What's Changed
- Node Library -> Block Library by @wintonzheng in #2183
- safety checks for CUA by @wintonzheng in #2188
- fix CUA pending checks schema by @wintonzheng in #2189
- Block Library naming fix by @wintonzheng in #2190
- Feature/self hosted proxy support by @piyushmittal20 in #2115
- acknowledged_safety_checks by @wintonzheng in #2192
- disable async operations for CUA agent by @wintonzheng in #2194
- remove terminate in cua fallback by @wintonzheng in #2195
- terminate action when CUA verification code is not received by @wintonzheng in #2196
- do not take fullpage screenshot post CUA action by @wintonzheng in #2197
- upgrade litellm to 1.67.0 by @wintonzheng in #2198
- support workflow_run_id in totp code by @wintonzheng in #2199
- Feature: Configuring OpenAI-Compatible (LiteLLM) Models by @TheDropZone in #2166
- add workflow_run_id in totp endpoint doc by @wintonzheng in #2200
- fix custom selection bug by @wintonzheng in #2201
- update latest openai model configs for azure & openai by @wintonzheng in #2202
- bedrock claude 3.7 sonnet by @wintonzheng in #2203
- support shadow dom mutation observer by @wintonzheng in #2206
- update need verification prompt by @wintonzheng in #2207
- fix prompt typo by @LawyZheng in #2208
- log skyvern's response to CUA questions by @wintonzheng in #2209
- add more scrape page methods by @wintonzheng in #2211
- handle null tagname by @wintonzheng in #2212
- fix task v2 block totp issue by @wintonzheng in #2214
- optimize and speed up custom selection by @wintonzheng in #2215
- fix phone number format issue by @wintonzheng in #2217
- Disable connection pooler if env specifies it by @wintonzheng in #2222
- debug log: Using general model configuration for unknown LLM key by @wintonzheng in #2223
- bump v0.1.78 by @wintonzheng in #2224
- add LLMCaller that supports message history by @wintonzheng in #2204
- optimize max steps failure reason for task v2 by @wintonzheng in #2225
- Fix Skyvern.node.ts for N8N Community Node by @dd36 in #2216
- bump up n8n version to 0.0.3 by @LawyZheng in #2226
- add current sha into log by @wintonzheng in #2227
- fix interactable parsing by @wintonzheng in #2228
- anthropic CUA by @wintonzheng in #2231
- increase download max wait time and change logs by @wintonzheng in #2232
- do not close the tab when download is not triggered by @wintonzheng in #2234
- improve custom selection by @wintonzheng in #2236
- use anthropic beta client by @wintonzheng in #2235
- bugfix by @wintonzheng in #2237
- Anthropic CUA fix by @wintonzheng in #2238
- fix anthropic messages image input pattern by @wintonzheng in #2239
- fix anthropic llm caller routing by @wintonzheng in #2241
- enable thinking in anthropic CUA by @wintonzheng in #2240
- fix tool_call_input parsing with anthropic sdk by @wintonzheng in #2242
- add vertex ai by @wintonzheng in #2243
- add google dependency by @wintonzheng in #2244
- Add organization_name and workflow_permanent_id to skyvern context, pass workflow_permanet_id when deciding which identifier to use with which llm by @wintonzheng in #2245
- fix anthropic tool result format by @wintonzheng in #2246
- fix bug by @wintonzheng in #2249
- support only selectable input element by @wintonzheng in #2250
- Show continue_on_failure in loop node by @wintonzheng in #2251
- Update docker compose with Bitwarden by @suchintan in #2253
- bugfix by @wintonzheng in #2254
- resize screenshots to make it compatible with anthropic CUA by @wintonzheng in #2255
- CUA action parser - generate_cua_fallback_actions helper by @wintonzheng in #2256
- remove mintlify doc by @wintonzheng in #2097
- support more anthropic actions by @wintonzheng in #2257
- action handlers back - SOLVE_CAPTCHA, CLICK, INPUT_TEXT by @wintonzheng in #2258
- bump version to v0.1.79 by @wintonzheng in #2259
New Contributors
- @TheDropZone made their first contribution in #2166
- @dd36 made their first contribution in #2216
Full Changelog: v0.1.77...v0.1.79