Bump version to 0.2.0 and enhance documentation

- Updated version number in pyproject.toml and __init__.py to 0.2.0.
- Revised README.md to reflect the current state of the project, including usage instructions and setup steps.
- Improved CLI documentation in cli.md, adding details about new commands and their functionalities.
- Enhanced the quick start section in README.md for better clarity on initial setup.
- Updated local folder documentation to clarify file handling and commands.
- Added a new command for listing GPU flavors and improved error handling in the CLI.
- Implemented a watchdog feature in the tunnel to manage server states effectively.

tests/test_hold_killer.py

@@ -0,0 +1,111 @@
+"""Tests for hold parsing and idle-killer busy classification."""
+
+from __future__ import annotations
+
+import importlib.util
+from datetime import datetime, timezone
+from pathlib import Path
+
+import pytest
+
+from gpu_rent.errors import GpuRentError
+from gpu_rent.hold import _parse_until
+
+
+ROOT = Path(__file__).resolve().parents[1]
+REMOTE_KILLER = ROOT / "src" / "gpu_rent" / "remote" / "idle_killer.py"
+
+
+def _load_remote():
+    spec = importlib.util.spec_from_file_location("idle_killer_remote", REMOTE_KILLER)
+    assert spec and spec.loader
+    mod = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(mod)
+    return mod
+
+
+def test_parse_until_iso():
+    ts = _parse_until("2030-01-01T00:00:00+00:00")
+    assert ts == int(datetime(2030, 1, 1, tzinfo=timezone.utc).timestamp())
+
+
+def test_parse_until_unix():
+    assert _parse_until("1700000000") == 1700000000
+
+
+def test_parse_until_bad():
+    with pytest.raises(GpuRentError):
+        _parse_until("not-a-date")
+
+
+def test_classify_busy_from_status(monkeypatch):
+    mod = _load_remote()
+
+    class FakeResp:
+        def __init__(self, payload):
+            self._payload = payload
+
+        def read(self):
+            import json
+
+            return json.dumps(self._payload).encode()
+
+        def __enter__(self):
+            return self
+
+        def __exit__(self, *args):
+            return False
+
+    calls = {"n": 0}
+
+    def fake_urlopen(req, timeout=0, context=None):
+        calls["n"] += 1
+        url = getattr(req, "full_url", None) or req.get_full_url()
+        if "GetNewSession" in url:
+            return FakeResp({"session_id": "abc"})
+        return FakeResp(
+            {
+                "status": {"waiting_gens": 0, "live_gens": 0, "loading_models": 0},
+                "backend_status": {"status": "idle"},
+            }
+        )
+
+    monkeypatch.setattr(mod.urllib.request, "urlopen", fake_urlopen)
+    busy, detail = mod.swarm_busy("http://127.0.0.1:7801")
+    assert busy is False
+    assert "idle" in detail
+
+
+def test_classify_busy_queue(monkeypatch):
+    mod = _load_remote()
+
+    class FakeResp:
+        def __init__(self, payload):
+            self._payload = payload
+
+        def read(self):
+            import json
+
+            return json.dumps(self._payload).encode()
+
+        def __enter__(self):
+            return self
+
+        def __exit__(self, *args):
+            return False
+
+    def fake_urlopen(req, timeout=0, context=None):
+        url = getattr(req, "full_url", None) or req.get_full_url()
+        if "GetNewSession" in url:
+            return FakeResp({"session_id": "abc"})
+        return FakeResp(
+            {
+                "status": {"waiting_gens": 2, "live_gens": 0, "loading_models": 0},
+                "backend_status": {"status": "idle"},
+            }
+        )
+
+    monkeypatch.setattr(mod.urllib.request, "urlopen", fake_urlopen)
+    busy, detail = mod.swarm_busy("http://127.0.0.1:7801")
+    assert busy is True
+    assert "waiting=2" in detail

