mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-06-01 07:01:41 +00:00
Phase 4 of the s6-overlay supervision plan. Activates the Phase 3
S6ServiceManager by hooking it into the profile lifecycle and the
`hermes gateway start/stop/restart` dispatcher, and adds a cont-
init.d-time reconciliation pass that survives `docker restart`.
Task 4.0 — container-boot reconciliation:
/run/service/ is tmpfs, so every `docker restart` wipes every
per-profile gateway slot. /etc/cont-init.d/02-reconcile-profiles
invokes hermes_cli.container_boot.reconcile_profile_gateways() on
every boot, which walks $HERMES_HOME/profiles/<name>/, reads each
gateway_state.json, recreates the s6 service slot, and auto-starts
only those whose last state was 'running'. Other states
(stopped, starting, startup_failed, missing) register the slot
in the down state — avoiding crash-loops across restarts for a
gateway that was broken last boot. Per-profile outcome is recorded
to $HERMES_HOME/logs/container-boot.log.
Implementation: hermes_cli/container_boot.py + 12 unit tests.
Profile-marker is SOUL.md, not config.yaml, because `hermes profile
create` only seeds SOUL.md by default (config.yaml comes from
`hermes setup`).
Task 4.1 / 4.2 — profile create/delete hooks:
hermes_cli/profiles.py::create_profile now calls
_maybe_register_gateway_service(<canon>) at the end, which routes
through ServiceManager.register_profile_gateway when running on s6
and no-ops on host backends. delete_profile mirrors with
_maybe_unregister_gateway_service. _allocate_gateway_port produces
a deterministic SHA-256-derived port in [9200, 9800).
Task 4.3 — gateway dispatch + remove rejection arms:
_dispatch_via_service_manager_if_s6(action) intercepts
start/stop/restart at the top of each subcommand and routes them
through S6ServiceManager.{start,stop,restart}. The pre-Phase-4
`elif is_container():` rejection arms are kept as fallback for
pre-s6 containers / unsupported runtimes, but only ever fire when
detect_service_manager() != 's6'. install/uninstall under s6
print informational guidance pointing users at profile create/delete.
Removed the two xfail(strict=True) markers from
tests/docker/test_profile_gateway.py — both tests now pass strictly.
Task 4.4 — status reporting:
get_gateway_runtime_snapshot() reports
Manager: 's6 (container supervisor)' inside an s6 container instead
of 'docker (foreground)'.
Plan-vs-reality drift fixed in this commit:
- Plan's S6ServiceManager._render_run_script used
`gateway start --foreground --port {port}` — invented args; the
real CLI is `gateway run`. Switched accordingly. port arg
retained for API parity but now documented as 'currently ignored'.
- Plan's reconciler keyed on config.yaml; switched to SOUL.md
(config.yaml is created by hermes setup, not by hermes profile
create, so the original gate caught nothing).
- The plan's _dispatch helper used _profile_arg() which returns
'--profile <name>' (i.e. with the flag prefix). Switched to
_profile_suffix() which returns the bare name.
- Architecture B's docker exec doesn't get /command on PATH or
the venv on PATH; Dockerfile's runtime PATH now includes
/opt/hermes/.venv/bin so 'docker exec <c> hermes ...' works
without sourcing the venv.
- stage2-hook now chowns $HERMES_HOME/profiles to hermes on every
boot, not just on the UID-remap path. Without this, files created
by docker-exec-as-root accumulate and the next reconciler run
fails with PermissionError reading SOUL.md.
Test harness:
19 passed, 0 xfailed (the two pre-Phase-4 xfail targets flip to
passing). 78 unit tests across service_manager + container_boot +
profiles_s6_hooks + gateway_s6_dispatch. Hadolint + shellcheck
pass cleanly.
Refs: docs/plans/2026-05-07-s6-overlay-dynamic-subagent-gateways.md
190 lines
6.7 KiB
Python
190 lines
6.7 KiB
Python
"""Tests for the Phase 4 s6 hooks in hermes_cli.profiles.
|
|
|
|
Specifically: _allocate_gateway_port, _maybe_register_gateway_service,
|
|
_maybe_unregister_gateway_service. The integration with
|
|
create_profile and delete_profile is covered indirectly by the
|
|
existing TestCreateProfile and TestDeleteProfile classes in
|
|
tests/hermes_cli/test_profiles.py; here we only exercise the new
|
|
helper surface that doesn't touch the filesystem.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
from typing import Any
|
|
|
|
import pytest
|
|
|
|
from hermes_cli.profiles import (
|
|
_allocate_gateway_port,
|
|
_maybe_register_gateway_service,
|
|
_maybe_unregister_gateway_service,
|
|
)
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# _allocate_gateway_port
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def test_allocate_gateway_port_is_deterministic() -> None:
|
|
"""Same profile name → same port across calls. This matters because
|
|
a profile's gateway must come back up on the same port across
|
|
container restarts."""
|
|
a = _allocate_gateway_port("coder")
|
|
b = _allocate_gateway_port("coder")
|
|
assert a == b
|
|
|
|
|
|
def test_allocate_gateway_port_in_advertised_range() -> None:
|
|
"""[9200, 9800) — the window the helper's docstring promises."""
|
|
for name in ("a", "b", "coder", "assistant", "very-long-profile-name-here"):
|
|
port = _allocate_gateway_port(name)
|
|
assert 9200 <= port < 9800, f"{name} got {port}"
|
|
|
|
|
|
def test_allocate_gateway_port_distributes_across_range() -> None:
|
|
"""Sanity check: ports for ~100 random-ish names should land in
|
|
enough distinct buckets that the distribution is plausibly uniform.
|
|
Catches accidental hash truncation that would collapse the range."""
