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/workflows/workflow_engine.py

@@ -429,7 +429,7 @@ class WorkflowEngine:
                     else {}
                 ),
                 "retriever_name": node_config.retriever or "classic",
-                "chunks": int(node_config.chunks) if node_config.chunks else 2,
+                "chunks": int(node_config.chunks) if node_config.chunks else 6,
                 "model_id": node_model_id,
                 "llm_name": node_llm_name,
                 "api_key": node_api_key,
@@ -1388,7 +1388,7 @@ class WorkflowEngine:
                 source={"active_docs": self._authorized_node_sources(node_config.sources)},
                 chat_history=[],
                 prompt="",
-                chunks=int(node_config.chunks) if node_config.chunks else 2,
+                chunks=int(node_config.chunks) if node_config.chunks else 6,
                 decoded_token=self.agent.decoded_token,
             )
             docs = retriever.search(query)