Plugins

Right-edge user-message navigator with an adaptive block layout that fits the available height, plus hover previews, keyboard controls, and click-to-jump navigation.

A single-character agent that lives across QQ (via SnowLuma / OneBot 11), Bilibili and Douyin (the Douyin channel needs an always-on Windows desktop): persona cards with slowly evolving traits, per-person memory with Ebbinghaus decay and correction, a virtual clock driving a daily routine, proactive messages, auto-extracted memories, and a ten-tab settings panel covering retrieval, persona, routine, memory inspection, channels, habits, models and usage. QQ groups are deny-by-default: a group is answered only when it is on the allowlist or allGroups is explicitly switched on, and it still has to @-mention the bot. Private chats answer QQ friends only. Bilibili/Douyin auto-reply is off by default, limited to the owner, allowlist and mutual follows on Bilibili, and to the owner and allowlist on Douyin unless reply-to-everyone is explicitly enabled. Vendors MIT-licensed code from dsh-qq-bridge and dsh-douyin-bridge, credited in-source with their LICENSE files; it does not need either installed alongside.

Autonomous Douyin watching in a dedicated Edge browser on Windows (requires Node.js 22.13+): sampling decisions, frame storyboards, danmaku-aware comments, persona memory and a watch diary, all under daily viewing limits. Fork of LockyBee/dsh-douyin-agent — uninstall the upstream plugin before installing this one.

Windows-only floating percentage meter for the DSH desktop (0.2.x) cookie jar: it estimates how much of the request-header budget the dsh-auth cookies occupy, turns red past half, and clears the jar on the next launch with one click, avoiding the lockout that hits after roughly 72 launches.

DeepSeek Harness's own fast mode: the same model on the same reasoning effort, fewer output tokens, all prompt-side. Only the output-discipline switch is on by default (late mode, active from step 4); every other switch is off and can be enabled on its own; turn on the tool-output trim switch when tool output is long. Measured on one machine, not a leaderboard: 30 task pairs with long output at the trim switch 0.756x wall clock and 21% fewer output tokens; 24 pairs on 6 real pallets/click PRs 0.805x and 23% fewer. On official SWE-bench Lite instance definitions with a self-built harness it does not show a gain (8 instances, three independent runs pooled to 72 pairs: 0.933x wall, 0.903x tokens, wall still crosses 1; single runs of the same configuration differ by 30%), and stacking switches on top of the trim switch is worse than the trim switch alone. Numbers and repro in the repo.

Evidence-first conclusion gate that cross-checks first-hand claims against a durable per-session tool-activity index, blocks unverified guesses and tracks blocked-versus-converted metrics.

During Beijing working-day peak hours (default 09:00-12:00 and 14:00-18:00) it blocks official DeepSeek requests or reroutes them to a configured target provider; off-peak traffic flows to official as usual.

Live security beacon for DSH that follows tool activity. Click to view call statistics, risk provenance chains and blocked actions, with read-only task restrictions and tool metadata change detection.

All-in-one DSH extension center in Settings: manage skills, MCP servers and plugins, a Plugin Market (curated + GitHub search, npm one-click install), and an Add-ons block to install, disable, uninstall and update companion features together.

A second brain for your DeepSeek Harness agent — strong-model review before risky tool calls, plus 67 models from one wallet. No accounts, no API keys.

Takes over the edit/write rows in the chat stream with the official native row shell and collapse behavior; expanding shows per-file code cards with file-type icon, add/delete stats, per-block collapse, highlight/plus-minus toggle, syntax-highlighted unified diff with real file line numbers, and a configurable context margin. Also ships a patch tool (beta, off by default) that applies multi-spot multi-file patches atomically via the *** Begin Patch envelope. Frozen archive: keep the pinned version, as the author no longer adapts it to newer DSH releases.

Auto-classify DeepSeek Harness sessions via Jev decision models or Agent tools, displayed as title emoji prefixes (wip 🚧, blocked ⏸️, review 👀, done ✅, plan 💡, bug 🐛). Features seamless lifecycle recovery, optional Jev inference (needs a Jev API key), model tool maintenance, and a visual settings panel.

Takes over the edit/write rows in the chat stream with the official native row shell and collapse behavior; expanding shows per-file code cards with file-type icon, add/delete stats, per-block collapse, highlight/plus-minus toggle, syntax-highlighted unified diff with real file line numbers, and a configurable context margin. Also ships a patch tool (beta, off by default) that applies multi-spot multi-file patches atomically via the *** Begin Patch envelope.

Kanban task board for DeepSeek Harness sessions: the main agent dispatches tasks to one-shot worker/verifier subagents, with dependency scheduling, file-level exclusion locks, arbitration hold/freeze, milestone progress reporting, and per-task token usage stats.

Sidebar session search that builds its own index instead of reusing DSH's full-text one: title to content toggle in one entry, results grouped per session with the strongest snippet and user/reply/tool tags, plus watermark-based incremental sync, archive-driven pruning of archived sessions, and a shadow rebuild that never blocks the live index.

Local-first persistent memory for DeepSeek Harness: bounded pre-step hot-memory injection, exact and Chinese-bigram BM25 cold recall, six agent tools, approval-gated lease-lock writes with recovery receipts, and read-only governance and trajectory-review candidates.

Enhanced ACP server for DeepSeek Harness: block & reasoning streaming, usage telemetry, model/effort switching, permission presets, session resume/archive, per-session MCP servers, and Zed file/terminal forwarding.

Nine complete dsh-web-ui skin replicas with custom skin-pack import, preview, apply, delete, restore-default, and readability fixes for bubbles and code blocks.

File claim/release protection for parallel DSH sessions on the same workspace (heartbeat stale takeover, pending 3-way merge area).

Keeps one reasoning-only turn from making an entire session unusable. When a turn produces no visible text and no tool call, the assistant message is persisted empty, the gateway then rejects every later request in that session with 'content or tool_calls must be set', and the session is dead with no way back through chat. This plugin registers a single llm/stream waterfall listener and, only when the turn carried nothing visible, injects a small text block immediately before the terminal finish, so the persisted message is never empty. Ships the fixture DSH's own mock cannot express (a strictly reasoning-only SSE server, since llm-mock-server forbids an empty successText and always appends text after reasoning), plus an end-to-end reproduction that replays a real persisted session through DSH's own serializeMessages. Preventive, not a repair. Zero dependencies, one file, no process or filesystem access.

ICVO coding-standards kit for DeepSeek Harness (formerly dsh-coding-kit): a bundle plugin that registers tools on load and injects the standards only when apply_coding_standards is called, plus a P0 gate CLI (npx spec-wave) with G1-G7 process commands, skills install, host apply, and IDE-block refresh.

Evidence-driven goal verification plugin for DeepSeek Harness. Locks goals via /ultragoal and verifies completion against command exit codes and generated artifacts, preventing the model from falsely reporting task completion.

Context Assembler plugin for DeepSeek Harness: topic-block context assembly, water-pressure topic splitting, tool trace/rewrite, reality recall injection and handoff planning.

ICVO coding-standards kit for DeepSeek Harness: a bundle plugin that registers tools on load and injects the standards only when apply_coding_standards is called, plus a P0 gate CLI (npx dsh-coding-kit) with G1-G7 process commands, skills install and IDE-block refresh.