Refine backendless share intake

docs/SETUP.md

@@ -25,7 +25,8 @@ flutter run --dart-define=USE_FAKE_BACKEND=true
 ## Background Sync
 
 Background sync (startup + resume + periodic ticks while authenticated) is
-enabled by default.
+disabled by default. The current product direction is backendless/local-first,
+so backend sync should be enabled only for REST transport development.
 
 In REST mode, auto-triggers are reachability-gated to avoid unnecessary sync
 attempts while offline.
@@ -78,7 +79,23 @@ Behavior notes:
 ## Phone-Only Private AI Digest
 
 The app can run without a production backend by keeping `USE_FAKE_BACKEND=true`
-and using the LLM integration only for a private weekly digest.
+and using the LLM integration for local profile extraction and private digest
+generation.
+
+Selected product flow:
+
+- share messages/text from WhatsApp, iMessage, Notes, Safari, or similar apps
+  into the app
+- auto-match only when identity evidence is strong
+- keep ambiguous or low-information shares in `Share Inbox`
+- let the user gradually resolve inbox items over days, weeks, and months
+- run local/profile-building extraction opportunistically and on scheduled
+  nightly windows when the OS allows it
+- run grounded weekly recommendations on request or on the configured digest
+  schedule
+
+Backend sync is not part of this path. The fake backend is intentionally inert
+for sync pulls and must not seed people or other relationship records.
 
 Digest behavior:
 
@@ -86,6 +103,10 @@ Digest behavior:
 - scheduled digest payloads use pseudonymous tokens such as `person_001`
 - names, aliases, sender names, source URLs, raw shared text, and sensitive
   notes are not sent in the scheduled digest prompt
+- repeated LLM work should be avoided by fingerprinting unresolved/new share
+  batches and skipping extraction when the same batch has already completed
+- weekly recommendation prompts should include previously suggested/dismissed
+  items so the model avoids repeats
 - LLM results are saved as pending AI review drafts first
 - accepting a draft creates a local idea, task, or reminder
 - dismissing a draft leaves existing local data unchanged