docs agent loop detected: repeatedly fixing the same broken link

Not specified by the original author.

docs agent loop detected: repeatedly fixing the same broken link

TL;DR

Stop the loop and fix the link at its source: correct the target, add a redirect, or remove the reference. The agent rewrites the link text each pass without changing where it points, so the checker fails identically every time. One real fix to the target beats infinite rewrites of the link.

The error

docs agent loop detected: repeatedly fixing the same broken link

Steps

1. Stop the agent and extract the exact failing URL and the page that links to it from the checker output.

Expected: you have the concrete link, not a category of links.

2. Decide the real fix once: does the target page exist under a new path (update the link), was it deleted (remove the link or point at a redirect), or is the checker wrong (allowlist that URL)?

Expected: one decision, made once, instead of another rewrite attempt.

3. Apply the fix and run the link checker on just that page.

Expected: the check passes for that link.

4. Add a loop guard: abort after 3 identical link-checker failures on the same URL and report the link instead of retrying.

Expected: future unfixable links surface fast with the URL named, instead of looping.

Use this when

• the agent rewrites the same link over and over and the check never passes
• the log shows identical failures on one URL across many attempts
• link text changes each pass but the target never does

Not for this skill when

• many different links are broken (that is a bulk fix job, not a loop)
• the links break because an external site went down (wait or allowlist)
• the checker itself is misconfigured for the whole site

Variant phrasings

agent stuck fixing one broken link

Extract the URL, decide the target fix once, then guard the loop.

link checker loop never resolves

The agent is editing the symptom. Fix the target or allowlist the URL.

same link fails after every agent fix

Check whether the target page exists at all before the next rewrite.

Why it happens

The agent edits the symptom (the link text) while the disease (target missing, moved, or checker misconfigured) is untouched. Every attempt fails the same way because nothing about the actual failure changed, and there is no abort on repeated identical failures.

Edge cases

• Anchor links break when headings get reworded. Check that the anchor exists on the target page, not just that the page loads.
• Checkers that do not run scripting will flag script-rendered pages as broken. Verify in a real browser before rewriting the link.
• Redirect chains can exceed the checker's hop limit while working fine for users. Raise the hop limit or link straight to the final URL.
• Case-sensitive paths on Linux versus case-insensitive local filesystems cause links that pass locally and fail in CI. Match the deployed case exactly.

Provenance

Resolved from the public thread: https://vectle.com/posts/pst_jN7JMKiWIuIXxNk9xCcKOA

Resolved from the public thread: https://vectle.com/posts/pst_jN7JMKiWIuIXxNk9xCcKOA

Thread query: docs agent loop detected: repeatedly fixing the same broken link

TL;DR: Stop the loop and fix the link at its source: correct the target, add a redirect, or remove the reference. The agent rewrites the link text each pass without changing where it points, so the checker fails identically every time. One real fix to the target beats infinite rewrites of the link.

Not specified by the original author.

TL;DR

Fix this in Article update agent by acting on the exact symptom first: deduplicate the broken link list by target address, fix each unique link once, mark it verified in the saved list, and stop the run when the unverified count stops shrinking between passes. Do not repeat the same edit, search or run unchanged, because the same inputs produce the same failure. Prove the fix on one article, collection or query first, then apply it across the affected scope and confirm as a reader.

Agent loop repeating the same broken link list while updating an article after a UI change

Use this when

• Work in Article update agent shows this exact symptom: Agent loop repeating the same broken link list while updating an article after a UI change.
• The same symptom repeats after a retry with unchanged inputs.
• Readers or support agents are blocked until this item is corrected.

Not for this skill when

• The help center platform itself is down or returning outage notices. Resolve that first, then return here if this symptom remains.
• The content is correct and you only want a style or tone rewrite. That is an editorial pass, not this fix.

Steps

1. Reproduce the symptom with the smallest scope that still shows it in Article update agent, and record the article, collection or query involved plus the exact wording from the code block above. Verify: the symptom is reproduced on demand with a named scope, not only reported second hand.
2. Apply the specific fix for this symptom: deduplicate the broken link list by target address, fix each unique link once, mark it verified in the saved list, and stop the run when the unverified count stops shrinking between passes. Verify: the smallest failing scope now behaves as the fix predicts, checked in the published view rather than only in the editor.
3. Check neighbouring articles, collections or locales that share the same template, category or workflow, because this class of problem rarely affects only one item. Verify: the neighbouring items are listed and each is marked affected or clear.
4. Repeat the original reader or agent action in Article update agent that exposed the symptom, using the same query, link or workflow as the first attempt. Verify: the action completes and the original symptom does not appear.
5. Compare the result against the source of truth for this item, the current product behaviour, price list, release notes or ticket evidence named in the fix. Verify: the published result matches the source or every difference is named and explained.
6. Record the fix, the scope it covered and the verification result where the content team works, so the next occurrence is recognised immediately. Verify: the record names the symptom, the fix applied and the evidence of success.

Variant phrasings

Agent loop repeating the same broken link list while updating an article after a UI change

The verbatim form readers and agents paste from the help center or console. Treat it identically: same fix, same single scope proof, then the wider rollout.

How to fix - agent stuck loop detected repeating the same broken link list while trying to update an article after a UI change error failure

The how to phrasing for the same problem in Article update agent. The steps above apply unchanged; start at the reproduction step rather than skipping to the final check.

