Plugins

DSH 插件:直接复用 Codex CLI 本地登录订阅凭证,在 DeepSeek Harness 中使用 ChatGPT 订阅模型,无需 API Key | DSH plugin: reuse your Codex CLI local subscription login to use ChatGPT subscription models in DeepSeek Harness, no API key required

Activity heatmap in the DSH Web sidebar: GitHub-style grid of daily commits, token usage, and estimated spend, with a today stats line for all-session token totals, cache hit rate, and per-model auto-priced cost.

Orchestration-mode preset generator for DSH: a lead agent delegates to four built-in role helpers that carry only their own tools, and the web panel adds or removes custom helpers with their own tools, skills, and models, per workspace — zero changes to the harness source.

Brings WorkBuddy desktop-app experts into DSH: a settings-page market scans the local WorkBuddy expert directory (experts land there after you summon them in WorkBuddy) read-only for browsing, search and category filtering, with one-click install (exported to ~/.dsh/experts/ as role prompt + skills + avatar), update and uninstall; a picker capsule next to the input box switches the current session's expert — swapping role prompt, skills and an optional tool whitelist wholesale while keeping full session history, applied at the next model-request boundary.

Use the Jev (System One) decision-model paradigm with any OpenAI-compatible LLM — no TypeSafe key required. Registers a jev_decide tool that returns probability-distributed answers to typed questions (choice/score/boolean) in one call.

TypeSafe Jev as a first-class Cordis service and three model-visible tools for DeepSeek Harness — offline by default, egress disclosed, never default-on.

Shows which graft index a dsh session is serving and whether it still matches the code, and gives the model graft_ask, graft_grep, graft_callers, graft_skeleton and graft_map as native tools.

Supervises a local workbuddy2api gateway process and exposes its models as an LLM provider, reading context windows and reasoning efforts from the gateway's own model endpoint.

Lazy MCP gateway for DeepSeek Harness: one stable proxy tool instead of N tool schemas, servers connect on first use and idle out, metadata cached to disk.

Remote development over SSH: pick a directory on a registered machine as the session workspace and the file, shell, bash, and search tools run on the remote host — the agent works there with the same local tools, and no extra model-facing tools are added.

Multi-model orchestrator: the main brain decomposes complex tasks and dispatches subtasks to GLM / Kimi / Qwen sub-agents by each model's strengths, with per-model token usage.

Fills missing context window, max tokens, thinking levels, and image input on custom DSH models from models.dev, and lists unmatched models for manual edits.

Prompt enhancer for the DSH web UI with basic/standard/expert modes: standard/expert modes rewrite drafts with project context and recent session history, retry gracefully when gateways reject reasoning-effort settings, and show a before/after review with undo.

A Mimi desktop companion for DSH that follows work-session states with animated reactions and bubbles, provides a separate chat mode, and bundles Windows Computer Use for observing and controlling desktop windows.

DeepSeek Harness plugin that aggressively saves tokens without affecting task quality: lossless head/tail truncation of tool results (default), grep-result folding, pressure-triggered dsh-compaction-basic delegation, and an LLM-summary CompactionEngine subclass for the aggressive mode. Saves 97.6% of input tokens on an 8-scenario synthetic suite, with all reductions routed through dsh event flow so model-visible = logged stays intact.

Tokenrhythm (基元律动) finance dashboard for DeepSeek Harness: account balance & expiring credits, category-filtered model price cards (with discounted prices), service status and platform key management; login via platform account or session cookie — credentials stay on the local host.

OpenCode Go subscription chat for DSH with per-model Completions, Responses, or Anthropic protocol selection, model discovery, context, vision and thinking metadata, effort defaults, and usage meters.

Give DeepSeek (text-only) models vision in Claude Code, Codex, and Agent Plugins clients: describe images via any OpenAI-compatible vision endpoint.

Concurrency guard and monitor for DeepSeek Harness: FIFO queue when concurrent model requests reach the limit, per-day persisted stats with error-kind classification, and interruption detection for abandoned streams.

LLM adapter plugin for locally deployed Qwen models behind a vLLM OpenAI-compatible endpoint, with per-model multimodal switch, fully configurable reasoning efforts, and a web settings page for editing the deployment from the frontend.

Rate-limits LLM requests per provider and per model using a reservation-based token bucket, with queue or reject modes, plus gateway identity rules that rewrite user-agent and inject custom headers.

Local-first token usage heatmap inside DSH settings: GitHub-style week/month/quarter/year grids, hourly usage per day, per-model and per-provider Top 5, and persisted history that survives session deletion. Zero network, zero billing.

Commander mode for the dsh web GUI: a one-click session header button injects a protocol brief into the session, then parses and auto-executes task blocks in the model reply — separating the strategist loop from worker loops via a visible badge.