0.0.37

Shriyansh Agnihotri (3):
      Changes in prompt and making clicks and dropdown faster, prompts help to improve accuracy
      Adding a skip for page wait in case if someone want to speed up the execution
      release: version 0.0.37 🚀

0.0.36

Shriyansh Agnihotri (3):
      Adding documentation of envrionment variables and fixing few prompts to avoid redundant steps, also fixing non OpenAI llms broken support
      Changes on README.md for adding env details
      release: version 0.0.36 🚀

0.0.35

Shriyansh Agnihotri (2):
      bug fixes, interaction logs creation with trivial selectors, adding screenshots with boundingbox and helpbox (#43)
      release: version 0.0.35 🚀

generalrobin (1):
      Added changes around python envs

0.0.34

Shriyansh Agnihotri (3):
      Few bug fixes related to prompts
      Fxing prompts for making testcase pass consistent
      release: version 0.0.34 🚀

0.0.33

Shriyansh Agnihotri (3):
Some refactor to prevent LLM language bais, waiter was in technical terms, LLM assumes it as human :D
removing in progress status response for sub agents
release: version 0.0.33 🚀

What's Changed

• Adding Dynamic LTM for learning long-term knowledge. by @shriyanshagnihotri in #42

Full Changelog: 0.0.31...0.0.33

0.0.32

Shriyansh Agnihotri (3):
      Adding Dynamic LTM for learning long-term knowledge. (#42)
      Fixing issue of result file writer with scenario of same name
      release: version 0.0.32 🚀

generalrobin (2):
      Added prompting guidelines for Hercules
      Added slack badge and notes on models

0.0.31

Emmanuel Ferdman (1):
      Update Salesforce examples (#39)

Shriyansh Agnihotri (3):
      Update README.md
      Bugfix dependency removal from llm_helper, _pydantic.model_dump not found issue
      release: version 0.0.31 🚀

generalrobin (1):
      Removed redundant downloads stats

0.0.30

Ikko Eltociear Ashimine (1):
      docs: update README.md (#36)

Shriyansh Agnihotri (8):
      o3-mini support
      fixing bulk inputs and some function call prompts to make it faster
      spliting reading page and read elements as 2 different tools
      Refactoring few prompts and tools to make it more precise
      Controlling hallucination because of optimisation bais in browser_agents
      fixing interactive mode some part to enable debugging
      fixing run script for command
      release: version 0.0.30 🚀

0.0.29

Shriyansh Agnihotri (3):
      Adding some validations so that gemini protobuf don't fail with parameters.entries is missing
      Solving #35
      release: version 0.0.29 🚀

generalrobin (2):
      Added visual tests (#34)
      Added block for citation

0.0.28

Shriyansh Agnihotri (2):
      few more changes in prompt to prevent function calling hallucination and updating new tests
      release: version 0.0.28 🚀

Shahal Thayyil (1):
      Add Playwright Tracing Feature (#32)

Shriyansh Agnihotri (8):
      Updating README and adding run_guide for bulk and non-bulk mode
      bumping ag2 version to get multimodal support enabled for hercules
      support of remote browser. Lamdatest, BrowserStack, browserbase, anchorbrowser. Added helper scripts to populate CDP_URL and proper documentation
      Adding deafult website as testzeus.com in browser launch
      few changes in the prompt to make it work with deepseek
      Adding bedrock, gemini support
      Adding few more prompts changes to make it work with loose validation
      release: version 0.0.27 🚀

generalrobin (1):
      Added video for visual validations and assertions

What's Changed

• Add Playwright Tracing Feature by @Shahalt1 in #32

New Contributors

• @Shahalt1 made their first contribution in #32

Full Changelog: 0.0.26...0.0.28