Feat: fit-aware Brain-Update (Speicher-Budget) + brains-Kontext gesenkt (Always-On-Footprint)

Browse Source

- Brain-Kontexte gesenkt (live config): hermes 128K->64K, fast/vision 128K->32K
  -> Always-Warm-Footprint 74GB->51GB, ~23GB frei; heavy/coder passen wieder daneben.
- /api/agent/brain liefert jetzt `budget`: projiziert den Always-On-Footprint mit dem
  empfohlenen Brain gegen das GTT-Budget (aus amdgpu.gttsize) und prueft, ob das groesste
  on-demand-Modell daneben passt (fit.estimate_memory_gb).
- Cockpit Agent-Hirn-Karte: Budget-Zeile (gruen/rot) + Warnung im Update-Confirm, wenn ein
  zu grosses Always-On-Brain das groesste on-demand-Modell verdraengen wuerde. Button wird rot.

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

...

This commit is contained in:

Hitonabi

2026-06-27 02:56:32 +02:00

parent 510de69250

commit 5b699aaa79

6 changed files with 141 additions and 56 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

frontend/dist/assets/index-eiqRvBvu.js

Vendored

+397

File diff suppressed because one or more lines are too long