mirror of
https://github.com/Significant-Gravitas/AutoGPT.git
synced 2026-02-03 03:14:57 -05:00
f107ff8cf0
- **FIX ALL LINT/TYPE ERRORS IN AUTOGPT, FORGE, AND BENCHMARK** ### Linting - Clean up linter configs for `autogpt`, `forge`, and `benchmark` - Add type checking with Pyright - Create unified pre-commit config - Create unified linting and type checking CI workflow ### Testing - Synchronize CI test setups for `autogpt`, `forge`, and `benchmark` - Add missing pytest-cov to benchmark dependencies - Mark GCS tests as slow to speed up pre-commit test runs - Repair `forge` test suite - Add `AgentDB.close()` method for test DB teardown in db_test.py - Use actual temporary dir instead of forge/test_workspace/ - Move left-behind dependencies for moved `forge`-code to from autogpt to forge ### Notable type changes - Replace uses of `ChatModelProvider` by `MultiProvider` - Removed unnecessary exports from various __init__.py - Simplify `FileStorage.open_file` signature by removing `IOBase` from return type union - Implement `S3BinaryIOWrapper(BinaryIO)` type interposer for `S3FileStorage` - Expand overloads of `GCSFileStorage.open_file` for improved typing of read and write modes Had to silence type checking for the extra overloads, because (I think) Pyright is reporting a false-positive: https://github.com/microsoft/pyright/issues/8007 - Change `count_tokens`, `get_tokenizer`, `count_message_tokens` methods on `ModelProvider`s from class methods to instance methods - Move `CompletionModelFunction.schema` method -> helper function `format_function_def_for_openai` in `forge.llm.providers.openai` - Rename `ModelProvider` -> `BaseModelProvider` - Rename `ChatModelProvider` -> `BaseChatModelProvider` - Add type `ChatModelProvider` which is a union of all subclasses of `BaseChatModelProvider` ### Removed rather than fixed - Remove deprecated and broken autogpt/agbenchmark_config/benchmarks.py - Various base classes and properties on base classes in `forge.llm.providers.schema` and `forge.models.providers` ### Fixes for other issues that came to light - Clean up `forge.agent_protocol.api_router`, `forge.agent_protocol.database`, and `forge.agent.agent` - Add fallback behavior to `ImageGeneratorComponent` - Remove test for deprecated failure behavior - Fix `agbenchmark.challenges.builtin` challenge exclusion mechanism on Windows - Fix `_tool_calls_compat_extract_calls` in `forge.llm.providers.openai` - Add support for `any` (= no type specified) in `JSONSchema.typescript_type`
112 lines
3.6 KiB
Python
112 lines
3.6 KiB
Python
import logging
|
|
import time
|
|
from pathlib import Path
|
|
from typing import AsyncIterator, Optional
|
|
|
|
from agent_protocol_client import (
|
|
AgentApi,
|
|
ApiClient,
|
|
Configuration,
|
|
Step,
|
|
TaskRequestBody,
|
|
)
|
|
|
|
from agbenchmark.agent_interface import get_list_of_file_paths
|
|
from agbenchmark.config import AgentBenchmarkConfig
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
async def run_api_agent(
|
|
task: str,
|
|
config: AgentBenchmarkConfig,
|
|
timeout: int,
|
|
artifacts_location: Optional[Path] = None,
|
|
*,
|
|
mock: bool = False,
|
|
) -> AsyncIterator[Step]:
|
|
configuration = Configuration(host=config.host)
|
|
async with ApiClient(configuration) as api_client:
|
|
api_instance = AgentApi(api_client)
|
|
task_request_body = TaskRequestBody(input=task, additional_input=None)
|
|
|
|
start_time = time.time()
|
|
response = await api_instance.create_agent_task(
|
|
task_request_body=task_request_body
|
|
)
|
|
task_id = response.task_id
|
|
|
|
if artifacts_location:
|
|
logger.debug("Uploading task input artifacts to agent...")
|
|
await upload_artifacts(
|
|
api_instance, artifacts_location, task_id, "artifacts_in"
|
|
)
|
|
|
|
logger.debug("Running agent until finished or timeout...")
|
|
while True:
|
|
step = await api_instance.execute_agent_task_step(task_id=task_id)
|
|
yield step
|
|
|
|
if time.time() - start_time > timeout:
|
|
raise TimeoutError("Time limit exceeded")
|
|
if step and mock:
|
|
step.is_last = True
|
|
if not step or step.is_last:
|
|
break
|
|
|
|
if artifacts_location:
|
|
# In "mock" mode, we cheat by giving the correct artifacts to pass the test
|
|
if mock:
|
|
logger.debug("Uploading mock artifacts to agent...")
|
|
await upload_artifacts(
|
|
api_instance, artifacts_location, task_id, "artifacts_out"
|
|
)
|
|
|
|
logger.debug("Downloading agent artifacts...")
|
|
await download_agent_artifacts_into_folder(
|
|
api_instance, task_id, config.temp_folder
|
|
)
|
|
|
|
|
|
async def download_agent_artifacts_into_folder(
|
|
api_instance: AgentApi, task_id: str, folder: Path
|
|
):
|
|
artifacts = await api_instance.list_agent_task_artifacts(task_id=task_id)
|
|
|
|
for artifact in artifacts.artifacts:
|
|
# current absolute path of the directory of the file
|
|
if artifact.relative_path:
|
|
path: str = (
|
|
artifact.relative_path
|
|
if not artifact.relative_path.startswith("/")
|
|
else artifact.relative_path[1:]
|
|
)
|
|
folder = (folder / path).parent
|
|
|
|
if not folder.exists():
|
|
folder.mkdir(parents=True)
|
|
|
|
file_path = folder / artifact.file_name
|
|
logger.debug(f"Downloading agent artifact {artifact.file_name} to {folder}")
|
|
with open(file_path, "wb") as f:
|
|
content = await api_instance.download_agent_task_artifact(
|
|
task_id=task_id, artifact_id=artifact.artifact_id
|
|
)
|
|
|
|
f.write(content)
|
|
|
|
|
|
async def upload_artifacts(
|
|
api_instance: AgentApi, artifacts_location: Path, task_id: str, type: str
|
|
) -> None:
|
|
for file_path in get_list_of_file_paths(artifacts_location, type):
|
|
relative_path: Optional[str] = "/".join(
|
|
str(file_path).split(f"{type}/", 1)[-1].split("/")[:-1]
|
|
)
|
|
if not relative_path:
|
|
relative_path = None
|
|
|
|
await api_instance.upload_agent_task_artifacts(
|
|
task_id=task_id, file=str(file_path), relative_path=relative_path
|
|
)
|