Plugins

Unified image generation router for DeepSeek Harness (DSH): auto-discovers image models from any OpenAI-compatible endpoint, provides draw_image and draw_list_sources tools, supports SenseNova, StepFun, Agnes, Qwen, Flux, SD, Imagen and more.

Learning Mode agent preset: a coding agent that teaches while coding — concrete scenario-grounded explanations, Socratic guidance, and TODO(你) practice blanks, modeled on Claude Code's Learning output style; installable via dsh plugin add (dsh-learning-mode on npm).

Tracks the agent's state as Yogācāra mental factors over a durable seed store, and feeds it back into the prompt as first-person inclination.

Cross-session archive: overview workbench, folded timeline, subagent lineage, full-text search, rule+LLM summaries, ZIP export, live tracking. Native session-page embeds: turn rail, docked right panel (live mode, pinned to original session on switch), rename (official-synced), conclusion digest, health monitoring + persistent header chip (idle / active / tool-wait / stalled). dsh v0.1.2+: fuses with the official TurnNavigatorRail — vector-icon info chips (duration, tool calls, errors, thinking) plus lazy tool distribution inside the official preview card, right-click opens the workbench; the classic piano-key strip is on by default and delegates unloaded-turn jumps to the official auto-load engine; the official rail can be hidden entirely. Settings dialog section with 10 tunable behavior params.

Adds ChatGPT/Codex OAuth-backed Codex models and gpt-image-2 generation/editing to DSH without requiring an OpenAI Platform API key.

Simulates a Codex environment for selected model routes to improve GPT-family model tool-call success.

Adds models.dev reasoning levels to unconfigured third-party DeepSeek Harness models.

DeepSeek account balance and current-session spend estimate in a top-bar chip and settings card, with pause-aware auto-refresh, an editable official price table, a `deepseek_balance` model tool, and a bilingual UI.

Provider-tabbed model picker for the dsh web composer: left provider column and right model list, both independently scrollable, with cross-provider search.

Floating Bilibili video mini-player for DSH — always-on-top window with discover/search/follow-UP channels, auto-playlist, mini & focus modes, persisted watch history and window minimize-to-ball.

Session header badge showing DeepSeek peak/off-peak status, per-model token prices on hover, and real session/turn costs from actual usage.

Four-module session companion: smart conversation export (Markdown/PDF/JSON/PNG long-image with privacy redaction and batch ZIP), context handoff summaries with template save/import, API cost optimization (live official pricing, peak/off-peak scheduling, daily/monthly budgets, model routing), and global conversation search with in-chat find (Ctrl+F, CSS Custom Highlight API).

Use local Codex App Server as a model provider in DeepSeek Harness

一个可以让ai自动调用VLM(多模态模型)进行视觉分析的dsh插件。A dsh plugin that allows AI to automatically invoke VLMs (multimodal models) for visual analysis.

Hosted free vision sidecar for DeepSeek Harness with durable session evidence

A corner HUD for DeepSeek Harness that shows your session's token pressure, per-model cost, and daily/monthly usage at a glance, with an editable budget and balance that tracks spending for you. 右下角常驻的 Token 仪表盘：实时看会话压力、按模型估算花费。预算和余额点一下就能改，每天每月用了多少都有记录。

Bridges session images to configurable vision providers and returns text-only analysis to eligible DeepSeek Harness model routes.

DeepSeek Harness LLM provider for Codex models using managed ChatGPT OAuth

11 shareable workflow skills (handoff, triage, to-spec, to-tickets, wayfinder, teach, wait-what, dsh-mode-routing, ask-matt, overnight-execution, full-throttle) as an installable skill pack.

DeepSeek Harness LLM provider for Codex models using managed ChatGPT OAuth

Deterministic keyword routing, allowlisted model switching, and an isolated image_gen channel for DeepSeek Harness.

Two-level model circuit breaker with failover: trip a model or a whole provider after repeated request failures and route the next request to a configured fallback.

Route each task to one model and its review to a different one, with qualification evidence, failover and a durable journal.

Brings the models included in the Xiaomi MiMo desktop app (free during beta) into DeepSeek Harness, with zero configuration in the DSH conversation window.