Plugins

Live DeepSeek API balance and this session's token usage in the conversation header, with a detail panel for the topped-up / granted balance split, request count, input, output and cache-hit tokens, and context pressure. The API key is read on every query and is never cached, written to disk or returned to the browser.

Local-first usage analytics for DSH: subscribes to session events and aggregates tool calls, turns, errors, latency and capability usage into daily tables, shown in a sidebar panel (6 KPIs, 14-day trend, top tools, capability breakdown) and served over a fenced local HTTP API with 18 JSON-RPC methods. Zero runtime dependencies, local mode makes no outbound requests, and no message bodies are collected.

A token toolbox for DSH: next-turn token forecast, a cross-session usage analytics panel built on the host session-projection unit, and prompt restructuring that writes back only when accepted.

Reorder configured models in the composer model picker, set cache-hit, cache-miss and output prices per million tokens, and estimate per-turn and session costs with built-in DeepSeek peak/off-peak rates.

DeepSeek account balance above the sidebar account area, the running cost of the open conversation, the cost of each turn beside its token count, and a one-click AI breakdown for any turn above a token threshold.

Watchdog for quota exhaustion: on a 429 or quota error it creates a recurring schedule that re-sends a continue-the-task prompt until a turn closes normally, so a long task resumes without manual restarts; /keep-running list and /keep-running cancel <id> manage those schedules. Requires @deepseek-ai/dsh-schedule to be mounted first (it registers the schedules).

Cross-session token dashboard for DSH: daily spend as bars, trend or cumulative views plus a GitHub-style annual activity calendar, model and workspace splits, cross-filtering between day, model and workspace, and a per-turn timeline that also covers web-search and auxiliary model calls.

Turns the DeepSeek Harness sidebar panel entries and footer entries into one row of icon-only squares with hover names, adds four icon-size presets, per-entry show/hide switches and up/down ordering, and puts a Settings shortcut in the footer row.

Turns one plain-language request into a live workbench window: a sidebar panel asks a few clarifying questions, the model writes a single-file HTML artifact, and the plugin mounts it in a resizable floating window or a standalone browser tab. Declared window actions are recorded as info-level project journal entries (without their payloads), and workbenches can be imported, exported, or installed from a market index.

Four whale-tail animations for the DeepSeek Harness thinking indicator, cycling on every thinking turn.

Windows-only power card injected into the DSH page: the artwork carries two hit zones (left shuts down, right restarts), the first click only turns the card into a yes/no question and the second click fires, and the restart engine stops only this instance's process tree, waits for the port to free, relaunches outside the host's Job Object and confirms the new instance answers on the plugin's own status route.

Predicts your next message after each completed turn and shows it as ghost text in the composer: press → to accept, or keep typing and finish it word by word with Ctrl+→, Esc to dismiss. The prediction model follows the session by default or can be picked in the settings card, which also has an on/off switch and a speed test.

An always-on-top desktop pet (a washing machine) that renders session state as washing actions: four switchable skins, multi-session counters, and proactive done / stuck / approval alerts on macOS and Windows, plus a detail panel with recent turns and timings.

Live preview inside the sidebar session hover card: what the session is doing right now (running tool with elapsed time, thinking, last tool duration), an attachment thumbnail with click-to-enlarge, the latest user prompt and assistant reply with injected system scaffolding stripped out, a recent-tool icon strip, turn count plus token totals plus model name on one line, and a 12-item settings page (11 switches plus a slider) persisted to the profile.

Composer enhancements: caches unsent drafts per workspace for new sessions and per Session id for existing ones, restoring them after switching away and dropping them once sent or cleared; adds an @plugin completion group that mentions an installed plugin so the agent receives that plugin's metadata as runtime context for the turn.

Shows the signed-in DeepSeek account's remaining balance in the DSH composer bottom bar, next to the shipped turn/step and token-usage pills, and refreshes it periodically and after each turn.

Freezes the DSH chat scroll position: new replies no longer drag the viewport to the bottom — it stays where you left it. Only after you send a message does it follow to the bottom so you can see your own input, then it locks again once the answer starts streaming. Each session remembers its own position (persisted across reloads), a settings toggle turns it off, and it never intercepts your own scrolling.

DSH guard against self-repetition in streamed model output: detects a degeneration loop in reasoning or visible text, aborts the runaway turn and wakes the agent with a corrective notice.

Turns the right edge of the chat scroll area into a theremin-style strip: the vertical mouse position picks the pitch (higher up, higher note), and blue ticks mark your own messages so you can click one to jump to it. Includes a draggable on/off pill and volume slider.

Watches a turn's thinking and output streams and cancels the turn when the model starts repeating itself. Four detectors: a verbatim cycle, a counting loop whose lines differ only by a number, repeated lines separated by other text, and a user-supplied phrase list. A catch raises a manual-dismiss alarm card in the global overlay with an optional tone, and a Monitor tab holds the switches, thresholds and hit history. Detection is local string comparison with no model calls, so it costs no tokens.

Adversarial review gate for tool calls. It hooks `tools/pre-execute`: a local regex pass over destructive commands (`rm -rf`, `git push --force`, `git reset --hard`, `DROP TABLE`, `format`, disk writes) and sensitive paths (`.env`, `id_rsa`, `.ssh`, `.git/`, `$DSH_HOME`) runs first with no latency, and only a hit is escalated to one review-model call that returns allow or deny. Plain reads and ordinary writes never enter that path, so everyday work pays no added delay. Every verdict is shown live in the Web GUI.

GitHub issue service for DSH: turns a telemetry failure analysis into a uniform issue report, builds a pre-filled new-issue URL that is shortened when it would exceed a configured length budget, rewrites a plain description into a structured issue with the deployment's model, and closes the intake loop by listing the open issues that carry a claim label and handing each one to a fresh session, skipping issues an earlier pass already dispatched and repeating the pass on the first start of each local day when autopilot is enabled.

Emails you when a long turn finishes or errors, when a goal completes or blocks, and when an approval or a question has waited past a timeout; each new notification deletes the previous one from the inbox over IMAP, so the inbox holds at most one.

System notifications, a tab-title dot and a PWA taskbar badge when a reply finishes in the background or a session waits for your approval, plan review or answer, all cleared when you return to the window.