes_cli/ + gateway/test_run_progress_topics.py green
- CLI smoke: `hermes curator status/pause/resume` work end-to-end
Companion to PR #16026 (class-first skill review prompt) — together
they form a loop: the review prompt stops near-duplicate skill creation
at the source, and the curator prunes/consolidates what still accumulates.
Refs #7816.
2026-04-26 06:08:39 -07:00
|
|
|
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)}")
|
|
|
|
|
|
2026-04-30 20:23:17 +08:00
|
|
|
# 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.
|
feat(curator): background skill maintenance (issue #7816)
Adds the Curator — an auxiliary-model background task that periodically
reviews AGENT-CREATED skills and keeps the collection tidy: tracks usage,
transitions unused skills through active → stale → archived, and spawns
a forked AIAgent to consolidate overlaps and patch drift.
Default: enabled, inactivity-triggered (no cron daemon). Runs on CLI
startup and gateway boot when the last run is older than interval_hours
(default 24) AND the agent has been idle for min_idle_hours (default 2).
Invariants (all load-bearing):
- Never touches bundled or hub-installed skills (.bundled_manifest +
.hub/lock.json double-filter)
- Never auto-deletes — archive only. Archives are recoverable
via `hermes curator restore <skill>`
- Pinned skills bypass all auto-transitions
- Uses the aux client; never touches the main session's prompt cache
New files:
- tools/skill_usage.py — sidecar .usage.json telemetry, atomic writes,
provenance filter
- agent/curator.py — orchestrator: config, idle gating, state-machine
transitions (pure, no LLM), forked-agent review prompt
- hermes_cli/curator.py — `hermes curator {status,run,pause,resume,
pin,unpin,restore}` subcommand
- tests/tools/test_skill_usage.py — 29 tests
- tests/agent/test_curator.py — 25 tests
Modified files (surgical patches):
- tools/skills_tool.py — bump view_count on successful skill_view
- tools/skill_manager_tool.py — bump patch_count on skill_manage
patch/edit/write_file/remove_file; forget record on delete
- hermes_cli/config.py — add curator: section to DEFAULT_CONFIG
- hermes_cli/commands.py — add /curator CommandDef with subcommands
- hermes_cli/main.py — register `hermes curator` subparser via
register_cli() from hermes_cli.curator
- cli.py — /curator slash-command dispatch + startup hook
- gateway/run.py — gateway-boot hook (mirrors CLI)
Validation:
- 54 new tests across skill_usage + curator, all passing in 3s
- 346 tests across all touched files' neighbors green
- 2783 tests across hermes_cli/ + gateway/test_run_progress_topics.py green
- CLI smoke: `hermes curator status/pause/resume` work end-to-end
Companion to PR #16026 (class-first skill review prompt) — together
they form a loop: the review prompt stops near-duplicate skill creation
at the source, and the curator prunes/consolidates what still accumulates.
Refs #7816.
2026-04-26 06:08:39 -07:00
|
|
|
active = sorted(
|
|
|
|
|
by_state.get("active", []),
|
2026-04-30 20:23:17 +08:00
|
|
|
key=lambda r: r.get("last_activity_at") or r.get("created_at") or "",
|
feat(curator): background skill maintenance (issue #7816)
Adds the Curator — an auxiliary-model background task that periodically
reviews AGENT-CREATED skills and keeps the collection tidy: tracks usage,
transitions unused skills through active → stale → archived, and spawns
a forked AIAgent to consolidate overlaps and patch drift.
Default: enabled, inactivity-triggered (no cron daemon). Runs on CLI
startup and gateway boot when the last run is older than interval_hours
(default 24) AND the agent has been idle for min_idle_hours (default 2).
Invariants (all load-bearing):
- Never touches bundled or hub-installed skills (.bundled_manifest +
.hub/lock.json double-filter)
- Never auto-deletes — archive only. Archives are recoverable
via `hermes curator restore <skill>`
- Pinned skills bypass all auto-transitions
- Uses the aux client; never touches the main session's prompt cache
New files:
- tools/skill_usage.py — sidecar .usage.json telemetry, atomic writes,
provenance filter
- agent/curator.py — orchestrator: config, idle gating, state-machine
transitions (pure, no LLM), forked-agent review prompt
- hermes_cli/curator.py — `hermes curator {status,run,pause,resume,
pin,unpin,restore}` subcommand
- tests/tools/test_skill_usage.py — 29 tests
- tests/agent/test_curator.py — 25 tests
Modified files (surgical patches):
- tools/skills_tool.py — bump view_count on successful skill_view
- tools/skill_manager_tool.py — bump patch_count on skill_manage
patch/edit/write_file/remove_file; forget record on delete
- hermes_cli/config.py — add curator: section to DEFAULT_CONFIG
- hermes_cli/commands.py — add /curator CommandDef with subcommands
- hermes_cli/main.py — register `hermes curator` subparser via
register_cli() from hermes_cli.curator
- cli.py — /curator slash-command dispatch + startup hook
- gateway/run.py — gateway-boot hook (mirrors CLI)
Validation:
- 54 new tests across skill_usage + curator, all passing in 3s
- 346 tests across all touched files' neighbors green
- 2783 tests across hermes_cli/ + gateway/test_run_progress_topics.py green
- CLI smoke: `hermes curator status/pause/resume` work end-to-end
Companion to PR #16026 (class-first skill review prompt) — together
they form a loop: the review prompt stops near-duplicate skill creation
at the source, and the curator prunes/consolidates what still accumulates.
Refs #7816.
2026-04-26 06:08:39 -07:00
|
|
|
)[:5]
|
|
|
|
|
if active:
|
2026-04-30 20:23:17 +08:00
|
|
|
print("\nleast recently active (top 5):")
|
feat(curator): background skill maintenance (issue #7816)
Adds the Curator — an auxiliary-model background task that periodically
reviews AGENT-CREATED skills and keeps the collection tidy: tracks usage,
transitions unused skills through active → stale → archived, and spawns
a forked AIAgent to consolidate overlaps and patch drift.
Default: enabled, inactivity-triggered (no cron daemon). Runs on CLI
startup and gateway boot when the last run is older than interval_hours
(default 24) AND the agent has been idle for min_idle_hours (default 2).
Invariants (all load-bearing):
- Never touches bundled or hub-installed skills (.bundled_manifest +
.hub/lock.json double-filter)
- Never auto-deletes — archive only. Archives are recoverable
via `hermes curator restore <skill>`
- Pinned skills bypass all auto-transitions
- Uses the aux client; never touches the main session's prompt cache
New files:
- tools/skill_usage.py — sidecar .usage.json telemetry, atomic writes,
provenance filter
- agent/curator.py — orchestrator: config, idle gating, state-machine
transitions (pure, no LLM), forked-agent review prompt
- hermes_cli/curator.py — `hermes curator {status,run,pause,resume,
pin,unpin,restore}` subcommand
- tests/tools/test_skill_usage.py — 29 tests
- tests/agent/test_curator.py — 25 tests
Modified files (surgical patches):
- tools/skills_tool.py — bump view_count on successful skill_view
- tools/skill_manager_tool.py — bump patch_count on skill_manage
patch/edit/write_file/remove_file; forget record on delete
- hermes_cli/config.py — add curator: section to DEFAULT_CONFIG
- hermes_cli/commands.py — add /curator CommandDef with subcommands
- hermes_cli/main.py — register `hermes curator` subparser via
register_cli() from hermes_cli.curator
- cli.py — /curator slash-command dispatch + startup hook
- gateway/run.py — gateway-boot hook (mirrors CLI)
Validation:
- 54 new tests across skill_usage + curator, all passing in 3s
- 346 tests across all touched files' neighbors green
- 2783 tests across hermes_cli/ + gateway/test_run_progress_topics.py green
- CLI smoke: `hermes curator status/pause/resume` work end-to-end
Companion to PR #16026 (class-first skill review prompt) — together
they form a loop: the review prompt stops near-duplicate skill creation
at the source, and the curator prunes/consolidates what still accumulates.
Refs #7816.
2026-04-26 06:08:39 -07:00
|
|
|
for r in active:
|
2026-04-30 20:23:17 +08:00
|
|
|
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}"
|
|
|
|
|
)
|
feat(curator): background skill maintenance (issue #7816)
Adds the Curator — an auxiliary-model background task that periodically
reviews AGENT-CREATED skills and keeps the collection tidy: tracks usage,
transitions unused skills through active → stale → archived, and spawns
a forked AIAgent to consolidate overlaps and patch drift.
Default: enabled, inactivity-triggered (no cron daemon). Runs on CLI
startup and gateway boot when the last run is older than interval_hours
(default 24) AND the agent has been idle for min_idle_hours (default 2).
Invariants (all load-bearing):
- Never touches bundled or hub-installed skills (.bundled_manifest +
.hub/lock.json double-filter)
- Never auto-deletes — archive only. Archives are recoverable
via `hermes curator restore <skill>`
- Pinned skills bypass all auto-transitions
- Uses the aux client; never touches the main session's prompt cache
New files:
- tools/skill_usage.py — sidecar .usage.json telemetry, atomic writes,
provenance filter
- agent/curator.py — orchestrator: config, idle gating, state-machine
transitions (pure, no LLM), forked-agent review prompt
- hermes_cli/curator.py — `hermes curator {status,run,pause,resume,
pin,unpin,restore}` subcommand
- tests/tools/test_skill_usage.py — 29 tests
- tests/agent/test_curator.py — 25 tests
Modified files (surgical patches):
- tools/skills_tool.py — bump view_count on successful skill_view
- tools/skill_manager_tool.py — bump patch_count on skill_manage
patch/edit/write_file/remove_file; forget record on delete
- hermes_cli/config.py — add curator: section to DEFAULT_CONFIG
- hermes_cli/commands.py — add /curator CommandDef with subcommands
- hermes_cli/main.py — register `hermes curator` subparser via
register_cli() from hermes_cli.curator
- cli.py — /curator slash-command dispatch + startup hook
- gateway/run.py — gateway-boot hook (mirrors CLI)
Validation:
- 54 new tests across skill_usage + curator, all passing in 3s
- 346 tests across all touched files' neighbors green
- 2783 tests across hermes_cli/ + gateway/test_run_progress_topics.py green
- CLI smoke: `hermes curator status/pause/resume` work end-to-end
Companion to PR #16026 (class-first skill review prompt) — together
they form a loop: the review prompt stops near-duplicate skill creation
at the source, and the curator prunes/consolidates what still accumulates.
