agent-work-layer 0.1.0 → 0.1.1

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.
Files changed (3) hide show
  1. package/CHANGELOG.md +5 -0
  2. package/README.md +18 -1
  3. package/package.json +10 -2
package/CHANGELOG.md CHANGED
@@ -1,5 +1,10 @@
1
1
  # Changelog
2
2
 
3
+ ## 0.1.1 — 2026-10-09
4
+
5
+ - Package metadata now links to the GitHub repository, homepage and issue tracker.
6
+ - README: diagrams, "How it works" section and contributing links.
7
+
3
8
  ## 0.1.0 — 2026-10-09
4
9
 
5
10
  First release.
package/README.md CHANGED
@@ -10,6 +10,19 @@
10
10
 
11
11
  Agent Cards say who an agent is. A2A carries messages between agents. MCP connects agents to tools. AWL describes **the job itself**, so any manager can hand work to any worker and check what came back. The format is defined in [SPEC.md](SPEC.md).
12
12
 
13
+ <p align="center"><img src="docs/layers.svg" alt="Manager and worker agents connected by Agent Card, A2A and the AWL work layer; the worker reaches tools through MCP" width="760"></p>
14
+
15
+ ## How it works
16
+
17
+ 1. A manager issues a **Work Order**: goal, criteria, budget, deadline, allowed tools.
18
+ 2. A worker accepts it and does the job with its tools.
19
+ 3. The worker returns a **Work Report** with evidence for every criterion and what it spent.
20
+ 4. The desk checks the report against the order. The manager approves it or sends it back.
21
+
22
+ <p align="center"><img src="docs/fields.svg" alt="Each Work Report field answers a Work Order field: evidence proves criteria, cost stays within budget, tools used stay within allowed tools" width="760"></p>
23
+
24
+ More diagrams: [message sequence](docs/sequence.svg) · [lifecycle](docs/lifecycle.svg) · [delegation](docs/delegation.svg)
25
+
13
26
  ## Install
14
27
 
15
28
  ```sh
@@ -183,6 +196,10 @@ npm run test:package # builds, packs, installs the tarball in a clean project
183
196
  npm run check # all of the above; runs automatically before npm publish
184
197
  ```
185
198
 
199
+ ## Contributing
200
+
201
+ Issues, ideas and pull requests are welcome. See [CONTRIBUTING.md](CONTRIBUTING.md) and the [roadmap](ROADMAP.md). Spec changes start as a **Spec proposal** issue.
202
+
186
203
  ## License
187
204
 
188
- Apache-2.0
205
+ [Apache-2.0](LICENSE). You can use, modify and ship it, including commercially. The license includes a patent grant.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "agent-work-layer",
3
- "version": "0.1.0",
3
+ "version": "0.1.1",
4
4
  "description": "Work Orders and Work Reports for AI agents: a typed SDK, validator, lifecycle desk and MCP server.",
5
5
  "keywords": [
6
6
  "ai",
@@ -14,7 +14,7 @@
14
14
  "orchestration"
15
15
  ],
16
16
  "license": "Apache-2.0",
17
- "author": "Murthy Guruswamy",
17
+ "author": "Probita",
18
18
  "type": "module",
19
19
  "engines": {
20
20
  "node": ">=20.11"
@@ -65,5 +65,13 @@
65
65
  },
66
66
  "publishConfig": {
67
67
  "access": "public"
68
+ },
69
+ "repository": {
70
+ "type": "git",
71
+ "url": "git+https://github.com/probita-ai/agent-work-layer.git"
72
+ },
73
+ "homepage": "https://github.com/probita-ai/agent-work-layer#readme",
74
+ "bugs": {
75
+ "url": "https://github.com/probita-ai/agent-work-layer/issues"
68
76
  }
69
77
  }