Claude Sonnet 5 delegated to a lesser agent to perform a code review

### Describe the bug

I asked Claude Sonnet 5 to perform a code review. I specifically chose Claude Sonnet 5 for deep reasoning. The agent proceeded to review the structure of my project and then delegate to a lesser agent:

"Good, all directories exist. I'll launch a general-purpose agent to perform this code review, since it involves reading through before/after/project directories, comparing changes, and producing a structured markdown report — genuinely multi-step work."

"General-purpose(gpt-5.4) Perform code review for issue 44206"

The code review produced was of little use. I corrected the agent and requested Sonnet 5 to perform the review itself:

"I would like to start this code review over. I see that you delegated to gpt-5.4 and I do not want a weaker model doing the review. Please execute the review prompt in file 44206-review-prompt2.txt."

Sonnet replied "I'll perform this review myself directly (no sub-agent delegation this time). Let me examine the before/after directories to identify actual changed files."

Sonnet completed the review the second time and the quality was as expected.

### Affected version

GitHub Copilot CLI 1.0.75

### Steps to reproduce the behavior

_No response_

### Expected behavior

I expected that when selecting the agent that it perform the work itself.

### Additional context

_No response_

Reproduce the behavior in GitHub Copilot CLI 1.0.75 using the review scenario and the 44206-review-prompt2.txt prompt, comparing the before, after, and project directories. Trace where the selected agent decides to delegate, then verify that Sonnet performs the requested review itself without an unintended lesser-agent handoff.

Written by the indexing model from the issue text.