chore(deps): bump browsergym from 0.3.4 to 0.4.3 (#3762)

* chore(deps): bump browsergym from 0.3.4 to 0.4.3

Bumps browsergym from 0.3.4 to 0.4.3.

---
updated-dependencies:
- dependency-name: browsergym
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>

* integration tests updated to browsergym

---------

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Engel Nyst <enyst@users.noreply.github.com>

poetry.lock

@@ -609,31 +609,32 @@ crt = ["awscrt (==0.21.2)"]
 
 [[package]]
 name = "browsergym"
-version = "0.3.4"
+version = "0.4.3"
 description = "BrowserGym: a gym environment for web task automation in the Chromium browser"
 optional = false
 python-versions = ">3.7"
 files = [
-    {file = "browsergym-0.3.4-py3-none-any.whl", hash = "sha256:ecc06a42a6b7541f9025fa9cdc208d48eb4a745283358524715447257fc80adc"},
-    {file = "browsergym-0.3.4.tar.gz", hash = "sha256:853937f29c3855577a5fbc038a4371e82e50e393f4bdfc458df222590470807c"},
+    {file = "browsergym-0.4.3-py3-none-any.whl", hash = "sha256:876bf47ac897041eba4a78089b854d77cbe104d929093ebecf9d2a8fb8f93003"},
+    {file = "browsergym-0.4.3.tar.gz", hash = "sha256:b70385fa83d31c6f3f9140fcb20cdca31ae43bd860eeed87468e5d11650e084c"},
 ]
 
 [package.dependencies]
-browsergym-core = "0.3.4"
-browsergym-experiments = "0.3.4"
-browsergym-miniwob = "0.3.4"
-browsergym-webarena = "0.3.4"
+browsergym-core = "0.4.3"
+browsergym-experiments = "0.4.3"
+browsergym-miniwob = "0.4.3"
+browsergym-visualwebarena = "0.4.3"
+browsergym-webarena = "0.4.3"
 browsergym-workarena = "*"
 
 [[package]]
 name = "browsergym-core"
-version = "0.3.4"
+version = "0.4.3"
 description = "BrowserGym: a gym environment for web task automation in the Chromium browser"
 optional = false
-python-versions = ">3.7"
+python-versions = ">3.9"
 files = [
-    {file = "browsergym_core-0.3.4-py3-none-any.whl", hash = "sha256:1d7164b9afab613af6ae269fb811721738b09d5935df567cceba87dd1ecb4f23"},
-    {file = "browsergym_core-0.3.4.tar.gz", hash = "sha256:357d4cc61f2447983f9c5c0c262d5d6cca129e926ab576ec72f6b974bd1f7fd6"},
+    {file = "browsergym_core-0.4.3-py3-none-any.whl", hash = "sha256:62d83f51fe1f656336bfd59b351cf2e23e120d5948eae9f7d1a6737813360040"},
+    {file = "browsergym_core-0.4.3.tar.gz", hash = "sha256:1028506d8d92e933aadddbf71934cec44c5c2a3d7e1d168006d38555e6a63c5e"},
 ]
 
 [package.dependencies]
@@ -647,46 +648,62 @@ pyparsing = ">=3"
 
 [[package]]
 name = "browsergym-experiments"
-version = "0.3.4"
+version = "0.4.3"
 description = "Experimentation tools for BrowserGym"
 optional = false
 python-versions = ">3.7"
 files = [
-    {file = "browsergym_experiments-0.3.4-py3-none-any.whl", hash = "sha256:d2e4a75b4a2e79f9300eb289c9b2432f07dee82622d384924972f4157069f3fe"},
-    {file = "browsergym_experiments-0.3.4.tar.gz", hash = "sha256:16309c6b2be59627ea90c7e36448eb897512bcef033cf481472879f4c5be317b"},
+    {file = "browsergym_experiments-0.4.3-py3-none-any.whl", hash = "sha256:235f99cfd64e2ef959ed3a7e218516359e2d2b51bde87ad1ff749b8e71bad278"},
+    {file = "browsergym_experiments-0.4.3.tar.gz", hash = "sha256:bfd6104287c86d22124fd0fc9e4a8ab8ee2c29f58463ee8c4410a1207bda451c"},
 ]
 
 [package.dependencies]
-browsergym-core = "0.3.4"
+browsergym-core = "0.4.3"
 tiktoken = ">=0.4"
 
 [[package]]
 name = "browsergym-miniwob"
-version = "0.3.4"
+version = "0.4.3"
 description = "MiniWoB++ benchmark for BrowserGym"
 optional = false
 python-versions = ">3.7"
 files = [
-    {file = "browsergym_miniwob-0.3.4-py3-none-any.whl", hash = "sha256:4de41ee146d6f0bcb2e49b0fb8fd49f519439bf44808aef6146f5ae00064062b"},
-    {file = "browsergym_miniwob-0.3.4.tar.gz", hash = "sha256:938d58a9882c4118e46160d303a9a6d93ac1a08288e81e2c6d5c768719f012fe"},
+    {file = "browsergym_miniwob-0.4.3-py3-none-any.whl", hash = "sha256:d81fe18c78f889059282d19c338f707ee79d652b0eb83d39994a44524ee2de76"},
+    {file = "browsergym_miniwob-0.4.3.tar.gz", hash = "sha256:6be98d4ef602d43488f6080820a5277d96960de221afc91950a6b7810692db87"},
+]
+
+[package.dependencies]
+browsergym-core = "0.4.3"
+
+[[package]]
+name = "browsergym-visualwebarena"
+version = "0.4.3"
+description = "VisualWebArena benchmark for BrowserGym"
+optional = false
+python-versions = ">3.7"
+files = [
+    {file = "browsergym_visualwebarena-0.4.3-py3-none-any.whl", hash = "sha256:e80775eaa0b42cbcacf42a9913b5603b9e33d53b1dd039f3d134019e4bf0da46"},
+    {file = "browsergym_visualwebarena-0.4.3.tar.gz", hash = "sha256:c422ead2f404f03597af5b6214ee9d31fc8b5e195598a3b0625819e224ccf0e1"},
 ]
 
 [package.dependencies]
-browsergym-core = "0.3.4"
+browsergym-core = "0.4.3"
+libvisualwebarena = "0.0.7"
+requests = "*"
 
 [[package]]
 name = "browsergym-webarena"
-version = "0.3.4"
+version = "0.4.3"
 description = "WebArena benchmark for BrowserGym"
 optional = false
 python-versions = ">3.7"
 files = [
-    {file = "browsergym_webarena-0.3.4-py3-none-any.whl", hash = "sha256:fd9f9bb4cdf1e32d22e6cd525fd0c28adf9dda615e4dc614b677c25f675a9b73"},
-    {file = "browsergym_webarena-0.3.4.tar.gz", hash = "sha256:ba921a76223910d8842d0c9dd6d3393db14819f9a74c477289f0d2625bdd8feb"},
+    {file = "browsergym_webarena-0.4.3-py3-none-any.whl", hash = "sha256:fe180c96f38205428422ee60067cc1c8fd6d06b7482fb457f7a73138b197ed96"},
+    {file = "browsergym_webarena-0.4.3.tar.gz", hash = "sha256:7b235b7a41d163573a1a5075a43e7ecf39823e513bf38de28e5454c91181d2ee"},
 ]
 
 [package.dependencies]
-browsergym-core = "0.3.4"
+browsergym-core = "0.4.3"
 libwebarena = "0.0.3"
 
 [[package]]
@@ -2907,6 +2924,39 @@ files = [
     {file = "idna-3.7.tar.gz", hash = "sha256:028ff3aadf0609c1fd278d8ea3089299412a7a8b9bd005dd08b9f8285bcb5cfc"},
 ]
 
