Ollama v0.40.14 更新 Claude Code 限制与 API 行为
AI 总结
据 Ollama 发布说明,v0.40.14 让 Claude Code 启动流程采用各模型的输出令牌上限,并在配置 Codex 前检查 ChatGPT 路由。该版本还修复了 /api/chat 云端网页搜索响应的解码、Responses 端点的可读输入保留、OpenAI 兼容端点的打包采样默认值,以及 Ollama 应用对 ChatGPT 断线的重试。Ollama 声称,大词表在 MLX 上的 top-k 采样速度有所提升。
深度见解
发布说明所列变化会影响 AI 编程工具和兼容 API 客户端处理输出限制、路由、输入内容、采样默认值、网页搜索响应及连接失败的方式。
What's Changed
ollama launch claudenow applies the model's output token limit for Claude Code, so cloud models no longer run into the 128k default cap- Cloud web search responses on
/api/chatare now decoded correctly, including compressed responses - OpenAI-compatible endpoints no longer override a model's packaged sampler defaults — clients that send no
temperature/top_pget the model's own values instead of 1.0, matching/api/chat /v1/responsesnow preserves readable input content, including prior assistant refusals, instead of flattening it- Ollama's app can now retry ChatGPT disconnect failures instead of leaving the connection in a broken state
ollama launch codexverifies ChatGPT routing before configuring, and reports a clear error when routing is unavailable- Faster top-k sampling on MLX for large vocabularies
Full Changelog: v0.40.13...v0.40.14