Weight personality and tonal reactions in the reflection prompt#217
Merged
Conversation
The reflection agent already enumerated four analysis axes (user facts, personality signals, reactions, self-guidance), but treated them as co-equal. Left to its defaults a model harvests concrete facts - the easy, extractable layer - and glosses over the behavioral signal that actually changes how the next turn should sound: how the user reacted to the assistant's tone and phrasing. Give the personality and reaction axes an explicit "pay special attention" weight, and name tone directly (the register the user uses and the register they want back, whether a phrasing landed or missed). Add a closing line stating the priority outright - fact extraction is the floor, not the goal; a future turn improves more from knowing how this person likes to be talked to than from another stored fact. Sync the design-comment block and the user-facing memory doc to the strengthened emphasis.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
SYNOPSIS
Give the reflection agent's personality and reaction analysis axes explicit weight, and name tone directly.
PURPOSE
The reflection prompt currently enumerates four analysis axes (user facts, personality signals, reactions, self-guidance) as co-equal. Left to its defaults a model harvests the easy, extractable layer - concrete facts - and glosses over the behavioral signal that actually changes how the next turn should sound: how the user reacted to the assistant's tone and phrasing. The result is a memory store that knows what the user does but not how they like to be talked to.
DESCRIPTION
How it behaves now.
REFLECTION_PROMPTlists four bullets the agent should "think about." Personality and reactions are present but flat - "how they communicate, what they value" and "did they push back? agree? redirect?" - with no signal that these matter more than fact extraction.What this PR changes, parallel to the same axes:
docs/user/memory.md) synced to the strengthened emphasis.How that closes the loop. Naming tone explicitly and weighting the two behavioral axes pushes the agent past easy fact-harvesting into capturing how this person likes to be addressed - the data a future turn most benefits from.
Notes:
https://claude.ai/code/session_01E2b3VvyyEgZwjvczp1jvUg
Generated by Claude Code