Files
cc-ci/runner/harness/abra.py
autonomic-bot e1147b5fe3 fix(2): F2-12 lasuite-drive upgrade tier — own convergence wait (abra -c) + collabora READY_PROBE
Adversary cold-verify FAILed Q3.2 (F2-12): the prev→PR-head chaos upgrade's abra converge monitor
FATAs while the NEW collabora 25.04.9.4.1's healthcheck is still in start_period (jail/config init),
even though it converges given swarm's healthcheck retries. My WOPI pre-gate fixed the OLD collabora
being killed mid-boot but not the NEW collabora's convergence. Flaky (3x green for me, 1x fail cold).

Fix (cc-ci-side, stronger verification — not weaker):
- abra.deploy gains no_converge_checks (`-c`); chaos_redeploy passes it for the upgrade op so abra's
  impatient monitor no longer FATAs (the stack spec is applied regardless).
- perform_upgrade now OWNS the convergence verification after the redeploy: wait_healthy (services
  N/N + app HEALTH_PATH) + new lifecycle.wait_ready_probes (recipe READY_PROBE), bounded by the
  recipe DEPLOY_TIMEOUT (generous) not abra's impatient window. meta threaded _perform_op→perform_upgrade.
- recipe_meta READY_PROBE hook (added to _load_meta whitelist): lasuite-drive probes collabora WOPI
  discovery (/hosting/discovery on collabora-<domain>) → 200. Called after install deploy AND after
  the upgrade redeploy. No-op for recipes without a READY_PROBE.

NOT re-claiming yet — validating the upgrade tier is now reliably green (incl. the slow-collabora
crossover) across multiple runs before re-claiming Q3.2. F2-12 stays open (Adversary-owned).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-05-29 11:55:53 +01:00

219 lines
8.7 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}")
subprocess.run(["git", "-C", path, "checkout", "--quiet", version], check=True)
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 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.
return _run_pty(["app", "backup", "create", domain, "-n", "-C", "-o"], timeout=timeout).stdout
def restore(domain: str, timeout: int = 900) -> None:
_run_pty(["app", "restore", domain, "-n", "-C", "-o"], timeout=timeout)
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 []