github/AutoGPT
1
1
Fork 0
mirror of https://github.com/Significant-Gravitas/AutoGPT.git synced 2026-04-08 03:00:28 -04:00
Code Issues Packages Projects Releases Wiki Activity

refactor(forge): remove VCR cassettes, use real API calls with skip for forks

Browse Source 
- Remove vcrpy and pytest-recording dependencies
- Remove tests/vcr/ directory and vcr_cassettes submodule
- Remove .gitmodules (only had cassette submodule)
- Simplify CI workflow - no more cassette checkout/push/PAT_REVIEW
- Tests requiring API keys now skip if not set (fork PRs)
- Update CLAUDE.md files to remove cassette references
- Fix broken agbenchmark path in pyproject.toml

Security improvement: removes need for PAT with cross-repo write access.
Fork PRs will have API-dependent tests skipped (GitHub protects secrets).

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Nicholas Tindle
2026-01-19 22:51:57 -06:00
parent e477150979
commit ab95077e5b
28 changed files with 63 additions and 78430 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
.github/workflows/classic-autogpt-ci.yml vendored
View File

@@ -6,11 +6,15 @@ on:
paths:
- '.github/workflows/classic-autogpt-ci.yml'
- 'classic/original_autogpt/**'
- 'classic/direct_benchmark/**'
- 'classic/forge/**'
pull_request:
branches: [ master, dev, release-* ]
paths:
- '.github/workflows/classic-autogpt-ci.yml'
- 'classic/original_autogpt/**'
- 'classic/direct_benchmark/**'
- 'classic/forge/**'
concurrency:
group: ${{ format('classic-autogpt-ci-{0}', github.head_ref && format('{0}-{1}', github.event_name, github.event.pull_request.number) || github.sha) }}
@@ -110,6 +114,10 @@ jobs:
- name: Install Python dependencies
run: poetry install
- name: Install direct_benchmark dependencies
working-directory: classic/direct_benchmark
run: poetry install
- name: Run pytest with coverage
run: |
poetry run pytest -vv \

115
.github/workflows/classic-forge-ci.yml vendored
View File

@@ -6,13 +6,11 @@ on:
paths:
- '.github/workflows/classic-forge-ci.yml'
- 'classic/forge/**'
- '!classic/forge/tests/vcr_cassettes'
pull_request:
branches: [ master, dev, release-* ]
paths:
- '.github/workflows/classic-forge-ci.yml'
- 'classic/forge/**'
- '!classic/forge/tests/vcr_cassettes'
concurrency:
group: ${{ format('forge-ci-{0}', github.head_ref && format('{0}-{1}', github.event_name, github.event.pull_request.number) || github.sha) }}
@@ -64,40 +62,6 @@ jobs:
- name: Checkout repository
uses: actions/checkout@v4
with:
fetch-depth: 0
submodules: true
- name: Checkout cassettes
if: ${{ startsWith(github.event_name, 'pull_request') }}
env:
PR_BASE: ${{ github.event.pull_request.base.ref }}
PR_BRANCH: ${{ github.event.pull_request.head.ref }}
PR_AUTHOR: ${{ github.event.pull_request.user.login }}
run: |
cassette_branch="${PR_AUTHOR}-${PR_BRANCH}"
cassette_base_branch="${PR_BASE}"
cd tests/vcr_cassettes
if ! git ls-remote --exit-code --heads origin $cassette_base_branch ; then
cassette_base_branch="master"
fi
if git ls-remote --exit-code --heads origin $cassette_branch ; then
git fetch origin $cassette_branch
git fetch origin $cassette_base_branch
git checkout $cassette_branch
# Pick non-conflicting cassette updates from the base branch
git merge --no-commit --strategy-option=ours origin/$cassette_base_branch
echo "Using cassettes from mirror branch '$cassette_branch'," \
"synced to upstream branch '$cassette_base_branch'."
else
git checkout -b $cassette_branch
echo "Branch '$cassette_branch' does not exist in cassette submodule." \
"Using cassettes from '$cassette_base_branch'."
fi
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
@@ -144,7 +108,10 @@ jobs:
env:
CI: true
PLAIN_OUTPUT: True
# API keys - tests that need these will skip if not available
# Secrets are not available to fork PRs (GitHub security feature)
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
S3_ENDPOINT_URL: ${{ runner.os != 'Windows' && 'http://127.0.0.1:9000' || '' }}
AWS_ACCESS_KEY_ID: minioadmin
AWS_SECRET_ACCESS_KEY: minioadmin
@@ -161,83 +128,9 @@ jobs:
token: ${{ secrets.CODECOV_TOKEN }}
flags: forge,${{ runner.os }}
- id: setup_git_auth
name: Set up git token authentication
# Cassettes may be pushed even when tests fail
if: success() || failure()
run: |
config_key="http.${{ github.server_url }}/.extraheader"
if [ "${{ runner.os }}" = 'macOS' ]; then
base64_pat=$(echo -n "pat:${{ secrets.PAT_REVIEW }}" | base64)
else
base64_pat=$(echo -n "pat:${{ secrets.PAT_REVIEW }}" | base64 -w0)
fi
git config "$config_key" \
"Authorization: Basic $base64_pat"
cd tests/vcr_cassettes
git config "$config_key" \
"Authorization: Basic $base64_pat"
echo "config_key=$config_key" >> $GITHUB_OUTPUT
- id: push_cassettes
name: Push updated cassettes
# For pull requests, push updated cassettes even when tests fail
if: github.event_name == 'push' || (! github.event.pull_request.head.repo.fork && (success() || failure()))
env:
PR_BRANCH: ${{ github.event.pull_request.head.ref }}
PR_AUTHOR: ${{ github.event.pull_request.user.login }}
run: |
if [ "${{ startsWith(github.event_name, 'pull_request') }}" = "true" ]; then
is_pull_request=true
cassette_branch="${PR_AUTHOR}-${PR_BRANCH}"
else
cassette_branch="${{ github.ref_name }}"
fi
cd tests/vcr_cassettes
# Commit & push changes to cassettes if any
if ! git diff --quiet; then
git add .
