Plugins

A fixed-corner whale widget for the DSH web GUI — balance, today's usage and per-turn cost with peak/off-peak pricing, editable balance-alert and daily-budget bubbles, a module-based custom bubble queue with A/B weighted choices and random lines or images, 30+ vendor templates (OpenAI, OpenRouter, Kimi, SiliconFlow, Ark, Zhipu, MiniMax and more) with per-model balance and subscription quota, plus task-end sound, imported audio, custom roles and a resource manager. Local-only, no telemetry.

A whale-girl companion for DeepSeek Harness with 45 achievements, daily quests and weekly check-ins, three mini-games, 92 artworks, 620 dialogue lines, a growth journal, weather and festival reactions, per-tool work poses, cross-device save export/import (JSON file or migration code), accessibility mode and an optional MiMo TTS bridge. Data stays in the host localStorage with no telemetry. Verified on DSH desktop 0.2.0-rc.2; compatible with 0.2.1-rc.1/rc.2 and legacy 0.1.x web.

A personal usage profile page in the DSH sidebar, folded from this machine's own session logs through ctx.sessionQuery. Five headline numbers (tokens with a small trend and the change against the previous period, spend, longest task, the active-day streak with your best, today's cache hit rate), a 12-month activity grid in daily / weekly / running-total views, a model-family chart by day, week or month as stacked columns or a share pie (version and tier stay apart, and vendor-specific ids collapse correctly), a token-stats ring chart of where the tokens went (system prompt, tool definitions, user messages, injected context, skills, tool calls, reasoning, answers), tokens and spend per project with the subagent share, and a per-provider split with each route's own hit rate and spend. A range switch in the header (today, this week, this month, all time or custom dates) drives the token and spend numbers, the token stats, the projects and the providers, and the selected range exports as CSV or JSON. Spend is priced at bundled list prices (peak and off-peak hours for DeepSeek direct); each provider can be set to list price, a discount, a monthly plan or not counted, stored only on this machine. The only outbound request is a six-hourly read of this package's own version from npm for the in-panel update button - no telemetry, no credentials, nothing uploaded.

Converts session, agent-loop, LLM, and tool lifecycle events into OpenTelemetry GenAI traces and metrics, exported over standard OTLP/HTTP to any compatible backend, with content capture off by default.

Exports the session event stream to OpenTelemetry OTLP and Langfuse as sanitized, buffered traces and metrics, off by default.

Usage tiers and shareable stats cards: 🐟→🐳 ranks by monthly token burn with a locally-computed estimated percentile, precise pricing for 46 models across 6 vendors (including size-tiered Chinese pricing), backfill of pre-install sessions, and old-vs-new comparison across the 2026-08-17 rate change. Local-only, no telemetry.

Exports the agent loop to GreptimeDB as OpenTelemetry traces, metrics and logs, with seven Grafana dashboards covering token usage, cost, session outcomes and per-turn latency.

eDEX-UI-style shell over the DSH web GUI: system-telemetry left bar with per-core CPU sparklines, encom-globe world-map right bar with up/down traffic chart, filesystem browser with file preview, and a terminal-styled composer that follows the active workspace.

An opencode-inspired terminal UI for DeepSeek Harness that boots as a dsh profile app plugin, with a session sidebar, streaming chat, markdown tool cards, todo lists, slash-command suggestions, a telemetry footer with a context meter and inline approval prompts.

Zero-LLM auto-capture and a symbolic \[ENGRAM\] index with progressive disclosure, an ESR-lite task/evidence protocol (esr_task / esr_node / esr_close / esr_link), and per-workspace usage telemetry with an offline recall benchmark (npm run eval).

Connects free and check-in account channels to DeepSeek: Huawei Cloud CodeArts, Tencent CodeBuddy / WorkBuddy, Qoder, TRAE, Raccoon, LobsterAI, MiniMax, ZCode and iFlytek Loomy. Sign in to each channel in settings, claim the daily check-in where the channel offers one, sync the available model pool, and use those models as ordinary providers in the model picker, with a local usage dashboard that counts requests and tokens per account and model. Credentials stay in ~/.dsh/get-it-for-free/ on this machine; no telemetry and no requests to upstream repositories. Its optional LAN relay is off by default and listens on 0.0.0.0 when you enable it.

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.

One-line sidebar badge for OpenCode Go quota (5-hour, weekly and monthly windows), switching to the DeepSeek official balance when that model source is selected. Read-only, no telemetry. The OpenCode Go quota needs OPENCODE_GO_API_KEY configured in DSH, or an OpenCode Console login (its local credential file is read as a fallback), and the DeepSeek balance needs DEEPSEEK_API_KEY configured in DSH.

