feat: Intelligence Pipeline v3 — full implementation

Multi-stage evidence-grounded inference architecture replacing the
monolithic 9B model extraction pipeline. CPU-first specialist services
handle routine extraction while the 9B vLLM model is preserved for
semantic adjudication of ambiguous cases.

Key components:
- Capability-aware inference gateway (OpenAI-compatible + Ollama)
- Endpoint registry with DB migrations and REST API
- Sentence-aware document segmenter (property tests)
- Deterministic financial parsing with offset integrity
- Symbol resolution with ambiguity detection
- Specialist service (GLiNER2, dynamic batching, K8s deployment)
- Company-specific sentiment (FinBERT, calibration)
- Retrieval-based novelty and duplicate detection
- Confidence calibration pipeline
- Deterministic routing engine (property tests)
- 9B adjudication layer with VRAM gating
- Stock-specific impact model (features, labels, baseline, trained)
- Pipeline orchestrator (state machine, queues, leases, feature flags)
- Bounded parallelism (async workers, semaphore, load shedding)
- Observability (tracing, metrics, alerts)
- Compatibility adapter (v3→v2 golden mapping tests)
- Shadow/canary promotion framework
- Active learning and fine-tuning pipeline

Test results: 1,161 tests pass, ruff lint clean.
All 282 spec tasks completed.

services/specialist/__init__.py

@@ -0,0 +1,12 @@
+"""Specialist inference service — CPU-first NER, classification, and extraction.
+
+Provides batch endpoints for entity extraction, event classification,
+relation extraction, and structured fact extraction. Uses GLiNER2 Large
+as the initial model candidate with a mock fallback for testing.
+
+Endpoints:
+    POST /api/specialist/entities  — batch entity extraction
+    POST /api/specialist/classify  — batch event classification
+    POST /api/specialist/relations — batch relation extraction
+    POST /api/specialist/extract   — batch structured extraction
+"""