Plugins

Stops compaction summaries and session titles from burning their output budget on reasoning, by lowering the thinking level and raising the token floor for auxiliary calls only.

Volcengine Ark Coding Plan provider route for DeepSeek Harness with all 15 Coding Plan models and per-model reasoning-effort control, generated from a single source and drift-checked weekly.

Exposes every model of every provider configured in DeepSeek Harness through one OpenAI-compatible endpoint on a fixed loopback port, with a sidebar page for the base URL, key, port and model ids.

One-click add Agnes AI free models to DeepSeek Harness.

Exposes the accounts in a local CC Switch database to DeepSeek Harness: every account (Claude Code, Codex, OpenCode, Grok Build) becomes a model category in the picker, and the SQLite database is re-read on every model listing and request, so switching accounts in CC Switch needs no DSH restart. Requires CC Switch and the DSH desktop app.

Adds Standard Compute as an OpenAI-compatible model provider through the built-in pi-ai adapter, with its standardcompute router model and two direct model pins; configuration only, no code.

Tiers free-channel models into three 1M fallback chains plus a custom chain; orders them by measured throughput, drops models below throughput or error-rate thresholds, and rotates accounts. Requires an OpenAI-compatible gateway (default :8326).

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.

A temp note in the DSH right sidebar with session, workspace, and global scopes, browser-local autosave, one-click copy, and one-click LLM polish through the default model.

Renders installed DSH plugin titles and descriptions in Simplified Chinese: at startup it translates the plugins the local JSON cache lacks through the harness LLM service, then projects { en, zh } metadata for resolveText() to render — no DOM changes, no third-party API.

Adds a reforge control to the DSH composer that rewrites the current draft into a sharper prompt in place, as one undoable edit, with one-click revert and cancellation.

Adds a sparkle button to the DSH composer that rewrites the current draft into a clearer, more specific prompt with a single tool-free LLM call, then writes the result back into the input.

Two games inside DeepSeek Harness where the model supplies intent and a local engine owns the rules: a twin-brain snake that periodically draws a strategy card, and Chinese chess where the model only comments on a move picked from locally generated legal candidates. Both keep running when the model is slow, offline or out of quota.

Removes the model-capability gate that blocks image prompts: patches llm.resolveModelInfo results and adapter model tables to declare image input, so routes with no declared input modality can send and read images. No app.asar or config-tree edits.

Replaces rolling narrative summaries with an append-only session index, so early facts survive compaction verbatim and shadowed text stays retrievable by anchor.

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.

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.

Runs MoE4All models locally in DSH with automatic engine installation, model discovery and downloads, inference settings, and live speed monitoring, or connects to an existing service.

Live estimated session spend in the composer dock, pricing each assistant step at DeepSeek's peak or off-peak rate for its own timestamp.

Queries the balance and token prices of the model providers configured in DSH, whichever endpoint or relay they use, accepts cc-switch usage scripts, and shows the selected provider's balance under the composer.

Select text in the DSH web client and a translate button appears at the end of the selection; clicking it translates that text in place. Translation goes through the host llm service, so it reuses the model the current session already has selected and needs no separate API key; an OpenAI-compatible endpoint can be configured instead. The result opens in a popover that stays inside the viewport, with one-click copy, a row of language buttons for instant retranslation, and smart Chinese-to-English / other-to-Chinese as the default. Configuration is stored host-side and its API key is never sent to the browser.

Connect multiple decision providers and models through one interface: Jev via TypeSafe, Clef via Cloudflare, Drex via Nace, Decider via meraGPT, self-hosted Laya, and compatible custom providers. Agents and plugins can classify content, filter candidates, score against criteria, or locate objects in images, then use structured results in their workflows.

Model manager for the composer picker: probes a model on demand and keeps the timestamped reason it failed, counts usage from committed assistant messages to rank models by proficiency level, pins, favourites and hides rows, and switches along a failover chain when a turn fails, asking the new model to pick the work back up.

Re-encodes WebP attachment images to PNG so alpha-channel images load on LLM backends that cannot decode WebP (e.g. llama.cpp).