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.

tests/storage/db/test_source_config.py

@@ -40,7 +40,7 @@ class TestParseLenient:
         r = RetrievalConfig()
         assert r.retriever == "classic"
         assert r.exposure == "prefetch"
-        assert r.chunks == 2
+        assert r.chunks == 6
         assert r.score_threshold is None
         assert r.rephrase_query is True
         assert r.reranker is None