Assistant: codex Assistant-Model: gpt-6-astra Assistant-Session: 01a0e76f-be98-7ae3-965d-e0b31290a4c4
1.7 KiB
test-driver
Agentic framework for integration, end-to-end, multi-user interaction and security testing, driven by use cases.
Tests mature alongside the software they protect: fluid and agentic while
behaviour is changing, deterministic once it settles. See INTENT.md for the
thesis and SCOPE.md for boundaries.
Status: research prototype. Deterministic claims, heuristic discovery,
adaptation classification and crystallization run locally. Three synthetic
multi-user use cases and a 38-mutation catalogue exercise the model. Live-model
economics, browser-engine coverage and independent authoring-cost measurement
remain blocked in workplans/TD-WP-0003-generalise-and-settle.md.
See readiness and interface decisions.
Run
python3 -m pytest -q # the whole suite
python3 -m pytest -q tests/test_reference_scenario.py
No third-party dependencies. Python ≥ 3.11, pytest for the suite.
Layout
src/testdriver/ the kernel — intent, world, actions, drivers,
observers, oracles, evidence, runner
usecases/ durable test intent, including not-yet-runnable use cases
lab/ the system under test
scenarios/ reference scenarios
research/ hypotheses, experiments, findings, fitness map
docs/ concept model, improvement loop, milestones, design notes
history/ assessments and completed-work write-ups
Reading order
INTENT.md— the thesisdocs/TestDriverConceptModel.md— canonical concept setdocs/TestDriverClassificationDesign.md— why adaptation cannot normalize a defect, and where model judgment is and is not permitteddocs/TestDriverInitialMilestones.md— canonical milestones M0–M10