tests/test_ready_snapshot.py

@@ -0,0 +1,75 @@
+from gpu_rent.notify import print_mcp_snippet
+from gpu_rent.snapshot import ensure_boot_snapshot
+
+
+class _Cfg:
+    boot_snapshot_name = "gpu-rent-boot-ok"
+    swarmui_local_port = 17801
+    notify_ready = True
+
+
+def test_ensure_boot_snapshot_skips_existing():
+    class Snap:
+        id = "snap1"
+        name = "gpu-rent-boot-ok"
+
+    class Conn:
+        class block_storage:
+            @staticmethod
+            def create_snapshot(**kwargs):
+                raise AssertionError("should not create")
+
+    logs = []
+    import gpu_rent.snapshot as snap_mod
+
+    # monkey via attribute
+    orig = snap_mod.find_snapshot_by_name
+    snap_mod.find_snapshot_by_name = lambda conn, name: Snap()
+    try:
+        got = ensure_boot_snapshot(Conn(), boot_volume_id="v1", cfg=_Cfg(), log=logs.append)
+        assert got is not None
+        assert any("уже есть" in m for m in logs)
+    finally:
+        snap_mod.find_snapshot_by_name = orig
+
+
+def test_ensure_boot_snapshot_creates(monkeypatch):
+    created = {}
+
+    class Snap:
+        def __init__(self):
+            self.id = "new"
+            self.status = "creating"
+
+    class Conn:
+        class block_storage:
+            @staticmethod
+            def create_snapshot(**kwargs):
+                created.update(kwargs)
+                return Snap()
+
+            @staticmethod
+            def get_snapshot(sid):
+                s = Snap()
+                s.status = "available"
+                return s
+
+    import gpu_rent.snapshot as snap_mod
+
+    monkeypatch.setattr(snap_mod, "find_snapshot_by_name", lambda conn, name: None)
+    monkeypatch.setattr(snap_mod.time, "sleep", lambda s: None)
+    logs = []
+    got = ensure_boot_snapshot(Conn(), boot_volume_id="vol-1", cfg=_Cfg(), log=logs.append)
+    assert created["volume_id"] == "vol-1"
+    assert created["force"] is True
+    assert created["name"] == "gpu-rent-boot-ok"
+    assert got.status == "available"
+
+
+def test_mcp_snippet(capsys):
+    logs = []
+    print_mcp_snippet(_Cfg(), logs.append)
+    text = "\n".join(logs)
+    assert "17801/mcp" in text
+    assert "gpu-rent tunnel" in text
+    assert "mcp.json" in text

tests/test_resize.py

@@ -0,0 +1,32 @@
+import pytest
+
+from gpu_rent.errors import GpuRentError
+from gpu_rent.resize import resize_data_volume
+from gpu_rent.state import SessionState, save_state
+
+
+class _Cfg:
+    pass
+
+
+def test_resize_rejects_shrink(monkeypatch):
+    save_state(SessionState(data_volume_id="d1", floating_ip=None))
+
+    class Vol:
+        id = "d1"
+        size = 200
+        status = "in-use"
+
+    class Conn:
+        class block_storage:
+            @staticmethod
+            def get_volume(vid):
+                return Vol()
+
+            @staticmethod
+            def extend_volume(*a, **k):
+                raise AssertionError("no extend")
+
+    monkeypatch.setattr("gpu_rent.resize.connect", lambda cfg: Conn())
+    with pytest.raises(GpuRentError, match="вниз нельзя"):
+        resize_data_volume(_Cfg(), 100, log=lambda m: None)

