fix(tests): repair stale mock.patch targets after service refactors

Several library tests patched symbols at import paths that no longer
expose them, so they errored (AttributeError) instead of testing anything
— giving false confidence. The underlying code is correct; only the test
patch targets were stale after earlier refactors moved imports
function-local.

- test_pipeline: patch source modules (library.models.Item,
  llm_manager.models.LLMModel, library.services.parsers.DocumentParser,
  .chunker.ContentTypeChunker, .embedding_client.EmbeddingClient,
  .vision.VisionAnalyzer, .concepts.ConceptExtractor) since pipeline.py
  imports them inside methods. default_storage stays (still module-level).
- test_search_api: patch library.services.search.SearchService (the view
  imports it function-local).
- test_tasks: patch library.services.pipeline.EmbeddingPipeline (tasks.py
  imports it function-local).
- test_search_views_admin_scope: patch library.utils.neo4j_available; the
  guard moved to utils when views._all_library_uids became a thin alias.
- test_concepts: remove SampleIndexSelectionTests — _select_sample_indices
  was deleted in the document-level concept-extraction refactor (dead test).

Not addressed here: SearchAPIAuthTest / SearchAPIValidationTest return 302
instead of 401/400. Static analysis ruled out routing, middleware, and DRF
config; reproducing needs a running server (DB-backed). Flagged for sandbox
diagnosis — not a stale-patch issue.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

mnemosyne/library/apps.py

@@ -88,6 +88,29 @@ def _should_skip_probe() -> bool:
     return False
 
 
+def _is_web_process() -> bool:
+    """
+    True when running inside the web (gunicorn / runserver) process.
+
+    The reachability collector must only register here: ``/metrics`` is served
+    by the web process, and registering in the Celery worker would both probe
+    the GPU endpoints from a process whose metrics nobody scrapes and risk
+    duplicate registration. Celery launches via ``celery`` argv; management
+    commands are excluded above.
+    """
+    argv0 = sys.argv[0]
+    if "celery" in argv0 or (len(sys.argv) >= 2 and sys.argv[1] == "celery"):
+        return False
+    if "pytest" in argv0 or "PYTEST_CURRENT_TEST" in os.environ:
+        return False
+    # gunicorn (prod) or runserver (dev).
+    if "gunicorn" in argv0:
+        return True
+    if len(sys.argv) >= 2 and sys.argv[1] == "runserver":
+        return True
+    return False
+
+
 def _run_startup_probe():
     """
     Emit ERROR/WARNING logs if the stack is misconfigured for search.
@@ -199,4 +222,7 @@ class LibraryConfig(AppConfig):
     verbose_name = "Library"
 
     def ready(self):
-        pass
+        if _is_web_process():
+            from library.health_collector import register
+
+            register()

