OpenAI发布Agents API托管Agent基础设施
Introducing the Agents API
这是OpenAI在Agent工程化落地上的关键一步，直接解决长周期任务管理的痛点，做Agent基建的同学值得重点关注其架构设计。
Getting a long-running agent into production takes a lot of work, even with a capable model. You need to connect tools, track progress, manage context, and secure and maintain the infrastructure around it. Today, we're launching the Agents API to handle that infrastructure for you. The Agents API brings a hosted version of the Codex harness to your applications. OpenAI handles orchestration, sessions, and context management so that you can stay focused on building.
即使拥有强大的模型，将长期运行的智能体投入生产环境也需要大量工作。你需要连接工具、跟踪进度、管理上下文，并保护和维护其周围的基础设施。今天，我们推出 Agents API 来为你处理这些基础设施。Agents API 将 Codex harness 的托管版本带入你的应用程序。OpenAI 负责编排、会话和上下文管理，让你能够专注于构建。
Let's look at an example. Suppose we want to build an agent that helps investigate incidents in our production stack. It would need access to observability data and recent code changes, along with our team's instructions for how to handle an outage. We can connect all of our necessary tools through MCPs and give the agent our investigation runbook via a skill. You control the agent's execution environment and the tools it has access to.
让我们看一个例子。假设我们要构建一个帮助调查生产栈中事件的智能体。它需要访问可观测性数据和最近的代码更改，以及团队关于如何处理停服事件的指令。我们可以通过 MCP 连接所有必要的工具，并通过技能（skill）将调查手册交给智能体。你控制智能体的执行环境及其可访问的工具。
That includes connecting a sandbox, whether it's through OpenAI, a third-party provider, or using your own infrastructure. In a situation like this, we'd also be working through a ton of logs, likely more than we could fit in the model's context window. With programmatic tool calling, the agent can process those logs and filter the results in code, meaning fewer tokens spent passing around raw data and more spent on the information the agent needs.
这包括连接沙箱，无论是通过 OpenAI、第三方提供商，还是使用你自己的基础设施。在这种情况下，我们还需要处理大量的日志，很可能超出模型上下文窗口的容量。借助编程式工具调用，智能体可以在代码中处理这些日志并过滤结果，这意味着用于传递原始数据的 token 更少，而用于智能体所需信息的 token 更多。
For the largest tasks, independent work can be delegated via multi-agent orchestration. In this case, we might want one sub-agent to examine recent changes, another to check telemetry, and then have the lead agent unify their findings. But even in a single agent session, long-running context windows still work really well with compaction. It gives the model a summary of all prior work completed so the agent can continue its investigation.
对于最大的任务，可以通过多智能体编排委派独立工作。在这种情况下，我们可能希望一个子智能体检查最近的更改，另一个检查遥测数据，然后由主智能体统一它们的发现结果。但即使在单个智能体会话中，长期运行的上下文窗口与压缩（compaction）功能配合也非常有效。它为模型提供之前完成工作的摘要，以便智能体继续进行调查。
Once the work is complete, the findings should be served as a report that the on-call team can review, a likely root cause, the supporting evidence, and suggested next steps bundled into a single shareable file. And there we have it. With the Agents API, we were able to drive an entire workflow without building or maintaining any of our own agent infrastructure. Infrastructure that will continue to get better alongside new models and new capabilities.
工作完成后，调查结果应以报告形式呈现，其中包含值班团队可以审查的可能根本原因、支持证据和建议的后续步骤，并打包成一个可共享的文件。就这样。借助 Agents API，我们能够驱动整个工作流程，而无需构建或维护任何自己的智能体基础设施。该基础设施将随着新模型和新能力的出现而持续改进。
We're excited to bring you an ever-improving harness behind one API. Happy building.
我们很高兴通过一个 API 为你带来不断完善的 harness。祝构建愉快。
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力