035: fix httpx.Response.ok -> httpx.Response.is_success in LLM client

httpx.Response does not have .ok attribute (that's requests.Response).
Async migration missed this: _llm_async_http.py used response.ok in two
places, causing 502 errors when LLM API responded.

Fix: response.ok -> response.is_success

backend/src/plugins/translate/_llm_async_http.py

@@ -117,7 +117,7 @@ async def call_openai_compatible(
     response, response_text = await _do_http_request(url, headers, payload)
     await _handle_response_format_fallback(response, response_text, payload, url, headers)
 
-    if not response.ok:
+    if not response.is_success:
         logger.explore(
             f"LLM API error status={response.status_code} "
             f"model={payload.get('model')} "
@@ -225,7 +225,7 @@ async def _handle_response_format_fallback(
     """Handle 400 errors from structured_outputs not being supported."""
     _patterns = ("response_format", "structured_outputs", "structured", "json_object")
     if (
-        not response.ok
+        not response.is_success
         and response.status_code == 400
         and any(p in (response_text or "").lower() for p in _patterns)
     ):