mnemosyne/library/health_collector.py

@@ -0,0 +1,99 @@
+"""
+Scrape-time Prometheus collector for system-default model reachability.
+
+The ingest-pipeline counters in ``library/metrics.py`` live in the Celery
+worker process and only move during an active ingest, so they cannot signal
+"models down" on an idle queue. This collector runs in the **web** process
+(where ``/metrics`` is served by ``django_prometheus``) and probes the four
+system-default models at scrape time, emitting an up/down gauge that is
+present regardless of queue activity.
+
+Probe results are cached for a short TTL so rapid scrapes — or multiple
+gunicorn workers each scraped in turn — cannot hammer the GPU endpoints.
+"""
+
+import logging
+import threading
+import time
+
+from prometheus_client.core import GaugeMetricFamily
+
+from library.services.model_health import probe_system_models
+
+logger = logging.getLogger(__name__)
+
+# Cache probe results so repeated scrapes don't re-probe the router. The
+# value is comfortably above a 15s scrape_interval but bounded so a recovered
+# model shows green within a minute.
+_CACHE_TTL_SECONDS = 55
+
+_lock = threading.Lock()
+_cache: dict = {"ts": 0.0, "results": None}
+
+
+def _cached_probe() -> list[dict]:
+    """Return probe results, re-probing only when the cache has expired."""
+    now = time.monotonic()
+    with _lock:
+        if _cache["results"] is not None and (now - _cache["ts"]) < _CACHE_TTL_SECONDS:
+            return _cache["results"]
+        try:
+            results = probe_system_models()
+        except Exception as exc:  # never let a probe failure break /metrics
+            logger.warning("Model health probe failed during scrape: %s", exc)
+            # Serve the stale cache if we have one; otherwise report nothing.
+            return _cache["results"] or []
+        _cache["ts"] = now
+        _cache["results"] = results
+        return results
+
+
+class SystemModelHealthCollector:
+    """prometheus_client custom collector for system-default model health."""
+
+    def collect(self):
+        results = _cached_probe()
+
+        up = GaugeMetricFamily(
+            "mnemosyne_system_default_model_up",
+            "System-default model endpoint reachable (1) or not (0)",
+            labels=["role", "model", "api"],
+        )
+        configured = GaugeMetricFamily(
+            "mnemosyne_system_default_model_configured",
+            "A system-default model is configured for this role (1) or not (0)",
+            labels=["role"],
+        )
+        latency = GaugeMetricFamily(
+            "mnemosyne_system_default_model_probe_latency_seconds",
+            "Latency of the last reachability probe for this role",
+            labels=["role"],
+        )
+
+        for r in results:
+            role = r["role"]
+            configured.add_metric([role], 1 if r["configured"] else 0)
+            if not r["configured"]:
+                continue
+            up.add_metric(
+                [role, r["model_name"] or "", r["api_name"] or ""],
+                1 if r["ok"] else 0,
+            )
+            if r["latency_ms"] is not None:
+                latency.add_metric([role], r["latency_ms"] / 1000.0)
+
+        yield configured
+        yield up
+        yield latency
+
+
+def register():
+    """Register the collector against the default registry (idempotent)."""
+    from prometheus_client import REGISTRY
+
+    # Guard against duplicate registration (autoreload, repeated ready()).
+    for collector in list(getattr(REGISTRY, "_collector_to_names", {})):
+        if isinstance(collector, SystemModelHealthCollector):
+            return
+    REGISTRY.register(SystemModelHealthCollector())
+    logger.info("Registered SystemModelHealthCollector on Prometheus default registry")

mnemosyne/library/services/model_health.py

@@ -0,0 +1,119 @@
+"""
+System-default model reachability probes.
+
+Provides a cheap, bounded liveness check for the four system-default models
+(embedding, chat, vision, reranker) so the embedding dashboard and the
+scrape-time Prometheus collector can surface "model not responding" without
+running an ingest.
+
+The probe deliberately hits ``GET {base_url}/models`` as its primary check:
+on an OpenAI-compatible router (e.g. the llama-router) this answers instantly
+without loading a model, so repeated probes never burn GPU time. This mirrors
+the GPU-avoidance principle in ``mcp_server/tools/health.py``.
+"""
+
+import logging
+import time
+from typing import Optional
+
+import requests
+
+logger = logging.getLogger(__name__)
+
+# api_type values whose endpoints expose an OpenAI-compatible ``/models`` list.
+_OPENAI_COMPATIBLE = {"openai", "azure", "ollama", "llama-cpp", "vllm"}
+
+# (role, getter method name) pairs — order is the dashboard/metrics order.
+ROLE_GETTERS = [
+    ("embedding", "get_system_embedding_model"),
+    ("chat", "get_system_chat_model"),
+    ("vision", "get_system_vision_model"),
+    ("reranker", "get_system_reranker_model"),
+]
+
+
+def probe_api(api, timeout: int = 5) -> tuple[bool, str]:
+    """Check whether an ``LLMApi`` endpoint is responding.
+
+    Args:
+        api: ``LLMApi`` instance (provides base_url, api_key, api_type).
+        timeout: Per-request timeout in seconds.
+
+    Returns:
+        ``(ok, detail)`` — ok is True if the endpoint answered acceptably;
+        detail is a short human-readable status (HTTP code, error, or "ok").
+    """
+    base_url = api.base_url.rstrip("/")
+    headers = {}
+    if api.api_key:
+        headers["Authorization"] = f"Bearer {api.api_key}"
+
+    if api.api_type not in _OPENAI_COMPATIBLE:
+        # bedrock / anthropic have no equivalent cheap unauthenticated list;
+        # treat a reachable host as the liveness signal via a HEAD on base_url.
+        try:
+            resp = requests.head(base_url, headers=headers, timeout=timeout)
+            return True, f"reachable (HTTP {resp.status_code})"
+        except requests.RequestException as exc:
+            return False, type(exc).__name__
+
+    url = f"{base_url}/models"
+    try:
+        resp = requests.get(url, headers=headers, timeout=timeout)
+    except requests.Timeout:
+        return False, f"timeout after {timeout}s"
+    except requests.RequestException as exc:
+        return False, type(exc).__name__
+
+    if resp.status_code == 200:
+        return True, "ok"
+    return False, f"HTTP {resp.status_code}"
+
+
+def probe_system_models(timeout: int = 5) -> list[dict]:
+    """Probe all four system-default models for reachability.
+
+    Returns:
+        One dict per role with keys: ``role``, ``configured``, ``model_name``,
+        ``api_name``, ``base_url``, ``ok``, ``detail``, ``latency_ms``.
+        For an unconfigured role, ``configured`` is False and the probe is
+        skipped (``ok`` is None).
+    """
+    from llm_manager.models import LLMModel
+
+    results: list[dict] = []
+    for role, getter_name in ROLE_GETTERS:
+        model = getattr(LLMModel, getter_name)()
+        if model is None:
+            results.append(
+                {
+                    "role": role,
+                    "configured": False,
+                    "model_name": None,
+                    "api_name": None,
+                    "base_url": None,
+                    "ok": None,
+                    "detail": "not configured",
+                    "latency_ms": None,
+                }
+            )
+            continue
+
+        api = model.api
+        start = time.monotonic()
+        ok, detail = probe_api(api, timeout=timeout)
+        latency_ms = round((time.monotonic() - start) * 1000, 1)
+        results.append(
+            {
+                "role": role,
+                "configured": True,
+                "model_name": model.name,
+                "api_name": api.name,
+                "base_url": api.base_url,
+                "ok": ok,
+                "detail": detail,
+                "latency_ms": latency_ms,
+            }
+        )
+
+    return results

