Summary

• Exercises the conversation stub — designed at length, never used. Writing the case proved the mechanism needed no change: a stub is named content, the case owns the trigger, and "once the discussion file has been created from the template, the map seeded, and the initialisation commit made" is as observable a moment as an engine dispatch. The stub writes the worked discussion and settles the map, then the walk resumes.
• Adds a third shape of end state, which the case forced. A discussion's subtopics are derived by the model from available context — "Derive initial subtopics from whatever context is available" — so their names and number differ run to run and no recipe can pin the resulting world. Such cases now set "world": "claims" in case.json: the delta is taken against the fixture, expected non-empty, and judged against the case's stated claims.
• It is deliberately the weakest of the three shapes and documented as a last resort — validation refuses claims alongside an assertion-state.cjs, because a world a recipe can build must be built.

The case itself walks initialisation for real: resume detection on a missing file, topic start before any map command (the map requires the item to exist), the file from the template with Triage seeded (none), subtopics recorded pending, the commit — then substitutes the session and stops at the review boundary without dispatching anything.

Test plan

• npm test green: 1699 tests, 0 fail. Corpus: 13 cases, 2 stubs, valid.
• Fixture snapshot built and byte-deterministic.
• Not yet walked by an agent — that's the next run, and it's the first real test of the mid-flow substitution.

🤖 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
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 👈 current
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
28. fix(prose-tests): keep the walk's closing turn, and name the one live difference #572
29. fix(prose-tests): prescribe the cross-check, drop a check that cannot fire, lint the scope #573
30. test(prose): declare the prose each case actually walks #574
31. fix(investigation): the symptom interview never ran for work shaped in discovery #575
32. feat(prose-tests): conduct — playing a person where a script cannot reach #576
33. fix(prose-tests): what a write put in a file is evidence, not incident #577
34. fix(investigation): the interview starts from the carrier, not over it #578
35. test(prose): quick-fix scoping, the whole definition stage in one walk #579
36. fix(prose-tests): the world log is the walker's record #580
37. fix(prose-tests): a confirmed failure reports both runs' checks #581
38. fix(prose-tests): each prescribed command runs as written #582
39. fix(scoping): context gathering reads the whole carrier, asks only the gaps #583