+[[package]]
+name = "imageio"
+version = "2.35.1"
+description = "Library for reading and writing a wide range of image, video, scientific, and volumetric data formats."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "imageio-2.35.1-py3-none-any.whl", hash = "sha256:6eb2e5244e7a16b85c10b5c2fe0f7bf961b40fcb9f1a9fd1bd1d2c2f8fb3cd65"},
+    {file = "imageio-2.35.1.tar.gz", hash = "sha256:4952dfeef3c3947957f6d5dedb1f4ca31c6e509a476891062396834048aeed2a"},
+]
+
+[package.dependencies]
+numpy = "*"
+pillow = ">=8.3.2"
+
+[package.extras]
+all-plugins = ["astropy", "av", "imageio-ffmpeg", "psutil", "tifffile"]
+all-plugins-pypy = ["av", "imageio-ffmpeg", "psutil", "tifffile"]
+build = ["wheel"]
+dev = ["black", "flake8", "fsspec[github]", "pytest", "pytest-cov"]
+docs = ["numpydoc", "pydata-sphinx-theme", "sphinx (<6)"]
+ffmpeg = ["imageio-ffmpeg", "psutil"]
+fits = ["astropy"]
+full = ["astropy", "av", "black", "flake8", "fsspec[github]", "gdal", "imageio-ffmpeg", "itk", "numpy (>2)", "numpydoc", "pillow-heif", "psutil", "pydata-sphinx-theme", "pytest", "pytest-cov", "rawpy", "sphinx (<6)", "tifffile", "wheel"]
+gdal = ["gdal"]
+itk = ["itk"]
+linting = ["black", "flake8"]
+pillow-heif = ["pillow-heif"]
+pyav = ["av"]
+rawpy = ["numpy (>2)", "rawpy"]
+test = ["fsspec[github]", "pytest", "pytest-cov"]
+tifffile = ["tifffile"]
+
 [[package]]
 name = "importlib-metadata"
 version = "8.0.0"
@@ -3635,6 +3685,52 @@ websocket-client = ">=0.32.0,<0.40.0 || >0.40.0,<0.41.dev0 || >=0.43.dev0"
 [package.extras]
 adal = ["adal (>=1.0.2)"]
 
+[[package]]
+name = "lazy-loader"
+version = "0.4"
+description = "Makes it easy to load subpackages and functions on demand."
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "lazy_loader-0.4-py3-none-any.whl", hash = "sha256:342aa8e14d543a154047afb4ba8ef17f5563baad3fc610d7b15b213b0f119efc"},
+    {file = "lazy_loader-0.4.tar.gz", hash = "sha256:47c75182589b91a4e1a85a136c074285a5ad4d9f39c63e0d7fb76391c4574cd1"},
+]
+
+[package.dependencies]
+packaging = "*"
+
+[package.extras]
+dev = ["changelist (==0.5)"]
+lint = ["pre-commit (==3.7.0)"]
+test = ["pytest (>=7.4)", "pytest-cov (>=4.1)"]
+
+[[package]]
+name = "libvisualwebarena"
+version = "0.0.7"
+description = "This is an unofficial, use-at-your-own risks port of the visualwebarena benchmark, for use as a standalone library package."
+optional = false
+python-versions = "<4,>=3.7"
+files = [
+    {file = "libvisualwebarena-0.0.7-py3-none-any.whl", hash = "sha256:20879c936c22e8c8f541b1d6422f84987a4367a8adb8b1cc54252ef816618006"},
+    {file = "libvisualwebarena-0.0.7.tar.gz", hash = "sha256:1f0b3dd90fa9445fb30ddab20df725c2c7461e7cf8d8fd06a5f6a6365f8dd7b9"},
+]
+
+[package.dependencies]
+aiolimiter = "*"
+beartype = "0.12.0"
+evaluate = "*"
+flask = "*"
+gymnasium = "*"
+nltk = "*"
+openai = ">=1"
+Pillow = "*"
+playwright = ">=1.32,<1.40"
+scikit-image = ">=0.16"
+text-generation = "*"
+tiktoken = "*"
+transformers = "*"
+types-tqdm = "*"
+
 [[package]]
 name = "libwebarena"
 version = "0.0.3"
@@ -7459,6 +7555,54 @@ files = [
 attrs = ">=18.0.0"
 pathspec = ">=0.10.1"
 
