Enhance Ollama model management and performance tuning

- Updated the `provision_llm` function to utilize the `/api/tags` endpoint for verifying available models, improving accuracy in model management.
- Introduced a new `already_have_ollama_tag` function to ensure exact tag matching, preventing mismatches during model checks.
- Enhanced the `pull_stream` function to require a successful status from the API before proceeding, ensuring reliable model downloads.
- Added logic to handle unwritten blob files, improving the robustness of the model pulling process.
- Updated documentation and tests to reflect these changes, ensuring clarity and reliability in Ollama model operations.

tests/test_warm_up_skips.py

@@ -88,6 +88,18 @@ def test_install_ollama_skips_restart_when_unit_unchanged():
     assert "skip restart" in text
 
 
+def test_provision_llm_skips_on_api_tags_not_cli_list():
+    from pathlib import Path
+
+    from gpu_rent import provision
+
+    text = Path(provision.__file__).read_text(encoding="utf-8")
+    assert "_ollama_api_tags" in text
+    assert "awk 'NR>1" not in text
+    assert "GPU не гасим" in text
+    assert "без моделей из ollama-models.yaml" not in text
+
+
 def test_cli_has_update_flag():
     from gpu_rent import cli