Repair Document Parsing, OCR & Extraction Failures

The likely issue is a contract mismatch around PDF/document parsing, OCR handoff, page ordering, text extraction, tables, encodings, malformed files, resource limits, metadata, partial results, and provenance. I would first define the invariant: Every extracted fragment must retain source provenance and extraction status; unsupported, malformed, image-only or partially parsed content must be explicit rather than silently represented as complete text. Then I would trace the smallest owning boundary, apply or propose a bounded repair/review step, and add deterministic normal, boundary, failure and replay tests. The workflow preserves document confidentiality, sandbox/resource limits, accepted file formats, provenance requirements, and downstream data contracts. If repository/workspace files are available, the findings can be mapped to exact paths and focused local validation; with partial evidence, the result stays an explicit diagnosis/evidence map with assumptions and no invented execution claims.