OpenAI GPT-6.1 Sol 发布，替代 Astra 的 Codex
OpenAI just launched GPT-6.1 Sol, and for coding it can 𝗿𝗲𝗽𝗹𝗮𝗰𝗲 𝗔𝘀𝘁𝗿𝗮 𝗼𝘂𝘁𝗿𝗶𝗴𝗵𝘁 a…
提供了具体的 AI 工具组合策略与可直接复用的配置代码，结构清晰且有实操细节。
OpenAI just launched GPT-6.1 Sol, and for coding it can 𝗿𝗲𝗽𝗹𝗮𝗰𝗲 𝗔𝘀𝘁𝗿𝗮 𝗼𝘂𝘁𝗿𝗶𝗴𝗵𝘁 at 1/5 the price. OpenAI also announced today that 20x Pro is being cut to 10x. I honestly don't dare use Astra anymore. Switch to 6.1 Sol before Astra eats your whole week.
OpenAI 刚刚发布了 GPT-6.1 Sol，在编码方面，它的价格仅为 Astra 的五分之一，却能直接取代 Astra。 OpenAI 今天还宣布将 Pro 版的 20x 额度削减至 10x。说实话，我都不敢再用 Astra 了。在 Astra 吃掉你整整一周的时间之前，赶紧切换到 6.1 Sol。
6.1 Sol is already in Codex. Set it up like the tree: 6.1 Sol runs the root orchestrator and all three subagents, and Astra only does an independent review before a big change ships. Reasoning effort comes from OpenAI's DeepSWE chart: 6.1 Sol scores highest on high, and 𝗴𝗼𝗶𝗻𝗴 𝘂𝗽 𝘁𝗼 𝘅𝗵𝗶𝗴𝗵 𝗼𝗿 𝗺𝗮𝘅 𝗮𝗰𝘁𝘂𝗮𝗹𝗹𝘆 𝘀𝗰𝗼𝗿𝗲𝘀 𝗹𝗼𝘄𝗲𝗿, so the orchestrator runs on high. Medium scores only about 2 points lower than high and costs over 30% less per task, so the subagents run on medium.
6.1 Sol 已经可以在 Codex 中使用。按照树状结构进行设置：6.1 Sol 运行根编排器（root orchestrator）和所有三个子代理（subagents），而 Astra 仅在大版本发布前进行独立审查。推理力度（Reasoning effort）参考 OpenAI 的 DeepSWE 图表：6.1 Sol 在高（high）档位得分最高，且𝗴𝗼𝗶𝗻𝗴 𝘂𝗽 𝘁𝗼 𝘅𝗵𝗶𝗴𝗵 𝗼𝗿 𝗺𝗮𝘅 𝗮𝗰𝘁𝘂𝗮𝗹𝗹𝘆 𝘀𝗰𝗼𝗿𝗲𝘀 𝗹𝗼𝘄𝗲𝗿（即提升至 xhigh 或 max 实际得分反而更低），因此编排器运行在高（high）档位。中（medium）档位的得分仅比高（high）低约 2 分，但每项任务的成本降低超过 30%，因此子代理运行在中（medium）档位。
Send the tree and this prompt to Codex 👇
将树状结构和以下提示词发送给 Codex 👇
"Set up my Codex to match this tree: → Main session: default to `gpt-6.1-sol` on high reasoning effort. It breaks down tasks, delegates, integrates, and verifies. Handle simple tasks directly; don't delegate them. → Three project-level custom agents, each with model `gpt-6.1-sol` and model_reasoning_effort `medium`: explorer reads code, worker edits code and runs tests, researcher looks up docs. Reuse fitting ones if they exist, and create only the missing ones. → reviewer: also a project-level custom agent, with model `gpt-6-astra` and model_reasoning_effort `xhigh`. Call it only before a big change ships. It reports problems and doesn't edit code. → Put the delegation rule in AGENTS.md: when spawning a subagent, set `fork_turns` to `"none"` or pass only the last few turns. If `fork_turns` is omitted or set to `"all"`, the subagent inherits the main session's model and effort and can't override them, and the tree stops working.
"将我的 Codex 设置为匹配此树状结构： → 主会话（Main session）：默认使用 `gpt-6.1-sol`，推理力度设为 high。它负责分解任务、委派、集成和验证。直接处理简单任务；不要委派它们。 → 三个项目级自定义代理（custom agents），每个代理的模型均为 `gpt-6.1-sol`，推理力度为 `medium`：explorer 读取代码，worker 编辑代码并运行测试，researcher 查阅文档。如果存在合适的代理则复用，仅创建缺失的代理。 → reviewer：也是一个项目级自定义代理，模型为 `gpt-6-astra`，推理力度为 `xhigh`。仅在大版本发布前调用它。它负责报告问题，不编辑代码。 → 将委派规则写入 AGENTS.md：在生成子代理时，将 `fork_turns` 设置为 `"none"` 或仅传递最后几次对话轮次。如果省略 `fork_turns` 或将其设置为 `"all"`，子代理将继承主会话的模型和力度，且无法覆盖它们，这将导致树状结构失效。"
Before changing anything, check: → Roles other than the reviewer that still use `gpt-6-astra` or an older Sol (like `gpt-6-sol` or `gpt-5.6-sol`). List them. → Roles moving to 6.1 Sol with effort set to `none` or `minimal`: change them to `low` (6.1 Sol supports neither), then compare the results. → Model assignments written only in AGENTS.md: check recent subagent session logs to confirm which model each role actually ran.
在进行任何更改之前，请检查： → 除 reviewer 外，仍在使用 `gpt-6-astra` 或较旧 Sol 版本（如 `gpt-6-sol` 或 `gpt-5.6-sol`）的角色。列出它们。 → 正在迁移至 6.1 Sol 且力度设置为 `none` 或 `minimal` 的角色：将它们改为 `low`（6.1 Sol 不支持前者），然后比较结果。 → 仅在 AGENTS.md 中编写的模型分配：检查最近的子代理会话日志，以确认每个角色实际运行的模型。
If you can't select a model in the tree, stop and ask me. Show me the changes first, and wait for my OK before writing anything."
如果你无法在树状结构中选择一个模型，请停止并询问我。先向我展示更改内容，并在编写任何内容之前等待我的批准。"
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