GPT Chat Task (LLM Task)

Parameters

# messages

optional

array

An array of message objects. The messages to submit for a chat completion. The messages in the array should be sorted ascending chronologically, meaning that the message at the first index in the array should be the earliest message, and the last message in the array should be the latest.

Each chat has an array of messages that is automatically handled by the Stubber system. When there is a back and forth discussion between an assistant and a user, the messages are appended to this array, unless the message_operation is set, then the messages are overwritten by the messages of the current task.

Default: []

# message_operation

optional

string

This can be either set or append. It defines the operation to use for the messages in the active chat (via gptchattaskuuid). The set operation erases the previous messages of the chat and sets the messages passed in this instance of the task as the messages for the chat completion. The append operation appends the messages of the current task to the existing messages in the chat.

Default: append

# model

optional

string

The model that the task should use to do this specific instance of chat completion. If it is the first instance of a chat, the model will be saved for next instances in the same chat. This parameter is thus not required, but recommended for at least the initial chat to set the desired model.

See Models for a full list of supported models.

Default: [changes based on current models available]

# submit_to_model

optional

boolean

Whether or not the task should actually submit the messages to the model/assistant for a response. This could be useful to set to false when a chat should be initiated by the assistant with a default message. Example:

Default: true

# set_model

optional

boolean

Override the model in the specific chat with this model. This will change the model for future chat instances in cases where the specific model is not specified. If a single task has model and set_model, the set_model model will be used

Examples:

• gpt-4o

Default: null

# gptchattaskuuid

optional

array

The gptchattaskuuid is the globally unique reference used inside Stubber to keep track of the specific details of a chat, such as the model details, the previous messages, token usage etc. This is by default a deterministic uuid generated from the stub's stubref, such that each stub automatically has a unique chat. It is only required to specify this if you want fine grain control over which GPT tasks should use which chats across various stubs. If you want multiple different chats on a single stub, use chat_name instead.

Default: {{#deterministicuuid stub.stubref}}

# chat_name

optional

array

The human readable name of the chat, such as "supervisor" or "contractor". Each chat has a unique id, gptchattaskuuid, that is used to enable tasks to keep appending messages and instructions to the same chat, continuously building on the chat context. This unique id is generated with a combination of the stubref and the chat_name. Chats happening on different stubs are thus automatically different. If you want to have different chats on the same stub, you have to give each chat its own chat_name, and then use this chat_name in all usages of the gpt_chat_task for that chat.

Default: ""

# function_call

optional

string or object

This parameter determines whether functions will be added to the chat completion task. With this parameter set to auto, the assistant will automatically choose when to call a function, and which function to call. If the assistant calls a function and everything is set up correctly, as described here, the action with the same name as the function will be run on the stub of the chat.

Force an action This parameter can be used to force a specific action to be run. This can be done by specifying the parameter as an object {"name": "get_weather"}. This example will force the assistant to call the get_weather action.

Prevent actions To prevent the model from calling any actions, set this parameter to false.

Default: auto

# tool_choice

optional

string or object

This parameter determines whether tools will be used in the chat completion task when function_method is set to tools. With this parameter set to auto, the assistant will automatically choose when to use a tool, and which tool to use. If the assistant uses a tool and everything is set up correctly, the action with the same name as the tool will be run on the stub of the chat.

Force a specific tool This parameter can be used to force a specific action to be run. This can be done by specifying the parameter as an object {"type": "function", "function": {"name": "get_weather"}}. This example will force the assistant to call the get_weather action.

Prevent tools To prevent the model from using any tools, set this parameter to "none".

Default: auto

# functions

optional

array

An array of function objects to make available to the assistant. It is important to note that actions with the action_meta containing ai_function_calling: true, will be added to the functions the assistant has access to automatically.

This parameter should only rarely be required. Below is an example of a single function object:

Function objects that are generated automatically from actions have the same structure. The fields of the action becomes the properties, the help of each field becomes the description of the property. The name of the action becomes the name of the function. The description of the action becomes the description of the function.

Default: null

# tools

optional

array

An array of tool objects to make available to the assistant. This parameter is used when the function_method is set to tools. It is important to note that actions with the action_meta containing ai_function_calling: true, will be added to the tools the assistant has access to automatically.

This parameter should only rarely be required. Below is an example of a single tool object:

Tool objects that are generated automatically from actions have the same structure as function objects. The fields of the action becomes the properties, the help of each field becomes the description of the property. The name of the action becomes the name of the function. The description of the action becomes the description of the function.

Default: null

# temperature

optional

array

This is a parameter to change the consistency of the response of the assistant. Lower values, such as 0.15, result in more consistent responses. Higher values, such as 0.80, will generate more creative and diverse results.

Default: null

# reasoning_effort

optional

string

Controls the amount of reasoning tokens used by models that support reasoning. This parameter determines how much computational effort the model dedicates to thinking through the problem before responding.

Available levels:

• "low": 1,024 reasoning tokens - faster, suitable for simpler tasks
• "medium": 8,192 reasoning tokens - balanced approach for most use cases
• "high": 24,576 reasoning tokens - maximum reasoning depth for complex problems

Default: null

# include_attachments

optional

object

This parameter can be used to automatically add files and images to the messages of the chat. File examples can be images, videos, PDFs, and audio files. This is useful for LLMs that support multimodal interactions, such as images or other supported files, that are not part of the regular messages.

