Default retrieval to 6 chunks instead of 2

chunks is a total per request, split across the attached sources, so an
agent with two sources and the default of 2 got a single chunk from each,
and its answers changed with whichever chunk won. 6 gives three per
source for about 4-5k more input tokens per retrieval turn.

Every literal default moves from 2 to 6: the request default, the
retrievers, the internal search tool, workflow agent nodes, scheduled and
headless runs, agent create/update/import, the source retrieval config and
the frontend forms. Existing agents and sources keep what they store; a
source saved with chunks=2 now counts as configured at 2, which is pinned
by a test.

Headless runs also read chunks=0 as unset (`or 2`), so an agent with
retrieval switched off retrieved anyway on scheduled runs; 0 now stays 0.

docsgpt/api/user/sharing/routes.py

@@ -205,7 +205,7 @@ class ShareConversation(Resource):
 
                 if is_promptable:
                     prompt_id_raw = data.get("prompt_id", "default")
-                    chunks_raw = data.get("chunks", "2")
+                    chunks_raw = data.get("chunks", "6")
                     try:
                         chunks_int = int(chunks_raw) if chunks_raw not in (None, "") else None
                     except (TypeError, ValueError):