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/document_processors/escalation.py

@@ -24,9 +24,11 @@ from __future__ import annotations
 from dataclasses import dataclass
 from typing import Any, Literal
 
-# Cheapest-first. ``llm`` is reserved (see base.DocumentProcessor.tier) and not
-# wired yet, so it is intentionally absent from the live ladder.
-TIER_LADDER: tuple[str, ...] = ("fast", "structured", "ocr")
+# Cheapest-first. OCR is split into two rungs: ``ocr-incluster`` (the on-demand
+# burst GPU, e.g. surya, reached via the embedding gateway over the tailnet) tried
+# BEFORE ``ocr-upstream`` (paid Mistral). ``llm`` is reserved (see
+# base.DocumentProcessor.tier) and not wired yet.
+TIER_LADDER: tuple[str, ...] = ("fast", "structured", "ocr-incluster", "ocr-upstream")
 
 
 def escalation_tiers_signature(settings: Any) -> str:
@@ -55,6 +57,7 @@ def escalation_tiers_signature(settings: Any) -> str:
     """
     return (
         f"ocr={int(bool(settings.document_ocr_enabled))};"
+        f"ocric={int(bool(settings.document_ocr_incluster_enabled))};"
         f"t1={settings.document_tier1_engine}"
     )