Skip to content

fix(entry-skills): every handoff arm says to invoke the skill#552

Merged
leeovery merged 1 commit into
mainfrom
fix/spec-entry-bugfix-invoke
Jul 27, 2026
Merged

fix(entry-skills): every handoff arm says to invoke the skill#552
leeovery merged 1 commit into
mainfrom
fix/spec-entry-bugfix-invoke

Conversation

@leeovery

@leeovery leeovery commented Jul 26, 2026

Copy link
Copy Markdown
Owner

Summary

  • A prose-test walker on the bugfix path recorded a DEVIATION: the arm hands over a fenced block of arguments and never says what to do with it — no invocation directive, and no directive to emit it either. Reproduced identically on both independent walks, against the already-fixed fences, so it isn't a rendering artefact.
  • Enumerating before fixing turned one arm into four, across three files:
file arm
workflow-specification-entry #### If work_type is bugfix
workflow-specification-entry #### If work_type is cross-cutting
workflow-investigation-entry #### If source is continue
workflow-planning-entry #### If continuing or reviewing existing plan
  • In every case a sibling arm in the same file carries the sentence and these don't. discussion-entry and research-entry carry it on every arm — the same proof structure that settled the fence bug: two files doing it correctly means the others are omissions, not house style.

Test plan

🤖 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 👈 current
  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
  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

This was referenced Jul 26, 2026
@leeovery
leeovery force-pushed the docs/contributing branch from 52f416f to bf2c67f Compare July 27, 2026 14:32
@leeovery
leeovery force-pushed the fix/spec-entry-bugfix-invoke branch from d7c7000 to 463421f Compare July 27, 2026 14:32
@leeovery
leeovery force-pushed the docs/contributing branch from bf2c67f to f051286 Compare July 27, 2026 14:34
@leeovery
leeovery force-pushed the fix/spec-entry-bugfix-invoke branch from 463421f to 1f0b42d Compare July 27, 2026 14:34
@leeovery
leeovery force-pushed the docs/contributing branch from f051286 to 3b02bab Compare July 27, 2026 14:37
@leeovery
leeovery force-pushed the fix/spec-entry-bugfix-invoke branch from 1f0b42d to 9cb8ef4 Compare July 27, 2026 14:37
@leeovery
leeovery force-pushed the docs/contributing branch from 3b02bab to c4da5c4 Compare July 27, 2026 14:39
@leeovery
leeovery force-pushed the fix/spec-entry-bugfix-invoke branch from 9cb8ef4 to 30714f1 Compare July 27, 2026 14:39
@leeovery
leeovery force-pushed the docs/contributing branch from c4da5c4 to 78dc5f1 Compare July 27, 2026 14:41
@leeovery
leeovery force-pushed the fix/spec-entry-bugfix-invoke branch from 30714f1 to 4324479 Compare July 27, 2026 14:41
@leeovery
leeovery force-pushed the docs/contributing branch from 78dc5f1 to 7c1dd40 Compare July 27, 2026 14:43
@leeovery
leeovery force-pushed the fix/spec-entry-bugfix-invoke branch from 4324479 to 74dccf4 Compare July 27, 2026 14:43
@leeovery
leeovery changed the base branch from docs/contributing to main July 27, 2026 14:45
Found by a prose-test walker on the bugfix path: the arm hands over a
fenced block of arguments and never says what to do with it — no
invocation directive, and no directive to emit it either. Reproduced on
both independent walks against the already-fixed fences, so it is not a
rendering artefact.

Enumerating before fixing turned one arm into four, across three files:
specification-entry's `bugfix` and `cross-cutting`, investigation-entry's
`continue`, and planning-entry's `continuing or reviewing`. In each case
a sibling arm in the same file carries the sentence and these do not.
discussion-entry and research-entry carry it on every arm, which is what
shows this is an omission rather than a house style — the same proof
that settled the fences.

Additions only; the fences were re-verified intact afterwards.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
@leeovery
leeovery force-pushed the fix/spec-entry-bugfix-invoke branch from 74dccf4 to 2bc520f Compare July 27, 2026 14:45
@leeovery
leeovery merged commit eec6723 into main Jul 27, 2026
@leeovery
leeovery deleted the fix/spec-entry-bugfix-invoke branch July 27, 2026 17:24
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant