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/shared/inference/__init__.py

@@ -0,0 +1,33 @@
+"""Inference gateway: shared client and routing layer.
+
+Exports:
+    InferenceGateway - Gateway facade for all LLM consumers
+    InferenceTarget - Resolved target configuration
+    StructuredGenerationRequest - Structured generation request
+    InferenceResult - Inference response with lineage
+    ModelLineage - Lineage record for persistence
+    build_lineage_from_result - Extract lineage from a result
+"""
+from services.shared.inference.gateway import InferenceGateway
+from services.shared.inference.lineage import build_lineage_from_result
+from services.shared.inference.models import (
+    ChatMessage,
+    InferenceResult,
+    InferenceTarget,
+    ModelLineage,
+    ProviderCapabilities,
+    StructuredGenerationRequest,
+    TokenUsage,
+)
+
+__all__ = [
+    "InferenceGateway",
+    "InferenceTarget",
+    "StructuredGenerationRequest",
+    "InferenceResult",
+    "ChatMessage",
+    "ModelLineage",
+    "ProviderCapabilities",
+    "TokenUsage",
+    "build_lineage_from_result",
+]