Skip to content

XY-847: [ELF benchmark suite] Add reviewable consolidation and dreaming cases #141

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
yvette-carlisle merged 1 commit into from
Jun 9, 2026
Merged

XY-847: [ELF benchmark suite] Add reviewable consolidation and dreaming cases #141

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
88 changes: 70 additions & 18 deletions Makefile.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -392,23 +392,26 @@ args = [


# Real-world job benchmark smoke
# | task | type | cwd |
# | -------------------------------- | --------- | --- |
# | real-world-job-smoke | composite | |
# | real-world-job-smoke-json | command | |
# | real-world-job-smoke-report | command | |
# | real-world-memory | composite | |
# | real-world-memory-json | command | |
# | real-world-memory-report | command | |
# | real-world-memory-evolution | composite | |
# | real-world-memory-evolution-json | command | |
# | real-world-memory-evolution-report | command | |
# | real-world-job-operator-ux | composite | |
# | real-world-job-operator-ux-json | command | |
# | real-world-job-operator-ux-report | command | |
# | real-world-memory-retrieval | composite | |
# | real-world-memory-retrieval-json | command | |
# | real-world-memory-retrieval-report | command | |
# | task | type | cwd |
# | -------------------------------------- | --------- | --- |
# | real-world-job-smoke | composite | |
# | real-world-job-smoke-json | command | |
# | real-world-job-smoke-report | command | |
# | real-world-memory | composite | |
# | real-world-memory-json | command | |
# | real-world-memory-report | command | |
# | real-world-memory-evolution | composite | |
# | real-world-memory-evolution-json | command | |
# | real-world-memory-evolution-report | command | |
# | real-world-memory-consolidation | composite | |
# | real-world-memory-consolidation-json | command | |
# | real-world-memory-consolidation-report | command | |
# | real-world-job-operator-ux | composite | |
# | real-world-job-operator-ux-json | command | |
# | real-world-job-operator-ux-report | command | |
# | real-world-memory-retrieval | composite | |
# | real-world-memory-retrieval-json | command | |
# | real-world-memory-retrieval-report | command | |

[tasks.real-world-job-smoke]
workspace = false
Expand Down Expand Up @@ -475,7 +478,7 @@ args = [
"--out",
"tmp/real-world-memory/real-world-memory-report.json",
"--run-id",
"real-world-memory-trust-resume-personalization",
"real-world-memory",
"--adapter-id",
"elf_real_world_memory_fixture",
"--adapter-name",
Expand Down Expand Up @@ -649,6 +652,55 @@ args = [
"tmp/real-world-memory/retrieval-report.md",
]

[tasks.real-world-memory-consolidation]
workspace = false
dependencies = [
"real-world-memory-consolidation-report",
]

[tasks.real-world-memory-consolidation-json]
workspace = false
command = "cargo"
args = [
"run",
"-p",
"elf-eval",
"--bin",
"real_world_job_benchmark",
"--",
"run",
"--fixtures",
"apps/elf-eval/fixtures/real_world_memory/consolidation",
"--out",
"tmp/real-world-memory/consolidation/report.json",
"--run-id",
"real-world-memory-consolidation",
"--adapter-id",
"fixture_consolidation",
"--adapter-name",
"ELF consolidation fixture",
]

[tasks.real-world-memory-consolidation-report]
workspace = false
dependencies = [
"real-world-memory-consolidation-json",
]
command = "cargo"
args = [
"run",
"-p",
"elf-eval",
"--bin",
"real_world_job_benchmark",
"--",
"publish",
"--report",
"tmp/real-world-memory/consolidation/report.json",
"--out",
"tmp/real-world-memory/consolidation/report.md",
]


# Meta
# | task | type | cwd |
Expand Down
6 changes: 4 additions & 2 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -161,8 +161,10 @@ Detailed evidence and interpretation:
- [Single-User Production Runbook](docs/guide/single_user_production.md)
- Future benchmark contract:
[Real-World Agent Memory Benchmark v1](docs/spec/real_world_agent_memory_benchmark_v1.md).
This contract defines job-level suites for agent work, but no system win is claimed
under it until a runner encodes and reports those suites.
This contract defines job-level suites for agent work. Checked-in fixture runners now
cover a smoke work-resume slice and proposal-only consolidation cases through
`cargo make real-world-job-smoke` and `cargo make real-world-memory-consolidation`,
but those reports are fixture-level evidence and not live external-adapter wins.

Quick comparison snapshot (objective/high-level).
This table compares capability coverage, not overall project quality.
Expand Down
Loading