Fix empty tool-use response handling

s02_tool_use/README.ja.md

@@ -21,7 +21,7 @@ s01 の Agent には bash 一つのツールしかない。ファイルを読む
 
 ![Tool Dispatch](images/tool-dispatch.ja.svg)
 
-s01 のループは完全に保持される（LLM 呼び出し、stop_reason 判定、メッセージ追加 — 一文字も変更なし）。唯一の変更点はツール実行の 1 行：`run_bash()` が `TOOL_HANDLERS[block.name]()` の検索ディスパッチに置き換わる。
+s01 のループは完全に保持される（LLM 呼び出し、`tool_use` block 判定、メッセージ追加 — 一文字も変更なし）。唯一の変更点はツール実行の 1 行：`run_bash()` が `TOOL_HANDLERS[block.name]()` の検索ディスパッチに置き換わる。
 
 Agent にツールを追加するには、たった二つ：
 
@@ -91,11 +91,10 @@ TOOL_HANDLERS = {
 }
 
 # ループ内で変更されたのは一行だけ — ハードコードの run_bash から検索ディスパッチへ：
-for block in response.content:
-    if block.type == "tool_use":
-        handler = TOOL_HANDLERS[block.name]    # 検索
-        output = handler(**block.input)         # 呼び出し
-        results.append(...)
+for block in tool_calls:
+    handler = TOOL_HANDLERS[block.name]    # 検索
+    output = handler(**block.input)         # 呼び出し
+    results.append(...)
 ```
 
 ツールの追加 = `TOOLS` 配列に一条 + `TOOL_HANDLERS` 辞書に一行。ループは変わらない。
@@ -128,7 +127,7 @@ for block in response.content:
 | ツール数 | 1 (bash) | 5 (+read, write, edit, glob) |
 | ツール実行 | ハードコード `run_bash()` | TOOL_HANDLERS 検索ディスパッチ |
 | パス安全性 | なし | safe_path 検証（file tools のみ） |
-| ループ | `while True` + `stop_reason` | s01 と完全に同一 |
+| ループ | `while True` + `tool_use` block | s01 と完全に同一 |
 
 ---
 

s02_tool_use/README.md

@@ -21,7 +21,7 @@ The model thinks "read this file" but has to spell out `cat path/to/file`. An ex
 
 ![Tool Dispatch](images/tool-dispatch.en.svg)
 
-The s01 loop is fully preserved (LLM call, stop_reason check, message append — not a single word changed). The only change is in that one line of tool execution: `run_bash()` is replaced with `TOOL_HANDLERS[block.name]()` dispatch lookup.
+The s01 loop is fully preserved (LLM call, `tool_use` block check, message append — not a single word changed). The only change is in that one line of tool execution: `run_bash()` is replaced with `TOOL_HANDLERS[block.name]()` dispatch lookup.
 
 Adding a tool to the Agent requires just two things:
 
@@ -91,11 +91,10 @@ TOOL_HANDLERS = {
 }
 
 # Only one line changed in the loop — from hardcoded run_bash to dispatch lookup:
-for block in response.content:
-    if block.type == "tool_use":
-        handler = TOOL_HANDLERS[block.name]    # lookup
-        output = handler(**block.input)         # call
-        results.append(...)
+for block in tool_calls:
+    handler = TOOL_HANDLERS[block.name]    # lookup
+    output = handler(**block.input)         # call
+    results.append(...)
 ```
 
 Adding a tool = one entry in `TOOLS` array + one line in `TOOL_HANDLERS` dict. The loop stays the same.
@@ -128,7 +127,7 @@ Calls are executed one by one in their original `response.content` order.
 | Tool count | 1 (bash) | 5 (+read, write, edit, glob) |
 | Tool execution | Hardcoded `run_bash()` | TOOL_HANDLERS dispatch lookup |
 | Path safety | None | safe_path validation (file tools only) |
-| Loop | `while True` + `stop_reason` | Identical to s01 |
+| Loop | `while True` + `tool_use` block | Identical to s01 |
 
 ---
 

s02_tool_use/README.zh.md

@@ -21,7 +21,7 @@ s01 的 Agent 只有一个 bash 工具。读文件要 `cat`，写文件要 `echo
 
 ![Tool Dispatch](images/tool-dispatch.svg)
 
-s01 的循环完全保留（LLM 调用、stop_reason 判断、消息追加）。唯一的变动在工具执行那 1 行：`run_bash()` 替换为 `TOOL_HANDLERS[block.name]()` 查表分发。
+s01 的循环完全保留（LLM 调用、`tool_use` block 判断、消息追加）。唯一的变动在工具执行那 1 行：`run_bash()` 替换为 `TOOL_HANDLERS[block.name]()` 查表分发。
 
