FlowiseAI/Flowise · error · Error

This agent only compatible with function calling models.

Error message

This agent only compatible with function calling models.

What it means

Worker's createAgent helper throws when `llm.bindTools === undefined` after assembling its prompt and splicing in any multimodal message template. The worker agent uses `llm.bindTools(tools)` to construct the tool-calling chain; without bindTools the agent cannot invoke its tools.

Source

Thrown at packages/components/nodes/multiagents/Worker/Worker.ts:200

            new MessagesPlaceholder('agent_scratchpad')
            /* Gettind rid of this for now because other LLMs dont support system message at later stage
            [
                'system',
                [
                    'Supervisor instructions: {instructions}\n' + tools.length
                        ? `Remember, you individually can only use these tools: ${toolNames}`
                        : '' + '\n\nEnd if you have already completed the requested task. Communicate the work completed.'
                ].join('\n')
            ]*/
        ])

        if (multiModalMessageContent.length) {
            const msg = HumanMessagePromptTemplate.fromTemplate([...multiModalMessageContent])
            prompt.promptMessages.splice(1, 0, msg)
        }

        if (llm.bindTools === undefined) {
            throw new Error(`This agent only compatible with function calling models.`)
        }
        const modelWithTools = llm.bindTools(tools)

        let agent

        if (!workerInputVariablesValues || !Object.keys(workerInputVariablesValues).length) {
            agent = RunnableSequence.from([
                RunnablePassthrough.assign({
                    //@ts-ignore
                    agent_scratchpad: (input: { steps: ToolsAgentStep[] }) => formatToOpenAIToolMessages(input.steps)
                }),
                prompt,
                modelWithTools,
                new ToolCallingAgentOutputParser()
            ])
        } else {
            agent = RunnableSequence.from([
                RunnablePassthrough.assign({

View on GitHub (pinned to abe4a8601a)

Solutions

1. Choose a tool-calling-capable model for any worker that has tools.
2. If the worker has no tools, consider a code path that skips bindTools (requires a code change).
3. Ensure the LangChain model package version exposes bindTools.
4. Validate at flow-save: refuse to attach tools to a non-tool-calling model.

Example fix

// before
if (llm.bindTools === undefined) {
  throw new Error(`This agent only compatible with function calling models.`)
}
// after
if (typeof llm.bindTools !== 'function') {
  throw new Error(`Worker needs a tool-calling model. ${llm?.constructor?.name ?? 'Model'} does not implement bindTools.`)
}

if (typeof llm.bindTools !== 'function') {
  throw new Error('Worker requires a tool-calling model.')
}

const isToolCallingModel = (m: any): boolean => typeof m?.bindTools === 'function'

When it happens

Trigger: Passing a non-function-calling model to a Worker that has tools attached; using a model integration that lacks bindTools in the installed LangChain version.

Common situations: Authoring a tool-using worker against a base/text-only model; downgrading LangChain; mixing in a custom model class.

Related errors

• This agent only compatible with function calling models.
• Agent needs to have a function calling capable models.
• This agent requires that the "bindTools()" method be impleme
• This agent requires that the "bindTools()" method be impleme
• Supervisor name is required!

AI-assisted analysis of FlowiseAI/Flowise@abe4a8601a (2026-08-12). Data as JSON: /api/errors/9e93ca61410b2e1e. Report an issue: GitHub.