feat(ai): chat continuation for photo insights (server v1)

Adds POST /insights/chat and GET /insights/chat/history. Replays the
stored agentic conversation through the same backend the insight was
generated with (or a per-turn override), runs a short tool-calling
loop, and persists the extended history in append or amend mode.

Backend switching: same-backend or hybrid->local replay verbatim;
local->hybrid is rejected in v1 (would require on-the-fly vision
description rewrite).

Per-(library, file) async mutex serialises concurrent turns. Soft
context budget drops oldest tool_call+result pairs when the
serialized history exceeds num_ctx - 2048 tokens.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/state.rs

@@ -1,3 +1,4 @@
+use crate::ai::insight_chat::{ChatLockMap, InsightChatService};
 use crate::ai::openrouter::OpenRouterClient;
 use crate::ai::{InsightGenerator, OllamaClient, SmsApiClient};
 use crate::database::{
@@ -44,6 +45,8 @@ pub struct AppState {
     pub openrouter_allowed_models: Vec<String>,
     pub sms_client: SmsApiClient,
     pub insight_generator: InsightGenerator,
+    /// Chat continuation service. Hold an Arc so handlers can clone cheaply.
+    pub insight_chat: Arc<InsightChatService>,
 }
 
 impl AppState {
@@ -76,6 +79,7 @@ impl AppState {
         openrouter_allowed_models: Vec<String>,
         sms_client: SmsApiClient,
         insight_generator: InsightGenerator,
+        insight_chat: Arc<InsightChatService>,
         preview_dao: Arc<Mutex<Box<dyn PreviewDao>>>,
     ) -> Self {
         assert!(
@@ -109,6 +113,7 @@ impl AppState {
             openrouter_allowed_models,
             sms_client,
             insight_generator,
+            insight_chat,
         }
     }
 
@@ -199,6 +204,18 @@ impl Default for AppState {
             libraries_vec.clone(),
         );
 
+        // Chat continuation reuses the generator for tool dispatch + image
+        // loading. The lock map starts empty and grows lazily per file.
+        let chat_locks: ChatLockMap =
+            Arc::new(tokio::sync::Mutex::new(std::collections::HashMap::new()));
+        let insight_chat = Arc::new(InsightChatService::new(
+            Arc::new(insight_generator.clone()),
+            ollama.clone(),
+            openrouter.clone(),
+            insight_dao.clone(),
+            chat_locks,
+        ));
+
         // Ensure preview clips directory exists
         let preview_clips_path =
             env::var("PREVIEW_CLIPS_DIRECTORY").unwrap_or_else(|_| "preview_clips".to_string());
@@ -218,6 +235,7 @@ impl Default for AppState {
             openrouter_allowed_models,
             sms_client,
             insight_generator,
+            insight_chat,
             preview_dao,
         )
     }
@@ -320,6 +338,16 @@ impl AppState {
             vec![test_lib],
         );
 
+        let chat_locks: ChatLockMap =
+            Arc::new(tokio::sync::Mutex::new(std::collections::HashMap::new()));
+        let insight_chat = Arc::new(InsightChatService::new(
+            Arc::new(insight_generator.clone()),
+            ollama.clone(),
+            None,
+            insight_dao.clone(),
+            chat_locks,
+        ));
+
         // Initialize test preview DAO
         let preview_dao: Arc<Mutex<Box<dyn PreviewDao>>> =
             Arc::new(Mutex::new(Box::new(SqlitePreviewDao::new())));
@@ -343,6 +371,7 @@ impl AppState {
             Vec::new(),
             sms_client,
             insight_generator,
+            insight_chat,
             preview_dao,
         )
     }