+[[package]]
+name = "scikit-image"
+version = "0.24.0"
+description = "Image processing in Python"
+optional = false
+python-versions = ">=3.9"
+files = [
+    {file = "scikit_image-0.24.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:cb3bc0264b6ab30b43c4179ee6156bc18b4861e78bb329dd8d16537b7bbf827a"},
+    {file = "scikit_image-0.24.0-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:9c7a52e20cdd760738da38564ba1fed7942b623c0317489af1a598a8dedf088b"},
+    {file = "scikit_image-0.24.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:93f46e6ce42e5409f4d09ce1b0c7f80dd7e4373bcec635b6348b63e3c886eac8"},
+    {file = "scikit_image-0.24.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:39ee0af13435c57351a3397eb379e72164ff85161923eec0c38849fecf1b4764"},
+    {file = "scikit_image-0.24.0-cp310-cp310-win_amd64.whl", hash = "sha256:7ac7913b028b8aa780ffae85922894a69e33d1c0bf270ea1774f382fe8bf95e7"},
+    {file = "scikit_image-0.24.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:272909e02a59cea3ed4aa03739bb88df2625daa809f633f40b5053cf09241831"},
+    {file = "scikit_image-0.24.0-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:190ebde80b4470fe8838764b9b15f232a964f1a20391663e31008d76f0c696f7"},
+    {file = "scikit_image-0.24.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:59c98cc695005faf2b79904e4663796c977af22586ddf1b12d6af2fa22842dc2"},
+    {file = "scikit_image-0.24.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fa27b3a0dbad807b966b8db2d78da734cb812ca4787f7fbb143764800ce2fa9c"},
+    {file = "scikit_image-0.24.0-cp311-cp311-win_amd64.whl", hash = "sha256:dacf591ac0c272a111181afad4b788a27fe70d213cfddd631d151cbc34f8ca2c"},
+    {file = "scikit_image-0.24.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:6fccceb54c9574590abcddc8caf6cefa57c13b5b8b4260ab3ff88ad8f3c252b3"},
+    {file = "scikit_image-0.24.0-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:ccc01e4760d655aab7601c1ba7aa4ddd8b46f494ac46ec9c268df6f33ccddf4c"},
+    {file = "scikit_image-0.24.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:18836a18d3a7b6aca5376a2d805f0045826bc6c9fc85331659c33b4813e0b563"},
+    {file = "scikit_image-0.24.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8579bda9c3f78cb3b3ed8b9425213c53a25fa7e994b7ac01f2440b395babf660"},
+    {file = "scikit_image-0.24.0-cp312-cp312-win_amd64.whl", hash = "sha256:82ab903afa60b2da1da2e6f0c8c65e7c8868c60a869464c41971da929b3e82bc"},
+    {file = "scikit_image-0.24.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:ef04360eda372ee5cd60aebe9be91258639c86ae2ea24093fb9182118008d009"},
+    {file = "scikit_image-0.24.0-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:e9aadb442360a7e76f0c5c9d105f79a83d6df0e01e431bd1d5757e2c5871a1f3"},
+    {file = "scikit_image-0.24.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5e37de6f4c1abcf794e13c258dc9b7d385d5be868441de11c180363824192ff7"},
+    {file = "scikit_image-0.24.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4688c18bd7ec33c08d7bf0fd19549be246d90d5f2c1d795a89986629af0a1e83"},
+    {file = "scikit_image-0.24.0-cp39-cp39-win_amd64.whl", hash = "sha256:56dab751d20b25d5d3985e95c9b4e975f55573554bd76b0aedf5875217c93e69"},
+    {file = "scikit_image-0.24.0.tar.gz", hash = "sha256:5d16efe95da8edbeb363e0c4157b99becbd650a60b77f6e3af5768b66cf007ab"},
+]
+
+[package.dependencies]
+imageio = ">=2.33"
+lazy-loader = ">=0.4"
+networkx = ">=2.8"
+numpy = ">=1.23"
+packaging = ">=21"
+pillow = ">=9.1"
+scipy = ">=1.9"
+tifffile = ">=2022.8.12"
+
+[package.extras]
+build = ["Cython (>=3.0.4)", "build", "meson-python (>=0.15)", "ninja", "numpy (>=2.0.0rc1)", "packaging (>=21)", "pythran", "setuptools (>=67)", "spin (==0.8)", "wheel"]
+data = ["pooch (>=1.6.0)"]
+developer = ["ipython", "pre-commit", "tomli"]
+docs = ["PyWavelets (>=1.1.1)", "dask[array] (>=2022.9.2)", "ipykernel", "ipywidgets", "kaleido", "matplotlib (>=3.6)", "myst-parser", "numpydoc (>=1.7)", "pandas (>=1.5)", "plotly (>=5.10)", "pooch (>=1.6)", "pydata-sphinx-theme (>=0.15.2)", "pytest-doctestplus", "pytest-runner", "scikit-learn (>=1.1)", "seaborn (>=0.11)", "sphinx (>=7.3)", "sphinx-copybutton", "sphinx-gallery (>=0.14)", "sphinx_design (>=0.5)", "tifffile (>=2022.8.12)"]
+optional = ["PyWavelets (>=1.1.1)", "SimpleITK", "astropy (>=5.0)", "cloudpickle (>=0.2.1)", "dask[array] (>=2021.1.0)", "matplotlib (>=3.6)", "pooch (>=1.6.0)", "pyamg", "scikit-learn (>=1.1)"]
+test = ["asv", "numpydoc (>=1.7)", "pooch (>=1.6.0)", "pytest (>=7.0)", "pytest-cov (>=2.11.0)", "pytest-doctestplus", "pytest-faulthandler", "pytest-localserver"]
+
 [[package]]
 name = "scikit-learn"
 version = "1.5.1"
@@ -8040,6 +8184,28 @@ files = [
     {file = "threadpoolctl-3.5.0.tar.gz", hash = "sha256:082433502dd922bf738de0d8bcc4fdcbf0979ff44c42bd40f5af8a282f6fa107"},
 ]
 
+[[package]]
+name = "tifffile"
+version = "2024.8.30"
+description = "Read and write TIFF files"
+optional = false
+python-versions = ">=3.9"
+files = [
+    {file = "tifffile-2024.8.30-py3-none-any.whl", hash = "sha256:8bc59a8f02a2665cd50a910ec64961c5373bee0b8850ec89d3b7b485bf7be7ad"},
+    {file = "tifffile-2024.8.30.tar.gz", hash = "sha256:2c9508fe768962e30f87def61819183fb07692c258cb175b3c114828368485a4"},
+]
+
+[package.dependencies]
+numpy = "*"
+
+[package.extras]
+all = ["defusedxml", "fsspec", "imagecodecs (>=2023.8.12)", "lxml", "matplotlib", "zarr"]
+codecs = ["imagecodecs (>=2023.8.12)"]
+plot = ["matplotlib"]
+test = ["cmapfile", "czifile", "dask", "defusedxml", "fsspec", "imagecodecs", "lfdfiles", "lxml", "ndtiff", "oiffile", "psdtags", "pytest", "roifile", "xarray", "zarr"]
+xml = ["defusedxml", "lxml"]
+zarr = ["fsspec", "zarr"]
+
 [[package]]
 name = "tiktoken"
 version = "0.7.0"
@@ -9521,4 +9687,4 @@ testing = ["coverage (>=5.0.3)", "zope.event", "zope.testing"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.11"
-content-hash = "f153b6e0e6dc7632af435d6706824a637e50f60f6f5afa7b91565704e17e0f16"
+content-hash = "82be9c0d9d3286e7cd05fbdddc93fff27985e79773b371f9219311f135a28a05"

pyproject.toml

@@ -27,7 +27,7 @@ uvicorn = "*"
 types-toml = "*"
 numpy = "*"
 json-repair = "*"
-browsergym = "0.3.4" # integrate browsergym as the browsing interface
+browsergym = "0.4.3" # integrate browsergym as the browsing interface
 html2text = "*"
 e2b = "^0.17.1"
 pexpect = "*"

tests/integration/mock/eventstream_runtime/BrowsingAgent/test_browse_internet/prompt_001.log

@@ -36,13 +36,13 @@ fill(bid: str, value: str)
 
 select_option(bid: str, options: str | list[str])
     Examples:
-        select_option('48', 'blue')
+        select_option('a48', 'blue')
 
-        select_option('48', ['red', 'green', 'blue'])
+        select_option('c48', ['red', 'green', 'blue'])
 
 click(bid: str, button: Literal['left', 'middle', 'right'] = 'left', modifiers: list[typing.Literal['Alt', 'Control', 'Meta', 'Shift']] = [])
     Examples:
-        click('51')
+        click('a51')
 
         click('b22', button='right')
 
@@ -98,13 +98,11 @@ goto(url: str)
     Examples:
         goto('http://www.example.com')
 
-Multiple actions can be provided at once. Example:
+Multiple actions can be provided at once, but will be executed sequentially without any feedback from the page.
+More than 2-3 actions usually leads to failure or unexpected behavior. Example:
 fill('a12', 'example with "quotes"')
-click('51')
+click('a51')
 click('48', button='middle', modifiers=['Shift'])
-Multiple actions are meant to be executed sequentially without any feedback from the page.
-Don't execute multiple actions at once if you need feedback from the page.
-
 
 
 ----------

tests/integration/mock/eventstream_runtime/BrowsingAgent/test_browse_internet/prompt_002.log

@@ -36,13 +36,13 @@ fill(bid: str, value: str)
 
 select_option(bid: str, options: str | list[str])
     Examples:
-        select_option('48', 'blue')
+        select_option('a48', 'blue')
 
-        select_option('48', ['red', 'green', 'blue'])
+        select_option('c48', ['red', 'green', 'blue'])
 
 click(bid: str, button: Literal['left', 'middle', 'right'] = 'left', modifiers: list[typing.Literal['Alt', 'Control', 'Meta', 'Shift']] = [])
     Examples:
-        click('51')
+        click('a51')
 
         click('b22', button='right')
 
@@ -98,13 +98,11 @@ goto(url: str)
     Examples:
         goto('http://www.example.com')
 
-Multiple actions can be provided at once. Example:
+Multiple actions can be provided at once, but will be executed sequentially without any feedback from the page.
+More than 2-3 actions usually leads to failure or unexpected behavior. Example:
 fill('a12', 'example with "quotes"')
-click('51')
+click('a51')
 click('48', button='middle', modifiers=['Shift'])
-Multiple actions are meant to be executed sequentially without any feedback from the page.
-Don't execute multiple actions at once if you need feedback from the page.
-
 
 
 ----------

tests/integration/mock/eventstream_runtime/BrowsingAgent/test_browse_internet/prompt_003.log

@@ -36,13 +36,13 @@ fill(bid: str, value: str)
 
 select_option(bid: str, options: str | list[str])
     Examples:
-        select_option('48', 'blue')
+        select_option('a48', 'blue')
 
-        select_option('48', ['red', 'green', 'blue'])
+        select_option('c48', ['red', 'green', 'blue'])
 
 click(bid: str, button: Literal['left', 'middle', 'right'] = 'left', modifiers: list[typing.Literal['Alt', 'Control', 'Meta', 'Shift']] = [])
     Examples:
-        click('51')
+        click('a51')
 
         click('b22', button='right')
 
@@ -98,13 +98,11 @@ goto(url: str)
     Examples:
         goto('http://www.example.com')
 
-Multiple actions can be provided at once. Example:
+Multiple actions can be provided at once, but will be executed sequentially without any feedback from the page.
+More than 2-3 actions usually leads to failure or unexpected behavior. Example:
 fill('a12', 'example with "quotes"')
-click('51')
+click('a51')
 click('48', button='middle', modifiers=['Shift'])
-Multiple actions are meant to be executed sequentially without any feedback from the page.
-Don't execute multiple actions at once if you need feedback from the page.
-
 
