mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-14 00:48:18 +00:00
Garry Tan
75fae742d5
Public, reproducible, cross-harness benchmark for the four ways agent memory fails (know-to-ask, push precision/recall, write-back fidelity, cross-session continuity). Hermetic PGLite, sealed gold, deterministic corpus, CI gate vs master's committed baseline, published JSON-schema foreign-runner contract. See docs/eval/BRAINBENCH.md.
20 lines
338 B
JSON
20 lines
338 B
JSON
{
|
|
"schema_version": 1,
|
|
"fixture_id": "gen-cont-001-reader",
|
|
"suites": [
|
|
"continuity"
|
|
],
|
|
"category": "continuity",
|
|
"turns": [
|
|
{
|
|
"turn_id": 1,
|
|
"role": "user",
|
|
"text": "Where did we land on Russetvane Systems?"
|
|
}
|
|
],
|
|
"continuity": {
|
|
"pair_id": "gen-cont-001",
|
|
"pair_role": "reader"
|
|
}
|
|
}
|