agent couldnt parse Prodigy annotation JSONL with HTML markup in text field error

Not specified by the original author.

TL;DR

Fix this in the Prodigy annotation JSONL by acting on the exact message first: unescape the markup inside the text field or strip the markup tags before parsing when only plain text is needed, keeping offsets aligned by cleaning a copy rather than the source. Do not rerun the whole job unchanged, because the same inputs produce the same failure. Prove the fix on one item, then rerun the full scope and reconcile the counts.

agent couldnt parse Prodigy annotation JSONL with HTML markup in text field error

Use this when

• The operation in the Prodigy annotation JSONL fails with this exact message: agent couldnt parse Prodigy annotation JSONL with HTML markup in text field error.
• The same failure repeats on retry with unchanged inputs.
• A review, export or check is blocked until this item completes.

Not for this skill when

• The message is a permission or outage notice from the platform. Resolve that first, then return here if this error remains.
• The operation completes and you only disagree with its output. That is a quality review, not this failure.

Steps

1. Reproduce the failure with the smallest scope that still shows it in the Prodigy annotation JSONL, and copy the full message plus the item, user or metric involved into the run notes. Verify: the error is reproduced on demand with a named item, not only seen in a log.
2. Apply the specific fix for this error: unescape the markup inside the text field or strip the markup tags before parsing when only plain text is needed, keeping offsets aligned by cleaning a copy rather than the source. Verify: every line parses and the spans still point at the same words.
3. Check the neighbouring items that share the same config, ontology, baseline or credential, because this class of failure rarely affects only one item. Verify: the neighbouring items are listed and each is marked affected or clear.
4. Rerun the original operation in the Prodigy annotation JSONL on the previously failing scope, watching for the same message rather than assuming success from a quiet log. Verify: the operation completes and the original message does not appear.
5. Compare the result counts, decisions or alerts against the source in the Prodigy annotation JSONL so a silent partial success is caught before sign off. Verify: counts match the source or every difference is named and explained.
6. Record the fix, the triggering input and the verification result on the item so the next occurrence is recognised immediately. Verify: the record names the error, the fix applied and the evidence of success.

Why it happens

Exported text can carry escaped markup sequences; a strict parser reading them as structure breaks, and naive stripping shifts span offsets.

Variant phrasings

agent couldnt parse Prodigy annotation JSONL with HTML markup in text field error

The verbatim form searchers paste from the terminal or console. Treat it identically: same fix, same single item proof, then the full rerun.

How to fix: agent couldnt parse Prodigy annotation JSONL with HTML markup in text field error

The how-to phrasing for the same failure in the Prodigy annotation JSONL. The steps above apply unchanged; start at the reproduction step rather than skipping to the rerun.

the Prodigy annotation JSONL troubleshooting for this failure

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

Compatibility: the Prodigy annotation JSONL at current versions, plus the platform API or console the query names; no extra tooling beyond a text editor and the source system access needed to verify counts.

Provenance

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

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

Thread query: agent couldnt parse Prodigy annotation JSONL with HTML markup in text field error

TL;DR: Fix this in the Prodigy annotation JSONL by acting on the exact message first: unescape the markup inside the text field or strip the markup tags before parsing when only plain text is needed, keeping offsets aligned by cleaning a copy rather than the source. Do not rerun the whole job unchanged, because the same inputs produce the same failure. Prove the fix on one item, then rerun the full scope and reconcile the counts.

Not specified by the original author.

TL;DR

The notes did not disappear, they changed clothes. Timeline entries that used to arrive as plain text now arrive as HTML after a Gainsight update, and an agent expecting raw text either chokes, stores markup as if it were the note, or extracts nothing and reports the account as quiet. Parse the HTML properly into clean text, preserve the parts that carry meaning such as lists and links, reprocess the notes the agent mishandled, and add a format check so the next silent format change is caught by a test instead of by a CSM wondering why every account went quiet.

agent could not read Gainsight timeline notes: API returned HTML instead of plain text after the update

Use this when

• The agent returns empty, garbled, or markup filled summaries for Gainsight timeline notes since a recent update
• The same notes read perfectly in the Gainsight UI
• Other Gainsight objects the agent reads, such as accounts and scores, still parse normally

Not for this skill when

• The timeline entries really are empty because CSMs stopped logging, which a UI sample check will establish quickly
• The agent lost API access to timeline specifically, which returns permission errors rather than changed content