|
|
ports = {_allocate_gateway_port(f"profile-{i}") for i in range(100)}
|
|
# 100 inputs mapped into 600 slots — expect at least ~60 distinct.
|
|
assert len(ports) >= 60, f"Only {len(ports)} distinct ports across 100 names"
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# _maybe_register_gateway_service / _maybe_unregister_gateway_service
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
class _HostManager:
|
|
"""Mimics a host backend that doesn't support runtime registration."""
|
|
kind = "systemd"
|
|
|
|
def supports_runtime_registration(self) -> bool:
|
|
return False
|
|
|
|
def register_profile_gateway(self, *args: Any, **kwargs: Any) -> None:
|
|
raise AssertionError("host backend register_profile_gateway should not be called")
|
|
|
|
def unregister_profile_gateway(self, *args: Any, **kwargs: Any) -> None:
|
|
raise AssertionError("host backend unregister_profile_gateway should not be called")
|
|
|
|
|
|
class _S6Manager:
|
|
"""Mimics S6ServiceManager just enough for the hooks."""
|
|
kind = "s6"
|
|
|
|
def __init__(self) -> None:
|
|
self.registered: list[tuple[str, int]] = []
|
|
self.unregistered: list[str] = []
|
|
self.raise_on_register: Exception | None = None
|
|
self.raise_on_unregister: Exception | None = None
|
|
|
|
def supports_runtime_registration(self) -> bool:
|
|
return True
|
|
|
|
def register_profile_gateway(
|
|
self, profile: str, *, port: int,
|
|
extra_env: dict[str, str] | None = None,
|
|
) -> None:
|
|
if self.raise_on_register is not None:
|
|
raise self.raise_on_register
|
|
self.registered.append((profile, port))
|
|
|
|
def unregister_profile_gateway(self, profile: str) -> None:
|
|
if self.raise_on_unregister is not None:
|
|
raise self.raise_on_unregister
|
|
self.unregistered.append(profile)
|
|
|
|
|
|
def test_register_noop_on_host(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
monkeypatch.setattr(
|
|
"hermes_cli.service_manager.get_service_manager",
|
|
lambda: _HostManager(),
|
|
)
|
|
# Should NOT raise the AssertionError from _HostManager.register
|
|
_maybe_register_gateway_service("hostprof")
|
|
|
|
|
|
def test_register_calls_through_on_s6(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
mgr = _S6Manager()
|
|
monkeypatch.setattr(
|
|
"hermes_cli.service_manager.get_service_manager", lambda: mgr,
|
|
)
|
|
_maybe_register_gateway_service("coder")
|
|
assert len(mgr.registered) == 1
|
|
profile, port = mgr.registered[0]
|
|
assert profile == "coder"
|
|
assert 9200 <= port < 9800
|
|
|
|
|
|
def test_register_swallows_duplicate_value_error(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
"""A pre-existing s6 registration (from container-boot reconcile)
|
|
is a benign condition — register must not propagate ValueError."""
|
|
mgr = _S6Manager()
|
|
mgr.raise_on_register = ValueError("already registered")
|
|
monkeypatch.setattr(
|
|
"hermes_cli.service_manager.get_service_manager", lambda: mgr,
|
|
)
|
|
# Should NOT raise
|
|
_maybe_register_gateway_service("coder")
|
|
|
|
|
|
def test_register_swallows_arbitrary_error(
|
|
monkeypatch: pytest.MonkeyPatch, capsys: pytest.CaptureFixture[str],
|
|
) -> None:
|
|
"""Even an unexpected exception from the manager must not bring
|
|
down `hermes profile create` — print and continue."""
|
|
mgr = _S6Manager()
|
|
mgr.raise_on_register = RuntimeError("svscanctl exploded")
|
|
monkeypatch.setattr(
|
|
"hermes_cli.service_manager.get_service_manager", lambda: mgr,
|
|
)
|
|
_maybe_register_gateway_service("coder")
|
|
captured = capsys.readouterr()
|
|
assert "Could not register" in captured.out
|
|
|
|
|
|
def test_register_swallows_no_backend_runtime_error(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
"""When `get_service_manager()` raises RuntimeError (no backend
|
|
detected), the hook must silently no-op."""
|
|
def _no_backend() -> None:
|
|
raise RuntimeError("no supported service manager detected")
|
|
monkeypatch.setattr(
|
|
"hermes_cli.service_manager.get_service_manager", _no_backend,
|
|
)
|
|
# Should NOT raise
|
|
_maybe_register_gateway_service("anywhere")
|
|
|
|
|
|
def test_unregister_noop_on_host(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
monkeypatch.setattr(
|
|
"hermes_cli.service_manager.get_service_manager",
|
|
lambda: _HostManager(),
|
|
)
|
|
_maybe_unregister_gateway_service("hostprof")
|
|
|
|
|
|
def test_unregister_calls_through_on_s6(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
mgr = _S6Manager()
|
|
monkeypatch.setattr(
|
|
"hermes_cli.service_manager.get_service_manager", lambda: mgr,
|
|
)
|
|
_maybe_unregister_gateway_service("coder")
|
|
assert mgr.unregistered == ["coder"]
|
|
|
|
|
|
def test_unregister_swallows_errors(
|
|
monkeypatch: pytest.MonkeyPatch, capsys: pytest.CaptureFixture[str],
|
|
) -> None:
|
|
mgr = _S6Manager()
|
|
mgr.raise_on_unregister = RuntimeError("svc gone weird")
|
|
monkeypatch.setattr(
|
|
"hermes_cli.service_manager.get_service_manager", lambda: mgr,
|
|
)
|
|
_maybe_unregister_gateway_service("coder")
|
|
captured = capsys.readouterr()
|
|
assert "Could not unregister" in captured.out
|