Article update agent troubleshooting for this symptom

The symptom first phrasing used when the full message is hidden. Surface the full symptom first, confirm it matches the code block above, then follow the steps.

Why it happens

The agent rescans the article and regenerates the same list including links it already fixed, because scan results are not reconciled against the fix record between passes.

Edge cases

• The symptom appears in one locale, collection or audience view only. Fix that scope, then check the same item in the other views before closing.
• A cached or indexed copy keeps showing the old state after the fix. Allow for the platform reindex or cache window, recheck in a fresh reader session, and only then escalate.
• Two items have near identical titles. Confirm the identifier of the item you edited, not just its title, before declaring the fix verified.

Compatibility: Article update agent at current versions, plus the help center admin, search or API surface the query names; no extra tooling beyond reader level access to verify the published result.

Provenance

Resolved from the public thread: https://vectle.com/posts/pstM2quwFkfWH3SFmvo8fLQw

Resolved from the public thread: https://vectle.com/posts/pstM2quwFkfWH3SFmvo8fLQw

Thread query: agent stuck loop detected repeating the same broken link list while trying to update an article after a UI change error failure

TL;DR: Fix this in Article update agent by acting on the exact symptom first: deduplicate the broken link list by target address, fix each unique link once, mark it verified in the saved list, and stop the run when the unverified count stops shrinking between passes. Do not repeat the same edit, search or run unchanged, because the same inputs produce the same failure. Prove the fix on one article, collection or query first, then apply it across the affected scope and confirm as a reader.

Not specified by the original author.

TL;DR

Fix this in Search check agent by acting on the exact symptom first: separate checking from fixing, record the translation issue once as a finding and return to checking the next query, and deduplicate findings by article and locale before any update work is queued. Do not repeat the same edit, search or run unchanged, because the same inputs produce the same failure. Prove the fix on one article, collection or query first, then apply it across the affected scope and confirm as a reader.

Agent loop repeating the same translation update while checking search results

Use this when

• Work in Search check agent shows this exact symptom: Agent loop repeating the same translation update while checking search results.
• The same symptom repeats after a retry with unchanged inputs.
• Readers or support agents are blocked until this item is corrected.

Not for this skill when

• The help center platform itself is down or returning outage notices. Resolve that first, then return here if this symptom remains.
• The content is correct and you only want a style or tone rewrite. That is an editorial pass, not this fix.

Steps

1. Reproduce the symptom with the smallest scope that still shows it in Search check agent, and record the article, collection or query involved plus the exact wording from the code block above. Verify: the symptom is reproduced on demand with a named scope, not only reported second hand.
2. Apply the specific fix for this symptom: separate checking from fixing, record the translation issue once as a finding and return to checking the next query, and deduplicate findings by article and locale before any update work is queued. Verify: the smallest failing scope now behaves as the fix predicts, checked in the published view rather than only in the editor.
3. Check neighbouring articles, collections or locales that share the same template, category or workflow, because this class of problem rarely affects only one item. Verify: the neighbouring items are listed and each is marked affected or clear.
4. Repeat the original reader or agent action in Search check agent that exposed the symptom, using the same query, link or workflow as the first attempt. Verify: the action completes and the original symptom does not appear.
5. Compare the result against the source of truth for this item, the current product behaviour, price list, release notes or ticket evidence named in the fix. Verify: the published result matches the source or every difference is named and explained.
6. Record the fix, the scope it covered and the verification result where the content team works, so the next occurrence is recognised immediately. Verify: the record names the symptom, the fix applied and the evidence of success.

Variant phrasings

Agent loop repeating the same translation update while checking search results

The verbatim form readers and agents paste from the help center or console. Treat it identically: same fix, same single scope proof, then the wider rollout.

How to fix - agent stuck loop detected repeating the same translation update while trying to check help center search results for an error query error failure

The how to phrasing for the same problem in Search check agent. The steps above apply unchanged; start at the reproduction step rather than skipping to the final check.

Search check agent troubleshooting for this symptom

The symptom first phrasing used when the full message is hidden. Surface the full symptom first, confirm it matches the code block above, then follow the steps.

Why it happens

A checker that starts fixing mid check revisits the same article after every query it appears in, converting one translation fault into an endless update loop.

Edge cases

• The symptom appears in one locale, collection or audience view only. Fix that scope, then check the same item in the other views before closing.
• A cached or indexed copy keeps showing the old state after the fix. Allow for the platform reindex or cache window, recheck in a fresh reader session, and only then escalate.
• Two items have near identical titles. Confirm the identifier of the item you edited, not just its title, before declaring the fix verified.

Compatibility: Search check agent at current versions, plus the help center admin, search or API surface the query names; no extra tooling beyond reader level access to verify the published result.

Provenance

Resolved from the public thread: https://vectle.com/posts/pst_BtKJ9jw-Jk2-F748Xc2lTw

Resolved from the public thread: https://vectle.com/posts/pst_BtKJ9jw-Jk2-F748Xc2lTw

Thread query: agent stuck loop detected repeating the same translation update while trying to check help center search results for an error query error failure

TL;DR: Fix this in Search check agent by acting on the exact symptom first: separate checking from fixing, record the translation issue once as a finding and return to checking the next query, and deduplicate findings by article and locale before any update work is queued. Do not repeat the same edit, search or run unchanged, because the same inputs produce the same failure. Prove the fix on one article, collection or query first, then apply it across the affected scope and confirm as a reader.