github/OpenHands
1
0
Fork 0
mirror of https://github.com/OpenHands/OpenHands.git synced 2026-03-22 13:47:19 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into openhands-fix-issue-4127

Browse Source
This commit is contained in:
Robert Brennan
2024-10-01 12:44:52 -04:00
committed by GitHub
parent d86f7a7e12 ec1a86f150
commit 8e832f9653
11 changed files with 68 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
docs/modules/usage/getting-started.mdx
View File

@@ -32,8 +32,7 @@ docker run -it --pull=always \
ghcr.io/all-hands-ai/openhands:0.9
```
You can also run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/modules/usage/how-to/headless-mode),
or as an [interactive CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode).
You can also run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/modules/usage/how-to/headless-mode), as an [interactive CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode), or using the [OpenHands GitHub Action](https://docs.all-hands.dev/modules/usage/how-to/github-action).
## Setup

15
docs/modules/usage/how-to/github-action.md Normal file
View File

@@ -0,0 +1,15 @@
# Using the OpenHands GitHub Action
This guide explains how to use the OpenHands GitHub Action, both within the OpenHands repository and in your own projects.
## Using the Action in the OpenHands Repository
To use the OpenHands GitHub Action in the OpenHands repository, an OpenHands maintainer can:
1. Create an issue in the repository.
2. Add the `fix-me` label to the issue.
3. The action will automatically trigger and attempt to resolve the issue.
## Installing the Action in a New Repository
To install the OpenHands GitHub Action in your own repository, follow the [directions in the OpenHands Resolver repo](https://github.com/All-Hands-AI/OpenHands-resolver?tab=readme-ov-file#using-the-github-actions-workflow).

4
docs/sidebars.ts
View File

@@ -72,6 +72,10 @@ const sidebars: SidebarsConfig = {
type: 'doc',
id: 'usage/how-to/headless-mode',
},
{
type: 'doc',
id: 'usage/how-to/github-action',
},
{
type: 'doc',
id: 'usage/how-to/custom-sandbox-guide',

5
evaluation/swe_bench/README.md
View File

@@ -69,7 +69,7 @@ This is in limited beta. Contact Xingyao over slack if you want to try this out!
```bash
# ./evaluation/swe_bench/scripts/run_infer.sh [model_config] [git-version] [agent] [eval_limit] [max_iter] [num_workers] [dataset] [dataset_split]
ALLHANDS_API_KEY="YOUR-API-KEY" RUNTIME=remote EVAL_DOCKER_IMAGE_PREFIX="us-docker.pkg.dev/evaluation-428620/swe-bench-images" \
ALLHANDS_API_KEY="YOUR-API-KEY" RUNTIME=remote SANDBOX_REMOTE_RUNTIME_API_URL="https://runtime.eval.all-hands.dev" EVAL_DOCKER_IMAGE_PREFIX="us-central1-docker.pkg.dev/evaluation-092424/swe-bench-images" \
./evaluation/swe_bench/scripts/run_infer.sh llm.eval HEAD CodeActAgent 300 30 16 "princeton-nlp/SWE-bench_Lite" test
# This example runs evaluation on CodeActAgent for 300 instances on "princeton-nlp/SWE-bench_Lite"'s test set, with max 30 iteration per instances, with 16 number of workers running in parallel
```
@@ -163,7 +163,8 @@ This is in limited beta. Contact Xingyao over slack if you want to try this out!
```bash
# ./evaluation/swe_bench/scripts/eval_infer_remote.sh [output.jsonl filepath] [num_workers]
ALLHANDS_API_KEY="YOUR-API-KEY" RUNTIME=remote EVAL_DOCKER_IMAGE_PREFIX="us-docker.pkg.dev/evaluation-428620/swe-bench-images" evaluation/swe_bench/scripts/eval_infer_remote.sh evaluation/outputs/swe_bench_lite/CodeActAgent/Llama-3.1-70B-Instruct-Turbo_maxiter_30_N_v1.9-no-hint/output.jsonl 16 "princeton-nlp/SWE-bench_Lite" "test"
ALLHANDS_API_KEY="YOUR-API-KEY" RUNTIME=remote SANDBOX_REMOTE_RUNTIME_API_URL="https://runtime.eval.all-hands.dev" EVAL_DOCKER_IMAGE_PREFIX="us-central1-docker.pkg.dev/evaluation-092424/swe-bench-images" \
evaluation/swe_bench/scripts/eval_infer_remote.sh evaluation/evaluation_outputs/outputs/swe_bench_lite/CodeActAgent/Llama-3.1-70B-Instruct-Turbo_maxiter_30_N_v1.9-no-hint/output.jsonl 16 "princeton-nlp/SWE-bench_Lite" "test"
