557 Commits

Author SHA1 Message Date
Zhou Xiao
8e69f8d151
fix(keybord): resolve selectAll/Copy/Paste event (#384)
* fix(keybord): resolve selectAll/Copy/Paste event

* chore: fix e2e test

* chore: upgrade deps

* chore: add keybord commands  ref
2025-02-13 15:53:53 +08:00
github-actions[bot]
f7c583cdf5 release: v0.11.1 2025-02-13 06:50:24 +00:00
yuyutaotao
2f2400dffa
fix: correctly collect elements in absolute container (#373) 2025-02-10 20:51:43 +08:00
yuyutaotao
efa4263b06
feat: export yaml runner in javascipt (#368)
---------

Co-authored-by: zhouxiao.shaw <zhouxiao.shaw@bytedance.com>
2025-02-10 20:00:14 +08:00
yuyutaotao
01b2461027
fix: upgrade langsmith sdk (#374)
---------

Co-authored-by: zhouxiao.shaw <zhouxiao.shaw@bytedance.com>
2025-02-10 19:55:52 +08:00
github-actions[bot]
d1e2e2b560 release: v0.11.0 2025-02-10 10:35:13 +00:00
yuyutaotao
38eb53d460
fix: ai evaluation (#371) 2025-02-10 17:44:12 +08:00
yuyutaotao
2a28472fa5
feat: use different color for annotations (#366) 2025-02-10 16:36:12 +08:00
Zhou Xiao
bdff171da6
fix(ui-tars): resolve page down and page up event error (#370) 2025-02-10 16:35:03 +08:00
yutao
a5f92b875f fix: lint in #365 2025-02-10 14:13:23 +08:00
Saurabh Srivastava
db86455eb7 fix: improve waitForNetworkIdle with timeout handling 2025-02-09 12:30:45 -06:00
Saurabh Srivastava
94450bf649 fix: improve waitForNetworkIdle with timeout handling 2025-02-09 12:23:13 -06:00
Zhou Xiao
25128fab1a
chore: optimize e2e test (#364) 2025-02-08 15:49:43 +08:00
Zhou Xiao
c502806acd
workflow: enhance error messages and improve the debugging experience (#363) 2025-02-08 14:38:04 +08:00
Zhou Xiao
195eaad903
feat(cache): supports ui-tars model caching capability (#361) 2025-02-08 13:05:17 +08:00
yuyutaotao
9d5f2fbcac
feat(web-extract): extract web content as a tree (#337)
* feat: extract web content as a tree

* chore: update test data

* chore: update test data

* feat: update answer of evaluation

* chore: update test cases

* chore: remove focusing on cases

* fix: ci

* fix: put rect in html tree

* fix: CI

* fix: AI test

* fix: lint

* fix: CI

* fix: static-page compatibility

* fix: CI

* fix: map by markerId

* fix: llm planning prompt

* chore: update hash length

* chore: ignore writing dump file

* fix: lint

* fix: ci snapshot

* chore: snapshot tree in web extractor

* chore: export tree utils in core

* chore: export tree utils in core

* fix: CI

* fix: update test case and evaluation

* chore: remove unused file

* refactor(extract): modify dependencies (#358)

* refactor(extract): modify dependencies

* chore: modify files config

* chore: add indexId as key for map

---------

Co-authored-by: Zhou Xiao <zhouxiao.shaw@bytedance.com>
2025-02-07 14:55:52 +08:00
github-actions[bot]
e86021535a release: v0.10.5 2025-01-31 03:07:52 +00:00
Zhou Xiao
16914bbee9
fix(prompt): resolve params format error (#343) 2025-01-31 11:03:28 +08:00
github-actions[bot]
6c908842f9 release: v0.10.4 2025-01-30 06:18:36 +00:00
Zhou Xiao
f8744e441a
fix(prompt): resolve the llm-planning format error (#341) 2025-01-30 14:14:14 +08:00
Zhou Xiao
e8a3ea4464
workflow(ci): optimize ai test workflow (#336) 2025-01-27 17:17:02 +08:00
github-actions[bot]
8eacc354a7 release: v0.10.3 2025-01-27 08:21:33 +00:00
Zhou Xiao
e3eb6f6fbc
fix: resolve shared exports error (#335) 2025-01-27 16:16:42 +08:00
Zhou Xiao
b4a6b6f44d
chore: change default model name (#333) 2025-01-27 14:05:42 +08:00
Zhou Xiao
02ad84cf6f
chore: fix ai test (#332) 2025-01-27 10:22:56 +08:00
github-actions[bot]
e6fc69eb81 release: v0.10.2 2025-01-26 12:39:17 +00:00
Zhou Xiao
9c88186540
feat(ui-tars): enhance the UI-TARS keyboard event handling and optimize parser logic (#330) 2025-01-26 20:34:56 +08:00
yuyutaotao
6d924e267f
feat(puppeteer): allow tracking new tab in puppeteer agent (#310) 2025-01-26 16:49:32 +08:00
Zhou Xiao
839dc6c799
feat(browser-event): support drag event (#321) 2025-01-26 12:00:55 +08:00
Zhou xiao
4b0aae2ad0
docs: optimize docs and fix ai test (#325) 2025-01-25 13:35:29 +08:00
Zhou xiao
2811f15da0
chore: refine AI test for failures (#323) 2025-01-25 11:14:15 +08:00
Zhou xiao
4c82eff526
chore: fix e2e test (#316)
* chore: fix e2e test

