Compare commits

..
Author SHA1 Message Date
ChuckBuilds 29f1c68bea fix(plugins): one bad metrics cache entry should not stop every plugin
Caught live on a rig: every plugin failing, once each, continuously.

    ERROR - src.plugin_system.plugin_manager - plugin geochron operation failed:
    ResourceMetrics.__init__() got an unexpected keyword argument
    'consecutive_failures'

    ERROR - ... plugin text-display operation failed: ...
    ERROR - ... plugin news operation failed: ...
    ERROR - ... plugin odds-ticker operation failed: ...

with /api/v3/health reporting plugin_system: not_initialized while the display
process itself kept running and updating the panel.

`consecutive_failures` is a plugin_health field, not a metrics one.
get_metrics() does ResourceMetrics(**cached), which raises TypeError on a
single unrecognised key, and that exception escapes into plugin_manager and is
reported per plugin. One malformed cache entry takes the whole plugin system
down.

How a health-shaped record came to sit under a plugin_metrics key on that
machine is not established, and I could not finish the diagnosis: the rig went
back into its EIO failure mode partway through -- SSH resetting pre-banner,
systemctl unexecutable -- while the web API kept answering from RAM. Checked
before that: the cache files on disk are correctly shaped and separate, and
CacheManager.get() returns the right record for each key, so it is not a live
key collision. A restored backup mixing two machines' caches is the likeliest
explanation, and that rig had one restored onto it.

Either way the loader should not be brittle enough for the answer to matter.
plugin_health already repairs its records field by field rather than trusting
what is on disk; this does the same. Known fields are kept, unknown ones are
dropped and named once in the log so a genuine schema change stays visible
rather than being silently discarded, and a non-mapping entry no longer raises.

Keeping the known fields matters: discarding the record wholesale would throw
away real call counts and timings because of an unrelated stray key.

Mutation-checked: restoring ResourceMetrics(**cached) fails 6 checks, dropping
the whole record fails the field-preservation check, and dropping unknown
fields silently fails the logging check. 28 tests pass across the resource
monitor and plugin health suites.
2026-08-20 03:26:20 -04:00
7 changed files with 157 additions and 147 deletions
Binary file not shown.

