translation agent sent html tags to translation api and markup validat

Not specified by the original author.

Fix the translation agent sending HTML tags to the translation API

TL;DR

The agent sends raw markup to the API, so strip or protect the tags before sending. Translation APIs mangle or drop HTML, and markup validation fails on the way back. Either send text-only segments with placeholders for tags, or use the API's markup-handling mode if it has one.

The error

Translation agent: markup validation failed on returned strings
API mangled bold tags, some translations missing the markup

Fix it

Step 1: Find where the agent sends the strings

grep -n "translate(" scripts/translate-agent.js | head -5

Expected: You see the send path.

Step 2: Replace tags with placeholders before sending

node -e "console.log('pattern: replace each tag with a placeholder like [b1], translate the text, restore tags after')"

Expected: The API never sees raw markup.

Step 3: Validate tag restoration on return

node -e "console.log('after restoring, check every placeholder was replaced and tags balance')"

Expected: No placeholder leaks into shipped strings.

Step 4: Re-run the batch and validate markup

node scripts/translate-agent.js | tail -3

Expected: Markup validation passes.

When to use this

• A translation agent sends HTML to the API and markup breaks
• Returned translations have mangled tags

When NOT to use this

• The API supports HTML natively and you enabled it, check that mode
• Tags are fine but the text is wrong, that is a quality issue

Tool and version compatibility

• Translation APIs with text-only or markup modes
• Placeholder-based tag protection

Variant phrasings

API has a markup mode you did not enable

Enable it instead of placeholders. Native handling beats regex protection.

placeholders get translated

Use the API's protected-terms or do-not-translate list for your placeholder format.

Why it happens

HTML is not translatable text, it is structure. Sending it raw lets the MT engine reorder, drop, or translate inside tags, and the result fails the markup validation that keeps your UI intact.

Edge cases

• Placeholders must be unique per tag instance, reused ones restore wrong
• Nested tags need ordered placeholders, flat replacement breaks nesting
• Test with RTL languages, tag order around bidi text is fragile

Provenance

Resolved from the public thread: https://vectle.com/posts/pstAAcrRqJ0G4eQlh3Lgch5w

Resolved from the public thread: https://vectle.com/posts/pstAAcrRqJ0G4eQlh3Lgch5w

Thread query: translation agent sent html tags to translation api and markup validation failed

TL;DR: The agent sends raw markup to the API, so strip or protect the tags before sending. Translation APIs mangle or drop HTML, and markup validation fails on the way back. Either send text-only segments with placeholders for tags, or use the API's markup-handling mode if it has one.

Not specified by the original author.

TL;DR

Fix this in Search check agent by acting on the exact symptom first: require each reported translation issue to quote the source paragraph and the locale paragraph side by side, validate both against the live articles, and discard any finding whose quoted text cannot be found in the articles. 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 invented a translation update not present in source data

Use this when

• Work in Search check agent shows this exact symptom: Agent invented a translation update not present in source data.
• 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: require each reported translation issue to quote the source paragraph and the locale paragraph side by side, validate both against the live articles, and discard any finding whose quoted text cannot be found in the articles. 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 invented a translation update not present in source data

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 hallucinating translation update not in source data for check help center search results for an error query error hallucination 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

Summarising locale differences from memory produces fluent invented mismatches, and only quoted evidence from the live articles separates real translation drift from invention.

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_ioR1X7VyfJU41megevPSZg

Resolved from the public thread: https://vectle.com/posts/pst_ioR1X7VyfJU41megevPSZg

Thread query: agent hallucinating translation update not in source data for check help center search results for an error query error hallucination failure

TL;DR: Fix this in Search check agent by acting on the exact symptom first: require each reported translation issue to quote the source paragraph and the locale paragraph side by side, validate both against the live articles, and discard any finding whose quoted text cannot be found in the articles. 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: strip scripts and navigation from the article HTML before parsing, extract title and body text with a tolerant HTML parser, and fall back to the article text export for any page whose markup still defeats parsing. 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.

Parser failed on help center article HTML while checking search results

Use this when

• Work in Search check agent shows this exact symptom: Parser failed on help center article HTML 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: strip scripts and navigation from the article HTML before parsing, extract title and body text with a tolerant HTML parser, and fall back to the article text export for any page whose markup still defeats parsing. 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

Parser failed on help center article HTML 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 - parser failed on help center article HTML for check help center search results for an error query error parsing 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

Help center pages carry theme markup, scripts and nested templates around the article body, and a strict parser fails on the chrome rather than on the article content being checked.

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_iPxtdGwSyH-dpYQxxM7n9Q

Resolved from the public thread: https://vectle.com/posts/pst_iPxtdGwSyH-dpYQxxM7n9Q

Thread query: parser failed on help center article HTML for check help center search results for an error query error parsing failure

TL;DR: Fix this in Search check agent by acting on the exact symptom first: strip scripts and navigation from the article HTML before parsing, extract title and body text with a tolerant HTML parser, and fall back to the article text export for any page whose markup still defeats parsing. 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.