Progress and error messages
Note: Progress messages, error messages, and empty LLM response handling all apply to regular (non-speech-to-speech) models. For speech-to-speech models, see Inactivity reminder. Max turns applies to both.
Progress message
Sometimes it may take the Agent too much time to generate response, for example, due to use of multiple tools or slow tool response. In such cases, consider using 'Progress message' and 'Progress timeout' parameters in the Miscellaneous tab to define progress message that will be played to user while agent is “thinking”.
- 'Progress timeout defines timeout in milliseconds' after which progress message will be played.
- 'Progress message defines message' that will be played.
- you may specify a single message. For example:
Let me think - you may specify multiple messages separated by comma and Agent will randomly choose one of them. For example:
Let me think, Just a moment - to specify single message that includes comma, enclose it in quotes. For example:
"umm, let me think" - to specify multiple messages where at least one of them includes commas, use JSON list syntax. For example:
["umm, let me think", "thinking"]
- you may specify a single message. For example:
- For multi-agent topologies 'Progress message' and 'Progress timeout' may be specified at "top-level" agent or at any "child" agent. "Child" agents that lack custom configuration inherit parameter values from the "top-level" agent.
In addition to the time-based progress message described above, you can configure progress messages per tool — played before, on success, or on failure of that specific tool's execution — on the tool's Progress tab. See Tool progress messages.
Alternatively, you can play progress messages when specific tools are called using the legacy progress_message_conditions advanced configuration parameter. For details, see Conditional progress messages when calling tools.
How progress messages interact with the model's own speech
An agent has three ways to keep the user engaged while it works, and the framework coordinates them so it never talks over itself:
- the time-based progress message above (played when the whole turn is slow);
- per-tool messages — During execution / On success / On failure (see Tool progress messages);
- dynamic per-tool progress messages — the agent generates that tool's During execution line itself, based on the state of the conversation (see Letting the model write the message).
When the model speaks its own message alongside a (non-terminal) tool call, that message already fills the pre-tool wait, so the framework suppresses the redundant pre-tool reassurance for that step:
- the time-based progress message is not played, and
- that tool's During execution message is not played.
Everything else is unaffected: the tool's On success / On failure messages still play (they report the outcome, not the wait), and a different tool called later in the same turn — one with no accompanying message — still plays its own During execution message. Per-tool messages can play more than once per turn; the time-based message plays at most once.
Whether the model's message actually reaches the user on a non-streaming connection is controlled by the llm_message_with_tool_call advanced configuration parameter (play delivers it, drop discards it). With TTS streaming it is always delivered. If the message is dropped, nothing filled the wait, so the pre-tool reassurance is not suppressed.
Call-control tools. end_call and transfer_call are the exception. Any message the model wants spoken before hanging up or transferring comes from the tool's own termination_message / transfer_message parameters (not from llm_message_with_tool_call), and these tools end or transfer the turn — so they don't use the Before / On success / On failure progress scheme.
Pause after a progress message
On voice calls, when the agent's response is ready while a progress message is still playing, the response waits for the progress message to finish and then for a short pause, so that the two don't run together. The pause is 500 msec by default; change it with the progress_message_pause advanced configuration parameter:
| Parameter | Type | Description |
|---|---|---|
progress_message_pause
|
int | Pause in milliseconds between a progress message and whatever the agent plays after it. Optional, default is 500, range is 0 to 5000. 0 disables the pause. |
For example:
{
"progress_message_pause": 800
}
The pause follows any kind of progress message – time-based, per-tool or conditional – and applies to whatever is played next, another progress message included.
Error message
If Live Hub AI Agents Framework fails to receive valid response from LLM or encounters some other unexpected error, it generates “error response” to user. The default value for this response is “Sorry, I didn't get it. Can you please say it again?”
You may change the value by configuring ‘Error message’ parameter in the Miscellaneous tab, in the Agent configuration screen. For example:
Sorry, can you please rephrase your last question?
Max turns
When a conversation exceeds the agent's ‘Max utterances’, the agent does not hang up straight away. It sends the model a reminder, asking it to wrap up the conversation and end the call itself – for example, by saying goodbye and hanging up. If the model is still going grace_turns responses later, the call is ended for it.
- With regular models, a turn is a user utterance, and the reminder is added to each of the user's utterances from then on, until the call ends.
- With speech-to-speech models, a turn is a model response, and the reminder is sent to the model as soon as it finishes the response that exceeded the limit.
Customize this behavior with the max_turns_reminder advanced configuration parameter:
| Parameter | Type | Description |
|---|---|---|
text
|
str | Reminder text sent to the model. Optional, defaults to NOTE: This conversation has gone on for too long. Politely wrap it up and end the call. |
grace_turns
|
int | Number of model responses, counting the response to the reminder itself, within which the model should end the call. Optional, default is 2, maximum is 10. 0 ends the call as soon as the limit is exceeded, without a reminder. |
For example:
{
"max_turns_reminder": {
"text": "NOTE: The call is running long. Offer to help with anything else briefly, then say goodbye and end the call.",
"grace_turns": 3
}
}
To customize the response provided to the user when the call is ended for the model, specify the max_turns_message advanced configuration parameter. It replaces the model's last response, and is not supported for speech-to-speech models:
{
"max_turns_message": "Sorry, I need to hang up."
}
When the agent hands the conversation over to another agent during the grace period, the grace period continues – the next agent does not get a fresh ‘Max utterances’ allowance. A response given by a consulted sub-agent counts as a turn of the agent that consulted it. Amazon Nova Sonic v1 cannot receive the reminder, so it ends the call as soon as the limit is exceeded.
Note: Flows do not support max_turns_reminder. A flow is closed as soon as it exceeds its ‘Max utterances’, with max_turns_message as its response.
Empty LLM responses
Some LLMs may produce empty responses due to various technical issues or intermittent processing errors. By default AI Agents perform automatic retry upon empty LLM response, thus ensuring that conversation continues smoothly and user experience is not disrupted. You may change this behavior by configuring empty_llm_response advanced configuration parameter.
| Parameter | Type | Description |
|---|---|---|
empty_llm_response
|
enum | Configures how the AI Agent treats empty LLM response. Supported values: • retry (default) – retry response generation; if response is still empty after the retry, treat it as an error• ignore – treat empty response as an error• allow – treat empty response as a valid response |