fix: correct /stats wiki page count and Wiki.js listing pagination

- /stats passed the bare user name as path prefix (matched nothing, always
  reported 0 of 138 pages); it now counts pages under users/{user}
- list_pages applied the API-side limit before client-side path/tag filters,
  dropping matching pages that sort late; limit now applies after filtering
- list_all_pages replaced the fake while/break pagination with a real
  limit-growth loop: Wiki.js 2.x pages.list supports only a limit argument
  (no offset - verified via GraphQL introspection), so the client doubles
  the limit until the API returns fewer pages than requested

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

CHANGELOG.md

@@ -15,6 +15,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - **Ollama generation model env collision** - Renamed the generation-model setting `ollama_model` to `ollama_llm_model` (env: `OLLAMA_LLM_MODEL`, default `gemma4:e2b`). The container env `OLLAMA_MODEL=nomic-embed-text` (meant for embeddings) was shadowing the generation model, breaking Phase 0 keyword extraction and Phase 4 LLM re-ranking on every request. Startup now logs the resolved generation model.
 - **LLM call timeouts** - Phase 0 keyword extraction and Phase 4 re-ranking are wrapped in a 12s `asyncio.wait_for` with graceful fallback, so a hung Ollama call can no longer gate retrieval for the full 120s client timeout.
+- **`/stats` wiki page count** - The endpoint passed the bare user name as path prefix (matching nothing) and always reported 0 pages; it now counts pages under `users/{user}`.
+- **Wiki.js page listing** - `list_pages` applied the API-side `limit` before client-side path/tag filters, dropping matching pages that sort late; the limit now applies after filtering. `list_all_pages` replaced its fake pagination loop with a real limit-growth loop (Wiki.js 2.x `pages.list` has no offset argument) that fetches until the API returns fewer pages than requested.
 
 ## [1.7.3] - 2026-01-07
 

src/clients/wikijs_client.py

@@ -96,24 +96,15 @@ class WikiJSClient:
             logger.error(f"GraphQL query failed: {e}", exc_info=True)
             raise
 
-    async def list_pages(
-        self,
-        path_prefix: str = "",
-        tags: Optional[List[str]] = None,
-        limit: int = 50
-    ) -> List[Dict[str, Any]]:
+    async def _fetch_pages(self, limit: int) -> List[Dict[str, Any]]:
         """
-        List pages with optional filtering.
-
-        Multi-tenancy: Use path_prefix to filter by user namespace.
+        Fetch a raw page listing from the GraphQL API (no client-side filtering).
 
         Args:
-            path_prefix: Filter by path prefix (e.g., "/users/jpmschweitzer")
-            tags: Filter by tags (e.g., ["projects"])
-            limit: Maximum results
+            limit: Maximum pages to request from the API
 
         Returns:
-            List of page objects
+            List of page objects with tags normalized to a list
         """
         query = """
         query ListPages($limit: Int, $orderBy: PageOrderBy) {
@@ -145,7 +136,39 @@ class WikiJSClient:
             if "tags" not in page or page["tags"] is None:
                 page["tags"] = []
 
-        # Filter by path prefix (client-side if API doesn't support)
+        return pages
+
+    async def _fetch_all_pages(self, initial_limit: int = 100) -> List[Dict[str, Any]]:
+        """
+        Fetch ALL pages from the GraphQL API.
+
+        The Wiki.js 2.x `pages.list` query only supports a `limit` argument
+        (no offset - verified via GraphQL introspection), so exhaustive
+        listing works by growing the limit until the API returns fewer
+        pages than requested.
+
+        Args:
+            initial_limit: Page count for the first request
+
+        Returns:
+            Complete list of page objects
+        """
+        max_limit = 100_000  # Safety cap against pathological growth
+        limit = max(initial_limit, 1)
+
+        while True:
+            pages = await self._fetch_pages(limit)
+            if len(pages) < limit or limit >= max_limit:
+                return pages
+            limit = min(limit * 2, max_limit)
+
+    @staticmethod
+    def _filter_pages(
+        pages: List[Dict[str, Any]],
+        path_prefix: str = "",
+        tags: Optional[List[str]] = None
+    ) -> List[Dict[str, Any]]:
+        """Apply client-side path-prefix and tag filters to a page listing."""
         if path_prefix:
             # Normalize paths to have leading slash for consistent comparison
             normalized_prefix = "/" + path_prefix.lstrip("/")
@@ -163,6 +186,38 @@ class WikiJSClient:
 
         return pages
 
+    async def list_pages(
+        self,
+        path_prefix: str = "",
+        tags: Optional[List[str]] = None,
+        limit: int = 50
+    ) -> List[Dict[str, Any]]:
+        """
+        List pages with optional filtering.
+
+        Multi-tenancy: Use path_prefix to filter by user namespace.
+
+        Args:
+            path_prefix: Filter by path prefix (e.g., "/users/jpmschweitzer")
+            tags: Filter by tags (e.g., ["projects"])
+            limit: Maximum results (applied AFTER filtering)
+
+        Returns:
+            List of page objects
+        """
+        if path_prefix or tags:
+            # The API limit applies before our client-side filters, so a
+            # small limit would drop matching pages that sort late. Fetch
+            # everything, filter, then apply the limit.
+            pages = self._filter_pages(
+                await self._fetch_all_pages(),
+                path_prefix=path_prefix,
+                tags=tags
+            )
+            return pages[:limit]
+
+        return await self._fetch_pages(limit)
+
     async def list_all_pages(
         self,
         path_prefix: str = "",
@@ -172,34 +227,22 @@ class WikiJSClient:
         """
         List ALL pages with pagination support.
 
-        Fetches pages in batches until all are retrieved.
+        Fetches pages in growing batches until all are retrieved (Wiki.js
+        `pages.list` has no offset argument), then applies filters.
 
         Args:
             path_prefix: Filter by path prefix (e.g., "users/jpmschweitzer")
             tags: Filter by tags
-            batch_size: Number of pages per batch (max 100)
+            batch_size: Page count for the first request
 
         Returns:
             Complete list of page objects
         """
-        all_pages = []
-        offset = 0
-
-        while True:
-            # Wiki.js list doesn't support offset, but limit is enough
-            # since we filter client-side by path_prefix
-            # Just fetch a large batch
-            pages = await self.list_pages(
-                path_prefix=path_prefix,
-                tags=tags,
-                limit=1000  # Fetch up to 1000 at once
-            )
-
-            if not pages:
-                break
-
-            all_pages = pages
-            break  # Wiki.js list doesn't paginate, so one call is enough
+        all_pages = self._filter_pages(
+            await self._fetch_all_pages(initial_limit=batch_size),
+            path_prefix=path_prefix,
+            tags=tags
+        )
 
         logger.info(f"list_all_pages: found {len(all_pages)} pages (prefix: {path_prefix or 'all'})")
         return all_pages

src/main.py

@@ -192,10 +192,10 @@ async def stats(
         logger.error(f"Failed to get Qdrant stats: {e}")
         qdrant_stats = {"error": str(e)}
 
-    # Wiki.js page count
+    # Wiki.js page count (pages live under the user namespace, e.g. "users/jpmschweitzer/...")
     wiki_pages = 0
     try:
-        pages = await wikijs.list_all_pages(user)
+        pages = await wikijs.list_all_pages(path_prefix=f"users/{user}")
         wiki_pages = len(pages)
     except Exception as e:
         logger.warning(f"Failed to get Wiki.js stats: {e}")