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

agents/s01_agent_loop.py

@@ -0,0 +1,105 @@
+#!/usr/bin/env python3
+"""
+s01_agent_loop.py - The Agent Loop
+
+The entire secret of coding agents in one pattern:
+
+    while stop_reason == "tool_use":
+        response = LLM(messages, tools)
+        execute tools
+        append results
+
+    +----------+      +-------+      +---------+
+    |   User   | ---> |  LLM  | ---> |  Tool   |
+    |  prompt  |      |       |      | execute |
+    +----------+      +---+---+      +----+----+
+                          ^               |
+                          |   tool_result |
+                          +---------------+
+                          (loop continues)
+
+That's it. The ENTIRE agent is a while loop that feeds tool
+results back to the model until the model decides to stop.
+"""
+
+import os
+import subprocess
+
+from anthropic import Anthropic
+from dotenv import load_dotenv
+
+load_dotenv(override=True)
+
+if os.getenv("ANTHROPIC_BASE_URL"):
+    os.environ.pop("ANTHROPIC_AUTH_TOKEN", None)
+
+client = Anthropic(base_url=os.getenv("ANTHROPIC_BASE_URL"))
+MODEL = os.environ["MODEL_ID"]
+
+SYSTEM = f"You are a coding agent at {os.getcwd()}. Use bash to solve tasks. Act, don't explain."
+
+TOOLS = [{
+    "name": "bash",
+    "description": "Run a shell command.",
+    "input_schema": {
+        "type": "object",
+        "properties": {"command": {"type": "string"}},
+        "required": ["command"],
+    },
+}]
+
+
+def run_bash(command: str) -> str:
+    dangerous = ["rm -rf /", "sudo", "shutdown", "reboot", "> /dev/"]
+    if any(d in command for d in dangerous):
+        return "Error: Dangerous command blocked"
+    try:
+        r = subprocess.run(command, shell=True, cwd=os.getcwd(),
+                           capture_output=True, text=True, timeout=120)
+        out = (r.stdout + r.stderr).strip()
+        return out[:50000] if out else "(no output)"
+    except subprocess.TimeoutExpired:
+        return "Error: Timeout (120s)"
+
+
+# -- The core pattern: a while loop that calls tools until the model stops --
+def agent_loop(messages: list):
+    while True:
+        response = client.messages.create(
+            model=MODEL, system=SYSTEM, messages=messages,
+            tools=TOOLS, max_tokens=8000,
+        )
+        # Append assistant turn
+        messages.append({"role": "assistant", "content": response.content})
+        # If the model didn't call a tool, we're done
+        if response.stop_reason != "tool_use":
+            return
+        # Execute each tool call, collect results
+        results = []
+        for block in response.content:
+            if block.type == "tool_use":
+                print(f"\033[33m$ {block.input['command']}\033[0m")
+                output = run_bash(block.input["command"])
+                print(output[:200])
+                results.append({"type": "tool_result", "tool_use_id": block.id,
+                                "content": output})
+        messages.append({"role": "user", "content": results})
+
+
+if __name__ == "__main__":
+    history = []
+    while True:
+        try:
+            query = input("\033[36ms01 >> \033[0m")
+        except (EOFError, KeyboardInterrupt):
+            break
+        if query.strip().lower() in ("q", "exit", ""):
+            break
+        history.append({"role": "user", "content": query})
+        agent_loop(history)
+        response_content = history[-1]["content"]
+        if isinstance(response_content, list):
+            for block in response_content:
+                if hasattr(block, "text"):
+                    print(block.text)
+        print()