Plugins

Injects the rule files under $DSH_HOME/rules and <cwd>/.dsh/rules into the conversation at the first agent pre-step, re-injecting them after compaction.

Codex-shaped coding tools and agent presets for GPT models on DeepSeek Harness: exec_command, write_stdin, apply_patch and view_image, plus OpenAI Chat Completions and Responses API routes, bridged to DSH-native plan, ask, approval and compaction. Long-running commands become DSH background jobs with bounded head/tail output readable through job_output, and each subagent type can be pinned to its own preset, provider, model and reasoning effort.

Context curation for DeepSeek Harness: content-aware tool-output slimming, dead-log sweep, pinned user requirements and in-flight work, archive-then-compact with an audit trail.

Floating GPU monitor for the DSH Web UI: a compact, draggable strip with one row per discrete GPU (exact name, utilization, VRAM, temperature, power draw) from nvidia-smi, stays visible over side panels and side cards, with a top-VRAM-process list when the driver reports it; degrades to an n/a pill on machines without an NVIDIA driver.

Composer code-quote collapse for the DSH Web UI: pasting a `path:line` header followed by code folds the input into one compact inline quote chip, and at send time the `agent/pre-step` hook injects the full pasted snapshot to the model as a separate context message. 0.5.x also folds sidebar file-selections that insert only a `path:lines` line (large selections), fetching the code from disk by session cwd, and preempts Ctrl+V paste interception.

Per-provider concurrency gate on the llm/stream waterfall: holds surplus model requests in a FIFO queue inside DSH so main agent, subagents and compaction take turns on a single-slot local server (llama.cpp --parallel 1) instead of timing out; maxConcurrent / maxQueued / queueTimeoutMs.

Slash commands ported from other coding agents (setup, connect, install, trust, browse, doctor, status, model, memory, compact, resume, review, mcp, init, suggest, improve, refactor), a zero-dependency static scanner for plugin source, and an in-repo catalog of audited plugin report cards that cite file-and-line evidence.

Compact DSH wallet panel for any Sub2API-compatible third-party balance site. Uses /v1/usage with a long-lived API Key, auto-discovers configured providers, and shows balance plus daily usage.

Type @ in the composer to reference another conversation: pick a historical session and inject its compacted context into the current prompt.

Compaction quality / hallucination detector: when a conversation span is compacted, check on two axes that key information survived 鈥?FIDELITY (assertions in the summary must be found verbatim in the original leaf events, else flagged as fabricated) and C

Step-0 observation probe for dsh-compaction-audit: logs every compaction/* session event and probes whether shadowedSeqs still resolve to readable events in session.events. Observe-only; never injects, never blocks.

DeepSeek Harness (dsh) plugin for @tabilo/ai-code-review: registers the ai_code_review tool (review | context) that reuses the Node.js engine to collect diffs, run tests/coverage, do impact analysis, and feed pack skills to the model.

DSH web search and Responses native V2 compaction for Sub2API-proxied or NewAPI-relayed GPT models

Global news monitoring skill: track world events and analyze impact across industries, currencies and commodities.

Adaptive Reversible Context (ARC) for DeepSeek Harness — provider-aware, cache-conscious context governance with reversible recovery.

Tiered model routing for DeepSeek Harness: think/build model tiers, vision delegation (the vision model only describes images; the working model acts), image generation, and a high-impact guard.

A Genshin Impact Columbina (哥伦比娅) themed plugin for DeepSeek Harness Web: preset/custom background images with a translucent mask, per light/dark scheme palettes, and a special glow for the active conversation title.

One-command bundle of the three AgentFrame plugins: memory-director, compaction, and aura-scheduler together.

Synesthesia Encoder for DSH: a vision model translates images into compact structured spatial text (canvas/elements/percentage coordinates), giving text-only LLMs pixel-level image understanding via the `mm_vision` tool.

Routes chat images to a fixed OpenAI-compatible vision model, returns factual observations to the selected main model, and reuses session-scoped observations across replay, compaction, and restarts.

Focus board for DeepSeek Harness agents: durable, model-maintained notes in the session workspace that pin the objective, constraints, and decisions across compaction and sessions, with automatic context injection, archive on clear, and an optional web panel.

会话级自动上下文压缩插件：回合中每步前 + 回合结束检测上下文用量，超过会话阈值自动 compact，摘要注入上下文后自然继续（DeepSeek Harness / DSH）

溢出兜底与续命：上下文超限、内置压缩放弃后自动再压一次并重试；仍失败时把原会话整理成交接包，在新会话接着聊。不换引擎、不加界面；续命默认显式触发，原会话只读。 · Overflow fallback and session revival for DeepSeek Harness: one last compaction retry, then continue the dead session in a fresh one with a handoff. No engine swap, no UI, o

Cross-workspace long-term memory for DeepSeek Harness: one machine-local store shared by every workspace, a compact index injected at session start, and a searchable tool for the details.