diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
new file mode 100644
index 0000000..02544ae
--- /dev/null
+++ b/.github/workflows/ci.yml
@@ -0,0 +1,92 @@
+name: CI
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
+
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v4
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Install Poetry
+      uses: snok/install-poetry@v1
+      with:
+        version: latest
+        virtualenvs-create: true
+        virtualenvs-in-project: true
+
+    - name: Load cached venv
+      id: cached-poetry-dependencies
+      uses: actions/cache@v3
+      with:
+        path: .venv
+        key: venv-${{ runner.os }}-${{ matrix.python-version }}-${{ hashFiles('**/poetry.lock') }}
+
+    - name: Install dependencies
+      if: steps.cached-poetry-dependencies.outputs.cache-hit != 'true'
+      run: poetry install --no-interaction --no-root
+
+    - name: Install project
+      run: poetry install --no-interaction
+
+    - name: Run linting with ruff
+      run: |
+        poetry run ruff check .
+
+    - name: Run type checking with mypy
+      run: |
+        poetry run mypy src/
+
+    - name: Run unit tests
+      run: |
+        poetry run pytest test/ -v --ignore=test/test_openai_integration.py
+
+    - name: Run integration tests
+      if: github.event_name == 'push' && github.ref == 'refs/heads/main'
+      env:
+        OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+      run: |
+        poetry run pytest test/test_openai_integration.py -v -m integration
+
+  integration-test:
+    runs-on: ubuntu-latest
+    if: github.event_name == 'push' && github.ref == 'refs/heads/main'
+    needs: test
+
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Set up Python 3.11
+      uses: actions/setup-python@v4
+      with:
+        python-version: "3.11"
+
+    - name: Install Poetry
+      uses: snok/install-poetry@v1
+      with:
+        version: latest
+        virtualenvs-create: true
+        virtualenvs-in-project: true
+
+    - name: Install dependencies
+      run: |
+        poetry install --no-interaction
+
+    - name: Run OpenAI integration tests
+      env:
+        OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+      run: |
+        poetry run pytest test/test_openai_integration.py -v -m integration --tb=short
\ No newline at end of file
diff --git a/README.md b/README.md
index e28e865..0ab8066 100644
--- a/README.md
+++ b/README.md
@@ -77,13 +77,59 @@ This project includes the following development tools:
 ### Running Tests
 
 ```bash
-# Run all tests
+# Run all tests (excluding integration tests)
 poetry run pytest
 
 # Run tests with coverage
 poetry run pytest --cov=openhands_playground
+
+# Run only unit tests (excluding integration tests)
+poetry run pytest -m "not integration"
+
+# Run integration tests (requires OPENAI_API_KEY environment variable)
+poetry run pytest -m integration
+
+# Run all tests including integration tests
+poetry run pytest --run-integration
+```
+
+#### Integration Tests
+
+Integration tests require a real OpenAI API key and make actual API calls. These tests are marked with the `@pytest.mark.integration` decorator and are skipped by default unless:
+
+1. The `OPENAI_API_KEY` environment variable is set
+2. You explicitly run integration tests with `-m integration`
+
+To run integration tests locally:
+
+```bash
+# Set your OpenAI API key
+export OPENAI_API_KEY="your-api-key-here"
+
+# Run integration tests
+poetry run pytest -m integration
 ```
 
+**Note**: Integration tests will consume OpenAI API credits, so use them sparingly during development.
+
+#### GitHub Actions and Secrets
+
+This repository includes a GitHub Actions workflow (`.github/workflows/ci.yml`) that:
+
+1. Runs unit tests, linting, and type checking on every push and pull request
+2. Runs integration tests only on pushes to the main branch using GitHub secrets
+
+To set up the OpenAI API key as a GitHub secret:
+
+1. Go to your repository on GitHub
+2. Navigate to Settings → Secrets and variables → Actions
+3. Click "New repository secret"
+4. Name: `OPENAI_API_KEY`
+5. Value: Your OpenAI API key
+6. Click "Add secret"
+
+The integration tests will then run automatically when code is pushed to the main branch, using the secret API key without exposing it in logs or code.
