 Nick Sweeting
|
fa974d6e2f
|
fix early Path.resolve call and other cubic comments
|
2025-06-09 20:25:39 -07:00 |
|
|
Nick Sweeting
|
2540693482
|
tweak agent_tasks for evals slightly
|
2025-06-09 20:20:41 -07:00 |
|
|
Nick Sweeting
|
b5ab4c6492
|
fix BrowserSession reuse in tests
|
2025-06-09 20:14:26 -07:00 |
|
|
Nick Sweeting
|
b8f7b7cae2
|
tweak actions used in mock LLM responses
|
2025-06-09 18:52:17 -07:00 |
|
|
Nick Sweeting
|
921da7cb22
|
fix downloads timing tests
|
2025-06-09 18:51:15 -07:00 |
|
|
Nick Sweeting
|
15bd78cf0f
|
add tests for all of the Re-Use a Browser examples
|
2025-06-09 18:39:14 -07:00 |
|
|
Nick Sweeting
|
68b033a8ff
|
clarify docs that session must be started and stopped manually when keep_alive=True
|
2025-06-09 18:38:24 -07:00 |
|
|
Nick Sweeting
|
b0ed680419
|
use patchright for stealth tests
|
2025-06-09 15:29:37 -07:00 |
|
|
Nick Sweeting
|
bd349e922f
|
stop playwright at the end of test
|
2025-06-09 15:28:58 -07:00 |
|
|
Magnus Müller
|
eaab9f04d7
|
Enhance GitHub Actions workflow and evaluate_tasks.py to include detailed task evaluation results. The workflow now captures and displays detailed results in a structured format, while the Python script outputs detailed results as JSON for better integration with GitHub Actions. This improves visibility and understanding of task outcomes in the evaluation process.
|
2025-06-07 13:39:16 +02:00 |
|
|
Magnus Müller
|
e6171e0fc1
|
Disable Chromium sandbox in BrowserProfile for CI environment in evaluate_tasks.py to improve compatibility with GitHub Actions.
|
2025-06-07 12:59:22 +02:00 |
|
|
Magnus Müller
|
43d96da06c
|
Enhance error handling and debugging in evaluate_tasks.py by adding browser and LLM test calls. Capture and log errors during browser session initiation and agent execution, improving overall troubleshooting capabilities.
|
2025-06-07 12:53:14 +02:00 |
|
|
Magnus Müller
|
9899262186
|
Add additional debug logging in evaluate_tasks.py to track task execution flow and subprocess outputs. Enhance error reporting by capturing and displaying full stdout and stderr for better troubleshooting during agent execution.
|
2025-06-07 12:48:04 +02:00 |
|
|
Magnus Müller
|
54226c7b51
|
Add detailed debug logging in evaluate_tasks.py to capture agent execution steps and outputs. Enhance error reporting for subprocess failures and improve output handling when no agent output is provided.
|
2025-06-07 12:43:51 +02:00 |
|
|
Magnus Müller
|
592b9afbce
|
Refactor evaluate_tasks.py to run agent tasks in separate subprocesses, enhancing isolation and error handling. Introduce argparse for task selection and improve logging management during task execution.
|
2025-06-07 12:37:07 +02:00 |
|
|
Magnus Müller
|
8246bcd299
|
Refactor run_task in evaluate_tasks.py to create a dedicated BrowserSession for each agent, improving session management and ensuring headless execution with --no-sandbox argument.
|
2025-06-07 11:58:01 +02:00 |
|
|
Magnus Müller
|
38cfa86738
|
Update browser_use_pip.yaml to simplify output requirements and refactor run_task in evaluate_tasks.py to remove shared profile parameter, enhancing browser session management with a dedicated profile.
|
2025-06-07 11:50:30 +02:00 |
|
|
Magnus Müller
|
bf13dbb452
|
Refactor run_task function in evaluate_tasks.py to accept a shared profile for consistent browser sessions across tasks
|
2025-06-07 11:40:19 +02:00 |
|
|
Magnus Müller
|
d50581e87c
|
Remove --no-sandbox argument from BrowserProfile in evaluate_tasks.py to simplify configuration
|
2025-06-07 11:28:46 +02:00 |
|
|
Magnus Müller
|
df14af7f00
|
Add --no-sandbox argument to BrowserProfile in evaluate_tasks.py for enhanced security during task execution
|
2025-06-07 11:20:26 +02:00 |
|
|
Magnus Müller
|
b29dbe5f2a
|
Remove keep_alive option from BrowserProfile in evaluate_tasks.py to streamline session management
|
2025-06-07 11:10:51 +02:00 |
|
|
Magnus Müller
|
576519ee40
|
Enhance CI workflow by adding agent tasks evaluation step and updating evaluate_tasks.py to output evaluation results
|
2025-06-07 10:59:24 +02:00 |
|
|
Magnus Müller
|
412904dc65
|
Add keep_alive option to BrowserProfile in evaluate_tasks.py for improved session persistence
|
2025-06-07 10:53:58 +02:00 |
|
|
Magnus Müller
|
3666d2b077
|
Add agent tasks evaluation script and update CI workflow to include it
|
2025-06-07 10:49:03 +02:00 |
|
|
Magnus Müller
|
9ef3d6198a
|
Update test_agent_real_tasks to enable headless mode for BrowserProfile, enhancing browser session management
|
2025-06-07 10:13:18 +02:00 |
|
|
Magnus Müller
|
b04d110d57
|
Refactor test_agent_real_tasks to utilize BrowserProfile for session management and improve browser session handling
|
2025-06-07 10:05:19 +02:00 |
|
|
Magnus Müller
|
6def4c24f1
|
Update test_agent_real_tasks to use temporary user data directory and disable headless mode
|
2025-06-07 09:25:36 +02:00 |
|
|
Magnus Müller
|
074169f80f
|
Merge branch 'main' into tests/eval
|
2025-06-07 09:15:41 +02:00 |
|
|
Nick Sweeting
|
11b980b3ae
|
fixture scoping
|
2025-06-06 19:26:29 -07:00 |
|
|
Nick Sweeting
|
f94d56910f
|
consistent test fixture scope, fix race condition on shutdown, improve logging
|
2025-06-06 19:21:51 -07:00 |
|
|
Magnus Müller
|
67fbcf46a5
|
Update test_agent_real_tasks to use None for user_data_dir in BrowserSession
|
2025-06-07 01:16:52 +02:00 |
|
|
Magnus Müller
|
25c96bcaca
|
Add README for contributing agent tasks with guidelines and testing instructions
|
2025-06-07 00:51:32 +02:00 |
|
|
Magnus Müller
|
2c355ce6d9
|
Add new agent task tests for Amazon laptop search, browser-use pip installation, and Cloudflare captcha solving
|
2025-06-07 00:49:39 +02:00 |
|
|
Magnus Müller
|
80dbad0811
|
Refactor test_agent_real_task to use temporary browser session and improve judge context handling
|
2025-06-07 00:46:58 +02:00 |
|
|
Magnus Müller
|
80fd5e97e8
|
Add tests for agent real tasks using pytest and ChatOpenAI
|
2025-06-07 00:46:43 +02:00 |
|
|
Nick Sweeting
|
8504bc4c7b
|
parallelize playwright tests using loop scope=session and pytest-xdist
|
2025-06-06 02:03:25 -07:00 |
|
|
Nick Sweeting
|
9b3dd67dad
|
stop playwright during browser teardown
|
2025-06-06 01:23:47 -07:00 |
|
|
Nick Sweeting
|
683a97e475
|
try and tweak test_registry to fix deadlock tests
|
2025-06-06 01:01:31 -07:00 |
|
|
Nick Sweeting
|
819859c006
|
add BrowserSession.kill method
|
2025-06-05 23:44:23 -07:00 |
|
|
Nick Sweeting
|
e1aa19bf5b
|
fix test deadlocks by setting max 30sec timeout on launch and close
|
2025-06-05 23:35:25 -07:00 |
|
|
Nick Sweeting
|
743e357f46
|
fix test deadlocks
|
2025-06-05 23:29:05 -07:00 |
|
|
Nick Sweeting
|
b07e838543
|
fix downloads tests
|
2025-06-05 23:16:58 -07:00 |
|
|
Nick Sweeting
|
02b4f2c5de
|
fix tests by using temp dirs and headless for all tests
|
2025-06-05 23:12:32 -07:00 |
|
|
Nick Sweeting
|
8306a01a02
|
cleaner agent and browser session logging on connect and disconnect
|
2025-06-05 22:21:42 -07:00 |
|
|
Nick Sweeting
|
2a39dfa1c5
|
use self.logger to shorten log lines
|
2025-06-05 21:21:10 -07:00 |
|
|
Nick Sweeting
|
23d3bf4205
|
rename .emit to .dispatch and prefix event params to prevent clashes
|
2025-06-05 21:04:26 -07:00 |
|
|
Nick Sweeting
|
f3c5672c46
|
better circular loop prevention for eventbus
|
2025-06-05 20:23:41 -07:00 |
|
|
Nick Sweeting
|
52b6b4b1cb
|
simplify eventbus methods
|
2025-06-05 19:43:43 -07:00 |
|
|
Nick Sweeting
|
57e1d6ebe4
|
remove dead code
|
2025-06-05 19:01:11 -07:00 |
|
|
Nick Sweeting
|
9da6c485b7
|
implement new EventBus module with cloud_events to send on agent steps
|
2025-06-05 18:51:22 -07:00 |
|