🤖 fix: clarify best-of-n prompt guidance#2949
Merged
Merged
Conversation
Collaborator
Author
|
@codex review |
|
Codex Review: Didn't find any major issues. 🎉 ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. Codex can also answer questions or update the PR. Try commenting "@codex address that feedback". |
Add a dedicated best-of-n section to the shared system prompt prelude so plain-English best-of-n requests map to the task tool's n parameter with suitable sub-agents. Also remove tautological prompt-copy assertions from systemMessage.test.ts and strengthen AGENTS guidance so tests focus on behavior instead of mirroring static strings. --- _Generated with `mux` • Model: `openai:gpt-5.4` • Thinking: `xhigh` • Cost: `3.12`_ <!-- mux-attribution: model=openai:gpt-5.4 thinking=xhigh costs=3.12 -->
ammar-agent
force-pushed
the
fix/best-of-n-task-guidance
branch
from
f9fd100 to
213cdcb
Compare
ammar-agent
changed the title
Collaborator
Author
|
@codex review |
|
Codex Review: Didn't find any major issues. Another round soon, please! ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. Codex can also answer questions or update the PR. Try commenting "@codex address that feedback". |
ammario
approved these changes
Mar 14, 2026
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Add explicit system-prompt guidance that a user request for best-of-n work should be interpreted as a request to use the
tasktool'snparameter with suitable sub-agents, and tighten the surrounding test guidance so we do not keep prompt-copy assertions around.Background
The task tool description already explains how best-of-n spawning works, but the shared prelude did not directly tell the model how to map a plain-English "best of n" request onto that mechanism. This follow-up also removes tautological tests that only mirrored static prompt prose and adds a stronger AGENTS rule against that pattern.
Implementation
<best-of-n>section to the shared system prompt prelude insrc/node/services/systemMessage.tsdocs/agents/system-prompt.mdxsrc/node/services/systemMessage.test.tsdocs/AGENTS.mdValidation
bun test src/node/services/systemMessage.test.tsmake static-checkRisks
Low: the production behavior change is still limited to prompt guidance, and the rest of the diff removes brittle tests plus adds repo guidance.
Generated with
mux• Model:openai:gpt-5.4• Thinking:xhigh• Cost:n/a