+
 ### Code Quality
 
 ```bash
diff --git a/poetry.lock b/poetry.lock
index 757f264..68532d9 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -50,6 +50,18 @@ files = [
     {file = "certifi-2025.7.14.tar.gz", hash = "sha256:8ea99dbdfaaf2ba2f9bac77b9249ef62ec5218e7c2b2e903378ed5fccf765995"},
 ]
 
+[[package]]
+name = "cfgv"
+version = "3.4.0"
+description = "Validate configuration and produce human readable error messages."
+optional = false
+python-versions = ">=3.8"
+groups = ["dev"]
+files = [
+    {file = "cfgv-3.4.0-py2.py3-none-any.whl", hash = "sha256:b7265b1f29fd3316bfcd2b330d63d024f2bfd8bcb8b0272f8e19a504856c48f9"},
+    {file = "cfgv-3.4.0.tar.gz", hash = "sha256:e52591d4c5f5dead8e0f673fb16db7949d2cfb3f7da4582893288f0ded8fe560"},
+]
+
 [[package]]
 name = "colorama"
 version = "0.4.6"
@@ -63,6 +75,18 @@ files = [
 ]
 markers = {main = "platform_system == \"Windows\"", dev = "sys_platform == \"win32\""}
 
+[[package]]
+name = "distlib"
+version = "0.4.0"
+description = "Distribution utilities"
+optional = false
+python-versions = "*"
+groups = ["dev"]
+files = [
+    {file = "distlib-0.4.0-py2.py3-none-any.whl", hash = "sha256:9659f7d87e46584a30b5780e43ac7a2143098441670ff0a49d5f9034c54a6c16"},
+    {file = "distlib-0.4.0.tar.gz", hash = "sha256:feec40075be03a04501a973d81f633735b4b69f98b05450592310c0f401a4e0d"},
+]
+
 [[package]]
 name = "distro"
 version = "1.9.0"
@@ -94,6 +118,23 @@ typing-extensions = {version = ">=4.6.0", markers = "python_version < \"3.13\""}
 [package.extras]
 test = ["pytest (>=6)"]
 
+[[package]]
+name = "filelock"
+version = "3.16.1"
+description = "A platform independent file lock."
+optional = false
+python-versions = ">=3.8"
+groups = ["dev"]
+files = [
+    {file = "filelock-3.16.1-py3-none-any.whl", hash = "sha256:2082e5703d51fbf98ea75855d9d5527e33d8ff23099bec374a134febee6946b0"},
+    {file = "filelock-3.16.1.tar.gz", hash = "sha256:c249fbfcd5db47e5e2d6d62198e565475ee65e4831e2561c8e313fa7eb961435"},
+]
+
+[package.extras]
+docs = ["furo (>=2024.8.6)", "sphinx (>=8.0.2)", "sphinx-autodoc-typehints (>=2.4.1)"]
+testing = ["covdefaults (>=2.3)", "coverage (>=7.6.1)", "diff-cover (>=9.2)", "pytest (>=8.3.3)", "pytest-asyncio (>=0.24)", "pytest-cov (>=5)", "pytest-mock (>=3.14)", "pytest-timeout (>=2.3.1)", "virtualenv (>=20.26.4)"]
+typing = ["typing-extensions (>=4.12.2) ; python_version < \"3.11\""]
+
 [[package]]
 name = "h11"
 version = "0.16.0"
@@ -153,6 +194,21 @@ http2 = ["h2 (>=3,<5)"]
 socks = ["socksio (==1.*)"]
 zstd = ["zstandard (>=0.18.0)"]
 
+[[package]]
+name = "identify"
+version = "2.6.1"
+description = "File identification library for Python"
+optional = false
+python-versions = ">=3.8"
+groups = ["dev"]
+files = [
+    {file = "identify-2.6.1-py2.py3-none-any.whl", hash = "sha256:53863bcac7caf8d2ed85bd20312ea5dcfc22226800f6d6881f232d861db5a8f0"},
+    {file = "identify-2.6.1.tar.gz", hash = "sha256:91478c5fb7c3aac5ff7bf9b4344f803843dc586832d5f110d672b19aa1984c98"},
+]
+
+[package.extras]
+license = ["ukkonen"]
+
 [[package]]
 name = "idna"
 version = "3.10"
@@ -338,6 +394,18 @@ files = [
     {file = "mypy_extensions-1.1.0.tar.gz", hash = "sha256:52e68efc3284861e772bbcd66823fde5ae21fd2fdb51c62a211403730b916558"},
 ]
 
+[[package]]
+name = "nodeenv"
+version = "1.9.1"
+description = "Node.js virtual environment builder"
+optional = false
+python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7"
+groups = ["dev"]
+files = [
+    {file = "nodeenv-1.9.1-py2.py3-none-any.whl", hash = "sha256:ba11c9782d29c27c70ffbdda2d7415098754709be8a7056d79a737cd901155c9"},
+    {file = "nodeenv-1.9.1.tar.gz", hash = "sha256:6ec12890a2dab7946721edbfbcd91f3319c6ccc9aec47be7c7e6b7011ee6645f"},
+]
+
 [[package]]
 name = "openai"
 version = "1.97.1"
@@ -378,6 +446,23 @@ files = [
     {file = "packaging-25.0.tar.gz", hash = "sha256:d443872c98d677bf60f6a1f2f8c1cb748e8fe762d2bf9d3148b5599295b0fc4f"},
 ]
 
+[[package]]
+name = "platformdirs"
+version = "4.3.6"
+description = "A small Python package for determining appropriate platform-specific dirs, e.g. a `user data dir`."
+optional = false
+python-versions = ">=3.8"
+groups = ["dev"]
+files = [
+    {file = "platformdirs-4.3.6-py3-none-any.whl", hash = "sha256:73e575e1408ab8103900836b97580d5307456908a03e92031bab39e4554cc3fb"},
+    {file = "platformdirs-4.3.6.tar.gz", hash = "sha256:357fb2acbc885b0419afd3ce3ed34564c13c9b95c89360cd9563f73aa5e2b907"},
+]
+
+[package.extras]
+docs = ["furo (>=2024.8.6)", "proselint (>=0.14)", "sphinx (>=8.0.2)", "sphinx-autodoc-typehints (>=2.4)"]
+test = ["appdirs (==1.4.4)", "covdefaults (>=2.3)", "pytest (>=8.3.2)", "pytest-cov (>=5)", "pytest-mock (>=3.14)"]
+type = ["mypy (>=1.11.2)"]
+
 [[package]]
 name = "pluggy"
 version = "1.5.0"
@@ -394,6 +479,25 @@ files = [
 dev = ["pre-commit", "tox"]
 testing = ["pytest", "pytest-benchmark"]
 
+[[package]]
+name = "pre-commit"
+version = "3.5.0"
+description = "A framework for managing and maintaining multi-language pre-commit hooks."
+optional = false
+python-versions = ">=3.8"
+groups = ["dev"]
+files = [
+    {file = "pre_commit-3.5.0-py2.py3-none-any.whl", hash = "sha256:841dc9aef25daba9a0238cd27984041fa0467b4199fc4852e27950664919f660"},
+    {file = "pre_commit-3.5.0.tar.gz", hash = "sha256:5804465c675b659b0862f07907f96295d490822a450c4c40e747d0b1c6ebcb32"},
+]
+
+[package.dependencies]
+cfgv = ">=2.0.0"
+identify = ">=1.0.0"
+nodeenv = ">=0.11.1"
+pyyaml = ">=5.1"
+virtualenv = ">=20.10.0"
+
 [[package]]
 name = "pydantic"
 version = "2.10.6"
@@ -566,6 +670,69 @@ files = [
 [package.extras]
 cli = ["click (>=5.0)"]
 
+[[package]]
+name = "pyyaml"
+version = "6.0.2"
+description = "YAML parser and emitter for Python"
+optional = false
+python-versions = ">=3.8"
+groups = ["dev"]
+files = [
+    {file = "PyYAML-6.0.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:0a9a2848a5b7feac301353437eb7d5957887edbf81d56e903999a75a3d743086"},
+    {file = "PyYAML-6.0.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:29717114e51c84ddfba879543fb232a6ed60086602313ca38cce623c1d62cfbf"},
+    {file = "PyYAML-6.0.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8824b5a04a04a047e72eea5cec3bc266db09e35de6bdfe34c9436ac5ee27d237"},
+    {file = "PyYAML-6.0.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:7c36280e6fb8385e520936c3cb3b8042851904eba0e58d277dca80a5cfed590b"},
+    {file = "PyYAML-6.0.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ec031d5d2feb36d1d1a24380e4db6d43695f3748343d99434e6f5f9156aaa2ed"},
+    {file = "PyYAML-6.0.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:936d68689298c36b53b29f23c6dbb74de12b4ac12ca6cfe0e047bedceea56180"},
+    {file = "PyYAML-6.0.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:23502f431948090f597378482b4812b0caae32c22213aecf3b55325e049a6c68"},
+    {file = "PyYAML-6.0.2-cp310-cp310-win32.whl", hash = "sha256:2e99c6826ffa974fe6e27cdb5ed0021786b03fc98e5ee3c5bfe1fd5015f42b99"},
+    {file = "PyYAML-6.0.2-cp310-cp310-win_amd64.whl", hash = "sha256:a4d3091415f010369ae4ed1fc6b79def9416358877534caf6a0fdd2146c87a3e"},
+    {file = "PyYAML-6.0.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:cc1c1159b3d456576af7a3e4d1ba7e6924cb39de8f67111c735f6fc832082774"},
+    {file = "PyYAML-6.0.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:1e2120ef853f59c7419231f3bf4e7021f1b936f6ebd222406c3b60212205d2ee"},
+    {file = "PyYAML-6.0.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5d225db5a45f21e78dd9358e58a98702a0302f2659a3c6cd320564b75b86f47c"},
+    {file = "PyYAML-6.0.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5ac9328ec4831237bec75defaf839f7d4564be1e6b25ac710bd1a96321cc8317"},
+    {file = "PyYAML-6.0.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3ad2a3decf9aaba3d29c8f537ac4b243e36bef957511b4766cb0057d32b0be85"},
+    {file = "PyYAML-6.0.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:ff3824dc5261f50c9b0dfb3be22b4567a6f938ccce4587b38952d85fd9e9afe4"},
+    {file = "PyYAML-6.0.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:797b4f722ffa07cc8d62053e4cff1486fa6dc094105d13fea7b1de7d8bf71c9e"},
+    {file = "PyYAML-6.0.2-cp311-cp311-win32.whl", hash = "sha256:11d8f3dd2b9c1207dcaf2ee0bbbfd5991f571186ec9cc78427ba5bd32afae4b5"},
+    {file = "PyYAML-6.0.2-cp311-cp311-win_amd64.whl", hash = "sha256:e10ce637b18caea04431ce14fabcf5c64a1c61ec9c56b071a4b7ca131ca52d44"},
+    {file = "PyYAML-6.0.2-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:c70c95198c015b85feafc136515252a261a84561b7b1d51e3384e0655ddf25ab"},
+    {file = "PyYAML-6.0.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:ce826d6ef20b1bc864f0a68340c8b3287705cae2f8b4b1d932177dcc76721725"},
+    {file = "PyYAML-6.0.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1f71ea527786de97d1a0cc0eacd1defc0985dcf6b3f17bb77dcfc8c34bec4dc5"},
+    {file = "PyYAML-6.0.2-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9b22676e8097e9e22e36d6b7bda33190d0d400f345f23d4065d48f4ca7ae0425"},
+    {file = "PyYAML-6.0.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:80bab7bfc629882493af4aa31a4cfa43a4c57c83813253626916b8c7ada83476"},
+    {file = "PyYAML-6.0.2-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:0833f8694549e586547b576dcfaba4a6b55b9e96098b36cdc7ebefe667dfed48"},
+    {file = "PyYAML-6.0.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8b9c7197f7cb2738065c481a0461e50ad02f18c78cd75775628afb4d7137fb3b"},
+    {file = "PyYAML-6.0.2-cp312-cp312-win32.whl", hash = "sha256:ef6107725bd54b262d6dedcc2af448a266975032bc85ef0172c5f059da6325b4"},
+    {file = "PyYAML-6.0.2-cp312-cp312-win_amd64.whl", hash = "sha256:7e7401d0de89a9a855c839bc697c079a4af81cf878373abd7dc625847d25cbd8"},
+    {file = "PyYAML-6.0.2-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:efdca5630322a10774e8e98e1af481aad470dd62c3170801852d752aa7a783ba"},
+    {file = "PyYAML-6.0.2-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:50187695423ffe49e2deacb8cd10510bc361faac997de9efef88badc3bb9e2d1"},
+    {file = "PyYAML-6.0.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0ffe8360bab4910ef1b9e87fb812d8bc0a308b0d0eef8c8f44e0254ab3b07133"},
+    {file = "PyYAML-6.0.2-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:17e311b6c678207928d649faa7cb0d7b4c26a0ba73d41e99c4fff6b6c3276484"},
+    {file = "PyYAML-6.0.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:70b189594dbe54f75ab3a1acec5f1e3faa7e8cf2f1e08d9b561cb41b845f69d5"},
+    {file = "PyYAML-6.0.2-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:41e4e3953a79407c794916fa277a82531dd93aad34e29c2a514c2c0c5fe971cc"},
+    {file = "PyYAML-6.0.2-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:68ccc6023a3400877818152ad9a1033e3db8625d899c72eacb5a668902e4d652"},
+    {file = "PyYAML-6.0.2-cp313-cp313-win32.whl", hash = "sha256:bc2fa7c6b47d6bc618dd7fb02ef6fdedb1090ec036abab80d4681424b84c1183"},
+    {file = "PyYAML-6.0.2-cp313-cp313-win_amd64.whl", hash = "sha256:8388ee1976c416731879ac16da0aff3f63b286ffdd57cdeb95f3f2e085687563"},
+    {file = "PyYAML-6.0.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:24471b829b3bf607e04e88d79542a9d48bb037c2267d7927a874e6c205ca7e9a"},
+    {file = "PyYAML-6.0.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d7fded462629cfa4b685c5416b949ebad6cec74af5e2d42905d41e257e0869f5"},
+    {file = "PyYAML-6.0.2-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d84a1718ee396f54f3a086ea0a66d8e552b2ab2017ef8b420e92edbc841c352d"},
+    {file = "PyYAML-6.0.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9056c1ecd25795207ad294bcf39f2db3d845767be0ea6e6a34d856f006006083"},
+    {file = "PyYAML-6.0.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:82d09873e40955485746739bcb8b4586983670466c23382c19cffecbf1fd8706"},
+    {file = "PyYAML-6.0.2-cp38-cp38-win32.whl", hash = "sha256:43fa96a3ca0d6b1812e01ced1044a003533c47f6ee8aca31724f78e93ccc089a"},
+    {file = "PyYAML-6.0.2-cp38-cp38-win_amd64.whl", hash = "sha256:01179a4a8559ab5de078078f37e5c1a30d76bb88519906844fd7bdea1b7729ff"},
+    {file = "PyYAML-6.0.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:688ba32a1cffef67fd2e9398a2efebaea461578b0923624778664cc1c914db5d"},
+    {file = "PyYAML-6.0.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:a8786accb172bd8afb8be14490a16625cbc387036876ab6ba70912730faf8e1f"},
