Add AI module with A2A wrapper and task agent

- Disable FuzzForge MCP connection (no Prefect backend)
- Add a2a_wrapper module for programmatic A2A agent tasks
- Add task_agent (LiteLLM A2A agent) on port 10900
- Create volumes/env/ for centralized Docker config
- Update docker-compose.yml with task-agent service
- Remove workflow_automation_skill from agent card

volumes/env/.env.example

@@ -0,0 +1,17 @@
+# FuzzForge Agent Configuration
+# Copy this to .env and configure your API keys
+
+# LiteLLM Model Configuration
+LITELLM_MODEL=gemini/gemini-2.0-flash-001
+# LITELLM_PROVIDER=gemini
+
+# API Keys (uncomment and configure as needed)
+# GOOGLE_API_KEY=
+# OPENAI_API_KEY=
+# ANTHROPIC_API_KEY=
+# OPENROUTER_API_KEY=
+# MISTRAL_API_KEY=
+
+# Agent Configuration
+# DEFAULT_TIMEOUT=120
+# DEFAULT_CONTEXT_ID=default

volumes/env/README.md

@@ -0,0 +1,22 @@
+# FuzzForge Environment Configuration
+
+This directory contains environment files that are mounted into Docker containers.
+
+## Files
+
+- `.env.example` - Template configuration file
+- `.env` - Your actual configuration (create by copying .env.example)
+
+## Usage
+
+1. Copy the example file:
+   ```bash
+   cp .env.example .env
+   ```
+
+2. Edit `.env` and add your API keys
+
+3. Restart Docker containers to apply changes:
+   ```bash
+   docker-compose restart
+   ```