test(prose): quick-fix scoping, the whole definition stage in one walk

[leeovery]

Summary

Quick-fix was the only work type with no coverage anywhere. This walks its entire definition stage — entry, context, complexity, specification, format, tasks, conclusion — stopping at the bridge handoff. The first case to take a phase from its opening argument to its completion render.

• Spine: a seven-element ordering chain across the pass — status check → spec start → spec complete → plan start → plan complete → scoping complete → completion render.
• conduct carries every user interaction, including the format menu, as a disposition of the described person — and the choice is made a fact by an invariant on project.defaults.plan_format local-markdown, not trusted to roleplay.
• The carrier deliberately lacks the "where" so gather-context's questioning arm is the only honest reading of its judgement-shaped guard — that's what keeps the case deterministic.
• New mainlines/quickfix.cjs (init + create, mirroring the feature mainline).

First run: FAIL, correctly — four findings

1. Confirmed prose defect (both walks): gather-context re-asks the what/why the carrier answers — guard blind to the session log's Exploration, question block a static fence. Fixed four PRs up.
2. The confirmation walk skipped prescribed registration calls while converging on a passing world — caught by calls_include, the exact hazard it exists for. Walker rule fixed three PRs up.
3. Orchestrator reported one run's checks for both. Fixed two PRs up.
4. Orchestrator's own commands leaked into the walker's action log. Fixed one PR up.

Test plan

• Corpus valid at 13; snapshot byte-deterministic; gates green
• Full verification is the re-run above the stack, post-reload

🤖 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
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 👈 current
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