feat(memory): codify SNR + latent structure as Prime Axioms#142
Merged
Conversation
memory-maintainer.md previously leaned on an unnamed heuristic
("you are not a note-taker", "every line must be high-value")
backed by a flat What Belongs / Does NOT Belong list. The agent
had no authoritative tiebreaker when workflow steps appeared to
permit noise, and no macro-level rule connecting multiple surface
observations to a single latent cause.
Promote the heuristic into two named axioms above Workflow:
- Axiom 1 (SNR per entry) — refuse entries reconstructible from
code / git log / LOOPAL.md in ~30s; SNR overrides explicit
user save requests.
- Axiom 2 (latent structure across entries) — the index encodes
latent causes, not surface symptoms; sharpen / merge / revise
instead of accumulating exception entries. The index should
read as an orthogonal factorization of project knowledge.
Axioms apply recursively to MEMORY.md itself.
Why: gives the agent an authoritative tiebreaker when later
workflow steps seem to permit noise, and a macro-level rule
that the negative-exemplar list alone could not express.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
## Prime Axiomssection in the memory-maintainer agent promptcode + git log + LOOPAL.mdin ~30sChanges
crates/loopal-memory/agent-prompts/memory-maintainer.md(+41)Motivation
The existing prompt leaned on an unnamed heuristic ("you are not a note-taker") plus a flat What Belongs / Does NOT Belong list. The agent had:
Promoting the heuristic to two named axioms gives the agent:
Axioms apply recursively to
MEMORY.mditself.Test plan