chore(config): lower default thresholds for faster skill evolution#1572
Merged
hijzy merged 1 commit intoApr 28, 2026
Merged
Conversation
Aligns built-in defaults with the values most installs already override in ~/.<agent>/memos-plugin/config.yaml. Strict legacy thresholds were starving the L2/L3/skill pipeline in real usage — candidate skills rarely promoted, world models never clustered. Changes (defaults.ts): reward.minExchangesForCompletion 2 → 1 reward.minContentCharsForCompletion 80 → 40 retrieval.minTraceSim 0.35 → 0.25 retrieval.llmFilterMinCandidates 1 → 2 l2Induction.minTraceValue 0.01 → 0.005 l3Abstraction.cooldownDays 1 → 0 l3Abstraction.clusterMinSimilarity 0.6 → 0.3 skill.minSupport 2 → 1 skill.candidateTrials 3 → 1 skill.cooldownMs 6 hours → 0 User-supplied config.yaml values continue to take precedence via the existing deep-merge in loadConfig().
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Aligns the built-in defaults in
core/config/defaults.tswith the values most installs already override in~/.<agent>/memos-plugin/config.yaml. The strict legacy thresholds were starving the L2/L3/skill pipeline in real usage — candidate skills rarely promoted to active, world models never clustered enough policies, and reward scoring ignored short single-exchange turns.reward.minExchangesForCompletionreward.minContentCharsForCompletionretrieval.minTraceSimretrieval.llmFilterMinCandidatesl2Induction.minTraceValuel3Abstraction.cooldownDaysl3Abstraction.clusterMinSimilarityskill.minSupportskill.candidateTrialsskill.cooldownMsUser-supplied
config.yamlvalues continue to take precedence via the existing deep-merge inloadConfig().Test plan