websearch: add scope=code programming search + provider extract chain

- search(..., scope=code) restricts to 15 programming domains
  (official docs, GitHub, registries, Stack Overflow, CVE/NVD):
  native include_domains/search_domain_filter where supported
  (Tavily, Exa, Perplexity), post-filtering for all providers
  (Brave, SearXNG, DuckDuckGo have no native filter).
- web_fetch now uses fetch_best: Tavily extract, then Exa
  contents, then direct fetch; both-fail errors name both
  failures, direct-fetch 403 under the egress whitelist is
  fail-closed, not bypassed. Default general scope and direct
  fetch_url behaviour unchanged.
- MCP web_search gains scope enum (general/code); docs updated.
- Tests all mock HTTP, no real keys.

cloud/websearch_mcp.py

@@ -20,10 +20,10 @@ import os
 import sys
 
 try:
-    from cloud.websearch import WebSearchError, fetch_url, search
+    from cloud.websearch import WebSearchError, fetch_best, search
 except ImportError:  # flat copy in a tenant codex-home
     sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
-    from websearch import WebSearchError, fetch_url, search  # noqa: E402
+    from websearch import WebSearchError, fetch_best, search  # noqa: E402
 
 SERVER_NAME = "websearch"
 SERVER_VERSION = "0.1.0"
@@ -37,7 +37,14 @@ _TOOLS = [
             "supplies one. Use web_fetch to read specific pages. "
             "provider may be 'auto' (walk Perplexity, Exa, Tavily, "
             "Brave, then keyless SearXNG / DuckDuckGo, falling back "
-            "on failure) or a single provider name to pin it."
+            "on failure) or a single provider name to pin it. "
+            "scope 'code' restricts results to programming sources "
+            "only (official language docs, GitHub, package "
+            "registries, Stack Overflow, CVE/NVD); anything else "
+            "is filtered out, never returned. Default scope "
+            "'general' is unfiltered. This tool does not do "
+            "shopping, social, places, travel, general news, "
+            "weather, finance, or browser checkout."
         ),
         "inputSchema": {
             "type": "object",
@@ -48,6 +55,12 @@ _TOOLS = [
                           "description": "Max results, 1-10"},
                 "provider": {"type": "string", "default": "auto",
                              "description": "auto or a provider name"},
+                "scope": {"type": "string", "default": "general",
+                          "enum": ["general", "code"],
+                          "description": "general: unfiltered web "
+                                         "search. code: programming "
+                                         "sources only, see tool "
+                                         "description."},
             },
             "required": ["query"],
         },
@@ -57,7 +70,13 @@ _TOOLS = [
         "description": (
             "Fetch one URL and return clean text plus its links, "
             "truncated head+tail when over char_limit. "
-            "Only http(s) URLs; localhost / private IPs are blocked."
+            "Extraction first: Tavily extract, then Exa contents "
+            "(only backends with a configured key are tried), "
+            "direct fetch last. Under the egress proxy, direct "
+            "fetch of a domain outside the Tinyproxy whitelist "
+            "fails 403 fail-closed; that error is reported, not "
+            "bypassed. Only http(s) URLs; localhost / private IPs "
+            "are blocked. This is not a sandbox boundary."
         ),
         "inputSchema": {
             "type": "object",
@@ -83,7 +102,7 @@ def handle_request(request, search_fn=None, fetch_fn=None):
     None for notifications (no id). Pure function for testability:
     the stdio loop passes the real search/fetch, tests pass fakes."""
     search_fn = search_fn or search
-    fetch_fn = fetch_fn or fetch_url
+    fetch_fn = fetch_fn or fetch_best
     if not isinstance(request, dict):
         return {"jsonrpc": "2.0", "id": None,
                 "error": _err(-32700, "request is not an object")}
@@ -123,7 +142,8 @@ def handle_request(request, search_fn=None, fetch_fn=None):
                 result = search_fn(
                     args.get("query"),
                     limit=args.get("limit", 5),
-                    provider=args.get("provider", "auto"))
+                    provider=args.get("provider", "auto"),
+                    scope=args.get("scope", "general"))
             elif name == "web_fetch":
                 result = fetch_fn(
                     args.get("url"),