How do you handle the risk of stripping out the exact stack trace the agent needed? That seems like the hard tradeoff here.

▲

zdkaster 2 hours ago | parent | next [-]

It has the strip aggressiveness level suport. You can tune up 3 levels for each template output of your stacktrace using lowfat-filter dsl, shellscript or python.

▲

ramon156 2 hours ago | parent | prev | next [-]

In a perfect world the LLM needs to be very explicit on what it wants to read

	▲	nixpulvis 2 hours ago \| parent [-]
		The LLMs already do that themselves with `tail` all the time. There's a lot of room for improvement on top of that. Though they usually figure it out after a few tries. I often just paste manual runs errors myself anyway.

▲

itsthecourier 3 hours ago | parent | prev [-]

gonna ask the same... do far it's has been manually choosing what's useful in each command for the agents?

	▲	zdkaster an hour ago \| parent [-]
		It requires a bit effort in doing long-term adjustment and tuning for your agent common cli tools commands called. kinda need to evolve on day-to-day basis. But, agent itself can be useful to help tuning this.