# Translation silently truncated when JSON stream parsing breaks (no error raised)
**URL:** https://meta.discourse.org/t/translation-silently-truncated-when-json-stream-parsing-breaks-no-error-raised/407251
**Category:** Bug
**Tags:** ai, dynaloc
**Created:** [July 10, 2026, 9:31am UTC](https://meta.discourse.org/t/translation-silently-truncated-when-json-stream-parsing-breaks-no-error-raised/407251 "2026-07-10T09:31:25Z")
**Posts on this page:** 4
**Page:** 1
### Author:  [@dorina](https://meta.discourse.org/u/dorina)
#### Post date: [July 10, 2026, 9:31am UTC](https://meta.discourse.org/t/translation-silently-truncated-when-json-stream-parsing-breaks-no-error-raised/407251/1 "2026-07-10T09:31:25Z")
**Summary**
`DiscourseAi::Translation::PostLocalizer` (content localization) occasionally
produces truncated translations with no error logged anywhere (Rails log,
Sidekiq log, Sidekiq dead/retry queues). The truncation happens mid-sentence,
silently, and the partial result is saved as if it were a complete, successful
translation.
**Observed on:** Discourse core + discourse-ai `46bea6613` (2026-07-09), LLM:
Gemini 2.5 Flash via Google provider.
**Reproduction evidence**
Two real cases on our instance:
- A ~2090-char German post translated to Spanish produced only 50 chars,
cutting off immediately before a quoted word (“aufwendiger”) in the source
text.
- A ~1830-char German post translated to English (83 chars) and Slovak
(97 chars) — both cut off at the _exact same point_ in the sentence,
immediately before an emoji shortcode (💥) in the source text.
All other locales (fr, it, pt, ru, he) for the same post translated
completely (1600–1950 chars).
**Root cause (as far as I can trace it)**
In lib/completions/structured\_output.rb, StructuredOutput#read\_buffered\_property
falls back to DiscourseAi::Utils::BestEffortJsonParser.extract\_key whenever
@partial\_json\_tracker.broken? is true. This fallback returns whatever was
parsed before the JSON stream broke — with no exception, no warning, no
indication anywhere that the output is incomplete. In
lib/translation/base\_translator.rb#get\_translation, this value is used as-is
as the final translation and persisted via PostLocalization#save!.
Both truncation points in our data land immediately before a “special”
character in the source text (a straight quote, an emoji shortcode),
suggesting the JSON streaming tracker becomes confused by certain
characters/sequences in the model’s streamed output and marks the stream
broken? prematurely.
**Impact**
Content is published with visibly incomplete, sometimes nonsensical
translations, and there’s no operational signal (log, dead job, admin
notification) to catch it. We only discovered it because a community member
spotted mid-sentence garbage in the UI.
**Suggested fixes**
- Surface a warning/error (Rails.logger + Discourse-error-log) whenever
StructuredOutput#broken? is true and the best-effort fallback is used, so
admins can detect this instead of silently shipping partial content.
- Consider validating translated length against a sanity threshold relative
to source length before saving a PostLocalization.
Happy to provide full raw/translated text pairs privately if useful for
debugging the JSON tracker.
---
### Author:  [@Denis\_Kovalenko](https://meta.discourse.org/u/Denis_Kovalenko)
#### Post date: [July 10, 2026, 6:20pm UTC](https://meta.discourse.org/t/translation-silently-truncated-when-json-stream-parsing-breaks-no-error-raised/407251/2 "2026-07-10T18:20:13Z")
Adding a data point to this — we’re seeing what looks like the same underlying
mechanism, but manifesting differently.
**Observed on:** Discourse core + discourse-ai, LLM: GPT-5.1 via OpenAI (custom API connection, not a seeded model).
**Reproduction evidence**
Same source post (Russian, ~2000 chars, headers/bold/bullet lists/links),
translated into multiple locales via native AI translation:
- Polish (pl): the embedded image markdown lost its structure — went from
`` to a malformed link missing the `!`
prefix and the `|` separator, with the alt text and dimensions run
together as plain text. Rendered as a clickable link instead of an
embedded image.
- Ukrainian (uk): literal `\n\n` sequences appear as plain text throughout
the entire post, in place of paragraph breaks. The image markdown in this
same translation was intact — so the corruption isn’t tied to one fixed
symptom, it varies by run.
