Plugins

Draggable ring gauge showing live model output speed (tok/s) with an expandable per-step detail panel (exact speed, TTFT, cache-hit rate, cache read/write, reasoning and input tokens, model, cumulative tokens).

Download progress panel: URL downloader, agent shell/SSH transfer tracking and workspace black-box file-growth monitoring, shown in a draggable floating panel with live bytes, speed, percentage and ETA.

Sidebar leaderboard for DeepSeek Harness (DSH): LMArena blind-test ratings, Artificial Analysis intelligence index, LiveBench 2.0 capability, OpenRouter weekly/monthly usage and market share, price, speed and context — plus a local token-usage dashboard built from your own session logs (tokens, estimated cost, per-model ranking), model detail drawers and CSV export. Daily snapshot, instant open, no API key; locally configured models are highlighted.

Pipeline for scanned textbooks: OCR at roughly 5x the ONNXRuntime speed (requires Python 3.10+ with pymupdf, rapidocr, openvino and numpy), then a structure report and a per-chapter reading plan before you open the PDF.

CRT terminal skin with a phosphor-green palette, scanlines and monospace type for DeepSeek Harness. Also adds a sidebar dashboard with output speed, CPU/memory and DeepSeek balance; the key stays in the host process.

Live download progress in the DSH session header — percentage, transfer speed, ETA and phase per download, with file-size probing before a transfer starts and byte-range resume after an interruption. The progress cards render as a fixed overlay at the top-right of the chat window.

Two-level model routing: pick the best model group first, then the best channel within that model; a failure switches channel before switching model. Preference mode pins one model across its channels, a status bar under the composer shows the live model, channel health and the day's token usage, and a speed/intelligence report can be imported as the routing prior. Exposes a model_orchestrator tool and a /route command.

Ranks the models a DeepSeek Harness install already discovered by measured connectivity and speed, and switches to the next candidate inside the same turn when the one in use fails without producing any output. Ships a settings page with a grouped model list, per-model and per-channel switches, and a quota-aware cooldown that rests an exhausted model until the next day.

Real-time generation-speed gauge for DSH: a half-circle dial and a flowing trend curve, sampling tok/s 50 times a second for finer, more accurate measurement.

Network explorer for kids: my identity, DNS lookup, a traceroute trip, speed test and who is home on the LAN.

A download-progress indicator for the DSH session header: it reads the background-job roster and parses what downloaders already print — curl --progress-bar, wget, aria2, or a JSON progress file — into a progress ring, animated bars, transfer speed and ETA. Jobs that report nothing show as unknown progress instead of being hidden. A finished file opens with one click, or reveals in the file manager. No third-party plugin required; the package ships zero runtime dependencies.

Live CPU, memory and GPU readout in the DeepSeek Harness composer status bar — a clickable badge with a details panel, per-metric toggles, and three refresh speeds.

Adds a speaker button immediately right of the Like button on every finalized assistant reply; click it to hear the reply through the browser speech engine, and hover it for a speed and voice panel. Text is sent to an unofficial Edge TTS endpoint.

Model channel manager: several provider/model candidates share one virtual route (roundrobin/<group>) with failover, retry, timeout and cooldown; a settings tab edits providers and groups, runs per-model speed tests and real single-model request tests, and a seven-day health panel aggregates latency, failures and upstream token usage (input, output, cache and reasoning).

Folds streaming reasoning and tool calls into collapsed step bars and collapses each finished turn into a single summary bar; step bars show native tool icons, filenames, edited line counts, and failure counts, finished turns restore duration, first-token time, token usage, generation speed, and cache hit metrics from recorded Session events, and preferences persist on the Host. Changes browser presentation only. Requires DSH 0.1.5-alpha.1.

Running pace calculator: converts distance and time to min/km pace and km/h speed.

Registers /wrapped, which reads the session's own stats and renders a shareable dark SVG summary card — tool vs. thinking time, decode speed, and a tool/thinking-ratio verdict.

Adds read-only, scriptable playback to native DSH conversations, with simulated user typing, forward and reverse playback, event stepping, speed control, idle-gap compression, and direct seeking by event, turn, or recorded time.

Global experience archive for DeepSeek Harness on Windows: probes local tools (with versions and PATH-first hits), convenient paths, network latency and disk speed; folds per-session stats from session/event; LLM-extracts durable facts; env_profile tool with remember; byte-stable summary injected every turn to speed up sessions and cut token use.

Vendor-based usage dashboard: per-provider token/cache/output KPI, a 53-week heatmap, trend chart with hourly "today" view, model drilldown, cost estimation, CSV export, and health cards (TTFT, generation speed, peak context, error rate).

Tool-execution efficiency suite for DeepSeek Harness: read-only result cache, speculative prefetch, and concurrent readonly shell commands. Honest scope: helps when tools are slow and calls repeat; model latency dominates otherwise.

Read-only dashboard for token usage, cost, request speed, and first-token latency across local DSH sessions.

Adds a decode-speed reading to each reply action row, right of the usage control: open it for the turn time breakdown, first-token latency, decode output, prefill, speed ranges and total usage. A setting can keep every message action row visible.

Adds a Speed setting (Standard, Fast, Ultrafast) for OpenAI and Codex models on a patched dsh build: the pinned dsh 0.2.1-alpha.2 web client needs the Model / Effort child-slot patch, the host pi-ai must be 0.87.1 or 1.1.0 (other versions refuse to load), and the terminal controls need a patched dsh-TUI. Then it appears in the Model / Effort menu; in dst /speed opens a picker or sets the speed directly, and the current speed shows in the bottom bar. The choice is kept per session, provider and model and is sent as the request service tier.