feat(cli): add streamlined gemini gemma local model setup (#25498)

Co-authored-by: Abhijit Balaji <abhijitbalaji@google.com>
Co-authored-by: Samee Zahid <sameez@google.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
Samee Zahid
2026-04-20 16:57:56 -07:00
committed by GitHub
parent 6afc47f81c
commit 1d383a4a8e
31 changed files with 2509 additions and 12 deletions
+20
View File
@@ -2169,6 +2169,26 @@ const SETTINGS_SCHEMA = {
default: false,
description:
'Enable the Gemma Model Router (experimental). Requires a local endpoint serving Gemma via the Gemini API using LiteRT-LM shim.',
showInDialog: true,
},
autoStartServer: {
type: 'boolean',
label: 'Auto-start LiteRT Server',
category: 'Experimental',
requiresRestart: true,
default: false,
description:
'Automatically start the LiteRT-LM server when Gemini CLI starts and the Gemma router is enabled.',
showInDialog: true,
},
binaryPath: {
type: 'string',
label: 'LiteRT Binary Path',
category: 'Experimental',
requiresRestart: true,
default: '',
description:
'Custom path to the LiteRT-LM binary. Leave empty to use the default location (~/.gemini/bin/litert/).',
showInDialog: false,
},
classifier: {