安全研究官方发布自动监测

ts-1.15.0

OpenLIT releases published ts-1.15.0. TypeScript SDK 1.15.0 Features Add per-evaluation-type threshold scores and API-key-authenticated create/update endpoints for offline evaluation types. Include thresholdScore in EvalType interface and fetchEvalTypes response. ( 1382 ) Add cached token pricing support across OpenAI, Anthropic, Bedrock, Groq, Google AI,…

原始内容为英文;当前页面提供中文导航与来源说明,具体事实请以原文为准。

人类阅读

为什么值得关注

OpenLIT releases published ts-1.15.0. This release-watch entry was generated from the project's official GitHub release feed and is kept separate from human-reviewed editorial analysis. Release notes: TypeScript SDK 1.15.0 Features Add per-evaluation-type threshold scores and API-key-authenticated create/update endpoints for offline evaluation types. Include thresholdScore in EvalType interface and fetchEvalTypes response. ( 1382 ) Add cached token pricing support across OpenAI, Anthropic, Bedrock, Groq, Google AI, Vertex AI, Azure AI Inference, Claude Agent SDK, Cursor SDK, and Strands. Implement inclusive and exclusive cache token accounting patterns. ( 1390 ) Fixes Fix AssemblyAI cost calculation to use audio duration instead of URL character length. Update wrapper and tests to match Python SDK behavior for per-second billing. ( 1381 )

Agent 解析

可执行摘要

Treat ts-1.15.0 as an official release signal. Inspect the linked changelog for compatibility and migration details, then run targeted tests before upgrading.

Agent 实用度
82/100
可信度
96%
机器格式
JSON + Markdown
下一步

开发者应核对什么

  • Review the official OpenLIT releases release notes before upgrading.
  • Check compatibility, migration, and security notes against your current agent stack.
  • Run focused regression tests before production rollout.
分类

标签与路由

observabilityopentelemetryevaluation
相关信号

继续阅读