dguiducci
5081ec2afe
Nightly Build / build (push) Successful in 6m50s
Remove the scope system end-to-end (llm_models.scope column, agent meta scope field, scope-based tier in model selection, UI checkboxes/pills): it was only a soft ranking hint, had drifted (6 UI scopes vs 3 used by agents, 'general' not even selectable) and duplicated what strength already decides. Strength stays the single AUTO-selection axis. Compaction: the summary model is now pickable from the Settings page via a new PropertyType::LlmModel config property (registry key compaction_model), instance-wide and live (no restart). Fallback chain: explicit pick -> compaction.strength from config.yml -> priority order; a deleted configured model degrades to AUTO. ContextCompactor reads the key at compact time through GlobalConfigManager.
20 lines
1.0 KiB
JSON
20 lines
1.0 KiB
JSON
{
|
|
"name": "Generalist",
|
|
"description": "General-purpose task executor: carries out the well-defined work ordered by the calling agent — file edits, shell commands, batch operations. No planning or QA.",
|
|
"friendly_description": "Carries out well-defined hands-on work — file edits, shell commands, batch operations — exactly as instructed.",
|
|
"i18n": {
|
|
"it": {
|
|
"name": "Generalista",
|
|
"friendly_description": "Esegue lavori pratici ben definiti — modifiche a file, comandi shell, operazioni batch — esattamente come richiesto."
|
|
},
|
|
"fr": {
|
|
"name": "Généraliste",
|
|
"friendly_description": "Exécute un travail pratique bien défini — modifications de fichiers, commandes shell, opérations par lots — exactement comme demandé."
|
|
}
|
|
},
|
|
"instructions": "Hand it a fully-specified task: what to change and where. It executes but does not plan, decide scope, or QA its own output, so be explicit about the desired outcome.",
|
|
"type": "task",
|
|
"strength": "average",
|
|
"icon": "icon.png"
|
|
}
|