docs-gates: hard-bound the smoke deadline (cap probe timeout + inter-round sleep to remaining budget)

Codex adversarial finding: DEADLINE_SECONDS was only checked BEFORE each op, so a
probe or sleep starting at 479s could overshoot to ~510s — 480 was a soft target,
not a hard bound.

Make it hard: run() now computes an absolute deadline = start + DEADLINE_SECONDS
plus a _remaining() helper. The per-probe socket timeout is capped to
min(PROBE_TIMEOUT_SECONDS, max(1, remaining)) — the previously hardcoded 30 is now
the PROBE_TIMEOUT_SECONDS constant; a probe with < 1s of budget is skipped and
counted unresolved. The inter-round sleep is capped to
min(RETRY_SLEEP_SECONDS, remaining) and is skipped entirely when the budget is
exhausted (falling into the existing deadline path). No body-read-level deadline is
added — pages are small, so the socket-op timeout bounds reads adequately.

Deadline-path failure accounting is unchanged. Tests: the probe timeout is capped
to the remaining budget (fake opener records the timeout it was opened with); the
inter-round sleep is capped to the remaining budget (sleep spy); the existing suite
stays green.

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

2 files changed, 59 insertions, 15 deletions

diff --git a/scripts/docs_gates/smoke.py b/scripts/docs_gates/smoke.py
index 34dc87d7..770e93e3 100644
--- a/scripts/docs_gates/smoke.py
+++ b/scripts/docs_gates/smoke.py
@@ -38,6 +38,10 @@ USER_AGENT = "vyos-docs-smoke/1.0 (+https://github.com/vyos/vyos-documentation)"
 MAX_ROUNDS = 5
 RETRY_SLEEP_SECONDS = 30
 DEADLINE_SECONDS = 480
+# Per-socket-op timeout (connect + read), capped down to the remaining deadline budget on each
+# probe so a probe that starts late cannot overshoot DEADLINE_SECONDS. Pages are small, so this
+# socket-op timeout also bounds body reads adequately — no separate body-read deadline is needed.
+PROBE_TIMEOUT_SECONDS = 30
 
 
 class _NoRedirect(urllib.request.HTTPRedirectHandler):
@@ -87,21 +91,24 @@ def search_mount_present(html: str) -> bool:
     return SEARCH_MOUNT_MARKER in html
 
 
-def _probe_once(host: str, probe: Probe, expect_sha: str, access_id: str,
-                access_secret: str) -> tuple[bool, int | None, str | None, str | None]:
+def _probe_once(host: str, probe: Probe, expect_sha: str, access_id: str, access_secret: str,
+                timeout: float = PROBE_TIMEOUT_SECONDS,
+                ) -> tuple[bool, int | None, str | None, str | None]:
     """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."""
+    transport error text — and is None when ok. `timeout` is the per-socket-op deadline (connect
+    + read); run() caps it to the remaining budget so a late probe can't overshoot the overall
+    deadline. 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)
     req.add_header("User-Agent", USER_AGENT)
     try:
         try:
-            with _OPENER.open(req, timeout=30) as resp:
+            with _OPENER.open(req, timeout=timeout) as resp:
                 status, headers, body = resp.status, resp.headers, resp.read()
         except urllib.error.HTTPError as e:  # non-2xx still carries headers/body
             with e:  # HTTPError is file-like and owns the response socket — always close it
@@ -130,12 +137,13 @@ def run(host: str, slug: str, expect_sha: str, access_id: str, access_secret: st
     DEADLINE_SECONDS bounds total wall-clock — on breach, unresolved probes count as failed."""
     plan = probe_plan(slug, pdf, critical)
     start = time.monotonic()
+    deadline = start + DEADLINE_SECONDS      # absolute — a hard upper bound on total wall-clock
     pending = list(plan)                     # probes not yet passed
     detail_by_path: dict[str, str] = {}      # last failure detail per path, for logging
     deadline_hit = False
 
-    def _past_deadline() -> bool:
-        return time.monotonic() - start >= DEADLINE_SECONDS
+    def _remaining() -> float:
+        return deadline - time.monotonic()
 
     for round_num in range(1, MAX_ROUNDS + 1):
         if not pending:
@@ -143,12 +151,14 @@ def run(host: str, slug: str, expect_sha: str, access_id: str, access_secret: st
         still_failing: list[Probe] = []
         unprobed: list[Probe] = []
         for i, probe in enumerate(pending):
-            if _past_deadline():             # checked before each probe
+            remaining = _remaining()         # checked before each probe
+            if remaining < 1:                # < 1s budget: don't start a probe that could overshoot
                 deadline_hit = True
                 unprobed = pending[i:]       # not reached this round → still unresolved
                 break
             ok, status, docs_build, detail = _probe_once(
-                host, probe, expect_sha, access_id, access_secret)
+                host, probe, expect_sha, access_id, access_secret,
+                timeout=min(PROBE_TIMEOUT_SECONDS, max(1, remaining)))
             if ok:
                 continue
             still_failing.append(probe)
@@ -157,13 +167,14 @@ def run(host: str, slug: str, expect_sha: str, access_id: str, access_secret: st
         pending = still_failing + unprobed
         if deadline_hit or not pending or round_num == MAX_ROUNDS:
             break
-        if _past_deadline():                 # checked before the inter-round sleep
+        remaining = _remaining()             # checked before the inter-round sleep
+        if remaining <= 0:                   # no budget left → deadline path (skip the sleep)
             deadline_hit = True
             break
         for probe in pending:
             print(f"SMOKE-RETRY {probe.path}: round {round_num} "
                   f"{detail_by_path[probe.path]}", file=sys.stderr)
-        time.sleep(RETRY_SLEEP_SECONDS)
+        time.sleep(min(RETRY_SLEEP_SECONDS, remaining))   # never sleep past the deadline
 
