fix(plugins): one bad metrics cache entry should not stop every plugin

src/plugin_system/resource_monitor.py

@@ -9,7 +9,7 @@
 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 @@ def __init__(self, cache_manager, enable_monitoring: bool = True):
                 "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 @@ def get_metrics(self, plugin_id: str, force_reload: bool = False) -> ResourceMet
                     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_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)