Plugins

Estimate the current session cost and view model costs and the DeepSeek API balance below the composer.

Keeps a root turn open until progressing child agents and the current-turn background jobs it started settle, then asks for one self-contained final answer in that same turn. Idle children that still have parked input do not delay closing. It observes job settlement without consuming job output, never cancels children, and does not decide task success. Verified on DSH 0.2.2-rc.2 only; on any other host version it stays inactive, logs one warning, and turns close natively. Each batch of results that arrives after a reply costs one extra model call; ordinary questions add none.

Read-only session dashboard for DeepSeek Harness over the local ~/.dsh data: a sidebar overview of every session (tokens, estimated cost, turns, tool calls, model mix, daily activity, searchable and sortable session table) and an in-conversation Dashboard view that shows the current conversation turn by turn with per-turn tokens, cost, timing and tools. Zero dependencies, no network.

Runs a four-task, 150-point model intelligence benchmark inside DeepSeek Harness (Qin 60, Pompeii 45, Pelican 22.5, Candy 22.5): each selected model × reasoning-effort pair executes every task in its own isolated subagent session, Qin and Pelican are graded by the selected judge model against rubrics, Pompeii and Candy programmatically, and batches keep scores, artifacts and cost. Adds a 0–1000 real-world performance score per model × effort computed from local session logs across seven dimensions (output speed, first-token latency, reasoning speed, tool cadence, tool latency, tool success rate, cache hit), with baseline deltas and controlled speed runs, plus a sidebar page with ranking, performance, history and settings views. Each batch spends real tokens of the candidate and judge models, and candidate subagents get file and bash tools inside an isolated run directory.

Adds a recap card under the composer for the current session: turns, steps, tool calls grouped by name, the uncached / cache-read / cache-write / output token split, the cache-hit rate, and a cost range computed from the official Flash off-peak and peak list prices. Exports the same card as Markdown or a standalone HTML page.

Per-session token, cost and wall-clock budgets that stop the model session at the limit, plus a DeepSeek peak and off-peak schedule.

Per-task cost dashboard and budget guard that prices each model call at peak or off-peak rates, turns the remaining budget into a per-turn work envelope in the system prompt, and stops the task at its cap until the user replies. The default cap is ¥0.5 per task.

A draggable task progress panel with local estimates, independent teammate progress, optional AI observations, and probe cost diagnostics. Release candidate for the Web profile only; needs Node 24.9 or later and Harness >=0.2.2-rc.1, tested on 0.2.2-rc.2. AI observations are off by default and, once enabled, spend tokens of the session's provider. It uses the same package name and mount id (dsh-task-progress) as chen8923/dsh-task-progress, so install only one of them.

Standalone rescue for a broken DeepSeek Harness profile: a CLI that runs without DSH diagnoses the crash logs (six classified causes, from real incidents), pre-flights the profile for command-name collisions and files plugins read at construction time, arms a safe mode that loads only official bundles until a healthy boot restores them, and keeps manifest snapshots for rollback. A resident watcher watches the crash-log directories via OS file events — idle costs nothing, and when the loader dies the report is written within seconds, one file overwritten per crash. Windows only: crash logs are read from %APPDATA% and the watcher autostarts from the Windows Startup folder.

Drives the Edge already open on your machine through a local WebSocket bridge and an unpacked MV3 extension: the agent reads the page as Markdown, dumps its interactive elements with stable refs, clicks and types with pre-action assertions and a three-valued effect state, and can capture pages from the extension popup as self-contained HTML snapshots, filed into a kb.py literature knowledge base when one is configured (kbRoot or DSH_KB_ROOT). Seven browser tools stay unregistered until edge_bridge is started, so an idle session pays no context cost.

DSH prompt-cache health guard and cost coach: install from npm as dsh-prompt-cache-guard (not the unrelated dsh-cache-guard package). cache_guard_health returns green/yellow/red health, a one-line hint and a PTC suggestion; cache_guard_config reads or updates settings.

Manage a domain portfolio in DeepSeek Harness: sync registrations from Namecheap and Cloudflare, track expiry dates, auto-renewal and yearly renewal costs, and check domain availability. Read-only towards registrars (never registers, transfers or renews). Syncing needs a Cloudflare API token, or a Namecheap API key with an allow-listed IP (or Namecheap's browser-login connector, which cannot read renewal prices).

Sidebar token and cost curve for the current conversation plus a local ledger across all sessions: monthly/weekly rollups, per-turn detail, Excel export with print-ready A4 layout, and a live account balance. Reads session logs only, prices every message by its own peak/off-peak timestamp, and drops fork-inherited history so it is never billed twice. Desktop app only, verified on Windows; the live balance needs a signed-in DSH account.

DeepSeek Harness usage meter: a current-session cost status bar plus a Codex-style statistics page with token KPIs, a 53-week activity heatmap and weekly cell bars, priced with DeepSeek peak/off-peak rates.

Usage and balance dock for the DeepSeek Harness sidebar: today's spend next to a Beijing-time peak/off-peak pricing band, today's tokens and cache hit rate, and a plain balance row that opens a detail panel. The panel lists the balance account, an eight-week activity heatmap where any day can be selected, and that day's tokens, cache hit rate, peak/off-peak cost and per-session breakdown with each session's own composition bar. Usage is read from the local session logs only; the only outbound request is the balance query against the provider base URL already configured in DSH. A heavily rewritten fork of Aisland-SJL/dsh-usage that uses the same plugin id (usage), so install only one of the two.

Estimates recorded DeepSeek model spend per conversation and turn, with a cost-ranked overview. Built-in tariff table covers 2026-09-11 to 2026-12-31.

Imports DeepSeek usage exports (ZIP, CSV, JSON) locally and renders token and cost trends, per-model and per-API-key breakdowns, cache savings, input/output composition and usage spikes. The interface is Chinese only.

Bottom-right whale widget showing DeepSeek balance, today's spend from the official usage API, per-turn cost narrated after each turn, and a peak/off-peak pricing countdown, with six expressions, click-to-refresh, weather and a bilingual (中文/English) UI.

Reads local DSH session logs to show real token totals, session count, estimated cost and budget, a 14-day usage timeline, per-session breakdown and CPU monitoring, plus a draggable token/cost status window and a whale-girl who eats rice as tokens are spent.

A cost bar for DSH relay users: current-session and today totals under the composer (today includes already-closed sessions), a peak/off-peak dot, and no call to the official balance API. Click for a per-model breakdown; narrow windows keep the money line first. Derived from KIDLi1412/dsh-session-cost (MIT); it uses the same plugin id and /api/session-cost/summary route, so do not install it alongside the original.

Per-turn cost meter and tool-loop guard for the DSH web GUI. It records model, tool and idle time for every turn, blocks runaway tool calls with a dynamic step gate, a retry breaker and a slow-command block, and renders the breakdown as a card under each reply plus a ledger view.

Models 64-token cache blocks and calculates per-turn API costs and cache ROI.

Super input suite — model and effort picker, prompt enhancer, follow-up suggestion chips, a full cost engine with daily heatmap and Coding Plan quotas, voice-input light effects and transcript cleanup (needs the built-in voice-input bundle enabled), prompt templates, selection reference chips with comments, a compaction ring and a settings hub. Bundles the author's standalone dsh-cost, dsh-power-picker, dsh-prompt-enhancer, dsh-followup, dsh-siri-voice and dsh-compaction-control; uninstall those before installing.

Reference-image picker for the DSH web composer: browse face, costume and pose libraries, then insert high-resolution images and a generated prompt into the current draft in one click.