no-mistakes(review): Restore quiet-mode silence; keep provenance on failure alert

docs/probe-drift-round2-evidence.md

@@ -240,7 +240,7 @@ The health script prints `📍 executed from: script=… cwd=…` and includes
 $ pwd -P
 /root/.treehouse/prose-contracts-9ce5f3/3/prose-contracts
 $ python3 -m pytest -q
-23 passed
+24 passed
 $ shellcheck scripts/prose-lint.sh
 (clean)
 ```

scripts/agent-health-check.py

@@ -46,7 +46,7 @@ Changelog:
     a stale-consumer report is distinguishable from a fault at read time.
 """
 
-import subprocess, json, sys, os, time, re
+import subprocess, json, sys, os, time, re, io, contextlib
 from datetime import datetime
 
 LITELLM = "http://192.168.68.116:80"
@@ -659,30 +659,7 @@ def deploy_self():
 # MAIN
 # ═══════════════════════════════════════════════════════════════════
 
-def main():
-    quiet = "--quiet" in sys.argv
-    as_json = "--json" in sys.argv
-
-    # Self-deploy to canonical location
-    if not quiet and "--no-deploy" not in sys.argv:
-        deploy_self()
-
-    # Provenance: a report is only actionable if the reader can tell WHICH copy
-    # of this script produced it. Emit the absolute execution path (script + cwd)
-    # in human, cron-alert, and --json output so a stale-consumer report is
-    # distinguishable from a real fault at read time. The production cron path
-    # runs --quiet, so provenance must NOT be behind the quiet guard.
-    script_path = os.path.abspath(__file__)
-    cwd = os.getcwd()
-
-    if not quiet:
-        print(f"🏥 Agent Health Check v4 — {datetime.now().strftime('%Y-%m-%d %H:%M UTC')}")
-    print(f"📍 executed from: script={script_path} cwd={cwd}")
-    if not quiet:
-        print()
-
-    load_agent_keys()
-
+def _run_checks():
     print("🔑 LiteLLM Keys:")
     check_keys()
     print()
@@ -710,6 +687,37 @@ def main():
     print("🔐 Vault Secrets:")
     check_vault_secrets()
 
+
+def main():
+    quiet = "--quiet" in sys.argv
+    as_json = "--json" in sys.argv
+
+    # Self-deploy to canonical location
+    if not quiet and "--no-deploy" not in sys.argv:
+        deploy_self()
+
+    # Provenance: a report is only actionable if the reader can tell WHICH copy
+    # of this script produced it. A normal run carries it in the header, --json
+    # carries it for machine consumers, and the cron ALERT line carries it on
+    # failure. --quiet is documented as "only output on failure", so the header
+    # is emitted only when not quiet and a healthy quiet run stays silent.
+    script_path = os.path.abspath(__file__)
+    cwd = os.getcwd()
+
+    if quiet:
+        captured = io.StringIO()
+        with contextlib.redirect_stdout(captured):
+            load_agent_keys()
+            _run_checks()
+        if FAIL:
+            sys.stdout.write(captured.getvalue())
+    else:
+        print(f"🏥 Agent Health Check v4 — {datetime.now().strftime('%Y-%m-%d %H:%M UTC')}")
+        print(f"📍 executed from: script={script_path} cwd={cwd}")
+        print()
+        load_agent_keys()
+        _run_checks()
+
     if FAIL:
         print(f"\n❌ {len(FAIL)} FAILURE(S): {' | '.join(FAIL)}")
         if quiet:

tests/test_probe_drift.py

@@ -137,17 +137,28 @@ def test_json_reports_absolute_execution_provenance(ahc, monkeypatch, capsys):
 
 
 def test_quiet_run_still_carries_provenance_on_the_alert_path(ahc, monkeypatch, capsys):
-    # The production cron runs --quiet; a report without provenance is
-    # unactionable (item 4). Both the header line and the ALERT line must carry it.
+    # The cron runs --quiet; a failure report must still carry provenance. The
+    # header line is suppressed in quiet mode, so the ALERT line is the carrier.
     code, out = _run_main(ahc, monkeypatch, capsys, ["--quiet"])
     assert code == 1
-    assert "📍 executed from: script=" in out
+    assert "📍 executed from:" not in out
     alerts = [ln for ln in out.splitlines() if ln.startswith("ALERT agent-health:")]
     assert alerts, out
     assert f"script={os.path.abspath(str(AHC))}" in alerts[0]
     assert f"cwd={os.getcwd()}" in alerts[0]
 
 
+def test_quiet_healthy_run_emits_no_stdout(ahc, monkeypatch, capsys):
+    # --quiet is documented as "only output on failure": a run with no fleet
+    # failures must produce no stdout at all (the production cron runs --quiet).
+    for name in ("check_keys", "check_gpu_ports", "check_agents", "check_ct_liveness",
+                 "check_config_integrity", "check_wrapper_integrity", "check_vault_secrets"):
+        monkeypatch.setattr(ahc, name, lambda: None)
+    code, out = _run_main(ahc, monkeypatch, capsys, ["--quiet"])
+    assert code == 0
+    assert out == ""
+
+
 def test_json_surfaces_report_only_findings_separately(ahc, monkeypatch, capsys):
     # Koby's down legs are reported but must not count as fleet failures; the
     # --json payload exposes them in their own array (item 1 + f8).