Plugins

Forces context compression when running low-context llama.cpp models such as Qwen3.8-27B, improving model efficiency and usage smoothness, together with well-refined compaction prompts.

Thinking in Chinese: injects a system prompt so thoughts and replies stay in Chinese, expands the reasoning block by default with interactive collapse, and localizes UI labels (npm: `dsh-think-zh-expand`).

Self-evolving team memory as plain Markdown in git: a native Cordis plugin that registers 38 bare-name memory tools plus a prompt-signals section re-evaluated at every assembly, with RPE reinforcement, decay and sleep consolidation; shares one data repo with its Claude Code (MCP) and OpenClaw hosts; verified against DSH 0.1.0-rc.6.

Self-evolving team memory as plain Markdown in git: a native Cordis plugin that registers 38 bare-name memory tools plus a prompt-signals section re-evaluated at every assembly, with RPE reinforcement, decay and sleep consolidation; shares one data repo with its Claude Code (MCP) and OpenClaw hosts; verified against DSH 0.1.0-rc.6.

Adds /pua to steer the agent to try another approach and verify results before claiming completion, with 15 company styles, persona modes, global and per-conversation settings, and an optional loop that continues until a verification command passes, the iteration limit is reached, or the user cancels.

Attaches a stable per-conversation x-opencode-session header to OpenCode / OpenCode Go provider requests, fixing 400 MissingSessionID errors and keeping session affinity and prompt-cache routing intact.

An opencode-inspired terminal UI for DeepSeek Harness that boots as a dsh profile app plugin, with a session sidebar, streaming chat, markdown tool cards, todo lists, slash-command suggestions, a telemetry footer with a context meter and inline approval prompts.

Scheduled tasks: run a prompt on cron schedules, each run opens a new agent session to do the work, with workspace binding, manual run, session auto-naming, and a fullscreen task management page.

Composer input toolkit: arrow-key session history (first/last-line gated, IME and command-menu safe), an instructions viewer/editor for global and project AGENTS.md/CLAUDE.md, and a prompt library of 780 Chinese prompts (Cherry Studio agents-zh corpus, AGPL-3.0) inserted into the composer in one click. Ships on npm as `dsh-composer-tools`.

Per-project scheduled prompts run as fresh headless agent sessions, with one-time, interval, and cron schedules plus durable run history.

Global Chinese mode: a compact pill switch beside the composer that injects a language requirement into any preset's system prompt (complete personas excepted); reply, thinking and tool output each toggle between Chinese and English, and anchored presets are supported.

Restart DSH: configurable restart method (Node native / legacy PowerShell), post-restart continue prompt, optional watchdog auto-relaunch.

Bring the deepseek.com web/app chat experience to DSH: edit your prompt and regenerate answers in place, with a per-message <i/N> version pager (tree model, stable across conversations).

Lossless context folding for DeepSeek Harness: the oldest span is replaced by a brief, and the originals stay in the session log.

Wraps work in named tasks and, once a task closes, folds its whole span of messages into one summary at the next step boundary; the original content can be restored on demand.

Tool-call discipline for DeepSeek Harness: injects a static behavior-constraint prompt section, drops the parallel pool to 1 after a tool failure (restoring after 3 consecutive successes), nudges the model to stop retrying after repeated failures, verifies writes with .bak rollback, gates high-risk commands, and tracks compliance stats via /behavior-status.

Self-healing Cloudflare quick-tunnel pool for the dsh web GUI: floating widget with QR phone access, generational rotation, chase service worker and prompt-free credential handoff.

Web GUI convenience suite with appearance controls, timeline navigation, project folders, prompts, conversation export, Mermaid rendering, quote reply, and DeepSeek balance and daily token usage.

Windows desktop launcher for the DSH Web UI: desktop shortcut, silent start, system tray with open/full-exit (stop service, close app window, quit tray), PWA app window with focus-instead-of-relaunch, install prompt, and task-completion notifications.

Injects one fixed system-prompt section so the agent thinks and replies in Chinese, regardless of the user's language.

One memory layer for every AI tool and agent: Context Bundle injection, prompt-time recall, MCP tools, and turn-end DSH thread capture.

Per-conversation x-opencode-session header injection for OpenCode Go in DeepSeek Harness (DSH). Fixes 400 MissingSessionID, keeps prompt-cache routing optimal, scoped strictly to opencode.ai, runtime-switchable without restart.

Injects one system-prompt section so the agent's chain-of-thought, planning and tool-invocation reasoning stay in Simplified Chinese. Zero external dependencies - clone and link-install from any local directory, no npm build or publish required.

One-click prompt enhancement in the composer — rewrites the draft into a structured prompt (role and goal, executable steps, output format, acceptance criteria, edge cases) with before/after preview, fill-back, and undo. Never changes intent, never fabricates requirements.