 给 Agent 加一个工具只需要做两件事：
 
@@ -91,11 +91,10 @@ TOOL_HANDLERS = {
 }
 
 # 循环里只改了一行——从硬编码 run_bash 变成查表：
-for block in response.content:
-    if block.type == "tool_use":
-        handler = TOOL_HANDLERS[block.name]    # 查表
-        output = handler(**block.input)         # 调用
-        results.append(...)
+for block in tool_calls:
+    handler = TOOL_HANDLERS[block.name]    # 查表
+    output = handler(**block.input)         # 调用
+    results.append(...)
 ```
 
 加一个工具 = 在 `TOOLS` 数组加一条 + 在 `TOOL_HANDLERS` 字典加一行。循环不变。
@@ -128,7 +127,7 @@ for block in response.content:
 | 工具数量 | 1 (bash) | 5 (+read, write, edit, glob) |
 | 工具执行 | 硬编码 `run_bash()` | TOOL_HANDLERS 查表分发 |
 | 路径安全 | 无 | safe_path 校验（仅 file tools） |
-| 循环 | `while True` + `stop_reason` | 与 s01 完全一致 |
+| 循环 | `while True` + `tool_use` block | 与 s01 完全一致 |
 
 ---
 

s02_tool_use/code.py

@@ -154,17 +154,19 @@ def agent_loop(messages: list):
         )
         messages.append({"role": "assistant", "content": response.content})
 
-        if response.stop_reason != "tool_use":
+        tool_calls = [
+            block for block in response.content if block.type == "tool_use"
+        ]
+        if not tool_calls:
             return
 
         results = []
-        for block in response.content:
-            if block.type == "tool_use":
-                print(f"\033[33m> {block.name}\033[0m")
-                handler = TOOL_HANDLERS.get(block.name)
-                output = handler(**block.input) if handler else f"Unknown: {block.name}"
-                print(str(output)[:200])
-                results.append({"type": "tool_result", "tool_use_id": block.id, "content": output})
+        for block in tool_calls:
+            print(f"\033[33m> {block.name}\033[0m")
+            handler = TOOL_HANDLERS.get(block.name)
+            output = handler(**block.input) if handler else f"Unknown: {block.name}"
+            print(str(output)[:200])
+            results.append({"type": "tool_result", "tool_use_id": block.id, "content": output})
 
         messages.append({"role": "user", "content": results})
 

s02_tool_use/images/tool-dispatch.en.svg

@@ -40,14 +40,14 @@
   <!-- LLM -->
   <rect x="270" y="82" width="150" height="52" rx="8" fill="#fff" stroke="#2563eb" stroke-width="1.5"/>
   <text x="345" y="104" fill="#1e3a5f" font-size="13" font-weight="700" text-anchor="middle">LLM</text>
-  <text x="345" y="122" fill="#64748b" font-size="10" text-anchor="middle">stop_reason check</text>
+  <text x="345" y="122" fill="#64748b" font-size="10" text-anchor="middle">tool_use block check</text>
 
   <!-- Arrow: LLM → Decision -->
   <line x1="345" y1="134" x2="345" y2="162" stroke="#555" stroke-width="1.5" marker-end="url(#arrow)"/>
 
   <!-- Decision Diamond -->
   <polygon points="345,166 415,196 345,226 275,196" fill="#fff8f0" stroke="#d97706" stroke-width="1.5"/>
-  <text x="345" y="194" fill="#92400e" font-size="10" font-weight="600" text-anchor="middle">tool_use?</text>
+  <text x="345" y="194" fill="#92400e" font-size="10" font-weight="600" text-anchor="middle">tool_use block?</text>
 
   <!-- No → Return -->
   <line x1="415" y1="196" x2="475" y2="196" stroke="#16a34a" stroke-width="1.5" marker-end="url(#arrow-green)"/>

s02_tool_use/images/tool-dispatch.ja.svg

@@ -40,14 +40,14 @@
   <!-- LLM -->
   <rect x="270" y="82" width="150" height="52" rx="8" fill="#fff" stroke="#2563eb" stroke-width="1.5"/>
   <text x="345" y="104" fill="#1e3a5f" font-size="13" font-weight="700" text-anchor="middle">LLM</text>
-  <text x="345" y="122" fill="#64748b" font-size="10" text-anchor="middle">stop_reason 判定</text>
+  <text x="345" y="122" fill="#64748b" font-size="10" text-anchor="middle">tool_use block 判定</text>
 
   <!-- 矢印：LLM → 判定 -->
   <line x1="345" y1="134" x2="345" y2="162" stroke="#555" stroke-width="1.5" marker-end="url(#arrow)"/>
 
   <!-- 判定ダイヤモンド -->
   <polygon points="345,166 415,196 345,226 275,196" fill="#fff8f0" stroke="#d97706" stroke-width="1.5"/>
-  <text x="345" y="194" fill="#92400e" font-size="10" font-weight="600" text-anchor="middle">tool_use?</text>
+  <text x="345" y="194" fill="#92400e" font-size="10" font-weight="600" text-anchor="middle">tool_use block?</text>
 
   <!-- いいえ → 返却 -->
   <line x1="415" y1="196" x2="475" y2="196" stroke="#16a34a" stroke-width="1.5" marker-end="url(#arrow-green)"/>

s02_tool_use/images/tool-dispatch.svg

@@ -40,14 +40,14 @@
   <!-- LLM -->
   <rect x="270" y="82" width="150" height="52" rx="8" fill="#fff" stroke="#2563eb" stroke-width="1.5"/>
   <text x="345" y="104" fill="#1e3a5f" font-size="13" font-weight="700" text-anchor="middle">大模型 (LLM)</text>
-  <text x="345" y="122" fill="#64748b" font-size="10" text-anchor="middle">stop_reason 判断</text>
+  <text x="345" y="122" fill="#64748b" font-size="10" text-anchor="middle">检查 tool_use block</text>
 
   <!-- 箭头：LLM → 判断 -->
   <line x1="345" y1="134" x2="345" y2="162" stroke="#555" stroke-width="1.5" marker-end="url(#arrow)"/>
 
   <!-- 判断菱形 -->
   <polygon points="345,166 415,196 345,226 275,196" fill="#fff8f0" stroke="#d97706" stroke-width="1.5"/>
-  <text x="345" y="194" fill="#92400e" font-size="10" font-weight="600" text-anchor="middle">tool_use?</text>
+  <text x="345" y="194" fill="#92400e" font-size="10" font-weight="600" text-anchor="middle">tool_use block?</text>
 
   <!-- 否 → 返回 -->
   <line x1="415" y1="196" x2="475" y2="196" stroke="#16a34a" stroke-width="1.5" marker-end="url(#arrow-green)"/>