dsh-research-report
Verifiable research-report engine for DeepSeek Harness: content-addressed evidence ledger (claim-snapshot binding, tamper-evident) plus versioned sealed reports with per-claim verification verdicts and a manifest-sealed directory.
Runssource: GitHubhomepageTypeScriptApache-2.0commit baa17487745e
TypeScript, Apache-2.0 licensed. The project labels itself: ai agent, ai agents, audit, citation verification, cordis, deepseek harness, developer tools and dsh.
dsh-research-report runs. An Argusic agent installed it in 3 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
dsh-research-report v0.3.21 is fully built, typechecked, and tested: 111/111 tests passing across 16 test files, all CI verification scripts green, and the CLI binary responds to --help.
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 100 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.
- System Node.js v18.19.1 below project minimum Node ^22.19.0 || >=24.0.0; pnpm not installed2 minutes
- Install time
- 3 minutes
- Cold machine to finish
- 2 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- pnpm test (vitest) exited 0: 111 passed across 16 test files; pnpm run typecheck passed; pnpm run build succeeded; pnpm run verify:self-contained, verify:artifacts, verify:frozen-contract, check:lockfile, and check-readme-sync all passed; lib/cli.js --help prints usage
- Model tokens used
- 45,330
- Exact commit tested
- baa17487745e
- 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.
Everything works perfectly. Let me verify the `pnpm run build && pnpm run verify:self-contained && … exec /bin/sh -lc 'export NVM_DIR="$HOME/.nvm"; [ -s "$NVM_DIR/nvm.sh" ] && '"\\. \""'$NVM_DIR/nvm.sh"; c… succeeded in 1063ms: $ node scripts/check-lockfile-drift.mjs Already up to date Done in 486ms using pnpm v11.7.0 lockfile ok: package.json and pnpm-lock.yaml agree Now I have all the data I need for the final report. tokens used 45,330 Now I have all the data I need for the 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 3 minutes, faster than the median of the 83 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.
- Ran without a GPU, so it does not need one to start.
- Licensed Apache-2.0, as reported by its host.
What did not, or is not known
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 84 ai-agent projects Argusic has installed and timed, dsh-research-report was the 32nd fastest to reach a running state, and 58 of 84 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 3 minutes after the clone.
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
Topics (from GitHub)
ai-agentai-agentsauditcitation-verificationcordisdeepseek-harnessdeveloper-toolsdshdsh-pluginevidence-ledgerresearchverifiable-reportworkflow-automation
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/dsh-research-report)Questions
- Does dsh-research-report run?
- Yes. dsh-research-report runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test dsh-research-report?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit baa17487745e. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test dsh-research-report?
- The run that produced this verdict cost $0.01: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does dsh-research-report 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 dsh-research-report need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing dsh-research-report?
- 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-research-report compare with the alternatives?
- Of the 84 ai-agent projects Argusic has installed and timed, dsh-research-report was the 32nd fastest to reach a running state, and 58 of 84 reached one at all.
- Where is the evidence for dsh-research-report?
- 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.