Plugins

21 read-only lifecycle governance tools in one self-contained DSH plugin: task tiering, state/plan/evidence validation, gate precheck and aggregation, release/install audits, context and progress analysis, critical path, resume reconciliation, and a mutation preview that always denies execution. Installs from npm as @240xu/dsh-tech-lead.

Adds a Branch Chat tab to dsh-better-sidebar that opens independent archived sessions with a head/middle/tail context digest and the same tools as the main agent.

Native DeepSeek Harness plugin for IsingQ: guided QUBO modeling and validation on-device, then user-confirmed remote solving.

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

LLM approval answerer for sandbox escalations beyond workspace-write: a deterministic regex filter first, then a clean-context reviewer model; humans are asked only when it is unsure. Requires the bundled core patches.

DeepSeek Harness plugin for NI Multisim circuit generation, simulation, optimization, and lab reports via MCP

Exposes the DSH dynamic-Cordis toolset to Claude Code over MCP (streamable HTTP on the existing web port, no new listener): ten tools to list, inspect, define, run, stop and permanently remove dynamic plugins in a live DSH session, with the same approval flow the GUI uses for packages that ship a client half. Bearer auth is mandatory — the token is configured on a DSH settings page, the endpoint answers 503 rather than serve without one, accepts loopback only and never emits CORS headers.

Local knowledge base RAG for DeepSeek Harness -- index project files and search for relevant context

Codex-style /side side conversations for DeepSeek Harness: a temporary fork of the current chat in a floating panel, inheriting context without interrupting the main task.

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.

LLM debug console for DeepSeek Harness: captures the full content of every model call at the llm/stream waterfall (options, stream chunks, usage, wire protocol) and shows it in a DevTools-style docked panel, with shared-prefix context diffing, wire-JSON reconstruction, JSON export and a runtime-tunable capture policy.

Screen capture and external vision recognition: take_screenshot, list_windows, analyze_image and view_image tools with a configurable GPT vision channel (gpt-5.5 / gpt-5.6-sol / gpt-5.6-terra), API key via the credentials service, and a settings card; view_image shows the screenshot in the Web UI while the model context keeps text only.

A searchable, sortable model picker for the DeepSeek Harness Web UI — provider groups, favorites, models.dev prices, context windows, live per-task token cost and a local-model filter. One-command install: dsh plugin add dsh-model-garden.

DSH 智能上下文压缩插件 —— 在有限窗口内管理认知资源，让 Agent 记住真正重要的信息。 Smart context compression for DSH — managing cognitive resources within limited windows, so your Agent remembers what truly matters.

Injects live time, weather, location, battery, and device context into the DSH system prompt, with a bilingual settings page.

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

DeepSeek Harness 动态上下文管理插件（Dynamic Context Pruning for dsh），对标 opencode-dcp

Sidebar meters for DeepSeek Harness Web: a DeepSeek account balance bar (orange, with a low-balance alarm) and a conversation context-usage bar (blue), rendered above the plugin store with a hover detail popover.

Codex-style context visibility for DeepSeek Harness: live context-window occupancy, composition breakdown, KV-cache hit rate, and a GitHub-style 53-week usage heatmap

DSH plugin: automatic dual-peer Honcho v3 memory, contextual recall, search, reasoning, conclusions, and health diagnostics

Ingestion-time tool-output curation: keeps error and warning lines plus head and tail, spills the full text to disk with a pointer the model can read back; covers every text tool, small results pass through untouched.

A slim port of Headroom: compresses tool output, cuts up to 20% of context, without affecting the model's context cache or agent performance.

Cross-session event-cue memory for DeepSeek Harness: auto-extracts task/conversation cues and user language habits from every turn into a persistent global cue bank, then re-injects remembered context on topic-switch detection (keyword or vector matching).

Auto-fills reasoning-effort levels, context windows, output limits and image modality for models from unofficial (custom) providers, with data from models.dev.