fix: harden planner + researcher + writer prompt against FM-3.1, FM-3.2 - #3
Open
akarsh-jain-790 wants to merge 1 commit into
Open
fix: harden planner + researcher + writer prompt against FM-3.1, FM-3.2#3akarsh-jain-790 wants to merge 1 commit into
akarsh-jain-790 wants to merge 1 commit into
Conversation
…mpts to demand brevity-
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
🤖 Automated prompt fix (MAST-diagnosed)
Failure modes: FM-3.1, FM-3.2
Source trace:
f76161644075dfdc01f0afd34e2e6a3bDiagnosis: All three agents produce outputs that are truncated mid-sentence, indicating they exceed context/generation limits without self-monitoring, and none successfully append their verification/completion sentinel lines.
Fix: Shortened and tightened all three prompts to demand brevity-first output with hard word limits, explicit self-check for completeness before stopping, and instructions to prefer concise finished output over detailed but truncated output.
Prompt changes
plannerresearcherwriterDiagnosed with the MAST taxonomy (Cemri et al., 2025). Reviewed and approved by a human before this PR was opened.