Fix panic on multi-byte chars in filter_json buffer truncation

The buffer truncation code was slicing at a raw byte offset which could
land in the middle of a multi-byte character (like emojis), causing a
panic. Fixed by using char_indices() to find valid character boundaries.

Also added stop_reason field to CompletionChunk initializers in tests
to complete the stop_reason feature addition.

- Fix byte boundary panic in filter_json.rs line 327
- Add test for multi-byte character handling
- Update test files with missing stop_reason field

crates/g3-providers/src/lib.rs

@@ -187,6 +187,8 @@ pub struct CompletionChunk {
     pub finished: bool,
     pub tool_calls: Option<Vec<ToolCall>>,
     pub usage: Option<Usage>, // Add usage tracking for streaming
+    /// Stop reason from the API (e.g., "end_turn", "max_tokens", "stop_sequence")
+    pub stop_reason: Option<String>,
 }
 
 #[derive(Debug, Clone, Serialize, Deserialize)]