ffyuuu/dsh-llm-longcat
LongCat-2.0 LLM adapter: 1M context, binary thinking mode, tool calling, and streaming over the OpenAI-compatible endpoint.
About this plugin
- Thinking mode — recognizes LongCat's reasoningcontent field and translates it into harness ReasoningBlocks - Tool calling — full function-calling support, with arguments kept a raw JSON string end to end - Multi-turn — replays reasoningcontent on tool-call turns, as thinking-mode passback requires - Streaming — SSE with the usage-before-finish ordering the harness relies on - Credential seam — the key resolves per request from ctx.credentials or the environment; no secret in any config file
$ dsh plugin --profile web add dsh-llm-longcat$ dsh plugin --profile web add github:ffyuuu/dsh-llm-longcatHealth breakdown
57 / 100Score reflects license, community signals, documentation and distribution. It is not a code audit — review the source before installing.
Security
Key metrics
Related
Related plugins
Browse, search and install community plugins from inside DeepSeek Harness settings, with category filters, one-click updates, enable/disable, theme switching and configuration backup.
[!WARNING] 📌 Announcement (v2.1.7) v2.1.7: Hardens remote/local capability boundaries, long-lived browser and persistent-cache resource ownership, DSH 0.1.5 connection/catalog compatibility, property-based fuzzing, and release provenance without raising the rc.8 Host floor. What’s new →
Tell your agent what you want ("notify me on WeChat when a task finishes"), and it searches the DSH plugin ecosystem on GitHub for you — top results by stars, each with a one-line description and an install command.
Free, keyless web search for DSH: 7 engines (DuckDuckGo/Bing/SearXNG free + Exa/Perplexity/DeepSeek paid), auto-failover, settings-page UI with API key inputs and official links, web_fetch, and an engine test tool.
One-click backup, export, import and migration of a whole DSH config: settings, plugins, MCP, skills and workspaces. Secrets are excluded by default and, if you opt in, are AES-256-GCM encrypted rather than written in the clear; imports preview first and auto-backup with rollback, profiles hold multiple setups, and remote sync pushes portable config through a private Git repo with secrets excluded.
Use your ChatGPT / Codex subscription with DeepSeek Harness via OAuth, with model access, usage quotas, search, and image generation — no API key or Codex CLI required.