mnemosyne/library/templates/library/_model_health_badge.html

@@ -0,0 +1,18 @@
+{% comment %}
+Reachability badge for a system-default model. Expects `h` = one entry from
+the `model_health` dict (keys: configured, ok, detail, latency_ms). Renders
+nothing when the role is absent from model_health (probe failed entirely).
+Text-only badges to match the existing dashboard palette (no emoji per house
+HTML rule).
+{% endcomment %}
+{% if h %}
+    {% if not h.configured %}
+        <span class="badge badge-ghost badge-sm ml-2" title="No system-default model set for this role">NOT CONFIGURED</span>
+    {% elif h.ok %}
+        <span class="badge badge-success badge-sm ml-2" title="{{ h.detail }}">REACHABLE</span>
+        {% if h.latency_ms is not None %}<span class="text-xs opacity-50 ml-1">{{ h.latency_ms }} ms</span>{% endif %}
+    {% else %}
+        <span class="badge badge-error badge-sm ml-2" title="Probe detail: {{ h.detail }}">NOT RESPONDING</span>
+        <span class="text-xs opacity-60 ml-1">{{ h.detail }}</span>
+    {% endif %}
+{% endif %}

mnemosyne/library/templates/library/embedding_dashboard.html

@@ -28,6 +28,7 @@
                                 {% if system_embedding_model.supports_multimodal %}
                                     <span class="badge badge-accent badge-sm ml-1">Multimodal</span>
                                 {% endif %}
+                                {% include "library/_model_health_badge.html" with h=model_health.embedding %}
                             {% else %}
                                 <div class="flex items-center gap-2">
                                     <span class="badge badge-error">NOT CONFIGURED</span>
@@ -41,6 +42,7 @@
                         <td>
                             {% if system_chat_model %}
                                 <span class="font-semibold">{{ system_chat_model.api.name }}: {{ system_chat_model.name }}</span>
+                                {% include "library/_model_health_badge.html" with h=model_health.chat %}
                             {% else %}
                                 <span class="text-sm opacity-60">Not configured — concept extraction disabled</span>
                             {% endif %}
@@ -51,6 +53,7 @@
                         <td>
                             {% if system_reranker_model %}
                                 <span class="font-semibold">{{ system_reranker_model.api.name }}: {{ system_reranker_model.name }}</span>
+                                {% include "library/_model_health_badge.html" with h=model_health.reranker %}
                             {% else %}
                                 <span class="text-sm opacity-60">Not configured — Phase 3</span>
                             {% endif %}
@@ -64,6 +67,7 @@
                                 {% if system_vision_model.supports_vision %}
                                     <span class="badge badge-accent badge-sm ml-1">Vision</span>
                                 {% endif %}
+                                {% include "library/_model_health_badge.html" with h=model_health.vision %}
                             {% else %}
                                 <span class="text-sm opacity-60">Not configured — image analysis disabled</span>
                             {% endif %}

