src/flask/static/css/app.css

@@ -498,6 +498,13 @@ table.data .comment { color: var(--text-muted); font-size: .84rem; }
 .chip--warn { background: var(--warn-dim); color: var(--warn); }
 .chip--danger { background: var(--danger-dim); color: var(--danger); }
 .chip--good { background: var(--success-dim); color: var(--success); }
+/* A run whose readings are impossible: shown in the table so it can be
+   corrected, but marked as not counted in the averages. */
+.data tbody tr.is-suspect td {
+    color: var(--text-muted);
+    background: rgba(232, 163, 61, .06);
+}
+
 .chip--tap {
     background: var(--bg-raised-2);
     border: 1px solid var(--amber-deep);

src/flask/static/js/charts.js

@@ -305,8 +305,12 @@
         fetch("/api/runs", { headers: { "Accept": "application/json" } })
             .then(function (r) { return r.json(); })
             .then(function (runs) {
+                // A run with an impossible reading has no attenuation, and
+                // is flagged as suspect.  Both are excluded, so one bad
+                // reading cannot become a bar in the chart.
                 var done = runs.filter(function (r) {
-                    return r.attenuation !== null && r.attenuation !== undefined;
+                    return !r.suspect &&
+                        r.attenuation !== null && r.attenuation !== undefined;
                 });
                 if (!done.length) { return; }
 
@@ -383,8 +387,11 @@
         fetch("/api/runs", { headers: { "Accept": "application/json" } })
             .then(function (r) { return r.json(); })
             .then(function (runs) {
+                // A run with an impossible reading has a broken curve - it
+                // plunges to a gravity below water - which would drag the
+                // median line down and stretch the envelope to cover it.
                 var withCurve = runs.filter(function (r) {
-                    return r.curve && r.curve.length > 1;
+                    return !r.suspect && r.curve && r.curve.length > 1;
                 });
                 if (!withCurve.length) { return; }
 

src/flask/templates/analysis.html

@@ -92,7 +92,7 @@
 <section class="card mb-lg">
     <div class="card__head">
         <h2 class="card__title">Every finished brew</h2>
-        <span class="card__hint">{{ stats.count }} brews</span>
+        <span class="card__hint">{{ stats.count }} brews{% if stats.suspect_count %} ({{ stats.trusted_count }} counted){% endif %}</span>
     </div>
     <div class="card__body card__body--flush">
         <div class="table-wrap">
@@ -112,9 +112,9 @@
                 </thead>
                 <tbody>
                 {% for row in rows %}
-                    <tr>
+                    <tr{% if row.suspect %} class="is-suspect"{% endif %}>
                         <td class="mono">{{ row.beer_run_id }}</td>
-                        <td>{{ row.name }}</td>
+                        <td>{{ row.name }}{% if row.suspect %} <span class="chip chip--warn">not counted</span>{% endif %}</td>
                         <td class="num">
                             {% if row.og_points is not none %}
                                 {{ '%.3f' % (row.og_points / 1000) }}
@@ -184,7 +184,7 @@
     </div>
     <div class="card__body">
         <p>
-            Across {{ stats.count }} finished brews the attenuation averages
+            Across {{ stats.trusted_count }} finished brews the attenuation averages
             <strong>{{ stats.consistency.mean }}%</strong>, with a standard
             deviation of <strong>{{ stats.consistency.stdev }} percentage
             points</strong> and a total range of {{ stats.consistency.spread }}

src/flask/views/analysis.py

@@ -48,10 +48,12 @@ def deep():
     finished = [r for r in runs if not r.is_active()]
 
