Compare commits
1 Commits
test/plaus
...
regression
| Author | SHA1 | Date | |
|---|---|---|---|
| 73427d6e36 |
19
tests/custom-html-bkp-bad/ops.py
Normal file
19
tests/custom-html-bkp-bad/ops.py
Normal file
@ -0,0 +1,19 @@
|
||||
"""custom-html-bkp-bad — lifecycle ops for bad-backup/bad-restore RED canaries.
|
||||
|
||||
Intentionally has NO pre_backup hook: the marker is never seeded before backup,
|
||||
so the backup snapshot has no ci-marker.txt. pre_restore writes "mutated" so that if
|
||||
restore DOES bring back the snapshot, the marker is gone/still-mutated → test fails.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from harness import lifecycle
|
||||
|
||||
MARKER_PATH = "/usr/share/nginx/html/ci-marker.txt"
|
||||
|
||||
|
||||
def pre_restore(domain: str, meta: dict) -> None:
|
||||
"""Write 'mutated' to the marker before restore runs. If restore brings back the
|
||||
snapshot (which has no marker — never seeded by pre_backup), the marker ends up
|
||||
MISSING or 'mutated' after restore → test_restore_returns_state FAILS → restore=RED."""
|
||||
lifecycle.exec_in_app(domain, ["sh", "-c", f"echo mutated > {MARKER_PATH}"])
|
||||
5
tests/custom-html-bkp-bad/recipe_meta.py
Normal file
5
tests/custom-html-bkp-bad/recipe_meta.py
Normal file
@ -0,0 +1,5 @@
|
||||
# custom-html-bkp-bad — regression fixture for bad-backup canary.
|
||||
# This recipe is custom-html WITHOUT backupbot labels. Setting BACKUP_CAPABLE=True here forces the
|
||||
# harness to run the backup tier; the recipe itself has no backupbot service, so
|
||||
# `abra app backup create` produces no snapshot → test_backup_artifact fails → backup tier RED.
|
||||
BACKUP_CAPABLE = True
|
||||
28
tests/custom-html-bkp-bad/test_backup.py
Normal file
28
tests/custom-html-bkp-bad/test_backup.py
Normal file
@ -0,0 +1,28 @@
|
||||
"""custom-html-bkp-bad — BACKUP assertion (bad-backup RED canary).
|
||||
|
||||
This recipe has no ops.py::pre_backup, so ci-marker.txt is NEVER seeded before the backup.
|
||||
Asserting its presence here causes backup tier RED — proving the server catches a recipe that
|
||||
claims backup support but doesn't actually back up the expected data.
|
||||
"""
|
||||
|
||||
import os
|
||||
import sys
|
||||
|
||||
sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "..", "runner"))
|
||||
from harness import lifecycle # noqa: E402
|
||||
|
||||
MARKER_PATH = "/usr/share/nginx/html/ci-marker.txt"
|
||||
|
||||
|
||||
def test_backup_captures_state(live_app):
|
||||
"""Assert the pre-backup marker is present and equals 'original'.
|
||||
|
||||
Since custom-html-bkp-bad has no ops.py::pre_backup to seed the marker, this file does NOT
|
||||
exist at backup time — exec_in_app returns empty or raises → assertion fails → backup tier RED.
|
||||
This models a recipe that declares backup capability but omits the data-seeding hook."""
|
||||
result = lifecycle.exec_in_app(live_app, ["sh", "-c", f"cat {MARKER_PATH} 2>/dev/null || echo MISSING"]).strip()
|
||||
assert result == "original", (
|
||||
f"backup did not capture the expected marker at {MARKER_PATH}: got {result!r}. "
|
||||
"Expected 'original' (seeded by pre_backup). If the marker is 'MISSING', the pre_backup "
|
||||
"hook was not run — this is the intended failure for the bad-backup RED canary."
|
||||
)
|
||||
25
tests/custom-html-bkp-bad/test_restore.py
Normal file
25
tests/custom-html-bkp-bad/test_restore.py
Normal file
@ -0,0 +1,25 @@
|
||||
"""custom-html-bkp-bad — RESTORE assertion (bad-restore RED canary).
|
||||
|
||||
pre_restore seeds 'mutated' to ci-marker.txt. The backup snapshot has no ci-marker.txt
|
||||
(never seeded by pre_backup). After restore, the marker is either MISSING or 'mutated' —
|
||||
never 'original' — so this assertion FAILS → restore tier RED.
|
||||
"""
|
||||
|
||||
import os
|
||||
import sys
|
||||
|
||||
sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "..", "runner"))
|
||||
from harness import lifecycle # noqa: E402
|
||||
|
||||
MARKER_PATH = "/usr/share/nginx/html/ci-marker.txt"
|
||||
|
||||
|
||||
def test_restore_returns_state(live_app):
|
||||
result = lifecycle.exec_in_app(
|
||||
live_app, ["sh", "-c", f"cat {MARKER_PATH} 2>/dev/null || echo MISSING"]
|
||||
).strip()
|
||||
assert result == "original", (
|
||||
f"restore did not return the pre-mutation (backed-up) state: got {result!r}. "
|
||||
"Expected 'original'. The backup had no marker (not seeded by pre_backup), so "
|
||||
"restore cannot recover it — this is the intended failure for the bad-restore RED canary."
|
||||
)
|
||||
15
tests/custom-html-rst-bad/ops.py
Normal file
15
tests/custom-html-rst-bad/ops.py
Normal file
@ -0,0 +1,15 @@
|
||||
"""custom-html-rst-bad — lifecycle ops for bad-restore RED canary.
|
||||
|
||||
NO pre_backup hook: marker never seeded before backup → snapshot has no ci-marker.txt.
|
||||
pre_restore writes "mutated". After restore, marker stays "mutated" (not in snapshot) → FAIL.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from harness import lifecycle
|
||||
|
||||
MARKER_PATH = "/usr/share/nginx/html/ci-marker.txt"
|
||||
|
||||
|
||||
def pre_restore(domain: str, meta: dict) -> None:
|
||||
lifecycle.exec_in_app(domain, ["sh", "-c", f"echo mutated > {MARKER_PATH}"])
|
||||
3
tests/custom-html-rst-bad/recipe_meta.py
Normal file
3
tests/custom-html-rst-bad/recipe_meta.py
Normal file
@ -0,0 +1,3 @@
|
||||
# custom-html-rst-bad — regression fixture for bad-restore canary.
|
||||
# BACKUP_CAPABLE=True forces the backup tier to run even though the recipe has no backupbot label.
|
||||
BACKUP_CAPABLE = True
|
||||
23
tests/custom-html-rst-bad/test_restore.py
Normal file
23
tests/custom-html-rst-bad/test_restore.py
Normal file
@ -0,0 +1,23 @@
|
||||
"""custom-html-rst-bad — RESTORE assertion (bad-restore RED canary).
|
||||
|
||||
No pre_backup → backup snapshot has no ci-marker.txt. pre_restore writes "mutated".
|
||||
After restore: marker is "mutated" (restore can't recover "original" — wasn't backed up) → FAIL.
|
||||
"""
|
||||
|
||||
import os
|
||||
import sys
|
||||
|
||||
sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "..", "runner"))
|
||||
from harness import lifecycle # noqa: E402
|
||||
|
||||
MARKER_PATH = "/usr/share/nginx/html/ci-marker.txt"
|
||||
|
||||
|
||||
def test_restore_returns_state(live_app):
|
||||
result = lifecycle.exec_in_app(
|
||||
live_app, ["sh", "-c", f"cat {MARKER_PATH} 2>/dev/null || echo MISSING"]
|
||||
).strip()
|
||||
assert result == "original", (
|
||||
f"restore did not return the pre-mutation (backed-up) state: got {result!r}. "
|
||||
"Expected 'original'. The backup had no marker, so restore cannot recover it."
|
||||
)
|
||||
136
tests/regression/README.md
Normal file
136
tests/regression/README.md
Normal file
@ -0,0 +1,136 @@
|
||||
# Regression canaries — E2E self-tests for the cc-ci server
|
||||
|
||||
A standing pytest suite that drives the **real** cc-ci lifecycle harness against pinned canary
|
||||
recipes and verifies both halves of the server's job:
|
||||
|
||||
1. **Good canaries** — healthy apps are reported GREEN (install + upgrade + backup/restore pass).
|
||||
2. **Bad canary** — broken apps are caught RED; a false-green makes the regression test itself fail.
|
||||
|
||||
These tests run the full cold lifecycle on the live cc-ci server. They are **slow** (minutes per
|
||||
canary) and **opt-in** — kept out of the per-commit fast path by the `canary` marker.
