Files
hermes-agent/tests/docker/test_dashboard.py
Ben cae6b5486f feat(dashboard): always enable embedded chat; remove dashboard --tui flag
The dashboard's embedded Chat surface (/chat, /api/ws, /api/pty) was gated
behind `hermes dashboard --tui` / HERMES_DASHBOARD_TUI=1. The desktop app and
the dashboard's own Chat tab both drive the agent over the /api/ws + /api/pty
WebSockets, so a dashboard started without the flag would pass the /api/status
health check but slam the chat WebSocket shut with WS code 4403 — the app
connects, reports "ready", and chat stays dead. This was the root cause behind
multiple user reports of the desktop app failing to connect to a self-hosted
gateway/dashboard, and it bit Docker and host installs alike.

Make the embedded chat unconditional:

- web_server.py: _DASHBOARD_EMBEDDED_CHAT_ENABLED defaults to True; drop the
  embedded_chat parameter and the runtime reassignment from start_server().
  The WS gates still read the constant (now always true) so the seam — and its
  "rejects when disabled" contract test — stays meaningful.
- main.py: remove the `--tui` argument from the dashboard subparser and the
  `embedded_chat = args.tui or HERMES_DASHBOARD_TUI==1` derivation.
- web/: isDashboardEmbeddedChatEnabled() returns true unconditionally; drop the
  deprecated __HERMES_DASHBOARD_TUI__ alias and the dead LEGACY_TUI_RE scrape in
  the vite dev-token plugin.
- apps/desktop/electron/main.cjs: drop `--tui` from the spawned dashboardArgs
  (it would now error with "unrecognized arguments: --tui") and the redundant
  HERMES_DASHBOARD_TUI env injection.
- Docker: no s6 run-script change needed — the script never passed --tui; the
  HERMES_DASHBOARD_TUI env var is now simply a no-op, so the image works out of
  the box with no extra var.
- Docs: remove every dashboard --tui / HERMES_DASHBOARD_TUI reference across the
  CLI reference, env-var reference, docker/desktop/web-dashboard guides, in-app
  tips, and the zh-Hans translations. The terminal `hermes --tui` / HERMES_TUI
  references are intentionally left untouched.

Tests: 270 passing across web_server, dashboard lifecycle, host-header,
auth-gate, and docker-override-scripts suites.
2026-06-04 03:03:35 -07:00

416 lines
17 KiB
Python

"""Harness: dashboard opt-in via HERMES_DASHBOARD.
Today (tini): dashboard starts once when HERMES_DASHBOARD=1; if it crashes
it stays dead. After Phase 2 (s6): dashboard starts once; if it crashes
it is restarted under supervision. The restart-after-crash test lives in
Phase 2 Task 2.5; this file only locks the opt-in surface (which must
not change between tini and s6).
Every ``docker exec`` here runs as the unprivileged ``hermes`` user
(via :func:`docker_exec`/:func:`docker_exec_sh` in conftest), matching
the realistic runtime context. See the conftest module docstring.
"""
from __future__ import annotations
import json
import subprocess
import time
from tests.docker.conftest import docker_exec, docker_exec_sh
def _poll(container: str, probe: str, *, deadline_s: float = 30.0,
interval_s: float = 0.5) -> tuple[bool, str]:
"""Repeatedly run ``probe`` inside the container until it exits 0 or
``deadline_s`` elapses. Returns (success, last stdout)."""
end = time.monotonic() + deadline_s
last = ""
while time.monotonic() < end:
r = docker_exec_sh(container, probe, timeout=10)
last = r.stdout
if r.returncode == 0:
return True, last
time.sleep(interval_s)
return False, last
def test_dashboard_not_running_by_default(
built_image: str, container_name: str,
) -> None:
"""Without HERMES_DASHBOARD, no dashboard process should be running."""
subprocess.run(
["docker", "run", "-d", "--name", container_name, built_image,
"sleep", "60"],
check=True, capture_output=True, timeout=30,
)
# Give the entrypoint enough time to finish bootstrap; if a dashboard
# were going to start it'd be visible by now.
time.sleep(5)
r = docker_exec(container_name, "pgrep", "-f", "hermes dashboard")
# pgrep exits non-zero when no match found
assert r.returncode != 0, (
"Dashboard should not be running without HERMES_DASHBOARD"
)
def test_dashboard_slot_reports_down_when_disabled(
built_image: str, container_name: str,
) -> None:
"""Without HERMES_DASHBOARD, s6-svstat should report the dashboard
slot as DOWN (not up-with-sleep-infinity, which would
false-positive `hermes doctor` and any other health check).
Locks the PR #30136 review item I3 fix: cont-init.d/03-dashboard-toggle
writes a `down` marker file in the live service-dir when
HERMES_DASHBOARD is unset, so the slot reflects reality.