git commit -m "Auto-update cassettes"
git push origin HEAD:$cassette_branch
if [ ! $is_pull_request ]; then
cd ../..
git add tests/vcr_cassettes
git commit -m "Update cassette submodule"
git push origin HEAD:$cassette_branch
fi
echo "updated=true" >> $GITHUB_OUTPUT
else
echo "updated=false" >> $GITHUB_OUTPUT
echo "No cassette changes to commit"
fi
- name: Post Set up git token auth
if: steps.setup_git_auth.outcome == 'success'
run: |
git config --unset-all '${{ steps.setup_git_auth.outputs.config_key }}'
git submodule foreach git config --unset-all '${{ steps.setup_git_auth.outputs.config_key }}'
- name: Apply "behaviour change" label and comment on PR
if: ${{ startsWith(github.event_name, 'pull_request') }}
run: |
PR_NUMBER="${{ github.event.pull_request.number }}"
TOKEN="${{ secrets.PAT_REVIEW }}"
REPO="${{ github.repository }}"
if [[ "${{ steps.push_cassettes.outputs.updated }}" == "true" ]]; then
echo "Adding label and comment..."
echo $TOKEN | gh auth login --with-token
gh issue edit $PR_NUMBER --add-label "behaviour change"
gh issue comment $PR_NUMBER --body "You changed AutoGPT's behaviour on ${{ runner.os }}. The cassettes have been updated and will be merged to the submodule when this Pull Request gets merged."
fi
- name: Upload logs to artifact
if: always()
uses: actions/upload-artifact@v4
with:
name: test-logs
name: test-logs-${{ matrix.platform-os }}-${{ matrix.python-version }}
path: classic/forge/logs/

3
.gitmodules vendored
View File

@@ -1,3 +0,0 @@
[submodule "classic/forge/tests/vcr_cassettes"]
path = classic/forge/tests/vcr_cassettes
url = https://github.com/Significant-Gravitas/Auto-GPT-test-cassettes

3
classic/CLAUDE.md
View File

@@ -130,10 +130,9 @@ Benchmark harness for testing agent performance:
## Testing Patterns
- VCR cassettes in `/forge/tests/vcr_cassettes/` for HTTP mocking
- Async support via pytest-asyncio
- Fixtures defined in `conftest.py` files provide: `tmp_project_root`, `storage`, `config`, `llm_provider`, `agent`
- Tests require `OPENAI_API_KEY` environment variable (defaults to "sk-dummy" for mocked tests)
- Tests requiring API keys (OPENAI_API_KEY, ANTHROPIC_API_KEY) will skip if not set
## Environment Setup

4
classic/forge/CLAUDE.md
View File

@@ -316,14 +316,14 @@ GET /ap/v1/agent/tasks/{id}/artifacts # List artifacts
**Fixtures** (`conftest.py`):
- `storage` - Temporary LocalFileStorage
- VCR cassettes in `tests/vcr_cassettes/`
```bash
poetry run pytest # All tests
poetry run pytest --cov=forge # With coverage
poetry run pytest --record-mode=all # Record HTTP cassettes
```
**Note**: Tests requiring API keys (OPENAI_API_KEY, ANTHROPIC_API_KEY) will be skipped if not set.
## Creating a Custom Component
```python

4
classic/forge/conftest.py
View File

@@ -6,9 +6,7 @@ import pytest
from forge.file_storage.base import FileStorage, FileStorageConfiguration
from forge.file_storage.local import LocalFileStorage
pytest_plugins = [
"tests.vcr",
]
pytest_plugins = []
@pytest.fixture(scope="session", autouse=True)

8
classic/forge/forge/components/image_gen/test_image_gen.py
View File

@@ -1,5 +1,6 @@
import functools
import hashlib
import os
from pathlib import Path
from unittest.mock import patch
@@ -12,6 +13,8 @@ from forge.components.image_gen.image_gen import ImageGeneratorConfiguration
from forge.file_storage.base import FileStorage
from forge.llm.providers.openai import OpenAICredentials
OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY")
@pytest.fixture
def image_gen_component(storage: FileStorage):
@@ -39,7 +42,7 @@ def image_size(request):
return request.param
@pytest.mark.vcr
@pytest.mark.skipif(not OPENAI_API_KEY, reason="OPENAI_API_KEY not set")
def test_dalle(
image_gen_component: ImageGeneratorComponent,
image_size,
@@ -53,8 +56,7 @@ def test_dalle(
@pytest.mark.xfail(
reason="The image is too big to be put in a cassette for a CI pipeline. "
"We're looking into a solution."
reason="HuggingFace image generation is unreliable in CI."
