Files
LEDMatrix/web_interface/blueprints/api_v3/display.py
T
ChuckandClaude Opus 5.5 c461f4efdb feat(ipc)!: remove the cache-key mailboxes (control socket stage 5)
The control socket is now the only way the web interface sends the display a
command. The display stops reading display_on_demand_request and
plugin_error_clear_request, and the web interface stops writing them.

- Display: no mailbox poll (MailboxWatch, the 1 s / 0.25 s cadence,
  _consume_on_demand_request, the deprecation log) and no persisted
  display_on_demand_processed_id guard; the error publisher reads no clear
  request. CacheManager.file_signature and MailboxWatch are removed.
- A write to either retired key is dropped by CacheManager.save_cache and
  logged once per writer, naming the plugin from the call stack (or the
  request's plugin_id), with the API to move to.
- Web: on-demand start with no display listening starts the service (when
  start_service) and sends the request again once the socket answers (45 s,
  10 s for a running service without a socket yet); every other failure is
  a 503 (400 for invalid_args). Stop answers 503 when no display listens,
  unless stop_service. errors/clear answers 503 with a reason-specific
  message instead of writing a request; clear_pending is always false.
  src.ipc.client.should_fall_back is replaced by display_not_listening.
- Kept: display_current_state, display_on_demand_state,
  plugin_runtime_snapshot and the heartbeat (read whenever the socket cannot
  answer), and display_on_demand_config (the display's resume record).

Tests: mailbox-only tests removed (test_on_demand_mailbox.py, the mailbox
cadence, file_signature and MailboxWatch tests); tests that injected
requests through the mailbox now use the socket queue or a plugin's
in-process request. The run-loop harness sends on-demand requests over its
fake control socket, so four golden traces change: on-demand starts and
stops land at the request instant instead of the next 0.25 s mailbox look
(one frame fewer on the screen they end), and in vegas.json within one
frame instead of 263 ms, which shifts the later 1 s-throttled WiFi-notice
check by under a second.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-05 09:32:22 -04:00

452 lines
20 KiB
Python

"""Display control, on-demand playback and preview.
Routes decorate the shared `api_v3` Blueprint from the package `__init__`,
so their endpoint names are unchanged by living here.
"""
from web_interface.blueprints.api_v3 import (
_QUIET_SOCKET_REASONS, _REPORTABLE_SOCKET_REASONS, # noqa: F401 - tests read them here
_coerce_to_bool, _ensure_display_service_running,
_get_display_service_status, _socket_reason_code, _stop_display_service, api_v3,
jsonify, logger, request, uuid,
)
from web_interface import display_preview, display_state
import web_interface.blueprints.api_v3 as _pkg
from src.ipc import client as control_client
# Read through the module rather than bound by value: tests patch these
# as module attributes, and a value binding would not see the patch.
# Several are also called from helpers that live in __init__, so the
# package is the only patch point that covers every caller.
def _cache_manager():
"""The web process's CacheManager, the one app.py puts on the blueprint.
Created on first use when nothing set it (a test app, an embedder), and
stored back on the blueprint so every route shares that one instance.
"""
cache = getattr(api_v3, 'cache_manager', None)
if cache is None:
from src.cache_manager import CacheManager
cache = api_v3.cache_manager = CacheManager()
return cache
#: How long the start route waits for a display it has just started (or one
#: systemd already reports running, which may still be loading its plugins)
#: to serve its control socket, before it gives up. The socket comes up when
#: the display's run loop starts, after every plugin has loaded.
ON_DEMAND_SOCKET_WAIT_SECONDS = 45.0
#: The same wait when the service was already running: a display that has
#: just been restarted by someone else. Shorter, because a running display
#: normally has its socket.
ON_DEMAND_SOCKET_WAIT_RUNNING_SECONDS = 10.0
#: Gap between two attempts while waiting for the socket.
ON_DEMAND_SOCKET_RETRY_INTERVAL = 0.5
def _send_on_demand(payload):
"""Hand an on-demand request to the display over the control socket.
Returns the display's acknowledgement: it has the command queued for
its render thread. Raises ``control_client.ControlError`` when it did
not take it; there is no other way to reach the display (the file
mailbox ``display_on_demand_request`` is gone).
