dsh-profile-plugin-switch
DeepSeek Harness (DSH) web plugin: toggle any plugin on/off from the GUI, live, without restarting the server.
238 results
DeepSeek Harness (DSH) web plugin: toggle any plugin on/off from the GUI, live, without restarting the server.
Self-control guard for DeepSeek Harness: intercept host-kill attempts from bash, teach the controlled exit/restart tools, run token-confirmed graceful exit/restart, and write the restart recovery roster.
A loader-independent rescue console for DeepSeek Harness when a broken plugin prevents the Web UI from starting.
Run the DeepSeek Harness agent's filesystem, bash and PTY terminals inside a Docker container, so execution state survives a harness restart.
Version management for the dsh Web GUI settings panel: inspect the installed @deepseek-ai/dsh against every npm channel or version line, install or downgrade with one click, roll back instantly from local snapshots, automate the whole cycle with a policy engine (silent auto-update, execution windows, daily checks), and restart the host seamlessly.
DSH web bundle: pause the current turn at the next step boundary (graceful drain), persist everything, and resume later — including after a DSH restart.
DSH web plugin: show every session's theme in the left sidebar on open — warms the session projection cache at startup so session.list carries titles for cold sessions.
team-task for DeepSeek Harness: long-horizon multi-agent tasks — a lead plans a reviewed DAG, durable members execute, an event log is the single truth, and a resident reconciler survives crashes and restarts.
Unified local plugin: session identity, global prompt, auto-resume, web restart, session log reposition, peer message (6 plugins consolidated).
Out-of-tree dsh web-profile bundle: enables --host 0.0.0.0 and gates the Web UI behind a --web_token access token (cookie after first ?web_token= open). Forks @deepseek-ai/dsh-host-webserver and @deepseek-ai/dsh-web-app/startup.
Start a DeepSeek Harness conversation without selecting a workspace: auto-provisions a default workspace and adds a "Chat without a workspace" option to the workspace picker
Auto-inject user-chosen skills (e.g. caveman, ponytail) into DeepSeek Harness sessions: every prompt or once at session start, with a settings page and a composer indicator. 在 DSH 会话中自动注入所选技能(如 caveman、ponytail):每轮提示或仅在会话开始时,含设置页与输入区指示。
DSH Auto Maintenance System — startup diagnosis, auto-fix, scheduled backups, smart-start, config monitoring, and automatic plugin-change self-check with rollback, in one Cordis plugin.
Long-task gatekeeper for DeepSeek Harness: detects one-shot mammoth requests, asks whether to plan first, and scaffolds plan.md + a capped goal before the agent starts
Manage the DSH web service from a settings panel: status, version, restart, stop, and one-click updates.
Safemode profile enforcer: force-restores ~/.dsh/profiles/safemode to a clean whitelist (dsh-base + dsh-web-app) on start and continuously guards it against modification, so `dsh --profile safemode` always boots with zero third-party plugins. No build scripts: the bundle row does all work.
DSH plugin: right-click a folder in Windows File Explorer to open it as a DSH workspace (launches DSH if needed, creates the workspace, starts a session, and switches the DSH page to it).
AgentSoul for DeepSeek Harness — a local personality, identity, state and long-term memory layer. Auto-loads as a bundle plugin on every dsh startup.
A floating one-click restart button for the DeepSeek Harness web GUI — fully self-contained, cross-platform, no launcher required. · DSH 网页界面右下角的一键重启按钮:完全自包含、跨平台、不依赖启动脚本。
Cross-platform Web UI launcher plugin for DeepSeek Harness: webui_start/stop/status/open model tools, a /webui slash command and a Settings-page launch card.
DeepSeek Harness (cordis) plugin: self-update for the harness launcher — checks npm for a newer @deepseek-ai/dsh, stages it, and applies it on harness exit (or update-and-restart from the web panel).
Reliable todo panel for DSH: survives restarts, verifies completion evidence
DSH plugin: start/stop a local llama.cpp llama-server from the settings → plugins page — two model slots (A/B) with per-slot model-file selection, eight editable launch-parameter groups (text/vision × fast/long × 2 slots), and one shared DSH provider carrying both slots' models with four thinking-effort levels.
Honcho memory for DeepSeek Harness — persistent, cross-session memory that survives context resets and restarts.