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/agents/headless_runner.py

@@ -153,7 +153,9 @@ def _run_agent_headless(
             source_active = str(src_row["id"])
             retriever_kind = src_row.get("retriever", retriever_kind)
     source = {"active_docs": source_active}
-    chunks = int(agent_config.get("chunks", 2) or 2)
+    # ``chunks=0`` switches retrieval off; only a missing value takes the default.
+    raw_chunks = agent_config.get("chunks")
+    chunks = 6 if raw_chunks in (None, "") else int(raw_chunks)
     prompt_id = agent_config.get("prompt_id", "default")
     user_api_key = agent_config.get("key")
     agent_id = _resolve_agent_id(agent_config)