Summary

• The deterministic layer of the prose-test framework (stage 2 of design/prose-tests.md): case parser + corpus validation (tests/prose/lib/cases.cjs), fixture recipes run under a frozen-clock preload with committed golden snapshots (lib/fixtures.cjs, lib/fake-clock.cjs), the world builder (lib/world.cjs — installed-layout skills, hermetic git, keyword-only knowledge store re-derived at materialise), and the runner CLI (run.cjs: list · select · world · prompt · grade · snap · verify · destroy).
• P4 enforced structurally: walker prompts are machine-assembled by run.cjs prompt and never contain expect: claims; grade runs state assertions deterministically via the world's own engine and emits routing claims for the grader agent only.
• Two token-free CI suites join npm test: corpus validation (parse, scoped paths, anchors, assertion grammar) and fixture golden checks (every snapshot rebuilds byte-identical from its recipe — drift lands as a reviewable snapshot diff, never silently). Plus the /prose-test dev skill (Sonnet walks, Opus confirms failures, quoted evidence required) and the base fixture with two smoke cases.

Test plan

• npm test green (1683 tests, includes both new suites; base fixture rebuild ~2.9s).
• Determinism proven: node tests/prose/run.cjs verify run twice, byte-identical both times.
• Full pipe executed live: world built, engine boot run in-world (knowledge ready, zero migrations), deterministic grade passed, walker prompt verified expect-free, world destroyed.

🤖 Generated with Claude Code

Stack

1. docs(design): prose-tests programme design log #544
2. feat(prose-tests): the framework — cases, worlds, runner, skill #545 👈 current
3. test(prose): feature happy-path corpus — five worlds, seven cases #546
4. test(prose): bugfix corpus — the investigation-centric surfaces #548
5. test: retry recursive teardown removals — kill a class of phantom failures #549
6. fix(entry-skills): close the handoff fences — six files render their arms wrong #550
7. docs: a contributing page for working on the system #551
8. fix(entry-skills): every handoff arm says to invoke the skill #552
9. fix(implementation): environment setup belongs to the setup reference alone #553
10. fix(prose-tests): the asserter is told which substitutions were armed #554
11. feat(prose-tests): the mid-flow substitution, and a world only prose can describe #555
12. test(prose): claims assert consequences, not what was displayed #556
13. feat(prose-tests): record everything the agents do, results included #557
14. fix(discussion-entry): the handoff reports the source it actually had #558
15. fix(prose-tests): the stop hook records, and names the model that walked #559
16. fix(prose-tests): command output was never actually recorded #560
17. feat(prose-tests): judge the walk as told, not the summary returned #561
18. feat(prose-tests): decide in code what an agent should not be deciding #562
19. test(prose): a case starts where a session starts #563
20. feat(prose-tests): walk on Sonnet, judge on Opus, escalate a failure #564
21. test(prose): give the eight read-only cases something that can fail #565
22. test(prose): only walks that can be observed, and checks that survive the trip #566
23. fix(prose-tests): the verdict names only the model the record names #567
24. test(prose): discovery, walked to the point where work first exists #568
25. fix(prose-tests): the asserter judges which of prose or walker was at fault #569
26. docs(conventions): a step whose reference routes every exit still signposts #570
27. test(prose): discovery's epic arm, to the same durability boundary #571