+    {file = "PyYAML-6.0.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d8e03406cac8513435335dbab54c0d385e4a49e4945d2909a581c83647ca0290"},
+    {file = "PyYAML-6.0.2-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f753120cb8181e736c57ef7636e83f31b9c0d1722c516f7e86cf15b7aa57ff12"},
+    {file = "PyYAML-6.0.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3b1fdb9dc17f5a7677423d508ab4f243a726dea51fa5e70992e59a7411c89d19"},
+    {file = "PyYAML-6.0.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:0b69e4ce7a131fe56b7e4d770c67429700908fc0752af059838b1cfb41960e4e"},
+    {file = "PyYAML-6.0.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:a9f8c2e67970f13b16084e04f134610fd1d374bf477b17ec1599185cf611d725"},
+    {file = "PyYAML-6.0.2-cp39-cp39-win32.whl", hash = "sha256:6395c297d42274772abc367baaa79683958044e5d3835486c16da75d2a694631"},
+    {file = "PyYAML-6.0.2-cp39-cp39-win_amd64.whl", hash = "sha256:39693e1f8320ae4f43943590b49779ffb98acb81f788220ea932a6b6c51004d8"},
+    {file = "pyyaml-6.0.2.tar.gz", hash = "sha256:d584d9ec91ad65861cc08d42e834324ef890a082e591037abe114850ff7bbc3e"},
+]
+
 [[package]]
 name = "ruff"
 version = "0.1.15"
@@ -682,7 +849,28 @@ files = [
     {file = "typing_extensions-4.13.2.tar.gz", hash = "sha256:e6c81219bd689f51865d9e372991c540bda33a0379d5573cddb9a3a23f7caaef"},
 ]
 
+[[package]]
+name = "virtualenv"
+version = "20.32.0"
+description = "Virtual Python Environment builder"
+optional = false
+python-versions = ">=3.8"
+groups = ["dev"]
+files = [
+    {file = "virtualenv-20.32.0-py3-none-any.whl", hash = "sha256:2c310aecb62e5aa1b06103ed7c2977b81e042695de2697d01017ff0f1034af56"},
+    {file = "virtualenv-20.32.0.tar.gz", hash = "sha256:886bf75cadfdc964674e6e33eb74d787dff31ca314ceace03ca5810620f4ecf0"},
+]
+
+[package.dependencies]
+distlib = ">=0.3.7,<1"
+filelock = ">=3.12.2,<4"
+platformdirs = ">=3.9.1,<5"
+
+[package.extras]
+docs = ["furo (>=2023.7.26)", "proselint (>=0.13)", "sphinx (>=7.1.2,!=7.3)", "sphinx-argparse (>=0.4)", "sphinxcontrib-towncrier (>=0.2.1a0)", "towncrier (>=23.6)"]
+test = ["covdefaults (>=2.3)", "coverage (>=7.2.7)", "coverage-enable-subprocess (>=1)", "flaky (>=3.7)", "packaging (>=23.1)", "pytest (>=7.4)", "pytest-env (>=0.8.2)", "pytest-freezer (>=0.4.8) ; platform_python_implementation == \"PyPy\" or platform_python_implementation == \"GraalVM\" or platform_python_implementation == \"CPython\" and sys_platform == \"win32\" and python_version >= \"3.13\"", "pytest-mock (>=3.11.1)", "pytest-randomly (>=3.12)", "pytest-timeout (>=2.1)", "setuptools (>=68)", "time-machine (>=2.10) ; platform_python_implementation == \"CPython\""]
+
 [metadata]
 lock-version = "2.1"
 python-versions = "^3.8"
-content-hash = "ba784f0dc36a60b00f5c16fa49b09c4678f5ee1df5b63b4b1e5746b1fb757e29"
+content-hash = "ec641242d0fb096807a42e3ae2fef004bff93537eb083ff71e558e08947a7721"
diff --git a/pyproject.toml b/pyproject.toml
index f0f8032..696d1ce 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -107,3 +107,6 @@ python_files = ["test_*.py"]
 python_classes = ["Test*"]
 python_functions = ["test_*"]
 addopts = "-v --tb=short"
+markers = [
+    "integration: marks tests as integration tests that require external services (deselect with '-m \"not integration\"')",
+]
diff --git a/test/test_openai_integration.py b/test/test_openai_integration.py
new file mode 100644
index 0000000..bf55700
--- /dev/null
+++ b/test/test_openai_integration.py
@@ -0,0 +1,116 @@
+"""Integration tests for OpenAI LLM that require a real API key."""