)
@pytest.mark.parametrize(
"image_model",

999
classic/forge/poetry.lock generated
View File

File diff suppressed because it is too large Load Diff

7
classic/forge/pyproject.toml
View File

@@ -24,8 +24,7 @@ classifiers = [
[tool.poetry.dependencies]
python = "^3.12"
agbenchmark = { path = "../benchmark", optional = true }
# agbenchmark = {git = "https://github.com/Significant-Gravitas/AutoGPT.git", subdirectory = "benchmark", optional = true}
# agbenchmark removed - use direct_benchmark instead
aiohttp = "^3.8.5"
anthropic = "^0.45.0"
beautifulsoup4 = "^4.12.2"
@@ -73,7 +72,7 @@ watchdog = "^6.0.0"
webdriver-manager = "^4.0.2"
[tool.poetry.extras]
benchmark = ["agbenchmark"]
# benchmark extra removed - use direct_benchmark instead
[tool.poetry.group.dev.dependencies]
black = "^23.12.1"
@@ -94,9 +93,7 @@ pytest = "^7.4.0"
pytest-asyncio = "^0.23.3"
pytest-cov = "^5.0.0"
pytest-mock = "*"
pytest-recording = "*"
mock = "^5.1.0"
vcrpy = { git = "https://github.com/Significant-Gravitas/vcrpy.git", rev = "master" }
[build-system]

81
classic/forge/tests/vcr/__init__.py
View File

@@ -1,81 +0,0 @@
import logging
import os
from hashlib import sha256
from typing import cast
import pytest
from openai import OpenAI
from openai._models import FinalRequestOptions
from openai._types import Omit
from openai._utils import is_given
from pytest_mock import MockerFixture
from .vcr_filter import (
before_record_request,
before_record_response,
freeze_request_body,
)
DEFAULT_RECORD_MODE = "new_episodes"
BASE_VCR_CONFIG = {
"before_record_request": before_record_request,
"before_record_response": before_record_response,
"match_on": ["method", "headers"],
}
@pytest.fixture(scope="session")
def vcr_config(get_base_vcr_config):
return get_base_vcr_config
@pytest.fixture(scope="session")
def get_base_vcr_config(request):
record_mode = request.config.getoption("--record-mode", default="new_episodes")
config = BASE_VCR_CONFIG
if record_mode is None:
config["record_mode"] = DEFAULT_RECORD_MODE
return config
@pytest.fixture()
def vcr_cassette_dir(request):
test_name = os.path.splitext(request.node.name)[0]
return os.path.join("tests/vcr_cassettes", test_name)
@pytest.fixture
def cached_openai_client(mocker: MockerFixture) -> OpenAI:
client = OpenAI()
_prepare_options = client._prepare_options
def _patched_prepare_options(self, options: FinalRequestOptions):
_prepare_options(options)
if not options.json_data:
return
headers: dict[str, str | Omit] = (
{**options.headers} if is_given(options.headers) else {}
)
options.headers = headers
data = cast(dict, options.json_data)
logging.getLogger("cached_openai_client").debug(
f"Outgoing API request: {headers}\n{data if data else None}"
)
# Add hash header for cheap & fast matching on cassette playback
headers["X-Content-Hash"] = sha256(
freeze_request_body(data), usedforsecurity=False
).hexdigest()
mocker.patch.object(
client,
"_prepare_options",
new=_patched_prepare_options,
)
return client

108
classic/forge/tests/vcr/vcr_filter.py
View File

@@ -1,108 +0,0 @@
import contextlib
import json
import re
from io import BytesIO
from typing import Any, cast
from vcr.request import Request
HOSTNAMES_TO_CACHE: list[str] = [
"api.openai.com",
"localhost:50337",
"duckduckgo.com",
]
IGNORE_REQUEST_HEADERS: set[str | re.Pattern] = {
"Authorization",
"Cookie",
"OpenAI-Organization",
"X-OpenAI-Client-User-Agent",
"User-Agent",
re.compile(r"X-Stainless-[\w\-]+", re.IGNORECASE),
}
LLM_MESSAGE_REPLACEMENTS: list[dict[str, str]] = [
{
"regex": r"\w{3} \w{3} {1,2}\d{1,2} \d{2}:\d{2}:\d{2} \d{4}",
"replacement": "Tue Jan 1 00:00:00 2000",
},
{
"regex": r"<selenium.webdriver.chrome.webdriver.WebDriver[^>]*>",
"replacement": "",
},
]
OPENAI_URL = "api.openai.com"
def before_record_request(request: Request) -> Request | None:
if not should_cache_request(request):
return None
request = filter_request_headers(request)
request = freeze_request(request)
return request
def should_cache_request(request: Request) -> bool:
return any(hostname in request.url for hostname in HOSTNAMES_TO_CACHE)
def filter_request_headers(request: Request) -> Request:
for header_name in list(request.headers):
if any(
(
(type(ignore) is str and ignore.lower() == header_name.lower())
or (isinstance(ignore, re.Pattern) and ignore.match(header_name))
)
for ignore in IGNORE_REQUEST_HEADERS
):
del request.headers[header_name]
return request
def freeze_request(request: Request) -> Request:
if not request or not request.body:
return request
with contextlib.suppress(ValueError):
if isinstance(request.body, BytesIO):
body_data: bytes | str = request.body.getvalue()
else:
body_data = cast(bytes, request.body)
request.body = freeze_request_body(json.loads(body_data))
return request
def freeze_request_body(body: dict) -> bytes:
"""Remove any dynamic items from the request body"""
if "messages" not in body:
return json.dumps(body, sort_keys=True).encode()
if "max_tokens" in body:
del body["max_tokens"]
for message in body["messages"]:
if "content" in message and "role" in message:
if message["role"] == "system":
message["content"] = replace_message_content(
message["content"], LLM_MESSAGE_REPLACEMENTS
)
return json.dumps(body, sort_keys=True).encode()
def replace_message_content(content: str, replacements: list[dict[str, str]]) -> str:
for replacement in replacements:
pattern = re.compile(replacement["regex"])
content = pattern.sub(replacement["replacement"], content)
return content
def before_record_response(response: dict[str, Any]) -> dict[str, Any]:
if "Transfer-Encoding" in response["headers"]:
del response["headers"]["Transfer-Encoding"]
return response

21
classic/forge/tests/vcr_cassettes/LICENSE
View File

@@ -1,21 +0,0 @@
MIT License
Copyright (c) 2023 Significant Gravitas
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.

