chore: uptick

This commit is contained in:
Brooklyn Nicholson
2026-05-02 03:19:39 -05:00
parent 420f68e4e2
commit db884f4646
240 changed files with 25206 additions and 3155 deletions
+149 -11
View File
@@ -800,6 +800,8 @@ def _print_tui_exit_summary(session_id: Optional[str], active_session_file: Opti
title = db.get_session_title(target)
message_count = int(session.get("message_count") or 0)
if message_count == 0:
return # No real conversation — don't show resume info
input_tokens = int(session.get("input_tokens") or 0)
output_tokens = int(session.get("output_tokens") or 0)
cache_read_tokens = int(session.get("cache_read_tokens") or 0)
@@ -5431,6 +5433,45 @@ def _find_stale_dashboard_pids() -> list[int]:
return dashboard_pids
def _print_curator_first_run_notice() -> None:
"""Print a short heads-up about the skill curator after `hermes update`.
Only fires when the curator is enabled AND has no recorded run yet, which
is exactly the window where the gateway ticker used to fire Curator
against a fresh skill library immediately after an update. We defer the
first real pass by one ``interval_hours``; this notice tells the user how
to preview or disable before then. Silent on steady state.
"""
try:
from agent import curator
except Exception:
return
try:
if not curator.is_enabled():
return
state = curator.load_state()
except Exception:
return
if state.get("last_run_at"):
# Curator has run before (real or already seeded) — no notice needed.
return
try:
hours = curator.get_interval_hours()
except Exception:
hours = 24 * 7
days = max(1, hours // 24)
print()
print(" Skill curator")
print(
f" Background skill maintenance is enabled. First pass is deferred "
f"~{days}d after installation; only agent-created skills are in "
f"scope and nothing is ever auto-deleted (archive is recoverable)."
)
print(" Preview now: hermes curator run --dry-run")
print(" Pause it: hermes curator pause")
print(" Docs: https://hermes-agent.nousresearch.com/docs/user-guide/features/curator")
def _kill_stale_dashboard_processes(
reason: str = "the running backend no longer matches the updated frontend",
) -> None:
@@ -5668,6 +5709,10 @@ def _update_via_zip(args):
print()
print("✓ Update complete!")
try:
_print_curator_first_run_notice()
except Exception as e:
logger.debug("Curator first-run notice failed: %s", e)
_kill_stale_dashboard_processes()
@@ -6673,6 +6718,7 @@ def _cmd_update_impl(args, gateway_mode: bool):
if gateway_mode
else None
)
assume_yes = bool(getattr(args, "yes", False))
print("⚕ Updating Hermes Agent...")
print()
@@ -6792,8 +6838,10 @@ def _cmd_update_impl(args, gateway_mode: bool):
else:
auto_stash_ref = _stash_local_changes_if_needed(git_cmd, PROJECT_ROOT)
prompt_for_restore = auto_stash_ref is not None and (
gateway_mode or (sys.stdin.isatty() and sys.stdout.isatty())
prompt_for_restore = (
auto_stash_ref is not None
and not assume_yes
and (gateway_mode or (sys.stdin.isatty() and sys.stdout.isatty()))
)
# Check if there are updates
@@ -7054,7 +7102,10 @@ def _cmd_update_impl(args, gateway_mode: bool):
print(f" {len(missing_config)} new config option(s) available")
print()
if gateway_mode:
if assume_yes:
print(" --yes: auto-applying config migration (skipping API-key prompts).")
response = "y"
elif gateway_mode:
response = (
_gateway_prompt(
"Would you like to configure new options now? [Y/n]", "n"
@@ -7080,14 +7131,17 @@ def _cmd_update_impl(args, gateway_mode: bool):
if response in ("", "y", "yes"):
print()
# In gateway mode, run auto-migrations only (no input() prompts
# for API keys which would hang the detached process).
results = migrate_config(interactive=not gateway_mode, quiet=False)
# In gateway mode OR under --yes, run auto-migrations only (no
# input() prompts for API keys which would hang the detached
# process / defeat the point of --yes).
results = migrate_config(
interactive=not (gateway_mode or assume_yes), quiet=False
)
if results["env_added"] or results["config_added"]:
print()
print("✓ Configuration updated!")
if gateway_mode and missing_env:
if (gateway_mode or assume_yes) and missing_env:
print(" API keys require manual entry: hermes config migrate")
else:
print()
@@ -7098,6 +7152,15 @@ def _cmd_update_impl(args, gateway_mode: bool):
print()
print("✓ Update complete!")
