mirror of
https://github.com/microsoft/vscode.git
synced 2026-08-23 15:34:20 +01:00
83dfbdd3a9
* chat: add experiment hook to test Luna for dictation LLM cleanup Adds a 'dictationLlmCleanupModel' assignment treatment so the LLM dictation cleanup model can be flighted. Control keeps the existing copilot-utility-small selector (gpt-4o-mini); the treatment value gpt-5.6-luna selects Luna. The lookup shares the existing cleanup deadline and preserves the raw-transcript fallback. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * copilot: publish hidden gpt-5.6-luna so dictation cleanup experiment can resolve it The copilot vendor only publishes models to the workbench language-model list when they are shown in the model picker (or are gpt-4o-mini). Luna is not a picker model, so selectLanguageModels({ id: 'gpt-5.6-luna' }) would return nothing and the dictation cleanup experiment would silently fall back to the raw transcript. Add gpt-5.6-luna to the always-published utility models so the treatment can resolve it while keeping it hidden from the picker. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * chat: harden dictation cleanup model experiment Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: b8fa5c4e-601e-4267-87f4-366139bc420c --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: b8fa5c4e-601e-4267-87f4-366139bc420c