[MODEL] Claude unaware of --continue / -c flag behavior

Preflight Checklist

• [x] I have searched existing issues for similar behavior reports
• [x] This report does NOT contain sensitive information (API keys, passwords, etc.)

Type of Behavior Issue

Other unexpected behavior

What You Asked Claude to Do

Asked Claude if there's a way to continue an existing conversation in a new Claude Code session.

What Claude Actually Did

Claude incorrectly said there's no way to carry conversation context into a new session, without mentioning the claude --continue (or -c) flag which does exactly that.

Expected Behavior

Claude should be aware of its own CLI flags and inform the user that claude --continue resumes the most recent conversation with full context in a new session.

Files Affected

Permission Mode

Accept Edits was ON (auto-accepting changes)

Can You Reproduce This?

Haven't tried to reproduce

Steps to Reproduce

<img width="956" height="331" alt="Image" src="https://github.com/user-attachments/assets/4c0e01a1-d7b4-4e29-ab9d-c64792c7cf11" />

Claude Model

Sonnet

Relevant Conversation

Impact

Low - Minor inconvenience

Claude Code Version

2.1.90 (Claude Code)

Platform

Anthropic API

Additional Context

_No response_