hash long href link

[LawyZheng]

Important

This PR hashes long href links in HTML elements, storing them in a context map, and updates LLM handlers to render responses using these hashes.

• Behavior:
  • Hashes href links longer than 300 characters in json_to_html() in scraper.py, storing them in SkyvernContext.hashed_href_map.
  • Renders LLM responses using hashed hrefs in llm_api_handler_with_router_and_fallback() and llm_api_handler() in api_handler_factory.py.
• Models:
  • Adds hashed_href_map to SkyvernContext in skyvern_context.py.
  • Adds HASHED_HREF_MAP and LLM_RESPONSE_RENDERED to ArtifactType in models.py.
• Storage:
  • Maps HASHED_HREF_MAP and LLM_RESPONSE_RENDERED to json in base.py.

^{This description was created by for e45ace0. It will automatically update as commits are pushed.}

[ellipsis-dev]

👍 Looks good to me! Reviewed everything up to e45ace0 in 1 minute and 25 seconds

More details

• Looked at 233 lines of code in 6 files
• Skipped 0 files when reviewing.
• Skipped posting 1 drafted comments based on config settings.

1. skyvern/webeye/scraper/scraper.py:106

• Draft comment:
  The comment suggests hashing href links longer than 69 characters, but the code uses a threshold of 300 characters. Ensure the comment and code are consistent.
• Reason this comment was not posted:
  Comment did not seem useful.

Workflow ID: wflow_LwaCcIYDKHbX8Ybx

---

You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet mode, and more.