refactor(usage): extract indexing metering helper; address review round 2

Round-2 claude-review findings:

- 🟡 Base-class recursion invariant: documented on embed_with_usage /
  embed_batch_with_usage that a provider overriding embed()/embed_batch() to
  delegate to the *_with_usage variant MUST also override that variant, or the
  two recurse. (No recursion today; the shipped providers pair the overrides.)
- 🟡 Processor metering had no unit test: extracted the two-event recording
  into a module-level record_indexing_usage() helper and added
  tests/unit/test_processor_metering.py (value mapping, flag/zero-chunk no-ops,
  best-effort failure swallowed).
- 🟡 SonarQube hotspots (python:S5332) were 3 http:// URLs in the new test
  fixtures (mock hosts, never contacted) blocking the quality gate
  (new_security_hotspots_reviewed). Switched them to https:// so no hotspot is
  raised.
- 🟢 Zero-chunk guard: record_indexing_usage() no-ops when chunk_count == 0, so
  an empty document no longer writes zero-value billing rows.

Deferred (stated on the PR): Mistral x.index-or-0 sort key (pre-existing,
equivalent), CHANGELOG note for the Ollama /api/embed switch (CHANGELOG is
commitizen-generated from commit bodies, which document it), class-var
query_token_count (safe under the per-request instance pattern).

Deck #67.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

tests/unit/providers/test_gateway_provider.py

@@ -331,8 +331,9 @@ def test_trailing_slash_base_url_normalized():
 async def test_gateway_embed_with_usage_forwards_after_bearer(monkeypatch):
     """embed_with_usage refreshes the bearer, then returns the (embedding,
     token_count) from the inherited OpenAI implementation."""
+    # https mock host (never contacted — the OpenAI client is patched below).
     provider = GatewayProvider(
-        base_url="http://gw:8083/v1", embedding_model="mistral/mistral-embed"
+        base_url="https://gw:8083/v1", embedding_model="mistral/mistral-embed"
     )
 
     order: list[str] = []
@@ -364,8 +365,9 @@ async def test_gateway_embed_with_usage_forwards_after_bearer(monkeypatch):
 
 async def test_gateway_embed_batch_with_usage_forwards_after_bearer(monkeypatch):
     """embed_batch_with_usage also refreshes the bearer before delegating."""
+    # https mock host (never contacted — the OpenAI client is patched below).
     provider = GatewayProvider(
-        base_url="http://gw:8083/v1", embedding_model="mistral/mistral-embed"
+        base_url="https://gw:8083/v1", embedding_model="mistral/mistral-embed"
     )
     ensured = {"n": 0}
 

tests/unit/providers/test_ollama.py

@@ -15,8 +15,9 @@ from nextcloud_mcp_server.providers.ollama import OllamaProvider
 @pytest.fixture
 def ollama_provider():
     # Construct with no models so __init__ skips _check_model_is_loaded (no
-    # network call), then enable embeddings post-construction.
-    provider = OllamaProvider(base_url="http://ollama:11434")
+    # network call), then enable embeddings post-construction. https mock host
+    # (never contacted — client.post is patched in each test).
+    provider = OllamaProvider(base_url="https://ollama:11434")
     provider.embedding_model = "nomic-embed-text"
     return provider
 

tests/unit/test_processor_metering.py

@@ -0,0 +1,104 @@
+"""Unit tests for the indexing-path usage-metering helper (Deck #67).
+
+``record_indexing_usage`` records the two billable events (``pages_chunks`` +
+``embeddings_queries``) after a document's chunks are embedded. These cover the
+value mapping, the flag/zero-chunk no-ops, and the best-effort failure path
+without standing up the full document pipeline.
+"""
+
+from unittest.mock import AsyncMock, MagicMock
+
+import pytest
+
+from nextcloud_mcp_server.vector import processor
+
+
+@pytest.fixture
+def store_spy(monkeypatch):
+    """Patch UsageEventStore.shared() to return a spy store."""
+    store = MagicMock()
+    store.record_usage_event = AsyncMock()
+    monkeypatch.setattr(
+        processor.UsageEventStore, "shared", AsyncMock(return_value=store)
+    )
+    return store
+
+
+@pytest.mark.unit
+async def test_records_pages_chunks_and_token_count(store_spy):
+    """Both events fire: pages_chunks = chunk count, embeddings_queries = tokens."""
+    await processor.record_indexing_usage(
+        enabled=True,
+        provider="mistral",
+        model="mistral-embed",
+        doc_type="file",
+        user_id="alice",
+        chunk_count=110,
+        token_count=4242,
+        total_chars=170826,
+    )
+
+    calls = store_spy.record_usage_event.await_args_list
+    by_metric = {c.kwargs["metric"]: c.kwargs["value"] for c in calls}
+    assert by_metric == {"pages_chunks": 110, "embeddings_queries": 4242}
+    for c in calls:
+        # Hot-path fast-gate + tenant-local attribution metadata.
+        assert c.kwargs["enabled"] is True
+        assert c.kwargs["metadata"]["provider"] == "mistral"
+        assert c.kwargs["metadata"]["model"] == "mistral-embed"
+        assert c.kwargs["metadata"]["user_id"] == "alice"
+        assert c.kwargs["metadata"]["doc_type"] == "file"
+
+
+@pytest.mark.unit
+async def test_disabled_is_noop(store_spy):
+    """Flag off → no store access, no events."""
+    await processor.record_indexing_usage(
+        enabled=False,
+        provider="mistral",
+        model="mistral-embed",
+        doc_type="file",
+        user_id="alice",
+        chunk_count=10,
+        token_count=20,
+        total_chars=5,
+    )
+    store_spy.record_usage_event.assert_not_awaited()
+
+
+@pytest.mark.unit
+async def test_zero_chunks_is_noop(store_spy):
+    """A document with no chunks records nothing (no zero-value rows)."""
+    await processor.record_indexing_usage(
+        enabled=True,
+        provider="mistral",
+        model="mistral-embed",
+        doc_type="file",
+        user_id="alice",
+        chunk_count=0,
+        token_count=0,
+        total_chars=0,
+    )
+    store_spy.record_usage_event.assert_not_awaited()
+
+
+@pytest.mark.unit
+async def test_store_failure_is_swallowed(monkeypatch):
+    """A store-construction failure is logged, never raised into indexing."""
+    monkeypatch.setattr(
+        processor.UsageEventStore,
+        "shared",
+        AsyncMock(side_effect=RuntimeError("boom")),
+    )
+
+    # Must not raise.
+    await processor.record_indexing_usage(
+        enabled=True,
+        provider="mistral",
+        model="mistral-embed",
+        doc_type="file",
+        user_id="alice",
+        chunk_count=3,
+        token_count=7,
+        total_chars=9,
+    )