@misterhuydo/sentinel 1.0.96 → 1.0.97

package/.cairn/session.json

@@ -1,6 +1,6 @@
 {
-  "message": "Auto-checkpoint at 2026-03-23T07:31:47.535Z",
-  "checkpoint_at": "2026-03-23T07:31:47.537Z",
+  "message": "Auto-checkpoint at 2026-03-23T07:34:25.856Z",
+  "checkpoint_at": "2026-03-23T07:34:25.857Z",
   "active_files": [],
   "notes": [],
   "mtime_snapshot": {}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@misterhuydo/sentinel",
-  "version": "1.0.96",
+  "version": "1.0.97",
   "description": "Sentinel — Autonomous DevOps Agent installer and manager",
   "bin": {
     "sentinel": "./bin/sentinel.js"

package/python/sentinel/sentinel_boss.py

@@ -172,8 +172,12 @@ reply with a short summary grouped by category:
 Tone: direct, professional, like a senior engineer who owns the system.
 Don't pad responses. Don't say "Great question!" or "Certainly!".
 If you don't know something, use a tool to find out before saying you don't know.
-CRITICAL: Never narrate what you are about to do ("I'll check that now", "Stand by", "Requesting...").
-Just call the tool immediately and reply with the results. No pre-action commentary.
+
+When to act vs. when to ask:
+- Clear command ("check status", "fetch logs", "pause sentinel") → call the tool immediately, reply with results.
+- Ambiguous or exploratory ("what does get_repo_status do?", "tell me about search_logs") → explain the tool naturally, then ask: "Want me to run it?"
+- Unclear intent (could be either) → use judgment: brief explanation + "Want me to run this now?"
+Never say "Stand by" or "Requesting..." and then return nothing. Either act, or ask.
 
 When the engineer's request is fully handled, end your LAST message with the token: [DONE]
 IMPORTANT: Always write your actual reply text FIRST, then append [DONE] at the end. Example: "Hello! I'm Sentinel. [DONE]". Never output [DONE] as your only content.