Profa 71dd5bb87e docs: add v3.7.14 QE fleet reports from 3 models + cross-model analysis ...

QE fleet reports generated using Claude Opus 4.6 (11 reports), GLM-5 (9 reports),
and Qwen 3.5 (9 reports) analyzing the same codebase. Includes a cross-model
analysis with devils-advocate verification of claims against actual codebase.

Key finding: model choice fundamentally determines report reliability, with
factual accuracy ranging from 88% (Opus) to 25% (Qwen). Qwen fabricated
27 CRITICAL vulnerabilities by confusing SQLite db.exec() with child_process.exec().

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-09 10:14:08 +00:00

..

agents

feat(edge): Phase 4 P2P integration with Edge Server

2026-01-03 13:06:48 +00:00

config

feat(goap): Phase 3 Task Orchestration + backup system after data loss

2025-12-29 19:20:15 +00:00

docs

feat(goap): Phase 3 Task Orchestration + backup system after data loss

2025-12-29 19:20:15 +00:00

workers

feat(test-generation): implement multi-language generators and infrastructure

2026-03-05 12:00:54 +00:00

aqe.rvf.manifest.json

docs: add v3.7.14 QE fleet reports from 3 models + cross-model analysis

2026-03-09 10:14:08 +00:00

claude-flow-integration.json

chore: update generated init artifacts and add v3 helper templates

2026-02-13 15:27:01 +00:00

config.yaml

feat(test-generation): implement multi-language generators and infrastructure

2026-03-05 12:00:54 +00:00

learning-config.json

feat(goap): Phase 3 Task Orchestration + backup system after data loss

2025-12-29 19:20:15 +00:00

start-learning.js

chore: remove all brand-specific (Audi) references from codebase

2025-12-14 13:19:18 +00:00