# This example evaluate patches generated by CodeActAgent on Llama-3.1-70B-Instruct-Turbo on "princeton-nlp/SWE-bench_Lite"'s test set, with 16 number of workers running in parallel
```

1
evaluation/swe_bench/eval_infer.py
View File

@@ -81,6 +81,7 @@ def get_config(instance: pd.Series) -> AppConfig:
# large enough timeout, since some testcases take very long to run
timeout=1800,
api_key=os.environ.get('ALLHANDS_API_KEY', None),
remote_runtime_api_url=os.environ.get('SANDBOX_REMOTE_RUNTIME_API_URL'),
),
# do not mount workspace
workspace_base=None,

1
evaluation/swe_bench/run_infer.py
View File

@@ -131,6 +131,7 @@ def get_config(
# large enough timeout, since some testcases take very long to run
timeout=300,
api_key=os.environ.get('ALLHANDS_API_KEY', None),
remote_runtime_api_url=os.environ.get('SANDBOX_REMOTE_RUNTIME_API_URL'),
),
# do not mount workspace
workspace_base=None,

6
evaluation/swe_bench/scripts/cleanup_remote_runtime.sh Normal file → Executable file
View File

@@ -2,10 +2,10 @@
# API base URL
BASE_URL="https://api.all-hands.dev/v0"
BASE_URL="https://runtime.eval.all-hands.dev"
# Get the list of runtimes
response=$(curl --silent --location --request GET "${BASE_URL}/runtime/list" \
response=$(curl --silent --location --request GET "${BASE_URL}/list" \
--header "X-API-Key: ${ALLHANDS_API_KEY}")
n_runtimes=$(echo $response | jq -r '.total')
@@ -16,7 +16,7 @@ runtime_ids=$(echo $response | jq -r '.runtimes | .[].runtime_id')
counter=1
for runtime_id in $runtime_ids; do
echo "Stopping runtime ${counter}/${n_runtimes}: ${runtime_id}"
curl --silent --location --request POST "${BASE_URL}/runtime/stop" \
curl --silent --location --request POST "${BASE_URL}/stop" \
--header "X-API-Key: ${ALLHANDS_API_KEY}" \
--header "Content-Type: application/json" \
--data-raw "{\"runtime_id\": \"${runtime_id}\"}"

8
frontend/package-lock.json generated
View File

@@ -42,7 +42,7 @@
"@testing-library/react": "^16.0.1",
"@testing-library/user-event": "^14.5.2",
"@types/node": "^22.7.3",
"@types/react": "^18.3.9",
"@types/react": "^18.3.10",
"@types/react-dom": "^18.3.0",
"@types/react-highlight": "^0.12.8",
"@types/react-syntax-highlighter": "^15.5.13",
@@ -4874,9 +4874,9 @@
"integrity": "sha512-5zvhXYtRNRluoE/jAp4GVsSduVUzNWKkOZrCDBWYtE7biZywwdC2AcEzg+cSMLFRfVgeAFqpfNabiPjxFddV1Q=="
},
"node_modules/@types/react": {
"version": "18.3.9",
"resolved": "https://registry.npmjs.org/@types/react/-/react-18.3.9.tgz",
"integrity": "sha512-+BpAVyTpJkNWWSSnaLBk6ePpHLOGJKnEQNbINNovPWzvEUyAe3e+/d494QdEh71RekM/qV7lw6jzf1HGrJyAtQ==",
"version": "18.3.10",
"resolved": "https://registry.npmjs.org/@types/react/-/react-18.3.10.tgz",
"integrity": "sha512-02sAAlBnP39JgXwkAq3PeU9DVaaGpZyF3MGcC0MKgQVkZor5IiiDAipVaxQHtDJAmO4GIy/rVBy/LzVj76Cyqg==",
"dependencies": {
"@types/prop-types": "*",
"csstype": "^3.0.2"

2
frontend/package.json
View File

@@ -65,7 +65,7 @@
"@testing-library/react": "^16.0.1",
"@testing-library/user-event": "^14.5.2",
"@types/node": "^22.7.3",
"@types/react": "^18.3.9",
"@types/react": "^18.3.10",
"@types/react-dom": "^18.3.0",
"@types/react-highlight": "^0.12.8",
"@types/react-syntax-highlighter": "^15.5.13",

30
openhands/server/session/agent_session.py
View File

@@ -1,4 +1,5 @@
import asyncio
import concurrent.futures
from threading import Thread
from typing import Callable, Optional
@@ -75,6 +76,13 @@ class AgentSession:
self.thread = Thread(target=self._run, daemon=True)
self.thread.start()
def coro_callback(task):
fut: concurrent.futures.Future = concurrent.futures.Future()
try:
fut.set_result(task.result())
except Exception as e:
logger.error(f'Error starting session: {e}')
coro = self._start(
runtime_name,
config,
@@ -85,7 +93,9 @@ class AgentSession:
agent_configs,
status_message_callback,
)
asyncio.run_coroutine_threadsafe(coro, self.loop) # type: ignore
asyncio.run_coroutine_threadsafe(coro, self.loop).add_done_callback(
coro_callback
) # type: ignore
async def _start(
self,
@@ -172,13 +182,17 @@ class AgentSession:
logger.info(f'Initializing runtime `{runtime_name}` now...')
runtime_cls = get_runtime_cls(runtime_name)
self.runtime = runtime_cls(
config=config,
event_stream=self.event_stream,
sid=self.sid,
plugins=agent.sandbox_plugins,
status_message_callback=status_message_callback,
)
try:
self.runtime = runtime_cls(
config=config,
event_stream=self.event_stream,
sid=self.sid,
plugins=agent.sandbox_plugins,
status_message_callback=status_message_callback,
)
except Exception as e:
logger.error(f'Runtime initialization failed: {e}')
raise
if self.runtime is not None:
logger.debug(

26
poetry.lock generated
View File

@@ -571,17 +571,17 @@ files = [
[[package]]
name = "boto3"
version = "1.35.29"
version = "1.35.30"
description = "The AWS SDK for Python"
optional = false
python-versions = ">=3.8"
files = [
{file = "boto3-1.35.29-py3-none-any.whl", hash = "sha256:2244044cdfa8ac345d7400536dc15a4824835e7ec5c55bc267e118af66bb27db"},
{file = "boto3-1.35.29.tar.gz", hash = "sha256:7bbb1ee649e09e956952285782cfdebd7e81fc78384f48dfab3d66c6eaf3f63f"},
{file = "boto3-1.35.30-py3-none-any.whl", hash = "sha256:d89c3459db89c5408e83219ab849ffd0146bc4285e75cdc67c6e45d390a12df2"},
{file = "boto3-1.35.30.tar.gz", hash = "sha256:d2851aec8e9dc6937977acbe9a5124ecc31b3ad5f50a10cd9ae52636da3f52fa"},
]
[package.dependencies]
botocore = ">=1.35.29,<1.36.0"
botocore = ">=1.35.30,<1.36.0"
jmespath = ">=0.7.1,<2.0.0"
s3transfer = ">=0.10.0,<0.11.0"
@@ -590,13 +590,13 @@ crt = ["botocore[crt] (>=1.21.0,<2.0a0)"]
[[package]]
name = "botocore"
version = "1.35.29"
version = "1.35.30"
description = "Low-level, data-driven core of boto 3."
optional = false
python-versions = ">=3.8"
files = [
{file = "botocore-1.35.29-py3-none-any.whl", hash = "sha256:f8e3ae0d84214eff3fb69cb4dc51cea6c43d3bde82027a94d00c52b941d6c3d5"},
{file = "botocore-1.35.29.tar.gz", hash = "sha256:4ed28ab03675bb008a290c452c5ddd7aaa5d4e3fa1912aadbdf93057ee84362b"},
{file = "botocore-1.35.30-py3-none-any.whl", hash = "sha256:3bb9f9dde001608671ea74681ac3cec06bbbb10cba8cb8c1387a25e843075ce0"},
{file = "botocore-1.35.30.tar.gz", hash = "sha256:ab5350e8a50e48d371fa2d517d65c29a40c43788cb9a15387f93eac5a23df0fd"},
]
[package.dependencies]
@@ -3762,13 +3762,13 @@ types-tqdm = "*"
[[package]]
name = "litellm"
version = "1.48.6"
version = "1.48.7"
description = "Library to easily interface with LLM API providers"
optional = false
python-versions = "!=2.7.*,!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,!=3.7.*,>=3.8"
files = [
{file = "litellm-1.48.6-py3-none-any.whl", hash = "sha256:7f6e0f787790d29c4464123bae92712ceb2dd1e05eef1ea90182663c4e4762a3"},
{file = "litellm-1.48.6.tar.gz", hash = "sha256:44584867d115ba0c1bb5f39efbc8a6131642e63d078e6a9cf2e7abe969d5edf6"},
{file = "litellm-1.48.7-py3-none-any.whl", hash = "sha256:4971a9e681188635c2ee6dc44fe35bb2774586e9018682adcccdbb516b839c64"},
{file = "litellm-1.48.7.tar.gz", hash = "sha256:ff1fef7049e9afa09598f98d1e510a6d5f252ec65c0526b8bfaf13eadfcf65e5"},
]
[package.dependencies]
@@ -8864,13 +8864,13 @@ zstd = ["zstandard (>=0.18.0)"]
[[package]]
name = "uvicorn"
version = "0.30.6"
version = "0.31.0"
description = "The lightning-fast ASGI server."
optional = false
python-versions = ">=3.8"
files = [
{file = "uvicorn-0.30.6-py3-none-any.whl", hash = "sha256:65fd46fe3fda5bdc1b03b94eb634923ff18cd35b2f084813ea79d1f103f711b5"},
{file = "uvicorn-0.30.6.tar.gz", hash = "sha256:4b15decdda1e72be08209e860a1e10e92439ad5b97cf44cc945fcbee66fc5788"},
{file = "uvicorn-0.31.0-py3-none-any.whl", hash = "sha256:cac7be4dd4d891c363cd942160a7b02e69150dcbc7a36be04d5f4af4b17c8ced"},
{file = "uvicorn-0.31.0.tar.gz", hash = "sha256:13bc21373d103859f68fe739608e2eb054a816dea79189bc3ca08ea89a275906"},
]
[package.dependencies]