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>
178 lines
5.3 KiB
Python
178 lines
5.3 KiB
Python
from __future__ import annotations
|
|
|
|
|
|
from pathlib import Path
|
|
|
|
|
|
from knoe.ui.screens.cfg import ConfigMixin
|
|
|
|
|
|
class _Var:
|
|
def __init__(self, value: str):
|
|
self._value = value
|
|
|
|
def get(self) -> str:
|
|
return self._value
|
|
|
|
|
|
class _DummyCfgApp(ConfigMixin):
|
|
def __init__(
|
|
self,
|
|
conf_dir: Path,
|
|
kubectx: str,
|
|
*,
|
|
mode: str = "k3d",
|
|
cluster_env: str = "dev",
|
|
service_namespace_input: str = "knoe-system",
|
|
resolved_service_namespace: str = "knoe-system",
|
|
existing_global: dict | None = None,
|
|
):
|
|
self._conf_dir = conf_dir
|
|
self._cfg_path_override = conf_dir / "knoe.cfg"
|
|
self._mode = mode
|
|
self._resolved_service_namespace = resolved_service_namespace
|
|
|
|
# Minimal surface required by ConfigMixin._save_knoe_cfg
|
|
self.cluster_env = _Var(cluster_env)
|
|
self.selected_kubectx = _Var(kubectx)
|
|
self.db_username = _Var("knoe-db")
|
|
self.db_password = _Var("secret")
|
|
self.db_namespace = _Var("knoe-system")
|
|
self.cnpg_cluster_name = _Var("knoe-db")
|
|
self.db_host_port = _Var("5432")
|
|
self.supabase_pv_node = _Var("")
|
|
self.supabase_pv_base_dir = _Var("")
|
|
self.gitops_node_selector = _Var("")
|
|
self.argocd_node_selector = _Var("")
|
|
self.k3s_server_url = _Var("")
|
|
self.k3s_token = _Var("")
|
|
self.prod_artifacts_path = _Var(str(conf_dir))
|
|
|
|
self.service_namespace = _Var(service_namespace_input)
|
|
|
|
self.knoe_cfg_data = {
|
|
"Global": dict(existing_global or {}),
|
|
"Initialize Cluster": {},
|
|
"Dev Cluster (k3d)": {},
|
|
"Service Cluster (k3s)": {},
|
|
"Prod Cluster (k8s)": {},
|
|
}
|
|
|
|
def _resolve_knoe_conf_dir(self) -> Path:
|
|
return self._conf_dir
|
|
|
|
def _deployment_mode(self) -> str:
|
|
return self._mode
|
|
|
|
def _get_service_namespace(self) -> str:
|
|
return self._resolved_service_namespace
|
|
|
|
def _secret_cfg_value(self, _section: str, _key: str, value: str, *_args) -> str:
|
|
return value
|
|
|
|
def _save_ansible_knoe_vault(self, _db_password: str):
|
|
return None
|
|
|
|
def _sanitize_sections_for_cfg(self, sections: dict) -> dict:
|
|
return sections
|
|
|
|
def _sync_port_forward_mappings(self):
|
|
# Not relevant for this unit test; avoids requiring optional-feature vars.
|
|
return None
|
|
|
|
def _collect_input_snapshot(self) -> dict:
|
|
return {}
|
|
|
|
|
|
def test_save_knoe_cfg_persists_kubecontext(tmp_path, monkeypatch):
|
|
# Avoid touching real env activation during unit test.
|
|
import knoe.ui.screens.cfg as cfg_mod
|
|
|
|
monkeypatch.setattr(cfg_mod.knoe_conf, "activate_environment", lambda *_a, **_k: None)
|
|
|
|
app = _DummyCfgApp(conf_dir=tmp_path, kubectx="k3d-knoe-system")
|
|
app._save_knoe_cfg()
|
|
|
|
text = (tmp_path / "knoe.cfg").read_text(encoding="utf-8")
|
|
assert "KUBECONTEXT" in text
|
|
assert "k3d-knoe-system" in text
|
|
|
|
|
|
def test_save_knoe_cfg_service_mode_drops_generated_localhost_values(
|
|
tmp_path, monkeypatch
|
|
):
|
|
import knoe.ui.screens.cfg as cfg_mod
|
|
|
|
monkeypatch.setattr(cfg_mod.knoe_conf, "activate_environment", lambda *_a, **_k: None)
|
|
|
|
app = _DummyCfgApp(
|
|
conf_dir=tmp_path,
|
|
kubectx="",
|
|
mode="k3s",
|
|
cluster_env="service",
|
|
service_namespace_input="",
|
|
resolved_service_namespace="knoe-system",
|
|
existing_global={
|
|
"SERVICE_HOSTNAME": "k3d.localhost",
|
|
"API_SERVICE_ENDPOINT": "http://localhost:8081",
|
|
"PROLE_OPENTOFU_URL": "http://127.0.0.1:8080",
|
|
},
|
|
)
|
|
app._save_knoe_cfg()
|
|
|
|
text = (tmp_path / "knoe.cfg").read_text(encoding="utf-8")
|
|
assert "SERVICE_HOSTNAME" not in text
|
|
assert "API_SERVICE_ENDPOINT" not in text
|
|
assert "localhost" not in text
|
|
assert "SERVICE_NAMESPACE" not in text
|
|
|
|
|
|
def test_save_knoe_cfg_service_mode_keeps_explicit_service_namespace(
|
|
tmp_path, monkeypatch
|
|
):
|
|
import knoe.ui.screens.cfg as cfg_mod
|
|
|
|
monkeypatch.setattr(cfg_mod.knoe_conf, "activate_environment", lambda *_a, **_k: None)
|
|
|
|
app = _DummyCfgApp(
|
|
conf_dir=tmp_path,
|
|
kubectx="",
|
|
mode="k3s",
|
|
cluster_env="service",
|
|
service_namespace_input="explicit-ns",
|
|
resolved_service_namespace="explicit-ns",
|
|
)
|
|
app._save_knoe_cfg()
|
|
|
|
text = (tmp_path / "knoe.cfg").read_text(encoding="utf-8")
|
|
assert "SERVICE_NAMESPACE = explicit-ns" in text
|
|
|
|
|
|
def test_save_knoe_cfg_service_mode_repeated_saves_remain_clean(tmp_path, monkeypatch):
|
|
import knoe.ui.screens.cfg as cfg_mod
|
|
|
|
monkeypatch.setattr(cfg_mod.knoe_conf, "activate_environment", lambda *_a, **_k: None)
|
|
|
|
app = _DummyCfgApp(
|
|
conf_dir=tmp_path,
|
|
kubectx="",
|
|
mode="k3s",
|
|
cluster_env="service",
|
|
service_namespace_input="",
|
|
resolved_service_namespace="knoe-system",
|
|
existing_global={
|
|
"SERVICE_HOSTNAME": "k3d.localhost",
|
|
"API_SERVICE_ENDPOINT": "http://localhost:8081",
|
|
},
|
|
)
|
|
|
|
app._save_knoe_cfg()
|
|
first = (tmp_path / "knoe.cfg").read_text(encoding="utf-8")
|
|
app._save_knoe_cfg()
|
|
second = (tmp_path / "knoe.cfg").read_text(encoding="utf-8")
|
|
|
|
for text in (first, second):
|
|
assert "SERVICE_HOSTNAME" not in text
|
|
assert "API_SERVICE_ENDPOINT" not in text
|
|
assert "localhost" not in text
|