FlowiseAI/Flowise · error · Error

Agent must have a predecessor!

Error message

Agent must have a predecessor!

What it means

Predecessor check inside the LLM Node. Note the message text says 'Agent' rather than 'LLM Node' — this is a copy-paste from the Agent node and is misleading, but the failing node is the LLM Node. Thrown at init when inputs.sequentialNode is missing or empty, so the node cannot join the sequential graph.

Source

Thrown at packages/components/nodes/sequentialagents/LLMNode/LLMNode.ts:412

        // Tools can be connected through ToolNodes
        let tools = nodeData.inputs?.tools
        tools = flatten(tools)

        let systemPrompt = nodeData.inputs?.systemMessagePrompt as string
        systemPrompt = transformBracesWithColon(systemPrompt)
        let humanPrompt = nodeData.inputs?.humanMessagePrompt as string
        humanPrompt = transformBracesWithColon(humanPrompt)
        const llmNodeLabel = nodeData.inputs?.llmNodeName as string
        const sequentialNodes = nodeData.inputs?.sequentialNode as ISeqAgentNode[]
        const model = nodeData.inputs?.model as BaseChatModel
        const promptValuesStr = nodeData.inputs?.promptValues
        const output = nodeData.outputs?.output as string
        const llmStructuredOutput = nodeData.inputs?.llmStructuredOutput

        if (!llmNodeLabel) throw new Error('LLM Node name is required!')
        const llmNodeName = llmNodeLabel.toLowerCase().replace(/\s/g, '_').trim()

        if (!sequentialNodes || !sequentialNodes.length) throw new Error('Agent must have a predecessor!')

        let llmNodeInputVariablesValues: ICommonObject = {}
        if (promptValuesStr) {
            try {
                llmNodeInputVariablesValues = typeof promptValuesStr === 'object' ? promptValuesStr : JSON.parse(promptValuesStr)
            } catch (exception) {
                throw new Error("Invalid JSON in the LLM Node's Prompt Input Values: " + exception)
            }
        }
        llmNodeInputVariablesValues = handleEscapeCharacters(llmNodeInputVariablesValues, true)

        const startLLM = sequentialNodes[0].startLLM
        const llm = model || startLLM
        if (nodeData.inputs) nodeData.inputs.model = llm

        const multiModalMessageContent = sequentialNodes[0]?.multiModalMessageContent || (await processImageMessage(llm, nodeData, options))
        const abortControllerSignal = options.signal as AbortController
        const llmNodeInputVariables = uniq([...getInputVariables(systemPrompt), ...getInputVariables(humanPrompt)])

View on GitHub (pinned to abe4a8601a)

Solutions

1. Connect an upstream sequential node's output into this LLM Node's 'Sequential Node' input.
2. Save the chatflow to persist the edge.
3. Remember the message is mislabeled — the fix is on the LLM Node, not an Agent node.

const seq = nodeData.inputs?.sequentialNode
if (!Array.isArray(seq) || seq.length === 0) throw new Error('LLM Node must have a predecessor sequential node')

const hasPredecessor = (n: INodeData): boolean => Array.isArray(n.inputs?.sequentialNode) && (n.inputs!.sequentialNode as any[]).length > 0

When it happens

Trigger: An LLM Node placed on the canvas with no incoming wire from another sequential node; sequentialNode lost during import/copy.

Common situations: Forgotten wiring; copy-paste of nodes without edges; the misleading 'Agent' text sending debugging toward the wrong node.

Related errors

• Custom function must have a predecessor!
• End must have a predecessor!
• Execute Flow must have a predecessor!
• LLM Node name is required!
• Agent must have a predecessor!

AI-assisted analysis of FlowiseAI/Flowise@abe4a8601a (2026-08-12). Data as JSON: /api/errors/12ec5a6beeef8afa. Report an issue: GitHub.