Refs #7816.
2026-04-26 06:08:39 -07:00
|
|
|
|
2026-04-30 10:37:33 -07:00
|
|
|
# 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}"
|
|
|
|
|
)
|
|
|
|
|
|
feat(curator): background skill maintenance (issue #7816)
Adds the Curator — an auxiliary-model background task that periodically
reviews AGENT-CREATED skills and keeps the collection tidy: tracks usage,
transitions unused skills through active → stale → archived, and spawns
a forked AIAgent to consolidate overlaps and patch drift.
Default: enabled, inactivity-triggered (no cron daemon). Runs on CLI
startup and gateway boot when the last run is older than interval_hours
(default 24) AND the agent has been idle for min_idle_hours (default 2).
Invariants (all load-bearing):
- Never touches bundled or hub-installed skills (.bundled_manifest +
.hub/lock.json double-filter)
- Never auto-deletes — archive only. Archives are recoverable
via `hermes curator restore <skill>`
- Pinned skills bypass all auto-transitions
- Uses the aux client; never touches the main session's prompt cache
New files:
- tools/skill_usage.py — sidecar .usage.json telemetry, atomic writes,
provenance filter
- agent/curator.py — orchestrator: config, idle gating, state-machine
transitions (pure, no LLM), forked-agent review prompt
- hermes_cli/curator.py — `hermes curator {status,run,pause,resume,
pin,unpin,restore}` subcommand
- tests/tools/test_skill_usage.py — 29 tests
- tests/agent/test_curator.py — 25 tests
Modified files (surgical patches):
- tools/skills_tool.py — bump view_count on successful skill_view
- tools/skill_manager_tool.py — bump patch_count on skill_manage
patch/edit/write_file/remove_file; forget record on delete
- hermes_cli/config.py — add curator: section to DEFAULT_CONFIG
- hermes_cli/commands.py — add /curator CommandDef with subcommands
- hermes_cli/main.py — register `hermes curator` subparser via
register_cli() from hermes_cli.curator
- cli.py — /curator slash-command dispatch + startup hook
- gateway/run.py — gateway-boot hook (mirrors CLI)
Validation:
- 54 new tests across skill_usage + curator, all passing in 3s
- 346 tests across all touched files' neighbors green
- 2783 tests across hermes_cli/ + gateway/test_run_progress_topics.py green
- CLI smoke: `hermes curator status/pause/resume` work end-to-end
Companion to PR #16026 (class-first skill review prompt) — together
they form a loop: the review prompt stops near-duplicate skill creation
at the source, and the curator prunes/consolidates what still accumulates.
Refs #7816.
2026-04-26 06:08:39 -07:00
|
|
|
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
|
|
|
|
|
|
fix(curator): defer first run and add --dry-run preview (#18373) (#18389)
* fix(curator): defer first run and add --dry-run preview (#18373)
Curator was meant to run 7 days after install, not on the very first
gateway tick. On a fresh install (no .curator_state), should_run_now()
returned True immediately because last_run_at was None — so the gateway
cron ticker fired Curator against a fresh skill library moments after
'hermes update'. Combined with the binary 'agent-created' provenance
model (anything not bundled and not hub-installed), this consolidated
hand-authored user workflow skills without consent.
Changes:
- should_run_now(): first observation seeds last_run_at='now' and returns
False. The next real pass fires one full interval_hours later (7 days
by default), matching the original design intent.
- hermes curator run --dry-run: produces the same review report without
applying automatic transitions OR permitting the LLM to call
skill_manage / terminal mv. A DRY-RUN banner is prepended to the
prompt and the caller skips apply_automatic_transitions. State is
NOT advanced so a preview doesn't defer the next scheduled real pass.
- hermes update: prints a one-liner on fresh installs pointing at
--dry-run, pause, and the docs. Silent on steady state.
- Docs: curator.md and cli-commands.md explain the deferred first-run
behavior and warn that hand-written SKILL.md files share the
'agent-created' bucket, with guidance to pin or preview before the
first pass.
Tests:
- test_first_run_defers replaces the old 'first run always eligible'
assertion — same fixture, inverted expectation.
- test_maybe_run_curator_defers_on_fresh_install covers the gateway tick
path end-to-end.
- Three new dry-run tests cover state-advance suppression, prompt
banner injection, and apply_automatic_transitions skipping.
Fixes #18373.
* feat(curator): pre-run backup + rollback (#18373)
Every real curator pass now snapshots ~/.hermes/skills/ into
~/.hermes/skills/.curator_backups/<utc-iso>/skills.tar.gz before calling
apply_automatic_transitions or the LLM review. If a run consolidates or
archives something the user didn't want touched, 'hermes curator
rollback' restores the tree in one command. Dry-run is skipped — no
mutation means no snapshot needed.
Changes:
- agent/curator_backup.py (new): tar.gz snapshot + safe rollback. The
snapshot excludes .curator_backups/ (would recurse) and .hub/ (managed
by the skills hub). Extract refuses absolute paths and .. components,
and uses tarfile's filter='data' on Python 3.12+. Rollback takes a
pre-rollback safety snapshot FIRST, stages the current tree into
.rollback-staging-<ts>/ so the extract lands in an empty dir, and
cleans the staging dir on success. A failed extract restores the
staged contents.
- agent/curator.py: run_curator_review() calls curator_backup.
snapshot_skills(reason='pre-curator-run') before apply_automatic_
transitions. Best-effort — a failed snapshot logs at debug and the
run continues (a transient disk issue shouldn't silently disable
curator forever).
- hermes_cli/curator.py: new 'hermes curator backup' and 'hermes curator
rollback' subcommands. rollback supports --list, --id <ts>, -y.
- hermes_cli/config.py: curator.backup.{enabled, keep} config block
with sane defaults (enabled=true, keep=5).
- Docs: curator.md gets a 'Backups and rollback' section; cli-commands
.md table gets the new rows.
Tests (new file tests/agent/test_curator_backup.py, 16 cases):
- snapshot creates tarball + manifest with correct counts
- snapshot excludes .curator_backups/ (recursion guard) and .hub/
- snapshot disabled via config returns None without creating anything
- snapshot uniquifies ids within the same second (-01 suffix)
- prune honors keep count, newest-first
- list_backups + _resolve_backup cover newest-default and unknown-id
- rollback restores a deleted skill with content intact
- rollback is itself undoable — safety snapshot shows up in list_backups
- rollback with no snapshots returns an error
- rollback refuses tarballs with absolute paths or .. components
- real curator runs take a 'pre-curator-run' snapshot; dry-runs do not
All curator tests: 210 passing locally.
2026-05-01 09:49:59 -07:00
|
|
|
dry = bool(getattr(args, "dry_run", False))
|
|
|
|
|
if dry:
|
|
|
|
|
print("curator: running DRY-RUN (report only, no mutations)...")
|
|
|
|
|
else:
|
|
|
|
|
print("curator: running review pass...")
|
feat(curator): background skill maintenance (issue #7816)
Adds the Curator — an auxiliary-model background task that periodically
reviews AGENT-CREATED skills and keeps the collection tidy: tracks usage,
transitions unused skills through active → stale → archived, and spawns
a forked AIAgent to consolidate overlaps and patch drift.
Default: enabled, inactivity-triggered (no cron daemon). Runs on CLI
startup and gateway boot when the last run is older than interval_hours
(default 24) AND the agent has been idle for min_idle_hours (default 2).
Invariants (all load-bearing):
- Never touches bundled or hub-installed skills (.bundled_manifest +
.hub/lock.json double-filter)
- Never auto-deletes — archive only. Archives are recoverable
via `hermes curator restore <skill>`
- Pinned skills bypass all auto-transitions
- Uses the aux client; never touches the main session's prompt cache
New files:
- tools/skill_usage.py — sidecar .usage.json telemetry, atomic writes,
provenance filter
- agent/curator.py — orchestrator: config, idle gating, state-machine
transitions (pure, no LLM), forked-agent review prompt
- hermes_cli/curator.py — `hermes curator {status,run,pause,resume,
pin,unpin,restore}` subcommand
- tests/tools/test_skill_usage.py — 29 tests
- tests/agent/test_curator.py — 25 tests
Modified files (surgical patches):
- tools/skills_tool.py — bump view_count on successful skill_view
- tools/skill_manager_tool.py — bump patch_count on skill_manage
patch/edit/write_file/remove_file; forget record on delete
- hermes_cli/config.py — add curator: section to DEFAULT_CONFIG
- hermes_cli/commands.py — add /curator CommandDef with subcommands
- hermes_cli/main.py — register `hermes curator` subparser via
register_cli() from hermes_cli.curator
- cli.py — /curator slash-command dispatch + startup hook
- gateway/run.py — gateway-boot hook (mirrors CLI)
Validation:
- 54 new tests across skill_usage + curator, all passing in 3s
- 346 tests across all touched files' neighbors green
- 2783 tests across hermes_cli/ + gateway/test_run_progress_topics.py green
- CLI smoke: `hermes curator status/pause/resume` work end-to-end
Companion to PR #16026 (class-first skill review prompt) — together
they form a loop: the review prompt stops near-duplicate skill creation
at the source, and the curator prunes/consolidates what still accumulates.
Refs #7816.
2026-04-26 06:08:39 -07:00
|
|
|
|
|
|
|
|
def _on_summary(msg: str) -> None:
|
|
|
|
|
print(msg)
|
|
|
|
|
|
|
|
|
|
result = curator.run_curator_review(
|
|
|
|
|
on_summary=_on_summary,
|
|
|
|
|
synchronous=bool(args.synchronous),
|
fix(curator): defer first run and add --dry-run preview (#18373) (#18389)
* fix(curator): defer first run and add --dry-run preview (#18373)
Curator was meant to run 7 days after install, not on the very first
gateway tick. On a fresh install (no .curator_state), should_run_now()
returned True immediately because last_run_at was None — so the gateway
cron ticker fired Curator against a fresh skill library moments after
'hermes update'. Combined with the binary 'agent-created' provenance
model (anything not bundled and not hub-installed), this consolidated
hand-authored user workflow skills without consent.