     # Runs whose gravity readings are physically impossible are excluded from
-    # the averages and listed separately, rather than being silently folded
+    # EVERY aggregate and listed separately, rather than being silently
-    # in (a final gravity below 1.000 would otherwise show as a 338%
+    # folded in.  A final gravity below 1.000 would otherwise show as a
-    # attenuation).
+    # 338% attenuation AND a 56-day brew AND the strongest beer in the
+    # history - one bad reading poisoning three different statistics.
     suspect = implausible_runs(finished)
+    suspect_ids = {s["beer_run_id"] for s in suspect}
 
     rows = []
     for run in finished:
@@ -71,14 +73,20 @@ def deep():
             "days_to_1015": days_to_target(run, 1015),
             "readings": summary["reading_count"],
             "curve": summary["curve"],
+            # A suspect run is shown in the table so it can be corrected,
+            # but it contributes to none of the averages.
+            "suspect": run.beer_run_id in suspect_ids,
         })
 
     # The rows with a usable curve, for the overlay chart.
     curves = [r for r in rows if r["curve"]]
 
-    attenuations = [r["attenuation"] for r in rows if r["attenuation"] is not None]
+    # Only the trustworthy runs feed the statistics.
-    durations = [r["days"] for r in rows if r["days"] is not None]
+    good = [r for r in rows if not r["suspect"]]
-    to_1010 = [r["days_to_1010"] for r in rows if r["days_to_1010"] is not None]
+
+    attenuations = [r["attenuation"] for r in good if r["attenuation"] is not None]
+    durations = [r["days"] for r in good if r["days"] is not None]
+    to_1010 = [r["days_to_1010"] for r in good if r["days_to_1010"] is not None]
 
     # --- consistency ------------------------------------------------------- #
     # How much the attenuation varies.  A tight spread means the process is
@@ -93,9 +101,9 @@ def deep():
             "spread": round(max(attenuations) - min(attenuations), 1),
         }
 
-    fastest = min((r for r in rows if r["days"] is not None),
+    fastest = min((r for r in good if r["days"] is not None),
                   key=lambda r: r["days"], default=None)
-    slowest = max((r for r in rows if r["days"] is not None),
+    slowest = max((r for r in good if r["days"] is not None),
                   key=lambda r: r["days"], default=None)
 
     return render_template(
@@ -105,6 +113,9 @@ def deep():
         suspect=suspect,
         stats={
             "count": len(rows),
+            "suspect_count": len(suspect),
+            # How many runs the figures are actually based on.
+            "trusted_count": len(good),
             "avg_attenuation": round(sum(attenuations) / len(attenuations), 1)
             if attenuations else None,
             "avg_days": _fmt_days(sum(durations) / len(durations)) if durations else None,
@@ -198,6 +209,8 @@ def history():
 
     summaries = [_decorate(run, metadata) for run in runs]
     completed = [s for s in summaries if not s["active"]]
+    # The Run objects for the finished brews, for the plausibility check.
+    completed_runs = [run for run in runs if not run.is_active()]
 
     # --- ABV comparison: standard formula vs the legacy one ---------------- #
     abv_rows = []
@@ -244,9 +257,17 @@ def history():
                     "comment": reading["comment"],
                 })
 
-    avg_abv = round(sum(r["abv"] for r in abv_rows) / len(abv_rows), 2) if abv_rows else 0
+    # A run with an impossible final gravity produces an impossible ABV
-    best = max(abv_rows, key=lambda r: r["abv"]) if abv_rows else None
+    # (run 12 reads 18.64%), which would make it the "strongest" beer in
-    worst = min(abv_rows, key=lambda r: r["abv"]) if abv_rows else None
+    # the history and drag the average up.  Those runs are excluded from
+    # the ABV figures here and listed on the analysis page.
+    history_suspect = {s["beer_run_id"] for s in implausible_runs(completed_runs)}
+    good_abv_rows = [r for r in abv_rows if r["beer_run_id"] not in history_suspect]
+
+    avg_abv = round(sum(r["abv"] for r in good_abv_rows) / len(good_abv_rows), 2) \
+        if good_abv_rows else 0
+    best = max(good_abv_rows, key=lambda r: r["abv"]) if good_abv_rows else None
+    worst = min(good_abv_rows, key=lambda r: r["abv"]) if good_abv_rows else None
 
     return render_template(
         "history.html",

src/flask/views/brews.py

@@ -9,7 +9,7 @@ from wtforms import (BooleanField, DateField, IntegerField, StringField,
                      SubmitField, TextAreaField)
 from wtforms.validators import DataRequired, Length, NumberRange, Optional
 
