- Invoice OCR migrated from Ollama (GPU-bound, local) to Gemini 2.5
Flash via new targo-hub /vision/invoice endpoint with responseSchema
enforcement. Ops VM no longer needs a GPU.
- Ops /j/* now has full camera scanner (TechScanPage) ported from
apps/field with 8s timeout + offline queue + auto-link to Dispatch
Job context on serial/barcode/MAC 3-tier lookup.
- New TechDevicePage reached via /j/device/:serial showing every
ERPNext entity related to a scanned device: Service Equipment,
Customer, Service Location, active Subscription, open Issues,
upcoming Dispatch Jobs, OLT info.
- New docs/VISION_AND_OCR.md (full pipeline + §10 relationship graph
+ §8.1 secrets/rotation policy). Cross-linked from ARCHITECTURE,
ROADMAP, HANDOFF, README.
- Nginx /ollama/ proxy blocks removed from both ops + field.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- Ollama container running llama3.2-vision:11b on server
- OCR page in ops app: camera/upload → Ollama extracts vendor, date,
amounts, line items → editable form → create Purchase Invoice
- nginx proxies /ollama/ to Ollama API (both ops + field containers)
- Added createDoc to erp.js API layer
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Move ERPNext API token from JS bundle to nginx proxy_set_header
(token only lives on server, never in client code)
- Switch ops + field apps from auth.targo.ca to id.gigafibre.ca SSO
- Fix "Aucun contenu" showing on tickets that have comments but no
description (check comments.length in v-if condition)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
