Plugins

Resumes turns interrupted by a DSH host restart: hooks agent activation (once a session is live), reads the crash-repair turn/end, and sends a continuation that requires verifying real-world state first rather than assuming a side effect succeeded or failed. Permanent failures (AUTH, QUOTA, context overflow) are skipped, with a cross-restart budget, adaptive backoff and a minimal-context payload.

Media-scape theme for the DSH web UI: standing/character-art and video wallpapers (mp4/webm, local + online) with boot animation, base color schemes (single-source JSON + presets + picker), capsule host-element styling, ambient particles, background music player (covers/playlists/random), typing sound effects, and a draggable dock toolbar with a unified upload entry — wallpapers and music uploaded together (suffix-classified), mid-upload no-disk buffering, pause→.part snapshots with offset resume, filename+size dedup with "skipped" notices, and true-delete removal with list refreshes.

Whale-girl desk pet in the corner of the DSH Web GUI. It sings along to a bundled track while the agent works; when a tool call fails a steel pipe falls on its head. Click it to bonk the basin it wears, which costs 12 rice — knock enough and it gets hungry and wanders off to beg, and rice appears somewhere on the page for it to dash across and eat. Draggable within the viewport, wriggles and complains if grabbed mid-dash, volume and behaviour configurable from Settings. All artwork, sound effects and the song ship inside the package.

Full-screen dynamic wallpaper from local videos and images, with live effect controls, wallpaper switching and Wallpaper Engine workshop import; settings persist automatically.

Manage multiple API keys per provider in Settings → API 密钥: keep a pool of keys with notes, switch the active key with one click, and the switch really takes effect on the next model call.

A live peak/off-peak pricing readout for the DeepSeek Harness Web GUI: one status pill under the composer, with the effective prices on hover. · DeepSeek Harness 错峰计价浮标

Provenance-aware execution security for DeepSeek Harness. Track sensitive data across tool calls and stop risky side effects before execution.

Folds older oversized tool results into spill files and replaces them with short, deterministic stubs at step boundaries, with no LLM call: the stub keeps the first 200 and last 80 characters plus the sequence number, tool name, line/char/size counts and the original file path, and each fold is a real surface replacement accompanied by compaction/prune shadow pricing so token counts stay honest. Triggers on context pressure at 25% of the model window (falling back to 32768 tokens when the window cannot be resolved) or on five accumulated candidates; the last three turns, error results and rich content are never folded. The original is recovered from the session log rather than the spill file, so /folds, /unfold <seq> and /unfold all keep working after spill cleanup; session_fold_recall lets the model fetch a folded result by sequence number or by keyword, and session_fold_diagnose reports the effective settings. /spill-prune removes orphaned spill directories, preview only unless --apply. A Settings page exposes 12 of the 13 options as draft-then-save fields; they are volatile, so saved changes apply without restarting the plugin.

Splits the composer model seat into a model chip and a reasoning-effort chip: the effort chip opens a draggable, wheel-adjustable slider, and the panel behind it animates 36 canvas effects across 12 categories.

A realistic humpback whale desktop pet for Windows: a DSH host bundle that spawns its own Electron overlay above the desktop (not inside the web UI), with click-triggered full-screen water ripples and screen refraction, 20 local sound effects, and 121 offline one-liners. No model calls or telemetry; the only network use is a one-time Electron download on first start when no shared runtime is found, plus a DeepSeek balance refresh that runs only when you click it.

Registers the video-studio skill in the DSH skill catalog. It builds a Chinese-narrated video from a script: edge-tts synthesizes the narration, the timeline is derived from each line's measured audio duration rather than estimated from text length, Pillow renders every frame deterministically and pipes the raw frames to ffmpeg as rawvideo, burned-in subtitles and SRT/ASS export come from that same timeline, physical-model sound effects and a generated score are mixed sample by sample with numpy, and QA runs in four layers: container, signal, temporal and page level (the page layer only when the browser engine is used). An optional Playwright-driven browser engine renders the whole film as Canvas2D instead, sending PNG frames through image2pipe. Needs network access for the narration, ffmpeg on PATH and Python with numpy, Pillow and edge-tts; the browser engine also needs Playwright with a local Edge/Chromium.

