Plugin

Live token cost for every chat in the DSH Web UI: the chat, its subagents and the whole session tree, priced from a bundled models.dev snapshot of seven providers and 139 priced models, with cache read and write rates wherever the provider publishes them and DeepSeek from its own peak and off-peak table. Every finished answer carries its own price in the transcript, and a chat that is not currently open is priced from the log instead of disappearing. Spend is costed per interval from an append-only JSONL ledger in the project folder, so logged work keeps the tariff it was billed at. On top of it: budget-aware work plans packed against a money limit, routing scenarios that show which models are worth connecting, a generated plan document in English, Chinese or Russian, and a warning when spend belongs to no plan unit.

Four right-Sidebar panels for the dsh web client: artifacts, long-term memory, terminal and notes. They pair two per tab with a draggable split, so two panes show all four at once. The host half ships nine memory_* tools, artifacts_list, the /memory command, and the /api/artifacts/* and /api/terminal-notes/* routes. The terminal runs one bash command per line, with a default 120-second deadline and a stop button. Requires dsh 0.1.5 or newer, and 0.2.

Shows DeepSeek peak/off-peak pricing status, a countdown to the next rate change, and the estimated session cost as inline text beside the model selector.

Git server: embeds ts-gogs (a TypeScript reimplementation of Gogs) and serves a full Git service on its own port — HTTP clone/push, web UI, issues/PRs/wiki — reusing user-management credentials, start/stop from the settings page.

Language-pack framework that rewrites model replies: A is an independent LLM rewrite, B injects FTS5 terminology retrieval into that rewrite, C applies local dictionary and regex rules, and composite runs a pipeline such as B then A then C. Ships a GitHub pack marketplace, a ZIP installer with path, size and file-type checks, and a mandatory risk disclaimer gate.

Peak / off-peak rate badges for the model selector (every row) and the composer tool row, judged per provider by its own time zone and schedule; the live catalog is served from the host over a fenced route.

Publishes the running dsh Web server's PID, port and tokenized URL to a runtime file for the DeepSeek Harness Switch Dock app, and removes it on shutdown.

Immersive read-only reading panel for DSH — the model delivers pre-formatted Markdown to a native right-sidebar tab via `reading_pad_send`, with three low-blue-light themes and 30em measure typography; also browse manuscript chapters read-only.

Folds streaming reasoning and tool calls into collapsed step bars and collapses each finished turn into a single summary bar; step bars show native tool icons, filenames, edited line counts, and failure counts, finished turns restore duration, first-token time, token usage, generation speed, and cache hit metrics from recorded Session events, and preferences persist on the Host. Changes browser presentation only. Requires DSH 0.1.5-alpha.1.

Adds a Long text button to the composer tool row: write or paste the body in an editor overlay, and on save it is written to <workspace>/.dsh-longtext/<timestamp>_<title>.md and an @ path reference to that file is appended to the composer, leaving the conversation free of the long text itself.

Text-to-image for DeepSeek Harness: a `draw_image` model tool, an input-bar 生图 button with a prompt popup (async generation, 4-grid results, download / keep / delete), an /imgdraw image route, and persisted history. Backends: DashScope wan2.7-image (free

macOS menu bar app for the DSH web server, plus the host plugin it reads: the plugin writes the running server's port, PID and tokenized URL to ~/.config/dsh-launcher/runtime.json and removes it on shutdown, so start, open, restart and stop work from the status bar even for a server started from a terminal.

Agent-native API client for DeepSeek Harness: Postman-like debugging UI (request tree with context menus and full keyboard navigation, resizable sidebar, layered auto-generated header preview with per-item suppression and constant secret masking), six api_client_* agent tools sharing the same request core, redaction and audit chain with the human UI, Postman Collection v2.1 import with a migration report, environment variables with SecretRef indirection, and a fail-closed SSRF network policy.

Polaris Memory: local-first project memory plugin for DeepSeek Harness. Uses per-project .dsh-memory.json; provides memory_read/recall/write/update/delete tools, /memory command and settings UI, with tiered injection (resident user profile + scene-triggered memories with P1/P2/P3 importance), semantic recall (IDF + synonym layer), and a hard-guard mechanism for bottom-line memories (detect deny-semantics -> authorize -> block AI deletion; user can confirm-override).

Knowledge base with a corrective acquisition loop for DeepSeek Harness: when the agent keeps hitting the same failure, a background worker fetches the web under a rate limit, distills the result into a staging area, and only a two-stage commit makes it recallable — pages without sources are refused.

Shows selectable DeepSeek, Kimi, Zhipu GLM, and TeamoRouter balances in the DSH Web sidebar, with per-provider details, usage data, and refresh controls.

DSH Web UI workspace document vault — a “文档” tab for previewing Markdown/PDF/Excel/images/code with wikilinks, Mermaid and in-page editing.

Automatic model-tier routing for DeepSeek Harness: one user instruction enters, one tier decision comes out — complex intent is planned on the strong tier and implemented on the cheap tier, simple intent stays cheap throughout, with a deterministic guard and a TTL escalation fallback.

Scheduled send: fire a drafted message into the bound conversation as a normal user bubble at a set time. Runs host-side, so the browser can stay closed; per-session isolation and restart-safe redelivery.

Use ChatGPT and Codex subscriptions in DeepSeek Harness with OAuth, quota runway forecast, safe resets, web search, image generation, and Fast mode.

Call a new-api (one-api style) relay station's video model from the conversation with @-referenced image/video materials, supporting Seedance 2.0 and Happyhorse text-to-video and image-to-video across four relay protocols.

DeepSeek Harness Web plugin: per-model input-modality selector (text/image) on the Models settings page for third-party (pi-ai) providers.

Draggable floating ball that shows the current DSH session todo checklist live — done/total on its face (capsule mode also shows the running task title) plus a matching progress ring. Click to expand or fold the full list, right-click to switch capsule mode, and state colours mark in-progress (pulsing), done, pending and empty. Replaced plans are archived as history rows that can be hidden one by one, cleared and restored instead of counting towards progress, and other sessions can be pinned side by side. Data comes from the runtime sessions projection first with the official todo panel as a fallback, so the full list survives even when the official strip is collapsed. Text colour can be forced to auto, black or white, the ball snaps back to the bottom-right corner on demand, and it stays draggable right up to the top edge of the window. 130 shared skins — including two official dark and light skins that follow the client light/dark theme automatically, plus a per-ball sync switch so each ball either follows the shared skin or keeps its own — with Shadow DOM style isolation and position remembered per profile, identical on desktop and web.

Smart checkpoints, workspace safety guards and instant rollback for DeepSeek Harness.