Plugins

Common Word Box (常用词盒子) — DeepSeek Harness web client plugin: a persistent slide-up word/phrase panel next to the composer input, with global/current-project buckets and one-click insert. Works in every workspace.

DeepSeek Harness (DSH) plugin: live conversation cost and DeepSeek account balance in the composer stats row — RMB in Chinese UI, USD in English UI

Token cost tracker for DeepSeek Harness -- track usage, calculate costs, budget warnings

DSH balance and quota card showing up to 3 recently used providers. Supports DeepSeek, Moonshot, Kimi For Coding, OpenAI Codex, and OpenCode Go, with auto-discovery, quota windows, reset times, color-coded status, dragging, and automatic refresh.

Two-way Slack messaging (notify/channels/inbox/reply/health) over Socket Mode, no public callback needed.

A minimal greet tool plugin for DeepSeek Harness.

Meme search, the fun way: describe the vibe, and the agent finds and sends a real meme that actually fits.

The model switch for DSH: point it at any OpenAI-compatible endpoint, with curated free/cheap DeepSeek provider presets and automatic fallback when a free tier rate-limits you.

Appends local hash-chained JSONL receipts for tool results and session events without storing prompts, tool arguments, result text, or raw session IDs.

Loader-independent startup recovery for DSH Web that detects likely broken plugins, temporarily skips them, and restores only Boot Guard-managed changes.

Notification outbox: agent proactively notifies via toast / Chinese TTS voice / sound effects (explosion, victory, alarm), 60s confirmation window voice-calls you back, volume boost, settings panel.

Loopback-first multi-agent message relay: HMAC-authenticated broker plus dsh plugin (relay_send/recv/peers/history), zero-dependency CLI and Python clients, wire protocol v1.0.

Task planning with experience muscle-memory: condition-reflex recall of past solutions, LLM capability matching, and auto-persisted lessons.

Agent trajectory governance and anomaly diagnosis: rebuilds flat session logs into multi-branch trajectory trees, detects loop deadlock, invalid retry, and goal drift, alerts with cost attribution, one-click interrupt and breakpoint fork via official APIs, independent GUI tab.

Session execution analytics: steps, tool calls, failures, repeated actions, token usage and verification signals, rendered as text/Markdown/JSON reports.

Upload local images and files to your image host through PicGo's existing configuration (PicGo Cloud, GitHub, S3, COS, Qiniu, or any installed uploader plugin), via a `picgo_upload` tool and a `/picgo` command.

Query 64 Chinese exams (高考/考研/四六级/CPA/法考…) with rule-aware date math (2nd-Saturday, 1st-Sunday) and countdowns.

Compile SVG paths and keyframe specs into self-contained Lottie JSON animation files.

Voice notes in, spoken answers out: dictate audio that becomes user messages (transcribe), have the agent read replies aloud (speak), local-first under ~/.dsh/voice.

Project .pack.json/.pack.zip into .agent-pack/modpacks/ and expose skills via a workspace allow-list.

Native LLM-provider vision bridge: images pasted in the chat are described by a vision model (Qwen3-VL via pi-ai/llama.cpp) and the text description is fed to text-only DeepSeek for the reply — image admission, routing and compaction all run through harness-native mechanisms, with an LRU description cache and 503 retry.

Export the current session to portable, schema-versioned Markdown and JSON files via the `session_export` tool and slash commands, with cross-platform-safe filenames.

Render local image paths from assistant replies inline in the message body (9 formats, click-to-zoom lightbox, adjustable size).

Microphone voice input for the composer: browser Web Speech API live transcription, dedupe/auto-continue, smart punctuation, language and auto-send settings.