Seed Assistent personas as overlay folders and tighten Ollama/Assistent glue.

gpu-rent now writes personas/<id>/ on the VM (not legacy personas.json), adds seed-personas/doctor checks, and shortens mid/high keep-alive now that Assistent parks the LLM before Generate.

Co-authored-by: Cursor <cursoragent@cursor.com>

tests/test_assistent_personas_seed.py

@@ -0,0 +1,81 @@
+"""Unit tests for assistent personas overlay seed helpers."""
+
+from __future__ import annotations
+
+import json
+from pathlib import Path
+from unittest.mock import MagicMock
+
+import pytest
+
+from gpu_rent.provision import _safe_persona_id, count_wanted_models_on_vm, seed_assistent_personas
+
+
+def test_safe_persona_id():
+    assert _safe_persona_id("neutral") == "neutral"
+    assert _safe_persona_id("lewd_v2") == "lewd_v2"
+    assert _safe_persona_id("../x") is None
+    assert _safe_persona_id("a/b") is None
+    assert _safe_persona_id("") is None
+
+
+def test_seed_assistent_personas_writes_overlay(tmp_path: Path, monkeypatch):
+    yaml_path = tmp_path / "assistent-personas.yaml"
+    yaml_path.write_text(
+        "default: cinema\n"
+        "personas:\n"
+        "  - id: cinema\n"
+        "    title: Кино\n"
+        "    prompt: |\n"
+        "      You are a DP.\n"
+        "  - id: neutral\n"
+        "    title: Нейтральный\n"
+        "    prompt: Calm.\n",
+        encoding="utf-8",
+    )
+    puts: dict[str, str] = {}
+    ssh_cmds: list[str] = []
+
+    def fake_put(cfg, host, remote, text, mode=0o644):
+        puts[remote] = text
+
+    def fake_ssh(cfg, host, cmd, check=False, timeout=60):
+        ssh_cmds.append(cmd)
+        if ".gpu-rent-gpu.json" in cmd:
+            return json.dumps({"vram_mib": 24576, "name": "4090", "compute_cap": "8.9"})
+        return ""
+
+    monkeypatch.setattr("gpu_rent.provision.put_text", fake_put)
+    monkeypatch.setattr("gpu_rent.provision.run_ssh", fake_ssh)
+    monkeypatch.setattr(
+        "gpu_rent.paths.assistent_personas_manifest_path", lambda: yaml_path
+    )
+    monkeypatch.setattr(
+        "gpu_rent.paths.assistent_personas_example_path", lambda: tmp_path / "missing"
+    )
+
+    cfg = MagicMock()
+    cfg.assistent_personas_manifest = str(yaml_path)
+    logs: list[str] = []
+    seed_assistent_personas(cfg, "1.2.3.4", logs.append)
+
+    assert any("personas/cinema/persona.json" in p for p in puts)
+    assert any("personas/cinema/extra.md" in p for p in puts)
+    assert "/mnt/swarm_data/Assistent/_base/assistant.json" in puts
+    asst = json.loads(puts["/mnt/swarm_data/Assistent/_base/assistant.json"])
+    assert asst["default_persona"] == "cinema"
+    assert asst["num_ctx"] == 16384
+    assert any("rm -f" in c and "personas.json" in c for c in ssh_cmds)
+    assert not any(p.endswith("personas.yaml") for p in puts)
+    assert not any(p.endswith("personas.json") for p in puts)
+    assert any("overlay personas/2" in m for m in logs)
+
+
+def test_count_wanted_models(monkeypatch):
+    raw = "lora:\n  - url: https://civitai.red/x?modelVersionId=1\n    title: A\n"
+
+    monkeypatch.setattr(
+        "gpu_rent.provision.run_ssh",
+        lambda *a, **k: raw,
+    )
+    assert count_wanted_models_on_vm(MagicMock(), "h") == 1