Teknium 9cdcf31cae docs(web-search): explain auxiliary-model summarization for web_extract (#23211) ...

web_extract runs returned page content through the web_extract auxiliary
model when pages exceed 5 000 chars (single-pass up to 500k, chunked up
to 2M, refused above that). The user-guide page didn't mention this —
users were surprised that long-page extracts produced summaries instead
of raw markdown, and that those summaries cost main-model tokens by
default.

Adds:
- size-driven behavior table (under 5k / 5k–500k / 500k–2M / over 2M)
- which auxiliary task does the work (auxiliary.web_extract)
- how to route summaries to a cheap model regardless of main
- escape hatch: browser_navigate when you need raw content
- troubleshooting entry for summarization timeouts

2026-05-10 06:40:23 -07:00

..

developer-guide

docs: round 2 audit — messaging, developer-guide, guides, integrations (#22858)

2026-05-09 15:00:24 -07:00

getting-started

docs: deep audit — fix stale config keys, missing commands, and registry drift (#22784)

2026-05-09 13:19:51 -07:00

guides

docs: round 2 audit — messaging, developer-guide, guides, integrations (#22858)

2026-05-09 15:00:24 -07:00

integrations

docs: round 2 audit — messaging, developer-guide, guides, integrations (#22858)

2026-05-09 15:00:24 -07:00

reference

chore(skills): move heavy training skills + outlines to optional-skills (#22912)

2026-05-09 18:44:12 -07:00

user-guide

docs(web-search): explain auxiliary-model summarization for web_extract (#23211)

2026-05-10 06:40:23 -07:00

index.md

docs: round 2 audit — messaging, developer-guide, guides, integrations (#22858)

2026-05-09 15:00:24 -07:00

user-stories.mdx

docs(website): add User Stories and Use Cases collage page (#18282)

2026-04-30 23:56:59 -07:00