@sulhadin/orchestrator 1.15.9 → 1.15.11

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/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@sulhadin/orchestrator",
3
- "version": "1.15.9",
3
+ "version": "1.15.11",
4
4
  "description": "AI Team Orchestration System — multi-role coordination for Claude Code",
5
5
  "bin": {
6
6
  "orchestrator": "bin/index.js"
@@ -27,8 +27,9 @@ When the user types `#start` or `#start --auto`:
27
27
  - When switching roles between phases: read the new role file, previous role context is no longer needed
28
28
  - Also read `.orchestra/knowledge.md` once at milestone start (if it exists)
29
29
  4. Scan `.orchestra/milestones/` for work — **you MUST list ALL directories** using `ls` or glob:
30
- - Run `ls .orchestra/milestones/` to get every milestone directory (do NOT rely on memory)
31
- - Read `milestone.md` in EACH directory to check its `Status` field
30
+ - Use the Glob tool with pattern `.orchestra/milestones/*/milestone.md` to find all milestones
31
+ - Read each `milestone.md` file individually using the Read tool to check its `Status` field
32
+ - Do NOT use complex bash for-loops or grep chains — use the dedicated Read/Glob tools
32
33
  - Find milestones with `status: in-progress` → resume from last incomplete phase
33
34
  - If none in-progress, find milestones with `status: planning` → start from the beginning
34
35
  - Only if ALL milestones are `status: done`, report: "✅ All milestones complete. Waiting for new work from PM."