Plugins

A prompt optimizer in the composer input tool row: pick a category and a template, then ✨ rewrites the draft in place with one-click undo. Pick from the Basic, Context and Image categories; you can cancel a run, and it shows elapsed time and token usage. Ships 15 templates covering task-instruction rewriting, step planning, safety-research framing, system-prompt role cards, and text-to-image / image-to-image prompts; context templates read the recent turns of the session for coreference resolution. Calls go through the host model service, and a settings section exposes the model and the budgets. Output guards check that user-written constraints survive, warning rather than auto-retrying. Adapted for dsh 0.1.7 and 0.2.

Role-play plugin for DeepSeek Harness: imports SillyTavern character cards (JSON/PNG) and world books (lorebooks), binds DSH skills to a character, and registers the combination as a native agent preset.

Chinese multi-agent workflow with per-role model fallback, versioned Mermaid task plans, independent Agent and Jev reviews, persistent expert collaboration, and pure-function calculation tools.

Dependency-ordered multi-agent team runner for DeepSeek Harness: define roles with their own model, persona and tools, run a node graph with an independent review gate and bounded rework, and watch progress in the web UI.

DeepSeek Harness native immersive roleplay studio & companion system. Unifies decoupled character cards with Hindsight graph memory.

File-defined subagent roles for DeepSeek Harness: roles live in project and global .dsh/roles files, a delegating agent sees one catalog line per role, and each role's tool policy decides which tools its child can see.

Fleet console for DeepSeek Harness: one local dsh page manages many remote dsh machines — live idle/running status, in-place switching without new tabs, keep-alive iframes, cross-device session reading, one-click refresh/restart, and a controller/managed role split.

Login gate for the dsh web UI: unauthenticated visitors get a login/register page and the first registrant becomes admin; includes user and role management plus login and access audit logs.

Context trimmer: lists the current session's context entries with role, preview and ≈token estimate (cl100k), highlights over-threshold items, and removes selected entries exactly without LLM summarization.

Cross-app project memory for DeepSeek Harness with role-separated writeback, a visual knowledge workspace, confirmed corrections, session controls, local Writer and organizer settings, and an account-free Windows local installation preview.

OpenAI-completions-compatible adapter for custom gateways (vLLM / LM Studio / self-hosted proxies): always role:"system", thinking driven by the model config, Qwen-style response split, and vision-model image input (single / multiple).

Branch-role guard for AI coding agents: configurable integration/preview/production/archive roles, blocking direct push, force-push and delete on protected branches and agent merges into production/archive.

Planner/executor delegation with named roles: a strong planner steers, disposable executor sub-agents (per-role routes and prompts) implement. Default role plus per-delegation override, a global reasoning-effort knob in the composer chip, and a settings page for role management.

One-click OpenAI-compatible API (CodeBuddy/vLLM/proxies) with thinking mode, avoiding developer-role content_filter rejection.

Ranked subagent delegation: role-based model routing with failover, per-route reasoning effort, model-transparent labels, fork delegation, and a visual route editor.

Headless Claude Code consultations with advisor, reviewer, and designer roles, returned as reference answers.

Discover and verify portable RoleHub roles, pin each exact bundle, then launch its prompt and bundled skills in an isolated, continuable DSH Session with Host-approved tool bindings and optional Agent Team Room attachment.

No-setup mode for the DSH web UI: hides advanced surfaces, auto-applies best defaults (chat mode, full access, account balance), and one-click role-play personas (maid/butler).

Agentic roleplay for DSH with structured worlds, autonomous characters, persistent sessions, world authoring, speech, and image generation. Requires Firefox2100/dsh-agentic-roleplay#state to be installed and enabled.

Persistent SQLite session state, story memory and recall, repositories, and model-facing record tools for DSH roleplay plugins.

Imports SillyTavern AI presets as switchable, editable prompt layers: preserves the raw JSON, edits prompt order and sampler parameters, previews the injected System Prompt, exports back to SillyTavern-compatible JSON, and archives or permanently deletes presets with confirmation. Applies temperature and maximum output tokens to Harness requests; other sampler fields are preserved and exported but not applied.

Replaces the new-session hero with a combined picker: role cards for the agent presets and a workspace card, collapsed into capsule buttons that expand into two scrollable rows.

Three-player LAN Dou Dizhu (斗地主) played from a floating window: one machine opens a room on its own port, the other two join with a six-character room code plus an address. Empty seats can be filled by computer players in four switchable strengths (easy, medium, hard, hell), so one or two people can still play a whole hand; the deal starts as soon as the three seats are filled. 54 cards in four suits, bidding of 1/2/3 or pass, the landlord takes the three bottom cards and holds 20, play runs clockwise, and the first-bid seat rotates clockwise between hands. The rule engine is pure and covers 11 legal shapes, with big joker > small joker > 2 > A > K down to 3, suits never compared, straights, pair-straights and planes excluding the 2s and the jokers, and a rocket that beats everything. The table itself is built to be read at a glance: three seat cards side by side in play order (you, then your next and previous seats) with role, hand count and a bar that runs out, one line that says whose hand is on the table and what would beat it, the bottom cards as text, an in-place play history that folds into a single summary line and unfolds into every trick including the passes, plus hint and auto-play buttons that pick the cheapest legal answer out of the local rule enumeration. Nicknames can be changed mid-hand (twelve characters, duplicates get a suffix). Computers run inside the authority and are handed only their own hand, the public record and the seat counts, so no hand can leak; the authority is the only place that decides which card ids leave it. Computers are driven by the room itself, so a one-person table keeps playing with nobody else on the LAN port. Humans have no turn timer, the collapsed floating pill can be dragged around the screen, and 179 unit tests pin the rules, the wire format, the theme tokens, the drag gesture, the history grouping and the computer seats.

Zagent — unified three-role self-improvement loop with three operators. Data-RSI (daily cross-sectional cleaning: winsorize → cross-sectional standardization → median fill, plus experience extraction), Harness-RSI (evolves system prompt / memory / skills), and Model-RSI (evolves alpha training recipes via framework-native walk-forward with 2-day gap and multi-seed). Offline one-command run, GPU auto-detect. Ships one skill.