Support Assistent persona packs via git and local sync.

Replace assistent-personas overlay seed with assistent-extensions SFTP and an assistent: section in extensions.yaml so personalities install like other extensions without private URLs in the public repo.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Leonid Pershin
2026-08-23 08:28:31 +03:00
co-authored by Cursor
parent b24c1b5d4b
commit 20ae7bd83a
25 changed files with 258 additions and 206 deletions
+1 -1
View File
@@ -113,7 +113,7 @@ Unit `gpu-rent-ollama` читает `/mnt/swarm_data/.gpu-rent-gpu.json`:
\*Flash на Ampere+ (compute ≥ 8.0). `NUM_PARALLEL=2`, `MAX_LOADED_MODELS=2` (chat VL + memory embed). Memory models use `use: memory` and a CPU Modelfile (`num_gpu 0`) so embed does not steal VRAM from the chat model. Ollama default `num_ctx` is 4096; we set `OLLAMA_CONTEXT_LENGTH` so Assistent + vision fits. Mid/high keep-alive is **5m** because Assistent parks the chat model before Generate (`AssistentParkLlm`) and warms after. Env: `/mnt/swarm_data/.gpu-rent-ollama.env`.
Personas: laptop `assistent-personas/` → on `up` / `seed-personas` overlay folders under `/mnt/swarm_data/Assistent/personas/<id>/` (+ `_base/assistant.json` with `default_persona` / `num_ctx`). Shelves are short JSON files (not a long prompt). See [extensions.md](extensions.md). Optional FTS examples: [datasets/README](../datasets/README.md) (`search.jsonl``Assistent/civitai-examples.jsonl`). Journal: `gpu-rent logs -u ollama`.
Personas: bundled `neutral` / `aggressive` / `dreamer` in swarm-assistent; extra packs via `extensions.yaml` `assistent:` or laptop `assistent-extensions/` `Assistent/extensions/` on `up` / `seed-personas` / `push` (+ `_base/assistant.json` with `default_persona` / `num_ctx`). See [extensions.md](extensions.md). Optional FTS examples: [datasets/README](../datasets/README.md) (`search.jsonl``Assistent/civitai-examples.jsonl`). Journal: `gpu-rent logs -u ollama`.
`ollama-models.yaml` entries: