fix(2.9.1): extractFromDocx — drop PHPWord dependency, parse word/document.xml directly

Browse Source

Root cause of the Shira hallucination incident in production case 46 Friedman:
DocumentAnalyzer::extractFromDocx relied on PhpOffice\PhpWord, but on the
EspoCRM prod image the PHPWord files are present in vendor/ yet are NOT
registered in the composer PSR-4 autoload map — class_exists() silently
returned false, the method returned null, and Shira's read_document fell
back to OCR. OCR then only saw the signature image, the AI got "[signature]"
as document content and fabricated the entire CTS appeal as a knee injury.

This change rewrites extractFromDocx to use ZipArchive + a small regex
parser of word/document.xml. Independent of PHPWord, more robust on
tables/footnotes/hyperlinks (which PHPWord's element walker missed at depth
>1), and verified on prod against the same Friedman appeal: 80 paragraphs /
16633 clean chars extracted (vs 0 before).

The paired Python fix in shira-hermes (commit 7b517e1) makes the OCR
fallback also read document.xml, so even if this PHP fix regresses again,
the AI will not be fed "[signature]" as document content.

Refs Task Master #5

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

...

This commit is contained in:

Chaim Marcus

2026-05-26 14:01:44 +00:00

parent 37a8b67b95

commit 89b3f5844e

3 changed files with 49 additions and 18 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

.taskmaster/tasks/tasks.json

+19 -5

File diff suppressed because one or more lines are too long