@aman_asmuei/aman-agent 0.26.0 → 0.28.0

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 +25 -11
  2. package/dist/index.js +1153 -238
  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-v0260)
50
+ - [What's New](#whats-new-in-v0280)
51
51
  - [The Problem](#the-problem)
52
52
  - [The Solution](#the-solution)
53
53
  - [Quick Start](#quick-start)
@@ -80,24 +80,38 @@
80
80
 
81
81
  ---
82
82
 
83
- ## What's New in v0.26.0
83
+ ## What's New in v0.28.0
84
84
 
85
- > **Your agent learns new skills from its own sessions.**
85
+ > **The learning loop is complete.**
86
86
 
87
- When a post-mortem runs, the LLM now proposes 0–2 reusable procedures it noticed you demonstrated. You accept or reject each one via a simple prompt at session end. Accepted skills are written to `~/.askill/skills.md` with embedded trigger keywords and **auto-activate** on subsequent sessions — zero extra LLM calls.
87
+ aman-agent now closes the full crystallization + adaptive intelligence cycle. Rejected skills are remembered. Repeated suggestions get reinforced. Near-duplicates get merged with version history. Nudges adapt to your actual response patterns. Frustration is predicted before it happens. All zero or near-zero LLM overhead.
88
88
 
89
89
  | Feature | What it does |
90
90
  |:---|:---|
91
- | **Skill crystallization** | Post-mortems identify reusable procedures → opt-in prompt → saved as auto-triggering skills |
92
- | **Runtime trigger matching** | Crystallized skills merge with hardcoded skill triggers — keyword match fires both |
93
- | **`/skills crystallize`** | Manually crystallize skills from the most recent post-mortem JSON sidecar |
94
- | **`/skills list --auto`** | List all crystallized skills with dates, confidence, and trigger keywords |
95
- | **Post-mortem JSON sidecar** | Every post-mortem now writes a `.json` alongside the `.md` for lossless re-parsing |
96
- | **Extended LLM schema** | Post-mortem prompt includes crystallization rules — narrow, reusable, confidence-gated |
91
+ | **Rejection feedback loop** | Rejected skill names injected into postmortem prompt — agent won't suggest them again |
92
+ | **Cross-session reinforcement** | Tracks how many times each skill candidate appears; auto-recommends after 3+ suggestions |
93
+ | **Skill merging + versioning** | Near-duplicate skills prompt merge instead of skip; old versions archived as `.v1`, `.v2`, etc. |
94
+ | **Adaptive nudge learning** | Wellbeing nudges that consistently precede low-rated sessions get automatically suppressed |
95
+ | **Semantic trigger matching** | TF-IDF cosine similarity alongside keyword matching — skills trigger on meaning, not just words |
96
+ | **Feed-forward v2** | Preemptive context injection from frustration correlations (late-night, long sessions) |
97
+ | **LLM-based sentiment** | Piggybacks tone analysis on memory extraction — zero extra LLM calls |
98
+ | **Burnout predictor** | Forecasts burnout risk from session patterns; surfaces care nudge when risk > 70% |
99
+ | **`/skills list --auto`** | Now shows reinforcement count (★) and version history per skill |
97
100
 
98
101
  <details>
99
102
  <summary><strong>Highlights from earlier releases</strong></summary>
100
103
 
104
+ **v0.27 — Dynamic user model**
105
+ - Cross-session profile: trust (EMA), sentiment baseline, energy distribution
106
+ - Feed-forward personalized energy/mode overrides
107
+ - Frustration correlations (Pearson r), nudge tracking
108
+ - `/identity dynamics` view + `--json` + `--reset`
109
+
110
+ **v0.26 — Skill crystallization**
111
+ - Post-mortems identify reusable procedures → opt-in prompt → saved as auto-triggering skills
112
+ - Runtime trigger matching, `/skills crystallize`, `/skills list --auto`
113
+ - Post-mortem JSON sidecar for lossless re-parsing
114
+
101
115
  **v0.24 — Observation & post-mortem**
102
116
  - Passive session telemetry (tool calls, errors, file changes, sentiment, blockers)
103
117
  - LLM-generated post-mortem reports with smart auto-trigger
@@ -1044,7 +1058,7 @@ On session end, if any smart trigger fires (≥3 tool errors, ≥2 blockers, &gt
1044
1058
  | `/profile` | Your profile + agent profiles `[me\|edit\|setup\|create\|list\|show\|delete]` |
1045
1059
  | `/delegate` | Delegate task to a profile `[<profile> <task>\|pipeline]` |
1046
1060
  | `/team` | Manage agent teams `[create\|run\|list\|show\|delete]` |
1047
- | `/identity` | View identity `[update <section>]` |
1061
+ | `/identity` | View identity `[update <section>]` `[dynamics [--json\|--reset]]` |
1048
1062
  | `/rules` | View guardrails `[add\|remove\|toggle ...]` |
1049
1063
  | `/workflows` | View workflows `[add\|remove ...]` |
1050
1064
  | `/tools` | View tools `[add\|remove ...]` |