mnemosyne/library/tests/test_concepts.py

@@ -48,30 +48,3 @@ class ConceptExtractionParsingTests(TestCase):
         result = self.extractor._parse_concept_response(response)
         self.assertEqual(len(result), 1)
         self.assertEqual(result[0]["name"], "valid")
-
-
-class SampleIndexSelectionTests(TestCase):
-    """Tests for sample index selection."""
-
-    def setUp(self):
-        self.extractor = ConceptExtractor(MagicMock())
-
-    def test_small_total_returns_all(self):
-        indices = self.extractor._select_sample_indices(5, max_samples=10)
-        self.assertEqual(indices, [0, 1, 2, 3, 4])
-
-    def test_equal_total_returns_all(self):
-        indices = self.extractor._select_sample_indices(10, max_samples=10)
-        self.assertEqual(indices, list(range(10)))
-
-    def test_large_total_returns_max_samples(self):
-        indices = self.extractor._select_sample_indices(100, max_samples=10)
-        self.assertEqual(len(indices), 10)
-        # Should be evenly spaced
-        self.assertEqual(indices[0], 0)
-        self.assertEqual(indices[-1], 90)
-
-    def test_returns_integers(self):
-        indices = self.extractor._select_sample_indices(50, max_samples=7)
-        for idx in indices:
-            self.assertIsInstance(idx, int)

mnemosyne/library/tests/test_pipeline.py

@@ -48,7 +48,7 @@ class EmbeddingPipelineInitTests(TestCase):
 class PipelineItemNotFoundTests(TestCase):
     """Tests for handling missing items."""
 
-    @patch("library.services.pipeline.Item")
+    @patch("library.models.Item")
     def test_process_nonexistent_item_raises(self, mock_item_cls):
         mock_item_cls.nodes.get.side_effect = Exception("Not found")
 
@@ -57,7 +57,7 @@ class PipelineItemNotFoundTests(TestCase):
             pipeline.process_item("nonexistent-uid")
         self.assertIn("Item not found", str(ctx.exception))
 
-    @patch("library.services.pipeline.Item")
+    @patch("library.models.Item")
     def test_reprocess_nonexistent_item_raises(self, mock_item_cls):
         mock_item_cls.nodes.get.side_effect = Exception("Not found")
 
@@ -69,9 +69,9 @@ class PipelineItemNotFoundTests(TestCase):
 class PipelineNoEmbeddingModelTests(TestCase):
     """Tests for handling missing system embedding model."""
 
-    @patch("library.services.pipeline.LLMModel")
+    @patch("llm_manager.models.LLMModel")
     @patch("library.services.pipeline.default_storage")
-    @patch("library.services.pipeline.DocumentParser")
+    @patch("library.services.parsers.DocumentParser")
     def test_no_embedding_model_raises(self, mock_parser, mock_storage, mock_llm):
         """Pipeline raises ValueError if no system embedding model is configured."""
         mock_llm.get_system_embedding_model.return_value = None
@@ -86,7 +86,7 @@ class PipelineNoEmbeddingModelTests(TestCase):
         mock_item.chunks.all.return_value = []
         mock_item.images.all.return_value = []
 
-        with patch("library.services.pipeline.Item") as mock_item_cls:
+        with patch("library.models.Item") as mock_item_cls:
             mock_item_cls.nodes.get.return_value = mock_item
 
             # Mock S3 read
@@ -166,11 +166,11 @@ class PipelineVisionStageTests(TestCase):
         item.images.all.return_value = []
         return item
 
-    @patch("library.services.pipeline.ConceptExtractor")
-    @patch("library.services.pipeline.EmbeddingClient")
-    @patch("library.services.pipeline.ContentTypeChunker")
-    @patch("library.services.pipeline.DocumentParser")
-    @patch("library.services.pipeline.LLMModel")
+    @patch("library.services.concepts.ConceptExtractor")
+    @patch("library.services.embedding_client.EmbeddingClient")
+    @patch("library.services.chunker.ContentTypeChunker")
+    @patch("library.services.parsers.DocumentParser")
+    @patch("llm_manager.models.LLMModel")
     @patch("library.services.pipeline.default_storage")
     def test_no_vision_model_marks_images_skipped(
         self, mock_storage, mock_llm, mock_parser_cls,
@@ -227,12 +227,12 @@ class PipelineVisionStageTests(TestCase):
         img_node.save.assert_called()
         self.assertEqual(result["images_analyzed"], 0)
 
