FlowiseAI/Flowise · error · Error

LLM response is missing the "output" key or it is not a stri

Error message

LLM response is missing the "output" key or it is not a string.

What it means

After the LLM responds, ConditionAgent.parseJsonMarkdown parses the content and requires parsedResponse.output to be a truthy string — the matched scenario name. If output is missing, null, a number, or an object, the agent cannot pick a scenario and throws this. It is then caught locally and re-thrown as the 'Failed to parse a valid scenario' message (error 14).

Source

Thrown at packages/components/nodes/agentflow/ConditionAgent/ConditionAgent.ts:415

            if (analyticHandlers && llmIds) {
                const analyticsOutput: any = {
                    content: responseContent
                }
                // Include usage metadata if available
                if (response.usage_metadata) {
                    analyticsOutput.usageMetadata = response.usage_metadata
                }
                // Include response metadata (contains model name) if available
                if (response.response_metadata) {
                    analyticsOutput.responseMetadata = response.response_metadata
                }
                await analyticHandlers.onLLMEnd(llmIds, analyticsOutput, { model: modelName, provider: model })
            }
            let calledOutputName: string
            try {
                const parsedResponse = this.parseJsonMarkdown(responseContent)
                if (!parsedResponse.output || typeof parsedResponse.output !== 'string') {
                    throw new Error('LLM response is missing the "output" key or it is not a string.')
                }
                calledOutputName = parsedResponse.output
            } catch (error) {
                throw new Error(
                    `Failed to parse a valid scenario from the LLM's response. Please check if the model is capable of following JSON output instructions. Raw LLM Response: "${responseContent}"`
                )
            }

            // Clean up empty inputs
            for (const key in nodeData.inputs) {
                if (nodeData.inputs[key] === '') {
                    delete nodeData.inputs[key]
                }
            }

            const matchedScenarioIndex = findBestScenarioIndex(_conditionAgentScenarios, calledOutputName)

            const conditions = _conditionAgentScenarios.map((scenario, index) => {

View on GitHub (pinned to abe4a8601a)

Solutions

1. Reinforce in the system prompt that the JSON must contain an 'output' string key holding exactly one scenario name.
2. Keep the provided few-shot example (which shows {"output": "..."}).
3. Switch to a model with stronger instruction-following or native JSON mode.
4. If you control the LLM tool/structured schema, enforce an 'output' string property.

function extractScenarioOutput(parsed) {
  if (!parsed || typeof parsed.output !== 'string' || parsed.output.length === 0) {
    throw new Error('LLM JSON must contain a non-empty string "output" key')
  }
  return parsed.output
}

function hasStringOutput(parsed) {
  return !!parsed && typeof parsed.output === 'string' && parsed.output.length > 0
}

try { calledOutputName = extractScenarioOutput(parsedResponse) }
catch { /* re-prompt the model with stricter instructions */ }

When it happens

Trigger: LLM returns valid JSON but with a different key (e.g. 'result', 'answer', 'scenario' instead of 'output'); output is a number/boolean; output is an empty string; output is an array of names instead of a single name.

Common situations: Model deviating from the few-shot schema; prompt override dropping the 'output' key requirement; model returning the scenario text under a key it guessed; structured-output schema drift.

Related errors

• Invalid JSON object. Error: ${error}
• Could not find JSON block in the output.
• Failed to parse a valid scenario from the LLM's response. Pl
• Model is required
• Scenarios are required

AI-assisted analysis of FlowiseAI/Flowise@abe4a8601a (2026-08-12). Data as JSON: /api/errors/1512eda9d8aed6d8. Report an issue: GitHub.