plexus.reports.blocks.feedback_contradictions module

FeedbackContradictions report block.

Analyzes feedback items for a score against published guidelines using a shared multi-model voting engine. Supports two modes: - contradictions: focus on contradictions/policy gaps - aligned: focus on non-contradicting vetted items

class plexus.reports.blocks.feedback_contradictions.FeedbackContradictions(config: Dict[str, Any], params: Dict[str, Any] | None, api_client: PlexusDashboardClient)

Bases: BaseReportBlock

Guideline-vetting report block with contradiction and aligned modes.

DEFAULT_DESCRIPTION: str | None = 'Guideline Contradiction Analysis'

DEFAULT_NAME: str | None = 'Feedback Contradictions'

async generate() → Tuple[Dict[str, Any] | None, str | None]

Generates the data for this report block asynchronously.

Access block configuration via self.config and report parameters via self.params. Use self.api_client for data fetching. Use self._log(“message”) to record log information.

Returns:

A tuple containing:

• A dictionary containing the generated data (JSON-serializable), or None on failure.

• A string containing concatenated log messages, or None if no logs.