写作

OpenAI organization-level data suggests that more coding-agent use shifts bottlenecks to task decomposition, concurrency, harnesses, evaluation, and selection.

Strands harness-sdk, Harness MCP Server, and HydraFusion show why agent engineering needs control over context, permissions, state, validation, and recovery.

从 Strands harness-sdk、Harness MCP Server 和 HydraFusion 看 Agent 工程为什么从模型调用转向上下文、权限、状态、验证与恢复控制。

Coding agents read and execute skills, MCP tools, dependencies, and repository instructions. These need software supply-chain controls.

说明 Coding Agent 会读取并执行 Skill、MCP、依赖和仓库指令，因此这些组件应按软件供应链治理，而不只是做 Prompt 安全。

How GitHub Agentic Workflows puts judgment-based automation inside GitHub Actions while retaining permissions, controlled outputs, approval, and security.

介绍 GitHub Agentic Workflows 如何把需要判断的自动化放进 GitHub Actions，同时保留权限、输出、审批和安全边界。

A multi-agent engineering workflow uses isolated worktrees, CI, cold-start review, evidence gates, and layered context to control delivery of AI-generated code.

介绍一个多 Agent 工程工作流，如何用独立 worktree、CI、冷启动审查、证据门和分层上下文控制 AI 生成代码的交付。

VEP/1 turns images into short evidence packets. Provider fallback, caching, and credential storage manage cost and reliability for text agents.

通过 VEP/1 把图片转换成短证据包，并用 Provider fallback、缓存和凭据存储控制文本 Agent 的视觉输入成本与可靠性。

A Hermes MiniMax plugin with image-01, Hailuo async video tasks, CN/global endpoint fallback, end-to-end tests, and a PyPI release.