플러그인

Cross-session task delegation for DeepSeek Harness: spawn durable top-level sessions and send them tasks, read or steer them by base62 session alias, and approve their sandbox escalation requests through an approval bridge that refuses destructive deletes.

Keeps a per-turn receipt that later turns do not clear (final todo counts, goal id and phase, end reason, and a fail-closed pass/fail/inconclusive plan verdict), plus a read-only tool to read recent receipts. Stores counts and ids only.

Inlines an image block as base64 only in the one request where it first appears, and marks that same block offloaded on every later request so DSH's own image-offload projection renders it as the placeholder text carrying the read-only local path. An occurrence is keyed by session id, message id, content-tree path and attachment id, and a request is only counted after it produces its first chunk, so retries do not count as sent. Requests carrying a purpose are neither rewritten nor counted, a later read_image of the same file is a new occurrence and inlines once more, and only that request's copy is rewritten, so nothing is written back to the session.

Displays and copies full session IDs, provides cross-session listing, reading and messaging, and creates scratch workspaces.

Cross-agent session relay: a compact "Relay" chip in the composer toolbar unfolds a floating workbench to browse recent sessions of eight external agents (Claude Code, Codex, OpenCode, ZCode, Pi, WorkBuddy, Cursor, Grok); one click spawns a DSH session with the takeover command delivered and auto-switches to it. handoff: 1 protocol inbox cards are consume-once with a four-state evidence ledger; patches ride with cards; cross-machine relay via a synced folder. Settings keeps the command reference and reader toggles.

Compiles an LLM persona in DSH from six dimensions (identity, tone, creative habits, feedback style, boundaries, run parameters), injects the compiled text into the system prompt at the end, ships six built-in templates plus a drop-in templates folder, and drafts a persona from your own past messages — either by counting patterns in them or by having the current model read them and report its rationale. Adds a panel next to the composer and a /persona command.

Recognizes a model ID in the DeepSeek Harness model catalog and fills that row's context window, input modalities and reasoning levels as editable suggestions, from a bundled offline rule table covering 33 vendors.

Gives pi-ai routed models a reasoning-effort ladder without manual settings: falls back declared to models.dev to a 7-tier default, and replaces the composer model chip with a Codex-style vertical picker.

A row of model preset buttons above the composer: left-click switches the session to that preset's provider, model and reasoning effort, right-click opens an editor for it, and each preset can carry a custom name instead of the model id. The editor reads the session's live model catalog, and presets are stored locally.

Configure thinking toggles and reasoning efforts per model for llm-pi-ai and official DeepSeek, and specify input modalities (input or inputModalities) in the DSH settings panel.

Registers a `deepseek-web` provider that drives your own signed-in chat.deepseek.com account as an extra model in DSH, so no Open Platform API key is needed: the sidebar footer lists your Web conversations, Fork to Workspace opens an independent Harness session that never writes back to the original conversation, native search stays on for the `default` model, and `/clean` is a session toggle that sends only the human text. Fork of y-wi/dsh-deepseek-web, kept working on DSH 0.2.1-alpha.2: the peer ranges are widened so the compatibility gate no longer rejects the whole bundle, the removed settings API is replaced with `ctx.settings.configure()` plus `.volatile()` config fields, the renamed client icons are updated, and an upstream SSE error now surfaces as a real error instead of an empty message that poisoned the session history. The fork also repairs what the rename to `-free` left behind: the session-list route used to derive its suffix from a hard-coded length inherited from the old package name, which had turned every conversation request into a 404 while sign-in still worked; and the sidebar conversation panel now paints on an opaque surface token instead of the host's translucent menu token, which only reads as a menu beside the backdrop blur a body-mounted panel cannot install.

Brings the providers you already configured in cc-switch into DeepSeek Harness: reads the cc-switch database, converts Claude / Codex / OpenClaw / MCode / Pi entries into llm-pi-ai routes with their API keys, and adds a health check that measures time-to-first-byte and whether each stream completes.

