Sync fork with original

.env.example

@@ -1,8 +1,15 @@
 OPENAI_API_KEY=
 ANTHROPIC_API_KEY=
+AZURE_ENDPOINT=
+AZURE_OPENAI_API_KEY=
+GEMINI_API_KEY=
+DEEPSEEK_API_KEY=
 
 # Set to false to disable anonymized telemetry
 ANONYMIZED_TELEMETRY=true
 
 # LogLevel: Set to debug to enable verbose logging, set to result to get results only. Available: result | debug | info
 BROWSER_USE_LOGGING_LEVEL=info
+
+# set this to true to optimize browser-use's chrome for running inside docker
+IN_DOCKER=false

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -81,4 +81,4 @@ body:
     attributes:
       label: Relevant Log Output
       description: Please copy and paste any relevant log output. This will be automatically formatted into code.
-      render: shell
+      render: shell

.github/ISSUE_TEMPLATE/config.yml

@@ -8,4 +8,4 @@ contact_links:
     about: Please ask questions in our Discord community
   - name: 📖 Documentation
     url: https://docs.browser-use.com
-    about: Check our documentation for answers first 
+    about: Check our documentation for answers first

.github/ISSUE_TEMPLATE/docs_issue.yml

@@ -46,10 +46,10 @@ body:
       description: If you have specific suggestions for how to improve the documentation, please share them
       placeholder: |
         The documentation could be improved by...
-        
+
         Example:
         ```python
         # Your suggested code example or text here
         ```
     validations:
-      required: true
+      required: true

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -40,4 +40,4 @@ body:
       placeholder: |
         - Example use cases
         - Screenshots or mockups
-        - Related issues or discussions 
+        - Related issues or discussions

.github/workflows/lint.yml

@@ -0,0 +1,24 @@
+name: Lint
+on:
+  push:
+  pull_request:
+  workflow_dispatch:
+jobs:
+  ruff:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: astral-sh/setup-uv@v5
+      - run: uv run ruff format
+      - run: uv run pre-commit run --all-files
+      # TODO: Fix the ignored pytests.
+      # openai.OpenAIError: The api_key client option must be set either by passing
+      # api_key to the client or by setting the OPENAI_API_KEY environment variable
+      - run: uv run --with=dotenv pytest
+                --ignore=tests/test_dropdown_error.py
+                --ignore=tests/test_gif_path.py
+                --ignore=tests/test_models.py
+                --ignore=tests/test_react_dropdown.py
+                --ignore=tests/test_save_conversation.py
+                --ignore=tests/test_vision.py
+                --ignore=tests/test_wait_for_element.py || true

.github/workflows/publish.yml

@@ -6,33 +6,87 @@
 # separate terms of service, privacy policy, and support
 # documentation.
 
-name: Upload Python Package
+name: Python Package Workflow
 
 on:
+  push:
+    branches:
+      - main
   release:
     types: [published]
+  schedule:
+    - cron: "0 17 * * FRI"  # Every Friday at 5 PM UTC
 
