Files
cc-ci/runner/harness/abra.py
autonomic-bot 9a7772563a style: repo-wide lint pass — make the lint gate green again
Push builds have been RED on the lint step since ~build 209 from accumulated
formatting drift. This is the mechanical cleanup: ruff format + ruff --fix
(UP038 isinstance unions, SIM105 contextlib.suppress, UP031 f-strings, SIM115
tempfile context manager), shfmt -i 2 -ci, nixpkgs-fmt/statix/deadnix (merged
attrsets, dropped unused lib args), yamllint, and shell quoting fixes in
tests/lasuite-docs/setup_custom_tests.sh. No behaviour changes intended;
lint: PASS, unit tests: 138 passed.
2026-06-09 21:56:15 +00:00

287 lines
12 KiB
Python

"""Thin, robust wrappers around the `abra` CLI for the CI harness (plan §4.3).
Bakes in the known abra gotchas (re-verify per installed abra version, currently 0.13.0-beta):
- `abra app undeploy` / `abra app volume remove` do NOT accept `--chaos` → never pass it.
- plumb a `timeout` through secret generate/insert/remove calls.
- `abra app ls -S -m` returns nested {server: {apps: [...]}} — parse the inner structure.
- run non-interactively with `-n` (`--no-input`) everywhere.
"""
from __future__ import annotations
import json
import subprocess
ABRA = "abra"
class AbraError(RuntimeError):
pass
def _run_pty(
args: list[str], timeout: int = 900, check: bool = True
) -> subprocess.CompletedProcess:
"""Run abra under a pseudo-TTY (via util-linux `script`). Needed for commands that exec into
a container interactively (backup create / restore: 'the input device is not a TTY')."""
cmd = "abra " + " ".join(args)
proc = subprocess.run(
["script", "-qec", cmd, "/dev/null"],
capture_output=True,
text=True,
timeout=timeout,
)
if check and proc.returncode != 0:
raise AbraError(f"[pty] {cmd} failed ({proc.returncode}):\n{proc.stdout}\n{proc.stderr}")
return proc
def _run(args: list[str], timeout: int = 300, check: bool = True) -> subprocess.CompletedProcess:
proc = subprocess.run(
[ABRA, *args],
capture_output=True,
text=True,
timeout=timeout,
)
if check and proc.returncode != 0:
raise AbraError(
f"abra {' '.join(args)} failed ({proc.returncode}):\n{proc.stdout}\n{proc.stderr}"
)
return proc
def app_new(
recipe: str,
domain: str,
server: str = "default",
version: str | None = None,
secrets: bool = False,
) -> None:
args = ["app", "new", recipe]
args += ["-s", server, "-D", domain, "-o", "-n"]
if version:
# pin to a published version tag (e.g. upgrade's previous-version deploy) — a clean tag
# checkout, which is incompatible with chaos.
args.append(version)
else:
# -C (chaos): deploy the recipe AT THE CURRENT CHECKOUT (the PR head under test).
args.append("-C")
if secrets:
args.append("-S")
_run(args)
def recipe_checkout(recipe: str, version: str) -> None:
"""git-checkout the recipe to a published version tag so the on-disk compose/.env match the pin.
`abra app new <recipe> <version>` records ENV VERSION but does NOT reliably check out the tag, and
a chaos (`-C`) deploy ignores ENV VERSION and uses the current checkout — together that silently
deployed LATEST for a 'previous-version' base, making the upgrade a no-op (Adversary F1d-2). With
this checkout + a non-chaos deploy, a pinned deploy genuinely deploys that version."""
import os
path = os.path.expanduser(f"~/.abra/recipes/{recipe}")
# -f (force): the version-pinning checkout must yield the EXACT ref tree. Without it, a cc-ci
# install_steps-provided overlay (e.g. discourse's compose.ccci.yml, copied into the pinned base)
# is an UNTRACKED file that collides with the same path TRACKED in a later ref, and
# `git checkout <ref>` aborts ("untracked working tree files would be overwritten"). Force resolves
# it by writing the ref's tracked version. Safe: we never want local recipe-tree state preserved
# across a version switch (and chaos deploys re-provide the overlay via install_steps when needed).
subprocess.run(["git", "-C", path, "checkout", "-f", "--quiet", version], check=True)
def has_lightweight_version_tags(recipe: str) -> bool:
"""True if the recipe's local checkout has any LIGHTWEIGHT (non-annotated) version tag.