63
classic/forge/tests/vcr_cassettes/format_cassettes.py
View File

@@ -1,63 +0,0 @@
import contextlib
import json
import os
from hashlib import sha256
from pathlib import Path
import yaml
from yaml import CDumper as Dumper
from yaml import CLoader as Loader
def convert_cassette_file(filename: str | Path):
print(f"{filename} STARTING")
with open(filename) as c:
cassette_content = yaml.load(c, Loader)
# Iterate over all request+response pairs
for interaction in cassette_content["interactions"]:
request_body: str = interaction["request"]["body"]
if request_body is None:
continue
with contextlib.suppress(json.decoder.JSONDecodeError):
request_obj = json.loads(request_body)
# Strip `max_tokens`, since its value doesn't matter
# as long as the request succeeds
if "max_tokens" in request_obj:
del request_obj["max_tokens"]
# Sort the keys of the request body
request_body = json.dumps(request_obj, sort_keys=True)
headers = interaction["request"]["headers"]
# Calculate hash for the request body, used for VCR lookup
headers["X-Content-Hash"] = [
sha256(request_body.encode(), usedforsecurity=False).hexdigest()
]
# Strip auth headers
if "AGENT-MODE" in headers:
del headers["AGENT-MODE"]
if "AGENT-TYPE" in headers:
del headers["AGENT-TYPE"]
if "OpenAI-Organization" in headers:
del headers["OpenAI-Organization"]
interaction["request"]["body"] = request_body
with open(filename, "w") as c:
c.write(yaml.dump(cassette_content, Dumper=Dumper))
print(f"{filename} DONE")
# Iterate over all .yaml files in the current folder and its subdirectories
for dirpath, _, files in os.walk("."):
for file in files:
if not file.endswith(".yaml"):
continue
convert_cassette_file(os.path.join(dirpath, file))

3679
classic/forge/tests/vcr_cassettes/test_browse_website/test_browse_website.yaml generated
View File

File diff suppressed because it is too large Load Diff

75
classic/forge/tests/vcr_cassettes/test_dalle[1024]/test_dalle[1024].yaml generated
View File

File diff suppressed because one or more lines are too long

75
classic/forge/tests/vcr_cassettes/test_dalle[256]/test_dalle[256].yaml generated
View File

File diff suppressed because one or more lines are too long

75
classic/forge/tests/vcr_cassettes/test_dalle[512]/test_dalle[512].yaml generated
View File

File diff suppressed because one or more lines are too long

24594
classic/forge/tests/vcr_cassettes/test_debug_code_challenge_a/test_debug_code_challenge_a.yaml generated
View File

File diff suppressed because it is too large Load Diff

214
classic/forge/tests/vcr_cassettes/test_generate_aiconfig_automatic_default/test_generate_aiconfig_automatic_default.yaml generated
View File

@@ -1,214 +0,0 @@
interactions:
- request:
body: '{"messages": [{"content": "\nYour task is to devise up to 5 highly effective
goals and an appropriate role-based name (_GPT) for an autonomous agent, ensuring
that the goals are optimally aligned with the successful completion of its assigned
task.\n\nThe user will provide the task, you will provide only the output in
the exact format specified below with no explanation or conversation.\n\nExample
input:\nHelp me with marketing my business\n\nExample output:\nName: CMOGPT\nDescription:
a professional digital marketer AI that assists Solopreneurs in growing their
businesses by providing world-class expertise in solving marketing problems
for SaaS, content products, agencies, and more.\nGoals:\n- Engage in effective
problem-solving, prioritization, planning, and supporting execution to address
your marketing needs as your virtual Chief Marketing Officer.\n\n- Provide specific,
actionable, and concise advice to help you make informed decisions without the
use of platitudes or overly wordy explanations.\n\n- Identify and prioritize
quick wins and cost-effective campaigns that maximize results with minimal time
and budget investment.\n\n- Proactively take the lead in guiding you and offering
suggestions when faced with unclear information or uncertainty to ensure your
marketing strategy remains on track.\n", "role": "system"}, {"content": "Task:
''Write a wikipedia style article about the project: https://github.com/significant-gravitas/Auto-GPT''\nRespond
only with the output in the exact format specified in the system prompt, with
no explanation or conversation.", "role": "user"}], "model": "gpt-3.5-turbo",
"temperature": 0.0}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '1669'
Content-Type:
- application/json
X-Content-Hash:
- cc4940b13e25117216dfcd3c7dcdc665cf7ef70a10b5633f2f67f1a832c3e89a
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
Access-Control-Allow-Origin:
- '*'
Alt-Svc:
- h3=":443"; ma=86400
- h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
Cache-Control:
- no-cache, must-revalidate
Cf-Cache-Status:
- DYNAMIC
Cf-Ray:
- 7cd79772daa6e157-ORD
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 26 May 2023 17:03:47 GMT
Function-Execution-Id:
- pegl0551txnb
Openai-Model:
- gpt-3.5-turbo-0301
Openai-Organization:
- significant-gravitas
Openai-Processing-Ms:
- '20547'
Openai-Version:
- '2020-10-01'
Server:
- Google Frontend
Strict-Transport-Security:
- max-age=15724800; includeSubDomains
Vary:
