bito-code-review[bot] commented on code in PR #42244:
URL: https://github.com/apache/superset/pull/42244#discussion_r3623519330
##########
superset/mcp_service/middleware.py:
##########
@@ -1331,6 +1333,141 @@ def _try_truncate_info_response(
return truncated
+ def _try_truncate_data_query_response(
+ self,
+ tool_name: str,
+ response: Any,
+ estimated_tokens: int,
+ ) -> Any | None:
+ """Attempt to truncate a data-query tool response by dropping tail
rows.
+
+ Returns the truncated response if successful, None otherwise.
+ """
+ extracted = self._extract_payload_from_tool_result(response)
+ truncation_target = extracted if extracted is not None else response
+
+ try:
+ truncated, was_truncated, notes = truncate_query_result(
+ truncation_target, self.token_limit, tool_name=tool_name
+ )
+ except Exception as trunc_error: # noqa: BLE001
+ logger.warning(
+ "Query result truncation failed for %s due to %s: %s",
+ tool_name,
+ type(trunc_error).__name__,
+ trunc_error,
+ )
+ return None
+
+ if not was_truncated:
+ return None
+
+ # Mirror the info-tool path: if truncation couldn't bring the
+ # response back under the limit (e.g. a single row/scalar field
+ # alone exceeds it), fall back to the hard size-limit error instead
+ # of shipping an over-budget response.
+ truncated_tokens = estimate_response_tokens(truncated)
+ if truncated_tokens > self.token_limit:
+ return None
+
+ logger.warning(
+ "Query result for %s truncated from ~%d to ~%d tokens (limit: %d).
%s",
+ tool_name,
+ estimated_tokens,
+ truncated_tokens,
+ self.token_limit,
+ "; ".join(notes),
+ )
+
+ try:
+ user_id = get_user_id()
+ event_logger.log(
+ user_id=user_id,
+ action="mcp_response_truncated",
+ curated_payload={
+ "tool": tool_name,
+ "original_tokens": estimated_tokens,
+ "truncated_tokens": truncated_tokens,
+ "token_limit": self.token_limit,
+ "truncation_notes": notes,
+ },
+ )
+ except Exception as log_error: # noqa: BLE001
+ logger.warning("Failed to log truncation event: %s", log_error)
+
+ if extracted is not None and isinstance(truncated, dict):
+ return self._rewrap_as_tool_result(truncated, response)
+
+ return truncated
Review Comment:
<!-- Bito Reply -->
The fix correctly addresses the identified gap by ensuring that the
truncation metadata (`_response_truncated` and `_truncation_notes`) is
explicitly set on the dictionary in the fallback path of
`_try_truncate_data_query_response`. This change ensures consistency with the
info-tool path and prevents silent truncation, making the implementation robust
and idempotent for both the row/CSV and fallback paths.
**superset/mcp_service/middleware.py**
```
if extracted is not None and isinstance(truncated, dict):
truncated["_response_truncated"] = True
truncated["_truncation_notes"] = notes
return self._rewrap_as_tool_result(truncated, response)
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
