Jordan-Hall / Jordan-Hall/browser

[TASK][PROGRAMME.T06] Establish continuous evaluation and release evidence

Open
#116 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
No language data
Stars
0
Forks
0
PR merge metrics
No merged PRs in 30d

Description

Parent: #1

Task ID: `PROGRAMME.T06`

## Proposed implementation
Build EVAL-01 fixtures, blocking security/recovery checks, model/provider version pinning and the anti-wrapper continuity suite. Define evidence artifacts linked to issue/task IDs.

## Done when
CI/evaluation architecture and release evidence schema are reviewable, and verified outcomes are determined independently of agent self-report.

## Guardrail
A high aggregate task score cannot override a failed permission, duplication or privacy invariant.

## Prerequisites
`PROGRAMME.T02`, `PROGRAMME.T03`

Review: pending · Implementation: not started.

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by reading prerequisites PROGRAMME.T02 and PROGRAMME.T03, then review the parent task #1 and the proposed EVAL-01, security/recovery, version-pinning, continuity, and evidence requirements. Done means the CI/evaluation architecture and release evidence schema are reviewable, with outcomes independently verified and permission, duplication, and privacy invariants enforced.

Written by the indexing model from the issue text.

Assessment

Domain
ci-cd, release, security, testing-qa
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Active
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.