test-driver/SCOPE.md
tegwick 7249c6a403 Register with State Hub, persist concept assessment, seed first workplan
- history/2026-08-22-concept-assessment-swot.md: SWOT assessment of the
  concept corpus with recommendations for the first workplan
- statehub register: infotech domain, TD-WP prefix, generated AGENTS.md,
  .custodian-brief.md and TD-WP-0001 bootstrap workplan
- .repo-classification.yaml: category research, domain infotech
- SCOPE.md rewritten with real repo boundaries
- TD-WP-0002: vertical spike reordering M0-M10 into one end-to-end thread
  that can falsify the crystallization thesis early
- commit previously untracked INTENT.md and docs/

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 1629012@bnt-lap001
Assistant-Session: 78d4fb13-8a1e-474b-87a3-9b9261c49a39
2026-08-22 22:40:39 +02:00

3.9 KiB
Raw Blame History

SCOPE

This file helps you quickly understand what this repository is about, when it is relevant, and when it is not.


One-liner

test-driver is a use-case-driven verification framework whose tests mature alongside the software they protect — fluid and agentic while behaviour is hot, deterministic once it cools.


Core Idea

A test is treated not as code but as a verification asset with identity, intent, evidence, lineage, maturity, temperature and energy. Use cases are the primary behavioural source; integration, journey, multi-user, security and resilience tests are projections of the same use case rather than separate suites.

Verification assets progress along a maturity continuum (T0 Exploratory → T5 Deterministic) called Crystallization. Agents may explore and realise semantic actions against unstable interfaces; oracles remain deterministic and independent from actors, so the framework can distinguish a legitimate mechanical change from a product defect rather than adapting to whatever the implementation happens to do.

Current state: research prototype. Concept corpus is complete (INTENT.md, docs/); implementation has not started. See history/2026-08-22-concept-assessment-swot.md for the standing assessment and the reasoning behind the current workplan sequence.


In Scope

  • The conceptual model: UseCase, Actor, Scenario, SemanticAction, Observation, Oracle, Verdict, VerificationAsset, Finding, Adaptation, Crystallization.
  • A deterministic semantic scenario kernel and its evidence format.
  • The test-driver lab — a small mutable application under test carrying labelled mechanical, semantic and defect mutations as ground truth.
  • Adaptation detection and the defect-vs-adaptation classifier.
  • Crystallization of agentic realisations into deterministic regression tests.
  • Security testing expressed as mutation of ordinary use cases.
  • Self-verification of the framework's own foundational guarantees.
  • The research control plane: hypotheses, experiments, findings, fitness map.

Out of Scope

  • Replacing unit-test frameworks, browser automation engines, or CI systems.
  • Building a load-testing, fuzzing, vulnerability-scanning or observability platform.
  • Test-management SaaS, distributed test clouds, or multi-tenant hosting.
  • Making all tests agentic, or using model judgment where a deterministic oracle is available.
  • Rewriting semantic requirements to match implementation behaviour.
  • Scale and performance verification before the conceptual model is proven.

Relevant When

  • You need the test-driver conceptual vocabulary or its canonical concept set.
  • You are working on the crystallization, adaptation-classification, or semantic-action binding mechanisms.
  • You are extending the lab or its mutation catalogue.
  • You need the framework's hypotheses, fitness scorecard, or evidence format.

Not Relevant When

  • You need ordinary unit or component tests for another repo — use that repo's own test stack.
  • You are looking for fleet coordination or cross-repo memory — that is State Hub.

Getting Oriented

  1. INTENT.md — purpose, thesis, design heuristics, non-goals.
  2. docs/TestDriverConceptModel.md — the canonical concept set v0.1.
  3. docs/TestDriverImprovementLoop.md — hypotheses, findings taxonomy, self-improvement cycle.
  4. docs/TestDriverInitialMilestones.md — M0M10 and the prototype success gate.
  5. history/2026-08-22-concept-assessment-swot.md — assessment and the reasons the first workplan reorders those milestones into a vertical spike.
  6. workplans/ — current work. Agent instructions: AGENTS.md.

Stack

Deliberately boring, per docs/TestDriverResearchPrototype.md: Python, pytest, Playwright, Pydantic/dataclasses, YAML, SQLite. One process, one database, one browser engine, one application under test. Novelty belongs in the verification model, not the infrastructure.