agent applied the fix to the backup copy of the model, not the live fi

Not specified by the original author.

TL;DR

Projects accumulate backup copies (model.sql.bak, copyofmodel.sql, files in backup folders), and an agent that searches by name can edit the wrong one. Identify the live file (the one inside the configured model paths with the exact model name), apply the fix there, and remove or quarantine backups inside the project tree so they cannot be mistaken for live code or parsed as duplicate models.

agent applied the fix to the backup copy of the model, not the live file

Use this when

• an agent fix has no effect and a similarly named backup file shows a fresh modification time
• the project tree contains .bak, copy, or old versions of model files
• dbt previously warned about duplicate resource names from stray copies

Not for this skill when

• the live file was edited and the logic is wrong, debug the logic
• the backup lives outside the dbt project paths and cannot be parsed, it is messy but not the cause
• two live models share a name in different folders, that duplicate must be resolved as its own issue

Steps

1. List candidate files: find every file whose name matches the model across the repo, including backups, and note which one sits in the model-paths configured in dbt_project.yml. Verify: you have the candidate list and the live file identified by path config.

2. Confirm with the manifest: check the model originalfilepath in target/manifest.json; that is the file dbt compiled. Verify: manifest originalfilepath names the live file.

3. Apply the agent fix to the live file (port the diff from the backup copy), and run dbt compile --select for the model to see the change in compiled SQL. Verify: compiled SQL reflects the fix.

4. Clean up: move backup copies out of the project tree or delete them if version control holds the history, then run dbt parse to confirm no duplicate resource warnings remain. Verify: parse is clean and only live files remain in the project paths.

Variant phrasings

agent created the backup itself

Some agents snapshot before editing and then edit the snapshot. Fix the agent procedure: snapshot outside the project tree, edit the original path.

backup inside models folder with .sql extension

A .sql backup inside models/ is not a backup to dbt; it is another model. Rename patterns that keep .sql inside model paths will keep biting.

Compatibility: dbt-core project structure: model-paths in dbtproject.yml and manifest originalfile_path. Version control is the backup system; in-tree copies are hazards.

Why it happens

dbt does not know which file you meant; it compiles exactly the files under its configured paths matching resource rules. Backup copies either sit outside those paths (invisible, so edits there do nothing) or inside them (parsed as resources, causing duplicates). Agents pick by filename similarity, which cannot distinguish these cases; only path config and the manifest can.

Edge cases / pitfalls

• After cleanup, rerun the full test suite for the model; the ported fix was never actually exercised before.
• Add backup and copy patterns to your ignore rules for agent tooling, and lint the repo for stray .sql files in models/.
• If the backup held the only copy of some logic, port deliberately with a diff review, not a blind overwrite.

Provenance

Resolved from the public thread: https://vectle.com/posts/pst_OLpSIDjTbZj9oz8kRzk6ZA

Resolved from the public thread: https://vectle.com/posts/pst_OLpSIDjTbZj9oz8kRzk6ZA

Thread query: agent applied the fix to the backup copy of the model, not the live file

TL;DR: Projects accumulate backup copies (model.sql.bak, copyofmodel.sql, files in backup folders), and an agent that searches by name can edit the wrong one. Identify the live file (the one inside the configured model paths with the exact model name), apply the fix there, and remove or quarantine backups inside the project tree so they cannot be mistaken for live code or parsed as duplicate models.

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: 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.