Plugin

Plugin di tracciamento costi per la Web GUI DeepSeek Harness — prezzi per turno ancorati a snapshot, saldo account e stime di costo in tempo reale.

Il misuratore del tempo di utilizzo DeepSeek per dsh: quanto è costata questa sessione, quale tariffa è attiva, quando cambia, e il saldo dell'account dietro — una riga sotto il composer.

Misurazione dei costi LLM per turno e per sessione: una riga di costo in dollari sotto ogni messaggio, un totale cumulativo di sessione con dettaglio al passaggio del mouse e uno strumento di aggiornamento automatico dei prezzi LLM+web.

Badge del costo in USD per turno nella Web UI: totale della sessione nell'intestazione e costo per turno nel footer di ogni messaggio, con dettaglio al passaggio del mouse

Per-session LLM cost meter for the DeepSeek Harness Web UI: folds provider usage into uncached input / cache read / cache write / output per model and prices it against DeepSeek and Xiaomi MiMo pay-as-you-go rates (DeepSeek peak-idle tiering included).

Motor-design AI assistant plugin: requirement parsing → parameter identification → candidate matrix → Top10 verification. L0 is a millisecond-level broad filter (pure JS, zero solver dependency) that ranks candidates and emits the handoff payload for the L1/L2 precision tools; usable as a local agent preset and Cordis plugin. L1 (RMxprt) and L2 (Motor-CAD) are reserved in this version — the level gate fails fast above l0.

Adds a sidebar panel to the DeepSeek Harness web UI that reports token usage and cost straight from DeepSeek's own usage API (today's spend, 7/30-day trends, today's hourly split, a history table, cost breakdown, peak/off-peak tier pricing), plus per-session detail from local logs. Zero-config: it reads the browser sign-in for the official figures, and falls back to local session logs with the source labelled.

AlphaRSI — three-role self-improvement loop that evolves the training recipe of alpha sequence models. Operator runs walk-forward, Evaluator grades with OOS RankIC, Refiner proposes hyperparameters via TPE Bayesian search; only strictly-better recipes are kept. Offline one-command run, data bundle shipped with sha1 reconciliation, GPU auto-detect. Ships one skill.

Declare any number of LLM providers, each with its own endpoint, credential and per-model parameters (reasoning-effort vocabulary, image input, retry policy), across the OpenAI Chat, OpenAI Responses, Anthropic Messages and Google Gemini wire formats, configured from a settings page.

Host-layer DeepSeek Harness plugin that normalizes whitespace and trailing newlines in tool path and pattern parameters.

DeepSeek Harness Web GUI plugin: real-time spend for the current session, priced from per-model token rates and shown as a pill under the composer

DSH plugin: inject per-model sampling parameters (top_p, top_k, min_p, repeat_penalty, presence_penalty, frequency_penalty) into every chat-completions request sent to a local llama.cpp / llama-server gateway.

Floating usage window for DSH Web showing Claude and Codex subscription windows with reset countdowns, plus DeepSeek API spend and balance; display-only companion to dsh-cost-meter.

Web management panel for Docker on DeepSeek Harness: manages Docker MCP servers (deploy/remove, official catalog search/pull, gateway start-stop-restart, custom deploy) and containers/images (list, start/stop/restart, remove, logs, inspect, interactive terminal, create, pull, build, load) across local CLI and SSH remote targets with one-click switching. Credentials are encrypted with Windows DPAPI, HTTP is loopback-only, and command parameters are whitelist-filtered. Build-free pure ESM; client is zero-dependency.

Capture selected DSH, local MCP, or native WebMCP calls as reviewed, parameterized routines, expose typed tools, and replay with fresh approval.

eDEX-UI-style shell over the DSH web GUI themed as an XRY/B1 medical HUD: ECG heartbeat waveform and a rotating radar scan disc on the right bar, power-gen energy-cell meters on the left bar, a DATA TIMELINE scan-log table on the bottom, all in a cyan-on-near-black CRT skin around the original UI.

Session cost chip in the DeepSeek Harness conversation header showing live token usage by bucket, peak/off-peak tariff pricing, and a countdown to the next tariff switch.

Standalone mobile surface for dsh: scan-to-pair device trust, realtime SSE sync, three-channel completion notifications (in-app / Web Push / Server酱·Bark·Telegram), offline outbox, approval & question panels, per-provider usage meters, PWA; a native narrow-screen phone UI.

Model-facing image-generation tool with a configurable channel and normalized image parameters.

Control panel for local LLM inference servers in the DSH web view: service registry with health checks and stop controls, named parameter profiles for llama.cpp, SGLang and vLLM with pre-save KV/VRAM validation, GPU detection, and tok/s benchmarks.

Manual context compaction for DeepSeek Harness: keep the latest N conversation items with stop or batch mode and a per-session compaction archive — embedded in the context meter popup when the meter panel slot exists, or a composer button otherwise.

Manual context compaction for DeepSeek Harness: keep the latest N conversation items with stop or batch mode and a per-session compaction archive — embedded in the context meter popup when the meter panel slot exists, or a composer button otherwise.

OpenAI-compatible LLM adapter plugin for DeepSeek Harness with configurable default sampling parameters (temperature / topP / topK / penalties / seed) over a providers dict.

Per-turn DeepSeek spend, live official pricing, and current balance for DeepSeek Harness Web.