make ai follow-up suggestions optional (#3591)

backend/app/gateway/routers/suggestions.py

@@ -135,6 +135,8 @@ async def generate_suggestions(
     request: Request,
     config: AppConfig = Depends(get_config),
 ) -> SuggestionsResponse:
+    if not config.suggestions.enabled:
+        return SuggestionsResponse(suggestions=[])
     if not body.messages:
         return SuggestionsResponse(suggestions=[])
 

backend/packages/harness/deerflow/config/app_config.py

@@ -28,6 +28,7 @@ from deerflow.config.skill_evolution_config import SkillEvolutionConfig
 from deerflow.config.skills_config import SkillsConfig
 from deerflow.config.stream_bridge_config import StreamBridgeConfig, load_stream_bridge_config_from_dict
 from deerflow.config.subagents_config import SubagentsAppConfig, load_subagents_config_from_dict
+from deerflow.config.suggestions_config import SuggestionsConfig
 from deerflow.config.summarization_config import SummarizationConfig, load_summarization_config_from_dict
 from deerflow.config.title_config import TitleConfig, load_title_config_from_dict
 from deerflow.config.token_usage_config import TokenUsageConfig
@@ -116,6 +117,7 @@ class AppConfig(BaseModel):
     acp_agents: dict[str, ACPAgentConfig] = Field(default_factory=dict, description="ACP-compatible agent configuration")
     subagents: SubagentsAppConfig = Field(default_factory=SubagentsAppConfig, description="Subagent runtime configuration")
     guardrails: GuardrailsConfig = Field(default_factory=GuardrailsConfig, description="Guardrail middleware configuration")
+    suggestions: SuggestionsConfig = Field(default_factory=SuggestionsConfig, description="Follow-up suggestions configuration.")
     circuit_breaker: CircuitBreakerConfig = Field(default_factory=CircuitBreakerConfig, description="LLM circuit breaker configuration")
     channel_connections: ChannelConnectionsConfig = Field(
         default_factory=ChannelConnectionsConfig,

backend/packages/harness/deerflow/config/suggestions_config.py

@@ -0,0 +1,7 @@
+from pydantic import BaseModel, Field
+
+
+class SuggestionsConfig(BaseModel):
+    """Configuration for automatic follow-up suggestions."""
+
+    enabled: bool = Field(default=True, description="Whether to enable follow-up question suggestions at the end of an AI response")

backend/tests/test_suggestions_router.py

@@ -74,7 +74,7 @@ def test_generate_suggestions_strips_inline_think_block(monkeypatch):
     fake_model.ainvoke = AsyncMock(return_value=MagicMock(content=content))
     monkeypatch.setattr(suggestions, "create_chat_model", lambda **kwargs: fake_model)
 
-    result = asyncio.run(suggestions.generate_suggestions.__wrapped__("t1", req, request=None, config=SimpleNamespace()))
+    result = asyncio.run(suggestions.generate_suggestions.__wrapped__("t1", req, request=None, config=SimpleNamespace(suggestions=SimpleNamespace(enabled=True))))
 
     assert result.suggestions == ["深度学习和机器学习的区别？", "常用框架有哪些？", "需要什么数学基础？"]
 
@@ -103,7 +103,7 @@ def test_generate_suggestions_parses_and_limits(monkeypatch):
 
     # Bypass the require_permission decorator (which needs request +
     # thread_store) — these tests cover the parsing logic.
-    result = asyncio.run(suggestions.generate_suggestions.__wrapped__("t1", req, request=None, config=SimpleNamespace()))
+    result = asyncio.run(suggestions.generate_suggestions.__wrapped__("t1", req, request=None, config=SimpleNamespace(suggestions=SimpleNamespace(enabled=True))))
 
     assert result.suggestions == ["Q1", "Q2", "Q3"]
     fake_model.ainvoke.assert_awaited_once()
@@ -125,7 +125,7 @@ def test_generate_suggestions_parses_list_block_content(monkeypatch):
 
     # Bypass the require_permission decorator (which needs request +
     # thread_store) — these tests cover the parsing logic.
-    result = asyncio.run(suggestions.generate_suggestions.__wrapped__("t1", req, request=None, config=SimpleNamespace()))
+    result = asyncio.run(suggestions.generate_suggestions.__wrapped__("t1", req, request=None, config=SimpleNamespace(suggestions=SimpleNamespace(enabled=True))))
 
     assert result.suggestions == ["Q1", "Q2"]
     fake_model.ainvoke.assert_awaited_once()
@@ -147,7 +147,7 @@ def test_generate_suggestions_parses_output_text_block_content(monkeypatch):
 
     # Bypass the require_permission decorator (which needs request +
     # thread_store) — these tests cover the parsing logic.
-    result = asyncio.run(suggestions.generate_suggestions.__wrapped__("t1", req, request=None, config=SimpleNamespace()))
+    result = asyncio.run(suggestions.generate_suggestions.__wrapped__("t1", req, request=None, config=SimpleNamespace(suggestions=SimpleNamespace(enabled=True))))
 
     assert result.suggestions == ["Q1", "Q2"]
     fake_model.ainvoke.assert_awaited_once()
@@ -166,6 +166,29 @@ def test_generate_suggestions_returns_empty_on_model_error(monkeypatch):
 
     # Bypass the require_permission decorator (which needs request +
     # thread_store) — these tests cover the parsing logic.
-    result = asyncio.run(suggestions.generate_suggestions.__wrapped__("t1", req, request=None, config=SimpleNamespace()))
+    result = asyncio.run(suggestions.generate_suggestions.__wrapped__("t1", req, request=None, config=SimpleNamespace(suggestions=SimpleNamespace(enabled=True))))
 
     assert result.suggestions == []
+
+
+def test_generate_suggestions_returns_empty_when_disabled(monkeypatch):
+    """Ensure suggestions are bypassed and returned an empty list when disabled in config."""
+    req = suggestions.SuggestionsRequest(
+        messages=[
+            suggestions.SuggestionMessage(role="user", content="Hi"),
+            suggestions.SuggestionMessage(role="assistant", content="Hello"),
+        ],
+        n=3,
+        model_name=None,
+    )
+
+    mock_config = SimpleNamespace(suggestions=SimpleNamespace(enabled=False))
+
+    fake_model = MagicMock()
+    fake_model.ainvoke = AsyncMock(side_effect=RuntimeError("Model should not be called."))
+    monkeypatch.setattr(suggestions, "create_chat_model", lambda **kwargs: fake_model)
+
+    result = asyncio.run(suggestions.generate_suggestions.__wrapped__("t1", req, request=None, config=mock_config))
+
+    assert result.suggestions == []
+    fake_model.ainvoke.assert_not_called()