OpenAI 公测 Agents API，将 Codex harness 封装为一次 API 调用

OpenAI 发布 Agents API 公测版，向所有开发者开放运行 Codex 的托管 harness 与基础设施。

OpenAI 已在公开测试版中发布 Agents API。它为开发者提供了与运行 Codex 相同的 harness 和基础设施。OpenAI 负责托管和维护该 harness。开发者可以在 OpenAI 管理的沙箱、自己的基础设施或合作伙伴沙箱中运行智能体的计算。

它可以部署吗？可以。它已在公开测试版中面向所有开发者上线。数据仅限美国境内，且不支持零数据保留。

Agents API 是一项基于开源 Codex harness 构建的托管服务。OpenAI 团队表示，为 Work 扩展 Codex 和 ChatGPT 的过程揭示了长时间运行的智能体需要什么。它们需要一个能够管理上下文、高效使用工具并协调子智能体的 harness。它们还需要能够让它们可靠运行数天的基础设施。

官方文档围绕 4 个概念来组织该 API：

一个会话分 4 步运行。你创建会话并给它一个任务。然后你通过流式传输或 webhook 跟进进度。最后，你继续执行新任务或引导当前轮次。

OpenAI 的公告展示了一个通过单次调用创建的事故调查智能体：

import OpenAI from "openai"; const client = new OpenAI(); const session = await client.beta.agents.sessions.create({ agent: { model: "gpt-6-astra", tools: [ { type: "mcp", server_label: "observability", transport: { type: "http", server_url: "https://observability.example.com/mcp", }, }, ], multi_agent: { enabled: true, max_concurrent_subagents: 3 }, }, vault_ids: ["vault_YOUR_VAULT_ID"], environment: { type: "openai_hosted", capability_directories: ["/workspace/capabilities/skills"], }, input: "Investigate service-api's elevated 5xx rate over the last 30 minutes. " + "Delegate deployment, error, and dependency analysis to subagents. " + "Save findings, evidence, and recommended mitigation in /workspace/outputs.", }); 快速入门涵盖了 API 密钥权限和 SDK 设置。

环境选择是主要的架构决策。Agents API 支持 3 种沙箱选项，也可以在没有沙箱的情况下运行。

OpenAI 与其模型一同维护该 harness，并在每次模型发布时提供带版本号的访问方式。

OpenAI 的 运行时对比对这三种方案做了如下定位：

OpenAI 发布了这些由客户报告的数据。它们由厂商提供，并非独立基准测试。

OpenAI has released the Agents API in public beta. It gives developers the same harness and infrastructure that run Codex. OpenAI hosts and maintains the harness. Developers run the agent’s compute in an OpenAI-managed sandbox, their own infrastructure, or a partner sandbox.

Is it deployable? Yes. It is live for all developers in public beta. Data stays US-only, and Zero Data Retention is unsupported.

The Agents API is a managed service built on the open-source Codex harness. OpenAI team states scaling Codex and ChatGPT for Work showed what long-running agents need. They need a harness that manages context, uses tools efficiently, and coordinates subagents. They also need infrastructure that keeps them running reliably for days.

The official docs organize the API around 4 concepts:

A session runs in 4 steps. You create it and give it a task. Then you follow progress through streaming or webhooks. Finally, you continue with a new task or steer the current turn.

OpenAI’s announcement shows an incident-investigation agent created in a single call:

import OpenAI from "openai"; const client = new OpenAI(); const session = await client.beta.agents.sessions.create({ agent: { model: "gpt-6-astra", tools: [ { type: "mcp", server_label: "observability", transport: { type: "http", server_url: "https://observability.example.com/mcp", }, }, ], multi_agent: { enabled: true, max_concurrent_subagents: 3 }, }, vault_ids: ["vault_YOUR_VAULT_ID"], environment: { type: "openai_hosted", capability_directories: ["/workspace/capabilities/skills"], }, input: "Investigate service-api's elevated 5xx rate over the last 30 minutes. " + "Delegate deployment, error, and dependency analysis to subagents. " + "Save findings, evidence, and recommended mitigation in /workspace/outputs.", }); The quickstart covers API key permissions and SDK setup.

Environment choice is the main architectural decision. The Agents API supports 3 sandbox options, and it can also run without a sandbox.

OpenAI maintains the harness alongside its models, with versioned access at each model launch.

OpenAI’s runtime comparison positions the 3 options this way:

OpenAI published these customer-reported numbers. They are vendor-supplied, not independent benchmarks.

来源：MarkTechPost（RSS）· marktechpost.com