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.
- package/.agents/skills/maestro-analyze/SKILL.md +78 -34
- package/.agents/skills/maestro-blueprint/SKILL.md +57 -24
- package/.agents/skills/maestro-brainstorm/SKILL.md +69 -34
- package/.agents/skills/maestro-execute/SKILL.md +45 -15
- package/.agents/skills/maestro-grill/SKILL.md +63 -38
- package/.agents/skills/maestro-init/SKILL.md +59 -17
- package/.agents/skills/maestro-milestone-audit/SKILL.md +48 -5
- package/.agents/skills/maestro-milestone-complete/SKILL.md +48 -6
- package/.agents/skills/maestro-milestone-release/SKILL.md +42 -11
- package/.agents/skills/maestro-plan/SKILL.md +19 -13
- package/.agents/skills/maestro-roadmap/SKILL.md +59 -29
- package/.agents/skills/maestro-verify/SKILL.md +46 -11
- package/.agents/skills/manage-codebase-rebuild/SKILL.md +4 -6
- package/.agents/skills/team-adversarial-swarm/scripts/__pycache__/pheromone.cpython-313.pyc +0 -0
- package/.agents/skills/team-adversarial-swarm/scripts/__pycache__/scoring.cpython-313.pyc +0 -0
- package/.agy/skills/maestro-analyze/SKILL.md +78 -34
- package/.agy/skills/maestro-blueprint/SKILL.md +57 -24
- package/.agy/skills/maestro-brainstorm/SKILL.md +69 -34
- package/.agy/skills/maestro-execute/SKILL.md +45 -15
- package/.agy/skills/maestro-grill/SKILL.md +63 -38
- package/.agy/skills/maestro-init/SKILL.md +59 -17
- package/.agy/skills/maestro-milestone-audit/SKILL.md +48 -5
- package/.agy/skills/maestro-milestone-complete/SKILL.md +48 -6
- package/.agy/skills/maestro-milestone-release/SKILL.md +42 -11
- package/.agy/skills/maestro-plan/SKILL.md +19 -13
- package/.agy/skills/maestro-roadmap/SKILL.md +59 -29
- package/.agy/skills/maestro-verify/SKILL.md +46 -11
- package/.agy/skills/manage-codebase-rebuild/SKILL.md +4 -6
- package/.agy/skills/team-adversarial-swarm/scripts/__pycache__/pheromone.cpython-313.pyc +0 -0
- package/.agy/skills/team-adversarial-swarm/scripts/__pycache__/scoring.cpython-313.pyc +0 -0
- package/.claude/commands/maestro-analyze.md +78 -34
- package/.claude/commands/maestro-blueprint.md +57 -24
- package/.claude/commands/maestro-brainstorm.md +69 -34
- package/.claude/commands/maestro-execute.md +45 -15
- package/.claude/commands/maestro-grill.md +63 -38
- package/.claude/commands/maestro-init.md +59 -17
- package/.claude/commands/maestro-milestone-audit.md +48 -5
- package/.claude/commands/maestro-milestone-complete.md +48 -6
- package/.claude/commands/maestro-milestone-release.md +42 -11
- package/.claude/commands/maestro-plan.md +19 -13
- package/.claude/commands/maestro-roadmap.md +59 -29
- package/.claude/commands/maestro-verify.md +46 -11
- package/.claude/commands/manage-codebase-rebuild.md +4 -6
- package/.claude/skills/team-adversarial-swarm/scripts/__pycache__/pheromone.cpython-313.pyc +0 -0
- package/.claude/skills/team-adversarial-swarm/scripts/__pycache__/scoring.cpython-313.pyc +0 -0
- package/.codex/skills/manage-codebase-rebuild/SKILL.md +2 -2
- package/dashboard/dist-server/dashboard/src/server/wiki/virtual-wiki-adapters.js +7 -7
- package/dashboard/dist-server/dashboard/src/server/wiki/virtual-wiki-adapters.js.map +1 -1
- package/dashboard/dist-server/dashboard/src/server/wiki/wiki-indexer.js +1 -1
- package/dashboard/dist-server/dashboard/src/server/wiki/wiki-indexer.js.map +1 -1
- package/package.json +1 -1
- package/workflows/codebase-rebuild.md +18 -107
- package/workflows/command-authoring.md +823 -0
- package/workflows/execute.md +6 -5
- package/workflows/interview-mechanics.md +7 -0
package/workflows/execute.md
CHANGED
|
@@ -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
|
|
299
|
-
|
|
300
|
-
|
|
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 ${fixedId}
|
|
306
|
-
|
|
307
|
-
|
|
307
|
+
Main flow post-dispatch: verify convergence criteria against file state
|
|
308
|
+
Main flow writes: .summaries/${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) |`
|