     if deadline_hit:
         print("SMOKE-DEADLINE: overall deadline reached — remaining probes counted as failed",
diff --git a/scripts/docs_gates/test_smoke.py b/scripts/docs_gates/test_smoke.py
index f0a37c7a..a2654dcf 100644
--- a/scripts/docs_gates/test_smoke.py
+++ b/scripts/docs_gates/test_smoke.py
@@ -101,15 +101,18 @@ class _FakeResp:
 
 
 class _FakeOpener:
-    """Yields queued responses in order; an Exception item is raised (models a transport
-    error, or a non-2xx delivered as HTTPError). Records each opened Request for assertions."""
+    """Yields queued responses in order; an Exception item is raised (models a transport error,
+    or a non-2xx delivered as HTTPError). Records each opened Request + the timeout it was
+    called with, for assertions."""
 
     def __init__(self, responses: list[object]):
         self._responses = list(responses)
         self.calls: list[urllib.request.Request] = []
+        self.timeouts: list[float | None] = []
 
     def open(self, req: urllib.request.Request, timeout: float | None = None) -> object:
         self.calls.append(req)
+        self.timeouts.append(timeout)
         item = self._responses.pop(0)
         if isinstance(item, Exception):
             raise item
@@ -150,10 +153,12 @@ class _PathOpener:
     def __init__(self, by_path: dict[str, list[object]]):
         self._by_path = {p: list(v) for p, v in by_path.items()}
         self.calls: list[str] = []
+        self.timeouts: list[float | None] = []
 
     def open(self, req: urllib.request.Request, timeout: float | None = None) -> object:
         path = urlsplit(req.full_url).path
         self.calls.append(path)
+        self.timeouts.append(timeout)
         item = self._by_path[path].pop(0)
         if isinstance(item, Exception):
             raise item
@@ -331,3 +336,31 @@ def test_probe_once_detail_joins_multiple_failed_checks(monkeypatch):
     ok, _, _, detail = smoke._probe_once("host", probe, "sha", "id", "sec")
     assert ok is False
     assert detail == "status+apex-build"
+
+
+# --- Adversarial round: DEADLINE_SECONDS is a HARD bound — the per-probe socket timeout and the
+# inter-round sleep are both capped to the remaining budget so neither can overshoot it. ---
+
+def test_probe_timeout_capped_to_remaining_budget(monkeypatch):
+    monkeypatch.setattr(smoke, "probe_plan", lambda slug, pdf, critical: _plan(["/a"]))
+    monkeypatch.setattr(smoke, "DEADLINE_SECONDS", 5)  # << PROBE_TIMEOUT_SECONDS (30)
+    opener = _PathOpener({"/a": [_FakeResp(200, {})]})
+    monkeypatch.setattr(smoke, "_OPENER", opener)
+    smoke.run("host", "rolling", "sha", "id", "sec", None, [])
+    assert opener.timeouts, "the probe recorded the timeout it was opened with"
+    t = opener.timeouts[0]
+    assert 1 <= t <= smoke.DEADLINE_SECONDS    # capped DOWN to the ~5s remaining budget
+    assert t < smoke.PROBE_TIMEOUT_SECONDS      # NOT the full 30s socket timeout
+
+
+def test_inter_round_sleep_capped_to_remaining_budget(monkeypatch):
+    monkeypatch.setattr(smoke, "probe_plan", lambda slug, pdf, critical: _plan(["/a"]))
+    monkeypatch.setattr(smoke, "DEADLINE_SECONDS", 10)  # << RETRY_SLEEP_SECONDS (30)
+    sleeps: list[float] = []
+    monkeypatch.setattr(smoke.time, "sleep", lambda s: sleeps.append(s))
+    opener = _PathOpener({"/a": [_FakeResp(500, {}), _FakeResp(200, {})]})  # fail r1, pass r2
+    monkeypatch.setattr(smoke, "_OPENER", opener)
+    assert smoke.run("host", "rolling", "sha", "id", "sec", None, []) == 0
+    assert len(sleeps) == 1
+    assert 0 < sleeps[0] <= smoke.DEADLINE_SECONDS  # capped to the ~10s remaining budget
+    assert sleeps[0] < smoke.RETRY_SLEEP_SECONDS     # NOT the full 30s sleep