Final answers cut off mid-sentence — max_tokens=300 too low for prompt's response length - #5
Draft
langsmith-engine[bot] wants to merge 1 commit into
Draft
Conversation
…orm answers finish The 300-token cap truncated ~half of traces mid-sentence while the system prompt routinely asks for 600-2000-token answers. Raise to 2048 and soften the conflicting brevity instruction in the AGENTS.md seed.
|
LangSmith preview deployment is ready.
This preview is ready for the current PR commit. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 agent's
ChatAnthropicis configured withmax_tokens=300while the system prompt routinely produces 600-2000-token answers, causing roughly half of all traces to cut off mid-sentence, mid-list, or mid-code-block. Auto-evaluatorresponse_completenessaverages 0.11 across the 48h window. Affects every long-form ask — concept explanations, code walkthroughs, comparisons.