tests/test_session.py

@@ -48,7 +48,14 @@ def test_cmd_up_does_not_create_second_gpu(monkeypatch):
     )
     monkeypatch.setattr("gpu_rent.session.wait_ssh", lambda cfg, host, timeout=420.0: None)
     monkeypatch.setattr("gpu_rent.session.run_bootstrap", lambda cfg, host, log: None)
-    monkeypatch.setattr("gpu_rent.session.provision_vm", lambda cfg, host, log: None)
+    monkeypatch.setattr("gpu_rent.session.provision_vm", lambda cfg, host, log, **kw: None)
+    monkeypatch.setattr("gpu_rent.session.wait_backend_idle", lambda cfg, host, log, **kw: None)
+    monkeypatch.setattr(
+        "gpu_rent.session.ensure_boot_snapshot",
+        lambda conn, boot_volume_id, cfg, log: None,
+    )
+    monkeypatch.setattr("gpu_rent.session.notify_ready", lambda cfg, log: None)
+    monkeypatch.setattr("gpu_rent.session.print_mcp_snippet", lambda cfg, log: None)
     monkeypatch.setattr(
         "gpu_rent.session.create_gpu_server",
         lambda *a, **k: created.append("created") or Server(),
@@ -79,7 +86,14 @@ def test_cmd_up_unshelves_expired(monkeypatch):
     )
     monkeypatch.setattr("gpu_rent.session.wait_ssh", lambda cfg, host, timeout=420.0: None)
     monkeypatch.setattr("gpu_rent.session.run_bootstrap", lambda cfg, host, log: None)
-    monkeypatch.setattr("gpu_rent.session.provision_vm", lambda cfg, host, log: None)
+    monkeypatch.setattr("gpu_rent.session.provision_vm", lambda cfg, host, log, **kw: None)
+    monkeypatch.setattr("gpu_rent.session.wait_backend_idle", lambda cfg, host, log, **kw: None)
+    monkeypatch.setattr(
+        "gpu_rent.session.ensure_boot_snapshot",
+        lambda conn, boot_volume_id, cfg, log: None,
+    )
+    monkeypatch.setattr("gpu_rent.session.notify_ready", lambda cfg, log: None)
+    monkeypatch.setattr("gpu_rent.session.print_mcp_snippet", lambda cfg, log: None)
     monkeypatch.setattr(
         "gpu_rent.session.create_gpu_server",
         lambda *a, **k: created.append("created"),

tests/test_tunnel_watch.py

@@ -0,0 +1,27 @@
+from gpu_rent.tunnel import decide_watch
+
+
+def test_decide_ok_active():
+    d = decide_watch("ACTIVE", tunnel_alive=True)
+    assert d.kind == "ok"
+
+
+def test_decide_reconnect_when_tunnel_dead():
+    d = decide_watch("ACTIVE", tunnel_alive=False)
+    assert d.kind == "reconnect"
+
+
+def test_decide_unshelve_expired():
+    for st in ("EXPIRED", "SHELVED", "SHELVED_OFFLOADED"):
+        d = decide_watch(st, tunnel_alive=True)
+        assert d.kind == "unshelve", st
+
+
+def test_decide_exit_error():
+    d = decide_watch("ERROR", tunnel_alive=True)
+    assert d.kind == "exit"
+
+
+def test_decide_exit_missing():
+    d = decide_watch(None, tunnel_alive=False)
+    assert d.kind == "exit"

tests/test_ux.py

@@ -0,0 +1,36 @@
+from gpu_rent.config import load_config
+from gpu_rent.inventory import FlavorInfo
+from gpu_rent.ux import cost_and_risk_lines, format_flavor_lines
+
+
+def test_format_flavor_lines_marks_pick():
+    ranked = [
+        FlavorInfo("a", "RTX 4090 24GB", 8, 32768, False, {}, "4090-24"),
+        FlavorInfo("b", "A5000", 8, 32768, False, {}, "a5000"),
+    ]
+    picked = ranked[0]
+    text = "\n".join(format_flavor_lines(ranked, picked))
+    assert "выберем" in text
+    assert "4090-24" in text
+
+
+def test_cost_lines_mention_disk_and_killer(monkeypatch, tmp_path):
+    monkeypatch.setenv("HOME", str(tmp_path))
+    monkeypatch.setenv("USERPROFILE", str(tmp_path))
+    monkeypatch.chdir(tmp_path)
+    for key in (
+        "OS_AUTH_URL",
+        "OS_USER_DOMAIN_NAME",
+        "OS_USERNAME",
+        "OS_PASSWORD",
+        "OS_PROJECT_ID",
+        "OS_REGION_NAME",
+        "GPU_RENT_AZ",
+    ):
+        monkeypatch.delenv(key, raising=False)
+    cfg = load_config(require_auth=False)
+    lines = cost_and_risk_lines(cfg, spot=True, flavor_name="GPU 4090")
+    blob = "\n".join(lines)
+    assert "24/7" in blob
+    assert "idle-killer" in blob
+    assert "панель" in blob.lower() or "Selectel" in blob