mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-05-30 06:41:51 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 15
hermes-agent/tests/hermes_cli/test_gateway_s6_dispatch.py
Ben Barclay 0927fb5584 feat(docker): auto-redirect gateway run to supervised mode inside s6 image 
Pre-s6, `docker run nousresearch/hermes-agent gateway run` was the
standard invocation: gateway ran as the container's main process,
tini reaped zombies, container exit code matched gateway exit code,
no supervision. With s6-overlay as PID 1, the same invocation now
auto-upgrades to supervised semantics — auto-restart on crash,
dashboard supervised alongside (when HERMES_DASHBOARD=1 is set),
multiple profile gateways under the same /init.

Users get the new behavior with zero changes to their docker run
command. A loud one-line breadcrumb on stderr explains the upgrade
and points at the opt-out for users who genuinely want pre-s6
foreground semantics.

How it works:

  1. `_gateway_command_inner` (the `gateway run` handler) checks if
     we're inside a container with s6 as PID 1.
  2. If yes, dispatches `start` to the s6 service manager (registers
     and starts gateway-default), then `exec sleep infinity` to keep
     the CMD process alive without binding container lifetime to
     gateway PID lifetime. The supervised gateway can flap freely;
     `docker stop` still tears everything down via /init stage 3.
  3. If no, falls through to the existing foreground code path
     unchanged. Host runs of `hermes gateway run` are unaffected.

Three gates make the redirect inert outside the intended scope:

  * `detect_service_manager() != "s6"` — host/non-s6-container runs.
  * `HERMES_S6_SUPERVISED_CHILD=1` env var (recursion guard) —
    exported by `S6ServiceManager._render_run_script` for the
    s6-supervised invocation itself. Without this guard, the
    supervised `gateway run --replace` would re-enter the redirect
    and recurse (run → start → run → start → ...) infinitely.
  * `--no-supervise` CLI flag OR `HERMES_GATEWAY_NO_SUPERVISE=1` env
    var — explicit user opt-out for CI smoke tests, debugging the
    foreground startup path, or any case wanting "CMD exit =
    container exit" semantics. Strict truthiness (1/true/yes,
    case-insensitive); typos like `=0` do NOT silently opt out.

Tests:

  * Unit tests in tests/hermes_cli/test_gateway_s6_dispatch.py
    cover all five paths (host no-op, supervised fire, sentinel
    recursion guard, CLI flag, env var truthy + falsy). The two
    load-bearing gates (sentinel + opt-out) were mutation-tested
    by removing each gate in isolation and confirming the dedicated
    test fails with the expected error.
  * Docker harness tests in tests/docker/test_gateway_run_supervised.py
    cover the round trips end-to-end against a built image: redirect
    fires (sleep-infinity heartbeat + supervised gateway-default
    slot + breadcrumb), --no-supervise opt-out (foreground gateway,
    no want-up on the slot), HERMES_GATEWAY_NO_SUPERVISE env var
    works identically, recursion is impossible (≤1 supervised
    python gateway-run + exactly 1 sleep-infinity parented to the
    CMD wrapper), and HERMES_DASHBOARD=1 produces both supervised
    gateway and supervised dashboard.

Docs:

  * Added a `:::tip Gateway runs supervised` admonition near the
    main docker.md example explaining the upgrade and pointing at
    the opt-out. Pre-s6 (tini-based) images still run gateway run
    as the foreground main process, so the note is scoped to the
    s6 image only.

Trade-off documented in the helper docstring: container exit code
under the redirect is sleep's exit code (always 0 on SIGTERM), not
the gateway's. That was an explicit design call — the supervised
gateway is allowed to flap without taking the container with it,
which is what "supervision" means. CI users who want exit-code
forwarding can pass --no-supervise.
2026-05-28 12:42:13 +10:00

