RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.
Go agent-harnessagent-native-databaseagentic-aiagentic-retrievalagentic-searchaiai-agentscontext-enginecontext-engineeringcontext-managementharness-engineeringknowledge-compilationragretrieval-augmented-generationretrieval-harnesssearch-harness
fix(chat): keep reasoning chats grounded when LLM lacks tool calling (#18983)
georgelichenf300b154b0b0
diff --git a/api/db/services/dialog_service.py b/api/db/services/dialog_service.pyindex 189bad8924..17c77f4b58 100644--- a/api/db/services/dialog_service.py+++ b/api/db/services/dialog_service.py@@ -1959,6 +1959,21 @@ async def rag_agent(dialog, messages, stream=True, **kwargs):yield ansreturnkbs, embd_mdl, rerank_mdl, chat_mdl, tts_mdl = get_models(dialog)++ # Agentic RAG depends on the outer model being able to call the bound+ # ``rag`` tool. Models without tool-calling support would otherwise receive+ # only the router prompt and could answer from their own knowledge without+ # ever running retrieval. Reuse the regular RAG path for those models so+ # the configured knowledge base and citation flow remain authoritative.+ if not getattr(chat_mdl, "is_tools", False):+ logging.info("LLM does not support tool calls; falling back to regular RAG chat")+ fallback_kwargs = dict(kwargs)+ if isinstance(fallback_kwargs.get("doc_ids"), list):+ fallback_kwargs["doc_ids"] = ",".join(str(doc_id) for doc_id in fallback_kwargs["doc_ids"] if doc_id)+ async for ans in async_chat(dialog, messages, stream, **fallback_kwargs):+ yield ans+ return+model_type = chat_mdl.model_config["model_type"]factory = chat_mdl.model_config.get("llm_factory", "") if chat_mdl.model_config else ""text_attachments_content, image_attachments, image_files = get_files_content(messages[-1], model_type)diff --git a/test/unit_test/api/db/services/test_dialog_service_rag_agent_messages.py b/test/unit_test/api/db/services/test_dialog_service_rag_agent_messages.pyindex 38d50d78da..86a7c18dfb 100644--- a/test/unit_test/api/db/services/test_dialog_service_rag_agent_messages.py+++ b/test/unit_test/api/db/services/test_dialog_service_rag_agent_messages.py@@ -88,6 +88,7 @@ class _RecordingChatModel:"""Records the message list rag_agent() hands to the provider."""def __init__(self):+ self.is_tools = Trueself.model_config = {"model_type": "chat", "llm_factory": "OpenAI"}self.mdl = Noneself.sent_messages = None@@ -123,6 +124,43 @@ def _drive_rag_agent(monkeypatch, messages):return chat_mdl+def test_rag_agent_falls_back_to_retrieval_when_model_has_no_tools(monkeypatch):+ """Reasoning must not bypass KB retrieval for models without tool support."""++ class _NoToolsChatModel(_RecordingChatModel):+ def __init__(self):+ super().__init__()+ self.is_tools = False++ chat_mdl = _NoToolsChatModel()+ fallback_calls = []++ async def _fallback(_dialog, _messages, stream=True, **_kwargs):+ fallback_calls.append((stream, _kwargs))+ yield {"answer": "retrieved answer", "reference": {"chunks": [{"doc_id": "doc-1"}]}}++ monkeypatch.setattr(dialog_service, "get_models", lambda _dialog, **_kw: ([_KB], None, None, chat_mdl, None))+ monkeypatch.setattr(dialog_service, "async_chat", _fallback)++ async def _run():+ return [+ event+ async for event in dialog_service.rag_agent(+ _DIALOG,+ [{"role": "user", "content": "What is RAGFlow?"}],+ False,+ reasoning="2",+ doc_ids=["doc-1"],+ )+ ]++ events = asyncio.run(_run())++ assert fallback_calls == [(False, {"reasoning": "2", "doc_ids": "doc-1"})]+ assert events[0]["answer"] == "retrieved answer"++@pytest.mark.p2def test_rag_agent_drops_bookkeeping_keys_before_the_provider_call(monkeypatch):"""Groq rejects any message property the chat schema does not define."""