Will my contributors secrets be sent to the model?

Layer 1 scans with nine regexes for tokens and keys and replaces values with [REDACTED:kind] before anything leaves the machine, because probably-not-a-secret is not good enough.

Can a confident model label security or write on its own?

No. A model never authorises its own writes, security sits in a never_auto set for human decision, and writes need --apply with a token, budget, and repo allowlist.

How do I know the confidence gates mean anything?

Run ghtriage eval against frozen sets; it reports calibration gap, selective coverage vs accuracy, macro-F1, and latency plus cost per thousand, failing CI on regression.

Why does it ask eight questions if I only need type?

The eighth costs input tokens but almost no extra latency in one parallel call, so mildly useful signals like duplicate_ish or good_first_issue come nearly free.

How do I install and run the triage tool?

Create a virtual environment, run pip install -e ".[dev]", and copy .env.example to .env with your TYPESAFE_API_KEY. That installs a ghtriage console script, and everything also works as python -m ghtriage.

What does this cost and how is it deployed?

Fractions of a cent per thousand issues and about two model calls per issue, deployed as a GitHub Action on the issues: [opened] trigger, so there is no server and no polling.

Why does the eval suite gate on ECE and selective prediction?

ECE is the size-weighted gap between stated confidence and observed accuracy, so it says whether a confidence gate means anything at all, and selective prediction shows the coverage you buy by letting the system refuse to answer.

CommunityJev Tools & CLIs

GitHub-Issue-Classification-Using-Jev

GitHub Action triage that asks eight Jev questions in one call, gates labels in plain Python, and layers regex redaction, a Jev guard battery, and a write guard.

See highlights

Open github.com

Stars: 0
Language: Python
License: MIT
Published by: Community
Author: KalyanM45
Last verified: Oct 2026

KalyanM45/GitHub-Issue-Classification-Using-Jev

User repository on GitHub

View on GitHub

This repository contains a GitHub issue classifier built on Jev, TypeSafe AI's System One model. It labels every new issue with typed values and calibrated confidence in milliseconds, labelling what it is sure about and escalating what it is not. Three guardrail layers guard every write, and a frozen eval suite gates each deploy.

Forks: 0
Last pushed: Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.

About this project

Automatic GitHub issue triage built on Jev, TypeSafe AI's System One model. Jev is not an LLM and writes no text: it returns typed values with calibrated probabilities, in 70–500 ms, at $0.042 per million input tokens with output free. An issue opens and, before you have finished reading the title:

Quoted from the project's README. Read the full README.

Tagscommunity github

Works forJev for Evaluation Jev for Classification

Used inJev for Software & DevTools

Languages: Python

Highlights

Eight questions in one system_one call: type, area, severity score, plus five noul probabilities.
Policy gates on numbers in code, withholding low-confidence labels and never auto-labeling duplicates.
Layer 1 redacts nine secret patterns locally before anything leaves the machine; layer 3 caps writes.
Frozen triage and red-team sets score accuracy, calibration, selective coverage, latency, and cost.

Watch out

Writing is off by default and security labels need a human; absolute floors are placeholders until a real baseline run. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

jev-seo

547

Live SEO audit that crawls a site from one homepage URL, checks 52 rules tied to Google Search Central, and asks Jev typed questions about every page to rank fixes.

Jev Tools & CLIs#community#jevbest#catalog-import

Community

AgriciDaniel/jev-seoPython

SmartMoney-Cub

Local-first trading journal and review harness that is read-only over markets, captures runs into frozen envelopes and evidence packs, and requires explicit human promotion before any rule returns.

Jev Tools & CLIs#community#jevbest#catalog-import

Community

myc0576/SmartMoney-CubPython

jevclip

Video tool where Jev scores subtitle segments and code assembles a short highlights cut plus a de-watered full cut with timestamped summaries.

Jev Tools & CLIs#community#jevbest#catalog-import

Community

cclank/jevclipPython

jev-yaba-wechat

macOS floating WeChat companion that reads the visible chat with on-device Vision OCR, judges intent and reply risk with Jev, drafts toned replies with GPT, and only fills text after you approve it.

Jev Tools & CLIs#community#jevbest#catalog-import

Community

wuxie888/jev-yaba-wechatPython

lejudge-jev-jepa

English-programmable cost module for JEPA PushT planning: linear probes verbalize imagined latents and Jev judges each constraint step, folded into CEM cost with memoised step facts.

Jev Tools & CLIs#community#awesomejev#catalog-import

Community

AbdelStark/lejudge-jev-jepaPython

jev-dimabsa

Research code that tackles dimensional sentiment scoring with Jev typed Score, Choice, and Noul calls plus small corpus statistics, without generation, fine-tuning, or GPU.

Jev Tools & CLIs#community#awesomejev#catalog-import

Community

ZhangYiqun018/jev-dimabsaPython

From the Jev guides

Original write-ups on what this entry is for.

Jev on the Gateways: Vercel, Workers AI, and OpenRouter

Oct 12, 2026

The request shape barely changes across surfaces; the surrounding contract does. When to call the API directly and when a gateway, a Worker binding, or a router entry earns its extra hop.

Jev Tools & CLIs#gateway#vercel#cloudflare

Read article

Exporting Decision Models: GGUF, ONNX, and Device Runtimes

Oct 10, 2026

Taking a decision checkpoint out of Python: what the GGUF and browser WebGPU exports preserve, what they change, and the parity evidence the model cards publish.

Jev Tools & CLIs#open-models#local#onnx

Read article

Records at Rest: Documents, Inboxes, and Risk Queues

Sep 28, 2026

Jev labels a record that already exists. Code moves, flags, or holds it. How the document, mail, and transfer tools keep the action out of the model.

Jev Tools & CLIs#classification#email#security

Read article

Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai