Plugins

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).

LocalAI provider for language models, embeddings, reranking, speech, and image generation with LocalAI-specific controls in DSH. Requires Firefox2100/dsh-ai-providers#runtime to be installed and enabled.

Cohere provider for language models, embeddings, and reranking through Cohere's native APIs in DSH. Requires Firefox2100/dsh-ai-providers#runtime to be installed and enabled.

Anthropic provider using the native Messages API for language models in DSH. Requires Firefox2100/dsh-ai-providers#runtime to be installed and enabled.

Declares image input on relay routes whose endpoint omits modality metadata, so models that can see photos stop being rejected as text-only. This also overrides routes that are explicitly declared text-only.

Multi-model deliberation pipeline for DeepSeek Harness: independent proposals, blind peer review, program-executed evidence verification, immutable revision and independent acceptance on a fresh context.

Apple Liquid Glass skin that re-keys the harness design tokens, then adds its own settings page, a grouped model picker with peak and off-peak rate badges, and a merged usage panel.

Local token totals, per-model usage and a 12-week heatmap in a Chinese sidebar panel.

Per-channel credit balances for the Our Free Model gateway in the DSH sidebar: one always-on card covering the channels the gateway supports (unconfigured channels stay hidden), collapsed to the channel the current conversation uses, expanded to one row per channel with a bar and remaining amount, with per-channel visibility toggles on the plugin detail page.

Reorder configured models in the composer model picker, set cache-hit, cache-miss and output prices per million tokens, and estimate per-turn and session costs with built-in DeepSeek peak/off-peak rates.

Distill over-long model reasoning into its useful core, replay the compressed version on every later request, and report each session's cost and savings. Disabled by default: select one rewrite backend first. derive needs no install and works on packaged DSH; in-place needs 14 source patches and a rebuild (recommended for source checkouts); message-edit needs a third-party plugin and is experimental only.

DeepSeek account balance capsule in the conversation session header. A same-origin route registered by the package's own host half resolves the API key from the credential service and calls api.deepseek.com/user/balance, so the key never reaches the page; the capsule polls every 60 seconds and expands into a panel with per-currency totals, granted and topped-up amounts, last-updated time and a manual refresh. Read-only UI: it never touches prompts, tool results or model traffic.

Token usage dashboard and per-session tree statistics: provides time-range filtering, 6 summary metric cards, GitHub-style activity heatmap, model stacked-bar charts with cache hit rate curves, and Top-5 model/provider rankings; enhances the native session status bar to display aggregated token usage across main agents and all subagents with detailed breakdowns.

Reads the local Codex CLI ChatGPT-plan quota (5-hour and weekly windows), defaults to gpt-6.1-sol at high reasoning, falls back to gpt-5.6-sol when a window has 10% or less left, and delegates tasks through codex exec with an explicit opt-in for the expensive gpt-6-astra model. Requires a signed-in Codex CLI (`codex login`).

Cross-session token dashboard for DSH: daily spend as bars, trend or cumulative views plus a GitHub-style annual activity calendar, model and workspace splits, cross-filtering between day, model and workspace, and a per-turn timeline that also covers web-search and auxiliary model calls.

Task details sidebar for DeepSeek Harness: a "View task details" button under every finished turn opens a resizable right-sidebar panel showing that task's input files, intermediate artifacts, output files, tools and skills used, inferred languages, a step-by-step flow timeline, and the model provider with token usage and cache hit rate.

Replaces the composer model control with an inline Provider/Model trigger — clicking it opens a two-column card with providers on the left and the hovered provider's models on the right — and moves the reasoning effort into its own trigger beside it, unlike single-button model pickers.

Replaces the composer model picker with a compact panel for provider-to-model navigation and an adaptive reasoning-effort slider, with a Default stop and no slider for models without adjustable efforts.

Adds a prompt enhancement button to the composer toolbar that rewrites the draft through a model call, keeps @file references verbatim, and offers one-click undo.

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 Gemini kitten widget for the DSH Web UI: live Google Gemini API free-tier quota per model, a model switcher, color-coded warnings, drag-to-snap, and click-to-change lines.

Turns one plain-language request into a live workbench window: a sidebar panel asks a few clarifying questions, the model writes a single-file HTML artifact, and the plugin mounts it in a resizable floating window or a standalone browser tab. Declared window actions are recorded as info-level project journal entries (without their payloads), and workbenches can be imported, exported, or installed from a market index.

Interactive cards in replies, built from a fixed catalog of 31 components (sliders, inputs, sortable tables, charts, function plots, typeset formulas, tabs, checklists, flowcharts, quiz buttons, an animation player): controls recompute in the browser without another model call, and the model never writes HTML or JavaScript. Includes a calculus engine (integrals, derivatives, limits, sums, roots, Taylor polynomials) and a bundled skill that teaches the model when to use a card.

Renders `latex` / `tex` code blocks in the chat as KaTeX formulae, and injects a system-prompt section that tells the model to write `$...$` and `$$...$$` instead of fenced code blocks.