|
||||
|
||||
---
|
||||
|
||||
## How to run
|
||||
|
||||
Run on the cc-ci server (abra + Docker + Swarm required):
|
||||
|
||||
```bash
|
||||
ssh cc-ci
|
||||
cd /root/cc-ci # or wherever the repo is checked out
|
||||
cc-ci-run python -m pytest tests/regression/ -m canary -v
|
||||
```
|
||||
|
||||
Or a single canary:
|
||||
|
||||
```bash
|
||||
cc-ci-run python -m pytest tests/regression/ -m canary -k good-simple -v
|
||||
```
|
||||
|
||||
From the orchestrator:
|
||||
|
||||
```bash
|
||||
ssh cc-ci "cd /root/cc-ci && cc-ci-run python -m pytest tests/regression/ -m canary -v"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Canaries
|
||||
|
||||
| ID | Recipe | Purpose | Expected verdict |
|
||||
|----|--------|---------|-----------------|
|
||||
| `good-simple` | `custom-html-tiny` | Minimal static server — fast signal | GREEN |
|
||||
| `good-significant` | `lasuite-docs` | Multi-service (backend + Postgres + Collabora + OIDC) | GREEN |
|
||||
| `bad-false-green` | `custom-html` @ `v5-stale-docroot` | App is UP but serves wrong Content-Type — catches false-green | RED |
|
||||
|
||||
### Why the bad canary exists
|
||||
|
||||
The scariest regression is a **false-green**: the server reports PASS while the app is broken.
|
||||
We already saw a fabricated full-PASS during the build. The `bad-false-green` canary pins a known-
|
||||
broken fixture (`v5-stale-docroot`: nginx serves `.txt` as `application/octet-stream`). The
|
||||
harness's `test_content_type_html_and_txt` catches this and returns RED (build #75 was RED for
|
||||
exactly this fixture).
|
||||
|
||||
The regression test asserts `rc != 0`. If the harness ever wrongly returns green for this fixture,
|
||||
that assert fires — false-green is caught before any merge.
|
||||
|
||||
---
|
||||
|
||||
## What each canary verifies
|
||||
|
||||
### Per-tier semantic assertions (the "teeth")
|
||||
|
||||
The tests assert MORE than the harness exit code: they check that **specific named assertions**
|
||||
ran and got the expected result. This guards against a different failure mode — a tier that
|
||||
nominally "passes" because the assertion was silently removed or made vacuous.
|
||||
|
||||
| Stage | Test name | What it proves |
|
||||
|-------|-----------|---------------|
|
||||
| install | `test_serving` | Generic HTTP readiness check actually ran |
|
||||
| install | `test_serving_and_frontend` | Lasuite-docs frontend (SPA shell) actually loaded |
|
||||
| custom | `test_content_type` | Content-type assertion actually ran (bad canary only) |
|
||||
|
||||
If a tier assertion is removed: the named test disappears from `results.json` → the semantic
|
||||
check fires → the regression suite catches the removal.
|
||||
|
||||
### Additional structural assertions (good canaries)
|
||||
|
||||
- `install` tier: "pass" (not fail, not skip)
|
||||
- No tier is "fail" (skips acceptable for recipes without backup/custom tests)
|
||||
- `flags.clean_teardown = True` (no leftover containers/volumes/secrets)
|
||||
- `flags.no_secret_leak = True` (no secret value in the results artifact)
|
||||
|
||||
---
|
||||
|
||||
## Cadence policy
|
||||
|
||||
**Do NOT run on every commit or PR.** These are slow and resource-heavy. Run them:
|
||||
|
||||
- Before a **release** of the cc-ci server (after a batch of server changes).
|
||||
- As a **polishing pass** or pre-merge check for significant server refactors.
|
||||
- On-demand when you suspect a regression: `pytest -m canary`.
|
||||
|
||||
They are NOT wired to the per-commit Drone pipeline. If adding a `!testme`-style trigger for the
|
||||
cc-ci repo, gate it behind a deliberate label (e.g. `run-canaries`) — not an automatic run on
|
||||
every push.
|
||||
|
||||
---
|
||||
|
||||
## How to add a canary
|
||||
|
||||
1. Identify a recipe that is already deployable and has pinned version tags.
|
||||
2. Decide the expected verdict (GREEN or RED) and which tier assertions have teeth.
|
||||
3. Add an entry to `CANARIES` in `test_canaries.py`:
|
||||
|
||||
```python
|
||||
{
|
||||
"id": "good-myrecipe",
|
||||
"recipe": "my-recipe",
|
||||
"src": "recipe-maintainers/my-recipe",
|
||||
"ref": "<pinned-sha>", # pin to a specific commit for stability
|
||||
"expected_green": True,
|
||||
"stage_pass_checks": [
|
||||
("install", "test_serving"), # verify this named test ran and passed
|
||||
],
|
||||
"stage_fail_checks": [],
|
||||
}
|
||||
```
|
||||
|
||||
4. Run the canary once to confirm it passes:
|
||||
`cc-ci-run python -m pytest tests/regression/ -m canary -k good-myrecipe -v`
|
||||
|
||||
5. Update the pin comment with the date and the recipe version it was pinned at.
|
||||
|
||||
---
|
||||
|
||||
## Pin maintenance
|
||||
|
||||
Canary refs are pinned to specific SHAs for stability. When a recipe publishes a new release:
|
||||
|
||||
1. Update the `"ref"` SHA in the canary definition (use the new main-branch HEAD).
|
||||
2. Update the pin comment with the new date/version.
|
||||
3. Re-run the canary to confirm GREEN before committing the pin update.
|
||||
|
||||
The bad canary (`v5-stale-docroot`) is a stable fixture branch — update only if the branch is
|
||||
deleted. If deleted, recreate the pattern: an app that is up + passes lifecycle tiers but fails
|
||||
one functional assertion.
