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_access_card.py

@@ -16,9 +16,10 @@ def test_collect_links_swarm_and_ollama(monkeypatch):
     links = collect_access_links(_Cfg(), tunneled=True)
     labels = [x.label for x in links]
     assert "SwarmUI UI" in labels
+    assert "Assistent" in labels
     assert "SwarmUI MCP" in labels
     assert "Ollama API" in labels
-    assert any("17811" in x.url for x in links)
+    assert any(x.label == "Assistent" and "вкладка" in x.note for x in links)
 
 
 def test_collect_links_no_tunnel():
@@ -57,7 +58,7 @@ def test_access_panel_hides_stale_llm_error_when_ollama_ok(monkeypatch):
                         {
                             "name": "ollama",
                             "ok": True,
-                            "detail": "1 models (huihui_ai/qwen2.5-vl-abliterated:7b)",
+                            "detail": "1 models (huihui_ai/qwen3-vl-abliterated:8b-instruct)",
                         }
                     ],
                 }

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

tests/test_doctor_llm.py

@@ -0,0 +1,61 @@
+"""Doctor LLM / Assistent local checks."""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+from gpu_rent.doctor import Check, _llm_assistent
+
+
+class _Cfg:
+    llm_runtime = "ollama"
+    ollama_models_manifest = None
+    extensions_manifest = None
+
+
+def test_llm_assistent_warns_without_ollama_yaml(tmp_path: Path, monkeypatch):
+    cfg = _Cfg()
+    cfg.ollama_models_manifest = tmp_path / "missing-ollama.yaml"
+    cfg.extensions_manifest = tmp_path / "extensions.yaml"
+    cfg.extensions_manifest.write_text(
+        "swarmui:\n"
+        "  - url: https://gitea.example/swarm-assistent.git\n"
+        "    dir: swarm-assistent\n"
+        "    requires: ollama\n",
+        encoding="utf-8",
+    )
+    monkeypatch.setattr(
+        "gpu_rent.paths.ollama_models_manifest_path",
+        lambda: cfg.ollama_models_manifest,
+    )
+    checks: list[Check] = []
+    _llm_assistent(cfg, checks)
+    names = {c.name: c for c in checks}
+    assert names["ollama-models.yaml"].ok is False
+    assert names["ollama-models.yaml"].blocking is True
+    assert names["Assistent ext"].ok is True
+
+
+def test_llm_assistent_ok_with_manifests(tmp_path: Path, monkeypatch):
+    ollama = tmp_path / "ollama-models.yaml"
+    ollama.write_text(
+        "models:\n  - name: foo:7b\n    use: chat\n    default: true\n",
+        encoding="utf-8",
+    )
+    ext = tmp_path / "extensions.yaml"
+    ext.write_text(
+        "swarmui:\n"
+        "  - url: https://gitea.example/swarm-assistent.git\n"
+        "    dir: swarm-assistent\n"
+        "    requires: ollama\n",
+        encoding="utf-8",
+    )
+    cfg = _Cfg()
+    cfg.ollama_models_manifest = ollama
+    cfg.extensions_manifest = ext
+    cfg.llm_runtime = "ollama"
+    checks: list[Check] = []
+    _llm_assistent(cfg, checks)
+    by = {c.name: c for c in checks}
+    assert by["ollama-models.yaml"].ok
+    assert "swarm-assistent" in by["Assistent ext"].detail

tests/test_llm_runtime.py

@@ -56,7 +56,9 @@ def test_write_preset(tmp_path: Path):
     path = tmp_path / "out.yaml"
     write_ollama_models_preset(path, "recommended")
     entries = parse_ollama_models(path)
-    assert entries[0].name == "huihui_ai/qwen2.5-vl-abliterated:7b"
+    assert entries[0].name == "huihui_ai/qwen3-vl-abliterated:8b-instruct"
+    assert entries[0].default is True
+    assert entries[1].name == "huihui_ai/qwen2.5-vl-abliterated:7b"
     write_ollama_models_preset(path, "big")
     assert parse_ollama_models(path)[0].name == "huihui_ai/qwen2.5-vl-abliterated:32b"
     write_ollama_models_preset(path, "text")

tests/test_ollama_warmup.py

@@ -43,10 +43,10 @@ def test_warmup_skips_when_ps_has_model(monkeypatch):
     def fake_urlopen(req, timeout=None):
         url = getattr(req, "full_url", str(req))
         assert "/api/ps" in url
-        return FakeResp('{"models":[{"name":"huihui_ai/qwen2.5-vl-abliterated:7b"}]}')
+        return FakeResp('{"models":[{"name":"huihui_ai/qwen3-vl-abliterated:8b-instruct"}]}')
 
     monkeypatch.setattr(_mod.urllib.request, "urlopen", fake_urlopen)
-    msg = _mod.warmup("huihui_ai/qwen2.5-vl-abliterated:7b", keep_alive="15m", num_ctx=16384, timeout=5)
+    msg = _mod.warmup("huihui_ai/qwen3-vl-abliterated:8b-instruct", keep_alive="15m", num_ctx=16384, timeout=5)
     assert "skip" in msg
     assert "VRAM" in msg
 

tests/test_perf_tiers.py

@@ -82,6 +82,6 @@ def test_ollama_mid_4090_context_16k():
     )
     tune = ollama_tune_for(info)
     assert tune.context_length == 16384
-    assert tune.keep_alive == "15m"
+    assert tune.keep_alive == "5m"
     assert "OLLAMA_CONTEXT_LENGTH=16384" in "\n".join(ollama_env_lines(tune))
-    assert "OLLAMA_KEEP_ALIVE=15m" in "\n".join(ollama_env_lines(tune))
+    assert "OLLAMA_KEEP_ALIVE=5m" in "\n".join(ollama_env_lines(tune))

tests/test_warm_up_skips.py

@@ -86,7 +86,7 @@ def test_install_ollama_skips_restart_when_unit_unchanged():
     text = files("gpu_rent.remote").joinpath("install_ollama.sh").read_text(encoding="utf-8")
     assert "cmp -s" in text
     assert "skip restart" in text
-    assert '"mid", 10 * 1024**3, "15m"' in text
+    assert '"mid", 10 * 1024**3, "5m"' in text
 
 
 def test_provision_llm_skips_on_api_tags_not_cli_list():