Files
computer-playbook/cli/administration/deploy/dedicated/runner.py
T
kevinveenbirkenbachandClaude Opus 4.7 8e293bd921 fix(compose-deploy): stop persisting runtime routing knobs into .env
Root cause of step-08 deploy failures across all 4 test-development
distros in run 26572559126: `make compose-deploy mode=reinstall
apps=web-app-dashboard INFINITO_SERVICES_DISABLED=matomo` (step 07)
made make export the cmdline var into the recipe's shell env, which
reached `runner.py` → `make setup` → `make dotenv`. The dotenv
generator's `setdefault` then baked the runtime-only value into the
on-disk `.env`. Step 08 sourced that .env, filtered `web-app-matomo`
out of its primary apps, and exited with "All primary apps disabled".

Fix:

- Drop the 7 routing knobs (apps, mode, purge, bundles, disable,
  full_cycle, variant) from `passthrough.STATIC_KEYS` and from
  `default.env`. They are per-invocation; .env is the persistent SPOT
  and must not capture them.
- Switch every consumer from `os.environ["KEY"]` strict access to
  `os.environ.get("KEY", "")` so the missing-key path stops at "no
  filter" instead of a KeyError.
- Rename the env-var surface to match the make-alias surface 1:1
  (lowercase): INFINITO_APPS → apps, INFINITO_SERVICES_DISABLED →
  disable, INFINITO_BUNDLES → bundles, INFINITO_FULL_CYCLE →
  full_cycle, INFINITO_VARIANT → variant, INFINITO_DEPLOY_MODE → mode,
  INFINITO_PURGE_ENTITIES → purge. The make alias was the user-facing
  name in every doc; routing-knob env vars now use the same name so
  the cmdline form, the recipe env-prefix, and the consumer reads
  all line up.
- Collapse the Makefile `compose-deploy` recipe to just the two
  knobs whose alias differs from the env name (`type` →
  INFINITO_DEPLOY_TYPE, `debug` → INFINITO_DEBUG). GNU Make
  auto-exports cmdline variables into the recipe's shell env, so the
  identical-name `$(if $(apps),apps="$(apps)")` lines were pure
  noise.
- Drop `disable: ${disable}` from compose.yml. The dev CLI builds
  `extra_env` per `docker exec` call and forwards `disable` via
  `-e`, so the container env never needs the value frozen at
  compose-up time.
- Update the 3 actual leak call sites
  (07/08/09_deploy_*.sh) to the make-alias form
  (`disable=matomo`, `full_cycle=true`, `variant=1`).
- Add `SIM112` to ruff's ignore set: the lowercase env names are
  the deliberate make/env parity, not a typo.

Repro before fix: `INFINITO_SERVICES_DISABLED=matomo make dotenv`
wrote `INFINITO_SERVICES_DISABLED=matomo` to `.env`. After fix:
`disable=matomo make dotenv` leaves `.env` untouched.

Tests: `make test` and `make autoformat` green (2711 tests, 8 lint
sub-targets).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-28 17:47:03 +02:00