Changes:
- should_run_now(): first observation seeds last_run_at='now' and returns
False. The next real pass fires one full interval_hours later (7 days
by default), matching the original design intent.
- hermes curator run --dry-run: produces the same review report without
applying automatic transitions OR permitting the LLM to call
skill_manage / terminal mv. A DRY-RUN banner is prepended to the
prompt and the caller skips apply_automatic_transitions. State is
NOT advanced so a preview doesn't defer the next scheduled real pass.
- hermes update: prints a one-liner on fresh installs pointing at
--dry-run, pause, and the docs. Silent on steady state.
- Docs: curator.md and cli-commands.md explain the deferred first-run
behavior and warn that hand-written SKILL.md files share the
'agent-created' bucket, with guidance to pin or preview before the
first pass.
Tests:
- test_first_run_defers replaces the old 'first run always eligible'
assertion — same fixture, inverted expectation.
- test_maybe_run_curator_defers_on_fresh_install covers the gateway tick
path end-to-end.
- Three new dry-run tests cover state-advance suppression, prompt
banner injection, and apply_automatic_transitions skipping.
Fixes #18373.
* feat(curator): pre-run backup + rollback (#18373)
Every real curator pass now snapshots ~/.hermes/skills/ into
~/.hermes/skills/.curator_backups/<utc-iso>/skills.tar.gz before calling
apply_automatic_transitions or the LLM review. If a run consolidates or
archives something the user didn't want touched, 'hermes curator
rollback' restores the tree in one command. Dry-run is skipped — no
mutation means no snapshot needed.
Changes:
- agent/curator_backup.py (new): tar.gz snapshot + safe rollback. The
snapshot excludes .curator_backups/ (would recurse) and .hub/ (managed
by the skills hub). Extract refuses absolute paths and .. components,
and uses tarfile's filter='data' on Python 3.12+. Rollback takes a
pre-rollback safety snapshot FIRST, stages the current tree into
.rollback-staging-<ts>/ so the extract lands in an empty dir, and
cleans the staging dir on success. A failed extract restores the
staged contents.
- agent/curator.py: run_curator_review() calls curator_backup.
snapshot_skills(reason='pre-curator-run') before apply_automatic_
transitions. Best-effort — a failed snapshot logs at debug and the
run continues (a transient disk issue shouldn't silently disable
curator forever).
- hermes_cli/curator.py: new 'hermes curator backup' and 'hermes curator
rollback' subcommands. rollback supports --list, --id <ts>, -y.
- hermes_cli/config.py: curator.backup.{enabled, keep} config block
with sane defaults (enabled=true, keep=5).
- Docs: curator.md gets a 'Backups and rollback' section; cli-commands
.md table gets the new rows.
Tests (new file tests/agent/test_curator_backup.py, 16 cases):
- snapshot creates tarball + manifest with correct counts
- snapshot excludes .curator_backups/ (recursion guard) and .hub/
- snapshot disabled via config returns None without creating anything
- snapshot uniquifies ids within the same second (-01 suffix)
- prune honors keep count, newest-first
- list_backups + _resolve_backup cover newest-default and unknown-id
- rollback restores a deleted skill with content intact
- rollback is itself undoable — safety snapshot shows up in list_backups
- rollback with no snapshots returns an error
- rollback refuses tarballs with absolute paths or .. components
- real curator runs take a 'pre-curator-run' snapshot; dry-runs do not
All curator tests: 210 passing locally.
2026-05-01 09:49:59 -07:00
|
|
|
dry_run=dry,
|
feat(curator): background skill maintenance (issue #7816)
Adds the Curator — an auxiliary-model background task that periodically
reviews AGENT-CREATED skills and keeps the collection tidy: tracks usage,
transitions unused skills through active → stale → archived, and spawns
a forked AIAgent to consolidate overlaps and patch drift.
Default: enabled, inactivity-triggered (no cron daemon). Runs on CLI
startup and gateway boot when the last run is older than interval_hours
(default 24) AND the agent has been idle for min_idle_hours (default 2).
Invariants (all load-bearing):
- Never touches bundled or hub-installed skills (.bundled_manifest +
.hub/lock.json double-filter)
- Never auto-deletes — archive only. Archives are recoverable
via `hermes curator restore <skill>`
- Pinned skills bypass all auto-transitions
- Uses the aux client; never touches the main session's prompt cache
New files:
- tools/skill_usage.py — sidecar .usage.json telemetry, atomic writes,
provenance filter
- agent/curator.py — orchestrator: config, idle gating, state-machine
transitions (pure, no LLM), forked-agent review prompt
- hermes_cli/curator.py — `hermes curator {status,run,pause,resume,
pin,unpin,restore}` subcommand
- tests/tools/test_skill_usage.py — 29 tests
- tests/agent/test_curator.py — 25 tests
Modified files (surgical patches):
- tools/skills_tool.py — bump view_count on successful skill_view
- tools/skill_manager_tool.py — bump patch_count on skill_manage
patch/edit/write_file/remove_file; forget record on delete
- hermes_cli/config.py — add curator: section to DEFAULT_CONFIG
- hermes_cli/commands.py — add /curator CommandDef with subcommands
- hermes_cli/main.py — register `hermes curator` subparser via
register_cli() from hermes_cli.curator
- cli.py — /curator slash-command dispatch + startup hook
- gateway/run.py — gateway-boot hook (mirrors CLI)
Validation:
- 54 new tests across skill_usage + curator, all passing in 3s
- 346 tests across all touched files' neighbors green
- 2783 tests across hermes_cli/ + gateway/test_run_progress_topics.py green
- CLI smoke: `hermes curator status/pause/resume` work end-to-end
Companion to PR #16026 (class-first skill review prompt) — together
they form a loop: the review prompt stops near-duplicate skill creation
at the source, and the curator prunes/consolidates what still accumulates.
Refs #7816.
2026-04-26 06:08:39 -07:00
|
|
|
)
|
|
|
|
|
auto = result.get("auto_transitions", {})
|
|
|
|
|
if auto:
|
fix(curator): defer first run and add --dry-run preview (#18373) (#18389)
* fix(curator): defer first run and add --dry-run preview (#18373)
Curator was meant to run 7 days after install, not on the very first
gateway tick. On a fresh install (no .curator_state), should_run_now()
returned True immediately because last_run_at was None — so the gateway
cron ticker fired Curator against a fresh skill library moments after
'hermes update'. Combined with the binary 'agent-created' provenance
model (anything not bundled and not hub-installed), this consolidated
hand-authored user workflow skills without consent.
Changes:
- should_run_now(): first observation seeds last_run_at='now' and returns
False. The next real pass fires one full interval_hours later (7 days
by default), matching the original design intent.
- hermes curator run --dry-run: produces the same review report without
applying automatic transitions OR permitting the LLM to call
skill_manage / terminal mv. A DRY-RUN banner is prepended to the
prompt and the caller skips apply_automatic_transitions. State is
NOT advanced so a preview doesn't defer the next scheduled real pass.
- hermes update: prints a one-liner on fresh installs pointing at
--dry-run, pause, and the docs. Silent on steady state.
- Docs: curator.md and cli-commands.md explain the deferred first-run
behavior and warn that hand-written SKILL.md files share the
'agent-created' bucket, with guidance to pin or preview before the
first pass.
Tests:
- test_first_run_defers replaces the old 'first run always eligible'
assertion — same fixture, inverted expectation.
- test_maybe_run_curator_defers_on_fresh_install covers the gateway tick
path end-to-end.
- Three new dry-run tests cover state-advance suppression, prompt
banner injection, and apply_automatic_transitions skipping.
Fixes #18373.
* feat(curator): pre-run backup + rollback (#18373)
Every real curator pass now snapshots ~/.hermes/skills/ into
~/.hermes/skills/.curator_backups/<utc-iso>/skills.tar.gz before calling
apply_automatic_transitions or the LLM review. If a run consolidates or
archives something the user didn't want touched, 'hermes curator
rollback' restores the tree in one command. Dry-run is skipped — no
mutation means no snapshot needed.
Changes:
- agent/curator_backup.py (new): tar.gz snapshot + safe rollback. The
snapshot excludes .curator_backups/ (would recurse) and .hub/ (managed
by the skills hub). Extract refuses absolute paths and .. components,
and uses tarfile's filter='data' on Python 3.12+. Rollback takes a
pre-rollback safety snapshot FIRST, stages the current tree into
.rollback-staging-<ts>/ so the extract lands in an empty dir, and
cleans the staging dir on success. A failed extract restores the
staged contents.
- agent/curator.py: run_curator_review() calls curator_backup.
snapshot_skills(reason='pre-curator-run') before apply_automatic_
transitions. Best-effort — a failed snapshot logs at debug and the
run continues (a transient disk issue shouldn't silently disable
curator forever).
- hermes_cli/curator.py: new 'hermes curator backup' and 'hermes curator
rollback' subcommands. rollback supports --list, --id <ts>, -y.
- hermes_cli/config.py: curator.backup.{enabled, keep} config block
with sane defaults (enabled=true, keep=5).
- Docs: curator.md gets a 'Backups and rollback' section; cli-commands
.md table gets the new rows.
Tests (new file tests/agent/test_curator_backup.py, 16 cases):
- snapshot creates tarball + manifest with correct counts
- snapshot excludes .curator_backups/ (recursion guard) and .hub/
- snapshot disabled via config returns None without creating anything
- snapshot uniquifies ids within the same second (-01 suffix)
- prune honors keep count, newest-first
- list_backups + _resolve_backup cover newest-default and unknown-id
- rollback restores a deleted skill with content intact
- rollback is itself undoable — safety snapshot shows up in list_backups
- rollback with no snapshots returns an error
- rollback refuses tarballs with absolute paths or .. components
- real curator runs take a 'pre-curator-run' snapshot; dry-runs do not
All curator tests: 210 passing locally.
