fix: use continue instead of break on low-relevance KB search results

Bug: Using break instead of continue when encountering low-relevance
results caused the search to stop prematurely, missing potentially
relevant chunks in subsequent results.

- Changed break to continue when score < 0.4 in search_single_collection
- Changed break to continue when score < 0.4 in search_single_kb
- Lowered threshold from 0.5 to 0.4 for consistency

This ensures all search results are evaluated, not just those before
the first low-relevance result.

src/core/bot/kb_context.rs

@@ -343,10 +343,10 @@ impl KbContextManager {
 
                 total_tokens += tokens;
 
-                if result.score < 0.4 {
-                    debug!("Skipping low-relevance result (score: {})", result.score);
-                    break;
-                }
+            if result.score < 0.4 {
+                debug!("Skipping low-relevance result (score: {})", result.score);
+                continue;
+            }
             }
 
             Ok(KbContext {
@@ -409,9 +409,9 @@ impl KbContextManager {
 
             total_tokens += tokens;
 
-            if result.score < 0.5 {
+            if result.score < 0.4 {
                 debug!("Skipping low-relevance result (score: {})", result.score);
-                break;
+                continue;
             }
         }