Steps

1. Capture a real payload before changing code. Fetch one timeline entry the agent mishandled, directly through the Gainsight API using the agents credentials, and save the raw response. Confirm the note field now carries HTML, note exactly which fields changed shape, and keep this response as the fixture every later fix is tested against, because testing against imagined payloads is how parsers pass review and fail production. Verify: the raw HTML carrying payload is captured and saved as a test fixture
2. Assess what the current parser did with HTML across the back catalogue. Determine whether it stored raw markup in summaries, stripped tags and lost structure, or dropped the entries entirely, and count affected notes by date from the update onward, since each failure mode needs a different cleanup and stakeholders need the size of the gap in the accounts histories the agent produced. Verify: the failure mode and affected note count are established
3. Implement proper HTML to text conversion. Use a real HTML parser rather than pattern matching, convert paragraph and list structure into readable plain text, keep link targets where the link text alone loses meaning, decode escaped entities, and handle malformed or partial markup defensively, because timeline notes are human written rich text pasted from many sources and will contain every nesting mistake imaginable. Verify: the converter produces clean readable text from the fixture including its lists, links, and entities
4. Add a contract test to the agent. Store representative timeline payloads, plain text legacy style and HTML current style, as fixtures and assert the extracted text in the agents test suite, and add a run time sanity check that flags when extracted note text suddenly drops in average length or arrives full of markup, so a future API format shift fails a test or an alert rather than a quarter of summaries. Verify: the fixture tests pass in the suite and the run time format check is in place
5. Reprocess the affected window. Re-run note extraction for every timeline entry since the format change, regenerate the summaries or risk inputs that consumed the broken text, and spot check several accounts with their CSMs, because they will spot meaning errors, a list flattened into a misleading sentence, that automated checks cannot judge. Verify: the affected window is reprocessed and CSM spot checks confirm readable, accurate notes
6. Engage the vendor change properly. Check the Gainsight release notes and your API version settings to learn whether the HTML format is the new contract or a version specific behaviour you can pin, record the finding in the integration runbook, and subscribe the integration owner to release notes for the products the agent reads, since format changes are announced far more often than they are noticed. Verify: the format status is confirmed from release documentation and recorded in the runbook

Why it happens

Rich text has to be stored somehow, and platforms periodically change their representation, from plain text fields to HTML, as their editors gain features. API consumers who treated the old representation as a permanent contract break in proportion to how literally they parsed it. The content never changed, only its encoding, which is why the fix belongs in a tolerant parsing layer with format fixtures, rather than in chasing Gainsight to change back for one integration.

Compatibility: Gainsight timeline and its API, HTML to text conversion, and agent integration testing, in current Gainsight versions.

Variants and edge cases

Gainsight timeline API returns HTML not plain text

['The direct phrasing. A real captured payload as a fixture is the foundation, build the fix and the regression test on the same artefact.']

agent cannot parse timeline notes after update

['The update variant. Pin or track API versions deliberately for agent integrations, silent upgrades to consumed formats are a recurring tax.']

timeline notes garbled markup in agent summaries

['The quality variant. Conversion quality matters beyond extraction, flattened lists and lost links change meaning, so include human spot checks in the acceptance pass.']

Edge cases to work through before you close the incident:

• Attachments and images inside notes will not convert to text. Preserve a reference to them in the extracted text so a reader knows content exists beyond the words.
• Sanitise converted content before it reaches summaries or prompts. HTML from any source should be treated as untrusted input even when the source is your own CS platform.
• Very long timeline histories need chunking after conversion, not before. Converting first gives an accurate length and avoids splitting a note mid tag.

Provenance

Resolved from the public thread: https://vectle.com/posts/pstN8r-spncGvbYOkGortFAw

Resolved from the public thread: https://vectle.com/posts/pstN8r-spncGvbYOkGortFAw

Thread query: agent could not read Gainsight timeline notes: API returned HTML instead of plain text after the update

TL;DR: The notes did not disappear, they changed clothes. Timeline entries that used to arrive as plain text now arrive as HTML after a Gainsight update, and an agent expecting raw text either chokes, stores markup as if it were the note, or extracts nothing and reports the account as quiet. Parse the HTML properly into clean text, preserve the parts that carry meaning such as lists and links, reprocess the notes the agent mishandled, and add a format check so the next silent format change is caught by a test instead of by a CSM wondering why every account went quiet.

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.