mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-31 06:51:29 +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
117 lines
3.9 KiB
Python
117 lines
3.9 KiB
Python
"""Tests for the Phase 4 s6 dispatch helper in hermes_cli.gateway.
|
|
|
|
`_dispatch_via_service_manager_if_s6` decides whether a
|
|
`hermes gateway start/stop/restart` invocation should be routed to
|
|
the in-container S6ServiceManager instead of falling through to the
|
|
host systemd/launchd/windows code path.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
from typing import Any
|
|
|
|
import pytest
|
|
|
|
|
|
class _CallRecorder:
|
|
"""Minimal stand-in for S6ServiceManager."""
|
|
kind = "s6"
|
|
|
|
def __init__(self) -> None:
|
|
self.calls: list[tuple[str, str]] = []
|
|
|
|
def start(self, name: str) -> None:
|
|
self.calls.append(("start", name))
|
|
|
|
def stop(self, name: str) -> None:
|
|
self.calls.append(("stop", name))
|
|
|
|
def restart(self, name: str) -> None:
|
|
self.calls.append(("restart", name))
|
|
|
|
|
|
def test_dispatch_returns_false_on_host(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
"""When the environment isn't s6 (host run), the helper must
|
|
return False and not invoke a manager — callers continue with
|
|
their existing systemd/launchd/windows path."""
|
|
from hermes_cli import gateway as gw
|
|
monkeypatch.setattr(
|
|
"hermes_cli.service_manager.detect_service_manager", lambda: "systemd",
|
|
)
|
|
# Should not even attempt to construct a manager.
|
|
monkeypatch.setattr(
|
|
"hermes_cli.service_manager.get_service_manager",
|
|
lambda: pytest.fail("manager should not be constructed on host"),
|
|
)
|
|
assert gw._dispatch_via_service_manager_if_s6("start", profile="x") is False
|
|
|
|
|
|
def test_dispatch_returns_true_and_calls_start_on_s6(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
from hermes_cli import gateway as gw
|
|
rec = _CallRecorder()
|
|
monkeypatch.setattr(
|
|
"hermes_cli.service_manager.detect_service_manager", lambda: "s6",
|
|
)
|
|
monkeypatch.setattr(
|
|
"hermes_cli.service_manager.get_service_manager", lambda: rec,
|
|
)
|
|
assert gw._dispatch_via_service_manager_if_s6("start", profile="coder") is True
|
|
assert rec.calls == [("start", "gateway-coder")]
|
|
|
|
|
|
@pytest.mark.parametrize("action,expected", [
|
|
("start", "start"),
|
|
("stop", "stop"),
|
|
("restart", "restart"),
|
|
])
|
|
def test_dispatch_translates_action_to_manager_method(
|
|
monkeypatch: pytest.MonkeyPatch, action: str, expected: str,
|
|
) -> None:
|
|
from hermes_cli import gateway as gw
|
|
rec = _CallRecorder()
|
|
monkeypatch.setattr(
|
|
"hermes_cli.service_manager.detect_service_manager", lambda: "s6",
|
|
)
|
|
monkeypatch.setattr(
|
|
"hermes_cli.service_manager.get_service_manager", lambda: rec,
|
|
)
|
|
assert gw._dispatch_via_service_manager_if_s6(action, profile="x") is True
|
|
assert rec.calls == [(expected, "gateway-x")]
|
|
|
|
|
|
def test_dispatch_unknown_action_returns_false(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
"""An unrecognized action (e.g. 'install') must not silently
|
|
succeed — return False so the host code path handles it."""
|
|
from hermes_cli import gateway as gw
|
|
rec = _CallRecorder()
|
|
monkeypatch.setattr(
|
|
"hermes_cli.service_manager.detect_service_manager", lambda: "s6",
|
|
)
|
|
monkeypatch.setattr(
|
|
"hermes_cli.service_manager.get_service_manager", lambda: rec,
|
|
)
|
|
assert gw._dispatch_via_service_manager_if_s6("install", profile="x") is False
|
|
assert rec.calls == []
|
|
|
|
|
|
def test_dispatch_defaults_profile_to_default(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
"""When profile is None, the helper resolves it via _profile_arg().
|
|
With no profile context set anywhere, that resolves to "default"."""
|
|
from hermes_cli import gateway as gw
|
|
rec = _CallRecorder()
|
|
monkeypatch.setattr(
|
|
"hermes_cli.service_manager.detect_service_manager", lambda: "s6",
|
|
)
|
|
monkeypatch.setattr(
|
|
"hermes_cli.service_manager.get_service_manager", lambda: rec,
|
|
)
|
|
monkeypatch.setattr(
|
|
"hermes_cli.gateway._profile_suffix", lambda: "",
|
|
)
|
|
assert gw._dispatch_via_service_manager_if_s6("start") is True
|
|
assert rec.calls == [("start", "gateway-default")]
|