HitonabiandClaude Opus 4.8 43880b1965 Fix: KV-Schaetzung kalibriert + Brain-Fit-Check brain-spezifisch ...

- fit.estimate_memory_gb: KV-Cache jetzt sqrt-skaliert (nicht linear mit Gesamt-Params),
  kalibriert an Hermes-14B@128K ~19GB KV -> realistische Footprints (vorher massive Ueberschaetzung).
- agent.hermes_brain_info Budget: prueft jetzt Brain (immer resident) + groesstes on-demand-Modell
  <= GTT-Budget (fast/vision duerfen verdraengt werden) -> brain-spezifische, aussagekraeftige Warnung.
- Cockpit: Budget-Zeile + Confirm-Warnung entsprechend ("Brain ~X GB + groesstes on-demand ~Y GB").

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-06-27 03:01:07 +02:00

..

__init__.py

feat(2.0): Phase 0 — Greenfield-Skeleton (FastAPI + React/shadcn)

2026-06-24 22:17:45 +02:00

agent.py

Fix: KV-Schaetzung kalibriert + Brain-Fit-Check brain-spezifisch

2026-06-27 03:01:07 +02:00

backup.py

Feat: Vulkan/RADV-Engine + vocab-gepruefte Spec-Drafts + Provisioning/Sync

2026-06-27 01:54:29 +02:00

caps.py

feat: simplify Discover view into socket cards & backend upgrades

2026-06-26 07:53:41 +02:00

connect.py

feat: simplify Discover view into socket cards & backend upgrades

2026-06-26 07:53:41 +02:00

discover.py

Feat: Discover zukunftssicher (Recency-Score) + Agent-Hirn (Hermes) im Modell-Manager

2026-06-27 02:44:27 +02:00

fit.py

Fix: KV-Schaetzung kalibriert + Brain-Fit-Check brain-spezifisch

2026-06-27 03:01:07 +02:00

gateway_stream.py

Refactor: Zentrales Logging + robuste Token-Erfassung (Phase 2)

2026-06-26 14:32:15 +02:00

gateway.py

feat(2.0): Phase 6c — eingebauter OpenAI-Gateway (model:auto) statt LiteLLM

2026-06-25 12:54:19 +02:00

gguf_meta.py

Fix: Modell-Manager Rollen-Taxonomie vereinheitlicht (5 Rollen) + echter Vocab-Check

2026-06-27 02:26:27 +02:00

hf.py

feat(2.0): W2+W3 — HF-Link/Suche + Modell-Verwaltungs-UX

2026-06-25 14:33:23 +02:00

jobengine.py

feat: simplify Discover view into socket cards & backend upgrades

2026-06-26 07:53:41 +02:00

llamaswap.py

Fix: Modell-Manager Rollen-Taxonomie vereinheitlicht (5 Rollen) + echter Vocab-Check

2026-06-27 02:26:27 +02:00

maintenance.py

Fix: "Modelle finden" bevorzugt faehigste passende Modelle (kein Downgrade) + Rollen-Farben zentral

2026-06-27 02:35:21 +02:00

memory.py

feat(2.0): Phase 3 — Memory + MCP

2026-06-25 08:16:12 +02:00

pricing.py

Refactor: Pricing/Draft-Pfad als Single Source of Truth (Phase 1)

2026-06-26 14:28:26 +02:00

router_logic.py

feat(2.0): W1 — fast-Spur ohne Thinking (flotte Antworten) + tool-call-Cap

2026-06-25 14:24:57 +02:00

sources.py

Fix: Modell-Manager Rollen-Taxonomie vereinheitlicht (5 Rollen) + echter Vocab-Check

2026-06-27 02:26:27 +02:00

system.py

Feat: Add manual updates check, Settings tab, direct model upgrades, logs password redirection, fix engine version detection, and expand AI agent Guide tab

2026-06-26 13:09:50 +02:00

token_stats.py

Refactor: Zentrales Logging + robuste Token-Erfassung (Phase 2)

2026-06-26 14:32:15 +02:00