Route dossier, geocode, and Wikimedia through the backend (#351, #352, #360)

Proxy region dossier, Sentinel search, Wikipedia, and Wikidata via self-hosted
APIs; remove LocateBar client-side Nominatim fallback; migrate legacy shadow-
operator handles to operator- prefix.

Co-authored-by: Cursor <cursoragent@cursor.com>

backend/routers/tools.py

@@ -85,6 +85,39 @@ async def api_geocode_reverse(
     return await asyncio.to_thread(reverse_geocode, lat, lng, local_only)
 
 
+# ── Wikimedia proxy (#360) — browser calls these instead of wikipedia.org ───
+@router.get("/api/wikipedia/summary")
+@limiter.limit("60/minute")
+def api_wikipedia_summary(
+    request: Request,
+    title: str = Query(..., min_length=1, max_length=256),
+):
+    """Proxy Wikipedia REST summaries through the self-hosted backend."""
+    from services.region_dossier import fetch_wikipedia_page_summary
+
+    summary = fetch_wikipedia_page_summary(title)
+    if summary is None:
+        return JSONResponse(status_code=404, content={"detail": "not_found"})
+    return summary
+
+
+class WikidataSparqlRequest(BaseModel):
+    query: str
+
+
+@router.post("/api/wikidata/sparql")
+@limiter.limit("30/minute")
+def api_wikidata_sparql(request: Request, body: WikidataSparqlRequest):
+    """Proxy Wikidata SPARQL so the browser never contacts query.wikidata.org."""
+    from services.region_dossier import fetch_wikidata_sparql_bindings
+
+    q = (body.query or "").strip()
+    if len(q) > 12_000:
+        raise HTTPException(400, "SPARQL query too large")
+    bindings = fetch_wikidata_sparql_bindings(q)
+    return {"bindings": bindings}
+
+
 # ── Sentinel proxy routes (Issue #299/#300/#301, reported by tg12) ──────────
 # These three endpoints relay external Sentinel / Planetary Computer
 # requests through the backend to avoid browser CORS blocks. They are

backend/services/network_utils.py

@@ -146,7 +146,12 @@ def get_operator_handle() -> str:
         # 3. On-disk handle from a previous run.
         persisted = _load_persisted_operator_handle()
         if persisted:
-            _OPERATOR_HANDLE_CACHE = _normalize_handle(persisted)
+            normalized = _normalize_handle(persisted)
+            # Migrate legacy auto-generated handles (pre-Round-7a ``shadow-`` prefix).
+            if normalized.startswith("shadow-"):
+                normalized = f"operator-{normalized[len('shadow-'):]}"
+                _persist_operator_handle(normalized)
+            _OPERATOR_HANDLE_CACHE = normalized
             return _OPERATOR_HANDLE_CACHE
 
         # 4. Generate, persist, return.
@@ -178,7 +183,7 @@ def outbound_user_agent(purpose: str = "") -> str:
 
     Returns something like::
 
-        Shadowbroker/0.9 (operator: shadow-7f3a92; purpose: wikipedia;
+        Shadowbroker/0.9 (operator: operator-7f3a92; purpose: wikipedia;
          +https://github.com/BigBodyCobain/Shadowbroker/issues)
 
     The ``purpose`` is optional but recommended — it tells the upstream

backend/services/region_dossier.py

@@ -301,3 +301,36 @@ def get_region_dossier(lat: float, lng: float) -> dict:
 
     dossier_cache[cache_key] = result
     return result
+
+
+def fetch_wikipedia_page_summary(title: str) -> dict | None:
+    """Wikipedia REST summary for a page title (backend-proxied for #360)."""
+    trimmed = (title or "").strip()
+    if not trimmed:
+        return None
+    data = _fetch_local_wiki_summary(trimmed, "")
+    if not data.get("extract") and not data.get("description"):
+        return None
+    return {
+        "title": trimmed,
+        "description": data.get("description", ""),
+        "extract": data.get("extract", ""),
+        "thumbnail": data.get("thumbnail", ""),
+        "type": "standard",
+    }
+
+
+def fetch_wikidata_sparql_bindings(sparql: str) -> list:
+    """Run a Wikidata SPARQL query; returns bindings list (empty on failure)."""
+    trimmed = (sparql or "").strip()
+    if not trimmed:
+        return []
+    url = f"https://query.wikidata.org/sparql?query={quote(trimmed)}&format=json"
+    try:
+        res = fetch_with_curl(url, timeout=8, headers=_wikimedia_request_headers())
+        if res.status_code == 200:
+            bindings = res.json().get("results", {}).get("bindings", [])
+            return bindings if isinstance(bindings, list) else []
+    except (ConnectionError, TimeoutError, ValueError, KeyError, OSError) as e:
+        logger.warning("Wikidata SPARQL failed: %s", e)
+    return []

backend/tests/test_wikimedia_proxy_routes.py

@@ -0,0 +1,34 @@
+"""Backend Wikimedia proxy routes (#360)."""
+from __future__ import annotations
+
+from unittest.mock import patch
+
+import pytest
+
+
+def test_wikipedia_summary_route_returns_payload(client):
+    sample = {
+        "title": "Paris",
+        "description": "capital",
+        "extract": "Paris is the capital of France.",
+        "thumbnail": "https://example.org/t.jpg",
+        "type": "standard",
+    }
+    with patch(
+        "services.region_dossier.fetch_wikipedia_page_summary",
+        return_value=sample,
+    ):
+        r = client.get("/api/wikipedia/summary", params={"title": "Paris"})
+    assert r.status_code == 200
+    assert r.json()["title"] == "Paris"
+
+
+def test_wikidata_sparql_route_returns_bindings(client):
+    bindings = [{"x": {"value": "1"}}]
+    with patch(
+        "services.region_dossier.fetch_wikidata_sparql_bindings",
+        return_value=bindings,
+    ):
+        r = client.post("/api/wikidata/sparql", json={"query": "SELECT ?x WHERE {}"})
+    assert r.status_code == 200
+    assert r.json()["bindings"] == bindings