From e2dba29c9bf27adb5f538e1e8c931c597fda8bef Mon Sep 17 00:00:00 2001 From: Aman Jaiswal Date: Thu, 30 Oct 2025 17:24:48 -0400 Subject: [PATCH 1/4] fix webarenalite build toml --- browsergym/webarenalite/pyproject.toml | 5 ----- 1 file changed, 5 deletions(-) diff --git a/browsergym/webarenalite/pyproject.toml b/browsergym/webarenalite/pyproject.toml index 2f4b7dc7..9e64f207 100644 --- a/browsergym/webarenalite/pyproject.toml +++ b/browsergym/webarenalite/pyproject.toml @@ -30,10 +30,5 @@ path = "../core/src/browsergym/core/__init__.py" [tool.hatch.metadata.hooks.requirements_txt] files = ["requirements.txt"] -[tool.hatch.build] -include = [ - "src/browsergym/webarenalite/test_webarena_lite.raw.json" -] - [tool.hatch.build.targets.wheel] packages = ["src/browsergym"] From 1cf8b22b3d0f1f59374c0e18a76a5a57fdf68670 Mon Sep 17 00:00:00 2001 From: Aman Jaiswal Date: Thu, 30 Oct 2025 17:26:51 -0400 Subject: [PATCH 2/4] version-bump-dev --- browsergym/assistantbench/requirements.txt | 2 +- browsergym/core/src/browsergym/core/__init__.py | 2 +- browsergym/experiments/requirements.txt | 2 +- browsergym/miniwob/requirements.txt | 2 +- browsergym/pyproject.toml | 16 ++++++++-------- browsergym/visualwebarena/requirements.txt | 2 +- browsergym/webarena/requirements.txt | 2 +- browsergym/webarenalite/requirements.txt | 4 ++-- docs/src/conf.py | 2 +- 9 files changed, 17 insertions(+), 17 deletions(-) diff --git a/browsergym/assistantbench/requirements.txt b/browsergym/assistantbench/requirements.txt index ebf342fd..b25a036e 100644 --- a/browsergym/assistantbench/requirements.txt +++ b/browsergym/assistantbench/requirements.txt @@ -1,4 +1,4 @@ -browsergym-core==0.14.3.dev0 +browsergym-core==0.14.3.dev1 datasets scipy numpy diff --git a/browsergym/core/src/browsergym/core/__init__.py b/browsergym/core/src/browsergym/core/__init__.py index c5dc6c47..945dd106 100644 --- a/browsergym/core/src/browsergym/core/__init__.py +++ b/browsergym/core/src/browsergym/core/__init__.py @@ -1,4 +1,4 @@ -__version__ = "0.14.3.dev0" +__version__ = "0.14.3.dev1" import playwright.sync_api diff --git a/browsergym/experiments/requirements.txt b/browsergym/experiments/requirements.txt index d4618b57..c0cbb7c7 100644 --- a/browsergym/experiments/requirements.txt +++ b/browsergym/experiments/requirements.txt @@ -1,3 +1,3 @@ -browsergym-core==0.14.3.dev0 +browsergym-core==0.14.3.dev1 tiktoken>=0.4 dataclasses-json diff --git a/browsergym/miniwob/requirements.txt b/browsergym/miniwob/requirements.txt index a805dd2a..885b7518 100644 --- a/browsergym/miniwob/requirements.txt +++ b/browsergym/miniwob/requirements.txt @@ -1 +1 @@ -browsergym-core==0.14.3.dev0 +browsergym-core==0.14.3.dev1 diff --git a/browsergym/pyproject.toml b/browsergym/pyproject.toml index aaf42b90..9489bfea 100644 --- a/browsergym/pyproject.toml +++ b/browsergym/pyproject.toml @@ -28,17 +28,17 @@ classifiers = [ "Topic :: Scientific/Engineering :: Artificial Intelligence", "License :: OSI Approved :: Apache Software License", ] -version="0.14.3.dev0" +version="0.14.3.dev1" dependencies = [ - "browsergym-core==0.14.3.dev0", - "browsergym-miniwob==0.14.3.dev0", - "browsergym-webarena==0.14.3.dev0", - "browsergym-visualwebarena==0.14.3.dev0", - "browsergym-assistantbench==0.14.3.dev0", - "browsergym-experiments==0.14.3.dev0", + "browsergym-core==0.14.3.dev1", + "browsergym-miniwob==0.14.3.dev1", + "browsergym-webarena==0.14.3.dev1", + "browsergym-visualwebarena==0.14.3.dev1", + "browsergym-assistantbench==0.14.3.dev1", + "browsergym-experiments==0.14.3.dev1", "browsergym-workarena>=0.4.1", "weblinx-browsergym>=0.0.2", - "browsergym-webarenalite==0.14.3.dev0" + "browsergym-webarenalite==0.14.3.dev1" ] [tool.setuptools] diff --git a/browsergym/visualwebarena/requirements.txt b/browsergym/visualwebarena/requirements.txt index e770725d..376e6b41 100644 --- a/browsergym/visualwebarena/requirements.txt +++ b/browsergym/visualwebarena/requirements.txt @@ -1,4 +1,4 @@ -browsergym-core==0.14.3.dev0 +browsergym-core==0.14.3.dev1 browsergym-webarena libvisualwebarena==0.0.15 requests diff --git a/browsergym/webarena/requirements.txt b/browsergym/webarena/requirements.txt index 0770aeca..3b5c8171 100644 --- a/browsergym/webarena/requirements.txt +++ b/browsergym/webarena/requirements.txt @@ -1,2 +1,2 @@ -browsergym-core==0.14.3.dev0 +browsergym-core==0.14.3.dev1 libwebarena==0.0.4 diff --git a/browsergym/webarenalite/requirements.txt b/browsergym/webarenalite/requirements.txt index 08e0743f..b918175f 100644 --- a/browsergym/webarenalite/requirements.txt +++ b/browsergym/webarenalite/requirements.txt @@ -1,3 +1,3 @@ -browsergym-core==0.14.3.dev0 -browsergym-webarena==0.14.3.dev0 +browsergym-core==0.14.3.dev1 +browsergym-webarena==0.14.3.dev1 libwebarena==0.0.4 diff --git a/docs/src/conf.py b/docs/src/conf.py index ace9faf2..594d0259 100644 --- a/docs/src/conf.py +++ b/docs/src/conf.py @@ -6,7 +6,7 @@ copyright = "2024, ServiceNow Research" author = "ServiceNow Research" -version = "0.14.3.dev0" +version = "0.14.3.dev1" release = version # -- General configuration From 4d89d258c1b2537b06a226060cf58d2d6e52d842 Mon Sep 17 00:00:00 2001 From: Aman Jaiswal Date: Fri, 31 Oct 2025 13:17:30 -0400 Subject: [PATCH 3/4] fix import path in evaluators.py --- .../webarenalite/src/browsergym/webarenalite/evaluators.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/browsergym/webarenalite/src/browsergym/webarenalite/evaluators.py b/browsergym/webarenalite/src/browsergym/webarenalite/evaluators.py index fc37a249..12d4de19 100644 --- a/browsergym/webarenalite/src/browsergym/webarenalite/evaluators.py +++ b/browsergym/webarenalite/src/browsergym/webarenalite/evaluators.py @@ -16,7 +16,7 @@ from beartype import beartype from nltk.tokenize import word_tokenize # type: ignore from playwright.sync_api import CDPSession, Page -from webarena.evaluation_harness.helper_functions import ( +from .helper_functions import ( PseudoPage, gitlab_get_project_memeber_role, llm_fuzzy_match, From 4b4d00d86a1be4fe89d0092cec7325ce987bfc0a Mon Sep 17 00:00:00 2001 From: Aman Jaiswal Date: Fri, 31 Oct 2025 16:27:16 -0400 Subject: [PATCH 4/4] make core test sequential temporarily --- .github/workflows/unit_tests.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/unit_tests.yml b/.github/workflows/unit_tests.yml index 49583682..e91be594 100644 --- a/.github/workflows/unit_tests.yml +++ b/.github/workflows/unit_tests.yml @@ -118,7 +118,7 @@ jobs: run: playwright install chromium --with-deps - name: Run browsergym-core Unit Tests - run: pytest -n 5 --durations=10 -m 'not pricy' -v tests/core + run: pytest -n 1 --durations=10 -m 'not pricy' -v tests/core browsergym-miniwob: runs-on: ubuntu-22.04