Plugins

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.

Slims oversized MCP tool JSON Schemas per agent without changing dispatch, and reports token usage, cache hits and context composition on a settings page.

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).

Distill over-long model reasoning into its useful core, replay the compressed version on every later request, and report each session's cost and savings. Disabled by default: select one rewrite backend first. derive needs no install and works on packaged DSH; in-place needs 14 source patches and a rebuild (recommended for source checkouts); message-edit needs a third-party plugin and is experimental only.

DeepSeek account balance capsule in the conversation session header. A same-origin route registered by the package's own host half resolves the API key from the credential service and calls api.deepseek.com/user/balance, so the key never reaches the page; the capsule polls every 60 seconds and expands into a panel with per-currency totals, granted and topped-up amounts, last-updated time and a manual refresh. Read-only UI: it never touches prompts, tool results or model traffic.

A draggable balance and usage card for the web UI. Clicking the character button slides the card out from the left side of the image and clicking it again retracts the card; it shows the official DeepSeek account balance split into granted credit and top-up, and token usage folded from local session logs for today, the last 7 days and the month, priced per call with the official peak/off-peak rates (cache hits, cache misses and output are priced separately).

Adds a Geek level to the Performance & usage setting: a live reading of the newest request in the composer status row (first-token latency, generation speed, output tokens, total time, amortised speed), and a drawer listing the last ten requests with an average row. Output tokens come from the provider usage; a calibrated character estimate is used only when usage is absent.

Floating overlay in the Harness Web UI with OpenCode Go usage: 5-hour rolling, weekly and monthly percentages, reset countdowns and the renewal date, with device-code sign-in and silent token refresh.

Reads the local Codex CLI ChatGPT-plan quota (5-hour and weekly windows), defaults to gpt-6.1-sol at high reasoning, falls back to gpt-5.6-sol when a window has 10% or less left, and delegates tasks through codex exec with an explicit opt-in for the expensive gpt-6-astra model. Requires a signed-in Codex CLI (`codex login`).

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.

Task details sidebar for DeepSeek Harness: a "View task details" button under every finished turn opens a resizable right-sidebar panel showing that task's input files, intermediate artifacts, output files, tools and skills used, inferred languages, a step-by-step flow timeline, and the model provider with token usage and cache hit rate.

Replaces the composer model control with an inline Provider/Model trigger — clicking it opens a two-column card with providers on the left and the hovered provider's models on the right — and moves the reasoning effort into its own trigger beside it, unlike single-button model pickers.

Startup video intro with per-clip playback parameters (segment, speed, brightness, fit, blurred cinema fill, hold ratio and fade duration) and light/dark clip variants selected by the app theme.

A client-side panel for DeepSeek Harness: it stacks the epic cards of a dsh-taskboard project in their epic:children order, shows the position, code, name and version of every module along the arc, and marks the start, middle and end modules. The order can be changed by drag or by buttons, and the new order is written back through the the taskboard own public update API, so it persists and is shared by everyone viewing the project. Requires the cloader/dsh-taskboard plugin.

Windows only, needs the NetEase Cloud Music client installed. NetEase Cloud Music player for the DSH Web UI: a mini bar that expands into a liquid-glass card with search, synced lyrics and volume, a click-to-open spinning vinyl view, and it signs in with the local NetEase client account (cookie decrypted on this machine only) so VIP tracks play and the client current song can be pulled in.

A2UI-inspired agent-authored application cards with a persistent machine directory, SSH probes, and reviewed monitoring and control actions. SSH probes require OpenSSH (ssh, ssh-keyscan, ssh-keygen).

Artifact center: search, preview and open files produced by DSH conversations.

Imports SillyTavern AI presets as switchable, editable prompt layers: preserves the raw JSON, edits prompt order and sampler parameters, previews the injected System Prompt, exports back to SillyTavern-compatible JSON, and archives or permanently deletes presets with confirmation. Applies temperature and maximum output tokens to Harness requests; other sampler fields are preserved and exported but not applied.

Editable prompt shortcuts beside the DSH composer: save the prompts and phrases you retype as buttons, then send the preset text or insert it into the draft, and reorder, move, or resize them. Text-only: runs no host commands and never overwrites an existing draft; a button can also read the previous message, the draft, or the selection when clicked, and ask you to fill in {{name}} slots before it runs.

Live multi-way tree of the current session's agents in the DeepSeek Harness conversation view and right sidebar, with status, plan progress, tokens, cost (requires dsh-cost-meter), and runtime on every card.

Replaces the new-session hero with a combined picker: role cards for the agent presets and a workspace card, collapsed into capsule buttons that expand into two scrollable rows.

Sparkle button immediately left of the model selector that rewrites the composer draft into an executable prompt in place, modelled on WorkBuddy: the host calls the conversation LLM with a prompt-engineering system prompt, multi-level undo keeps up to 8 previous drafts, and a token-level diff card shows added and removed spans, the number of changed spots and the net character delta. Runs on the session model, is disabled while the draft is empty, and keeps the browser-session cookie fence in front of the LLM call.

Adds a Traditional Chinese (zh-Hant) language to the web GUI, registered through the locale service with one dictionary per namespace and selectable in Settings, General, Language.

Replaces the host-side folder chooser in the Add workspace flow with a name dialog, so a remote browser can create and open a workspace instead of an OS dialog appearing on the Host screen.