526 lines
19 KiB
Python
Raw Blame History

"""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")]
# ---------------------------------------------------------------------------
# _dispatch_all_via_service_manager_if_s6 — --all under s6
# ---------------------------------------------------------------------------
class _ListingRecorder(_CallRecorder):
"""_CallRecorder that also exposes a profile list."""
def __init__(self, profiles: list[str]) -> None:
super().__init__()
self._profiles = profiles
def list_profile_gateways(self) -> list[str]:
return list(self._profiles)
def test_dispatch_all_returns_false_on_host(
monkeypatch: pytest.MonkeyPatch,
) -> None:
from hermes_cli import gateway as gw
monkeypatch.setattr(
"hermes_cli.service_manager.detect_service_manager", lambda: "systemd",
)
monkeypatch.setattr(
"hermes_cli.service_manager.get_service_manager",
lambda: pytest.fail("manager should not be constructed on host"),
)
assert gw._dispatch_all_via_service_manager_if_s6("stop") is False
def test_dispatch_all_iterates_every_profile_on_stop(
monkeypatch: pytest.MonkeyPatch,
capsys: pytest.CaptureFixture,
) -> None:
from hermes_cli import gateway as gw
rec = _ListingRecorder(["coder", "writer", "assistant"])
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_all_via_service_manager_if_s6("stop") is True
assert rec.calls == [
("stop", "gateway-coder"),
("stop", "gateway-writer"),
("stop", "gateway-assistant"),
]
out = capsys.readouterr().out
assert "Stopped 3 profile gateway(s)" in out
def test_dispatch_all_iterates_every_profile_on_restart(
monkeypatch: pytest.MonkeyPatch,
capsys: pytest.CaptureFixture,
) -> None:
from hermes_cli import gateway as gw
rec = _ListingRecorder(["coder", "writer"])
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_all_via_service_manager_if_s6("restart") is True
assert rec.calls == [
("restart", "gateway-coder"),
("restart", "gateway-writer"),
]
out = capsys.readouterr().out
assert "Restarted 2 profile gateway(s)" in out
def test_dispatch_all_handles_partial_failure(
monkeypatch: pytest.MonkeyPatch,
capsys: pytest.CaptureFixture,
) -> None:
"""A failure on one profile must not skip the others; the helper
reports each failure and the success count."""
from hermes_cli import gateway as gw
class _FailOnWriter(_ListingRecorder):
def stop(self, name: str) -> None:
if name == "gateway-writer":
raise RuntimeError("supervise FIFO permission denied")
super().stop(name)
rec = _FailOnWriter(["coder", "writer", "assistant"])
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_all_via_service_manager_if_s6("stop") is True
# The two successful ones were called; writer raised before recording.
assert ("stop", "gateway-coder") in rec.calls
assert ("stop", "gateway-assistant") in rec.calls
assert ("stop", "gateway-writer") not in rec.calls
out = capsys.readouterr().out
assert "Stopped 2 profile gateway(s)" in out
assert "Could not stop gateway-writer" in out
assert "supervise FIFO permission denied" in out
def test_dispatch_all_empty_list_reports_and_returns_true(
monkeypatch: pytest.MonkeyPatch,
capsys: pytest.CaptureFixture,
) -> None:
"""With no profile gateways registered the helper still claims the
dispatch (returns True) and prints a friendly message — the host
fallback would just pkill nothing, which isn't useful inside a
container."""
from hermes_cli import gateway as gw
rec = _ListingRecorder([])
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_all_via_service_manager_if_s6("stop") is True
assert rec.calls == []
assert "No profile gateways" in capsys.readouterr().out
def test_dispatch_all_unknown_action_returns_false(
monkeypatch: pytest.MonkeyPatch,
) -> None:
"""`start --all` is not a supported CLI surface; the helper must
fall through to the host code path rather than no-op."""
from hermes_cli import gateway as gw
monkeypatch.setattr(
"hermes_cli.service_manager.detect_service_manager", lambda: "s6",
)
monkeypatch.setattr(
"hermes_cli.service_manager.get_service_manager",
lambda: pytest.fail(
"manager should not be constructed for unsupported --all action",
),
)
assert gw._dispatch_all_via_service_manager_if_s6("start") is False
# ---------------------------------------------------------------------------
# Friendly error rendering — GatewayNotRegisteredError / S6CommandError
# (PR #30136 review item I2)
# ---------------------------------------------------------------------------
def test_dispatch_renders_gateway_not_registered_friendly(
