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)

docsgpt/agents/tools/internal_search.py

@@ -36,7 +36,7 @@ class InternalSearchTool(Tool):
                 source=self.config.get("source", {}),
                 chat_history=[],
                 prompt="",
-                chunks=int(self.config.get("chunks", 2)),
+                chunks=int(self.config.get("chunks", 6)),
                 doc_token_limit=int(self.config.get("doc_token_limit", 50000)),
                 model_id=self.config.get("model_id", "docsgpt-local"),
                 model_user_id=self.config.get("model_user_id"),
@@ -464,7 +464,7 @@ def add_internal_search_tool(tools_dict: Dict, retriever_config: Dict) -> None:
 def build_internal_tool_config(
     source: Dict,
     retriever_name: str = "classic",
-    chunks: int = 2,
+    chunks: int = 6,
     doc_token_limit: int = 50000,
     sources: Optional[List[Dict]] = None,
     model_id: str = "docsgpt-local",

docsgpt/agents/workflows/schemas.py

@@ -45,7 +45,7 @@ class AgentNodeConfig(BaseModel):
     stream_to_user: bool = True
     tools: List[str] = Field(default_factory=list)
     sources: List[str] = Field(default_factory=list)
-    chunks: str = "2"
+    chunks: str = "6"
     retriever: str = ""
     model_id: Optional[str] = None
     json_schema: Optional[Dict[str, Any]] = None

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)