requirements-ci.txt

@@ -1,5 +1,5 @@
 # This file was autogenerated by uv via the following command:
-#    uv pip compile pyproject.toml -o requirements-ci.txt --extra dev --extra memory --python-version 3.11
+#    uv pip compile pyproject.toml -o /tmp/regen-req.txt --extra dev --extra memory --python-version 3.11
 aiohappyeyeballs==2.7.1
     # via aiohttp
 aiohttp==3.14.3
@@ -34,7 +34,7 @@ httpcore==1.0.9
     # via httpx
 httpx==0.28.1
     # via rune (pyproject.toml)
-idna==3.19
+idna==3.20
     # via
     #   anyio
     #   httpx

scripts/ci_event_wait.py

@@ -134,6 +134,17 @@ OPERATION_SPECS = {
 DEFAULT_OP_TYPE = "master_ci"
 
 
+def normalize_verdict(verdict: str) -> str:
+    """T21.5 §18 audit fix: pending-class verdicts are ALL nonterminal.
+    deploy_qualify emits "pending (probe failed)" for a transient probe
+    failure — that is pending, never a terminal answer. The wait loop
+    must not return control to the model over a string variant."""
+    v = (verdict or "").strip().lower()
+    if v.startswith("pending"):
+        return "pending"
+    return (verdict or "").strip()
+
+
 def op_spec(op_type: str) -> dict:
     spec = OPERATION_SPECS.get(op_type)
     if spec is None:
@@ -290,9 +301,9 @@ def run(*, sha: str, deadline_secs: int,
             "%Y-%m-%dT%H:%M:%SZ", time.gmtime())
         resumed_at = event_at
         # the event is a WAKE, never truth — canonical authority decides
-        verdict = authority_after_wake(op_type, sha)
+        verdict = normalize_verdict(authority_after_wake(op_type, sha))
         if verdict == "pending" and not op_ci_alive(op_type, sha):
-            verdict = op_authority_verdict(op_type, sha)
+            verdict = normalize_verdict(op_authority_verdict(op_type, sha))
         mode = ("event_replayed" if verdict != "pending"
                 else "authority_unresolved")
         verdict_at = time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime())
@@ -340,7 +351,7 @@ def run(*, sha: str, deadline_secs: int,
                                            time.gmtime())
                 # WAKE received — canonical authority decides, never the
                 # event payload
-                verdict = authority_after_wake(op_type, sha)
+                verdict = normalize_verdict(authority_after_wake(op_type, sha))
                 if verdict != "pending":
                     mode = "event"
                     break
@@ -360,7 +371,7 @@ def run(*, sha: str, deadline_secs: int,
                         "%Y-%m-%dT%H:%M:%SZ", time.gmtime())
                     resumed_at = time.strftime("%Y-%m-%dT%H:%M:%SZ",
                                                time.gmtime())
-                    verdict = authority_after_wake(op_type, sha)
+                    verdict = normalize_verdict(authority_after_wake(op_type, sha))
                     if verdict != "pending":
                         mode = "event_recovered_from_durable_record"
                         break
@@ -374,26 +385,30 @@ def run(*, sha: str, deadline_secs: int,
                 rearm_reason = ("watchdog expiry; op runs non-terminal "
                                 "in Gitea — internal re-arm")
                 continue
-            # no live runs for THIS op's authority: terminal-in-Gitea but
-            # possibly aggregator-lagging — bounded re-read, then resolve
-            verdict = op_authority_verdict(op_type, sha)
-            if verdict == "pending":
-                # T21.4 cause C fixed: a pending verdict with no live runs
-                # may still be a lagging aggregator; one more bounded
-                # re-read before resolving truthfully. Still no control
-                # returned to the model — deadline governs.
-                verdict = op_authority_verdict(op_type, sha)
-            if verdict == "pending":
-                mode = "watchdog_lost_event_no_verdict"
-            else:
+            # no live runs visible for THIS op's authority: either the
+            # operation has not started yet (EXPECTED nonterminal — the
+            # §18-audit generator: this must re-arm, never return to the
+            # model) or it finished between probes. Bounded re-read.
+            verdict = normalize_verdict(op_authority_verdict(op_type, sha))
+            if verdict != "pending":
                 mode = "watchdog_authority_recovered"
-            break
+                break
+            verdict = normalize_verdict(op_authority_verdict(op_type, sha))
+            if verdict != "pending":
+                mode = "watchdog_authority_recovered"
+                break
+            # still pending: runs not started OR lagging aggregator —
+            # internal re-arm; the deadline is the only other exit
+            rearm_count += 1
+            rearm_reason = ("watchdog expiry; op pending (not started or "
+                            "lagging) — internal re-arm")
+            continue
     finally:
         os.close(fifo_fd)
     if verdict == "pending":
         if mode == "event":
             mode = "deadline_pending"
-        verdict = op_authority_verdict(op_type, sha)  # final one-shot truth
+        verdict = normalize_verdict(op_authority_verdict(op_type, sha))  # final one-shot truth
     verdict_at = time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime())
     out = {
         "sha": sha,

tests/test_single_logical_await.py

@@ -134,6 +134,56 @@ def test_single_logical_wait_survives_nonterminal_wakes(wr_daemon, monkeypatch):
     assert n >= 3  # authority re-read internally after each wake
 
 
+def test_pending_probe_failed_is_nonterminal(wr_daemon, monkeypatch):
+    """§18 audit fix: "pending (probe failed)" is a pending-class verdict —
+    the tool must re-arm internally, never return it as terminal."""
+    mod = _load()
+    assert mod.normalize_verdict("pending (probe failed)") == "pending"
+    assert mod.normalize_verdict("pending") == "pending"
+    assert mod.normalize_verdict("success") == "success"
+    # live: authority alternates probe-failure and pending, then success;
+    # ONE run() call absorbs all of it
+    rc, n = _single_wait_scenario(
+        wr_daemon, monkeypatch,
+        ["pending (probe failed)", "pending", "success"])
+    assert rc == 0
+    assert n >= 3
+
+
+def test_not_started_operation_rearms_internally(wr_daemon, monkeypatch):
+    """§18 audit fix: runs not visible yet is EXPECTED nonterminal —
+    internal re-arm, no model return."""
+    mod = _load()
+    seq = {"n": 0}
+
+    def authority(op_type, sha):
+        seq["n"] += 1
+        return "pending" if seq["n"] <= 2 else "success"
+
+    monkeypatch.setattr(mod, "op_authority_verdict", authority)
+    monkeypatch.setattr(mod, "op_ci_alive", lambda t, sha: False)
+
+    def post_wakes():
+        for _ in range(3):
+            deadline = time.time() + 10
+            while time.time() < deadline:
+                if ew.operation_wait(OP) is not None:
+                    wr_daemon.post_event({"operation_id": OP,
+                                          "provider": "gitea",
+                                          "event_type": "ci_completed",
+                                          "sha": SHA, "exit_code": 0,
+                                          "completed_at": time.time()})
+                    break
+                time.sleep(0.05)
+            time.sleep(1.0)
+
+    threading.Thread(target=post_wakes, daemon=True).start()
+    rc = mod.run(sha=SHA, deadline_secs=30, watchdog_secs=3,
+                 op_type="branch_ci", daemon_url=wr_daemon.url())
+    assert rc == 0
+    assert seq["n"] >= 3
+
+
 def test_deadline_is_the_only_model_return_for_pending(wr_daemon,
                                                        monkeypatch):
     """Authority stays pending the whole time: run() returns only at real