Add reconnectable async chat-turn flow with in-memory TurnRegistry

Replace the one-shot SSE chat stream with an async dispatch + reconnectable
replay flow so the mobile client survives backgrounding, network blips, and
OS-killed sockets without losing an in-flight agentic turn.

- TurnRegistry/TurnEntry: in-memory per-turn event buffer (cap 500, front
  eviction) shared by the agentic loop (writer) and SSE replay readers.
  ReplayOutcome + replay_from/next_batch distinguish Events/CaughtUp/Gone;
  next_batch registers the Notify before reading state (no lost wakeup) and
  drains every buffered event before signaling terminal, so the final
  Done/Error is never dropped and the stream closes cleanly.
- Endpoints: POST /insights/chat/turn (202 + turn_id), GET
  /insights/chat/turn/{id} (SSE replay, ?skip_before= resume, per-event seq,
  410 on eviction), DELETE /insights/chat/turn/{id} (real task abort +
  cooperative is_running() check at each loop boundary).
- Cancellation actually stops the task (AbortHandle stored on the entry) and
  emits a Done{cancelled:true}; callers skip persistence on cancel.
- Background sweeper drops stale turns; interval clamped to <=300s.
- OpenTelemetry spans: ai.chat.turn.execute/replay/cancel.
- Legacy POST /insights/chat/stream path preserved unchanged.

Tests: registry coverage for terminal delivery (race guard), waiting, Gone,
abort, eviction; handler integration tests for 404/410, skip_before, seq
stamping, completed replay, and cancel.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

src/state.rs

@@ -4,6 +4,7 @@ use crate::ai::face_client::FaceClient;
 use crate::ai::insight_chat::{ChatLockMap, InsightChatService};
 use crate::ai::llamacpp::LlamaCppClient;
 use crate::ai::openrouter::OpenRouterClient;
+use crate::ai::turn_registry::TurnRegistry;
 use crate::ai::{InsightGenerator, OllamaClient, SmsApiClient};
 use crate::database::{
     CalendarEventDao, DailySummaryDao, ExifDao, InsightDao, InsightGenerationJobDao, KnowledgeDao,
@@ -78,19 +79,10 @@ pub struct AppState {
     pub insight_generator: InsightGenerator,
     /// Chat continuation service. Hold an Arc so handlers can clone cheaply.
     pub insight_chat: Arc<InsightChatService>,
-    /// Face inference client (calls Apollo's `/api/internal/faces/*`).
-    /// Disabled (`is_enabled() == false`) when neither `APOLLO_FACE_API_BASE_URL`
-    /// nor `APOLLO_API_BASE_URL` is set; the file-watch hook (Phase 3) and
-    /// manual-face-create handler short-circuit in that case.
+    pub turn_registry: Arc<TurnRegistry>,
     pub face_client: FaceClient,
-    /// CLIP inference client (calls Apollo's `/api/internal/clip/*`).
-    /// Same disabled semantics as `face_client`: unset env → no-op
-    /// backlog drain, /photos/search returns an empty result.
     pub clip_client: ClipClient,
-    /// Tracks async insight generation jobs (spawned by generate endpoints).
     pub insight_job_dao: Arc<Mutex<Box<dyn InsightGenerationJobDao>>>,
-    /// In-memory map from job_id → tokio AbortHandle for running tasks.
-    /// Used to abort server-side tasks on cancel or regenerate.
     pub insight_job_handles: Arc<Mutex<HashMap<i32, tokio::task::AbortHandle>>>,
 }
 
@@ -127,6 +119,7 @@ impl AppState {
         sms_client: SmsApiClient,
         insight_generator: InsightGenerator,
         insight_chat: Arc<InsightChatService>,
+        turn_registry: Arc<TurnRegistry>,
         preview_dao: Arc<Mutex<Box<dyn PreviewDao>>>,
         face_client: FaceClient,
         clip_client: ClipClient,
@@ -171,6 +164,7 @@ impl AppState {
             sms_client,
             insight_generator,
             insight_chat,
+            turn_registry,
             face_client,
             clip_client,
             insight_job_dao,
@@ -310,6 +304,14 @@ impl Default for AppState {
             chat_locks,
         ));
 
+        // Turn registry for reconnectable chat turns. 5-minute timeout for
+        // stale turns (background cleaner drops entries older than this).
+        let timeout_secs: u64 = env::var("INSIGHT_CHAT_TURN_TIMEOUT_SECS")
+            .ok()
+            .and_then(|v| v.parse().ok())
+            .unwrap_or(300);
+        let turn_registry = Arc::new(TurnRegistry::new(timeout_secs));
+
         // Ensure preview clips directory exists
         let preview_clips_path =
             env::var("PREVIEW_CLIPS_DIRECTORY").unwrap_or_else(|_| "preview_clips".to_string());
@@ -332,6 +334,7 @@ impl Default for AppState {
             sms_client,
             insight_generator,
             insight_chat,
+            turn_registry,
             preview_dao,
             face_client,
             clip_client,
@@ -490,6 +493,9 @@ impl AppState {
             chat_locks,
         ));
 
+        // Turn registry for test state.
+        let turn_registry = Arc::new(TurnRegistry::new(300));
+
         // Initialize test preview DAO
         let preview_dao: Arc<Mutex<Box<dyn PreviewDao>>> =
             Arc::new(Mutex::new(Box::new(SqlitePreviewDao::new())));
@@ -518,6 +524,7 @@ impl AppState {
             sms_client,
             insight_generator,
             insight_chat,
+            turn_registry,
             preview_dao,
             FaceClient::new(None), // disabled in test
             ClipClient::new(None), // disabled in test