"""
if payload['action'] == 'start':
return control_client.on_demand_start(
payload['request_id'], payload.get('plugin_id'), payload.get('mode'),
payload.get('duration'), bool(payload.get('pinned', False)))
return control_client.on_demand_stop(payload['request_id'])
def _send_on_demand_when_listening(payload, wait_seconds):
"""_send_on_demand, retried while no display is listening yet (a display
still starting), for up to ``wait_seconds``. Any other failure, or the
last one once the time is up, raises ``control_client.ControlError``."""
deadline = _pkg.time.monotonic() + wait_seconds
while True:
try:
return _send_on_demand(payload)
except control_client.ControlError as e:
if (not control_client.display_not_listening(e)
or _pkg.time.monotonic() + ON_DEMAND_SOCKET_RETRY_INTERVAL > deadline):
raise
_pkg.time.sleep(ON_DEMAND_SOCKET_RETRY_INTERVAL)
def _socket_error_response(request_id, action, reason, message=None, **extra):
"""The answer when the display did not take an on-demand request: ``400``
for arguments it refused, else ``503``."""
status = 400 if reason == 'invalid_args' else 503
data = {'request_id': request_id, 'transport': 'socket', 'socket_error': reason}
data.update(extra)
return jsonify({
'status': 'error',
'message': message or (f'The display service did not accept the on-demand {action} '
f'request ({reason})'),
'data': data,
}), status
def _socket_failure_reason(error):
"""The reportable reason code for an exception from _send_on_demand, logged."""
if isinstance(error, control_client.ControlError):
reason = _socket_reason_code(error.reason)
if reason in _QUIET_SOCKET_REASONS:
logger.debug("On-demand request not taken over the control socket: %s", error)
else:
logger.warning("On-demand request not taken over the control socket: %s", error)
return reason
logger.error("Control socket client failed", exc_info=error)
return 'internal'
@api_v3.route('/display/current', methods=['GET'])
def get_display_current():
"""The latest display preview, as the /stream/display SSE stream sends it.
``data`` is ``{timestamp, width, height, image}``; ``image`` is the
snapshot PNG base64-encoded, or null when there is none to show.
"""
# Get display dimensions from config: the logical size DisplayManager
# renders at, so double-sided setups preview one screen
from src.display_geometry import logical_size
try:
config = api_v3.config_manager.load_config() if api_v3.config_manager else {}
width, height = logical_size(config)
except Exception:
width, height = logical_size({})
try:
image = display_preview.read_snapshot_base64()
except FileNotFoundError:
image = None # the display service has not written one yet
except OSError:
logger.warning("Could not read the display preview snapshot", exc_info=True)
image = None
return jsonify({'status': 'success',
'data': display_preview.preview_payload(width, height, image)})
@api_v3.route('/display/modes', methods=['GET'])
def get_display_modes():
"""Every display mode that can be requested on-demand, with its plugin.
/plugins/installed carries no mode information, so anything driving the
display from outside the web UI (the Home Assistant MQTT bridge, a script)
had to read each plugin's manifest.json off disk and reimplement the
fallbacks in PluginManager.get_plugin_display_modes to do it. This is the
same list the force-display dialog offers, from the source that owns it.
Knowing each mode's plugin_id also matters because /display/on-demand/start
falls back to find_plugin_for_mode when plugin_id is omitted, and that
lookup only sees modes declared in a static manifest -- a plugin whose
modes are generated (each installed Starlark app is one) 404s there.
Sending the plugin_id from this list skips the lookup entirely.
Query params:
include_disabled: '1' to list modes of disabled plugins too. They can
still be requested on-demand -- the controller enables the plugin
for the duration -- so they are reported with enabled: false
rather than omitted.
"""
if not api_v3.plugin_catalog:
return jsonify({'status': 'error', 'message': 'Plugin catalog not initialized'}), 500
# Discovery is lazy and normally triggered by whichever endpoint runs
# first, which is a person opening the dashboard. A caller that never
# visits it would otherwise see an empty list.
api_v3.plugin_catalog.discover_plugins()
include_disabled = request.args.get('include_disabled') in ('1', 'true', 'True')
full_config = api_v3.config_manager.load_config() if api_v3.config_manager else {}
modes = []
for plugin_id, manifest in sorted(api_v3.plugin_catalog.plugin_manifests.items()):
# A hand-edited or migrated config.json can hold a non-dict under a
# plugin id; DisplayController._reconcile guards the same shape, so
# it happens in practice. Without this, .get() raises AttributeError,
# the loop aborts and the endpoint answers 500 with no modes at all
# -- one bad section would blank every entity the MQTT bridge builds
# from this list.
plugin_config = full_config.get(plugin_id)
if not isinstance(plugin_config, dict):
if plugin_config is not None:
logger.warning(
"Config for plugin %r is %s, not an object; treating it as disabled",
plugin_id, type(plugin_config).__name__)
plugin_config = {}
enabled = bool(plugin_config.get('enabled', False))
if not enabled and not include_disabled:
continue
plugin_name = (manifest or {}).get('name') or plugin_id
plugin_modes = api_v3.plugin_catalog.get_plugin_display_modes(plugin_id) or [plugin_id]
for mode in plugin_modes:
# A single-mode plugin's mode is the plugin, so its own name is
# the readable label. Multi-mode plugins have no per-mode name
# anywhere, so the raw mode string is the only thing to show.
modes.append({
'mode': mode,
'plugin_id': plugin_id,
'plugin_name': plugin_name,
'name': plugin_name if len(plugin_modes) == 1 else mode,
'enabled': enabled,
})
return jsonify({'status': 'success', 'data': {'modes': modes}})
@api_v3.route('/display/on-demand/status', methods=['GET'])
def get_on_demand_status():
"""Return the current on-demand display state.
From the display's state stream over the control socket when it is
available (``source: "socket"``), else the cache key it also writes
(``source: "cache"``).
"""
state = display_state.on_demand_state(display_state.read_state())
source = 'socket'
if state is None:
source = 'cache'
cache = _cache_manager()
# memory_ttl=0: the display service writes this key, so only the file
# is current. This process's memory tier would keep serving the first
# copy it read for the full max_age -- "active" for two minutes after
# the display had already stopped.
state = cache.get('display_on_demand_state', max_age=120, memory_ttl=0)
if state is None:
state = {
'active': False,
'status': 'idle',
'last_updated': None
}
service_status = _get_display_service_status()
return jsonify({
'status': 'success',
'data': {
'state': state,
'service': service_status,
'source': source,
}
})
@api_v3.route('/display/on-demand/start', methods=['POST'])
def start_on_demand_display():
"""Request the display controller to run a specific plugin on-demand."""
data = request.get_json(silent=True) or {}
plugin_id = data.get('plugin_id')
mode = data.get('mode')
duration = data.get('duration')
# _coerce_to_bool: bool("false") is True, so a string "false" pinned the
# mode or (re)started the service it asked to leave alone.
pinned = _coerce_to_bool(data.get('pinned', False))
start_service = _coerce_to_bool(data.get('start_service', True))
if not plugin_id and not mode:
return jsonify({'status': 'error', 'message': 'plugin_id or mode is required'}), 400
resolved_plugin = plugin_id
resolved_mode = mode
if api_v3.plugin_catalog:
if resolved_plugin and resolved_plugin not in _pkg._discovered_plugin_manifests(resolved_plugin):
return jsonify({'status': 'error', 'message': f'Plugin {resolved_plugin} not found'}), 404
if resolved_plugin and not resolved_mode:
modes = api_v3.plugin_catalog.get_plugin_display_modes(resolved_plugin)
resolved_mode = modes[0] if modes else resolved_plugin
elif resolved_mode and not resolved_plugin:
_pkg._discovered_plugin_manifests()
resolved_plugin = api_v3.plugin_catalog.find_plugin_for_mode(resolved_mode)
if not resolved_plugin:
# Not among what was discovered: the plugin that declares
# it may have been installed since. Scan once more.
_pkg._discovered_plugin_manifests(rescan=True)
resolved_plugin = api_v3.plugin_catalog.find_plugin_for_mode(resolved_mode)
if not resolved_plugin:
return jsonify({'status': 'error', 'message': f'Mode {resolved_mode} not found'}), 404
# On-demand works with disabled plugins: the running display loads one
# for the session and unloads it afterwards, leaving config.json alone
# (DisplayController._load_plugin_for_on_demand). Logged for debugging.
if api_v3.config_manager and resolved_plugin:
config = api_v3.config_manager.load_config()
plugin_config = config.get(resolved_plugin, {})
if 'enabled' in plugin_config and not plugin_config.get('enabled', False):
logger.info(
"On-demand request for disabled plugin '%s' - will be temporarily enabled",
resolved_plugin,
)
# The request goes over the control socket, the only way to reach the
# display. A display that is not listening (stopped, or still starting)
# is started when start_service asks for it, and the request is sent
# again once its socket is up.
request_id = data.get('request_id') or str(uuid.uuid4())
request_payload = {
'request_id': request_id,
'action': 'start',
'plugin_id': resolved_plugin,
'mode': resolved_mode,
'duration': duration,
'pinned': pinned,
'timestamp': _pkg.time.time()
}
try:
_send_on_demand(request_payload)
except Exception as e: # pylint: disable=broad-except
error = e
else:
# A socket acknowledgement is the display itself answering: it is
# running and has the request queued, whatever systemd says (a
# display run by hand or in the emulator has no active unit). So
# nothing is checked or started for it. The service is still
# reported the way _ensure_display_service_running reports a
# running one.
service_result = (dict(_get_display_service_status(), started=False)
if start_service else None)
return _on_demand_started(request_id, resolved_plugin, resolved_mode,
duration, pinned, service_result)
reason = _socket_failure_reason(error)
if not control_client.display_not_listening(error):
# The display had it and refused it, is too old for the command, or
# this web process cannot use the socket at all (switched off, no
# Unix sockets): starting a service would not change that.
return _socket_error_response(request_id, 'start', reason)
service_status = _get_display_service_status()
if not service_status.get('active') and not start_service:
return jsonify({
'status': 'error',
'message': 'Display service is not running. Please start the display service or enable "Start Service" option.',
'service_status': service_status,
'data': {'request_id': request_id, 'transport': 'socket', 'socket_error': reason},
