ersatztv/scripts/tests/test_merge_consent_base_change.py

"""Tests for the base-change detection in `.claude/hooks/pretooluse-merge-consent.sh` (#632).

`review-verdict/h10` is a per-sha commit status, which makes "a new commit inherits an old verdict"
impossible by construction (#622). Retargeting a PR's base reaches the same end by the opposite
route: the head sha does not move, so the status stays green, while the merge-base — and therefore
the effective diff the verdict was formed against — changes underneath it.

What is asserted here is DETECTION on the hook path only, and the tests are written to keep that
claim narrow:

  * a status carries no base field of its own, so the server-side required check cannot see this at
    all; a merge driven through the Gitea UI or API is unaffected. No test here implies otherwise.
  * a verdict posted before #632 has no `(base: …)` in its description and must get NO opinion,
    rather than denying every in-flight PR the day this lands.

Observable contract: the hook exits 0 with EMPTY stdout when it has no opinion (passthrough to
normal permissioning), and emits a JSON `permissionDecision` otherwise.
"""

from __future__ import annotations

import json
import os
import subprocess
from pathlib import Path

import pytest

REPO_ROOT = Path(__file__).resolve().parents[2]
HOOK = REPO_ROOT / ".claude" / "hooks" / "pretooluse-merge-consent.sh"

SHA = "a9e3e23abf337980ca4c05854f5b1e210099d08b"

# The PR is deliberately NOT docs-only: the docs-only exemption short-circuits the whole gate, so a
# docs PR would never reach the base check and the tests would pass without exercising it.
CURL_SHIM = r'''#!/usr/bin/env python3
import json, os, sys, pathlib, urllib.parse

state = pathlib.Path(os.environ["STUB_DIR"])
args = sys.argv[1:]
url = [a for a in args if a.startswith("http")][-1]

if "/pulls/" in url and "/files" in url:
    q = urllib.parse.parse_qs(urllib.parse.urlparse(url).query)
    page = int(q.get("page", ["1"])[0])
    if page == 1:
        print(json.dumps([{"filename": "ErsatzTV/Program.cs", "status": "modified"}]))
    else:
        print("[]")
    sys.exit(0)

if "/status" in url:
    desc = (state / "verdict_desc").read_text()
    if desc == "TRANSPORT-ERROR":
        sys.exit(22)
    if desc == "GARBAGE":
        print('{"message":"internal error"}'); sys.exit(0)
    if desc == "SCALAR-ROW":
        print('{"state":"success","statuses":[1]}'); sys.exit(0)
    if desc == "NONSTRING-DESC":
        print(json.dumps({"state": "success", "statuses": [
            {"context": "review-verdict/h10", "status": "success", "description": {"x": 1}}]}))
        sys.exit(0)
    rows = [] if desc == "NONE" else [
        {"context": "review-verdict/h10", "status": "success", "description": desc}]
    print(json.dumps({"state": "success", "statuses": rows}))
    sys.exit(0)

if "/pulls/" in url:
    body = {"head": {"sha": os.environ["STUB_SHA"]}, "body": "fixes #1"}
    live = (state / "live_base").read_text().strip()
    if live != "MISSING":
        body["base"] = {"ref": live}
    print(json.dumps(body))
    sys.exit(0)

print("{}")
'''


@pytest.fixture
def hook(tmp_path):
    bindir = tmp_path / "bin"; bindir.mkdir()
    curl = bindir / "curl"; curl.write_text(CURL_SHIM); curl.chmod(0o755)
    state = tmp_path / "state"; state.mkdir()
    (state / "live_base").write_text("main")
    (state / "verdict_desc").write_text("Review-verdict: MERGEABLE @ a9e3e23 (base: main)")

    env = dict(os.environ)
    env["PATH"] = f"{bindir}{os.pathsep}{env['PATH']}"
    env["STUB_DIR"] = str(state)
    env["STUB_SHA"] = SHA
    env["ETV_GITEA_TOKEN"] = "stub"
    env["ETV_GITEA_URL"] = "http://gitea.example"
    env.pop("ETV_GITEA_BASICAUTH", None)

    class Handle:
        def set_live_base(self, ref):
            (state / "live_base").write_text(ref)

        def set_verdict_description(self, desc):
            """'NONE' serves a head with no review-verdict/h10 status at all."""
            (state / "verdict_desc").write_text(desc)