monkeypatch: pytest.MonkeyPatch,
capsys: pytest.CaptureFixture,
) -> None:
"""`hermes -p typo gateway start` should print a clear message and
exit 1 — not dump a traceback at the user."""
from hermes_cli import gateway as gw
from hermes_cli.service_manager import GatewayNotRegisteredError
class _RaisesMissing:
kind = "s6"
def start(self, name: str) -> None:
raise GatewayNotRegisteredError("typo")
monkeypatch.setattr(
"hermes_cli.service_manager.detect_service_manager", lambda: "s6",
)
monkeypatch.setattr(
"hermes_cli.service_manager.get_service_manager", lambda: _RaisesMissing(),
)
with pytest.raises(SystemExit) as excinfo:
gw._dispatch_via_service_manager_if_s6("start", profile="typo")
assert excinfo.value.code == 1
out = capsys.readouterr().out
assert "no such gateway 'typo'" in out
assert "hermes profile create typo" in out
# And critically: no traceback prefix.
assert "Traceback" not in out
def test_dispatch_renders_s6_command_error_friendly(
monkeypatch: pytest.MonkeyPatch,
capsys: pytest.CaptureFixture,
) -> None:
"""An s6-svc failure (e.g. EACCES on the supervise FIFO) should
surface the stderr inline, not as an opaque traceback."""
from hermes_cli import gateway as gw
from hermes_cli.service_manager import S6CommandError
class _RaisesS6Error:
kind = "s6"
def start(self, name: str) -> None:
raise S6CommandError(
service=name,
action="start",
returncode=111,
stderr="s6-svc: fatal: Permission denied",
)
monkeypatch.setattr(
"hermes_cli.service_manager.detect_service_manager", lambda: "s6",
)
monkeypatch.setattr(
"hermes_cli.service_manager.get_service_manager", lambda: _RaisesS6Error(),
)
with pytest.raises(SystemExit) as excinfo:
gw._dispatch_via_service_manager_if_s6("start", profile="coder")
assert excinfo.value.code == 1
out = capsys.readouterr().out
assert "rc=111" in out
assert "Permission denied" in out
assert "Traceback" not in out
# =============================================================================
# `_maybe_redirect_run_to_s6_supervision`: the "upgrade old `gateway run`
# invocation to supervised semantics inside an s6 container" helper.
# =============================================================================
class _Args:
"""Lightweight argparse-like namespace for the helper."""
def __init__(self, no_supervise: bool = False) -> None:
self.no_supervise = no_supervise
def _stub_s6(monkeypatch: pytest.MonkeyPatch, *, on_s6: bool) -> _CallRecorder:
"""Wire up service-manager stubs so the underlying dispatcher will
fire (on_s6=True) or return False (on_s6=False)."""
rec = _CallRecorder()
monkeypatch.setattr(
"hermes_cli.service_manager.detect_service_manager",
lambda: "s6" if on_s6 else "systemd",
)
monkeypatch.setattr(
"hermes_cli.service_manager.get_service_manager", lambda: rec,
)
return rec
class _ExecvpCalled(BaseException):
"""Sentinel raised by the os.execvp stub so tests can assert on it
without actually replacing the test runner process. Inherits from
BaseException so it bypasses generic ``except Exception`` blocks in
the code under test (just like a real exec would)."""
def __init__(self, argv: list[str]) -> None:
self.argv = argv
def _stub_execvp(monkeypatch: pytest.MonkeyPatch) -> list[list[str]]:
"""Replace os.execvp with a recorder that raises _ExecvpCalled."""
calls: list[list[str]] = []
def fake_execvp(file: str, args: list[str]) -> None: # noqa: ANN401
calls.append([file, *args])
raise _ExecvpCalled([file, *args])
monkeypatch.setattr("hermes_cli.gateway.os.execvp", fake_execvp)
return calls
def test_redirect_noop_on_host(monkeypatch: pytest.MonkeyPatch) -> None:
"""Host runs (non-s6) must not redirect. Returns False; caller
continues to the foreground gateway code path unchanged."""
from hermes_cli import gateway as gw
_stub_s6(monkeypatch, on_s6=False)
# If execvp got called we'd raise — keep it bound so test fails loudly.
monkeypatch.setattr(
"hermes_cli.gateway.os.execvp",
lambda *a, **kw: pytest.fail("execvp should not be called on host"),
)
monkeypatch.delenv("HERMES_S6_SUPERVISED_CHILD", raising=False)
monkeypatch.delenv("HERMES_GATEWAY_NO_SUPERVISE", raising=False)
assert gw._maybe_redirect_run_to_s6_supervision(_Args()) is False
def test_redirect_fires_inside_s6_container(
monkeypatch: pytest.MonkeyPatch, capsys: pytest.CaptureFixture[str],
) -> None:
"""Inside an s6 container, `gateway run` should:
