mirror of
https://github.com/dredx/prole.git
synced 2026-09-23 10:13:58 +00:00
Junie's session targeted the prompt "stabilize ./install.py -c conf/k3d.cfg
using strict TDD" — broad installer-side work, not the k3d-mirror Phase 3
brief I had filed (which she didn't pick up; phase-3 brief stays open). All
750 installer tests pass post-change.
What Junie produced:
install.py (NEW) Top-level CLI entry point. Was
imagined by the prompt but didn't
exist; this commit makes it real.
knoe/deployment.py (NEW) `KnoeDeployment` orchestrator for
the k3s service-mode deploy pipeline.
Wraps Ansible kubeconfig fetch,
opentofu apply, init_*.sh post-apply
scripts, and (optionally) supabase/
deploy.sh.
knoe/ui/screens/cluster.py Dual-cluster GKE kubecontext UI: prod env
knoe/ui/screens/cfg.py now shows separate "App Cluster:" and
"DB Cluster:" dropdowns instead of a
single "Kubernetes Context:" combo.
New _app_kubectx_combo + _db_kubectx_combo
widgets; new app/db_cluster_kubecontext
tk.StringVars.
knoe/core/{actions,env,milestones}.py
knoe/core/ops/storage.py
knoe/config.py, knoe/knoe_conf.py Plumbing changes for the dual-cluster
kubecontext flow + storage-class topology
detection cleanup.
knoe/tools/cleanup_cnpg_storage.py (NEW) Stand-alone cleanup utility.
tools/dashboard.sh (NEW) Dashboard helper.
conf/knoe.cfg (NEW) Master cfg generated by knoe_conf.
conf/dev/ (NEW) Dev-mode cfg directory.
conf/port-mapping.cfg Port mapping tweaks for k3d.
tests/installer/* (8 files) New + extended tests for the dual-cluster
tests/test_database_options.py TUI, kubecontext save flow, storage ops,
topology detection, deploy helpers,
database-options screen.
Issues found in Junie's working state and fixed here:
1. install.py was a 11-line import shim with no shebang, no `chmod +x`,
no `if __name__ == '__main__'` block. `./install.py -c conf/k3d.cfg`
returned `Permission denied` and `python install.py` did nothing.
Added `#!/usr/bin/env python3`, `chmod +x`, and a __main__ block
that delegates to `knoe.ui.screens.main()`. `./install.py --help`
now prints the canonical argparse help.
2. knoe/deployment.py had FIVE `subprocess.run()` call sites with no
`timeout=` argument (`_run_script`, `_run_cmd`, the Ansible playbook
fetch, `tofu init`, `tofu apply`). A hung child process — typical
failure mode is a script waiting on stdin or a stalled network
call — would lock up the installer indefinitely. Added timeouts:
- Ansible kubeconfig fetch: 120s
- tofu init: 300s
- tofu apply, _run_script, _run_cmd: bounded by new module
constant `_MILESTONE_TIMEOUT` (default 1800s = 30 min, override
via `KNOE_MILESTONE_TIMEOUT_SECONDS` env var).
`subprocess.TimeoutExpired` is caught explicitly; on timeout the
run helpers return exit code 124 (conventional timeout code).
3. `conf/k3d.cfg` was corrupted with MagicMock string-reprs on disk:
KNOE_CONF = <MagicMock name='Canvas().tk.call().strip()' id='4743999712'>
argocd.node_selector = <MagicMock name='mock.StringVar().get().strip()' id='...'>
Likely path: Junie ran `./install.py -c conf/k3d.cfg` interactively
in a non-Tk environment (or with a partially-mocked widget set) and
the installer's "save current state" path wrote the mock-objects'
`__repr__` strings into the cfg file. This commit reverts the cfg
to its pre-Junie state. **Followup: harden the cfg save path
against non-string widget values** — track separately.
4. The corrupted cfg caused the installer to call `os.makedirs()` on
the mock-string values, producing 10 directories on disk literally
named `<MagicMock name='Canvas().tk.call().strip()' id='4733210304'>/`
etc., with 5–86 files of install artifacts inside each. Removed.