2026-05-01 09:49:59 -07:00
|
|
|
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)}"
|
|
|
|
|
)
|
feat(curator): background skill maintenance (issue #7816)
Adds the Curator — an auxiliary-model background task that periodically
reviews AGENT-CREATED skills and keeps the collection tidy: tracks usage,
transitions unused skills through active → stale → archived, and spawns
a forked AIAgent to consolidate overlaps and patch drift.
Default: enabled, inactivity-triggered (no cron daemon). Runs on CLI
startup and gateway boot when the last run is older than interval_hours
(default 24) AND the agent has been idle for min_idle_hours (default 2).
Invariants (all load-bearing):
- Never touches bundled or hub-installed skills (.bundled_manifest +
.hub/lock.json double-filter)
- Never auto-deletes — archive only. Archives are recoverable
via `hermes curator restore <skill>`
- Pinned skills bypass all auto-transitions
- Uses the aux client; never touches the main session's prompt cache
New files:
- tools/skill_usage.py — sidecar .usage.json telemetry, atomic writes,
provenance filter
- agent/curator.py — orchestrator: config, idle gating, state-machine
transitions (pure, no LLM), forked-agent review prompt
- hermes_cli/curator.py — `hermes curator {status,run,pause,resume,
pin,unpin,restore}` subcommand
- tests/tools/test_skill_usage.py — 29 tests
- tests/agent/test_curator.py — 25 tests
Modified files (surgical patches):
- tools/skills_tool.py — bump view_count on successful skill_view
- tools/skill_manager_tool.py — bump patch_count on skill_manage
patch/edit/write_file/remove_file; forget record on delete
- hermes_cli/config.py — add curator: section to DEFAULT_CONFIG
- hermes_cli/commands.py — add /curator CommandDef with subcommands
- hermes_cli/main.py — register `hermes curator` subparser via
register_cli() from hermes_cli.curator
- cli.py — /curator slash-command dispatch + startup hook
- gateway/run.py — gateway-boot hook (mirrors CLI)
Validation:
- 54 new tests across skill_usage + curator, all passing in 3s
- 346 tests across all touched files' neighbors green
- 2783 tests across hermes_cli/ + gateway/test_run_progress_topics.py green
- CLI smoke: `hermes curator status/pause/resume` work end-to-end
Companion to PR #16026 (class-first skill review prompt) — together
they form a loop: the review prompt stops near-duplicate skill creation
at the source, and the curator prunes/consolidates what still accumulates.
Refs #7816.
2026-04-26 06:08:39 -07:00
|
|
|
if not args.synchronous:
|
|
|
|
|
print("llm pass running in background — check `hermes curator status` later")
|
fix(curator): defer first run and add --dry-run preview (#18373) (#18389)
* fix(curator): defer first run and add --dry-run preview (#18373)
Curator was meant to run 7 days after install, not on the very first
gateway tick. On a fresh install (no .curator_state), should_run_now()
returned True immediately because last_run_at was None — so the gateway
cron ticker fired Curator against a fresh skill library moments after
'hermes update'. Combined with the binary 'agent-created' provenance
model (anything not bundled and not hub-installed), this consolidated
hand-authored user workflow skills without consent.
Changes:
- should_run_now(): first observation seeds last_run_at='now' and returns
False. The next real pass fires one full interval_hours later (7 days
by default), matching the original design intent.
- hermes curator run --dry-run: produces the same review report without
applying automatic transitions OR permitting the LLM to call
skill_manage / terminal mv. A DRY-RUN banner is prepended to the
prompt and the caller skips apply_automatic_transitions. State is
NOT advanced so a preview doesn't defer the next scheduled real pass.
- hermes update: prints a one-liner on fresh installs pointing at
--dry-run, pause, and the docs. Silent on steady state.
- Docs: curator.md and cli-commands.md explain the deferred first-run
behavior and warn that hand-written SKILL.md files share the
'agent-created' bucket, with guidance to pin or preview before the
first pass.
Tests:
- test_first_run_defers replaces the old 'first run always eligible'
assertion — same fixture, inverted expectation.
- test_maybe_run_curator_defers_on_fresh_install covers the gateway tick
path end-to-end.
- Three new dry-run tests cover state-advance suppression, prompt
banner injection, and apply_automatic_transitions skipping.
Fixes #18373.
* feat(curator): pre-run backup + rollback (#18373)
Every real curator pass now snapshots ~/.hermes/skills/ into
~/.hermes/skills/.curator_backups/<utc-iso>/skills.tar.gz before calling
apply_automatic_transitions or the LLM review. If a run consolidates or
archives something the user didn't want touched, 'hermes curator
rollback' restores the tree in one command. Dry-run is skipped — no
mutation means no snapshot needed.
Changes:
- agent/curator_backup.py (new): tar.gz snapshot + safe rollback. The
snapshot excludes .curator_backups/ (would recurse) and .hub/ (managed
by the skills hub). Extract refuses absolute paths and .. components,
and uses tarfile's filter='data' on Python 3.12+. Rollback takes a
pre-rollback safety snapshot FIRST, stages the current tree into
.rollback-staging-<ts>/ so the extract lands in an empty dir, and
cleans the staging dir on success. A failed extract restores the
staged contents.
- agent/curator.py: run_curator_review() calls curator_backup.
snapshot_skills(reason='pre-curator-run') before apply_automatic_
transitions. Best-effort — a failed snapshot logs at debug and the
run continues (a transient disk issue shouldn't silently disable
curator forever).
- hermes_cli/curator.py: new 'hermes curator backup' and 'hermes curator
rollback' subcommands. rollback supports --list, --id <ts>, -y.
- hermes_cli/config.py: curator.backup.{enabled, keep} config block
with sane defaults (enabled=true, keep=5).
- Docs: curator.md gets a 'Backups and rollback' section; cli-commands
.md table gets the new rows.
Tests (new file tests/agent/test_curator_backup.py, 16 cases):
- snapshot creates tarball + manifest with correct counts
- snapshot excludes .curator_backups/ (recursion guard) and .hub/
- snapshot disabled via config returns None without creating anything
- snapshot uniquifies ids within the same second (-01 suffix)
- prune honors keep count, newest-first
- list_backups + _resolve_backup cover newest-default and unknown-id
- rollback restores a deleted skill with content intact
- rollback is itself undoable — safety snapshot shows up in list_backups
- rollback with no snapshots returns an error
- rollback refuses tarballs with absolute paths or .. components
- real curator runs take a 'pre-curator-run' snapshot; dry-runs do not
All curator tests: 210 passing locally.
2026-05-01 09:49:59 -07:00
|
|
|
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."
|
|
|
|
|
)
|
feat(curator): background skill maintenance (issue #7816)
Adds the Curator — an auxiliary-model background task that periodically
reviews AGENT-CREATED skills and keeps the collection tidy: tracks usage,
transitions unused skills through active → stale → archived, and spawns
a forked AIAgent to consolidate overlaps and patch drift.
Default: enabled, inactivity-triggered (no cron daemon). Runs on CLI
startup and gateway boot when the last run is older than interval_hours
(default 24) AND the agent has been idle for min_idle_hours (default 2).
Invariants (all load-bearing):
- Never touches bundled or hub-installed skills (.bundled_manifest +
.hub/lock.json double-filter)
- Never auto-deletes — archive only. Archives are recoverable
via `hermes curator restore <skill>`
- Pinned skills bypass all auto-transitions
- Uses the aux client; never touches the main session's prompt cache
New files:
- tools/skill_usage.py — sidecar .usage.json telemetry, atomic writes,
provenance filter
- agent/curator.py — orchestrator: config, idle gating, state-machine
transitions (pure, no LLM), forked-agent review prompt
- hermes_cli/curator.py — `hermes curator {status,run,pause,resume,
pin,unpin,restore}` subcommand
- tests/tools/test_skill_usage.py — 29 tests
- tests/agent/test_curator.py — 25 tests
Modified files (surgical patches):
- tools/skills_tool.py — bump view_count on successful skill_view
- tools/skill_manager_tool.py — bump patch_count on skill_manage
patch/edit/write_file/remove_file; forget record on delete
- hermes_cli/config.py — add curator: section to DEFAULT_CONFIG
- hermes_cli/commands.py — add /curator CommandDef with subcommands
- hermes_cli/main.py — register `hermes curator` subparser via
register_cli() from hermes_cli.curator
- cli.py — /curator slash-command dispatch + startup hook
- gateway/run.py — gateway-boot hook (mirrors CLI)
Validation:
- 54 new tests across skill_usage + curator, all passing in 3s
- 346 tests across all touched files' neighbors green
- 2783 tests across hermes_cli/ + gateway/test_run_progress_topics.py green
- CLI smoke: `hermes curator status/pause/resume` work end-to-end
Companion to PR #16026 (class-first skill review prompt) — together
they form a loop: the review prompt stops near-duplicate skill creation
at the source, and the curator prunes/consolidates what still accumulates.
Refs #7816.
2026-04-26 06:08:39 -07:00
|
|
|
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
|
2026-04-26 06:17:01 -07:00
|
|
|
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
|
feat(curator): background skill maintenance (issue #7816)
Adds the Curator — an auxiliary-model background task that periodically
reviews AGENT-CREATED skills and keeps the collection tidy: tracks usage,
transitions unused skills through active → stale → archived, and spawns
a forked AIAgent to consolidate overlaps and patch drift.
Default: enabled, inactivity-triggered (no cron daemon). Runs on CLI
startup and gateway boot when the last run is older than interval_hours
(default 24) AND the agent has been idle for min_idle_hours (default 2).
