agent-framework-js 0.4.2 → 1.0.0
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.
- package/CHANGELOG.md +15 -0
- package/README.md +5 -0
- package/package.json +1 -1
package/CHANGELOG.md
CHANGED
|
@@ -7,6 +7,21 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
|
|
7
7
|
|
|
8
8
|
## [Unreleased]
|
|
9
9
|
|
|
10
|
+
## [1.0.0] - 2026-06-17
|
|
11
|
+
|
|
12
|
+
First stable release. The public API across `core`, `providers`, `tools`, `agents`, `mcp`, `skills`,
|
|
13
|
+
`workflows`, `middleware`, `persistence`, `observability`, and `declarative` is now considered
|
|
14
|
+
stable and follows semantic versioning.
|
|
15
|
+
|
|
16
|
+
### Added
|
|
17
|
+
|
|
18
|
+
- **Definitive orchestration recipes for AI agents** in the agent-usage skill
|
|
19
|
+
(`.github/skills/agent-framework-usage/SKILL.md`): Recipe A — orchestrator with subagents exposed
|
|
20
|
+
as tools (dynamic routing, multi-turn `Thread`); Recipe B — fixed `Planner → Calculator →
|
|
21
|
+
Summarizer` pipeline via a streamed sequential workflow. The workflow section now documents
|
|
22
|
+
`runStream` events (`round` / `awaiting-input` / `done`) and the small/local-model robustness
|
|
23
|
+
guarantee. README cross-links each runnable example to its recipe.
|
|
24
|
+
|
|
10
25
|
## [0.4.2] - 2026-06-17
|
|
11
26
|
|
|
12
27
|
### Fixed
|
package/README.md
CHANGED
|
@@ -139,6 +139,11 @@ as a live check of the public API. Each of the three scenarios ships in two flav
|
|
|
139
139
|
| Multi-turn orchestrator + 2 subagents | `examples/backend/orchestrator-subagents` | `examples/frontend/orchestrator-subagents` |
|
|
140
140
|
| Workflow with live agent-order visuals | `examples/backend/workflow-visual` | `examples/frontend/workflow-visual` |
|
|
141
141
|
|
|
142
|
+
The two multi-agent scenarios map to the **definitive orchestration recipes** documented for AI
|
|
143
|
+
agents in the [agent-usage skill](.github/skills/agent-framework-usage/SKILL.md#7-orchestration-recipes-end-to-end--the-definitive-patterns):
|
|
144
|
+
the *orchestrator + subagents* example is **Recipe A** (subagents exposed as tools, dynamic routing)
|
|
145
|
+
and the *workflow* example is **Recipe B** (a fixed `Planner → Calculator → Summarizer` pipeline).
|
|
146
|
+
|
|
142
147
|
Every example has a **GitHub Copilot ⇄ LM Studio** toggle (LM Studio is assumed to be running
|
|
143
148
|
locally). The differences between the two flavors mirror real deployment constraints:
|
|
144
149
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "agent-framework-js",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "1.0.0",
|
|
4
4
|
"description": "Modular, tree-shakeable JavaScript/TypeScript agent framework for no-backend deployments (browser, edge, Node). Agents, tools, MCP, skills, multi-agent workflows, middleware, persistence, and OpenTelemetry observability.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"license": "MIT",
|