Accidental triggering of extended thinking by using a commonly used word `think`.

Problem Description

The current implementation uses "think" as a trigger word for extended thinking mode, which is problematic for several reasons:

Frequent Accidental Activation

• The word "think" is commonly used in natural speech and dictation
• Users inadvertently trigger the mode during normal conversation
• This creates an unintended barrier to natural communication

User Behavior Modification

• Users are unconsciously training themselves to avoid using "think" in their speech
• This self-censorship feels unnatural and restrictive
• The tool is changing user behavior in an unwanted way

Suggested Improvements

More Specific Trigger Words

• Use less common terms like "ultrathink"
• Implement clear markers (e.g., "/think" or similar syntax)
• Choose triggers that are obviously intentional commands rather than natural language

User Experience Impact

Poor Discoverability

• The feature's existence isn't immediately obvious to new users
• Users discover it accidentally rather than through clear documentation
• Inconsistent activation leads to confusion about when/why it appears

Personal Experience

• During initial weeks of use, the appearance of italic grey text was confusing
• The inconsistent triggering made it difficult to understand the pattern
• Only discovered the cause through later documentation review

Recommendation

Implement a more deliberate trigger mechanism that doesn't interfere with natural speech patterns while maintaining the feature's utility.