"""
subprocess.run(
["docker", "run", "-d", "--name", container_name, built_image,
"sleep", "60"],
check=True, capture_output=True, timeout=30,
)
time.sleep(5)
# /command/ isn't on PATH for docker-exec sessions, so call by
# absolute path.
r = docker_exec(
container_name, "/command/s6-svstat", "/run/service/dashboard",
)
assert r.returncode == 0, f"s6-svstat failed: {r.stderr!r} / {r.stdout!r}"
assert "down" in r.stdout, (
f"Dashboard slot should be 'down' without HERMES_DASHBOARD; "
f"svstat reports: {r.stdout!r}"
)
def test_dashboard_slot_reports_up_when_enabled(
built_image: str, container_name: str,
) -> None:
"""Symmetry: with HERMES_DASHBOARD=1, s6-svstat reports the slot as up."""
subprocess.run(
["docker", "run", "-d", "--name", container_name,
"-e", "HERMES_DASHBOARD=1",
# The default dashboard host is 0.0.0.0, which now engages the
# OAuth auth gate. Without a provider registered (no
# HERMES_DASHBOARD_OAUTH_CLIENT_ID in this test env), start_server
# would fail closed and the slot would never come up. Pin the
# explicit insecure opt-in to keep this test focused on the s6
# supervision contract, not the auth gate.
"-e", "HERMES_DASHBOARD_INSECURE=1",
built_image, "sleep", "120"],
check=True, capture_output=True, timeout=30,
)
# uvicorn takes a moment to bind; poll svstat.
deadline = time.monotonic() + 30.0
last = ""
while time.monotonic() < deadline:
r = docker_exec(
container_name, "/command/s6-svstat", "/run/service/dashboard",
)
last = r.stdout
if r.returncode == 0 and "up " in r.stdout:
return # success
time.sleep(0.5)
raise AssertionError(
f"Dashboard slot never reached up state; last svstat: {last!r}"
)
def test_dashboard_opt_in_starts(
built_image: str, container_name: str,
) -> None:
"""With HERMES_DASHBOARD=1, a dashboard process should be visible."""
subprocess.run(
["docker", "run", "-d", "--name", container_name,
"-e", "HERMES_DASHBOARD=1",
# Default bind is 0.0.0.0; pin insecure opt-in so the auth gate
# doesn't fail-closed before the process can come up. See
# test_dashboard_slot_reports_up_when_enabled for the full rationale.
"-e", "HERMES_DASHBOARD_INSECURE=1",
built_image, "sleep", "120"],
check=True, capture_output=True, timeout=30,
)
# Poll for the dashboard subprocess to appear — the entrypoint
# backgrounds it and bootstrap (skills sync etc.) can take a few
# seconds before the python process actually launches.
ok, _ = _poll(
container_name, "pgrep -f 'hermes dashboard'", deadline_s=30.0,
)
assert ok, "Dashboard should be running with HERMES_DASHBOARD=1"
def test_dashboard_port_override(
built_image: str, container_name: str,
) -> None:
"""HERMES_DASHBOARD_PORT changes the dashboard's listen port."""
subprocess.run(
["docker", "run", "-d", "--name", container_name,
"-e", "HERMES_DASHBOARD=1", "-e", "HERMES_DASHBOARD_PORT=9120",
# Default bind is 0.0.0.0; pin insecure opt-in so the auth gate
# doesn't fail-closed before the port is bound. See
# test_dashboard_slot_reports_up_when_enabled for the full rationale.
"-e", "HERMES_DASHBOARD_INSECURE=1",
built_image, "sleep", "120"],
check=True, capture_output=True, timeout=30,
)
# The dashboard process appearing in pgrep doesn't mean it's bound
# to the port yet — uvicorn takes another second or two to come up.
# The image doesn't ship ss/netstat, so probe /proc/net/tcp directly:
# port 9120 = 0x23A0, state 0A = LISTEN.
ok, stdout = _poll(
container_name,
"grep -E ' 0+:23A0 .* 0A ' /proc/net/tcp /proc/net/tcp6 "
"2>/dev/null",
deadline_s=60.0,
)
assert ok, f"Dashboard not listening on port 9120: stdout={stdout!r}"
def test_dashboard_restarts_after_crash(
built_image: str, container_name: str,
) -> None:
"""Phase 2 invariant: under s6 supervision, killing the dashboard
process should be recovered automatically.
Pre-s6 (tini) behavior was "stays dead" — the test wouldn't have
passed against that image. After the s6-overlay migration the
dashboard runs as a longrun s6-rc service and s6-supervise restarts
it after a ~1s backoff (the default).