Runtime policy guards that block repeated failing tool calls, oversized shell commands and network commands chained with local ones, composite batch tools (read_batch/edit_batch), a SYSTEM.md mode that replaces the official system-prompt sections with your own file, soft convergence notices, and turn telemetry for DeepSeek Harness.

Host-side orchestrator for DSH agent teams. Every turn it injects an 11-section orchestration methodology into the system prompt and backs it with a counting tool-layer gate, so parallel dispatch, task-board tracking, cross-session handoff, employee-pool reuse and preset routing become the default in any preset and any session instead of something you have to ask for. The gate counts real dispatches (subagent / subagent_fork / spawn_teammate) rather than words: a todo listing N unmarked items only needs the base threshold, items explicitly marked as parallel must be launched in one batch up to a configurable cap, and a genuine single-step task is exempt by writing one marker. Read-only tools (read, glob, grep, context-management tools) are never gated. Team members are woken up and reused before new ones are hired, and subagents are reserved for work that must run under a specific preset. Local-only settings (preset routes, domain keywords, profile name, active tier) live in <DSH_HOME>/team-orchestrator.local.json and never ship inside the package. Status is exposed on a loopback-only HTTP route. Zero telemetry, no hosted service, no account. Adapts DSH kernel 0.2.2-rc.1.

Runtime plugin firewall for sessions started through its launcher (the DSH Desktop app cannot be injected and is not covered): filesystem, network and subprocess calls plugins make are attributed to the plugin that made them and judged against what that plugin declares, so a plugin doing its declared job stays silent and leaving it is recorded. Attribution is best-effort, not a guarantee - uncovered calls fall back to host, never to another plugin. Also adds a pre-install health card (capability surface, red-line combinations, PASS/WARN/BLOCK), boundary judging, opt-in pre-execution blocking with a credential-exfil rule, update diff with a trial install in an isolated child process, SARIF/CSV audit export, and multi-source aggregation. Local-only storage, no telemetry; the optional webhook is off by default.

Eight academic skills bundled for one-command install — publication-ready academic figures designed from real data with visual review, AI-text humanization, paper polishing and rewriting, PubMed citation verification (DOI/PMID reconciliation), Chinese citation and medical-book reference checks, and WeChat medical article structuring. Three skills run fully local, five call external services only when used (NCBI E-utilities, DOI resolvers, publishing platforms), declared per skill. Zero telemetry, no install-time scripts. Skills run local Python 3.8+; the academic-figures skill also needs its pip dependencies installed.

Continues work across coding agents inside DeepSeek Harness: six sessionflow_* tools query a local session index built by sessionFlow to find past work, show where the current project left off, and hand the goal, files and open items to the next agent. Requires the separate sessionFlow core, installed from its GitHub repo. Everything stays local — no cloud, no telemetry.

Self-tending living memory in one local SQLite file — a nightly patrol dedupes, merges, decays and cross-links entries on its own, with seven-signal RRF hybrid recall (FTS5 + jieba Chinese-first tokenization, optional vector KNN, graph PPR), a typed knowledge graph, conflict detection instead of silent overwrites, and web telemetry panels.

Zero-touch runtime telemetry for DSH: every session auto-writes task, model tier, tools, failures, duration, status into a human-readable journal with a stats section (pure observer — no tools, no LLM calls, no injection).

OpenTelemetry traces backend for the DeepSeek Harness telemetry seam: folds agent session events into OTLP span trees

Langfuse observability for DeepSeek Harness: exports session logs as OpenTelemetry traces (GenAI semantic conventions) to Langfuse's OTLP endpoint

Redacts supported secret patterns from the `session-telemetry/record` export copy before configured telemetry backends receive it.

Adds the MathWorks MATLAB Agentic Toolkit skills and the MATLAB MCP Server tools to DeepSeek Harness. Needs a local MATLAB R2021a or later. Installs from the plugin's own prebuilt release archive. A DSH restart is usually unnecessary: the market mounts the plugin live, and a page refresh shows the MATLAB settings page; restart only when the market reports that the live mount failed. By default (autoProvision) it downloads the MathWorks MCP Server binary and installs the newest Agentic Toolkit release on first use. With the China download region or a configured GitHub prefix, both are fetched through the fastest measured acceleration prefix first (the plugin's own, DSH's market setting, or the built-in gh-proxy.com and ghfast.top routes) and then directly. The downloaded server binary is verified against the SHA-256 digest GitHub publishes for its release asset when the release metadata can be read, and a mismatch refuses the install; if api.github.com cannot be reached the digest is read through the same mirror, so the check then only catches a corrupted or truncated download. MathWorks telemetry is disabled by default; set disableTelemetry to false to re-enable it.