915aca69e4
Makes suppression stats visible in the deep-scan report so users can audit why the scanner produced the counts it did. Before: synthesizer would acknowledge "true risk is High, not Extreme" in prose while verdict stayed BLOCK/Extreme — inconsistent. After Commit 1 the orchestrator verdict is coherent on its own; synthesizer's job shrinks to transparency. - Adds 'Scan Calibration' section instruction consuming scanner.calibration.* fields (entropy files_skipped_by_extension, policy_source, thresholds). - Heuristic: omit the section if < 5% of files skipped (no signal). Flag the section if > 80% skipped (policy may be too aggressive). - Explicit 'Don't override verdict' directive in DON'T DO list. Discrepancy goes in calibration, not in a rewritten dashboard. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| ai-psychosis | ||
| config-audit | ||
| linkedin-thought-leadership | ||
| llm-security | ||
| ms-ai-architect | ||
| okr | ||
| ultraplan-local | ||