fix(llm): avoid interrupting reasoning display with streamed content

[jexShain]

Summary

• Only emit content_delta events during streaming when tool calls are present, preventing the reasoning Live display from being disrupted in plain conversations
• Expose content_was_streamed property on PTYAIShell for clean cross-object access, replacing getattr on private attributes
• Remove redundant emit_content_delta(is_final=True) in non-streaming path without tool calls

Test plan

• Verify plain conversation (no tool calls) does not stream content to terminal during LLM response
• Verify tool-call conversations still display streamed content correctly
• Verify error fix and question flows render responses properly in both modes

[github-actions]

Thanks for the pull request. A maintainer will review it when available.

Please keep the PR focused, explain the why in the description, and make sure local checks pass before requesting review.

Contribution guide: https://github.com/AI-Shell-Team/aish/blob/main/CONTRIBUTING.md

[github-actions]

This pull request description looks incomplete. Please update the missing sections below before review.

Missing items:

• User-visible Changes
• Compatibility
• Testing
• Change Type
• Scope