플러그인

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

Runtime governor for DeepSeek Harness: zero-progress steering, generation-bound verification evidence, evidence-aware completion guarding, and task-profile tool restriction.

Scheduled bilingual financial reports for DSH: market quotes, news and macro calendar, with per-target timezones and delivery through eight dsh-im channels.

Auto Mode for DSH: a flash-model router that auto-picks the best agent preset (standard/code/minimal/cordis) for each new session and executes immediately, no confirmation.

Local WeChat OCR tool for DSH: `wechat_ocr_recognize` returns recognized text and the engine structured result for a local image path.

Local-memory lifecycle for the official Hindsight plugin on DSH desktop: one-click start/stop of the hindsight-embed daemon, auto-start on boot, stop on exit, hides the uv.exe console window, and installs the vault/models to another drive.

30 classic open-source theme palettes (Catppuccin, Nord, Tokyo Night, Gruvbox, Solarized, etc.) mapped to official ThemeService tokens for DeepSeek Harness, with a Style Settings panel for live color/font/radius tweaks and JSON export/import for sharing config packs.

Polishes the draft in the composer into a clearer, better-structured prompt from the ✨ button or Alt+O; streams the result live over SSE with reasoning shown first, and follows the session's default model with zero configuration or any OpenAI-compatible endpoint.

Floating workspace file-preview window for the Web client: lazy file tree, CodeMirror preview and in-window edit with save, Markdown and image preview, Quick Open search, and opening paths clicked in the conversation.

Beautified archive-manager settings section listing archived sessions grouped by workspace, with a hover unarchive action and relative timestamps.

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.

Add six languages (繁體中文, 日本語, 한국어, Français, Deutsch, Español) to the DeepSeek Harness Web UI language options, with hand-polished per-language translations and automatic fallbacks (Simplified-to-Traditional conversion for zh-TW, English for the others) covering upstream updates and third-party plugins.

Local code knowledge graph for agents: parse a codebase (Python/JS/TS/Go/Java/Rust) into a SQLite index and answer callers, callees, deps, dependents, impact and full-text questions over it.

Parses natural-language relative time (e.g. "in 2 hours") into ISO timestamps, fail-fast.

Parses cron expressions into human-readable text and previews upcoming run times.

Workspace-owned durable process supervision, readiness checks, and a Runtime Center for DeepSeek Harness.

One-click Windows/WSL2 environment switcher for DSH (coexistence mode): both environments run simultaneously on separate ports and switch from the web UI without killing any process.

Alternative WorkflowEngine provider for DSH 0.1.0-rc.7 that runs model-written orchestration in fresh QuickJS/WASM runtimes with a JSON-only host bridge and bounded memory, execution time, and child-agent fan-out.

vision_analyze tool: analyze a local image or URL with an OpenAI-compatible vision model.

8 curated color schemes plus custom palette import (name + scheme + seed colors derive a full token map), a Palette row in General settings, hot-plug install.

System parameter adjustment UI: grouped settings page for timeouts, parallelism, LLM retry policy, model params, web search, permissions and presets; safe profile-config editing with line-level YAML matching and post-write validation.

Chinese localization for tool results: intercepts tool execution output and translates English markers (`[exit code]`, `[timed out]`, `[sandbox: ...]`, etc.) into Chinese, with a settings toggle.

Rewrite the current composer draft through an auxiliary LLM call without sending a message.

Model-agnostic visual-inspection pipeline for text-only agents: page-by-page HTML screenshots plus a ready-made vision-subagent briefing contract (gewu_prep), then source-code truth verification of every finding (gewu_locate); validated on mimo-v2.5 & qwen3.7-plus.