feat: build an AI agent from 0 to 1 -- 11 progressive sessions

- 11 sessions from basic agent loop to autonomous teams
- Python MVP implementations for each session
- Mental-model-first docs in en/zh/ja
- Interactive web platform with step-through visualizations
- Incremental architecture: each session adds one mechanism

web/src/data/scenarios/s03.json

@@ -0,0 +1,53 @@
+{
+  "version": "s03",
+  "title": "TodoWrite",
+  "description": "Agent creates a visible plan before executing",
+  "steps": [
+    {
+      "type": "user_message",
+      "content": "Build a CLI calculator that supports add, subtract, multiply, divide",
+      "annotation": "A multi-step task that benefits from planning"
+    },
+    {
+      "type": "tool_call",
+      "content": "[\n  { \"id\": 1, \"task\": \"Create calc.py with argument parsing\", \"status\": \"in_progress\" },\n  { \"id\": 2, \"task\": \"Implement 4 operations\", \"status\": \"pending\" },\n  { \"id\": 3, \"task\": \"Add error handling\", \"status\": \"pending\" },\n  { \"id\": 4, \"task\": \"Test all operations\", \"status\": \"pending\" }\n]",
+      "toolName": "todo_write",
+      "annotation": "TodoManager creates a visible plan BEFORE any code is written"
+    },
+    {
+      "type": "tool_result",
+      "content": "Todo list created with 4 tasks",
+      "toolName": "todo_write",
+      "annotation": "The plan is now visible and trackable"
+    },
+    {
+      "type": "tool_call",
+      "content": "calc.py\n---\nimport sys\n\ndef calculate(op, a, b):\n    ops = {'+': a+b, '-': a-b, '*': a*b, '/': a/b}\n    return ops.get(op, 'Unknown operator')\n\nif __name__ == '__main__':\n    a, op, b = float(sys.argv[1]), sys.argv[2], float(sys.argv[3])\n    print(calculate(op, a, b))",
+      "toolName": "write_file",
+      "annotation": "Executing task #1 and #2: create file with operations"
+    },
+    {
+      "type": "tool_result",
+      "content": "File written successfully",
+      "toolName": "write_file",
+      "annotation": "Code written"
+    },
+    {
+      "type": "tool_call",
+      "content": "python calc.py 10 + 5",
+      "toolName": "bash",
+      "annotation": "Executing task #4: testing"
+    },
+    {
+      "type": "tool_result",
+      "content": "15.0",
+      "toolName": "bash",
+      "annotation": "Test passes"
+    },
+    {
+      "type": "assistant_text",
+      "content": "Calculator built and tested. All 4 operations work correctly.",
+      "annotation": "Visible plans improve task completion by making progress trackable"
+    }
+  ]
+}