feat(prose-tests): the mid-flow substitution, and a world only prose can describe

[leeovery]

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