Plugins

Persists unsent composer attachments per session, so images and files pasted into the input box survive page switches, conversation switches and app restarts: the bytes are mirrored in IndexedDB and handed back through the official createDrafts/addAttachments channel, and are dropped as soon as the message is sent or you remove them.

E-commerce product image generation for DSH: 24 prompt modules covering main, detail and ad images, style transfer from a reference shot, batch runs, and a project gallery with live preview.

Adds native Codex OAuth sign-in, main-Agent default model selection, and direct or local-proxy settings for DSH Desktop 0.2.0-rc.2 on Windows.

星穹召唤 · DeepSeek Harness (dsh) 插件：二次元抽卡 + 和抽到的角色聊天 | A dsh plugin: anime gacha cards you can chat with

各个模型厂商/中转 实时显示账户余额插件

Grounded web search for DeepSeek Harness through OpenRouter-compatible gateways: the built-in web_search tool runs on the same endpoint and key as your chat models, returns citeable sources, and is configurable from the Plugins settings page.

DSH 插件市场：浏览官方与社区插件，装之前先给出兼容性结论，一键交给官方安装管线。Plugin market for DeepSeek Harness: browse official and community DSH plugins with a compatibility verdict, and install them through the official plugin manager.

anagenesis —— DeepSeek Harness 上的可编程记忆编排层 + 自我进化引擎：自带闭环记忆存储（不依赖任何外部记忆插件）、17 个面向 Agent 的语义记忆工具（召回/提交/提升/降级/拆分/锁定/过期/反事实重思）、运行时可切换的注入策略、带审计与回滚的元策略自调节、全程可逆效应、自动注册 `anagenesis` Agent 预设，以及零依赖可视化层（终端仪表盘 + mermaid/d2/ascii 文本图表 + 可选桌面窗口）。

AI-agent-driven automated testing platform for DeepSeek Harness (dsh): drives the harness agent through long-lived multi-round sessions to write and run Markdown test cases, file bug reports, fix the code and re-verify the fix, with a per-project serial queue, a development board and built-in load testing.

Long sessions get expensive, and the platform compacts the context on its own. This plugin adds an occupancy badge (hover to see how it is computed), writes a handover draft into HANDOVER.md from 45% — files changed, money spent, what recent turns were about — and reminds you once at 60% to wrap up. On compaction it records the reading from just before, so you can check it later. No model calls, nothing added to the conversation; it does not prevent compaction.

A persistent multi-step task stack for DeepSeek Harness agents: focus_task / focus_complete / read_focus plus a /focus command, with zero automatic prompt injection

Save whole turns — the question plus the full answer — as plain Markdown inside the session workspace, promote the good ones into a cross-project personal knowledge base, and let the model search it on demand. No database and no runtime dependencies.

Native token-based themes for the DeepSeek Harness Web GUI, with custom colors and system font pickers.

Russian localization for the DeepSeek Harness (dsh) web UI — registers the `ru` language (63 namespaces, 3119 strings)

Context fullness bands, the per-session compaction threshold derived from the model window, per-step cost computed from cache read and cache write rates, cache-hit, DeepSeek balance with the peak/off-peak tariff, and a one-click handoff. It never calls a model and spends no tokens.

Makes the WorkBuddy desktop app's web search the dsh web_search provider, reusing the app's existing sign-in with no extra configuration.

Manage skills and MCP servers from one DSH settings panel. Skills are read from disk: browse, search, preview the body, create, rename and delete, with a backup written before every removal. Global MCP servers are the real cordis.patch.yml loader rows; per-project entries mount only for sessions in that project. Each expanded card lists the tools that server actually registered, and a per-server allow/deny rule keeps only the ones you need — a blocked tool never enters the tool registry, so it costs no context on every turn. Every MCP card carries a connection status tag (connected with a tool count, retrying, gave up, activation failed) plus a one-click reconnect, so a server that fails at startup is visible instead of silently missing its tools. Imports existing configs from 26 other MCP clients.

Opens the DSH settings dialog as a full-page screen and moves the close control to a back row at the top left.

Cone crusher selection and crushing-plant design for MACKORN NH/NS single-cylinder hydraulic cone crushers: requirement-form intake, equipment selection, plant configuration, proposal generation, product-size simulation and field-data calibration. 21 tools, 6 skills, an MCP server, no runtime dependencies.

Codebase Memory MCP bridge for DeepSeek Harness: six knowledge-graph code tools, auto-started background daemon with visualization Web UI, and bundled agent skill.

DeepSeek Harness plugin: tells the model its real, host-measured context occupancy every turn — and keeps compaction summaries from carrying false "context is nearly exhausted" claims.

Plugin security review for DeepSeek Harness: dependency advisories, contextual static evidence, a call-time gate for high-risk plugins, and reversible review-gated enforcement.

Run one instruction on every online Windows and macOS machine, across networks and regions: a dependency-free relay talks to each machine over outbound connections only (Tailscale, a public VPS behind TLS, or a tunnel), every machine runs the command in its own checkout, and results come back with a commit, a working-tree fingerprint and a command hash so an environment mismatch is reported as unverifiable instead of being mistaken for a different result. Sending work needs its own operator token, separate from the per-machine device token.

Create Blender product scenes in DSH with editable recipes, model imports, previews and PNG/MP4 delivery; includes workbench and agent configuration.