{"version":"2.1.285","anchor":"webfetch-subagent-prompt-page-fetch-limits-and-no-retry-wor","canonical_anchor":"webfetch-subagent-prompt-page-fetch-limits-and-no-retry-wor","heading":"Web fetching may follow a few more links and stops sooner on failures","tier":"notice","area":"Web Fetch","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.285\/e\/webfetch-subagent-prompt-page-fetch-limits-and-no-retry-wor","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.285","markdown":"### Web fetching may follow a few more links and stops sooner on failures\n\nThe helper behind WebFetch may now follow about five same-site links, must not guess URLs, and retries a failed fetch at most once\n\n**Unclear.** Whether these instructions apply in every configuration is not settled.\n\n**What**\n\nWhen Claude uses the `WebFetch` tool, a helper subagent (a separate Claude working on its behalf) does the fetching. Its instructions changed:\n\n- It may follow up to about five links on the same site. Before, it was limited to the URLs it was given, redirect targets, or an obviously relevant next page.\n\n- It must not guess URLs.\n\n- It retries once on a timeout or a status that says to try again.\n\n- Other failures, including rejections by a proxy or a policy, are treated as permanent and not worked around.\n\nThe `WebFetch` tool's own description is unchanged in this release; only the helper's instructions moved.\n\n**Why**\n\nIt changes how far a fetch can reach and how failures are handled: a blocked page now stays blocked rather than being retried by other routes.\n\n- Area: Web Fetch\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 1\/5"}