fix(sql): attribute a duplicated key to its own tags; key-value cap gets 2x headroom (R06:S-1 review I-1, m-3)

One stray duplicate row used to fail every tag in a key-value group or none of them,
depending on whether an unrelated key was absent. Duplicated keys are now refused
per key: only that key's tags publish BadConfigurationError and the rest of the group
reads normally. The key-value cap reads up to 2x the distinct keys (+1 to detect
excess), so a few stray duplicates are attributed per key and only a gross excess
(history/events table) fails the whole group. Duplicated-key refusals count as
answered refusals for health. The row-cap, duplicate-key and multi-row warnings now
use the per-plan limiter (m-3); the reader-wide limiter is removed. Unit tests pin
both the all-keys-present and absent-key cases with Good controls; live SQL Server
gate added (23/23).

Refs #744
Claude-Session: https://claude.ai/code/session_01Ub9hGmYLQvn9XETzw7CMsT
This commit is contained in:
Joseph Doherty
2026-10-22 16:32:23 -04:00
parent 8f0046ed05
commit c1b9c7ec5c
8 changed files with 206 additions and 85 deletions
@@ -116,6 +116,69 @@ public sealed class SqlServerReadTests
}
}
/// <summary>
/// Review I-1, live: one stray duplicate row in a key-value table fails ONLY that key's tag; the other
/// key in the same group (one capped <c>SELECT TOP (5) … IN (@k0, @k1)</c>) reads Good — the positive
/// control — and the driver stays Healthy.
/// </summary>
[Fact]
public async Task ReadAsync_realSqlServer_aDuplicatedKeyFailsOnlyItsOwnTag()
{
SkipUnlessLive();
const string table = "RowCapCurrent";
var qualified = $"{SqlPollServerFixture.Schema}.{table}";
await using (var arrange = await _sql.OpenInspectionConnectionAsync())
{
await using var command = arrange.CreateCommand();
command.CommandText = $"""
IF OBJECT_ID(N'{qualified}') IS NOT NULL DROP TABLE {qualified};
CREATE TABLE {qualified} (
{SqlPollServerFixture.KeyColumn} nvarchar(64) NOT NULL,
{SqlPollServerFixture.ValueColumn} float NULL,
{SqlPollServerFixture.TimestampColumn} datetime2 NOT NULL);
INSERT INTO {qualified} VALUES
(N'Pump7', 1.0, '2026-07-24T10:00:00'),
(N'Pump7', 2.0, '2026-07-24T10:00:01'),
(N'Pump8', 8.5, '2026-07-24T10:00:00');
""";
await command.ExecuteNonQueryAsync(TestContext.Current.CancellationToken);
}
try
{
await using var driver = await StartAsync(
KeyValueOn("Sql/Current/Pump7", "Pump7", table),
KeyValueOn("Sql/Current/Pump8", "Pump8", table));
var snapshots = await driver.ReadAsync(
["Sql/Current/Pump7", "Sql/Current/Pump8"], TestContext.Current.CancellationToken);
snapshots[0].StatusCode.ShouldBe(SqlStatusCodes.BadConfigurationError);
snapshots[1].StatusCode.ShouldBe(SqlStatusCodes.Good);
Convert.ToDouble(snapshots[1].Value).ShouldBe(8.5);
driver.GetHealth().State.ShouldBe(DriverState.Healthy);
}
finally
{
await using var cleanup = await _sql.OpenInspectionConnectionAsync();
await using var drop = cleanup.CreateCommand();
drop.CommandText = $"DROP TABLE IF EXISTS {qualified}";
await drop.ExecuteNonQueryAsync(CancellationToken.None);
}
}
private static RawTagEntry KeyValueOn(string rawPath, string key, string table) => Tag(rawPath, new JsonObject
{
["driver"] = "Sql",
["model"] = "KeyValue",
["table"] = SqlPollServerFixture.Qualified(table),
["keyColumn"] = SqlPollServerFixture.KeyColumn,
["keyValue"] = key,
["valueColumn"] = SqlPollServerFixture.ValueColumn,
["timestampColumn"] = SqlPollServerFixture.TimestampColumn,
});
// ---- key-value model ----
/// <summary>The plan's headline case: a seeded key-value row round-trips as a Good snapshot.</summary>
@@ -32,8 +32,9 @@ public class SqlGroupPlannerTests
// ---- R06:S-1: the row cap ----
/// <summary>
/// A key-value plan asks for one row more than it has distinct keys, and a where-pair wide-row plan for
/// two: enough to SEE an ambiguous selector, never enough to materialise a history table every poll.
/// A key-value plan reads up to twice its distinct keys (so stray duplicates are attributed per key) and
/// asks for one row more; a where-pair wide-row plan asks for two. Enough to SEE an ambiguous selector,
/// never enough to materialise a history table every poll.
/// The topByTimestamp form keeps its single-row limit and needs no cap.
/// </summary>
[Fact]
@@ -49,8 +50,8 @@ public class SqlGroupPlannerTests
], new SqlServerDialect()).ToList();
var kv = plans.Single(p => p.Model == SqlTagModel.KeyValue);
kv.RowCap.ShouldBe(2);
kv.SqlText.ShouldStartWith("SELECT TOP (3) ");
kv.RowCap.ShouldBe(4); // 2 distinct keys, with 2x headroom for per-key attribution
kv.SqlText.ShouldStartWith("SELECT TOP (5) ");
var wherePair = plans.Single(p => p.Parameters.Count == 1 && p.Model == SqlTagModel.WideRow);
wherePair.RowCap.ShouldBe(1);
@@ -90,7 +91,7 @@ public class SqlGroupPlannerTests
new SqlServerDialect());
plans[0].SqlText.ShouldBe(
"SELECT TOP (2) [tag_name], [num_value], [sample_ts] FROM [dbo].[TagValues] WHERE [tag_name] IN (@k0)");
"SELECT TOP (3) [tag_name], [num_value], [sample_ts] FROM [dbo].[TagValues] WHERE [tag_name] IN (@k0)");
plans[0].ParameterNames.ShouldBe(new[] { "@k0" });
plans[0].SelectedColumns.ShouldBe(new[] { "tag_name", "num_value", "sample_ts" });
plans[0].Model.ShouldBe(SqlTagModel.KeyValue);
@@ -107,7 +108,7 @@ public class SqlGroupPlannerTests
new SqlServerDialect());
plans[0].SqlText.ShouldBe(
"SELECT TOP (2) [tag_name], [num_value] FROM [dbo].[TagValues] WHERE [tag_name] IN (@k0)");
"SELECT TOP (3) [tag_name], [num_value] FROM [dbo].[TagValues] WHERE [tag_name] IN (@k0)");
plans[0].TimestampColumn.ShouldBeNull();
}
@@ -233,7 +234,7 @@ public class SqlGroupPlannerTests
KvTag("B", "TagValues", "tag_name", "Line1.Temp", "num_value", null),
], new ColonMarkerDialect()).ToList();
plans[0].SqlText.ShouldEndWith("IN (:k0, :k1) LIMIT 3");
plans[0].SqlText.ShouldEndWith("IN (:k0, :k1) LIMIT 5");
plans[0].SqlText.ShouldNotContain("@");
plans[0].ParameterNames.ShouldBe(new[] { ":k0", ":k1" });
}
@@ -456,7 +457,7 @@ public class SqlGroupPlannerTests
// A column name is an identifier — it cannot be parameterized, so the guarantee is that it is
// bracket-quoted with ] doubled, leaving one (nonexistent) identifier rather than executable SQL.
plans[0].SqlText.ShouldBe(
"SELECT TOP (2) [tag_name], [v]] ; DROP TABLE Users --] FROM [dbo].[T] WHERE [tag_name] IN (@k0)");
"SELECT TOP (3) [tag_name], [v]] ; DROP TABLE Users --] FROM [dbo].[T] WHERE [tag_name] IN (@k0)");
}
// ---- contract edges ----
@@ -272,25 +272,59 @@ public sealed class SqlPollReaderTests
snapshots[0].SourceTimestampUtc!.Value.ShouldBe(snapshots[0].ServerTimestampUtc);
}
/// <summary>
/// <b>R06:S-1 review I-1.</b> One stray duplicate row is attributed to ITS key: that key's tags publish
/// <see cref="SqlStatusCodes.BadConfigurationError"/> and every other key in the group reads normally.
