feat(ingest): split OCR into tier2 in-cluster (GPU, gateway-only) + tier3 upstream

Insert a configurable in-cluster OCR rung into the escalation ladder (Deck #353):
a tier2-eligible doc is OCR'd on the on-demand burst GPU before falling through to
paid upstream OCR. The in-cluster backend is reached ONLY via the embedding gateway
(model prefix routes to the GPU over the tailnet) and is a config value (default
surya/surya-ocr-2, swappable to e.g. lightonocr) — never hard-coded.

Ladder: fast -> structured -> ocr-incluster -> ocr-upstream
(queues ingest-ocr-incluster / ingest-ocr-upstream).

- escalation.py: 4-tier ladder; in-cluster flag folded into the dead-letter signature.
- ocr.py: OcrProcessor(name, tier, model_setting, gateway_only); build_ocr_backend(
  ..., model=, gateway_only=) — gateway_only forces the gateway backend (never the
  direct Mistral fallback), disabling the tier with a warning if no gateway URL.
- registry.py: per-rung enable map; scanned docs target minimum="ocr-incluster";
  inline path runs the cheapest available OCR rung.
- procrastinate.py: two OCR queues; legacy ingest-ocr kept as a drain target.
- config.py: DOCUMENT_OCR_INCLUSTER_ENABLED (off) + DOCUMENT_OCR_INCLUSTER_MODEL.
- __init__.py: register the two OCR instances; vector/processor.py: pages_ocr
  metered for the upstream (paid) rung only; cli.py: new --tier choices + legacy drain.
- metrics.py: zero the legacy ingest-ocr queue gauge during rollout.
- tests: migrated to the split ladder + new tests (gateway-only forcing, per-tier
  model incl. lightonocr override, no-hard-coded-surya guard). 1792 pass; ruff + ty green.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

nextcloud_mcp_server/vector/processor.py

@@ -353,10 +353,13 @@ async def record_indexing_usage(
             )
             # Paid-OCR pages are metered as a SEPARATE line (Deck #323) so the
             # expensive tier's cost is billable independently of CPU-cheap parsing
-            # -- pages_embedded counts all parsed pages, pages_ocr only the OCR
-            # tier's. Gated on the tier so it's emitted exactly when the doc was
-            # actually OCR'd; the same page_count guard above applies.
-            if pipeline_tier == "ocr":
+            # -- pages_embedded counts all parsed pages, pages_ocr only the paid
+            # OCR tier's. After the OCR split (Deck #353) "paid" = the UPSTREAM
+            # (Mistral) rung; the in-cluster GPU rung's cost is recovered via the
+            # burst lifecycle, not per-page, so it is NOT metered here (separate
+            # per-tier OCR metering is a billing follow-up). Gated on the tier so
+            # it's emitted exactly when the doc hit upstream OCR.
+            if pipeline_tier == "ocr-upstream":
                 await store.record_usage_event(
                     metric="pages_ocr",
                     value=page_count,