- Accept-Encoding
X-Cloud-Trace-Context:
- ec4c1070b2d54378e4ddcf13cd8366b7
X-Powered-By:
- Express
X-Ratelimit-Limit-Requests:
- '3500'
X-Ratelimit-Limit-Tokens:
- '90000'
X-Ratelimit-Remaining-Requests:
- '3499'
X-Ratelimit-Remaining-Tokens:
- '89605'
X-Ratelimit-Reset-Requests:
- 17ms
X-Ratelimit-Reset-Tokens:
- 262ms
X-Request-Id:
- bb863118d90782f50f13ec29157a7a7f
status:
code: 200
message: OK
- request:
body: '{"messages": [{"content": "\nYour task is to devise up to 5 highly effective
goals and an appropriate role-based name (_GPT) for an autonomous agent, ensuring
that the goals are optimally aligned with the successful completion of its assigned
task.\n\nThe user will provide the task, you will provide only the output in
the exact format specified below with no explanation or conversation.\n\nExample
input:\nHelp me with marketing my business\n\nExample output:\nName: CMOGPT\nDescription:
a professional digital marketer AI that assists Solopreneurs in growing their
businesses by providing world-class expertise in solving marketing problems
for SaaS, content products, agencies, and more.\nGoals:\n- Engage in effective
problem-solving, prioritization, planning, and supporting execution to address
your marketing needs as your virtual Chief Marketing Officer.\n\n- Provide specific,
actionable, and concise advice to help you make informed decisions without the
use of platitudes or overly wordy explanations.\n\n- Identify and prioritize
quick wins and cost-effective campaigns that maximize results with minimal time
and budget investment.\n\n- Proactively take the lead in guiding you and offering
suggestions when faced with unclear information or uncertainty to ensure your
marketing strategy remains on track.\n", "role": "system"}, {"content": "Task:
''Write a wikipedia style article about the project: https://github.com/significant-gravitas/Auto-GPT''\nRespond
only with the output in the exact format specified in the system prompt, with
no explanation or conversation.", "role": "user"}], "model": "gpt-4-0314", "temperature":
0.0}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '1666'
Content-Type:
- application/json
X-Content-Hash:
- ac6044440efb25bc33deca1c1be80cfef40e6a3eeb43febe36cc11c8f17b869c
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 803a41a718048023-IAD
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 08 Sep 2023 21:24:24 GMT
Server:
- cloudflare
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0314
openai-organization:
- significant-gravitas
openai-processing-ms:
- '17436'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '200'
x-ratelimit-limit-tokens:
- '40000'
x-ratelimit-remaining-requests:
- '199'
x-ratelimit-remaining-tokens:
- '31828'
x-ratelimit-reset-requests:
- 300ms
x-ratelimit-reset-tokens:
- 12.258s
x-request-id:
- 1c0d220cb7a5d43e8e407a3576681ad7
status:
code: 200
message: OK
version: 1

202
classic/forge/tests/vcr_cassettes/test_generate_aiconfig_automatic_fallback/test_generate_aiconfig_automatic_fallback.yaml generated
View File

@@ -1,202 +0,0 @@
interactions:
- request:
body: '{"messages": [{"content": "\nYour task is to devise up to 5 highly effective
goals and an appropriate role-based name (_GPT) for an autonomous agent, ensuring
that the goals are optimally aligned with the successful completion of its assigned
task.\n\nThe user will provide the task, you will provide only the output in
the exact format specified below with no explanation or conversation.\n\nExample
input:\nHelp me with marketing my business\n\nExample output:\nName: CMOGPT\nDescription:
a professional digital marketer AI that assists Solopreneurs in growing their
businesses by providing world-class expertise in solving marketing problems
for SaaS, content products, agencies, and more.\nGoals:\n- Engage in effective
problem-solving, prioritization, planning, and supporting execution to address
your marketing needs as your virtual Chief Marketing Officer.\n\n- Provide specific,
actionable, and concise advice to help you make informed decisions without the
use of platitudes or overly wordy explanations.\n\n- Identify and prioritize
quick wins and cost-effective campaigns that maximize results with minimal time
and budget investment.\n\n- Proactively take the lead in guiding you and offering
suggestions when faced with unclear information or uncertainty to ensure your
marketing strategy remains on track.\n", "role": "system"}, {"content": "Task:
''T&GF\u00a3OIBECC()!*''\nRespond only with the output in the exact format specified
in the system prompt, with no explanation or conversation.", "role": "user"}],
"model": "gpt-3.5-turbo", "temperature": 0.0}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '1590'
Content-Type:
- application/json
X-Content-Hash:
- 0731f601a012ca7c6e2e389a9dc0ebe08f6a7e3bfb004b72d5c24da757085b68
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA0zOPW4CMRCG4T6nGE2TxqBlEWTxDVAo0iQFUYSMPbAG27OyZyEIcfcI8kPabzSP
3jN6hxpta8TGLgyent+a2PbbaJt6GV75cFwcFrt2Ppst1xYV8npHVn4+hpZjF0g8J1RoMxkhh3o0
bSajuprWlcLIjgJq3HYyGA8nA+nzmgfVuBqhwr6YLaE+Y5c5drIS3lMqqOumUni3/+0KhcWEv2Vc
NReFtmVvqaB+P2Ok8qtmDoQaTSm+iElybeQklK7988cIhXM+KZiDNSmxQJf54B2BScC9dL3A0UvL