|
||||
106
tests/regression/conftest.py
Normal file
106
tests/regression/conftest.py
Normal file
@ -0,0 +1,106 @@
|
||||
"""Shared fixtures and helpers for E2E canary regression tests.
|
||||
|
||||
The regression tests call the real cc-ci harness (run_recipe_ci.py) as a subprocess and assert on
|
||||
its outputs (exit code, results.json). They run ON the cc-ci server, not the orchestrator — abra,
|
||||
Docker, and Swarm must be present.
|
||||
|
||||
Invoke: cc-ci-run python -m pytest tests/regression/ -m canary -v
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
import subprocess
|
||||
import sys
|
||||
import time
|
||||
|
||||
ROOT = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
|
||||
def pytest_configure(config):
|
||||
config.addinivalue_line(
|
||||
"markers",
|
||||
"canary: slow E2E canary test — drives the full cold CI lifecycle; run on-demand only.",
|
||||
)
|
||||
config.addinivalue_line(
|
||||
"markers",
|
||||
"canary_fast: fast per-tier RED canary (still tagged canary); subset for quick pre-merge checks.",
|
||||
)
|
||||
|
||||
|
||||
def run_recipe_ci(
|
||||
recipe: str,
|
||||
src: str,
|
||||
ref: str,
|
||||
pr: str = "0",
|
||||
stages: str = "install,upgrade,backup,restore,custom",
|
||||
runs_dir: str | None = None,
|
||||
run_id_prefix: str = "regression",
|
||||
timeout: int = 3600,
|
||||
) -> tuple[int, dict | None, str]:
|
||||
"""Invoke run_recipe_ci.py with the given canary params.
|
||||
|
||||
Returns (rc, results_dict_or_None, run_artifact_dir).
|
||||
Stdout/stderr stream live so a human can follow progress.
|
||||
"""
|
||||
ts = int(time.time())
|
||||
run_id = f"{run_id_prefix}-{recipe}-{ref[:12]}-{ts}"
|
||||
if runs_dir is None:
|
||||
runs_dir = "/var/lib/cc-ci-runs"
|
||||
|
||||
env = dict(os.environ)
|
||||
env.update(
|
||||
{
|
||||
"RECIPE": recipe,
|
||||
"REF": ref,
|
||||
"SRC": src,
|
||||
"PR": pr,
|
||||
"STAGES": stages,
|
||||
"CCCI_RUN_ID": run_id,
|
||||
"CCCI_RUNS_DIR": runs_dir,
|
||||
"HOME": "/root",
|
||||
}
|
||||
)
|
||||
# Keep PLAYWRIGHT env from the outer cc-ci-run wrapper (already in os.environ if running under it)
|
||||
|
||||
script = os.path.join(ROOT, "runner", "run_recipe_ci.py")
|
||||
result = subprocess.run(
|
||||
[sys.executable, script],
|
||||
env=env,
|
||||
timeout=timeout,
|
||||
)
|
||||
rc = result.returncode
|
||||
|
||||
artifact_dir = os.path.join(runs_dir, run_id)
|
||||
results_path = os.path.join(artifact_dir, "results.json")
|
||||
results_data: dict | None = None
|
||||
if os.path.exists(results_path):
|
||||
with open(results_path) as f:
|
||||
results_data = json.load(f)
|
||||
|
||||
return rc, results_data, artifact_dir
|
||||
|
||||
|
||||
def find_stage_tests(results: dict, stage_name: str) -> list[dict]:
|
||||
"""Return the per-test list for a named stage from results.json, or []."""
|
||||
for stage in results.get("stages", []):
|
||||
if stage.get("name") == stage_name:
|
||||
return stage.get("tests", [])
|
||||
return []
|
||||
|
||||
|
||||
def stage_has_passing_test(results: dict, stage_name: str, test_name_substr: str) -> bool:
|
||||
"""True if the named stage contains a passing test whose name includes test_name_substr."""
|
||||
for t in find_stage_tests(results, stage_name):
|
||||
if test_name_substr in t.get("name", "") and t.get("status") == "pass":
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
def stage_has_failing_test(results: dict, stage_name: str, test_name_substr: str) -> bool:
|
||||
"""True if the named stage contains a failing test whose name includes test_name_substr."""