The "final step is timing out" the user reported was almost certainly
issue #2 above: install.py walked the milestone pipeline, hit one of
the unbounded subprocess.run calls, and the wrapped command (probably
supabase/deploy.sh, which Junie was reading for context when her
session timed out) hung. With the timeouts in place that path now
exits cleanly with rc=124 instead of locking up.
Verification:
- pytest tests/installer/ -q 750 passed in ~25s
- python3 -c "import knoe.deployment" imports clean
- ./install.py --help prints argparse help
- find . -maxdepth 1 -type d -name '<MagicMock*' | wc -l 0
- head -7 conf/k3d.cfg clean (no MagicMock)
Out of scope for this commit (followups):
- The cfg save-path that wrote mock-objects-as-strings (issue #3 root cause).
Reproducer: launch the installer in an env where Tk widget vars are
`unittest.mock.MagicMock` instances. The cfg save code should refuse to
serialize non-str values rather than calling `str()` on a MagicMock.
- The k3d-mirror Phase 3 brief (`docs/plans/junie/k3d-knoe-auth-pod-deploy.md`)
is still open — Junie picked a different prompt this round.
Co-authored-by: Junie <junie@jetbrains.com>
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
139 lines
5.2 KiB
Python
139 lines
5.2 KiB
Python
import sys
|
|
import tkinter as tk
|
|
from pathlib import Path
|
|
from unittest.mock import MagicMock
|
|
|
|
import pytest
|
|
|
|
# Ensure `installer` is importable when tests are invoked directly via `pytest`
|
|
PROJECT_ROOT = Path(__file__).resolve().parents[2]
|
|
if str(PROJECT_ROOT) not in sys.path:
|
|
sys.path.insert(0, str(PROJECT_ROOT))
|
|
|
|
import knoe.ui.screens.cluster as cluster_mod
|
|
from knoe.ui.screens.base import ScreenBaseMixin
|
|
from knoe.ui.screens.cluster import ClusterScreenMixin
|
|
|
|
|
|
class _DummyClusterSaveApp(ScreenBaseMixin, ClusterScreenMixin):
|
|
"""Minimal surface to exercise the Cluster Environment screen Save behavior."""
|
|
|
|
def __init__(self, root: tk.Tk):
|
|
self.root = root
|
|
# Canvas is not required by `_validate_and_save_cluster_config`, but other mixins
|
|
# assume it exists.
|
|
self.bg_canvas = tk.Canvas(root, width=1, height=1)
|
|
self._canvas_items = []
|
|
self._overlay_widgets = []
|
|
|
|
self.cluster_env = tk.StringVar(master=root, value="service")
|
|
self.selected_k3d_cluster = tk.StringVar(master=root, value="")
|
|
self.selected_kubectx = tk.StringVar(master=root, value="")
|
|
self.service_namespace = tk.StringVar(master=root, value="knoe-system")
|
|
self.prod_artifacts_path = tk.StringVar(master=root, value=str(Path.home()))
|
|
|
|
self.k3s_server_url = tk.StringVar(master=root, value="")
|
|
self.k3s_token = tk.StringVar(master=root, value="")
|
|
|
|
self.supabase_enabled = tk.BooleanVar(master=root, value=False)
|
|
self.gitops_enabled = tk.BooleanVar(master=root, value=False)
|
|
self.kerberos_enabled = tk.BooleanVar(master=root, value=False)
|
|
self.at_rest_encryption_enabled = tk.BooleanVar(master=root, value=False)
