P3: llama-swap capabilities deklariert + Plugin lernt Tool-Namen (Hermes-0.18-API)

- deploy-Config: capabilities (in/out/tools/context) je Modell — /v1/models informiert
  Clients korrekt; context = nutzbarer Kontext pro Request (c/parallel)
- mc2-memory: sync_turn nutzt messages aus Hermes >=0.18 — nur Tool-NAMEN (Ergebnisse
  bleiben draussen: untrusted/Poisoning-Vektor); deployt, Postcheck gruen
- Mem0 v3-Algorithmus auf der Box verifiziert (BM25/Entity/Hybrid in 2.0.8 aktiv)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Hitonabi
2026-07-02 11:25:46 +02:00
parent 6f7498a956
commit 88c2659a9c
2 changed files with 42 additions and 0 deletions
+30
View File
@@ -13,24 +13,44 @@ models:
aliases:
- hermes
- fast
# context = nutzbarer Kontext PRO REQUEST (c geteilt durch parallel-Slots).
capabilities:
in: [text]
out: [text]
tools: true
context: 65536
Qwen3.5-122B-A10B:
cmd: |
llama-server -m /srv/models/Qwen3.5-122B-A10B-GGUF/Q4_K_M/Qwen3.5-122B-A10B-Q4_K_M-00001-of-00003.gguf --host 127.0.0.1 --port ${PORT} -c 32768 -ngl 999 -fa on --no-mmap --jinja --cache-reuse 256 -cram 16384
ttl: 600
aliases:
- heavy
capabilities:
in: [text]
out: [text]
tools: true
context: 32768
Qwen3-Coder-Next:
cmd: |
llama-server -m /srv/models/Qwen3-Coder-Next-GGUF/Qwen3-Coder-Next-Q4_K_M.gguf --host 127.0.0.1 --port ${PORT} -c 131072 -ngl 999 -fa on --no-mmap --jinja --cache-reuse 256 -cram 16384
ttl: 600
aliases:
- coder
capabilities:
in: [text]
out: [text]
tools: true
context: 131072
Qwen3-VL-8B-Instruct:
cmd: |
llama-server -m /srv/models/Qwen3-VL-8B-Instruct-GGUF/Qwen3VL-8B-Instruct-Q4_K_M.gguf --host 127.0.0.1 --port ${PORT} -c 32768 -ngl 999 -fa on --no-mmap --mmproj /srv/models/Qwen3-VL-8B-Instruct-GGUF/mmproj-Qwen3VL-8B-Instruct-F16.gguf --jinja
ttl: 300
aliases:
- vision
capabilities:
in: [text, image]
out: [text]
context: 32768
Qwen3-Embedding-0.6B:
cmd: |
llama-server -m /srv/models/Qwen3-Embedding-0.6B-GGUF/Qwen3-Embedding-0.6B-Q8_0.gguf --host 127.0.0.1 --port ${PORT} --embedding --pooling last -ngl 999 -fa on --no-mmap -c 8192
@@ -43,12 +63,22 @@ models:
ttl: 300
aliases:
- coder-lite
capabilities:
in: [text]
out: [text]
tools: true
context: 131072
GLM-4.6V-Flash:
cmd: |
llama-server -m /srv/models/GLM-4.6V-Flash-GGUF/GLM-4.6V-Flash-Q4_K_M.gguf --host 127.0.0.1 --port ${PORT} -c 131072 -ngl 999 -fa on --no-mmap --mmproj /srv/models/GLM-4.6V-Flash-GGUF/mmproj-BF16.gguf --jinja
ttl: 300
aliases:
- scout
capabilities:
in: [text, image]
out: [text]
tools: true
context: 131072
groups:
brains:
swap: false