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/intelligence_pipeline_v3/audit/__init__.py

@@ -0,0 +1,23 @@
+"""Audit and review module for the v3 intelligence pipeline.
+
+Provides evidence display, reviewer corrections, filtering by confidence/
+claims/adjudication, and immutable correction event storage.
+"""
+
+from services.intelligence_pipeline_v3.audit.models import (
+    AuditRecord,
+    CorrectionEvent,
+    CorrectionType,
+    ReviewFilter,
+    ReviewStatus,
+)
+from services.intelligence_pipeline_v3.audit.store import AuditStore
+
+__all__ = [
+    "AuditRecord",
+    "AuditStore",
+    "CorrectionEvent",
+    "CorrectionType",
+    "ReviewFilter",
+    "ReviewStatus",
+]