Move agenthub within openhands (#4130)

.github/workflows/ghcr-build.yml

@@ -294,7 +294,7 @@ jobs:
           SANDBOX_RUNTIME_CONTAINER_IMAGE=$image_name \
           TEST_IN_CI=true \
           RUN_AS_OPENHANDS=false \
-          poetry run pytest -n 3 -raRs --reruns 2 --reruns-delay 5 --cov=agenthub --cov=openhands --cov-report=xml -s ./tests/runtime
+          poetry run pytest -n 3 -raRs --reruns 2 --reruns-delay 5 --cov=openhands --cov-report=xml -s ./tests/runtime
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v4
         env:
@@ -372,7 +372,7 @@ jobs:
           SANDBOX_RUNTIME_CONTAINER_IMAGE=$image_name \
           TEST_IN_CI=true \
           RUN_AS_OPENHANDS=true \
-          poetry run pytest -n 3 -raRs --reruns 2 --reruns-delay 5 --cov=agenthub --cov=openhands --cov-report=xml -s ./tests/runtime
+          poetry run pytest -n 3 -raRs --reruns 2 --reruns-delay 5 --cov=openhands --cov-report=xml -s ./tests/runtime
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v4
         env:

.github/workflows/lint.yml

@@ -46,4 +46,4 @@ jobs:
       - name: Install pre-commit
         run: pip install pre-commit==3.7.0
       - name: Run pre-commit hooks
-        run: pre-commit run --files openhands/**/* agenthub/**/* evaluation/**/* tests/**/* --show-diff-on-failure --config ./dev_config/python/.pre-commit-config.yaml
+        run: pre-commit run --files openhands/**/* evaluation/**/* tests/**/* --show-diff-on-failure --config ./dev_config/python/.pre-commit-config.yaml

.github/workflows/py-unit-tests.yml

@@ -93,7 +93,7 @@ jobs:
         id: buildx
         uses: docker/setup-buildx-action@v3
       - name: Run Tests
-        run: poetry run pytest --forked --cov=agenthub --cov=openhands --cov-report=xml ./tests/unit --ignore=tests/unit/test_memory.py
+        run: poetry run pytest --forked --cov=openhands --cov-report=xml ./tests/unit --ignore=tests/unit/test_memory.py
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v4
         env:
@@ -125,7 +125,7 @@ jobs:
       - name: Build Environment
         run: make build
       - name: Run Tests
-        run: poetry run pytest --forked --cov=agenthub --cov=openhands --cov-report=xml -svv ./tests/unit --ignore=tests/unit/test_memory.py
+        run: poetry run pytest --forked --cov=openhands --cov-report=xml -svv ./tests/unit --ignore=tests/unit/test_memory.py
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v4
         env:

CONTRIBUTING.md

@@ -14,11 +14,12 @@ There are many ways that you can contribute:
 
 To understand the codebase, please refer to the README in each module:
 - [frontend](./frontend/README.md)
-- [agenthub](./agenthub/README.md)
 - [evaluation](./evaluation/README.md)
 - [openhands](./openhands/README.md)
+    - [agenthub](./openhands/agenthub/README.md)
     - [server](./openhands/server/README.md)
 
+
 When you write code, it is also good to write tests. Please navigate to the `tests` folder to see existing test suites.
 At the moment, we have two kinds of tests: `unit` and `integration`. Please refer to the README for each test suite. These tests also run on GitHub's continuous integration to ensure quality of the project.
 

containers/app/Dockerfile

@@ -69,7 +69,7 @@ RUN playwright install --with-deps chromium
 
 COPY --chown=openhands:app --chmod=770 ./openhands ./openhands
 COPY --chown=openhands:app --chmod=777 ./openhands/runtime/plugins ./openhands/runtime/plugins
-COPY --chown=openhands:app --chmod=770 ./agenthub ./agenthub
+COPY --chown=openhands:app --chmod=770 ./openhands/agenthub ./openhands/agenthub
 COPY --chown=openhands:app ./pyproject.toml ./pyproject.toml
 COPY --chown=openhands:app ./poetry.lock ./poetry.lock
 COPY --chown=openhands:app ./README.md ./README.md

dev_config/python/.pre-commit-config.yaml

@@ -38,6 +38,6 @@ repos:
       - id: mypy
         additional_dependencies:
           [types-requests, types-setuptools, types-pyyaml, types-toml]
-        entry: mypy --config-file dev_config/python/mypy.ini openhands/ agenthub/
+        entry: mypy --config-file dev_config/python/mypy.ini openhands/
         always_run: true
         pass_filenames: false

docs/modules/usage/how-to/evaluation-harness.md

@@ -84,7 +84,7 @@ To create an evaluation workflow for your benchmark, follow these steps:
 
