History

wantsong 5d0286d8e4 feat: publish CCPE lite agents and migration gates		2026-06-03 11:47:41 +08:00
..
articles	feat: publish CCPE lite agents and migration gates	2026-06-03 11:47:41 +08:00
prompts	feat: publish CCPE lite agents and migration gates	2026-06-03 11:47:41 +08:00
reports	feat: publish CCPE lite agents and migration gates	2026-06-03 11:47:41 +08:00
results	feat: publish CCPE lite agents and migration gates	2026-06-03 11:47:41 +08:00
rubrics	feat: publish CCPE lite agents and migration gates	2026-06-03 11:47:41 +08:00
HANDOFF-COGNITIVE-IMAGING.md	feat: publish CCPE lite agents and migration gates	2026-06-03 11:47:41 +08:00
HANDOFF.md	feat: publish CCPE lite agents and migration gates	2026-06-03 11:47:41 +08:00
README.md	feat: publish CCPE lite agents and migration gates	2026-06-03 11:47:41 +08:00

README.md

Review Agent Regression Test Workspace

This workspace isolates regression testing for review-oriented CCPE artifacts.

Purpose

Evaluate whether migrated CCPE System Lite prompts preserve or improve the review quality of mature CCPE 2.0 prompts.

Primary question:

Should mature review agents be migrated by full CCPE System rewrite, or by original-kernel + minimal Lite wrapping?

Directory Layout

articles/
  User-provided full article texts for testing.

prompts/
  Prompt variants under test.

results/
  Raw model outputs from ChatGPT/Codex-side tests and Gemini-side tests.

rubrics/
  Evaluation rubric and scoring protocol.

reports/
  Final comparison reports.

Test Families

1. 巨人认知 / Giant Cognition
2. 认知显影 / Cognitive Imaging

Each family should test three prompt variants:

A. original-ccpe-2
B. ccpe-system-lite
C. original-kernel-minimal-lite

Each variant should be tested in two environments:

1. ChatGPT / Codex-side model
2. Gemini 3.1 Pro

Use a fresh thread or subthread for each test run to avoid context contamination.