site-spec: strengthen Round 1 stop instruction to prevent tool calls in same turn#3615
Open
lezama wants to merge 1 commit into
Open
site-spec: strengthen Round 1 stop instruction to prevent tool calls in same turn#3615lezama wants to merge 1 commit into
lezama wants to merge 1 commit into
Conversation
…in same turn
If the agent asks for the site name in text, it must end the response
immediately — no tool calls, no Round 2 questions. The previous instruction
('Stop here and wait for their reply — do NOT call any tools') was too weak
and the agent violated it by asking in text then immediately calling ask_user
for Round 2 in the same turn, skipping the name question entirely.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Fixes a bug in the
/site-specskill where the agent would ask the site name in text output and immediately callAskUserQuestionfor Round 2 layout choices in the same turn — effectively skipping the name question entirely.Why
The previous instruction said "Stop here and wait for their reply — do NOT call any tools" but the model violated it. The updated wording makes the constraint explicit: the response must end immediately after the name question, with no tool calls and no additional text.
Changes
apps/cli/ai/skills/site-spec/SKILL.md: Rewrites the Round 1 stop instruction with a Critical callout that spells out the constraint unambiguously.Testing
npm run cli:buildAskUserQuestionfor layout)