 1. Import relevant OpenHands utilities:
    ```python
-    import agenthub
+    import openhands.agenthub
     from evaluation.utils.shared import (
         EvalMetadata,
         EvalOutput,

evaluation/EDA/scripts/run_infer.sh

@@ -36,7 +36,7 @@ fi
 
 # IMPORTANT: Because Agent's prompt changes fairly often in the rapidly evolving codebase of OpenHands
 # We need to track the version of Agent in the evaluation to make sure results are comparable
-AGENT_VERSION=v$(poetry run python -c "import agenthub; from openhands.controller.agent import Agent; print(Agent.get_cls('$AGENT').VERSION)")
+AGENT_VERSION=v$(poetry run python -c "import openhands.agenthub; from openhands.controller.agent import Agent; print(Agent.get_cls('$AGENT').VERSION)")
 
 echo "AGENT: $AGENT"
 echo "AGENT_VERSION: $AGENT_VERSION"

evaluation/regression/conftest.py

@@ -8,7 +8,7 @@ import pytest
 
 SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
 CASES_DIR = os.path.join(SCRIPT_DIR, 'cases')
-AGENTHUB_DIR = os.path.join(SCRIPT_DIR, '../../', 'agenthub')
+AGENTHUB_DIR = os.path.join(SCRIPT_DIR, '../', 'agenthub')
 
 
 def agents():

evaluation/swe_bench/run_infer.py

@@ -8,7 +8,7 @@ import pandas as pd
 import toml
 from datasets import load_dataset
 
-import agenthub
+import openhands.agenthub
 from evaluation.swe_bench.prompt import CODEACT_SWE_PROMPT
 from evaluation.utils.shared import (
     EvalMetadata,
@@ -470,7 +470,7 @@ if __name__ == '__main__':
         raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')
 
     details = {}
-    _agent_cls = agenthub.Agent.get_cls(args.agent_cls)
+    _agent_cls = openhands.agenthub.Agent.get_cls(args.agent_cls)
     if hasattr(_agent_cls, 'system_message'):
         details['system_message'] = _agent_cls.system_message
     if hasattr(_agent_cls, 'in_context_example'):

evaluation/utils/version_control.sh

@@ -42,5 +42,5 @@ checkout_original_branch() {
 get_agent_version() {
     # IMPORTANT: Because Agent's prompt changes fairly often in the rapidly evolving codebase of OpenHands
     # We need to track the version of Agent in the evaluation to make sure results are comparable
-    AGENT_VERSION=v$(poetry run python -c "import agenthub; from openhands.controller.agent import Agent; print(Agent.get_cls('$AGENT').VERSION)")
+    AGENT_VERSION=v$(poetry run python -c "import openhands.agenthub; from openhands.controller.agent import Agent; print(Agent.get_cls('$AGENT').VERSION)")
 }

agenthub/README.md → openhands/agenthub/README.md

@@ -2,7 +2,7 @@
 
 In this folder, there may exist multiple implementations of `Agent` that will be used by the framework.
 
-For example, `agenthub/codeact_agent`, etc.
+For example, `openhands/agenthub/codeact_agent`, etc.
 Contributors from different backgrounds and interests can choose to contribute to any (or all!) of these directions.
 
 ## Constructing an Agent

agenthub/__init__.py → openhands/agenthub/__init__.py

@@ -1,13 +1,13 @@
 from dotenv import load_dotenv
 
-from agenthub.micro.agent import MicroAgent
-from agenthub.micro.registry import all_microagents
+from openhands.agenthub.micro.agent import MicroAgent
+from openhands.agenthub.micro.registry import all_microagents
 from openhands.controller.agent import Agent
 
 load_dotenv()
 
 
-from agenthub import (  # noqa: E402
+from openhands.agenthub import (  # noqa: E402
     browsing_agent,
     codeact_agent,
     codeact_swe_agent,

agenthub/browsing_agent/__init__.py → openhands/agenthub/browsing_agent/__init__.py

@@ -1,4 +1,4 @@
-from agenthub.browsing_agent.browsing_agent import BrowsingAgent
+from openhands.agenthub.browsing_agent.browsing_agent import BrowsingAgent
 from openhands.controller.agent import Agent
 
 Agent.register('BrowsingAgent', BrowsingAgent)

agenthub/browsing_agent/browsing_agent.py → openhands/agenthub/browsing_agent/browsing_agent.py

@@ -3,7 +3,7 @@ import os
 from browsergym.core.action.highlevel import HighLevelActionSet
 from browsergym.utils.obs import flatten_axtree_to_str
 
-from agenthub.browsing_agent.response_parser import BrowsingResponseParser
+from openhands.agenthub.browsing_agent.response_parser import BrowsingResponseParser
 from openhands.controller.agent import Agent
 from openhands.controller.state.state import State
 from openhands.core.config import AgentConfig

agenthub/browsing_agent/prompt.py → openhands/agenthub/browsing_agent/prompt.py

@@ -12,7 +12,7 @@ from browsergym.core.action.base import AbstractActionSet
 from browsergym.core.action.highlevel import HighLevelActionSet
 from browsergym.core.action.python import PythonActionSet
 
-from agenthub.browsing_agent.utils import (
+from openhands.agenthub.browsing_agent.utils import (
     ParseError,
     parse_html_tags_raise,
 )

agenthub/codeact_agent/__init__.py → openhands/agenthub/codeact_agent/__init__.py

@@ -1,4 +1,4 @@
-from agenthub.codeact_agent.codeact_agent import CodeActAgent
+from openhands.agenthub.codeact_agent.codeact_agent import CodeActAgent
 from openhands.controller.agent import Agent
 
 Agent.register('CodeActAgent', CodeActAgent)

agenthub/codeact_agent/codeact_agent.py → openhands/agenthub/codeact_agent/codeact_agent.py

@@ -1,7 +1,7 @@
 import os
 from itertools import islice
 
-from agenthub.codeact_agent.action_parser import CodeActResponseParser
+from openhands.agenthub.codeact_agent.action_parser import CodeActResponseParser
 from openhands.controller.agent import Agent
 from openhands.controller.state.state import State
 from openhands.core.config import AgentConfig

agenthub/codeact_swe_agent/__init__.py → openhands/agenthub/codeact_swe_agent/__init__.py

@@ -1,4 +1,4 @@
-from agenthub.codeact_swe_agent.codeact_swe_agent import CodeActSWEAgent
+from openhands.agenthub.codeact_swe_agent.codeact_swe_agent import CodeActSWEAgent
 from openhands.controller.agent import Agent
 
 Agent.register('CodeActSWEAgent', CodeActSWEAgent)

agenthub/codeact_swe_agent/codeact_swe_agent.py → openhands/agenthub/codeact_swe_agent/codeact_swe_agent.py

@@ -1,10 +1,12 @@
-from agenthub.codeact_swe_agent.prompt import (
+from openhands.agenthub.codeact_swe_agent.prompt import (
     COMMAND_DOCS,
     SWE_EXAMPLE,
     SYSTEM_PREFIX,
     SYSTEM_SUFFIX,
 )
-from agenthub.codeact_swe_agent.response_parser import CodeActSWEResponseParser
+from openhands.agenthub.codeact_swe_agent.response_parser import (
+    CodeActSWEResponseParser,
+)
 from openhands.controller.agent import Agent
 from openhands.controller.state.state import State
 from openhands.core.config import AgentConfig

agenthub/codeact_swe_agent/response_parser.py → openhands/agenthub/codeact_swe_agent/response_parser.py

@@ -1,4 +1,4 @@
-from agenthub.codeact_swe_agent.action_parser import (
+from openhands.agenthub.codeact_swe_agent.action_parser import (
     CodeActSWEActionParserCmdRun,
     CodeActSWEActionParserFinish,
     CodeActSWEActionParserIPythonRunCell,

agenthub/delegator_agent/__init__.py → openhands/agenthub/delegator_agent/__init__.py

@@ -1,4 +1,4 @@
-from agenthub.delegator_agent.agent import DelegatorAgent
+from openhands.agenthub.delegator_agent.agent import DelegatorAgent
 from openhands.controller.agent import Agent
 
 Agent.register('DelegatorAgent', DelegatorAgent)

agenthub/dummy_agent/__init__.py → openhands/agenthub/dummy_agent/__init__.py

@@ -1,4 +1,4 @@
-from agenthub.dummy_agent.agent import DummyAgent
+from openhands.agenthub.dummy_agent.agent import DummyAgent
 from openhands.controller.agent import Agent
 
 Agent.register('DummyAgent', DummyAgent)

agenthub/micro/agent.py → openhands/agenthub/micro/agent.py

@@ -1,7 +1,7 @@
 from jinja2 import BaseLoader, Environment
 
-from agenthub.micro.instructions import instructions
-from agenthub.micro.registry import all_microagents
+from openhands.agenthub.micro.instructions import instructions
+from openhands.agenthub.micro.registry import all_microagents
 from openhands.controller.agent import Agent
 from openhands.controller.state.state import State
 from openhands.core.config import AgentConfig

agenthub/planner_agent/__init__.py → openhands/agenthub/planner_agent/__init__.py

@@ -1,4 +1,4 @@
-from agenthub.planner_agent.agent import PlannerAgent
+from openhands.agenthub.planner_agent.agent import PlannerAgent
 from openhands.controller.agent import Agent
 
 Agent.register('PlannerAgent', PlannerAgent)

agenthub/planner_agent/agent.py → openhands/agenthub/planner_agent/agent.py

@@ -1,5 +1,5 @@
-from agenthub.planner_agent.prompt import get_prompt_and_images
-from agenthub.planner_agent.response_parser import PlannerResponseParser
+from openhands.agenthub.planner_agent.prompt import get_prompt_and_images
+from openhands.agenthub.planner_agent.response_parser import PlannerResponseParser
 from openhands.controller.agent import Agent
 from openhands.controller.state.state import State
 from openhands.core.config import AgentConfig

openhands/core/cli.py

@@ -4,7 +4,7 @@ from typing import Type
 
 from termcolor import colored
 
-import agenthub  # noqa F401 (we import this to get the agents registered)
+import openhands.agenthub  # noqa F401 (we import this to get the agents registered)
 from openhands import __version__
 from openhands.controller import AgentController
 from openhands.controller.agent import Agent

openhands/core/download.py

@@ -1,2 +1,2 @@
 # Run this file to trigger a model download
-import agenthub  # noqa F401 (we import this to get the agents registered)
+import openhands.agenthub  # noqa F401 (we import this to get the agents registered)

openhands/core/main.py

@@ -4,7 +4,7 @@ import sys
 import uuid
 from typing import Callable, Protocol, Type
 
-import agenthub  # noqa F401 (we import this to get the agents registered)
+import openhands.agenthub  # noqa F401 (we import this to get the agents registered)
 from openhands.controller import AgentController
 from openhands.controller.agent import Agent
 from openhands.controller.state.state import State
@@ -66,7 +66,7 @@ def create_runtime(
     event_stream = EventStream(session_id, file_store)
 
     # agent class
-    agent_cls = agenthub.Agent.get_cls(config.default_agent)
+    agent_cls = openhands.agenthub.Agent.get_cls(config.default_agent)
 
     # runtime and tools
     runtime_cls = get_runtime_cls(config.runtime)

openhands/server/listen.py

@@ -34,7 +34,7 @@ from fastapi.security import HTTPBearer
 from fastapi.staticfiles import StaticFiles
 from pydantic import BaseModel
 
-import agenthub  # noqa F401 (we import this to get the agents registered)
+import openhands.agenthub  # noqa F401 (we import this to get the agents registered)
 from openhands.controller.agent import Agent
 from openhands.core.config import LLMConfig, load_app_config
 from openhands.core.logger import openhands_logger as logger

pyproject.toml

@@ -8,7 +8,6 @@ readme = "README.md"
 repository = "https://github.com/All-Hands-AI/OpenHands"
 include = ["poetry.lock"]
 packages = [
-  { include = "agenthub/**/*" },
   { include = "openhands/**/*" }
 ]
 
@@ -86,6 +85,7 @@ reportlab = "*"
 [tool.coverage.run]
 concurrency = ["gevent"]
 
+
 [tool.poetry.group.runtime.dependencies]
 jupyterlab = "*"
 notebook = "*"
@@ -116,6 +116,7 @@ ignore = ["D1"]
 [tool.ruff.lint.pydocstyle]
 convention = "google"
 