|
||||
for t in find_stage_tests(results, stage_name):
|
||||
if test_name_substr in t.get("name", "") and t.get("status") in ("fail", "error"):
|
||||
return True
|
||||
return False
|
||||
344
tests/regression/test_canaries.py
Normal file
344
tests/regression/test_canaries.py
Normal file
@ -0,0 +1,344 @@
|
||||
"""E2E canary regression tests — the server's standing self-test suite.
|
||||
|
||||
Seven canaries prove both halves of the server's job:
|
||||
1. GREEN canaries — good apps are reported healthy (install+upgrade+backup/restore pass).
|
||||
2. RED canaries — broken apps are caught at the intended tier; a false-green makes THIS test fail.
|
||||
|
||||
Fast subset (@pytest.mark.canary_fast): the four per-tier RED canaries on custom-html-tiny — fast
|
||||
because the recipe deploys in seconds. Run with `-m canary_fast` as a pre-merge quick check.
|
||||
Full suite (-m canary): includes good-significant (lasuite-docs, 10-20 min).
|
||||
|
||||
Run: cc-ci-run python -m pytest tests/regression/ -m canary -v
|
||||
Pin policy: canary refs are pinned to specific SHAs. Update only after confirming the new ref gives
|
||||
the expected verdict.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import sys
|
||||
|
||||
import pytest
|
||||
|
||||
sys.path.insert(0, os.path.dirname(__file__))
|
||||
import conftest as _reg # noqa: E402
|
||||
|
||||
run_recipe_ci = _reg.run_recipe_ci
|
||||
stage_has_passing_test = _reg.stage_has_passing_test
|
||||
stage_has_failing_test = _reg.stage_has_failing_test
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Canary definitions
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
# Good canary 1: minimal static-file server — fast signal, few deps.
|
||||
_SIMPLE = {
|
||||
"id": "good-simple",
|
||||
"recipe": "custom-html-tiny",
|
||||
"src": "recipe-maintainers/custom-html-tiny",
|
||||
# Pin: main @ 2026-06-02 — update if the recipe publishes a new release and pin goes stale.
|
||||
"ref": "435df8fc98ef7598084fcffcd6225470eca80053",
|
||||
"expected_green": True,
|
||||
# Named tests that MUST appear with "pass" in the result — these are the semantic teeth.
|
||||
# If the generic install assertion is removed/vacated, test_serving disappears → this fails.
|
||||
"stage_pass_checks": [
|
||||
("install", "test_serving"),
|
||||
],
|
||||
"stage_fail_checks": [],
|
||||
}
|
||||
|
||||
# Good canary 2: multi-service stack — backend + Postgres + Collabora WOPI + OIDC.
|
||||
# Exercises real breadth. Slowest canary (~10-20 min full lifecycle).
|
||||
_SIGNIFICANT = {
|
||||
"id": "good-significant",
|
||||
"recipe": "lasuite-docs",
|
||||
"src": "recipe-maintainers/lasuite-docs",
|
||||
# Pin: main @ 2026-06-02
|
||||
"ref": "290a8ad72d06232f0b3f302d976af14bef0f3c53",
|
||||
"expected_green": True,
|
||||
"stage_pass_checks": [
|
||||
("install", "test_serving_and_frontend"),
|
||||
],
|
||||
"stage_fail_checks": [],
|
||||
}
|
||||
|
||||
# Bad canary: app is UP + passes all lifecycle tiers but the custom functional assertion detects a
|
||||
# semantic defect (wrong Content-Type for .txt files). The harness MUST report RED.
|
||||
# If the harness wrongly returns green for this fixture, assert rc != 0 fails → false-green caught.
|
||||
_BAD = {
|
||||
"id": "bad-false-green",
|
||||
"recipe": "custom-html",
|
||||
"src": "recipe-maintainers/custom-html",
|
||||
# Pin: v5-stale-docroot @ 71e7326 — serves .txt as application/octet-stream; build #75 was RED.
|
||||
# Recreate pattern if branch disappears: app up + passes lifecycle, fails one content assertion.
|
||||
"ref": "71e7326a99bbb69035a046fba8fa51859ca66115",
|
||||
"expected_green": False,
|
||||
# The specific test that must have FAILED, proving the content-type assertion has teeth.
|
||||
# If the assertion is vacated and the test disappears, stage_has_failing_test() returns False
|
||||
# → the assert below fails → we detect that the guard was removed.
|
||||
"stage_pass_checks": [],
|
||||
"stage_fail_checks": [
|
||||
("custom", "test_content_type"),
|
||||
],
|
||||
}
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Per-tier RED canaries (fast subset: @pytest.mark.canary_fast)
