Show tool and web search activity in the chat UI

Tool calls were invisible until the answer arrived: the only trace was the
sources list, and only for web searches. Surface them as they happen instead.

Add llm.stream_tool_calls(), an incremental version of resolve_tool_calls()
that yields a start and a completion event per tool call and ends with a
"resolved" event carrying the previous return value. resolve_tool_calls() is
kept as a thin wrapper that drops the progress events.

api/chat.py relays those events as a new SSE "tool" event, and wraps the
search-summary/knowledge-save step in one of the same shape, since it is a
noticeable pause of its own.

On the front end, ToolActivityList.vue renders one row per tool above the
assistant bubble (label, target, spinner while running, short result when
done). The store merges events by id and marks anything still running as
interrupted when the stream ends early. Display only - not persisted, so the
rows disappear when the session is reloaded, same as sources.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

docs/api.md

@@ -24,6 +24,8 @@ SSE でストリーミング応答を返す。
 |---|---|---|
 | `session_id` | セッション UUID | 新規セッション作成直後 |
 | `chunk` | テキスト断片 | LLM トークン生成ごと |
+| `tool` | `{id, name, label, detail, status, result}` | ツール実行の開始時 (`status: running`) と完了時 (`status: done`)。同じ `id` で 2 回届くのでフロントはマージして表示する |
+| `sources` | `[{title, url}]` | Web 検索した時のみ（出典一覧） |
 | `notes_updated` | — | AI が共有ノートを書き換えた直後 |
 | `done` | — | 正常完了 |
 | `error` | エラーメッセージ | 例外発生時 |