Set the search summary model from the settings panel

Summarizing web search results falls back to DEFAULT_MODEL, so a local Ollama
model ends up doing it and the call can fail — which surfaces only as
"保存できる要約なし" in the chat. Make SEARCH_SUMMARY_MODEL settable at runtime:
add it to the settings allowlist and read it from os.environ on each call
(knowledge._summary_model), the way LOCAL_KB_EMBEDDING_MODEL already works.
Importing it as a config constant would keep the old value until a restart.

Show the current value of the settings that are not secrets. A model name
rendered as ••••qwen3 gives no way to tell what is in effect, so the store now
marks those keys (NON_SECRET_KEYS) and returns them unmasked; the API field is
renamed masked -> display_value and carries a secret flag that the panel uses
to pick the input type, replacing the list it kept on its own side.

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

backend/app/core/memory_kb/knowledge.py

@@ -1,5 +1,6 @@
 import asyncio
 import logging
+import os
 import re
 
 import httpx
@@ -10,7 +11,6 @@ from app.core import llm
 from app.core.config import (
     KNOWLEDGE_CONTEXT_LIMIT,
     KNOWLEDGE_TOOL_CONTENT_LIMIT,
-    SEARCH_SUMMARY_MODEL,
 )
 from app.core.memory_kb import local_knowledge
 from app.db.models import KnowledgeEntry, KnowledgeSource
@@ -37,6 +37,14 @@ _SUMMARY_PROMPT = (
 _HEADLINE_MARKERS = ("要約:", "要約：")
 
 
+def _summary_model() -> str | None:
+    """GUIの設定画面から実行時に変更できるよう、起動時定数ではなく都度 os.environ を見に行く。
+
+    未設定（空文字含む）なら None を返し、llm.complete() 側で DEFAULT_MODEL にフォールバックさせる。
+    """
+    return os.environ.get("SEARCH_SUMMARY_MODEL") or None
+
+
 def _split_headline(text: str) -> tuple[str, str]:
     """LLMの出力を (一行要約, 本文) に分ける。1行目が想定の形式でなければ見出しは空で返す。"""
     lines = text.strip().splitlines()
@@ -87,7 +95,7 @@ async def summarize_results(query: str, results: list[dict], model: str | None =
     try:
         text = await llm.complete(
             [{"role": "user", "content": prompt}],
-            model=model or SEARCH_SUMMARY_MODEL,
+            model=model or _summary_model(),
         )
     except Exception:
         logger.exception("Failed to summarize search results for query=%r", query)