Invariants (all load-bearing):
- Never touches bundled or hub-installed skills (.bundled_manifest +
.hub/lock.json double-filter)
- Never auto-deletes — archive only. Archives are recoverable
via `hermes curator restore <skill>`
- Pinned skills bypass all auto-transitions
- Uses the aux client; never touches the main session's prompt cache
New files:
- tools/skill_usage.py — sidecar .usage.json telemetry, atomic writes,
provenance filter
- agent/curator.py — orchestrator: config, idle gating, state-machine
transitions (pure, no LLM), forked-agent review prompt
- hermes_cli/curator.py — `hermes curator {status,run,pause,resume,
pin,unpin,restore}` subcommand
- tests/tools/test_skill_usage.py — 29 tests
- tests/agent/test_curator.py — 25 tests
Modified files (surgical patches):
- tools/skills_tool.py — bump view_count on successful skill_view
- tools/skill_manager_tool.py — bump patch_count on skill_manage
patch/edit/write_file/remove_file; forget record on delete
- hermes_cli/config.py — add curator: section to DEFAULT_CONFIG
- hermes_cli/commands.py — add /curator CommandDef with subcommands
- hermes_cli/main.py — register `hermes curator` subparser via
register_cli() from hermes_cli.curator
- cli.py — /curator slash-command dispatch + startup hook
- gateway/run.py — gateway-boot hook (mirrors CLI)
Validation:
- 54 new tests across skill_usage + curator, all passing in 3s
- 346 tests across all touched files' neighbors green
- 2783 tests across hermes_cli/ + gateway/test_run_progress_topics.py green
- CLI smoke: `hermes curator status/pause/resume` work end-to-end
Companion to PR #16026 (class-first skill review prompt) — together
they form a loop: the review prompt stops near-duplicate skill creation
at the source, and the curator prunes/consolidates what still accumulates.
Refs #7816.
2026-04-26 06:08:39 -07:00
|
|
|
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
|
|
|
|
|
|
|
|
|
|
|
fix(curator): defer first run and add --dry-run preview (#18373) (#18389)
* fix(curator): defer first run and add --dry-run preview (#18373)
Curator was meant to run 7 days after install, not on the very first
gateway tick. On a fresh install (no .curator_state), should_run_now()
returned True immediately because last_run_at was None — so the gateway
cron ticker fired Curator against a fresh skill library moments after
'hermes update'. Combined with the binary 'agent-created' provenance
model (anything not bundled and not hub-installed), this consolidated
hand-authored user workflow skills without consent.
Changes:
- should_run_now(): first observation seeds last_run_at='now' and returns
False. The next real pass fires one full interval_hours later (7 days
by default), matching the original design intent.
- hermes curator run --dry-run: produces the same review report without
applying automatic transitions OR permitting the LLM to call
skill_manage / terminal mv. A DRY-RUN banner is prepended to the
prompt and the caller skips apply_automatic_transitions. State is
NOT advanced so a preview doesn't defer the next scheduled real pass.
- hermes update: prints a one-liner on fresh installs pointing at
--dry-run, pause, and the docs. Silent on steady state.
- Docs: curator.md and cli-commands.md explain the deferred first-run
behavior and warn that hand-written SKILL.md files share the
'agent-created' bucket, with guidance to pin or preview before the
first pass.
Tests:
- test_first_run_defers replaces the old 'first run always eligible'
assertion — same fixture, inverted expectation.
- test_maybe_run_curator_defers_on_fresh_install covers the gateway tick
path end-to-end.
- Three new dry-run tests cover state-advance suppression, prompt
banner injection, and apply_automatic_transitions skipping.
Fixes #18373.
* feat(curator): pre-run backup + rollback (#18373)
Every real curator pass now snapshots ~/.hermes/skills/ into
~/.hermes/skills/.curator_backups/<utc-iso>/skills.tar.gz before calling
apply_automatic_transitions or the LLM review. If a run consolidates or
archives something the user didn't want touched, 'hermes curator
rollback' restores the tree in one command. Dry-run is skipped — no
mutation means no snapshot needed.
Changes:
- agent/curator_backup.py (new): tar.gz snapshot + safe rollback. The
snapshot excludes .curator_backups/ (would recurse) and .hub/ (managed
by the skills hub). Extract refuses absolute paths and .. components,
and uses tarfile's filter='data' on Python 3.12+. Rollback takes a
pre-rollback safety snapshot FIRST, stages the current tree into
.rollback-staging-<ts>/ so the extract lands in an empty dir, and
cleans the staging dir on success. A failed extract restores the
staged contents.
- agent/curator.py: run_curator_review() calls curator_backup.
snapshot_skills(reason='pre-curator-run') before apply_automatic_
transitions. Best-effort — a failed snapshot logs at debug and the
run continues (a transient disk issue shouldn't silently disable
curator forever).
- hermes_cli/curator.py: new 'hermes curator backup' and 'hermes curator
rollback' subcommands. rollback supports --list, --id <ts>, -y.
- hermes_cli/config.py: curator.backup.{enabled, keep} config block
with sane defaults (enabled=true, keep=5).
- Docs: curator.md gets a 'Backups and rollback' section; cli-commands
.md table gets the new rows.
Tests (new file tests/agent/test_curator_backup.py, 16 cases):
- snapshot creates tarball + manifest with correct counts
- snapshot excludes .curator_backups/ (recursion guard) and .hub/
- snapshot disabled via config returns None without creating anything
- snapshot uniquifies ids within the same second (-01 suffix)
- prune honors keep count, newest-first
- list_backups + _resolve_backup cover newest-default and unknown-id
- rollback restores a deleted skill with content intact
- rollback is itself undoable — safety snapshot shows up in list_backups
- rollback with no snapshots returns an error
- rollback refuses tarballs with absolute paths or .. components
- real curator runs take a 'pre-curator-run' snapshot; dry-runs do not
All curator tests: 210 passing locally.
2026-05-01 09:49:59 -07:00
|
|
|
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', '?')}")
|
fix(curator): authoritative absorbed_into on delete + restore cron skill links on rollback (#18671) (#18731)
* fix(curator): authoritative absorbed_into declarations on skill delete
Closes #18671. The classification pipeline that feeds cron-ref rewriting
used to infer consolidation vs pruning from two brittle signals: the
curator model's post-hoc YAML summary block, and a substring heuristic
scanning other tool calls for the removed skill's name. Both miss in
real consolidations — the model forgets the YAML under reasoning
pressure, and the heuristic misses when the umbrella's patch content
describes the absorbed behavior abstractly instead of naming the old
slug. When both miss, the skill falls through to 'no-evidence fallback'
pruned, and #18253's cron rewriter drops the cron ref entirely instead
of mapping it to the umbrella. Same observable symptom as pre-#18253:
'Skill(s) not found and skipped' at the next cron run.
The fix makes the model declare intent at the moment of deletion.
skill_manage(action='delete') now accepts absorbed_into:
- absorbed_into='<umbrella>' -> consolidated, target must exist on disk
- absorbed_into='' -> explicit prune, no forwarding target
- missing -> legacy path, falls through to heuristic/YAML
The curator reconciler reads these declarations off llm_meta.tool_calls
BEFORE either the YAML block or the substring heuristic. Declaration
wins. Fallback logic stays intact for backward compat with any caller
(human or older curator conversation) that doesn't populate the arg.
Changes
- tools/skill_manager_tool.py: add absorbed_into param to skill_manage
+ _delete_skill. Validate target exists when non-empty. Reject
absorbed_into=<self>. Wire through dispatcher + registry + schema.
- agent/curator.py: new _extract_absorbed_into_declarations() walks
tool calls for skill_manage(delete) with the arg. _reconcile_classification
accepts absorbed_declarations= and treats them as authoritative. Curator
prompt updated to require the arg on every delete.
- Tests: 7 new skill_manager tests covering the tool contract (valid
target, empty string, nonexistent target, self-reference, whitespace,
backward compat, dispatcher plumbing). 11 new curator tests covering
the extractor + authoritative reconciler path + mixed-legacy-and-
declared runs.
Validation
- 307/307 targeted tests pass (curator + cron + skill_manager suites).
- E2E #18671 repro: 3 narrow skills, 1 umbrella, cron job referencing
all 3. Model emits NO YAML block. Heuristic misses (patch prose
doesn't name old slugs). Delete calls carry absorbed_into. Result:
both PR skills correctly classified 'consolidated' + cron rewritten
['pr-review-format', 'pr-review-checklist', 'stale-junk'] ->
['hermes-agent-dev']; stale-junk pruned via absorbed_into=''.
- E2E backward-compat: delete without absorbed_into, model emits YAML
-> routed via existing 'model' source, cron still rewritten correctly.
* feat(curator): capture + restore cron skill links across snapshot/rollback
Before this, rolling back a curator run restored the skills tree but cron
jobs still pointed at the umbrella skills the curator had rewritten them
to. The user would see their old narrow skills back on disk but their
cron jobs still configured with the merged umbrella — not actually 'back
to how it was'.
Snapshot side: snapshot_skills() now captures ~/.hermes/cron/jobs.json
alongside the skills tarball, as cron-jobs.json. The manifest gets a new
'cron_jobs' block with {backed_up, jobs_count} so rollback (and the CLI
confirm dialog) can surface what's in the snapshot. If jobs.json is
missing/unreadable/malformed, snapshot proceeds without cron data — the
skills backup is the core guarantee; cron is additive.
Rollback side: after the skills extract succeeds, the new
_restore_cron_skill_links() reconciles the backed-up jobs into the live
jobs.json SURGICALLY. Only 'skills' and 'skill' fields are restored, and
only on jobs matched by id. Everything else about a cron job — schedule,
last_run_at, next_run_at, enabled, prompt, workdir, hooks — is live
state the user or scheduler has modified since the snapshot; overwriting
it would regress unrelated activity.
Reconciliation rules:
- Job in backup AND live, skills differ → skills restored.
- Job in backup AND live, skills match → no-op.
- Job in backup, NOT in live → skipped (user deleted it
after snapshot; their choice
is later than the snapshot).
- Job in live, NOT in backup → untouched (user created it
after snapshot).
- Snapshot missing cron-jobs.json at all → rollback still succeeds,
reports 'not captured'
(older pre-feature snapshots
keep working).
Writes go through cron.jobs.save_jobs under the same _jobs_file_lock the
scheduler uses, so rollback doesn't race tick().
