trace_query_events

[analysis]

Queries normalized GliderTrace evidence events by session, kind, text, severity, and cursor.

Try it locally in the GliderTrace playground

Parameters

Examples

Replace sample paths and symbol keys with values from your workspace.

Find exception events in a session

{
  "sessionId": "trc_20260507_123044_ab12cd34",
  "kinds": [
    "exception"
  ]
}

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "trace_query_events",
    "arguments": {
      "sessionId": "trc_20260507_123044_ab12cd34",
      "kinds": [
        "exception"
      ]
    }
  }
}

Response Notes

Returns matching normalized events, a pagination cursor, severity counts, and artifact context. It carries a coverage block. An incomplete block adds a warning. A zero-match page may still hide dropped events. Paging is a presentation limit, not incompleteness.

Unreleased builds with text provenance add source and exceptionRelation to recognized text exceptions. source.sourceId identifies one text input within the session; treat it as opaque. source.line and source.column use one-based lines and UTF-16 columns within that source. source.rawArtifactUri identifies retained raw text, or is null when no copy remains. A known sourceId with null rawArtifactUri means unretained text; missing sourceId in older records means unknown identity. evidence.artifactUri can identify normalized storage; it cannot replace an absent rawArtifactUri.

source.timestampBasis is ingestion for imported text or collection for captured command output. Neither establishes original event time. Missing fields in older sessions mean unknown provenance.

Positions recover order within one sourceId, including when raw text is unretained. They establish neither source-code identity nor chronology across inputs. Source IDs establish no identity across sessions.

exceptionRelation contains chainId, parentEvidenceId, zero-based chainIndex, parsedChainLength, and rootKnown. Explicit inner-exception markers establish supported linear relationships. parsedChainLength counts recognized headers; rootKnown identifies a recognized outer header. Neither proves complete capture. Independent exceptions remain separate; AggregateException branches and arbitrary multiline message continuations remain unsupported.

A parent ID can refer outside the filtered page or stored capture. Read coverage, remove filters, and follow nextCursor to recover available related events.

GliderTrace 1.0.0 returns compact JSON for every tool. Result fields appear beside success; there is no response-format parameter. success describes the tool call. Check the process or session status and exitCode separately. Scalar results and fields that conflict with reserved names appear under result.

To migrate an envelope consumer, read response.sessionId instead of response.data.sessionId. Stored sessions and exported files keep their formats. --max-response-chars limits response text to 60,000 UTF-16 characters by default. Use 0 to disable it, or at least 1,000. This limit counts text characters, not transport bytes or tokens.

outputLimit.truncated marks omitted response detail. It does not change capture completeness. Use the returned next tool and arguments when available. Do not repeat a command or feedback submission to recover omitted output. For event pages, keep the filters and cursor while reducing limit.

For session details, set includeArtifacts and includeTopFindings to false to reduce output. Check error, actionable meta, warnings, and coverage before drawing conclusions. Internal diagnostics stay in local server logs.