|
||||
# Prove the server catches failure at EVERY lifecycle tier — false-green at any tier is caught.
|
||||
# Each uses custom-html-tiny (deploys in seconds) or custom-html (fast nginx, has backup support).
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
# Shared bad-image branch: deploy fails at prepull because the image doesn't exist on Docker Hub.
|
||||
# Used for install-RED (STAGES=install → chaos of HEAD with bad image → install=fail)
|
||||
# and upgrade-RED (STAGES=install,upgrade → prev-version install passes, upgrade chaos fails).
|
||||
_BAD_IMAGE_REF = "4ae8866100563204d40435c5aba00374aa5a8ed3" # regression-bad-image @ 2026-06-02
|
||||
|
||||
_BAD_INSTALL = {
|
||||
"id": "bad-install",
|
||||
"recipe": "custom-html-tiny",
|
||||
"src": "recipe-maintainers/custom-html-tiny",
|
||||
"ref": _BAD_IMAGE_REF,
|
||||
"expected_green": False,
|
||||
# STAGES=install only → no upgrade tier → prev=None → chaos deploy of HEAD (bad image) → fails.
|
||||
"stages": "install",
|
||||
# Assertions: install must be the failing tier.
|
||||
"failing_tier": "install",
|
||||
"passing_tiers_before": [],
|
||||
"stage_pass_checks": [],
|
||||
"stage_fail_checks": [],
|
||||
}
|
||||
|
||||
_BAD_UPGRADE = {
|
||||
"id": "bad-upgrade",
|
||||
"recipe": "custom-html-tiny",
|
||||
"src": "recipe-maintainers/custom-html-tiny",
|
||||
"ref": _BAD_IMAGE_REF,
|
||||
"expected_green": False,
|
||||
# Default stages → prev-version deploy (good image) → install=PASS; upgrade chaos (bad image) → FAIL.
|
||||
"stages": "install,upgrade,custom",
|
||||
"failing_tier": "upgrade",
|
||||
"passing_tiers_before": ["install"],
|
||||
"stage_pass_checks": [],
|
||||
"stage_fail_checks": [],
|
||||
}
|
||||
|
||||
_BAD_BACKUP = {
|
||||
"id": "bad-backup",
|
||||
"recipe": "custom-html-bkp-bad",
|
||||
"src": "recipe-maintainers/custom-html-bkp-bad",
|
||||
# Pin: custom-html-bkp-bad main @ 2026-06-02 — custom-html WITHOUT backupbot labels.
|
||||
# cc-ci recipe_meta sets BACKUP_CAPABLE=True → harness runs backup tier.
|
||||
# No backupbot.backup=true label → backup-bot-two finds no containers → no snapshot.
|
||||
# parse_snapshot_id returns None → test_backup_artifact fails → backup tier RED.
|
||||
"ref": "b6fe99de41601f9e51bc7ea5b6072f0c3f56cdc3",
|
||||
"expected_green": False,
|
||||
"stages": "install,upgrade,backup",
|
||||
"failing_tier": "backup",
|
||||
"passing_tiers_before": ["install"],
|
||||
"stage_pass_checks": [],
|
||||
"stage_fail_checks": [],
|
||||
}
|
||||
|
||||
_BAD_RESTORE = {
|
||||
"id": "bad-restore",
|
||||
"recipe": "custom-html-rst-bad",
|
||||
"src": "recipe-maintainers/custom-html-rst-bad",
|
||||
# Pin: custom-html-rst-bad main @ 2026-06-02 (9a73a184).
|
||||
# No pre_backup hook → backup snapshot has no ci-marker.txt.
|
||||
# pre_restore writes "mutated". After restore: marker stays "mutated" → FAIL → restore=RED.
|
||||
# install+backup PASS (no test_backup.py in cc-ci dir); upgrade=skip (no version tags).
|
||||
"ref": "9a73a184e739691bc6a621a5f1e6efc799743c5b",
|
||||
"expected_green": False,
|
||||
"stages": "install,backup,restore,custom",
|
||||
"failing_tier": "restore",
|
||||
"passing_tiers_before": ["install", "backup"],
|
||||
"stage_pass_checks": [],
|
||||
"stage_fail_checks": [
|
||||
("restore", "test_restore_returns_state"),
|
||||
],
|
||||
}
|
||||
|
||||
CANARIES = [_SIMPLE, _SIGNIFICANT, _BAD]
|
||||
CANARIES_FAST = [_BAD_INSTALL, _BAD_UPGRADE, _BAD_BACKUP, _BAD_RESTORE]
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Tests
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
@pytest.mark.canary
|
||||
@pytest.mark.parametrize("canary", CANARIES, ids=[c["id"] for c in CANARIES])
|
||||
def test_canary(canary, tmp_path):
|
||||
"""Drive the full cold CI lifecycle for a canary recipe and verify the outcome.
