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

How to gate agent merges on test output probability with Agent Jev

Ask AgentJev whether a test run passed and block the merge when the probability is too low.

Who it is forA developer running a coding agent that opens pull requests, where a wrong green test result would let broken code move forward.

The problemAgents often read a test summary and declare success too early, and parsing a language model's free-text answer is fragile.

The outcomeA probability that the tests passed, returned without decoded text, which the agent loop can threshold before it continues.

What you need first

  • Python with PyTorch and Transformers installed (the README benchmarks used PyTorch 2.9.1+cu128 and Transformers 4.57.6)
  • A GPU; the README timings were measured on one RTX 5060 with 8 GB
  • Git access to clone malevrigns/agent-jev and download weights from the linked Hugging Face model repository
  • A state to evaluate, such as a test runner summary, plus questions you have already phrased as boolean, choice, or score

Steps

  1. Clone the repository with git clone https://github.com/malevrigns/agent-jev and enter the folder. (inferred, check the README)
  2. Fetch the coding-gates candidate weights with python fetch_v1_weights.py --variant coding-gates.
  3. Start the server with python -m jev_service.server --checkpoint models/agentjev-coding-gates/model.safetensors --model-path models/agentjev-coding-gates --temperatures models/agentjev-coding-gates/temperatures.json --port 8149. (inferred, check the README)
  4. Send the captured test output as the state and the boolean question 'Did the tests pass?' to http://localhost:8149 using the request format in the repository's HTTP section. (inferred, check the README)
  5. Block the merge when the returned probability of true is below your chosen threshold, and log the probability with the run.

Prompt for your agent

In the agent-jev repository at <repo-path>, start the coding-gates server on port 8149, send the test output in <log-file> with the boolean question 'Did the tests pass?', and return the probability of true. Verify the response by sending a log from a known failing run and confirming the probability is low.

Caveat. The README says the v1 default calls 123 of 348 failing test cases green, so use the probability as one gate and check the candidate's stated weaknesses, such as passing go test runs that print no test files.

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