Matches each new task against installed skills with deterministic keyword scoring and injects the best one without being asked; records effective operations as per-skill notes for later runs.

Runs loudness normalization, silence trimming, format conversion and batch processing through local ffmpeg, with presets for game sound effects, music uploads and voice cleanup.

Drives the Edge already open on your machine through a local WebSocket bridge and an unpacked MV3 extension: the agent reads the page as Markdown, dumps its interactive elements with stable refs, clicks and types with pre-action assertions and a three-valued effect state, and can capture pages from the extension popup as self-contained HTML snapshots, filed into a kb.py literature knowledge base when one is configured (kbRoot or DSH_KB_ROOT). Seven browser tools stay unregistered until edge_bridge is started, so an idle session pays no context cost.

Switches the tone of DSH replies from Settings → 人格模式 or the /persona command (/persona catgirl, /persona off), effective from the next turn. Only the active persona is injected, as runtime context, so the system prompt keeps a single stable short strategy; with the mode off the injected persona text is 0 characters. Facts, code and engineering discipline are unchanged.

Removes AI phrasing so replies and documents sound human: an always-on de-slop style section injected into every session (on by default, switch it off with deslop_mode), four deslop_* tools (0-100 slop scan, deterministic rewrite, intensity switch, voice profile) and four skills (rewriting, conversation, technical docs, Chinese reports), copied into the DSH skills folder at startup. The effect is measurable: a typical AI-flavoured Chinese paragraph scores 49 before deslop_rewrite and 6 after.

Super input suite — model and effort picker, prompt enhancer, follow-up suggestion chips, a full cost engine with daily heatmap and Coding Plan quotas, voice-input light effects and transcript cleanup (needs the built-in voice-input bundle enabled), prompt templates, selection reference chips with comments, a compaction ring and a settings hub. Bundles the author's standalone dsh-cost, dsh-power-picker, dsh-prompt-enhancer, dsh-followup, dsh-siri-voice and dsh-compaction-control; uninstall those before installing.

Gives the web UI the same keyboard shortcuts on Linux that Windows and macOS already get: the host half injects one script into index.html, so a Linux browser reports a Windows platform before the shortcut service reads it, and the built-in table resolves instead of staying empty; a Settings row reports whether the mapping took effect.

Configurable startup splash screen for the DeepSeek Harness desktop app on Windows only — a real main-process splash with live preview and light/dark themes. Deploys by rewriting the app's app.asar (a backup is kept) and takes effect on the next launch after you quit DSH; redeploy after each DSH upgrade.

Explains Chinese internet memes to an agent: registers a meme_explain tool that returns the meaning, tone, origin and lifecycle of a sticker, which memes can and cannot be combined, occasions to avoid, and both a meme-version and a plain-version reply. Answers come from a local memory store with spacing-effect decay, falling back to a user-configured OpenAI-compatible vision endpoint (BYOK).

An animated cat companion for the DSH chat UI. It reacts to session states, shows editable click-to-read lines and per-turn token counts, and supports dragging with a squish effect, left/right flipping and Ctrl+wheel resizing.

Passive recorder that replays the main agent and every subagent on one timeline, flags repeated calls, loops, recurring errors and truncated output, and writes an AI cause-and-effect review on demand.

A merge of the dsh-effort-dial card structure and the reasoning-slider gradient/particle effects: a Codex-style reasoning-effort card in the composer with one control for model and effort, per-level accent colors, a quota line on the top level, and a blue-purple gradient with drifting particles. It takes over the composer model slot, so it cannot be enabled alongside dsh-effort-dial or reasoning-slider.

Agent application development evaluation skill (skill bundle) for DeepSeek Harness: offline/online suites judged from audit side effects, baseline diff with zero tolerance for safety regressions, and mutation tests proving the evaluators themselves catch regressions. Framework-agnostic - needs a callable chat endpoint and queryable tool-call records. DSH host compatibility is deliberately undeclared.