+
 [tool.poetry.group.evaluation.dependencies]
 streamlit = "*"
 whatthepatch = "*"

tests/integration/regenerate.sh

@@ -119,7 +119,7 @@ run_test() {
   local pytest_cmd="poetry run pytest --cache-clear -vvsxx $SCRIPT_DIR/test_agent.py::$test_name"
   # Check if TEST_IN_CI is defined
   if [ -n "$TEST_IN_CI" ]; then
-    pytest_cmd+=" --cov=agenthub --cov=openhands --cov-report=xml --cov-append"
+    pytest_cmd+=" --cov=openhands --cov-report=xml --cov-append"
   fi
 
   env SCRIPT_DIR="$SCRIPT_DIR" \

tests/unit/test_browsing_agent_parser.py

@@ -1,6 +1,6 @@
 import pytest
 
-from agenthub.browsing_agent.response_parser import (
+from openhands.agenthub.browsing_agent.response_parser import (
     BrowseInteractiveAction,
     BrowsingResponseParser,
 )

tests/unit/test_codeact_agent.py

@@ -2,7 +2,7 @@ from unittest.mock import Mock
 
 import pytest
 
-from agenthub.codeact_agent.codeact_agent import CodeActAgent
+from openhands.agenthub.codeact_agent.codeact_agent import CodeActAgent
 from openhands.core.config import AgentConfig, LLMConfig
 from openhands.core.message import TextContent
 from openhands.events.observation.commands import (

tests/unit/test_micro_agents.py

@@ -6,7 +6,7 @@ import pytest
 import yaml
 from pytest import TempPathFactory
 
-from agenthub.micro.registry import all_microagents
+from openhands.agenthub.micro.registry import all_microagents
 from openhands.controller.agent import Agent
 from openhands.controller.state.state import State
 from openhands.core.config import AgentConfig
@@ -44,7 +44,7 @@ def test_all_agents_are_loaded():
     assert all_microagents is not None
     assert len(all_microagents) > 1
 
-    base = os.path.join('agenthub', 'micro')
+    base = os.path.join('openhands', 'agenthub', 'micro')
     full_path = os.path.dirname(__file__) + '/../../' + base
     agent_names = set()
     for root, _, files in os.walk(full_path):

tests/unit/test_microagent_utils.py

@@ -3,7 +3,7 @@ import os
 import pytest
 from pytest import MonkeyPatch
 
-import agenthub  # noqa: F401
+import openhands.agenthub  # noqa: F401
 from openhands.core.exceptions import (
     AgentNotRegisteredError,
     MicroAgentValidationError,

tests/unit/test_prompt_caching.py

@@ -2,7 +2,7 @@ from unittest.mock import MagicMock, Mock, patch
 
 import pytest
 
-from agenthub.codeact_agent.codeact_agent import CodeActAgent
+from openhands.agenthub.codeact_agent.codeact_agent import CodeActAgent
 from openhands.core.config import AgentConfig, LLMConfig
 from openhands.events import EventSource, EventStream
 from openhands.events.action import CmdRunAction, MessageAction

tests/unit/test_prompt_manager.py

@@ -10,8 +10,8 @@ from openhands.utils.prompt import PromptManager
 
 @pytest.fixture
 def prompt_dir(tmp_path):
-    # Copy contents from "agenthub/codeact_agent" to the temp directory
-    shutil.copytree('agenthub/codeact_agent', tmp_path, dirs_exist_ok=True)
+    # Copy contents from "openhands/agenthub/codeact_agent" to the temp directory
+    shutil.copytree('openhands/agenthub/codeact_agent', tmp_path, dirs_exist_ok=True)
 
     # Return the temporary directory path
     return tmp_path

tests/unit/test_response_parsing.py

@@ -1,7 +1,9 @@
 import pytest
 
-from agenthub.micro.agent import parse_response as parse_response_micro
-from agenthub.planner_agent.prompt import parse_response as parse_response_planner
+from openhands.agenthub.micro.agent import parse_response as parse_response_micro
+from openhands.agenthub.planner_agent.prompt import (
+    parse_response as parse_response_planner,
+)
 from openhands.core.exceptions import LLMResponseError
 from openhands.core.utils.json import loads as custom_loads
 from openhands.events.action import (

tests/unit/test_runtime_build.py

@@ -56,7 +56,6 @@ def _check_source_code_in_dir(temp_dir):
 
     # The source code should only include the `openhands` folder, but not the other folders
     assert set(os.listdir(code_dir)) == {
-        'agenthub',
         'openhands',
         'pyproject.toml',
         'poetry.lock',