On October 1, the Earendil team released the Agent Harness Pi 1.0, with roughly 11.1 stars and 1.4 forks on GitHub, plus an experimental new package called Pi Durable.
Why it matters: Pi 1.0 and Pi Durable bring distributed concepts like checkpoints, idempotent commits, and ownership trees into the Agent runtime, which you can use to weigh the engineering trade-offs of long-running Agents.
Гига Писарь 为 Mac 端推出其史上最明显的更新，设置窗口按 macOS 系统设置风格完全重做，用左侧分区、卡片和图片取代原来的四个标签页与表格。新增「Мозг」区域可用 GigaChat 或 Qwen 本地模型改写听写文本，本地模型约 2GB 起、可一键删除，并支持多个云端服务按各自密钥切换。更新提示改为菜单栏图标上的小红点，不再弹出窗口打断用户。
Awaiting translation
Cloudflare 正式发布 Vinext 1.0，用 Vite 重新实现了一套高度兼容 Next.js 的运行时，把 App Router、Pages Router、RSC、Server Actions、Middleware、ISR 等能力重新实现，官方称核心高频功能测试兼容度超过 99%，但 Cache Components 尚未完全覆盖。
Awaiting translation
OpenAI 发布 GPT-6 Sol 和 Luna，Sol 定价 $2/$10 MTok、约为 GPT-5.6 的一半，DeepSWE 68.8%，Luna 定价 $0.10/$0.50 MTok。
Awaiting translation
Lovable has released OJ, a preview engine written from scratch in Rust. It reads your existing vite.config.ts and runs real Vite plugins through a compatibility layer, all in a single binary, with no toolchain installed into the project.
Why it matters: Lovable rewrote its preview engine OJ in Rust, sharing cold start and memory comparisons against Vite, plus canary data from production.
Steve Yegge 宣布 Gas Town 和 Beads 同日发布 v1.0.0。Beads 是面向编码智能体的记忆系统与知识图谱，v1.0 用 Dolt 替换了原先 SQLite + JSONL 的架构，双向同步、三方合并和合并冲突等问题被移除，同时支持嵌入式和服务器模式，本周 GitHub star 数突破 20k。
Awaiting translation
Terminal-Bench has released version 2.0 and the Harbor package. The former is a more rigorously validated, harder benchmark for evaluating agents; the latter is for evaluating and optimizing agents. Harbor rewrites Terminal-Bench's test harness, supports deploying containers in the cloud, provides rollout interfaces for RL and SFT, and works with any agent you can put in a container.
Why it matters: Terminal-Bench 2.0 and Harbor are released together, so readers can see how the agent evaluation benchmark is validated and how to scale it in the cloud.
Terminal-Bench 新增 parallelize-graph 和 feal-linear-cryptanalysis 两个高难度任务，分别要求智能体用 Unified Parallel C 实现基因组组装的并行 de Bruijn 图构建，以及对 FEAL 类分组密码实施已知明文线性密码分析攻击。
Awaiting translation
Terminal-Bench 发布首个版本，用于量化 AI 智能体在终端中执行复杂任务的能力，首发数据集 Terminal-Bench-Core-v0 包含 80 个手工编写并人工验证的任务，每个任务配有独立 Docker 环境、人工验证的解法与测试用例。
Awaiting translation
Why it matters: Terminal-Bench 给出 80 个带 Docker 环境和测试用例的终端任务，可用来横向比较不同智能体在命令行中的实际表现。