feat(channel): stream LLM responses to Telegram via draft message edits

Wire the existing provider-layer streaming infrastructure through the
channel trait and agent loop so Telegram users see tokens arrive
progressively via editMessageText, instead of waiting for the full
response.

Changes:
- Add StreamMode enum (off/partial/block) and draft_update_interval_ms
  to TelegramConfig (backward-compatible defaults: off, 1000ms)
- Add supports_draft_updates/send_draft/update_draft/finalize_draft to
  Channel trait with no-op defaults (zero impact on existing channels)
- Implement draft methods on TelegramChannel using sendMessage +
  editMessageText with rate limiting and Markdown fallback
- Add on_delta mpsc::Sender<String> parameter to run_tool_call_loop
  (None preserves existing behavior)
- Wire streaming in process_channel_message: when channel supports
  drafts, send initial draft, spawn updater task, finalize on completion

Edge cases handled:
- 4096-char limit: finalize draft and fall back to chunked send
- Broken Markdown: use no parse_mode during streaming, apply on finalize
- Edit failures: fall back to sending complete response as new message
- Rate limiting: configurable draft_update_interval_ms (default 1s)

src/tools/git_operations.rs

@@ -735,10 +735,7 @@ mod tests {
         });
         let tool = GitOperationsTool::new(security, tmp.path().to_path_buf());
 
-        let result = tool
-            .execute(json!({"operation": "branch"}))
-            .await
-            .unwrap();
+        let result = tool.execute(json!({"operation": "branch"})).await.unwrap();
         // Branch listing must not be blocked by read-only autonomy
         let error_msg = result.error.as_deref().unwrap_or("");
         assert!(