DS-Bot
A team of long-lived bots for DeepSeek Harness, with main bots, bot-to-bot messages and group chats.
Runs with mockssource: GitHubJavaScriptApache-2.0commit de55888a9398
JavaScript, Apache-2.0 licensed. The project labels itself: bot, deepseek harness, dsh plugin and multi agent.
DS-Bot runs, with stand-ins for the services it depends on. An Argusic agent installed it in 3 minutes and hit 3 errors on a clean machine with no GPU, and the whole session was recorded.
The ds-bot plugin builds, lints with 0 errors, passes all its 1060 unit tests using the mock LLM and DSH test harness. The desktop app installs its dependencies and passes 139 of 141 tests.
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 85.3 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page. 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.
- Node.js v18.19.1 installed but project requires v22.19+1 minute
- app/package-lock.json out of sync (missing [email protected]), npm ci failed
- App test fails: [email protected] is a peer dependency not listed in 'dependencies'
- Install time
- 3 minutes
- Cold machine to finish
- 5 minutes
- Errors hit and fixed
- 3 hit, 2 fixed with no human help
- How the result was proved
- npm test in ds-bot/: 1062 tests, 1060 pass, 0 fail, 2 skipped (both Windows-only file-locking tests). npm test in app/: 141 tests, 139 pass, 1 fail (pre-existing dependency completeness check), 1 skip. npm run lint: warnings only, 0 errors.
- Model tokens used
- 277,821
- Exact commit tested
- de55888a9398
- 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
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
277,821 Here is the complete report: **Install**: `npm ci` in `ds-bot/` installed 2 packages (esbuild). `npm run harness` installed 653 … **Tests**: - **`ds-bot/` (plugin)**: `npm test` — **1062 tests, 1060 pass, 0 fail, 2 skipped** (Windows-only f… - **`app/` (desktop)**: `npm test` — **141 tests, 139 pass, 1 fail, 1 skip**. The one failure is a … **Errors encountered**: 1. Node.js v18 was installed but project needs v22.19+. Fix: downloaded and used a prebuilt v22.19.… 2. `app/package-lock.json` was out of sync (missing `[email protected]`), so `npm ci` failed. Fix: used `np… 3. The `app/` test `package.test.mjs` checks that all peer deps are in `dependencies` — `[email protected]`… **No third-party credentials required**: The unit tests use a mock LLM (`dev/mock-llm.mjs`) and the… **The most important number**: `npm test` in `ds-bot/` exits 0 with **1060 passing tests + 2 intent…
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
- Installed in 3 minutes, faster than the median of the 4 comparable projects Argusic has measured.
- Licensed Apache-2.0, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Hit 3 errors during setup, 1 of which were not solved.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 5 bot projects Argusic has installed and timed, DS-Bot was the 2nd fastest to reach a running state, and 1 of 5 reached one at all.
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 | 1/3 | Runs with mocks | 85.33 | 0.04 |
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/ds-bot)Questions
- Does DS-Bot run?
- DS-Bot runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 3 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test DS-Bot?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit de55888a9398. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test DS-Bot?
- The run that produced this verdict cost $0.04: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does DS-Bot take to install?
- 3 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 DS-Bot need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing DS-Bot?
- 3 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does DS-Bot compare with the alternatives?
- Of the 5 bot projects Argusic has installed and timed, DS-Bot was the 2nd fastest to reach a running state, and 1 of 5 reached one at all.
- Where is the evidence for DS-Bot?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.