mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-11-12 22:20:33 +00:00
1fbc06279a
* feat(benchmark): add offline memory vs project-context comparison suite (part of #7884) * fix(benchmark): route prompts through DynamicContextMiddleware, flatten rows, and share test run * refactor(benchmark): run through local Gateway and simplify first-pass suite (#7884) * docs(agents): keep context memory benchmark guidance within chain budget * fix(benchmark): verify DeerMem scope rejection --------- Co-authored-by: Totoro <msy626836554@gmail.com> Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
29 lines
749 B
JSON
29 lines
749 B
JSON
{
|
|
"dataset": "context-memory-synthetic-v1",
|
|
"question": "Which context applies here?",
|
|
"thread_history_control": "BENCH-THREAD-HISTORY",
|
|
"default_fact": "BENCH-DEFAULT-PREFERENCE",
|
|
"agent": "bench-agent",
|
|
"agent_fact": "BENCH-AGENT-PREFERENCE",
|
|
"project_only_fact": "BENCH-PROJECT-ONLY-PREFERENCE",
|
|
"projects": {
|
|
"alpha": {
|
|
"instructions": "BENCH-ALPHA-INSTRUCTIONS",
|
|
"document": "BENCH-ALPHA-DOCUMENT.md"
|
|
},
|
|
"beta": {
|
|
"instructions": "BENCH-BETA-INSTRUCTIONS",
|
|
"document": "BENCH-BETA-DOCUMENT.md"
|
|
}
|
|
},
|
|
"invalidation": {
|
|
"replacement": {
|
|
"old": "BENCH-OLD-REPLACEMENT",
|
|
"new": "BENCH-NEW-REPLACEMENT"
|
|
},
|
|
"deletion": {
|
|
"old": "BENCH-OLD-DELETION"
|
|
}
|
|
}
|
|
}
|