Plugins

Modular frontier execution discipline for DSH: evidence-first routing across 26 skills, Manus-style file planning, verification gates, fail-streak recovery, and an interactive web dashboard.

Codex-style window capture for DSH Desktop on macOS and Windows: press both Command keys (macOS) or both Ctrl keys (Windows), or the camera button, to grab the frontmost window, attach it to the current chat, and inject a VoiceOver-style accessibility tree as hidden context.

Cache-stable progressive tool discovery: a fixed tool_search and tool_dispatch surface on every request, in-memory catalog search, nested dispatch through the Harness pipeline, and a byte-stable native tool list across discovery.

Kiro model provider with Builder ID, Identity Center, Google, GitHub and credential-import sign-in, automatic token and profile refresh, account usage, live model discovery, selectable reasoning efforts, streaming tool calls, provider stop-reason and context-overflow handling, and token accounting that uses Kiro's exact counters when it sends them and otherwise scales the context-usage percentage it does send by the model's advertised window.

Per-round thinking-level (reasoning_effort) control for DeepSeek Harness: pick Auto and it schedules low/high/max from the recent tool-call history, or fix a wire level (off/on/minimal/low/medium/high/xhigh/max) manually, with custom wire mapping, a model-aware capability guard, and context-window presets (64K–1M); its per-model capability card pairs with a separate plugin, [dsh-llm-openai-completions](https://github.com/drscrewdriver/dsh-llm-openai-completions) (installable from dsh-market), so custom OpenAI-compatible gateways (vLLM / LM Studio / self-hosted) can try reasoning — the card writes llm-pi-ai capabilities, the adapter drives the wire (compat.thinkingFormat), and this plugin auto-maintains the takeover list.

LLM-free lossless* compaction engine for DeepSeek Harness

One memory layer for every AI tool and agent: Context Bundle injection, prompt-time recall, MCP tools, and turn-end DSH thread capture.

Make your dsh ready for serious coding. (Tools x Schemas)^REPL. `skill://`, `ctx://`, `agent://`, `dvc://`, `dsh://`, IPython REPL, Context as Variables, cross compactions recallable, full context revive. `hash-edit`, `dvc://browser`, subagent as function, workflow as function.

Drop-in agent loop with bounded-slice context engine (cordis).

Manage MCP servers, skills, and tools for your agent — true in-context state (loaded/truncated/evicted) and per-session switches.

Model-facing display_file tool that renders 36 file extensions inline in the web UI: images with a click-to-zoom lightbox, seekable video, audio, PDF, Office and OpenDocument files converted to PDF on the host via LibreOffice, and local HTML in a sandboxed frame; bytes stream from a signed HTTP route with range support, and PNG/JPEG/WebP/GIF also enter model context on image-capable routes.

Make your dsh ready for serious coding. (Tools x Schemas)^REPL. `skill://`, `ctx://`, `agent://`, `dvc://`, `dsh://`, IPython REPL, Context as Variables, cross compactions recallable, full context revive. `hash-edit`, `dvc://browser`, subagent as function, workflow as function.

Git-style conversation branching that mirrors how real programmers collaborate: a secretary root branch dispatches tasks to child branches with their own contexts, merging back only compressed summaries via squash or rebase; ships /branch commands, a branch tab, branch-to-branch messaging, and a governance baseline pairing each session branch with a git worktree.

Context Assembler plugin for DeepSeek Harness: topic-block context assembly, water-pressure topic splitting, tool trace/rewrite, reality recall injection and handoff planning.

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

Performance profiling and LLM cache diagnostics for DeepSeek Harness — context engineering, latency profiling, and cache behavior reports.

MCP & Skill manager: enable/disable MCP servers and skills from a Settings panel to free context in real time; optional AI middle layer (mcp_search/mcp_call) calls disabled servers on demand, with state-based visibility filtering that keeps user-enabled servers visible.

Exports metadata-only DSH turn, model, tool, approval, retry, and error events to Tuning Engines for governed traces, policy evaluation, cost analysis, and Work Session review, with a disk-backed retry queue.

Chinese localization for DeepSeek Harness: translates all system prompts, tool descriptions, and runtime contexts into Chinese at runtime via the system-prompt/assemble waterfall (1788 entries, zero source modification, uninstall restores English).

Honcho memory bridge: auto-syncs every conversation turn to a self-hosted Honcho service, with recall/search/remember/context/status tools, context injection on session start, and a visual settings panel.

MCP server manager plugin for DeepSeek Harness: Settings → MCP page, OAuth (PKCE + dynamic client registration) or static-token auth, tools registered as mcp__<name>__*

MCP server installer and verifier for DeepSeek Harness: interactive init writes real patch entries into a profile, list and validate inspect them, and a CI-enforced verifier connects to every curated server.

Takes over the edit/write rows in the chat stream with the official native row shell and collapse behavior; expanding shows per-file code cards with file-type icon, add/delete stats, per-block collapse, highlight/plus-minus toggle, syntax-highlighted unified diff with real file line numbers, and a configurable context margin. Also ships a patch tool (beta, off by default) that applies multi-spot multi-file patches atomically via the *** Begin Patch envelope.

Kanban task board for DeepSeek Harness sessions: the main agent dispatches coding tasks to one-shot worker/verifier subagents, with dependency scheduling, pipeline tiers, escalation handling, and file/notes context injection.