DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to measure your own session with the graded metrics script with DSH Routing Suite

Run the measurement script on a session log to get numeric metrics without exposing the session content.

Who it is forA developer or researcher who wants to check how a long agent session behaved and compare it with the published figures.

The problemJudging long-session attention drop or protocol effects by reading raw logs is slow, and sharing the raw log can expose private content.

The outcomeA list of computed metrics for the session, printed as numbers only, that can be compared with the published tables in DATA.md.

What you need first

  • DSH CLI installed, version >=0.1.0-rc.6 (the README lists this as the DSH target; DSH is in developer preview with possible breaking changes)
  • PowerShell for the README install commands (install.ps1 and the Copy-Item steps)
  • git, to clone the repository for the manual install path
  • Node.js, to run graded/scripts/measure.mjs (inferred from the node command in the README)

Steps

  1. Clone the repository and open the graded folder.
  2. Export your session to a .jsonl file.
  3. Run node scripts/measure.mjs 你的会话.jsonl from the graded folder, replacing the file name with your session file.
  4. Compare the printed numbers with the tables in graded/docs/DATA.md.

Prompt for your agent

In the repository yjh051108/dsh-routing-suite, go to the graded folder and run `node scripts/measure.mjs <session-file>.jsonl` on the session file <session-file>.jsonl. Return only the numeric output. Verify that the output contains numbers only and no session text.

Caveat. The script needs a session log in .jsonl format, and the README does not say how to export one from DSH, so you must find that step yourself.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page