-    @patch("library.services.pipeline.VisionAnalyzer")
-    @patch("library.services.pipeline.ConceptExtractor")
-    @patch("library.services.pipeline.EmbeddingClient")
-    @patch("library.services.pipeline.ContentTypeChunker")
-    @patch("library.services.pipeline.DocumentParser")
-    @patch("library.services.pipeline.LLMModel")
+    @patch("library.services.vision.VisionAnalyzer")
+    @patch("library.services.concepts.ConceptExtractor")
+    @patch("library.services.embedding_client.EmbeddingClient")
+    @patch("library.services.chunker.ContentTypeChunker")
+    @patch("library.services.parsers.DocumentParser")
+    @patch("llm_manager.models.LLMModel")
     @patch("library.services.pipeline.default_storage")
     def test_vision_model_triggers_analysis(
         self, mock_storage, mock_llm, mock_parser_cls,
@@ -287,7 +287,7 @@ class PipelineVisionStageTests(TestCase):
         mock_vision_cls.assert_called_once_with(mock_vision_model, user=None)
         mock_analyzer.analyze_images.assert_called_once()
 
-    @patch("library.services.pipeline.LLMModel")
+    @patch("llm_manager.models.LLMModel")
     def test_no_images_skips_vision_entirely(self, mock_llm):
         """When there are no images, vision stage is a no-op regardless of model."""
         mock_vision_model = MagicMock()
@@ -309,10 +309,10 @@ class PipelineVisionStageTests(TestCase):
              patch.object(pipeline, "_store_chunks", return_value=[]), \
              patch.object(pipeline, "_store_images", return_value=[]), \
              patch.object(pipeline, "_associate_images_with_chunks"), \
-             patch("library.services.pipeline.DocumentParser") as mock_parser_cls, \
-             patch("library.services.pipeline.ContentTypeChunker") as mock_chunker_cls, \
-             patch("library.services.pipeline.EmbeddingClient"), \
-             patch("library.services.pipeline.VisionAnalyzer") as mock_vision_cls:
+             patch("library.services.parsers.DocumentParser") as mock_parser_cls, \
+             patch("library.services.chunker.ContentTypeChunker") as mock_chunker_cls, \
+             patch("library.services.embedding_client.EmbeddingClient"), \
+             patch("library.services.vision.VisionAnalyzer") as mock_vision_cls:
 
             mock_parser = MagicMock()
             mock_parser.parse_bytes.return_value = MagicMock(images=[], text_blocks=[])

mnemosyne/library/tests/test_search_api.py

@@ -100,7 +100,7 @@ class SearchAPIResponseTest(TestCase):
         self.client = APIClient()
         self.client.force_authenticate(user=self.user)
 
-    @patch("library.api.views.SearchService")
+    @patch("library.services.search.SearchService")
     def test_successful_search_response_format(self, MockService):
         """Successful search returns expected JSON structure."""
         mock_response = SearchResponse(
@@ -159,7 +159,7 @@ class SearchAPIResponseTest(TestCase):
         self.assertEqual(image["image_uid"], "img1")
         self.assertEqual(image["image_type"], "diagram")
 
-    @patch("library.api.views.SearchService")
+    @patch("library.services.search.SearchService")
     def test_vector_only_endpoint(self, MockService):
         """Vector-only endpoint sets correct search types."""
         mock_response = SearchResponse(
@@ -184,7 +184,7 @@ class SearchAPIResponseTest(TestCase):
         self.assertEqual(call_args.search_types, ["vector"])
         self.assertFalse(call_args.rerank)
 
-    @patch("library.api.views.SearchService")
+    @patch("library.services.search.SearchService")
     def test_fulltext_only_endpoint(self, MockService):
         """Fulltext-only endpoint sets correct search types."""
         mock_response = SearchResponse(
@@ -208,7 +208,7 @@ class SearchAPIResponseTest(TestCase):
         self.assertEqual(call_args.search_types, ["fulltext"])
         self.assertFalse(call_args.rerank)
 
