AI Coding Live News

On Oct 31, deepseek-ai open-sourced dsh-superagent-prototype on GitHub under the MIT license: a proactive coding agent that runs as a DeepSeek Harness bundle, lives on one GitHub repository and can optionally listen to Feishu. When an allowed person asks for work, it opens a work item, works in its own session and directory, and answers in the original conversation, for example with a pull request. The README states it is a research prototype, not an official DeepSeek product. The companion article, Exploring Super-agent Design, proposes a two-layer Router-Worker architecture; the team test, as reproduced by media, reports a p95 completion time of 15.7 minutes versus 29.5 minutes for a single-session setup.

GitHub dsh-v0.2.1-alpha.1 (2026-10-03T06:42:19Z) adds an experimental Claude Code Mods compatibility layer to MIT DeepSeek Harness (~243k stars)—explicitly to test that Mods APIs are broadly a subset of dsh plugins, not full compatibility—continuing v0.2 desktop apps. Get it at deepseek.com/harness or npx @deepseek-ai/dsh web.

@akshay_pachaar highlighted HarnessRouter (github.com/HarnessRouter/harnessrouter, Apache-2.0): an “OpenRouter for agent harnesses” implementing the Unified Harness Protocol (UHP) so Codex, Claude Code, Hermes, DeepSeek Harness, System One (Jev), and 9+ other harnesses share one API for sessions, streaming, files, cancellation, and failure handling—self-hosted with your own keys.

Open-source dsh-ios (DeepSeek Harness plugin) wires the iOS Simulator and USB devices into the chat: 22 tools cover build, boot, logs, OCR, accessibility tree, and UI control, with a live sidebar for tap/drag. Device signing follows configurable Xcode teams and stays local with short-lived signatures; requires macOS and full Xcode (github.com/ZSeven-W/dsh-ios).

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.

Milvus released an official integration plugin for DeepSeek Harness 0.1, providing high-concurrency hybrid vector retrieval and secure read-only context injection for open-source autonomous agents.

DeepSeek launched deepseek-v4-flash-vision-exp on its API, maintaining ultra-low V4-Flash pricing while achieving multimodal coding and agent performance approaching Claude Opus 4.8.

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.