Spike: agent-side diary consolidation workflow and evals#585
Draft
legreffier[bot] wants to merge 1 commit intomainfrom
Draft
Spike: agent-side diary consolidation workflow and evals#585legreffier[bot] wants to merge 1 commit intomainfrom
legreffier[bot] wants to merge 1 commit intomainfrom
Conversation
MoltNet-Diary: f63d8d9f-2558-41a8-9e81-02d24dd24ac3 Task-Group: agent-side-consolidation-skill Task-Family: feature Refs: #584
Contributor
🚨 Dependency Audit — Vulnerabilities foundFull report |
Contributor
|
Owner
|
@claude review |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Agent-Side Consolidation Skill Spike
Summary
legreffier-consolidateis currently stronger in documentation than inimplementation. The product schema supports a useful relation graph, but the
existing consolidation story is still too server-centric and too weakly
auditable for trustworthy diary maintenance.
This spike proposes an intentional, agent-driven consolidation workflow.
Problem
contradiction vs elaboration, causal chain vs temporal adjacency, replacement
vs disagreement, implementation reference vs same-topic similarity
auto-accepts relations
Proposal
Treat consolidation as editorial graph curation:
proposedrelations by defaultmetadata to every proposal
Relation policy
The skill should support:
supportselaboratescontradictscaused_byreferencessupersedesNo auto-accept by default.
Dream pass
A dream pass should be a bounded background proposal loop:
20-40entries or one subsystem sliceDeliverables in this spike
.agents/skills/legreffier-consolidate/SKILL.mdhandling, dream-pass guardrails, and verification
Follow-up work
align the server-side
diaries_consolidateendpoint with an agent-side reviewrole instead of pretending to perform semantic consolidation
define a stable metadata schema for relation proposals
decide whether any narrow auto-accept rules are ever acceptable
evaluate whether accepted/proposed relations should influence pack ranking
differently
Fixes Spike agent-side diary consolidation workflow and evals #584