166 lines
5.6 KiB
Python

from __future__ import annotations
import datetime
import os
import subprocess
import sys
from pathlib import Path
from typing import Any
from cli.administration.inventory.provision.services_disabler import (
ServicesDisabledConflictError,
assert_services_disabled_inventory_consistency_from_env,
)
from cli.meta.roles.services.called import verify as verify_required_system_services
from .proc import run, run_make
def run_ansible_playbook(
*,
repo_root: str,
playbook_path: str,
inventory_validator_path: str,
inventory: str,
modes: dict[str, Any],
limit: str | None = None,
allowed_applications: list[str] | None = None,
password_file: str | None = None,
verbose: int = 0,
skip_build: bool = False,
diff: bool = False,
ansible_args: list[str] | None = None,
) -> None:
"""Run ansible-playbook with the given parameters and execution modes."""
start_time = datetime.datetime.now(tz=datetime.UTC)
print(f"\n▶️ Script started at: {start_time.isoformat()}\n")
# ---------------------------------------------------------
# 1) Cleanup Phase (wrapper-level)
# ---------------------------------------------------------
if modes.get("MODE_CLEANUP", False):
print("\n🧹 Cleaning up...\n", flush=True)
run_make(repo_root, "clean")
else:
print("\n🧹 Cleanup skipped (MODE_CLEANUP not set or False)\n")
# ---------------------------------------------------------
# 2) Build Phase
# ---------------------------------------------------------
if not skip_build:
print("\n🛠️ Running project build (make setup)...\n")
run_make(repo_root, "setup")
else:
print("\n🛠️ Build skipped (--skip-build)\n")
# ---------------------------------------------------------
# 3) `disable` env var consistency guard
# ---------------------------------------------------------
try:
assert_services_disabled_inventory_consistency_from_env(
inventory_dir=Path(inventory).resolve().parent,
roles_dir=Path(repo_root).resolve() / "roles",
)
except ServicesDisabledConflictError as exc:
print(f"\n[ERROR] {exc}\n", file=sys.stderr)
sys.exit(1)
# ---------------------------------------------------------
# 4) Inventory Validation Phase
# ---------------------------------------------------------
if modes.get("MODE_ASSERT") is False:
print("\n🔍 Inventory assertion explicitly disabled (MODE_ASSERT=false)\n")
else:
print("\n🔍 Validating inventory before deployment...\n")
try:
run(
[sys.executable, inventory_validator_path, str(Path(inventory).parent)],
cwd=repo_root,
check=True,
)
except subprocess.CalledProcessError:
print(
"\n[ERROR] Inventory validation failed. Aborting deployment.\n",
file=sys.stderr,
)
sys.exit(1)
# ---------------------------------------------------------
# 5) Build ansible-playbook command
# ---------------------------------------------------------
cmd: list[str] = ["ansible-playbook", "-i", inventory, playbook_path]
if limit:
cmd.extend(["-l", limit])
# Wrapper-provided extra-vars first; user can override via passthrough -e later.
if allowed_applications:
joined = ",".join(allowed_applications)
cmd.extend(["-e", f"APPLICATIONS_WHITELIST={joined}"])
for key, value in modes.items():
val = str(value).lower() if isinstance(value, bool) else str(value)
cmd.extend(["-e", f"{key}={val}"])
if password_file:
cmd.extend(["--vault-password-file", password_file])
if diff:
cmd.append("--diff")
if modes.get("MODE_DEBUG", False):
verbose = max(verbose, 3)
if verbose:
cmd.append("-" + "v" * verbose)
# Native ansible-playbook flags passthrough (must come last for override behavior)
if ansible_args:
cmd.extend(ansible_args)
ansible_log_path = (
os.environ.get("ANSIBLE_LOG_PATH") or "/tmp/infinito-deploy.log" # noqa: S108
)
os.environ["ANSIBLE_LOG_PATH"] = ansible_log_path
try:
log_offset_before = Path(ansible_log_path).stat().st_size
except OSError:
log_offset_before = 0
print("\n🚀 Launching Ansible Playbook...\n")
result = subprocess.run(cmd, cwd=repo_root, check=False)
if result.returncode != 0:
print(
f"\n[ERROR] ansible-playbook exited with status {result.returncode}\n",
file=sys.stderr,
)
sys.exit(result.returncode)
if allowed_applications:
ok, missing = verify_required_system_services(
roles_dir=Path(repo_root) / "roles",
log_path=ansible_log_path,
log_byte_offset=log_offset_before,
deployed_role_ids=allowed_applications,
)
if not ok:
print(
f"\n[ERROR] required role(s) did not execute for deploy "
f"{allowed_applications}:",
file=sys.stderr,
)
for role in missing:
print(f" - {role}", file=sys.stderr)
print(
" See `required_by` declarations in roles/*/meta/services.yml — "
"the role(s) above must run on every deploy whose primaries match.",
file=sys.stderr,
)
sys.exit(2)
end_time = datetime.datetime.now(tz=datetime.UTC)
print(f"\n✅ Script ended at: {end_time.isoformat()}\n")
print(f"⏱️ Total execution time: {end_time - start_time}\n")