"""
subprocess.run(
["docker", "run", "-d", "--name", container_name,
"-e", "HERMES_DASHBOARD=1",
# Default bind is 0.0.0.0; pin insecure opt-in so the auth gate
# doesn't fail-closed before the supervised dashboard can come up.
# See test_dashboard_slot_reports_up_when_enabled for the full
# rationale.
"-e", "HERMES_DASHBOARD_INSECURE=1",
built_image, "sleep", "120"],
check=True, capture_output=True, timeout=30,
)
# Wait for the first dashboard to come up.
ok, _ = _poll(
container_name, "pgrep -f 'hermes dashboard'", deadline_s=30.0,
)
assert ok, "Dashboard never started initially"
# Grab the initial PID. s6 may briefly transition through restart
# state between our poll-success and the follow-up pgrep, so retry
# a couple of times before giving up.
first_pid: str | None = None
for _attempt in range(10):
first_pid_result = docker_exec(
container_name, "pgrep", "-f", "hermes dashboard",
)
first_pids = first_pid_result.stdout.strip().split()
if first_pids:
first_pid = first_pids[0]
break
time.sleep(0.5)
assert first_pid is not None, "Could not capture initial dashboard PID"
# Kill the dashboard. The dashboard process runs as hermes, so the
# hermes user can kill it (same UID).
docker_exec(container_name, "kill", "-9", first_pid)
# s6 backs off ~1s before restart; allow up to 15s for the new
# process to appear with a different PID.
deadline = time.monotonic() + 15.0
while time.monotonic() < deadline:
r = docker_exec(container_name, "pgrep", "-f", "hermes dashboard")
pids = r.stdout.strip().split() if r.returncode == 0 else []
if pids and pids[0] != first_pid:
return # success
time.sleep(0.5)
raise AssertionError(
f"Dashboard not restarted after kill (first_pid={first_pid})"
)
# ---------------------------------------------------------------------------
# OAuth auth-gate behaviour — regression guard for the dashboard-insecure
# auto-injection bug. Pre-fix, the s6 run script appended `--insecure`
# whenever `HERMES_DASHBOARD_HOST` was non-loopback, silently disabling
# the OAuth gate on every container-deployed dashboard. The matching
# static-text guard lives in tests/test_docker_home_override_scripts.py;
# this is the behavioural end-to-end check.
# ---------------------------------------------------------------------------
def _http_probe(
container: str,
path: str,
*,
deadline_s: float = 60.0,
) -> tuple[int, str]:
"""Poll ``http://127.0.0.1:9119<path>`` from inside the container.
Returns ``(status_code, body)`` as soon as the dashboard answers any
HTTP response — 200, 401, 503, anything. The image doesn't ship
``curl`` but the venv's stdlib ``urllib`` is good enough; we use a
proper ``try``/``except`` to intercept ``HTTPError`` because
``urlopen`` raises on 4xx/5xx, and we treat those as legitimate
responses (the OAuth gate's 401 IS the success signal for the
gate-engaged test).
Connection errors (uvicorn still starting, fail-closed exited) keep
the poll loop running until ``deadline_s`` elapses.
The probe Python program is fed over stdin (``python -``) rather
than ``python -c`` so we can use proper multi-line syntax with
``try``/``except`` blocks without escaping hell.
Raises ``AssertionError`` on timeout.
"""
py_program = f"""\
import urllib.request, urllib.error
req = urllib.request.Request("http://127.0.0.1:9119{path}")
try:
r = urllib.request.urlopen(req, timeout=5)
print(r.status)
print(r.read().decode(), end="")
except urllib.error.HTTPError as h:
print(h.code)
print(h.read().decode(), end="")
"""
# Feed the program over stdin via a heredoc so docker_exec_sh's
# single bash string stays clean. The 'PY' delimiter is quoted to
# disable shell expansion inside the heredoc body.
probe = (
"/opt/hermes/.venv/bin/python - <<'PY'\n"
f"{py_program}"
"PY"
)
end = time.monotonic() + deadline_s
last_err = ""
while time.monotonic() < end:
r = docker_exec_sh(container, probe, timeout=10)
if r.returncode == 0 and r.stdout.strip():
lines = r.stdout.split("\n", 1)
try:
status = int(lines[0].strip())
body = lines[1] if len(lines) > 1 else ""
return status, body
except (ValueError, IndexError) as exc:
last_err = f"parse: {exc!r} / stdout={r.stdout!r}"
else:
last_err = f"rc={r.returncode} stderr={r.stderr!r}"
time.sleep(0.5)
raise AssertionError(
f"Probe of {path} never returned HTTP within {deadline_s}s; "
f"last error: {last_err}"
)
def test_dashboard_oauth_gate_engages_on_non_loopback_bind(
built_image: str, container_name: str,
) -> None:
"""The s6 dashboard run script must NOT auto-add ``--insecure`` when the
dashboard binds to ``0.0.0.0``. The OAuth auth gate engages on its own
when a ``DashboardAuthProvider`` is registered (the bundled nous
provider activates whenever ``HERMES_DASHBOARD_OAUTH_CLIENT_ID`` is
set).
