Agent never calls its tools — system prompt explicitly forbids tool use - #6
Draft
langsmith-engine[bot] wants to merge 1 commit into
Draft
Agent never calls its tools — system prompt explicitly forbids tool use#6langsmith-engine[bot] wants to merge 1 commit into
langsmith-engine[bot] wants to merge 1 commit into
Conversation
…ool-first guidance Removes the 'Do not use any tools' instruction that was suppressing lookup_concept / get_setup_guide / get_security_advice calls and defeating the agent's grounded-answer value prop.
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 seed AGENTS.md in
src/chat_langchain_lite/context_hub.pycontains the instruction "Do not use any tools — answer entirely from your own expertise," so the agent answers in-domain LangChain/LangGraph/LangSmith questions from memory instead of callinglookup_concept,get_setup_guide, orget_security_advice. The auto-evaluatortool_usageaverages 0.19 across the 48h window and 12 of 18 traces have zero tool calls, defeating the agent's core value proposition of grounded answers from canonical sources and compounding factual drift.