fix(usage): embed query once across doc_types; address review round 1

Round-1 claude-review findings:

- 🔴 Multi-doc_type search billed N embedding calls as 1. nc_semantic_search
  loops search() once per doc_type on one BM25HybridSearchAlgorithm instance,
  and each call re-embedded the query, so only the last query_token_count was
  recorded. Cache the dense embedding per query on the (per-request) instance
  so the query is embedded — and metered — exactly once regardless of how many
  doc_types are searched. This also removes the redundant per-type embed work
  and avoids billing a user N× for one logical query.
- 🟡 Ollama embed() now delegates to embed_with_usage() so single and batch
  embeds use the same /api/embed endpoint (was the legacy /api/embeddings),
  keeping _detect_dimension and other embed() callers consistent.
- 🟢 round() instead of truncating int() when coercing provider-reported token
  counts (forward-compatible if a provider ever returns a float).

Tests: per-instance query-embedding cache (embedded once across 3 doc_types;
re-embeds on a different query).

Deferred (stated on the PR): mistral/openai single-embed dual path (changes
tested error/request semantics on the cloud-critical path — separate refactor),
bedrock boto3 sync-in-async (pre-existing; no new invoke_model calls per doc).

Deck #67.

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

nextcloud_mcp_server/providers/bedrock.py

@@ -194,7 +194,7 @@ class BedrockProvider(Provider):
 
             token_count = response_body.get("inputTextTokenCount")
             tokens = (
-                int(token_count)
+                round(token_count)
                 if isinstance(token_count, (int, float))
                 else self._estimate_tokens([text])
             )

nextcloud_mcp_server/providers/mistral.py

@@ -209,7 +209,7 @@ class MistralProvider(Provider):
         # gives an int, but test doubles / partial responses can surface a
         # non-numeric attribute — fall back to the estimate there.
         tokens = (
-            int(total_tokens)
+            round(total_tokens)
             if isinstance(total_tokens, (int, float))
             else self._estimate_tokens(batch)
         )

nextcloud_mcp_server/providers/ollama.py

@@ -82,17 +82,12 @@ class OllamaProvider(Provider):
         Raises:
             NotImplementedError: If embeddings not enabled (no embedding_model)
         """
-        if not self.supports_embeddings:
-            raise NotImplementedError(
-                "Embedding not supported - no embedding_model configured"
-            )
-
-        response = await self.client.post(
-            f"{self.base_url}/api/embeddings",
-            json={"model": self.embedding_model, "prompt": text},
-        )
-        response.raise_for_status()
-        return response.json()["embedding"]
+        # Delegate to embed_with_usage so single and batch embeds use the same
+        # /api/embed endpoint (the legacy /api/embeddings differs in payload and
+        # omits prompt_eval_count). _detect_dimension() and other embed() callers
+        # therefore stay consistent with the search/indexing path.
+        embedding, _ = await self.embed_with_usage(text)
+        return embedding
 
     async def embed_batch(
         self, texts: list[str], batch_size: int = 32
@@ -166,7 +161,7 @@ class OllamaProvider(Provider):
 
             prompt_eval = data.get("prompt_eval_count")
             total_tokens += (
-                int(prompt_eval)
+                round(prompt_eval)
                 if isinstance(prompt_eval, (int, float))
                 else self._estimate_tokens(batch)
             )

nextcloud_mcp_server/providers/openai.py

@@ -233,7 +233,7 @@ class OpenAIProvider(Provider):
         # gives an int, but test doubles / partial responses can surface a
         # non-numeric attribute — fall back to the estimate there.
         tokens = (
-            int(total_tokens)
+            round(total_tokens)
             if isinstance(total_tokens, (int, float))
             else self._estimate_tokens(batch)
         )