vYABG8hkMMlBnxzlK+jMOhCIKfshvAQyhe4CHEzw7naEDWeIBMLwnQIn7m/yEC8KNz750q4ymcIJ
NRbhDhX65OgTdXX5uDx8AQAA//8DANQ76GClAQAA
headers:
Access-Control-Allow-Origin:
- '*'
Alt-Svc:
- h3=":443"; ma=86400
- h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
Cache-Control:
- no-cache, must-revalidate
Cf-Cache-Status:
- DYNAMIC
Cf-Ray:
- 7cd797c7b8172d19-ORD
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 26 May 2023 17:03:45 GMT
Function-Execution-Id:
- u75a1w60qkmd
Openai-Model:
- gpt-3.5-turbo-0301
Openai-Organization:
- significant-gravitas
Openai-Processing-Ms:
- '4635'
Openai-Version:
- '2020-10-01'
Server:
- Google Frontend
Strict-Transport-Security:
- max-age=15724800; includeSubDomains
Vary:
- Accept-Encoding
X-Cloud-Trace-Context:
- 6444596b1ff59b706e529742bac3a855;o=1
X-Powered-By:
- Express
X-Ratelimit-Limit-Requests:
- '3500'
X-Ratelimit-Limit-Tokens:
- '90000'
X-Ratelimit-Remaining-Requests:
- '3499'
X-Ratelimit-Remaining-Tokens:
- '89626'
X-Ratelimit-Reset-Requests:
- 17ms
X-Ratelimit-Reset-Tokens:
- 248ms
X-Request-Id:
- 8328aeaa91a9fdfa98e92438444f1258
status:
code: 200
message: OK
- request:
body: '{"messages": [{"content": "\nYour task is to devise up to 5 highly effective
goals and an appropriate role-based name (_GPT) for an autonomous agent, ensuring
that the goals are optimally aligned with the successful completion of its assigned
task.\n\nThe user will provide the task, you will provide only the output in
the exact format specified below with no explanation or conversation.\n\nExample
input:\nHelp me with marketing my business\n\nExample output:\nName: CMOGPT\nDescription:
a professional digital marketer AI that assists Solopreneurs in growing their
businesses by providing world-class expertise in solving marketing problems
for SaaS, content products, agencies, and more.\nGoals:\n- Engage in effective
problem-solving, prioritization, planning, and supporting execution to address
your marketing needs as your virtual Chief Marketing Officer.\n\n- Provide specific,
actionable, and concise advice to help you make informed decisions without the
use of platitudes or overly wordy explanations.\n\n- Identify and prioritize
quick wins and cost-effective campaigns that maximize results with minimal time
and budget investment.\n\n- Proactively take the lead in guiding you and offering
suggestions when faced with unclear information or uncertainty to ensure your
marketing strategy remains on track.\n", "role": "system"}, {"content": "Task:
''T&GF\u00a3OIBECC()!*''\nRespond only with the output in the exact format specified
in the system prompt, with no explanation or conversation.", "role": "user"}],
"model": "gpt-4-0314", "temperature": 0.0}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '1587'
Content-Type:
- application/json
X-Content-Hash:
- 4cadf80f0732cd8436f50227b74845f28c012766a5c6c6e832045b5a064e3a1c
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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==
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 803a4292be81064d-IAD
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 08 Sep 2023 21:25:03 GMT
Server:
- cloudflare
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0314
openai-organization:
- significant-gravitas
openai-processing-ms:
- '18455'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '200'
x-ratelimit-limit-tokens:
- '40000'
x-ratelimit-remaining-requests:
- '199'
x-ratelimit-remaining-tokens:
- '24247'
x-ratelimit-reset-requests:
- 300ms
x-ratelimit-reset-tokens:
- 23.629s
x-request-id:
- aa451d1c6c5532d93e60c287fd091162
status:
code: 200
message: OK
version: 1

212
classic/forge/tests/vcr_cassettes/test_generate_aiconfig_automatic_typical/test_generate_aiconfig_automatic_typical.yaml generated
View File

@@ -1,212 +0,0 @@
interactions:
- request:
body: '{"messages": [{"content": "\nYour task is to devise up to 5 highly effective
goals and an appropriate role-based name (_GPT) for an autonomous agent, ensuring
that the goals are optimally aligned with the successful completion of its assigned
task.\n\nThe user will provide the task, you will provide only the output in
the exact format specified below with no explanation or conversation.\n\nExample
input:\nHelp me with marketing my business\n\nExample output:\nName: CMOGPT\nDescription:
a professional digital marketer AI that assists Solopreneurs in growing their
businesses by providing world-class expertise in solving marketing problems
for SaaS, content products, agencies, and more.\nGoals:\n- Engage in effective
problem-solving, prioritization, planning, and supporting execution to address
your marketing needs as your virtual Chief Marketing Officer.\n\n- Provide specific,
actionable, and concise advice to help you make informed decisions without the
use of platitudes or overly wordy explanations.\n\n- Identify and prioritize
quick wins and cost-effective campaigns that maximize results with minimal time
and budget investment.\n\n- Proactively take the lead in guiding you and offering
suggestions when faced with unclear information or uncertainty to ensure your
