dsh-file-link-menu
Right-click menus for files and links in the DSH Web UI, plus file-type glyphs and short names on conversation path chips
890 results
Right-click menus for files and links in the DSH Web UI, plus file-type glyphs and short names on conversation path chips
Persian (Farsi) RTL fix for DeepSeek Harness: automatic per-paragraph direction and mixed-language detection (Persian text starting with English words), thinking cells, tool cells, user bubbles and question boxes.
DSH plugin: richer session hover cards — corner icons that copy the session id and workspace path, a configurable metrics block (turns, steps, tokens, compactions, context, subagents, …) fed by the hoverInfo projection + Typert remote, all gated by a Settings → Plugins card
Per-message delete for DeepSeek Harness: remove a user message, one reply step, or a whole assistant reply from the derived model context through the official surface-replace contract, and hide it from the visible transcript without rewriting the append-only log.
Claude Code style auto-memory plugin for DeepSeek Harness: typed memory files + MEMORY.md index auto-injected into the system prompt
Universal on-screen translator for DeepSeek Harness Web UI: translates UI text, attributes, Shadow DOM, and iframes across 45+ languages.
Workspace file references for DeepSeek Harness: pick a file with '@' and inject its content into the model context
Unsloth for DeepSeek Harness - a pure-client tool plugin that connects the harness online model to a locally running Unsloth Desktop (Unsloth Studio) server for repetitive text and vision (OCR) labor.
A paper-review panel for the DeepSeek Harness: converts PDF papers into structured, selectable text (columns, headings, tables, sub/superscripts, table of contents) with figure and display-equation rendering, a floating ask-about-the-selection dialog, and per-project paper stores under a Paper workspace.
Cut MCP context and API cost in DeepSeek Harness with two model-facing tools, lazy discovery, and exact-schema calls
In-process DeepSeek Harness context compression bundle
Save messy notes (text + images) to a Yuque knowledge base, classified by the model.
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
DeepSeek Harness Telegram mobile remote: workspace→session, /last context, /model — dsh-plugin
Full session management for the DSH web UI: delete (with trash/restore/purge), restore archived sessions, activity stats, continue/pause, fork to a new chat, unread markers, session rename, export transcripts as Markdown/JSON, open log folders, workspace grouping and sorting, and move sessions between workspaces. Plus a global context compaction threshold. No harness changes.
Session reference plugin for DeepSeek Harness: one-click copy of the current session's @session-id reference in the header, an @ mention menu that lists sessions by title, and a session_read tool that reads any local session by @session-id / dsh-session:URI / @title and projects it to readable conversation text — no more download-transfer-unzip to share context between sessions.
Visual percentage and token settings for official DeepSeek Harness compaction
行级文本 diff
Evidence-backed working memory for DeepSeek Harness: a cited ledger of what already worked in this workspace, built from the session log you already have
Search for and select local files or directories from the DSH Web GUI for conversation context.
AI Agent runtime authorization & evidence verification — tool-call GuardrailProvider, CCS 7-dimension verification standard, MCP/DSH security scanner, SSRF/command-injection/credential-exfil blocking with Ed25519 signed receipts.
Give DeepSeek Harness eyes: a vision_analyze tool that sends an image (local path or URL) to an OpenAI-compatible vision model and returns a text description.
Image generation for DeepSeek Harness: a generate_image tool with pluggable providers — the FAL queue API or any OpenAI-compatible images API. The picture is shown inline in the conversation; the model receives either a link (works with any chat model) or the image itself (needs dsh-vision-bridge or a vision-capable model).
dsh auto-vision bridge: paste an image into a text-only model's composer and a configured multimodal model transcribes it as text, automatically.