gossipcat 0.5.6 → 0.6.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -44,8 +44,8 @@
44
44
  <link rel="preconnect" href="https://fonts.googleapis.com">
45
45
  <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
46
46
  <link rel="stylesheet" href="https://fonts.googleapis.com/css2?family=JetBrains+Mono:wght@400;500&family=Fraunces:opsz,wght@9..144,500;9..144,600&display=swap">
47
- <script type="module" crossorigin src="/dashboard/assets/index-Chrn1WHu.js"></script>
48
- <link rel="stylesheet" crossorigin href="/dashboard/assets/index-DUZrYB2U.css">
47
+ <script type="module" crossorigin src="/dashboard/assets/index-Jl6prXe-.js"></script>
48
+ <link rel="stylesheet" crossorigin href="/dashboard/assets/index-BLbA9JYk.css">
49
49
  </head>
50
50
  <body>
51
51
  <div id="root"></div>
@@ -81,7 +81,7 @@ The correct order is always: verify finding → record signal → next finding
81
81
 
82
82
  ## Performance Signals & Agent Scores
83
83
 
84
- Call `gossip_scores()` to see: accuracy (0-1), uniqueness (0-1), dispatchWeight (0.5-1.5).
84
+ Call `gossip_scores()` to see: accuracy (0-1), uniqueness (0-1), dispatchWeight (0.3-2.0).
85
85
  - High-accuracy agents → solo tasks, primary reviewers
86
86
  - High-uniqueness, low-accuracy → always use in consensus, never solo
87
87
  - Check scores periodically to track improvement