Skip to content

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

default to PNG everywhere

mertunsall67d2f126652b
diff --git a/browser_use/actor/README.md b/browser_use/actor/README.md
index 24363ac13..82e5cc367 100644
--- a/browser_use/actor/README.md
+++ b/browser_use/actor/README.md
@@ -75,7 +75,7 @@ await element.drag_to(target_element) # Drag and drop
value = await element.get_attribute("value")
box = await element.get_bounding_box() # Returns BoundingBox or None
info = await element.get_basic_info() # Comprehensive element info
-screenshot_b64 = await element.screenshot(format='jpeg')
+screenshot_b64 = await element.screenshot(format='png')
# Execute JavaScript on element (this context is the element)
text = await element.evaluate("() => this.textContent")
@@ -108,7 +108,7 @@ await page.press("Escape") # Single keys
# Page controls
await page.set_viewport_size(width=1920, height=1080)
-page_screenshot = await page.screenshot() # JPEG by default
+page_screenshot = await page.screenshot() # PNG by default
page_png = await page.screenshot(format="png", quality=90)
# Page information
@@ -166,7 +166,7 @@ products = await page.extract_content(
- `evaluate(page_function: str, *args)` → `str` - Execute JavaScript (MUST use (...args) => format)
- `press(key: str)` - Press key on page (supports "Control+A" format)
- `set_viewport_size(width: int, height: int)` - Set viewport dimensions
-- `screenshot(format='jpeg', quality=None)` → `str` - Take page screenshot, return base64
+- `screenshot(format='png', quality=None)` → `str` - Take page screenshot, return base64
- `get_url()` → `str`, `get_title()` → `str` - Get page information
- `mouse` → `Mouse` - Get mouse interface for this page
@@ -181,7 +181,7 @@ products = await page.extract_content(
- `evaluate(page_function: str, *args)` → `str` - Execute JavaScript on element (this = element)
- `get_attribute(name: str)` → `str | None` - Get attribute value
- `get_bounding_box()` → `BoundingBox | None` - Get element position/size
-- `screenshot(format='jpeg', quality=None)` → `str` - Take element screenshot, return base64
+- `screenshot(format='png', quality=None)` → `str` - Take element screenshot, return base64
- `get_basic_info()` → `ElementInfo` - Get comprehensive element information
diff --git a/browser_use/actor/element.py b/browser_use/actor/element.py
index 755995047..217a09cf2 100644
--- a/browser_use/actor/element.py
+++ b/browser_use/actor/element.py
@@ -679,7 +679,7 @@ class Element:
except Exception:
return None
- async def screenshot(self, format: str = 'jpeg', quality: int | None = None) -> str:
+ async def screenshot(self, format: str = 'png', quality: int | None = None) -> str:
"""Take a screenshot of this element and return base64 encoded image.
Args:
diff --git a/browser_use/actor/page.py b/browser_use/actor/page.py
index 71904010c..e76da29fc 100644
--- a/browser_use/actor/page.py
+++ b/browser_use/actor/page.py
@@ -188,7 +188,7 @@ class Page:
return js_code
- async def screenshot(self, format: str = 'jpeg', quality: int | None = None) -> str:
+ async def screenshot(self, format: str = 'png', quality: int | None = None) -> str:
"""Take a screenshot and return base64 encoded image.
Args:
diff --git a/browser_use/agent/cloud_events.py b/browser_use/agent/cloud_events.py
index 4ff893df4..ed7b3c4b3 100644
--- a/browser_use/agent/cloud_events.py
+++ b/browser_use/agent/cloud_events.py
@@ -155,7 +155,7 @@ class CreateAgentStepEvent(BaseEvent):
# Capture screenshot as base64 data URL if available
screenshot_url = None
if browser_state_summary.screenshot:
- screenshot_url = f'data:image/jpeg;base64,{browser_state_summary.screenshot}'
+ screenshot_url = f'data:image/png;base64,{browser_state_summary.screenshot}'
import logging
logger = logging.getLogger(__name__)
diff --git a/browser_use/agent/judge.py b/browser_use/agent/judge.py
index a6220f0f2..32cf63690 100644
--- a/browser_use/agent/judge.py
+++ b/browser_use/agent/judge.py
@@ -158,9 +158,9 @@ Set `reached_captcha` to true if:
Respond with EXACTLY this JSON structure (no additional text before or after):
{{
- "reasoning": "Breakdown of user task into key points. Detailed analysis covering: what went well, what didn't work, trajectory quality assessment, tool usage evaluation, output quality review, and overall user satisfaction prediction",
+ "reasoning": "Breakdown of user task into key points. Detailed analysis covering: what went well, what didn't work, trajectory quality assessment, tool usage evaluation, output quality review, and overall user satisfaction prediction.",
"verdict": true or false,
- "failure_reason": "If verdict is false, provide the key reason why the task was not completed successfully. If verdict is true, use an empty string.",
+ "failure_reason": "A brief explanation of key reasons why the task was not completed successfully in case of failure. If verdict is true, use an empty string. Keep it concise and easy to read.",
"impossible_task": true or false,
"reached_captcha": true or false
}}
diff --git a/browser_use/agent/prompts.py b/browser_use/agent/prompts.py
index c01a40413..86fc0c1ac 100644
--- a/browser_use/agent/prompts.py
+++ b/browser_use/agent/prompts.py
@@ -373,8 +373,8 @@ Available tabs:
content_parts.append(
ContentPartImageParam(
image_url=ImageURL(
- url=f'data:image/jpeg;base64,{screenshot}',
- media_type='image/jpeg',
+ url=f'data:image/png;base64,{screenshot}',
+ media_type='image/png',
detail=self.vision_detail_level,
),
)
diff --git a/browser_use/agent/service.py b/browser_use/agent/service.py
index b9e706a8f..a5fe7b578 100644
--- a/browser_use/agent/service.py
+++ b/browser_use/agent/service.py
@@ -973,7 +973,7 @@ class Agent(Generic[Context, AgentStructuredOutput]):
verdict_text = '✅ PASS' if judgement.verdict else '❌ FAIL'
judge_log += f'⚖️ {verdict_color}Judge Verdict: {verdict_text}\033[0m\n'
if judgement.failure_reason:
- judge_log += f' Failure: {judgement.failure_reason}\n'
+ judge_log += f' Failure Reason: {judgement.failure_reason}\n'
if judgement.reached_captcha:
judge_log += ' 🤖 Captcha Detected: Agent encountered captcha challenges\n'
judge_log += ' 👉 🥷 Use Browser Use Cloud for the most stealth browser infra: https://docs.browser-use.com/customize/browser/remote\n'
diff --git a/browser_use/agent/views.py b/browser_use/agent/views.py
index 4289c8c47..66246c81d 100644
--- a/browser_use/agent/views.py
+++ b/browser_use/agent/views.py
@@ -94,7 +94,8 @@ class JudgementResult(BaseModel):
reasoning: str | None = Field(default=None, description='Explanation of the judgement')
verdict: bool = Field(description='Whether the trace was successful or not')
failure_reason: str | None = Field(
- default=None, description='If the trace was not successful, the reason why. Otherwise empty.'
+ default=None,
+ description='A brief explanation of key reasons why the task was not completed successfully in case of failure. If verdict is true, use an empty string. Keep it concise and easy to read.',
)
impossible_task: bool = Field(
default=False,
diff --git a/browser_use/browser/watchdogs/screenshot_watchdog.py b/browser_use/browser/watchdogs/screenshot_watchdog.py
index 7fea7a226..9cbd8fff6 100644
--- a/browser_use/browser/watchdogs/screenshot_watchdog.py
+++ b/browser_use/browser/watchdogs/screenshot_watchdog.py
@@ -39,7 +39,7 @@ class ScreenshotWatchdog(BaseWatchdog):
cdp_session = await self.browser_session.get_or_create_cdp_session()
# Prepare screenshot parameters
- params = CaptureScreenshotParameters(format='jpeg', quality=60, captureBeyondViewport=False)
+ params = CaptureScreenshotParameters(format='png', captureBeyondViewport=False)
# Take screenshot using CDP
self.logger.debug(f'[ScreenshotWatchdog] Taking screenshot with params: {params}')
diff --git a/browser_use/code_use/service.py b/browser_use/code_use/service.py
index 3456fd230..f7b1cfb02 100644
--- a/browser_use/code_use/service.py
+++ b/browser_use/code_use/service.py
@@ -614,8 +614,8 @@ class CodeAgent:
content_parts.append(
ContentPartImageParam(
image_url=ImageURL(
- url=f'data:image/jpeg;base64,{self._last_screenshot}',
- media_type='image/jpeg',
+ url=f'data:image/png;base64,{self._last_screenshot}',
+ media_type='image/png',
detail='auto',
),
)
diff --git a/browser_use/llm/messages.py b/browser_use/llm/messages.py
index f2b09ac75..75a5d8f6e 100644
--- a/browser_use/llm/messages.py
+++ b/browser_use/llm/messages.py
@@ -61,7 +61,7 @@ class ImageURL(BaseModel):
[Vision guide](https://platform.openai.com/docs/guides/vision#low-or-high-fidelity-image-understanding).
"""
# needed for Anthropic
- media_type: SupportedImageMediaType = 'image/jpeg'
+ media_type: SupportedImageMediaType = 'image/png'
def __str__(self) -> str:
url_display = _format_image_url(self.url)