Before

Width:  |  Height:  |  Size: 467 B

+46 -2
View File
@@ -9,7 +9,7 @@ import time
import logging
import threading
from typing import Dict, Optional, Any, Callable
from dataclasses import dataclass, field
from dataclasses import dataclass, field, fields
try:
import psutil
@@ -102,6 +102,50 @@ class PluginResourceMonitor:
"psutil not available - resource monitoring will be limited to execution time only"
)
def _metrics_from_cache(self, plugin_id: str, cached: Any) -> "ResourceMetrics":
"""Build metrics from a cached record, ignoring anything unrecognised.
ResourceMetrics(**cached) raises TypeError on a single unexpected key,
and that exception escapes into plugin_manager, which reports it as
"plugin <id> operation failed". Every plugin fails, and the plugin
system never finishes initialising.
Seen on a live rig: every plugin failing with
ResourceMetrics.__init__() got an unexpected keyword argument
'consecutive_failures'
which is a plugin_health field, not a metrics one. How a health-shaped
record came to sit under a plugin_metrics key on that machine is not
established -- a restored backup that mixed two machines' caches is the
likeliest explanation -- but the loader should not be brittle enough for
it to matter. plugin_health already repairs its records field by field
rather than trusting whatever is on disk; this does the same.
Unknown keys are dropped and named once, so a genuine schema change is
visible in the log instead of silently discarded.
"""
if not isinstance(cached, dict):
self.logger.warning(
"Ignoring cached metrics for %s: expected a mapping, got %s",
plugin_id, type(cached).__name__)
return ResourceMetrics()
known = {f.name for f in fields(ResourceMetrics)}
unknown = sorted(set(cached) - known)
if unknown:
self.logger.warning(
"Dropping unrecognised field(s) from cached metrics for %s: %s",
plugin_id, ", ".join(unknown))
usable = {k: v for k, v in cached.items() if k in known}
try:
return ResourceMetrics(**usable)
except (TypeError, ValueError) as e:
self.logger.warning(
"Cached metrics for %s unusable (%s); starting fresh",
plugin_id, e)
return ResourceMetrics()
def _get_metrics_key(self, plugin_id: str) -> str:
"""Get cache key for plugin metrics."""
return f"plugin_metrics:{plugin_id}"
@@ -126,7 +170,7 @@ class PluginResourceMonitor:
cache_key, max_age=None, memory_ttl=0 if force_reload else None
)
if cached:
metrics = ResourceMetrics(**cached)
metrics = self._metrics_from_cache(plugin_id, cached)
else:
metrics = ResourceMetrics()
self._metrics[plugin_id] = metrics
+1 -34
View File
@@ -143,12 +143,6 @@ def mask_secret_fields(config: Dict[str, Any], schema_properties: Dict[str, Any]
return result
#: What a masked secret looks like on the wire. Named because the write path
#: has to recognise it coming back: a client that renders the mask and posts
#: it unchanged must not store the mask as if it were the secret.
SECRET_MASK = '\u2022' * 8
def mask_all_secret_values(config: Dict[str, Any]) -> Dict[str, Any]:
"""Blanket-mask every non-empty value in a secrets config dict.
@@ -167,7 +161,7 @@ def mask_all_secret_values(config: Dict[str, Any]) -> Dict[str, Any]:
if isinstance(v, dict):
masked[k] = mask_all_secret_values(v)
elif v not in (None, '') and not (isinstance(v, str) and v.startswith('YOUR_')):
masked[k] = SECRET_MASK
masked[k] = '••••••••'
else:
masked[k] = v
return masked
@@ -195,30 +189,3 @@ def remove_empty_secrets(secrets: Dict[str, Any]) -> Dict[str, Any]:
elif v is not None and not (isinstance(v, str) and v.strip() == ''):
result[k] = v
return result
def strip_masked_values(secrets: Dict[str, Any]) -> Dict[str, Any]:
"""Remove values a client echoed back rather than changed.
The counterpart to :func:`mask_all_secret_values`. A client that GETs the
masked secrets, edits one field and POSTs the whole object back is sending
``SECRET_MASK`` for every field it did not touch. Storing those would
replace each untouched credential with eight bullet characters.
Drops the mask and, like :func:`remove_empty_secrets`, blank values -- so
the caller can merge the result onto what is already stored and have
"unchanged" mean unchanged. Empty nested dicts are pruned.
"""
result: Dict[str, Any] = {}
for k, v in secrets.items():
if isinstance(v, dict):
nested = strip_masked_values(v)
if nested:
result[k] = nested
elif v is None:
continue
elif isinstance(v, str) and (v.strip() == '' or v == SECRET_MASK):
continue
else:
result[k] = v
return result
+100
View File
@@ -0,0 +1,100 @@
"""A malformed metrics cache entry must not take every plugin down with it.
`ResourceMetrics(**cached)` raises TypeError on a single unexpected key, and
that exception escapes into plugin_manager, which reports it per plugin as
"plugin <id> operation failed". Every plugin fails and the plugin system never
finishes initialising -- the health endpoint reports
