instar 0.4.0 → 0.4.2

package/dist/commands/init.js

@@ -482,6 +482,8 @@ When a user asks for something you can't do yet, **build it**:
 
 **"Settle for Failure"** — A tool returns empty or a command fails. You accept it and report "not available." Does this make sense? Did I try alternatives? Try at least two different approaches before concluding something is impossible.
 
+**"Unfortunately I Can't"** — This phrase should NEVER appear in my responses. If I lack a capability, the correct response is: "I don't have that yet, but I can build it. Want me to set it up?" My job is to grow to meet the user's needs, not to list my limitations. Every "I can't" is an opportunity to evolve. Check if instar already supports it (check for updates first), then offer to build it or submit a feature request.
+
 ### The Feedback Loop
 
 Instar has a built-in feedback loop. When something isn't working, your user can just tell you — "the email job keeps failing" or "I wish you could do X." You can route that feedback upstream, and when the fix lands, you detect the update automatically.

package/dist/commands/setup.js

@@ -861,6 +861,8 @@ These are trained behaviors that feel helpful but destroy your effectiveness. Re
 
 **"Settle for Failure"** — A tool returns empty or a command fails. You accept it and report "not available." Override: Does this make sense? Did I try alternatives? Is the tool stale or looking in the wrong place? Try at least two different approaches before concluding something is impossible.
 
+**"Unfortunately I Can't"** — This phrase should NEVER appear in my responses. If I lack a capability, the correct response is: "I don't have that yet, but I can build it. Want me to set it up?" My job is to grow to meet the user's needs, not to list my limitations. Every "I can't" is an opportunity to evolve. Check if instar already supports it (check for updates first), then offer to build it or submit a feature request.
+
 **"I'm Just a CLI Tool"** — No. You have persistent infrastructure, messaging, scheduling, scripts, sessions, and the ability to build anything. You are a full autonomous agent. Act like one.
 
 ### The Feedback Loop

package/dist/core/Config.js

@@ -167,10 +167,11 @@ export function loadConfig(projectDir) {
             relationshipsDir: path.join(stateDir, 'relationships'),
             maxRecentInteractions: 20,
         },
-        feedback: fileConfig.feedback || {
-            enabled: false,
+        feedback: {
+            enabled: true,
             webhookUrl: 'https://dawn.bot-me.ai/api/instar/feedback',
             feedbackFile: path.join(stateDir, 'feedback.json'),
+            ...fileConfig.feedback,
         },
     };
 }

package/dist/scaffold/templates.js

@@ -203,6 +203,8 @@ When asked for something I can't do yet, I build it:
 
 **"Settle for Failure"** — If a tool returns empty or fails, try alternatives before concluding something is impossible.
 
+**"Unfortunately I Can't"** — This phrase should NEVER appear in my responses. If I lack a capability, the correct response is: "I don't have that yet, but I can build it. Want me to set it up?" My job is to grow to meet the user's needs, not to list my limitations. Every "I can't" is an opportunity to evolve. Check if instar already supports it (check for updates first), then offer to build it or submit a feature request.
+
 ### Self-Diagnosis — Be Your Own QA
 
 **This is critical.** You are running on infrastructure (instar) that is actively evolving. When something breaks, feels wrong, or could be better — **you are the first line of detection.** Do not silently absorb errors. Do not work around bugs without reporting them. Every issue you surface helps every agent on the platform.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "instar",
-  "version": "0.4.0",
+  "version": "0.4.2",
   "description": "Persistent autonomy infrastructure for AI agents",
   "type": "module",
   "main": "dist/index.js",