Plugins

File encoding guard: byte-exact read/write/edit for GBK, Big5, Shift-JIS, EUC-KR, Windows-125x, UTF-16 and UTF-32 files, so editing a legacy file leaves it in its original encoding instead of silently rewriting it as UTF-8; UTF-8 BOM preserved exactly as it was, line endings (CRLF/LF/CR) kept, characters the encoding cannot represent refused rather than written as "?", and non-UTF-8 files listed with candidate encodings so the model can re-read them explicitly.

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.

Claude Code CLI as an LLM provider for dsh: live model list, per-session resume, approval relay, images, a memory/rewind/changes panel, and workspaces on remote SSH boxes.

Free model provider plugin for DSH with 20+ models including Gemini, MiMo, GLM, etc.

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.

Adds ChatGPT-style stop, edit-and-resend, native quote annotations, and an independent sidebar follow-up chat with model and image input for DeepSeek Harness Desktop.

Automatic session retrospective: after a conversation wraps up, distills useful experience into reusable skills stored in the skill library for the model to call, with signal-accelerated triggers, manual runs, an approval mode, and skill-library governance (archive/restore, never deletes directly).

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.

Model Capability Manager for DSH Web: thinking levels, context window, output caps, input modalities, gateway compat presets, EN/中文 UI.

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.

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.

Unified Godot asset and project-goal management for DSH: godot_* model tools, a /gap REST surface, and a better-sidebar UI with asset manager, scene-tree viewer, and Git panel.

Manages OpenCode Zen free-tier and Go-tier models in settings.yaml — fetches the live model listings from opencode.ai, reports configured-versus-live drift per route, and adds or removes entries through four agent tools and an OpenCode Models settings section.

Desktop-grade companion: browser native notifications for user questions and approval interactions, screen capture model tool, multi-agent tiling grid view, and lightweight Tauri desktop shell.

DSH model provider for the locally authenticated AGY CLI: Gemini/Claude model discovery, independent reasoning effort, DSH-owned tools, bounded context and tool-result handling, and Windows-safe streaming. Report problems in GitHub Issues: https://github.com/darkings/dsh-agy-provider/issues.

RLM mode for dsh: recursive sub-agents via a unified rlm() function — spawn, await, and chain child agents as first-class Python calls. Adds a persistent IPython kernel with tools.* bindings and context-as-variable.

Proactive multi-model scheduling plugin: multi-source signal intake with dedup and urgency ranking, a four-way execute/defer/dismiss/ask-user decision engine, DAG plan generation with parallel model execution, quality reflection with automatic retry and model switch, long-term memory for task patterns and lessons, and strategy evolution via genetic algorithms with sandboxed evaluation and canary rollout.

Requires DSH 0.1.5-alpha.1. Annotate selected text in finished assistant messages, then submit multiple drafts with official composer text, images, and files as one Session user message; the model answers each annotation in order with hoverable reply chips.

Local-first usage and cost meter for the DSH web UI: composer button with live session cost and balance; panel with a stacked per-model daily/7-day chart priced per effective list-price interval (official pricing page synced daily), monthly usage tiers with a canvas share card, 30/50/85% context-pressure warnings with one-click /compact, budget alerts, and an in-panel npm update check with one-click update.

Reference verification for DeepSeek Harness (参考文献真实性检查器): the reference_checker model tool checks a paper's bibliography (.pdf/.bib/.tex/.txt or pasted text) against Crossref, OpenAlex and arXiv, reports found / partial / not_found / error per entry, and emits corrected citations in the input's style (APA, GB/T 7714, IEEE, Vancouver, MLA, Chicago, Harvard, ACS, BibTeX).

Routes agent requests to configurable default, planner, and subagent models, automatically using the planner role in plan mode, with per-role reasoning effort and Web UI configuration.

Cost dashboard for DeepSeek Harness: aggregates model input/output/cache tokens across all local sessions, prices them with a builtin table (including DeepSeek peak/off-peak), and shows daily trends plus per-model and per-session tables.