Product Feedback: maxSteps reached termination is not obvious in the logs
AgentTools
Hello everyone 
Thanks to the Mastra Team, you're doing a great job, it's a pleasure to work with your framework everyday !! Typescript will soon rule the AI Kingdom
Quick product feedback though : when an agent fails due to Max Steps reached, the failure is quite silent and can lead to a llooooonnnngggg investigation figuring out what's wrong.
It occured to me already a couple of times (few hours scratching my head about why is this stupid LLM stubbornly stopping on Step 4+ after spending 1$ !! ) . Since LLMs are not determinist, troubleshooting is not obvious, it does not fail always at the same business step
- I use Mastra standalone w/ Next, out of Mastra server environment,
- And Langfuse for observability
I may be missing something but there is no Error thrown, neither an obvious message appened to the message stream.
Does anyone share this feedback as well ?
Thanks to the Mastra Team, you're doing a great job, it's a pleasure to work with your framework everyday !! Typescript will soon rule the AI Kingdom
Quick product feedback though : when an agent fails due to Max Steps reached, the failure is quite silent and can lead to a llooooonnnngggg investigation figuring out what's wrong.
It occured to me already a couple of times (few hours scratching my head about why is this stupid LLM stubbornly stopping on Step 4+ after spending 1$ !! ) . Since LLMs are not determinist, troubleshooting is not obvious, it does not fail always at the same business step
- I use Mastra standalone w/ Next, out of Mastra server environment,
- And Langfuse for observability
I may be missing something but there is no Error thrown, neither an obvious message appened to the message stream.
Does anyone share this feedback as well ?
