Add amber manifest

Author: staverm

README.md

@@ -12,8 +12,9 @@ src/
 └─ messenger.py   # A2A messaging utilities
 tests/
 └─ test_agent.py  # Agent tests
-Dockerfile        # Docker configuration
-pyproject.toml    # Python dependencies
+Dockerfile            # Docker configuration
+pyproject.toml        # Python dependencies
+amber-manifest.json5  # Amber manifest
 .github/
 └─ workflows/
    └─ test-and-publish.yml # CI workflow
@@ -27,7 +28,9 @@ pyproject.toml    # Python dependencies
 
 3. **Configure your agent card** - Fill in your agent's metadata (name, skills, description) in [`src/server.py`](src/server.py)
 
-4. **Write your tests** - Add custom tests for your agent in [`tests/test_agent.py`](tests/test_agent.py)
+4. **Fill out your [Amber](https://github.com/RDI-Foundation/amber) manifest** - Update [`amber-manifest.json5`](amber-manifest.json5) to use your agent in Amber scenarios
+
+5. **Write your tests** - Add custom tests for your agent in [`tests/test_agent.py`](tests/test_agent.py)
 
 For a concrete example of implementing a green agent using this template, see this [draft PR](https://github.com/RDI-Foundation/green-agent-template/pull/3).
 

amber-manifest.json5

@@ -0,0 +1,51 @@
+{
+  manifest_version: "0.1.0",
+
+  // TODO: Declare all config your agent needs from the deployer
+  // Use secret: true for sensitive values like API keys
+  config_schema: {
+    type: "object",
+    properties: {
+      my_api_key: { type: "string", secret: true },
+    },
+    required: ["my_api_key"],
+    additionalProperties: false,
+  },
+
+  // External services this agent uses
+  slots: {
+    proxy: { kind: "a2a", optional: true },
+  },
+
+  // Runtime configuration
+  program: {
+    // TODO: Replace with your docker image
+    image: "ghcr.io/<your-username>/<your-repo-name>:latest",
+    entrypoint: "uv run python src/server.py --host 0.0.0.0 --port 9009",
+
+    // TODO: Pass config values as environment variables
+    env: {
+      MY_API_KEY: "${config.my_api_key}",
+    },
+
+    network: {
+      endpoints: [
+        { name: "a2a_endpoint", port: 9009 }, // ensure port matches your entrypoint
+      ],
+    },
+  },
+
+  // Capabilities provided by this agent
+  provides: {
+    a2a: { kind: "a2a", endpoint: "a2a_endpoint" },
+  },
+
+  // Capabilities exposed to the scenario
+  exports: { a2a: "a2a" },
+
+  // TODO: Describe the assessment request your green agent receives
+  metadata: {
+    assessment_config: {}, // replace with your default assessment parameters, e.g. {"num_rounds": 2}
+    participant_roles: [], // list the roles your green agent expects, e.g. ["pro_debater", "con_debater"]
+  },
+}