Plugins

A separate narrow-screen web surface for DeepSeek Harness rather than the desktop GUI scaled down: it serves its own session list and chat stream behind a random access token over LAN, a tunnel (cloudflared, localtunnel or localhost.run) or an SSH reverse forward through a server you own. On the phone it streams assistant text, thinking, tool calls and results, sends prompts, stops the running turn, answers blocking questions and tool approvals (including ones waiting in other sessions), switches model, thinking level and permission preset, sends up to four photos compressed on the device, and keeps the computer awake.

Merge requests, review threads and pipeline job logs for GitLab over its REST API with a personal access token, in a side panel, with comment, reply, resolve and approve actions that wait for confirmation. Reads need the read_api scope, writes need api.

Keeps bulk output out of the conversation: ctk_execute, ctk_execute_file and ctk_batch_execute run code in a child process and return only the conclusion, ctk_index and ctk_search file long material into a local FTS5 knowledge base built on node:sqlite, and a routing gate refuses curl and wget before they execute. Ships ctk_stats and ctk_doctor plus a settings page with a live context-occupancy panel. No third-party runtime dependencies.

Context governance for DSH: folds oversized tool results, collapses the tool surface and keeps the prompt cache warm, so long sessions stop getting more expensive.

Connects a locally-signed-in Cursor desktop app to dsh as a native LlmAdapter — reads the Cursor login token from state.vscdb or auth.json, drives the private agent.v1.AgentService/Run HTTP/2 bidi stream, and translates InteractionUpdate deltas into dsh StreamChunks. No loopback proxy. macOS, Windows and Linux.

Model channel auto-enricher for DeepSeek Harness: eliminates manually configuring contextWindow, maxTokens, \[text, image] multimodal input, and {low, high, max} reasoning effort tiers model by model after adding a provider channel, with live auto-enrichment on save, a Settings UI page, and timestamped backups.

Token usage dashboard in the DeepSeek Harness sidebar: daily totals from session logs with a 12-month heatmap, per-provider breakdown over today/7d/30d/all (hourly for today) including each route's average output speed, and a per-session ranking that includes archived and deleted sessions and folds subagent usage into its parent.

DeepSeek Harness plugin for SuperGrok and X Premium subscriptions: device-code sign-in, the xai provider, account-visible chat models with context and per-million-token prices, reasoning efforts read from model capabilities, and subscription usage.

Per-turn tool cost line in the chat stream: after each turn a collapsible row under the reply lists which tools ran, how many times, and how many tokens each tool injected into the context (input plus output), expandable to per-tool detail.

DeepSeek balance and usage monitor for DSH: a corner widget showing topped-up balance, per-model period consumption, token breakdown, and a Beijing-time peak/off-peak price reminder. Add a DeepSeek API key in the settings first.

Shows your DeepSeek balance and what the current session has cost in a corner overlay, with budget alerts, peak-hour warnings and opt-in official price sync.

Token usage dashboard and per-session tree statistics: provides time-range filtering, 6 summary metric cards, GitHub-style activity heatmap, model stacked-bar charts with cache hit rate curves, and Top-5 model/provider rankings; enhances the native session status bar to display aggregated token usage across main agents and all subagents with detailed breakdowns.

Per-turn first-token latency and output speed beside the built-in usage pill, folded on the host over the durable event log: first-token time is replayed from each message's compact stream, so historical turns stay exact after a reload rather than showing an estimate.

Cuts session input tokens three ways, each with its own switch in a panel under the composer: lossless structure-aware compression of tool results on `tools/post-execute`, then a per-tool head/tail elision that always names a recovery path through the shared spill store; tool-catalogue visibility per agent on `agent/created`; and a per-workspace memory document that recall matches against each new message and injects through `agent.inject`, so the transcript is not re-read. Measured 41.76% fewer prompt tokens over 149 recorded requests, with a bundled script that re-measures any profile.

Registers an apiCost session projection that estimates DeepSeek spend from reported token usage at published peak / off-peak rates, in CNY and USD, over self, delegation-tree or verified-team scopes: a composer-dock pill and its detail panel, the /cost command, a session_cost tool, and GET routes for the view and the current rate card. A panel switch parks model requests at the llm/stream waterfall while peak rates apply and dispatches them unchanged once the off-peak window opens, so the call is billed at the off-peak rate with no failure reported to the session.

A Herta theme for DeepSeek Harness: an ASCII boot opening ported from the upstream Herta project, a violet palette of design tokens, swappable wallpapers (four bundled, plus image URL, local import, solid colour or off) and a "Herta Appearance" page in DSH settings. Doubles as the theme that dsh-herta ships with.

Adds a refresh button and a power menu (restart / close DeepSeek Harness) to the conversation header. Client-only, zero tokens, no dependencies. The power menu is Windows-only.

Shows what each completed turn cost in CNY on its own row under the turn, with a click-to-open breakdown naming the tokens per category, the unit rate, the matched price rule and the billing instant; per-model rates are edited on a settings page inside DSH — four token categories plus weekly recurring peak/valley rules with arbitrary multipliers and absolute time-window promo prices that override them. 0.2.3 adds account awareness: it reads the balance or remaining quota of 14 providers (DeepSeek, OpenRouter, Zhipu GLM, Moonshot, MiniMax, Kimi Coding, OpenAI-compatible relays and more) and shows today / this month / this session spend next to it; spend is accumulated in a local ledger (atomic writes, one book per API key, 1-24 month retention, JSON export), and a monthly calendar lets any day be corrected by hand - including days with no balance observation - with an optional note. Usage and rates are computed locally from what the provider reported; balance is read straight from the provider API with your own key, and nothing is sent to a third party.

Nai milk-frog mascot appearance layer for the DeepSeek Harness web GUI: wears the bundled milk-frog artwork as the GUI background (surface-token fade with opacity, blur, scrim and position controls), seats the matching square avatar as the sidebar and conversation brand mark, and edits it all from a Settings section; the host serves the artwork and config locally under /api/nai, and the config lives at $DSH_HOME/nai.json.

A token-based DeepSeek Harness theme plugin with ten presets, custom colors, and system font pickers.

Long sessions get expensive, and the platform compacts the context on its own. This plugin adds an occupancy badge (hover to see how it is computed), writes a handover draft into HANDOVER.md from 45% — files changed, money spent, what recent turns were about — and reminds you once at 60% to wrap up. On compaction it records the reading from just before, so you can check it later. No model calls, nothing added to the conversation; it does not prevent compaction.

Native token-based themes for the DeepSeek Harness Web GUI, with custom colors and system font pickers.

Context fullness bands, the per-session compaction threshold derived from the model window, per-step cost computed from cache read and cache write rates, cache-hit, DeepSeek balance with the peak/off-peak tariff, and a one-click handoff. It never calls a model and spends no tokens.

DeepSeek Harness plugin: tells the model its real, host-measured context occupancy every turn — and keeps compaction summaries from carrying false "context is nearly exhausted" claims.