marketing strategy remains on track.\n", "role": "system"}, {"content": "Task:
''Help me create a rock opera about cybernetic giraffes''\nRespond only with
the output in the exact format specified in the system prompt, with no explanation
or conversation.", "role": "user"}], "model": "gpt-3.5-turbo", "temperature":
0.0}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '1623'
Content-Type:
- application/json
X-Content-Hash:
- 85e7cf25528e4015877bc3db5bbf9674c92e7d77d5476788f64bbf697481c3c0
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
Access-Control-Allow-Origin:
- '*'
Alt-Svc:
- h3=":443"; ma=86400
- h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
Cache-Control:
- no-cache, must-revalidate
Cf-Cache-Status:
- DYNAMIC
Cf-Ray:
- 7cd79738dd8022d0-ORD
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 26 May 2023 17:03:38 GMT
Function-Execution-Id:
- u75anm04ybm4
Openai-Model:
- gpt-3.5-turbo-0301
Openai-Organization:
- significant-gravitas
Openai-Processing-Ms:
- '20744'
Openai-Version:
- '2020-10-01'
Server:
- Google Frontend
Strict-Transport-Security:
- max-age=15724800; includeSubDomains
Vary:
- Accept-Encoding
X-Cloud-Trace-Context:
- c402bf3036960902e1be5293361e5c65;o=1
X-Powered-By:
- Express
X-Ratelimit-Limit-Requests:
- '3500'
X-Ratelimit-Limit-Tokens:
- '90000'
X-Ratelimit-Remaining-Requests:
- '3499'
X-Ratelimit-Remaining-Tokens:
- '89617'
X-Ratelimit-Reset-Requests:
- 17ms
X-Ratelimit-Reset-Tokens:
- 254ms
X-Request-Id:
- b44e6c90eb755e0bef60a3f2b20c1e10
status:
code: 200
message: OK
- request:
body: '{"messages": [{"content": "\nYour task is to devise up to 5 highly effective
goals and an appropriate role-based name (_GPT) for an autonomous agent, ensuring
that the goals are optimally aligned with the successful completion of its assigned
task.\n\nThe user will provide the task, you will provide only the output in
the exact format specified below with no explanation or conversation.\n\nExample
input:\nHelp me with marketing my business\n\nExample output:\nName: CMOGPT\nDescription:
a professional digital marketer AI that assists Solopreneurs in growing their
businesses by providing world-class expertise in solving marketing problems
for SaaS, content products, agencies, and more.\nGoals:\n- Engage in effective
problem-solving, prioritization, planning, and supporting execution to address
your marketing needs as your virtual Chief Marketing Officer.\n\n- Provide specific,
actionable, and concise advice to help you make informed decisions without the
use of platitudes or overly wordy explanations.\n\n- Identify and prioritize
quick wins and cost-effective campaigns that maximize results with minimal time
and budget investment.\n\n- Proactively take the lead in guiding you and offering
suggestions when faced with unclear information or uncertainty to ensure your
marketing strategy remains on track.\n", "role": "system"}, {"content": "Task:
''Help me create a rock opera about cybernetic giraffes''\nRespond only with
the output in the exact format specified in the system prompt, with no explanation
or conversation.", "role": "user"}], "model": "gpt-4-0314", "temperature": 0.0}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '1620'
Content-Type:
- application/json
X-Content-Hash:
- 37e220315181f2969a9b7eb6fa5df305799392e544329f68fdae60fe01200a18
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 803a42163cee084c-IAD
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 08 Sep 2023 21:24:44 GMT
Server:
- cloudflare
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0314
openai-organization:
- significant-gravitas
openai-processing-ms:
- '19598'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '200'
x-ratelimit-limit-tokens:
- '40000'
x-ratelimit-remaining-requests:
- '199'
x-ratelimit-remaining-tokens:
- '27304'
x-ratelimit-reset-requests:
- 300ms
x-ratelimit-reset-tokens:
- 19.043s
x-request-id:
- 8dba4e8ded88e2d7797cf85ea3dae37d
status:
code: 200
message: OK
version: 1

3206
classic/forge/tests/vcr_cassettes/test_information_retrieval_challenge_a/test_information_retrieval_challenge_a.yaml generated
View File

File diff suppressed because it is too large Load Diff

2433
classic/forge/tests/vcr_cassettes/test_information_retrieval_challenge_b/test_information_retrieval_challenge_b.yaml generated
View File

File diff suppressed because it is too large Load Diff

3384
classic/forge/tests/vcr_cassettes/test_json_memory_get_relevant/test_json_memory_get_relevant.yaml generated
View File

File diff suppressed because it is too large Load Diff

25958
classic/forge/tests/vcr_cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml generated
View File

File diff suppressed because it is too large Load Diff

5633
classic/forge/tests/vcr_cassettes/test_memory_challenge_c/test_memory_challenge_c.yaml generated
View File

File diff suppressed because it is too large Load Diff

7256
classic/forge/tests/vcr_cassettes/test_write_file/test_write_file.yaml generated
View File

File diff suppressed because it is too large Load Diff

73
classic/original_autogpt/tests/integration/test_strategy_benchmark.py
View File

@@ -1,12 +1,12 @@
"""Pytest wrapper for strategy benchmark test harness.
