Plugins

Turns DSH permissions into 9 selectable presets (3 sandbox modes x 4 approval tiers), with rule plus LLM risk classification across four risk levels, password-gated approval for high-risk operations, and a JSONL audit log.

Semantic risk grading and progressive authorization: classifies tool calls into safe/risky/redline, asks before irreversible actions, auto-allows only approved-and-succeeded signatures.

Runtime observability and plugin operations panel for DeepSeek Harness: shows the profile plugin tree, real Loader fiber state, capabilities/dependencies/compatibility, current-session plugin activity and upstream source/version checks, with one-click enable/disable/update/uninstall plus a standalone startup-failure diagnostics page that works while DSH is not running.

In-app local notification center for DSH: a sidebar Notifications entry with unread badge, full-screen center with level color coding (info/success/warn/error), time/source filters, sorting, title/content search, read/unread, delete, detail popup with one-click copy, and pagination; written by the notify_add agent tool or the dsh-localnotify CLI (with auto-cleanup retention), page refreshes live, UI follows dsh web language (zh/en).

Turn-level workspace undo for Git worktrees: every agent turn gets a private snapshot, /undo previews a red/green diff card that is confirmed in place, files changed after the turn are refused with a conflict diff unless --force or --skip-conflicts is passed, and HEAD, index, stash and commit history of the user repository are never written.

Records scoped workflow rules and correction reminders with bounded evidence, local settings, and optional Brain Hub integration.

Recurring task scheduler with an append-only delivery ledger: window-aligned dedup execution, failure/abandoned rows, and same-window retry redelivery.

A DeepSeek Harness bundle of 14 obra/superpowers engineering skills with a native agent preset, automatic session bootstrap, and Windows sandbox compatibility.

Reads AI replies aloud as they stream, with voiced waiting phrases while the model thinks. Edge TTS built in, any OpenAI-compatible cloud engine supported.

Configure multiple image providers in Settings and call image_generate with the one selected model; images save under generate/image and show inline in the conversation.

Resume screening plugin for HR in DeepSeek Harness: ingest up to 100k Word/PDF/Excel resumes into one searchable library with skills / coarse categories / ingest time, auto-ingest & de-dupe new resumes, then screen by plain-language criteria — rule pre-filter in the database plus LLM fine-judge on the shortlisted few, CSV export.

Input-box floating translation widget for DSH: translate drafts via session model, Zhipu GLM, or custom endpoints, with preview/replace/append, connectivity testing, and recent history.

Adds a markitdown tool that converts PDF, Word, Excel, PowerPoint, HTML, CSV, EPUB and URLs to Markdown, using a real Microsoft MarkItDown installation when one is reachable and a bundled dependency-free converter otherwise.

Terminal plugin for DeepSeek Harness: stays in sync with the Workspace in real time, with isolated terminals that each keep their own command history.

Keeps notes as local Markdown files grouped by directory under a root folder you choose, with a sidebar page, AGENTS-style rule files surfaced as writing context, and six agent tools.

Project-scoped local memory with review-before-recall, source references, reversible consolidation, and a portable Cordis service; the Harness adapter provides search and settings, with optional Brain integration.

Tiered persistent memory (user/env/project) with per-tier char budgets and semantic query routing; full layers refuse writes instead of silently evicting.

Polaris Memory: local-first project memory plugin for DeepSeek Harness. Uses per-project .dsh-memory.json; provides memory_read/recall/write/update/delete tools, /memory command and settings UI, with tiered injection (resident user profile + scene-triggered memories with P1/P2/P3 importance), semantic recall (IDF + synonym layer), and a hard-guard mechanism for bottom-line memories (detect deny-semantics -> authorize -> block AI deletion; user can confirm-override).

Measures what an llm-pi-ai endpoint really accepts — context window from its own model list, output-token limit and reasoning levels read out of its own range errors, image support from a generated test image — then reports declared values that contradict that evidence and rewrites them only after confirmation.

Dark navy glass theme for DeepSeek Harness Web with a cyber-city background and holographic-cube cyan accents.

Floating usage window for DSH Web showing Claude and Codex subscription windows with reset countdowns, plus DeepSeek API spend and balance; display-only companion to dsh-cost-meter.

Shows selectable DeepSeek, Kimi, Zhipu GLM, and TeamoRouter balances in the DSH Web sidebar, with per-provider details, usage data, and refresh controls.

Provider-aware account balance chip for the DSH sidebar, showing the active model provider balance for DeepSeek, OpenRouter, Moonshot/Kimi, Zhipu/GLM, and MiniMax, plus DeepSeek peak/off-peak status.

Minimal DSH Web transcript toggle: hide thinking, tool-call, and turn-process rows from the session header while preserving assistant answer text.