Skip to content

Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.

vision defaults to True

mertunsalld3a88ce3514a
diff --git a/AGENTS.md b/AGENTS.md
index f5dca30ea..4bf52638e 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -199,7 +199,7 @@ Complete reference for all agent configuration options
### Vision & Processing
-* `use_vision` (default: `"auto"`): Vision mode - `"auto"` includes screenshot tool but only uses vision when requested, `True` always includes screenshots, `False` never includes screenshots and excludes screenshot tool
+* `use_vision` (default: `"True"`): Vision mode - `"auto"` includes screenshot tool but only uses vision when requested, `True` always includes screenshots, `False` never includes screenshots and excludes screenshot tool
* `vision_detail_level` (default: `'auto'`): Screenshot detail level - `'low'`, `'high'`, or `'auto'`
* `page_extraction_llm`: Separate LLM model for page content extraction. You can choose a small & fast model because it only needs to extract text from the page (default: same as `llm`)
diff --git a/browser_use/agent/message_manager/service.py b/browser_use/agent/message_manager/service.py
index 25e25670e..a8b71253e 100644
--- a/browser_use/agent/message_manager/service.py
+++ b/browser_use/agent/message_manager/service.py
@@ -292,7 +292,7 @@ class MessageManager:
model_output: AgentOutput | None = None,
result: list[ActionResult] | None = None,
step_info: AgentStepInfo | None = None,
- use_vision: bool | Literal['auto'] = 'auto',
+ use_vision: bool | Literal['auto'] = True,
page_filtered_actions: str | None = None,
sensitive_data=None,
available_file_paths: list[str] | None = None, # Always pass current available_file_paths
diff --git a/browser_use/agent/service.py b/browser_use/agent/service.py
index a5fe7b578..cc6438a8d 100644
--- a/browser_use/agent/service.py
+++ b/browser_use/agent/service.py
@@ -150,7 +150,7 @@ class Agent(Generic[Context, AgentStructuredOutput]):
register_should_stop_callback: Callable[[], Awaitable[bool]] | None = None,
# Agent settings
output_model_schema: type[AgentStructuredOutput] | None = None,
- use_vision: bool | Literal['auto'] = 'auto',
+ use_vision: bool | Literal['auto'] = True,
save_conversation_path: str | Path | None = None,
save_conversation_path_encoding: str | None = 'utf-8',
max_failures: int = 3,
diff --git a/browser_use/agent/views.py b/browser_use/agent/views.py
index 66246c81d..e65c9d953 100644
--- a/browser_use/agent/views.py
+++ b/browser_use/agent/views.py
@@ -33,7 +33,7 @@ logger = logging.getLogger(__name__)
class AgentSettings(BaseModel):
"""Configuration options for the Agent"""
- use_vision: bool | Literal['auto'] = 'auto'
+ use_vision: bool | Literal['auto'] = True
vision_detail_level: Literal['auto', 'low', 'high'] = 'auto'
save_conversation_path: str | Path | None = None
save_conversation_path_encoding: str | None = 'utf-8'