|
||||
|
||||
For GREEN canaries: proves the harness correctly reports a healthy app as healthy, and that
|
||||
the per-tier semantic assertions actually ran (not vacuous).
|
||||
|
||||
For the RED canary: proves the harness catches a broken app — if the harness wrongly returned
|
||||
green, `assert rc != 0` fails, catching the false-green.
|
||||
"""
|
||||
stages = canary.get("stages", "install,upgrade,backup,restore,custom")
|
||||
rc, results, artifact_dir = run_recipe_ci(
|
||||
recipe=canary["recipe"],
|
||||
src=canary["src"],
|
||||
ref=canary["ref"],
|
||||
runs_dir=str(tmp_path),
|
||||
stages=stages,
|
||||
)
|
||||
|
||||
_note = f"artifact_dir={artifact_dir}" # visible in -v output via assert messages
|
||||
|
||||
if canary["expected_green"]:
|
||||
_assert_green(rc, results, canary, _note)
|
||||
else:
|
||||
_assert_red(rc, results, canary, _note)
|
||||
|
||||
|
||||
@pytest.mark.canary
|
||||
@pytest.mark.canary_fast
|
||||
@pytest.mark.parametrize("canary", CANARIES_FAST, ids=[c["id"] for c in CANARIES_FAST])
|
||||
def test_canary_fast(canary, tmp_path):
|
||||
"""Fast per-tier RED canaries: each proves the server catches failure at a specific lifecycle tier.
|
||||
|
||||
Each canary is broken at exactly one tier; the test asserts:
|
||||
- Overall verdict: RED (rc != 0)
|
||||
- The intended failing tier has status "fail"
|
||||
- Tiers BEFORE the intended failure have status "pass" (proving tier-specific detection, not
|
||||
"fails somewhere")
|
||||
|
||||
These use fast recipes (custom-html-tiny deploys in seconds, custom-html is similarly fast)
|
||||
and are intended as a pre-merge quick check alongside the full slow suite.
|
||||
"""
|
||||
stages = canary.get("stages", "install,upgrade,backup,restore,custom")
|
||||
rc, results, artifact_dir = run_recipe_ci(
|
||||
recipe=canary["recipe"],
|
||||
src=canary["src"],
|
||||
ref=canary["ref"],
|
||||
runs_dir=str(tmp_path),
|
||||
stages=stages,
|
||||
)
|
||||
|
||||
_note = f"artifact_dir={artifact_dir}"
|
||||
_assert_red_at_tier(rc, results, canary, _note)
|
||||
|
||||
|
||||
def _assert_green(rc: int, results: dict | None, canary: dict, note: str) -> None:
|
||||
"""Assert a good-canary run is GREEN with real semantic assertions."""
|
||||
|
||||
# 1. Harness exit code must be 0 (GREEN).
|
||||
assert rc == 0, f"[{canary['id']}] harness returned non-zero rc={rc} — expected GREEN. {note}"
|
||||
|
||||
assert (
|
||||
results is not None
|
||||
), f"[{canary['id']}] results.json not written — harness may have crashed. {note}"
|
||||
|
||||
# 2. Install tier must have passed.
|
||||
assert results.get("results", {}).get("install") == "pass", (
|
||||
f"[{canary['id']}] install tier did not pass: " f"results={results.get('results')}. {note}"
|
||||
)
|
||||
|
||||
# 3. No tier may have FAILED (skips are acceptable for recipes without backup or custom tests).
|
||||
failed_tiers = [t for t, s in results.get("results", {}).items() if s == "fail"]
|
||||
assert not failed_tiers, f"[{canary['id']}] tiers failed: {failed_tiers}. {note}"
|
||||
|
||||
# 4. Teardown must be clean (no leftover containers/volumes/secrets).
|
||||
assert (
|
||||
results.get("flags", {}).get("clean_teardown") is True
|
||||
), f"[{canary['id']}] clean_teardown=False — residual state left on server. {note}"
|
||||
|
||||
# 5. No secret values leaked into the results artifact.
|
||||
assert (
|
||||
results.get("flags", {}).get("no_secret_leak") is True
|
||||
), f"[{canary['id']}] no_secret_leak=False — a secret value appeared in results.json. {note}"
|
||||
|
||||
# 6. Semantic stage assertions — TEETH CHECK.
|
||||
# These verify that specific named tests actually ran and passed in the expected stage.
|
||||
# If a tier assertion is removed or made vacuous, the named test disappears from results.json
|
||||
# and this assert fires — proving the regression suite guards against silent test removal.
|
||||
for stage_name, test_name_substr in canary.get("stage_pass_checks", []):
|
||||
assert stage_has_passing_test(results, stage_name, test_name_substr), (
|
||||
f"[{canary['id']}] expected a passing test containing {test_name_substr!r} in "
|
||||
f"stage={stage_name!r}, but none found. "
|
||||
f"Stage tests: {[t['name'] for t in _stage_tests(results, stage_name)]}. {note}"
|
||||
)
|
||||
|
||||
|
||||
def _assert_red(rc: int, results: dict | None, canary: dict, note: str) -> None:
|
||||
"""Assert a bad-canary run is RED (false-green guard).
