MCP builder tools return wrong results without an error: `min`/`max` of a DateTime is 0, and unknown options such as `having` are silently ignored

Ouverte
#3,543 1 commentaire 0 réactions 0 personnes assignées Voir sur GitHub

Les mainteneurs répondent en général sous 1 jour

Personne n'a encore pris cette issue.

Évaluation

Difficulté
4/5
Temps estimé
3-5 jours
Accessibilité débutants
55/100
Type d'issue
Bug
Clarté
Clairement spécifiée
Activité
Active
Stack technique
clickhouse, typescript
Domaine
api, backend

Piste de recherche

Start with packages/common-utils/src/core/renderChartConfig.ts around lines 540–543 and packages/api/src/mcp/tools/query/table.ts around line 32; compare the generated aggregate SQL and how the input schema handles unknown keys. Reproduce both cases using the SQL example in the issue and a clickstack_table call with having. Done means DateTime min/max return timestamps and unsupported options produce a validation error or are applied as specified.

Rédigé par le modèle d'indexation à partir du texte de l'issue.

Description

external

Summary

Two cases where clickstack_table / clickstack_timeseries return a plausible-looking answer that is wrong, with no error or warning. Agents can't tell, so they build conclusions on them.

  1. min/max on a DateTime column return 0. Every non-count aggregate wraps its value in toFloat64OrDefault(toString(expr)) (packages/common-utils/src/core/renderChartConfig.ts:540-543). For Date/DateTime/DateTime64, toString() gives '2026-11-04 08:00:00.000000000', which doesn't parse as a float, so every value becomes 0 and max(Timestamp) is 0.
  2. Unknown options are dropped. The tool input schemas are plain z.object(...) (e.g. tableSchema in packages/api/src/mcp/tools/query/table.ts:32), so zod strips keys it doesn't know. having: "lines > 5" is accepted, the SQL has no HAVING, and rows with 1 come back. Agents try having because dashboard tiles support it (packages/api/src/mcp/tools/dashboards/schemas.ts:839).

Environment

HyperDX 2-nightly image (late Oct 2026) with ClickHouse 26.10.3. Code references checked on main at d08b2fa7 (2026-11-03, 2.43.1).

Steps to reproduce

  1. clickstack_table on a log or trace source, select: [{aggFn: "min", valueExpression: "Timestamp", alias: "first_seen"}, {aggFn: "max", valueExpression: "Timestamp", alias: "last_seen"}], any time range with data.
  2. Result: first_seen: 0, last_seen: 0. The SQL in system.query_log is max(toFloat64OrDefault(toString(Timestamp))).

The cast alone, on any ClickHouse:

WITH arrayJoin([toDateTime64('2026-11-04 07:59:01.123', 9), toDateTime64('2026-11-04 08:00:00', 9)]) AS Timestamp
SELECT max(toFloat64OrDefault(toString(Timestamp))) AS rendered, max(Timestamp) AS expected
-- rendered = 0, expected = 2026-11-04 08:00:00.000000000
  1. clickstack_table with groupBy and having: "count > 5": no validation error, the generated SQL has no HAVING, and groups with count 1 are returned.

Expected vs actual

Expected Actual
max(Timestamp) the latest timestamp (or a clear error) 0
unknown option having a validation error naming the valid options, or having applied silently ignored

Impact

In 4 agent investigations on production-size data (about 170 MCP calls), 3 asked "first seen / last seen" questions and got 0 back, and 2 used having and got unfiltered results (one call returned 1,044 groups, which then hit response trimming, see #3542).

Proposed fix

  • min, max and any don't need a Float64 value. Pass the expression through uncast for them, or convert dates numerically (e.g. toUnixTimestamp64Milli) instead of via toString. The aggregate already handles numbers and numeric strings today, so a type check (date-like → no cast) keeps that behaviour.
  • Make the MCP tool input schemas .strict(), so an unknown key returns a validation error listing the accepted options. Adding having and limit to clickstack_table itself, as tiles already support, is part of #3542.

Related

  • #3542: MCP response trimming, and clickstack_table has no limit, having or default order
  • #3499: valueExpression ignored on metric selects
  • #2311 / #3237: count_distinct on metric tiles
Langage dominant
TypeScript
Étoiles
10.1k
Forks
527
Merge moyen
1 j 20 h
PR mergées (30 j)
186

Préparer son environnement

Par où commencer

  1. Lisez l'issue en entier, puis le guide de contribution du projet.
  2. Signalez en commentaire que vous la prenez — cela évite que deux personnes fassent le même travail.
  3. Forkez le dépôt et travaillez sur une branche.
  4. Ouvrez une pull request qui référence le numéro de l'issue.

Autres issues de ClickHouse/ClickStack

Toutes les issues de ClickHouse/ClickStack

Issues similaires

Plus d'issues TypeScript

Recevez les nouvelles issues par e-mail

Un résumé court des issues GitHub adaptées aux débutants.