agentic-flow 1.5.4 → 1.5.5
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.
package/CHANGELOG.md
CHANGED
|
@@ -5,6 +5,18 @@ All notable changes to this project will be documented in this file.
|
|
|
5
5
|
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
|
|
6
6
|
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
|
|
7
7
|
|
|
8
|
+
## [1.5.5] - 2025-10-11
|
|
9
|
+
|
|
10
|
+
### Fixed
|
|
11
|
+
- **Enhancement:** Added dotenv loading to ReasoningBank demo
|
|
12
|
+
- Demo now loads `.env` file automatically to pick up ANTHROPIC_API_KEY
|
|
13
|
+
- Enables full LLM-powered judgment and distillation when API key is available
|
|
14
|
+
- Falls back gracefully to template-based approach when key is missing
|
|
15
|
+
|
|
16
|
+
### Technical Details
|
|
17
|
+
- Added `import { config } from 'dotenv'; config();` to demo-comparison.ts
|
|
18
|
+
- Ensures environment variables are loaded before ReasoningBank initialization
|
|
19
|
+
|
|
8
20
|
## [1.5.4] - 2025-10-11
|
|
9
21
|
|
|
10
22
|
### Fixed
|
|
@@ -6,6 +6,9 @@
|
|
|
6
6
|
* 1. Traditional approach: Agent starts fresh every time
|
|
7
7
|
* 2. ReasoningBank approach: Agent learns from experience
|
|
8
8
|
*/
|
|
9
|
+
// Load environment variables from .env file
|
|
10
|
+
import { config } from 'dotenv';
|
|
11
|
+
config();
|
|
9
12
|
import { initialize, runTask, retrieveMemories, db } from './index.js';
|
|
10
13
|
console.log('🎯 ReasoningBank vs Traditional Approach - Live Demo\n');
|
|
11
14
|
console.log('='.repeat(80));
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "agentic-flow",
|
|
3
|
-
"version": "1.5.
|
|
3
|
+
"version": "1.5.5",
|
|
4
4
|
"description": "Production-ready AI agent orchestration platform with 66 specialized agents, 213 MCP tools, ReasoningBank learning memory, and autonomous multi-agent swarms. Built by @ruvnet with Claude Agent SDK, neural networks, memory persistence, GitHub integration, and distributed consensus protocols.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "dist/index.js",
|