1. Dispatch `start` to the service manager.
2. Print the loud breadcrumb to stderr.
3. exec `sleep infinity` to keep the CMD alive without binding
container lifetime to gateway PID lifetime.
"""
from hermes_cli import gateway as gw
rec = _stub_s6(monkeypatch, on_s6=True)
monkeypatch.setattr("hermes_cli.gateway._profile_suffix", lambda: "")
execvp_calls = _stub_execvp(monkeypatch)
monkeypatch.delenv("HERMES_S6_SUPERVISED_CHILD", raising=False)
monkeypatch.delenv("HERMES_GATEWAY_NO_SUPERVISE", raising=False)
with pytest.raises(_ExecvpCalled) as excinfo:
gw._maybe_redirect_run_to_s6_supervision(_Args())
# 1. Dispatcher fired.
assert rec.calls == [("start", "gateway-default")]
# 2. Breadcrumb went to stderr and mentions the opt-out path.
err = capsys.readouterr().err
assert "s6 supervision" in err
assert "--no-supervise" in err
assert "HERMES_GATEWAY_NO_SUPERVISE" in err
# 3. exec'd `sleep infinity`.
assert execvp_calls == [["sleep", "sleep", "infinity"]]
assert excinfo.value.argv == ["sleep", "sleep", "infinity"]
def test_redirect_short_circuits_supervised_child(
monkeypatch: pytest.MonkeyPatch,
) -> None:
"""The recursion guard: when the supervised gateway s6-supervise is
running execs `hermes gateway run --replace`, the
HERMES_S6_SUPERVISED_CHILD sentinel must short-circuit the redirect
so the gateway actually starts foreground. Without this guard the
supervised process would re-dispatch `start` → re-exec `run` → ...
in an infinite loop.
"""
from hermes_cli import gateway as gw
monkeypatch.setattr(
"hermes_cli.service_manager.detect_service_manager",
lambda: pytest.fail("dispatcher should not run when sentinel is set"),
)
monkeypatch.setattr(
"hermes_cli.gateway.os.execvp",
lambda *a, **kw: pytest.fail("execvp should not run when sentinel is set"),
)
monkeypatch.setenv("HERMES_S6_SUPERVISED_CHILD", "1")
monkeypatch.delenv("HERMES_GATEWAY_NO_SUPERVISE", raising=False)
assert gw._maybe_redirect_run_to_s6_supervision(_Args()) is False
def test_redirect_respects_no_supervise_flag(
monkeypatch: pytest.MonkeyPatch,
) -> None:
"""`--no-supervise` (CLI flag) must skip the redirect even inside
an s6 container, restoring pre-s6 foreground semantics."""
from hermes_cli import gateway as gw
monkeypatch.setattr(
"hermes_cli.service_manager.detect_service_manager",
lambda: pytest.fail("dispatcher should not run when --no-supervise is set"),
)
monkeypatch.setattr(
"hermes_cli.gateway.os.execvp",
lambda *a, **kw: pytest.fail("execvp should not run when --no-supervise is set"),
)
monkeypatch.delenv("HERMES_S6_SUPERVISED_CHILD", raising=False)
monkeypatch.delenv("HERMES_GATEWAY_NO_SUPERVISE", raising=False)
assert gw._maybe_redirect_run_to_s6_supervision(_Args(no_supervise=True)) is False
@pytest.mark.parametrize("value", ["1", "true", "TRUE", "yes", "Yes"])
def test_redirect_respects_no_supervise_env(
monkeypatch: pytest.MonkeyPatch, value: str,
) -> None:
"""`HERMES_GATEWAY_NO_SUPERVISE=1` (env var) must skip the redirect.
Truthiness mirrors the dashboard service's own env var parsing —
1/true/yes are all accepted, case-insensitively.
"""
from hermes_cli import gateway as gw
monkeypatch.setattr(
"hermes_cli.service_manager.detect_service_manager",
lambda: pytest.fail("dispatcher should not run when env opt-out is set"),
)
monkeypatch.setattr(
"hermes_cli.gateway.os.execvp",
lambda *a, **kw: pytest.fail("execvp should not run when env opt-out is set"),
)
monkeypatch.delenv("HERMES_S6_SUPERVISED_CHILD", raising=False)
monkeypatch.setenv("HERMES_GATEWAY_NO_SUPERVISE", value)
assert gw._maybe_redirect_run_to_s6_supervision(_Args()) is False
def test_redirect_no_supervise_env_falsy_values_dont_opt_out(
monkeypatch: pytest.MonkeyPatch,
) -> None:
"""Falsy / unrecognized values of HERMES_GATEWAY_NO_SUPERVISE must
NOT opt out. We're strict about what counts as "yes" so a typo
like `HERMES_GATEWAY_NO_SUPERVISE=0` doesn't silently enable the
historical foreground behavior."""
from hermes_cli import gateway as gw
_stub_s6(monkeypatch, on_s6=True)
monkeypatch.setattr("hermes_cli.gateway._profile_suffix", lambda: "")
_stub_execvp(monkeypatch)
monkeypatch.delenv("HERMES_S6_SUPERVISED_CHILD", raising=False)
for falsy in ("", "0", "false", "no", "off", "garbage"):
monkeypatch.setenv("HERMES_GATEWAY_NO_SUPERVISE", falsy)
with pytest.raises(_ExecvpCalled):
gw._maybe_redirect_run_to_s6_supervision(_Args())
Reference in a new issue View git blame Copy permalink