maestro-flow 0.4.22 → 0.4.24

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (55) hide show
  1. package/.agents/skills/maestro-analyze/SKILL.md +78 -34
  2. package/.agents/skills/maestro-blueprint/SKILL.md +57 -24
  3. package/.agents/skills/maestro-brainstorm/SKILL.md +69 -34
  4. package/.agents/skills/maestro-execute/SKILL.md +45 -15
  5. package/.agents/skills/maestro-grill/SKILL.md +63 -38
  6. package/.agents/skills/maestro-init/SKILL.md +59 -17
  7. package/.agents/skills/maestro-milestone-audit/SKILL.md +48 -5
  8. package/.agents/skills/maestro-milestone-complete/SKILL.md +48 -6
  9. package/.agents/skills/maestro-milestone-release/SKILL.md +42 -11
  10. package/.agents/skills/maestro-plan/SKILL.md +19 -13
  11. package/.agents/skills/maestro-roadmap/SKILL.md +59 -29
  12. package/.agents/skills/maestro-verify/SKILL.md +46 -11
  13. package/.agents/skills/manage-codebase-rebuild/SKILL.md +4 -6
  14. package/.agents/skills/team-adversarial-swarm/scripts/__pycache__/pheromone.cpython-313.pyc +0 -0
  15. package/.agents/skills/team-adversarial-swarm/scripts/__pycache__/scoring.cpython-313.pyc +0 -0
  16. package/.agy/skills/maestro-analyze/SKILL.md +78 -34
  17. package/.agy/skills/maestro-blueprint/SKILL.md +57 -24
  18. package/.agy/skills/maestro-brainstorm/SKILL.md +69 -34
  19. package/.agy/skills/maestro-execute/SKILL.md +45 -15
  20. package/.agy/skills/maestro-grill/SKILL.md +63 -38
  21. package/.agy/skills/maestro-init/SKILL.md +59 -17
  22. package/.agy/skills/maestro-milestone-audit/SKILL.md +48 -5
  23. package/.agy/skills/maestro-milestone-complete/SKILL.md +48 -6
  24. package/.agy/skills/maestro-milestone-release/SKILL.md +42 -11
  25. package/.agy/skills/maestro-plan/SKILL.md +19 -13
  26. package/.agy/skills/maestro-roadmap/SKILL.md +59 -29
  27. package/.agy/skills/maestro-verify/SKILL.md +46 -11
  28. package/.agy/skills/manage-codebase-rebuild/SKILL.md +4 -6
  29. package/.agy/skills/team-adversarial-swarm/scripts/__pycache__/pheromone.cpython-313.pyc +0 -0
  30. package/.agy/skills/team-adversarial-swarm/scripts/__pycache__/scoring.cpython-313.pyc +0 -0
  31. package/.claude/commands/maestro-analyze.md +78 -34
  32. package/.claude/commands/maestro-blueprint.md +57 -24
  33. package/.claude/commands/maestro-brainstorm.md +69 -34
  34. package/.claude/commands/maestro-execute.md +45 -15
  35. package/.claude/commands/maestro-grill.md +63 -38
  36. package/.claude/commands/maestro-init.md +59 -17
  37. package/.claude/commands/maestro-milestone-audit.md +48 -5
  38. package/.claude/commands/maestro-milestone-complete.md +48 -6
  39. package/.claude/commands/maestro-milestone-release.md +42 -11
  40. package/.claude/commands/maestro-plan.md +19 -13
  41. package/.claude/commands/maestro-roadmap.md +59 -29
  42. package/.claude/commands/maestro-verify.md +46 -11
  43. package/.claude/commands/manage-codebase-rebuild.md +4 -6
  44. package/.claude/skills/team-adversarial-swarm/scripts/__pycache__/pheromone.cpython-313.pyc +0 -0
  45. package/.claude/skills/team-adversarial-swarm/scripts/__pycache__/scoring.cpython-313.pyc +0 -0
  46. package/.codex/skills/manage-codebase-rebuild/SKILL.md +2 -2
  47. package/dashboard/dist-server/dashboard/src/server/wiki/virtual-wiki-adapters.js +7 -7
  48. package/dashboard/dist-server/dashboard/src/server/wiki/virtual-wiki-adapters.js.map +1 -1
  49. package/dashboard/dist-server/dashboard/src/server/wiki/wiki-indexer.js +1 -1
  50. package/dashboard/dist-server/dashboard/src/server/wiki/wiki-indexer.js.map +1 -1
  51. package/package.json +1 -1
  52. package/workflows/codebase-rebuild.md +18 -107
  53. package/workflows/command-authoring.md +823 -0
  54. package/workflows/execute.md +6 -5
  55. package/workflows/interview-mechanics.md +7 -0
@@ -295,16 +295,17 @@ For each wave in execution_queue (sequential):
295
295
  IF executor == "agent":
296
296
  Spawn workflow-executor agent (fresh 200k context) with:
297
297
  task definition, phase context, prior wave summaries, specs_content, context.md, analysis.md
298
- Agent: implement task verify convergence → auto-fix (max 3) → checkpoint if blocked
299
- On success: atomic commit (if auto-commit), write .summaries/${task_id}-summary.md
300
- Update .task/${task_id}.json: status = "completed" | "blocked"
298
+ Agent internally handles full lifecycle:
299
+ implement verify convergence auto-fix (max 3) → commit → write .summaries/${task_id}-summary.md → update .task/${task_id}.json status
300
+ (checkpoint if blocked)
301
+ Main flow: verify agent wrote summary + updated status, collect result
301
302
 
302
303
  ELSE (CLI path via maestro delegate):
303
304
  fixedId = "${PHASE_NUM || 'scratch'}-${PHASE_SLUG}-${task_id}"
304
305
  Store fixedId in index.json.execution.delegate_ids[task_id]
305
306
  Dispatch: maestro delegate "${prompt}" --to ${executor} --mode write --id ${fixedId}
306
- Post-dispatch: verify convergence criteria against file state
307
- Write summary, update task status, auto-commit if enabled
307
+ Main flow post-dispatch: verify convergence criteria against file state
308
+ Main flow writes: .summaries/${task_id}-summary.md, update .task/${task_id}.json status, auto-commit if enabled
308
309
 
309
310
  Collect result: { task_id, status, executor, summary_path, commit_hash, delegate_id }
310
311
  Clear state.json.current_task_id
@@ -0,0 +1,7 @@
1
+ # Interview Interaction Mechanics
2
+
3
+ - **One decision per turn** via AskUserQuestion, 2-4 options, first marked `(Recommended)`. User can redirect via `Other`.
4
+ - **Search-first**: resolve via state.json → session artifacts → `maestro spec/wiki` → Glob/Grep/Read → Agent(Explore) / delegate. Never ask what code can answer.
5
+ - **Writeback**: each decision **immediately written to disk** before the next question. No batching.
6
+ - **Skip**: auto mode (`-y`), resume (`-c`), or unambiguous input → skip entire interview.
7
+ - **Decision table**: `| # | Decision | Choice | Source (user / code / default) |`