}), 400
# start_service means "start it if it is not running", as the UI's
# checkbox says; _ensure_display_service_running leaves a running
# service alone (restarting it cost seconds of blank panel for nothing).
# Either way the display has no socket yet: wait for it, then send the
# request again.
wait = ON_DEMAND_SOCKET_WAIT_RUNNING_SECONDS
service_result = None
if not service_status.get('active'):
service_result = _ensure_display_service_running()
if service_result and not service_result.get('active'):
return jsonify({
'status': 'error',
'message': 'Failed to start display service. Please check service logs or start it manually.',
'service_result': service_result
}), 500
wait = ON_DEMAND_SOCKET_WAIT_SECONDS
elif start_service:
service_result = dict(service_status, started=False)
try:
_send_on_demand_when_listening(request_payload, wait)
except Exception as e: # pylint: disable=broad-except
reason = _socket_failure_reason(e)
if control_client.display_not_listening(e):
message = (f'The display service is running but its control socket did not '
f'answer within {int(wait)} seconds ({reason}). It may still be '
f'starting; try again shortly, or check its logs.')
return _socket_error_response(request_id, 'start', reason, message,
service=service_result)
return _socket_error_response(request_id, 'start', reason, service=service_result)
return _on_demand_started(request_id, resolved_plugin, resolved_mode,
duration, pinned, service_result)
def _on_demand_started(request_id, plugin_id, mode, duration, pinned, service_result):
"""The success answer of /display/on-demand/start."""
response_data = {
'request_id': request_id,
'plugin_id': plugin_id,
'mode': mode,
'duration': duration,
'pinned': pinned,
'service': service_result,
'transport': 'socket',
}
return jsonify({'status': 'success', 'data': response_data})
@api_v3.route('/display/on-demand/stop', methods=['POST'])
def stop_on_demand_display():
"""Request the display controller to stop on-demand mode."""
data = request.get_json(silent=True) or {}
# _coerce_to_bool: bool("false") is True, which stopped the service.
stop_service = _coerce_to_bool(data.get('stop_service', False))
# The running display takes the stop over the control socket and
# resumes normal rotation in place (_clear_on_demand); nothing is
# restarted.
request_id = data.get('request_id') or str(uuid.uuid4())
request_payload = {
'request_id': request_id,
'action': 'stop',
'timestamp': _pkg.time.time()
}
socket_error = None
try:
_send_on_demand(request_payload)
except Exception as e: # pylint: disable=broad-except
socket_error = _socket_failure_reason(e)
if not stop_service:
if control_client.display_not_listening(e):
service_status = _get_display_service_status()
message = ('Display service is not running, so the stop could not be '
'delivered. If it resumes an on-demand session when it starts, '
'stop it then.' if not service_status.get('active') else
f'The display service is running but its control socket did '
f'not answer ({socket_error}). It may still be starting; '
f'try again shortly.')
return _socket_error_response(request_id, 'stop', socket_error, message,
service=service_status)
return _socket_error_response(request_id, 'stop', socket_error)
# Stopping the service ends on-demand too, whatever the display did
# with the request.
service_result = None
if stop_service:
service_result = _stop_display_service()
response_data = {
'request_id': request_id,
'service': service_result,
'transport': 'socket',
}
if socket_error:
response_data['socket_error'] = socket_error
return jsonify({'status': 'success', 'data': response_data})
@api_v3.route('/display/current-status', methods=['GET'])
def get_current_display_status():
"""Return the display mode/plugin currently intended to be shown.
Read from the display's state stream over the control socket when it is
available (``source: "socket"``). Otherwise from what the display
publishes to the shared cache (display_controller._publish_current_mode_state)
when the active mode changes (``source: "cache"``). Unknown (every field
None) when the socket and the heartbeat both say the display is gone
(display_state.display_gone).
"""
snapshot = display_state.read_state()
state = display_state.current_status(snapshot)
source = 'socket'
if state is None:
source = 'cache'
# A stopped display leaves its last answer in the cache, where it
# read as on (is_display_active: true) for the 120 s max_age. With
# no socket and no live heartbeat there is no display behind it.
if not display_state.display_gone(snapshot):
cache = _cache_manager()
# memory_ttl=0: written by the display service; see get_on_demand_status.
state = cache.get('display_current_state', max_age=120, memory_ttl=0)
if state is None:
state = {
'mode': None,
'plugin_id': None,
'last_updated': None,
}
return jsonify({'status': 'success', 'data': dict(state, source=source)})