플러그인

DeepSeek Harness plugin: ingest research PDFs into a citable OKF markdown library, then search, graph, measure coverage, and write surveys in the same conversation

LLM-as-a-Verifier for dsh with the Best-of-N conversation mode built in: rank N candidates with a fine-grained verifier (expected grade over the logprob distribution), on demand via the verify tool or automatically on every turn of a Best-of-N session. In

Schedules workspace Agent runs in fresh Result Sessions with persistent audit history, using a stock DSH Conversation tab or a global Shell page when its slots are available.

Deterministic DeepSeek Harness Web client plugin that explains the Windows-sandbox `spawn EPERM` failure as a distinct Conversation Node.

DSH plugin: append each answer's token usage to the conversation

Desktop pet surface: a free-roaming, conversation-aware pet that floats over the whole dsh web UI

ChatGPT-style conversation-history rail for the DeepSeek Harness web GUI: a strip of bars at the transcript's right edge with a hover panel listing every user message, click-to-jump and scroll-synced highlighting.

Conversation question index for the DSH Web UI: every question you asked in a session, searchable, paginated, with one-click jump to the exact message.

Auto-compact a DSH conversation after the current task finishes, at a user-set context threshold. Settings-page switch + slider included.

DSH plugin: auto-import local AI CLI conversations (Claude Code, Codex CLI, Cursor Agent) as real DSH sessions

Turn histogram navigation rail for DeepSeek Harness Web with mixed, DeepSeek, and Codex visual variants.

Left-edge conversation rail for the Web UI: one bar per turn, length scaled to the turn text, hover for a question and answer preview, click to jump; bars come from a host-side outline of the whole session log, so turns outside the loaded window are drawn too and history is paged in on click.

Collapsible in-conversation interactive terminal with multi-tab live shells, auto-reconnect, one-click quick commands, and a bilingual UI that follows the theme.

Record & Replay for the dsh web GUI: (1) replay every automatically recorded session as a readable timeline, export/import shareable replay packs, re-run a recorded conversation; (2) Codex-style screen recording -> skill generation - record a computer-use

An intent-calibrated DSH discussion mode that prevents complex conversations from drifting and turns them into evidence-based next steps.

Surgical rewriting of the model-visible conversation history of a DSH session (surface replacement); edit reply and reasoning chain separately. 上下文手术刀：强制改写会话的模型可见历史，回复与思考链分开编辑。

Export the current DSH conversation, or selected turns, as clean readable Markdown.

FAL image generation for DeepSeek Harness: a generate_image tool backed by the FAL queue API (default model fal-ai/flux-2/klein/9b). Images render directly in the conversation, are saved to the workspace, and all settings are editable from the Web GUI.

Trellis × DSH workspace dashboard: a conversation-view tab showing the current task + progress (prd.md acceptance checklist), spec/skill usage, and workspace session summary.

dsh plugin: launch the dsh-desktop Windows shell (region screenshot, tray, session manager) from the DSH conversation via a desktop_launch tool.

Prompt optimizer in the composer: rewrites the draft into an eleven-section analytical prompt using the conversation, workspace files and the session's selected model, with one-click undo.

Project/task dual-mode workspaces for DSH: a task skips the workspace picker and gets a fresh scratch directory (D:\dsh_working\<name>-<timestamp>) per conversation, Codex-style; no-workspace sessions are grouped under a persistent Tasks section in the sidebar with empty states, and the new-session workspace picker gains a "no workspace (task)" option.

蜗蜗 (Sumikko Gurashi snail) desktop pet for the DeepSeek Harness Web UI: 8-direction crawling, slime trail, file-drop feeding, sleep, and conversation reactions

Pure-incremental directive-driven compaction for DeepSeek Harness: /compact-directive <requirement> summarizes the session middle per your requirement, /trim-directive <requirement> trims the whole conversation per your requirement