mrleo1nid/gpu-rent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Expose ollama-roles default_chat for Assistent senior model default.

Browse Source 
Write preferred chat tag into Assistent/ollama-roles.json so UI and warmup align with manifest default: true.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Leonid Pershin
2026-08-22 03:50:58 +03:00
co-authored by Cursor
parent 3620ac2b5e
commit d934fc9366
4 changed files with 10 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/llm.md
+2 -2
View File
@@ -96,7 +96,7 @@ Qwen3-VL (`huihui_ai/qwen3-vl-abliterated:…`) требует **Ollama ≥ 0.12
Рекомендуемый пресет — **abliterated Qwen3-VL Instruct**; light / text / big пока Qwen2.5. Официальные censored-теги (`qwen2.5vl:…`) в меню нет.
`default: true` в yaml — preferred в логе; pull идёт по всему списку.
`default: true` в yaml — preferred в логе и в `Assistent/ollama-roles.json` → `default_chat` (Assistent UI + warmup); pull идёт по всему списку.
---
@@ -127,7 +127,7 @@ Personas: laptop `assistent-personas/` → on `up` / `seed-personas` overlay fol
use: memory
```
Roles are written to `/mnt/swarm_data/Assistent/ollama-roles.json` for the Assistent extension (chat select vs memory select).
Roles are written to `/mnt/swarm_data/Assistent/ollama-roles.json` for the Assistent extension (`chat` / `memory` lists + `default_chat` for UI default and warmup).
---