Hermes contribution

Explicitly disable web_extract

Proposes disabling page extraction with `web.extract_backend=disabled` (also `off` or `false`) without falling back to another backend; `web_search` can remain available. The value `none` is intentionally not treated as disabled.

This Hermes contribution comes from the source PR. See the source PR for status and discussion; release inclusion is checked separately.

GitHub data verified: 2026-10-16

PR status

Open — proposal

PR inclusion in a release is unverified

Changed files (2)

tests/tools/test_web_extract_disable.py
tools/web_tools.py

Open GitHub

Topics for this object

Help with this task

AI consultation and workflow review
Diagnosis of the workflow, bottlenecks, risks, and ROI: what is worth automating, where an agent helps, and where manual control is safer.
Discuss the task
AI agent setup for a specific business task
An agent for a concrete process: data sources, rules, quality checks, safe autonomy boundaries, and ongoing support.
Discuss the task

How counters work

Counts are concrete object views and GitHub outbound events, not people or installations. Interests stay in the browser; the new store holds only counters, with IPs used briefly in memory for request limits. No events means no popularity claim.

Explicitly disable web_extract

PR status

Topics for this object

Help with this task

AI consultation and workflow review

AI agent setup for a specific business task