`plugin_system: not_initialized` while the display itself keeps running.
Seen on a live rig, once per plugin, continuously:
ERROR - src.plugin_system.plugin_manager - plugin geochron operation failed:
ResourceMetrics.__init__() got an unexpected keyword argument
'consecutive_failures'
`consecutive_failures` belongs to plugin_health, not to metrics. How a
health-shaped record came to sit under a plugin_metrics key on that machine is
not established -- a restored backup that mixed two machines' caches is the
likeliest explanation, and the same rig had one restored onto it -- but a
loader that turns one bad cache entry into a total outage is the part worth
fixing. plugin_health already repairs its own records field by field rather
than trusting what is on disk.
"""
import logging
from dataclasses import fields
from unittest.mock import MagicMock
import pytest
from src.plugin_system.resource_monitor import PluginResourceMonitor, ResourceMetrics
class _Cache:
def __init__(self, payload=None):
self.payload = payload
def get(self, key, max_age=None, memory_ttl=None, **kwargs):
return self.payload
def set(self, key, data, ttl=None, **kwargs):
pass
def _monitor(payload):
m = PluginResourceMonitor(cache_manager=_Cache(payload))
m.logger = logging.getLogger("test")
return m
#: What the rig actually had under the metrics key.
HEALTH_SHAPED = {
"consecutive_failures": 0, "circuit_state": "closed",
"circuit_opened_time": None, "half_open_start_time": None,
"last_error": None, "last_failure_time": None,
"last_success_time": 1_700_000_000.0, "total_failures": 0,
"total_successes": 42,
}
def test_a_health_record_under_the_metrics_key_does_not_raise():
"""The exact failure: it must degrade, not take the plugin system down."""
monitor = _monitor(HEALTH_SHAPED)
metrics = monitor.get_metrics(" plugin-a".strip())
assert isinstance(metrics, ResourceMetrics)
def test_recognised_fields_in_a_mixed_record_are_kept():
"""Dropping the record wholesale would lose real history unnecessarily."""
mixed = dict(HEALTH_SHAPED, call_count=7, memory_mb=12.5)
metrics = _monitor(mixed).get_metrics("plugin-b")
assert metrics.call_count == 7
assert metrics.memory_mb == 12.5
def test_a_clean_record_still_loads_unchanged():
clean = {f.name: 3 for f in fields(ResourceMetrics)}
metrics = _monitor(clean).get_metrics("plugin-c")
for name in (f.name for f in fields(ResourceMetrics)):
assert getattr(metrics, name) == 3
def test_unknown_fields_are_named_in_the_log(caplog):
"""Silently discarding them would hide a real schema change."""
with caplog.at_level(logging.WARNING):
_monitor(HEALTH_SHAPED).get_metrics("plugin-d")
# getMessage(), not .message: the latter is only populated once a handler
# formats the record, so the obvious spelling silently never matches.
assert any("consecutive_failures" in r.getMessage() for r in caplog.records), \
caplog.text
@pytest.mark.parametrize("payload", ["a string", 42, ["a", "list"]])
def test_a_non_mapping_cache_entry_does_not_raise(payload):
metrics = _monitor(payload).get_metrics("plugin-e")
assert isinstance(metrics, ResourceMetrics)
def test_values_of_the_wrong_type_do_not_raise():
"""A dataclass will accept these, but a later float() on them would not."""
metrics = _monitor({"call_count": "not a number"}).get_metrics("plugin-f")
assert isinstance(metrics, ResourceMetrics)
@@ -1,82 +0,0 @@
"""GET /config/secrets must not hand out credentials, and the client's
read-modify-write cycle must not destroy them.
This interface has no authentication. The endpoint returned the whole
config_secrets.json to anyone who could reach the port; on one rig that was a
40-character GitHub token, a 183-character Home Assistant token and three API
keys. Masking it alone is not enough: the only client fetches every secret,
edits one field and posts all of them back, so the write path has to treat an
echoed mask as "unchanged".
"""
import json
import sys
from pathlib import Path
sys.path.insert(0, str(Path(__file__).parent))
from test_api_v3_secret_roundtrip import env, _on_disk # noqa: F401,E402
from src.web_interface.secret_helpers import SECRET_MASK # noqa: E402
STORED = {
"github": {"api_token": "ghp_" + "x" * 36},
"ledmatrix-weather": {"api_key": "w" * 32},
"incoming-packages": {"ha_token": "h" * 183},
"unset-plugin": {"api_key": ""},
"placeholder-plugin": {"api_key": "YOUR_API_KEY_HERE"},
}
def _seed(env):
env.secrets_file.write_text(json.dumps(STORED))
def _get(env):
r = env.client.get("/api/v3/config/secrets")
assert r.status_code == 200, r.get_data(as_text=True)[:200]
return r.get_json()["data"]
def test_no_credential_leaves_the_process(env):
_seed(env)
body = json.dumps(_get(env))
for secret in ("ghp_" + "x" * 36, "w" * 32, "h" * 183):
assert secret not in body, "endpoint returned a stored credential"
def test_set_and_unset_remain_distinguishable(env):
_seed(env)
data = _get(env)
assert data["github"]["api_token"] == SECRET_MASK
assert data["unset-plugin"]["api_key"] == ""
assert data["placeholder-plugin"]["api_key"] == "YOUR_API_KEY_HERE"
def test_the_clients_read_modify_write_preserves_every_other_secret(env):
"""What the GitHub-token save button actually does."""
_seed(env)
secrets = _get(env) # everything arrives masked
secrets["github"]["api_token"] = "ghp_" + "n" * 36 # user changes one
r = env.client.post("/api/v3/config/raw/secrets", json=secrets)
assert r.status_code == 200, r.get_data(as_text=True)[:200]
on_disk = _on_disk(env.secrets_file)
assert on_disk["github"]["api_token"] == "ghp_" + "n" * 36, "new token not saved"
assert on_disk["ledmatrix-weather"]["api_key"] == "w" * 32
assert on_disk["incoming-packages"]["ha_token"] == "h" * 183
def test_a_mask_echoed_back_is_never_stored(env):
_seed(env)
env.client.post("/api/v3/config/raw/secrets", json=_get(env))
on_disk = _on_disk(env.secrets_file)
assert SECRET_MASK not in json.dumps(on_disk), "the mask was stored as a secret"
assert on_disk["github"]["api_token"] == "ghp_" + "x" * 36
def test_a_brand_new_secret_can_still_be_added(env):
_seed(env)
env.client.post("/api/v3/config/raw/secrets",
json={"new-plugin": {"api_key": "brand-new"}})
on_disk = _on_disk(env.secrets_file)
assert on_disk["new-plugin"]["api_key"] == "brand-new"
assert on_disk["github"]["api_token"] == "ghp_" + "x" * 36
+4 -21
View File
@@ -21,8 +21,7 @@ logger = logging.getLogger(__name__)
# Import new infrastructure
from src.web_interface.api_helpers import success_response, error_response, validate_request_json
from src.web_interface.errors import ErrorCode
from src.web_interface.secret_helpers import (find_secret_fields, mask_all_secret_values,
separate_secrets, strip_masked_values)
from src.web_interface.secret_helpers import find_secret_fields, separate_secrets
from src.web_interface.error_handler import describe_exception, redact_text
from src.plugin_system.operation_types import OperationType
from src.web_interface.validators import (
@@ -1334,12 +1333,7 @@ def get_secrets_config():
return jsonify({'status': 'error', 'message': 'Config manager not initialized'}), 500
config = api_v3.config_manager.get_raw_file_content('secrets')
# This interface has no authentication, and this file is nothing but
# credentials. It was handing all of them to anyone who could reach
# the port. Values are masked; empty and YOUR_* placeholders are left
# alone so a client can still tell "set" from "not set".
return jsonify({'status': 'success',
'data': mask_all_secret_values(config)})
return jsonify({'status': 'success', 'data': config})
except Exception as e:
logger.error('Unhandled exception', exc_info=True)
return jsonify({'status': 'error', 'message': 'An error occurred; see logs for details', 'details': describe_exception(e)}), 500
@@ -1401,19 +1395,8 @@ def save_raw_secrets_config():
if not data:
return jsonify({'status': 'error', 'message': 'No data provided'}), 400
# The GET above masks what it returns, and this endpoint's only client
# reads the whole file, edits one field and posts all of it back. So
# most of what arrives here is the mask, echoed rather than changed --
# storing it verbatim would replace every untouched credential with
# eight bullets. Strip those, then merge onto what is already stored,
# which makes "unchanged" mean unchanged.
#
# The cost is that a secret can no longer be cleared by blanking it.
# That needs its own affordance; a control that erases credentials as
# a side effect of saving an unrelated one is not it.
current = api_v3.config_manager.get_raw_file_content('secrets') or {}
merged = deep_merge(current, strip_masked_values(data))
api_v3.config_manager.save_raw_file_content('secrets', merged)
# Save the secrets config
api_v3.config_manager.save_raw_file_content('secrets', data)
# Reload GitHub token in plugin store manager if it exists
if api_v3.plugin_store_manager:
+6 -8
View File
@@ -4622,17 +4622,15 @@ window.loadGithubToken = function() {
// Handle empty data (secrets file doesn't exist) - API returns {} in this case
const secrets = data.data || {};
const token = secrets.github?.api_token || '';
const configured = token && token !== 'YOUR_GITHUB_PERSONAL_ACCESS_TOKEN';
if (input) {
// The endpoint masks what it returns, so this never holds
// the real token -- and the field is deliberately left
// empty rather than filled with the mask, which would be
// saved verbatim the next time the user pressed Save.
input.value = '';
if (configured) {
showNotification('A GitHub token is saved. Enter a new one to replace it.', 'success');
if (token && token !== 'YOUR_GITHUB_PERSONAL_ACCESS_TOKEN') {
// Token exists and is valid
input.value = token;
showNotification('GitHub token loaded successfully', 'success');
} else {
// No token configured or placeholder value
input.value = '';
showNotification('No GitHub token configured. Enter a new token to save.', 'info');
}
}