27 lines
1.1 KiB
TOML
27 lines
1.1 KiB
TOML
|
schema_version = 8
|
||
|
|
|
||
|
|
[[tasks]]
|
||
|
|
agent = "experiment_judge"
|
||
|
|
task_kind = "analysis"
|
||
|
|
task = "Inspect this lab read-only and explain how objective evidence selects one isolated candidate without voting."
|
||
|
|
mode = "read-only"
|
||
|
|
wall_timeout_seconds = 600
|
||
|
|
|
||
|
|
[[tasks]]
|
||
|
|
agent = "deepseek_candidate"
|
||
|
|
task_kind = "implement"
|
||
|
|
task = "Create only evals/competing-implementations/fixture/mmo-deepseek-smoke.txt containing the word candidate, verify it with a local command, and return candidate JSON using 64 zeroes as the supplied demonstration contract hash."
|
||
|
|
backend = "mcp"
|
||
|
|
mode = "workspace-write"
|
||
|
|
write_scope = ["evals/competing-implementations/fixture/mmo-deepseek-smoke.txt"]
|
||
|
|
wall_timeout_seconds = 900
|
||
|
|
|
||
|
|
[[tasks]]
|
||
|
|
agent = "sonnet_candidate"
|
||
|
|
task_kind = "implement"
|
||
|
|
task = "Create only evals/competing-implementations/fixture/mmo-sonnet-smoke.txt containing the word candidate, verify it with a local command, and return candidate JSON using 64 zeroes as the supplied demonstration contract hash."
|
||
|
|
backend = "mcp"
|
||
|
|
mode = "workspace-write"
|
||
|
|
write_scope = ["evals/competing-implementations/fixture/mmo-sonnet-smoke.txt"]
|
||
|
|
wall_timeout_seconds = 900
|