MCP response trimming replaces the largest values whole (often the top result) and ignores topN; `clickstack_table` has no `limit`, `having` or default order

Aperta
#3,542 2 commenti 0 reazioni 0 assegnatari Vedi su GitHub

I maintainer di solito rispondono entro 1 giorno

Nessuno ha ancora preso questa issue.

Valutazione

Difficoltà
4/5
Tempo stimato
3-5 giorni
Idoneità per principianti
52/100
Tipo di issue
Bug
Chiarezza
Specificata chiaramente
Stato di attività
Attiva
Stack tecnologico
clickhouse, typescript

Direzione di ricerca

Start with packages/api/src/utils/trimToolResponse.ts and reproduce the trimming behavior with the self-contained repro.mts described in the issue. Then inspect the clickstack_table tool and compare its options with packages/api/src/mcp/tools/dashboards/schemas.ts. Done means long values are shortened before results are dropped, pattern results preserve requested topN where possible, grouped tables have bounded and ordered results, and the note describes what was cut.

Scritto dal modello di indicizzazione a partire dal testo della issue.

Descrizione

external

Summary

When a tool result is over the size budget, trimToolResponse (packages/api/src/utils/trimToolResponse.ts) keeps the first items of an array and replaces any value that is still too big with {"__hdx_trimmed": true, "originalSize": N}. It never shortens a string. Because the budget is split equally across keys, the biggest values go first, and in pattern and log results the biggest values are usually the most important ones: long stack traces.

For clickstack_table, the tool has no limit, no having and no default ORDER BY, so a large grouped result is cut to its first rows in whatever order ClickHouse returned them.

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_event_patterns with topN: 30 on a service whose top errors are multi-line stack traces.
  2. The response has 10 patterns, and the top ones look like {"rank":1,"pattern":{"__hdx_trimmed":true,"originalSize":7443},"whereSnippet":{"__hdx_trimmed":true,…},"samples":[{"__hdx_trimmed":true,…}]}.

Self-contained (repro.mts below; runs the real trimToolResponse from main on an event_patterns-shaped object with 3 long and 27 short patterns):

isTrimmed=true; topN requested=30, patterns returned=10
rank 1: pattern={"__hdx_trimmed":true,"originalSize":4736} whereSnippet={"__hdx_trimmed":true,…} samples[0]={"__hdx_trimmed":true,…}
rank 2: … same
rank 3: … same
rank 4: pattern="Short INFO line 0 took <*> ms" (complete)
  1. clickstack_table with a groupBy that yields a few thousand groups and no orderBy: the response holds the first rows of an unordered result (one run: 2,638 rows in, about 75 out), plus "Result was trimmed".

Expected vs actual

Expected Actual
Over-budget pattern result the top N patterns, with long strings shortened (…(+6,900 chars)) and fewer samples 10 patterns; the top 3 replaced by markers
Large grouped table the top rows by the first select (or by orderBy), up to a limit the first rows in arbitrary order

Impact

In 4 agent investigations on production-size data: the most frequent error pattern of one service (99.5% of its ERROR lines) came back as a marker in 3 of 4 calls; topN 15–30 returned 10 every time; 66 KB and 81 KB responses still overflowed the client; and table calls returned 89–12,194 unordered groups that were then cut.

Proposed fix

  1. In trimToolResponse, shorten long strings (e.g. to 500–2,000 chars with a suffix saying how much was cut) before replacing values or dropping array items.
  2. For pattern results, drop samples (keep 1) before dropping patterns, and keep the requested topN when it fits after that.
  3. Add limit (default about 50) and having to clickstack_table, as dashboard tiles already have (packages/api/src/mcp/tools/dashboards/schemas.ts:839, :947), and default ORDER BY to the first select descending when groupBy is set.
  4. Say in the note what was cut (e.g. "20 patterns dropped, 3 strings shortened").

Related

  • #2337: shared MCP helpers and error hints
repro.mts
// Repro for trimToolResponse (packages/api/src/utils/trimToolResponse.ts) on an
// event_patterns-shaped result: long values are replaced, not shortened, and the
// array is cut to 10 items regardless of topN.
// Run from <hyperdx>/packages/api:  npx tsx <this file> ./src/utils/trimToolResponse.ts
import { pathToFileURL } from 'node:url';
const { trimToolResponse } = await import(pathToFileURL(process.argv[2]).href);

const stack = (n: number) => `java.lang.NullPointerException: Cannot invoke "Catalog.items()" (case ${n})\n` +
  Array.from({ length: 90 }, (_, i) => `\tat com.example.svc.Layer${i}.call(Layer${i}.java:${i + 10})`).join('\n'); // ~7.4 KB

const pattern = (rank: number, text: string, count: number) => ({
  rank, id: `p${rank}`, pattern: text, estimatedCount: count, sampleCount: count, shareOfTotal: 0,
  whereSnippet: `Body:"${text.slice(0, 2000)}"`, samples: Array.from({ length: 5 }, () => text),
});
const patterns = [
  ...[0, 1, 2].map(i => pattern(i + 1, stack(i), 9950 - i)),               // the 3 most frequent: long stack traces
  ...Array.from({ length: 27 }, (_, i) => pattern(i + 4, `Short INFO line ${i} took <*> ms`, 30 - i)),
];
const output = { summary: { totalCount: 100000, patternsReturned: patterns.length }, patterns, usage: 'shareOfTotal is …' };

const { data, isTrimmed } = trimToolResponse(output);
console.log(`isTrimmed=${isTrimmed}; topN requested=30, patterns returned=${data.patterns.length}`);
for (const p of data.patterns.slice(0, 4)) {
  const show = (v: unknown) => (typeof v === 'string' ? `"${v.slice(0, 40)}…" (${v.length} chars)` : JSON.stringify(v));
  console.log(`rank ${p.rank}: pattern=${show(p.pattern)} whereSnippet=${show(p.whereSnippet)} samples[0]=${show(Array.isArray(p.samples) ? p.samples[0] : p.samples)}`);
}
Lingua principale
TypeScript
Stelle
10.1k
Fork
527
Merge medio
1g 20h
PR unite (30g)
186

Preparare l'ambiente

Come iniziare

  1. Leggi tutta la issue e poi la guida ai contributi del progetto.
  2. Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
  3. Fai un fork del repository e lavora su un branch.
  4. Apri una pull request che faccia riferimento al numero della issue.

Altre issue di ClickHouse/ClickStack

Tutte le issue di ClickHouse/ClickStack

Issue simili

Altre issue su TypeScript

Ricevi le nuove issue nella tua casella

Un breve riepilogo di issue GitHub adatte ai principianti.