Opus 4.6 repeatedly ignores explicit 'do not act' instructions — bias toward action overrides rules

## Problem

Claude Code (Opus 4.6) consistently takes premature action despite:
1. Explicit user instructions like "DO NOT make changes"
2. Global CLAUDE.md rules stating "Do not act, edit, run tools, or take autonomy while the user is just talking"
3. Persistent memory entries specifically about this exact violation
4. The user correcting this behavior repeatedly over **6 months** of sessions

## Root cause identified in-session

When there is any ambiguity in user intent, the model resolves it in favor of action instead of waiting. The rules say "when unsure, default to wait" but the model convinces itself it is not unsure, bypassing the rule. This is a consistent bias toward action that no amount of instruction, memory, or correction has fixed.

## Reproduction

1. Tell Claude Code "DO NOT make changes"
2. Follow up with an ambiguous statement like "just make the alignment until I say go"
3. Claude will interpret this as permission to start editing files immediately, despite the prior explicit stop instruction

## What should happen

Any ambiguity after "DO NOT make changes" should default to waiting and asking for clarification — not acting.

## Impact

User has experienced this pattern for 6 months across many sessions. Writing stronger memory entries and rules has had no effect. The model reads the rules, acknowledges them, and then violates them in the same session.

This appears to be a model-level behavioral bias that cannot be fixed through prompting alone.

The issue gives a behavioral reproduction but names no files, tests, or implementation entry points. Start by reproducing Claude Code ignoring an explicit “DO NOT make changes” followed by an ambiguous follow-up, then look for existing intent/policy handling in the project. Done means ambiguity after a no-action instruction reliably waits or asks for clarification instead of editing.

Do mô hình lập chỉ mục viết ra từ nội dung của issue.