Make local inference limits and workstation setup reproducible
This commit is contained in:
admin committed
1 parent
7006991843
commit
8544abd2d4
28 files changed
+1022
-21
No files matched your search
@@ -0,0 +1,146 @@
|
||||
import hashlib
|
||||
import importlib.util
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
import shutil
|
||||
import subprocess
|
||||
import tempfile
|
||||
import unittest
|
||||
from unittest.mock import patch
|
||||
|
||||
ROOT = Path(__file__).resolve().parents[1]
|
||||
spec = importlib.util.spec_from_file_location("prepare", ROOT / "scripts/prepare-workstation.py")
|
||||
prepare = importlib.util.module_from_spec(spec)
|
||||
spec.loader.exec_module(prepare)
|
||||
|
||||
|
||||
class PreparationTests(unittest.TestCase):
|
||||
def setUp(self):
|
||||
self.temp = tempfile.TemporaryDirectory()
|
||||
self.addCleanup(self.temp.cleanup)
|
||||
self.root = Path(self.temp.name)
|
||||
self.data = b"test model weights"
|
||||
self.item = {"name": "weights.gguf", "sha256": hashlib.sha256(self.data).hexdigest(), "size": len(self.data)}
|
||||
self.group = {"repo": "owner/model", "revision": "a" * 40, "directory": "model/revision", "files": [self.item]}
|
||||
|
||||
def test_download_uses_fixed_revision_and_publishes_only_verified_file(self):
|
||||
def download(args, **kwargs):
|
||||
self.assertIn("/resolve/" + "a" * 40 + "/weights.gguf", args[-3])
|
||||
Path(args[-1]).write_bytes(self.data)
|
||||
with patch.object(prepare.subprocess, "run", side_effect=download):
|
||||
paths = prepare.ensure_model(self.group, self.root, True)
|
||||
self.assertEqual(paths[0].read_bytes(), self.data)
|
||||
self.assertFalse(paths[0].with_name("weights.gguf.part").exists())
|
||||
|
||||
def test_corrupt_download_cannot_become_live_model(self):
|
||||
with patch.object(prepare.subprocess, "run", side_effect=lambda args, **_: Path(args[-1]).write_bytes(b"broken")):
|
||||
with self.assertRaisesRegex(ValueError, "nicht aktiviert"):
|
||||
prepare.ensure_model(self.group, self.root, True)
|
||||
self.assertFalse((self.root / "model/revision/weights.gguf").exists())
|
||||
|
||||
def test_existing_wrong_file_is_preserved_without_download(self):
|
||||
path = self.root / "model/revision/weights.gguf"
|
||||
path.parent.mkdir(parents=True)
|
||||
path.write_bytes(b"user file")
|
||||
with patch.object(prepare.subprocess, "run") as download, self.assertRaises(ValueError):
|
||||
prepare.ensure_model(self.group, self.root, True)
|
||||
download.assert_not_called()
|
||||
self.assertEqual(path.read_bytes(), b"user file")
|
||||
|
||||
def test_config_merge_preserves_unrelated_settings_and_external_provider(self):
|
||||
config = {"terminal": {"backend": "docker"}, "plugins": {"enabled": ["private"]},
|
||||
"custom_providers": [{"name": "Other", "base_url": "https://other.invalid/v1", "model": "other"}]}
|
||||
updated = prepare.configure_hermes(config, True)
|
||||
self.assertEqual(updated["terminal"]["backend"], "docker")
|
||||
self.assertEqual(updated["plugins"]["enabled"], ["private"])
|
||||
self.assertEqual(updated["custom_providers"][0]["model"], "other")
|
||||
self.assertEqual(updated["custom_providers"][1]["extra_body"]["max_tokens"], 2048)
|
||||
self.assertEqual(updated["auxiliary"]["compression"]["base_url"], "http://127.0.0.1:8081/v1")
|
||||
|
||||
def test_existing_profiles_preserved_and_explicit_selection_backed_up(self):
|
||||
path = self.root / "llama.env"
|
||||
path.write_text("custom tuning\n")
|
||||
prepare.write_config(path, "generated\n")
|
||||
self.assertEqual(path.read_text(), "custom tuning\n")
|
||||
prepare.write_config(path, "generated\n", replace=True)
|
||||
prepare.write_config(path, "generated\n", replace=True)
|
||||
self.assertEqual(len(list(self.root.glob("llama.env.before-setup-*"))), 1)
|
||||
self.assertEqual(path.stat().st_mode & 0o777, 0o600)
|
||||
|
||||
def test_profiles_quote_other_user_paths_and_do_not_use_remote_hf_start(self):
|
||||
text = prepare.profile_config("routine", [self.root / "user space/model.gguf", self.root / "projector.gguf"])
|
||||
result = subprocess.run(["bash", "-c", text + '\nprintf "%s|%s|%s" "$LLAMA_MODEL" "$LLAMA_HF_REPO" "${LLAMA_ARGS[*]}"'], text=True, capture_output=True, check=True)
|
||||
self.assertTrue(result.stdout.startswith(str(self.root / "user space/model.gguf") + "||"))
