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.

src/logging_config.py

@@ -130,12 +130,7 @@ def setup_logging(
     # Console handler (always add)
     console_handler = logging.StreamHandler(sys.stdout)
     console_handler.setLevel(level)
-    # Under systemd, tag each line so the journal records the real severity
+    console_handler.setFormatter(formatter)
-    # rather than filing everything as informational. The file handler below
-    # keeps the plain formatter: the prefix is meaningful to journald and noise
-    # anywhere else.
-    console_handler.setFormatter(
-        JournalPriorityFormatter(formatter) if _under_systemd() else formatter)
     root_logger.addHandler(console_handler)
     
     # File handler (if specified)
@@ -150,54 +145,6 @@ def setup_logging(
             sys.stderr.write(f"Warning: Could not set up file logging to {log_file}: {e}\n")
 
 
-#: syslog priorities, which is what systemd parses from a "<N>" prefix on
-#: stdout. Mapped from Python's levels.
-_SYSLOG_PRIORITY = {
-    logging.CRITICAL: 2,   # LOG_CRIT
-    logging.ERROR: 3,      # LOG_ERR
-    logging.WARNING: 4,    # LOG_WARNING
-    logging.INFO: 6,       # LOG_INFO
-    logging.DEBUG: 7,      # LOG_DEBUG
-}
-
-
-class JournalPriorityFormatter(logging.Formatter):
-    """Wraps a formatter, prefixing each line with its syslog priority.
-
-    Under systemd everything this process writes to stdout lands in the journal
-    as PRIORITY=6, whatever the Python level was. Measured on a live rig: 55
-    ERROR lines and 13 WARNING lines in a day, every one of them recorded as
-    informational, so `journalctl -p err -u ledmatrix` returned nothing at all
-    while errors were being logged. Anyone triaging has to grep the message
-    text instead, which is both slower and wrong -- a search for "oom" matches
-    the radar logging "zoom=9".
-
-    systemd reads a leading "<N>" on each line and uses it as the priority
-    (sd-daemon(3)), so this needs no extra dependency. Multi-line records get
-    the prefix on every line, since the journal splits them and an unprefixed
-    continuation would fall back to the default.
-    """
-
-    def __init__(self, inner: logging.Formatter):
-        super().__init__()
-        self._inner = inner
-
-    def format(self, record: logging.LogRecord) -> str:
-        text = self._inner.format(record)
-        prefix = f"<{_SYSLOG_PRIORITY.get(record.levelno, 6)}>"
-        return "\n".join(prefix + line for line in text.split("\n"))
-
-
-def _under_systemd() -> bool:
-    """True when stdout is the journal.
-
-    systemd sets JOURNAL_STREAM for services whose output it captures. Without
-    this check the "<N>" prefixes would show up as literal noise when the
-    program is run from a terminal, in the emulator, or in tests.
-    """
-    return bool(os.environ.get("JOURNAL_STREAM"))
-
-
 class PluginLoggerAdapter(logging.LoggerAdapter):
     """LoggerAdapter that stamps every record with its plugin_id.
 

src/plugin_system/resource_monitor.py

@@ -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

test/test_journald_log_priority.py

@@ -1,101 +0,0 @@
-"""Log lines must reach the journal with their real severity.
-
-Everything this process writes to stdout lands in the journal as PRIORITY=6,
-whatever the Python level was, because journald has no other signal. Measured
-on a live rig over 24 hours: 55 lines containing " - ERROR - " and 13
-containing " - WARNING - ", every one of them recorded as informational. So
-
-    journalctl -p err -u ledmatrix
-
-returned nothing while errors were being logged, and anyone triaging has to
-grep the message text instead. That is slower and it is wrong: a search for
-"oom" also matches the radar logging "zoom=9", which is exactly the false
-positive it produced during this audit.
-
-systemd reads a leading "<N>" on each stdout line and uses it as the priority
-(sd-daemon(3)), so this needs no extra dependency -- and it must only be
-applied when systemd is actually reading, or the prefixes become literal noise
-in a terminal, the emulator, and test output.
-"""
-import logging
-import os
-from unittest.mock import patch
-
-import pytest
-
-from src.logging_config import JournalPriorityFormatter, _SYSLOG_PRIORITY, _under_systemd
-
-
-class _Plain(logging.Formatter):
-    def format(self, record):
-        return record.getMessage()
-
-
-def _record(level, msg="hello"):
-    return logging.LogRecord("t", level, "f.py", 1, msg, None, None)
-
-
-@pytest.mark.parametrize("level,expected", [
-    (logging.CRITICAL, 2),
-    (logging.ERROR, 3),
-    (logging.WARNING, 4),
-    (logging.INFO, 6),
-    (logging.DEBUG, 7),
-])
-def test_each_level_maps_to_its_syslog_priority(level, expected):
-    out = JournalPriorityFormatter(_Plain()).format(_record(level))
-    assert out.startswith(f"<{expected}>"), out
-    assert _SYSLOG_PRIORITY[level] == expected
-
-
-def test_error_and_info_are_distinguishable():
-    """The whole point: journalctl -p err must be able to tell them apart."""
-    fmt = JournalPriorityFormatter(_Plain())
-    assert fmt.format(_record(logging.ERROR))[:3] != fmt.format(_record(logging.INFO))[:3]
-
-
-def test_every_line_of_a_multiline_record_is_tagged():
-    """The journal splits them, and an untagged continuation loses its level.
-
-    A traceback is the case that matters -- it is the most important thing in
-    the log and the longest.
-    """
-    out = JournalPriorityFormatter(_Plain()).format(
-        _record(logging.ERROR, "Traceback:\nline one\nline two"))
-    lines = out.split("\n")
-    assert len(lines) == 3
-    assert all(line.startswith("<3>") for line in lines), lines
-
-
-def test_the_message_survives_intact():
-    out = JournalPriorityFormatter(_Plain()).format(_record(logging.WARNING, "disk full"))
-    assert out == "<4>disk full"
-
-
-def test_an_unknown_level_falls_back_to_info():
-    out = JournalPriorityFormatter(_Plain()).format(_record(25))
-    assert out.startswith("<6>")
-
-
-def test_prefixing_is_off_outside_systemd():
-    """Otherwise a terminal run, the emulator and pytest all show `<6>`."""
-    with patch.dict(os.environ, {}, clear=True):
-        assert not _under_systemd()
-    with patch.dict(os.environ, {"JOURNAL_STREAM": "8:12345"}):
-        assert _under_systemd()
-
-
-def test_setup_uses_the_wrapper_only_under_systemd():
-    from src.logging_config import setup_logging
-
-    for env, expect_wrapped in (({}, False), ({"JOURNAL_STREAM": "8:1"}, True)):
-        with patch.dict(os.environ, env, clear=True):
-            setup_logging()
-            handlers = [h for h in logging.getLogger().handlers
-                        if isinstance(h, logging.StreamHandler)]
-            assert handlers, "no stream handler installed"
-            wrapped = any(isinstance(h.formatter, JournalPriorityFormatter)
-                          for h in handlers)
-            assert wrapped is expect_wrapped, (
-                f"JOURNAL_STREAM={env}: wrapped={wrapped}, expected {expect_wrapped}")
-    logging.getLogger().handlers.clear()

test/test_metrics_cache_unknown_fields.py

@@ -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)