mirror of
https://github.com/aljazceru/Auto-GPT.git
synced 2025-12-17 22:14:28 +01:00
Squashed commit of the following: commit 7d6476d3297860f74c276d571da995d958a8cc1a Author: Reinier van der Leer <pwuts@agpt.co> Date: Tue Jan 9 18:10:45 2024 +0100 refactor(benchmark/challenge): Set up structure to support more challenge providers - Move `Challenge`, `ChallengeData`, `load_challenges` to `challenges/builtin.py` and rename to `BuiltinChallenge`, `BuiltinChallengeSpec`, `load_builtin_challenges` - Create `BaseChallenge` to serve as interface and base class for different challenge implementations - Create `ChallengeInfo` model to serve as universal challenge info object - Create `get_challenge_from_source_uri` function in `challenges/__init__.py` - Replace `ChallengeData` by `ChallengeInfo` everywhere except in `BuiltinChallenge` - Add strong typing to `task_informations` store in app.py - Use `call.duration` in `finalize_test_report` and remove `timer` fixture - Update docstring on `challenges/__init__.py:get_unique_categories` - Add docstring to `generate_test.py` commit 5df2aa7939b45d85a2c2b5de9ac0522330d1502a Author: Reinier van der Leer <pwuts@agpt.co> Date: Tue Jan 9 16:58:01 2024 +0100 refactor(benchmark): Refactor & rename functions in agent_interface.py and agent_api_interface.py - `copy_artifacts_into_temp_folder` -> `copy_challenge_artifacts_into_workspace` - `copy_agent_artifacts_into_folder` -> `download_agent_artifacts_into_folder` - Reorder parameters of `run_api_agent`, `copy_challenge_artifacts_into_workspace`; use `Path` instead of `str` commit 6a256fef4c7950b7ee82fb801e70c83afe6b6f8b Author: Reinier van der Leer <pwuts@agpt.co> Date: Tue Jan 9 16:02:25 2024 +0100 refactor(benchmark): Refactor & typefix report generation and handling logic - Rename functions in reports.py and ReportManager.py to better reflect what they do - `get_previous_test_results` -> `get_and_update_success_history` - `generate_single_call_report` -> `initialize_test_report` - `finalize_reports` -> `finalize_test_report` - `ReportManager.end_info_report` -> `SessionReportManager.finalize_session_report` - Modify `pytest_runtest_makereport` hook in conftest.py to finalize the report immediately after the challenge finishes running instead of after teardown - Move result processing logic from `initialize_test_report` to `finalize_test_report` in reports.py - Use `Test` and `Report` types from report_types.py where possible instead of untyped dicts: reports.py, utils.py, ReportManager.py - Differentiate `ReportManager` into `SessionReportManager`, `RegressionTestsTracker`, `SuccessRateTracker` - Move filtering of optional challenge categories from challenge.py (`Challenge.skip_optional_categories`) to conftest.py (`pytest_collection_modifyitems`) - Remove unused `scores` fixture in conftest.py commit 370d6dbf5df75d78e3878877968e8cd309d6d7fb Author: Reinier van der Leer <pwuts@agpt.co> Date: Tue Jan 9 15:16:43 2024 +0100 refactor(benchmark): Simplify models in report_types.py - Removed ForbidOptionalMeta and BaseModelBenchmark classes. - Changed model attributes to optional: `Metrics.difficulty`, `Metrics.success`, `Metrics.success_percentage`, `Metrics.run_time`, and `Test.reached_cutoff`. - Added validator to `Metrics` model to require `success` and `run_time` fields if `attempted=True`. - Added default values to all optional model fields. - Removed duplicate imports. - Added condition in process_report.py to prevent null lookups if `metrics.difficulty` is not set.
70 lines
2.3 KiB
Python
70 lines
2.3 KiB
Python
import json
|
|
import logging
|
|
import os
|
|
from pathlib import Path
|
|
from typing import Any
|
|
|
|
from agbenchmark.reports.processing.get_files import (
|
|
get_latest_report_from_agent_directories,
|
|
)
|
|
from agbenchmark.reports.processing.report_types import Report, Test
|
|
from agbenchmark.utils.data_types import STRING_DIFFICULTY_MAP
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
def get_reports_data(report_path: str) -> dict[str, Any]:
|
|
latest_files = get_latest_report_from_agent_directories(report_path)
|
|
|
|
reports_data = {}
|
|
|
|
if latest_files is None:
|
|
raise Exception("No files found in the reports directory")
|
|
|
|
# This will print the latest file in each subdirectory and add to the files_data dictionary
|
|
for subdir, file in latest_files:
|
|
subdir_name = os.path.basename(os.path.normpath(subdir))
|
|
with open(Path(subdir) / file, "r") as f:
|
|
# Load the JSON data from the file
|
|
json_data = json.load(f)
|
|
converted_data = Report.parse_obj(json_data)
|
|
# get the last directory name in the path as key
|
|
reports_data[subdir_name] = converted_data
|
|
|
|
return reports_data
|
|
|
|
|
|
def get_agent_category(report: Report) -> dict[str, Any]:
|
|
categories: dict[str, Any] = {}
|
|
|
|
def get_highest_category_difficulty(data: Test) -> None:
|
|
for category in data.category:
|
|
if (
|
|
category == "interface"
|
|
or category == "iterate"
|
|
or category == "product_advisor"
|
|
):
|
|
continue
|
|
categories.setdefault(category, 0)
|
|
if data.metrics.success and data.metrics.difficulty:
|
|
num_dif = STRING_DIFFICULTY_MAP[data.metrics.difficulty]
|
|
if num_dif > categories[category]:
|
|
categories[category] = num_dif
|
|
|
|
for _, test_data in report.tests.items():
|
|
get_highest_category_difficulty(test_data)
|
|
|
|
return categories
|
|
|
|
|
|
def all_agent_categories(reports_data: dict[str, Any]) -> dict[str, Any]:
|
|
all_categories: dict[str, Any] = {}
|
|
|
|
for name, report in reports_data.items():
|
|
categories = get_agent_category(report)
|
|
if categories: # only add to all_categories if categories is not empty
|
|
logger.debug(f"Adding {name}: {categories}")
|
|
all_categories[name] = categories
|
|
|
|
return all_categories
|