"""Pytest wrapper for direct_benchmark harness.
This provides CI-friendly integration of the strategy benchmark,
This provides CI-friendly integration of the direct_benchmark harness,
allowing it to be run as part of the pytest suite.
Usage:
# Run tests that don't need an agent (--help, --compare-only, etc.)
# Run tests that don't need an agent (--help, invalid args, etc.)
poetry run pytest tests/integration/test_strategy_benchmark.py \
-v -k "help or invalid or compare"
-v -k "help or invalid"
# Run full tests (requires API keys and agent to be configured)
poetry run pytest tests/integration/test_strategy_benchmark.py -v
@@ -49,25 +49,25 @@ requires_agent = pytest.mark.skipif(
)
def get_project_root() -> Path:
"""Get the original_autogpt project root directory."""
return Path(__file__).parent.parent.parent
def get_direct_benchmark_dir() -> Path:
"""Get the direct_benchmark directory."""
return Path(__file__).parent.parent.parent.parent / "direct_benchmark"
def run_harness(*args: str, timeout: int = 600) -> subprocess.CompletedProcess:
"""Run the test harness with given arguments.
"""Run the direct_benchmark harness with given arguments.
Args:
*args: Arguments to pass to test_prompt_strategies.py
*args: Arguments to pass to direct_benchmark run command
timeout: Timeout in seconds (default: 10 minutes)
Returns:
CompletedProcess with stdout/stderr captured
"""
cmd = [sys.executable, "agbenchmark_config/test_prompt_strategies.py", *args]
cmd = [sys.executable, "-m", "direct_benchmark", "run", *args]
return subprocess.run(
cmd,
cwd=get_project_root(),
cwd=get_direct_benchmark_dir(),
capture_output=True,
text=True,
timeout=timeout,
@@ -79,13 +79,18 @@ def test_strategy_comparison_quick():
"""Run quick strategy comparison as CI smoke test.
This test:
1. Starts the agent with each strategy
2. Runs interface tests (fastest category)
3. Verifies at least one strategy produces passing results
1. Starts the agent with one_shot strategy
2. Runs general category tests
3. Verifies at least one test produces passing results
Note: Requires API keys to be configured in environment.
"""
result = run_harness("--quick")
result = run_harness(
"--strategies", "one_shot",
"--categories", "general",
"-N", "1",
"--tests", "ReadFile", # Single fast test for smoke testing
)
# Print output for debugging
print(result.stdout)
@@ -99,41 +104,17 @@ def test_strategy_comparison_quick():
)
def test_harness_compare_only():
"""Test that compare-only mode works with existing reports.
This test doesn't run any benchmarks, just verifies the report
comparison logic works correctly.
"""
result = run_harness("--compare-only")
# Print output for debugging
print(result.stdout)
if result.stderr:
print("STDERR:", result.stderr)
# compare-only returns 0 if it can read reports (even if empty)
# It returns 1 only if there's an actual error
# We check that it ran without crashing
assert "PROMPT STRATEGY" in result.stdout or result.returncode in (0, 1), (
f"Harness crashed unexpectedly\n"
f"stdout: {result.stdout[-2000:]}\n"
f"stderr: {result.stderr[-500:]}"
)
@requires_agent
def test_single_strategy():
"""Test running a single strategy with interface tests.
"""Test running a single strategy with coding tests.
This is a more focused test that only runs one_shot strategy
to verify basic functionality without testing all strategies.
"""
result = run_harness(
"--strategies",
"one_shot",
"--categories",
"interface",
"--strategies", "one_shot",
"--categories", "coding",
"--tests", "ReadFile,WriteFile",
)
# Print output for debugging
@@ -154,7 +135,7 @@ def test_harness_help():
assert result.returncode == 0, "Harness --help should return 0"
assert "strategies" in result.stdout.lower(), "Help should mention strategies"
assert "quick" in result.stdout.lower(), "Help should mention quick mode"
assert "categories" in result.stdout.lower(), "Help should mention categories"
def test_harness_invalid_strategy():
@@ -162,4 +143,6 @@ def test_harness_invalid_strategy():
result = run_harness("--strategies", "invalid_strategy", timeout=30)
assert result.returncode != 0, "Invalid strategy should return non-zero"
assert "invalid" in result.stdout.lower(), "Should mention invalid strategy"
# Error message may be in stdout or stderr depending on the CLI framework
combined_output = (result.stdout + result.stderr).lower()
assert "invalid" in combined_output, "Should mention invalid strategy"