Fix: Modell-Manager Rollen-Taxonomie vereinheitlicht (5 Rollen) + echter Vocab-Check
- Rollen ueberall = fast/heavy/coder/vision/scout (eine Quelle der Wahrheit): sources.py CATEGORIES (agent/reasoning raus, fast/heavy rein), llamaswap.ROLE_IDS, maintenance ROLE_MAP entfernt (Discover-Rollen == Serving-Rollen), Discover.tsx ROLE_METADATA, ModelBadges.ROLES, ActiveModelsCard (stale reasoning-Farbe raus). Behebt: Discover zeigte "Reasoning"/"agent"; aus Discover installierte Modelle landeten in keinem Cockpit-Slot. - gguf_meta: Vocab-Check jetzt ECHT - sha256 ueber die vollstaendige Token-Liste statt nur Metadaten. Familienunabhaengig (Qwen/Llama/Mistral/...). Verifiziert: Coder + Qwen3-0.6B byte-identisch (kompatibel), Qwen3.6 abweichend (inkompatibel), 0.11s/Scan. - RolesCard SPEC-Badge -> spec_active (Konsistenz mit Cockpit). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
@@ -8,7 +8,6 @@ const ROLE_TONE: Record<string, string> = {
|
||||
fast: "bg-cyan-500/15 text-cyan-400 border-cyan-500/25",
|
||||
heavy: "bg-amber-500/15 text-amber-400 border-amber-500/25",
|
||||
coder: "bg-violet-500/15 text-violet-400 border-violet-500/25",
|
||||
reasoning: "bg-emerald-500/15 text-emerald-400 border-emerald-500/25",
|
||||
vision: "bg-pink-500/15 text-pink-400 border-pink-500/25",
|
||||
scout: "bg-teal-500/15 text-teal-400 border-teal-500/25",
|
||||
hermes: "bg-indigo-500/15 text-indigo-400 border-indigo-500/25",
|
||||
|
||||
@@ -57,7 +57,7 @@ export function RolesCard() {
|
||||
PC
|
||||
</span>
|
||||
)}
|
||||
{m.spec_draft_model && (
|
||||
{m.spec_active && (
|
||||
<span className="text-[7px] leading-none font-mono font-bold bg-emerald-500/10 text-emerald-400 border border-emerald-500/20 px-1 py-0.5 rounded" title={`Speculative Decoding aktiv (Draft: ${m.spec_draft_model})`}>
|
||||
SPEC
|
||||
</span>
|
||||
|
||||
Reference in New Issue
Block a user