FlowiseAI/Flowise · error · ToolInputParsingException

Received tool input did not match expected schema

Error message

Received tool input did not match expected schema

What it means

Thrown inside CodeInterpreterE2B StructuredTool._call when parseWithTypeConversion(this.schema, arg) rejects. Unlike the agentflow/chatflow variants (which throw a plain Error), this one throws ToolInputParsingException with the raw arg passed as the second argument — a LangChain-specific exception that downstream agents can recognize as a 'fix your tool call and retry' signal rather than a fatal error.

Source

Thrown at packages/components/nodes/tools/CodeInterpreterE2B/CodeInterpreterE2B.ts:164

            domainCodeInterpreterE2B: options.domainCodeInterpreterE2B
        })
    }

    async call(
        arg: z.infer<typeof this.schema>,
        configArg?: RunnableConfig | Callbacks,
        tags?: string[],
        flowConfig?: { sessionId?: string; chatId?: string; input?: string; state?: ICommonObject }
    ): Promise<string> {
        const config = parseCallbackConfigArg(configArg)
        if (config.runName === undefined) {
            config.runName = this.name
        }
        let parsed
        try {
            parsed = await parseWithTypeConversion(this.schema, arg)
        } catch (e) {
            throw new ToolInputParsingException(`Received tool input did not match expected schema`, JSON.stringify(arg))
        }
        const callbackManager_ = await CallbackManager.configure(
            config.callbacks,
            this.callbacks,
            config.tags || tags,
            this.tags,
            config.metadata,
            this.metadata,
            { verbose: this.verbose }
        )
        const runManager = await callbackManager_?.handleToolStart(
            this.toJSON(),
            typeof parsed === 'string' ? parsed : JSON.stringify(parsed),
            undefined,
            undefined,
            undefined,
            undefined,
            config.runName

View on GitHub (pinned to abe4a8601a)

Solutions

1. Inspect JSON.stringify(arg) in the exception to see the actual payload.
2. Align the tool description with the schema — make the required 'code' field explicit.
3. Because this is a ToolInputParsingException, let the agent loop retry the tool call after the exception rather than aborting the run.

Example fix

// before
try {
  parsed = await parseWithTypeConversion(this.schema, arg)
} catch (e) {
  throw new ToolInputParsingException(`Received tool input did not match expected schema`, JSON.stringify(arg))
}
// after: surface the parse reason so the agent can self-correct
try {
  parsed = await parseWithTypeConversion(this.schema, arg)
} catch (e) {
  const reason = e instanceof Error ? e.message : String(e)
  throw new ToolInputParsingException(
    `Received tool input did not match expected schema (${reason})`,
    JSON.stringify(arg)
  )
}

function preflightSchema(schema: z.ZodTypeAny, arg: unknown) {
  const r = schema.safeParse(arg)
  if (!r.success) throw new Error(`Preflight schema violation: ${r.error.message}`)
}

function looksLikeToolArg(v: unknown): v is Record<string, unknown> {
  return typeof v === 'object' && v !== null && !Array.isArray(v)
}

// ToolInputParsingException is meant to be caught and retried by the agent loop
try {
  return await e2bTool.invoke(arg)
} catch (e) {
  if (e instanceof ToolInputParsingException) {
    // ask the model to correct the payload, then retry once
  } else throw e
}

When it happens

Trigger: LLM emitted a code string where the schema expected an object, omitted required fields (e.g. the code to execute), or sent malformed JSON.

Common situations: Schema requires { code: string } but the model sends a bare string; model wraps the payload in extra quotes; switching to a model with weaker function-calling.

Related errors

• Received tool input did not match expected schema: ${JSON.st
• Received tool input did not match expected schema: ${JSON.st
• Error parsing Zod Schema: ${exception}
• Received tool input did not match expected schema ${e}
• Unsupported type: ${typeInfo.base}

AI-assisted analysis of FlowiseAI/Flowise@abe4a8601a (2026-08-12). Data as JSON: /api/errors/bea596025571116f. Report an issue: GitHub.