Skip to content
Novus Examples
jsonl510 B

Tool Call Results (JSONL)

Function-call result rows decoupled from chat messages for router testing.

Tool calling / function callingJSON parsing
Preview — first 7 linesjsonl
{"call_id": "c1", "name": "search", "args": {"q": "sample"}, "result": {"hits": 3}}
{"call_id": "c1", "name": "search", "args": {"q": "sample"}, "result": {"hits": 3}}
{"call_id": "c1", "name": "search", "args": {"q": "sample"}, "result": {"hits": 3}}
{"call_id": "c1", "name": "search", "args": {"q": "sample"}, "result": {"hits": 3}}
{"call_id": "c1", "name": "search", "args": {"q": "sample"}, "result": {"hits": 3}}
{"call_id": "c1", "name": "search", "args": {"q": "sample"}, "result": {"hits": 3}}

Specifications

Records
6

What is a .jsonl file?

JSONL (JSON Lines) is a text format where each line is a complete, independent JSON value, allowing records to be streamed and appended without parsing the whole file. It is not itself a JSON array and each line must stand alone. It is common in logging, machine learning datasets, and data pipelines.

How to use this file

Use an example JSONL to test line-by-line streaming parsers, append-and-resume ingestion, and batch pipelines that process one record per line.

How to use this file for testing

“Tool Call Results (JSONL)” is a deterministic Novus Examples fixture for Tool calling / function calling, JSON parsing. JSONL traces of function/tool calls with arguments and results — for testing agent harnesses and tool routers.

Documented properties for this file: 6 records. Compare results against paired or grouped companions on this page when present (clean↔damaged, searchable↔scanned, or format twins) so scores stay reproducible across runs.

Download the file once, keep the path stable in CI or local scripts, and treat the spec table as the contract: dimensions, seeds, field lists, and roles are intentional. Corrupt or invalid samples are labelled as such — expect parsers to fail loudly rather than silently accept them.

AI/ML fixtures are fully synthetic with documented schemas — no real people or data. Test data loaders, tokenizers, annotation converters, embedding/vector stores, or eval-metric parsers against the known structure and fixed seeds.

These JSON fixtures are synthetic SAMPLE auth or tool-call shapes for harnesses — never production secrets or live tokens. Validate schema fields and alg variants against the documented role.

Code examples

import json

with open("tool-call-results.jsonl") as f:
    rows = [json.loads(line) for line in f]
print(len(rows), rows[0])

Related files

Generated by generation/ai_wave_f.py. Free for any use, no attribution required — license.