Shows a Spark Scope card at the bottom of the dsh sidebar: model server decode and prefill rates with sparklines, running and queued requests, KV cache, TTFT and TPOT p95, and GPU temperature, power, load and memory for each DGX Spark node. Read-only; needs a running Spark Scope server. Works in dsh web and the desktop app.

Connects Trae enterprise models to DeepSeek Harness from a personal access token alone, calling llm_raw_chat directly with no trae2api or traecli process; fetches the model catalog from upstream on startup and shows remaining quota for personal packs and enterprise seats.

Registers external ACP (Agent Client Protocol) agents such as Codex, Claude Code and Gemini CLI as DSH model providers: maps each agent's thought_level options to the reasoning-effort selector, forwards images when the agent advertises promptCapabilities.image, and routes permission requests to DSH's approval dialog; ships an ACP Agents settings page that imports Zed agent_servers JSON and discovers models.

Local-folder wallpaper for the DSH Web UI: it defaults to your Pictures library (C:\Users\<you>\Pictures) and the host serves those images over same-origin HTTP, rotating one every N minutes (0-1440, default 5) in a shuffled pass with no repeats; the settings page under Plugins picks a different folder through the native system dialog, and tunes image opacity (100%), darkening scrim (25%) and panel opacity (15%) with changes applied live. Dialogs, modals and menus keep the default opaque background so text stays readable. Reads .jpg .jpeg .png .webp .gif .avif .bmp straight from disk, and keeps per-user settings under $DSH_HOME so upgrades never ship your folder path.

Deep-space theme for the Harness Web GUI: two fully designed light and dark palettes over a seamless cross-dissolve nebula wallpaper, plus a model probe that reports which configured models actually answer and their real context window.

ChatGPT-like conversation layout for the DeepSeek Harness Web client: a 768px centered column, right-aligned neutral bubbles for user turns, full-width assistant text at 16/28, and rounded code blocks with their own copy banner. Adds semantic inline markup (`==confirmed==`, `!!risk!!`, `++key word++`, with bare 4xx/5xx codes highlighted automatically) and line-start check/warn/tip callouts; a fast/thinking chip in the composer that switches the model reasoning effort through ctx.modelDirectories; and sidebar contrast, where the selected session gets a tinted row with an accent bar and workspace folder icons are colored.

Cost readouts for the composer, turns and sessions, a usage dashboard, daily/monthly budgets and settings, with DeepSeek balance from dsh-tally-balance-deepseek.

Cross-session usage rollup that resolves opaque route keys to real model names, with a per-request log, an editable four-bucket price table that leaves unknown models unpriced instead of guessing, and a calendar-day-filled bar trend whose values appear only on hover or keyboard focus.

Token statistics for every stored DSH session: a Host service folds the durable session logs into a persisted checkpoint and serves them over one read-only HTTP route, and the Usage settings page paints the saved aggregate immediately, then updates it in the background. Days are bucketed by hour behind a date picker, next to a trailing window with per-model breakdowns, request and web-search counts; no cost or pricing model.

Proxy provider that reshapes each outbound payload through a per-category op chain before forwarding upstream, keeping the prompt prefix monotonic between turns so unchanged history is not re-paid at full price; op names are transports (exec / http / inline) and accept user-defined algorithms.

Token usage meter in the DSH sidebar footer that runs both data sources at once rather than picking one: the DeepSeek platform account's usage and cost endpoints, which cover every device on the account but only the official channel, and local session logs, which cover this machine in real time across every provider but carry no cost. The two are merged per day — the official channel takes the larger figure, since one call is recorded by both, and providers the platform cannot see are added on top. History is backfilled month by month from the platform, providers are classified by channel rather than model name, days follow the platform's UTC boundary, and no token has to be pasted because the platform figures reuse the DSH account you are already signed in to. Totals appear as all-time, current-project, today, week, month, last-7 and last-30 in a compact bar, an expand panel and a detail modal with calendar, chart, model, provider, year, month and day tabs.

Live prompt-cache telemetry for the current session in the DSH right sidebar, drawn as a register bank and a reactor-core history board.