instar 0.12.3 → 0.12.4

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.
@@ -19,16 +19,31 @@ You are running the **instar setup wizard**. Your job is to walk the user throug
19
19
 
20
20
  The only exception is when the user explicitly asks "what command do I run?" or "show me the CLI."
21
21
 
22
+ ## CRITICAL: NEVER Use AskUserQuestion
23
+
24
+ **The `AskUserQuestion` tool is BANNED from this wizard.** Do not use it at any step, for any reason. Its multichoice overlay hides the text above it in the terminal, making the wizard feel broken and truncated.
25
+
26
+ Instead, always present choices as **inline numbered options in your text output**, then wait for the user to type their choice. Example:
27
+
28
+ > How much initiative should the agent take?
29
+ >
30
+ > 1. Guided — follows your lead, confirms before acting
31
+ > 2. Proactive — takes initiative, asks when uncertain
32
+ > 3. Fully autonomous — owns outcomes end-to-end
33
+ >
34
+ > Type a number or describe what you'd prefer.
35
+
36
+ This keeps all context visible. The user types "1", "2", "guided", or a free-text answer.
37
+
22
38
  ## CRITICAL: Terminal Display Rules
23
39
 
24
40
  This wizard runs in a terminal that may be narrow (80-120 chars). Long text gets **truncated and cut off**, making the wizard feel broken. Follow these rules strictly:
25
41
 
26
42
  1. **Keep paragraphs to 2-3 sentences max.** Break long explanations into multiple short paragraphs.
27
43
  2. **Never write a sentence longer than ~100 characters.** Break long sentences into two.
28
- 3. **Put details in question descriptions**, not in free text above the question. The AskUserQuestion option descriptions render properly; long text above the question gets cut off.
29
- 4. **Use bullet points** instead of dense paragraphs for explanations.
30
- 5. **Avoid parenthetical asides** they make sentences too long. Use a separate sentence instead.
31
- 6. **When reassuring the user** (e.g., "you can change this later"), keep it to ONE short sentence. Don't elaborate.
44
+ 3. **Use bullet points** instead of dense paragraphs for explanations.
45
+ 4. **Avoid parenthetical asides** they make sentences too long. Use a separate sentence instead.
46
+ 5. **When reassuring the user** (e.g., "you can change this later"), keep it to ONE short sentence. Don't elaborate.
32
47
 
33
48
  **Bad** (gets truncated):
34
49
  > Everything we set up here is just a starting point. The agent's identity, autonomy level, communication style — all of it lives in simple markdown and config files in your project's .instar/ directory. You can edit them anytime, or even just tell the agent to adjust itself.
@@ -561,7 +576,7 @@ Ask conversationally — not as a form, but as a getting-to-know-you:
561
576
  - **Proactive** — Takes initiative on obvious next steps. Asks when uncertain.
562
577
  - **Fully autonomous** — Owns outcomes end-to-end. Asks only when blocked.
563
578
 
564
- Before presenting this question, say ONE short sentence like: "You can always change this later." Do NOT write a long paragraph reassuring them. Put the descriptions in the AskUserQuestion option descriptions, not in free text.
579
+ Before presenting this question, say ONE short sentence like: "You can always change this later." Do NOT write a long paragraph reassuring them. Present these as inline numbered options in your text never use AskUserQuestion.
565
580
 
566
581
  ### Step 2c: Learn About the Agent
567
582
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "instar",
3
- "version": "0.12.3",
3
+ "version": "0.12.4",
4
4
  "description": "Persistent autonomy infrastructure for AI agents",
5
5
  "type": "module",
6
6
  "main": "dist/index.js",
@@ -1,8 +1,8 @@
1
1
  {
2
2
  "$schema": "./builtin-manifest.schema.json",
3
3
  "schemaVersion": 1,
4
- "generatedAt": "2026-03-03T18:00:12.103Z",
5
- "instarVersion": "0.12.3",
4
+ "generatedAt": "2026-03-03T18:10:21.922Z",
5
+ "instarVersion": "0.12.4",
6
6
  "entryCount": 165,
7
7
  "entries": {
8
8
  "hook:session-start": {
@@ -295,7 +295,7 @@
295
295
  "type": "skill",
296
296
  "domain": "skills",
297
297
  "sourcePath": ".claude/skills/setup-wizard/skill.md",
298
- "contentHash": "b2fde46d780510726cc2e3d7d3c5617fd710d4941f0b44ec1b474f9884801cbb",
298
+ "contentHash": "3a6c862351f559993cac82ec6da668a2118ea5737c1f92b9f4019beb5398f564",
299
299
  "since": "2025-01-01"
300
300
  },
301
301
  "route-group:health": {
@@ -0,0 +1,19 @@
1
+ # Upgrade Guide — v0.12.4
2
+
3
+ <!-- bump: patch -->
4
+
5
+ ## What Changed
6
+
7
+ `AskUserQuestion` is now completely banned from the setup wizard. A new `## CRITICAL: NEVER Use AskUserQuestion` section at the top of the skill prohibits its use at any step. All choice points now use inline numbered text options with typed user responses.
8
+
9
+ The previous fix (v0.12.3) only addressed Entry Point B. This fix applies the same pattern globally — every step that presents options now uses inline numbered text instead of the multichoice overlay.
10
+
11
+ ## What to Tell Your User
12
+
13
+ - **Setup wizard improvement**: "All wizard choices now show inline instead of in popup menus. No more hidden or truncated text."
14
+
15
+ ## Summary of New Capabilities
16
+
17
+ | Capability | How to Use |
18
+ |-----------|-----------|
19
+ | Overlay-free wizard | Automatic — just run `npx instar` |