From f97b0d9e901b74790d42a42840f0e1db6ad44a2b Mon Sep 17 00:00:00 2001 From: Theodore Song Date: Fri, 21 Aug 2026 15:11:31 -0400 Subject: [PATCH] Expand agent-scoped learning capacity --- README.md | 8 ++++++++ index.html | 13 +++++++------ sw.js | 2 +- 3 files changed, 16 insertions(+), 7 deletions(-) diff --git a/README.md b/README.md index c342482..28f6496 100644 --- a/README.md +++ b/README.md @@ -329,6 +329,14 @@ lists the agents that earned an aggregate promotion. Explicit empty scopes do not leak to any agent, legacy unlabeled outcomes remain readable for migration, and eligibility metadata survives local/offline and cloud-state compaction. +Build 80 expands the pending forward-research queue from 300 to 600 records and +the retained graded history from 500 to 1,000 outcomes. This keeps the 300 +legacy observations through their remaining checkpoints while opening capacity +for strategy-scoped observations immediately. The larger history retains enough +independent events for per-agent 6-hour risk vetoes and 24-hour/72-hour +promotion confidence checks without relaxing execution, cost, or evidence +requirements. + Build 77 separates the directional learner's evidence lineage from the global strategy release. Code-history verification found the same trend/reversal generator and 24-hour/72-hour grading policy in Strategy 51 through Strategy diff --git a/index.html b/index.html index 82f0d1a..9de5818 100644 --- a/index.html +++ b/index.html @@ -341,7 +341,7 @@ footer{margin-top:34px;padding-top:22px;border-top:1px solid var(--border);color