Outbound data restrictions after searching data sources (#1106)

app/MindWork AI Studio/Plugins/configuration/plugin.lua

@@ -276,6 +276,13 @@ CONFIG["EMBEDDING_PROVIDERS"] = {}
 -- }
 
 -- ERI v1 data sources for retrieval-augmented generation:
+--
+-- "OutboundDataRestriction" is optional and decides where a chat may still send data once the
+-- AI found something in the data source: ONLY_CONFIGURED_SERVICES, ONLY_LINKS_FROM_CHAT, or
+-- UNRESTRICTED, see DataSourceSecuritySettings.MinimumOutboundDataRestriction below. Without it,
+-- the data source gets ONLY_LINKS_FROM_CHAT, and a value AI Studio cannot read counts as
+-- ONLY_CONFIGURED_SERVICES. A data source with the security policy SELF_HOSTED always gets
+-- ONLY_CONFIGURED_SERVICES, whatever it says here.
 CONFIG["DATA_SOURCES"] = {}
 
 -- Example: ERI v1 data source with a shared access token.
@@ -288,6 +295,7 @@ CONFIG["DATA_SOURCES"] = {}
 --     ["AuthMethod"] = "TOKEN",
 --     ["Token"] = "ENC:v2:<base64-encoded encrypted token>",
 --     ["SecurityPolicy"] = "SELF_HOSTED",
+--     ["OutboundDataRestriction"] = "ONLY_CONFIGURED_SERVICES",
 --     ["SelectedRetrievalId"] = "<retrieval process ID from the ERI server>",
 --     ["MaxMatches"] = 10,
 -- }
@@ -304,6 +312,7 @@ CONFIG["DATA_SOURCES"] = {}
 --     ["Username"] = "<shared username>",
 --     ["Password"] = "ENC:v2:<base64-encoded encrypted password>",
 --     ["SecurityPolicy"] = "SELF_HOSTED",
+--     ["OutboundDataRestriction"] = "ONLY_CONFIGURED_SERVICES",
 --     ["SelectedRetrievalId"] = "<retrieval process ID from the ERI server>",
 --     ["MaxMatches"] = 10,
 -- }
@@ -319,6 +328,7 @@ CONFIG["DATA_SOURCES"] = {}
 --     ["UsernamePasswordMode"] = "OS_USERNAME_SHARED_PASSWORD",
 --     ["Password"] = "ENC:v2:<base64-encoded encrypted password>",
 --     ["SecurityPolicy"] = "SELF_HOSTED",
+--     ["OutboundDataRestriction"] = "ONLY_CONFIGURED_SERVICES",
 --     ["SelectedRetrievalId"] = "<retrieval process ID from the ERI server>",
 --     ["MaxMatches"] = 10,
 -- }
@@ -1240,6 +1250,23 @@ CONFIG["SETTINGS"] = {}
 --     "00000000-0000-0000-0000-000000000001",
 -- }
 
+-- Configure the least strict outbound data restriction a data source may have, i.e., a local
+-- file, a local folder, or an external data source (ERI server). Each data source decides where
+-- a chat may still send data once the AI found something in it:
+--   ONLY_CONFIGURED_SERVICES  Only services configured in AI Studio, such as your data sources,
+--                             your Confluence, or the allowed private hosts of the tool Read Web
+--                             Page. No other web pages, no web search.
+--   ONLY_LINKS_FROM_CHAT      Also web pages whose addresses stand in the chat, written by the
+--                             user or returned by a tool. No web search, and no addresses the AI
+--                             chooses itself outside the configured services.
+--   UNRESTRICTED              Every tool the user selected.
+-- A data source set to a less strict level gets this one whenever its passages reach a chat, and
+-- the dialog of the data source no longer offers the less strict levels. An external data source
+-- which only self-hosted providers may use always gets ONLY_CONFIGURED_SERVICES. A chat which
+-- found something before keeps the level it got then. The default is UNRESTRICTED, which leaves
+-- the choice to the user. New data sources start with ONLY_LINKS_FROM_CHAT either way.
+-- CONFIG["SETTINGS"]["DataSourceSecuritySettings.MinimumOutboundDataRestriction"] = "ONLY_LINKS_FROM_CHAT"
+
 -- Configure the least strict outbound data restriction a mailbox may have. Mails come from
 -- strangers and may contain instructions meant for the AI, so each mailbox decides where a chat
 -- may still send data once it has read mails from it: