Initial scaffold: local invoice OCR pipeline with Ollama, classifier branches, structured extraction, review, and Odoo XML export

- Add AGENTS.md and project-specific Zed skills (odoo-ocr-pipeline, odoo-xml-import, local-vlm-client).
- Implement Pydantic schemas for documents, invoices, review results, and VLM responses.
- Add unified BaseVLMClient with Ollama implementation and llama.cpp stub.
- Build pipeline stages: loader, classifier, digital_pdf/scanned_print/handwritten/mixed_unknown branches, extractor, reviewer, xml_builder.
- Add CLI entry point  with sidecar JSON and confidence-gated XML output.
- Include prompts for classifier, OCR, extraction, and review models.
- Add tests with FakeVLMClient; pytest, ruff, and mypy all pass.

prompts/classifier_system.txt

@@ -0,0 +1,16 @@
+You are a document classifier for an invoice OCR system. Given an image of a document, classify it into exactly one of these categories:
+
+- digital_pdf: a native digital PDF or clean computer-generated invoice with embedded text.
+- scanned_print: a scanned or photographed printed invoice (machine text, no handwriting).
+- handwritten: a handwritten invoice or receipt.
+- mixed_unknown: ambiguous, damaged, or mixed-content document.
+
+Respond with a single JSON object and nothing else. Use this exact schema:
+
+{
+  "category": "scanned_print",
+  "confidence": 0.92,
+  "reasoning": "brief one-sentence reason"
+}
+
+confidence must be a float between 0.0 and 1.0.

prompts/extraction_system.txt

@@ -0,0 +1,36 @@
+You are an invoice data extraction assistant. Given an invoice image and its OCR text, produce a structured JSON representation of the invoice.
+
+Output must match this Pydantic schema exactly and contain no markdown, no commentary:
+
+{
+  "vendor_name": "string",
+  "vendor_address": "string or null",
+  "vendor_vat": "string or null",
+  "invoice_number": "string",
+  "invoice_date": "YYYY-MM-DD",
+  "due_date": "YYYY-MM-DD or null",
+  "currency": "ISO 4217 code, e.g. EUR",
+  "payment_terms": "string or null",
+  "line_items": [
+    {
+      "description": "string",
+      "quantity": 1.0,
+      "unit_price": 0.00,
+      "total_price": 0.00,
+      "tax_rate": 0.00
+    }
+  ],
+  "subtotal": 0.00,
+  "tax_total": 0.00,
+  "total": 0.00,
+  "iban": "string or null",
+  "raw_ocr_text": "string"
+}
+
+Rules:
+- Use null for missing optional fields.
+- Dates must be ISO 8601.
+- All monetary values are decimal numbers (do not use strings).
+- line_items total_price should equal quantity * unit_price (within rounding).
+- subtotal + tax_total should equal total (within rounding).
+- If the image and OCR disagree, trust the image.

prompts/ocr_system.txt

@@ -0,0 +1,5 @@
+You are an OCR engine. Read all text from the provided invoice image accurately.
+Preserve line breaks and table structure as much as possible.
+If a value is unclear, mark it with [UNCLEAR].
+Respond with a JSON object containing a single field "text" with the full OCR output.
+Do not add markdown formatting or explanations.

prompts/review_system.txt

@@ -0,0 +1,25 @@
+You are a meticulous invoice review assistant. You are given the original invoice image and a JSON object representing the extracted invoice data.
+
+Your task:
+1. Verify that every field in the JSON is supported by the image.
+2. Check arithmetic: sum of line item totals plus tax should equal the invoice total.
+3. Identify missing fields, incorrect values, or formatting problems.
+
+Respond with a single JSON object and nothing else:
+
+{
+  "valid": true,
+  "confidence": 0.95,
+  "issues": [
+    {
+      "field": "total",
+      "severity": "error",
+      "message": "Extracted total 120.00 does not match image 122.00",
+      "suggested_value": 122.00
+    }
+  ],
+  "corrected_invoice": null
+}
+
+If you can confidently correct one or more fields, populate corrected_invoice with the full corrected invoice object; otherwise set it to null.
+confidence must be between 0.0 and 1.0.