alibaba/spring-ai-alibaba · error · IllegalStateException

No default output or error next node provided

Error message

No default output or error next node provided

What it means

The generated LLM node's routing lambda requires either a default next node or an error next node to decide where to go after execution. If both are absent, the generated code throws IllegalStateException at runtime.

Source

Thrown at spring-ai-alibaba-admin/spring-ai-alibaba-admin-server-start/src/main/java/com/alibaba/cloud/ai/studio/admin/builder/generator/service/generator/workflow/sections/LLMNodeSection.java:140

						            catch (Exception e) {
						                try {
						                    Thread.sleep(retryInterval);
						                } catch (InterruptedException ie) {
						                    Thread.currentThread().interrupt();
						                    break;
						                }
						            }
						        }

						        // error handling
						        if (defaultOutput != null) {
						            return %s;
						        }
						        else if (errorNextNode != null) {
						            return Map.of(nextNodeKey, errorNextNode);
						        }
						        else {
						            throw new IllegalStateException("No default output or error next node provided");
						        }
						    };
						}
						""",
				dialectType.equals(DSLDialectType.DIFY) ? "Map.of(outputKeyPrefix + \"text\", content)"
						: "Map.of(outputKeyPrefix + \"output\", content, outputKeyPrefix + \"reasoning_content\", content)",
				dialectType.equals(DSLDialectType.DIFY) ? "Map.of(outputKeyPrefix + \"text\", defaultOutput)"
						: "Map.of(outputKeyPrefix + \"output\", defaultOutput, outputKeyPrefix + \"reasoning_content\", defaultOutput)");
	}

	@Override
	public List<String> getImports() {
		return List.of("org.springframework.ai.chat.messages.Message",
				"org.springframework.ai.chat.messages.AssistantMessage",
				"org.springframework.ai.chat.messages.MessageType",
				"org.springframework.ai.chat.messages.SystemMessage",
				"org.springframework.ai.chat.messages.UserMessage",
				"com.alibaba.cloud.ai.dashscope.chat.DashScopeChatOptions",

View on GitHub (pinned to f82da0b50f)

Solutions

1. Add an outgoing edge from the LLM node to a downstream node (default output)
2. Configure an error next node so failures route to an error handler branch
3. Restructure the workflow so the LLM node is not unconditionally required to route

Example fix

// before
{"id": "llm1", ...} // no outgoing edges
// after
{"id": "llm1", ...}, {"source": "llm1", "target": "end1", "type": "default"}

boolean hasOutgoingEdge = edges.stream().anyMatch(e -> e.getSource().equals(llmNodeId) && ("default".equals(e.getType()) || "error".equals(e.getType()))); if (!hasOutgoingEdge) { throw new IllegalArgumentException("LLM node needs a default or error edge: " + llmNodeId); }

null

try { stateRouter.apply(state); } catch (IllegalStateException e) { log.error("LLM node routing failed: {}", e.getMessage()); }

When it happens

Trigger: An LLM node in the DSL has no downstream edge marked as the default/normal output and no error edge, and the generated routing function executes.

Common situations: Dangling LLM node at the end of an incomplete workflow graph; edges deleted during DSL editing; imported DSL where the LLM node is terminal but the generator still emits routing code.

Understand the failure class

Background: "missing required argument" and "the following required arguments were not provided": what required-argument errors mean and how to fix them — this error's family across 20 libraries.

Related errors

• WORKFLOW_CONFIG_INVALID
• invalid output
• Routing sub-agents must be BaseAgent for merge support
• Routing flow requires at least one sub-agent
• Routing flow requires a ChatModel for decision making

AI-assisted analysis of alibaba/spring-ai-alibaba@f82da0b50f (2026-09-09). Data as JSON: /api/errors/113530a016e1dc44. Report an issue: GitHub.