|
||||
self.assertIn("--n-gpu-layers 99 --fit off", result.stdout)
|
||||
|
||||
def test_prepare_whole_new_workstation_offline_without_home_override(self):
|
||||
repository = self.root / "repository"
|
||||
(repository / "config").mkdir(parents=True)
|
||||
shutil.copy2(ROOT / "config/config.env.example", repository / "config")
|
||||
(repository / "config/models.lock.json").write_text(json.dumps({"models": {"routine": self.group}}))
|
||||
path = self.root / "models/model/revision/weights.gguf"
|
||||
path.parent.mkdir(parents=True)
|
||||
path.write_bytes(self.data)
|
||||
config = self.root / "config/hermes-stack-maintenance"
|
||||
hermes = self.root / "hermes/config.yaml"
|
||||
args = ["prepare", "--models", "routine", "--model-dir", str(self.root / "models"),
|
||||
"--config-dir", str(config), "--hermes-config", str(hermes),
|
||||
"--configure-hermes", "--select", "routine"]
|
||||
with patch.object(prepare, "ROOT", repository), patch("sys.argv", args), \
|
||||
patch.dict(os.environ, {"XDG_RUNTIME_DIR": str(self.root)}), \
|
||||
patch.object(prepare.subprocess, "check_output", return_value="inactive\n"):
|
||||
prepare.main()
|
||||
self.assertEqual((config / "llama.env").read_text(), (config / "llama-routine.env").read_text())
|
||||
self.assertIn("LLAMA_MAX_REQUEST_SECONDS=600", (config / "config.env").read_text())
|
||||
self.assertIn("run_budget_seconds: 1800", hermes.read_text())
|
||||
|
||||
def test_local_cron_unpin_does_not_touch_other_provider_jobs(self):
|
||||
path = self.root / "jobs.json"
|
||||
path.write_text(json.dumps({"jobs": [
|
||||
{"id": "local", "model": "qwen38-27b-local", "provider": "custom"},
|
||||
{"id": "cloud", "model": "qwen38-27b-local", "provider": "other"},
|
||||
{"id": "remote", "model": "qwen38-27b-local", "provider": "custom", "base_url": "https://other.invalid/v1"}]}))
|
||||
with patch.object(prepare.subprocess, "run") as edit:
|
||||
prepare.unpin_local_jobs(path)
|
||||
edit.assert_called_once_with(["hermes", "cron", "edit", "local", "--unpin"], check=True)
|
||||
|
||||
|
||||
class ModelSwitchTests(unittest.TestCase):
|
||||
def setUp(self):
|
||||
self.temp = tempfile.TemporaryDirectory()
|
||||
self.addCleanup(self.temp.cleanup)
|
||||
self.root = Path(self.temp.name)
|
||||
self.bin = self.root / "bin"
|
||||
self.bin.mkdir()
|
||||
self.config = self.root / "config/hermes-stack-maintenance"
|
||||
self.config.mkdir(parents=True)
|
||||
(self.config / "llama.env").write_text("LLAMA_MODEL=old.gguf\n")
|
||||
(self.config / "llama-routine.env").write_text("LLAMA_MODEL=new.gguf\n")
|
||||
shutil.copy2(ROOT / "libexec/hermes-stack-model", self.bin)
|
||||
for name, body in {"hermes-stack-llama-run": "exit 0",
|
||||
"systemctl": 'echo "$*" >>"$TEST_CALLS"; if [[ "$*" == *"restart llama-qwen"* && "${TEST_FAIL:-0}" == 1 ]]; then exit 1; fi',
|
||||
"curl": "echo '{\"status\":\"ok\"}'"}.items():
|
||||
p = self.bin / name
|
||||
p.write_text("#!/usr/bin/env bash\n" + body + "\n")
|
||||
p.chmod(0o755)
|
||||
self.env = dict(os.environ, PATH=str(self.bin) + ":" + os.environ["PATH"],
|
||||
XDG_CONFIG_HOME=str(self.config.parent), XDG_RUNTIME_DIR=str(self.root), TEST_CALLS=str(self.root / "calls"))
|
||||
|
||||
def test_successful_switch_through_path_entrypoint(self):
|
||||
(self.root / "entrypoint").symlink_to(self.bin / "hermes-stack-model")
|
||||
result = subprocess.run(["bash", str(self.root / "entrypoint"), "routine"], env=self.env, capture_output=True, text=True)
|
||||
self.assertEqual(result.returncode, 0, result.stderr)
|
||||
self.assertEqual((self.config / "llama.env").read_text(), "LLAMA_MODEL=new.gguf\n")
|
||||
self.assertIn("start hermes-gateway.service", (self.root / "calls").read_text())
|
||||
|
||||
def test_failed_switch_restores_configuration_and_still_attempts_gateway_start(self):
|
||||
result = subprocess.run(["bash", str(self.bin / "hermes-stack-model"), "routine"],
|
||||
env=dict(self.env, TEST_FAIL="1"), capture_output=True, text=True)
|
||||
self.assertNotEqual(result.returncode, 0)
|
||||
self.assertEqual((self.config / "llama.env").read_text(), "LLAMA_MODEL=old.gguf\n")
|
||||
self.assertIn("start hermes-gateway.service", (self.root / "calls").read_text())
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
Reference in new issue
Block a user