-from brewing import is_plausible_sg, run_summary
+from brewing import implausible_runs, is_plausible_sg, run_summary
 
 bp = Blueprint("brews", __name__)
 
@@ -178,6 +178,11 @@ def api_runs():
     runs = repo().runs()
     metadata = repo().all_run_metadata()
 
+    # The runs whose readings are physically impossible.  They are flagged
+    # rather than dropped: the charts use the flag to leave them out of the
+    # averages and the curve envelope, but a caller can still see them.
+    suspect_ids = {s["beer_run_id"] for s in implausible_runs(runs)}
+
     payload = []
     for run in runs:
         meta = metadata.get(run.beer_run_id, {})
@@ -185,6 +190,7 @@ def api_runs():
         summary["canonical_name"] = meta.get("name") or run.display_name()
         summary["tap_number"] = meta.get("tap_number")
         summary["last_date"] = _last_reading_date(run)
+        summary["suspect"] = run.beer_run_id in suspect_ids
         payload.append(summary)
 
     return jsonify(payload)

tests/conftest.py

@@ -53,6 +53,17 @@ def repo(mongo_client):
     return BeerRepository(client=mongo_client)
 
 
+@pytest.fixture()
+def logged_in(client, repo):
+    """A client with an authenticated session and a user in the database."""
+    repo.users.insert_one({"username": "beer", "password": "beer_pass"})
+
+    response = client.post("/login", data={"username": "beer", "password": "beer_pass"},
+                           follow_redirects=True)
+    assert response.status_code == 200
+    return client
+
+
 def seed_readings(repository, rows):
     """Insert reading documents directly, bypassing the app.
 

tests/test_analysis.py

@@ -9,6 +9,7 @@ import pytest
 
 from brewing import (Run, attenuation_percent, days_to_target,
                      fermentation_curve)
+from conftest import seed_readings
 
