Evidence record / github-copilot-cli

A dated record of one change, kept so the writing that cites it can be checked. Compiled from the sources listed below by the research run, not written for reading. The judgment lives in the issues that cite it, below.

2026-10-24-github-copilot-cli-gpt-5-responses-requests-regain-model-specific-default-verbosity

GPT-5 Responses requests regain model-specific default verbosity. Model-specific default Responses verbosity now applies correctly for GPT-5 models unless session verbosity is explicitly set. No universal verbosity value or numerical token saving is stated.

Channel: tagged-release. Half: defect. Date: 2026-10-22.

Operator consequence: Recheck output-length expectations and evaluation settings after moving to 1.0.103. Set session verbosity explicitly when a comparison requires it, and record the selected model. This is a default-sensitive request repair, not evidence of improved answer correctness or lower billed cost.

Receipt

Finding metadata

Run: 2026-10-24-weekly-digest-2026-10-13_2026-10-24-frontier-v0

Finding ID: 2026-10-24-github-copilot-cli-gpt-5-responses-requests-regain-model-specific-default-verbosity

Profile citations

Source links

Primary links, including exact changelog lines when available.

Versioned source: run artifact