docs-gates: close HTTPError response; name failed assertion in smoke logs (CR round 2)

Two accepted GitHub-side CodeRabbit findings on the smoke gate:

Close the HTTPError response stream: _probe_once read the non-2xx body via
e.read() but never closed the HTTPError, which is file-like and owns the
response socket — leaking it / raising ResourceWarning on the expected-404 path
every run. The read is now wrapped in "with e:" INSIDE the crash-containment
nesting, so the stream is closed even if the read raises (still yielding the
retryable transport-error result, never a traceback).

Name the failed assertion in retry/fail logs: _probe_once now returns a compact
`detail` naming which check failed ("status" / "docs-build" / "apex-build" /
"search-mount", multiple joined by "+", or the transport error text; None when
ok) instead of a bare transport-only field. SMOKE-RETRY / SMOKE-FAIL lines gain
`detail=<...>` alongside the existing status / docs-build fields, so an apex-build
or search-mount failure no longer logs an opaque "status=200 docs-build=<sha>".
ok-path behavior and the JSON / exit contract are unchanged.

Tests: HTTPError stream is closed on the happy-404 path and when the read raises
(RecordingBody close recorder); apex-build-only and search-mount-only failures
name their detail in the logs; _probe_once joins multiple failed checks with "+".
Removed the now-unused _http_error helper.

🤖 Generated by [robots](https://vyos.io)

2 files changed, 101 insertions, 29 deletions

diff --git a/scripts/docs_gates/smoke.py b/scripts/docs_gates/smoke.py
index 2dab82ff..874eb5cf 100644
--- a/scripts/docs_gates/smoke.py
+++ b/scripts/docs_gates/smoke.py
@@ -87,10 +87,12 @@ def search_mount_present(html: str) -> bool:
 
 def _probe_once(host: str, probe: Probe, expect_sha: str, access_id: str,
                 access_secret: str) -> tuple[bool, int | None, str | None, str | None]:
-    """One probe attempt. Returns (ok, status, docs_build, error). ANY exception in the open
-    OR body-read path — including a transport error DURING HTTPError.read() — is contained and
-    yields (False, None, None, <msg>): a retryable failure, never a traceback that crashes the
-    gate. status/docs_build are surfaced for retry logging."""
+    """One probe attempt. Returns (ok, status, docs_build, detail). `detail` names the failed
+    check(s) — "status" / "docs-build" / "apex-build" / "search-mount" joined by "+", or the
+    transport error text — and is None when ok. ANY exception in the open OR body-read path
+    (including a transport error DURING HTTPError.read()) is contained and yields
+    (False, None, None, <error text>): a retryable failure, never a traceback. The HTTPError
+    response stream is always closed — it owns a socket, so a bare e.read() would leak it."""
     req = urllib.request.Request(f"https://{host}{probe.path}", method="GET")
     req.add_header("CF-Access-Client-Id", access_id)
     req.add_header("CF-Access-Client-Secret", access_secret)
@@ -100,18 +102,22 @@ def _probe_once(host: str, probe: Probe, expect_sha: str, access_id: str,
             with _OPENER.open(req, timeout=30) as resp:
                 status, headers, body = resp.status, resp.headers, resp.read()
         except urllib.error.HTTPError as e:  # non-2xx still carries headers/body
-            status, headers, body = e.code, e.headers, e.read()
+            with e:  # HTTPError is file-like and owns the response socket — always close it
+                status, headers, body = e.code, e.headers, e.read()
     except Exception as e:  # noqa: BLE001 — open OR read failure → retryable probe result
         return False, None, None, str(e)
-    ok = status == probe.expect_status
+    reasons: list[str] = []
+    if status != probe.expect_status:
+        reasons.append("status")
     if probe.assert_docs_build and not docs_build_ok(headers.get("X-Docs-Build"), expect_sha):
-        ok = False
+        reasons.append("docs-build")
     if probe.assert_apex_build and not headers.get("X-Apex-Build"):
-        ok = False
+        reasons.append("apex-build")
     if probe.assert_search_mount and not search_mount_present(
             body.decode("utf-8", errors="replace")):
-        ok = False
-    return ok, status, headers.get("X-Docs-Build"), None
+        reasons.append("search-mount")
+    detail = "+".join(reasons) if reasons else None
+    return not reasons, status, headers.get("X-Docs-Build"), detail
 
 
 def run(host: str, slug: str, expect_sha: str, access_id: str, access_secret: str,
@@ -139,15 +145,13 @@ def run(host: str, slug: str, expect_sha: str, access_id: str, access_secret: st
                 deadline_hit = True
                 unprobed = pending[i:]       # not reached this round → still unresolved
                 break
-            ok, status, docs_build, error = _probe_once(
+            ok, status, docs_build, detail = _probe_once(
                 host, probe, expect_sha, access_id, access_secret)
             if ok:
                 continue
             still_failing.append(probe)
-            detail = f"status={status} docs-build={docs_build}"
-            if error is not None:
-                detail += f" error={error}"
-            detail_by_path[probe.path] = detail
+            detail_by_path[probe.path] = (
+                f"status={status} docs-build={docs_build} detail={detail}")
         pending = still_failing + unprobed
         if deadline_hit or not pending or round_num == MAX_ROUNDS:
             break
diff --git a/scripts/docs_gates/test_smoke.py b/scripts/docs_gates/test_smoke.py
index 063b3a7a..d32ec0cb 100644
--- a/scripts/docs_gates/test_smoke.py
+++ b/scripts/docs_gates/test_smoke.py
@@ -116,24 +116,30 @@ class _FakeOpener:
         return item
 
 
-def _http_error(code: int, headers: dict[str, str]) -> urllib.error.HTTPError:
-    hdrs = Message()
-    for k, v in headers.items():
-        hdrs[k] = v
-    return urllib.error.HTTPError("https://host.invalid/x", code, "msg", hdrs, io.BytesIO(b""))
+class _RecordingBody(io.BytesIO):
+    """HTTPError.fp stand-in: records close() (so tests can assert the response stream is
+    closed) and can optionally raise on read (a transport error DURING body read). urllib's
+    addbase binds read through to fp and closes fp on close(), so overriding them here is what
+    e.read() / closing e actually hit."""
 
-
-class _ReadBoom(io.BytesIO):
-    """A body whose .read() raises — models a transport error DURING HTTPError.read().
-    urllib's addbase binds the instance's read to fp.read, so overriding it on the fp is the
-    reliable way to make e.read() blow up."""
+    def __init__(self, data: bytes = b"", raise_on_read: bool = False):
+        super().__init__(data)
+        self.close_calls = 0
+        self._raise_on_read = raise_on_read
 
     def read(self, *args: object) -> bytes:  # noqa: D401
-        raise OSError("reset during body read")
+        if self._raise_on_read:
+            raise OSError("reset during body read")
+        return super().read(*args)
+
+    def close(self) -> None:
+        self.close_calls += 1
+        super().close()
 
 
 def _http_error_read_boom(code: int) -> urllib.error.HTTPError:
-    return urllib.error.HTTPError("https://host.invalid/x", code, "msg", Message(), _ReadBoom())
+    return urllib.error.HTTPError(
+        "https://host.invalid/x", code, "msg", Message(), _RecordingBody(raise_on_read=True))
 
 
 class _PathOpener:
@@ -188,10 +194,10 @@ def test_httperror_read_crash_is_contained_as_failure(monkeypatch):
     monkeypatch.setattr(smoke, "_OPENER", _FakeOpener([_http_error_read_boom(502)]))
     probe = smoke.Probe("/en/rolling/index.html", 200,
                         assert_docs_build=False, assert_apex_build=False)
-    ok, status, docs_build, error = smoke._probe_once("host", probe, "sha", "id", "sec")
+    ok, status, docs_build, detail = smoke._probe_once("host", probe, "sha", "id", "sec")
     assert ok is False
     assert status is None and docs_build is None
-    assert error is not None and "reset during body read" in error
+    assert detail is not None and "reset during body read" in detail
 
 
 def test_sleeps_once_per_inter_round_gap_not_per_probe(monkeypatch):
@@ -263,3 +269,65 @@ def test_probe_plan_dedups_index_html():
     assert len(index_probes) == 1                       # not duplicated by the critical list
     assert index_probes[0].assert_search_mount is True  # still the single search-mount probe
     assert sum(1 for p in plan if p.path == "/en/rolling/cli.html") == 1  # cli.html preserved
+
+
+# --- CR round 2: close the HTTPError response stream (it owns a socket) + name the failed
+# assertion in retry/fail logs. ---
+
+def test_httperror_response_is_closed(monkeypatch):
+    # HTTPError owns the response socket; the expected-404 path must close it, not leak.
+    body = _RecordingBody(b"not found")
+    monkeypatch.setattr(smoke, "_OPENER", _FakeOpener([
+        urllib.error.HTTPError("https://host.invalid/x", 404, "msg", Message(), body)]))
+    probe = smoke.Probe("/en/rolling/missing.html", 404,
+                        assert_docs_build=False, assert_apex_build=False)
+    ok, *_ = smoke._probe_once("host", probe, "sha", "id", "sec")
+    assert ok is True                # 404 expected → passes
+    assert body.close_calls >= 1     # response stream closed (no socket leak / ResourceWarning)
+
+
+def test_httperror_response_is_closed_even_when_read_raises(monkeypatch):
+    body = _RecordingBody(raise_on_read=True)
+    monkeypatch.setattr(smoke, "_OPENER", _FakeOpener([
+        urllib.error.HTTPError("https://host.invalid/x", 502, "msg", Message(), body)]))
+    probe = smoke.Probe("/en/rolling/index.html", 200,
+                        assert_docs_build=False, assert_apex_build=False)
+    ok, status, docs_build, detail = smoke._probe_once("host", probe, "sha", "id", "sec")
+    assert ok is False
+    assert detail is not None and "reset during body read" in detail
+    assert body.close_calls >= 1     # close still attempted despite the read raising
+
+
+def test_apex_build_failure_is_named_in_logs(monkeypatch, capsys):
+    # 200 but no X-Apex-Build: without a named detail the log read "status=200 docs-build=None".
+    probe = smoke.Probe("/versions.json", 200, assert_docs_build=False, assert_apex_build=True)
+    monkeypatch.setattr(smoke, "probe_plan", lambda slug, pdf, critical: [probe])
+    monkeypatch.setattr(smoke, "MAX_ROUNDS", 1)
+    monkeypatch.setattr(smoke, "_OPENER", _PathOpener({"/versions.json": [_FakeResp(200, {})]}))
+    assert smoke.run("host", "rolling", "sha", "id", "sec", None, []) == 1
+    err = capsys.readouterr().err
+    assert "SMOKE-FAIL /versions.json:" in err
+    assert "detail=apex-build" in err   # names the failed check
+    assert "status=200" in err          # existing fields preserved
+
+
+def test_search_mount_failure_is_named_in_logs(monkeypatch, capsys):
+    # 200 + correct build, but the HTML lacks the #vyos-search mount div.
+    probe = smoke.Probe("/en/rolling/index.html", 200, assert_docs_build=True,
+                        assert_apex_build=False, assert_search_mount=True)
+    monkeypatch.setattr(smoke, "probe_plan", lambda slug, pdf, critical: [probe])
+    monkeypatch.setattr(smoke, "MAX_ROUNDS", 1)
+    monkeypatch.setattr(smoke, "_OPENER", _PathOpener({
+        "/en/rolling/index.html": [_FakeResp(200, {"X-Docs-Build": "goodsha"},
+                                             b"<html>no search</html>")]}))
+    assert smoke.run("host", "rolling", "goodsha", "id", "sec", None, []) == 1
+    assert "detail=search-mount" in capsys.readouterr().err
+
+
+def test_probe_once_detail_joins_multiple_failed_checks(monkeypatch):
+    # wrong status AND missing X-Apex-Build → detail "status+apex-build"
+    monkeypatch.setattr(smoke, "_OPENER", _FakeOpener([_FakeResp(500, {})]))
+    probe = smoke.Probe("/versions.json", 200, assert_docs_build=False, assert_apex_build=True)
+    ok, status, docs_build, detail = smoke._probe_once("host", probe, "sha", "id", "sec")
+    assert ok is False
+    assert detail == "status+apex-build"