Some upstream coop-cloud recipes ship a stray lightweight tag (e.g. lasuite-meet's
`0.3.0+v1.16.0`). abra's pinned (non-chaos) deploy runs `abra recipe lint`, which FATAs R014
('only annotated tags used for recipe version') for the WHOLE recipe — blocking the upgrade tier's
prev-version base deploy. (Re-annotating locally doesn't help: abra force-fetches tags from origin
before linting and reverts it; repointing origin to a local mirror tripped a go-git
'reference not found'.) The caller (deploy_app) uses this to fall back to a chaos base deploy
(which skips lint and deploys the explicitly-checked-out pinned version — see lifecycle.deploy_app).
Read-only: just `git tag` + `cat-file -t`; no fetch/mutation, so it can't trigger abra's revert."""
import os
path = os.path.expanduser(f"~/.abra/recipes/{recipe}")
tags = subprocess.run(
["git", "-C", path, "tag", "-l"], capture_output=True, text=True
).stdout.split()
for t in tags:
objtype = subprocess.run(
["git", "-C", path, "cat-file", "-t", t], capture_output=True, text=True
).stdout.strip()
if objtype == "commit": # lightweight (annotated tags are objtype "tag")
return True
return False
def env_set(domain: str, key: str, value: str) -> None:
"""Set a key in the app's .env (abra has no setter; edit the file directly)."""
import os
import re
path = os.path.expanduser(f"~/.abra/servers/default/{domain}.env")
with open(path) as fh:
lines = fh.read().splitlines()
out, seen = [], False
pat = re.compile(rf"^\s*#?\s*{re.escape(key)}=")
for ln in lines:
if pat.match(ln):
out.append(f"{key}={value}")
seen = True
else:
out.append(ln)
if not seen:
out.append(f"{key}={value}")
with open(path, "w") as fh:
fh.write("\n".join(out) + "\n")
def env_get(domain: str, key: str) -> str | None:
"""Read a key from the app's .env (last uncommented assignment wins). None if absent. Symmetric
with env_set; abra has no getter. Strips surrounding quotes from the value."""
import os
import re
path = os.path.expanduser(f"~/.abra/servers/default/{domain}.env")
if not os.path.exists(path):
return None
pat = re.compile(rf"^\s*{re.escape(key)}=(.*)$")
val = None
with open(path) as fh:
for ln in fh.read().splitlines():
m = pat.match(ln)
if m:
val = m.group(1).strip().strip('"').strip("'")
return val
def secret_generate(domain: str, timeout: int = 300) -> None:
# -m avoids the TTY/table (ioctl) path; output (which contains the generated values) is
# captured by _run and never logged. -C -o keep the recipe at the PR checkout (without -o it
# re-resolves to a version tag, dropping the PR's files incl. tests/). check=False: recipes with
# no secrets are a no-op.
_run(
["app", "secret", "generate", domain, "--all", "-m", "-C", "-o", "-n"],
timeout=timeout,
check=False,
)
def deploy(
domain: str, chaos: bool = True, timeout: int = 900, no_converge_checks: bool = False
) -> None:
args = ["app", "deploy", domain, "-o", "-n"]
if chaos:
args.append("-C")
if no_converge_checks:
# `-c`: skip abra's own post-deploy convergence monitor. Used by the upgrade chaos redeploy
# of heavy stacks (lasuite-drive): abra's monitor FATAs while a slow service (collabora's
# new-version jail/config init) is still becoming healthy, even though it converges given
# time. The caller then performs its OWN, stricter convergence+health wait (services N/N +
# app health + recipe READY_PROBE) with a generous deadline — see lifecycle.chaos_redeploy.
args.append("-c")
_run(args, timeout=timeout)
def upgrade(domain: str, version: str | None = None, timeout: int = 900) -> None:
args = ["app", "upgrade", domain]
if version:
args.append(version)
# -f no prompt, -D skip public-DNS checks, -o offline (local tags, no private-origin 401),
# -c no-converge-checks: abra's convergence poll gives up too early on a slow heavy rolling
# upgrade (e.g. lasuite-docs' 9-service stop-first roll while pulling new images) and reports a
# FALSE "deploy failed" even though all services do converge. We disable abra's check and rely on
# the harness's own wait_healthy + data-survival assertion (more patient + the real test) to gate
# the upgrade. A genuinely-failed upgrade still fails the test (app never gets healthy). upgrade
# has no --chaos flag.
args += ["-f", "-D", "-n", "-o", "-c"]
_run(args, timeout=timeout)
def backup_create(domain: str, timeout: int = 900) -> str:
# -C -o: use the current recipe checkout, no remote fetch — like every other recipe-touching
# call (DECISIONS.md). Without -o, abra tries to fetch recipe tags from the (possibly private)
# remote and fails "authentication required: Unauthorized". Returns the captured output, whose
# restic JSON summary line carries the produced "snapshot_id" (the backup artifact, DG3) — note
# `abra app backup snapshots` needs a TTY and is awkward to script, so we read the create output.
out = (
_run_pty(["app", "backup", "create", domain, "-n", "-C", "-o"], timeout=timeout).stdout
or ""
)
# Echo the backup output (incl. backupbot's pre-hook run / any "Failed to run command" or
# "Container ... not running" ERROR) into the run log. Backup is otherwise opaque: a pre-hook that
# fails to register/run leaves the DB dump out of the snapshot, surfacing only as a downstream
# restore RED with no cause. Bounded tail keeps it readable.
print(f" [backup output]\n{out[-4000:]}", flush=True)
return out
def restore(domain: str, timeout: int = 900) -> None:
# Echo the restore output (incl. backupbot's restore.post-hook stdout/stderr, e.g. a recipe's
# pg_backup.sh reimport) into the run log. Restore is otherwise opaque: a post-hook that fails or
# silently no-ops shows up only as a downstream data-integrity assertion RED with no cause. Bounded
# tail keeps it readable.
out = _run_pty(["app", "restore", domain, "-n", "-C", "-o"], timeout=timeout).stdout or ""
tail = out[-4000:]
print(f" [restore output]\n{tail}", flush=True)
def recipe_head_commit(recipe: str) -> str | None:
"""The current HEAD commit of the recipe checkout — captured right after fetch (the PR head, or
the catalogue current) so the upgrade tier can re-checkout it for the chaos redeploy after the
prev-tag base deploy reset the working tree (HC1)."""
import os
path = os.path.expanduser(f"~/.abra/recipes/{recipe}")
proc = subprocess.run(["git", "-C", path, "rev-parse", "HEAD"], capture_output=True, text=True)
out = proc.stdout.strip()
return out or None
def recipe_versions(recipe: str) -> list[str]:
"""Published versions of a recipe, oldest→newest (from the recipe git tags)."""
import os
import subprocess
path = os.path.expanduser(f"~/.abra/recipes/{recipe}")
proc = subprocess.run(
["git", "-C", path, "tag", "--sort=creatordate"], capture_output=True, text=True
)
return [t for t in proc.stdout.split("\n") if t.strip()]
def undeploy(domain: str, timeout: int = 600) -> None:
# NB: no --chaos here (unsupported).
_run(["app", "undeploy", domain, "-n"], timeout=timeout, check=False)
def volume_remove(domain: str, timeout: int = 300) -> None:
# NB: no --chaos here (unsupported); -f to skip prompts.
_run(["app", "volume", "remove", domain, "-f", "-n"], timeout=timeout, check=False)
def secret_remove_all(domain: str, timeout: int = 300) -> None:
_run(["app", "secret", "remove", domain, "--all", "-n"], timeout=timeout, check=False)
def app_config_remove(domain: str, server: str = "default") -> None:
"""Delete the app's .env config so a re-run can recreate it (teardown completeness)."""
import contextlib
import os
path = os.path.expanduser(f"~/.abra/servers/{server}/{domain}.env")
with contextlib.suppress(FileNotFoundError):
os.remove(path)
def app_ls(server: str = "default") -> list[dict]:
"""Parse `abra app ls -S -m` nested {server: {apps: [...]}} structure."""
proc = _run(["app", "ls", "-S", "-m", "-n"], check=False)
try:
data = json.loads(proc.stdout)
except (ValueError, json.JSONDecodeError):
return []
node = data.get(server) or {}
return node.get("apps", []) if isinstance(node, dict) else []