@aman_asmuei/aman-agent 0.29.0 → 0.30.0

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.
Files changed (4) hide show
  1. package/README.md +11 -6
  2. package/dist/index.js +796 -682
  3. package/dist/index.js.map +1 -1
  4. package/package.json +1 -1
package/README.md CHANGED
@@ -47,7 +47,7 @@
47
47
  <details>
48
48
  <summary><strong>Table of Contents</strong></summary>
49
49
 
50
- - [What's New](#whats-new-in-v0290)
50
+ - [What's New](#whats-new-in-v0300)
51
51
  - [The Problem](#the-problem)
52
52
  - [The Solution](#the-solution)
53
53
  - [Quick Start](#quick-start)
@@ -80,20 +80,25 @@
80
80
 
81
81
  ---
82
82
 
83
- ## What's New in v0.29.0
83
+ ## What's New in v0.30.0
84
84
 
85
- > **Ecosystem parity — the knowledge graph wires up.**
85
+ > **Agent hardening — trust, durability, and insight.**
86
86
 
87
- Memories now auto-relate after extraction, building a knowledge graph of connected insights across sessions. Admin tools for memory health diagnostics, repair, config, and reflection are fully wired. Stale references cleaned up.
87
+ The agent now asks before delegating, persists background task state across crashes, and gives you a real analytics dashboard in `/eval report`.
88
88
 
89
89
  | Feature | What it does |
90
90
  |:---|:---|
91
- | **Auto-relate memories** | After each successful extraction, `autoRelateMemory` finds and links semantically similar memories — builds a knowledge graph automatically |
92
- | **Stale reference cleanup** | `aman-claude-code` → `aman-plugin` across all docs |
91
+ | **Delegation confirmation** | Agent prompts you before executing `delegate_task` or `team_run` — no silent autonomous work |
92
+ | **Persistent background tasks** | Background task state saved to `~/.aman-agent/bg-tasks.json` — survives crashes, visible in `/eval report` |
93
+ | **Rich `/eval report`** | Shows trust score, sentiment trend, energy distribution, burnout risk, frustration correlations, and background task stats |
93
94
 
94
95
  <details>
95
96
  <summary><strong>Highlights from earlier releases</strong></summary>
96
97
 
98
+ **v0.29 — Ecosystem parity**
99
+ - Auto-relate memories after extraction (knowledge graph edges)
100
+ - Stale reference cleanup
101
+
97
102
  **v0.28 — Learning loop completion**
98
103
  - Rejection feedback, cross-session reinforcement, skill merging + versioning
99
104
  - Adaptive nudge learning, semantic trigger matching, feed-forward v2