|
|
|
|
# Minimal config structure required by `_validate_and_save_cluster_config`.
|
|
self.knoe_cfg_data = {
|
|
"Initialize Cluster": {
|
|
"ENVIRONMENT": "service",
|
|
"K3S_SERVER_URL": "",
|
|
"K3S_TOKEN": "",
|
|
},
|
|
"Global": {
|
|
# Keep old/new equal so we don't trigger the namespace cleanup prompt.
|
|
"SERVICE_NAMESPACE": "knoe-system",
|
|
},
|
|
"Optional Features": {},
|
|
"Prod Cluster (k8s)": {},
|
|
}
|
|
|
|
self.saved_calls = 0
|
|
self.status_check_calls = 0
|
|
|
|
def _save_knoe_cfg(self):
|
|
self.saved_calls += 1
|
|
|
|
def _verify_k3s_services(self):
|
|
self.status_check_calls += 1
|
|
|
|
|
|
def test_cluster_env_save_triggers_status_check(monkeypatch):
|
|
# Some test modules replace tkinter with MagicMocks at import-time.
|
|
if isinstance(sys.modules.get("tkinter"), MagicMock):
|
|
pytest.skip("tkinter is mocked in this test run")
|
|
|
|
# Avoid depending on a real kubeconfig file.
|
|
monkeypatch.setattr(cluster_mod, "_find_kubeconfig_file", lambda: "/tmp/kubeconfig")
|
|
# Avoid any real secret handling.
|
|
monkeypatch.setattr(cluster_mod, "_encrypt_cfg_secret", lambda s: s)
|
|
|
|
root = tk.Tk()
|
|
root.withdraw()
|
|
try:
|
|
app = _DummyClusterSaveApp(root)
|
|
|
|
assert app._validate_and_save_cluster_config() is True
|
|
assert app.saved_calls == 1
|
|
|
|
# Requirement: clicking Save should immediately run a status check.
|
|
assert app.status_check_calls == 1
|
|
finally:
|
|
try:
|
|
root.destroy()
|
|
except Exception:
|
|
pass
|
|
|
|
|
|
def test_cluster_env_prod_artifacts_dir_expands_knoe_home_from_cfg(monkeypatch, tmp_path):
|
|
# Some test modules replace tkinter with MagicMocks at import-time.
|
|
if isinstance(sys.modules.get("tkinter"), MagicMock):
|
|
pytest.skip("tkinter is mocked in this test run")
|
|
|
|
# Ensure `$KNOE_HOME` is NOT available as an OS env var; it must come from config.
|
|
monkeypatch.delenv("KNOE_HOME", raising=False)
|
|
monkeypatch.chdir(tmp_path)
|
|
monkeypatch.setattr(cluster_mod, "_encrypt_cfg_secret", lambda s: s)
|
|
monkeypatch.setattr(cluster_mod, "_find_kubeconfig_file", lambda: "/tmp/kubeconfig")
|
|
root = tk.Tk()
|
|
root.withdraw()
|
|
try:
|
|
app = _DummyClusterSaveApp(root)
|
|
# Stub out prod-specific helpers not present on the dummy.
|
|
app._ensure_prod_config_state = lambda: None
|
|
app._prod_put_config = lambda show_dialog=True: {"errors": []}
|
|
app._prod_payload_from_vars = lambda: {}
|
|
app.prod_config_api = MagicMock()
|
|
app.prod_config_api.post_plan.return_value = {"yaml": "", "opentofuVars": {}, "installPlan": [], "messages": []}
|
|
app.prod_tab_messages = tk.StringVar(master=root, value="")
|
|
|
|
# Switch to prod so the artifacts directory is validated/created.
|
|
app.cluster_env.set("prod")
|
|
|
|
# Provide KNOE_HOME via config data only.
|
|
knoe_home = tmp_path / "knoe-home"
|
|
knoe_home.mkdir(parents=True, exist_ok=True)
|
|
app.knoe_cfg_data.setdefault("System Environment", {})["KNOE_HOME"] = str(
|
|
knoe_home
|
|
)
|
|
|
|
# Use a path expression that previously would create a literal `$KNOE_HOME` dir.
|
|
app.prod_artifacts_path.set("$KNOE_HOME/staging")
|
|
|
|
assert app._validate_and_save_cluster_config() is True
|
|
|
|
assert (knoe_home / "staging").is_dir()
|
|
assert not (tmp_path / "$KNOE_HOME" / "staging").exists()
|
|
finally:
|
|
try:
|
|
root.destroy()
|
|
except Exception:
|
|
pass
|