feat: add supports_parallel_tool_calls for MCP servers

Port from openai/codex#17667: MCP servers can now opt-in to parallel
tool execution by setting supports_parallel_tool_calls: true in their
config. This allows tools from the same server to run concurrently
within a single tool-call batch, matching the behavior already available
for built-in tools like web_search and read_file.

Previously all MCP tools were forced sequential because they weren't in
the _PARALLEL_SAFE_TOOLS set. Now _should_parallelize_tool_batch checks
is_mcp_tool_parallel_safe() which looks up the server's config flag.

Config example:
  mcp_servers:
    docs:
      command: "docs-server"
      supports_parallel_tool_calls: true

Changes:
- tools/mcp_tool.py: Track parallel-safe servers in _parallel_safe_servers
  set, populated during register_mcp_servers(). Add is_mcp_tool_parallel_safe()
  public API.
- run_agent.py: Add _is_mcp_tool_parallel_safe() lazy-import wrapper. Update
  _should_parallelize_tool_batch() to check MCP tools against server config.
- 11 new tests covering the feature end-to-end.
- Updated MCP docs and config reference.

website/docs/reference/mcp-config-reference.md

@@ -28,6 +28,7 @@ mcp_servers:
     enabled: true
     timeout: 120
     connect_timeout: 60
+    supports_parallel_tool_calls: false
     tools:
       include: []
       exclude: []
@@ -47,6 +48,7 @@ mcp_servers:
 | `enabled` | bool | both | Skip the server entirely when false |
 | `timeout` | number | both | Tool call timeout |
 | `connect_timeout` | number | both | Initial connection timeout |
+| `supports_parallel_tool_calls` | bool | both | Allow tools from this server to run concurrently |
 | `tools` | mapping | both | Filtering and utility-tool policy |
 | `auth` | string | HTTP | Authentication method. Set to `oauth` to enable OAuth 2.1 with PKCE |
 | `sampling` | mapping | both | Server-initiated LLM request policy (see MCP guide) |