DeepSeek-Balance-Whale-Widget
DeepSeek Harness(DSH)一只住在 DSH 界面右下角的小鲸鱼娘,帮你盯着DeepSeek账户余额。QQ弹弹,支持拖拽吸附、左吸附翻转、数字滚动动画,随界面自动启用,建议直接喊来你的dsh安装
Runssource: GitHubJavaScriptMITcommit 770d3f55ff40
JavaScript, MIT licensed. The project labels itself: cordis, deepseek, deepseek harness, developer tools, dsh, dsh plugin, dsh plugins and floating widget.
DeepSeek-Balance-Whale-Widget runs. An Argusic agent installed it in 22 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
DSH web 0.2.0-rc.2 boots with dsh-whale-widget 0.3.18; all plugin routes serve content correctly; CI audit (layer z-index, syntax, core invariants, dead-settings) passes 5/5.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 75 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- DSH profile not initialized; web profile had no package.json or bundle deps5 minutes
- Native binary node-addon-require-builtin-linux-x64-gnu not installed (optionalDependency npm skipped)4 minutes
- Node.js v18 too old — DSH requires >=22; many packages required >=203 minutes
- DSH web process exited silently after URL printed — nohup from wrong CWD lost module resolution3 minutes
- npm global install failed (EACCES — /usr/local locked down)2 minutes
- Install time
- 22 minutes
- Cold machine to finish
- 24 minutes
- Errors hit and fixed
- 5 hit, 5 fixed with no human help
- How the result was proved
- curl against running DSH web server (port 3080) with auth cookies: /dsh-whale/widget.js returned 200 (861,966 bytes), /dsh-whale/image.png returned 200 (255,988 bytes, image/png), /dsh-whale/balance.json returned 200 (structured JSON: version 0.3.18, NO_KEY error), /dsh-whale/sound/press.mp3?set=duck returned 200 (6,370 bytes, audio/mpeg), main page HTML contains dsh-whale/widget.js script tag.
- Model tokens used
- 405,030
- Exact commit tested
- 770d3f55ff40
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
succeeded in 0ms: Start time: 07:48 UTC End time: 08:10 UTC widget.js: 861966 bytes image.png: 255988 bytes image/png sound mp3: 6370 bytes audio/mpeg balance: structured JSON (NO_KEY - expected without credentials) widget injected in HTML: YES Here's my final report: tokens used 405,030 Here's my final report:
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Installed in 22 minutes.
- Recovered from all 5 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs | 100.00 | 0.26 | |
| Argusic Runner | 1/3 | Did not run | 50.00 | 0.35 |
Topics (from GitHub)
cordisdeepseekdeepseek-harnessdeveloper-toolsdshdsh-plugindsh-pluginsfloating-widgetplugin
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/deepseek-balance-whale-widget)Questions
- Does DeepSeek-Balance-Whale-Widget run?
- Yes. DeepSeek-Balance-Whale-Widget runs. Argusic installed and launched it on a clean machine in 22 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test DeepSeek-Balance-Whale-Widget?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 770d3f55ff40. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test DeepSeek-Balance-Whale-Widget?
- The run that produced this verdict cost $0.26: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does DeepSeek-Balance-Whale-Widget take to install?
- 22 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does DeepSeek-Balance-Whale-Widget need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing DeepSeek-Balance-Whale-Widget?
- 5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for DeepSeek-Balance-Whale-Widget?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.