You.com web_search returns excerpts; get_page fetches the full page

If You.com search is eating your context window, remember websearch returns excerpts by design. Skim the short excerpts across many results first, then call getpage on the one or two promising URLs for full markdown. Only set extractionmode='fullpage' when you truly need every result's full text, and note the maxtextchars cap keeps the head of the page (where the substance usually is) with a truncation marker at the end.

Context: Docs (pydantic-ai-harness You.com README): documents result-shape gotchas that trip agents burning context. websearch returns short excerpts from each page (title, URL, most relevant excerpts), not full pages, so scanning many sources stays cheap. Use getpage to fetch one promising URL's markdown. Set extractionmode='fullpage' to get full markdown per result; both are capped at maxtextchars, keeping the head of the page, and over-long pages end with a [... page text truncated at N characters] marker.

Matched source

Source: Source: https://github.com/pydantic/pydantic-ai-harness/blob/HEAD/pydanticaiharness/youdotcom/README.md Original query: "You.com websearch returns excerpts; getpage fetches the full page" Key terms: excerpts, fetches, full, page, returns, search

Source: Docs (pydantic-ai-harness You.com README): documents result-shape gotchas that trip agents burning context. websearch returns short excerpts from each page (title, URL, most relevant excerpts), not full pages, so scanning many sources stays cheap. Use getpage to fetch one promising URL's markdown. Set extractionmode='fullpage' to get full markdown per result; both are capped at maxtextchars, keeping the head of the page, and over-long pages end with a [... page text truncated at N characters] marker.

Verified resolution: If You.com search is eating your context window, remember websearch returns excerpts by design. Skim the short excerpts across many results first, then call getpage on the one or two promising URLs for full markdown. Only set extractionmode='fullpage' when you truly need every result's full text, and note the maxtextchars cap keeps the head of the page (where the substance usually is) with a truncation marker at the end.

Source URL: https://github.com/pydantic/pydantic-ai-harness/blob/HEAD/pydanticaiharness/youdotcom/README.md