        def decision(self):
            payload = {"tool_input": {"method": "merge", "owner": "timothy",
                                      "repo": "ersatztv", "pull_number": 42}}
            r = subprocess.run(["bash", str(HOOK)], input=json.dumps(payload),
                               env=env, capture_output=True, text=True)
            assert r.returncode == 0, r.stderr
            if not r.stdout.strip():
                return None
            return json.loads(r.stdout)

        def reason(self):
            d = self.decision()
            return "" if d is None else json.dumps(d)

    return Handle()


def test_a_retargeted_base_denies_a_verdict_formed_against_the_old_one(hook):
    hook.set_live_base("release/26.4")
    reason = hook.reason()
    assert "deny" in reason, "a verdict formed against a different base was allowed to stand"
    assert "release/26.4" in reason and "main" in reason, (
        "the deny must name both bases; a reader cannot act on 'the base changed'")


def test_positive_control_an_unchanged_base_does_not_trigger_the_base_deny(hook):
    """Without this, the test above could pass because the hook denies on every path — which it
    very nearly does, since this PR is non-docs and the rest of the gate is unstubbed."""
    reason = hook.reason()
    assert "ersatztv#632" not in reason, (
        "the base check fired on a PR whose base never moved")


@pytest.mark.parametrize("desc", [
    "Review-verdict: MERGEABLE @ a9e3e23",          # posted before #632
    "NONE",                                          # no verdict status on this head at all
])
def test_a_verdict_with_no_recorded_base_gets_no_opinion(hook, desc):
    """Graceful adoption. Denying here would block every in-flight PR the day this lands, and the
    window closes on its own: verdicts are per-head and short-lived, so every verdict posted after
    #632 carries the field.

    Asserting on the word "base" rather than on the issue tag, per cold review: the tag-only check
    would have passed for a base-specific ask or deny whose wording happened to omit it, which is
    the failure mode most likely to appear when someone edits these messages.
    """
    hook.set_live_base("release/26.4")
    hook.set_verdict_description(desc)
    assert "base" not in hook.reason(), (
        "a pre-#632 verdict drew a base-related decision for a field it could not have carried")


@pytest.mark.parametrize("failure", ["SCALAR-ROW", "NONSTRING-DESC"])
def test_a_malformed_status_MEMBER_asks_too(hook, failure):
    """One level below the previous fix, and it survived it.

    Validating only that `.statuses` is an array left `{"statuses":[1]}` passing the guard, after
    which `.context` on a number errors and a `|| true` on the extraction turned that error into an
    empty description — straight back onto the graceful-adoption path, which is precisely the
    outcome the guard exists to distinguish from. Same swallow-the-error shape as the bug one level
    up, which is why the validation domain must match the CONSUMPTION domain rather than stopping at
    the top-level type.
    """
    hook.set_live_base("release/26.4")
    hook.set_verdict_description(failure)
    reason = hook.reason()
    assert "ask" in reason and "base" in reason


@pytest.mark.parametrize("failure", ["TRANSPORT-ERROR", "GARBAGE"])
def test_an_UNREADABLE_status_response_asks_rather_than_skipping_the_check(hook, failure):
    """"Could not check" is a third outcome, not a quiet synonym for "no base recorded".

    The first draft collapsed the two: an unreadable status response produced an empty
    `recorded_base`, took the graceful-adoption path, and skipped validation in silence — after
    which a later successful status read could still auto-grant, emitting "merge gate: satisfied"
    for a comparison that never happened. A transient Gitea hiccup is not evidence that the base is
    unchanged.
    """
    hook.set_live_base("release/26.4")
    hook.set_verdict_description(failure)
    reason = hook.reason()
    assert "ask" in reason, "an unreadable status response silently skipped the base check"
    assert "base" in reason, "the ask must name what could not be checked"


def test_a_pr_with_no_resolvable_base_asks(hook):
    """A null/absent `.base.ref` is also 'could not check', not 'nothing to check'."""
    hook.set_live_base("MISSING")
    reason = hook.reason()
    assert "ask" in reason and "base" in reason


def test_the_comparator_is_the_base_REF_not_its_tip_sha():
    """The design decision this test exists to freeze. `base.sha` tracks the base branch's TIP,
    which moves every time anything merges to `main` — comparing that would invalidate every open
    verdict on every unrelated merge, turning a rare-event guard into a permanent merge deadlock.
    A base branch that merely ADVANCES must be silent here; rebasing onto it moves the head sha,
    which the per-sha binding already covers."""
    assert ".base.ref" in HOOK.read_text(), "the hook must compare the base BRANCH, not its tip sha"
    assert ".base.sha" not in HOOK.read_text(), (
        "comparing base.sha deadlocks every open PR whenever main advances")