refactor(search): centralize the web-scraping User-Agent into one constant (#4325)

The outbound UA for web_fetch / web_search was inlined in four places with
two different values and nothing keeping them current: content.py pinned a
mid-2021 Chrome 91 build, and providers.py sent a bare Mozilla/5.0 in three
spots. Some sites serve a degraded or blocked page to a UA that old.

Add WEB_FETCH_USER_AGENT to src/constants.py (env-overridable, matching the
existing Copilot/Kimi UA-constant pattern) and import it in content.py and
providers.py. Default to a current, common desktop UA so pages return their
normal HTML: the market-leading desktop OS (Windows; NT 10.0 covers Windows
10 and 11) and browser (Chrome) on a current stable build. The version is now
bumped in one place.

Service-specific self-identifying agents (Copilot, Kimi, webhooks, cookbook)
are intentionally left separate. Adds a regression pinning the constant shape,
the env override, and a guard against a new inline Mozilla literal in the
search sources.

Closes #4324

src/constants.py

@@ -78,6 +78,13 @@ MAX_CONTEXT_MESSAGES = 90
 REQUEST_TIMEOUT = 20
 OPENAI_COMPAT_PATH = "/v1/chat/completions"
 
+# Outbound UA for web_fetch / web_search scraping; common desktop UA so pages serve normal HTML.
+WEB_FETCH_USER_AGENT = os.environ.get(
+    "WEB_FETCH_USER_AGENT",
+    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 "
+    "(KHTML, like Gecko) Chrome/148.0.0.0 Safari/537.36",
+)
+
 # Environment variables with defaults
 DEFAULT_HOST = os.getenv("LLM_HOST", "localhost")
 LLM_HOSTS = [h.strip() for h in os.getenv("LLM_HOSTS", "").split(",") if h.strip()]