 permissions:
-  contents: read
+  contents: write
 
 jobs:
-  deploy:
+  pre_commit_and_tests:
+    if: github.event_name == 'push' && github.ref_name == 'main'
     runs-on: ubuntu-latest
-
     steps:
       - uses: actions/checkout@v4
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
           python-version: "3.x"
-      - name: Install dependencies
+      - uses: astral-sh/setup-uv@v5
+      - run: uv run ruff check --no-fix --select PLE  # check only for syntax errors
+      - run: uv build
+      - run: uv run --isolated --no-project --with pytest --with dist/*.whl tests/conftest.py
+      - run: uv run --isolated --no-project --with pytest --with dist/*.tar.gz tests/conftest.py
+      - run: uv run --with=dotenv pytest \
+                --ignore=tests/test_dropdown_error.py \
+                --ignore=tests/test_gif_path.py \
+                --ignore=tests/test_models.py \
+                --ignore=tests/test_react_dropdown.py \
+                --ignore=tests/test_save_conversation.py \
+                --ignore=tests/test_vision.py \
+                --ignore=tests/test_wait_for_element.py || true
+      - run: uv publish --trusted-publishing always
+
+  tag_pre_release:
+    if: github.event_name == 'schedule'
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Create pre-release tag
         run: |
-          python -m pip install --upgrade pip
-          pip install build hatch
-      - name: Build package
-        run: python -m build
-      - name: Publish package
-        uses: pypa/gh-action-pypi-publish@release/v1
+          git fetch --tags
+          latest_tag=$(git tag --list --sort=-v:refname | grep -E '^v[0-9]+\.[0-9]+\.[0-9]+rc[0-9]+$' | head -n 1)
+          if [ -z "$latest_tag" ]; then
+            new_tag="v0.1.0rc1"
+          else
+            new_tag=$(echo $latest_tag | awk -F'rc' '{print $1 "rc" $2+1}')
+          fi
+          git tag $new_tag
+          git push origin $new_tag
+
+  deploy:
+    if: github.event_name == 'release'
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python
+        uses: actions/setup-python@v5
         with:
-          user: __token__
-          password: ${{ secrets.PYPI_API_TOKEN }}
+          python-version: "3.x"
+      - uses: astral-sh/setup-uv@v5
+      - run: uv run ruff check --no-fix --select PLE  # check only for syntax errors
+      - run: uv build
+      - run: uv run --isolated --no-project --with pytest --with dist/*.whl tests/conftest.py
+      - run: uv run --isolated --no-project --with pytest --with dist/*.tar.gz tests/conftest.py
+      - run: uv run --with=dotenv pytest \
+                --ignore=tests/test_dropdown_error.py \
+                --ignore=tests/test_gif_path.py \
+                --ignore=tests/test_models.py \
+                --ignore=tests/test_react_dropdown.py \
+                --ignore=tests/test_save_conversation.py \
+                --ignore=tests/test_vision.py \
+                --ignore=tests/test_wait_for_element.py || true
+      - run: uv publish --trusted-publishing always
+      - name: Push to stable branch (if stable release)
+        if: startsWith(github.ref_name, 'v') && !contains(github.ref_name, 'rc')
+        run: |
+          git checkout -b stable
+          git push origin stable

.gitignore

@@ -187,4 +187,4 @@ gcp-login.json
 *.json
 *.jsonl
 
-uv.lock
+uv.lock

.pre-commit-config.yaml

@@ -1,18 +1,32 @@
 repos:
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.3.0
+    rev: v0.11.2
     hooks:
       - id: ruff
-        args: [
-            --line-length=130,
-            --select=E,F,I,
-            --fix,
-        ]
+      - id: ruff-format
+      # see pyproject.toml for more details on ruff config
 
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.5.0
+    rev: v5.0.0
     hooks:
-      - id: trailing-whitespace
-      - id: end-of-file-fixer
-      - id: check-yaml
       - id: check-toml
+      - id: check-yaml
+      - id: check-json
+      - id: end-of-file-fixer
+      - id: check-merge-conflict
+      - id: check-illegal-windows-names
+      - id: check-case-conflict
+      - id: check-added-large-files
+      - id: check-shebang-scripts-are-executable
+      - id: check-symlinks
+      - id: destroyed-symlinks
+      - id: detect-private-key
+      - id: mixed-line-ending
+      - id: fix-byte-order-marker
+
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.4.1
+    hooks:
+      - id: codespell # See pyproject.toml for args
+        additional_dependencies:
+          - tomli

.vscode/launch.json

@@ -39,7 +39,7 @@
                 "-v",
                 "-k",
                 "test_captcha_solver",
-                "--capture=no",
+                "--capture=no"
             ],
             "console": "integratedTerminal",
             "justMyCode": false
@@ -54,7 +54,7 @@
                 "-v",
                 "-k",
                 "test_ecommerce_interaction",
-                "--capture=no",
+                "--capture=no"
             ],
             "console": "integratedTerminal",
             "justMyCode": false
@@ -85,4 +85,4 @@
             "justMyCode": false
         }
     ]
-}
+}

README.md

@@ -28,10 +28,9 @@ With pip (Python>=3.11):
 pip install browser-use
 ```
 
-install playwright:
-
+Install Playwright:
 ```bash
-playwright install
+playwright install chromium
 ```
 
 Spin up your agent:
@@ -57,6 +56,11 @@ Add your API keys for the provider you want to use to your `.env` file.
 
 ```bash
 OPENAI_API_KEY=
+ANTHROPIC_API_KEY=
+AZURE_ENDPOINT=
+AZURE_OPENAI_API_KEY=
+GEMINI_API_KEY=
+DEEPSEEK_API_KEY=
 ```
 
 For other settings, models, and more, check out the [documentation 📕](https://docs.browser-use.com).
@@ -133,7 +137,7 @@ Tell your computer what to do, and it gets it done.
 ### Rerunning tasks
 
 - [ ] LLM as fallback
-- [ ] Make it easy to define workfows templates where LLM fills in the details
+- [ ] Make it easy to define workflow templates where LLM fills in the details
 - [ ] Return playwright script from the agent
 
 ### Datasets
@@ -156,6 +160,11 @@ We love contributions! Feel free to open issues for bugs or feature requests. To
 
 To learn more about the library, check out the [local setup 📕](https://docs.browser-use.com/development/local-setup).
 
+
+`main` is the primary development branch with frequent changes. For production use, install a stable [versioned release](https://github.com/browser-use/browser-use/releases) instead.
+
+---
+
 ## Cooperations
 
 We are forming a commission to define best practices for UI/UX design for browser agents.
@@ -181,7 +190,7 @@ If you use Browser Use in your research or project, please cite:
 }
 ```
 
- <div align="center"> <img src="https://github.com/user-attachments/assets/402b2129-b6ac-44d3-a217-01aea3277dce" width="400"/> 
+ <div align="center"> <img src="https://github.com/user-attachments/assets/06fa3078-8461-4560-b434-445510c1766f" width="400"/> 
 
 [![Twitter Follow](https://img.shields.io/twitter/follow/Gregor?style=social)](https://x.com/gregpr07)
 [![Twitter Follow](https://img.shields.io/twitter/follow/Magnus?style=social)](https://x.com/mamagnus00)

SECURITY.md

@@ -17,4 +17,3 @@ Please include as much of the information listed below as you can to help me bet
 * Impact of the issue, including how an attacker might exploit the issue
 
 This information will help me triage your report more quickly.
-

browser_use/agent/gif.py

@@ -155,10 +155,28 @@ def _create_task_frame(
 	# Calculate vertical center of image
 	center_y = image.height // 2
 
-	# Draw task text with increased font size
+	# Draw task text with dynamic font size based on task length
 	margin = 140  # Increased margin
 	max_width = image.width - (2 * margin)
-	larger_font = ImageFont.truetype(regular_font.path, regular_font.size + 16)  # Increase font size more
+
+	# Dynamic font size calculation based on task length
+	# Start with base font size (regular + 16)
+	base_font_size = regular_font.size + 16
+	min_font_size = max(regular_font.size - 10, 16)  # Don't go below 16pt
+	max_font_size = base_font_size  # Cap at the base font size
+
+	# Calculate dynamic font size based on text length and complexity
+	# Longer texts get progressively smaller fonts
+	text_length = len(task)
+	if text_length > 200:
+		# For very long text, reduce font size logarithmically
+		font_size = max(base_font_size - int(10 * (text_length / 200)), min_font_size)
+	else:
+		font_size = base_font_size
+
+	larger_font = ImageFont.truetype(regular_font.path, font_size)
+
+	# Generate wrapped text with the calculated font size
 	wrapped_text = _wrap_text(task, larger_font, max_width)
 
 	# Calculate line height with spacing

browser_use/agent/memory/__init__.py

@@ -0,0 +1,3 @@
+from browser_use.agent.memory.service import Memory, MemorySettings
+
+__all__ = ['Memory', 'MemorySettings']