A unified framework bridging Behavior-Driven Development & Model-Based Testing through PAP synthesis and LLM-driven coverage gap detection
Automatically derives a GraphWalker-compatible state-machine model from any Gherkin corpus. Zero manual model authoring.
37 production scenarios, 4 feature files, 4 quantitative metrics: SSRR, ERR, MC, GIA — on a live Next.js web application.
LLM analyzes the synthesized model and execution history to propose missing transitions as structured EdgeProposal records.
| Guard source | Example tag/pattern | Inferred guard |
|---|---|---|
| Cucumber tag | @requires-account | isLoggedIn |
| Cucumber tag | @live-write | canWrite |
| Negative-path detection | invalid / fail / error in title | !isValid |
_X_v_ prefixe_ prefixGherkin .feature files → PAP Parser → BddToMbtSynthesizer → GraphWalker JSON model → AI coverage loop (MbtCoverageAdvisor + EdgeProposal) → Step Def Generator → BDD Runner → Test Reports
Run against system under test; record per-edge execution history
Traversal count, failure count, failure category per edge
Submit model JSON + history → Claude / GPT-4o / Ollama
Validate JSON schema; filter by confidence threshold (≥ 0.7)
Provenance tag: source="AI", proposalRound=N; loop until convergence