Regression guard for the wildcard-subdomain rollout where every
portal-provisioned agent binds ``0.0.0.0`` and relies on the OAuth
gate to authenticate browser callers. Before this fix, the run script
flipped ``--insecure`` on for any non-loopback bind, which routed
``start_server`` straight back into the legacy ``allow_public=True``
branch and disabled the gate every time.
We verify two independent observable consequences of the gate being
on:
1. ``/api/auth/providers`` (publicly reachable through the gate so
the login page can bootstrap) returns 200 with ``nous`` in the
provider list — proves the bundled provider registered.
2. ``/api/sessions`` (a gated route under both the legacy
``_SESSION_TOKEN`` middleware and the OAuth gate) returns 401
to an unauthenticated caller — proves the OAuth gate is actively
intercepting browser traffic. We deliberately probe a gated route
here rather than ``/api/status``: status sits in the shared
``PUBLIC_API_PATHS`` allowlist (portal liveness probe target) and
responds 200 without a cookie under both gates, so it cannot
distinguish "gate on" from "gate off".
"""
subprocess.run(
["docker", "run", "-d", "--name", container_name,
"-e", "HERMES_DASHBOARD=1",
"-e", "HERMES_DASHBOARD_HOST=0.0.0.0",
"-e", "HERMES_DASHBOARD_OAUTH_CLIENT_ID=agent:test-instance",
built_image, "sleep", "120"],
check=True, capture_output=True, timeout=30,
)
# (1) Provider registry visible via the public bootstrap endpoint.
status_code, body = _http_probe(container_name, "/api/auth/providers")
assert status_code == 200, (
f"/api/auth/providers should return 200 when a provider is "
f"registered; got {status_code} body={body!r}"
)
payload = json.loads(body)
provider_names = [p.get("name") for p in payload.get("providers", [])]
assert "nous" in provider_names, (
"Bundled dashboard_auth/nous provider should register when "
f"HERMES_DASHBOARD_OAUTH_CLIENT_ID is set. Got: {payload!r}"
)
# (2) A gated route (``/api/sessions``) returns 401 to an
# unauthenticated caller — the OAuth gate is intercepting.
status_code, body = _http_probe(container_name, "/api/sessions")
assert status_code == 401, (
"OAuth gate must intercept gated /api/* routes on 0.0.0.0 bind "
"when a provider is registered and HERMES_DASHBOARD_INSECURE "
f"is unset. Got: status={status_code} body={body!r}"
)
# (3) ``/api/status`` remains 200 under the gate — it's in the shared
# ``PUBLIC_API_PATHS`` allowlist so NAS's wildcard-subdomain
# liveness probe (``fly-provider.ts`` ``getInstanceRuntimeStatus``)
# can reach it without a cookie. Regression guard: this allowlist
# drifted once already and surfaced every healthy agent as
# STARTING/down in the portal UI.
status_code, body = _http_probe(container_name, "/api/status")
assert status_code == 200, (
"/api/status must remain publicly reachable under the OAuth gate "
"— the portal uses it as the wildcard-subdomain liveness probe. "
f"Got: status={status_code} body={body!r}"
)
status = json.loads(body)
assert status.get("auth_required") is True, (
"/api/status must report auth_required=True when the OAuth gate "
f"is engaged so the SPA/portal can distinguish modes. Got: {status!r}"
)
def test_dashboard_insecure_env_var_opts_out_of_gate(
built_image: str, container_name: str,
) -> None:
"""``HERMES_DASHBOARD_INSECURE=1`` re-enables the legacy no-gate mode
for operators running on trusted LANs behind a reverse proxy without
the OAuth contract. Same opt-out shape as the rest of the s6 boolean
envs (e.g. ``HERMES_DASHBOARD``).
With the gate off, ``/api/status`` (a public endpoint under the
legacy ``_SESSION_TOKEN`` middleware) returns 200 with the
``auth_required: false`` body — proves the gate is bypassed.
"""
subprocess.run(
["docker", "run", "-d", "--name", container_name,
"-e", "HERMES_DASHBOARD=1",
"-e", "HERMES_DASHBOARD_HOST=0.0.0.0",
"-e", "HERMES_DASHBOARD_INSECURE=1",
built_image, "sleep", "120"],
check=True, capture_output=True, timeout=30,
)
status_code, body = _http_probe(container_name, "/api/status")
assert status_code == 200, (
f"/api/status should return 200 with the auth gate disabled; "
f"got {status_code} body={body!r}"
)
status = json.loads(body)
assert status.get("auth_required") is False, (
"HERMES_DASHBOARD_INSECURE=1 must disable the auth gate (explicit "
f"opt-in for trusted-LAN deployments). Got: {status!r}"
)