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

How to review the stages of a recorded DSH session by turn with DSH Jev Plugin

Classifies complete recorded model steps on request and links stages to their original trajectory evidence.

Credentials. Tool arguments are sent for classification only after credential redaction, and incomplete argument JSON is replaced with a marker, so check the input shown on the page before relying on it.

Who it is forA developer reviewing a past DSH session who wants to see which stage each step belonged to, such as exploration or editing.

The problemA long recorded session is hard to scan step by step, and it is unclear where each phase of the work began and ended.

The outcomeCompleted turns get stage labels with confidence values and links to the original steps, while the session records stay unchanged.

What you need first

  • A supported DeepSeek Harness release: 0.1.7-rc.1, 0.1.7-rc.2, 0.2.0-rc.1, 0.2.0-rc.2, 0.2.1-alpha.2 or 0.2.1-alpha.3
  • A saved Jev or Luna Decisions connection, with OpenRouter or OpenAI for Luna, and its request address and credential reference
  • The plugin package file added to a DSH profile through the Web UI install steps in the README

Steps

  1. Follow the Install through the Web UI section to add the plugin to a jev profile, then run dsh --profile jev.
  2. Open Jev, then Settings and features, and turn on the Stage navigation switch.
  3. Open the Stage navigation tab in the Web client, which follows Trajectory.
  4. Select a completed turn, or request the session's unanalyzed completed turns, and review the classification input and answer shown on the page.

Prompt for your agent

Using the repo luobosibing2/dsh-jev-plugin, turn on Stage navigation in a DSH profile named jev, then classify the completed turns of the session <target session id>. Report the stage labels per turn and confirm the original session records are unchanged. Verify that tool arguments shown in the classification input are redacted.

Caveat. Stage labels and confidence values do not establish tool success or classification accuracy.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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