Plugins

Composer meter for the DeepSeek Harness Web UI: a pill under the input shows draft character count, estimated tokens and this session's estimated cost from DeepSeek's published prices (peak/off-peak, Flash/Pro or custom rates), and opens a panel with the token breakdown, a six-snapshot per-session draft vault and a draft cleaner; every write goes through the host setDraft API instead of touching the editor DOM.

Adds a full-screen dialog for writing long messages: Markdown on the left rendered live by marked on the right, with a draggable splitter that remembers its ratio. Confirming writes the text back to the composer draft, keeping command tokens and @-reference chips as a fixed prefix; Esc asks whether to discard or write back before closing.

Opens chat.deepseek.com inside DSH Desktop from a conversation view tab (next to Chat / Trajectory / Context, scoped to the open conversation) and from a left-rail globe button — all entries share one embedded page, so switching between them never reloads it. Keeps you signed in across restarts by replaying a localStorage plus readable-cookie snapshot before the page's own scripts run, strips only the Electron/<version> token from the user agent, and keeps navigation inside deepseek.com while sending everything else to the system browser. Pure client code: no host-side script, no file access, no credential service, no server route.

Token-usage profile for DeepSeek Harness — a Codex-style usage panel inside Settings: lifetime tokens, a year of activity, cache hit rate and top models. · DSH 用量统计面板：在设置里查看累计 token、一年活动热力图、缓存命中率与最常用模型。

Two DeepSeek Harness tools for the local tempguard watchdog: read temperatures and alertd health, and send alerts through alertd; it does not start or stop the watchdog. Needs the separate tempguard Python watchdog and its alertd service running locally, with projectDir and alertdToken set in the profile patch; there is no npm package, so install from a local clone of the repository subfolder.

A gold switch beside the composer that raises every model request to the strongest reasoning effort the current model declares and to its default max output tokens, and adds a system-prompt section asking for exhaustive, self-checked work.

Per-step context ledger for dsh: measures what every step actually re-sends, then offers three opt-in gates — a schema-budgeted tool table, long-tail result externalization, and duplicate-read pointers. In the author's A/B test the tool-table gate cut 16,110 first-step prompt tokens (-49.7%), about -23% of per-step context on long sessions. v0.3.1 adds a read-only /budget-doctor self-check, spill index maintenance and a growth forecast.

Real-time per-session token cost for the DeepSeek Harness web GUI, with per-provider pricing and configurable peak/off-peak tariffs

DSH 插件：web_focus 工具按关键词对抓取页面做相关度筛选，压缩链接、过滤导航、保留可回取的原文并缓存，让 web_fetch 不再一次性消耗大量token。

Rice on a Stick: Expose control over DeepSeek Harness (dsh) through MCP (Streamable HTTP) and dsh's native tools, with a configurable list of allowed models. Long-tail host endpoints can be invoked via a generic, audited bridge. By default, it listens only on 127.0.0.1, with an optional access token.

Web GUI enhancement bundle: a standalone password gateway (optional HTTPS via your own certificate or a self-signed local CA) for LAN and remote access without `?token=`, PWA install with icon and app name, desktop and mobile Web Push notifications for task/approval events, and optional session-id request-header injection for third-party OpenAI-compatible routes, all configured from a settings page.

Agent tool that returns the running DSH Web GUI URL including its per-process launch token, so browser automation can open the GUI instead of getting a 401.

123 Cloud Drive (123pan) client: signs in with a phone number or email plus password, or a pasted token, browses and drag-drop uploads and downloads through a sidebar panel, backs up a workspace incrementally while keeping its directory tree, and exposes 15 tools for an agent to list, upload, download, rename, move and delete files. Network, MD5, 16MB multipart upload and token encryption run in a bundled statically linked C++ core, so it needs no Python or other runtime. Windows 10/11 x64 only.

Tide Memory: a long-term memory that forgets on purpose. It keeps what matters and lets the rest fade. Whether an entry enters the context is decided by an evidence score C = s/(s+2): below the threshold (0.35 by default) it never enters. Events decay by half-life (30 days, or 7 days when they carry emotion); facts never decay; superseded entries are kept and marked stale instead of deleted. Recalled lines do enter the context and therefore do consume tokens — small, but real. No embeddings, no network calls, no cloud.

Prepares context summaries in the background and applies them at safe step boundaries, with native compaction fallback and a per-conversation history of summaries, application status, timings, and token usage.

Two-level model routing: pick the best model group first, then the best channel within that model; a failure switches channel before switching model. Preference mode pins one model across its channels, a status bar under the composer shows the live model, channel health and the day's token usage, and a speed/intelligence report can be imported as the routing prior. Exposes a model_orchestrator tool and a /route command.

Derivative of dingminhua/dsh-subagent-default-model (do not install both): routes subagent delegations by role with candidate pools, cross-provider failover and fork window slicing; shows running subagents in a header panel with duration and token counts; supports mid-run and batch model switching and exposes routing tools the model can call. Subagent pages also carry a context / usage stats strip (context occupancy, output speed, cache hit rate, token buckets) and a model menu limited to that page’s whitelist — a pick outside the whitelist is substituted with an allowed model instead of running unlisted.

Cross-session usage panel for DeepSeek Harness: an always-on usage ring plus a draggable panel that aggregates token usage, cache-hit rate, cost and balance from local session logs, with per-tool cost attribution, iOS-style tile layout editing and an optional animated companion face.

Token usage and cost dashboard: requests, tokens, RPM/TPM over the last 60 minutes, cache hit rate, per-model and per-provider breakdown, a 12-month activity heatmap, and cost estimated from OpenRouter prices. Data stays in a local ledger; no telemetry.

Live tokens-per-second readout for the current session, docked to the sidebar or draggable as a floating card, with the placement chosen at the card's top-right corner.

Token usage dashboard for the whole harness: billed tokens from every session are rolled up per session and turn (uncached input, cache read, cache write and output) with a peak/off-peak CNY cost estimate, and a "Token 用量" entry above Settings in the sidebar opens the dashboard at /token-stats, in a new tab on the web and in an in-app popup on the Desktop. The page recollects and repaints every 60 seconds while the tab is visible. Usage is read from the same session event stream dsh-token-meter consumes, accepting 0.1.x assistant/chunk and 0.2.x assistant/message and assistant/attempt, and counting an attempt repeated after an llm retry as its own billed call; cold history is seeded once from a persisted rollup file and afterwards only logs whose mtime or size changed are re-parsed. Host half and client half ship in the one package.

Buckets every model call by local date, provider and model, then shows the totals in a sidebar card, a per-chat pill under the composer and a settings page, alongside each provider's account balance and subscription windows.

Shows DeepSeek account balance and today's token usage in the sidebar footer, and reconciles locally estimated spend against the balance the account actually lost over the days it has sampled.

Real-time generation-speed gauge for DSH: a half-circle dial and a flowing trend curve, sampling tok/s 50 times a second for finer, more accurate measurement.