* chore: ignore todo test

* chore: fix e2e test

* chore: upgrade gpt api version

* chore: fix e2e test

* chore: fix e2e test

* chore: fix direction

* chore: fix direction

* chore: split test

* chore: split test

* chore: modify input info

* fix: scroll param in ci

* fix: lint

* fix: ai test

* fix: ai test

---------

Co-authored-by: yutao <yutao.tao@bytedance.com>
2025-01-24 15:02:50 +08:00
github-actions[bot]
0f92941f54 release: v0.10.1 2025-01-23 07:15:56 +00:00
yuyutaotao
57f6786628
feat(extract-data): extract data from same-origin iframe (#258)
* feat: extract data from same-origin iframe

* fix: ci snapshot

* fix: extracting timeout error

* fix: ci timeout

* fix: update assets

* feat: set default size of yaml as 1920x1080

* chore: update default viewport size

---------

Co-authored-by: zhouxiao.shaw <zhouxiao.shaw@bytedance.com>
2025-01-22 20:52:11 +08:00
Zhou xiao
6c188d09e8
fix(e2e): optimize e2e error (#307)
* fix(e2e): optimize e2e error

* chore: ignore unless e2e
2025-01-22 13:51:40 +08:00
yuyutaotao
3d95460f44
docs(ai-model): update docs for ui-tars (#305)
* feat: update docs for ui-tars

* doc: update

* doc: update

* doc: update

* chore: update readme

* fix: ci

* docs: upgrade video

* chore: modify huagging face icon

---------

Co-authored-by: zhouxiao.shaw <zhouxiao.shaw@bytedance.com>
2025-01-22 09:24:29 +08:00
yuyutaotao
ed45cfab6c
fix(action): keyboard and div extracting (#304)
* fix: clearInput in browser

* fix: input issue on mac

* fix: playwright input

* fix: issue when collecting fixed item
---------

Co-authored-by: zhouxiao.shaw <zhouxiao.shaw@bytedance.com>

* fix: extract fixed style content

* fix: extract fixed style content

* fix: customize window size in yaml
2025-01-21 19:21:09 +08:00
yuyutaotao
3aa1b33955
feat: use jpeg as default image format (#301)
---------

Co-authored-by: zhouxiao.shaw <zhouxiao.shaw@bytedance.com>
2025-01-20 20:02:49 +08:00
github-actions[bot]
9b86067ea6 release: v0.10.0 2025-01-17 10:31:04 +00:00
yuyutaotao
a114e707d1
feat: show pointer position in chrome extension (#286)
---------

Co-authored-by: zhouxiao.shaw <zhouxiao.shaw@bytedance.com>
2025-01-17 18:19:22 +08:00
yuyutaotao
918e6a3ec3
chore: move ai test into example repo (#293)
* chore: move ai test into example repo

* chore: update readme
2025-01-17 00:05:23 +08:00
Zhou xiao
836768878e
fix(extract-data): position ignore container element (#290) 2025-01-16 15:01:28 +08:00
yuyutaotao
4cad2e13eb
feat(ai-model): remove dom info in assertion to make it reliable (#284)
---------

Co-authored-by: zhouxiao.shaw <zhouxiao.shaw@bytedance.com>
2025-01-16 14:37:35 +08:00
yuyutaotao
f68b6f3139
feat(chrome-devtool): allow tracking active tab in bridge mode (#282)
---------

Co-authored-by: zhouxiao.shaw <zhouxiao.shaw@bytedance.com>
2025-01-15 19:54:03 +08:00
yuyutaotao
fb2b9d123f
feat(chrome-devtool): add 'stop' button in extension (#281)
* feat: add 'stop' to playground

* feat: make extension stopable

---------

Co-authored-by: zhouxiao.shaw <zhouxiao.shaw@bytedance.com>
2025-01-15 19:18:26 +08:00
Zhou xiao
ff9ef70941
chore(prompt): switch thought language according to timezone in vlm mode (#283)
* chore: switch Thought Language to english

* chore: use timezone to select language
2025-01-15 18:54:23 +08:00
github-actions[bot]
d580bd02fe release: v0.9.2 2025-01-15 03:22:10 +00:00
Zhou xiao
38c844cd9c
fix(extract-data): resolve match multiple element (#280) 2025-01-15 11:09:54 +08:00
yuyutaotao
afd0934c4f
doc: update the instructions to configure the model service (#274)
---------

Co-authored-by: zhouxiao.shaw <zhouxiao.shaw@bytedance.com>
2025-01-15 10:14:36 +08:00
Zhou xiao
beb74f12e8
chore: optimize devtool tab connect (#279) 2025-01-14 21:31:33 +08:00