https://pypi.org/project/confidence-escalation/ Recent updates to the Python Package Index for confidence-escalation en https://pypi.org/project/confidence-escalation/0.1.0/ Framework-agnostic confidence-gated escalation middleware for LLM agents: multi-signal scoring (logprob, verbalized, tool risk), threshold policies, and escalation handlers for LangChain, CrewAI, AutoGen, and Google ADK. 17191144+ashutoshrana@users.noreply.github.com Mon, 27 Apr 2026 02:31:44 GMT