Plugins

DSH 日志分析插件：选择本机 Java 服务文本日志，分析 ERROR/异常堆栈，提供 AI 工具与 Web 仪表盘

Decides whether Python code is original or a derivative work: reports the longest identical expression span against an upstream tree, an exemption rationale per finding, and a risk list. Pure stdlib `ast` analysis — offline, no model calls.

MaxCompute (ODPS) data analysis plugin for DeepSeek Harness: metadata browsing, cost-gated SQL execution, background jobs and result export.

Foggy Java data-analysis integration for DeepSeek Harness with a managed Runtime, CLI, Launcher, onboarding Skills, and semantic-layer workflows.

保险产品分析对比专家(险析君)·DSH插件｜条款解读/性价比/产品横向对比/保障规划(含重疾+医疗)，中立公允第三方。Insurance product expert (InsureGuide): clause analysis, cost-effectiveness, comparison & coverage planning.

Read-only repository fact scanner kernel for DSH analysis plugins: deterministic probe / file index / modules / dependencies / entry points / symbols / graphs and git facts over a stable JSON schema (CLI + library + skill runbook).

Codegraph CLI as eight code-intelligence tools for DSH — symbol search, callers/callees, impact analysis, codebase exploration, symbol/file reading, index status and sync.

Read-only Excel analysis toolkit for dsh (DeepSeek Harness). Streaming xlsx reader (yauzl + sax), describe / filter / pivot tools, big-file safe.

DSH plugin: dsh-repo-map

Reports the semantic blast radius of agent code edits: which symbols changed, who calls them, and which of those callers have no covering test.

Hands repetitive text and vision labor (OCR, image analysis, comparison) to a locally running Unsloth Desktop (Unsloth Studio) server through unsloth_run and unsloth_vision tools; pure HTTP client, never spawns or owns processes.

Hands repetitive text and vision labor (OCR, image analysis, comparison) to a local KoboldCpp (llama.cpp) server through koboldcpp_run and koboldcpp_vision tools, with on-demand server lifecycle management.

Vision für rein textbasierte LLMs: Bildbeschreibung / OCR / VQA über kostenlose Gemini- und GLM-Vision-APIs.

Agent-FinOps-/Token-Analyse für DeepSeek Harness: Nutzungserfassung, zeitbewusste Kosten-Engine, Cache-Analyse und Sitzungs-Drilldown

Echtzeit-Code-Feedback für DeepSeek Harness — LSP, Linter, Formatter, Typprüfung und Strukturanalyse.