FlowiseAI/Flowise · error · Error

Error in Condition Agent node: ${error instanceof Error ? er

Error message

Error in Condition Agent node: ${error instanceof Error ? error.message : String(error)}

What it means

Top-level catch in ConditionAgent.run. Reports analytics via onLLMError when configured, re-throws Abort errors verbatim, and wraps every other failure as 'Error in Condition Agent node: <message>'. It is the umbrella error for anything that went wrong inside the node; the inner cause is in the interpolated tail.

Source

Thrown at packages/components/nodes/agentflow/ConditionAgent/ConditionAgent.ts:515

            const returnOutput = {
                id: nodeData.id,
                name: this.name,
                input: { messages: messagesWithFileReferences },
                output,
                state,
                chatHistory: [...inputMessages]
            }

            return returnOutput
        } catch (error) {
            if (options.analyticHandlers && llmIds) {
                await options.analyticHandlers.onLLMError(llmIds, error instanceof Error ? error.message : String(error))
            }

            if (error instanceof Error && error.message === 'Aborted') {
                throw error
            }
            throw new Error(`Error in Condition Agent node: ${error instanceof Error ? error.message : String(error)}`)
        }
    }

    /**
     * Handles memory management based on the specified memory type
     */
    private async handleMemory({
        messages,
        memoryType,
        pastChatHistory,
        runtimeChatHistory,
        llmNodeInstance,
        nodeData,
        input,
        abortController,
        options,
        modelConfig
    }: {

View on GitHub (pinned to abe4a8601a)

Solutions

Read the interpolated message to find the underlying cause.
If it nests error 9-14, follow those solutions (model choice, prompt, temperature, max_tokens).
For auth/rate-limit, fix the credential or reduce request frequency.
For Abort, trace the upstream cancellation.
Check onLLMError analytics events for structured detail.

Defensive patterns

Strategy: try-catch

Try / catch

try { await conditionAgent.run(nodeData, question, options) }
catch (e) {
  const m = e instanceof Error ? e.message : String(e)
  if (m === 'Aborted') { /* expected */ return }
  if (m.startsWith('Error in Condition Agent node: ')) {
    const inner = m.slice('Error in Condition Agent node: '.length)
    // route by inner: parse failure -> model/prompt; auth -> credential; etc.
  }
  throw e
}

Prevention

Pre-validate model, scenarios, and credentials before run().
Wire onLLMError analytics to alerting.
Keep the system prompt's JSON mandate intact when overriding.

When it happens

Trigger: Any uncaught throw inside ConditionAgent.run: the model/init failures, the scenario/JSON errors (9-14), LLM invocation network/auth errors, message-building errors, or memory-handling errors. AbortController.abort() is re-thrown unwrapped.

Common situations: Invalid/expired model credential; provider rate limit or 5xx; missing scenarios; weak model producing unparseable output; overridden system prompt breaking the format; context overflow from large chat history.

Related errors

AI-assisted analysis of FlowiseAI/Flowise@abe4a8601a (2026-08-12). Data as JSON: /api/errors/697caf8e3af59477. Report an issue: GitHub.