PDF uploads were stored in S3 and had text extracted during upload, but
fetch_upload_images() filtered exclusively for image MIME types, so
document content never reached the AI.
- Add fetch_upload_documents() in storage_service.py to retrieve
extracted_content for PDFs and text files
- Update ai_sessions.py chat endpoint to call both fetch_upload_images
and fetch_upload_documents, injecting document text as context
- Add PDF text extraction in _generate_ai_description (pypdf)
- Add pypdf>=4.0.0 to requirements.txt
- Fix test_db teardown to avoid connection pool issues
- Add 5 tests for fetch_upload_documents
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Adds _generate_ai_description background task that fires after a
successful upload: images get a one-sentence vision description via
Claude, text/log/config files get extracted_content + AI summary when
>2000 chars. Runs as asyncio.create_task so it never blocks the upload
response. Errors are logged and swallowed.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- POST /uploads: multipart upload with content-type/size validation, per-session limits, S3 storage
- GET /uploads/{id}/url: presigned download URL with account ownership check
- GET /uploads: list uploads for a session
- DELETE /uploads/{id}: delete with ownership enforcement (403 for non-owners)
- Returns 503 gracefully when STORAGE_ENDPOINT is not configured
- 15 integration tests covering auth, validation, 503 behavior, and ownership
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