/// It used to be last-row-wins Good, or the whole group Bad, depending on whether an UNRELATED key was
/// absent. Both variants are pinned: every other key present, and another key absent. The other keys'
/// Good / BadNoData are the positive controls.
/// </summary>
[Theory]
[InlineData(false)]
[InlineData(true)]
public async Task ReadAsync_aDuplicatedKey_failsOnlyThatKeysTags_whateverElseIsAbsent(bool withAnAbsentKey)
{
using var fixture = new SqlitePollFixture();
var logger = new RecordingLogger();
fixture.Execute(
$"INSERT INTO {SqlitePollFixture.KeyValueTable} " +
$"({SqlitePollFixture.KeyColumn}, {SqlitePollFixture.ValueColumn}, {SqlitePollFixture.TimestampColumn}) " +
$"VALUES ('{SqlitePollFixture.PresentKey}', 99.0, '2026-07-24T10:00:09Z')");
var tags = new List<SqlTagDefinition>
{
KvTag("Speed", SqlitePollFixture.PresentKey),
KvTag("Speed2", SqlitePollFixture.PresentKey), // a second tag on the duplicated key
KvTag("Pressure", SqlitePollFixture.SecondPresentKey),
};
if (withAnAbsentKey) tags.Add(KvTag("Gone", SqlitePollFixture.AbsentKey));
var reader = Reader(fixture, logger, [.. tags]);
var snapshots = await reader.ReadAsync([.. tags.Select(t => t.Name)], CancellationToken.None);
snapshots[0].StatusCode.ShouldBe(SqlStatusCodes.BadConfigurationError);
snapshots[1].StatusCode.ShouldBe(SqlStatusCodes.BadConfigurationError);
snapshots[2].StatusCode.ShouldBe(SqlStatusCodes.Good);
snapshots[2].Value.ShouldBe(SqlitePollFixture.SecondPresentValue);
if (withAnAbsentKey) snapshots[3].StatusCode.ShouldBe(SqlStatusCodes.BadNoData);
var warning = logger.Entries.ShouldHaveSingleItem();
warning.Message.ShouldContain(SqlitePollFixture.PresentKey);
}
/// <summary>The driver counts a duplicated-key refusal as the database answering, like an over-cap one.</summary>
[Fact]
public async Task ReadAsync_whenASourceViolatesOneRowPerKey_takesTheLastRowDeterministically()
public async Task ReadDetailedAsync_aDuplicatedKey_isReportedAsAnAnsweredRefusal()
{
using var fixture = new SqlitePollFixture();
fixture.Execute(
$"INSERT INTO {SqlitePollFixture.KeyValueTable} " +
$"({SqlitePollFixture.KeyColumn}, {SqlitePollFixture.ValueColumn}, {SqlitePollFixture.TimestampColumn}) " +
$"VALUES ('{SqlitePollFixture.PresentKey}', 99.0, '2026-07-24T10:00:09Z')");
// Two keys, one absent: the duplicate fits inside the row cap (2), so it is not provably a history
// table — the last-row-wins rule still applies there (the cap test below covers the other side).
var reader = Reader(fixture,
KvTag("Speed", SqlitePollFixture.PresentKey), KvTag("Gone", SqlitePollFixture.AbsentKey));
var reader = Reader(fixture, KvTag("Speed", SqlitePollFixture.PresentKey));
var clean = Reader(fixture, KvTag("Pressure", SqlitePollFixture.SecondPresentKey));
var snapshots = await reader.ReadAsync(["Speed", "Gone"], CancellationToken.None);
// Design §3.6: the contract is one row per key; when a source breaks it the reader is at least
// deterministic — last occurrence in reader order — rather than silently arbitrary.
snapshots[0].Value.ShouldBe(99.0);
snapshots[1].StatusCode.ShouldBe(SqlStatusCodes.BadNoData);
(await reader.ReadDetailedAsync(["Speed"], CancellationToken.None)).AnsweredRefusalGroups.ShouldBe(1);
(await clean.ReadDetailedAsync(["Pressure"], CancellationToken.None)).AnsweredRefusalGroups.ShouldBe(0);
}
/// <summary>