Tool abstention is advisory
For tool routing (task_type: "tool"), abstain is a hint, not a validated guarantee. On real requests where none of the offered tools applies, Krun One v0 still picks a tool about 39% of the time at the current threshold (BFCL live irrelevance, see Benchmarks).
What to do: keep your own fallback for tool calls, such as argument validation, confirmation before side effects, or a “none of these” path in your agent.
Abstention is calibrated only for label-only intents
abstention_status is calibrated only for intent questions whose options have no descriptions. Intent questions with descriptions, and all tool questions, return advisory. See Abstention.
Confidence is a margin, not a probability of being correct
confidence is the top-1 probability minus the top-2 probability. A confidence of 0.4 does not mean the answer is correct 40% of the time. See Confidence and probabilities.
Probabilities are calibrated on benchmark data
Calibration was measured on public intent and function-calling benchmarks. Text that differs a lot from that data, such as other languages, very long documents or highly specialized domains, can have less reliable probabilities.choice is the only question type
Every question picks exactly one option from 2 to 64 options. Krun does not support multi-label answers, numeric scores, free text or yes/no questions as separate types yet. For a yes/no decision, use a choice question with two options.
Cold starts affect latency
The model runs on serverless GPUs that scale to zero. After a period without traffic, the first request can take noticeably longer, typically tens of seconds, while the model starts. Use a client timeout of about 70 seconds and see Production best practices.Limits per request
Requests over these limits fail with
400 or 413 before any inference runs. See Errors.