 
 ----------

tests/integration/mock/eventstream_runtime/CodeActAgent/test_browse_internet/prompt_002.log

@@ -36,13 +36,13 @@ fill(bid: str, value: str)
 
 select_option(bid: str, options: str | list[str])
     Examples:
-        select_option('48', 'blue')
+        select_option('a48', 'blue')
 
-        select_option('48', ['red', 'green', 'blue'])
+        select_option('c48', ['red', 'green', 'blue'])
 
 click(bid: str, button: Literal['left', 'middle', 'right'] = 'left', modifiers: list[typing.Literal['Alt', 'Control', 'Meta', 'Shift']] = [])
     Examples:
-        click('51')
+        click('a51')
 
         click('b22', button='right')
 
@@ -98,13 +98,11 @@ goto(url: str)
     Examples:
         goto('http://www.example.com')
 
-Multiple actions can be provided at once. Example:
+Multiple actions can be provided at once, but will be executed sequentially without any feedback from the page.
+More than 2-3 actions usually leads to failure or unexpected behavior. Example:
 fill('a12', 'example with "quotes"')
-click('51')
+click('a51')
 click('48', button='middle', modifiers=['Shift'])
-Multiple actions are meant to be executed sequentially without any feedback from the page.
-Don't execute multiple actions at once if you need feedback from the page.
-
 
 
 ----------

tests/integration/mock/eventstream_runtime/CodeActAgent/test_browse_internet/prompt_003.log

@@ -36,13 +36,13 @@ fill(bid: str, value: str)
 
 select_option(bid: str, options: str | list[str])
     Examples:
-        select_option('48', 'blue')
+        select_option('a48', 'blue')
 
-        select_option('48', ['red', 'green', 'blue'])
+        select_option('c48', ['red', 'green', 'blue'])
 
 click(bid: str, button: Literal['left', 'middle', 'right'] = 'left', modifiers: list[typing.Literal['Alt', 'Control', 'Meta', 'Shift']] = [])
     Examples:
-        click('51')
+        click('a51')
 
         click('b22', button='right')
 
@@ -98,13 +98,11 @@ goto(url: str)
     Examples:
         goto('http://www.example.com')
 
-Multiple actions can be provided at once. Example:
+Multiple actions can be provided at once, but will be executed sequentially without any feedback from the page.
+More than 2-3 actions usually leads to failure or unexpected behavior. Example:
 fill('a12', 'example with "quotes"')
-click('51')
+click('a51')
 click('48', button='middle', modifiers=['Shift'])
-Multiple actions are meant to be executed sequentially without any feedback from the page.
-Don't execute multiple actions at once if you need feedback from the page.
-
 
 
 ----------

tests/integration/mock/eventstream_runtime/CodeActAgent/test_browse_internet/prompt_004.log

@@ -36,13 +36,13 @@ fill(bid: str, value: str)
 
 select_option(bid: str, options: str | list[str])
     Examples:
-        select_option('48', 'blue')
+        select_option('a48', 'blue')
 
-        select_option('48', ['red', 'green', 'blue'])
+        select_option('c48', ['red', 'green', 'blue'])
 
 click(bid: str, button: Literal['left', 'middle', 'right'] = 'left', modifiers: list[typing.Literal['Alt', 'Control', 'Meta', 'Shift']] = [])
     Examples:
-        click('51')
+        click('a51')
 
         click('b22', button='right')
 
@@ -98,13 +98,11 @@ goto(url: str)
     Examples:
         goto('http://www.example.com')
 
-Multiple actions can be provided at once. Example:
+Multiple actions can be provided at once, but will be executed sequentially without any feedback from the page.
+More than 2-3 actions usually leads to failure or unexpected behavior. Example:
 fill('a12', 'example with "quotes"')
-click('51')
+click('a51')
 click('48', button='middle', modifiers=['Shift'])
-Multiple actions are meant to be executed sequentially without any feedback from the page.
-Don't execute multiple actions at once if you need feedback from the page.
-
 
 
 ----------