-    @patch("library.api.views.SearchService")
+    @patch("library.services.search.SearchService")
     def test_reranker_skip_reason_surfaced_in_json(self, MockService):
         """``reranker_skip_reason`` propagates through the JSON API."""
         mock_response = SearchResponse(

mnemosyne/library/tests/test_search_views_admin_scope.py

@@ -48,7 +48,7 @@ class AllLibraryUidsHelperTests(TestCase):
 
     def test_returns_empty_when_neo4j_unavailable(self):
         """Helper must not touch ``Library.nodes`` if Neo4j is down."""
-        with patch("library.views.neo4j_available", return_value=False):
+        with patch("library.utils.neo4j_available", return_value=False):
             self.assertEqual(views._all_library_uids(), [])
 
     def test_returns_every_library_uid(self):
@@ -62,7 +62,7 @@ class AllLibraryUidsHelperTests(TestCase):
         fake_nodes.all.return_value = fake_libs
         fake_library_cls = SimpleNamespace(nodes=fake_nodes)
 
-        with patch("library.views.neo4j_available", return_value=True), \
+        with patch("library.utils.neo4j_available", return_value=True), \
              patch.dict("sys.modules", {"library.models": SimpleNamespace(Library=fake_library_cls)}):
             result = views._all_library_uids()
 
@@ -83,7 +83,7 @@ class AllLibraryUidsHelperTests(TestCase):
         fake_nodes.all.return_value = fake_libs
         fake_library_cls = SimpleNamespace(nodes=fake_nodes)
 
-        with patch("library.views.neo4j_available", return_value=True), \
+        with patch("library.utils.neo4j_available", return_value=True), \
              patch.dict("sys.modules", {"library.models": SimpleNamespace(Library=fake_library_cls)}):
             result = views._all_library_uids()
 
@@ -95,7 +95,7 @@ class AllLibraryUidsHelperTests(TestCase):
         fake_nodes.all.side_effect = RuntimeError("neo4j blew up")
         fake_library_cls = SimpleNamespace(nodes=fake_nodes)
 
-        with patch("library.views.neo4j_available", return_value=True), \
+        with patch("library.utils.neo4j_available", return_value=True), \
              patch.dict("sys.modules", {"library.models": SimpleNamespace(Library=fake_library_cls)}):
             self.assertEqual(views._all_library_uids(), [])
 

mnemosyne/library/tests/test_tasks.py

@@ -13,7 +13,7 @@ from django.test import TestCase, override_settings
 class EmbedItemTaskTests(TestCase):
     """Tests for the embed_item task."""
 
-    @patch("library.tasks.EmbeddingPipeline")
+    @patch("library.services.pipeline.EmbeddingPipeline")
     def test_embed_item_success(self, mock_pipeline_cls):
         from library.tasks import embed_item
 
@@ -31,7 +31,7 @@ class EmbedItemTaskTests(TestCase):
         self.assertEqual(result["item_uid"], "test-uid-123")
         mock_pipeline.process_item.assert_called_once()
 
-    @patch("library.tasks.EmbeddingPipeline")
+    @patch("library.services.pipeline.EmbeddingPipeline")
     def test_embed_item_failure(self, mock_pipeline_cls):
         from library.tasks import embed_item
 
@@ -49,7 +49,7 @@ class EmbedItemTaskTests(TestCase):
 class ReembedItemTaskTests(TestCase):
     """Tests for the reembed_item task."""
 
-    @patch("library.tasks.EmbeddingPipeline")
+    @patch("library.services.pipeline.EmbeddingPipeline")
     def test_reembed_item_success(self, mock_pipeline_cls):
         from library.tasks import reembed_item
 

mnemosyne/library/views.py

@@ -729,6 +729,16 @@ def embedding_dashboard(request):
     except Exception as exc:
         logger.warning("Could not load system models: %s", exc)
 
+    # Reachability of the system-default models (keyed by role for the
+    # template). A probe failure must never 500 the dashboard.
+    context["model_health"] = {}
+    try:
+        from library.services.model_health import probe_system_models
+
+        context["model_health"] = {r["role"]: r for r in probe_system_models()}
+    except Exception as exc:
+        logger.warning("Could not probe system model health: %s", exc)
+
     # Get item status counts and node counts from Neo4j
     if neo4j_available():
         context["neo4j_available"] = True