Alterssss/dsh-bili-whale
A Bilibili companion that keeps its own schedule. A 60-second tick in the plugin host wakes a dedicated agent session at a random moment inside the configured time windows (opting out of a day is a configurable chance), then hands it a bundled CLI of 38 subcommands — feed, subtitles, danmaku, comments, ffmpeg frame grabs, and two diaries. Shares at most N items a day by commenting on them and @-mentioning the owner (default 3, enforced from a written quota log, and it stops on rate-limit or captcha signals). Also polls comment replies, direct messages and live-room danmaku; replies to anyone but the owner are queued for approval in Settings. Settings → 养鱼 writes ~/.dsh/bili-whale.config.json; cookies live separately in ~/.bili-ai/credentials.json and are never echoed back. The HTTP routes are loopback-only behind DSH's trust fence. Needs Node 18+ and ffmpeg on PATH for frame extraction.
Install
via GitHub · GitHub source
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.
The desktop app keeps its own profile, desktop, and only the dsh command it ships may change it — the npm-installed dsh refuses that profile. Install the command from the app menu (Manage dsh Command…), open Desktop once, quit it fully, run the line below, then reopen Desktop.
via GitHub · GitHub source
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/desktop/pnpm-workspace.yaml.
Our install check ran in a web profile on npm's dsh, not in the desktop app.
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 8d agoon DeepSeek Harness 0.2.2-rc.1.
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
Security
No build script was blocked in our run.
Source: our sandbox install on DeepSeek Harness 0.2.2-rc.1, 8d ago.
package.json declares no preinstall, install or postinstall script.
Source: package.json on GitHub, read at our last sync. prepare is not recorded; it runs only on a GitHub install, and shows up under build scripts when pnpm blocks it.
shell commands (bash, exec, spawn …)
Source: a keyword match on the README — a hint about what the plugin touches, not an analysis of its code.
Not an audit. These are the record of one install and two text scans; nobody has read this plugin's code on your behalf. Plugins run with your agent's permissions.
What it is — A DeepSeek Harness Bilibili companion that runs its own schedule for random waking, video processing, diary writing, and sharing.
Who it is for — If you want to use an agent session in DeepSeek Harness to run a Bilibili companion with its own schedule for video reading, diary writing, and sharing, this plugin supports it. If you want to install it in an existing profile, this plugin is not suitable because it requires a new profile and registration with the harness.
Watch out — Requires Node 18+ and ffmpeg on PATH. Sandbox test passed in new profile. Agent session requires full access permissions.
The verdict — I would install it because it uses conservative defaults to protect account security, but the premise is to grant full access to the agent session.
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-bili-whale is a DeepSeek Harness plugin that runs a scheduled Bilibili companion through a dedicated agent session. A 60-second host tick chooses a random wake-up time inside configured activity windows, with a configurable chance of skipping the day. The session uses a bundled CLI with 38 subcommands to read feeds, subtitles, danmaku, comments and video frames, then writes two diaries. Frame extraction uses ffmpeg; debrief <BV> --substrip can turn hard-subtitle strips into an image for inspection.
DeepSeek Harness starts the session with the plugin’s configured permissions. The plugin reads Bilibili credentials from ~/.bili-ai/credentials.json, stores settings in ~/.dsh/bili-whale.config.json, and can load persona text from ~/.bili-ai/persona.md or general instructions from ~/.dsh/AGENTS.md. It may comment on selected videos while mentioning the configured owner, subject to a daily quota log, request limits, cooldowns and captcha or rate-limit stops. It also polls configured message sources; replies to people other than the owner become approval drafts.
This is intended for developers who want an agent to monitor and selectively discuss Bilibili content using their account. It is a poor fit where terminal access, account automation or persistent polling is unacceptable, or where Node 18+ and ffmpeg are unavailable. The terminal surface matters: the agent runs bundled commands and needs sufficient permissions to read and write the listed files, invoke ffmpeg, and make Bilibili requests. The plugin does not perform follows, payments, gifts, mass operations or account-security changes.
DeepSeek Harness loads settings from ~/.dsh/bili-whale.config.json; credentials are kept separately in ~/.bili-ai/credentials.json and are not echoed in the settings page. The settings page can configure the owner, activity windows, sharing, message polling, notifications and risk controls. New installations use conservative values:
| Setting | Documented default |
|---|---|
| Comment polling | Off |
| Direct-message polling | On, every 60 seconds |
| All-day listening | Off |
| Request interval | 1500 ms |
| Read budget | 600 per hour, 3000 per day |
| Write budget | 12 per hour, 30 per day |
| Write cooldown | 120 seconds |
| Direct-message cooldown | 60 seconds |
| Daily sharing limit | 3 items |
| Minimum share score | 13 out of 20 |
The persona editor writes ~/.bili-ai/persona.md; DeepSeek Harness also hot-loads ~/.dsh/AGENTS.md for all sessions. Persona text is limited to the first 3000 characters when prompts are built.
The bundled CLI is run with node bili.mjs. selftest checks configuration, credentials, login state, data directories and dependencies. traffic status reports the effective request-protection values. dm --status shows the direct-message status, dm --msg "..." --dry previews a message, and dm --msg "..." --go sends it. debrief <BV> --substrip prepares a hard-subtitle strip for frame-based reading.
DeepSeek Harness wakes the dedicated session at a random time in the configured window. Sharing uses either a public comment mentioning the owner or a direct message, and shares the same quota and validation checks. Owner replies can be sent directly; other replies are queued for approval. Rate-limit, captcha and related platform signals stop writing.
DeepSeek Harness requires Node 18+ for this plugin. ffmpeg must be on PATH for frame extraction. Direct-message mode requires two distinct, logged-in Bilibili accounts that manually follow each other; one account cannot provide that separate identity. HTTP routes accept loopback traffic behind DeepSeek Harness’s trust fence.
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.
No one-line install — this plugin lives inside a larger repository and publishes no npm package.
PC2005-cloud
Desktop pet for the DSH Web UI on Windows, macOS and Linux: 106 transparent animations in the browser overlay or a transparent always-on-top desktop window, throw-and-bounce drag physics with squash and particle scoring, a work-status bubble driven by live session events, self-talk and chat with persistent memory, balance display, meme-image bubbles, multiple pets on screen, and drop-in custom animations and pet packs.
Installed cleanly when we ran it
flizzywine
Installs, updates, and switches to a separate DSH Tavern profile on official DeepSeek Harness Desktop for Windows and macOS. Forked from 2NF/dsh-profile-bridge (MIT); install this launcher or the upstream plugin, not both — they claim the same /profile-bridge channel.
No one-line install — this plugin lives inside a larger repository and publishes no npm package.
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
