AI Coding Live News

Google AI Studio shared Managed Agents for the Gemini API, adding an updated agent harness, a Files API, and managed credentials. The combination brings long-running agent execution, file context, and credential handling into a managed path instead of forcing developers to assemble each control plane themselves.

Anthropic officially announced the General Availability (GA) of three core agent APIs: Computer Use (direct OS and application interaction), Skills API (dynamic workflow knowledge injection), and Files API. Concurrently, it launched Browser Use, enabling agents to navigate and manipulate web browsers autonomously.

Google AI Studio launched an updated Managed Agents harness in the Gemini API. antigravity-preview-09-2026 is live in the Interactions API and AI Studio, giving agents isolated Linux execution, filesystem tools, web search, persistent environments, and MCP connectivity. The release also adds Files and Credentials APIs so developers can move artifacts between turns and connect external services without putting secrets in the model context.

OpenRouter launched a new stateful server tool, Shell: any model on the platform can run commands in a hosted Linux container and move files in/out via a new Files API. It is available in beta as openrouter:shell.

DeepSeek launched DeepSeek-V4-Flash-Vision-Exp on its API: an experimental multimodal model that matches V4-Flash on text, agents, and reasoning, while jumping close to Claude Opus 4.8 on multimodal agent benchmarks. A free Files API and DeepSeek Harness 0.1.1 landed the same day, with images billed at up to 384 tokens each.

DeepSeek-V4-Flash-Vision-Exp is live on the API: it matches V4-Flash on text—including agents, reasoning, and world knowledge—while jumping on multimodal agent benchmarks to near Claude Opus 4.8. A free Files API and DeepSeek Harness 0.1.1 ship with it; images bill at V4-Flash rates (up to 384 tokens each) and drop into existing agent frameworks.

DeepSeek launched experimental DeepSeek-V4-Flash-Vision-Exp on its API platform. The company said the model matches DeepSeek-V4-Flash on text capabilities, including agents, reasoning, and world knowledge, while multimodal agent benchmarks jump substantially over V4-Flash and land close to Opus 4.8. Developers call it with model='deepseek-v4-flash-vision-exp'. It supports Chat Completions, Messages, and Responses, with mixed text-plus-image input via base64, external URLs, or the Files API. Images are billed at up to 384 tokens each at V4-Flash pricing. DeepSeek Harness 0.1.1 shipped the same day with out-of-the-box support, and a free Files API lets teams upload an image once and reuse it by file_id. For coding agents, the relevant use cases are screenshot-to-fix, visual UI diffs, and tool-using workflows that need to see the page or IDE rather than only the repo.

DeepSeek launched experimental DeepSeek-V4-Flash-Vision-Exp on its API. Text capability—including agents, reasoning, and world knowledge—matches V4-Flash, while multimodal agent benchmarks jump toward Opus 4.8. It supports Chat Completions, Messages, and Responses, with mixed text/image input via base64, URLs, or the new Files API. Images bill at up to 384 tokens each at V4-Flash prices. DeepSeek Harness 0.1.1 ships with out-of-the-box support.