Also:
- hermes_cli/curator.py: rollback confirm dialog now shows
'cron jobs: N (will be restored for skill-link fields only)' when the
snapshot has cron data, or 'not in snapshot (<reason>)' otherwise.
- rollback()'s message string includes a 'cron links: ...' clause
summarizing the reconciliation outcome.
Tests
- 9 new cases: snapshot-with-cron, snapshot-without-cron, malformed-json
captured-as-raw, full rollback-restores-skills-and-cron, rollback
touches only skill fields, rollback skips user-deleted jobs, rollback
leaves user-created jobs untouched, rollback still works with
pre-feature snapshot that has no cron-jobs.json, standalone unit test
on _restore_cron_skill_links exercising the full report shape.
Validation
- 484/484 targeted tests pass (curator + cron + skill_manager suites).
- E2E: real snapshot_skills, real cron rewrite, real rollback. Before:
['pr-review-format', 'pr-review-checklist', 'pr-triage-salvage'].
After curator: ['hermes-agent-dev']. After rollback: ['pr-review-format',
'pr-review-checklist', 'pr-triage-salvage']. Non-skill fields (id,
name, prompt) preserved across the round trip.
2026-05-02 01:29:57 -07:00
|
|
|
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})")
|
fix(curator): defer first run and add --dry-run preview (#18373) (#18389)
* fix(curator): defer first run and add --dry-run preview (#18373)
Curator was meant to run 7 days after install, not on the very first
gateway tick. On a fresh install (no .curator_state), should_run_now()
returned True immediately because last_run_at was None — so the gateway
cron ticker fired Curator against a fresh skill library moments after
'hermes update'. Combined with the binary 'agent-created' provenance
model (anything not bundled and not hub-installed), this consolidated
hand-authored user workflow skills without consent.
Changes:
- should_run_now(): first observation seeds last_run_at='now' and returns
False. The next real pass fires one full interval_hours later (7 days
by default), matching the original design intent.
- hermes curator run --dry-run: produces the same review report without
applying automatic transitions OR permitting the LLM to call
skill_manage / terminal mv. A DRY-RUN banner is prepended to the
prompt and the caller skips apply_automatic_transitions. State is
NOT advanced so a preview doesn't defer the next scheduled real pass.
- hermes update: prints a one-liner on fresh installs pointing at
--dry-run, pause, and the docs. Silent on steady state.
- Docs: curator.md and cli-commands.md explain the deferred first-run
behavior and warn that hand-written SKILL.md files share the
'agent-created' bucket, with guidance to pin or preview before the
first pass.
Tests:
- test_first_run_defers replaces the old 'first run always eligible'
assertion — same fixture, inverted expectation.
- test_maybe_run_curator_defers_on_fresh_install covers the gateway tick
path end-to-end.
- Three new dry-run tests cover state-advance suppression, prompt
banner injection, and apply_automatic_transitions skipping.
Fixes #18373.
* feat(curator): pre-run backup + rollback (#18373)
Every real curator pass now snapshots ~/.hermes/skills/ into
~/.hermes/skills/.curator_backups/<utc-iso>/skills.tar.gz before calling
apply_automatic_transitions or the LLM review. If a run consolidates or
archives something the user didn't want touched, 'hermes curator
rollback' restores the tree in one command. Dry-run is skipped — no
mutation means no snapshot needed.
Changes:
- agent/curator_backup.py (new): tar.gz snapshot + safe rollback. The
snapshot excludes .curator_backups/ (would recurse) and .hub/ (managed
by the skills hub). Extract refuses absolute paths and .. components,
and uses tarfile's filter='data' on Python 3.12+. Rollback takes a
pre-rollback safety snapshot FIRST, stages the current tree into
.rollback-staging-<ts>/ so the extract lands in an empty dir, and
cleans the staging dir on success. A failed extract restores the
staged contents.
- agent/curator.py: run_curator_review() calls curator_backup.
snapshot_skills(reason='pre-curator-run') before apply_automatic_
transitions. Best-effort — a failed snapshot logs at debug and the
run continues (a transient disk issue shouldn't silently disable
curator forever).
- hermes_cli/curator.py: new 'hermes curator backup' and 'hermes curator
rollback' subcommands. rollback supports --list, --id <ts>, -y.
- hermes_cli/config.py: curator.backup.{enabled, keep} config block
with sane defaults (enabled=true, keep=5).
- Docs: curator.md gets a 'Backups and rollback' section; cli-commands
.md table gets the new rows.
Tests (new file tests/agent/test_curator_backup.py, 16 cases):
- snapshot creates tarball + manifest with correct counts
- snapshot excludes .curator_backups/ (recursion guard) and .hub/
- snapshot disabled via config returns None without creating anything
- snapshot uniquifies ids within the same second (-01 suffix)
- prune honors keep count, newest-first
- list_backups + _resolve_backup cover newest-default and unknown-id
- rollback restores a deleted skill with content intact
- rollback is itself undoable — safety snapshot shows up in list_backups
- rollback with no snapshots returns an error
- rollback refuses tarballs with absolute paths or .. components
- real curator runs take a 'pre-curator-run' snapshot; dry-runs do not
All curator tests: 210 passing locally.
2026-05-01 09:49:59 -07:00
|
|
|
print(
|
|
|
|
|
"\nThis will replace the current ~/.hermes/skills/ tree (a safety "
|
fix(curator): authoritative absorbed_into on delete + restore cron skill links on rollback (#18671) (#18731)
* fix(curator): authoritative absorbed_into declarations on skill delete
Closes #18671. The classification pipeline that feeds cron-ref rewriting
used to infer consolidation vs pruning from two brittle signals: the
curator model's post-hoc YAML summary block, and a substring heuristic
scanning other tool calls for the removed skill's name. Both miss in
real consolidations — the model forgets the YAML under reasoning
pressure, and the heuristic misses when the umbrella's patch content
describes the absorbed behavior abstractly instead of naming the old
slug. When both miss, the skill falls through to 'no-evidence fallback'
pruned, and #18253's cron rewriter drops the cron ref entirely instead
of mapping it to the umbrella. Same observable symptom as pre-#18253:
'Skill(s) not found and skipped' at the next cron run.
The fix makes the model declare intent at the moment of deletion.
skill_manage(action='delete') now accepts absorbed_into:
- absorbed_into='<umbrella>' -> consolidated, target must exist on disk
- absorbed_into='' -> explicit prune, no forwarding target
- missing -> legacy path, falls through to heuristic/YAML
The curator reconciler reads these declarations off llm_meta.tool_calls
BEFORE either the YAML block or the substring heuristic. Declaration
wins. Fallback logic stays intact for backward compat with any caller
(human or older curator conversation) that doesn't populate the arg.
Changes
- tools/skill_manager_tool.py: add absorbed_into param to skill_manage
+ _delete_skill. Validate target exists when non-empty. Reject
absorbed_into=<self>. Wire through dispatcher + registry + schema.
- agent/curator.py: new _extract_absorbed_into_declarations() walks
tool calls for skill_manage(delete) with the arg. _reconcile_classification
accepts absorbed_declarations= and treats them as authoritative. Curator
prompt updated to require the arg on every delete.
- Tests: 7 new skill_manager tests covering the tool contract (valid
target, empty string, nonexistent target, self-reference, whitespace,
backward compat, dispatcher plumbing). 11 new curator tests covering
the extractor + authoritative reconciler path + mixed-legacy-and-
declared runs.
Validation
- 307/307 targeted tests pass (curator + cron + skill_manager suites).
- E2E #18671 repro: 3 narrow skills, 1 umbrella, cron job referencing
all 3. Model emits NO YAML block. Heuristic misses (patch prose
doesn't name old slugs). Delete calls carry absorbed_into. Result:
both PR skills correctly classified 'consolidated' + cron rewritten
['pr-review-format', 'pr-review-checklist', 'stale-junk'] ->
['hermes-agent-dev']; stale-junk pruned via absorbed_into=''.
- E2E backward-compat: delete without absorbed_into, model emits YAML
-> routed via existing 'model' source, cron still rewritten correctly.
* feat(curator): capture + restore cron skill links across snapshot/rollback
Before this, rolling back a curator run restored the skills tree but cron
jobs still pointed at the umbrella skills the curator had rewritten them
to. The user would see their old narrow skills back on disk but their
cron jobs still configured with the merged umbrella — not actually 'back
to how it was'.
Snapshot side: snapshot_skills() now captures ~/.hermes/cron/jobs.json
alongside the skills tarball, as cron-jobs.json. The manifest gets a new
'cron_jobs' block with {backed_up, jobs_count} so rollback (and the CLI
confirm dialog) can surface what's in the snapshot. If jobs.json is
missing/unreadable/malformed, snapshot proceeds without cron data — the
skills backup is the core guarantee; cron is additive.
Rollback side: after the skills extract succeeds, the new
_restore_cron_skill_links() reconciles the backed-up jobs into the live
jobs.json SURGICALLY. Only 'skills' and 'skill' fields are restored, and
only on jobs matched by id. Everything else about a cron job — schedule,
last_run_at, next_run_at, enabled, prompt, workdir, hooks — is live
state the user or scheduler has modified since the snapshot; overwriting
it would regress unrelated activity.
Reconciliation rules:
- Job in backup AND live, skills differ → skills restored.
- Job in backup AND live, skills match → no-op.
- Job in backup, NOT in live → skipped (user deleted it
after snapshot; their choice
is later than the snapshot).
- Job in live, NOT in backup → untouched (user created it
after snapshot).
- Snapshot missing cron-jobs.json at all → rollback still succeeds,
reports 'not captured'
(older pre-feature snapshots
keep working).
Writes go through cron.jobs.save_jobs under the same _jobs_file_lock the
scheduler uses, so rollback doesn't race tick().
Also:
- hermes_cli/curator.py: rollback confirm dialog now shows
'cron jobs: N (will be restored for skill-link fields only)' when the
snapshot has cron data, or 'not in snapshot (<reason>)' otherwise.
- rollback()'s message string includes a 'cron links: ...' clause
summarizing the reconciliation outcome.