Unlike the truncation described above, our case shows no missing content —
the full text is present, but with corrupted escape sequences / markdown
syntax rather than a shortened output. Different provider (OpenAI vs Google
here), different symptom (corruption vs truncation), same suspected root:
StructuredOutput#read\_buffered\_property falling back to
BestEffortJsonParser#extract\_key, which doesn’t unescape JSON string
sequences (`\n` stays literal) and appears to also mishandle special
characters adjacent to markdown syntax when the fallback triggers mid-parse.
No errors in Sidekiq or Rails logs on our side either — same silent-failure
behavior.
---
### Author:  [@Falco](https://meta.discourse.org/u/Falco)
#### Post date: [July 14, 2026, 11:39pm UTC](https://meta.discourse.org/t/translation-silently-truncated-when-json-stream-parsing-breaks-no-error-raised/407251/4 "2026-07-14T23:39:19Z")
Started working on a possible fix at
>
>
> Reported at https://meta.discourse.org/t/translation-silently-truncated-when-jso…n-stream-parsing-breaks-no-error-raised/407251
>
> \## The bug
>
> Some providers stream structured output whose string values were unescaped by an outer JSON parse, so real newlines appear inside string values. When that happened, \`JsonStreamingTracker\` had two failure modes:
>
> \- It marked the stream broken and \`StructuredOutput\` fell back to \`BestEffortJsonParser\`, whose extraction regex (\`\[^"\]+\`) cut the value at the first escaped quote and left \`\\n\` sequences as literal text. A 2,000-char translation could come back as ~50 chars, cut right before the first quoted word — exactly what the report shows.
> \- Its escape-and-resume hack (\`String#dump\` + buffer-growth offset) miscomputed the resume index whenever the chunk contained non-ASCII, quotes, or backslashes, silently duplicating or corrupting content \*\*without ever marking the stream broken\*\*.
>
> Testing a realistic corrupted payload across chunk sizes 1–60: 31 produced the truncated fallback, 27 produced silent corruption, 1 raised, and only 1 came out correct. Either way the result was persisted as a successful translation with nothing in the logs.
>
> \## The fix
>
> Replace the hand-rolled parsing with two gems and keep only glue:
>
> \- \*\*json\_completer\*\* (pure Ruby): \`JsonStreamingTracker\` now feeds the cumulative buffer — with control characters re-escaped — to an incremental, truncation-tolerant parser and notifies consumers of changed keys. The corrupted payloads above stream correctly at every chunk size, so the broken-stream path is only reached for responses that aren't JSON at all.
> \- \*\*smarter\_json\*\*: \`BestEffortJsonParser\` becomes a three-attempt chain (strict-with-completion → control-chars re-escaped → lenient) covering the quirk shapes the old regexes handled: single quotes, unquoted keys, markdown fences, prose-wrapped JSON.
>
> This deletes the vendored 668-line SAX parser, the resume hack, and all manual regex extraction (net −694 lines), and adds a log warning whenever a response falls back to best-effort parsing.
>
> \## Behavior changes
>
> \- Scalars now stream progressively: mid-stream \`read\_buffered\_property(:number)\` returns the digits buffered so far instead of \`nil\`. Consumers act on final values, so this only affects mid-stream reads.
> \- Arrays of objects stream partial objects mid-stream instead of returning \`nil\` until finish.
> \- A trailing comma in an array reads as a \`nil\` placeholder slot until the next element arrives.
> \- Partial tool calls surface a few more progressive updates (the openai endpoint spec count moved 128 → 134); values still only ever grow.
>
> \## Tests
>
> \- Regression specs for the report: unescaped control characters with escaped quotes/emoji streamed across chunk boundaries, fenced + unescaped responses, truncated JSON, numeric casting.
> \- 916 examples green across \`completions/\`, \`translation/\`, \`modules/ai\_helper/\`, and \`utils/\`.
---
### Author:  [@Falco](https://meta.discourse.org/u/Falco)
#### Post date: [July 27, 2026, 11:00am UTC](https://meta.discourse.org/t/translation-silently-truncated-when-json-stream-parsing-breaks-no-error-raised/407251/5 "2026-07-27T11:00:52Z")
This topic was automatically closed after 11 days. New replies are no longer allowed.