# Curator first-run heads-up. Only prints when curator is enabled AND
# has never run — i.e. the window where the ticker would otherwise
# have fired against a fresh skill library. Kept silent on steady
# state so we don't nag.
try:
_print_curator_first_run_notice()
except Exception as e:
logger.debug("Curator first-run notice failed: %s", e)
# Repair RHEL-family root installs where /usr/local/bin isn't on PATH
# for non-login interactive shells. No-op on every other platform.
try:
@@ -7137,6 +7200,8 @@ def _cmd_update_impl(args, gateway_mode: bool):
supports_systemd_services,
_ensure_user_systemd_env,
find_gateway_pids,
find_profile_gateway_processes,
launch_detached_profile_gateway_restart,
_get_service_pids,
_graceful_restart_via_sigusr1,
)
@@ -7240,6 +7305,7 @@ def _cmd_update_impl(args, gateway_mode: bool):
restarted_services = []
killed_pids = set()
relaunched_profiles = []
# --- Systemd services (Linux) ---
# Discover all hermes-gateway* units (default + profiles)
@@ -7429,7 +7495,33 @@ def _cmd_update_impl(args, gateway_mode: bool):
manual_pids = find_gateway_pids(
exclude_pids=service_pids, all_profiles=True
)
profile_processes = {
proc.pid: proc
for proc in find_profile_gateway_processes(exclude_pids=service_pids)
if proc.pid in manual_pids
}
for pid, proc in profile_processes.items():
if not launch_detached_profile_gateway_restart(proc.profile, pid):
continue
# Prefer a graceful SIGUSR1 drain so in-flight agent runs
# finish before the watcher respawns the gateway. If the
# gateway doesn't support SIGUSR1 or doesn't exit within
# the drain budget, fall back to SIGTERM — the watcher
# still sees the exit and relaunches either way.
drained = _graceful_restart_via_sigusr1(
pid, drain_timeout=_drain_budget,
)
if not drained:
try:
os.kill(pid, _signal.SIGTERM)
except (ProcessLookupError, PermissionError):
pass
killed_pids.add(pid)
relaunched_profiles.append(proc.profile)
for pid in manual_pids:
if pid in profile_processes:
continue
try:
os.kill(pid, _signal.SIGTERM)
killed_pids.add(pid)
@@ -7440,11 +7532,14 @@ def _cmd_update_impl(args, gateway_mode: bool):
print()
for svc in restarted_services:
print(f" ✓ Restarted {svc}")
if killed_pids:
print(f" → Stopped {len(killed_pids)} manual gateway process(es)")
if relaunched_profiles:
names = ", ".join(relaunched_profiles)
print(f" ✓ Restarting manual gateway profile(s): {names}")
unmapped_count = len(killed_pids) - len(relaunched_profiles)
if unmapped_count:
print(f" → Stopped {unmapped_count} manual gateway process(es)")
print(" Restart manually: hermes gateway run")
# Also restart for each profile if needed
if len(killed_pids) > 1:
if unmapped_count > 1:
print(
" (or: hermes -p <profile> gateway run for each profile)"
)
@@ -7453,6 +7548,42 @@ def _cmd_update_impl(args, gateway_mode: bool):
# No gateways were running — nothing to do
pass
# --- Post-restart survivor sweep -----------------------------
# Issue #17648: some gateways ignore SIGTERM (stuck drain,
# blocked I/O, PID dead but zombie). The detached profile
# watchers wait 120s for the old PID to exit — if it never
# does, no respawn happens and the user keeps hitting
# ImportError against a stale sys.modules. Give the
# graceful paths a brief window to complete, then SIGKILL
# any remaining pre-update PIDs so the watcher / service
# manager can relaunch with fresh code.
try:
_time.sleep(3.0)
_service_pids_after = _get_service_pids()
_surviving = find_gateway_pids(
exclude_pids=_service_pids_after, all_profiles=True,
)
# Scope to PIDs we already tried to kill during this
# update (killed_pids). Anything new is a gateway that
# started AFTER our restart attempt — respecting user
# intent, we don't kill those.
_stuck = [pid for pid in _surviving if pid in killed_pids]
if _stuck:
print()
print(
f"{len(_stuck)} gateway process(es) ignored SIGTERM — force-killing"
)
for pid in _stuck:
try:
os.kill(pid, _signal.SIGKILL)
except (ProcessLookupError, PermissionError):
pass
# Give the OS a beat to reap the processes so the
# watchers see them exit and respawn.
_time.sleep(1.5)
except Exception as _sweep_exc:
logger.debug("Post-restart survivor sweep failed: %s", _sweep_exc)
except Exception as e:
logger.debug("Gateway restart during update failed: %s", e)
@@ -9861,6 +9992,13 @@ Examples:
default=False,
help="Force a pre-update backup for this run (off by default; overrides updates.pre_update_backup)",
)
update_parser.add_argument(
"--yes",
"-y",
action="store_true",
default=False,
help="Assume yes for interactive prompts (config migration, stash restore). API-key entry is skipped; run 'hermes config migrate' separately for those.",
)
update_parser.set_defaults(func=cmd_update)
# =========================================================================