 
 def _doc(run_id="1", beer_type="Ale", sg="1045", date_="2026-01-01",
@@ -241,3 +242,136 @@ def test_attenuation_chart_truncates_long_names():
     assert "name.length > 18" in charts_js, (
         "the attenuation chart is not trimming long beer names"
     )
+
+# ------------------------------------------- suspect runs are not counted #
+
+def _two_runs(repo):
+    """One good brew and one with an impossible final gravity.
+
+    The bad run mimics the live data: run 12 has a final gravity of 900,
+    which is below water and makes the run look like a 56-day brew that
+    reached 18.64% alcohol.
+    """
+    seed_readings(repo, [
+        ("1", "Good ale", "1050", "2026-01-01", False, ""),
+        ("1", "Good ale", "1010", "2026-01-10", True, ""),
+        # 56 days, and a final gravity below 1.000.
+        ("12", "Bad brew", "1042", "2026-01-01", False, ""),
+        ("12", "Bad brew", "0900", "2026-02-26", True, "typo"),
+    ])
+
+
+def _stat_values(body):
+    """The figures in the analysis stat tiles, in order.
+
+    The tiles are rendered as label/value pairs, so the numbers can be
+    pulled out without depending on the exact markup.
+    """
+    import re
+    values = re.findall(r'<div class="stat__value">([^<]+)</div>', body)
+    return [v.strip() for v in values]
+
+
+def test_a_suspect_run_is_excluded_from_the_brew_time_average(logged_in, repo):
+    """The 56-day bad run must not drag the average brew time up.
+
+    This was the review finding: the run was excluded from the attenuation
+    average but not from the brew-time average, so one bad reading was
+    poisoning two different statistics.
+    """
+    _two_runs(repo)
+
+    response = logged_in.get("/analysis")
+    assert response.status_code == 200
+
+    body = response.get_data(as_text=True)
+    values = _stat_values(body)
+    assert values, "the analysis page rendered no stat tiles"
+
+    # The stat tiles are: average attenuation, spread, average brew time,
+    # time to 1.010.  The good run took 9 days; with the bad run folded
+    # in the average would be (9 + 56) / 2 = 32.5 days.
+    assert "9d" in values, f"expected a 9 day brew time, got {values}"
+
+
+def test_a_suspect_run_is_excluded_from_the_time_to_1010_average(logged_in, repo):
+    """Same for the "time to 1.010" figure."""
+    _two_runs(repo)
+
+    response = logged_in.get("/analysis")
+    body = response.get_data(as_text=True)
+    values = _stat_values(body)
+    assert values
+    # The good run reached 1.010 in 9 days; the bad one "reached" it in 56.
+    assert "9d" in values, f"expected 9 days to 1.010, got {values}"
+
+
+def test_the_suspect_run_is_still_listed_for_review(logged_in, repo):
+    """Excluding it from the averages must not hide it.
+
+    The run has to stay visible so it can be corrected.
+    """
+    _two_runs(repo)
+
+    response = logged_in.get("/analysis")
+    body = response.get_data(as_text=True)
+    assert "Readings that need a second look" in body
+    assert "0.900" in body
+
+
+def test_a_suspect_run_is_flagged_in_the_api(logged_in, repo):
+    """The charts fetch /api/runs, so the flag has to be in the payload."""
+    _two_runs(repo)
+
+    response = logged_in.get("/api/runs")
+    assert response.status_code == 200
+
+    payload = response.get_json()
+    by_run = {str(r["beer_run_id"]): r for r in payload}
+    assert by_run["12"]["suspect"] is True
+    assert by_run["1"]["suspect"] is False
+
+
+def test_a_suspect_run_is_not_the_strongest_brew_in_the_history(logged_in, repo):
+    """The history page showed the bad run as the strongest beer.
+
+    An impossible final gravity produced an 18.64% ABV, which made run 12
+    the "strongest" brew in the history and pulled the average up.
+
+    The run's own row still shows its ABV - it is real data, and hiding it
+    would be worse - but it must not be counted as the strongest brew, and
+    it must not appear in the "Strongest" figure.
+    """
+    _two_runs(repo)
+
+    response = logged_in.get("/history")
+    assert response.status_code == 200
+
+    body = response.get_data(as_text=True)
+
+    # The "Strongest" tile shows the good run's 4.76%, not the bad
+    # run's 18.64%.  Find the Strongest tile and read its value.
+    import re
+    strongest = re.search(
+        r"Strongest.*?stat__value[^>]*>([^<]+)<", body, re.DOTALL
+    )
+    assert strongest, "the history page has no Strongest figure"
+    assert "18.64" not in strongest.group(1), (
+        f"the suspect run was counted as the strongest brew: {strongest.group(1)}"
+    )
+
+
+def test_the_charts_skip_suspect_runs():
+    """The chart script must leave the suspect runs out.
+
+    A suspect run's fermentation curve plunges to a gravity below water,
+    which would drag the median line down and stretch the envelope.
+    """
+    charts_js = (
+        Path(__file__).resolve().parents[1]
+        / "src" / "flask" / "static" / "js" / "charts.js"
+    ).read_text()
+
+    assert charts_js.count("!r.suspect") >= 2, (
+        "the charts must filter out the runs flagged as suspect"
+    )

tests/test_app.py

@@ -7,17 +7,6 @@ import pytest
 from conftest import seed_readings
 
 
-@pytest.fixture()
-def logged_in(client, repo):
-    """A client with an authenticated session and a user in the database."""
-    repo.users.insert_one({"username": "beer", "password": "beer_pass"})
-
-    response = client.post("/login", data={"username": "beer", "password": "beer_pass"},
-                           follow_redirects=True)
-    assert response.status_code == 200
-    return client
-
-
 # ------------------------------------------------------------------ public #
 
 def test_healthz_is_public(client):