dsh-superagent-prototype
Towards a More Autonomous Agent System
Runs with mockssource: GitHubTypeScriptMITcommit 6337fc823ce2
TypeScript, MIT licensed.
dsh-superagent-prototype runs, with stand-ins for the services it depends on. An Argusic agent installed it in 4.2 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
pnpm install, typecheck, test (1196/1197 pass), and build all succeed; dsh profile superagent starts on :3082, setup resolves repository/agent, GitHub source polls notifications, management API returns 200 on state/sources/overview/tickets/settings.
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 71 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.
- tests/sources.spec.ts: feishu malformed-line test fails: expects health.state=="error" when reading a non-JSON event line, but async .catch chain in feishu-loops.ts stdout handler has not settled when the assertion checks health.feishu from board.all30 minutes
- Install time
- 4 minutes
- Cold machine to finish
- 69 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- pnpm check (typecheck + test + build): 1196/1197 tests pass, typecheck passed, build completed. DSH superagent profile starts on port 3082, API responds 200, github source polls notifications with health ready
- Model tokens used
- 4,452,882
- Exact commit tested
- 6337fc823ce2
- 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.
- **`pnpm build`** completed cleanly
- **`pnpm check`** = typecheck + test + build — only the same failing test
- **DSH profile launch**: profile `superagent` created from Web template, bundle installed via `pnp…
- **Setup**: resolved `repository=acme/widgets`, `agent=agent-bot` (mock `gh` CLI at `/tmp/fakebin/…
- **GitHub Source**: polls notifications, shows `"ready"` with `"0 notifications; next poll ≥ 60s"`
- **API**: `GET /orchestrator/api/state`, `/sources`, `/overview`, `/tickets`, `/settings` all resp…
- **Policy saved**: allowed list for `alice`, overview shows `"problems": []`
exec
/bin/sh -lc "echo 'ARGUSIC_RESULT: {\"install_succeeded\": true, \"launch_succeeded\": true, \"inst…
succeeded in 0ms:
tokens used
4,452,882Replay 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 4.2 minutes, faster than the median of the 34 comparable projects Argusic has measured.
- Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
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.
Of the 35 TypeScript projects Argusic has installed and timed, dsh-superagent-prototype was the 16th fastest to reach a running state, and 25 of 35 reached one at all.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 0.99 | |
| Argusic Runner | 1/3 | Did not run | 50.00 | 0.07 |
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/dsh-superagent-prototype)Questions
- Does dsh-superagent-prototype run?
- dsh-superagent-prototype runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 4 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test dsh-superagent-prototype?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 6337fc823ce2. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test dsh-superagent-prototype?
- The run that produced this verdict cost $0.99: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does dsh-superagent-prototype take to install?
- 4.2 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 dsh-superagent-prototype need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing dsh-superagent-prototype?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does dsh-superagent-prototype compare with the alternatives?
- Of the 35 TypeScript projects Argusic has installed and timed, dsh-superagent-prototype was the 16th fastest to reach a running state, and 25 of 35 reached one at all.
- Where is the evidence for dsh-superagent-prototype?
- 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.