Plugins

TypeSafe Jev (System One decision model) as the jev_decide tool for DeepSeek Harness: noul, choice and score questions return calibrated probabilities; credentials reuse the DSH credential seam; 429/529 backoff retry built in.

Agent-structured prompt optimizer for DeepSeek Harness: rewrites composer drafts into role/task/context/constraint/format with normal, slim, and expand modes, a confirm modal with score, continue-optimize, and local, hybrid, DSH, or cloud-API engines.

Visual goal lifecycle for the DSH web UI: a composer dock to create, multiline-edit, pause, resume, complete and clear session goals with live round progress, plus a phase-dot composer entry and a settings-page goal overview.

Persona engine for DeepSeek Harness: one config.json drives the AI's self-name (per model, per tier), how it addresses you, relationship stance, character text, per-item work contracts with individual toggles, thinking-chain language, appearance and reply tone (both opt-in and per-model overridable), and long-term memory gated by human confirmation - the AI can only append proposed candidates, a human confirm line flips them into effect, and the log is physically append-only and replayable. Confirmed entries are injected as a quoted data-not-instructions block; entries tagged with a kind can instead be routed to arbitrary files on confirmation and never reach the prompt. Three prompt sections re-evaluate from disk on every assembly, so edits apply on the next step with no restart. Persona presets are shareable JSON snapshots (imports and exports SillyTavern character cards, v2/v3 read, v2 written) and deliberately never carry memory. Zero runtime dependencies, no network, no shell; any error degrades to an empty section rather than a broken session. Ships blank - installing changes nothing until you write something.

Advisor reviews that converge over rounds, an engineering mode whose writes require a design token, escalation of a task to a stronger model, and parallel multi-model consultation; a settings page edits the model routes, timeouts and budgets.

Model switching and reasoning-effort control for DeepSeek Harness: set_model and list_models agent tools let the agent autonomously change its provider, model or thinking depth (reasoning effort) mid-task with a mandatory reason, a provider whitelist and a context-window token-pressure guard, the active model is injected into the runtime context, and Plan Mode auto-transition switches to a configured planning model on entering plan mode and restores the previous execution model on exit.

WeChat article typesetting workbench: renders Markdown into inline-styled HTML you paste into the WeChat editor, with a right-sidebar panel and five model tools for block-level revision.

Custom modes / assistant manager: give each mode its own system prompt in the settings page — a custom prompt that is a plain file the agent loop re-reads before every model step, so an edit applies to the running session on its next step — and start it from the official standard / PTC / minimal / Cordis composition, toggling the plugin rows it mounts one by one (a custom plugin composition per mode), renaming it as you like. Several assistants coexist with their own prompts, so one machine can keep a coding assistant, a chat companion and a roleplay (RP) persona side by side — a multi-agent setup you pick from per new session. Rows left untouched stay byte-identical to the shipped ones, platform conditions included.

FriendliAI serverless LLM adapter for DeepSeek Harness — OpenAI-compatible chat completions with dynamic model discovery and reasoning support

dsh plugin + agent preset that replicates opencode + oh-my-openagent (omo): opencode's toolchain and system prompt, omo's multi-role subagent orchestration, and browser-side omo role selection + per-role model/fallback settings.

Pairs the running executor with a stronger reviewer model through zero-parameter advisor() calls and step-based patrol checks, returning plan, correction, or stop guidance.

OpenCode Zen 免费模型面板插件：实时展示 OpenCode Zen 最新免费模型，一键置入 DSH 模型选择器，无需密钥即用（共享字面量密钥由宿主注入）。后台支持总开关 / 单模型下架管理。

Free Kilo Gateway and OpenCode Zen models for DeepSeek Harness (DSH) via native dsh-llm adapters.

Model-driven context-window rollover bundle for the DeepSeek Harness: fresh working context, durable model-managed notes, a small verbatim recent tail, and targeted history recovery — no summarization.

Per-model appearance for the DSH Web UI: an ordered rule list matched against the current session model name, each rule carrying its own wallpaper, theme colour, layout mode, framing and wallpaper opacity and blur, plus per-surface opacity and frosted-glass blur for the main background, left panel, right panel, cards and panels, input and controls, settings panel, conversation text frame and trajectory view.

Automatic approval and review for tool calls that need approval: keyword buckets match red lines without context, then a judge model classifies what was requested and sends it to allow, reject or a human according to the matching row and risk level; a judgment that never ran always goes to a human, and rejections tell the model why.

Adds a reasoning-level editor with OpenAI and Anthropic protocol presets (llm-pi-ai), input-modality switches and a 1M/128K context and max-output preset to model rows in Settings.

Remote-control bridge: pair a running dsh web/desktop client with the Happy mobile app by QR code, then remote-control the same harness sessions from the phone (send messages, read replies, approve tool calls, switch models)

Keep declared workspace subpaths (e.g. .git) read-only, honor a read-only rules file at the workspace root, grant extra writable roots under workspace-write, and let the model request session-scoped write access; enforced for sandboxed CLI commands and the write/edit tools.

Auto-fills reasoning-efforts, context windows, output limits and image modality fields for models from unofficial (custom) providers (with data from models.dev), and provides user experience improvements such as compatibility enhancement and remembering reasoning effort.

Expert manager: manage ntd-format experts and expert teams (plugin.json + Agent MD + skill sets), browse and install from a built-in market of 50+ experts, and run tasks in an expert persona via /expert-<name> without consuming model directory tokens.

Models+ settings page for the DSH web UI: per-model reasoning-effort tables, input modalities and compat flags saved through the official settings pipeline, with models.dev metadata prefill and API key management.

Host-side guard that lets the write tool only create new files: when the target already exists it denies the call before execution and tells the model to use edit instead, applied to all sessions.