feat: add test data cleanup endpoint

Add POST /maintenance/cleanup/test-data endpoint to purge LLM test data
from wiki, graph, and vectors. Security-restricted to test user namespace
only (users/llm-tester/*, users/llm_tester/*).

- Supports dry_run=true (default) to preview before deleting
- Cleans vectors, graph nodes, and wiki pages
- Scheduler task configured for weekly cleanup (Sunday 3:00 AM)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

src/routers/maintenance.py

@@ -22,6 +22,7 @@ from src.core.dependencies import (
     QdrantDep, OllamaDep, verify_api_key
 )
 from src.config import get_settings
+from src.core.multi_tenancy import DEFAULT_USER
 from datetime import datetime, timezone
 
 logger = logging.getLogger(__name__)
@@ -220,6 +221,35 @@ class VolatileCleanupResponse(BaseModel):
     duration_ms: float
 
 
+class TestDataCleanupResponse(BaseModel):
+    """Response from test data cleanup operation."""
+    success: bool
+    dry_run: bool
+    wiki_pages_deleted: int
+    graph_nodes_deleted: int
+    vector_chunks_deleted: int
+    pages_found: List[Dict[str, Any]] = Field(default_factory=list)
+    duration_ms: float
+
+
+# Test data path patterns - restricted to test user namespace only
+# These are the only paths that can be cleaned up for safety
+TEST_USER_PATH_PREFIXES = [
+    "users/llm-tester/",
+    "users/llm_tester/",
+]
+
+
+def _matches_test_user_path(path: str) -> bool:
+    """Check if a path is in the test user namespace.
+
+    Only matches paths that START with test user prefixes for safety.
+    This prevents accidental deletion of non-test data.
+    """
+    path_lower = path.lower()
+    return any(path_lower.startswith(prefix) for prefix in TEST_USER_PATH_PREFIXES)
+
+
 # ========== Endpoints ==========
 
 @router.post("/cleanup/vectors", response_model=VectorCleanupResponse)
@@ -556,6 +586,95 @@ async def cleanup_volatile(
         raise HTTPException(status_code=500, detail=str(e))
 
 
+@router.post("/cleanup/test-data", response_model=TestDataCleanupResponse)
+async def cleanup_test_data(
+    dry_run: bool = Query(default=True, description="Preview only, don't delete"),
+    wiki: WikiJSDep = None,
+    vector_service: VectorServiceDep = None,
+    graph_service: GraphServiceDep = None,
+    api_key: str = Depends(verify_api_key)
+):
+    """
+    Purge LLM tester data from wiki, graph, and vectors.
+
+    **Security**: Only deletes pages in the test user namespace:
+    - users/llm-tester/*
+    - users/llm_tester/*
+
+    This endpoint cannot delete data outside these paths.
+
+    **Use dry_run=true (default) to preview what would be deleted.**
+
+    **Scheduler Integration:**
+    ```json
+    {
+      "task_name": "test_data_cleanup",
+      "schedule": "0 3 * * 0",
+      "endpoint": "POST /maintenance/cleanup/test-data?dry_run=false",
+      "description": "Weekly cleanup of LLM test data"
+    }
+    ```
+    """
+    start_time = time.time()
+
+    try:
+        # List all wiki pages
+        all_pages = await wiki.list_all_pages(batch_size=500)
+
+        # Filter for test user paths only (security: restricted to test namespace)
+        test_pages = [
+            {"id": p["id"], "path": p["path"], "title": p.get("title", "")}
+            for p in all_pages
+            if _matches_test_user_path(p.get("path", ""))
+        ]
+
+        logger.info(f"Found {len(test_pages)} test pages matching patterns: {TEST_USER_PATH_PREFIXES}")
+
+        wiki_deleted = 0
+        graph_deleted = 0
+        vector_deleted = 0
+
+        if not dry_run and test_pages:
+            for page in test_pages:
+                page_id = page["id"]
+                page_path = page["path"]
+
+                try:
+                    # Delete vector chunks for this page (using DEFAULT_USER collection)
+                    chunks_removed = await vector_service.delete_page_chunks(page_id, DEFAULT_USER)
+                    vector_deleted += chunks_removed
+
+                    # Delete graph node for this page (returns count, may be 0 if no node)
+                    graph_removed = await graph_service.delete_page(page_id, DEFAULT_USER)
+                    graph_deleted += graph_removed
+
+                    # Delete wiki page (raises exception on failure, returns None on success)
+                    await wiki.delete_page(page_id)
+                    wiki_deleted += 1
+
+                    logger.info(f"Deleted test page: {page_path} (id={page_id})")
+
+                except Exception as e:
+                    logger.error(f"Failed to delete page {page_path}: {e}")
+                    continue
+
+        duration_ms = (time.time() - start_time) * 1000
+
+        return TestDataCleanupResponse(
+            success=True,
+            dry_run=dry_run,
+            wiki_pages_deleted=wiki_deleted,
+            graph_nodes_deleted=graph_deleted,
+            vector_chunks_deleted=vector_deleted,
+            pages_found=test_pages,
+            duration_ms=duration_ms
+        )
+
+    except Exception as e:
+        logger.error(f"Test data cleanup failed: {e}", exc_info=True)
+        raise HTTPException(status_code=500, detail=str(e))
+
+
 @router.get("/health", response_model=HealthCheckResponse)
 async def maintenance_health(
     user: str = Query(..., description="User identifier"),