Plugins

Adds a produced-files card row to the chat and a resizable split-screen preview panel for workspace artifacts (Markdown, source code, CSV, JSON, images, HTML), plus a localhost port preview.

DSH plugin: visible cost/balance stats pill below the composer, with settings page and one-click reset. Fixed fork-level issues of dsh-cost-balance (slot id collision, missing ctx, invisible 5px bar).

Fail-closed LLM-assisted approval reviewer for DeepSeek Harness

Native Windows Computer Use tools for DeepSeek Harness.

Slacking-off companion: a floating mini player that streams Bilibili videos (native player, danmaku, comments, search) and pauses when your agent needs you, resuming exactly where you left off.

A draggable mascot invites you to play Xiangqi (Chinese chess) while the AI thinks, with a built-in engine, move-record export, and optional multi-model commentary.

One-click skin switching for DSH Web settings: auto-detects installed themes, keeps exactly one active at a time, and falls back to the official look when all are off. Changes apply instantly and survive restarts.

Plugin insight center: one answer to "哪些值得装" — plugin_guide matches needs to plugins, recipe installs whole environments, plugin_rank scores health (0-100), plugin_audit static-scans a local checkout for security, and plugin_verdict outputs install / caution / research / avoid.

Automated approval review: auto-approve read-only tools, auto-deny dangerous commands, fail-closed policy engine.

Codex-style auto-review permission mode: adds an auto-review preset that auto-approves safe sandbox escalations, asks on risky or ambiguous ones, and rejects critical unconfirmed operations.

Installation safety gate for DSH plugins: antivirus-style scan of install scripts, permissions, secrets and network callbacks on local directories or npm tarballs, returning a BLOCK/WARN/PASS verdict before "dsh plugin add".

Keeps what the agent builds at runtime: turns a `cordis_define` dynamic package into a real installed plugin that survives restart, writing the bundle and registering the profile layer with no pnpm, no network, and no build authorization.

Test-stability tools: repeatedly run vitest/jest/pytest/node:test suites, classify flaky cases, keep history, maintain a quarantine manifest and health self-check.

Metadata-first runtime profiler for DSH agents: turn/step traces, model and tool wall-time timelines, provider usage, retries, errors, and live or historical sessions.

Update copilot for DeepSeek Harness: one scan covers the DeepSeek Harness core and every profile plugin; explains what changed and how risky each update is, then updates only what you confirm.

Contract regression harness for plugin authors: a scripted LLM adapter drives the real pipeline in isolated child processes with session-event assertions (load/contract/behavior/fault layers); zero API key, CI-ready.

Automatic type-check diagnostics: after the model edits or creates TS files, runs `tsc --noEmit` in the background (debounced per project) and reports errors via the `code_check` tool — grouped by file with line/column, severity and TS error codes, closing the "edit → check → fix" loop.

Real-time stage, ETA & cost dashboard for headless dsh tasks: turns the black-box session event stream into a live multi-task grid (cordis plugin + standalone local dashboard, no API calls).

Two-way TickTick/Dida365 (滴答清单) task sync via the official OAuth Open API: pull tasks across lists, create/update/complete/delete tasks, and one-shot title-deduped sync, with a web settings panel.

Task-completion notifications via ServerChan / DingTalk / Feishu / generic webhooks.

OS-level system notifications for the dsh web GUI: popups when a turn finishes or the agent needs your approval, answer, or plan review while the page is in the background.

Provider-neutral CI/CD capability for DeepSeek Harness with GitHub Actions support, bounded failure evidence, source-aware diagnostics, and approval-gated rerun/cancel controls.

A project-agnostic multi-agent collaboration protocol for the DeepSeek Harness: loop guards that stop runaway agent loops, a six-field handoff format, risk-tiered review routing, and a fixed verify→commit→push→review→close sequence. One skill instead of the same rules copy-pasted into every agent's instructions.

Clusters arXiv, first-party lab, official artifact, hardware-vendor, and opt-in X signals into versioned release evidence bundles, then gates claim-level reproduction on commands, artifacts, metrics, and verifiers.