The parameter takes an object with two properties:

• include_method: either "prepend" or "append" to control where attachments are added
• attachments: an array of objects where each object needs to have a fileuuid property

Use this to:

• add images to the LLM chat context
• add videos to the LLM chat context for models that support video (Like Gemini)
• add PDF files to the LLM chat context for models that support PDF files (Like Gemini, Claude)
• add audio files to the LLM chat context for models that support audio files

Multimodal models are a powerful way to enhance the interaction with the assistant, as they can understand and respond to images, videos, and other file types. Use this parameter to add these files to the chat context easily.

Parameter Examples:

Prepend the attachments of the current stub post:

Append files from the current stub:

Prepend a single file with a specific fileuuid:

When using "prepend", attachments will be inserted just before the last message in the messages array. When using "append", attachments will be added at the end of the messages array.

Example of included file in the messages

Default: null

# function_method

optional

string

The method to use for function calls, this can be either tools or functions. These two methods are not interchangeable in the same chat, if you use a specific function_method in a chat, you have to use the same method for all tasks in that chat.

The default function_method for all models released from May 2025 onwards is tools. The default function_method for all models released before May 2025 is functions.

Default: null

# max_tokens

optional

integer

The maximum tokens that the assistant can respond with. In general this is not required, and should mainly be used if an abnormally short response is required.

Default: null

# set_system_message

optional

string

The system message passed here will replace the system message in the existing chat. It will remain the system message for all subsequent chats in the same conversation. So it will not last just a single task instance, but will be the new system message until it is changed again.

Default: null

# penultimate_system_message

optional

object

An object that defines a system message to be injected just before the last user message in the conversation. This is useful for providing last-minute instructions or context to the model immediately before it processes the user's final message.

The object has two properties:

• enabled: a boolean that controls whether the message should be injected
• message: the system message string to inject

This setting is sticky — once set, it will persist for all subsequent tasks in the same chat until it is changed or disabled by explicitly setting enabled to false.

If there is no user message in the conversation, the system message will be appended to the end of the messages array instead.

Default: null

# response_format

optional

object

This works for models that support this feature. For the assistant to respond in only json, this parameter has to be set to {"type": "json_object"}, and you have to mention the word "json" somewhere in the system message.

Default: null

# extract_data_from_message

optional

boolean

Set this to false if you do not want the model to extract tags such as <thinking>...</thinking> or <span>...</span> as data points. This is required if you attempt to force the model to respond in HTML, since all tags will be extracted as data points and be removed from the message.

Default: true

# disable_model_response

optional

boolean

When this is set to true, the task will not publish the feedback action, by default _update_from_chat_assistant_task. The task can still execute actions, which can be disabled with disable_model_action_execution.

Default: false

# disable_model_action_execution

optional

boolean

Controls whether the LLM model can execute Stubber actions. When set to true, the model will still see available functions/tools (actions marked with ai_function_calling: true in their action_meta), and can choose to call them, but Stubber will not convert these function calls into actual action executions.

This parameter is useful for testing function calling behavior without triggering real actions in the system, or if you want the model to provider specific structured data with a custom function.

Default: false

# assistant_response_action_name

optional

string

The feedback action that the task will call with the result of the chat completion.

Default: _update_from_chat_gpt

# set_assistant_response_action_name

optional

string

This will set the feedback action that the task will call with the result of the chat completion. This will be the feedback action for all future tasks in the chat.

Default: null

# append_response_to_messages

optional

string

Each chat has an array of messages that is automatically handled by the Stubber system. When there is a back and forth discussion between an assistant and a user, the messages are appended to this array, unless the message_operation is set, then the messages are overwritten. When append_response_to_messages is false, the response of the assistant is not appended to the array of messages of the chat.

Default: true

# stop_on_high_messages

optional

integer

boolean

Controls the maximum number of messages allowed in a single chat conversation before the task is blocked. This count includes all message types (user, system, assistant) present in the chat at the time of execution.

This parameter serves as a failsafe mechanism to prevent infinite conversations, particularly in bot-to-bot interactions. The default limit is set to 200 messages, which can be:

• Increased by specifying a higher number
• Disabled by setting to false (not recommended)
• Reset by using message_operation: "set" to clear previous messages

The default limit is intentionally conservative since model performance can degrade with very long message histories. It's recommended to periodically reset the conversation using message_operation: "set" rather than significantly increasing this limit.

Examples:

• false - Disables the message limit check
• 500 - Sets a custom message limit
• true - Uses the default limit (200)

Default: 200

# stop_on_high_interactions

optional

string

Controls the maximum number of model interactions allowed for a specific chat (identified by chat_name) before the task is blocked. An interaction is counted each time the chat communicates with the model, regardless of the number of messages exchanged.

This parameter provides an additional failsafe layer that:

• Persists across message resets (unlike stop_on_high_messages)
• Cannot be reset by clearing messages
• Helps prevent infinite loops in automated conversations

The interaction counter:

• Increments with each model call
• Persists even when messages are cleared via message_operation: "set"
• Is specific to each unique chat

Examples:

• false - Disables the interaction limit check
• 500 - Sets a custom interaction limit
• true - Uses the default limit (1000)

Default: 1000

# action_call_result_method

optional

string

By default, when the assistant decides to run an action, a dynamic task is added to that action to return the result of the action back to the assistant, allowing the assistant to respond on the result of the action it initiated. A custom dynamic task can be passed instead of the default one by setting this parameter to custom.

Default: null

# dynamic_tasks

optional

array

The tasks to dynamically add to an action that the assistant has chosen to run. The default task that is added, return_gpt_function_data, returns the result of the action, the stubpost, to the assistant. The assistant will then respond normally with the passed feedback action, by default _update_from_chat_assistant_task.

This parameter is only used if action_call_result_method is set to custom. If it is specified as custom, only the tasks specified in dynamic_tasks will be added to the action.

Default: