refactor: Update agent skills and version to 0.12.1; refactor tools to skills

Signed-off-by: Eden Reich <[email protected]>

Author: edenreich

.well-known/agent.json

@@ -38,38 +38,33 @@ docker run -p 8080:8080 documentation-agent
 - `GET /health` - Health check endpoint
 - `POST /a2a` - A2A protocol endpoint
 
-## Available Tools
-- **resolve_library_id** - Resolves library by its id
-- **get_library_docs** - Get the docs for the specific library
+## Available Skills
+
+| Skill | Description | Parameters |
+|-------|-------------|------------|
+| `resolve_library_id` | Resolves library by its id |id |
+| `get_library_docs` | Get the docs for the specific library |library |
 
 ## Configuration
 
 Configure the agent via environment variables:
 
-### Core Application Settings
-
-- `ENVIRONMENT` - Deployment environment
-
-### A2A Agent Configuration
-
-#### Server Configuration
-
-- `A2A_SERVER_PORT` - Server port (default: `8080`)
-- `A2A_SERVER_READ_TIMEOUT` - Maximum duration for reading requests (default: `120s`)
-- `A2A_SERVER_WRITE_TIMEOUT` - Maximum duration for writing responses (default: `120s`)
-- `A2A_SERVER_IDLE_TIMEOUT` - Maximum time to wait for next request (default: `120s`)
-- `A2A_SERVER_DISABLE_HEALTHCHECK_LOG` - Disable logging for health check requests (default: `true`)
-
-#### LLM Client Configuration
-
-- `A2A_AGENT_CLIENT_PROVIDER` - LLM provider: `openai`, `anthropic`, `groq`, `ollama`, `deepseek`, `cohere`, `cloudflare`
-- `A2A_AGENT_CLIENT_MODEL` - Model to use
-- `A2A_AGENT_CLIENT_API_KEY` - API key for LLM provider
-- `A2A_AGENT_CLIENT_BASE_URL` - Custom LLM API endpoint
-- `A2A_AGENT_CLIENT_TIMEOUT` - Timeout for LLM requests (default: `30s`)
-- `A2A_AGENT_CLIENT_MAX_RETRIES` - Maximum retries for LLM requests (default: `3`)
-- `A2A_AGENT_CLIENT_MAX_TOKENS` - Maximum tokens for LLM responses (default: `4096`)
-- `A2A_AGENT_CLIENT_TEMPERATURE` - Controls randomness of LLM output (default: `0.7`)
+| Category | Variable | Description | Default |
+|----------|----------|-------------|---------|
+| **Core Application** | `ENVIRONMENT` | Deployment environment | - |
+| **Server** | `A2A_SERVER_PORT` | Server port | `8080` |
+| **Server** | `A2A_SERVER_READ_TIMEOUT` | Maximum duration for reading requests | `120s` |
+| **Server** | `A2A_SERVER_WRITE_TIMEOUT` | Maximum duration for writing responses | `120s` |
+| **Server** | `A2A_SERVER_IDLE_TIMEOUT` | Maximum time to wait for next request | `120s` |
+| **Server** | `A2A_SERVER_DISABLE_HEALTHCHECK_LOG` | Disable logging for health check requests | `true` |
+| **LLM Client** | `A2A_AGENT_CLIENT_PROVIDER` | LLM provider (`openai`, `anthropic`, `groq`, `ollama`, `deepseek`, `cohere`, `cloudflare`) | - |
+| **LLM Client** | `A2A_AGENT_CLIENT_MODEL` | Model to use | - |
+| **LLM Client** | `A2A_AGENT_CLIENT_API_KEY` | API key for LLM provider | - |
+| **LLM Client** | `A2A_AGENT_CLIENT_BASE_URL` | Custom LLM API endpoint | - |
+| **LLM Client** | `A2A_AGENT_CLIENT_TIMEOUT` | Timeout for LLM requests | `30s` |
+| **LLM Client** | `A2A_AGENT_CLIENT_MAX_RETRIES` | Maximum retries for LLM requests | `3` |
+| **LLM Client** | `A2A_AGENT_CLIENT_MAX_TOKENS` | Maximum tokens for LLM responses |`4096` |
+| **LLM Client** | `A2A_AGENT_CLIENT_TEMPERATURE` | Controls randomness of LLM output |`0.7` |
 
 ## Development
 

Dockerfile

@@ -16,9 +16,11 @@ spec:
       You are a helpful assistant for managing and searching through Documentations queries.
     maxTokens: 4096
     temperature: 0.7
-  tools:
-    - name: resolve_library_id
+  skills:
+    - id: resolve_library_id
+      name: resolve_library_id
       description: "Resolves library by its id"
+      tags: ["docs", "libraries"]
       schema:
         type: object
         properties:
@@ -27,8 +29,10 @@ spec:
             description: "Library ID"
         required:
           - id
-    - name: get_library_docs
+    - id: get_library_docs
+      name: get_library_docs
       description: "Get the docs for the specific library"
+      tags: ["docs", "libraries"]
       schema:
         type: object
         properties: