feat(ai): iteration budget in prompt + preserve photo-knowledge links

- Inject the max-iterations budget into the agentic system prompt for
  both insight generation and chat turns. Chat does this per-turn by
  appending a note to the replayed system message and restoring it
  before persistence so the note doesn't accumulate across turns.
- Stop deleting entity_photo_links at the start of agentic insight
  generation. The clear made recall_facts_for_photo always return
  empty, wasting a tool call and discarding knowledge from prior runs.
  Re-linking the same entity is already an INSERT OR IGNORE no-op.

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

src/ai/insight_chat.rs

@@ -382,6 +382,12 @@ impl InsightChatService {
         // 7. Append the new user turn.
         messages.push(ChatMessage::user(req.user_message.clone()));
 
+        // Temporarily annotate the system message with this turn's iteration
+        // budget so the model knows how many tool-calling rounds it has. We
+        // restore the original content before persistence so the note doesn't
+        // accumulate across turns.
+        let original_system_content = annotate_system_with_budget(&mut messages, max_iterations);
+
         let insight_cx = parent_cx.with_span(span);
 
         // 8. Agentic loop — same shape as insight_generator's, but capped
@@ -468,6 +474,10 @@ impl InsightChatService {
 
         loop_cx.span().set_status(Status::Ok);
 
+        // Drop the per-turn iteration-budget note from the system message
+        // before we persist so it doesn't snowball on each subsequent turn.
+        restore_system_content(&mut messages, original_system_content);
+
         // 9. Persist. Append mode rewrites the JSON blob in place; amend
         //    mode regenerates the title and inserts a new insight row,
         //    relying on store_insight to flip prior rows' is_current=false.
@@ -789,6 +799,8 @@ impl InsightChatService {
 
         messages.push(ChatMessage::user(req.user_message.clone()));
 
+        let original_system_content = annotate_system_with_budget(&mut messages, max_iterations);
+
         let mut tool_calls_made = 0usize;
         let mut iterations_used = 0usize;
         let mut last_prompt_eval_count: Option<i32> = None;
@@ -917,6 +929,10 @@ impl InsightChatService {
             messages.push(final_response);
         }
 
+        // Drop the per-turn iteration-budget note from the system message
+        // before we persist so it doesn't snowball on each subsequent turn.
+        restore_system_content(&mut messages, original_system_content);
+
         // Persist.
         let json = serde_json::to_string(&messages)
             .map_err(|e| anyhow!("failed to serialize chat history: {}", e))?;
@@ -1080,6 +1096,40 @@ fn env_max_iterations() -> usize {
         .max(1)
 }
 
+/// Append a per-turn iteration-budget reminder to the replayed system
+/// message so the model knows how many tool-calling rounds this turn gets.
+/// Returns the original `content` so the caller can restore it before
+/// persistence — otherwise the note would accumulate across turns.
+///
+/// No-op (returns `None`) when `messages` has no leading system message.
+fn annotate_system_with_budget(
+    messages: &mut [ChatMessage],
+    max_iterations: usize,
+) -> Option<String> {
+    let first = messages.first_mut()?;
+    if first.role != "system" {
+        return None;
+    }
+    let original = first.content.clone();
+    first.content = format!(
+        "{}\n\n(Budget for this chat turn: up to {} tool-calling iterations. Produce your final reply before the budget is exhausted.)",
+        first.content, max_iterations
+    );
+    Some(original)
+}
+
+/// Restore a system-message content previously captured by
+/// [`annotate_system_with_budget`]. No-op when `original` is `None` or the
+/// first message isn't a system message.
+fn restore_system_content(messages: &mut [ChatMessage], original: Option<String>) {
+    let Some(original) = original else { return };
+    if let Some(first) = messages.first_mut()
+        && first.role == "system"
+    {
+        first.content = original;
+    }
+}
+
 /// View returned to clients for chat-UI rendering.
 #[derive(Debug)]
 pub struct HistoryView {