Tests
- 9 new cases: snapshot-with-cron, snapshot-without-cron, malformed-json
captured-as-raw, full rollback-restores-skills-and-cron, rollback
touches only skill fields, rollback skips user-deleted jobs, rollback
leaves user-created jobs untouched, rollback still works with
pre-feature snapshot that has no cron-jobs.json, standalone unit test
on _restore_cron_skill_links exercising the full report shape.
Validation
- 484/484 targeted tests pass (curator + cron + skill_manager suites).
- E2E: real snapshot_skills, real cron rewrite, real rollback. Before:
['pr-review-format', 'pr-review-checklist', 'pr-triage-salvage'].
After curator: ['hermes-agent-dev']. After rollback: ['pr-review-format',
'pr-review-checklist', 'pr-triage-salvage']. Non-skill fields (id,
name, prompt) preserved across the round trip.
2026-05-02 01:29:57 -07:00
|
|
|
"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."
|
fix(curator): defer first run and add --dry-run preview (#18373) (#18389)
* fix(curator): defer first run and add --dry-run preview (#18373)
Curator was meant to run 7 days after install, not on the very first
gateway tick. On a fresh install (no .curator_state), should_run_now()
returned True immediately because last_run_at was None — so the gateway
cron ticker fired Curator against a fresh skill library moments after
'hermes update'. Combined with the binary 'agent-created' provenance
model (anything not bundled and not hub-installed), this consolidated
hand-authored user workflow skills without consent.
Changes:
- should_run_now(): first observation seeds last_run_at='now' and returns
False. The next real pass fires one full interval_hours later (7 days
by default), matching the original design intent.
- hermes curator run --dry-run: produces the same review report without
applying automatic transitions OR permitting the LLM to call
skill_manage / terminal mv. A DRY-RUN banner is prepended to the
prompt and the caller skips apply_automatic_transitions. State is
NOT advanced so a preview doesn't defer the next scheduled real pass.
- hermes update: prints a one-liner on fresh installs pointing at
--dry-run, pause, and the docs. Silent on steady state.
- Docs: curator.md and cli-commands.md explain the deferred first-run
behavior and warn that hand-written SKILL.md files share the
'agent-created' bucket, with guidance to pin or preview before the
first pass.
Tests:
- test_first_run_defers replaces the old 'first run always eligible'
assertion — same fixture, inverted expectation.
- test_maybe_run_curator_defers_on_fresh_install covers the gateway tick
path end-to-end.
- Three new dry-run tests cover state-advance suppression, prompt
banner injection, and apply_automatic_transitions skipping.
Fixes #18373.
* feat(curator): pre-run backup + rollback (#18373)
Every real curator pass now snapshots ~/.hermes/skills/ into
~/.hermes/skills/.curator_backups/<utc-iso>/skills.tar.gz before calling
apply_automatic_transitions or the LLM review. If a run consolidates or
archives something the user didn't want touched, 'hermes curator
rollback' restores the tree in one command. Dry-run is skipped — no
mutation means no snapshot needed.
Changes:
- agent/curator_backup.py (new): tar.gz snapshot + safe rollback. The
snapshot excludes .curator_backups/ (would recurse) and .hub/ (managed
by the skills hub). Extract refuses absolute paths and .. components,
and uses tarfile's filter='data' on Python 3.12+. Rollback takes a
pre-rollback safety snapshot FIRST, stages the current tree into
.rollback-staging-<ts>/ so the extract lands in an empty dir, and
cleans the staging dir on success. A failed extract restores the
staged contents.
- agent/curator.py: run_curator_review() calls curator_backup.
snapshot_skills(reason='pre-curator-run') before apply_automatic_
transitions. Best-effort — a failed snapshot logs at debug and the
run continues (a transient disk issue shouldn't silently disable
curator forever).
- hermes_cli/curator.py: new 'hermes curator backup' and 'hermes curator
rollback' subcommands. rollback supports --list, --id <ts>, -y.
- hermes_cli/config.py: curator.backup.{enabled, keep} config block
with sane defaults (enabled=true, keep=5).
- Docs: curator.md gets a 'Backups and rollback' section; cli-commands
.md table gets the new rows.
Tests (new file tests/agent/test_curator_backup.py, 16 cases):
- snapshot creates tarball + manifest with correct counts
- snapshot excludes .curator_backups/ (recursion guard) and .hub/
- snapshot disabled via config returns None without creating anything
- snapshot uniquifies ids within the same second (-01 suffix)
- prune honors keep count, newest-first
- list_backups + _resolve_backup cover newest-default and unknown-id
- rollback restores a deleted skill with content intact
- rollback is itself undoable — safety snapshot shows up in list_backups
- rollback with no snapshots returns an error
- rollback refuses tarballs with absolute paths or .. components
- real curator runs take a 'pre-curator-run' snapshot; dry-runs do not
All curator tests: 210 passing locally.
2026-05-01 09:49:59 -07:00
|
|
|
)
|
|
|
|
|
|
|
|
|
|
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
|
|
|
|
|
|
|
|
|
|
|
feat(curator): background skill maintenance (issue #7816)
Adds the Curator — an auxiliary-model background task that periodically
reviews AGENT-CREATED skills and keeps the collection tidy: tracks usage,
transitions unused skills through active → stale → archived, and spawns
a forked AIAgent to consolidate overlaps and patch drift.
Default: enabled, inactivity-triggered (no cron daemon). Runs on CLI
startup and gateway boot when the last run is older than interval_hours
(default 24) AND the agent has been idle for min_idle_hours (default 2).
Invariants (all load-bearing):
- Never touches bundled or hub-installed skills (.bundled_manifest +
.hub/lock.json double-filter)
- Never auto-deletes — archive only. Archives are recoverable
via `hermes curator restore <skill>`
- Pinned skills bypass all auto-transitions
- Uses the aux client; never touches the main session's prompt cache
New files:
- tools/skill_usage.py — sidecar .usage.json telemetry, atomic writes,
provenance filter
- agent/curator.py — orchestrator: config, idle gating, state-machine
transitions (pure, no LLM), forked-agent review prompt
- hermes_cli/curator.py — `hermes curator {status,run,pause,resume,
pin,unpin,restore}` subcommand
- tests/tools/test_skill_usage.py — 29 tests
- tests/agent/test_curator.py — 25 tests
Modified files (surgical patches):
- tools/skills_tool.py — bump view_count on successful skill_view
- tools/skill_manager_tool.py — bump patch_count on skill_manage
patch/edit/write_file/remove_file; forget record on delete
- hermes_cli/config.py — add curator: section to DEFAULT_CONFIG
- hermes_cli/commands.py — add /curator CommandDef with subcommands
- hermes_cli/main.py — register `hermes curator` subparser via
register_cli() from hermes_cli.curator
- cli.py — /curator slash-command dispatch + startup hook
- gateway/run.py — gateway-boot hook (mirrors CLI)
Validation:
- 54 new tests across skill_usage + curator, all passing in 3s
- 346 tests across all touched files' neighbors green
- 2783 tests across hermes_cli/ + gateway/test_run_progress_topics.py green
- CLI smoke: `hermes curator status/pause/resume` work end-to-end
Companion to PR #16026 (class-first skill review prompt) — together
they form a loop: the review prompt stops near-duplicate skill creation
at the source, and the curator prunes/consolidates what still accumulates.
Refs #7816.
2026-04-26 06:08:39 -07:00
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
# 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)",
|
|
|
|
|
)
|
fix(curator): defer first run and add --dry-run preview (#18373) (#18389)
* fix(curator): defer first run and add --dry-run preview (#18373)
Curator was meant to run 7 days after install, not on the very first
gateway tick. On a fresh install (no .curator_state), should_run_now()
returned True immediately because last_run_at was None — so the gateway
cron ticker fired Curator against a fresh skill library moments after
'hermes update'. Combined with the binary 'agent-created' provenance
model (anything not bundled and not hub-installed), this consolidated
hand-authored user workflow skills without consent.
Changes:
- should_run_now(): first observation seeds last_run_at='now' and returns
False. The next real pass fires one full interval_hours later (7 days
by default), matching the original design intent.
- hermes curator run --dry-run: produces the same review report without
applying automatic transitions OR permitting the LLM to call
skill_manage / terminal mv. A DRY-RUN banner is prepended to the
prompt and the caller skips apply_automatic_transitions. State is
NOT advanced so a preview doesn't defer the next scheduled real pass.
- hermes update: prints a one-liner on fresh installs pointing at
--dry-run, pause, and the docs. Silent on steady state.
- Docs: curator.md and cli-commands.md explain the deferred first-run
behavior and warn that hand-written SKILL.md files share the
'agent-created' bucket, with guidance to pin or preview before the
first pass.
Tests:
- test_first_run_defers replaces the old 'first run always eligible'
assertion — same fixture, inverted expectation.
- test_maybe_run_curator_defers_on_fresh_install covers the gateway tick
path end-to-end.
- Three new dry-run tests cover state-advance suppression, prompt
banner injection, and apply_automatic_transitions skipping.
Fixes #18373.
* feat(curator): pre-run backup + rollback (#18373)
Every real curator pass now snapshots ~/.hermes/skills/ into
~/.hermes/skills/.curator_backups/<utc-iso>/skills.tar.gz before calling
apply_automatic_transitions or the LLM review. If a run consolidates or
archives something the user didn't want touched, 'hermes curator
rollback' restores the tree in one command. Dry-run is skipped — no
mutation means no snapshot needed.
Changes:
- agent/curator_backup.py (new): tar.gz snapshot + safe rollback. The
snapshot excludes .curator_backups/ (would recurse) and .hub/ (managed
by the skills hub). Extract refuses absolute paths and .. components,
and uses tarfile's filter='data' on Python 3.12+. Rollback takes a
pre-rollback safety snapshot FIRST, stages the current tree into
.rollback-staging-<ts>/ so the extract lands in an empty dir, and
cleans the staging dir on success. A failed extract restores the
staged contents.
- agent/curator.py: run_curator_review() calls curator_backup.
snapshot_skills(reason='pre-curator-run') before apply_automatic_
transitions. Best-effort — a failed snapshot logs at debug and the
run continues (a transient disk issue shouldn't silently disable
curator forever).
- hermes_cli/curator.py: new 'hermes curator backup' and 'hermes curator
rollback' subcommands. rollback supports --list, --id <ts>, -y.
- hermes_cli/config.py: curator.backup.{enabled, keep} config block
with sane defaults (enabled=true, keep=5).
- Docs: curator.md gets a 'Backups and rollback' section; cli-commands
.md table gets the new rows.
Tests (new file tests/agent/test_curator_backup.py, 16 cases):
- snapshot creates tarball + manifest with correct counts
- snapshot excludes .curator_backups/ (recursion guard) and .hub/
- snapshot disabled via config returns None without creating anything
- snapshot uniquifies ids within the same second (-01 suffix)
- prune honors keep count, newest-first
- list_backups + _resolve_backup cover newest-default and unknown-id
- rollback restores a deleted skill with content intact
- rollback is itself undoable — safety snapshot shows up in list_backups
- rollback with no snapshots returns an error
- rollback refuses tarballs with absolute paths or .. components
- real curator runs take a 'pre-curator-run' snapshot; dry-runs do not
All curator tests: 210 passing locally.
2026-05-01 09:49:59 -07:00
|
|
|
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)",
|
|
|
|
|
)
|
feat(curator): background skill maintenance (issue #7816)
Adds the Curator — an auxiliary-model background task that periodically
reviews AGENT-CREATED skills and keeps the collection tidy: tracks usage,
transitions unused skills through active → stale → archived, and spawns
a forked AIAgent to consolidate overlaps and patch drift.
Default: enabled, inactivity-triggered (no cron daemon). Runs on CLI
startup and gateway boot when the last run is older than interval_hours
(default 24) AND the agent has been idle for min_idle_hours (default 2).
Invariants (all load-bearing):
- Never touches bundled or hub-installed skills (.bundled_manifest +
.hub/lock.json double-filter)
- Never auto-deletes — archive only. Archives are recoverable
via `hermes curator restore <skill>`
- Pinned skills bypass all auto-transitions
- Uses the aux client; never touches the main session's prompt cache
New files:
- tools/skill_usage.py — sidecar .usage.json telemetry, atomic writes,
provenance filter
- agent/curator.py — orchestrator: config, idle gating, state-machine
transitions (pure, no LLM), forked-agent review prompt
- hermes_cli/curator.py — `hermes curator {status,run,pause,resume,
pin,unpin,restore}` subcommand
- tests/tools/test_skill_usage.py — 29 tests
- tests/agent/test_curator.py — 25 tests
Modified files (surgical patches):
- tools/skills_tool.py — bump view_count on successful skill_view
- tools/skill_manager_tool.py — bump patch_count on skill_manage
patch/edit/write_file/remove_file; forget record on delete
- hermes_cli/config.py — add curator: section to DEFAULT_CONFIG
- hermes_cli/commands.py — add /curator CommandDef with subcommands
- hermes_cli/main.py — register `hermes curator` subparser via
register_cli() from hermes_cli.curator
- cli.py — /curator slash-command dispatch + startup hook
- gateway/run.py — gateway-boot hook (mirrors CLI)
Validation:
- 54 new tests across skill_usage + curator, all passing in 3s
- 346 tests across all touched files' neighbors green
- 2783 tests across hermes_cli/ + gateway/test_run_progress_topics.py green
- CLI smoke: `hermes curator status/pause/resume` work end-to-end
Companion to PR #16026 (class-first skill review prompt) — together
they form a loop: the review prompt stops near-duplicate skill creation
at the source, and the curator prunes/consolidates what still accumulates.
Refs #7816.
2026-04-26 06:08:39 -07:00
|
|
|
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)
|
|
|
|
|
|
fix(curator): defer first run and add --dry-run preview (#18373) (#18389)
* fix(curator): defer first run and add --dry-run preview (#18373)
Curator was meant to run 7 days after install, not on the very first
gateway tick. On a fresh install (no .curator_state), should_run_now()
returned True immediately because last_run_at was None — so the gateway
cron ticker fired Curator against a fresh skill library moments after
'hermes update'. Combined with the binary 'agent-created' provenance
model (anything not bundled and not hub-installed), this consolidated
hand-authored user workflow skills without consent.
Changes:
- should_run_now(): first observation seeds last_run_at='now' and returns
False. The next real pass fires one full interval_hours later (7 days
by default), matching the original design intent.
- hermes curator run --dry-run: produces the same review report without
applying automatic transitions OR permitting the LLM to call
skill_manage / terminal mv. A DRY-RUN banner is prepended to the
prompt and the caller skips apply_automatic_transitions. State is
NOT advanced so a preview doesn't defer the next scheduled real pass.
- hermes update: prints a one-liner on fresh installs pointing at
--dry-run, pause, and the docs. Silent on steady state.
- Docs: curator.md and cli-commands.md explain the deferred first-run
behavior and warn that hand-written SKILL.md files share the
'agent-created' bucket, with guidance to pin or preview before the
first pass.
Tests:
- test_first_run_defers replaces the old 'first run always eligible'
assertion — same fixture, inverted expectation.
- test_maybe_run_curator_defers_on_fresh_install covers the gateway tick
path end-to-end.
- Three new dry-run tests cover state-advance suppression, prompt
banner injection, and apply_automatic_transitions skipping.
Fixes #18373.
* feat(curator): pre-run backup + rollback (#18373)
Every real curator pass now snapshots ~/.hermes/skills/ into
~/.hermes/skills/.curator_backups/<utc-iso>/skills.tar.gz before calling
apply_automatic_transitions or the LLM review. If a run consolidates or
archives something the user didn't want touched, 'hermes curator
rollback' restores the tree in one command. Dry-run is skipped — no
mutation means no snapshot needed.
Changes:
- agent/curator_backup.py (new): tar.gz snapshot + safe rollback. The
snapshot excludes .curator_backups/ (would recurse) and .hub/ (managed
by the skills hub). Extract refuses absolute paths and .. components,
and uses tarfile's filter='data' on Python 3.12+. Rollback takes a
pre-rollback safety snapshot FIRST, stages the current tree into
.rollback-staging-<ts>/ so the extract lands in an empty dir, and
cleans the staging dir on success. A failed extract restores the
staged contents.
- agent/curator.py: run_curator_review() calls curator_backup.
snapshot_skills(reason='pre-curator-run') before apply_automatic_
transitions. Best-effort — a failed snapshot logs at debug and the
run continues (a transient disk issue shouldn't silently disable
curator forever).
- hermes_cli/curator.py: new 'hermes curator backup' and 'hermes curator
rollback' subcommands. rollback supports --list, --id <ts>, -y.
- hermes_cli/config.py: curator.backup.{enabled, keep} config block
with sane defaults (enabled=true, keep=5).
- Docs: curator.md gets a 'Backups and rollback' section; cli-commands
.md table gets the new rows.
Tests (new file tests/agent/test_curator_backup.py, 16 cases):
- snapshot creates tarball + manifest with correct counts
- snapshot excludes .curator_backups/ (recursion guard) and .hub/
- snapshot disabled via config returns None without creating anything
- snapshot uniquifies ids within the same second (-01 suffix)
- prune honors keep count, newest-first
- list_backups + _resolve_backup cover newest-default and unknown-id
- rollback restores a deleted skill with content intact
- rollback is itself undoable — safety snapshot shows up in list_backups
- rollback with no snapshots returns an error
- rollback refuses tarballs with absolute paths or .. components
- real curator runs take a 'pre-curator-run' snapshot; dry-runs do not
All curator tests: 210 passing locally.
2026-05-01 09:49:59 -07:00
|
|
|
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)
|
|
|
|
|
|
feat(curator): background skill maintenance (issue #7816)
Adds the Curator — an auxiliary-model background task that periodically
reviews AGENT-CREATED skills and keeps the collection tidy: tracks usage,
transitions unused skills through active → stale → archived, and spawns
a forked AIAgent to consolidate overlaps and patch drift.
Default: enabled, inactivity-triggered (no cron daemon). Runs on CLI
startup and gateway boot when the last run is older than interval_hours
(default 24) AND the agent has been idle for min_idle_hours (default 2).
Invariants (all load-bearing):
- Never touches bundled or hub-installed skills (.bundled_manifest +
.hub/lock.json double-filter)
- Never auto-deletes — archive only. Archives are recoverable
via `hermes curator restore <skill>`
- Pinned skills bypass all auto-transitions
- Uses the aux client; never touches the main session's prompt cache
New files:
- tools/skill_usage.py — sidecar .usage.json telemetry, atomic writes,
provenance filter
- agent/curator.py — orchestrator: config, idle gating, state-machine
transitions (pure, no LLM), forked-agent review prompt
- hermes_cli/curator.py — `hermes curator {status,run,pause,resume,
pin,unpin,restore}` subcommand
- tests/tools/test_skill_usage.py — 29 tests
- tests/agent/test_curator.py — 25 tests
Modified files (surgical patches):
- tools/skills_tool.py — bump view_count on successful skill_view
- tools/skill_manager_tool.py — bump patch_count on skill_manage
patch/edit/write_file/remove_file; forget record on delete
- hermes_cli/config.py — add curator: section to DEFAULT_CONFIG
- hermes_cli/commands.py — add /curator CommandDef with subcommands
- hermes_cli/main.py — register `hermes curator` subparser via
register_cli() from hermes_cli.curator
- cli.py — /curator slash-command dispatch + startup hook
- gateway/run.py — gateway-boot hook (mirrors CLI)
Validation:
- 54 new tests across skill_usage + curator, all passing in 3s
- 346 tests across all touched files' neighbors green
- 2783 tests across hermes_cli/ + gateway/test_run_progress_topics.py green
- CLI smoke: `hermes curator status/pause/resume` work end-to-end
Companion to PR #16026 (class-first skill review prompt) — together
they form a loop: the review prompt stops near-duplicate skill creation
at the source, and the curator prunes/consolidates what still accumulates.
Refs #7816.
2026-04-26 06:08:39 -07:00
|
|
|
|
|
|
|
|
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())
|