docs_agent emits incomplete synthesis — answer dangles on a colon or stray tab labels with the promised example missing - #660
Draft
langsmith-engine-dev[bot] wants to merge 1 commit into
Conversation
…ate to docs_agent prompt Prevent truncated answers that dangle on a colon or leak provider-tab labels without the promised example/code content.
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The
docs_agentruns retrieval successfully and begins writing a synthesized answer, but the synthesis LLM stops before delivering content it just promised: the final message is short and ends either on a dangling colon that introduces an example/config that never appears, or on stray markdown provider-tab labels ("Google / OpenAI / Anthropic") leaked from a docs page, with the code/example missing. This is distinct fromno_synthesis(issue 4de55bff, where the trajectory ends with no assistant message or a raw guardrail-JSON final) — here a prose answer IS produced but is truncated. Both observed cases were Chinese-language answers, so it may interact with multilingual generation.