FlowiseAI/Flowise · error · Error

Invalid JSON in the ChatPromptTemplate's promptValues: ${exc

Error message

Invalid JSON in the ChatPromptTemplate's promptValues: ${exception}

What it means

ChatPromptTemplate.init parses `nodeData.inputs?.promptValues` as JSON when it is a string. If the user typed invalid JSON, JSON.parse throws and the catch rethrows with this message.

Source

Thrown at packages/components/nodes/prompts/ChatPromptTemplate/ChatPromptTemplate.ts:156

                if (!Array.isArray(parsedResponse)) {
                    throw new Error('Returned message history must be an array')
                }
                prompt = ChatPromptTemplate.fromMessages([
                    SystemMessagePromptTemplate.fromTemplate(systemMessagePrompt),
                    ...parsedResponse,
                    HumanMessagePromptTemplate.fromTemplate(humanMessagePrompt)
                ])
            } catch (e) {
                throw new Error(e)
            }
        }

        let promptValues: ICommonObject = {}
        if (promptValuesStr) {
            try {
                promptValues = typeof promptValuesStr === 'object' ? promptValuesStr : JSON.parse(promptValuesStr)
            } catch (exception) {
                throw new Error("Invalid JSON in the ChatPromptTemplate's promptValues: " + exception)
            }
        }
        // @ts-ignore
        prompt.promptValues = promptValues

        return prompt
    }
}

module.exports = { nodeClass: ChatPromptTemplate_Prompts }

View on GitHub (pinned to abe4a8601a)

Solutions

Use valid JSON with double-quoted keys and string values.
Pass an actual object (from a previous node) to skip the parse path.
Validate the JSON in an external linter first.
Improve the error to include the parse offset and a snippet of the input.

Example fix

// before
promptValues = typeof promptValuesStr === 'object' ? promptValuesStr : JSON.parse(promptValuesStr)
// after
if (typeof promptValuesStr === 'string') {
  try { promptValues = JSON.parse(promptValuesStr) }
  catch (e) { throw new Error(`promptValues JSON parse failed: ${(e as Error).message}. Input: ${promptValuesStr.slice(0,120)}`) }
} else promptValues = promptValuesStr

Defensive patterns

Strategy: validation

Validate before calling

function parseJsonOrThrow(s: string, label: string): ICommonObject {
  try { return JSON.parse(s) }
  catch (e) { throw new Error(`${label} invalid JSON: ${(e as Error).message}`) }
}

Type guard

const isJson = (s: string): boolean => { try { JSON.parse(s); return true } catch { return false } }

Prevention

Use double-quoted JSON keys and string values.
Pass objects between nodes to skip parsing.
Lint before pasting.

When it happens

Trigger: promptValues field contains malformed JSON — single quotes, trailing commas, unquoted keys, JS object literal syntax.

Common situations: Manually typing prompt values in the node UI; passing values from an expression that did not JSON-encode; copy-paste from a JS source file.

Understand the failure class

Parsing and encoding errors: unexpected token, malformed input — why parsers reject input and how to find the real culprit.

Related errors

AI-assisted analysis of FlowiseAI/Flowise@abe4a8601a (2026-08-12). Data as JSON: /api/errors/43d5b18942089307. Report an issue: GitHub.