mirror of
https://github.com/Significant-Gravitas/AutoGPT.git
synced 2026-02-08 05:45:07 -05:00
ef7cfbb860
Restructuring the Repo to make it clear the difference between classic autogpt and the autogpt platform: * Move the "classic" projects `autogpt`, `forge`, `frontend`, and `benchmark` into a `classic` folder * Also rename `autogpt` to `original_autogpt` for absolute clarity * Rename `rnd/` to `autogpt_platform/` * `rnd/autogpt_builder` -> `autogpt_platform/frontend` * `rnd/autogpt_server` -> `autogpt_platform/backend` * Adjust any paths accordingly
31 lines
933 B
JSON
31 lines
933 B
JSON
{
|
|
"command": "agbenchmark start --test TestDebugSimpleTypoWithGuidance",
|
|
"completion_time": "2023-07-18-07:27",
|
|
"metrics": {
|
|
"run_time": "59.13 seconds",
|
|
"highest_difficulty": "basic: 2"
|
|
},
|
|
"tests": {
|
|
"TestDebugSimpleTypoWithGuidance": {
|
|
"data_path": "agbenchmark/challenges/code/d1_debug",
|
|
"is_regression": false,
|
|
"task": "1- Run test.py.\n2- Read code.py.\n3- Modify code.py.\nRepeat step 1, 2 and 3 until test.py runs without errors.\n",
|
|
"answer": "[0, 1] [2, 5] [0, 3]",
|
|
"description": "Tests ability for the agent to debug python code with a simple typo in it.",
|
|
"metrics": {
|
|
"difficulty": "basic",
|
|
"success": true,
|
|
"success_%": 100.0,
|
|
"run_time": "58.869 seconds"
|
|
},
|
|
"reached_cutoff": false
|
|
}
|
|
},
|
|
"config": {
|
|
"workspace": "${os.path.join(Path.home(), 'miniagi')}"
|
|
},
|
|
"additional": {
|
|
"model": "gpt-4"
|
|
}
|
|
}
|