|
||||
|
||||
The PRIMARY assertion is rc != 0. If the harness wrongly returns 0 (green) for this fixture,
|
||||
this assert fails → the regression suite catches the false-green. This is the core guard.
|
||||
"""
|
||||
|
||||
# PRIMARY: harness must return non-zero (RED).
|
||||
# If the harness returns 0 for a broken app, the regression suite fails here — false-green caught.
|
||||
assert rc != 0, (
|
||||
f"[{canary['id']}] harness returned rc=0 (GREEN) for a KNOWN-BAD fixture — "
|
||||
f"FALSE-GREEN detected. The harness failed to catch the broken app. {note}"
|
||||
)
|
||||
|
||||
# SECONDARY: verify the specific failing test is present in results.json.
|
||||
# If the content-type assertion is removed/vacuated, stage_has_failing_test() returns False here
|
||||
# → this assert fires → we detect that the guard itself was removed (a meta-failure).
|
||||
if results is not None:
|
||||
for stage_name, test_name_substr in canary.get("stage_fail_checks", []):
|
||||
assert stage_has_failing_test(results, stage_name, test_name_substr), (
|
||||
f"[{canary['id']}] expected a failing test containing {test_name_substr!r} in "
|
||||
f"stage={stage_name!r}, but none found. "
|
||||
f"The guard may have been removed or vacuated. "
|
||||
f"Stage tests: {[t['name'] for t in _stage_tests(results, stage_name)]}. {note}"
|
||||
)
|
||||
|
||||
|
||||
def _assert_red_at_tier(rc: int, results: dict | None, canary: dict, note: str) -> None:
|
||||
"""Assert a per-tier RED canary: overall RED, failing_tier=fail, passing_tiers_before=pass.
|
||||
|
||||
Proves the server catches failure AT THE INTENDED TIER (not just "fails somewhere"), and that
|
||||
the tiers before it still PASSED (no collateral damage from the fixture).
|
||||
If the harness returns 0 for any of these fixtures, false-green is detected at the primary assert.
|
||||
"""
|
||||
failing_tier = canary.get("failing_tier")
|
||||
passing_before = canary.get("passing_tiers_before", [])
|
||||
|
||||
# PRIMARY: harness must return non-zero.
|
||||
assert rc != 0, (
|
||||
f"[{canary['id']}] harness returned rc=0 (GREEN) for a KNOWN-BAD fixture at tier "
|
||||
f"{failing_tier!r} — FALSE-GREEN. {note}"
|
||||
)
|
||||
|
||||
if results is None:
|
||||
return
|
||||
|
||||
tier_results = results.get("results", {})
|
||||
|
||||
# The intended failing tier must be "fail".
|
||||
if failing_tier:
|
||||
actual = tier_results.get(failing_tier)
|
||||
assert actual == "fail", (
|
||||
f"[{canary['id']}] expected tier {failing_tier!r}='fail', got {actual!r}. "
|
||||
f"All tier results: {tier_results}. {note}"
|
||||
)
|
||||
|
||||
# Tiers before the failing tier must have passed (no collateral damage from the fixture).
|
||||
for tier in passing_before:
|
||||
actual = tier_results.get(tier)
|
||||
assert actual == "pass", (
|
||||
f"[{canary['id']}] expected prior tier {tier!r}='pass' before failing at "
|
||||
f"{failing_tier!r}, got {actual!r}. All results: {tier_results}. {note}"
|
||||
)
|
||||
|
||||
# Optional: specific failing test name (for the restore-RED canary).
|
||||
for stage_name, test_name_substr in canary.get("stage_fail_checks", []):
|
||||
assert stage_has_failing_test(results, stage_name, test_name_substr), (
|
||||
f"[{canary['id']}] expected a failing test containing {test_name_substr!r} in "
|
||||
f"stage={stage_name!r}. "
|
||||
f"Stage tests: {[t['name'] for t in _stage_tests(results, stage_name)]}. {note}"
|
||||
)
|
||||
|
||||
|
||||
def _stage_tests(results: dict, stage_name: str) -> list[dict]:
|
||||
for stage in results.get("stages", []):
|
||||
if stage.get("name") == stage_name:
|
||||
return stage.get("tests", [])
|
||||
return []
|
||||
Reference in New Issue
Block a user