hellodigua/dsh-emoji
Automatically add emojis to AI replies.
Install
via npm
Resolves a published tarball rather than cloning the repository, and installs without any extra setup. Swap `web` for your profile name if you run another one.
via GitHub · npm package
Installing from GitHub runs the project's build script, which pnpm blocks until you allowlist it — run the command once and pnpm prints the exact key to add under `allowBuilds` in ~/.dsh/profiles/web/pnpm-workspace.yaml.
What happened when we ran it
Installed cleanly when we ran it
Every command here is run in a throwaway container against a clean profile, and the result is whatever the harness recorded — not a guess from the source. Last run 18d ago.
Show it in your README
For maintainers: the badge serves this listing's latest sandbox verdict, so a re-run updates it on its own — and it links readers to the full result here.
Due diligence
What it is — Add inline emoji support to DeepSeek Harness replies via semantic markers that render as images.
Who it is for — When using DeepSeek Harness models for customer service or creative replies that require tone or emotion, this plugin inserts markers like ::happy::. If you prefer pure text responses in conversations, this plugin is not needed.
Watch out — No obvious issues found. After installation in a fresh profile, it registers with harness. Custom ZIP uploads take effect on the next call.
The verdict — I would install it because it allows switching emoji styles within the same conversation to fit different expression needs.
Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.
dsh-emoji is a DeepSeek Harness plugin that adds switchable inline emoji images to AI replies. DeepSeek Harness reads the model’s approved Unicode emoji output and, on the Host side, replaces 40 recognised semantic emojis with images from the selected pack. This requires no additional model call and does not infer emotions from surrounding text.
The plugin’s settings let an operator turn emoji use off, choose 智能 or 高频 frequency, select a pack, choose one of four image sizes, and provide additional prompt instructions. Uploaded ZIP packs are validated and stored under $DSH_HOME/emoji-packs/ (by default ~/.dsh/emoji-packs/); settings retain the selected id@version. The same 40 semantic keys are used by built-in and custom packs.
dsh-emoji is intended for conversations where decorative, community-style expressions are useful and where the Web Profile can load a plugin compatible with @deepseek-ai/dsh@0.1.0-rc.7. It is a poor fit when replies must remain free of inserted images, when arbitrary Unicode emoji should be transformed, or when emotion should be inferred automatically. Code, links, ordinary Markdown images and unrecognised emoji remain unchanged, and frequency choices still depend on the model following the supplied prompt.
After DeepSeek Harness loads dsh-emoji in the Web Profile, its settings card, 设置 → 插件 → 表情（Whale Emoji）, provides these controls:
| Setting | Behaviour |
|---|---|
关闭 |
Disables emoji use. |
智能 |
The default; allows up to 3 images per reply when they help express meaning. |
高频 |
Requests one suitable emoji in every reply, with up to 4 images per reply. |
| Additional prompt | Adds instructions for selection, tone and usage context. |
| Pack and size | Selects the image set and one of four sizes: small, normal, large-ish and large. |
Changes apply from the next reply without restarting the Web Host. The frequency policy still depends on model compliance.
The model selects from 42 permitted Unicode emojis representing 40 stable semantic keys. DeepSeek Harness’s Host converts recognised output to an inline image from the active pack. The conversion also recognises 😄, 🙂 and images produced by dsh-emoji. It leaves other Unicode emoji, code, links, double-colon text and ordinary Markdown images unchanged. Multiple plugin images must be separated by valid body text, while the same image may recur in different positions.
The settings card accepts a ZIP containing pack.json and an images/ directory, optionally inside one same-named directory. pack.json must declare schemaVersion: 1, keySet: "dsh-emoji-core@1", an id, a name and a SemVer version. The archive must provide exactly one PNG for each of the 40 standard keys. ZIP size is limited to 20 MiB, extracted size to 80 MiB, each file to 2 MiB, and image dimensions to 512 pixels. DeepSeek Harness stores packs in $DSH_HOME/emoji-packs/. Removing a pack from the selection list does not delete its bytes, preserving versioned URLs in historical messages.
The current release targets npm @deepseek-ai/dsh@0.1.0-rc.7 and declares DSH peers ^0.1.0-rc.7. Local development requires Node.js ^22.19.0 || >=24 and pnpm 11.
Written from the project's own documentation and kept in sync with it. Where the two disagree, the source is authoritative — read the README on GitHub
Same category
zhu1090093659
A whale-girl companion for the dsh web GUI: animations follow the agent state, with pat interactions and a feeding mechanic that raises intimacy from a calf to deep-sea bonds.
Installed cleanly when we ran it
PC2005-cloud
Desktop pet for the DSH Web UI with 25 transparent animations, screen wandering, click reactions and drag, plus a reproducible asset-generation pipeline.
Installed cleanly when we ran it
Nagi-ovo
Parody ads in 2005-Chinese-web style: sidebar banners, in-chat feeds, corner popups, and a close button whose hit area is smaller than it looks. All fictional.
Installed cleanly when we ran it
QCYTSN
Desktop-native BigFish companion for DeepSeek Harness — real Agent status, always on top on Windows.
Installed cleanly when we ran it
vlln
Desktop pet (QQ-pet style): floats in the corner, draggable, feedable, playable.
Installed cleanly when we ran it
yyh-001
Meme search, the fun way: describe the vibe, and the agent finds and sends a real meme that actually fits.
Installed cleanly when we ran it