+
+import os
+import pytest
+from openhands_playground.llm import LLMFactory
+from openhands_playground.llm.llms import OpenAILLM
+
+
+@pytest.mark.integration
+@pytest.mark.skipif(
+    not os.getenv("OPENAI_API_KEY"),
+    reason="OPENAI_API_KEY environment variable not set"
+)
+class TestOpenAIIntegration:
+    """Integration tests for OpenAI LLM using real API calls."""
+
+    def test_openai_llm_generate_integration(self):
+        """Test OpenAI LLM text generation with real API."""
+        llm = OpenAILLM(model_name="gpt-3.5-turbo")
+        
+        # Test simple generation
+        response = llm.generate(
+            "Say 'Hello, World!' and nothing else.",
+            max_tokens=10,
+            temperature=0.0
+        )
+        
+        assert isinstance(response, str)
+        assert len(response) > 0
+        assert "Hello" in response
+
+    def test_openai_llm_chat_integration(self):
+        """Test OpenAI LLM chat functionality with real API."""
+        llm = OpenAILLM(model_name="gpt-3.5-turbo")
+        
+        messages = [
+            {"role": "user", "content": "What is 2+2? Answer with just the number."}
+        ]
+        
+        response = llm.chat(
+            messages,
+            max_tokens=5,
+            temperature=0.0
+        )
+        
+        assert isinstance(response, str)
+        assert len(response) > 0
+        assert "4" in response
+
+    def test_openai_llm_factory_integration(self):
+        """Test creating OpenAI LLM through factory with real API."""
+        llm = LLMFactory.create_openai_llm(model_name="gpt-3.5-turbo")
+        
+        response = llm.generate(
+            "Respond with exactly: 'Factory test successful'",
+            max_tokens=10,
+            temperature=0.0
+        )
+        
+        assert isinstance(response, str)
+        assert len(response) > 0
+
+    def test_openai_llm_different_models_integration(self):
+        """Test OpenAI LLM with different models if available."""
+        # Test with gpt-3.5-turbo (should always be available)
+        llm = OpenAILLM(model_name="gpt-3.5-turbo")
+        
+        response = llm.generate(
+            "Say 'Model test' and nothing else.",
+            max_tokens=5,
+            temperature=0.0
+        )
+        
+        assert isinstance(response, str)
+        assert len(response) > 0
+
+    def test_openai_llm_temperature_effects_integration(self):
+        """Test that temperature parameter affects responses."""
+        llm = OpenAILLM(model_name="gpt-3.5-turbo")
+        
+        # Test with low temperature (more deterministic)
+        response_low = llm.generate(
+            "Complete this sentence: 'The sky is'",
+            max_tokens=5,
+            temperature=0.0
+        )
+        
+        # Test with higher temperature (more creative)
+        response_high = llm.generate(
+            "Complete this sentence: 'The sky is'",
+            max_tokens=5,
+            temperature=1.0
+        )
+        
+        assert isinstance(response_low, str)
+        assert isinstance(response_high, str)
+        assert len(response_low) > 0
+        assert len(response_high) > 0
+        # Note: We can't assert they're different since even with high temperature
+        # the responses might be the same for such a simple prompt
+
+    def test_openai_llm_max_tokens_integration(self):
+        """Test that max_tokens parameter limits response length."""
+        llm = OpenAILLM(model_name="gpt-3.5-turbo")
+        
+        # Test with very low max_tokens
+        response = llm.generate(
+            "Write a long story about a dragon.",
+            max_tokens=3,
+            temperature=0.0
+        )
+        
+        assert isinstance(response, str)
+        assert len(response) > 0
+        # With max_tokens=3, the response should be quite short
+        assert len(response.split()) <= 10  # Allow some flexibility for tokenization
\ No newline at end of file