fix(sensei): switch agent model from haiku to sonnet

.claude-plugin/marketplace.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
   "name": "code-sensei",
-  "version": "1.1.0",
+  "version": "1.1.1",
   "description": "In-context coding tutor for Claude Code. Learn from your real project with explanations, quizzes, diagnostics, and belt-based progression — locally and privately.",
   "owner": {
     "name": "Dojo Coding",
@@ -11,7 +11,7 @@
     {
       "name": "code-sensei",
       "description": "In-context coding tutor for Claude Code. Explains what AI just built, quizzes you on your own project, and tracks progress locally with a martial arts belt progression system.",
-      "version": "1.1.0",
+      "version": "1.1.1",
       "author": {
         "name": "Dojo Coding",
         "email": "team@dojocoding.io"

.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "code-sensei",
-  "version": "1.1.0",
+  "version": "1.1.1",
   "description": "In-context coding tutor for Claude Code. Learn from your real project with explanations, quizzes, diagnostics, and belt-based progression — locally and privately.",
   "author": {
     "name": "Dojo Coding",

CHANGELOG.md

@@ -2,6 +2,10 @@
 
 All notable changes to CodeSensei will be documented in this file.
 
+## 1.1.1
+
+- Fixed the `sensei` subagent failing to launch (0 tool uses) because its configured `haiku` model is unavailable; switched to `sonnet`
+
 ## 1.1.0
 
 - Added `/code-sensei:doctor` for setup verification and local storage inspection

agents/sensei.md

@@ -6,7 +6,7 @@ description: >
   and test comprehension with micro-quizzes. Adapts to the user's belt level and background.
   Use this agent when the user asks to learn about, understand, or get explanations of code.
 tools: Read, Glob, Grep, Bash
-model: haiku
+model: sonnet
 ---
 
 You are **CodeSensei** 🥋, the AI coding mentor by **Dojo Coding**.